Omniscio

Settings reference (every configurable setting)

Every setting Omniscio can store, one row each: its key, the kind of value it takes, the values it accepts, and what it does. Use it to answer "is there a setting for X?" and "how do I configure X?" without opening the app. > Generated from the settings schema by npm run settings:catalog -- do NOT edit by hand. It is rebuilt whenever the app changes, so it is always current. Each row is one setting: its key (the id used by PATCH /settings/:key and shown in GET /settings), the kind of value it takes, the accepted values, and what it does. Rows are grouped by area below, and each area is split into the toggles and fields shown on a settings surface and the CLI/advanced keys with no on-screen control. Secret credentials and server-managed keys are omitted (they are not user-settable).

Settings shown in the Settings UI (913)

The toggles and fields you can change on an Omniscio settings surface — the Settings screens, or the Dev Pipeline panel's Setup wall.

Getting Started (2)

Installing Omniscio, signing in, and finding your way around for the first time.

Setting Type Accepted values What it does
heardAboutUs text string (≤64) Tell us where you first found the app — helps us know what is working
userRole text string (≤80) Your role — a short description of what you do, asked during setup

Sessions & Agents (166)

Running AI sessions and agents — starting them, steering them, and orchestrating many.

Setting Type Accepted values What it does
agentAlertsEnabled toggle true | false Agents drop persistent inbox rows via POST /alert
agentChatReplyWatchDailyLimit number integer 1..10000 Limit how many replies from one Team Chat conversation your agent is woken for in a day. Leave blank for no limit
agentDrivenMaxConcurrent number integer 0..20 Global concurrency limit across all active agent-driven sessions. New spawns are refused beyond this count.
agentDrivenMaxConcurrentLeads number integer 0..20 Agent-driven sessions that lead a crew use these places instead of helper places. Helpers plus crew leads can never pass both limits added together.
agentDrivenMaxDollarsPerSession number number 0..20 Ceiling in USD on the cumulative cost of a single agent-driven session. NOT enforced today - the value is stored and shown back to you, but nothing stops a session at the amount.
agentDrivenMaxTurnsPerSession number integer 0..200 Ceiling on follow-up turns for a single agent-driven session. NOT enforced today - the value is stored and shown back to you, but nothing stops a session at the count.
agentDrivenSessionsEnabled toggle true | false Allow external scripts to spawn Omniscio sessions and send follow-up messages on their own. Off by default — leave it off unless you have a script you trust to do so.
agentInputRequestsEnabled toggle true | false Lets a session pop a box asking you to fill in a value it cannot set itself, like an API key. The AI never sees what you type.
agentInstructionsSyncCanonical select "CLAUDE.md" | "AGENTS.md" Which filename Omniscio reads as the source of truth for agent instructions sync. CLAUDE.md by default; switch to AGENTS.md if that is your primary tool.
agentInstructionsSyncEnabled toggle true | false Mirror your canonical agent instructions file (CLAUDE.md or AGENTS.md) into the filenames other AI coding tools read — Codex, Gemini CLI, Cursor, Cline, Copilot, Windsurf. Off by default.
agentInstructionsSyncExcludedProjectIds list array of string (≤64) Tick or untick each hub for agent instructions sync. An unticked hub is left alone — no writes, no alerts — while the others keep syncing.
agentInstructionsSyncGitMode select "local" | "committed" Whether the generated agent-instruction copies are committed to git or kept out of it. Keeping them out avoids merge conflicts; committing them is for teammates who use other AI tools.
agentInstructionsSyncMirrors list array of "AGENTS.md" | "CLAUDE.md" | "GEMINI.md" | ".cursorrules" | ".clinerules/base.md" | ".github/copilot-instructions.md" | ".windsurfrules" Pick which agent-instruction filenames to write alongside the canonical file. The canonical file itself is hidden — no self-copies.
agentKeyDirectSaveEnabled toggle true | false When you hand an AI session on this computer a key, password or web address, it saves it straight away — no box, no Save click. AI provider keys are checked with the provider first, and a rejected key is never saved. Off by default.
agentKeyProposalsEnabled toggle true | false Lets an AI session offer a key it already holds so you can review it, edit it, and press Save to store it. Nothing is saved unless you press Save.
agentPermissionLevel select "read_only" | "guarded" | "smart" | "autonomous" | "full" How much an agent can do on its own before Omniscio stops to ask you. Below Full trust, the built-in protection for sensitive files (SSH keys, credentials, system files) always asks; Full trust auto-approves them too, with one exception: writing to SSH keys, cloud credentials, a shell startup file or a git hook always asks, at every level. External engines (Kimi Code, Hermes, DeepSeek Harness) refuse a sensitive file outright at every level, Full trust included. Email-triggered sessions stay locked down at every level. Applies to Claude Code sessions, to new Codex sessions unless Codex has its own level set under Accounts, and to the external engines.
agentStatusBoardEnabled toggle true | false Show a live board of every agent Omniscio has launched — its workspace, status, dev-pipeline phase, and to-do checklist — each with one click to jump to that session. Adds an Agent Board icon to the toolbar.
agentTaskSystemEnabled toggle true | false Agents keep their work in Omniscio's own agent task system, one list per project, apart from your Tasks. Their own to-do list stays their own checklist. Needs the Agent Status Board on. On by default for developers, off for everyone else.
agentWebBrowserBinary select "auto" | "chrome" | "edge" Which installed browser agents use: Automatic (Chrome, or Edge if Chrome is missing; a session keeps its browser); Chrome only; Edge only.
agentWebMaxConcurrentBrowsers number integer 1..5 How many agents can have a browser open at once; agents past the limit wait in line.
aiCoachingCliEnabled toggle true | false Allow external agents to read your AI coaching artifacts (interview prompts, drafts) and start coaching interviews over the local CLI control server. On by default. Flip off to disable all AI coaching CLI access at once.
aiProjectManagerEnabled toggle true | false This feature runs on your default API key or chosen model. {pmName} reads your Mission Control projects - board item names, comments, documents and the people assigned to them - and sends that content, including other people's names and comments, to the AI provider behind that key so it can answer. You can turn it off any time in Settings.
aiProjectManagerInboxTabEnabled toggle true | false Turn this off to hide the tab. Its notifications still reach your main Inbox.
aipmAutonomyLevel select "suggest" | "ask" | "act" The app checks every change Omni tries to make. A change your choice does not allow waits under Needs your OK until you approve it.
aipmControlCenterVisualTheme unknown "app" | "glassmorphism" | "linear" | "warm-charcoal" | "aurora" | "soft-depth" | "neon" | "spotify" | "luxury" | "gradient-sidebar" | "neumorphic" | "frosted-tiers" | "vercel" | "liquid-glass" | "aurora-glass" | "macos" | any Give the control center its own look. Follow the page, pick a built-in theme, or use a theme file you imported.
aipmMatchOmniscioTheme toggle true | false Off by default: the Omni page and its windows use Mission Control's teal. Turn this on to use your Omniscio theme color instead. Mission Control has its own switch for itself.
aipmSuggestionLevel select "high" | "medium" | "all" Choose which suggestions {pmName} lists: High only, Medium and up, or All. Hidden ones are not deleted.
allowAgentAppRestart toggle true | false When OFF (default), the local CLI restart route is disabled, so an agent or external script can never quit and relaunch Omniscio on its own — not even one holding the global CLI token. Your own "Restart Omniscio" button is unaffected. Turn ON only if you want to let a headless caller restart the app.
allowAgentDirectNavigation toggle true | false When OFF (default), an agent's request to switch your view — jump you to a project, the inbox, a settings pane, a note, a mind map, or a Gmail thread — drops a click-to-go toast instead of moving you, so Omniscio never takes over your screen and puts you somewhere else. When ON, agents may switch your view immediately (guided tours, "let me show you this"). Either way your own clicks, taps, notification and link clicks always navigate instantly, and if you're away in another app the request still can't move you — you get a dismissible inbox note instead.
allowAgentForegroundFromBackground toggle true | false When OFF (default), an agent's request to focus or pop Omniscio to the front is ignored while you're working in another app — instead you get a dismissible inbox note naming the session that tried. When ON, agents may pull Omniscio to the front from behind. Either way agents can still drive the UI while you're already in Omniscio (settings tours, tutorials), and your own shortcuts, notification clicks, and phone taps are never affected.
allowAgentTokenSpawn toggle true | false When OFF (default), a command-line session spawn is rejected if it presents only an agent's scoped token (the Omniscio-injected $AMC_CLI_TOKEN) — so a compromised MCP server or npm dependency that reads an agent's environment can't spend your money by spawning paid sessions. Agents still spawn normally using the global CLI token. Turn ON to let an agent spawn sessions directly with its own scoped token.
allowAgentTokenSupermail toggle true | false When OFF (default), Supermail's mailbox routes over the CLI (reading, searching, archiving, labeling, snoozing, and requesting a send or reply) refuse an agent's own scoped token — including a cloud session's — so a compromised add-on that reads an agent's environment can't read your mail. Turn ON to let your agents, including cloud sessions, work in your inbox. Sending or replying still follows your CLI email-approval setting, and mail rules, the AI filter, blocked domains, snippets and splits stay yours alone. An agent that reads an email can be steered by what it says, so only turn this on if you want agents in your mail.
allowAgentTokenTeamChat toggle true | false When OFF (default), a Team Chat write over the CLI (send a DM or channel message, react, edit, delete, pin, schedule a DM, invite a guest) is rejected if it presents only an agent's scoped token (the Omniscio-injected $AMC_CLI_TOKEN) — so a compromised MCP server or npm dependency that reads an agent's environment can't message your teammates as you. Turn ON to let your agents write to Team Chat with their own token; every message they send is still labeled "<your name>'s agent".
amcAwarenessPromptEnabled toggle true | false Adds a short note to every session so the agent knows it is running in Omniscio and how to reach it.
archiveAuditRunGuardEnabled toggle true | false Before you archive a session that is still working a Nighty Tidy audit run, ask first. Archive anyway always goes ahead.
archiveSafetyIndicatorEnabled toggle true | false Draw a yellow shield on a session in the sidebar when archiving it would cut off work still coming back to it, such as a running background job, a wake-up or a queued message. Hover it to see the reason. Off by default.
archiveSafetyNetEnabled toggle true | false Before you archive a session, check whether anything is still due back to it, and ask first. Archive anyway always goes ahead.
archiveWhenDoneKeepRules object object { customRules: array of object { id: string (≤40); text: string (≤200) }; presets: array of "question" | "failed" | "deliverable" | "screen-change" | "new-feature" | "cost-security-data" } With Archive when done on, a finished session leaves your inbox by itself unless one of these is true.
askAmcEnabled toggle true | false Adds an Ask Omniscio virtual project — a friendly tutor agent pre-loaded with the Omniscio docs and live state.
askAmcModel text string (≤200) The model Ask Omniscio answers with — Automatic uses a top-tier (Opus class) model on your own AI account
audienceStylePromptEnabled toggle true | false Assume the reader may not be technical — plain language, no jargon, start brief — while favoring clean headers and tight bullet points so replies are easy to skim.
autoApproveConfigFiles toggle true | false Automatically approve when Claude wants to modify its own config files (.claude/, CLAUDE.md). When off, you'll be asked to approve each change
autoApprovePlans toggle true | false When Claude proposes a plan before writing code, approve it automatically instead of asking you first
autoContinueEnabled toggle true | false Automatically nudges the agent to keep going when it pauses mid-task without a question. Prevents unnecessary inbox interruptions during long jobs.
autoDetectQuestions toggle true | false Spot questions in the agent's reply automatically, even when the agent doesn't explicitly ask you.
autoRestartUnresponsiveSessions toggle true | false When a session gets stuck showing "thinking" with no reply — the agent's process wedged and stopped responding — Omniscio restarts the stuck turn so it continues, instead of leaving it spinning forever.
autoResumeOnCrash toggle true | false Automatically restart sessions that were active when the app was closed or crashed. Running sessions receive a continue nudge. Sessions waiting for your input are restored.
bookmarkToolbarPinsEnabled toggle true | false Shows a Pin button on each bookmark. A pinned bookmark gets its own toolbar icon that opens it in one click. Turning this off hides the icons but keeps your pins.
bookmarksCliEnabled toggle true | false Allow external agents to list, create, update, delete, reorder, and launch bookmarks over the local CLI control server. On by default. Flip off to disable all bookmark CLI access at once.
cloudBoxesKeepRunningOnQuit toggle true | false When on (the default), restarting Omniscio leaves your cloud sessions' machines running, so a session you were in the middle of keeps its place and picks up where it was, like any other session. Closing Omniscio for good still stops them: nothing on a machine stops it while the app is closed, so it would keep billing. When off, a restart stops them too.
cloudFirstWorkerSpawn toggle true | false Runs a helper agent's session in the cloud instead of on this computer, so your machine carries the coordinators and not the helpers. Only helpers move: a crew lead, a coordinator, and anything you start yourself stay local. Applies to your next helper spawn; switch it off and every spawn is local again.
cloudRunnerEnabled select "auto" | "on" | "off" Run a session on a cloud machine and drive it from here like one of your own computers. Auto turns it on for an account the Cloud Runner service has enabled. Lives in the Dev Pipeline panel, Setup tab, All settings.
cloudSessionReviewsEnabled toggle true | false When a cloud session’s work is brought back to this computer, run the AI Code Review reviewers you configured in the Dev Pipeline panel against the returned branch, and record what they found. Off by default: a cloud session now asks for its own review while it runs — the reviewers are seated on the same cloud machine that produced the work — so returned work is normally reviewed there, in-process, before it comes home. Switch this on to add an extra capture-time review on top of that. The findings are delivered to you and kept with the branch, and a review does not currently hold the branch back from landing.
cloudSessionSignInProvider text string (≤40) Choose which account signs you in to the machine vendor for cloud sessions. Appears only when the vendor offers more than one sign-in account.
cloudSessionTranscriptReadEnabled toggle true | false When ON, an agent running on a cloud machine can read the transcript of a session other than its own, and every one of those reads is recorded. When OFF, a cloud session can read only its own transcript. ON by default; this is the one switch that closes the door, and only you can change it — an agent’s own token can never turn it back on.
confirmBeforeArchivingAudit toggle true | false When a session is still running an audit, archiving it ends the audit and its results are lost. With this on, closing such a session asks first. Every other session archives exactly as it does today.
contextStallAutoRecoverEnabled toggle true | false When a session fills its context window and stops mid-task without finishing, Omniscio automatically frees space and continues it — so you see a finished reply instead of a blank.
contextWarning75Enabled toggle true | false Post an in-chat note once a conversation is about 75% full of the model's context window. Off by default.
contextWarning90Enabled toggle true | false Post an in-chat note once a conversation is about 90% full — the point where Claude may start summarizing and dropping older messages. Off by default.
crossOrgAgentMessageSelfArchiveEnabled toggle true | false When OFF (default), a message from an agent working for someone outside your workspace is never allowed to close the session quietly — its reader is told plainly not to archive that turn, so the arrival stays on your board for you to see. When ON, an arrival like that ends its turn exactly as a teammate's message does: if the reply leaves you nothing to receive or decide, the session may archive itself. This only affects messages that arrive while “Agent-to-agent messages” is on.
defaultAgentInstructionsCustom text string (≤10000) Free-form custom text appended to every spawned session alongside preset instructions.
defaultAgentInstructionsEnabled toggle true | false Inject curated instruction presets into every Claude Code session — attribution removal, cloud safety, private repos, README standards.
devPipelineArchiveGuardEnabled toggle true | false Refuse to archive a session whose worktree branch has not been pushed, tagged ready-to-merge, or landed on master, so unshipped work is not closed away by accident. Off by default.
dripEnabled toggle true | false Surfaces the Drip virtual project — queue mixed content (text, links, files, folders) into named queues that release into the inbox on a user-chosen cadence.
dripGlobalPause toggle true | false Master pause for every drip. When on, drips keep their cadence but skip every release until you turn this off.
dripHtmlPreviewEnabled toggle true | false When on, a drip item that is an .html file renders live in a sandboxed preview — HTML, CSS and JavaScript run, but the page is isolated (no network, no access to your app). Off shows the file as a plain chip.
engineeringPrinciplesPromptEnabled toggle true | false Adds a short note to every session so the agent follows senior-engineer habits: keep it simple, fix root causes instead of band-aids, believe your bug reports, write real tests, and watch performance and security.
executionBiasPromptEnabled toggle true | false Adds a short note to every session so the agent acts on an actionable request right away, pushes to a real finish instead of stopping at a plan, and backs up a completion claim with evidence.
finalMessageCliBoundaryWins toggle true | false A sub-option of "Show only the final message": Claude Code tells Omniscio where an agent’s real answer begins, and with this on that wins over the marker the agent printed. Stops an agent that wrote you something — a draft email, a document, a list — and then misplaced its marker from hiding it and leaving a reply that says "see above" about text you cannot see. The trade-off is that on some replies you will also see the agent’s working notes above its report. Off by default — turn it on to try it.
finalMessageMarkerAlwaysHide toggle true | false A sub-option of "Show only the final message": when the final-answer marker is present, hide EVERYTHING before it, even on a plain answer with no tool steps, folding it into a collapsible row you can expand. Nothing is deleted; it stays one click away. On by default.
finalMessageMarkerDebug toggle true | false A sub-option of "Show only the final message": draw a distinct divider showing exactly where an agent placed the final-answer marker instead of hiding it. Nothing else changes — the same content stays folded, and it only appears on turns where the agent actually printed the marker. For debugging where agents put the marker. Off by default.
finalMessageMarkerShowAllBlocks toggle true | false A sub-option of "Show only the final message": when an agent marks more than one final message in a single turn (say a report, then a follow-up), show ALL of them instead of only the last, with the work between them tucked into the collapsible row. Nothing is ever deleted. On by default.
finalMessageStructuralFloor toggle true | false A sub-option of "Show only the final message": on a turn that used tools, never let the marker hide the answer or a live question the model wrote after its last tool step — only tool-calls and thinking collapse. Fixes non-Claude models (DeepSeek, Codex, GLM) that place the marker in the wrong spot. Single-step turns are unchanged. On by default.
frictionTriageOverseerEnabled toggle true | false Hand each triage round to this project’s Overseer instead of starting the triage session directly. The Overseer reads the ranked list, decides which problems are worth fixing, and starts the triage helper and its fixers itself. Off by default. If no Overseer is running — or the one that is there is busy — the loop starts the triage session itself, so a round is never skipped.
imageBridgeMode select "off" | "auto" When a selected model cannot see images, send attached images to a vision-capable model first and pass a text brief to the selected model. Uses an extra model call. Off by default.
initialTitleModel text string (≤100) Per-feature model override for naming a session the first time — null inherits the global Utility AI model
keyRemindersPromptEnabled toggle true | false Add a short reminders block to every turn — believe bug reports, act and prove, default to yes, fix root causes, write clean markdown.
learningBigTaskMinutes number integer 1..480 A session that works for at least this many minutes counts as a big task and is looked at for a reusable skill.
learningBigTaskToolSteps number integer 5..500 A session that takes at least this many tool steps counts as a big task and is looked at for a reusable skill.
learningChatLineDetail select "off" | "on" | "detailed" How much a session says in its chat when something is learned from it.
learningDailyCapUsd number number 0.1..100 The most the Learning Loop may spend in a day on pay-per-use models. Once it is reached, reviews pause until tomorrow.
learningHistoryDays number integer 7..3650 How many days of learning history are kept before older entries are removed.
learningMaxNewSkillsPerDay number integer 0..50 The most new skills the Learning Loop may draft in a day. Set 0 to stop new skills.
learningMemoryAreaLimitChars number integer 5000..200000 How much saved memory one area (about you, people, or a single project) may hold before near-duplicates are merged into shorter ones. Nothing is merged while an area is under this size.
learningMemoryCombineEnabled toggle true | false When an area is over its size limit, the Learning Loop merges memories that say nearly the same thing into one. Every merge is listed in the timeline and can be undone.
learningQuietMinutes number integer 5..1440 How long a session must sit untouched before it is reviewed, so work you are still doing is never interrupted.
learningReviewAutomatedSessions toggle true | false Skills only, never memories. Every skill these sessions suggest waits for your approval, and each scheduled job or recipe is reviewed at most once a day, after it finishes. Recipes started by email, messages, boards, other agents or automations are never reviewed.
learningReviewModel unknown "utility" | "haiku" | "sonnet" | "opus" | "luna" The model that reads a finished session and decides whether anything is worth learning. "Follow the Utility AI model" uses whichever model you chose for background helpers.
learningReviewToolActivity toggle true | false Shows the reviewer which tools a session ran and what came back, with secrets removed, so it can learn from what actually happened. Only applies to Claude sessions.
learningShareProjectSkillsWithEngines toggle true | false Lets Codex, Gemini and Hermes sessions use a project's own skills and the skills learned for it, not just Claude sessions.
learningSkillDraftModel unknown "best-available" | "haiku" | "sonnet" | "opus" | "luna" The model that writes a new skill from a hard task. "Best available" picks the strongest model your accounts can reach.
mcOmniPanelRailLabelVisible toggle true | false Shows {pmName}'s name on the slim strip at the right edge of Mission Control. Off leaves just the arrow and the Omni mark. On by default.
mcTasksSidePanelEnabled toggle true | false Docks a collapsible Tasks panel on the right edge of Mission Control so you can see your personal tasks alongside the board.
mcTasksSidePanelRailLabelVisible toggle true | false Shows "My Tasks" on the slim Tasks strip at the right edge of Mission Control. Off leaves just the arrow, the Tasks icon and the task count. On by default.
meetingRoomsEnabled toggle true | false Enable Meeting Rooms
moveProjectWorkspaceEnabled toggle true | false Show "Move to workspace" on a hub’s right-click menu, so a hub can be moved from your personal space into a company workspace (or back) without losing its sessions, history, files or pins. Turning this off hides the action and refuses the move.
omniReadsProjectPages select "ask" | "allowed" | "declined" Omni reads the pages you open, such as a form and its answers, and files what needs doing where you choose. It never changes your pages. Turn this off and Omni leaves them alone, except pages you made from a '+ Omni' template, which keep being read because creating one was your yes for that page. Switch Omni off to stop those too.
outsideMemoryHonchoBaseUrl text string (≤2048) Leave this as it is to use Honcho itself. A server you run yourself must start with https://, or http:// when it runs on this computer.
outsideMemoryHonchoWorkspace text string The Honcho workspace your copies go into. Letters, numbers, dashes and underscores only. It is created for you if it does not exist.
outsideMemoryMem0BaseUrl text string (≤2048) Leave this as it is to use Mem0 itself. A server you run yourself must start with https://, or http:// when it runs on this computer.
outsideMemoryService select "off" | "mem0" | "honcho" Which service keeps a copy of the memories Omniscio saves. Off sends nothing anywhere. Only one service is used at a time.
outsideMemoryShareConversations toggle true | false Off by default. When on, the chat lines you and your agent wrote in a conversation Omniscio has reviewed, with passwords and keys hidden, are also sent to the service picked above. Tool output is never sent. The service may make its own memories from them, and those stay in your account there.
pauseRetriesWhileOffline toggle true | false When Omniscio believes this computer has no internet, it holds the automatic retries that would otherwise reopen sessions, so a momentary outage can't send every session into a doomed reconnect at once. Turn this off if your computer does have internet but Omniscio keeps reporting it as offline — for example on a work network that only reaches the internet through a proxy.
personaPromptEnabled toggle true | false Give every agent a warm, resourceful, get-it-done character up front — agentic, plain-spoken, and biased toward action and yes.
pipelineIntakeGateAutoAdvance toggle true | false Sentry errors, GitHub issues, in-app reports, emailed bugs and Help Desk tickets start their own fix runs. Off, those runs stop at every gate for you. On, they clear the gates like a run you started, and a finished one can reach the ready tag and be landed for you.
pmAssistantName text string (≤40) What {pmName} calls itself. Letters, numbers and spaces, up to 40 characters. Leave it empty to use Omni.
pmBoardDensity select "dense" | "compact" | "comfortable" | "spacious" How tightly items are packed on Mission Control boards. Set in Mission Control settings.
pmBusinessDaysOnly toggle true | false The Risk Heatmap judges timeframes and pace on Monday–Friday only, so “Next 7 days” becomes “Next 5 business days”.
pmCalendarBoardIds list array of string (≤200) Pick which projects' due dates appear on the Calendar. Lives in the Calendar panel settings (the gear).
pmCalendarOverlayEnabled toggle true | false Show or hide due dates and timelines from your projects on the Calendar. Lives in the Calendar panel settings (the gear).
pmHandoffAskFirst toggle true | false On by default: when Mission Control can't answer a question on the spot, it shows a "Keep going with {pmName}" button, and a {pmName} session only starts when you tap it. Turn this off to have the session open on its own.
pmInboxAutomationFailures toggle true | false Send an Inbox alert when a Mission Control automation fails. Set in Mission Control settings.
pmInboxAutomationInvolvesMe toggle true | false Send an Inbox alert when a Mission Control automation changes something assigned to you, that you follow, or on a board only you use. Set in Mission Control settings.
pmInboxDigestMode toggle true | false Batch project events into a single digest notification instead of notifying for each event. Overdue items always notify immediately.
pmInboxEnabled toggle true | false Surface project events (assignments, status changes, due dates) as rows in the unified Inbox so you notice them without checking the project.
pmInboxLevel select "everything" | "involves-me" | "mentions-me" | "nothing" How much Mission Control activity reaches your Inbox: Everything, Involves me, Mentions me or Nothing. Set in Mission Control settings.
pmInboxQuietHoursEnabled toggle true | false Pause project event notifications during a daily window. Overdue items always notify immediately.
pmInboxQuietHoursEnd text string The time each day when project event notifications resume.
pmInboxQuietHoursStart text string The time each day when project event notifications pause.
pmInboxQuietHoursTimeZone text string The timezone used for quiet hours. Defaults to the system timezone when not set.
pmPersonMemoryEnabled toggle true | false Turn this off and it stops saving new facts about you, without turning Mission Control off. What it already saved stays visible in the About You card until you erase it.
pmSetupAiComfort select "low" | "medium" | "high" At Low, Mission Control never sends anything to an AI, so its AI answers are off. Pick Medium or High to turn them on. High uses AI more often.
pmSetupPreset select "tasks" | "projects" | "operations" | "first-agent-board" | "trello" | "jira" | "asana" | "linear" | "notion" | "clickup" | "airtable" | "engineering-linear" | "engineering-jira" Your Mission Control preset (Tasks, Projects or Operations), which sets the columns, views and features new projects start with. Change it, or redo the setup checklist, in Mission Control settings.
pmWhatNextAutoAsk toggle true | false Off by default: the "What should I do next?" card asks only when you press its button. Turn this on to get a fresh answer every time you open the Mission Control home page. Each ask uses AI and costs money.
pmWhatNextCheaperAi toggle true | false Off by default: the "What next?" answer uses the smart AI, the most careful one we tested, on your own AI key. Turn this on for a faster AI that costs about half as much but is less careful.
prMergeQueueAutoMergeDryRun toggle true | false Log what the daemon would auto-merge each tick, but do not actually spawn Claude sessions. Useful for previewing behavior before going live.
prMergeQueueAutoMergePollMinutes number integer 1..120 How often the auto-merge daemon re-checks each repo for new fast-lane PRs (1-120 minutes)
prMergeQueueEnabled toggle true | false Adds the PR Merge Queue sidebar entry and toolbar icon for triaging open pull requests across configured GitHub repos.
prMergeQueueShardCount number integer 1..64 How many machines share the PR merge workload when splitting across machines
prMergeQueueShardEnabled toggle true | false Run the auto-merge daemon on two or more machines so each handles a different, non-overlapping share of the open PRs and no two machines merge the same PR
prMergeQueueShardIndex number integer 0..63 The slot number for this machine in the split (each machine gets a different number, starting at 0)
programHandoffToWindowsEnabled toggle true | false Off by default. The first request puts a card in your inbox so you can allow it for one session or for good. Only a program you were already running qualifies, never a shell or script host.
projectSwitchTarget select "needs_you_or_new_chat" | "last_chat" What opens when you switch to a project. The default shows the top Needs You session for that project, or a new empty chat when nothing needs you. Choose the last chat to pick up where you left off instead.
readLoopBreakerEnabled toggle true | false When an agent gets stuck repeating the same action over and over — re-reading the same unchanged file, or running the same command again and again — Omniscio breaks the loop and re-launches it to continue, instead of letting it spin and burn through your usage.
refreshTitleModel text string (≤100) Per-feature model override for staleness checks and title refreshes (Journey, Latest Topic, and Custom with refresh enabled) — Automatic uses a fast, low-cost model
relentlessSessionRelaunch toggle true | false When a session that was running fails to launch because the machine is momentarily overloaded (a transient OS hiccup), keep retrying — with a growing gap between tries — until it comes back, instead of giving up after a few attempts. Genuine errors still stop and turn red.
requireSpawnSourceSession toggle true | false When on, a session spawned over the command-line API is rejected unless the caller says which session requested it (the X-AMC-Source-Session-Id header — Omniscio-spawned agents have it as $AMC_SESSION_ID). Keeps every spawned session traceable to its origin. On by default — turn off to allow anonymous script or manual spawns.
reviewLoopBreakerEnabled toggle true | false When a session keeps running code-review rounds without hearing from you, it pauses after a set number of rounds and waits for your reply.
runningAppsEnabled toggle true | false Show the Running Apps entry in the sidebar — a live list of the dev servers Omniscio launched through the bundled portless proxy at their .localhost URLs.
scheduledMessagesEnabled toggle true | false Surfaces the Scheduled Messages virtual project — compose a rich-markdown note to yourself and have it dropped into your inbox once or on a recurring schedule.
sessionAutoFocusInput toggle true | false Automatically place cursor in the text box when switching sessions. When off, press R to focus the input (Gmail-style).
sessionForensicsAutoWeeklyEnabled toggle true | false When on, the deep analysis runs on its own once a week (Monday morning). It spawns a paid session and respects the daily spend cap above.
sessionForensicsDailyCostCapUsd number number 0.05..20 Maximum the opt-in deep analysis run can spend per calendar day before it is refused (it spawns a paid session).
sessionForensicsScanIntervalHours number integer 1..168 How often the free deterministic friction scan runs (1-168 hours).
sessionRecallDailyCapUsd number number 0.1..100 Summaries stop for the day once they have cost this much. The matching lines keep coming back.
sessionRecallSummaries toggle true | false Each search asks the background model for a short summary of the three closest sessions, within the daily limit below. Off: agents get the matching lines only.
sessionRefillAllowReopenUserClosed toggle true | false Off by default, and worth understanding before you turn it on. Normally the governor never restarts a session you closed — closing one is a decision, and undoing it stays yours. With this on, sessions you closed count as restartable too, and that includes a session you stopped with Stop: this switch treats a Stop exactly like a plain close. Turn it back off and a Stop is held back again, named as "you stopped" in the held-back list on the Queue page. It is the only way to reach work you closed in bulk earlier, and it is easy to under-count: on one machine 136 sessions were waiting behind this switch. The risk is the same one that keeps it off — a session parked on purpose comes back.
sessionRefillBatch number integer 1..20 How many sessions to revive at most on each 5-minute check.
sessionRefillCooldownMinutes number integer 1..1440 Do not re-poke the same session within this many minutes.
sessionRefillDailySpendCapUSD number number 0..100000 The most the governor may spend per day reviving sessions. Only pay-per-use sessions count (API keys and per-token vendors) — a session on one of your Claude Pro/Max subscription accounts costs nothing extra, so it does not count. Once today’s revives reach this, it pauses until tomorrow. Set 0 to turn the $ cap off (the daily revive-count limit still applies).
sessionRefillIncludePaused toggle true | false Normally only interrupted work is restarted — a session that crashed, was cut off, or failed to answer. Turn this on and a session you PAUSED counts too, and gets un-paused when its turn comes. Off by default: pausing is something you did on purpose, so undoing it stays your call.
sessionRefillMaxCandidateAgeHours number integer 1..720 A session whose last activity is older than this is skipped. Abandoned work is not restarted merely because it was interrupted.
sessionRefillMaxRevivesPerSessionPerDay number integer 1..50 How many times one session may be restarted in a single day. The cooldown above is only a delay; this is a budget, and it is what stops the governor circling back to the same session over and over. Leave it at 1 unless you specifically want repeat nudges.
sessionRefillTargetCount number integer 1..500 When fewer than this many sessions are running, the governor restarts recently-active INTERRUPTED work sessions until you are back to this number. Interrupted means the turn ended abnormally and left work unfinished — the process stopped mid-work, or the turn failed to deliver an answer. It never restarts a session that finished its turn cleanly, one that is waiting on you, one you stopped yourself, or one that recovers on its own.
sessionSelfArchiveOpenWorkGuardEnabled toggle true | false When ON (default), a session that tries to archive itself stays on your board while its branch still has work that is not on master, such as an open pull request. It is told why and can sign off once the work lands. Turn this off to let finished sessions archive themselves whatever their branch holds.
sessionSelfArchiveWithoutApproval toggle true | false When ON, a session that has finished its work can archive itself immediately — even if "Require approval for session pause / snooze / archive" is on — with nothing landing in your inbox. Only a session archiving itself is exempt; archiving another session over the CLI still asks. Off by default.
sessionSharedComposer toggle true | false The box you type prompts into uses the same editor as the other writing boxes: lists nest with Tab, Enter continues them, and an empty bullet steps back one level. Your send key is unchanged. Turn this off to go back to the old box.
sessionTitleStyle select "brief" | "descriptive" | "journey" | "latest_topic" | "custom" Pick how AI-generated session titles are written — Brief, Descriptive, Journey, Latest Topic, or Custom. Journey and Latest Topic auto-refresh as the conversation evolves.
sharesSidebarEnabled toggle true | false Show or hide the Shares entry in the sidebar; links keep working either way
shellCwdPersistNudgeEnabled toggle true | false Tells each session that its command line stays in whatever folder it moved to, so the agent switches folders once instead of repeating the same switch on every command. That repetition was nearly half of all commands agents ran.
showBookmarksInToolbar toggle true | false Show the bookmarks toolbar button + popover. On by default. When off, the bookmark icon is hidden and the popover is unreachable. Saved bookmark rows are preserved.
skillSlashAutocomplete toggle true | false Type / in the composer to pick a skill from a filtering menu
sshKeepSessionsRunningWhileAsleep toggle true | false Sessions on your own Linux machines keep running there when this computer sleeps or closes — and keep spending. They approve what your approval level allows and wait for you on the rest. Needs Node.js on the machine.
stickyNotesEnabled toggle true | false Enable floating sticky notes on the desktop
teamTimeEnabled toggle true | false World clock dashboard for managing team members across timezones with live clocks, working-hours status, and a meeting planner.
wheresMyWorkEnabled toggle true | false One screen showing what actually happened to your changes: landed on the shared repo, waiting on review, turned down, or stranded with no pull request.

Inbox & Notifications (150)

Everything waiting on you, and how Omniscio tells you about it.

Setting Type Accepted values What it does
activityNudgesEnabled toggle true | false Cards that react to what you are doing on unless you turn them off — save a phrase you keep typing, clear out an unused quick reply, a reminder when your inbox is piling up.
agentEmailEnabled toggle true | false Give your agent its own email address so people can email it to start or continue a session. Off by default; turning it on lets you claim an address in the sidebar under Agent Tools, Agent Email.
alarmNlpDailyCostCap number number 0..5 Max daily spend on Haiku-assisted natural-language alarm parsing
alarmsAssertiveness select "modal" | "banner" | "silent-banner" How alarms surface when they fire.
alarmsBringToForeground toggle true | false Raise the Omniscio window above other apps when an alarm fires
alarmsDefaultMaxSnoozes number integer -1..20 Maximum number of times an alarm can be snoozed before only Dismiss remains
alarmsDefaultSnoozeMinutes unknown 5 | 9 | 15 | 30 How long to snooze a firing alarm by default
alarmsDefaultSound text string (≤200) Sound played when an alarm fires
alarmsDefaultSoundDurationSeconds number integer -1..300 How long the alarm sound plays before stopping (or forever)
alarmsDefaultSoundFadeInSeconds number integer 0..300 Ramp the alarm volume from silent to full over this many seconds — gentle wake or crescendo
alarmsDefaultSoundPlayMode select "once" | "loop" Play the alarm sound once or loop until you dismiss
alarmsDefaultSpeakLabel toggle true | false Have the alarm read its label aloud when it fires (text-to-speech)
alarmsMaxRingingMinutes number integer 1..60 Auto-dismiss alarms to inbox after this many minutes
alarmsPierceFocusMode toggle true | false Fire alarms immediately even during Focus Mode batching
alertAutoDismissEnabled toggle true | false Dismiss an alert on its own after it has sat there for the set time while you were active at this computer. Time you spend away does not count. Questions, critical alerts, sign-in and security alerts are never cleared this way. A cleared alert sits in Recently dismissed and can be restored.
alertAutoDismissHours number number 1..720 Hours of your active time an alert may sit before it clears itself. Between 1 and 720.
alertOwnerFirstSighting toggle true | false The first time a kind of system alert is raised, the card also stays in your inbox so you see it before it becomes routine. Every later card of that kind follows the routing above. Once you set a route or mute a kind, your choice always wins.
alertPushFollowsSeverity toggle true | false Send an alert the app marks critical to your phone, and leave everything else in the inbox unless you switch that type on
alertRegistryOwnerRouting toggle true | false An alert type that names its owning crew is delivered to that crew instead of your inbox. Alert routes you set yourself always win, and safety alerts always stay with you.
alertSessionDefaultProjectId text string (≤64) Which hub the Start session button on an alert opens in, when the alert does not name one itself. Automatic uses the hub holding this app’s own code if you have one, so alerts about Omniscio start where you develop it — otherwise Claude.
alertTriageDeskCrewId text string (≤64) The id of the triage desk crew. Leave it empty to use the crew that sorts alerts. The id is the one shown on the crew in the Overseer panel.
alertTriageDeskEnabled toggle true | false While a triage desk crew has a live lead, an alert that would have started its own session is sent to that lead instead, and the lead decides whether it is a new fault or part of one it is already fixing. Off means every alert starts its own session, exactly as before.
alertUnclaimedCrewId text string (≤64) The id of the crew that receives new system alerts no one owns. Leave it empty to keep every one of those cards in your inbox — the triage desk setting below does not change this. The id is the one shown on the crew in the Overseer panel.
alertUnclaimedCrewRouting toggle true | false A new system alert with no owner goes to the crew you name below instead of your inbox, and one card a day lists what was sent away. Sign-ins, security, approvals, people waiting, disk warnings and your digests still reach you. With no crew named below, every one of those cards stays with you.
archiveDigestCadence select "off" | "daily" | "weekly" How often to post an Archive Insights AI digest to your inbox automatically — off, daily, or weekly. On-demand analysis is always available inside Archive Insights.
autoFocusOnNeedsYou toggle true | false Bring the app to the foreground when a session needs your attention.
autoSwitchToInbox toggle true | false Automatically navigate to the inbox when another session needs attention, but only if you've been idle for at least 5 seconds. Won't interrupt scrolling, clicking, or typing
bugIntakeAppendPrompt text string (≤10000) Extra instructions added to the investigation prompt for every bug report routed to this project (email, Sentry, in-app). Stacks after the global Bug Intake instructions.
bugIntakeEnabled toggle true | false Show the Bug Intake sidebar entry — collects bug reports from Sentry, GitHub, bug-report emails and in-app reports and triages them via spawned agents. When off, no report from any source starts a session.
bugReportEmailEnabled toggle true | false When on, clicking the bug-report icon, sending feedback, or reporting a missed question widget sends the report to the Omniscio team by email and to the report database. Off sends nothing: reports stay on this computer and go out when you turn this back on.
calendarDailyAgendaEnabled toggle true | false Post a 'Today's Agenda' card to your inbox each morning listing the day's events.
calendarEnabled toggle true | false Show upcoming calendar events and get reminders before meetings in the sidebar.
calendarNotificationDelivery select "inbox" | "toast" | "both" Deliver calendar notifications as an inbox alert, a toast pop-up, or both
calendarReminderMinutes number integer 0..120 How many minutes before an event starts to send the "starting soon" reminder
calendarWeekStartDay select "sunday" | "monday" Choose which day the calendar week begins on.
cardsModeAllowAlways toggle true | false A session that asks to report by cards normally waits for your answer on a card. On, a session that asks is switched on at once. Off by default, and only you can change it.
contentFreeMobilePush toggle true | false Send push notifications to your phone without the sender, subject, or message text
crashAlertEmailEnabled toggle true | false When diagnostics email is on, also email the team on each crash. Turn OFF to email only the weekly digest — crashes still auto-triage inside Omniscio (via Sentry), and the on-disk crash log continues.
dailyDigestEnabled toggle true | false Generate a daily briefing summarising AI session activity across all projects.
dailyDigestSources object object { calendar: true | false; gmail: true | false; pm-events: true | false; pm-feed-digest: true | false; rss: true | false; sessions: true | false; slack: true | false; sms: true | false; telegram: true | false } Choose which data sources are included in your daily briefing
deepSeekBalanceAlertLeadHours number number 0..720 Get the DeepSeek balance forecast alert this many hours before the projected run-out
desktopIconBadgeEnabled toggle true | false Show or hide the count badge on your taskbar or dock icon for sessions that need you.
developerMessagesEnabled toggle true | false Turning this off stops announcements, surveys, and read receipts from the Omniscio team.
driveEnabled toggle true | false Browse, upload, and manage Google Drive files from the sidebar.
dropboxEnabled toggle true | false Browse, upload, and manage Dropbox files from the sidebar.
educationTipsEnabled toggle true | false Cards that appear once and stay away — emptying your inbox, turning off desktop notifications. Off unless you turn them on.
emailBlockRemoteImages toggle true | false Stop email senders from loading external images when you open a message. Remote images quietly report your IP address and that you opened the email back to the sender; blocking them keeps that private. Inline and attached images still show. Off by default.
emailCleanupClassicLayout toggle true | false Use the original flat sender list for Email Cleanup instead of the AI-guided walkthrough. Turn on if you prefer the simpler view.
emailInboundEnabled toggle true | false Receive emails via AgentMail, process them with Claude, and send replies
emailInboundInboxId text string (≤200) AgentMail inbox identifier for receiving emails
emailInboundPrescreenPrompt text string (≤16000) Full classifier prompt for inbound emails (default shown when empty; JSON output format always enforced)
emailSummarizerArchiveEnabled toggle true | false Archive in AgentMail after a successful summary
emailSummarizerDailyCostCapUsd number number 0.1..20 Combined daily spend limit for the email summarizer
emailSummarizerDefaultPrompt text string (≤20000) Generic prompt used when no rule matches
emailSummarizerEnabled toggle true | false Auto-summarize forwarded emails
emailSummarizerGmailEnabled toggle true | false Auto-summarize Gmail threads tagged with your label
emailSummarizerInboxId text string Inbox to watch for summarizable emails
featureDiscoveryNudgesEnabled toggle true | false Short "did you know" cards for features you have not tried, plus shortcut coaching. Off unless you turn them on.
focusModeFeatureEnabled toggle true | false Master kill-switch for Focus Mode. When off the toolbar pill is hidden and alerts always fire individually
gmailAutoFocusReply toggle true | false Place cursor in the reply textarea automatically when you open an email. Off (Superhuman/Gmail-style) keeps focus on the message body so triage shortcuts (E archive, S star, U unread, ! spam, X select, H snooze) work — press R to start typing a reply.
gmailAutoMarkRead toggle true | false Automatically mark email threads as read when you open them
gmailDefaultQuery text string (≤500) Default Gmail search query used when loading the inbox
gmailEmailDarkRecolor toggle true | false A new way to show designed emails in dark mode. Instead of inverting the whole email, it recolours backgrounds and text, keeps photos and brand colours as they are, uses the sender's own dark design when there is one, and keeps logos readable. Off by default; turn it off to go back to the current dark mode.
gmailEnabled toggle true | false Show Gmail in the sidebar for reading and sending email
gmailInboxZeroCelebration toggle true | false Show a brief animation when you clear all emails from your inbox
gmailPageSize number integer 1..100 Number of email threads to load at a time (10–100)
gmailSharedComposer toggle true | false The compose and reply boxes use the same editor as the other writing boxes: lists nest with Tab, Enter continues them, and an empty bullet steps back one level. Your send shortcut does not change. Turn this off to go back to the old plain text box.
googleDocImportEnabled toggle true | false When you paste a Google Doc or Slides URL into chat, fetch its contents instead of pasting the URL as text. Hold Shift while pasting to bypass.
googleDocsDestFolderId text string When set (and no template is configured), new Docs are created inside this Drive folder
googleDocsExportEnabled toggle true | false Right-click a project doc, scratchpad, or agent message and publish its Markdown to a Google Doc
googleDocsTemplateId text string When set, each publish appends a new tab to this Doc instead of creating a new one
hideRoutineUpdatesFromInbox toggle true | false When a session finishes a turn and says its own reply was a routine update, that turn stays out of the inbox. Nothing is deleted, and a turn that asks a question is never hidden. On by default.
inboxAnalyticsEnabled toggle true | false When on, Omniscio records how your inbox items behave — how long they wait before you clear them, how many pile up on average, how often you look without acting, and how long you spend on each — for the Stats → Inbox tab. The report stays on this device and never stores message content, phone numbers, or ids.
inboxClearSessionEnabled toggle true | false Adds "Clear from inbox" to a session row's menu. It removes only that row: the session keeps running, its scheduled wake-ups still fire, and other sessions can still message it. The row comes back by itself the next time the session needs you — a new finished turn or a question. Dismiss on a session still archives it, and now says so.
inboxEnterRequiresChosenCard toggle true | false When the inbox opens a card for you (after you approve, dismiss or reply), Enter, X and the other one-key shortcuts on the card do nothing until you click or Tab into it. This stops a stray Enter from approving the next card. When off, the keys work as soon as the card appears.
inboxHiddenHubIds list array of string Keep a hub out of your inbox without disturbing the hub itself: switch a hub off and its items leave the Inbox list and the Inbox count, while its sidebar row keeps its needs-you badge. Every hub starts switched on.
inboxShowAutomations toggle true | false Automation rules waiting for your approval
inboxShowCalendar toggle true | false Google Calendar reminders and agenda
inboxShowCliPending toggle true | false Pending CLI approval requests
inboxShowCron toggle true | false Cron jobs waiting for your approval
inboxShowDigest toggle true | false Daily briefing summaries
inboxShowRecipes toggle true | false Recipe approvals and failed, stalled or incomplete runs
inboxShowSessions toggle true | false Claude Code sessions needing attention
inboxShowSms toggle true | false Incoming text messages via Pushbullet
inboxShowTelegram toggle true | false Telegram messages via MTProto
inboxSortOrder select "oldest" | "newest" Oldest first groups the inbox by project. Newest first shows one list with the newest item at the top and no project groups.
kimiBalanceMonitorEnabled toggle true | false Watch your Moonshot (Kimi) API balance and raise an inbox card with a one-click Recharge button before it runs out
kimiBalanceThresholdUSD number number 0..10000 Get the Kimi low-balance alert once your Moonshot balance falls under this dollar amount
messageInboundApprovedSenders map map of string → array of string (≤200) Allowlist of email addresses permitted to send messages to your inbox
mobileReliabilityAlertsEnabled toggle true | false Get one inbox alert if a device opens the mobile web app but never finishes loading (a sign the mobile app is broken on that device); it clears itself when the app loads again
notificationBehavior select "always" | "backgrounded" | "never" When to show system notifications: always, backgrounded, or never
notificationHistoryEnabled toggle true | false Keep a log of recent chimes — which sessions triggered them, whether they played, and why they were suppressed.
notificationSoundFinishedEnabled toggle true | false Turn the chime on or off per event — needs you, approval waiting, session finished, stalled, error — and pick a different sound for each.
onedriveEnabled toggle true | false Browse, upload, and manage your Microsoft OneDrive files from the sidebar
overseerOmniNoticesEnabled toggle true | false Short notes about how your Overseer and {pmName} share your inbox. Turning them off never changes what your Overseer may hold.
overseerScreensOmniCards toggle true | false Off: your Overseer never holds or hides {pmName} or Mission Control cards. They come straight to you. On: it screens them like any other card.
ownerAlertsInOmniscioHub toggle true | false Alerts you need to see yourself appear in your Omniscio hub instead of the general Alerts list. Machine alarms stay in Alerts.
pasteRichTextAsMarkdown toggle true | false When pasting from Google Docs, Word, or web pages into the chat composer, convert the HTML formatting to Markdown. Off makes {mod}+V behave like {mod}+Shift+V.
pomodoroAutoEnableFocusModeDefault toggle true | false When on, starting a focus block silences notifications via Focus Mode; breaks release them. Manually toggling the bell icon during a run stops Pomodoro from managing it for the rest of the run. Per-preset overrides still win.
pomodoroPhaseForeground toggle true | false Raise the Omniscio window above other apps on each Pomodoro phase transition (focus → break and back). Off by default — most users prefer just the chime.
pomodoroScheduleEnabled toggle true | false Allow weekday rules to auto-start Pomodoro runs at their scheduled times (turn off to silence the scheduler without deleting rules)
postSendNavigation list array of "stay" | "next_in_project" | "next_in_inbox" | "waiting_room" What happens after sending a message: stay, next session, or clear panel
prLandCardsSkipOwnAuthors toggle true | false When a pull request you wrote lands, no landed card is made for it. Other developers' lands still arrive as usual. Turn this off if you want to see your own lands too.
pushOriginationAlertsEnabled toggle true | false Get one inbox alert if a phone or browser is set up for push notifications and sessions need your attention, but nothing was sent to any device — the case where your phone has quietly stopped being notified; it clears itself as soon as push reaches your devices again
quietHoursEnabled toggle true | false Silence the notification chime during a daily window or for 1, 2 or 4 hours. Your inbox, alerts and pop-ups keep working.
quietHoursEnd text string The time the daily quiet window ends and the chime can play again. Appears once Quiet hours is on.
quietHoursStart text string The time the daily quiet window begins, shown as From under Quiet hours. Appears once Quiet hours is on.
rssDigestEnabled toggle true | false AI-curated morning briefing summarising your RSS feeds
rssDigestInterests text string (≤1000) Personalise the digest by listing topics you care about
rssDigestTime text string Time of day the daily digest is delivered
rssEnabled toggle true | false Subscribe to RSS and Atom feeds in the sidebar
securityAlertOffsiteEmailEnabled toggle true | false Send yourself a copy of every security alert, so the notice still exists even if someone deletes the records on this computer. At most one email per kind of alert per hour.
sheetsEnabled toggle true | false Browse and edit spreadsheets from the sidebar.
slackEnabled toggle true | false Monitor Slack channels and DMs in the sidebar
slackPersonalEnabled toggle true | false Send messages as yourself using OAuth instead of as the bot (requires bot setup first)
smsEnabled toggle true | false Send and receive text messages via Pushbullet
smsHealthAlertsEnabled toggle true | false Raise an inbox alert (and one notification) when SMS is on but not working — a missing/expired Pushbullet token or a sustained disconnect. Clears itself once SMS reconnects.
smsProvider select "pushbullet" | "native" Pushbullet routes texts through Pushbullet’s cloud. Native (my phone) sends and receives over your own phone’s real SIM via a self-hosted gateway app — no third-party cloud.
spamFilterAgentEmailEnabled toggle true | false New email from strangers to your agent's address and your public support address. Caught mail starts no session and gets no reply.
spamFilterCalendarDeleteEvent toggle true | false Also delete an invite from your Google Calendar when it comes from a sender you marked as spam. Invites the automatic check catches are only hidden, never deleted. Deleted invites stay in Google Calendar's trash for 30 days.
spamFilterCalendarEnabled toggle true | false Invites from organizers outside your own organization. A caught invite gets no notice.
spamFilterEnabled toggle true | false Check messages from people you don't know and keep junk in Spam. Messages from people you know are never checked.
spamFilterSmsEnabled toggle true | false Texts from numbers that aren't saved as contacts and that you have never texted. Short-code senders such as bank and login codes are never checked.
supermailAiPlainSpeakAutoSplitId text string (≤120) Which Supermail inbox gets a Plain Speak card written for it automatically. Email in every other inbox waits until you press V.
supermailAiSummaryAutoSenders list array of string (≤320) The senders and domains whose threads the Catch me up AI summary generates automatically on open (the “Chosen senders” mode).
supermailAiSummaryModel text string (≤120) Which AI model writes the Catch me up summary. Leave on the default for the built-in fast, low-cost model.
supermailAiSummaryPrompt text string (≤4000) The prompt the Catch me up AI summary uses. Leave blank for the built-in default.
supermailAiSummaryTrigger select "manual" | "auto" | "selective" Whether the Catch me up AI summary runs on a button you click, automatically on every thread, or automatically only for chosen senders.
supermailArchiveSync toggle true | false Archiving an email card also archives it in Gmail, and archiving it in Gmail clears the card. Only applies while emails are shown in your inbox.
supermailDensity select "tight" | "compact" | "comfortable" | "spacious" | "roomy" How much space between emails in the Supermail list — Compact, Comfortable, or Spacious.
supermailEmailDarkRecolor toggle true | false A new way to show designed emails in dark mode. Instead of inverting the whole email, it recolours backgrounds and text, keeps photos and brand colours as they are, uses the sender's own dark design when there is one, and keeps logos readable. Off by default; turn it off to go back to the current dark mode.
supermailEmailsInInbox select "off" | "all" | "important" Choose whether incoming Supermail email reaches the Omniscio inbox as a card with an inline reply box — off, all mail, or only mail Gmail marks important.
supermailHeaderLayout select "current" | "unified" | "rail" Choose how the Mail/Sessions switch and mail toolbar are arranged.
supermailInboxBadgeMode select "unread" | "total" What the number next to Supermail in the sidebar counts — Unread (drops as you read, like Apple Mail / Gmail) or Total in inbox (drops as you archive / snooze / label, like Superhuman)
supermailUseAmcGmail toggle true | false Read your inbox through the Google account you connected in Settings — no separate Supermail sign-in. Turn off to use Supermail's own sign-in.
telegramEnabled toggle true | false View and reply to Telegram messages via MTProto
telegramEngine select "mtcute" | "gramjs" Choose the MTProto engine: mtcute (maintained, recommended) or legacy GramJS. Switching engines signs you out of Telegram until you reconnect.
telemetryEmailEnabled toggle true | false Master switch for Omniscio's diagnostic emails from this install. On = the weekly usage digest, plus each crash unless you turn off 'Email crash reports' below. Off silences both; the on-disk crash log, Sentry, and Omniscio triage keep working.
toastDisplayDurationSeconds number integer 3..30 How long error and warning toasts stay on screen before dismissing.
traySystemNotificationsEnabled toggle true | false Send Omniscio's own notices — an outage, a failed scheduled job, a budget or balance warning — from the tray icon, labelled so they read apart from your session alerts.
vendorKeyWatchSharedKeyVendors list array of string (≤64) Mark a vendor key that other computers also use, so its spend is not compared with this computer
vendorKeyWatchUnexplainedUsd number number 0..10000 Get the Vendor key watch alert once a vendor reports this many dollars more spend than Omniscio recorded
watchingRunningAgentNudgeEnabled toggle true | false Show a small hint inside a session when you have been watching a running agent for a while, reminding you it will come to your inbox when it is done. Desktop only.
watchingTimeRecapCardEnabled toggle true | false On a day you spend a lot of time watching agents work, add an inbox card at most once a week with the time and a nudge to run more agents in parallel.
webhooksEnabled toggle true | false Receive messages from external services like CI/CD pipelines, monitoring tools, or custom apps by giving them a URL to send data to.
weeklySecurityDigestEnabled toggle true | false Every week, one card that rounds up the security alerts, spend alerts, scan findings and control-server activity of the last seven days, and emails the same summary to you. Off unless you turn it on, and the first one only arrives once this computer has been set up for a week.
weeklySummaryDailyCostCapUsd number number 0.05..5 Maximum spend per day on weekly summary Haiku calls before generation pauses.
weeklySummaryEnabled toggle true | false Generates a summary every Monday at the scheduled hour. Disable to pause future runs; existing summaries stay visible.
weeklySummaryIncludeOmni toggle true | false Add how much Omni did this week (answers sorted, action items filed, spreadsheets reviewed) to your Weekly Summary. Counts only.
weeklySummaryScheduleHour number integer 0..23 Hour-of-day (local time, Monday only) when the weekly summary generates.

Projects & Tasks (53)

The work you keep in Omniscio — folders, to-dos, boards, notes and your own writing.

Setting Type Accepted values What it does
autoCapitalizeTasks toggle true | false Capitalize the first word and the start of each sentence as you type a task — skips URLs, file paths, and abbreviations. Matches the behavior of the Vault notes app.
pmOpsQuietShiftReportsEnabled toggle true | false {pmName} always reports busy work shifts. Turn this on to also get a short note when {pmName} had nothing to do, so you know it is still keeping watch. Off by default.
pmQuietNudgeSendRightAway toggle true | false When off, Nudge opens a draft update you can edit before it is sent.
tasksV2AllProjectsView toggle true | false Show every project stacked in one long scroll instead of one project at a time. Off by default: Tasks opens on the last project you had open (or Inbox), and the All Projects entry is hidden. Turn it on to open on the all-projects view.
tasksV2ArrangeAiEnabled toggle true | false Let the richer AI pass reorder your day when you arrange the plate. Off keeps Arrange free: it still sorts by your pins and due dates, but never calls a model.
tasksV2ArrangeModel text string (≤100) Model for arranging your day
tasksV2BreakdownNudgesEnabled toggle true | false Show a gentle 'this looks big - break it down?' hint on large or vague tasks (a free local hint; costs nothing until you click). On by default. Switch it with 'Looks-big nudges' in the Tasks header's More menu (shown while the break-it-down helper is on), in the Customize panel, or under Settings > Performance - all three change this one setting.
tasksV2CalendarShowTitles toggle true | false
tasksV2CatchesEnabled toggle true | false When a session ends or is archived, the end of its transcript and the titles of your open tasks are sent to OpenRouter, an outside AI service, to look for follow-up tasks and stage them in the Caught view for you to approve or dismiss. Turning it on also reads sessions that ended during the look-back window below, not only sessions that end from now on; that first look back belongs to the first account to use Caught on this computer. Off sends nothing: no transcript read, no AI spend.
tasksV2CatchesGuidance text string (≤2000) Optional. Tell the AI in your own words what makes a follow-up worth catching (for example "only things I still owe someone" or "skip anything about code"). It steers which suggestions are kept; the format it returns is fixed, so a wording change can never break catching. Leave it empty for the standard behavior.
tasksV2CatchesLookbackDays number integer 1..14 How many days back Caught looks (1 to 14). This window also applies to the first check after you turn Caught on, so sessions that ended before then are read too. On a shared computer that first check belongs to the first account to use Caught here; a later account starts from the first sweep it runs.
tasksV2CatchesProjectIds unknown pipeline Only catch from these projects
tasksV2CaughtColor text string (≤32) An accent-colour override for the built-in Caught view in Tasks (the triage view for tasks captured from elsewhere), so you can tell it apart from your own lists. Null (the default) uses the standard theme colour. Synonyms: caught view colour, caught accent, recolour the caught view, tint caught.
tasksV2CaughtFromMeetings toggle true | false Bring in action items from Meetings
tasksV2CaughtIcon text string (≤64) An icon override for the built-in Caught view in Tasks, by Lucide icon name. Null (the default) renders the standard Caught glyph. Synonyms: caught view icon, caught glyph, change the caught icon.
tasksV2CaughtName unknown pipeline A custom display name for the built-in Caught view in Tasks. An empty string (the default) uses the translated 'Caught' label. Synonyms: caught view name, rename caught, caught view label, what the caught view is called.
tasksV2CaughtWhoseItems select "mine" | "everyone" Whose action items from calls
tasksV2CheckboxSelects toggle true | false Makes task checkboxes work like email: checking a box picks the task instead of finishing it, so one stray click can never clear a task. An action bar appears as soon as one task is checked, with Done and Dropped on it. Off by default. Holding Ctrl or Shift while clicking always selects, either way.
tasksV2CheckinHour number integer 0..23 Daily check-in hour
tasksV2CloseoutAutoOpenEnabled toggle true | false Automatically show the end-of-day close-out screen once when you open Today at or after your evening hour (6pm unless you change it). On by default.
tasksV2CloseoutDigestEnabled toggle true | false Once a day at your wrap-up hour, get one inbox note with how today went and what's coming tomorrow. Skipped on days you've already wrapped up.
tasksV2CloseoutHour number integer 0..23 Evening wrap-up hour
tasksV2CompactDensity toggle true | false Tightens the vertical spacing of task rows for a denser list. Off by default; turn it on to fit more tasks on screen. Applies to both the All-{projectNounPlural} view and each {projectNounLower} outliner.
tasksV2DailyCheckinEnabled toggle true | false A short AI conversation once a day that reviews what is on your plate and sets today’s focus. Off stops the automatic daily run. You can still start a check-in yourself.
tasksV2DeletedPurgeEnabled toggle true | false A task you delete stays recoverable for 30 days, then is permanently removed together with its private day-log text. Off keeps deleted tasks forever instead.
tasksV2DueSoonAlertHours number integer 0..168 How many hours before a task deadline to send an early heads-up alert. Muting any task reminder card turns off all task reminders, including email, text and phone. Set to 0 to turn off only the due-soon heads-up.
tasksV2HideCompleted toggle true | false Hides finished tasks wherever they still show, mainly the Today plate Done section (most tasks archive out of the list when you finish them). Off by default.
tasksV2InboxTriageEnabled toggle true | false Allow starting the project-manager sessions that organize your Caught items (the Caught lane's Triage button) and file your unsorted Inbox tasks (the Inbox triage card). Off and neither triage session can be started.
tasksV2InstantFinish toggle true | false Removes a task the moment you finish it, instead of showing it crossed out for a short pause and then folding it away. Undo still works with Ctrl+Z and the Undo button. Off by default.
tasksV2InterviewEnabled toggle true | false Turn on the on-demand 'break this down' interview that expands a task into sub-steps. On by default; free until you open it.
tasksV2KeepWarmEnabled toggle true | false Keeps your Tasks panel loaded in the background once you’ve opened it, so switching back into it is an instant flip instead of rebuilding the list every time. Desktop only. On by default; turn off to load Tasks fresh each time (the old behavior).
tasksV2MemoryEnabled toggle true | false Journals what you planned vs. finished each day and lets the AI arrange read your real patterns: typical capacity, chronic carry-overs, tasks you keep snoozing. Once a day it also uses AI to note what it has learned about you. Those notes are stored only on this computer, and when Global Memory is on they also help your other sessions.
tasksV2MilestoneNudgesEnabled toggle true | false Brief tips at natural points as you use Tasks, such as your fifth task or your first project, each pointing at a feature you might not have found yet. Each tip shows only once. The “Don’t show these” button on a tip turns this off; turn it back on here.
tasksV2PlanMyDayEnabled toggle true | false An AI planner that reads your tasks (and your calendar, when connected) and proposes a plan for today for you to review. Uses AI. Off blocks every Plan my day AI call, including the session it runs.
tasksV2PlanMyDayLoadLabelsEnabled toggle true | false Shows a small label above Plan my day's AI message (Light day, Normal day, Heavy day or Overloaded day) so you can see how full your day looks at a glance. Off hides the label only.
tasksV2QuickAddPosition select "top" | "bottom" Choose where a task you add with the Quick Add row appears in the list. Top puts new tasks above the others (the default); Bottom adds them to the end.
tasksV2ReminderEmail toggle true | false Emails due, due-soon, snooze and follow-up reminders to the email you sign in with, sent from your agent email address. Quiet hours apply.
tasksV2ReminderPhonePush toggle true | false Buzzes your paired phone for due, due-soon, snooze, follow-up and draft-ready reminders, and when task agents keep failing to start or a draft does not finish. Quiet hours apply. Nothing is sent until a browser or the phone app has connected once through Web Access.
tasksV2ReminderSms toggle true | false Texts reminders to your alert phone number through Twilio. Quiet hours apply.
tasksV2RightNowAiEnabled toggle true | false 'Right now' uses a paid AI call to refine its suggestions instead of the free local ranking. Off by default: turning it on sends your task text to an outside AI service.
tasksV2RightNowCardEnabled toggle true | false Shows the Right now card at the top of Today in Tasks, suggesting your best next task and a short list of alternatives. On by default. Turn it off to hide the card and stop computing the suggestion. Synonyms: right now card, next task suggestion, top task on today, what to do now.
tasksV2ShareAllAttachmentsWithAgents toggle true | false Every file attached to a task is offered to agents launched on that task, without ticking each one. Off: only files you mark Share with agent are offered.
tasksV2Shortcuts unknown pipeline Customize the Tasks command-mode keys — snooze, deadline, archive, done, context, launch agent, break down, command line, focus moves, and the cheat-sheet.
tasksV2ShowCheckboxes toggle true | false Shows the little checkbox at the start of every task. On by default; turn it off for a cleaner list with no checkboxes. You can still finish a task with the keyboard (x or e), a middle-click on the row, or the row menu.
tasksV2ShowModeLabel toggle true | false Shows a small label on the task you are on for a few seconds — "Shortcuts on · Space to type" when single letters act as shortcuts, "Typing · Esc for shortcuts" while you type — then it steps away. On by default; turn it off to rely on the outline color alone.
tasksV2SkipFinishConfirm toggle true | false Skips the "are you sure?" step when you finish or drop tasks, so a batch clears in one click instead of two. The Undo button still appears every time, and finished tasks go to Archived rather than being deleted, so a mis-click is always recoverable. Deleting tasks always asks, no matter how this is set. Off by default.
tasksV2TodayCalendarEnabled toggle true | false Let Today and Plan my day read your Google Calendar meetings. Off keeps your calendar out of Tasks, Plan my day included. Needs the Calendar integration on. On by default.
tasksV2TodayColor text string (≤32) An accent-colour override for the built-in Today view in Tasks, so you can tell it apart from your own lists. Null (the default) uses the standard theme colour. Toggles the appearance of the Today view only. Synonyms: today view colour, today accent, recolour the today view, tint today.
tasksV2TodayIcon text string (≤64) An icon override for the built-in Today view in Tasks, by Lucide icon name. Null (the default) renders the standard Today glyph. Synonyms: today view icon, today glyph, change the today icon.
tasksV2TodayName unknown pipeline A custom display name for the built-in Today view in Tasks. An empty string (the default) uses the translated 'Today' label. Synonyms: today view name, rename today, today view label, what the today view is called.
tasksV2TrickleWhileHidden toggle true | false When you hide Tasks, your trickles pause and pick up again when Tasks comes back. Turn this on to keep them sending tasks to your inbox even while Tasks is hidden. Off by default.
tasksV2UnsortedClass select "unsorted" | "do-first" | "plan" | "delegate" | "drop" When a task has neither importance nor urgency set, Tasks cannot tell which group it belongs in. Choose what it shows as: Not sorted yet (the default) until you set a priority, or one of the four groups.
tasksV2UrgencyEnabled toggle true | false

Automation & Scheduling (15)

Work Omniscio does on its own — on a schedule, on a trigger, or as a pipeline.

Setting Type Accepted values What it does
autoLanderEnabled toggle true | false The master switch for the auto-lander — the background service that merges each branch you mark ready-to-merge into your main branch automatically, on this computer only; it never pushes. Switching the Dev Pipeline panel on arms it for the repos that panel already covers, so you usually do not have to turn it on by hand — and your own choice here always wins, in both directions. Off means nothing lands on its own and finished branches wait for you. The same switch also lives in the Dev Pipeline panel's Setup tab.
autoLanderRepos list array of object { dryRun: true | false; enabled: true | false; integrationBranch: string (≤200); projectId: string (≤100); settleGeneratedIndexes: true | false } The list of repositories the auto-lander watches. Each repo can be enabled, set to observe-only, and given an integration branch.
autoRespondPreviewBeforeSend toggle true | false Hold an AI-written auto-reply in your inbox to approve or reject before it sends
automationsEnabled toggle true | false Master toggle for automatic message processing with rules or AI
cronFailureAlertsAlwaysFire toggle true | false Bypass Focus Mode batching for cron-failure alerts
cronFailureAlertsEnabled toggle true | false Show a system notification and inbox card when a cron job fails permanently
cronHealSelfArchiveEnabled toggle true | false When on, the session Omniscio starts to fix a failed scheduled job archives itself once the job is fixed and its schedule is back on, instead of waiting in your inbox as a finished session. Turn it off to review every fix yourself.
gitGuardrailsEnforcementLevel select "advisory" | "required" Whether a blocked git action is hard-blocked or just warned about. The full git-guardrails controls also live in the Dev Pipeline panel.
gitGuardrailsProtectedBranches list array of string Which branch names agents may not commit, push, or edit on directly. Defaults to master and main.
gitGuardrailsReadyTagGateEnabled toggle true | false Optionally require a ready-to-merge tag before an agent can push a feature branch. Off by default.
prSpawnerBatchSize number integer 1..50 How many pull requests one session works through. Bigger batches are markedly cheaper: measured across 343 real sessions, 7 per session cost $11.43 per pull request against $30.94 when each got its own session, because the session’s start-up reading is paid once and shared. Pull requests being held for your review are always worked alone, whatever this says.
prSpawnerMaxSessions number integer 1..100 How many agent sessions may be working on pull requests at the same time. Lower it when you want the machine back; raise it to drain a backlog faster. Sessions already running are never cut off — the limit only decides whether a new one starts.
recipeApprovalTimeoutDays number integer 1..90 Default wait time before a recipe approval gate auto-resolves. Applies only when the step does not specify its own timeout. 7 days by default. Range 1-90.
showRecipeLaneSessions toggle true | false Reveal the per-lane sub-sessions spawned by recipe pipelines. Off by default to keep the sidebar clean — lanes auto-archive on clean completion. Notifications stay silent for lanes regardless.
silenceRecipeStepsOnSuccess toggle true | false Auto-archive mainline recipe step sessions and the orchestrator when they finish cleanly with no errors, questions, or trouble markers (STEP_FAILED:, LANE_FAILED:, PREFLIGHT_FAILED:, NEEDS_ATTENTION:, RECIPE_NEEDS_ATTENTION:). Off by default — flip on to declutter the inbox after long audit runs.

Knowledge & Memory (26)

What Omniscio remembers — your vault, its memory, and what it captures for you.

Setting Type Accepted values What it does
clipboardHistoryShowInComposer toggle true | false Show or hide the clipboard history icon in the message box.
nothariAggregationCostCapMicroUsd number integer 10000..10000000 Maximum to spend on AI calls per aggregation run. Deep-dive extraction stops when the cap is reached.
nothariAggregationDaily toggle true | false Enable or disable the daily knowledge aggregation digest.
nothariAggregationDailyHour number integer 0..23 What hour to run the daily knowledge aggregation digest.
nothariAggregationDeepDiveMax number integer 1..50 Maximum number of notable sessions to run the expensive transcript extraction on per aggregation run.
nothariAggregationEnabled toggle true | false Periodically scans your sessions, extracts notable insights, and writes a curated Markdown digest into your vault.
nothariAggregationSections object object { activity: true | false; bugs: true | false; decisions: true | false; lessons: true | false; openQuestions: true | false; patterns: true | false; vaultActivity: true | false } Choose which sections appear in the generated knowledge aggregation digest notes.
nothariAggregationWeekly toggle true | false Enable or disable the weekly knowledge aggregation digest.
nothariAggregationWeeklyDay number integer 0..6 What day and hour to run the weekly knowledge aggregation digest.
nothariAutoRegenEnabled toggle true | false When a Vault note drifts far enough from its stored summary, a background worker regenerates it on a schedule. Notes marked user-edited are never touched. Off by default — summaries otherwise refresh only on a manual Regenerate.
nothariAutoRegenIntervalMs number number 60000..86400000 How often (in minutes) the Vault auto-regen worker scans the vault for stale summaries. Stored internally as milliseconds. Applies only while auto-regenerate is enabled. Range 1–1440 minutes.
nothariAutoRegenPerNoteCooldownMs number number 60000..86400000 Minimum gap (in minutes) before the same Vault note can be auto-regenerated again, so one rapidly-edited note cannot dominate the worker budget. Stored internally as milliseconds. Applies only while auto-regenerate is enabled. Range 1–1440 minutes.
nothariBulkSeedCostCapUsd number number 1..50 Per-run cap (USD) on the one-time Vault bulk-seed worker that summarizes every note in the vault. The per-day summary cap still applies on top of it, so the run stops at whichever limit is reached first.
nothariColorMode select "system" | "light" | "dark" Give the Vault its own light or dark mode, or follow the app.
nothariEditorBackground select "theme" | "paper" | "sepia" Set the Vault editor page background — follow theme, paper, or sepia.
nothariEditorFont select "sans" | "serif" | "mono" Choose the Vault editor font — sans-serif, serif, or monospace.
nothariEditorFontSize select "sm" | "md" | "lg" | "xl" Set the Vault editor text size — small, medium, large, or extra large.
nothariEditorWidth select "narrow" | "normal" | "wide" | "full" Set the Vault editor reading width — narrow, normal, wide, or full width.
nothariEnabled toggle true | false Surfaces the Vault virtual project — a Markdown notes editor over a local folder, with wiki-links, backlinks, tags and full-text search across all notes. Agents can read and write your notes.
nothariOverviewEnabled toggle true | false Show a searchable table of every indexed note with its title, summary, and size. On by default whenever the Vault is enabled.
nothariSidebarPosition select "left" | "right" Which side the Vault file list sits on — in the Vault panel and the pop-out window. Left by default.
nothariSummaryCostCapUsd number number 0.5..50 Maximum USD spent per day generating Vault AI summaries on the active API-key account. When the daily total reaches this figure, summary generation pauses until local midnight. Spans haiku-nothari-summary and haiku-nothari-bulk sources.
nothariTabsPreviewMode toggle true | false Opening a note previews it in a single tab that the next note replaces, so tabs stay tidy instead of piling up. Pin a note to keep it as a permanent tab.
nothariTrashHidesPublicPage toggle true | false The public link of a shared note stops working while the note is trashed and works again when you restore it. Turn this off and trashing takes the page down for good.
nothariVaultRootPath text string (≤500) Absolute path to the Markdown vault folder the Vault indexes. Must exist on disk; symlinks and system paths are rejected.
nothariVisualTheme unknown "app" | "glassmorphism" | "linear" | "warm-charcoal" | "aurora" | "soft-depth" | "neon" | "spotify" | "luxury" | "gradient-sidebar" | "neumorphic" | "frosted-tiers" | "vercel" | "liquid-glass" | "aurora-glass" | "macos" | any Give the Vault its own visual theme, including imported custom themes, or follow the app.

AI Features (201)

The AI surfaces beyond a plain session — coaching, writing help, voice and media.

Setting Type Accepted values What it does
agentShortLinkDefault toggle true | false When on, agents that publish a share use a short link by default instead of the long one (paid plans)
aiCoachingAskForFeedback toggle true | false Show a short rating prompt when a coaching session finishes
aiCoachingInvitationsEnabled toggle true | false At most once a day the coach may suggest a short sitting about something it noticed
aiCoachingStyle select "warm" | "neutral" | "direct" Set the overall tone — warm, neutral, or direct — for all coaching interviews
aiSuggestionModel text string (≤100) Model used for session suggestions and session title generation
articleReaderModel text string (≤100) Per-feature model override for RSS article summarization — null inherits the global Utility AI model
asideCostCapUsd number number 0..50 Maximum cost per side question in USD. Asides exceeding this cap are aborted before spawn.
autoFixMasterDebt toggle true | false When on, Omniscio automatically spawns fix sessions for accumulated debt on master. Off (default) drops an inbox card asking you first. Requires the Master-Debt Auto-Fixer (above) to be enabled.
autoModelRouterEnabled toggle true | false Automatically select the best model for each new session based on the task.
autoModelRoutes list array of object { enabled: true | false; id: string (≤100); keywords: array of string (≤100); label: string (≤200); target: object { model: string (≤120); provider: string (≤50) }; whenToUse: string (≤2000) } Configure which models handle which types of tasks.
autoWaitMinutes number integer 5..240 How long Omniscio keeps a waiting session running on its own before it flips to your inbox, both when the agent says it is waiting on something and when it dispatches a background task.
canvaMcpEnabled toggle true | false Connect your Claude sessions to Canva for design creation, management, and export. Sessions can generate designs, search your library, export to various formats, and manage assets — all through conversation.
cheapUtilityModel text string (≤100) Global model override for all cheap/background AI helpers — titles, suggestions, summaries, digests
cliProxyAiModel text string (≤160) Inside the CLI proxy card, once a proxy key is saved. Picks the proxy model that titles, summaries and other small AI helpers use. Automatic uses a fast Claude model if your proxy has one. Test connection refreshes the list.
cliProxyRouteGpt toggle true | false Inside the CLI proxy card, once a proxy key is saved. Sends GPT sessions through your CLIProxyAPI too.
cliProxyRouteXai toggle true | false Inside the CLI proxy card, once a proxy key is saved. Sends Grok sessions through your CLIProxyAPI too.
coachingEnabled toggle true | false Contextual suggestions to help you discover features and work more efficiently
confirmUnansweredQuestions toggle true | false Show a confirmation dialog when the question widget would submit a question you haven't answered.
councilEvaluatorModel text string (≤120) Analyzes and compares panelist answers before synthesis.
councilSynthesizerModel text string (≤120) Merges the panelist answers into one final answer.
customFormatBlockEnabled toggle true | false Silently add a short, editable formatting standard to the FIRST message of each session, right alongside the question-widget hint, so the agent shapes its responses to be easy to skim. Edit the text below; turn off to stop it reaching the model.
dailyDigestModel text string (≤100) Per-feature model override for daily digest generation — null inherits the global Utility AI model
dailyJournalTime text string Time of day your Journal nudge, daily check-in and weekly review nudge appear
dailyJournalTimeZone text string The time zone your Daily Journal check-in and weekly review times are read in
dailyJournalWeeklyDay number integer 0..6 Which day of the week your longer weekly review nudge appears
elevenlabsVoiceId text string (≤100) ElevenLabs voice ID for text-to-speech playback
formatQuestionOptions toggle true | false Display lettered options (A, B, C) as clean indented sub-items instead of bullet points
frozenPanelRetentionEnabled toggle true | false Keep the sessions you’ve looked at recently fully built in memory (the way a browser keeps background tabs ready) so switching back to one is instant instead of rebuilding it. Only applies to sessions that aren’t actively streaming, and a small limit caps how many are held so memory stays bounded. Off by default — it trades memory for speed.
geminiTtsVoiceId text string (≤100) Choose a preset Google Gemini TTS voice for text-to-speech playback
grokVoiceId text string (≤100) Choose a preset Grok voice for text-to-speech playback
grokbotWebhookUrl text string (≤2000) Optional backup route to the Grok Bot app when its saved sign-in is unavailable
heroSloganPersonalizationEnabled toggle true | false Let a low-cost AI model write new-session welcome headlines that fit your project, based on recent session titles and opening messages. Off shows the standard set only.
hideAsidesByDefault toggle true | false Collapse side-question bubbles behind a one-line divider in the transcript by default.
hideAutoWaitedUnlessFinal toggle true | false Collapse repeated "⏱ Auto-waited" messages (prose waits and scheduled wake-ups) to one-line markers you can expand, keeping the latest visible. The first wait (attached to your prompt) and the live/in-flight wait always stay visible. Nothing is deleted. Off by default.
hotkeyTrainingMode toggle true | false When on, clicking a button that also has a keyboard shortcut is blocked the first time and shows you the key to press instead. Click the same control twice more right away and it goes through. Keyboard shortcuts always work, and this never applies on a touch screen. Off by default.
interruptionsAvoidedEnabled toggle true | false Show a running tally of the interruptions Omniscio avoided in Statistics
jarvisBriefingAutoOnOpen toggle true | false Speak a briefing when opening a session with new messages
jarvisBriefingEnabled toggle true | false A spoken summary of a single session
jarvisBriefingHotkey unknown string (≤100) | array of string (≤100) Key combination
jarvisBriefingHotkeyEnabled toggle true | false Global hotkey
jarvisBriefingModel text string (≤100) Which Claude model summarizes the session. Haiku is faster; Sonnet is more nuanced.
journalCoachAccessEnabled toggle true | false Choose whether AI Coaching sessions can read your recent Journal entries
journalGuidedAiEnabled toggle true | false Choose whether guided Journal writing is sent to an AI so it can reply
journalGuidedAiService select "claude-subscription" | "ai-service" Pick which AI handles your Journal replies and AI Coaching: your Claude subscription (best results) or your own AI service
journalReplyStyle select "calm" | "upbeat" | "minimal" Pick how Journal replies sound: Calm, Upbeat or Minimal
kmsKeepWarmEnabled toggle true | false Keeps your Vault editor loaded in the background once you’ve opened it, so switching back into The Vault is an instant flip instead of rebuilding the editor every time. Holds one editor in memory, and only after you first open The Vault. Desktop only. On by default; turn off to load The Vault fresh each time (the old behavior).
kmsSummaryModel text string (≤100) Per-feature model override for knowledge base note summarization — null inherits the global Utility AI model
leanHiddenPanels toggle true | false When you have many sessions open at once, Omniscio stops the ones you can't see from doing background work every time another session sends a message. This keeps scrolling smooth and the chat landing in the right place no matter how many sessions are running. On by default; turn off to mount every hidden session in full like before.
masterDebtFixerModel select "default" | "claude-worker" | "claude-basic" | "deepseek-v4.1-flash" | "deepseek-v4-flash" | "deepseek-v4-pro" | "crofai/deepseek-v4-flash" | "crofai/deepseek-v4-pro" Which model the master-debt fixers run on when they clear failures that were already red on master. DeepSeek V4.1 Flash is the default — that work is mechanical and highly repeated, so the cheapest capable engine is the right pick. If the engine you choose is not set up on this machine (no key, no access to Omniscio's shared gateway), fixers quietly fall back to the reporting project's own engine, so a fix never stalls on this choice.
meetingSummaryModel text string (≤100) Per-feature model override for meeting note enhancement — null inherits the global Utility AI model
meetingsAutoDetectEnabled toggle true | false Detects when a call goes live — including browser calls like Google Meet and Teams — and shows a heads-up display so you can start taking notes.
meetingsLiveIndicator toggle true | false Show the small floating window with the live transcript while a meeting records.
meetingsSpeakerAttribution toggle true | false Show who said what in the transcript by labelling each speaker.
meetingsSttProvider select "deepgram" | "elevenlabs" | "groq" | "grok" | "gemini" | "meta" | "openrouter" | "local" | "apple" Which speech service writes your meeting transcripts. Separate from the voice-typing engine — you can use a different one here. Paid engines bill to your own key.
meetingsSummaryLanguage text string The language the AI-written notes and summaries are produced in.
meetingsTranscriptRetention select "off" | "30" | "90" | "365" Automatically delete raw transcripts after this long. Your notes and summaries are always kept.
meetingsTranscriptionLanguage text string The language spoken in your meetings — used by the live transcriber.
mempalaceEnabled toggle true | false Persistent cross-session memory — search past sessions and auto-recall context
mindmapAiCostCapUsd number number 0.5..50 Daily spending limit for Mind Map AI (expand node, generate map); when reached, AI pauses until tomorrow
mindmapModel text string (≤100) Per-feature model override for Mind Map AI features — null inherits the global Utility AI model
mobileFastLoadEnabled toggle true | false Load the mobile web app faster by fetching feature code only when needed instead of all at startup
narrationMode select "off" | "auto" | "click" Choose how new replies are narrated: auto-play, click to play, or don’t narrate
narrationPromptOverride text string (≤10000) Override the built-in prompt used to write the spoken script for each reply
narrationShowReadView toggle true | false Adds a “Narration” option to the per-message Plain Speak / Original toggle; turn off to hide the readable recap (the play button still works)
narrationVoiceReplyAutoSend toggle true | false Automatically send your spoken reply after you pause, instead of reviewing and tapping Send
opencodeModel text string (≤120) Which model OpenCode runs — Claude (default), Kimi, GPT, or a custom provider/model
overseerMessageTagsEnabled toggle true | false Shows the tag an agent put on its message at the bottom of the bubble: the topic, what kind of message it is, and whether it replaced your open card or opened a new one. Off hides it and the message reads exactly as before.
panelKeepWarmEnabled toggle true | false Keeps recently-opened panels — AI Coaching, Calendar, Drive, Sheets, Supermail, and Team Chat — loaded in the background once you’ve opened them, so switching back into one is an instant flip instead of rebuilding and re-fetching it every time. Each panel is held in memory only after its first open. Desktop only. On by default; turn off to load each panel fresh every time (the old behavior).
panelMountStaggerEnabled toggle true | false Spreads out the building of background session panels after the app starts or reloads, instead of building all of them at once (which can freeze the window for several seconds on launch). The session you’re looking at always loads first and immediately; the rest follow within a few seconds. Off by default while this is being evaluated — turn it on to try it, turn it off to go back to exactly the old behavior.
piModel text string (≤120) Which model Pi runs as a coding agent, picked from your configured provider
pikaVoiceId text string (≤100) Choose a preset Pika voice for text-to-speech playback
pinnedLeadQuestionsEnabled toggle true | false Show a “Has questions” button in a crew lead's header while it has an open question for you. Press it to open the question and answer it.
prInboxEnabled toggle true | false Surface GitHub pull requests waiting on you — review requested from you, plus your own PRs that have changes requested — as rows in the unified Inbox. Requires the Pull Requests tab (above) to be enabled and the GitHub CLI (gh) signed in. Off by default; checks GitHub in the background every few minutes only while on.
preloadSessionsEnabled toggle true | false Pre-load new sessions
prerenderInboxSessionsEnabled toggle true | false Pre-builds your most recent inbox (needs-you) sessions in the background so switching into them is instant. A built-in limit keeps the app fast even when the inbox is large — older inbox sessions load in about half a second when you open them. On by default; turn off to do no inbox pre-rendering at all.
promoteRealMessages toggle true | false Show the agent’s in-between commentary (headings, lists, longer prose) as regular message bubbles instead of folding it into the activity row.
questionWidgetEnabled toggle true | false Show an interactive wizard for answering structured questions instead of typing responses manually
qwFormatHintInjectionEnabled toggle true | false Silently appends a short formatting hint to the FIRST message you send in each new session so the agent shapes its clarifying questions to trigger the QuestionWidget parser. The hint is invisible in your chat bubble — only the outgoing prompt carries it. Turn off if you don't want the hint reaching the model.
qwMissReportingEnabled toggle true | false Show the "Report missed question widget" menu item on agent messages. Captures parser misses as pending fixtures so the parser team can investigate.
qwRaisedChromeEnabled toggle true | false Give the question widget's option buttons and Send button the same glossy, raised 3D look as the app's filled buttons — a soft top sheen and a drop shadow. On by default; turn off for flat buttons.
qwRecommendedHighlightEnabled toggle true | false Outline the option the agent recommends (its text ends with "(recommended)") with a soft green glow in the question widget. On by default.
realConversationLayoutEnabled toggle true | false Show just your messages and the agent’s final replies. Per-turn tool work folds into a collapsed “N actions” pill you can expand on demand. The single biggest render-cost reduction on busy sessions. Off = the legacy stream of every intermediate step.
redactPastedSecrets toggle true | false Replaces API keys and secrets you paste into a chat with a placeholder before the message is saved, so your keys aren't stored in plain text on this computer. The agent still receives the real key to act on.
replySuggestionModel text string (≤100) Per-feature model override for email, SMS, and Telegram reply suggestions — null inherits the global Utility AI model
screenRecorderAutoCaptionsEnabled toggle true | false Transcribe every finished recording, so its captions and transcript are ready without asking. This is the ONLY switch that arms the transcript job — it is deliberately separate from the auto-title toggle below. Default ON. With the on-device engine selected in Voice settings, Whisper runs locally and the transcript is stored with the recording. This is NOT a no-egress guarantee: the cloud dictation engine is the DEFAULT (sttEngine: 'cloud'), and then the take's audio is streamed to Omniscio cloud dictation under the user's sign-in instead of being transcribed locally. A take with no microphone and no system audio is skipped — there is nothing to transcribe and the encoder would only fail on it. Turn it off to have a recording wait until you ask for captions.
screenRecorderAutoDndEnabled toggle true | false Mute Omniscio's own notifications for the duration of a recording, then restore them when it ends. This silences the app only, not your whole computer. Inside Extras in the Advanced tab of the Screen Recording settings.
screenRecorderAutoShareOnStop toggle true | false When you stop recording, upload the video in the background and copy its share link to your clipboard with a 'Link copied' message. On by default.
screenRecorderAutoSummaryEnabled toggle true | false Write a TL;DR and chapters for every finished recording, automatically, once its transcript lands — the Loom behaviour, with no button to press. Default ON. Nothing is sent until the one-time notice has been shown on this machine, and that notice's button turns this off. A silent take spends nothing — no speech in its transcript means no model call — and automatic summaries stop at the shared daily AI cap. The switch is the off-ramp. Synonyms: auto summary, summarize automatically, automatic chapters, AI summary when recording finishes.
screenRecorderAutoTitleEnabled toggle true | false Auto-generate a title from the transcript (sends the recording's speech to Claude) after a recording finishes. Fires once, only when credentials are available and after the captions above have produced a transcript (on-device Whisper, or the cloud dictation engine when Voice settings select it). A manual sourceLabel always wins over the AI title. Default OFF (opt-in). This toggle is the switch for a CLOUD egress: on every finished recording with audio the transcript is sent to Claude Haiku for a title. With system audio captured (the default for a screen recording), that transcript is mostly OTHER PEOPLE — the voices of a call or meeting — who never consented to being sent to an LLM vendor, and no notice was shown before the first send. Same posture as the other third-party-egress features (voice-stt, voiceprint-training, flowvoice-dictation): opt in first. A title needs a transcript, and the transcript comes from screenRecorderAutoCaptionsEnabled above — so with captions off this toggle does nothing. It is no longer the only road to a title: the automatic summary below writes one too, once its one-time notice has been shown, so turning this switch off alone does not keep recordings AI-free. A recording is never left unnamed either way — it carries its creation date and time until a title lands.
screenRecorderClickRingColor text string Colour of the ring drawn around your clicks in a recording. Default gold (#ffd700).
screenRecorderClickRingSizePx number integer 16..200 Size in pixels of the ring drawn around your clicks. Default 48.
screenRecorderClickRingStyle select "outline" | "filled" | "pulse" How the click highlight looks: an 'outline' ring, a 'filled' dot, or a 'pulse'. Default outline.
screenRecorderClickSoundEnabled toggle true | false Play a subtle blip each time you click while recording. It plays in the app, not into the file, but if you are capturing system audio it may be picked up. Inside Extras in the Advanced tab of the Screen Recording settings.
screenRecorderCountdownSeconds number integer 0..10 How many seconds the on-screen countdown runs before recording starts. 0 turns the countdown off. Default 3.
screenRecorderDefaultExpiry select "1day" | "7days" | "30days" | "never" Default expiry for share links you create by hand from the share box: 1 day, 7 days, 30 days or never. Default 7 days.
screenRecorderDefaultShareExpiry select "1day" | "7days" | "30days" | "never" Expiry for links created automatically when a recording is shared on stop, and by the 'Stop & share' button. Defaults to 'never' so a quick link you paste does not silently die.
screenRecorderDesktopNoticesEnabled toggle true | false Desktop pop-ups when a screen recording's share link is copied, and again when its upload finishes.
screenRecorderDiscardRestartHotkey unknown string (≤100) | array of string (≤100) Press this shortcut anywhere to throw away the recording in progress and start a new one with the same source. In the Recording tab of the Screen Recording settings.
screenRecorderEnabled toggle true | false Show the Screen Recording entry in the sidebar — record your screen (webcam, multi-source, hotkeys) with an editor and library.
screenRecorderFinishSoundEnabled toggle true | false Play a short, pleasant three-note chime when a stopped recording has finished saving and is ready to share, so you know it is done without watching the screen. On by default. Synonyms: recording done sound, ready to share chime, finished recording alert, completion sound, notify when recording is ready.
screenRecorderForAgentEnabled toggle true | false Show the Record for Agent tools: mark moments while you record, then send the recording to an agent to review with you. Inside Extras in the Advanced tab of the Screen Recording settings.
screenRecorderGeminiVideoParseEnabled toggle true | false Sends the whole recording to Google so Gemini can describe what actually happens on screen, such as flickering or reloading that a still screenshot cannot show. Everything visible for the entire take is uploaded, not just the moments you marked. Off by default and needs your Gemini API key. Without it, a review sends only a few cropped screenshots and a transcript made on this computer. Shown under Record for Agent when that is on.
screenRecorderIntroCardEnabled toggle true | false Show a title card before recording begins. Off by default.
screenRecorderIntroCardName text string (≤100) The name or title shown on the intro card that is prepended to exported recordings. Appears when Intro card is on, in the Watermark & intro tab.
screenRecorderLocalExportFolder text string (≤500) Folder where exported recordings are saved. Blank means the app's own screen-recordings export folder.
screenRecorderMarkMomentHotkey unknown string (≤100) | array of string (≤100) While you are recording for an agent, press this to mark the moment you are pointing at. In the Recording tab of the Screen Recording settings.
screenRecorderMouseZoomEnabled toggle true | false When a new recording opens in the editor, automatically add smooth zoom-ins around your clicks so the action is easy to follow. You can undo or tweak them. Inside Extras in the Advanced tab of the Screen Recording settings; shown only when the full recording editor is available or this is already on.
screenRecorderOpenReviewOnStop toggle true | false Opens the review window by itself when a screen recording finishes saving. On by default. Turn it off and stopping a recording only copies the share link and shows a confirmation, with no window opening over your work. The review popup's Don't show this again button turns this off too. Synonyms: open review after recording, recording review popup, auto open recording preview, show review when recording stops.
screenRecorderPanicMuteHotkey unknown string (≤100) | array of string (≤100) Press this shortcut anywhere to mute your microphone and camera instantly while recording. In the Recording tab of the Screen Recording settings.
screenRecorderPauseHotkey unknown string (≤100) | array of string (≤100) Press this shortcut anywhere to pause the recording in progress, and again to resume it. In the Recording tab of the Screen Recording settings.
screenRecorderPenHotkey unknown string (≤100) | array of string (≤100) While you are recording, press this to draw on the screen, and your drawing is in the video. Press it again to put the pen away. In the Recording tab of the Screen Recording settings.
screenRecorderPickerHotkey unknown string (≤100) | array of string (≤100) Press this shortcut anywhere to open the recording picker and choose what to record. In the Recording tab of the Screen Recording settings.
screenRecorderQuality select "economy" | "balanced" | "high" | "studio" Recording quality preset: 'economy', 'balanced', 'high' or 'studio'. Higher looks better but makes bigger files. Default high.
screenRecorderQuickRecordHotkey unknown string (≤100) | array of string (≤100) Press this shortcut anywhere to start a recording instantly, and press it again to finish. No picker, no setup. In the Recording tab of the Screen Recording settings.
screenRecorderSnipCaptureNotifications select "all" | "errors" | "off" How much the screenshot tool notifies you: 'all' shows every capture and failure, 'errors' shows only failures, 'off' shows nothing. Default all.
screenRecorderSnipCaptureSound toggle true | false Play a short camera-shutter tone when a screenshot is captured. On by default.
screenRecorderSnipCopyOnly toggle true | false When on, a screenshot is copied to the clipboard only, with no file saved. Off by default, which saves the file and copies it.
screenRecorderStartSoundEnabled toggle true | false Play a short sound the moment recording starts, as a cue that capture began. On by default.
screenRecorderVideoCornerRadius number number 0..0.5 How round the corners of a recorded video block are, for the "Rounded" video shape — a fraction of the block's shorter side, from 0 (a sharp square) to 0.5 (a fully rounded cap); 0.12 (about 12%) is the default. Has no effect on the "Square" or "Circle" shapes. Synonyms: corner radius, how round the corners, video roundness, rounded corners amount, corner softness.
screenRecorderVideoShape select "rect" | "rounded-rect" | "circle" The shape of the recorded video block itself — "Rounded" (default), "Square", or "Circle". Applies to a plain screen/window recording (no camera). The recording is saved as a plain rectangle and this shape is applied when you watch the video or open it in the editor, so a shared link and the editor always show the take at its own shape and changing this later never needs the recording to be re-encoded; exporting from the editor bakes the shape into the exported file. A square keeps the recording exactly as it was before shapes existed. The corner softness of "Rounded" is set by the Video block corner radius setting. Synonyms: video shape, rounded video, round the recording, video corners, square video, circle video, rounded rectangle.
screenRecorderWatermarkImagePath text string (≤500) A PNG, JPG or SVG logo to stamp into the corner. Transparent PNGs work best. Appears when Watermark is set to Image, in the Watermark & intro tab.
screenRecorderWatermarkMode select "off" | "text" | "image" Stamp a small logo or line of text into a corner of every exported recording. Choose Off, Text or Image. In the Watermark & intro tab of the Screen Recording settings.
screenRecorderWatermarkPosition select "top-left" | "top-right" | "bottom-left" | "bottom-right" Which corner the watermark sits in: top left, top right, bottom left or bottom right. Appears when a watermark is on, in the Watermark & intro tab.
screenRecorderWatermarkText text string (≤100) The text to stamp into the corner, for example your name or brand. Appears when Watermark is set to Text, in the Watermark & intro tab.
screenRecorderWebcamKeepCameraShape toggle true | false Keep the camera's own wide proportions instead of cropping it to a square — the Rectangle and Rounded rectangle webcam shapes. Pairs with the webcam shape above (which is stored on every recording and so cannot grow new values); ignored for a Circle. Off by default, so existing recordings keep their square camera. Synonyms: rectangle webcam, wide webcam, keep webcam aspect, don't crop the camera.
screenRecorderWebcamMirror toggle true | false Flip the webcam left-to-right, like a mirror — in the live bubble, the Record preview and the finished video alike. ON keeps the look every take had before this setting existed; OFF records the camera the right way round, so text and gestures read correctly. Synonyms: mirror camera, flip webcam, reverse camera, un-mirror, selfie view.
screenRecorderWebcamPreviewCorner select "top-left" | "top-right" | "bottom-left" | "bottom-right" Screen corner ("top-left" | "top-right" | "bottom-left" | "bottom-right", default "bottom-right") the floating LIVE webcam self-view preview docks into WHILE recording. Controls only the on-screen preview overlay, never the webcam in the final video. Synonyms: webcam preview position, self-view corner, live camera pill corner.
screenRecorderWebcamPreviewSize select "small" | "medium" | "large" Size ("small" | "medium" | "large", default "medium") of the floating LIVE webcam self-view preview shown on-screen WHILE recording so you can tell you are in frame. Controls only the on-screen preview overlay, never the webcam composited into the final video. Synonyms: webcam preview size, self-view size, live camera pill size.
screenRecorderWebcamShape select "circle" | "rounded-square" | "fullbleed" Shape of the webcam bubble in recordings: 'circle', 'rounded-square' or 'fullbleed'. Default circle.
screenshotOcrEnabled toggle true | false Turn on Snip to Text: capture part of the screen and get the text in it transcribed into an editable window. Each capture is a paid AI call, so it is off by default.
screenshotSnipHotkey text string (≤100) The keyboard shortcut that starts a screenshot snip. Change it in the Screenshots settings page — open Screenshots and choose Settings at the foot of its sidebar, or use the button on this row.
screenshotsEnabled toggle true | false Show the Screenshots entry in the sidebar — snip a region of your screen with a global hotkey, then annotate, copy, and browse them in a library.
shareCommentsCrosspostTeamChat toggle true | false Automatically cross-post share comments to the linked Team Chat channel
shareCommentsDefaultOn toggle true | false When off, new shares get no comment box and comments are hidden in Shares. Shares you already published keep their comment box until you republish them
shareCommentsNotifyInbox toggle true | false Show a count on Shares in the sidebar when someone comments on your shares or mentions you
sharePageBrandColor text string (≤7) The accent colour on your branded share pages
sharePageBrandEnabled toggle true | false Put your own name, logo and colour on the public page of every screen recording you share (Pro and above)
sharePageBrandName text string (≤60) The name shown at the top of your branded share pages
sharePageBrandUrl text string (≤500) Where your brand name and logo link to on your share pages
sharesAutoOpenOnCreate toggle true | false Surface a newly created share right away — yours opens in the viewer, an agent’s raises a one-click notification
sharesOpenInApp toggle true | false When enabled, share links open in the built-in viewer instead of your browser
sharesShowAuthorName toggle true | false Show your name and photo under the title of every video you share, beside the date
showComposerAttachButton toggle true | false Show or hide the attach-files button in the message box.
showComposerPermissionPicker toggle true | false Show or hide the per-session permission level button in the message box.
showComposerQuickRepliesButton toggle true | false Show or hide the quick-replies picker button in the message box.
showComposerSnapShotButton toggle true | false Show or hide the SnapShot button in the message box.
showCurrentBranchInHeader toggle true | false Display the active git branch next to the session name. Can be disabled per project.
showSessionContextIndicator toggle true | false Show the context-percent ring in the session header so you can see how full the context window is at a glance. Hidden by default to keep the header clean.
showSessionVoiceButton toggle true | false Show the voice/TTS speaker button in the session header for reading agent messages aloud. Hidden by default. Text-to-speech must also be enabled for the button to do anything.
showSubagentActivity toggle true | false Show a chip in the session UI when the agent has dispatched subagents (Task tool fan-outs) that have been running for more than ~15 seconds, AND a collapsible per-result card in the transcript when each subagent finishes (errors auto-expand, success collapsed). Off by default; both the chip and the cards are hidden. The underlying tracking that keeps the stall watchdog patient during long fan-outs runs regardless of this setting.
smsNameInferCostCapUsdPerDay number number 0.05..5 Maximum spend per calendar day on Haiku calls that infer a friendly name for unknown short codes (e.g. 62438 → "eBay security code"). When the cap is hit, inference pauses until the next day. Range: $0.05 – $5.00.
snoozeNoteEnabled toggle true | false Show an optional note field in the snooze palette so you can leave a reminder for future-you.
sonioxVoiceId text string (≤100) Choose a preset Soniox voice for text-to-speech playback
speechifyVoiceId text string (≤100) Choose which Speechify voice to use for text-to-speech playback
stableQuestionPosition toggle true | false When navigating between multiple questions, lock the question text at a stable position so your eyes don't need to re-track. Pills extend below the locked area. Turn off to return to the legacy behavior where each question renders at its own height.
storeOwnAiKeysOnServer toggle true | false Inside each provider card. Keeps your own saved key encrypted on our server so cloud sessions can use it without going through this computer. Removing the key withdraws the stored copy, and turning this off withdraws every copy stored this way.
storyboardCostCheckEnabled toggle true | false Warn before generating when your credit balance may not cover the run. Turn off to skip the balance warning and the per-frame price confirm.
supermailSummaryModel text string (≤100) Per-feature model override for Supermail Catch me up, video summaries, and Archive Digest — null inherits the global Utility AI model
textCorrectionModel text string (≤100) Per-feature model override for AI text correction and Instant Fix — null uses a fast default
trailingThinkingBoundaryV2Enabled toggle true | false Fixes a rare case where a late-returning background tool added an "Extended thinking" line after the agent's real answer, which pushed that answer into the collapsed activity section and left only a short acknowledgement visible. Off by default (the clean folded view) — turn it on to recover those answers instead.
treeDiagramWidgetEnabled toggle true | false When an agent draws a tree with lines and branches, show it as a real tree you can fold and unfold — instead of a fixed-width block whose alignment breaks on a narrow screen. Any single diagram can still be flipped back to the exact text the agent wrote, and copying always gives you that original.
ttsAutoRead toggle true | false Automatically read the response when you first open a session that needs attention
ttsConfirmationSpeed number number 0.5..2 Playback speed for voice command confirmations
ttsCustomVoices list array of object { id: string; name: string (≤200); voiceId: string (≤200) } Voices you added yourself, by name and provider voice ID
ttsEnabled toggle true | false Have AI responses read aloud in a natural voice
ttsMaxChars number integer 100..10000 Limit how much of a message is read aloud (longer messages cost more)
ttsProvider select "fish-audio" | "grok" | "elevenlabs" | "speechify" | "pika" | "soniox" | "gemini-tts" | "openai-tts" | "piper" | "custom-command" Choose which service reads messages aloud (Fish Audio, Grok, or ElevenLabs)
ttsSpeed number number 0.5..2 Playback speed for text-to-speech audio
ttsSummarizationMode select "verbatim" | "summarize" | "auto" How long responses are read aloud: auto, always in full, or always summarized
ttsSummarizationThreshold number number 100..5000 Responses shorter than this character count are read verbatim; longer responses are summarized
ttsVoiceId text string (≤200) Choose a voice model for text-to-speech playback
ttsVolume number number 0..1 Volume level for text-to-speech playback
tweetShotCardsEnabled toggle true | false When a message, inbox alert, or drip item links to an X/Twitter post, show the post as a real screenshot inline instead of a plain link. Rendering a screenshot is a paid call, so each post is fetched once and then reused. Turn off to always keep the plain link.
typingInsightsEnabled toggle true | false Measure your real typing speed in the message composer and show it in Statistics
voiceCommandCaptureMode select "auto" | "single" | "continuous" | "buffered" How the microphone behaves after you speak a voice command
voiceEnabled toggle true | false Speak to dictate messages or run hands-free voice commands
voiceFeedbackSounds toggle true | false Play a sound when recording starts and stops
voiceL3Enabled toggle true | false Ask Omniscio about a session by voice: hear a summary or ask a question, hands-free.
voiceL4Enabled toggle true | false Queue a spoken question to a running session and get notified when its agent answers.
voiceLanguage text string (≤10) Language for speech recognition
voiceReportBackEnabled toggle true | false Speak the AI response aloud after each voice command result
voiceReportBackMaxChars number integer 50..10000 Limit how many characters of the AI response are spoken
voiceResponseStyle select "off" | "short" | "conversational" Speak a short confirmation aloud after running a voice command
voiceSilenceTimeout number number 0..10000 Stop listening after this many seconds of audio silence (no speech detected). Set to 0 for manual stop only
voiceSttProvider select "deepgram" | "elevenlabs" | "groq" | "grok" | "gemini" | "meta" | "openrouter" | "local" | "apple" Service that converts speech into text (Deepgram, ElevenLabs, Groq Whisper, or the free Built-in engine)
waitConfirmEnabled toggle true | false When an agent ends on unclear "am I waiting?" wording, quietly ask it to confirm instead of flipping straight to your inbox — the hidden check runs at most once per wait
wakeWordEnabled toggle true | false Say “Hey Omniscio” or “Computer” to activate voice commands hands-free
wakeWordEngine select "openwakeword" | "picovoice" Choose between the free built-in option (the default, no account) and Picovoice (needs a paid access key)
weeklySummaryModel text string (≤100) Per-feature model override for the weekly summary analysis phases — null inherits the global Utility AI model
wokenWakeSelfIdentifyEnabled toggle true | false When on, Omniscio's automatic "keep going" nudges identify themselves as coming from the app (not you), and agents are told any message without that marker is really from you, so a short message like "add this" is not mistaken for a background nudge and brushed off with "Nothing to do here." Off by default.
wordExportEnabled toggle true | false Show an "Export to Word" option in the export menus (session ⋯ Exports submenu + the Export… button on docs, scratchpads, and messages). Markdown and PDF stay available. Off by default.
writerAutocompleteEnabled toggle true | false In Writer Studio, the AI menu switch for ghost-text suggestions as you type. Press Tab to accept and Esc to dismiss. Off by default.
writerContextAllowUtilityAi toggle true | false While a Writer document has context attached, Writer AI uses your Writer model; turn on to let the cheaper Utility AI model handle it and receive your attached context
writerEnglishVariant select "en-US" | "en-GB" | "en-CA" | "en-AU" In Writer Studio, decides which spellings count as correct, like color or colour. Found in the Writer Spelling & grammar dialog.
writerGrammarEnabled toggle true | false In Writer Studio, marks likely grammar slips, like a doubled word or "should of", with a short reason. It never changes your words by itself. Found in the Writer Spelling & grammar dialog.
writerHouseStyles list array of object { baseGuide: "news" | "book" | "mla" | "apa"; id: string; name: string (≤80); preferences: array of object { avoid: string (≤64); note: string (≤200); use: string (≤64) } } In Writer Studio, marks the conventions of a rule set you choose, each with a short reason that names the set. Choose one for a document or for its whole folder, or write your own house style sheets. Found in the Writer Spelling & grammar dialog.
writerProofingMarks object object { grammar: object { color: "red" | "orange" | "amber" | "green" | "teal" | "blue" | "violet" | "pink" | "gray"; style: "squiggle" | "underline" | "highlight" | "none"; timing: "pause" | "instant" }; spelling: object { color: "red" | "orange" | "amber" | "green" | "teal" | "blue" | "violet" | "pink" | "gray"; style: "squiggle" | "underline" | "highlight" | "none"; timing: "pause" | "instant" }; style: object { color: "red" | "orange" | "amber" | "green" | "teal" | "blue" | "violet" | "pink" | "gray"; style: "squiggle" | "underline" | "highlight" | "none"; timing: "pause" | "instant" }; unfamiliar: object { color: "red" | "orange" | "amber" | "green" | "teal" | "blue" | "violet" | "pink" | "gray"; style: "squiggle" | "underline" | "highlight" | "none"; timing: "pause" | "instant" } } In Writer Studio, picks a style, a timing and a color for each kind of spelling, grammar and style mark. A sample shows the result. Found in the Writer Spelling & grammar dialog.
writerProofingQuiet toggle true | false In Writer Studio, hides every spelling and grammar mark while drafting. Checking keeps running, and the marks return when you turn this off. Found in the Writer Spelling & grammar dialog.
writerSpellingEnabled toggle true | false In Writer Studio, marks words that look misspelled and offers fixes. Checking happens on this computer. Found in the Writer Spelling & grammar dialog.
writerVoiceFlagStock toggle true | false In Writer Studio, Check voice also flags stock AI phrases, not just your own banned phrases. Sits under Banned phrases in the Writer Spelling & grammar dialog.
zapierEnabled toggle true | false Connect your Claude sessions to 8,000+ apps via Zapier. Create your MCP server at mcp.zapier.app, then paste the server URL below.

Integrations (6)

Connecting the other products you use, including the AI providers that run sessions.

Setting Type Accepted values What it does
jiraInboxEnabled toggle true | false Surface your assigned, not-done Jira issues as rows in the unified Inbox, and get a row when one of them updates — so you don't have to keep checking the board. Requires the Jira board (above) to be enabled and connected. Off by default; checks Jira in the background every few minutes only while on.
linearInboxEnabled toggle true | false Surface your unread Linear notifications — mentions, replies, status changes, new assignments — as rows in the unified Inbox, and get a row when a new one arrives, so you don't have to keep checking Linear. Requires the Linear board (above) to be enabled and connected. Off by default; checks Linear in the background every few minutes only while on.
notionAutoSyncEnabled toggle true | false Keep the open Notion board and page in sync automatically: while the board is open and this window is focused, Omniscio quietly re-checks the open page for edits and periodically refreshes the view, pausing when the window is hidden. On by default; turn off to refresh only with the refresh button.
notionInboxEnabled toggle true | false Surface your recently-edited Notion pages as rows in the unified Inbox, and get a row when a page changes, so you don't have to keep checking Notion. Requires the Notion board (above) to be enabled and connected. Off by default; checks Notion in the background every few minutes only while on.
notionShowImages toggle true | false Load image blocks when reading a Notion page. Off by default for privacy — like the rest of the integration, external media (images, avatars, covers) is not loaded unless you opt in. While off, an image shows a placeholder with a link to open the page in Notion.
outboundWebhooksEnabled toggle true | false Master toggle that enables or pauses outbound webhook event dispatching

Plugins & Marketplace (7)

The plugin system, the plugins that ship with it, and where to find more.

Setting Type Accepted values What it does
marketplaceEnabled toggle true | false Show the Marketplace sidebar entry and the marketplace browser under Settings → Apps for discovering and installing community apps. Off by default.
marketplaceReviewEnabled toggle true | false Show the Marketplace Review sidebar entry — the admin queue for approving or rejecting submitted apps. Off by default.
pluginAutoCheckUpdates toggle true | false Keeps your installed apps up to date: an update that asks for nothing new is applied by itself, in the background, and a newer version wanting access you have not approved asks you first.
pluginSessionDailyLimits map map of string → integer 0..500 How many AI sessions one app may start in the background each day. 20 unless you change it; 0 stops them.
pluginSessionFloorEnabled toggle true | false Apps' AI agents run without your own setup, with only the tools they need and only on Claude-family engines. On by default.
pluginUsageCountsEnabled toggle true | false Lets a marketplace plugin count which of its own features get used: bare counts of actions it listed in advance, sent as an anonymous daily document. Turn it off and nothing is counted, nothing new is queued, and any day already waiting is discarded.
supermailInboxEnabled toggle true | false Unread emails from the Supermail app

Cloud & Teams (17)

Work that leaves this computer — cloud sessions, teams, sharing and other devices.

Setting Type Accepted values What it does
autoCapitalizeTeamChat toggle true | false In Team Chat, auto-capitalize the first word, sentence starts, and new paragraphs as you type, while skipping links, file paths, and abbreviations. The same smart capitalization used in Tasks and Quick Email.
fleetSafetyGovernorSevereSpacingSeconds number number 0.05..60 Controls how cautiously background agent work proceeds while Omniscio detects severe interface lag. Higher values provide stronger protection; lower values let agents progress faster. Healthy operation and work you start yourself are never delayed. Changes take effect within one second, with no restart.
teamChatDmAutoClearNeedsReply toggle true | false A direct message stops showing as needing a reply once you have looked at it. The conversation stays in your list, and a new message brings the tag back.
teamChatIncomingWebhooksEnabled toggle true | false Let the webhook URLs created inside Team Chat post into their channels. Off stops every inbound Team Chat webhook at once, without turning Team Chat off.
teamChatNoticesOnThisComputer toggle true | false Turn off to keep new Team Chat messages out of this computer's Inbox, Needs you list and Needs reply marks, while the chat stays readable and answerable here
teamChatNotifyReactions toggle true | false Show an Inbox notice when someone reacts with an emoji to a message you wrote. Off by default.
teamChatNotifyThreadReplies toggle true | false Show an Inbox notice when someone replies in a thread to a message you wrote, or @-mentions you in a reply.
teamChatPhoneAlerts toggle true | false Turn off to stop Team Chat pushes reaching a paired phone for direct messages and @-mentions, while notices on this computer keep working
teamChatPublicWebhooksEnabled toggle true | false Show the option to give a channel a public address that outside tools post into, even when your computer is off. Off only hides the option; existing addresses keep working until they are deleted.
teamChatQuoteOnSelect toggle true | false In Team Chat, show a Quote button when you select text in a message, so you can quote just that passage. The Quote option in the message menu is always available.
teamChatTopicPreviewStyle select "brief" | "descriptive" | "journey" | "latest_topic" | "custom" Controls how topic previews appear in the Topics list — brief (first line only), descriptive (full text), or inherit from your session title style.
teamsChannelsEnabled toggle true | false Read and post in the channels of your Teams. Usually needs an IT admin to approve it for your organization.
teamsChatAlertsEnabled toggle true | false Alert you when a new Teams message arrives.
teamsChatEnabled toggle true | false Read your Microsoft Teams one-to-one and group chats inside the app. Needs a work or school account and the Allow Teams chat permission.
teamsChatHistoryImportEnabled toggle true | false Allow importing your past Teams chat history into Team Chat.
teamsChatInboxEnabled toggle true | false Show new Teams chat and channel messages as rows in your main inbox, next to Slack and email.
teamsChatSendEnabled toggle true | false Allow sending Teams chat and channel messages from the app. A message is only sent when you press Send.

Settings & Customization (63)

Making the app yours — how it looks, how it behaves, and what each setting does.

Setting Type Accepted values What it does
animatedLogo toggle true | false Let the Omniscio logo swirl in the title bar, Quick Launch and the loading screen while you use the app. It stays still whenever your computer asks for less motion or Low Power Mode is on. You can also right-click the logo to turn it off.
autoDetectProjectIcons toggle true | false Scan project folders for favicons and logos to display in the sidebar
autoTidyEnabled toggle true | false When on, Omniscio moves sidebar integrations and toolbar icons you have not used in 30+ days into a quiet spot (an "Unused" group / the "…" overflow) to reduce clutter, and tells you in the inbox. Nothing is deleted — restore anything in the list below. On by default.
backupMirrorIncludeScreenRecordings toggle true | false Off by default — screenshots are always backed up, but screen recordings can be very large (often 1–3 GB each), so mirrors include them only when this is on
brandedProjectReadyScreen toggle true | false Show the orb and a gradient headline on the start screen, instead of the plain rocket icon.
chatDepth select "flat" | "soft" | "glass" How much shadow and glassy depth the chat messages have. Flat is the classic look; Glass is the most three-dimensional.
codebaseStatsBackgroundEnabled toggle true | false When on, Omniscio quietly analyzes and caches each project’s codebase stats (size, languages, git activity, code health) in the background, so the "Codebase Stats" view opens instantly instead of computing on the spot. It is heavily throttled — one project at a time, only what changed, and it backs off when your computer is busy. It is designed to stay out of your way, but it is real work: on a very busy machine you may occasionally notice it. Turn it off here if you would rather not run it at all. (Dependency security scans still run only when you open a project and refresh.)
conciergeReadMailEnabled toggle true | false Let your Chief of Staff look through your email when you ask it something like “did anyone email me about the move?”. It can list, search and open messages, and it never sends anything without your OK. Turn this off and it will tell you email is switched off instead of looking.
conciergeReadNotesEnabled toggle true | false Let your Chief of Staff look through your saved notes when you ask about something you wrote down before. Turn this off and it will tell you notes are switched off instead of looking.
conciergeReadPastChatsEnabled toggle true | false Let your Chief of Staff look through your past chats — everything you have done in this app, including your coding sessions — when you ask something like “what did I get done yesterday?”. It only ever sees your own chats. Turn this off and it will say past chats are switched off instead of looking.
conversationFullWidth toggle true | false Full-width conversation
copyFullPaths toggle true | false Copy absolute paths to clipboard instead of relative paths from agent output
customCssEnabled toggle true | false Write your own CSS against the whole app and see it apply straight away. The switch turns the stylesheet on or off app-wide; off puts the standard look back at once.
defaultProjectsFolder text string (≤1000) Base directory for quick-creating project folders
diagnosticTracingEnabled toggle true | false When on, Omniscio also attributes each slow frame to the code that caused it and keeps a click-by-click trace in the local troubleshooting logs (renderer diagnostics + interaction.log). It is off by default because it adds work to every animation frame and every click. Your crash reports, error logs and the freeze recorder stay on either way. Nothing is sent anywhere.
diffFontSize number integer 10..20 Default font size for diff content
diffMinimap toggle true | false Show the VSCode-style minimap overview on the modified side of the diff
diffSyntaxHighlight toggle true | false Apply language-aware syntax coloring to diff content
diffTabSize number integer 2..8 How many spaces wide a tab character appears in diffs
diffWordWrap toggle true | false Wrap long lines instead of horizontal scrolling
fileViewerMinimap toggle true | false Show the VSCode-style minimap overview on the right of the file viewer
fileViewerWordWrap toggle true | false Wrap long lines in the file viewer instead of horizontal scrolling
fontSize select "extra-small" | "small" | "medium" | "large" | "extra-large" | "xx-large" | "xxx-large" Adjust text size on desktop (phones use the separate Mobile text size)
glassDialogsEnabled toggle true | false Give pop-up windows a frosted glass look with a soft glow in your accent color. It follows your theme, light or dark. Turn off for the classic flat look.
glassPanelBlurEnabled toggle true | false Blur the colors behind the side columns and the top bar. Off by default because the background behind them never changes, so the blur only costs graphics work. Turn on if the glass looks wrong without it.
globalHotkey unknown string (≤100) | array of string (≤100) System-wide shortcut to bring Omniscio to the foreground
googleCliBackend select "gws" | "gog" Which command-line tool Omniscio uses for Gmail and Calendar. Defaults to gog (the backend installed and signed in on this machine today). gws is the official Google CLI — fully wired, but it needs its own separate Google sign-in before you switch to it.
instantFixLevel select "fix-only" | "tidy" How much Instant Fix changes the text you select: fix and tidy up, or fix mistakes only
instantFixStyleNote text string (≤500) Describe your writing style so Instant Fix keeps your voice
lowDiskSpaceAlertEnabled toggle true | false When on, you get an inbox warning if free disk space drops below the threshold below and automatic cleanup cannot free enough. Turning it off silences the warning only. The automatic cleanup that protects your disk keeps running.
lowDiskSpaceFloorGb number number 5..500 The amount of free space to keep on your working drive. Below this, finished worktrees are cleaned up automatically, and you are warned (when the warning above is on) if cleanup cannot free enough.
menuLetterShortcutsEnabled toggle true | false Show one underlined letter on each menu item. Press it while the menu is open to run that item. On by default.
mobileFontSize select "extra-small" | "small" | "medium" | "large" | "extra-large" | "xx-large" | "xxx-large" Text size on phones and narrow touch screens, kept separate from the desktop size
mobileHeaderStyle select "current" | "bare" | "frosted" | "seamless" | "solid" | "dawn" | "card" | "hairline" | "condensed" | "island" | "horizon" How the top header looks on phones. Changes apply live. Experimental.
mobileRowDensity select "normal" | "compact" Condense the height of session rows on phones.
noMouseTouchModeEnabled toggle true | false When Windows reports no mouse (for example with Mouse Without Borders or a remote-control app), the app acts like a touch screen: buttons that normally appear on hover stay visible and hover tips stay off. Turn this off if you do use a mouse, so those buttons appear only when you point at them. Applies after a restart.
openPdfInAppViewer toggle true | false When on, clicking a PDF opens it in the app's built-in viewer instead of your computer's default PDF app.
projectLooksEnabled toggle true | false Give a project a colour and, if you like, one of the ready-made colour sets. The workspace wears it while one of that project's sessions is open, and its rows carry a small marker.
projectsSidebarHidden toggle true | false Collapse the projects sidebar to maximize chat area. A thin edge gutter remains clickable to re-open it. Shortcut: Ctrl+\
quickChatHotkeysEnabled toggle true | false When on, the per-target hotkeys you assign open the Quick Launch composer pre-aimed at that person or channel
quickEmailRecipients list array of object { email: string (≤320); hotkey: string (≤100) | array of string (≤100); id: string (≤64); name: string (≤100) } Up to 6 saved addresses you can reach from the Quick Email composer
quickEmailSignature text string (≤1000) A short sign-off appended to the bottom of every quick email you send, after a blank line
quickEmailUndoSeconds number integer 1..30 After hitting send, Quick Email shows an Undo toast for this long before actually sending
quickLaunchFollowCursor toggle true | false Open Quick Launch on whichever monitor your mouse is on, instead of always the primary display
quickLaunchHotkey unknown string (≤100) | array of string (≤100) Floating composer hotkey for starting a new session from anywhere
quickLaunchPreserveDraft toggle true | false Keep your Quick Launch draft when you close the popup without sending, instead of starting blank
quickLaunchShowHarnessPicker toggle true | false Add an optional engine + model chooser to the Quick Launch Session tab so you can start a session on a different engine or model
scratchpadReopenLast toggle true | false Opening the Quick Scratchpad or floating capture box brings back the last note you opened instead of a blank note.
sessionStateStylesEnabled toggle true | false Pick the colour, icon and words for each session state. They show on sidebar rows, cards and the inbox, and custom CSS can read them as --session-state-<state>.
sessionsSidebarHidden toggle true | false Hide Sessions Sidebar
sidebarPosition select "left" | "right" Place project and session sidebars on the left or right side of the window
statusShapeIconsEnabled toggle true | false Show a small shape icon on session status dots (a bell for needs-you, a question bubble for a question, a clipboard for approvals, an alert for problems) so status is readable without relying on color alone. Turn off for plain colored dots.
tasksV2RailCollapsed toggle true | false Whether the Tasks view's side rail is collapsed (default expanded/false). Toggled from the collapse button or the reopen strip on the Tasks view; the choice is remembered.
teamChatMessageStyle select "bubbles" | "clean" | "compact" How Team Chat lays out messages: Bubbles (3D bubbles, your messages on the right), Clean (one calm stream), or Compact (dense).
textFocusLockEnabled toggle true | false Once you start typing in a text box, only you can move the cursor out. A box the app rebuilds or pauses mid-typing still gets your letters, and no one-letter shortcut fires.
theme select "dark" | "light" | "system" Dark, light, or system theme
trimOldSubagentOutput toggle true | false When on, Omniscio clears the hidden sub-agent (Task helper) output from sessions you archived over 14 days ago. Your conversations are untouched and a full backup is taken first; you just lose the raw text of those collapsed "subagent result" cards in old archived sessions.
turnDiffCardEnabled toggle true | false A one-line summary under each agent reply listing the files it changed. Off by default.
uiLanguage select "en" | "en-XA" | "es" | "tl" | "zh-TW" | "ceb" | "ilo" | "hil" | "war" | "bcl" | "pam" | "pag" | "id" | "sr" | "hi" | "ur" | "ro" | "hu" | "tr" | "zh-CN" | "pt-BR" | "ja" | "de" | "fr" | "ar" | "ka" | "ru" | "ko" | "vi" | "bn" | "it" | "th" | "pl" | "pa" | "sw" | "fa" Choose the display language for the interface
usageWidgetShowFiveHour toggle true | false Show the 5-hour rolling usage meter inside the usage widget on the toolbar.
usageWidgetShowResets toggle true | false Show the countdown to the next usage-window reset inside the usage widget on the toolbar.
usageWidgetShowWeekly toggle true | false Show the weekly usage meter inside the usage widget on the toolbar.
visualTheme unknown "glassmorphism" | "linear" | "warm-charcoal" | "aurora" | "soft-depth" | "neon" | "spotify" | "luxury" | "gradient-sidebar" | "neumorphic" | "frosted-tiers" | "vercel" | "liquid-glass" | "aurora-glass" | "macos" | any Choose a dark-mode skin for panels and accents

Account & Billing (53)

Your accounts, your keys, and what you are spending.

Setting Type Accepted values What it does
accountAutoReloginEnabled toggle true | false Check every few hours and automatically sign back in any Claude account that has dropped out, instead of waiting for you to press the button
accountsClassicLayout toggle true | false Switch the Accounts page back to the previous flat layout instead of the grouped "Other AI tools" list
agentModelTiers object object { basic: string (≤100); genius: string (≤100); smart: string (≤100); worker: string (≤100) } When an agent asks for a model by tier instead of by name, these are the models it gets. Agents cannot reliably remember model names, so asking by tier is what keeps them from starting a session on a model that no longer exists.
allowAntigravitySessionSpawn toggle true | false Enable spawning Anti-Gravity-provider sessions across all projects
allowCodexSessionSpawn toggle true | false Enable spawning Codex-provider sessions across all projects
allowDevinSessionSpawn toggle true | false Opt-in toggle to expose Devin as a session provider in the new-session menu
allowGeminiSessionSpawn toggle true | false Opt-in toggle to allow spawning Gemini-provider sessions across all projects
allowGptSessionSpawn toggle true | false Opt-in toggle to expose GPT (your ChatGPT subscription, via the local model proxy) as a session provider in the new-session menu
allowGrokBotSessionSpawn toggle true | false Opt-in toggle to expose the Grok Bot desktop agent as a session provider
allowReasonSessionSpawn toggle true | false Opt-in toggle to expose Reason as a session provider in the new-session menu
allowXaiSessionSpawn toggle true | false Opt-in toggle to expose xAI Grok (your Grok subscription, via the local model proxy) as a session provider in the new-session menu
alwaysUseDefaultStartConfig toggle true | false Hide the tool/model/thinking picker on new sessions so they start on your default; you can still change one session before its first message
antigravityProjectEnabled toggle true | false Adds a dedicated Anti-Gravity virtual project to the sidebar
authPathway select "managed" | "apiKeyOnly" | "passthrough" | "ownLogin" | "cliProxy" Choose how your Claude sessions get their Anthropic credentials: your own API key, your terminal login, or your own in-app login
autoAccountSwitch toggle true | false Switch to another account when rate-limited instead of waiting
autoPlaceAgentSpawns toggle true | false When an agent starts a session without choosing where it runs, it goes to whichever of your computers has the fewest sessions working. Off: agent sessions always start on this computer. Shows under Link my computers when it is on.
claudeOnLimit select "wait" | "use-credits" Inside the Claude card of Who pays. Choose Wait for it to reset or Use Omniscio credits when your Claude plan runs out. Appears only when Omniscio credits are switched on as a Claude backup.
codexApprovalMode select "inherit" | "ask" | "ask-on-request" | "auto" Choose how much access a Codex session gets and when it asks you: follow Agent Permissions (default), ask before every command, ask only when it reaches outside the project, or allow all
codexProjectEnabled toggle true | false Adds a dedicated Codex virtual project to the sidebar
customPromptRules list array of object { id: string (≤64); targets: array of string (≤200); text: string (≤8000) } Custom instructions injected into the prompts of a specific engine or model (Codex, Claude, and others) — target whole engines or specific model ids
customProvidersEnabled toggle true | false Master switch for your custom providers (and the built-in OpenRouter entry) in the session picker — on by default
defaultModel text string (≤100) Which engine and model new sessions start on, across all projects
distributeSessionsAcrossAccounts toggle true | false Spread new sessions across login accounts by usage instead of filling one first
favoriteModels list array of string (≤100) Star the models you want agents to reach for first. Starring only changes what they try first — every other model stays just as usable. Each model shows what it costs per million tokens.
geminiProjectEnabled toggle true | false Adds a dedicated Gemini virtual project to the sidebar
globalAuthInviteOnly toggle true | false Only invited or already-approved users can sign in; everyone else is blocked and can request access
keepWarmSessionsOnTheirAccount toggle true | false When Omniscio spreads sessions across several Claude accounts, a session that has just been working with a large context is left where it is instead of being moved. Moving it throws away the cached conversation the model had already read, so the new account has to read all of it again. Only a proactive tidy-up is affected: an account that has actually run out, been signed out or hit a limit is still left immediately. Needs "Distribute sessions across accounts" turned on.
linkedCodeAutoRestart toggle true | false When a change to linked computers lands, restart this computer once so it runs the new code. It waits while a session started from another computer is mid-turn, and never touches a checkout with unsaved edits. Off by default. Shows under Link my computers when it is on.
linkedComputerStatsMode select "combined" | "by-computer" | "this-computer" Stats and the daily briefing add up the sessions your other computers ran, each counted once on the computer that ran it. Choose Combined, Combined with a per-computer breakdown, or This computer only. Shows under Link my computers when it is on.
linkedComputersMirrorAlerts toggle true | false Alert cards waiting in a followed computer’s inbox appear here too, labelled with that computer’s name. Dismissing one here puts it away there as well. Only Dismiss works on those cards. Shows under Link my computers when it is on.
mobileInstantShell toggle true | false Opens the app instantly from the last downloaded version and fetches updates in the background (you are at most one open behind). Turn off to always wait for the newest version on every open.
modelAutoUpgradeEnabled toggle true | false When an update adds a newer model in the same family as your Claude or Codex default (for example a new Opus), switch your default to it and tell you in your inbox. You can undo each switch with one click.
modelLimitAutoSwitchEnabled toggle true | false Some models have their own usage limit. With this on, a session that runs out of one continues on your backup model and goes back when the limit resets. With it off, you get one inbox card asking whether to switch.
pickerToolIds list array of string Choose which tools appear in the new-session picker (Claude Code is always available)
providerConfigSyncAuto toggle true | false Runs a background re-sync about every 6 hours so the target tools pick up changes to your instructions and MCP servers. Off means manual sync only.
providerConfigSyncAutoTargets toggle true | false On by default — your skills, instructions and MCP servers go to every AI tool you have turned on, so nothing needs ticking by hand. Turn this off to pick the tools yourself below.
providerConfigSyncEnabled toggle true | false Master switch. Syncs your skills, and optionally your agent instructions and chosen MCP servers, into Codex, Gemini, OpenCode, Cursor, Grok, Antigravity, Pi and Hermes.
providerConfigSyncIngest toggle true | false Also bring in skills from other tools
providerConfigSyncInstructions toggle true | false Mirror your agent instructions into the target tools global instructions file.
providerConfigSyncSkills toggle true | false Install your skills (SKILL.md folders) into the target tools so you can run them there.
providerConfigSyncTargets list array of string (≤100) Which AI tools receive your synced config — Codex, Gemini, OpenCode, Cursor. Only installed tools sync.
requireApprovalForAiSessionSpawn toggle true | false Off by default — trusted AI orchestration runs without friction. Turn ON if you want a human-in-the-loop checkpoint before any AI-initiated session spawns.
shareLinkedLogins toggle true | false Every one of your own computers can run every Claude account signed in on any of them, and its agents are signed in to the websites you saved on any of them. Only a short-lived Claude sign-in is copied; website sign-ins are copied as their browser cookies. Turning this off removes the copies here. Shows under Link my computers when it is on.
showAlternateProviders toggle true | false Master toggle for Codex, Gemini, Anti-Gravity, DeepSeek, Kimi, OpenCode, and Cursor in the new-session menu
supplyLists map map of string → array of object { onlyDuring: "deepseek-peak"; pay: "you" | "omniscio" | "company"; vendor: string } One ordered list per AI family (DeepSeek, GLM, Kimi, MiniMax, Meta, Qwen, OpenRouter): who pays (your own account or Omniscio credits) and which company serves. A session connects through the first row that can serve; the model you picked never changes. Also editable as JSON.
syncRecommendedEngineSettings toggle true | false Keeps each engine's default model and thinking level on Omniscio's current recommendation, and updates them when we change it. Picking your own default turns this off.
usageCascade list array of object { enabled: true | false; maxParallel: integer 1..500; model: string (≤100); provider: string (≤64) } The ordered ladder of fallback providers used once every Claude account is at its usage limit, or when the provider a session runs on (GLM, DeepSeek, Kimi, MiniMax) runs out. Each session takes the first one that is on, set up, and not already full.
usageForecastEnabled toggle true | false Predicted time until your Claude rate-limit window is exhausted
usageForecastWarnHoursFiveHour number number 0..5 Notify me when the 5-hour bucket will exhaust within N hours (0 = off, max 5)
usageForecastWarnHoursWeekly number number 0..168 Notify me when the weekly limit will exhaust within N hours (0 = off, max 168)
usageTrackingEnabled toggle true | false When on, Omniscio records which buttons, menus, and sidebar integrations you actually use, so you can see what is used vs never used in the "UI Usage" panel below and decide what to remove or hide. The report stays on this device; anonymous click counts also ride the daily diagnostics digest when Error Reporting is on.
webAccessBindHost select "0.0.0.0" | "127.0.0.1" Which network interface the mobile-access server listens on
wsOffloadEnabled toggle true | false Keeps your phone connected while the app is briefly frozen, by answering your device from a separate thread. Falls back automatically if it cannot start. Takes effect after a restart.

Troubleshooting (1)

When something is wrong — recovering it, diagnosing it, or making it fast again.

Setting Type Accepted values What it does
resourceAuditorAutoFixSessions toggle true | false When the hourly audit finds something heavy it cannot name, it may start a session that works out why and fixes it — at most one every four hours. That session costs money, so this is off until you say yes; it is on by default on a developer’s own copy of the app, which is where the hourly audit runs today.

CLI & API Reference (36)

Driving Omniscio from outside — the local control server, its routes and look-up tables.

Setting Type Accepted values What it does
requireApprovalForCliAdminActions toggle true | false Commands an agent could otherwise take on its own: claiming the public support address, letting — or stopping — a project’s cloud box read its repository, moving live sessions between Overseers, and starting (a paid session) or deleting (irreversibly) the abandoned worktree of someone who has gone.
requireApprovalForCliAiCoaching toggle true | false Starting a coaching interview, or creating a custom one (an interview spawns Claude).
requireApprovalForCliAiCoachingArtifacts toggle true | false An agent creating, changing or deleting a coaching artifact — those become facts every session is told.
requireApprovalForCliAutohotkeySetup toggle true | false Setting up AutoHotkey via the CLI turns the AutoHotkey app on, installs AutoHotkey itself when it is missing, edits your own AutoHotkey script to include the generated file, and starts it.
requireApprovalForCliAwayMode toggle true | false Creating, editing or deleting auto-run rules.
requireApprovalForCliCaptureAi toggle true | false Screen-capture AI
requireApprovalForCliCaptureStart toggle true | false An agent starting a screen recording via the CLI. Nothing is recorded until you approve the card.
requireApprovalForCliDrip toggle true | false Drip campaigns + their folder / book sources.
requireApprovalForCliEmailSummarizer toggle true | false Email-summarizer rule changes + setup wizard.
requireApprovalForCliGmailSend toggle true | false Sending, replying to, or forwarding an email via the CLI sends a real email to a recipient.
requireApprovalForCliHelpdeskReply toggle true | false Sending a reply from the Help Desk console via the CLI emails a real message to the customer who opened the ticket.
requireApprovalForCliImageGeneration toggle true | false Generating an image, upscaling one, or removing a background via the CLI spends the gateway image credits on your account.
requireApprovalForCliIntakeSources toggle true | false Enabling a bug-intake source arms a recurring paid poll.
requireApprovalForCliKmsDelete toggle true | false Deleting a Vault note, tag, image, or recovered draft via the CLI. Notes move to the vault trash (recoverable).
requireApprovalForCliKmsImageAnalysis toggle true | false Analyzing Vault images via the CLI calls the paid Anthropic vision API.
requireApprovalForCliKmsSummary toggle true | false Generating or bulk-seeding Vault note summaries via the CLI calls the paid Anthropic API.
requireApprovalForCliMeetingsAi toggle true | false AI-enhancing a meeting note (Generate notes) via the CLI calls the paid Anthropic API.
requireApprovalForCliMemoryArchive toggle true | false Archiving, restoring, or editing a memory via the CLI (all recoverable). Hard delete is separate and always requires approval.
requireApprovalForCliNightyTidyRun toggle true | false Running an audit now, or starting a fix wave, spawns a real Claude session (costs money).
requireApprovalForCliPluginToggle toggle true | false Installing or enabling an app via the CLI activates its code (UI, backend, and any scheduled work); uninstalling deletes its files. Deleting a row through the generic plugin-data CLI is irreversible when the collection has no soft-delete column.
requireApprovalForCliProjectDelete toggle true | false Deleting a project (soft-delete — recoverable) or a sidebar group (its projects become ungrouped).
requireApprovalForCliProjectEdits toggle true | false Bug-intake settings and project doc uploads / deletes.
requireApprovalForCliRecipeRun toggle true | false Running a recipe spawns a real Claude session (costs money).
requireApprovalForCliSessionHandoff toggle true | false Handing a session off summarizes it (a paid AI call) and spawns a fresh successor session that continues its work.
requireApprovalForCliSessionLifecycle toggle true | false Pausing, unpausing, snoozing or archiving a session.
requireApprovalForCliSessionRerun toggle true | false Re-running from a message forks a new Claude session (costs money).
requireApprovalForCliSettings toggle true | false Changing an app setting via the CLI (Settings → any toggle).
requireApprovalForCliShareSend toggle true | false Delivering a share link via the CLI sends a real email / SMS / Slack message to a recipient (SMS counts against your monthly limit).
requireApprovalForCliSlackSend toggle true | false Posting a Slack message via the CLI puts words in front of real people in a real channel.
requireApprovalForCliSmsSend toggle true | false Sending a text via the CLI sends a real SMS (counts against your monthly limit).
requireApprovalForCliSupermailControl toggle true | false Writing sensitive Supermail settings (AI-filter rule, filter mode, master on/off) or dispatching destructive commands (send, trash, sign-out, …) from the CLI.
requireApprovalForCliSupermailFilters toggle true | false Creating, editing, deleting, or reordering a Supermail filter rule from the CLI changes how your incoming mail is triaged from then on, and an archive or spam rule hides real mail. Seeds ON: you review each change first — turn it off to let filter edits apply immediately.
requireApprovalForCliSupermailSend toggle true | false Sending or replying to an email via Supermail sends a real email; opening a thread assistant spawns a paid Claude session. One switch governs all three.
requireApprovalForCliTags toggle true | false Creating, renaming or deleting tags in the library.
requireApprovalForCliTasksV2Ai toggle true | false Tasks ranking, daily check-ins and task breakdowns all call paid Claude.
requireApprovalForCliTelegramSend toggle true | false Sending, editing, deleting, or forwarding a Telegram message via the CLI is a real action a real person sees.

General (117)

Setting Type Accepted values What it does
aboutYouEntries list array of object { id: string (≤64); text: string (≤300) } Facts about you that every new chat reads, so you never have to explain yourself again
admissionBrokerV2Enabled toggle true | false When more agent sessions are created at once than your computer can comfortably run, the app starts them in the order that best fits the machine instead of all at once, and lets the rest in as room frees up. Turn this off and every new session starts the moment it is created.
agentCliUpdateAlertsEnabled toggle true | false Inbox card with a one-click Update now whenever Claude Code or Codex CLI falls behind its latest release; the update runs in the background on your computer, the card goes as the update starts, and you get a card saying so if it does not finish. Omniscio never updates them on its own. On by default
agentFindBatchingEnabled toggle true | false Rewrites your agents’ find commands to run their per-file work in efficient batches instead of launching one process per file — one runaway find can otherwise spawn tens of thousands of processes and freeze this computer. On by default and actually faster. Only turn off if a specific command genuinely needs the old one-process-per-file behavior. Takes effect on your next new session.
agentWebCloudBackend select "none" | "browserbase" | "browser-use" Run agent browsers on Browserbase or Browser Use instead of Chrome on this computer. Cloud browsers never use your saved passwords; the service bills you directly.
approvalTimeoutMinutes select "off" | "5" | "15" | "30" What happens to an approval card you have not answered. By default it waits for you. Choose a time and an unanswered request is refused when it runs out, and the session is told.
autoApproveAgentReadyOverrides toggle true | false Auto-approve the ready mint's human-override card instead of waiting for a click. Default OFF — nothing changes until you turn it on. WHAT IT CHANGES. When an agent marks its branch ready to merge while a check is failing, the mint raises an inbox card and refuses the tag until a person clicks Approve. That click is the whole mechanism: a credential says who HOLDS it, never who CLICKED, so the inbox row is the one thing an agent cannot forge. ON, the mint approves that card itself and stamps the tag — the lever really does pass to the agent, and that is the point of the setting, not an oversight. WHAT SURVIVES IT, and these are the design rather than decoration: - The card is still RAISED, still bound to the branch + full head sha + the exact checks being waived, still consumed exactly once. The tag still carries override-approval: [<id>] and the land-time veto still verifies it, so the land path is untouched. - A card YOU rejected is still refused. Turning this on never overturns an explicit human "no" — it binds to that one commit only. - The auto-approval is VISIBLE: the card's preview text is stamped, so nothing in the audit trail reads as a human click. - It waives only what a human override already waived. Every LAND-time veto (secret scan, mass-deletion, dependency change, pipeline completion) is unaffected. - FAIL-CLOSED toward the click: an unreadable settings read refuses and raises the card, so a settings fault can never START auto-approving. HOW IT IS ARMED. YOU have to turn this one on yourself, in the app (Dev Pipeline → Setup → Auto-lander): an AI agent cannot set it for you, and neither can your phone. That is deliberate — the whole point of the approval it skips is that holding a credential is not the same as being a person, so if an agent could switch it on, it could switch off its own supervision. Read live per mint — flipping it needs no restart.
autoInstallWhenIdle toggle true | false When an update is ready, install and restart on its own once your computer has been idle. Running agents pick up again after the restart. On by default — turn this off to make updates wait until you click Restart.
autoLanderLandingV3OwnEnabled toggle true | false Which engine moves your main branch. Off — the auto-lander lands exactly as it always has. On — Lander V3 takes the hand-over: the old lander stops moving main and Lander V3 lands the branches themselves, in batches called trains. Takes effect on the next landing, with no restart.
autoLanderLandingV3ShadowModeEnabled toggle true | false Off by default. On — Lander V3 builds every train it would land and writes down where it would have chosen differently from the old lander, but never moves main. The old lander keeps landing exactly as before. Handing main-branch landing to Lander V3 wins when both are on.
autoLanderStaleTagHealMaxConcurrent number integer 0..50 How many stale-tag self-heal sessions may run at the same time. These sessions automatically re-check the gate and re-tag a branch whose commits moved past its ready-to-merge tag — so the auto-lander can land it without waiting for a human. They use a separate pool from the auto-lander's conflict-rescue sessions, so raising this never slows those down. 0 = no limit (default). Set to a positive number to impose a cap.
autoLanderSupervisorEnabled toggle true | false The one switch that stops every landing at once. Off — neither engine moves your main branch: nothing is merged, and the branches you marked ready simply stay ready until you turn this back on. Both engines obey it, so it stops Lander V3 as well as the auto-lander. On — landing runs normally. A timed pause set by a session or from the command line still ends by itself; this switch stays where you put it.
autoUpdateTools toggle true | false Silently update Playwright, AgentMail, Repomix in the background; Claude Code, Git and GitHub CLI notify only
backgroundRunnerEnabled toggle true | false Omniscio runs scheduled background jobs on its own — health checks, clean-ups, watchers. With this on, they all run inside one long-lived helper process, so a job no longer starts a whole new program every time it runs — hundreds fewer program starts an hour. Turning it off runs each job in a program of its own again from its next run; the jobs, and when they run, stay exactly the same.
boostAmcProcessPriority toggle true | false While an Omniscio window is in the foreground, raises Omniscio's own processes (main + renderer + GPU + utility) to Above-Normal priority so they win scheduler fights against Claude CLI children at Below-Normal. Keeps the Omniscio window — and other foreground apps like Chrome — snappy when many sessions are saturating the machine. No effect on macOS or Linux.
browserbaseProjectId text string (≤128) The project in your Browserbase account that agent browsers run in.
bulkDrivePacingEnabled toggle true | false Runs Omniscio's own big file jobs — clearing out retired worktrees and building the shared dependency folders on the Dev Drives — one at a time and at a steady rate, and pauses them while Windows is busy. That stops the whole computer locking up for 10–20 seconds, which it did most often right after a restart. On by default; turn it off for the old, unpaced behaviour.
claudeInstallerMoveEnabled toggle true | false One-click button on the Claude Code row when this computer's copy came from winget or npm; installs Anthropic's copy and removes the old one after the new one is proven. On by default
cliSpawnSpacingSeconds number integer 0..300 How long to wait between starting brand-new sessions that an agent or automation creates in a burst (for example a script spawning many sessions in a row). Keeps rapid automated spawns from piling up all at once. Sessions you open yourself are never affected. Set to 0 to start them immediately. Takes effect immediately, no restart needed.
closeToTray toggle true | false When you close the window, keep the app running in the background (system tray) so sessions stay alive instead of quitting
commandGateCap number integer 1..512 Number of agent Bash and PowerShell calls allowed through at once while the trial control is on. Extra calls queue for up to 20 seconds. Changes take effect while the app is running.
commandGateEnabled toggle true | false Trial control for Bash and PowerShell calls from Claude sessions started by this app. When the limit below is reached, later calls wait for a slot. They run anyway after 20 seconds or if the hook service is unavailable. Changes take effect while the app is running; your own terminals and other agent tools are unaffected.
dbWorkerAbForceOn toggle true | false Diagnostics measurement lever, shown only in dev builds. Forces the off-thread DB worker ON right now — the same as launching with AMC_ENABLE_DB_WORKER=1, bypassing the migration safety interlock and the RAM floor — so it can be A/B-measured from the app with no terminal. Applies live (no restart); for a clean measurement window, restart Omniscio after toggling. The AMC_DISABLE_DB_WORKER kill switch still overrides this, and it is NOT the shipping default.
dbWorkerBulkReadHostEnabled toggle true | false Starts one more background helper that runs Omniscio's large, non-urgent database reads — the crew roster and the scheduled-jobs list — on their own read-only connection, so they cannot queue in front of the reads your agents are waiting on. It costs about 120 MB of memory, so it is off by default; turn it on if you run many agents at once. Takes full effect after a restart.
disableGpu toggle true | false Uses your GPU for hardware-accelerated rendering. Disabling this falls back to software rendering with a significant performance cost.
docsLibraryAutoRefreshEnabled toggle true | false Checks the published Omniscio documentation site for a newer documentation build and quietly updates the copy the app reads (Ask Omniscio and the Help Center).
fastSessionSwitchingEnabled toggle true | false Makes clicking between sessions feel snappier by skipping redundant re-rendering of the session panels you are not switching to. On by default — if you ever want the previous behavior back, flip it off and it reverts instantly. No restart, and no effect on what your sessions actually do.
fleetSafetyGovernorEnforce toggle true | false Enforce the fleet safety governor
getUpdatesRightAway toggle true | false Skip the gradual rollout: take a new release as soon as it is published, instead of waiting until this copy is picked. Off by default — turning it on checks for an update straight away.
guardPreScreenEnabled toggle true | false When on, Omniscio skips a slow per-command security check for commands that cannot possibly trigger it, so each agent command is much cheaper. It still runs the full check, unchanged, for anything git or master related. It manages a hook in your global Claude config automatically, with a backup and an instant off switch, and does nothing on machines that do not have that heavy check installed.
hookHostEnabled toggle true | false Every agent tool call runs a few safety and housekeeping hooks. With this on, Omniscio keeps one long-lived helper process running them, so each tool call starts one tiny native program instead of a full Node runtime — hundreds of fewer process starts a minute on a busy machine. Turning it off restores the one-process-per-hook behaviour at the next session start. Windows only for now; other systems keep the per-call behaviour regardless.
idleSessionReleaseMinutes number integer 0..1440 Fully releases the background Claude engine of a session that finished its turn and has been waiting on you for at least this many minutes — reclaiming all of its RAM (~250-450 MB each), not just trimming it. The conversation stays on screen; your next message reloads it in the background (a slightly longer first reply). Sessions waiting on a question or plan keep their engine. Set to 0 to disable. Works on every platform.
isolatedSessionViewEnabled toggle true | false Render the active session in its own background process inside the main window, so it stays responsive while the rest of the app is busy. Takes effect on the next session you click.
keepAmcResidentInMemory toggle true | false Locks Omniscio's database in physical RAM (Windows) so it can't be pushed out to the disk pagefile and then re-read from a busy disk — the cause of the occasional whole-app freeze under heavy multi-agent load. On by default: it auto-sizes to your machine, caps itself so it can't crowd out other apps, and turns itself off on low-memory PCs. Only Omniscio's own engine is pinned, never your agents. No effect on macOS or Linux.
keepAwakeWhileSessionsRunning toggle true | false Prevents your computer from going to sleep while one or more sessions are running or a plugin job is running, so long jobs keep working when you step away. The display can still sleep to save power — only system sleep is blocked. Sleep returns to normal the moment the last session or plugin job finishes. Works on Windows and macOS; on Linux it depends on your desktop environment. On by default; turn it off to let your computer sleep normally while work runs.
keepDbInPrivateCache toggle true | false Serves Omniscio's database from a large block of private memory instead of mapping it from the file on disk. Under heavy multi-agent disk load Windows evicts the file-mapped database from RAM and the app freezes while it re-reads from the busy disk — private memory can't be evicted that way, so the database stays resident and the freezes stop. Opt-in and fully reversible: turn it off and restart to go back. Takes effect on the next restart. No effect on macOS or Linux.
lanUploadSharingEnabled toggle true | false Omniscio computers on the same Wi-Fi or wired network split the upload fairly, so their big uploads never swamp the line together. Only anonymous upload numbers are shared, and never over a VPN.
landerAutoPreserveClearEnabled toggle true | false When on, the auto-lander automatically preserves idle uncommitted changes in a paused checkout to a recovery ref and clears them so landing can resume — instead of pausing and asking you to clear them yourself. Nothing is discarded; you get an inbox alert with how to recover. Off by default.
landingV2Enabled toggle true | false How finished branches are landed. Off — the way they are landed today. On — the new landing judge, which does not re-run the checks a branch already passed when it was tagged, as long as that is on record; a branch with no such record still gets the full checks. Takes effect on the next landing, with no restart.
launchOnStartup toggle true | false Automatically start when you log in to your computer
liteMode toggle true | false One switch to make Omniscio lighter on low-spec machines: turns on Low Power Mode, holds new sessions when memory is low, reclaims RAM from idle sessions (Windows), staggers session loading, and stops keeping extra chats pre-built in the background. Turn it off to restore your previous settings. Startup-related changes take effect on the next launch.
logLevel select "error" | "warn" | "info" | "verbose" | "debug" | "dev-quiet" Controls how much detail is written to the log file. Higher levels include all lower levels. Use "Info" for normal operation or "Verbose" when troubleshooting.
lowPowerMode toggle true | false Disables GPU-expensive visual effects (background blur, heavy animations, decorative shadows) for smoother rendering on integrated graphics and low-power laptops. Takes effect immediately — no restart required.
memoryReclaimEnabled toggle true | false When your computer's free memory drops and stays low, Omniscio trims the memory its own idle sessions are holding — a safe, automatic tidy-up that never touches a session mid-reply. On by default. No effect on macOS or Linux.
memoryReclaimFreePercent number integer 1..90 The trigger point. When free RAM stays below this percentage of your total memory, the automatic reclaim kicks in. Higher = reclaims sooner; lower = only under real pressure.
mergePriorityBoostEnabled toggle true | false While "merge all ready branches" runs, gives that session Above-Normal CPU priority and briefly drops your other sessions to Below-Normal so the batch finishes faster on a busy machine. Other sessions keep running — they just yield. Reverts automatically when the merge ends, after a 30-minute safety timeout, or if you turn this off. On macOS it lowers your other sessions but cannot raise the merge session above normal, so the speed-up is gentler; no effect on Linux.
mobileDeviceLocationEnabled toggle true | false Look up a rough location (city/region) from the network address a device connects from, so you can tell where a connection came from. Turn off to stop this lookup entirely.
offThreadDbWorkerEnabled toggle true | false Runs database reads for Omniscio on a background thread instead of the thread that draws the window, so a slow disk cannot freeze the interface mid-query. On by default; machines with less than 13 GB of memory stay on the old path automatically. Turn it off to run every query on the window thread instead. Takes effect immediately, on or off — no restart needed.
openaiTtsModel select "gpt-4o-mini-tts" | "tts-1" | "tts-1-hd" Choose which OpenAI text-to-speech model speaks, trading cost against quality
openaiTtsVoice select "alloy" | "ash" | "ballad" | "coral" | "echo" | "fable" | "nova" | "onyx" | "sage" | "shimmer" | "verse" Choose which OpenAI voice to use for text-to-speech playback
otherToolUpdateAlertsEnabled toggle true | false Inbox card with a one-click Update now whenever one of your other tools falls behind its latest release; a tool installed by hand opens its download page instead. On by default
overseerCardSubscription select "decisions" | "decisions-and-reports" | "everything" Pick which agent cards reach your inbox: decisions only, decisions and reports, or everything. Questions always reach you; cards below the level are kept but stay out of the inbox.
pauseAllTesting toggle true | false Immediately stops any NEW test, typecheck, lint or build run from starting anywhere on this computer, so background testing load stops piling up. Test runs that are already going will finish normally — nothing is killed and no paid cloud run is thrown away. This is the switch to reach for when the machine feels bogged down by agent testing: pausing your sessions does not stop it, because a test run keeps going on its own after the session that started it has stopped. It stays on until you turn it off: it never times out, restarting Omniscio does not clear it, and agents cannot lift it. Every run that waits because of this says so clearly, so nobody mistakes it for something being broken.
peerToolBoundaryDeliveryEnabled toggle true | false When another agent sends a session a message while it is mid-task, the message normally waits until the session finishes its turn — measured on a busy machine at 16, 47 and even 56 minutes. With this on, a held agent message is handed over at the session’s next tool call instead, so it is seen while the work is still in progress. It only ever carries messages from other agents, never your own typing, which is what starts a session working. Turning it off restores the old behaviour, where every agent message waits for the turn to end.
perSessionSubscriptionIsolation toggle true | false Cuts the cost of each live update when many sessions stream at once, so a busy agent only wakes its own panel instead of nudging every open one. Off by default; turn it on to try it. It re-wires instantly with no restart, and it never changes what your sessions do.
perfMonitorMode select "auto" | "on" | "off" The background watch that fills the Performance Monitor panel and warns you when this machine is struggling. Auto turns it on at 13 GB of RAM or more and off below, so a small PC keeps that memory for its sessions.
reduceTerminalPopups toggle true | false Stop stray terminal windows from popping up and stealing focus while agents run commands — switches the Windows default terminal to the classic Console Host (Windows only, reversible)
refCleanupOnLaunch toggle true | false Clean up Git refs at launch
rendererHarmHeartbeatEnabled toggle true | false Always on. Omniscio records how long your clicks and keypresses take, and how long the window is blocked by slow frames, so it can tell when it is slowing you down rather than guessing. Only the slow ones are recorded, nothing is sent anywhere, and turning it off stops it.
reserveUiCoreEnabled toggle true | false Sets aside a full performance (P) core just for Omniscio's window, so a swarm of running sessions can never freeze the interface by crowding it off the CPU. Your sessions are kept off the reserved core and share the rest — they give up about 6% of the cores and keep running normally, while Omniscio always has a clear core to stay responsive. Best for heavy multi-session use on a powerful hybrid CPU (Intel 12th-gen+ Alder Lake, Raptor Lake, Core Ultra). No effect on non-hybrid CPUs or non-Windows systems, and it steps aside automatically during a CPU burst. Off by default.
safetyAllowPrivateNetworkUrls toggle true | false Off by default: agent web fetches to your own computer, your home or office network and cloud metadata addresses are refused. Turn on only if agents must call a local service.
safetyCredentialWritesBlocked toggle true | false Agents cannot write to folders that hold keys and logins (your SSH keys, cloud credentials, password stores) at any permission level, Full trust included.
safetyDangerousCommandsAsk toggle true | false Commands that can destroy work or change shared history (force-pushes, recursive deletes, disk formatting) always stop and ask you, even at the Autonomous and Full trust levels. Catastrophic commands are refused outright by the always-on protection in Agent permissions.
safetyEnvScrubEnabled toggle true | false Removes environment variables that look like keys, tokens and passwords before a command or tool process starts, so a script an agent runs cannot read them. Names you list below are let through.
safetyHardlineEnabled toggle true | false Refuse catastrophic commands
safetyPackageAdvisories toggle true | false Once a day, the engine command-line tools and the pinned npx packages your MCP servers use are looked up in a public list of known security problems, and you are warned about a malicious or critical one. The lookup sends only package names, versions and the package type.
safetyRedactOutboundEnabled toggle true | false Remove secrets before text leaves this computer
safetyScanInstructionFiles toggle true | false Before a session reads a project’s CLAUDE.md, AGENTS.md or similar files, they are checked for text that tries to take over the agent. A suspicious file is still loaded, but marked as untrusted text the agent must not follow, and you get a notice about it.
safetyScanMemoryEdits toggle true | false New memories, edits to memories and imported memory files are checked for hidden instructions before they are saved, because a saved memory is read by every later session.
safetyScanScheduledPrompts toggle true | false Prompts for scheduled jobs are checked for hidden instructions when they are saved, since nobody is watching when they run.
safetySiteBlocklistEverywhere toggle true | false Sites you blocked for Agent Web are also refused by agents that fetch pages some other way, such as a web fetch or search tool.
safetySuggestRules toggle true | false When you keep allowing the same kind of command by hand, a suggested rule appears in Agent permissions. Nothing is added until you click Add as a rule.
safetyUnattendedDenyEnabled toggle true | false Refuse asks nobody is there to answer
secretRotationCheckEnabled toggle true | false When on, Omniscio checks once a week whether any key this computer holds — your default credentials bundle, the FlowVoice token, the build-time .env, your cloud test key, your test-fleet git credentials — has gone longer than its rotation interval since it was last changed, or has never been recorded as changed. You get one inbox card naming what is overdue and how to change it. Recording a change is one command: npm run secrets:rotated -- <name>. Nothing is ever rotated for you, no key value is ever read, and nothing leaves this computer.
securityIntegrityCheckEnabled toggle true | false When on, Omniscio keeps a signed record of the files that matter because of what they run — your Claude settings and hooks, this project's equivalent, the CLI token file, the security-relevant settings, and the installed app itself — and checks it at every start and once a day. If one of them changes and Omniscio did not change it, you get one inbox card naming what moved. Nothing about a file's contents ever leaves this computer. Turning this off stops the checking and retires the card.
sessionAdaptiveEcoreAffinity toggle true | false On hybrid CPUs (Intel 12th-gen+ Alder Lake, Raptor Lake, Core Ultra), confines Claude CLI sessions to the efficiency (E) cores when host CPU averages above 85%, releasing them back to all cores when it drops below 60%. Lets sessions keep grinding while the performance (P) cores stay available for Omniscio and Chrome. No effect on non-hybrid CPUs or non-Windows systems — the setting is safe to leave on; it stays a no-op when the host doesn't support it.
sessionAdaptiveMemoryPaging toggle true | false When your machine runs low on memory, Omniscio tells busy sessions (and the tests they run) to keep less in fast RAM and spill the rest to the disk pagefile. Sessions keep running — they just slow down until memory frees up. Kicks in only above ~85% RAM use and lifts automatically below ~70%. Never affects Omniscio itself, and never cancels, blocks, or kills anything. No effect on macOS or Linux.
sessionCpuCapEnabled toggle true | false Soft-caps the combined CPU usage of all Omniscio Claude CLI processes (sessions, subagents, test runs, builds — everything they spawn) when the host is contended. An isolated single session can still use the full machine; the cap only kicks in when other things want CPU. Below-normal process priority is also applied so Omniscio yields to your foreground apps. No effect on macOS or Linux.
sessionCpuCapPercent number integer 25..90 Maximum percentage of total host CPU that all Omniscio Claude processes can use combined when contended. Lower = friendlier to your foreground apps, slower for batch work. Range 25-90, step 5.
sessionCpuCapStrict toggle true | false By default the cap is soft: it only kicks in when other apps want CPU, so a single session you are waiting on can still use the whole machine. Turn this on to make the cap a hard ceiling — Omniscio sessions can never go above the percentage above, even when nothing else is running. Guarantees the limit, but can slow a lone session. No effect on macOS or Linux.
sessionMaxProcessesEnabled toggle true | false Puts a kernel-level ceiling on how many processes a single Omniscio session can run at once, so one misbehaving agent (a runaway loop, a fork bomb, an over-parallel command) can't flood the machine and freeze it. The ceiling is generous — far above any normal session — so it only ever stops a genuine runaway; new processes past it simply fail until some finish, and nothing already running is killed. No effect on macOS or Linux.
sessionMemoryGuardEnabled toggle true | false When your computer is running low on memory, pause starting NEW sessions that arrive in a burst (auto-created bug/feature sessions, recipe runs, mass restarts) until memory frees up — so a flood of sessions can't drive the machine into a freeze. A single session you open by hand is never delayed, and any held session always starts within a few seconds. Sessions resuming after an app restart are always paced this way regardless of this toggle. Works on every platform.
sessionMemoryGuardPercent number integer 50..95 Start holding new burst sessions once total system memory in use reaches this percentage. Lower = more cautious (holds sooner); higher = only holds when memory is nearly full. Range 50-95, step 5.
sessionRestartSpacingAfterWarmupSeconds number number 0..30 While a big batch of sessions first comes back after a restart, Omniscio uses the spacing above. Once the warm-up time below has passed, the sessions still waiting start this far apart instead. Lowering this speeds up the long tail of a restart without making the first few minutes any rougher. Set to 0 to keep using the spacing above for the whole batch. Takes effect immediately, no restart needed.
sessionRestartSpacingSeconds number number 0..30 When several sessions come back at the same time (restored after an app restart, auto-recovered from a rate limit, or restarted together from the Bulk session manager), this is how far apart Omniscio spaces their starts, so a big batch does not storm your computer all at once — and no more than a handful of them are ever working at once. While the app is still opening it may start them sooner than this, but only once your computer has room to spare. If things get busy again it slows back down. Sessions you start or restart by hand, one at a time, are never delayed. Set to 0 to fall back to the built-in spacing. Takes effect immediately, no restart needed.
sessionRestartSpacingWarmupMinutes number integer 0..60 How long the spacing above keeps applying once sessions start coming back after a restart, before switching to the spacing after the warm-up. Counted from the moment the batch starts returning, not from when the app opened. Set to 0 to skip the warm-up and use the later spacing straight away. Takes effect immediately, no restart needed.
sessionStoreV2Enabled toggle true | false Runs the rebuilt session engine (V2) behind your session list, switching, and history. On by default — it behaves identically to the old engine but is built on cleaner internals. Switch it off only if you notice a problem, then restart the app to apply (the engine is chosen when the app starts).
sessionStrictMcpConfig toggle true | false Each session normally starts every tool server listed in your global Claude config — including ones it never uses, like the Playwright browser tool, which can take roughly 95 MB of memory each. With many sessions open those idle tool servers pile up into gigabytes of wasted memory and can slow the whole computer down. When on, each session loads only the tools Omniscio actually set up for it, so the waste can not accumulate (and sessions start a touch faster). Your Omniscio tools — memory, The Vault, Google, and custom servers — keep working exactly as before. Applies to Claude sessions; Codex, Gemini, and Cursor are unaffected. On by default.
sessionTreeBelowNormalPriority toggle true | false Runs every Claude session — and everything it spawns (searches, git, builds, tests, subagents) — at Below-Normal priority, so it gives way to the Omniscio window and your other apps when the machine is busy. A session you are waiting on alone still uses the full machine; it only steps aside when something else needs the CPU. This is the lighter, always-safe alternative to a hard CPU cap. Works on Windows and macOS (no effect on Linux).
sessionTreeLowIoPriority toggle true | false The disk-and-memory sibling of the priority setting above. Runs every Claude session — and everything it spawns — at low disk priority and below-normal memory priority, so when the app needs to read from disk (or pull its own memory back in) it goes first, and Windows frees the sessions’ cached files before the app’s. This is what keeps typing and clicking responsive while many sessions hammer the disk. Sessions at full speed when the app is idle; they only queue behind it under load. Windows only.
showWorktreeCleanupToasts toggle true | false When you archive a session that already has a pull request, the worktree is cleaned up automatically. This shows a brief notification when that happens. Turn it off for fully silent cleanup.
smallPcProfileMode select "auto" | "on" | "off" Runs this copy of the app with lighter defaults on a PC with less than 17 GB of RAM: idle sessions are released at 5 minutes, panels are not kept warm, inbox sessions are not pre-rendered and the local session ceiling shrinks. Auto turns it on and off with the machine. Nothing you have saved in Settings is changed, and turning it off restores every one of those settings to your own choice. On a Windows PC with less than 13 GB of RAM it also stops using the graphics card to draw the app windows, which frees about 130 MB; that part takes effect after a restart and turns the frosted panels solid until then.
smartApprovalDailyCapUsd number number 0.05..10 The most the Smart permission level may spend in a day on its background model, between 5 cents and 10 dollars. Once it is reached, Smart sessions ask you instead until tomorrow.
smoothLoadEnabled toggle true | false When many sessions run at once, Omniscio eases up on its own background monitoring so your machine stays responsive — without changing anything your sessions produce. On by default; turn off for the older, always-on monitoring.
smrzzLinkOfferEnabled toggle true | false A YouTube video link in a session or Team Chat gets a quiet "Summarize with Smrzz" action. Nothing happens unless you click it.
streamingThrottleEnabled toggle true | false Paints rapid streaming text at 30 frames per second instead of on every token, which makes fast Claude responses noticeably smoother and keeps the rest of the app responsive while many sessions stream at once. Default on. Turn off only if you want every keystroke painted as it arrives — costs more CPU and offers no correctness benefit.
streamingThrottleHiddenMs number integer 100..5000 How often text from sessions you are NOT currently looking at gets repainted, in milliseconds. Higher = less background work when many sessions stream at once; the session you are viewing always stays smooth. When you switch to a background session it catches up within this window. Default 500. Only applies when smooth streaming output is on.
toolUpdateNotificationsEnabled toggle true | false Periodically check your recommended tools and remind you when an update is available — one click runs its own updater in the background (Claude Code, Git, GitHub CLI), or it updates quietly by itself (Playwright, AgentMail, Repomix). Off by default
updateEverythingAutoEnabled toggle true | false Run the whole-install update by itself on launch and every six hours, speaking up only when something needs you
updateEverythingEnabled toggle true | false One toolbar action that updates Omniscio, your command-line tools, your skills and your apps together
voiceLiveBargeIn toggle true | false Talk over the live voice and it stops at once; turn off for strict take-turns
voiceLiveDailyCapUSD number number 0..100 Daily spending limit for the live voice, in dollars; you are warned out loud and a walk under way keeps going
voiceLiveModel text string (≤100) Which live voice model the conversational inbox walk uses
voiceLiveProvider select "gemini" | "openai" | "grok" Whose live voice powers the conversational inbox walk: Google Gemini or OpenAI Realtime
warnOnCloseWithWorkingAgents toggle true | false Ask before closing the app while agents are mid-task; off means closing just quits and the agents resume next time
weatherReportArchiveTime text string A weather report you have not opened by this time archives itself
weatherReportEnabled toggle true | false A short forecast in your inbox each morning, free and with no account needed
weatherReportLocation text string (≤200) The city or ZIP code the weather report is written for
weatherReportTime text string Time of day the weather report arrives in your inbox
weatherReportUnits select "fahrenheit" | "celsius" Show temperatures in Fahrenheit and mph, or Celsius and km/h
widgetHomeEnabled toggle true | false Show the same widgets, bigger, in a large window of its own.
widgetSidebarEnabled toggle true | false Show a side panel of live widgets beside your sessions.
worktreeReaperEnabled toggle true | false When a work area's session is archived or ended, or its branch has landed, its folder is removed within minutes. Unsaved work is saved first and branches are always kept. Deleting runs in a low-priority background program so your computer is not slowed down. Turn off to stop all automatic removal.
worktreeSessionCleanupDailyBudgetUsd number number 0..100 Hard daily spend cap (USD) for this feature's sessions, ON TOP of the global daily budget cap — once today's feature spend reaches it, no further sessions spawn. Range 0-100. Default 2. F107 — $0 MEANS "NEVER SPAWN", AND THAT IS THE OPPOSITE OF THE SIBLING MONEY CAPS. The compare is a strict < (withinDailyCaps, session-cleanup-decide.ts), so a $0 budget is reached by a $0 spend and the tick alerts instead of spawning a paid investigation. The global dailyBudgetCapHardUSD (daily-spend-gate.ts) and automationRepairDailyCapUSD (automation-fix-alert.ts) both read 0 as "no cap". A user carrying that meaning over would silently switch every paid cleanup investigation off, so the two are deliberately named differently — this one is a budget the feature must stay UNDER, not a ceiling that is off when it is zero. Which reading is right is not obvious from the number alone, hence this note.
worktreeSessionCleanupEnabled toggle true | false Master switch for the SESSION-BASED per-repo worktree cleanup — the newer cleanup that reasons about your ledger of worktrees and their sessions. Off by default. Works on every platform. Synonyms: session worktree cleanup, per-repo worktree cleanup, worktree ledger cleanup, advanced worktree cleanup.
worktreeSessionCleanupMaxSessionsPerDay number integer 1..50 Hard cap on how many paid cleanup sessions this feature may spawn per day, ON TOP of the global daily budget cap. Range 1-50. Default 5.
wsTrimIdleMinutes number integer 0..1440 Periodically asks Windows to evict the working set of Claude CLI child processes that have been idle for at least this many minutes. Reclaims physical RAM without killing the session — pages re-load on next use (~80 ms). Set to 0 to disable. No effect on macOS or Linux.

CLI / advanced settings (1914)

Settable programmatically via PATCH /settings/:key but with no on-screen control -- CLI/agent-facing options plus internal remembered state (migration markers, cached values). Listed so every settable key is discoverable.

Getting Started (31)

Installing Omniscio, signing in, and finding your way around for the first time.

Setting Type Accepted values What it does
aiExperienceLevel select "new" | "ai-chat" | "ai-coding" | "power-user" Your AI-experience level captured once during the Setup v2 onboarding intake ("new", "ai-chat", "ai-coding", or "power-user"). It steers the onboarding flow only — advanced users get the optional extra-engine step and a leaner path; newcomers get a Claude-only, more-guided path. Optional: undefined until answered, treated as the more-guided "new" default. Synonyms: AI experience, skill level, how experienced I am with AI.
alreadyUsingAgents toggle true | false Whether you already run AI agents on this computer, captured once during the Setup v2 onboarding intake (yes/no, default "no"). It steers the onboarding flow only: a "yes" unlocks the preferred-harness pick (and may install + enable Codex); a "no" (the safe default) follows the pure Claude Code path. Optional: undefined until you answer. Synonyms: already using AI agents, run agents on this computer, agent usage.
appTourCompleted toggle true | false Internal bookkeeping: whether you have finished the app tour. Written by the tour, not a setting to change.
credentialBannerDismissed toggle true | false Internal bookkeeping: whether you dismissed the banner saying a saved login could not be unlocked. Written by that banner, not a setting to change.
downloadAttributionCheckedAt text string (≤40) Internal bookkeeping: when Omniscio looked for the one-time code from your download page. Written by Omniscio, not a setting to change.
downloadAttributionClaimedAt text string (≤40) Internal bookkeeping: when your download code was matched to your account. Written by Omniscio, not a setting to change.
downloadAttributionCode text string (≤64) Internal bookkeeping: the one-time code carried by the installer you downloaded, used once to tell which website visit led to your account. Written by Omniscio, not a setting to change.
downloadAttributionOutcome text string (≤40) Internal bookkeeping: the result of matching your download code to your account. Written by Omniscio, not a setting to change.
extensionsPromptSnoozedUntil text string Internal bookkeeping: the time until which the browser-extensions suggestion stays hidden. Written by the suggestion, not a setting to change.
firstMissionCompleted toggle true | false Internal bookkeeping: whether you have finished the First Mission guided tour. Written by the tour, not a setting to change.
firstMissionDismissed toggle true | false Internal bookkeeping: whether you dismissed the First Mission offer. Written by that offer, not a setting to change.
heardAboutUsSyncedAt text string (≤40) Internal bookkeeping: when your 'how did you hear about us' answer was last sent to the cloud. Written by Omniscio, not a setting to change.
onboardingCadenceEnabled toggle true | false In-development: the video-led onboarding cadence that replaces the mission trickle. After setup, drips short intro VIDEOS to a new user one inbox card at a time — the next releases when the current is archived or after a timeout, and only while the user is active. ON by default (2026-08-28 launch — the welcome-tour card #1 is seeded); the toggle stays live to turn off with one setting flip.
onboardingCompleted toggle true | false Internal bookkeeping: whether you have finished the first-run setup. Written by the setup flow, not a setting to change.
onboardingDemoTourOverride unknown unknown Internal storage for a customised demo tour you built in the Onboarding Studio. Holds the tour itself, edited through the Studio rather than by hand.
onboardingMissionTrickleEnabled toggle true | false In-development: the guided-mission suggestion cards. RETIRED from new users (owner 2026-08-26) — off by default, being replaced by the video-led onboarding cadence. The toggle stays live to turn the old mission cards back on with one setting flip.
onboardingPrespawnEnabled toggle true | false When a new user finishes Setup v2, pre-spawns the guided missions in the background on a company-paid DeepSeek route so they return to agents already working. Fail-closed (needs the funded company DeepSeek lane + sign-in), one-time per user, capped. ON by default (2026-08-25 — the company deepseek-v4-flash lane now serves end-to-end, verified live: the failover chain is 6/6 healthy and a real deepseek-v4-flash completion returns clean output, so the earlier "model unavailable" gateway failure is fixed). The toggle stays live to turn off with one setting flip; the mission trickle remains the fallback.
onboardingPrespawnFundingMode select "auto" | "company" | "own-account" Who pays for the starter agents Omniscio gets ready during setup. Auto follows the fleet-wide setting; Company charges Omniscio; My own account runs them on your own provider instead.
onboardingPrespawnStartedAt text string Internal bookkeeping: when the first sessions were started ahead of time during setup. Written by setup, not a setting to change.
onboardingReplyNudgeDismissed toggle true | false Internal bookkeeping: whether you dismissed the setup prompt about replying to a session. Written by that prompt, not a setting to change.
onboardingSetupAssistantCardEnabled toggle true | false In-development: after a new user finishes onboarding, shows a one-time, optional inbox card offering a guided setup assistant. Launching it opens an Ask Omniscio session that walks them through connecting an AI provider, adding API keys, integrations, automations, agent autonomy, and backups; it never sees a raw API key. Off by default; hidden until shipped.
onboardingStudioFlow unknown unknown Internal storage for a customised setup flow you built in the Onboarding Studio. Holds the flow itself, edited through the Studio rather than by hand.
preferredHarness select "claude" | "codex" | "other" | "not-sure" Your preferred AI-agent harness, captured once during the Setup v2 onboarding intake ("claude" | "codex" | "other" | "not-sure"). It steers the onboarding install only: "codex" also enables Codex sessions and installs the Codex CLI, and Claude Code always installs for everyone. Optional: undefined until you answer; "claude" is the safe default. Synonyms: preferred agent, harness choice, which agent I use.
setupExitedAt text string The timestamp (ISO 8601) of when you last exited first-run setup without finishing it — the onboarding "exit" marker. When set, onboarding does NOT auto-reopen on the next launch; instead the "Finish setting up" inbox reminder nudges you to complete setup. Unset (undefined) until you have exited setup early at least once. Distinct from setupV2CompletedAt (a genuinely finished setup). Internal remembered state, not a user-facing toggle. Synonyms: setup exited at, skipped setup time, first-run exit timestamp, exited onboarding.
setupV2CompletedAt text string Internal bookkeeping: when you finished the setup flow. Written by setup, not a setting to change.
setupV2ResumeFrame text string Which step of first-run setup you had reached — the Setup v2 frame id (e.g. "install", "sign-in") remembered so a relaunch resumes you there instead of restarting the flow at the first screen. Cleared when you finish setup; kept when you exit early, so the "Finish setting up" reminder returns you to the same step. Internal remembered state, not a user-facing toggle. Synonyms: setup resume position, last setup step, where I left off in setup.
superpowersMigrationNudgedAt text string Internal bookkeeping: when you were last reminded about the Superpowers migration. Written by Omniscio, not a setting to change.
terminalAutomationStatus select "granted" | "denied" The last answer macOS gave when Omniscio opened Terminal for you (a sign-in, a tool install, or the Allow button on the setup Permissions step): "granted" when Terminal opened, "denied" when macOS refused Omniscio permission to control Terminal (Privacy & Security → Automation). Remembered because macOS offers no way to check that permission without risking its prompt. Unset until Omniscio has opened Terminal at least once. Internal remembered state, not a user-facing toggle; change the permission itself in System Settings. Synonyms: terminal permission, automation permission, terminal access, apple events.
toolchainWizardDismissed toggle true | false Internal bookkeeping: whether you dismissed the toolchain setup wizard. Written by that wizard, not a setting to change.
tourCompletions map map of string → true | false Internal bookkeeping: which guided tours you have finished. Written by the tours, not a setting to change.
tourLastOfferAt number integer 0..∞ Internal bookkeeping: when a guided tour was last offered to you. Written by Omniscio, not a setting to change.

Sessions & Agents (474)

Running AI sessions and agents — starting them, steering them, and orchestrating many.

Setting Type Accepted values What it does
abortedResponseRecoveryEnabled toggle true | false Automatically recover and resume a session whose reply was cut off mid-answer by an interrupt.
absoluteTurnCapSeconds number integer 600..86400 Hard ceiling, in seconds, on how long a SINGLE turn may run before the watchdog ends it. This is the backstop for a turn that keeps producing output but never finishes — the one failure the silence-based stallThresholdSeconds can never catch, because every chunk of output resets that timer. Default 14400 (4 hours). Raise it if you run long autonomous audits that legitimately run past 4 hours. It measures ONE turn, not the whole session, and is re-anchored each time a new turn starts (including a recovery respawn).
acceptLinkedReviewSeats toggle true | false
adStudioFindAdsSkillEnabled toggle true | false Install the optional Ad Studio ad-finding skill. It searches Meta's public Ad Library through Agent Reach, in a Chrome profile signed in to a separate spare Facebook account that is tied to nothing personal (never your own account), and hands the ads it finds to Ad Studio. Meta's rules limit automated collection and Facebook can restrict an account that does it, so it is off by default and stops for the day at the first sign of a block.
agent37SessionShare number integer 0..100 Sets what percentage, from 0 to 100, of new cloud sessions are started on the Agent 37 provider instead of the usual primary provider. At 0, the default, none are; at 100, all new ones are. Each new launch is decided by a random roll against this number. Synonyms: Agent 37 percentage, cloud provider split, share of cloud sessions, provider traffic share.
agentChatSubscriptionDailyLimit number integer 1..10000 The most times your Team Chat subscriptions (the threads and people you follow) may wake one agent session in a UTC day, counted across all of that session's subscriptions. Default 50. Every wake is a model turn in your session, so this is what bounds a busy thread: posts past the limit wait, nothing is lost, and they are delivered after midnight UTC or as soon as you raise the number. Set it to any number up to 10000. A second wake never arrives sooner than five minutes after the last one, so a burst of posts arrives together. Synonyms: subscription daily limit, thread watch cap, how often a followed thread wakes my agent, team chat subscription per day.
agentCrewRegistryEnabled toggle true | false Any session can register a role — overseer or member — into a mission crew, and the app does the rest: a numbered title, seeded heartbeats, who it reports to, and one board for the crew. A member finishing a routine turn checks in with its lead instead of your inbox; only a reply addressed to you ever reaches it. On by default; registering costs nothing, and the toggle stays live so you can turn it off with one setting flip.
agentDeviceEnabled toggle true | false In-development: your agents on two computers signed into the same account can message each other. Each conversation is a named thread you route to its own session on each computer, so several can run at once; messages arrive framed as another machine's words, never as your own instructions. Every conversation starts muted and out of the way — unmute any of them to read along — and a turn budget stops two agents talking to each other forever. Off by default.
agentDmCooldownSeconds number integer 0..3600 The smallest gap, in seconds, between two agent messages arriving on one cross-org connection — a pace limit, not a count. Blank (the default) means no gap at all, which is how this ships. A message that arrives inside the gap is HELD and delivered on a later check, never dropped. Synonyms: agent dm cooldown, cross org agent message pace, slow down another persons agent, gap between agent messages on a connection.
agentDmDailyLimit number integer 1..10000 The most messages one cross-org agent connection may deliver per UTC day, for agent messages from ANOTHER person's agent over a Team Chat connection. Blank (the default) means no daily limit, which is how this ships: a bound nobody chose is what made the feature go quiet after a handful of exchanges. Synonyms: agent dm daily limit, cross org agent messages per day, connection agent daily quota, limit another persons agent messages.
agentDmEnabled toggle true | false In-development: when you turn this on for a specific person whose connection you have accepted, their agent can send messages directly into one of your local sessions. You choose per person; no one gets access without a deliberate connection. Incoming messages are budgeted and can be cut off instantly. Off by default and completely inert until switched on.
agentDmMessageLimit number integer 1..10000 How many agent messages may pass on one cross-org connection in a row with no person writing in the thread. Blank (the default) means no limit, which is how this ships. Only a person can set it — an agent asking to change it raises an approval card. Synonyms: agent dm message limit, cross org agent message limit, agent chatter back and forth cap over a connection, teammates agent talking to an outsider limit.
agentDrivenSidebarEnabled toggle true | false Shows the Agent-Driven Sessions row in the sidebar's Agent Tools group, listing top-level sessions that were started by an agent rather than by you. On by default. Turn it off to hide that list. Synonyms: agent driven sessions, sidebar agent sessions, show agent started sessions, agent tools sidebar.
agentEmailSidebarEnabled toggle true | false Show the Agent Email row in the sidebar. On by default.
agentFirewallEnabled toggle true | false Screen the web content tools return (web pages, search results, output of commands that fetch from the internet) for prompt injection before an agent trusts it. On by default; turn it off here.
agentFirewallEnforcementLevel select "advisory" | "ask" | "enforce" How the Agent Firewall handles content it flags as a possible prompt injection in a tool's output (a file, web page, or command result). "advisory" = warn the agent to treat it as untrusted but continue; "ask" (default) = warn the agent AND raise an inbox alert for you to review; "enforce" = tell the agent the content is blocked. Only applies when the Agent Firewall feature is on and the session is externally-spawned or its project opted in. Synonyms: firewall enforcement level, injection flag handling, advisory vs ask vs enforce, what happens when the firewall flags something.
agentFirewallOptInProjectIds list array of string The list of project ids that opted their sessions into the Agent Firewall injection screening ("available for users"). Externally-spawned/automated sessions are screened regardless of this list; adding a project id here also screens that project's own interactive sessions. Empty by default. Synonyms: firewall opt-in projects, which projects use the agent firewall, enable injection screening for a project.
agentFirewallScreenInteractive toggle true | false When on, the Agent Firewall ALSO screens your OWN interactive sessions for prompt injection in tool output — not just externally-spawned/automated sessions and per-project opt-ins ("protect everywhere"). Off by default. Only takes effect when the Agent Firewall feature is on; it widens which sessions are screened, it does not turn the firewall on. Synonyms: protect everywhere, screen my own sessions, firewall all sessions, screen interactive sessions.
agentFrictionPlainLanguage toggle true | false In the Agent Friction panel, show each reported problem in plain English instead of the raw agent-written title. On by default; the technical wording stays one click away.
agentFrictionReportsEnabled toggle true | false In-development: a developer-tools panel showing what keeps costing your agents time — the problems they hit, collapsed so that forty agents hitting one wall read as ONE problem with a count of forty, ranked by measured cost and how often it fires. Shows each cluster's severity, time lost, how many reports came from an agent's judgement versus passive telemetry, and the command and output behind the first sighting, with a Plain English / Technical switch so the list is readable without knowing the jargon. SPENDS MONEY: turning this on also starts the triage loop, which every four hours at most may start a Claude session to verify the costliest problems and dispatch sessions to fix them — real sessions at real cost. A spending limit (default $25 a day, "Friction triage spending limit") stops new triage runs once it is reached; it cannot recall fixers a running triage session has already started. Turning it off stops all of it — collection, the automatic capture, and the triage loop. Closing a problem out still stays on the CLI. Hidden until shipped.
agentFrictionSidebarEnabled toggle true | false Whether the Agent Friction item appears in the sidebar (default on). A visibility toggle only — hiding the entry does not turn the feature off and does not stop anything being collected; agentFrictionReportsEnabled is the switch that does both. Settings → Sidebar. Synonyms: hide agent friction from the sidebar, show agent friction, sidebar agent friction item, remove the friction panel from the sidebar, agent friction sidebar visibility.
agentLanesAnyTeammate toggle true | false When on, any workspace member's agent — never a guest — may message your agent in an agent lane without you approving each one first. Off by default, and reserved to a person: an agent asking to change it raises an approval card. Synonyms: agent lanes, let teammates agents message mine, agent to agent messaging, approve each agent message, teammate agent DM.
agentLanesDailyLimit number integer 1..10000 The most agent-lane messages one lane may send per UTC day. Blank (the default) means no daily limit. Synonyms: agent lanes daily limit, cap agent messages per day, agent lane daily quota, limit agent to agent messages.
agentLanesEnabled toggle true | false In-development: a direct message with a teammate gains a second tab where your agents talk to each other, kept apart from your own conversation. Neither of you is notified — no push, no unread badge, just a quiet dot on the tab when they have been talking — and either of you can open it and read the whole thing at any time. Once a day you get a single summary of what they worked out. Nothing is sent until both people switch the lane on, and a turn budget you set stops two agents talking to each other forever. Off by default and completely inert until switched on.
agentLanesGeneralProjectPath text string (≤500) The project the general agent lane's session opens in. Blank (the default) opens the general Claude folder. Synonyms: agent lanes project, general lane project path, where the general agent lane opens, agent lane working folder.
agentLanesMessageLimit number integer 1..10000 How many agent messages may be sent in a row with no person speaking in the lane. Blank (the default) means no limit. Synonyms: agent lanes message limit, agent chatter back and forth cap, agents talking to each other limit, consecutive agent messages.
agentLanesMessagingGuide text string (≤8000) Your own rules for how your agents message teammates: per teammate or topic, what goes agent-to-agent, what reaches you, and what should alert you. Blank (the default) means the built-in rules only; your rules win where they disagree. Reserved to a person: an agent asking to change it raises an approval card. Synonyms: agent messaging guide, agent routing rules, which teammate gets what, agent lane rules, alert me rules, agent to agent instructions.
agentMarkdownFormattingEnabled toggle true | false On by default: an agent formats a reply the way it already writes on GitHub — callouts, centred text, sized images, collapsible sections, keyboard keys — and any shape outside that fixed list still prints as literal text, exactly as before. The toggle stays live, so turning it off renders every message as it did before this existed.
agentMessageCardsEnabled toggle true | false In-development: when an answer carries a lot of information, an agent can split it into cards you page through inside the one message instead of reading one long wall. A card may also carry its own question, and answering one is recorded without starting a new agent turn, so what you answer there comes back as ONE reply. It is for breaking up heavy content — never a substitute for asking several questions in one question widget. Off by default; hidden until shipped.
agentMessagesEnabled toggle true | false In-development: one place to watch your agents talk to each other — who messaged whom, when, what they said, and whether it arrived. Includes the messages that never arrived, which are recorded but have never been visible anywhere in the app. Read-only: it shows the traffic, it never sends, retries or interrupts you. Off by default; hidden until shipped.
agentMessagesMainComputer toggle true | false Which computer answers agent messages that are not aimed at a particular computer — a general teammate message, an inbound agent email. Exactly ONE computer is the main one; every other computer stays quiet for those, which is what stops the same message being acted on twice. Per computer, and never carried by a settings import/export, so copying your settings to another machine does not hand it this role. Settings → Agent Device → "Main computer". Synonyms: main computer, agent messages main computer, which computer answers agent messages, one computer for general agent messages, main machine for agent email.
agentPermissionAllowRules list array of object { commandPrefix: string (≤200); createdAt: string (≤40); expiresAt: string (≤40); id: string (≤100); overseerSeat: string (≤220); projectId: string (≤200); sessionId: string (≤200); toolName: string (≤100) } Human-authored allow-rules that pre-approve specific agent actions. Consulted BELOW the dangerous-path denylist, the Clean Room fence, and the email lockdown — a rule can never relax those. Always read settings.agentPermissionAllowRules ?? []: an existing config predates the field and getSettings does not merge defaults. Never writable from the CLI control server.
agentPermissionScopedAllowRules list array of object { commandPrefix: string (≤200); createdAt: string (≤40); expiresAt: string (≤40); id: string (≤100); overseerSeat: string (≤220); projectId: string (≤200); sessionId: string (≤200); toolName: string (≤100) } Stores the always-allow permissions that are limited to one session, one seat, or a set time, so they can expire. The app checks them alongside your regular always-allow rules and removes expired ones automatically. Empty by default. This list is managed by the app when you grant a limited always-allow. Synonyms: temporary always allow, timed permissions, session-only approvals, expiring allow rules.
agentRoad select "cloud" | "worktree" | "patch" How agents change code on this computer: cloud, worktree or patch. A projection of the machine-local agent-road record, never stored here: reads fill it from that record (or from agentsNeverLeaseWorktrees before the record exists), and a one-key update writes the record.
agentScreenCaptureEnabled toggle true | false Lets agents take screenshots and start or stop screen recordings through the app's automation. Off by default; when off those requests are refused.
agentTaskSystemDefaultBackfilled toggle true | false
agentToolsCollapsed toggle true | false Whether the Agent Tools sidebar group (CLI Tools, Skills, MCP Servers) is collapsed. Collapsed by default so the sidebar opens tidy.
agentWebEnabled toggle true | false Give every agent its own real Chrome browser — headless, one per session — through one command, amc-web: open pages, read them as elements, click, type and fill forms. Sites you block stay blocked, and finance, payment and social sites ask first.
aiCouncilLaunchSidebarEnabled toggle true | false Show the AI Council one-click launcher row under Prompt Tools (default true, feature-gated by multi-model-council). Mirrors bakeoffSidebarEnabled.
aiProjectManagerPreviewEnabled toggle true | false Omni, your AI project manager: one sidebar page with your Projects and Sessions, and one conversation that understands every Mission Control project.
aiProjectManagerSectionOrder list array of "needsOk" | "whatChanged" | "suggestions"
aiProjectManagerSetUpHowIWorkUsed toggle true | false Records that you have already used the Set up how I work starter in the AI Project Manager. Once it is set, that starter card is replaced by an improve-my-workflow suggestion. Off by default, and the app sets it for you after you launch that starter. Synonyms: how I work starter used, project manager starter card, setup starter done, welcome card state.
aiToolsCollapsed toggle true | false Whether the AI Tools sidebar group is collapsed. Collapsed by default, so the sidebar opens tidy.
aipmActiveControlCenterId text string (≤200)
aipmControlCenterColorMode select "system" | "light" | "dark"
aipmControlCenters unknown pipeline
aipmListColumnWidth number integer 240..560 How wide the list column on the Omni page is, in pixels, remembered from the last time you dragged its divider. Synonyms: Omni list width, control center list width, Omni sidebar width.
aipmProjectBriefingOrder list array of "points" | "needsOk" | "changes" | "forecast" The order of the cards below Omni's take on a project's page in an Omni control center: points (Worth knowing), needsOk (Needs your OK), changes (Last 24 hours) and forecast (Project Forecast). Default points, needsOk, changes, forecast. Set under Look in Omni's own settings window (the gear on the control center) by dragging a row or using its arrows; the phone uses the same order, and an unknown, repeated or missing card is cleaned up so each shows once. Synonyms: project page order, reorder project page, card order, section order, needs your ok first.
alertsSidebarEnabled toggle true | false Show the Alerts row in the sidebar. It only shows or hides the row and does not turn the alert feature itself on or off. On by default.
apiKeysSidebarEnabled toggle true | false Show the API Keys row in the sidebar. On by default.
appRestartSessionGrants list array of string (≤200) The sessions you have personally allowed to restart the Omniscio app over the CLI using their own scoped agent-session token. A restart is powerful, so it is granted one named session at a time rather than to every agent: an ordinary session is listed by its id, an Overseer by its slot so its daily respawn keeps the grant. Managed from the session permission request and the in-app toggle, not typed by hand; capped at 50 and pruned of sessions that no longer exist. Synonyms: allow a session to restart the app, agent restart permission, restart the app from a session, app restart grant, scoped token restart.
approvalsSidebarEnabled toggle true | false Show the Approvals row in the sidebar, which lists agent requests waiting for your permission. Approvals still work even when the row is hidden. On by default.
archivedBundledSkills list array of string (≤128) The built-in skills you have archived. The app skips reinstalling these on the next launch. Internal stored list of folder names, not something to edit by hand.
askAmcUseLuna toggle true | false RETIRED — it no longer has any effect. Ask Omniscio answers typed questions on DeepSeek V4.1 Flash on the company-provided model whatever this says; Haiku is used only for an image/PDF question or a retry after a temporary failure. The stored value is kept so nothing changes under it.
askOmniscioPinBackfilled toggle true | false Internal one-time marker: the app has already pinned Ask Omniscio to the top of the sidebar for an existing install. Not a setting to change.
askOmniscioPlacementBackfilled toggle true | false Internal one-time marker: the app has already placed Ask Omniscio at its default sidebar spot, after which your own arrangement is kept. Not a setting to change.
auditFixSessionsPublishOwnPr toggle true | false Whether an unattended audit-fix session that passes its checks also publishes its own pull request to GitHub. Unset follows this computer's role: on for a developer's computer, off on the main computer.
autoColorMatchProject toggle true | false Automatically give each session its project's color.
autoColorRules list array of object { color: string; icon: string (≤64); id: string; keyword: string } Rules that automatically color a session by keyword (for example, title contains 'bug' shows red).
autoCompactWindowTokens number integer 100000..1000000
autoContinueMaxConsecutive number integer 1..20 How many times in a row a session may continue on its own before it stops and waits (1 to 20). A safety cap.
automationDigestEnabled toggle true | false Automation Helper — the weekly, cost-free health DIGEST (on by default). Once a week it raises ONE inbox card summarizing every registered automation's health (healthy / paused / needs attention), so you can see at a glance which of your automations are working and which need a look — with no paid AI spawn to produce it. Turn it off to stop the weekly card; gated overall by automationHelperEnabled. Synonyms: automation health digest, weekly automation summary, automation status card, which automations are healthy.
automationDiscoveryEnabled toggle true | false In-development: watches your own session history for work you repeat by hand on a schedule (a digest or report you keep asking for) and raises ONE dismissible "want me to automate this?" card that seeds an Automation Builder session pre-briefed on the pattern. Detection is 100% local and cost-free — only accepting a suggestion ever spends. Off until shipped; at release it flips to on-by-default with this as the off switch.
automationGroupCollapsed toggle true | false Whether the Automation sidebar group (Cron Jobs, Recipes, Automations, Quick Replies, Scheduled Messages) is collapsed. Collapsed by default.
automationHelperEnabled toggle true | false Turns the Automation Helper on or off: the feature that builds automations for you and adds its project, Quick Launch tab and sidebar entry.
automationRepairDailyCapUSD number number 0..1000 Automation Helper — the per-automation daily repair-spend cap in US dollars (0 = repair spending is uncapped for a single automation; default $5). Bounds what a single runaway automation can spend on AI repair attempts in one day, on top of the fleet-wide global daily cap, so one broken automation can never burn through your budget while the repair loop tries to fix it. Set it over the CLI. Synonyms: automation repair cap, per-automation spend cap, runaway automation limit, auto-fix daily budget.
automationsFolder text string (≤1000) Optional folder where your built automations are stored. Leave blank to use the default Automations folder under your projects.
bakeoffSidebarEnabled toggle true | false Shows or hides the Bake-Off entry in the sidebar — a prompt-tools feature that runs a prompt across options and compares the results side by side. One of the per-section sidebar visibility toggles; on by default, turn it off to remove Bake-Off from the sidebar. Synonyms: bakeoff sidebar, bake-off, compare prompts or models side by side.
beautifySiteSkillEnabled toggle true | false Install the Beautify Site skill. Off by default; the skill is added only once you turn this on.
boardChairPreference list array of string (≤120) Who chairs a crew's board of directors, strongest first: an ordered list of provider:model keys, and the board seats the first one that is actually ready to run. Defaults to Claude Fable, then GPT-6 Astra, then Claude Opus, then GPT-6.1 Sol. An entry naming a model you have no key for is skipped rather than blocking the board, and only when none of them is ready does the board fall back to picking a chair itself. Synonyms: board chair, who chairs the board, chair model, board of directors chair preference, grok should not chair the board, board chair model order.
boardPostClaimsEnabled toggle true | false Lets an agent reply to a posted fault on a message board and claim the work, so the first claim takes ownership and others can see who has it. On by default. Turning it off makes a claim reply an ordinary reply that claims nothing. Synonyms: board claims, claim a post, take ownership of a fault, claim reply.
boardsSidebarEnabled toggle true | false When on (the default), the sidebar shows the Boards row — the read-only window onto the shared agent board, where Overseers, swarms and ordinary agent-to-agent messages all write. Turn it off to hide that row. It is deliberately its own switch rather than part of the Overseer feature: the board keeps collecting work from those other sources, so the row stays reachable even with Overseers switched off. Synonyms: boards sidebar row, show the agent board, hide the boards row, shared board in sidebar, sidebar boards toggle.
botCreationModeEnabled toggle true | false In-development: describe a job in plain language and a guided interview builds you a ready-to-use bot — its own hub, pre-loaded with a persona, the knowledge it needs, and the right skills. Off by default; hidden until shipped.
browserLoginsSidebarEnabled toggle true | false Show the Browser Logins row in the sidebar. On by default.
bugIntakeRouterEnabled toggle true | false In-development: forwards an incoming bug report to the matching intake destination based on routing rules. Hidden until shipped.
capsLockSendsMessage toggle true | false Let pressing Caps Lock send the message in the composer.
cleanRoomSidebarEnabled toggle true | false Shows or hides the Clean Room entry in the sidebar — a prompt-tools action that spawns a fresh, isolated session. One of the per-section sidebar visibility toggles; on by default, turn it off to remove Clean Room from the sidebar. Synonyms: clean room sidebar, fresh isolated session, clean session.
cliControlPort number integer 1024..65535 Sets the network port the app's local control server listens on, so scripts and agents can talk to the app. The value is read once at startup, so a change needs a restart, and it must be between 1024 and 65535. An explicit port set in the environment still wins. Synonyms: control server port, CLI port, local API port, agent connection port.
cliToolsSidebarEnabled toggle true | false Show the CLI Tools row in the sidebar. On by default.
cloneReportToCrewEnabled toggle true | false When a one-off copy of a crew member finishes, its report goes to the crew that owns the original instead of landing in your inbox. On by default. Turning it off sends those copy reports to you directly, as before. Synonyms: clone reports, copy reports to crew, route clone results, crew clone routing.
cloudGoogleBackupEnabled toggle true | false Allows the app to fall back to a Google cloud machine when the main providers cannot start your cloud session. On by default. Turning it off means a failed launch is not moved to Google, so no session lands on that paid provider by accident. Synonyms: Google backup machine, cloud fallback provider, backup cloud provider, failover to Google.
cloudLockedAppRunSeats toggle true | false Run the app's own REVIEWER-LOCKED crew workers on a cloud box — the memory scribe, the judge and a mission review round (locked-seat-on-a-box-contract). ON by default, like its siblings: the box lock is proved before a seat is placed, and with the proof unavailable the seat stays on this computer. OFF is the behaviour before this existed: every locked kind stays local, byte-for-byte, with nothing asked of the cloud. READ AT SPAWN TIME, and by BOTH doors that can place such a seat.
cloudMachineSharingEnabled toggle true | false May several of this person's agents share ONE cloud machine? DEFAULT ON: the app places agents together by default rather than making the user choose a placement per project. WHAT OFF MEANS, precisely: every session gets its own machine, exactly as it did before this feature existed. It does NOT strand sessions already on a shared machine — those keep working, because the machines and their links already exist. It only stops NEW joins. An operator-level emergency kill switch is honoured too, and off means off either way.
cloudOneOffCloneSpawn toggle true | false Start a ONE-OFF COPY of a session (POST /session/:id/clone, kind one-off) on a cloud box instead of on this computer (overseer-autonomy-contract, one-off-copy-runs-in-the-cloud). ON by default, like its siblings: a copy does a bounded job and finishes, so it is exactly the work that should not take a slot here. The copy goes through the same cloud-first admission every helper reroute uses, and a refusal is the COPY'S refusal — it never falls back to a local run, because a copy is an app-started session and the cloud refusing it is the answer, not a reason to spend this computer's capacity instead. OFF is byte-for-byte the previous behaviour: every copy is created here, and the cloud is never asked. An install that does not offer cloud sessions at all keeps creating copies here too, and says so with an allow-listed reason on the answer; a caller that explicitly asked for the cloud is refused rather than moved here. READ AT CLONE TIME, so it applies to the next copy with no restart.
cloudOutboxOnlyReturn toggle true | false Makes the cloud outbox the ONLY road a git-project cloud session takes home. Each commit such a session makes is already copied into a private per-session outbox, and this computer pulls those commits home whenever it runs. With this on, the older patch capture and checkpoint recovery stand down for exactly the sessions that have an outbox install on record, each answering one named reason and recording no return, so one session can never come home twice or by two different routes. Sessions in projects that are not git projects, older sessions with no outbox, and any session whose install this computer cannot prove are untouched either way. Off by default; check first how many sessions already come home through the outbox and how many still use another road. Set in the Dev Pipeline panel, Setup tab, Returned cloud work card. Synonyms: outbox only, only the outbox, stop the old capture roads, cloud return road cut-over, one road home, sunsets syncback, checkpoint recovery stand down, cloud session return route.
cloudReturnedWorkAutoLand toggle true | false A cloud session that ends with changes brings them home as a branch. With this on, the app lands that branch on its own — for this project, by testing it and marking it ready to merge; for any other project, by running that project’s own test command on the cloud machine and merging the result into that project’s main branch here on this computer. Nobody has to run ready-to-merge on a returned branch by hand. A branch that conflicts with the main branch, or whose merge the app could not work out, is left for you rather than landed, as is a returned branch for a project with no test command. On by default; turn it off in the Dev Pipeline panel.
cloudReviewSeats toggle true | false When on, code review sessions may run on a cloud machine that is already awake and working on the same project, instead of using a slot on your computer. Off by default, so reviews run locally. It also needs cloud sessions and machine sharing to be on. Synonyms: cloud reviewers, run reviews in the cloud, review seats on cloud machines, offload code review.
cloudRunnerApiUrl text string Where the Cloud Runner controller answers. Empty means the production controller, unless the switch above is Off — then no Cloud Runner call leaves this computer at all.
cloudSessionGitRoadEnabled toggle true | false The OFF switch for the git road (Cloud Sessions v2) — the road cloud sessions launch and return over by default, which carries the agent's own commits home as real commits. ON by default, per the rule that a feature ships switched on in code with an explicit off switch and never behind an environment variable. ON is the road that keeps a cloud branch indistinguishable from a local one: every commit the agent wrote comes home as that same commit, with its message, its trailers (Roadmap:, Dropped-work-approved:) and its ancestry intact. OFF restores the tree-shipping road for every project the list below does not name, byte for byte as it behaved before this switch existed — the same road, the same commit, the same message shape. It is therefore a true escape hatch rather than a degraded mode, and it is the state to reach for when the new road misbehaves on a project. A boolean rather than the list below inverted, deliberately: the list is PERSISTED per project and a person may already have named one, so re-reading it as an opt-OUT would silently move the very project that was canaried. Two flags keep that project exactly where it was. It is a preference read at launch and at return, so it applies to the NEXT cloud session with no restart, and it is inert while cloud sessions are off.
cloudSessionGitRoadProjects list array of string (≤500) Project folders KEPT on the git road when the switch above is off — the canary list, and the only thing that puts one project on the new road while every other stays on the old one. It matters only while cloudSessionGitRoadEnabled is off: with the switch on, every project is on the git road and this list changes nothing. It is what lets the new road be proven one project at a time without moving anybody else, and un-naming a project restores the previous behaviour byte-for-byte. A list of PATHS, not a boolean, because the road is proven one project at a time. Comparison is case- and separator-insensitive (isListedGitRoadProject), because the same folder arrives spelled differently from a picker, a settings row and a session record.
cloudSessionHomeSetupEnabled toggle true | false Copy your OWN Claude setup — the global rules file and every skill that exists only on this machine — to a cloud box at bring-up. ON by default, and that is not a question: a feature ships switched on in code with an explicit off switch, never behind an environment variable. OFF is not a degraded mode — it restores today's behaviour exactly, with the same argv and the same bring-up rungs, so a user who wants the previous behaviour gets it byte-for-byte, and the session's one-line notice says the setup is not on the box. A preference, not a gate: cloud sessions themselves are still off until released, and nothing here reaches the user before that. The copy never carries a file holding a credential, and it is inert while cloud sessions are off.
cloudSessionTemplatesEnabled toggle true | false Start a cloud session from a copy of the project saved once with its dependencies already installed, so a launch sends only what changed instead of the whole tree. ON by default — the rule is that a feature ships switched on in code with an explicit off switch, never behind an environment variable. OFF is not a degraded mode: it restores today's full ship exactly, with the same argv, the same ship plan and the same baseline command, so a user who wants the previous behaviour gets it byte-for-byte. This is a preference, not a gate: cloud sessions themselves are still off until released, and nothing here reaches the user before that.
cloudSessionsEnabled toggle true | false In-development: optionally run an agent session on a cloud VM instead of locally, so your machine stays light and you can run more at once. Off by default; local is unaffected.
cloudSessionsSpendConfirmed toggle true | false The ONE-TIME acknowledgement that cloud sessions cost money — set by the user's own click on the confirm dialog the Run-location picker raises on the first Cloud pick, and never written by anything else. This is the memory of consent, not a feature gate: cloudSessionsEnabled decides whether the option EXISTS, this decides whether the user has agreed to PAY. Every cloud provision reads it, so a launch arriving from anywhere the dialog cannot reach is refused rather than quietly spending the user's money on a machine they never agreed to rent.
cloudSharedSshLinkEnabled toggle true | false Carry every cloud session on one machine over a single shared connection held by one background helper, instead of starting a new connection for every turn. Off by default.
cloudStartedMaxChildrenPerParent number integer 0..10 How many live helper sessions ONE cloud session may have at the same time. Default 3, the same ceiling an agent-started session already has on your desktop. A request past it is refused by name, so the agent is told to wait rather than left retrying. Synonyms: cloud helper limit, max helpers per session, cloud children cap.
cloudStartedMaxDailyDollars number number 0..500 The US-dollar ceiling for ALL cloud-started helper sessions in one day, across every tree — default $20. This is the backstop the per-tree ceiling cannot give you, and it is what stops a day of many small trees adding up. Past it, no further cloud-started session runs until tomorrow. Synonyms: cloud daily budget, daily cloud helper cap, cloud session spend per day.
cloudStartedMaxTreeDepth number integer 0..5 How deep a tree of cloud-started sessions may go. Default 2, which means a cloud session and its direct helpers — a helper cannot start a further session. This is the setting that stops a fan-out, and it is enforced by the app, never by asking the agent to behave. Synonyms: cloud session tree depth, nesting limit, how deep can cloud helpers go.
cloudStartedMaxTreeDollars number number 0..100 The US-dollar ceiling for the helper sessions ONE tree starts, in total — default $5. It counts what the sessions the tree STARTED spend, never the session that started them (that one is yours, and it alone runs far more than this). Past the ceiling, further helpers in that tree are refused by name. Synonyms: cloud tree budget, cloud helper spend cap, how much can cloud helpers cost.
cloudTeamOrgId text string (≤200) The team whose wallet a TEAM cloud session's machine time bills — the ONE switch that turns team billing off, and the org id it turns it on for. null is the OFF state and the default: the machine bills the developer's OWN vendor wallet. That is the honest first state of an install nobody has configured, and equally the state a person chooses when they clear it — so it is set by a person, through a settings change they approve, and by nothing automatic, and a team session is REFUSED with a sentence that says so rather than created and billed to whoever happens to be active. It is a vendor org ID rather than a name because the ids are stable and names are not.
cloudV2RoadEnabled toggle true | false Allows new cloud sessions to use the newer controller-managed launch path, which tracks each session with a lease. On by default. Turning it off sends those launches back to the older path instead. Synonyms: cloud sessions v2, new cloud launch path, cloud controller, cloud session lease.
communicationCollapsed toggle true | false Whether the Communication sidebar group is collapsed. Collapsed by default.
composerBusySendDefault select "steer" | "queue"
composerListContinuation toggle true | false Automatically continue a numbered or bulleted list onto the next line when you press Enter in the composer.
connectorSweepReleaseCap number integer 0..10000 The most stopped cloud machines (Agent 37 and Google) the hourly cleanup may delete in one pass. Default 3, so a large release rolls out a few machines at a time and can be checked before the rest go; set it to 0 to remove the cap. Every delete still needs the machine to prove its work is home. Read on every pass, so a change applies to the next pass with no restart. Synonyms: release cap, staged machine release, delete at most, connector sweep limit, agent 37 cleanup batch.
contextWindowDepth number integer 1..500 How many past messages the main conversation panel loads and keeps (1 to 500).
contextdockEnabled toggle true | false In-development: a cloud knowledge library that feeds compressed context (bundles, lists, docs) into any project’s sessions — agents see linked material in their first message. Off by default; hidden until shipped.
contextdockNativeEnabled toggle true | false In-development: the local-first native ContextDock library UI reading Omniscio's own store; off by default; hidden until shipped.
costControlSidebarEnabled toggle true | false Whether the Cost Control section is shown in the sidebar — one of the per-section sidebar visibility toggles. On by default; turn off to hide the Cost Control entry from the sidebar. Synonyms: show/hide cost control in the sidebar, cost control sidebar visibility.
councilSidebarEnabled toggle true | false Show the Council row in the sidebar. On by default.
councilsSidebarHubIds list array of string Hub (project) ids the user has opted into showing the "Councils" section in their sessions sidebar. Default []: the section otherwise renders ONLY in the standalone AI Council hub or a hub that already has council sessions. Toggled via the hub right-click "Show AI Council" menu item.
creativeCollapsed toggle true | false Whether the Creative sidebar group is collapsed. Collapsed by default.
crewApprovalHoldOwnCrewQuietEnabled toggle true | false An automatic notice about one branch held for its crew lead's APPROVED line (the hand-off's HELD line and the 6 h sweep's Approval hold line) goes only to the owning crew's board, carries quiet so it rides that lead's next delivery, is posted once per hold per tip, and becomes ONE daily digest line for a crew with no live lead. A row already parked by a later decision, or whose commits are already on the base, produces no line. ON by default; OFF restores the old behaviour exactly — one loud line per hold, the crew board else the shared overseers board, and no digest.
crewBoardOutsideViewEnabled toggle true | false When a crew has a board of directors acting as its outside view, the regular mission review skips its goal-alignment check for that crew so the same question is not asked twice. On by default. Turning it off makes every review check run again. Synonyms: board outside view, skip duplicate review, goal alignment check, board of directors review.
crewBoundedMemoryDeliveryEnabled toggle true | false Keeps the full crew memory sent to a crew lead within a size budget so one giant message does not fill the lead's working memory. On by default. Turning it off sends the whole memory uncapped, which only suits a small memory. Synonyms: memory size limit, cap crew memory, trim memory delivery, lead context budget.
crewCardInbox object object { report: true | false; update: true | false }
crewCardInboxByCrew map map of string → object { report: true | false; sendTo: "owner" | "hub-overseer"; update: true | false }
crewCheckInQuietEnabled toggle true | false When on (the default), a helper's routine report never interrupts its crew lead: a report the lead has already been sent is not repeated, a report arriving while the lead is mid-turn waits for the end of that turn instead of being slipped into the middle of it, and a second waiting report from the same helper replaces the first rather than stacking behind it. Approvals and READY hand-offs still arrive at the lead's next tool call, so nothing that needs a decision is held back. Turn it off to restore the old behaviour, where every check-in was delivered the moment the helper finished. Synonyms: quiet check-ins, fewer check-ins, stop interrupting the overseer, hold check-ins to end of turn, crew message noise, duplicate check-ins, collapse check-ins.
crewCheckinAfterDirectReportEnabled toggle true | false A crew check-in switch, on by default, that is kept only so saved preferences still load. Nothing in the app reads it today, so turning it on or off changes nothing. Synonyms: crew check-in after a direct report, crew check-in switch, retired crew check-in setting.
crewCheckinStaleApprovalAskEnabled toggle true | false Before a crew member's check-in asks its lead to approve a change, the app checks whether that exact change was already approved or already landed. If so, the ask is replaced with a note that no reply is needed and the lead is not woken. On by default. Synonyms: stale approval, already approved, duplicate approval ask, skip needless wake.
crewCloudReturnHold toggle true | false When on, a cloud session that a crew lead or foreman starts for one of its own members comes home HELD: its work is registered but never tags or lands itself until the lead sends an APPROVED line for the exact commit and mints it. Off by default, so a crew's cloud work lands on its own like any other cloud session. Turn it on (set it to true) to restore the hold; turn it off again and the holds already written are released as well, so a dispatched job held by a crew drains instead of waiting for an approval — a spawn-road return already held still waits for its crew's own mint. Cloud sessions started by anyone who is not a crew member, and dispatcher jobs that did not ask for a hold, are never held either way. Synonyms: crew cloud return hold, crew approval hold, held for APPROVED, stop holding crew cloud work, crew spawn hold switch, cloud return waits for lead.
crewCommitLandedOtherReposEnabled toggle true | false When a crew task is closed as done, the app checks that its linked work has landed. With this on, if the crew's main repository does not recognize the work, the app also checks the crew's other repositories. On by default. Turning it off checks only the first repository. Synonyms: landed check, other repositories, done close check, commit landed.
crewConversationsFollowTheSeatEnabled toggle true | false When a crew member is replaced by a successor, chats that were pointed at the old session move over to the new one. On by default. Turning it off leaves those chats on the old session, which then shows as gone. Synonyms: crew chats follow replacement, move conversations to new seat, crew handoff chats, successor keeps conversations.
crewDarkClockOwnerOffEnabled toggle true | false Stops the crew silent-lead alarm from raising a card when you yourself switched off a lead's wake timers on purpose. On by default. Turning it off makes the alarm keep raising cards about timers you turned off deliberately. Synonyms: dark clock alarm, silent lead alarm, timers turned off, stop repeat alarm.
crewDarkClockPersonPauseEnabled toggle true | false Stops the crew silent-lead alarm from raising a card about a lead that a person paused on purpose, such as with the Pause button or a bulk pause. On by default. Turning it off makes the alarm report every paused lead again. Synonyms: dark clock alarm, paused lead, silent lead alarm, manual pause.
crewDeliverableSupersedeEnabled toggle true | false Lets a crew replace one of its promises with a new one that names the old promise it supersedes, instead of leaving both open. On by default. Turning it off makes the app refuse any promise that tries to replace another. Synonyms: replace a promise, supersede promise, re-plan promise, deliverable replacement.
crewDoneCloseNeedsAcceptanceEnabled toggle true | false Requires a crew task to carry a passing acceptance check before it can be closed as done, and refuses a close with no check or an unreadable one. On by default. Turning it off lets tasks close without proof, as before. Synonyms: acceptance check, close needs proof, done task check, task close rules.
crewDoneCloseNeedsLandingEnabled toggle true | false Refuses to close a crew code task as done while the commit or branch it links to has not landed on the main branch. On by default. Turning it off lets a task close even if its linked work never landed. Synonyms: landed before done, unlanded work, close needs landing, done close check.
crewEndPromisesEnabled toggle true | false When a crew ends, its still-open promises are settled instead of left dangling: they move to a live crew with the same goal if one exists, otherwise they are marked dropped. On by default. Turning it off leaves them untouched. Synonyms: ended crew promises, carry over promises, drop open promises, crew shutdown cleanup.
crewFindingEscalationEnabled toggle true | false Every 15 minutes the app looks for crew review findings that have gone past their ruling window with no decision, then logs it, posts to the crew's board, and wakes the lead to rule on them. On by default. Turning it off stops these reminders. Synonyms: overdue findings, unruled findings, finding reminders, review finding escalation.
crewFindingEscalationEndedCrewsEnabled toggle true | false Limits overdue-finding reminders to crews that are still live, so the app stops nagging about findings of crews that already ended. On by default. Turning it off brings back reminders for ended crews too. Synonyms: ended crews, overdue finding reminders, stop old crew reminders, live crews only.
crewForemanSeatClocksEnabled toggle true | false When a session registers as, or is promoted to, a crew Foreman, its regular heartbeat and review wakes are switched on the same way a lead's are. On by default. Turning it off leaves a Foreman with no schedule until someone sets one by hand. Synonyms: foreman schedule, foreman heartbeat, foreman wake timers, foreman review clock.
crewFreshStartRecordsHandoffEnabled toggle true | false When a crew lead or Foreman is replaced through a fresh start, the crew record notes that the outgoing one handed its post over. On by default. Turning it off records the departure as a plain fresh start instead. Synonyms: fresh start, handoff record, lead replacement, seat change record.
crewGoalLineageEnabled toggle true | false When someone registers a crew for a goal that a live or recently ended crew already holds, the new registration continues that crew instead of starting a second board. On by default. Turning it off lets a duplicate crew form for the same goal. Synonyms: same goal crew, continue crew, duplicate crew, crew registration.
crewHelperCrewTitlesEnabled toggle true | false Gives crew helper sessions, the memory scribe and the promise judge, clear titles that show the crew, the role and the job. On by default. Turning it off goes back to the older plain titles such as the crew name followed by judge. Synonyms: helper titles, scribe title, judge title, crew session names.
crewHelperDeadSeatWatchEnabled toggle true | false Lets the app notice when a crew helper's session has crashed into an error state and give up on it right away, with a clearer message, instead of waiting out the full time limit. On by default. Turning it off watches only running and finished states. Synonyms: dead helper, crashed helper session, helper watchdog, scribe stuck.
crewLadderAuditEnabled toggle true | false Lets the app start one fresh independent review when a crew is truly stalled, such as a success number stuck red for a full cycle or a promise past its window, even while the regular app-run reviews are off. On by default. Turning it off starts no such review. Synonyms: stall audit, stalled crew review, independent audit, stuck mission.
crewLadderHeldIncidentSignalEnabled toggle true | false Treats a crew stall alert that the lead already answered, with its re-plan window still open, as a stall the app already knows about. Your message during that time is then not counted as a stall you caught yourself. On by default. Turning it off ignores answered alerts. Synonyms: owner caught stall, held stall alert, re-plan window, stall signal.
crewLeadBudgetReseatEnabled toggle true | false When a crew lead session is stopped because its automatic retries ran out, the app seats a fresh replacement lead instead of leaving it red for you to click. On by default. When off, a stopped lead stays stopped until you act. Synonyms: replace stopped lead, retry limit new lead, crew lead recovery, lead reseat.
crewLeadCapGrantEnabled toggle true | false Lets one session you have allowed raise any crew's lead limit by itself, with no card each time, and records every raise. On by default. When off, every raise goes back to waiting for your click on a card, even for a session that already holds the permission. Synonyms: lead cap permission, raise lead limit, standing permission, crew lead cap.
crewLeadCardRepairTurnSilentEnabled toggle true | false When a crew lead repairs its own progress card during a turn, the app does not raise a second card from that turn's final words, which would overwrite the repair. On by default. When off, that turn raises a card as usual. Synonyms: repaired card quiet, duplicate lead card, lead card overwrite, silent repair turn.
crewLeadCardsFollowSeatEnabled toggle true | false When a crew gets a new lead, the open progress cards of the old lead move over to the new one so they are not left behind. On by default. When off, the cards stay attached to the session that left. Synonyms: lead cards transfer, new lead inherits cards, crew handover cards, seat change cards.
crewLeadGrantsFollowSeatEnabled toggle true | false When a crew gets a new lead, the permissions the old lead held, such as the app restart permission, the lead limit permission and message board access, are passed to the new one. On by default. When off, nothing is carried over. Synonyms: lead permissions transfer, new lead inherits grants, crew handover permissions, seat change grants.
crewLeadItemEscalationEnabled toggle true | false Checks a crew lead's open items and, when one has gone unanswered past its due time, escalates it upward to the hub overseer. On by default. When off, the overdue check still tidies items but nothing is escalated. Synonyms: overdue lead items, unanswered item escalation, lead item reminder, overdue escalation.
crewLeadModelFloorEnabled toggle true | false When on (the default), a session may take the overseer post or the Foreman badge only on Claude Opus 5.5 or better, and the app itself starts its own overseers on Opus 5.5. Turn it off to restore the previous behaviour and let any engine lead. It has no on-screen control, so set it with the CLI. Synonyms: crew lead model floor, leaders run on the top model, opus for overseers, minimum model for a lead, foreman model floor, stop cheap models leading.
crewLeadTerminalReseatEnabled toggle true | false When the app starts, a crew lead that was already giving up, because its retries ran out earlier or its cloud machine keeps failing, is given a successor. On by default. When off, such a crew stays without a lead. Synonyms: startup lead recovery, leaderless crew, dead lead replacement, boot reseat.
crewLeadTurnsRecordedEnabled toggle true | false Keeps a record of each turn a crew lead takes: when a request reached the lead, when the lead started, and how it ended. On by default. Turning it off stops that recording but does not change how the lead works. Synonyms: record crew lead turns, lead turn history, crew lead activity log, lead response tracking.
crewLeadWakeAppOriginEnabled toggle true | false Counts the app's own wake-ups of a crew lead as the app's machinery instead of as messages from outside the crew, and reads the sender list of combined messages. On by default. When off, the earlier counts and alarm trips return. Synonyms: lead wake sender, app wake count, peer traffic count, wake origin.
crewMemberReportsNeedAReasonEnabled toggle true | false Keeps an ordinary finished turn from a crew member out of its lead's inbox unless it has a reason, such as a route-to-user tag, a question or another decision to make. On by default, so routine turns are parked quietly. When off, every turn is handed to the lead. Synonyms: crew check-in noise, quiet member reports, routine turn parking, lead check-ins.
crewMemoryScribeEnabled toggle true | false Allows a helper session to read each crew's conversation and write down what its lead should remember. Each pass is a paid session. Off by default. When off, no scribe runs and crews keep the memory already written. Synonyms: crew memory, memory scribe, crew notes helper, lead memory writer.
crewMissionFocusReminderEnabled toggle true | false When on (the default), every overseer is shown one line — its own mission in a sentence, plus the question of what its next move on it is — inside a turn it was already taking, at most once an hour. It starts nothing and costs nothing: no extra session, no wake, no extra turn. Only a crew lead (the overseer of a mission or a sub-mission) sees it; a worker never does. Turn it off and the line stops appearing for every overseer everywhere, and nothing else changes. Overseers hub → Fleet settings → How they behave → "Mission focus reminder". Synonyms: mission focus reminder, remind the overseer of its mission, keep the mission moving, overseer drifts to the inbox, lead forgets its mission, focus line, turn off the mission reminder.
crewMissionStatusStripEnabled toggle true | false
crewNoticesStayInOwnCrew toggle true | false A notice about ONE crew is delivered inside that crew — the hand-off's held-for-approval board line, and an inbox alert route carrying a crew-scoped card. ON by default; only a literal false opts out, which restores the old fallbacks (the fleet-wide overseers board, and whatever crew or seat a route names).
crewOutcomeConsequenceEnabled toggle true | false When a crew's lead stays below its outcome bar across three of its own turns, the app opens the first step of the crew's escalation once per mission. On by default and applies to crews that have declared a success number. When off, falling below the bar triggers nothing. Synonyms: below bar escalation, crew score consequence, outcome score step one, crew stall trigger.
crewOwnerCaughtStallAnswerExclusionEnabled toggle true | false When the app records stalls that you noticed before it did, your replies that simply answer a question the lead asked are not counted as stalls. On by default. When off, every message you send into a stalled crew is recorded as a stall. Synonyms: owner caught stall, stall count accuracy, ignore my answers, stall measurement.
crewOwnerCaughtStallEnabled toggle true | false Records the stalls you notice before the app does, so the app can measure how often it misses one. On by default. When off, no new records are written; nothing else about crew memory changes. Synonyms: owner caught stall, missed stall record, stall measurement, stall log.
crewPromiseAutoDeliveryEnabled toggle true | false When on (the default), the app itself marks a crew promise delivered as soon as the promise's own check says it is done — a done test the app runs has passed, or an independent judge has scored it at or above its bar. The promise closes with that result in its history, so a lead no longer has to notice it and move it by hand. Turn it off to go back to recording the result and leaving every promise open for its lead to deliver. Synonyms: auto deliver promises, mark promises done automatically, promise auto delivery, delivered on its own check, promises still open, undelivered promises.
crewQueuePlacementDefaultsToCloudEnabled toggle true | false Crew work-queue placement — a placement says where an item goes, not whether it may be queued. Default ON: an item or a task with no placement is cloud-ok, and a local-only item must name one of the crew-worker local reasons. OFF makes THIS COMPUTER the default everywhere the app supplies one: a queued item, a task's ready-mark, and the repair of a run a pre-fix build stranded with no placement all become local-only, and no reason is demanded — a local run is then the norm rather than the exception. A task that explicitly asked for cloud-ok still runs in the cloud. Read live, so a flip needs no restart.
crewReportsFollowTheSeatEnabled toggle true | false When a crew leader is replaced by a successor, the members who reported to the old session now report to the new one. On by default. Turning it off leaves their reporting line on the old session. Synonyms: crew reports follow replacement, reassign crew reporting line, crew handoff reports, successor takes over reports.
crewReviewEngine text string (≤64) Which AI a crew side-mission reviewer runs on. Empty (the default) picks automatically — a low-cost vendor different from the lead's own, so the review comes from a different mind. Any provider id or model tier you name is used as given. Synonyms: crew review engine, which model reviews the crew, reviewer model, different model for reviews, crew reviewer provider.
crewReviewWakesEnabled toggle true | false Master switch for the scheduled reviews every overseer gets every few hours, when it steps back and checks its work. On by default. When off, no review runs, neither the independent reviewer session nor the lead wake. The schedules stay in place and resume when you switch it back on. Synonyms: scheduled reviews, step back review, overseer review, periodic review.
crewReviewerBoxReleaseEnabled toggle true | false When a reviewer session running on a cloud machine ends with nothing to save, the app puts that machine to rest so it stops running. On by default. Turning it off leaves the machine awake after the review ends. Synonyms: release reviewer machine, stop idle cloud reviewer, park cloud box after review, save cloud machine after review.
crewScorecardAnsweredTurnsEnabled toggle true | false When on (the default), a crew lead's scorecard counts a run of messages answered together as ONE turn, not one turn per message. Messages that arrive while the agent is already working are answered by the turn it is in, so they never cost a separate paid turn — before this rule they inflated the denominator behind "moves per turn" by about a quarter. The owner-touch column is unchanged: it still counts every message you typed. Turn it off to count one turn per message row again, exactly as before. A stored day remembers which count produced it, so flipping this re-scores the days it covers. Synonyms: paid turns, turns per day, moves per turn, message rows counted as turns, scorecard turn count, lead workload measure.
crewScorecardJudgedProofEnabled toggle true | false Lets a lead's scorecard count a promise judged against a rubric as checked, and a latest judge score at or above the bar as proven. On by default. When off, only promises with a passing done test count, so a mission whose promises are all judged can read as unproven. Synonyms: scorecard judged promises, judge score proof, promise coverage, lead scorecard.
crewScorecardOwnerTypedOnlyEnabled toggle true | false When on (the default), a crew lead's scorecard counts as an "owner touch" only a reply you actually typed: words in the composer, or a typed answer into an inbox card's answer bar or a question card's Custom/Other field. Your away-mode auto-rule, Inbox Pilot, the dev-pipeline auto-advance and a question card's plain option pick are your side answering, not you typing, and are not counted — they were what pushed the number far above the target. Turn it off to count every reply made on your behalf again, exactly as before. A stored day remembers which count produced it, so flipping this re-scores the days it covers instead of leaving an old figure beside a new one. Synonyms: owner touches, owner replies per day, auto replies counted, scorecard owner count, typed replies only, owner interruptions, owner attention metric.
crewScribeConsolidationPartialEnabled toggle true | false When on (the default), one bad merge in a crew memory tidying pass costs only itself: a merge that names an item the pass was not shown, or one that changed while the scribe was thinking, is refused by name and every good merge beside it is still saved. Turn it off to restore the earlier all-or-nothing behaviour, where a single stray merge refused the whole answer and nothing was written — an over-budget crew memory then stood still while its conversation kept adding to it. Synonyms: crew memory scribe keeps none, memory never merges down, merge-down refused whole, over budget memory not shrinking, consolidation all or nothing off switch, stray merge voids the batch.
crewScribeCursorJumpEnabled toggle true | false Lets the crew memory scribe skip ahead past conversation it cannot usefully read, instead of reading strictly page by page. On by default. When off, the scribe goes back to reading page by page exactly as before. Only matters when crew memory scribes are running. Synonyms: scribe skip ahead, memory scribe paging, scribe cursor, conversation skipping.
crewScribeMergeCeilingEnabled toggle true | false Sets how long a merged note may be when the crew memory scribe tidies an over-budget memory. On by default, the scribe is allowed the larger size the store actually keeps. When off, it is asked for the smaller new-item size, which can leave it merging nothing. Synonyms: scribe merge size, memory merge limit, memory tidy length, crew memory consolidation.
crewScribeMergeDownEnabled toggle true | false Makes the memory scribe's tidy-up pass take on as much of an oversized crew memory as one request can carry and tells it what size to shrink to. A pass that merges nothing over budget also tells the lead. On by default. When off, it uses a fixed small slice. Synonyms: memory consolidation size, shrink crew memory, over budget memory, scribe tidy.
crewScribeReachableAskEnabled toggle true | false Keeps the memory scribe's request to shrink a very oversized crew memory within what one pass can honestly achieve, so the memory comes down step by step. On by default. When off, the scribe is asked for the memory's whole overshoot at once. Synonyms: scribe realistic target, memory shrink limit, consolidation target, crew memory budget.
crewScribeSpawnRecoveryEnabled toggle true | false When the app cannot start a memory scribe pass because the reviewer limit is full, it waits and asks again a few times instead of giving up at once. On by default. When off, the first refusal ends the pass. Synonyms: scribe retry, helper start retry, reviewer cap retry, memory scribe spawn.
crewStatusCheckinEnabled toggle true | false When on (the default), a crew lead that has posted nothing you could see for that crew's own status interval is told so on its next scheduled wake, and asked for a brief status of its system and current goals. Turn it off to stop forcing those check-ins for every crew — a single crew is switched off from its own settings menu instead. Synonyms: crew status check in, force overseers to report, make leads post a status, crew lead updates, overseer status nudge.
crewStatusIntervalMinutes map map of string → integer 0..1440 How often one crew's overseer owes you a status update, in minutes, set from that crew's settings menu. Leave it unset for the four-hour default; set it to 0 to switch the forced update off for that crew alone. When the interval passes with nothing of the overseer's having reached you, the app makes it post one — Done since last update, In progress, Blocked or needs you, Next. Empty/absent means every crew keeps the four-hour default. Synonyms: overseer status interval, how often do overseers report, crew update frequency, status check in interval, reporting cadence.
crewStatusReportSingleCardEnabled toggle true | false Keeps a crew lead's status reports to a single card in your inbox: when a new status report lands, older superseded ones that are unread and unanswered are retired. On by default. When off, earlier status report cards pile up. Synonyms: status report cards, duplicate status cards, old status report cleanup, lead status inbox.
crewSuccessNumberAskEnabled toggle true | false Asks a crew's lead to declare the number its mission is judged on when it has none, once at registration, once on its next wake and with one nudge after a day. The ask rides a wake that was already going out. On by default. When off, nothing is asked. Synonyms: success number, crew goal metric, ask crews for target, mission scoring.
crewSuccessorReplacementEnabled toggle true | false Watches new replacement leads and, when a successor seat stays dead and silent past a grace period after a warning, replaces it once through the normal hand-off. It writes to the crew log, never your inbox. On by default. When off, the check stands down. Synonyms: dead successor, unready lead replacement, hand-off watch, seat readiness.
crewTagBackfillPendingDeliveryEnabled toggle true | false When a crew session finishes without a crew tag on its reply, the app asks for the tag. With this on, the default, that request waits and is delivered with the session's next incoming message. Turning it off sends the request right away as its own message. Synonyms: crew tag reminder, delay tag request, crew reply tag backfill, hold tag nudge.
crewTagPathHealthEnabled toggle true | false Shows one line on a crew's mission screen saying whether tagging work as ready can happen now, based on the crew registry, the phase manifest and the last ready attempt. It is checked only while the screen is open. On by default. When off, the line disappears and nothing is checked. Synonyms: tag path health, ready tag status, mission screen health, tagging readiness.
crewWakeNeedsNothingEnabled toggle true | false Lets arrivals that ask for nothing, such as a status-only check-in, a board pointer that is just an approval hold or the cloud return notice, wait for the lead's next turn instead of waking it. The cloud notice goes to the foreman. On by default. When off, they wake the lead. Synonyms: quiet wake, avoid waking lead, no-ask messages, wake noise.
crewWakeOwnerAnswerCarryEnabled toggle true | false When a lead is woken by the app while a question to you is still unanswered, keeps that open question attached to every turn of that wake, not just the first. On by default. When off, only the first turn of a woken round hands the question back. Synonyms: unanswered owner question, wake carries question, lead wake round, owner gate carry.
customColors list array of string Your saved custom colors (up to 20) that appear in the color picker.
dailyBriefEnabled toggle true | false One calm summary a day of what the agents shipped, what is still moving, and what is waiting on you. A quiet day sends nothing.
deepTargetHighlightEnabled toggle true | false Let an agent or a shareable link navigate you to any page AND spotlight a specific control on it in one step (e.g. jump to a Settings section and point at the exact toggle). Navigate-only, so it never spawns a session.
defaultAgentInstructionsOverrides unknown pipeline Remembers which of the built-in default instruction presets you have switched on or off. Internal preference map; edit it from the settings screen, not by hand.
defaultRunLocation unknown any | "auto" Where a NEW blank session runs when the user has not picked: the "Save as default" hint's Everywhere scope for the Run chip. A saved 'cloud' pre-selects (stages) Cloud only where Cloud is genuinely on offer — cloud visible, a cloud-capable engine, a real project, and the spend ack above already given — so it can never rent a machine the user did not agree to pay for.
defaultSessionSetupPresetId text string (≤100) The id of the session setup preset applied to every new blank session, once, before you pick anything yourself. Set it with "Make default" on a preset in the Preset menu, or tick "Use this for every new session" when saving one. Empty means no default preset. Synonyms: default preset, default session setup, startup preset.
depSecurityScanEnabled toggle true | false Dependency Security Scan
devPipelineAiReviewEnabled toggle true | false The AI Code Review master switch, on by default. Turning it off takes every AI Code Review step out of the step list agents read and refuses a reviewer spawn — so no review runs at all. Chosen in the Dev Pipeline panel's Setup tab. Synonyms: ai code review, turn off code review, disable ai review, dev pipeline review step, reviewer spawns.
devPipelineAutoRepliesEnabled toggle true | false Dev Pipeline extra: adds the pipeline's bundled auto-reply rules to your sessions, and removes them again if you turn it off. Off by default.
devPipelineCustomPhasesEnabled toggle true | false Turns on the Dev Pipeline's custom-phase editor: you can add phases of your own (and their approval gates) at the point in the flow where they belong, alongside the built-in ones, and each custom gate then gets its own auto-approve switch at its true position rather than being appended after the built-in five. Your phases live in ~/.claude/dev-pipeline/phases.json, the one file both Omniscio and the Claude skill read, so a phase you define is visible to the run it configures — a normal setting would be invisible to it. Off by default; the Dev Pipeline panel's Setup tab. Synonyms: custom phases, enable custom phases, add my own pipeline phase, phase manifest, phases.json, custom gate, extra pipeline step.
devPipelineDailyMaintenanceEnabled toggle true | false When on (the default), Omniscio runs its dev-pipeline maintenance once a day on its own: housekeeping across your worktrees and ready-to-merge branches, so the fleet stays tidy without you asking. It runs a free check first and starts a paid Claude Code housekeeping session only when that check finds something that needs a person, so a healthy fleet costs nothing — turn it off to keep maintenance entirely manual. Its model and provider are chosen by devPipelineDailyMaintenanceModel / devPipelineDailyMaintenanceProvider / devPipelineDailyMaintenanceThinkingLevel. Synonyms: daily maintenance, dev pipeline housekeeping, automatic maintenance job, nightly cleanup, who cleans up my worktrees.
devPipelineDailyMaintenanceModel text string (≤100) Daily-maintenance MODEL override. null ⇒ the engine default's model.
devPipelineDailyMaintenanceProvider text string (≤100) Daily-maintenance ENGINE override — the harness/provider its background session runs on. null ⇒ MAINTENANCE_DEFAULT_ENGINE, the engine the maintenance module ships. The Setup-tab picker only offers Claude-binary engines (native Claude + the anthropic-compat vendors), since maintenance runs the Claude Code housekeeping skills. Resolved with the model by resolveMaintenanceSpawnConfig.
devPipelineDailyMaintenanceThinkingLevel select "auto" | "minimal" | "low" | "medium" | "high" | "max" | "xhigh" | "ultra" How much the daily dev-pipeline maintenance job is allowed to think before it acts — a thinking level (for example low, medium or high) rather than a model name. Blank means the default for the model it runs on. Higher thinks harder about what is safe to tidy, and costs more per run; lower is cheaper and quicker. Only used when devPipelineDailyMaintenanceEnabled is on. Synonyms: maintenance thinking level, how hard should maintenance think, maintenance reasoning depth, daily maintenance cost.
devPipelineFileNoteEnabled toggle true | false Dev Pipeline extra: writes the 'route work through /dev-pipeline' reminder into the repo's own CLAUDE.md or AGENTS.md file. Off by default.
devPipelinePanelEnabled toggle true | false A projects-bar panel to oversee the dev-pipeline workflow — see every active pipeline run and which gate it is waiting at, turn gate auto-approval on/off, and control the auto-lander plus a history of every branch it has landed.
devPipelinePlanGateRule object object { customRules: array of object { id: string (≤40); text: string (≤200) }; holdKinds: array of "ui" | "new-feature" | "user-default" | "contract-change" | "refactor" | "bug-fix" | "docs" | "infra" | "tooling"; maxRisk: "low" | "medium" | "high"; maxSize: "small" | "medium" | "large"; minConfidence: "low" | "medium" | "high"; takeRecommendedAnswers: true | false } Your own rule for which Dev Pipeline plans may be approved without you, used only when the Plan step does not wait for you. The agent labels its plan (how confident it is, how risky, how big, what kind of change it is, how many open questions it has and whether each has a recommended answer, and which of your own rules it matches) and the app decides: the plan goes ahead only when confidence is at least your minimum, risk and size are at most your maximums, none of the kinds you chose to hold apply, none of your own rules match, and every question is answered (or has a recommended answer when you allow taking it). A plan with no fresh labels, or one the agent labelled as touching spend, data, security, new packages or anything hard to undo, always waits for you. An empty or unreadable value falls back to the safe default, which holds screen changes, new features and new settings for users. Changing it through the CLI asks you to approve first. Chosen in the Dev Pipeline panel, Your pipeline, under the Plan step. Synonyms: plan auto-approve rule, when to approve a plan, plan gate rule, plan labels, hold plans for me, plan confidence, plan risk, plan size, custom plan rules.
devPipelineQuickRepliesEnabled toggle true | false Dev Pipeline extra: adds the pipeline's bundled quick-reply buttons (common git actions) to your quick replies. Off by default.
devPipelineQuickRepliesSeeded list array of string (≤200) Internal bookkeeping: the list of Dev Pipeline quick replies already offered once, so they are not added twice. Not a setting to change.
devPipelineReminderEnabled toggle true | false Dev Pipeline extra: injects the pipeline reminder into sessions and seeds its quick replies. Off by default.
devPipelineRepos list array of object { enabled: true | false; projectId: string (≤100) } Which repositories the Dev Pipeline - and through it the auto-lander - is on for, one entry per project as { projectId, enabled }. A project with NO entry is ON, so an EMPTY list is not "off" - it leaves every project you have added turned on. The list is a per-repo override, never a whitelist: an entry turns that one project on or off and every project you did not list keeps the state it had, so listing one repository never narrows the Dev Pipeline (or the auto-lander) to that repository alone. Only your own edits change it, so there is nothing to undo. Edited from the Dev Pipeline panel Setup tab. Synonyms: dev pipeline repos, which repos is the dev pipeline on, watched repositories, auto lander repos, add a repo to the dev pipeline, per-repo enable.
devPipelineRetrospectiveEnabled toggle true | false The Retrospective switch, on by default. While on, every full Dev Pipeline run looks back at itself after Docs and before the Standards Audit and the ready-to-merge tag: the agent asks, with evidence from the run, which tool, command or skill would have done the work faster, whether each test it wrote or ran was worth it, which mistakes and retries could have been avoided, where the time went, and whether any step added nothing. It fixes the small things in its own work, files real problems and tool wishes to the friction ledger so they get fixed for everyone, and repeats anything it could not file in the final report. Quick Lane runs skip it. Turning it off takes the step out of the step list, including in runs already under way. Chosen in the Dev Pipeline panel's All settings, beside the Scout Report. Synonyms: retrospective, retro, look back, lessons learned, post-mortem of the run, what could have gone faster, were the tests worth it, friction, avoidable mistakes, turn off the retrospective.
devPipelineScoutEnabled toggle true | false The Scout Report switch, on by default. While on, every Dev Pipeline run starts with a Scout Report before any plan exists: the agent reads the project's rules and the code around the change, then reports deeper problems (a tangled system, patch on patch, duplicated or dead code, a refactor that should come first), gives a design verdict (sound, showing wear, or needs a rethink), and stops every run, crew and hands-off runs included, to ask you when the area needs a rethink, once per folder. Turning it off takes the step out of the step list, including in runs already under way. Chosen in the Dev Pipeline panel's All settings, beside Step Back. Synonyms: scout report, code health report, deeper problems, refactor first, rethink, design verdict, turn off the scout, pre-plan review.
devPipelineSidebarEnabled toggle true | false Whether the Dev Pipeline panel's row appears in the sidebar (default on). A visibility toggle only - hiding the row does not turn off the controls inside the panel and does not stop the background jobs behind it (the auto-lander, daily maintenance). Settings - Sidebar. Synonyms: dev pipeline sidebar, hide the dev pipeline panel from the sidebar, show dev pipeline, sidebar dev pipeline item, pipeline panel visibility.
devPipelineSkillEnabled toggle true | false The Dev Pipeline SKILL bundle — installs the dev-pipeline and ready-to-merge skills into this machine's Claude skills. There is no separate switch for it: the Dev Pipeline panel's own on/off switch (devPipelinePanelEnabled) is the master and keeps this in step, installing these skills when you switch the pipeline on and removing them when you switch it off. Off by default. Synonyms: dev pipeline skill, install the dev pipeline skill, ready to merge skill, skill bundle.
devPipelineStepBack select "off" | "report" | "stop"
devPipelineSystemRulings unknown pipeline
developerStatusEnabled toggle true | false One read-only screen with the app's own developer readouts: whether the running build is behind, whether GitHub is in sync, what is waiting to land, Verdict health, cloud sessions, and how long agent command calls are waiting. It shows the same numbers as the strip at the bottom of the desktop sidebar and the command-wait chip in the toolbar, so you can check the machine from your phone.
developerToolsGroupCollapsed toggle true | false Whether the Developer Tools sidebar group (Dev Pipeline, Job Monitor, Running Apps, New Terminal) is collapsed. Collapsed by default.
dictationsSidebarEnabled toggle true | false Shows or hides the Dictations entry in the sidebar, the Communication panel that lists what you dictated with FlowVoice. One of the per-section sidebar visibility toggles; on by default, turn it off to remove Dictations from the sidebar. Synonyms: dictations sidebar, flow voice history, show/hide dictation list.
emailCleanupSidebarEnabled toggle true | false Show the Email Cleanup row in the sidebar. On by default.
enableSkillsIntegration toggle true | false Master switch for the Skills feature that lets your sessions use installed skills. On by default.
engineHistoryImportEnabled toggle true | false Bring conversations you had in Claude Code or Codex outside the app into a project as sessions you can read and continue — an "Import Claude Code and Codex history" item in the project menu. Importing spends nothing; only your own next message to an imported session starts a turn.
extensionsSidebarEnabled toggle true | false Show the Extensions row in the sidebar. On by default.
fanoutEnabled toggle true | false Bake-Off
fanoutPresets list array of object { id: string (≤100); name: string (≤80); peerAwareness: true | false; projectIds: array of string (≤200); prompt: string (≤200000); setups: array of object { customProviderId: string (≤100); location: "local" | "cloud"; mcpOverrides: map of string → true | false; model: string (≤100); provider: string (≤64); route: string (≤64); thinkingLevel: string (≤32) }; swarm: true | false; updatedAt: string (≤40) } Your saved Bake-Off (fan-out) presets — named configurations for the Bake-Off launcher, each remembering the selected projects, the harness/model setups, and optionally a prompt, so you can reload a whole comparison in one click instead of rebuilding it. Managed from the Bake-Off dialog's Presets bar (Save, load from the dropdown, delete with undo), not a Settings toggle; stored locally and readable over the CLI. Loading a preset restores its projects and setups and, if it saved a prompt, fills the prompt box — a preset saved WITHOUT a prompt never overwrites what you have already typed. Synonyms: bake-off presets, fanout presets, saved bake off setups, save a bake-off configuration, reload my contestants, saved model comparison, preset lineups, bake off save preset.
fileConverterSidebarEnabled toggle true | false Show the File Converter row in the sidebar. On by default.
finalMessageMarkerEnabled toggle true | false Adds the setup-time nudge reminding agents to mark their final message for you. Detection always runs; this only turns the nudge on or off. On by default.
finalMessageShapePromptEnabled toggle true | false When on (default), every regular agent session gets a system-prompt note describing what its final turn message must contain — the outcome first, evidence, any deliverable inline, and the next move. Skipped on Ask-Omniscio / Ask-about-this-page helper sessions. No Settings-UI control; set via CLI/PATCH.
finishedNoAskAppRunAutoArchiveEnabled toggle true | false
finishedNoAskAutoArchiveEnabled toggle true | false When a finished turn just tells you to close it and asks nothing, that session leaves the board on its own. Off by default; turning it on or off affects only new auto-clears, and already-archived sessions stay put.
finishedNoAskMachineAutoArchiveEnabled toggle true | false
flowchartSidebarEnabled toggle true | false Show the Flowchart row in the sidebar. On by default.
gitPackedObjectWrites toggle true | false
githubMcBranchCreationEnabled toggle true | false In-development: create a GitHub branch directly from a Mission Control board item and auto-link it back. Off by default.
githubPrAutoCloseEnabled toggle true | false When on (default), a PM board item auto-moves to its board's Done group once every GitHub PR linked to it has merged. Also gated behind the github-pr-linking feature. No Settings-UI control yet; set via CLI/PATCH.
globalMemoryEnabled toggle true | false In-development: a progressive-disclosure, agent-written memory tree on the Context Dock store; agents browse + load memory across sessions; off by default; hidden until shipped.
goalDefaultMaxTurns number integer 1..50
goalDefaultSpendCapMicroUsd number integer 10000..50000000
handoffNoticeAuto toggle true | false Automatically size the handoff warning to the model's real context limit. Off lets you pin a fixed token number instead.
handoffNoticeEnabled toggle true | false Warn you before a session gets close to its context limit, so you can hand off to a fresh session.
handoffNoticeTokens number integer 20000..∞ The operator's PINNED absolute context-in-use token threshold, used ONLY when handoffNoticeAuto is false ("Custom"). Absolute, not a percentage, because quality drift tracks context LENGTH. Floor 20_000; set it very high to effectively mute the notice. Retained but IGNORED while Automatic is on (the derived per-model threshold governs). Default 150_000 — the legacy flat value, and exactly 0.75 × 200k.
hubOverseerInstructions text string (≤2000) Your own standing instructions to whoever holds the hub-wide overseer seat: free text, delivered with every wake the holder takes and never parsed by the app, so it is exactly what you want that seat to keep in mind. Capped so a pasted document cannot ride the wake path. On screen it is the "Anything you want it to know" box, under Overseers hub → Fleet settings → How they behave. Synonyms: hub overseer instructions, standing orders for the hub seat, tell the hub overseer what to do, seat instructions, hub behaviour notes.
hubOverseerMode select "everything" | "inbox-only" What the hub-wide overseer seat is for: "everything" (the default) means it covers your inbox plus every crew and overseer, while "inbox-only" screens just your inbox and leaves the crews alone. Read by the seat on its next wake, so a change needs no restart and no reassignment. On screen it is the switch "Let your master overseer run everything", under Overseers hub → Fleet settings → How they behave. Synonyms: hub overseer mode, what the hub seat does, inbox only overseer, overseer covers everything, scope of the hub overseer seat.
idleCompactionMode select "off" | "on-return" | "before-cache-lost"
inboxAgentCrewId text string (≤128)
inboxAgentEnabled toggle true | false One agent that owns your Needs-You inbox: it reads everything waiting on a five-minute pass, routes what it can settle itself, answers the agents that are blocked on a reply so their work keeps moving while you are away, and reports in a short digest on a cadence you choose. It learns your sorting rules one example at a time and keeps them where you can read and change them. Off until you start one — starting it runs a session on a schedule, so it is never switched on for you.
inboxDigestQuietHours object object { enabled: true | false; end: string; start: string; summaryAt: string } The quiet window for your inbox digest: while it is on (the default) no digest is delivered between 22:15 and 08:15, and one summary at 08:15 carries whatever the night had to report. The times are local wall-clock HH:MM. Turn it off to receive digests around the clock. On screen it is "Hold inbox digests while I sleep", under Overseers hub → Fleet settings → Quiet hours. Synonyms: inbox digest quiet hours, do not disturb the digest, no nightly digests, digest summary in the morning, quiet window for the inbox digest.
inboxOverseerGateAlwaysThrough list array of string (≤200) Dedup keys (or key prefixes) the inbox gate NEVER holds — an item whose dedup key matches one goes straight to you, whatever the gate decides. Useful for keys you always want to see immediately. Accepts up to 200 entries, each up to 200 characters; a blank list (the default) means the gate decides on everything. Synonyms: inbox gate always through, always let these through the inbox gate, inbox items the overseer must not hold, inbox gate bypass keys, urgent alerts skip the inbox gate.
inboxOverseerGateEnabled toggle true | false Master switch for the inbox Overseer gate — when on, one Overseer screens every new inbox item and holds it out of your list until that Overseer releases or disposes it (lets it through, or handles it itself by answering, archiving, merging or routing). Off by default, because it points an always-on agent at your intake. Separate from overseerGatekeeperEnabled, which screens alert cards fleet-wide; this one is a single named Overseer gating the whole inbox. Synonyms: inbox overseer gate, overseer holds my inbox, let the overseer screen new inbox items, inbox gate on, route my inbox through the overseer.
inboxOverseerGateMaxHoldMinutes number integer 5..120 The longest the inbox gate may hold one item before it is released on its own — the fail-open bound, so a gate that is off, crashed or unreachable can never strand your intake. Range 5–120 minutes; default 10. Synonyms: inbox gate max hold, how long the overseer holds an inbox item, inbox gate fail-open timeout, maximum inbox hold time, release held inbox items after N minutes.
inboxOverseerGateSlot text string (≤128) Which Overseer runs the inbox gate. Leave it blank (the default) to use the global Overseer; otherwise give a slot id or a crew entry id (crew:<uuid>) naming the agent that screens your inbox. Synonyms: which overseer gates my inbox, inbox gate overseer slot, pick the inbox overseer, inbox gate agent, assign the inbox gate.
inboxReviewClockEnabled toggle true | false Have the app itself track each inbox-review round, re-run a round an agent never finishes, and build the periodic digest from its own record. On by default; off restores the old behavior where a round goes unrecorded.
insightsGroupCollapsed toggle true | false Whether the Insights sidebar group (Stats, Shares) is collapsed. Collapsed by default.
isolationDefault toggle true | false Whether a NEW session starts isolated by default — running against its own copy of the project on its own branch instead of the shared project folder, so two sessions running at once cannot overwrite one another. Off by default. This is the app-wide default only: a project can carry its own (Edit Project, More options, Isolate new sessions), and any single session can override it at launch by holding the + button and toggling Isolate. It applies to the sessions you start next, never to the ones already running. See the Session isolation page for where that copy lives and how the work comes back.
isolationFallbackDir text string (≤500) Absolute path to a fallback folder used only when requireWorktreeIsolation is on AND creating a git worktree fails. Instead of erroring or touching your main repo, the session runs from a plain source copy at <fallbackDir>/<sessionName>-<sessionId>/. Empty (the default) means there is no fallback — the session simply errors when a worktree cannot be made. Synonyms: isolation fallback directory, worktree fallback path, scratch copy folder, safe place to run when worktree creation fails.
jobMonitorEnabled toggle true | false Show the Job Monitor row in the sidebar, a read-only test and build dashboard. The background tracking runs either way. On by default.
leadCardQuietReRaiseEnabled toggle true | false When on (the default), a crew lead reporting the same picture again does not pull back a card you already put away or read: the newest words are written onto that card in place and it stays archived, or stays read, so your inbox stops re-popping it every few minutes. It comes back unread only when the new card asks you something, asks you to decide, offers an Unblock, carries a Heads up, or brings news that is worse than what you already had. Turn it off to get every reappearance back as a fresh unread card, exactly as before. Synonyms: card keeps coming back, archived crew card reappears, stop lead cards re-popping, unread again after archiving, quiet re-raise.
leadCardRoutineHoldEnabled toggle true | false When on (the default), a crew lead's routine progress card — one whose Plain Speak card says Wait or Archive, asks nothing and names nothing wrong — is kept as the lead's Latest and counted on its crew's Dashboard instead of arriving in your inbox. Questions, decisions, results and bad news always reach you. Turn it off to get every lead update in your inbox. Synonyms: routine crew updates, hold overseer updates, fewer lead cards, quiet overseer progress, inbox minutiae, keep lead progress out of inbox.
learnSidebarEnabled toggle true | false
learningEnabled toggle true | false In-development: agents review finished work in the background, turn hard tasks into skills and facts about you into memories, with checks, approvals and undo; off by default; hidden until shipped.
learningMemoryTransitionHandledAt text string
learningMemoryTransitionNotedAt text string When the one-time "Memory review moved to the Learning Loop" inbox card was shown, as a date and time, or empty when it has not been shown yet. Omniscio writes this itself the first time it starts with Global Memory on and the Learning Loop off, so the card that explains where memory saving went appears once and never again; it is stamped even if the inbox hid the card. Clearing it makes the card eligible to show once more on the next start. It changes nothing about saving or reviewing memories. Synonyms: memory transition card, memory review moved card, global memory moved to learning loop notice, show the memory card again, learning loop memory notice.
linkedReviewSeatComputer text string (≤200)
localTitleModel text string (≤100) Ollama model that names sessions ON THIS MACHINE, ahead of the cloud cascade. '' = off (cloud only). Defaults to the fine-tuned title model rather than off, because the model name IS the switch: a machine that does not have this model installed fails the availability probe and takes the byte-identical cloud path, so shipping it on costs nothing and saves the one person who DOES have it from a setup step. A local title never leaves the machine and never bills. Local output is validated against the built-in prompt's own rules and falls through to the cloud cascade on ANY miss.
machineLifecycleV2Modes object object { agent37: "off" | "shadow" | "on"; box: "off" | "shadow" | "on"; google: "off" | "shadow" | "on" } HOW FAR MACHINE LIFECYCLE V2 MAY GO, PER MACHINE PROVIDER. shadow (the shipped default) lists and records what ML2 would do and deletes nothing; on lets ML2 own the provider's lifecycle, which only takes effect once that provider's old deleter has been switched off; off excludes the provider from ML2 entirely. Each provider moves independently, so the three can be promoted one at a time.
maxSessionsPerProject number integer 1..1000 Retired — the per-project session cap was removed on 2026-08-25; this value is kept only for config compatibility and nothing enforces it. Omniscio no longer limits how many sessions a project can run. Synonyms: max sessions per project, session limit per project, cap sessions per project, maximum concurrent sessions, project session cap, limit how many sessions a project can run.
mcApprovalColumnEnabled toggle true | false In-development: an approval column type for Mission Control boards. Items can be approved or rejected by team members, with configurable thresholds and rejection modes. Hidden until shipped.
mcNavDashboardsVisible toggle true | false Whether the Dashboards section shows in the Mission Control sidebar. On by default, like every other sidebar category. Change it in Settings under Mission Control, Sidebar Categories, or on the Sidebar card of Mission Control's own Settings page. Synonyms: show dashboards in the sidebar, hide the dashboards section, Mission Control sidebar categories.
mcNavDocumentsVisible toggle true | false Whether the Documents section shows in the Mission Control sidebar. On by default, like every other sidebar category. Change it in Settings under Mission Control, Sidebar Categories, or on the Sidebar card of Mission Control's own Settings page. Synonyms: show documents in the sidebar, hide the documents section, Mission Control sidebar categories.
mcNavFormsVisible toggle true | false Whether the Forms section shows in the Mission Control sidebar. On by default, like every other sidebar category. Change it in Settings under Mission Control, Sidebar Categories, or on the Sidebar card of Mission Control's own Settings page. Synonyms: show forms in the sidebar, hide the forms section, Mission Control sidebar categories.
mcNavGoalsVisible toggle true | false Whether the Goals section shows in the Mission Control sidebar. On by default, like every other sidebar category. Change it in Settings under Mission Control, Sidebar Categories, or on the Sidebar card of Mission Control's own Settings page. Synonyms: show goals in the sidebar, hide the goals section, OKRs in the sidebar, Mission Control sidebar categories.
mcNavPortfoliosVisible toggle true | false Whether the Portfolios section shows in the Mission Control sidebar. On by default, like every other sidebar category. Change it in Settings under Mission Control, Sidebar Categories, or on the Sidebar card of Mission Control's own Settings page. Synonyms: show portfolios in the sidebar, hide the portfolios section, Mission Control sidebar categories.
mcNavProjectsVisible toggle true | false Whether the All Projects section (your project boards) shows in the Mission Control sidebar. On by default. Change it in Settings under Mission Control, Sidebar Categories, or on the Sidebar card of Mission Control's own Settings page. Synonyms: show projects in the sidebar, hide all projects, boards list in the sidebar, Mission Control sidebar categories.
mcNavSpreadsheetsVisible toggle true | false Whether the Spreadsheets section shows in the Mission Control sidebar. On by default, like every other sidebar category. Change it in Settings under Mission Control, Sidebar Categories, or on the Sidebar card of Mission Control's own Settings page. Synonyms: show spreadsheets in the sidebar, hide the spreadsheets section, Mission Control sidebar categories.
mcNavVisibilitySeeded toggle true | false Whether Mission Control has already switched on the sidebar categories you were using when the Sidebar Categories picker arrived. It runs once, the first time the sidebar loads without an error, and only ever turns categories on. Not a switch you change yourself. Synonyms: sidebar categories seeded, first-run sidebar setup.
mcOmniPanelCollapsed toggle true | false Remembers whether the AI Project Manager side panel in Mission Control is collapsed to a thin rail or open. It starts collapsed by default, and the app updates it when you expand or hide the panel. Synonyms: project manager panel collapsed, side panel open or closed, hide AI panel, mission control panel state.
mcOmniPanelWidth number integer 300..640 Remembers how wide you dragged the AI Project Manager side panel in Mission Control. The width is kept between 300 and 640 pixels and starts at 380. Dragging the panel's edge saves the new width. Synonyms: project manager panel width, side panel size, resize AI panel, panel width pixels.
mcTasksSidePanelCollapsed toggle true | false Whether the Mission Control tasks side panel is collapsed.
mcTasksSidePanelColorMode select "system" | "light" | "dark" The light/dark/system theme for the Mission Control Tasks side panel specifically (default 'system' — follows the app's dark-mode state). Set with the sun/moon icon inside the Tasks side panel itself, not a Settings-page control.
mcTasksSidePanelWidth number integer 240..500 Width in pixels of the Mission Control tasks side panel (240–500).
mcpServersSidebarEnabled toggle true | false Show the MCP Servers row in the sidebar. On by default.
memoryDistillerDailyCapUsd number number 0..1000 Global Memory — the daily US-dollar cap on the session-end memory distiller LLM spend (0 = disabled). Default 1. The distiller runs automatically at session end and calls a lightweight AI model (Haiku) to extract durable memories; this cap bounds the total charged per day per account so background distillation never drains your budget. Set it to 0 to disable the cap entirely, or raise it if you run many long sessions and want more memories extracted per day. Synonyms: memory distiller cap, memory distiller budget, daily memory spend, global memory cost cap.
memoryDistillerModel select "haiku" | "sonnet" | "opus" | "luna" | "off" | "deepseek-v4-flash" The model the Global Memory session-end distiller uses to extract memories from a finished session — for A/B-testing summarization quality across models. Haiku (the default), Sonnet, Opus, DeepSeek V4 Flash, or GPT-5.6 Luna. Agent/CLI-only (set it over the CLI); there is no UI toggle. Synonyms: memory distiller model, memory summarizer model, which model writes memories, global memory model.
memoryRetentionDays number integer 0..3650
messageVirtualizationEnabled toggle true | false Only draw the messages on screen in very long conversations to keep them fast. Applies to the legacy flat message list.
messageVirtualizationThreshold number integer 50..1000 How many messages a conversation must reach before on-screen-only drawing turns on (50 to 1000).
missionBoardActsOnItsOwn toggle true | false
missionBoardEnabled toggle true | false
missionBoardIntervalHours number integer 1..12
missionBoardSeats list array of string (≤120)
missionControlEnabled toggle true | false
missionControlInviteCheckedAt text string (≤40) Records the time the app checked once for a waiting Mission Control team invitation for you. After a check gets a final answer, it is not repeated. Empty by default, which means the check has not finished yet. Synonyms: pending invite check, team invitation lookup, mission control invite checked, invite already checked.
missionCoreEnabled toggle true | false
missionDocsRepositoryEnabled toggle true | false
missionLoopEnabled toggle true | false
missionOverseerEngine object object { model: string (≤100); provider: "claude" | "codex" | "gemini" | "antigravity" | "deepseek" | "kimi" | "glm" | "minimax" | "meta" | "qwen" | "openrouter" | "cursor" | "hermes" | "grok" | "gpt" | "xai" | "pi" | "opencode" | "terminal" | "devin" | "grokbot" | "reason" | "kimicode" | "dsh" | "musecode" | "acp" | "ultramarine" | "t3code" | "crofai" | "deepinfra" | "geminicc" | "runinfra" | "inferx" | "venice" | "abliteration" | "engy" | "refuseless" }
missionTaskTreeEnabled toggle true | false
missionsSidebarEnabled toggle true | false When on (the default), the sidebar shows the Missions row. Turn it off to hide just that row. This is the row's own visibility gate, separate from the Missions feature itself — hiding the row does not stop anything running. Synonyms: missions sidebar row, show missions in sidebar, hide the missions row, sidebar missions toggle, missions visibility.
mobileShareTargetEnabled toggle true | false In-development: on your phone, share a screenshot into Omniscio (Android share sheet) or paste it (iPhone), then pick which session it attaches to. Off by default; dev builds only.
moveProjectsEnabled toggle true | false In-development: catch up projects whose folders you moved outside Omniscio. One window finds them all and brings their chats, agents' working copies and saved settings along. Moving project folders from inside Omniscio comes next. Hidden until shipped.
multiplayerSessionsEnabled toggle true | false In-development: invite a teammate into a live session so they can follow the whole conversation in their own Omniscio, reply into it under their own name, and be @mentioned. You choose view-only or can-reply per person and can revoke at any time. Sharing copies that one conversation to your cloud for the people you invite; revoking deletes it. Only the session owner needs a paid plan. Off by default and completely inert until switched on.
multiplayerShareUploadNoticeAcknowledged toggle true | false Internal: remembers you've seen the one-time notice about uploading before sharing. Not a setting to change.
multiplayerTurnOnDismissedShareIds list array of string Remembers which shared-session invitations you already dismissed, so the app does not offer to turn on Multiplayer Sessions for them again. Empty by default and capped to the most recent 500 entries. It is filled in by the app when you dismiss the offer. Synonyms: dismissed multiplayer invites, shared session prompt dismissed, hide turn on multiplayer offer, ignored share invitations.
myAutomationsSidebarEnabled toggle true | false Show the My Automations row in the sidebar. On by default.
needsYouSectionEnabled toggle true | false On by default: when a session's latest message has a section listing what only you can do — "Waiting on you", "Needs you", "What you need to do" and the like — that section glows in a neon frame with a glass "Waiting on you" tab. Older messages, empty sections and "nothing needed" sections stay plain. Turn it off to render every message as before.
notificationHistorySidebarEnabled toggle true | false When on (the default), the sidebar shows the Notification History row — the read-only list of notifications you have already been sent. Turn it off to hide just that row. It sits beside the Notification History feature switch, which is the one that turns the history itself off; this one only controls the sidebar row. Synonyms: notification history sidebar row, show notification history, hide the notification history row, past notifications in sidebar, notification log row.
oneOffCloneAutoArchiveEnabled toggle true | false Automatically archives a one-off clone session once it has delivered its report back to the session that launched it and is waiting for you, and also tidies finished idle clones at startup. On by default. Turn it off to keep these short-lived helper sessions in your list until you archive them yourself. Synonyms: auto archive clones, one-off helper cleanup, close finished clone sessions, tidy helper sessions.
orphanBranchSweepEnabled toggle true | false
outsideMemoryEnabled toggle true | false In development: copy the memories Omniscio has saved to your own Mem0 or Honcho account, and bring what that service knows into memory search as clearly labelled notes. Nothing leaves this computer until you pick a service and give it a key.
outsideMemoryPersonId text string (≤200)
overseerAutoPerProject toggle true | false When on, EVERY project automatically gets its own Overseer watching it, instead of opting each project in one at a time. Off by default, because each one is a real running session that costs money. You can still switch an individual project off while this is on — an explicit per-project choice always wins. Synonyms: overseer for every project, always have an overseer, auto per-project overseer, one overseer per project, automatic overseers.
overseerCloneHandoffEnabled toggle true | false When on (the default), an Overseer may hand its post to a successor on its own: it asks for a standing-peer copy of itself, its session ends, and a fresh session takes over the SAME Overseer, carrying its notes and the reason it handed over. There is still only ever one of that Overseer running. Turn it off and every such request is refused, so the Overseer keeps running as it is; one-off copies of an Overseer are not affected. Takes effect on the next request, with no restart. A built-in guard still refuses more than a few hand-offs in one hour either way. Replaces the old "Copies of itself" limit. Synonyms: overseer hand-offs, let an overseer replace itself, stop overseers restarting themselves, overseer standing peer, overseer clone itself, overseer self clone, turn off overseer succession, overseer copies of itself.
overseerDailyBudgetUsd number number 1..100000 A hard ceiling, in US dollars, on what the Overseer and the swarm it runs may spend in one day across both estates. Reaching it pauses further spend rather than slowing it. Deliberately separate from overseerSpendBreakerMultiplier, which is a ratio-based anomaly detector calibrated on an Overseer working alone — this is the shared dollar ceiling, and the two must not be conflated. Accepts 1 to 100000. Synonyms: overseer daily budget, overseer spend cap, how much can the overseer spend per day, swarm cost ceiling, daily dollar limit for the overseer.
overseerDigestEnabled toggle true | false When on (the default), the crew lead updates that did not interrupt you come back as ONE missions digest card in your inbox — a line per mission that moved, linked to the mission — sent more often when more is moving and never when nothing moved. It stays quiet during your inbox quiet hours. Turn it off to get no digest. Synonyms: missions digest, overseer digest, summary of overseer updates, crew updates summary, rollup of routine updates.
overseerDigestMaxPerDay number integer 1..24 The most missions digests a day when a lot is moving (default 24, about every hour). The more missions move, the closer the digest gets to this. Synonyms: fastest digest, maximum digests per day, overseer digest frequency, digest cap.
overseerDigestMinPerDay number integer 1..24 The fewest missions digests a day while something is moving (default 4, about every six hours). When little moves, the digest waits this long. Synonyms: slowest digest, minimum digests per day, overseer digest frequency, how often the missions digest comes.
overseerEnabled toggle true | false An always-on assistant that guides your agents, watches for patterns, and screens your inbox. Nothing runs until you approve it.
overseerFleetBoardChannelId text string The Team Chat channel id the Overseer posts its fleet-board updates to and reads from each heartbeat round. Empty (the default) means the fleet board is off. An opaque destination id you already picked, not a credential. No Settings-UI control yet; set via CLI/PATCH. Synonyms: overseer fleet board channel, overseer team chat channel.
overseerFleetBoardWorkspaceId text string The Team Chat workspace id paired with overseerFleetBoardChannelId for the Overseer's fleet-board posts. Empty (the default) lets the relay resolve its own workspace. Has no effect unless overseerFleetBoardChannelId is also set. No Settings-UI control yet; set via CLI/PATCH. Synonyms: overseer fleet board workspace.
overseerFreshStartEnabled toggle true | false When on (the default), a crew overseer — or one of its foremen — starts a fresh conversation with a full briefing before its context fills up: it is asked for a hand-off note first, and at the hand-off point (overseerFreshStartTokens, 800,000 tokens by default) the app starts it fresh either way. It keeps its post, cards, schedules and crew. A foreman gets the same fresh start shaped to its own slice, and one switch covers both. Turn it off to let them run until their conversation is compacted. Synonyms: overseer fresh start, foreman fresh start, overseer handoff, succession, context reset, compaction, briefing.
overseerFreshStartNoteAskTokens number integer 20000..2000000 How many tokens of conversation a crew lead may reach before the app asks it, once, to write a hand-off note for whoever takes its post. Raise it to keep a sharp lead in place longer; lower it to have the note written sooner. Always kept below the hand-off point. Range 20,000–2,000,000 tokens; default 700,000. Synonyms: overseer hand-off note, when the lead writes its hand-off, note ask point, context threshold.
overseerFreshStartTokens number integer 20000..2000000 How many tokens of conversation a crew lead may reach before the app hands its post to a brand-new session with the full briefing, whether or not a hand-off was written. The two shipped points (this one at 800,000, the note point at 700,000) were raised on 2026-10-19 because a lead on a 1M-token window was still being replaced at 40% of it; before that they were about 400,000 and 450,000. A session on a smaller window caps each point at the same fraction of its own window, and so does a session whose auto-compact point is lowered, so a hand-off never lands after a compaction. Range 20,000–2,000,000 tokens; default 800,000. Synonyms: overseer fresh start, when the lead is replaced, hand-off point, context reset, succession.
overseerGatekeeperEnabled toggle true | false When on (the default), the Overseer holds new inbox items for the hold window (overseerHoldWindowMinutes) before routing them, screening for noise and spam. Turn it off to let items through immediately without the screening delay. Synonyms: overseer gatekeeper, inbox hold, inbox screening, hold new items, noise filter.
overseerGroups list array of object { collapsed: true | false; id: string (≤64); name: string (≤80); slotIds: array of string (≤128) } The groups you arrange your Overseers into, each with a name, a colour, a folded-or-open state and its members by slot id — so an Overseer keeps its group across the restarts that give it a new session. The group position is not stored here; it rides your single Overseer arrangement so groups and ungrouped Overseers share one order. Arranged on the Overseers hub itself. Synonyms: overseer groups, group my overseers, overseer folders, organise overseers, crew groups, overseer colours.
overseerHandoffEnabled toggle true | false When on (the default), a session an Overseer OWNS hands its finished turn to that Overseer instead of raising it in your inbox — the Overseer reads the report and only brings you what actually needs you. Turn it off to get every finished turn yourself, whoever owns the session. Deliberately separate from overseerGatekeeperEnabled: that one screens ALERT CARDS on their way to you, this one redirects an OWNED AGENT'S REPORT, and you may want one without the other. Only affects sessions an Overseer owns, which happens by explicit assignment or by that Overseer spawning them. Overseer panel → Behaviour. Synonyms: overseer handoff, let the overseer take my agents' reports, stop overseer sessions filling my inbox, route finished turns to the overseer, overseer answers for its sessions, turn off overseer handoff.
overseerHeartbeatMinutes number integer 0..1440 Minutes between each Overseer wake-up (default 15; range 0-1440). Every wake-up is a real paid turn — set this with that in mind. 0 turns cadence wake-ups off entirely. An individual Overseer can set its own pace in the Overseers list, overriding this fleet-wide default. Settings → Overseer → Behaviour → "How often they wake up".
overseerHeldQuestionHoldEnabled toggle true | false When a replaced overseer still holds a question that was queued for delivery, the app hands it to the replacement before filing the old session away, so the question is not lost. On by default. When off, the old session is filed away without that check. Synonyms: lost overseer question, replaced overseer handover, queued question, overseer restart.
overseerHoldWindowMinutes number integer 1..120 How many minutes the Overseer holds a new inbox item before routing it through the gatekeeper screening step (only meaningful when overseerGatekeeperEnabled is on). Range 1–120 minutes; default 10. Synonyms: overseer hold window, gatekeeper delay, inbox hold time, screening window, how long to hold new items.
overseerProjectOverrides map map of string → true | false Per-project override for whether an Overseer runs on that project, keyed by project id (true/false forces it on/off for that one project). A project with no entry here follows the blanket overseerAutoPerProject setting instead. Set via the "Run this Overseer" toggle on each project's Overseer row. Synonyms: per-project overseer, overseer on or off per project.
overseerQuestionSurvivesRestartEnabled toggle true | false When on (the default), a question an Overseer asked you is never lost to its own restart: the app holds a fresh start while that question is still unanswered in your inbox, and on a restart that has to happen anyway the question card follows the Overseer onto its replacement instead of being put away with the old session. Turn it off to let a restart end the session and put the unanswered question away with it, which is how it worked before. Synonyms: overseer question lost, question card archived, unanswered question, overseer restart, question follows the overseer, do not lose my question.
overseerRestartHours number integer 1..168 How many hours between automatic Overseer session restarts. The Overseer periodically restarts to stay fresh and pick up any new instructions. Range 1–168 hours (up to 1 week); default 24. Synonyms: overseer restart interval, how often the overseer restarts, overseer session lifetime, restart every N hours.
overseerSessionAssignments map map of string → string Which Overseer slot is explicitly watching each session, keyed by session id and valued by the assigned Overseer slot id. An explicit assignment here outranks the project-level rule for routing that session; a session with no entry falls back to its project's Overseer. Set via the "Sessions it watches" picker on an Overseer's row, or by CLI/API. Synonyms: overseer session assignment, which overseer watches this session.
overseerSlotOrder list array of string (≤128) Your arrangement of the Overseer list — slot ids in the order they are drawn, most significant first. An id that is not listed sorts after every arranged one and holds its own relative order, so a newly created Overseer lands at the end and never reshuffles a list you already set. Synonyms: overseer order, reorder overseers, arrange the overseer list, overseer slot order, sort my overseers.
overseerSlots map map of string → object { allProjects: true | false; allowedAgentTypes: array of "builder" | "reviewer" | "fixer" | "researcher" | "tester" | "janitor" | "planner" | "auditor" | "first-principles" | "pattern-finder" | "red-teamer" | "triager" | "tool-builder" | "documenter" | "optimizer"; approvedAt: string; autoActions: array of object { agentType: "builder" | "reviewer" | "fixer" | "researcher" | "tester" | "janitor" | "planner" | "auditor" | "first-principles" | "pattern-finder" | "red-teamer" | "triager" | "tool-builder" | "documenter" | "optimizer"; approvedAt: string; id: string (≤64); job: string (≤4000); maxPerHour: integer 1..60; trigger: discriminatedunion }; autoTitle: string (≤80); enabled: true | false; engine: object { model: string; provider: "claude" | "codex" | "gemini" | "antigravity" | "deepseek" | "kimi" | "glm" | "minimax" | "meta" | "qwen" | "openrouter" | "cursor" | "hermes" | "grok" | "gpt" | "xai" | "pi" | "opencode" | "terminal" | "devin" | "grokbot" | "reason" | "kimicode" | "dsh" | "customOpenai" | "customAnthropic" | "acpAgents" | "musecode" | "acp" | "ultramarine" | "t3code" | "crofai" | "deepinfra" | "geminicc" | "runinfra" | "inferx" | "venice" | "abliteration" | "engy" | "refuseless" }; heartbeatMinutes: integer 0..1440; homeProjectId: string (≤128); instructions: string (≤10000); interruptBudgetPerHour: integer 0..100; name: string (≤80); purpose: string (≤2000); reportsToPerson: true | false; routesProjectId: string (≤128) } The name and instructions for each individual Overseer — the global one, each project one, and any you create yourself. Leave the instructions empty and that Overseer runs the built-in stock job description, so turning one on never requires writing a prompt first. For a custom Overseer, creating its entry here is what brings it into existence; you can pause one without losing what you wrote for it. Synonyms: overseer prompt, overseer instructions, custom overseer, name an overseer, multiple overseers, per-overseer prompt, what my overseer does.
overseerSpendBreakerMultiplier number integer 2..50 Multiplier on the user's average session spend that triggers the Overseer's spend breaker: if a session's cost exceeds this multiple of the average, the Overseer pauses further activity until you review it. Range 2–50; default 4 (four times the average). Synonyms: overseer spend breaker, cost multiplier, spend safety, runaway cost protection, pause if spend exceeds N times average.
overseerTagDebugEnabled toggle true | false Developer-only: shows the routing tag an overseer used on each of its messages — card, latest, report, routine or acknowledgement — as a small chip under the message, plus anything the app rejected or later corrected. Every message hides its tag today, so this is the only way to see which one was chosen. Off by default.
overseerTeamIcons map map of string → "crown" | "headset" | "wrench" | "bug" | "rocket" | "shield" | "cloud" | "globe" | "book" | "database" | "palette" | "hammer" | "users"
overseerWorkerReportCardsEnabled toggle true | false When on (the default), a report or question that a session could NOT hand to its Overseer — the delivery was refused or failed — appears in your inbox as one card per session, so nothing an Overseer-owned session says can be silently dropped. A report the Overseer did receive raises no card: it is already being handled, and copying it to you would make the inbox a second reader of every report. The card updates in place with the newest undelivered report and clears itself once the session is answered. Replying on the card sends your words to that Overseer, whichever seat of it is running now. The session itself stays out of Needs You. Synonyms: overseer worker report card, show me what my overseer sessions report, worker reports in my inbox, never drop an overseer report, overseer session questions in inbox.
overseersBoardAddressingEnabled toggle true | false Delivers posts on the shared overseers board to the people they are addressed to, or to thread participants, and lets urgent posts wake the board. On by default. When off, the older broad delivery returns and every post reaches everyone. Synonyms: board addressing, overseers board notices, targeted board posts, urgent board wake.
overseersDigestRidesTurnEnabled toggle true | false Controls how unaddressed, non-urgent overseers board posts reach each crew lead as a digest. On by default, the digest rides along with the lead's next real delivery and never starts a turn by itself. When off, it is delivered at the end of the lead's turn even if nothing else is queued. Synonyms: board digest, overseers digest, digest wake, lead notice delivery.
ownerAssignmentsEnabled toggle true | false In-development: route an incoming bug to a designated owner so it lands on the right person instead of a shared queue. Hidden until shipped.
peerCoordinatorSessionIds list array of string (≤200) Session ids you designate as coordinators. A cross-session message sent TO one of these runs in a separate, larger rate-limit lane instead of the standard one, so one coordinator's fan-in is not starved by routine chatter. Being listed only grants a larger send allowance to the sessions messaging it — it grants no authority over anything.
peerCorrectionReplacesOriginalEnabled toggle true | false When one agent sends another a correction to a message that has not been picked up yet, the correction replaces the original so the receiver gets one message, not two. On by default. Turning it off delivers corrections as ordinary extra messages. Synonyms: agent message correction, replace queued message, peer message fix, avoid duplicate agent messages.
perProjectWorktreeLocationEnabled toggle true | false In-development switch that adds a per-project control for choosing where that project's git worktrees are created, kept private to this machine. Off by default; hidden until released.
perfStatusSidebarEnabled toggle true | false Whether the Performance Status item appears in the sidebar (default on). It is a visibility toggle only — turning it off hides the entry, it does not disable performance monitoring or change anything the app measures. Settings → Sidebar. Synonyms: hide performance status from the sidebar, show perf status, sidebar performance item, remove the perf panel from the sidebar, performance sidebar visibility.
permissionReadNudgeEnabled toggle true | false Adds the setup-time note telling agents to just read files instead of asking for read permission first. On by default.
pipelineAutoAdvanceEnabled toggle true | false Deprecated old option for automatically advancing the dev pipeline. Kept only so older saved settings still load; the app no longer writes it.
pipelineAutoApprovePlanGate toggle true | false Deprecated old option for automatically approving the dev pipeline's plan step. Kept only so older saved settings still load; the app no longer writes it.
pipelineGateAutoApprove object object { build: true | false; docs: true | false; elegance: true | false; plan: true | false; redTeam: true | false } Per-gate auto-approval for the dev-pipeline: one switch per gate (Plan, Red Team, Build, Elegance, Docs) saying whether Omniscio clears it itself the moment a phase reports done, or always waits for you. Plan asks you by default; the other four auto-clear by default. A gate that asks a real question or reports a blocker is never auto-approved whatever its switch says. Set it in Settings → Optional Features or the Dev Pipeline panel — both bind the same map. Synonyms: gate auto approval, auto approve gates, skip the gate click, which gates ask me, dev pipeline gates automatic.
pipelineGateAutoContinue object object { build: integer 0..1440; docs: integer 0..1440; elegance: integer 0..1440; plan: integer 0..1440; redTeam: integer 0..1440 } How many minutes a Development Pipeline approval gate may sit unanswered before a timer carries the run past it, set per gate (plan, red team, build, elegance, docs). Ships at 30 minutes on gates 2-5 and 0 on Plan, so a stalled mid-pipeline gate continues after half an hour while GATE 1 stays manual; an absent key takes that default, a saved value wins, and setting a gate to 0 keeps it off explicitly. For a team that wants long runs to keep moving without a waiting gate. Synonyms: pipeline gate auto continue, auto pass a gate after a delay, keep pipelines moving, gate timeout minutes, auto-approve a stalled gate.
pipelineStandardsGateAutoApprove object object { retrospective: true | false; scout: true | false; standards-audit: true | false; standards-check: true | false } Per-gate auto-approval for the two bundled standards gates (the Standards Check and the Standards Audit), on the same footing as pipelineGateAutoApprove. Absent means automatic, resolved from the gate's own default, so a gate you have never touched behaves the way it always has. Synonyms: standards gate auto approve, standards check automatic, standards audit automatic, bundled standards gates.
pmAgentTrustEnabled toggle true | false Agent trust levels, approval gates, progressive trust, and enriched activity timeline for Mission Control boards.
pmBoardChecklistAnswers unknown pipeline Boards with their own Customize choices: board id to the setup-checklist boxes ticked for that board only. A board not listed follows your default (the setup checklist answers). Set from Mission Control Settings, How you work, Customize, one board; Reset to my default removes the board. Synonyms: board features, per-board features, customize a board, only this board.
pmCommentVisibilityEnabled toggle true | false Internal vs external comment visibility for Mission Control items. Team members can discuss items internally, then selectively share comments with external stakeholders. Comments default to internal (team-only); individual comments can be toggled to external. Role-based filtering ensures viewers see only external comments.
pmComposabilityEnabled toggle true | false Validates feature interactions before enabling or disabling PM features. Checks prerequisites, warns about behavior changes, and provides a 30-day undo window.
pmConnected toggle true | false Internal remembered flag for whether the Mission Control / Project Management integration is currently connected (signed in and syncing PM boards). Default true; set by the PM auth/sync layer — it reflects live connection state, not a user preference. Synonyms: PM connected, mission control connected, project management sync status.
pmDismissedHelpTips list array of string (≤200) The Mission Control help tips you have dismissed, so they do not show again.
pmDismissedNudges list array of string (≤200) The Mission Control nudges you have dismissed, so they do not show again.
pmDocumentsEnabled toggle true | false Document, spreadsheet, and form entities in Mission Control — each with its own sidebar section, list page, and detail page, stored per workspace alongside boards and dashboards. On by default; the toggle stays live so you can turn it off with one setting flip.
pmFeatureProfilesEnabled toggle true | false PM Feature Profiles
pmFeedSignificanceWeights object object { maxRecencyBoost: number; mentionBoost: number; mutedBoardPenalty: number; promotedBoardBonus: number; tierCritical: number; tierImportant: number; tierNotable: number } Advanced override for the PM Unified Feed's ranking weights — the promoted-board bonus, muted-board penalty, mention boost, max recency boost, and the critical/important/notable tier thresholds. null (the default) uses the built-in weights. A power-user/debug escape hatch; no Settings-UI control, set via CLI/PATCH.
pmHomeBeaconActive toggle true | false Internal state flag for whether the Project Management "home beacon" is currently active — the attention indicator the PM home entry point uses to draw you to the PM home surface. Default false; managed by the PM home flow, not a user preference. Synonyms: PM home beacon, mission control home beacon, PM home indicator.
pmInboxBoardPreferences unknown pipeline Retired per-board Inbox choices from the old Settings dropdowns. Read once and folded into the per-board Mission Control mute list (None stays muted, Assigned to me only caps the board at Involves me), then emptied. Not a user control.
pmItemHistoryEnabled toggle true | false Full change history timeline on PM board items with quick undo (Ctrl+Z), point-in-time rollback, actor provenance (human/agent/automation), and session-linked audit trail.
pmMatchOmniscioTheme toggle true | false Makes Mission Control use your Omniscio theme's accent color instead of its own brand color. Off by default, so Mission Control keeps its own look. Turn it on if you want it to blend in with your chosen theme. Synonyms: mission control accent color, match app theme, use my theme colors, project board theme.
pmOnboardingBoardCreated toggle true | false Remembers that onboarding created your first Mission Control board.
pmOnboardingCheckedItems list array of string (≤200) The Mission Control onboarding checklist items you have ticked.
pmOnboardingComplete toggle true | false Set once you finish the Mission Control onboarding help checklist.
pmOnboardingHelpEnabled toggle true | false In-development: preset-scoped onboarding checklist, contextual help tips, scoped help search, and one-click escape to AI sessions with PM context. Hidden until shipped.
pmPersonaBAspirationEnabled toggle true | false The setup checklist that picks the Mission Control setup lane (Quick start, Guided setup, or Build with Omni) from what the user ticks. On by default for new users.
pmPersonaCImportEnabled toggle true | false First-run entry screen for Mission Control: asks whether the user has data in another tool, and its starting-fresh choice opens the setup checklist. On by default for new users.
pmPostImportHomeDismissedAt text string When you last closed the Mission Control home screen that greets you after an import, so it only shows projects you imported since.
pmPostImportHomeEnabled toggle true | false After you import projects from another tool or a file, Mission Control Home shows the projects you brought in and one useful observation about them.
pmPrdTaskBoardWorkspaceId text string (≤200)
pmProjectSetupHabits object object { last: object { automationLevel: "hands-on" | "balanced" | "automated"; checkInCadence: "daily" | "twice-weekly" | "weekly" | "biweekly" | "as-needed"; taskTracking: "mc" | "tasks-v2" | "both" | "neither"; usesVault: true | false }; setupsDone: integer 0..∞ } How many project setups Omni has built for you, and the choices you made on the last one (where to track tasks, how hands-on you want it, how often to check in, and whether you use a vault), so the next setup can start from "same as last time?".
pmRoleEntryPointsEnabled toggle true | false In-development: multi-lane onboarding with quick-pick, guided setup, and AI-driven deep interview. Maps AI comfort and organizational role to a default workspace configuration. Hidden until shipped.
pmSavedViewsEnabled toggle true | false Private, per-user saved views on Mission Control boards. A saved view is visible only to the person who created it, separate from the shared team views everyone else on the board sees.
pmSelectedImportPlatforms list array of string (≤200) The outside tools (like Asana) you chose to import your work from during Mission Control setup.
pmSetupAspirationAnswers list array of string (≤64) The boxes you ticked on the Mission Control setup checklist ("In your perfect world..."), so redoing the checklist opens with them already ticked. Only the box ids are kept, never anything you typed.
pmSetupChecklist list array of string (≤200) The features you picked during Mission Control setup.
pmSetupChecklistBoardId text string (≤200) Internal pointer to the PM board Omniscio auto-created for your setup checklist. App-written when the checklist board is created; not user-set.
pmSetupChecklistChosen toggle true | false Whether you have saved your Mission Control setup checklist at least once. Once set, unticking every box keeps every box unticked instead of bringing back the starting defaults.
pmSetupChecklistItemMap unknown pipeline Internal lookup mapping each onboarding checklist step to the concrete PM item id on your auto-created setup-checklist board, so "launch AI on this step" can jump straight to it. App-written when the checklist board is created; not user-set.
pmSetupComplete toggle true | false Set once you finish the Mission Control setup wizard.
pmSetupLane select "quick-pick" | "interview" | "deep-session" Which setup path you took in Mission Control: quick-pick, interview, or deep-session.
pmSetupOrgRole select "tasks" | "team" | "department" | "engineering" The role you chose during Mission Control setup: tasks, team, department, or engineering.
pmSetupResume object object { cardShows: integer 0..∞; checkedIds: array of string; dismissedVisit: integer -1..∞; dontAsk: true | false; freeText: string (≤500); guidedSteps: map of string → object { data: map of string → unknown; status: "pending" | "completed" | "skipped" }; lastCardVisit: integer -1..∞; lastVisitAt: number; reason: "later" | "partial"; sampleBoardId: string; sampleCreatedAt: number; startedVisit: integer 0..∞; step: "import" | "checklist" | "guided"; visits: integer 0..∞ } Stores where you left off in Mission Control setup, such as which step you reached, items you checked, notes you typed, and how many times you have seen the reminder. It lets setup pick up again later. Starts empty, and the app manages it. Synonyms: finish setup later, mission control setup progress, resume setup, setup reminder state.
pmSetupWizardEnabled toggle true | false Onboarding interview and preset picker shown when Mission Control is first enabled. Asks four questions (AI comfort, role, feature needs, free text) and recommends a preset (Tasks, Projects, Operations, or Engineering).
pmSyncStaleThresholdMs number integer 30000..∞ How old (in milliseconds) a PM board's data may get before it is re-synced, while you are NOT connected via the realtime websocket (default 300000 = 5 minutes; minimum 30000). No Settings-UI control yet; set via CLI/PATCH.
pmSyncStaleThresholdWsActiveMs number integer 60000..∞ How old (in milliseconds) a PM board's data may get before it is re-synced while a realtime websocket connection is active (default 900000 = 15 minutes; minimum 60000) — longer than pmSyncStaleThresholdMs since a live connection already keeps data fresh. No Settings-UI control yet; set via CLI/PATCH.
pmSyncTickIntervalMs number integer 30000..∞ How often (in milliseconds) the scheduled 'PM Board Sync' job ticks (default 300000 = 5 minutes; minimum 30000). No Settings-UI control yet; set via CLI/PATCH.
pmTeamId text string The Mission Control team you have chosen to work in. When set, the app sends it with Mission Control requests so you see that team's boards. When empty, which is the default, your home team is used. It is cleared if you are no longer a member. Synonyms: mission control team, selected team, active workspace team, switch team.
pmWhatNextEnabled toggle true | false A home-page card that answers "what should I do next?" with one pick, two backups and who you are waiting on, each with its evidence. Board fixes only after you say yes; nudges are drafts you send.
prMergeQueueAiSummariesEnabled toggle true | false AI ONE-LINE SUMMARIES — OFF by default (false). When true, the queue generates a plain-English one-sentence summary of each open PR during refresh and shows it as the pill headline (falling back to the PR title while one is still generating or if the AI call fails). Cached per PR head SHA in pr_merge_queue_summaries, so each PR is summarised once per head. Off → zero AI calls; pills show #num · <title>. Title + description + changed-file list are sent to the configured lightweight AI provider.
prMergeQueueAutoBatchEnabled toggle true | false AUTO-BATCH — when true, the auto-merge daemon combines several eligible (fast-lane, non-overlapping, this-shard, not-in-flight) PRs into ONE merge session that applies them together and runs the gate ONCE, instead of one session per PR — cutting the duplicated test/build cost. Default true (ON, so a box that enables auto-merge pays the fixed per-PR spawn + gate cost once per group); an explicit false restores one-PR-per-tick behavior. Only NON-overlapping PRs are grouped (their file sets are disjoint), so the single gate run is trustworthy.
prMergeQueueAutoBatchMaxSize number integer 2..32 Max PRs the daemon packs into one auto-batch session. Default 8 (range 2-32). A batch may be smaller if fewer non-overlapping PRs are available this tick. Only meaningful when prMergeQueueAutoBatchEnabled is true.
prMergeQueueAutoMergeEnabled toggle true | false AUTO-MERGE DAEMON — master gate. When true AND a repo's trustLevel === 'autonomous', the daemon will automatically spawn merge sessions for fast-lane PRs without human approval. Default false (off by default; users must opt in explicitly through a confirmation modal in Settings).
prMergeQueueDailyBudgetUsd number number 0..100 Daily-spend budget cap in USD for daemon-initiated merge sessions. Default 5.00. Range: 0–100. A value of 0 switches autonomous spawning OFF entirely (dry-run logging still runs) — it is a spending STOP, never an unlimited ceiling. Queried per-repo as the summed metered cost of the daemon's OWN merge sessions (pr_merge_queue_runs → sessions), never api_cost_log — a merge session's spend is metered onto its sessions row, which is what made the old api_cost_log query silently inert. The boundary is TODAY: the shared sessionSpendTodayWindow day delta (cost_micro_usd - cost_micro_usd_day_start, over sessions whose cost_day_start_iso names the local day the cost writer stamps), the one read every other daily spend cap in the app already uses.
prPushbackEnabled toggle true | false Push-back's own switch. It publishes to GitHub only together with the main-computer role, the sync and the lease, so this alone does not push anything. Off by default, and reserved to a person. Synonyms: pr pushback, push back to github, enable pushback, publish pull requests back, pushback switch.
prStandingConsentEnabled toggle true | false
prdHandoffBuildMode select "pipeline-gated" | "pipeline-auto" | "build-test-land"
prdStudioSidebarEnabled toggle true | false Shows or hides the PRD Studio entry in the sidebar, the AI Tools panel where an interview turns an idea into a product requirements document. One of the per-section sidebar visibility toggles; on by default, turn it off to remove PRD Studio from the sidebar. Synonyms: prd studio sidebar, product requirements document, show/hide prd interview panel.
productivityCollapsed toggle true | false Whether the Productivity sidebar group is collapsed. Collapsed by default.
programHandoffSessionGrant list array of string (≤128) Holds the short list of sessions (up to eight, most recent kept) that you allowed to hand a program off to Windows for just that one session. The app fills it in when you click the allow-for-this-session choice on a handoff approval card. It is empty by default and cannot be changed by agents. Synonyms: allowed handoff sessions, program handoff permission, per-session program approval, session grant.
programLaunchEnabled toggle true | false Lets agents ask the app to launch a program on your computer. On by default. Turn it off to refuse every program launch request and to stop telling agents that launching programs is available. Synonyms: program launch, launch apps, open programs from agents, app launcher switch, run programs.
projectDefaultRunLocations map map of string → any | "auto" Per-project override of defaultRunLocation (projectId → 'local' | 'cloud' | 'auto') — the hint's "Only this project" scope. A project entry beats the Everywhere value.
projectPauseAndSpendEnabled toggle true | false
projectSshFolders map map of string → map of string → string (≤1024)
promptToolsCollapsed toggle true | false Whether the Prompt Tools sidebar group (Super Prompts, prompt creator, bake-off, clean room) is collapsed. Collapsed by default.
quickRepliesBuiltinSeeded list array of string (≤200) Internal bookkeeping: the built-in quick replies this computer has already been offered once, so the app never re-adds one you deleted. Not a setting to change.
quickRepliesSidebarEnabled toggle true | false Show the Quick Replies row in the sidebar. On by default.
readyAskJudgementEnabled toggle true | false When a crew member tells its lead a branch is READY, the app checks that a recent ready check exists for that exact version and has no blockers. If not, the message is refused. On by default. When off, such messages go through unchecked. Synonyms: ready check, ready claim, branch ready message, ready receipt.
regimeStatusSidebarEnabled toggle true | false Shows or hides the Test Regime Monitor entry in the sidebar — the developer-tools dashboard for the end-to-end merge-gating + cloud-testing regime status. One of the per-section sidebar visibility toggles; on by default, turn it off to remove Test Regime Monitor from the sidebar. Synonyms: test regime monitor sidebar, gate and cloud status panel, show/hide regime dashboard.
remoteMachinesEnabled toggle true | false Add your other Omniscio computers by their Tailscale name and see their sessions here, grouped by computer. Turn it on on both computers: until it is on there, that computer answers no pairing or identity request.
repoFoundationsPanelEnabled toggle true | false Repo Foundations
repoFoundationsSkillEnabled toggle true | false Install the Repo Foundations skill. On by default (existing installs were switched on automatically).
repoPipelinePackEditorEnabled toggle true | false A "Your pipeline" screen in Dev Pipeline → Setup that shows a repo’s own committed pipeline and lets you change it in place — start from a preset, rename, move, un-stop or remove a step, or add a custom step with commands that must pass and file patterns that decide whether it runs. Saves the repo’s pipeline file after a change check; it never commits.
requireWorktreeIsolation toggle true | false When on, a session whose git worktree could not be created is stopped with an error instead of silently falling back to run inside your main project checkout — so an agent can never edit or commit to your shared project tree when isolation fails (for example under heavy load). Off by default for backward compatibility; turn it on if you rely on worktree isolation as a safety net. Pairs with isolationFallbackDir, which (when set) runs a source copy in a safe scratch folder instead of erroring. Env kill switch: AMC_DISABLE_REQUIRE_ISOLATION=1 (a developer from-source run only — an installed build ignores it). Synonyms: require worktree isolation, fail-closed isolation, never run in the main repo, keep agents off my project folder.
reviewLoopRoundCap number integer 2..20 Sets how many review rounds a session can go through after your last message before it stops and asks for you. The default is 5, and you can choose from 2 to 20. It only applies while the review-loop breaker is on. Synonyms: review rounds limit, review loop cap, rounds before pausing, stop endless reviews.
runningJobsSidebarEnabled toggle true | false Shows the Running jobs entry in the sidebar's System group, which opens the job monitor for builds and tests that are currently running. On by default. Turn it off to hide the entry from the sidebar. Synonyms: running jobs, job monitor sidebar, show jobs row, background jobs list.
scheduledMessagesSidebarEnabled toggle true | false Show the Scheduled Messages row in the sidebar. The feature and its inbox delivery still work when the row is hidden. Off by default.
scratchpadsSidebarEnabled toggle true | false Show the Scratchpads row in the sidebar. Off by default; the scratchpad is still reachable from its toolbar button and shortcut.
sessionForensicsEnabled toggle true | false A developer-tools panel that mines your past agent sessions for friction patterns — command timeouts, hook blocks, tool errors, redundant directory changes, and spend concentration — via a free periodic scan. An opt-in WEEKLY deep run spawns a paid AI session to produce a full analysis report with ranked fixes.
sessionForensicsSidebarEnabled toggle true | false Show the Session Forensics row in the sidebar. On by default.
sessionHandoffEnabled toggle true | false Roll a long session over into a fresh one that is already caught up — a "Hand off to a fresh session…" item in the session ⋯ menu, plus a one-per-session in-chat note once a chat has used a lot of context, and the same actionable note at a context give-up. The note never spends; only confirming the handoff pays for the one summary call.
sessionHealthMonitorEnabled toggle true | false In-development: detect sessions stalled mid-task, classify via LLM, and auto-recover with context-aware nudges. Hidden until shipped.
sessionHealthMonitorSkipPipelineComplete toggle true | false When the session health monitor is on, don't flag a session that's waiting simply because its dev pipeline just finished.
sessionNamingMode select "ai_title" | "first_prompt" | "session_number" How new session names are chosen: an AI-written title, the first prompt, or the session number.
sessionRecallEnabled toggle true | false In development: agents can search this project's past sessions for how something was done before — the matching lines with passwords and keys hidden, plus a short summary of the closest sessions. Nothing from other projects, and nothing from sessions started by email, an intake, another agent or an automation.
sessionRefillDailyMaxRevives number integer 1..5000 Session Refill Governor — hard backstop on the number of sessions it may revive per local day regardless of cost, bounding absolute worst-case spend. Default 200 (range 1–5000). Synonyms: daily revive cap, refill max revives per day, session refill daily ceiling.
sessionRefillEnabled toggle true | false In-development: a per-user background governor that keeps X sessions running — when the live running count drops below your target it revives recently-active interrupted work sessions back up to X every ~5 minutes. Reuses the existing revive + spawn-pacing path; bounded by a per-tick batch cap, per-session cooldown, a restart-safe daily $ ceiling, and a daily revive-count backstop. It spends money autonomously and is cost-capped. Off by default; hidden until shipped.
sessionRefillExcludeNamePatterns list array of string (≤200) Session Refill Governor — case-insensitive regex name patterns that EXCLUDE a session from revival, so generic shells and outward-facing intake are never brought back. Defaults exclude names like "^Session 1", "[BUG]", "[FEEDBACK]", "Email:", and "Tweet:". Synonyms: exclude session names, never revive these, refill exclusion patterns, don't revive.
sessionRefillIncludeProjectNamePatterns list array of string (≤200) Which projects the Session Refill governor is allowed to restart sessions in, as a list of case-insensitive patterns matched against the project name. Empty (the shipped default) means every project. Once you set it the list FAILS CLOSED: a session must match one of your patterns or it is left alone — so a renamed project, or a list whose patterns are all invalid, restarts nothing rather than quietly widening back to everything. It exists because the governor previously had no notion of a project at all and would pick up whatever happened to be interrupted, across every project at once. Synonyms: limit session refill to a project, which projects can be auto-restarted, session refill project allow list, restrict the refill governor by project name, only revive sessions in these projects.
sessionRefillNudgeText text string (≤2000) Session Refill Governor — the "continue" message sent to a revived session, e.g. "Please continue where you left off and finish the task." (default). Synonyms: revive nudge text, continue prompt, refill message.
sessionSearchSidebarEnabled toggle true | false Show the Session Search row in the sidebar. On by default.
sessionSelfArchiveEnabled toggle true | false Master switch for session self-archiving. On (default): a finished agent session may archive itself off your board once it decides nothing is left for you to see, decide, or receive (it emits a self-archive marker at the end of its turn). Off: that marker is ignored and every session stays on your board until you archive it yourself. This kill-switch overrides sessionSelfArchiveWithoutApproval.
sessionSetupPresets list array of object { icon: string (≤16); id: string (≤100); name: string (≤60); setup: object { customProviderId: string (≤100); location: "local" | "cloud"; mcpOverrides: map of string → true | false; model: string (≤100); provider: string (≤64); route: string (≤64); thinkingLevel: string (≤32) }; updatedAt: string (≤40) } Your saved session setup presets — named sets of new-session picks (harness and provider, model, thinking level, run location Local or Cloud, and MCP servers), each with an optional icon. Pick one from the Preset menu at the top right of a new session's Session setup card (or press Alt+P, then 1-9) and every chip is set at once; nothing starts until you send. Save, update, rename and delete them from that menu. Synonyms: session presets, setup presets, new session presets, saved model setups, launch presets, quick setups, chip presets.
sessionSetupPresetsEnabled toggle true | false Saved presets on the new-session Session setup card: one pick sets the harness, provider, model, thinking level, run location and MCP servers. One preset can be the default for every new session.
sessionSupervisorEnabled toggle true | false Run a cloud session's agent UNDER the box-side supervisor, so its running turn outlives the connection that started it — the thing that makes a disconnect, a crash or an app restart cost you nothing. On by default, deliberately. Off is a real state, not a degraded mode: every remote command returns to the direct exec claude form, byte-for-byte. READ AT SPAWN TIME, so it applies to the NEXT launch with no restart — which is the whole point of it being a switch rather than a build flag.
sessionTitleAppendPrompt text string (≤10000) Free-form text describing how AI-generated session titles should be written, appended BELOW the built-in title prompt (whose rules always win) for EVERY project. A per-project Project.sessionTitleAppendPrompt stacks AFTER this, so the narrower scope wins a conflict. Only consulted in ai_title naming mode — the other modes never call the model. '' = none, and empty at both levels reproduces pre-feature titling byte-for-byte.
sessionTitleCustomPrompt text string (≤10000) User-written prompt that replaces the built-in title prompt when sessionTitleStyle === 'custom'. Ignored for other styles.
sessionTitleCustomRefresh toggle true | false Allow refreshing a session's AI title using your custom title prompt, for the custom title style.
sessionTitleStylesEnabled toggle true | false Choose how AI-generated session titles are written with five presets (Brief, Descriptive, Journey, Latest Topic, Custom). Journey and Latest Topic auto-refresh as the conversation evolves. Off by default; hidden until shipped.
settingsSidebarEnabled toggle true | false Show the Settings row in the sidebar. On by default.
skillsTrustedSourceAcknowledged toggle true | false Internal flag: turns on after you accept the one-time warning about where skills come from. Not a setting to change.
sshHostEnvironmentsEnabled toggle true | false Open a saved SSH remote as a whole place: whether it can be reached, the projects with a folder there, its sessions, its files and git read-only, and a terminal. Uses the same trust rules as remote sessions.
stallThresholdSeconds number integer 30..3600 How long a session may go silent with no output before it's marked stalled, in seconds (30 to 3600).
statsSidebarEnabled toggle true | false Show the Stats row in the sidebar. On by default.
stickyNotesOverlayOpen toggle true | false Remembered open/closed state of the Sticky Notes overlay, persisted to config.json so the overlay reopens (or stays closed) after a hard reload or app restart — the durable backstop to the instant localStorage flag the overlay reads on first paint. Written automatically whenever you open or close the overlay; it is not a Settings-UI toggle (the on/off feature switch is stickyNotesEnabled). Optional — undefined until you first open or close the overlay. Synonyms: keep sticky notes open after restart, remember sticky notes overlay visibility, sticky notes stay open, persist sticky notes open state.
submitKeyMode select "enter" | "ctrl_enter" Which key sends a message in the session composer: Enter, or Ctrl+Enter (so Enter makes a new line).
superPromptCreatorSidebarEnabled toggle true | false Shows or hides the Super Prompt Creator entry in the sidebar — the prompt-tools helper for building a reusable "super prompt". One of the per-section sidebar visibility toggles; on by default, turn it off to remove it from the sidebar. Synonyms: super prompt creator sidebar, show/hide prompt builder.
superPromptPublicLinkConfirmDismissed toggle true | false "Don't ask again" dismissal for the "Create a public link?" confirmation shown before a Super Prompt's "Copy link" publishes it to a public Shares page. When true, Copy link publishes + copies with no confirmation. Default false.
superPromptsSidebarEnabled toggle true | false Shows or hides the Super Prompts entry in the sidebar — your library of saved, reusable "super prompt" templates. One of the per-section sidebar visibility toggles; on by default, turn it off to remove Super Prompts from the sidebar. Synonyms: super prompts sidebar, show/hide saved prompts library, prompt templates panel.
swarmDefaultDailyBudgetUsd number number 1..500 The default daily USD spend cap copied onto a new Swarm slot when you don't set one of your own (default $10; range $1-500). Once a slot has its own daily budget, that value — not this default — is what the tick loop checks against spend. Synonyms: swarm daily budget, default swarm spend cap, swarm budget default.
swarmDefaultWorkerCap number integer 1..10 The default maximum worker count copied onto a new Swarm slot when you don't set one of your own (default 3; range 1-10). Once a slot has its own worker cap, that value — not this default — is what's checked live each tick before spawning another worker. Synonyms: swarm worker cap, default max workers, swarm worker limit.
swarmEnabled toggle true | false Part of Overseers: give an Overseer a goal and it runs a lead agent with a small team of paid worker sessions, capped by the Overseer budget and a worker limit. On whenever Overseers is on.
swarmMaxConsecutiveFailures number integer 2..20 How many consecutive worker failures a Swarm slot tolerates before the tick loop auto-pauses it, rather than letting it keep spawning failing workers (default 3; range 2-20). Checked live every tick; applies to every slot (no per-slot override). Synonyms: swarm failure limit, auto-pause swarm, consecutive failure kill-switch.
swarmSlots map map of string → object { dailyBudgetUsd: number 0..500; goal: string (≤4000); goalDone: true | false; name: string (≤80); orchestrationFailures: integer 0..100; paused: true | false; pausedReason: string (≤500); projectId: string; retryAfter: string; workerCap: integer 1..10; workerModel: string (≤100); workerModelTier: "genius" | "smart" | "worker" | "basic"; workerProvider: "claude" | "codex" | "gemini" | "antigravity" | "deepseek" | "kimi" | "glm" | "minimax" | "meta" | "qwen" | "openrouter" | "cursor" | "hermes" | "grok" | "gpt" | "xai" | "pi" | "opencode" | "terminal" | "devin" | "grokbot" | "reason" | "kimicode" | "dsh" | "customOpenai" | "customAnthropic" | "acpAgents" | "musecode" | "acp" | "ultramarine" | "t3code" | "crofai" | "deepinfra" | "geminicc" | "runinfra" | "inferx" | "venice" | "abliteration" | "engy" | "refuseless" } Your active Swarm slots — one entry per swarm, holding its goal, worker cap, daily budget, project, and pause/done state. Created from the Swarm panel's "Create" form; this key IS the swarm store the tick loop reads every cycle to run each one, not a toggle you flip directly. Synonyms: swarm list, active swarms, swarm database, my swarms.
swarmWorkerDeadlineMinutes number integer 5..240 How many minutes of inactivity mark a live Swarm worker as stuck and owed a reap/retro (default 45; range 5-240). Checked live every tick against each worker's last-active timestamp; the swarm lead is exempt. Synonyms: swarm worker timeout, stuck worker deadline, swarm inactivity limit.
swarmsSidebarEnabled toggle true | false Shows or hides the Swarms entry in the sidebar, the Agent Tools hub for bake-off swarms that run one prompt across several agents. One of the per-section sidebar visibility toggles; on by default, turn it off to remove Swarms from the sidebar. Synonyms: swarms sidebar, bake-off swarms, show/hide swarms hub.
syncConflictAutoStartForTeammates toggle true | false Whether a pull request opened by ANOTHER developer starts a PR conflict conversation on its own. Off by default — until you turn it on, only your own pull requests start automatically. Set from the Dev Pipeline panel's Setup tab, never an environment variable. Synonyms: teammates pull requests, auto start conflict conversations for teammates, other developers prs, conflict conversation auto start, teammate pull request handling.
syncSkillsToClaudeCode toggle true | false Install the app's built-in skills into Claude Code automatically. On by default; turn off to stop the app adding any bundled skills.
tasksSidebarEnabled toggle true | false Show the Tasks row in the sidebar. On by default.
teachRecorderSidebarEnabled toggle true | false Shows or hides the Teach Recorder entry in the sidebar - the (in-development) tool that records what you do on Windows and turns the recording into a reusable AI skill. One of the per-section sidebar visibility toggles; on by default, turn it off to remove Teach Recorder from the sidebar. Synonyms: teach recorder sidebar, teach by demonstration, record a task, demonstration recorder.
teamChatSidebarEnabled toggle true | false Show the Team Chat row in the sidebar. On by default.
timeTrackerSidebarEnabled toggle true | false Show the Time Tracker row in the sidebar. On by default.
trunkAuthority select "unenrolled" | "local" | "github" | "unknown"
trunkAuthorityEpoch number number
trunkAuthorityReason text string
trunkShadowPublish toggle true | false
unifiedWorkFinishingEnabled toggle true | false Enrolls newly launched sessions in the unified work-finishing coordinator. It records a durable finish choice so another computer can own completion safely; turning enrollment off does not change the executor already recorded for active work. Off by default. Synonyms: unified finish, work finishing, shared finish coordinator, finish work automatically, finish handoff.
unreadGuardSkipsConsumedReportsEnabled toggle true | false Stops the final-message unread guard from blocking an archive of a report whose real audience already consumed it, such as a reviewer, judge or scribe session the app reads, or a crew member whose report reached its lead. On by default. When off, every automatic archive meets the guard. Synonyms: unread guard, archive blocked unread, consumed report, final message unseen.
verdictPanelSidebarEnabled toggle true | false Shows or hides the Verdict entry in the sidebar — the developer-tools panel that shows what the Verdict verification broker on this machine is doing (broker health, queue, executions, deliveries, requests, red flags, diagnostics readout, owner policy). One of the per-section sidebar visibility toggles; on by default, turn it off to remove Verdict from the sidebar (the panel itself is revealed by the verdict-panel Lab toggle). Synonyms: verdict sidebar, verification broker panel, show/hide verdict dashboard.
voiceHistorySidebarEnabled toggle true | false A viewable history of your voice conversations, in the sidebar. Keeps your hands-free "Omniscio Voice" chats and your per-session "Session Voice" questions, each clearly labeled, so you can revisit what was said.
voiceprintStudioSidebarEnabled toggle true | false In-development: a studio in the sidebar that builds an email style guide in your WRITING voice (not audio). Tag your Sent mail, watch the AI re-draft a real email blind, judge it, and approve fixes that sharpen the guide you paste into any AI.
workFinishingActionsPaused toggle true | false Pauses new finish actions and retries while keeping status and reconciliation live. An external action already executing may continue. This is a pause boundary for future effects, not a cancellation signal. Off by default. Synonyms: pause finish actions, pause land or pull request, stop finish retries, pause work finishing.
workFinishingComputerStandards list array of object { computerId: string (≤128); finishId: "local-merge" | "keep-branch" | "pull-request" | "tag" | "ready-tag" | "command"; scope: "this-computer" | "cloud" | "linked" | "computer" } The finish standard for each place a session can run: this computer, cloud machines, or one named linked computer. Each row picks how finished work leaves (for example land on local master or open a pull request) for new sessions that run there, unless the session or a project and computer preference chose otherwise. A row whose finish the repository cannot run (a team command with no command set up) is ignored. Empty by default, which follows each project’s own setting. Edit in Dev Pipeline settings under Unified work finishing. Synonyms: finish standard per computer, default finish for this computer, cloud finish default, how sessions finish on this machine, land on master by default.
workFinishingPreferences list array of object { executionComputerId: string (≤128); override: object { destinationComputerId: string (≤128); finishId: "local-merge" | "keep-branch" | "pull-request" | "tag" | "ready-tag" | "command" }; projectId: string (≤100) } Per-project and per-execution-computer overrides for the finish destination and recipe. Each field can remain inherited from the repository profile or linked-computer defaults. Edit in Dev Pipeline settings under Unified work finishing. Synonyms: finish preferences, finish destination by computer, project finish recipe, where work finishes.
workflowsEnabled toggle true | false In-development: build n8n/Zapier-style automations on a visual canvas — a trigger plus a graph of steps (deterministic actions and AI steps) that Omniscio runs for you.
workflowsSidebarEnabled toggle true | false Show the Workflows row in the sidebar. On by default.
worktreeLedgerEnabled toggle true | false Plain-language view of every workspace in flight, backed by the observed worktree ledger, with a Saved Work vault.
writerSidebarEnabled toggle true | false Show the Writer row in the sidebar. On by default.
wslRunLocationsEnabled toggle true | false Windows only: offer each installed WSL 2 distro as a place a new session can run, with its agent, terminal and git inside the distro. Listing distros never starts one; nothing is installed or changed inside a distro.

Inbox & Notifications (167)

Everything waiting on you, and how Omniscio tells you about it.

Setting Type Accepted values What it does
agentEmailAddress text string (≤320) The agent email address you have claimed, so others can email your agent and start a session. Empty means no address has been set up yet.
agentEmailApprovedSenders list array of string (≤200) Extra email addresses allowed to email your agent and start a new session, when the sender policy is set to "approved".
agentEmailDomain text string (≤320) Internal cache of the mail domain your agent address uses, so the address preview can show the real domain even while offline. The live value comes from the server, not this field.
agentEmailReceivingEnabled toggle true | false Whether your agent email address accepts incoming mail. On by default; turning it off pauses receiving without giving up the address.
agentEmailSenderPolicy select "owner" | "approved" | "anyone" Who may email your agent address and start a new session: "owner" (only your own email, the default), "approved" (your email plus your approved-senders list), or "anyone". A reply always continues the conversation when its sender is part of it — someone who wrote on the thread, or someone the agent wrote to — and anyone else is treated as a new correspondent this setting decides about.
agentEmailSessionProjectPath text string (≤500) Which project new sessions started from incoming agent email are created in. Empty uses the built-in agent-email project.
agentEmailSupportAddress text string (≤320) The support address for this install — mail addressed TO exactly this address is accepted from ANY sender, because a support desk has to take mail from people who are not on your approved list. Blank (the default) means support is not configured. Every other address keeps your normal approved-sender policy, so turning support on never opens your personal address to strangers; setting it back to blank returns the install to its previous behaviour. Synonyms: support email address, help desk address, which address accepts outside mail, open a support inbox, public support address.
agentEmailSupportReplyFromAddress text string (≤320) The address support replies are sent from when public mail is forwarded to your agent address. Leave empty to reply from the address mail actually lands at.
agentEmailTagRoutes list array of object { instructions: string (≤4000); open: true | false; projectPath: string (≤500); tag: string (≤32) } Where mail sent to your agent address with a plus tag opens its session: one entry per tag, naming the project. A tag you have not listed changes nothing. Synonyms: plus addressing, subaddress, tagged email routing, route email by tag, sort incoming mail into projects.
agentForegroundAlertEnabled toggle true | false Show the inbox card explaining that an agent was blocked from bringing the window forward while you were in another app. Off only silences the notice, not the block.
agentMailIntakeRetiredNotified toggle true | false Remembers that you have already been shown the one-time notice that the old AgentMail email intake feature was retired, so the notice is not repeated. Off by default and set automatically once the notice is raised; it is not meant to be changed by hand. Synonyms: AgentMail retired notice, email intake retirement notice shown, retired intake alert seen, notice already shown.
alarmsEnabled toggle true | false Alarms — virtual project with scheduled fire-time triggers.
alertChannelOverrides map map of string → array of "push" | "email" | "sms" | "call" Lets you pick, for a specific kind of alert, exactly which delivery channels it uses: phone push, email, text message, or phone call. An alert type with an entry here uses your list instead of its built-in default. Empty by default, so every alert uses its normal channels. Synonyms: alert delivery channels, per-alert notification method, text or call for alerts, notification routing.
alertCustomGroups list array of object { id: string (≤47); label: string (≤40) } The alert groups you made yourself, each with a name of up to 40 characters, up to 50 in all. Any alert type, including a built-in one, can be filed in one of them. Empty by default. Deleting a group sends its cards back to where they would have been. Managed from Settings, Notifications, Your alert groups. Synonyms: my alert groups, custom alert group, rename alert group, delete alert group.
alertGroupsEnabled toggle true | false Sorts the open cards in the Alerts hub into named groups, adds a search box and a Dismiss all button, and clears old cards after a day of your active time. On by default; turn it off to see the Alerts hub as one flat list again.
alertOwnerPhoneNumber text string (≤40) Your own phone number, where text message and phone-call alerts are delivered. Text and call alert channels only work when this and the three Twilio settings are all filled in; otherwise those channels are skipped. Empty by default. It is never sent to a paired phone or web browser, or included in a diagnostic bundle. Synonyms: my phone number for alerts, SMS alert recipient, call alert number, where alerts are texted.
alertSessionRoutes list array of object { category: "cloud-fleet" | "git-worktrees" | "spend" | "sessions" | "system-health" | "integrations" | "security" | "tips-nudges" | "maintenance" | "messaging" | "automation" | "product"; enabled: true | false; match: string (≤200); ownerCopy: true | false; target: object { id: string (≤64); kind: "session" | "crew" | "owning-crew-of-alert-session" | "overseer" } } A list of rules that hand matching alerts to an Overseer, a session, or a crew instead of leaving them with you. Each rule matches by text prefix or category and can be turned off or removed. Empty by default. Synonyms: alert routing rules, send alerts to session, hand alerts to overseer, alert forwarding.
alertSurfaceOverrides map map of string → array of "inbox" | "toast" | "banner" | "popup" Lets you choose, for each kind of alert, whether it also appears as a toast, banner, or pop-up in addition to the inbox. The inbox is always kept. Empty by default, so each alert uses its own built-in choice. Synonyms: alert pop-ups, toast or banner per alert, loud alerts, how alerts appear.
alertTypeAutoDismiss map map of string → true | false Per alert type, whether its cards may dismiss themselves (true) or must always stay until you dismiss them (false), keyed by alert type. It beats the built-in default for that type, except that a card asking for your answer is never auto-dismissed. Empty by default. Set from Never auto-dismiss this type on an alert card and from Settings, Notifications, Alert types. Synonyms: never auto dismiss, keep this alert, alert auto dismiss exceptions.
alertTypeGroups map map of string → string (≤47) Which group each alert type is filed in, keyed by alert type, so you can move a type out of the group the app chose. A type with no entry keeps its normal group, and your choice survives app updates. Empty by default. Set from the Move to group menu on an alert card and from Settings, Notifications, Alert types. Synonyms: move alert to group, alert group override, file alerts differently.
alertTypeHubs map map of string → string (≤200) Lets you send a kind of alert to a chosen hub in the inbox instead of letting the app decide automatically. Each alert type can have its own destination, and removing the entry returns it to automatic routing. Empty by default, so every alert is placed automatically. Synonyms: alert destination, inbox hub routing, move alerts to another hub, alert placement.
alertTypeMutes map map of string → true | false Which individual alert types you have turned off, one dedupKey per muted type (true = muted). Only types you explicitly turn off appear here — an absent key always means that alert still fires, and this is never pre-populated with the full alert catalog. Read once, at the moment an alert is about to be raised, so a type you turned off never comes back no matter which script, cron job, or producer tried to raise it; turning a type back on just removes its key. Controlled from Settings → Notifications → Alert types, and from the quiet mute button on each alert card. Synonyms: alert types, mute an alert, unmute an alert, turn off an alert, disable a notification type, silence this alert, stop this alert, per-alert-type switch, alert off switches, notification type toggle.
alertsHubGroupsCollapsed toggle true | false Remembers whether the list of alert groups under Alerts in the sidebar is folded away. Off by default, so the groups show. It is set by the arrow beside Alerts. Synonyms: collapse alert groups, hide groups under alerts, fold alerts sidebar.
alertsHubShowEmptyGroups toggle true | false Remembers whether alert groups with no open cards are shown in the sidebar. Off by default, so only groups with open cards appear and a Show empty row reaches the rest. It is set by that row. Synonyms: show empty alert groups, hidden alert groups, empty groups.
anthropicStatusMonitorEnabled toggle true | false Watch Anthropic's public status page and raise one inbox card when an Anthropic outage is breaking Claude sessions, auto-clearing when it recovers.
archiveDigestEnabled toggle true | false Supermail "Archive Insights" AI digest. When on, Supermail suggests cleanup actions for the senders you archive without reading; to make specific suggestions, the sender and subject of the emails you archive are sent to the AI provider. Off by default. Synonyms: archive insights, AI cleanup digest, archived-sender suggestions.
archiveDigestPreview toggle true | false In-development: a periodic AI digest of your recently-archived Supermail emails — a daily or weekly summary of what landed in your archive, spotting patterns, recurring senders, and anything worth revisiting. Off by default, and cost-capped.
broadcastFormsEnabled toggle true | false An inbox alert can carry a short inline FORM (a few questions) that you answer right on the card and submit back to whoever sent it.
broadcastReceiptsEnabled toggle true | false When you receive a targeted broadcast, your app confirms back to the sender that it was received, shown in your inbox, and opened — so the operator can see per-recipient delivery. Honors your "developer messages" opt-out; nothing is reported when that is off.
bugIntakeDailyCap number integer 1..1000 Maximum number of incoming bug reports processed per day (default 50).
bugIntakeLiaisonFromAddress text string (≤200) The brand "from" address the bug-report email liaison sends the reporter from — the acknowledgement and the warm progress updates come from here (default support@omniscio.com). Sent via the Omniscio Agent Email / Cloudflare transport, not third-party AgentMail. The recipient is always the original reporter, bound on the server, so this only sets who the mail appears to come FROM. Internal-only (devOnly); blank disables the liaison send. Synonyms: liaison from address, bug report email sender, support from address, reporter email from, who bug-report emails come from.
bugIntakeLiaisonReplyToAddress text string (≤200) The Reply-To address on bug-report liaison emails — when a reporter replies, their message goes here and routes back to the same fixing session (default support@omnisciomail.com, a Cloudflare-received address). The brand "from" domain is send-only, so replies are directed here to continue the conversation. Internal-only (devOnly). Synonyms: liaison reply-to address, bug report reply address, where reporter replies go, support reply-to, reporter reply routing address.
bugIntakeSplitWidth number number 320..900 Width in pixels of the side panel next to a bug-fix session in the Dashboard (320 to 900; default 460). Set by dragging the divider.
bugReportTransport select "both" | "email" | "firebase" How in-app feedback is sent out: both email and cloud (default), email only, or cloud only.
calendarChangeNotificationsEnabled toggle true | false Notify you when a calendar event is added or changed. These can be chatty, so they have their own switch.
calendarDailyAgendaHour number integer 0..23 The hour (0-23, local time; default 7) each morning's "Today's Agenda" inbox card is posted. Settings → Calendar → "Agenda delivery time" (paired with calendarDailyAgendaMinute).
calendarDailyAgendaMinute number integer 0..59 The minute (0-59, local time; default 0) each morning's "Today's Agenda" inbox card is posted. Settings → Calendar → "Agenda delivery time" (paired with calendarDailyAgendaHour).
calendarHiddenIds list array of string (≤200) The calendars you have hidden. Empty means every subscribed calendar is shown and newly subscribed ones appear automatically.
calendarNotificationsEnabled toggle true | false Notify you before a calendar event starts. Runs only while Google Calendar and its background sync are on.
calendarSyncEnabled toggle true | false Keep the calendar fresh in the background so open views refresh and change alerts can fire. Only runs when the calendar itself is on.
collapsedInboxGroups list array of string (≤64) Which inbox groups you have folded shut, remembered between restarts. A display choice only — an entry for a group that no longer exists is ignored.
costAlertsEnabled toggle true | false Show the AI-cost inbox cards (unusually high spend and cost-saving suggestions). A genuine runaway still alerts even when this is off.
crashAutoSendEnabled toggle true | false When on, Omniscio may e-mail you when the app crashes. It sits on top of the telemetry e-mail setting: turning it off stops the per-crash e-mails and the crash entry in the anonymous usage telemetry, while leaving the weekly digest alone. Crash capture itself (Sentry) still runs.
dailyDigestDailyCostCapUsd number number 0.05..5 Daily spending limit in dollars for generating the daily digest, guarding against a runaway retry loop. Only hit in unusual cases.
dailyDigestDeliverEmail toggle true | false When on, your generated Daily Digest is also emailed to you, in addition to posting as an in-app inbox card. Off by default. No Settings-UI control yet; set via CLI/PATCH.
dailyDigestExcludedProjectIds list array of string (≤200) Projects left out of the daily digest.
dailyDigestExcludedSectionIds list array of "greeting" | "stats" | "alerts" | "projects" | "communications" | "calendar" | "feeds" | "actionItems" | "suggestions" | "featureIdeas" | "todaySchedule" Sections left out of the daily digest (for example stats, alerts, calendar, or suggestions).
dailyDigestScheduleHour number integer 0..23 Hour of the day (0–23, your local time) the daily digest is generated.
dailyDigestScheduleMinute number integer 0..59 Minute of the hour (0–59) the daily digest is generated.
dailySpendDigestEnabled toggle true | false Send one morning inbox card summarizing yesterday's AI spend, broken down by provider. Off by default.
deepSeekBalanceMonitorEnabled toggle true | false Warn before a DeepSeek API account runs out of credit: read the balance every 15 minutes, measure how fast it is actually draining, and raise one inbox card with a one-click Recharge when the account is projected to hit zero inside your warning window. On by default, and the toggle stays live so you can turn it off with one setting flip.
desktopNotificationDeliveryAlertDismissed toggle true | false Set when the person archived the "desktop alerts are not reaching you" card. While it is true the card is never raised again, and the next desktop toast that actually shows clears it, so a genuinely new outage still gets one card. There is no Settings control: it is the card's own memory of the person's decision.
emailArrivalNotificationsEnabled toggle true | false Agent Email — raise a quiet inbox row when a new incoming email either starts OR continues a session. On by default. It is an inbox row, NOT an OS toast (it survives Focus Mode as the durable record). Bug-intake triage emails ([BUG]/[FR]/…) take the separate bug-report path and never raise it. Turn off to stop arrival notices for new agent-email sessions. Synonyms: email arrival notifications, incoming email notice, agent email inbox row, notify on new email.
emailSummarizerDefaultModel text string (≤100) The AI model used to summarize your emails by default.
emailSummarizerOnboardingComplete toggle true | false Internal bookkeeping: set once you've finished the email-summarizer setup wizard, so it stops auto-opening. Not a setting to change.
focusModeState object object { enabled: true | false; perProjectLastBatchAt: map of string → string; startedAt: string; whitelistedSessions: array of string (≤64) } Internal: remembers Focus Mode's running state (whether it's on, when it started, per-project batch times, and the session whitelist). Not a setting to change by hand.
helpdeskReplyNotificationsEnabled toggle true | false
inboxBacklogNudgeEnabled toggle true | false When on (default), Omniscio drops a gentle inbox card at most once a day when your session inbox has piled up — at least 15 sessions that have been waiting 3+ days for you — while you are actively working but not archiving, nudging you to archive what you are done with so your inbox does not grow to hundreds of stale items. It never fires on a busy day of fresh items (the trigger is quantity AND age), runs entirely on your machine with no AI, and clears itself once the backlog clears. Turn it off in Settings under Notifications or with the card's "Turn off these nudges" button. Synonyms: inbox backlog nudge, archive reminder, clear your inbox, too many sessions, stale sessions piling up, backlog nudges.
inboxPilotEnabled toggle true | false Turns the Inbox on for this install. Off unless you opted into the pilot, and the Inbox panel and its alerts stay hidden while it is off.
inboxPilotRetireMigrationDone toggle true | false Internal bookkeeping: whether the one-time upgrade that retired the Inbox pilot flag has run. Written by the upgrade, not a setting to change.
inboxPostSendBehavior select "stay" | "return_to_inbox" What happens after you send a reply while you are in the Inbox. "return_to_inbox" (the default, labelled "Auto-advance in inbox") moves you to the next inbox item that needs you, or clears the panel when none remain. "stay" does not decide on its own: it hands the choice to the "After sending a message" list (postSendNavigation), which by default still advances you to the next session that needs attention in the inbox — so it only truly stays put if that list is set to just "stay". Settings → Workflow → "After sending while in inbox". Synonyms: auto advance in inbox, after sending in inbox, post send behavior inbox, go to next inbox item after reply, stay on session after reply, return to inbox after sending, inbox reply navigation.
inboxQuietHubIds list array of string Lists the inbox hubs you moved to the Quiet setting. Their items show in a Quieter section below your Inbox with their own count instead of the main badge. Empty by default. Synonyms: quiet inbox hubs, quieter section, mute hub in inbox, lower priority inbox sources.
inboxRulesEnabled toggle true | false In-development: define plain-language rules that automatically suppress, archive, or snooze new inbox alerts the moment they arrive — no manual triage needed. Off by default.
installReaperAlertEnabled toggle true | false Show the inbox notice when stuck dependency installs are cleaned up. Off only silences the notice, not the cleanup.
intakeDedupEnabled toggle true | false Check incoming bug reports for a duplicate of an already-open report and warn the agent. On by default.
intakeGloballyPaused toggle true | false Pause ALL bug intake: no Sentry, GitHub, or email source will start a session while this is on. Off by default.
meetingDigestScheduleCadence select "daily" | "weekly" How often the meeting digest runs: daily or weekly.
meetingDigestScheduleDayOfWeek number integer 0..6 For a weekly meeting digest, which day it runs on (0 = Sunday through 6 = Saturday; default Monday).
meetingDigestScheduleEnabled toggle true | false Turn on the scheduled meeting digest, which runs your "Prep my day" or "Catch me up" meeting recipe on a schedule. Off by default; it starts a paid session each time.
meetingDigestScheduleHour number integer 0..23 Hour of the day (0–23, your local time) the scheduled meeting digest runs.
meetingDigestScheduleMinute number integer 0..59 Minute of the hour (0–59) the scheduled meeting digest runs.
meetingDigestScheduleRecipeId text string (≤64) Which meeting recipe the scheduled meeting digest runs.
mobileSoundEnabled toggle true | false Play a short chime on your phone and web clients when a session needs attention.
newModelWatcherEnabled toggle true | false Watch your configured providers for newly released AI models and raise one inbox card per new model, with a one-click Add button.
notificationSoundApproval text string (≤200) Chooses which sound plays when an agent needs your approval. The default is the built-in alert ping. It only plays if the approval sound is turned on and the master notification sound switch is on. Synonyms: approval sound, permission request chime, approval alert tone, approval notification sound.
notificationSoundApprovalEnabled toggle true | false Turns the approval sound on or off. On by default, so you hear a sound when an agent needs your approval. Turning it off keeps that one event silent while other notification sounds keep playing. Synonyms: approval sound switch, mute approval sound, permission request chime, approval alert sound on off.
notificationSoundEnabled toggle true | false Master on and off switch for notification sounds on this computer.
notificationSoundError text string (≤200) The sound played for error notifications. Can be a built-in chime or your own sound.
notificationSoundErrorEnabled toggle true | false Turns the error sound on or off. On by default, so you hear an attention sound when a session hits an error. Turning it off keeps errors silent while other notification sounds keep playing. Synonyms: error sound switch, mute error sound, session error chime, failure alert sound.
notificationSoundFinished text string (≤200) Chooses which sound plays when a session finishes its work. The default is the built-in alert ping. It only plays if the finished sound is turned on and the master notification sound switch is on. Synonyms: finished sound, task complete chime, done sound, session completed tone.
notificationSoundNeedsYou text string (≤200) The sound played when a session needs your attention.
notificationSoundNeedsYouEnabled toggle true | false Turns the needs-you sound on or off. On by default, so you hear a sound when a session is waiting for you. Turning it off keeps that event silent while other notification sounds keep playing. Synonyms: needs you sound switch, mute needs you chime, waiting for me sound, attention sound on off.
notificationSoundRecordingLinkReady text string (≤200) Chooses which sound plays when a recording's shareable link is ready. The default is a soft marimba tone. It only plays if the link-ready sound is turned on and the master notification sound switch is on. Synonyms: recording link ready sound, recording link chime, share link ready tone, recording notification sound.
notificationSoundRecordingLinkReadyEnabled toggle true | false Turns the recording link-ready sound on or off. On by default, so you hear a soft tone when a recording's link is ready to share. Turning it off keeps that event silent while other notification sounds keep playing. Synonyms: recording link sound switch, mute recording link chime, link ready sound on off, recording alert sound.
notificationSoundRecordingUploaded text string (≤200) Chooses which sound plays when a recording finishes uploading. The default is a soft marimba tone. It only plays if the upload-done sound is turned on and the master notification sound switch is on. Synonyms: recording uploaded sound, upload done chime, recording finished uploading tone, recording upload notification sound.
notificationSoundRecordingUploadedEnabled toggle true | false Turns the recording upload-done sound on or off. On by default, so you hear a soft tone when a recording finishes uploading. Turning it off keeps that event silent while other notification sounds keep playing. Synonyms: recording uploaded sound switch, mute upload chime, upload complete sound on off, recording upload alert.
notificationSoundStalled text string (≤200) The sound played when a session stalls.
notificationSoundStalledEnabled toggle true | false Turns the stalled sound on or off. On by default, so you hear a soft bell when a session stops making progress. Turning it off keeps stalls silent while other notification sounds keep playing. Synonyms: stalled sound switch, mute stalled chime, stuck session sound, session stopped sound.
notificationSoundTeamChatChannelMessage text string (≤200)
notificationSoundTeamChatChannelMessageEnabled toggle true | false
notificationSoundTeamChatDm text string (≤200)
notificationSoundTeamChatDmEnabled toggle true | false
notificationSoundTeamChatMention text string (≤200)
notificationSoundTeamChatMentionEnabled toggle true | false
notificationSoundTeamChatThreadReply text string (≤200)
notificationSoundTeamChatThreadReplyEnabled toggle true | false
notificationSoundVolume number number 0..1 How loud notification sounds play, from 0 (silent) to 1 (full volume).
problemAlertReRaiseThrottleEnabled toggle true | false After you dismiss a problem alert, keep that same alert from reappearing for 24 hours. Off lets it resurface on its own schedule.
providerStatusMonitorEnabled toggle true | false Watch the status pages of OpenAI, Cursor, and Groq, but only for providers you've used in the last week, raising one card per outage.
quietHoursDays list array of integer 0..6 Which days of the week (0=Sunday..6=Saturday; default all 7) the quiet-hours window applies on. Only takes effect when quietHoursEnabled is on. No Settings-UI control yet; set via CLI/PATCH.
recordBreakInboxAlertsEnabled toggle true | false Raise an inbox card when you break a celebration-worthy personal record in Stats. Off by default.
repeatedPhraseQuickReplyNudgeEnabled toggle true | false Raise one inbox card offering to save a phrase you keep retyping as a quick reply.
repeatedPhraseQuickReplyNudgeThreshold number integer 2..100 How many times a phrase must repeat before the quick-reply nudge fires (2 to 100).
rssDigestDailyCostCapUsd number number 0.05..5 Daily spending limit in dollars for the RSS digest's two paid AI passes, guarding against a runaway retry loop. Only hit in unusual cases.
rssReaderFontSize select "sm" | "md" | "lg" | "xl" Text size in the RSS article reader: small, medium, large, or extra large.
rssReaderWidth select "narrow" | "medium" | "wide" | "full" Column width in the RSS article reader: narrow, medium, wide, or full.
rssRetentionDays number integer 7..730 How many days RSS articles are kept before older ones are automatically removed (7–730).
sentryTriageAiDailyCapUsd number number 0..100 Daily dollar limit for the AI second-look on borderline Sentry issues (default 0.25); once reached, those issues are held instead.
sentryTriageAiSecondLookEnabled toggle true | false Let a cheap AI call decide whether borderline Sentry issues should start a fix session, be held, or be ignored. On by default; needs an API-key account.
sentryTriageAutoPromoteEventCount number integer 0..1000000 If a held Sentry issue keeps gathering events up to this number, it's promoted to a fix session. 0 turns auto-promote off (default 100).
sentryTriageAutoSpawnHeld toggle true | false When on (the default), a Sentry error the triage gate would have parked for review starts an investigation session the moment it arrives, instead of waiting in your inbox for you to click Spawn — so nothing from your Sentry source queues up for a manual start. Your muted issues still never spawn, and a bug already being investigated (or investigated in the last day) still does not buy a second session; the pre-spawn safety screen and the one-time first-connect cap also still apply. Turn it off to get the review queue back: issues below your spawn bar, and a bug seen for the first time, wait for you in Bug Intake → Review. Bug Intake → Settings → "Auto-spawn held issues". Synonyms: auto spawn sentry issues, sentry sessions without clicking, stop bug intake waiting in inbox, never hold sentry issues for review, sentry triage review queue off, automatic bug intake sessions.
sentryTriageAutoSpawnMinLevel select "fatal" | "error" | "warning" | "info" | "debug" The seriousness level at or above which a Sentry issue automatically starts a fix session (fatal, error, warning, info, debug). Default 'error'.
sentryTriageConsolidateByClass toggle true | false Hold a new Sentry issue as a duplicate instead of starting a second investigation when a session for the same kind is already running. On by default.
sentryTriageEnabled toggle true | false Master switch for the Sentry triage gate: screen every new Sentry issue before deciding whether to start a fix session. On by default.
sessionBadgeMode select "all" | "unread" Controls session badge counts. All, the default, counts every session waiting on you. Unread leaves out sessions whose badge you already acknowledged until the session needs you again. Synonyms: badge count mode, unread badges only, mark badge as read, needs you badge.
slackOneClickSetupEnabled toggle true | false In-development: connect Slack by signing in, pressing Create and pressing Allow, and Omniscio builds your own Slack app and connects the Slack sidebar and the Team Chat import for you.
smsNotificationsEnabled toggle true | false Show an on-screen pop-up and chime for incoming text messages. Off quiets SMS pop-ups without silencing session or budget notices.
soundQuietUntil text string Holds the time until which notification sounds are silenced after you pick a quick quiet period. While that time is still in the future, sounds stay quiet, and once it passes they return to normal. Empty by default, meaning no quick quiet period is active. Synonyms: mute sounds for a while, snooze notification sounds, quiet period, temporary mute.
spamFilterGmailAiEnabled toggle true | false Use an AI second pass to filter Gmail spam.
spamFilterGmailEnabled toggle true | false Turn on basic spam filtering for Gmail.
spamFilterSmsAiEnabled toggle true | false Use an AI second pass to filter SMS spam.
spamFilterUiVisible toggle true | false In-development: an automatic spam filter for texts, calendar invites and your agent's email. Strangers' messages are checked, junk waits in the Inbox's Spam view, and one click brings a message back. Revealing it adds the Spam view and the Inbox → Spam settings; filtering itself stays off until you turn it on there.
supermailAiFilter map map of string → object { enabled: true | false; instruction: string (≤8000); mode: "preview" | "live" } Supermail — per-identity AI Filtering settings, keyed by the signed-in identity (or "anon"): an enable override (inherit / force on / force off), a mode (preview / live), and an instruction. An empty or absent entry inherits the global AI-filter toggle. Controls how the AI filter runs per account when reading and triaging email. Synonyms: AI filter per account, triage AI instruction, per-identity filter override.
supermailAiFilterEnabled toggle true | false In-development: let AI read each new email in Supermail and triage it against a plain-language instruction you write — keeping, archiving, labeling, marking read, or starring it. Starts in preview mode (shows what it would do without touching anything) until you switch it to live; it never trashes mail, and it is cost-capped. Off by default.
supermailAiPlainSpeakEnabled toggle true | false In-development: a Plain Speak toggle in every email thread that flips the conversation to a short glance card — the TLDR, what the sender wants from you, any deadline, and one recommended next step, in plain English. It is written in the background by a cheap AI model (DeepSeek by default, served through your own AI key order) — by itself only for email in the one inbox you pick in Settings → Supermail, and when you press V for everything else. Cached for each thread so re-opening never pays twice, and says plainly when it cannot summarize. Off by default, and cost-capped.
supermailAiSummaryEnabled toggle true | false In-development: a "Catch me up" AI summary in Supermail that reads an open conversation and summarizes it in two parts — what the thread has been about so far, then what the most recent email says. You choose whether it runs on a button or automatically when a thread opens, and you can edit the prompt it uses. Off by default, and cost-capped.
supermailArchiveInsightsDwell toggle true | false The more sensitive Archive Insights dwell switch: whether Supermail may record how long each email was open before you archived it, to improve its insights. On by default. Turn it off to stop dwell-time tracking while keeping the rest of Archive Insights. Synonyms: dwell tracking, time-spent tracking, how long an email was open.
supermailArchiveInsightsEnabled toggle true | false Master switch for Supermail Archive Insights tracking: whether Supermail records your archive behaviour at all to power its insights. On by default. Turning it off disables the whole feature. Synonyms: archive insights, archive tracking, track what I archive.
supermailArchiveInsightsSuggestFilters toggle true | false The Archive Insights proactive-nudge switch: whether Supermail may surface a "create a filter" toast when it notices you repeatedly archiving similar mail. On by default and independent of the master Archive Insights switch. Synonyms: suggest filters, create-a-filter nudge, archive filter suggestions.
supermailComposeSharedEditor toggle true | false Makes the Supermail compose window use the shared compose editor, the same one used elsewhere in the app, with real lists and emoji shortcodes. On by default. Turn it off to return to the older plain text box. Synonyms: shared compose editor, Supermail rich editor, email composer editor, plain text compose fallback.
supermailContactGroups map map of string → array of object { id: string (≤80); members: array of object { email: string (≤320); name: string (≤200) }; name: string (≤200); source: "local" } Supermail — your own device-local contact GROUPS, keyed by the signed-in account (or "anon" when signed out). Each group has an id, name, and member emails. Per-account privacy is an invariant: a group made under one account never surfaces under another. Written by the contact-groups store; no Settings-UI control. Synonyms: contact groups, supermail groups, email contact lists.
supermailContactGroupsEnabled toggle true | false In-development: name a reusable group of people once, then drop it into a Supermail recipient field (To/Cc/Bcc) to address everyone at once. Reads your existing Google Contacts groups (read-only) and lets you make quick device-local groups in the app; picking a group fills in each person as an individual, removable recipient. Off by default.
supermailContactPaneVisible toggle true | false Whether the right-hand contact rail (the contact's photo, role, and recent emails) is shown beside an open Supermail conversation. Opt-in and off by default. Turn it on with the Settings "Contact pane" toggle or the Show/Hide Contact Pane command. Synonyms: contact pane, sender details panel, people pane, contact rail.
supermailEnabled toggle true | false
supermailHoverActEnabled toggle true | false Act on the hovered conversation with keyboard shortcuts in Supermail. On by default: moving the mouse onto a thread row moves the keyboard cursor to it, so the one-key shortcuts (e = Done, # = Trash, s = Star, u = Unread, and the rest) act on whatever is under the pointer with no click or select first. It moves the cursor only and never opens the reading pane (that still needs a click or Enter). Off restores hover to prefetch-only, so the cursor moves only via click and j/k. Synonyms: hover to act, act on hover, hover keyboard cursor, hover selection.
supermailLeftHandedNav toggle true | false Left-handed inbox navigation in Supermail. When on, the inbox list can be driven with the left hand: W moves up and S moves down, mirroring the default K/J and arrow keys onto the WASD region. Because S then means down, the one-key Star action relocates to D while this mode is on. Off by default (opt-in). Note that the app-wide one-handed keyboard preset (Settings, Keybindings) forces this on regardless. Synonyms: left-handed mode, one-handed nav, WASD navigation, left hand keyboard.
supermailNavHidden toggle true | false Whether the Supermail navigation sidebar is unpinned. When true (the Superhuman-style default), the persistent sidebar slot is empty and the nav is reached through a hamburger that opens an overlay drawer. When false, the sidebar is pinned permanently in the sub-sidebar slot ("Show sidebar" on). The Settings "Show sidebar" toggle is the inverse of this value. Synonyms: hide sidebar, show sidebar, pin the nav, hamburger nav, collapse navigation, folders and labels rail.
supermailNotificationPrefs object object { desktopEnabled: true | false; filter: "all" | "important" | "vip" | "off"; quietHoursEnabled: true | false; quietHoursEnd: string (≤64); quietHoursStart: string (≤64); timezone: string } A read-only mirror of the notification preferences held by your Supermail account: whether desktop notifications are on, which mail notifies you (all / important / VIP / off), and the quiet-hours window with its timezone. The Supermail server stays the source of truth — you change these on the Supermail notifications page, and Omniscio copies them here so its own notification producers stop pinging you about mail you have muted. Empty until that page is first opened, which reads as the account defaults (desktop notifications on, all mail, no quiet hours). Synonyms: supermail notification preferences, mute supermail notifications, quiet hours, which mail notifies me, supermail desktop notifications, VIP notifications, notification filter.
supermailOmniscioGrantEnabled toggle true | false In-development: when you Connect Google, also register an email-only Google consent with the Supermail backend so unified sign-in works fully without a second full sign-in. A precondition for moving Supermail into the Omniscio cloud. Headless and off by default; it needs the backend deploy configured before it does anything.
supermailReadingLayout select "standard" | "centered" | "editorial" The reading-column personality for an open Supermail email: "standard" (the default, full width), "centered" (a centered column), or "editorial" (a narrower editorial measure). A pure display preference. It is deliberately not a colour or theme setting, since Supermail follows the active app theme automatically. Synonyms: reading layout, email column width, centered reading, editorial layout, reading pane personality.
supermailReadingPaneVisible toggle true | false Whether every Supermail thread-list page (Inbox, labels, Snoozed, Follow-ups) renders as two panes, the list plus a reading pane (true, the default), or as a single full-width list where clicking a row opens the thread on its own page (false). Synonyms: reading pane, preview pane, split view, two-pane inbox, single-column list.
supermailRowHoverActions toggle true | false Master on/off for the per-row hover action strip (Mark Done and Remind Me) shown at the right of each dense Supermail inbox row. On by default. When off, the strip never renders on any row: the row keeps its metadata (the relative time still shows on hover) and the E / H keyboard shortcuts still work. The finer-grained toolbar-button controls still apply on top of this. Synonyms: row hover buttons, inbox row quick actions, hover action strip, mark done and remind me buttons.
supermailSplitInboxEnabled toggle true | false Master switch for Supermail's Split Inbox. Off by default: the inbox is a single unified list with no split scoping and no tab strip, while your configured splits stay saved on the backend and return the instant this is turned back on. On: the inbox splits into its configured lanes and tabs. Synonyms: split inbox, inbox tabs, inbox sections, unified vs split inbox, inbox lanes.
supermailSubjectWarningEnabled toggle true | false Warn before sending or scheduling a Supermail email that has no subject line, via the "Send without a subject?" confirmation. On by default as a light safety net. When off, a blank-subject email goes out immediately with no prompt. Synonyms: empty subject warning, missing subject prompt, no-subject confirmation, send without a subject.
supermailToolbarDone select "shown" | "keyboard" | "off" Visibility of Supermail's Done (Archive) toolbar button: "shown" (visible and its shortcut and command work, the default), "keyboard" (hidden but the shortcut and command still work), or "off" (hidden and disabled). Synonyms: done button, archive button, mark done, hide done, done toolbar control.
supermailToolbarFilter select "shown" | "keyboard" | "off" Visibility of Supermail's "Filter like these" toolbar button: "shown" (visible and its shortcut and command work, the default), "keyboard" (hidden but the shortcut and command still work), or "off" (hidden and disabled). Synonyms: filter button, filter like these, hide filter, filter toolbar control.
supermailToolbarFocus select "shown" | "keyboard" | "off" Visibility of Supermail's Focus-mode toolbar button, the reading-view focus toggle: "shown" (visible and its shortcut and command work, the default), "keyboard" (hidden but the shortcut and command still work), or "off" (hidden and disabled). Synonyms: focus button, focus mode toggle, hide focus, focus toolbar control.
supermailToolbarReply select "shown" | "keyboard" | "off" Visibility of Supermail's Reply toolbar button: "shown" (button visible and its keyboard shortcut and Ctrl+K command work, the default), "keyboard" (button hidden but the shortcut and command still work), or "off" (button hidden and its shortcut and command disabled). Synonyms: reply button, hide reply, reply toolbar control.
supermailToolbarSnooze select "shown" | "keyboard" | "off" Visibility of Supermail's Snooze (Remind me) toolbar button: "shown" (visible and its shortcut and command work, the default), "keyboard" (hidden but the shortcut and command still work), or "off" (hidden and disabled). Synonyms: snooze button, remind me, hide snooze, snooze toolbar control.
supermailToolbarStar select "shown" | "keyboard" | "off" Visibility of Supermail's Star toolbar button: "shown" (visible and its shortcut and command work, the default), "keyboard" (hidden but the shortcut and command still work), or "off" (hidden and disabled). Synonyms: star button, hide star, star toolbar control.
supermailTriageActionOrder list array of string (≤40) Supermail — the ordered list of enabled reading-pane triage-action ids for the customizable triage bar (the default out-of-the-box 8-button bar: done, snooze, follow-up, mark-unread, label, trash, previous, next). Empty [] is a real empty-bar state. Controls the order (and set) of the triage buttons you see when reading an email. Synonyms: triage bar order, triage actions, reading pane buttons, supermail action bar.
supermailUndoToastEnabled toggle true | false Show the Undo toast (the bottom-left snackbar) after a Supermail triage action such as Mark done, Trash, Snooze, or Spam. On by default: the toast is both the confirmation and the one-click Undo. When off, those actions apply silently, but Z / Ctrl+Z still reverses the last one within the usual 10-second window (the toast is only the visual, not the undo ability). Synonyms: undo toast, undo snackbar, undo bar, undo after archive, hide the undo popup.
supermailVideoSummariesEnabled toggle true | false In-development: auto-detects Loom and Vimeo links in a Supermail message, pulls the video transcript (auto-transcribing the audio when no captions exist), and shows a short AI summary card in the message detail when you click into the message. Off by default, and cost-capped.
teamChatSoundsMuted toggle true | false
telegramMtcuteEnabled toggle true | false The maintained mtcute engine is now the DEFAULT for Telegram. The engine choice moved to a shipped setting (Settings → Channels → Telegram engine); GramJS remains a reversible opt-out. This entry is retained as shipped so older persisted configs parse cleanly; its reveal toggle no longer gates anything.
toastPreferences object object { accountActions: true | false; agentAccess: true | false; aiCoachingProfile: true | false; aiCoachingRecords: true | false; alertActions: true | false; attentionAlerts: true | false; automationRuns: true | false; boardActions: true | false; browserActions: true | false; browserLogins: true | false; budgetAlerts: true | false; calendarEvents: true | false; clipboardCopied: true | false; deletions: true | false; deployProfiles: true | false; errors: true | false; extraUsageAlerts: true | false; general: true | false; imageStudio: true | false; inboxActions: true | false; infrastructureActions: true | false; learnMilestones: true | false; mailActions: true | false; marketplaceAutomations: true | false; marketplacePlugins: true | false; messagingActions: true | false; notesActions: true | false; projectActions: true | false; recipeActions: true | false; recordings: true | false; screenshotCaptured: true | false; sessionActions: true | false; sessionArchived: true | false; sessionExports: true | false; sessionSpawn: true | false; sessionTitles: true | false; sessionTools: true | false; settingsChanges: true | false; settingsConfirmations: true | false; setupSteps: true | false; smsCodes: true | false; statusAlerts: true | false; tasksChanges: true | false; tasksFinished: true | false; tasksTips: true | false; teamChatChannels: true | false; teamChatMessages: true | false; teamChatPeople: true | false; voiceAlerts: true | false; warnings: true | false; workspaceLayouts: true | false; workspaceTools: true | false; writerDocuments: true | false; writerSendTo: true | false } Per-category on and off switches for which kinds of toast messages are shown (errors, warnings, session actions, and so on).
trustedSheetFoldersDriveScopeEnabled toggle true | false In-development: let a Trusted Sheets folder be checked against Google Drive, which needs Google's restricted Drive metadata permission. Google has not approved that permission for this app yet, so it is only ever asked for while this is switched on. Off by default.
twilioAccountSid text string (≤64) The account ID of the Twilio account that sends your text message and phone-call alerts, the identifier that starts with AC. Text and call alert channels only work when this, the Twilio token, the sender number and your own phone number are all filled in; otherwise those channels are skipped. Empty by default. Synonyms: Twilio account ID, Twilio SID, SMS alert account, call alert account.
twilioFromNumber text string (≤40) The phone number your text messages and phone-call alerts are sent from, taken from your Twilio account. Text and call alert channels only work when this, the Twilio account ID, the Twilio token, and your own phone number are all filled in; otherwise those channels are skipped. Empty by default. Synonyms: Twilio phone number, SMS sender number, call alert number, text alert from number.
unusedQuickReplyDeclutterNudgeEnabled toggle true | false Raise one inbox card offering to remove a saved quick reply you haven't used in 30 or more days.
upworkChannelEnabled toggle true | false In-development: read your Upwork client conversations in the sidebar, reply to them, send a finished Writer Studio document from Export, and get an inbox card when a client writes. Nothing is sent unless you press Send or confirm Send to Upwork. Needs the Upwork connector signed in. Off by default.
upworkCheckEvery30Minutes toggle true | false
vendorKeyWatchEnabled toggle true | false Watch each AI vendor’s own account every hour and compare what it says was spent on your key with what Omniscio recorded. When spend appears that Omniscio did not make, raise an inbox card and a desktop notification so a leaked key is caught early. It only reads, costs nothing, and is on by default.
weeklySummaryScheduleMinute number integer 0..59 Minute of the hour (0–59) the weekly summary is generated.
whatsappEnabled toggle true | false In-development: adds a WhatsApp row of its own to the sidebar's hub list that shows WhatsApp's own WhatsApp Web inside Omniscio, in a persistent login partition used only by WhatsApp. Omniscio never reads your messages, adds no script or style to the page and never automates it; it reads only the page title for the unread count and tells the page which color scheme to use, the same signal a browser sends. This shows the regular WhatsApp Web page inside Omniscio. WhatsApp may show a warning about unofficial clients; your messages stay in WhatsApp. Not made or endorsed by WhatsApp or Meta. Off by default; hidden until shipped.
whatsappNotificationsEnabled toggle true | false In-development: while the WhatsApp row is switched on, Omniscio shows its own Windows notice ("New message · N unread") when your unread count goes up and you are not looking at the WhatsApp row. The notice never carries a sender or message text, opens the WhatsApp row when clicked, and has a button that turns this setting off. On by default; turn it off here to silence it.
zapCoachEnabled toggle true | false When on, Omniscio drops a gentle inbox card when you hand-type a phrase that already has a one-tap shortcut — your Zap (Alt+Z), a saved quick reply (Alt+S), or the "Please continue" button — naming the shortcut so you can use it next time. The inverse of the "save repeated phrases" nudge. OFF by default (opt-in); each phrase is tipped at most once.

Projects & Tasks (59)

The work you keep in Omniscio — folders, to-dos, boards, notes and your own writing.

Setting Type Accepted values What it does
decksContextTokenBudget number integer 1000..150000 How much session or project text Decks reads and summarizes when building a presentation brief. Larger means more context and higher cost. Default 20000.
decksDailyCostCapUsd number number 0..1000 Daily spending limit, in US dollars, for Decks. Default 5; 0 means no limit.
decksDefaultTheme text string (≤100) The theme new decks start with. Default is 'default'.
decksEnabled toggle true | false Turns the Decks presentation builder on or off. Off by default.
decksPremiumModel toggle true | false Use the premium, higher-cost model when Decks generates content. Off by default.
githubMcReviewNotificationsEnabled toggle true | false In-development: surfaces GitHub PR review requests (pending, approved, changes requested) on linked Mission Control item cards. Polls review state for PRs linked via cross-entity links and raises inbox alerts on changes. Off by default.
habitsEnabled toggle true | false Adds a "Habit Tracker" sidebar tab — a personal habit / daily-routine tracker (define habits by category, log each day, see streaks, a calendar grid, and trends), fully local to Omniscio. Optional daily reminders. Beta: expect the odd rough edge.
habitsRemindersEnabled toggle true | false When the Habit Tracker is enabled, whether its daily reminder nudge fires. On by default, so an enabled habit with a reminder time gets its nudge; turn off to keep habits without any reminder nudges. Synonyms: habit reminders, daily habit nudge, habit tracker notifications.
mcConnectWithXEnabled toggle true | false In-development: when you move your projects into Mission Control from another tool such as Trello, press one Connect button, click Allow in your web browser, and Omniscio picks up the key by itself instead of you copying and pasting it. You can always do it by hand instead.
pinnedSheetIds list array of string (≤200) Which spreadsheets you have pinned, remembered between restarts. A display choice only.
pmAdvisorDailyLlmCap number integer 0..∞ How many times per day the PM "quick question" advisor may escalate a template answer to a real LLM call (default 100). Once hit, no more comfort-tier escalations happen until the next day. No Settings-UI control yet; set via CLI/PATCH.
pmAdvisorDailySpendCapUsd number number 0..∞ Daily USD spend cap on the PM advisor's LLM calls (default $5). Once cumulative spend for the day hits this, further advisor LLM calls are refused until it resets. No Settings-UI control yet; set via CLI/PATCH.
pmApprovalWorkflowsEnabled toggle true | false Multi-step approval chains for board items — define serial steps with parallel approvers, three approval types (any-one, all-must-approve, majority), triggered by status column changes.
pmAutomationCostWarnEnabled toggle true | false Master switch for the PM automation cost guard — when on (default), a PM automation that crosses its daily cost threshold (pmAutomationCostWarnThreshold) logs a warning, is auto-paused for the rest of the day, and raises an alert. No Settings-UI control yet; set via CLI/PATCH.
pmAutomationCostWarnThreshold number number 0.1..100 Per-automation daily USD cost threshold for PM automations (default $1; range $0.10-$100). Crossing it, with pmAutomationCostWarnEnabled on, pauses that one automation for the rest of the day and raises an alert. No Settings-UI control yet; set via CLI/PATCH.
pmAutomationFailureThreshold number integer 2..50 How many rule failures inside the failure window trip a PM automation rule's circuit breaker and stop it firing (default 5). Synonyms: pm automation failures, when a pm rule gives up, automation circuit breaker, too many rule failures, stop a failing pm rule.
pmAutomationFailureWindowMs number integer 60000..3600000 The window, in milliseconds, that PM automation failures are counted over before a rule is tripped (default 600000, i.e. 10 minutes). Synonyms: pm automation failure window, failure counting window, how long failures count, automation breaker window.
pmAutomationMaxCascadeDepth number integer 1..20 How many rule-to-rule hops one PM event may cascade through before the chain stops (default 5), so one event cannot set off an endless chain of automation. Synonyms: pm cascade depth, automation chain length, how far automation cascades, rule to rule hops, stop an automation loop.
pmAutomationMaxEventsPerBatch number integer 10..5000 The most PM events processed in a single automation batch (default 500). Synonyms: pm automation batch size, events per batch, automation throughput cap, how many events at once.
pmAutomationRuleCooldownMs number integer 0..60000 How long, in milliseconds, a PM automation rule waits before it may fire again (default 5000, i.e. 5 seconds). Synonyms: pm rule cooldown, automation cooldown, wait between rule runs, how often a pm rule can fire.
pmAutomationSuggestionsEnabled toggle true | false Mission Control spots a follow-up you keep doing by hand on a project and offers it as a "Suggested for you" automation on that project's Automations page. Rare by design, opened pre-filled for you to review. On by default; turn it off anytime.
pmAutomationsEnabled toggle true | false Automation triggers on board item changes — when a status changes, an item is created, or a due date passes, run an action chain (notify, move item, set column value, or start a session). On by default; turn it off anytime.
pmCrossboardIntelligenceEnabled toggle true | false PM Cross-Board Intelligence
pmDataDensityEnabled toggle true | false Tracks per-domain usage density to gate PM intelligence (the "Earn the Right to Speak" system), and detects user behavior patterns like repeated status changes, recurring subtask creation, and batch workflows.
pmEmailIntegrationEnabled toggle true | false Link email threads to PM items, create tasks from emails, and trigger PM automations from incoming mail. Works across Gmail, Agent Email, and Supermail.
pmFeedSummaryConsentAckVersion number integer 0..∞ Internal bookkeeping: which version of the AI-summary privacy note you accepted, so a materially changed note is shown again.
pmFeedSummaryConsentGiven toggle true | false Remembers that you accepted the privacy note for the AI summary in the What Changed feed, so it is not shown again.
pmImportEnabled toggle true | false Unified import framework for bringing data into PM boards from external sources — Google Sheets (SOP-aware with tab/header color detection), Excel, CSV. Connected sources with scheduled refresh.
pmNotificationsEnabled toggle true | false Smart PM event notifications with session-scoped batching, per-board mute/promote, and due-date alerts. Routes PM changes to the right people through the right channels.
pmOpsDailyActionBudget number integer 0..∞ Daily cap on how many automated actions the PM autonomous ops engine may take (default 200). Hitting it raises an inbox alert and blocks further automated ops actions until the next day. No Settings-UI control yet; set via CLI/PATCH.
pmOpsEngineEnabled toggle true | false PM Operations Engine
pmOpsSessionSpawnCostWeight number integer 1..∞ What one session SPAWN costs against pmOpsDailyActionBudget, so a day of spawning is not counted as a day of cheap edits. Read by the ops engine's weighted daily-action count.
pmOpsShiftHandoffCompactEnabled toggle true | false Internal format toggle: include a compact summary in shift handoff output. No user-facing UI.
pmOpsShiftHandoffNarrativeEnabled toggle true | false Internal format toggle: include a narrative summary in shift handoff output. No user-facing UI.
pmPredictiveAnalyticsEnabled toggle true | false Velocity tracking, Monte Carlo completion predictions, what-if scenarios, three-tier pattern detection with proactive warnings, and analytics dashboard widgets.
pmProjectHolidaysEnabled toggle true | false Each project keeps one shared list of company holidays (starting with the US paid holidays), and Mission Control skips those days wherever it counts working days: the Risk Heatmap, quiet items, seasonal risk and Who's Out. Turn on once the Mission Control team server has holiday support.
pmQuietItemFlagEnabled toggle true | false Flags Mission Control items with no due date that have stopped moving ("Quiet 3 days", "Not started 1 week"), asks once whether that is normal for that kind of item, and learns from the answer and the board's own pace.
pmSprintsEnabled toggle true | false First-class time-boxed iterations for Mission Control boards — sprint lifecycle (planned, active, completed), sprint planning view, completion with velocity snapshots, and burndown tracking.
pmTimeOffCalendarImport toggle true | false Imports your away and out-of-office events from your Google Calendar so they appear as your time off in the Mission Control Who's out list. On by default. Turn it off to stop reading your calendar for time off. Synonyms: time off from calendar, import away events, who's out calendar sync, out of office import.
pmUnifiedFeedDigestEnabled toggle true | false Send a once-daily 8am digest of the unified project-management feed. Off by default; part of an in-development feature.
pmUnifiedFeedDigestTimeZone text string The IANA time zone the daily project-management feed digest’s 8am fire hour is resolved against. Captured automatically on the first run (your current host zone) so the digest keeps posting at 8am local after an OS time-zone change. Null until captured. Synonyms: PM digest time zone, project feed digest fire zone.
pmUnifiedFeedEnabled toggle true | false Unified cross-board activity timeline ranked by significance, with inline actions, daily digest, and AI summaries.
pmUsageDailyWarnEnabled toggle true | false Master switch for the PM backend API usage warning — when on (default), a 'high daily usage' alert fires once your daily PM backend call count hits pmUsageDailyWarnThreshold. No Settings-UI control yet; set via CLI/PATCH.
pmUsageDailyWarnThreshold number integer 100..50000 The daily PM backend API call count that triggers the 'High Task backend API usage' alert (default 5000; range 100-50000), when pmUsageDailyWarnEnabled is on. Counts all PM backend calls, not just automations. No Settings-UI control yet; set via CLI/PATCH.
tasksV2AlertsEnabled toggle true | false When on (the default), Tasks raises its reminder cards in your Inbox: a task is due soon, a task is due, a snoozed task is back, and time to follow up on a task you are waiting on. Turn it off to stop all four, along with the phone, email and text reminders that come with them. Snoozed tasks still come back into your list on time; they just arrive without a card. Turned off from the "Turn off these alerts" button on any of those cards, and back on in Settings → Notifications → Alert types. Synonyms: mute task reminders, stop task alerts, turn off Tasks notifications, silence due date alerts, no follow-up reminders.
tasksV2CatchLookBackDone toggle true | false
tasksV2CatchStrandedWatermark text string
tasksV2CaughtFromFathom toggle true | false
tasksV2CaughtFromFireflies toggle true | false
tasksV2CollapsedProjectIds unknown pipeline Remembers which task lists you've folded closed, so the view stays that way after a reload. Only view state, not task data.
tasksV2CollapsedTaskIds unknown pipeline Remembers which individual tasks you've folded (hiding their sub-items), so the fold survives a reload. Only view state, not task data.
tasksV2DelegationEnabled toggle true | false Hand a task to an AI helper. It writes a draft and waits for your review before anything is saved. You get an inbox card when the draft is ready, and a draft you accept is saved onto the task. Still in testing.
tasksV2Enabled toggle true | false Your to-do list: add tasks fast, sort them into projects and plan your day. Still in testing.
tasksV2KeyboardTourOfferShown toggle true | false
tasksV2PinnedProjectIds unknown pipeline
tasksV2SetupDialogShown toggle true | false
workflowFavoriteKeys list array of string (≤80) The steps and app groups you have PINNED in the Workflows step picker, in pin order. Pinned entries show first in both places you add a step — the drag rail and the "Add step" popup. Managed by the pin button in those pickers rather than a Settings toggle; a pin for a step the engine no longer offers is simply ignored. Empty by default. Synonyms: pinned workflow steps, workflow favorites, favourite nodes, pin a step to the top, my pinned workflow apps, unpin a workflow step.
workflowRecentStepTypes list array of string (≤80) The step types you added most recently in the Workflows editor, newest first and capped at a short list, so the picker's "Recent" row survives a restart instead of resetting each session. Maintained automatically as you build workflows — not something you set. Unknown or removed step types are skipped when the row renders. Empty by default. Synonyms: recent workflow steps, recently used nodes, workflow picker recents, steps I used last, clear workflow recents.
writerLastOpenedDocId text string (≤200) Internal record of which Writer document you last had open, used to reopen it automatically the next time you open Writer. Not user-facing; updated automatically every time you switch documents.

Automation & Scheduling (40)

Work Omniscio does on its own — on a schedule, on a trigger, or as a pipeline.

Setting Type Accepted values What it does
autoLanderBatchLandingEnabled toggle true | false Land several ready branches per update to your main branch instead of one at a time: the auto-lander builds one combined update, applies it in a single step, and records a separate receipt for every branch inside it, while the next candidates are prepared alongside. ON by default (unset = on); set it to false to go back to landing exactly one branch per update, unchanged. Answered from this setting alone — there is no separate stored default to keep in step with it — and an operator kill switch can also force it off. This switch does NOT cover a group hand-land. When something explicitly asks for several named branches to land together as ONE update, that request uses the batch lane even while this reads false. Turning this off therefore does not stop a group request from landing several branches in one update.
autoLanderLoadTriageEnabled toggle true | false Hand off stuck conflicts even while the machine is too busy to land, so a conflicting branch is not left un-handed-off for hours behind the load gate. Cheap, rate-limited, and it never lands under load — it only hands back. On by default (unset = on); set it to false to disable.
autoRunEnabled toggle true | false Master switch for Away Mode — when on, the away-mode engine automatically fires your away-mode rules (auto-reply, start a session, retitle, archive, add an inbox note, and so on) against sessions that need you, so Omniscio keeps working while you are away. Off by default (opt-in). The billable actions (auto-reply and start-session) are spend-capped per rule per day and by your budget caps. The engine reads this live, so toggling it takes effect without a restart. Synonyms: away mode, auto run, auto-respond, hands-free automation, run rules while away.
automationAiConditionDailyCostCapUsd number number 0..1000 Daily dollar limit for paid AI checks on incoming automation messages (default 10); 0 removes the limit.
cloudFlakeRegistryEnabled toggle true | false Persists the per-test flake identity the cloud gate already computes into a durable cross-run registry, and adds a flakiness-rate view on the cloud dashboard plus a quarantine list of chronically-flaky tests. Internal-only development tooling — no sidebar surface. On by default; turn it off in Settings → Lab. The ledger writer that runs outside the app, from the command line, has its own separate off-switch.
cronGroupLabels map map of string → string (≤80) Custom display names you've given to groups in the Cron sidebar. Empty until renamed.
customHooksEnabled toggle true | false In-development: a Hooks panel (under Agent Tools) to manage the hooks Omniscio runs in your spawned sessions — the built-in ones (Git Guardrails, Secret Paste Guard, Write-Time Lint, Agent Firewall) plus your own custom hooks (run a command at a lifecycle event such as before/after a tool, on stop, or on prompt), global with per-project overrides. Desktop-only; creating or editing hooks is human-only. Off by default; hidden until shipped.
enableCronJobs toggle true | false Show and enable the Cron Jobs area and its sidebar entry. On by default.
enableRecipes toggle true | false Show and enable the Recipes area and its sidebar entry. On by default.
featureRoadmapAutoActivityLastRunDate text string 'YYYY-MM-DD' (local) of the last date the activity append ran. Its OWN marker, not the check-in's: the two halves are independently gated, so one marker could not say which had run. Written AFTER the append, so a failed write retries on the next tick instead of writing off the day (the check-in's marker is written BEFORE its spawn for the opposite reason — a crashed session must not re-trigger).
featureRoadmapEodCheckInLastRunDate text string 'YYYY-MM-DD' (local) of the last date the end-of-day check-in successfully ran. Prevents a second trigger on the same calendar day. Written BEFORE the session is spawned so a crashed session does not re-trigger — but CLEARED when the spawn is observed to fail, so a day the check-in knows it did not deliver is retried on the next hourly tick rather than written off.
gitGuardrailsEnabled toggle true | false Omniscio-enforced git safety for agent sessions — blocks an agent from committing or pushing to a protected branch (master/main), a destructive git stash, and edits while on a protected branch, with a per-repo exclusion list + a time-boxed pause. On by default; turn it off in Settings → Features or the Dev Pipeline panel.
gitGuardrailsSelfPauseEnabled toggle true | false When on (default), an agent blocked by a git guardrail may open a brief, bounded self-pause window (up to 10 minutes, limited to 3 per hour) to unblock itself, with an inbox notice. Off: only a human can lift the block. Settings → Features → "Let an agent unblock itself briefly".
landStandardModes map map of string → "block" | "advisory" | "measured" | "off" Per-standard mode overrides for the auto-lander's landing standards. Each standard is one check a branch must pass before it lands. block refuses the land, advisory runs the check and only records its reason without blocking, measured runs the check and withholds the ready TAG — never a land — for a failure the branch itself is proven to have caused; a master-owned, unplaced or unanswered red is recorded on the tag and refused by nothing. off never runs it. Unset = every standard at its own default, which is the lander exactly as it was before this setting existed. Keys are validated against the catalogue of standards, so a misspelled one is refused rather than kept. Supersedes the older "PR checklist mode" setting for the PR-checklist standard, which is still honoured when this map says nothing about it.
nightShiftAutoMonitoringEnabled toggle true | false Night Shift — when on (the default), while a Night Shift plan runs Omniscio keeps the sessions the plan ITSELF spawned moving overnight (auto-continue, auto-nudge, and the session health monitor), scoped to those sessions only. Your unrelated and already-finished sessions are never auto-continued, nudged, or health-checked just because a plan is running, and your own global monitoring switches are left exactly as you set them. Off: Night Shift will not drive even its own sessions. Synonyms: night shift monitoring, auto-enable monitoring during plans, proactive monitoring while a plan runs, auto nudge and continue during a night shift plan, scoped session monitoring.
nightShiftUiEnabled toggle true | false In-development: an overnight plan runner. Define an ordered list of steps (spawn sessions, run recipes, wait, branch) and let it execute in order, on its own timing.
nightyTidyApplyLocation select "local" | "cloud" Chooses where a Nighty Tidy fix wave runs: on this computer, or queued as a job on the cloud worker road. The default is local. With cloud chosen, an automatic fix that has no session to hand the job to is refused rather than quietly run here. Synonyms: where fixes run, Nighty Tidy cloud or local, fix wave location, apply fixes in cloud.
nightyTidyAutoFixLevels map map of string → "off" | "critical" | "high" | "medium" | "low" | "all" Each Nighty Tidy audit's own auto-fix level, keyed by audit name: off, critical, high, medium, low or all. When a run or automation has auto-fix switched on, its fix waves start automatically only for findings at or above that audit's level, and never wider than the run or automation allows. Only audits you changed are stored; an audit with no entry uses its default — critical and high for most audits, off for the ones that would substantially change the app (dependency upgrades, UI changes, feature ideas, strategy). Edited in Nighty Tidy's Auto-fix levels window. Synonyms: auto-fix level per audit, auto spawn fix waves, which audits fix themselves, auto-fix severity, nighty tidy auto-fix, turn off auto-fix for an audit.
nightyTidyAutoRestartOnCrash toggle true | false Startup crash-recovery for Nighty Tidy 2 scheduled audits: when the app restarts after a crash, a run that was left stranded in "running" (its audit never finished) is re-queued and re-dispatched automatically instead of being marked failed. Default true (on). Set to false to reap a stranded run as failed on restart instead of re-running it. Synonyms: nighty tidy auto restart, restart crashed audits, requeue orphaned runs, resume interrupted audits.
nightyTidyConcurrencyCap number integer 1..50 The most scheduled code-audit runs allowed to run at once across all automations (1 to 50; default 8). The hard runaway guard; manual runs aren't limited.
nightyTidyCostCapUsd number number 0..1000 The nightly spending ceiling, in US dollars, for Nighty Tidy's automatic code checks across all of your automations in one cycle. 0 turns the cap off.
nightyTidyFindingsRetentionDays number integer 0..3650 How many days a finished Nighty Tidy run's stored findings are kept; 0 keeps them forever (default 90). Retention is what keeps the store bounded, and pruning is by run AGE — it never touches the run row itself, so History, cost and the report path all stay exactly as they were. Synonyms: findings retention, how long are audit findings kept, prune old findings, nighty tidy history retention, delete old audit findings.
nightyTidyFixOverseersAtOnce number integer 0..60 How many audits may have fix sessions running at the same time (0 to 60; default 1). An audit that is already fixing can always keep going. 0 means no limit.
nightyTidyFixWorkersPerOverseer number integer 0..60 How many fix sessions one audit may run at once (0 to 60; default 2). Fix sessions write code and create worktrees. 0 means no limit.
nightyTidyNightlyAuditCountLimit number integer 0..500 The most code audits that may start in one nightly cycle across all automations; 0 means no limit (default).
nightyTidyTaggerEnabled toggle true | false
prBodyCheckEnabled toggle true | false On by default. Checks that a pull request describes its real changes before it is pushed. Off skips the check.
prMergeQueueArchivedPrs unknown pipeline ARCHIVED PRs — per-PR personal dismissals, keyed by AMC projectId → the archived PR numbers for that repo. An archived PR is hidden from the queue lanes AND dropped from BOTH the inbox reviewNeededCount nudge AND the stuckCount — archiving clears a PR everywhere, stuck merges included (the I26 reversal), so dismissing a PR quiets it like archiving an email. The inbox shows one row PER attention-needing PR; dismissing that row archives just that PR. A transient "Show archived" view toggle re-reveals them (dimmed, in their lane) with an Unarchive action. Stored here (not a DB table) so the renderer reads it reactively via the settings-store and main reads it via getSettings(). Unset = nothing archived. Each repo's list is capped at 500 in the Zod schema (the map at 100 repos); orthogonal to lane (a render+count filter, never a new Lane value).
prMergeQueueBatchPromptTemplate text string (≤20000) Optional custom instructions used when an AI merges a batch of pull requests. Blank uses the built-in prompt.
prMergeQueueMergePromptTemplate text string (≤20000) EDITABLE MERGE PROMPTS (global). Optional operator overrides for the prompt sent to a single-PR / batch merge session. When set + non-blank AND it keeps every anchor its own type requires (REQUIRED_MERGE_PROMPT_ANCHORS for the single-PR prompt, REQUIRED_BATCH_MERGE_PROMPT_ANCHORS for the batch one, in shared/pr-merge-queue-prompt-templates.ts — the reviewed-head placeholder and the never-touch-base / never-push / never-force-push guardrails), the template is rendered (with {{token}} substitution) INSTEAD of the built-in default in pr-merge-queue/prompt.ts; an override MISSING an anchor is skipped and the next candidate (or the built-in default) is used, recorded only as a merge-time log warning. A per-repo override (PrMergeQueueRepoConfig.mergePromptTemplate / batchPromptTemplate) takes precedence over these. Unset = use the built-in default (recommended — the default is the version that never touches master). A saved custom prompt is a frozen copy and won't receive future default edits; Reset-to-default in Settings re-syncs it. Capped 20000 chars.
prMergeQueueRepos list array of object { baseBranch: string (≤120); batchPromptTemplate: string (≤20000); ghSlug: string (≤140); mergePromptTemplate: string (≤20000); name: string (≤120); projectId: string (≤100); riskyPaths: array of string (≤300); standingInstructions: string (≤4000); trustLevel: "pause-and-ask" | "fast-lane-only" | "autonomous" } One entry per AMC project that opts into the queue. Each entry pairs an AMC project ID with a GitHub repo slug, so the queue knows which sessions to spawn (project-scoped) and which repo's PRs to triage.
prPrepPromptCustomRules text string (≤10000) CUSTOM RULES for the AUTOMATIC PR-prep prompt — the EASY way to add standing rules without rewriting the whole prPrepPromptTemplate (and having to preserve its load-bearing anchors). When set + non-blank, this text is appended to the END of the effective prompt (under an advisory "Your custom rules" header) that the scheduled "PR prep (auto)" cron gives every session — see appendCustomRules / resolveEffectivePrepPromptTemplate in shared/pr-prep-prompt.ts. It is ADDITIVE: applied on top of the built-in default OR a full override (even an invalid one, which still falls back to the safe default), and it can only ADD text — never remove an anchor or weaken the never-push-master guardrail. Unset/blank = zero change (today's behavior). Capped 10000 chars.
prPrepPromptTemplate text string (≤30000) EDITABLE AUTOMATIC PR-PREP PROMPT. Optional operator override for the prompt the scheduled "PR prep (auto)" cron gives each session it spawns to prepare an open PR for merge (this is the prompt driving your automatic PR merging, NOT the in-app queue's merge prompts above). When set + non-blank AND it keeps every one of the four load-bearing anchors (REQUIRED_PREP_PROMPT_ANCHORS in shared/pr-prep-prompt.ts — the {{pr_number}} placeholder, the ready-to-merge hand-off, the pipeline success marker, the never-push-master guardrail), the main process serves it to the cron over GET /pr-prep/effective-prompt; an override MISSING an anchor is ignored and the built-in default is used instead, so a bad edit can never silently break merging. Unset = built-in default. Reset-to-default in Settings re-syncs a custom copy. Capped 30000 chars (the default is ~15k).
prReplyDelivery select "prefer-original" | "always-restart" | "card-only" Who handles a reply to a note the app posted on a pull request: 'prefer-original' tries the original session then falls back to a fresh one or a card; 'always-restart' always starts fresh; 'card-only' only raises a card. No reply is ever dropped.
prReplyRestartMaxSessions number integer 1..20 How many paid reply-handling sessions one sweep may start. This is a per-sweep spawn budget, not a limit on how many are live at the same time; replies past it wait as inbox cards instead of starting more paid sessions. Default 3.
prSpawnerEnabled toggle true | false Master switch for handing pull-request work to agents. Off by default; flip it off by hand when the machine is busy.
recipeConcurrencyWarningEnabled toggle true | false Show a one-time 'shared account capacity' warning when you start a recipe while another is already running. On by default.
recipeDefaultCostCapUsd number number 0..1000 Default dollar limit applied to any recipe that doesn't set its own, so a run can't spend without a ceiling; hitting it pauses for your approval. 0 removes the limit.
worktreePinLeaseStartedAt text string
writeTimeLintHookEnabled toggle true | false Format + lint each file an agent writes, feeding fixes back to the agent. Off by default.

Knowledge & Memory (23)

What Omniscio remembers — your vault, its memory, and what it captures for you.

Setting Type Accepted values What it does
clipboardHistoryAutoPaste toggle true | false When you pick an item in the Win+V picker, auto-paste it into the app that had focus (best-effort: writes the clipboard ALWAYS, then synthesizes Ctrl+V only when it can safely target the prior foreign window). Default true; off = copy-to-clipboard only (you press Ctrl+V). Windows-only. Read as ?? true.
clipboardHistoryEnabled toggle true | false A clipboard-history button in the chat composer that keeps your recent copies (text + images) so you can re-insert them. Captured in memory and cleared when Omniscio restarts — unless you opt into keeping it across restarts (saved encrypted on this PC).
clipboardHistoryHotkey unknown string (≤100) | array of string (≤100) Global hotkey (Electron accelerator) that summons the standalone clipboard picker window from anywhere. Default 'CommandOrControl+Alt+V' (= Ctrl+Alt+V) — NOT Win+V, which Windows reserves for its own clipboard history so Electron's globalShortcut.register always fails on it; Ctrl+Alt+V registers cleanly and coexists with the OS Win+V. Only auto-registers on Windows and only while the clipboard-history feature is visible; the picker window + auto-paste are Windows-only in v1. Read as settings.clipboardHistoryHotkey ?? 'CommandOrControl+Alt+V'. Existing installs are rebound off the stale Win+V default once by migrate-clipboard-history-hotkey-default-for-existing-users. See global-hotkeys.ts.
clipboardHistoryHotkeyEnabled toggle true | false Per-hotkey on/off for the clipboard picker global hotkey. Default true (so turning the feature on gives you the Ctrl+Alt+V picker). Read as ?? true.
clipboardHistoryPersist toggle true | false Keep the clipboard history across app restarts. Default TRUE — once the clipboard feature is on, the full history (text + images + pins) is saved to disk ENCRYPTED at rest (safeStorage / DPAPI, machine-bound) and reloaded on the next launch; turning it off — or turning the whole clipboard feature off — deletes the saved file, and each launch drops anything older than the 14-day memory. Sensitive copies are never captured, so they are never persisted either. Desktop-only.
nothariAgentToolsEnabled toggle true | false Retired: no longer changes anything. The per-session Vault tools it switched on were removed; agents reach your notes through the app's own Vault routes, and sessions started in the Vault read and edit its Markdown files directly.
nothariAgentWriteToolsEnabled toggle true | false Retired: no longer changes anything. It only ever applied to the retired per-session Vault tools, so the switch has no effect; agents reach your notes through the app's own Vault routes.
nothariAggregationTimeZone text string The IANA time zone the Knowledge (KMS) daily/weekly aggregation digest hours + weekly day are resolved against. Captured automatically on the first run (your current host zone) so the off-peak digest keeps firing at the intended wall-clock after an OS time-zone change. Null until captured. Synonyms: KMS digest time zone, aggregation fire zone.
nothariAggregationWeeklyHour number integer 0..23 The hour of day (0-23, local time) the weekly knowledge-vault digest runs. Default 6 (6am).
nothariChecklistStrikethrough toggle true | false On by default. Checked checklist items get a strikethrough and dimmed text.
nothariEditorShortcuts map map of string → string (≤100) | array of string (≤100) Your custom keyboard shortcuts for the knowledge-vault editor's formatting actions (lists, code blocks, strikethrough, and so on).
nothariFileWatcherEnabled toggle true | false On by default. Whether the knowledge vault watches its folder and picks up changes made outside the app.
nothariImageAnalysisCostCapUsd number number 0.5..20 KMS — the cap, in plain US DOLLARS, on manually-triggered AI image analysis of vault images. Default $2, range $0.50-$20. Enforced as the bulk handler's pre-spawn check, so a run can overshoot by at most one image's billed cost (about $0.05). In dollars, unlike nothariAggregationCostCapMicroUsd. Synonyms: kms image analysis cap, analyze images budget, vault image ai cost limit.
nothariImageAnalysisModel text string (≤120) The AI model used to analyze images added to the knowledge vault.
nothariMinimalDiffSaveEnabled toggle true | false Saves change only the parts of a note you edited. Turn off to go back to whole-note saves.
nothariQuickReferenceCompleted toggle true | false Internal bookkeeping: remembers you have finished the vault's first-time quick-reference tour so it does not auto-open again. Not a setting to change.
nothariRecentCommands unknown pipeline Internal remembered state: the knowledge-vault commands you used most recently, newest first. Not a setting to change.
nothariRightPaneOpen toggle true | false Whether the knowledge vault's right-side panel drawer is open. Closed by default.
nothariRightPanePanels map map of string → object { collapsed: true | false; order: integer 0..100 } Internal remembered state: the collapsed state and order of each panel in the vault's right-side stack. Not a setting to change.
nothariSaveDiskCheckEnabled toggle true | false Before saving, check the note file was not changed by another program.
nothariShortcuts map map of string → string (≤100) | array of string (≤100) Your custom keyboard shortcuts for the knowledge-vault panel's commands. Blank an entry to disable that command's shortcut.
nothariStarterContentSeeded toggle true | false Internal bookkeeping: remembers whether the vault's starter notes have been created. Not a setting to change.
nothariVaultOwnerAccountId text string

AI Features (355)

The AI surfaces beyond a plain session — coaching, writing help, voice and media.

Setting Type Accepted values What it does
aiBrowserActiveSpaceId text string (≤256) Internal bookkeeping: remembers which browser Space you were last viewing so the app reopens it on relaunch. Not a setting to change.
aiBrowserEnabled toggle true | false Turns the in-app Browser panel into a full browser for you: tabs, spaces, bookmarks, history, downloads, saved passwords, and AI tools that work on your own tabs. Agents do not drive this panel. They browse in their own Agent Web browser, or in your everyday Chrome through My Real Chrome — Lite.
aiBrowserMemoryIngestEnabled toggle true | false Whether each page you visit in the browser is added to Memories search. On by default; turn off to stop indexing new pages (existing memories are kept).
aiBrowserSideChatWidth number integer 280..560 Internal remembered state: the last width you dragged the side chat panel to. Not a setting to change.
aiBrowserTabArchiveAfterHours number integer 1..720 Hours of inactivity before an ordinary browser tab is auto-closed (its page stays in history). Pinned and favorite tabs are exempt. Default 24.
aiBrowserTabDiscardAfterMinutes number integer 1..10080 Minutes of inactivity before a sleeping tab is fully discarded (its scroll position is lost and reopening is a cold load). Default 120.
aiBrowserTabLifecycleEnabled toggle true | false Master switch for the tab memory-saving ladder (auto-sleep, discard, and archive). On by default; off keeps every tab fully loaded forever.
aiBrowserTabSleepAfterMinutes number integer 1..1440 Minutes of inactivity before a background browser tab is unloaded to save memory. Its address, title, and scroll position are kept. Default 15.
aiBrowserTabStripOrientation select "horizontal" | "vertical" Whether browser tabs appear in a vertical left-side strip (default) or the classic horizontal strip along the top.
aiCoachingEnabled toggle true | false Personalized coaching sessions with structured interviews, artifacts, and progress tracking.
aiCoachingFeedbackDismissed toggle true | false Remembers that you ticked "Don't ask again" on the AI Coaching feedback pop-up. Retired: it is carried over once to "Ask for feedback after sessions" and no longer read.
aiCoachingPromptVariant select "A" | "B" | "C" Which version of the AI Coaching wording to use for its persona and greeting messages: A (original), B (revised), or C (a mix).
aiExtrasJobPicks object object { replyDrafts: "openrouter" | "anthropic" | "openai" | "gemini" | "credits" | "allowance" | "deepseek"; suggestions: "openrouter" | "anthropic" | "openai" | "gemini" | "credits" | "allowance" | "deepseek"; summaries: "openrouter" | "anthropic" | "openai" | "gemini" | "credits" | "allowance" | "deepseek"; titles: "openrouter" | "anthropic" | "openai" | "gemini" | "credits" | "allowance" | "deepseek" } A per-job override for the AI-extras key order: pick one key to pay for a single job — titles, suggestions, reply drafts or summaries — while every other job keeps following your main order. An empty slot means that job follows the order as usual. Settings → API keys → AI extras. Synonyms: ai extras per job, pick a key for titles, override key order for one job, suggestions use a specific key, reply drafts payer, per-helper key choice.
aiExtrasKeyOrder list array of "openrouter" | "anthropic" | "openai" | "gemini" | "credits" | "allowance" | "deepseek" Which key pays for the built-in AI helpers — titles, suggestions, reply drafts and summaries — tried top to bottom until one works. You list your own provider keys first and the Omniscio allowance as one row, or reorder to prefer a different payer. Read leniently, so a missing or partial list can never strand a helper. Settings → API keys → AI extras. Synonyms: ai extras key order, which key pays for titles, order my api keys, provider key priority, ai helper billing order, own key before omniscio credits.
aiManager object object { aiRouterDefaultOnForNewSessions: true | false; aiRouterDryRunByDefault: true | false; allowApiKey: true | false; dailyCapUsd: number 0..100; inboxPilotEvaluatorFallbackEnabled: true | false; inboxPilotEvaluatorFallbackModel: string (≤200); inboxPilotEvaluatorModel: string (≤200); inboxPilotEvaluatorProvider: "groq" | "together" | "deepseek" | "openrouter" | "openai" | "anthropic"; overlay: object { enabled: true | false; prompt: string (≤75000) }; overlayAllowApiKey: true | false; overlayDailyCapUsd: number 0..100; overlayDefaultOnMigrated: true | false; overlayDefaultToPlainSpeak: true | false; overlayForcedOffMigratedV2: true | false; overlayInlineAgentGenerated: true | false; overlayInlineDefaultMigrated: true | false; overlayPauseRetirementMigratedV1: true | false; overlayPaused: true | false; overlayPromptMigratedV8: true | false; overlayPromptPreV8Backup: string (≤75000); overlayResetBannerPending: true | false; overlayShipOnMigratedV1: true | false; overlaySkipPatterns: array of string (≤200); paused: true | false; router: object { enabled: true | false; prompt: string (≤75000) }; routerAllowApiKey: true | false; routerAutoRespondEnabled: true | false; routerDailyCapUsd: number 0..100; routerPaused: true | false; routerScheduleRespondEnabled: true | false; splitMigrationApplied: true | false } Advanced settings for the AI Manager: the rules that decide how it responds, its daily spending limit, and whether it is paused.
aiProjectIconsEnabled toggle true | false In-development: adds a searchable icon picker, a "Suggest with AI" button and a "Fill missing icons with AI" batch action, plus three ways for a session to make a CUSTOM icon — draw it in code, preview it at real sidebar sizes, or generate one image sheet and split it into tiles. The AI picks a bundled brand mark, an icon from the free library, or a matching colour. On-demand only, never automatic; suggesting is a cheap AI call, and only an image generation spends. Off by default; hidden until shipped.
aiSuggestionsEnabled toggle true | false Turn on AI smart-reply suggestions in the chat composer.
aiSuggestionsEnabledAt text string (≤100) Internal bookkeeping: the date and time smart-reply suggestions were switched on, used to estimate their running cost. Written automatically — not a setting to change.
aiWriterEnabled toggle true | false In-development: a standalone writing editor with saved documents, writing guidance, and (in later updates) inline AI editing, options, autocomplete, and a chat assistant.
appWorkspaceSwitcherEnabled toggle true | false In-development: a compact workspace switcher at the top of the Hubs sidebar. It lists every workspace you belong to (Personal first, then your organizations and chat workspaces) and switches which one the app is scoped to, which filters the sidebar to that workspace. Switch-only (no create or join); off by default; hidden until shipped.
appleSttEnabled toggle true | false In development: transcribe your voice with Apple's own speech engine, right on your Mac — free, offline, and your audio never leaves the computer. Needs macOS 26 or newer. When it is on, the voice settings on a Mac gain an "Apple (on this Mac, free)" speech option.
arijEnabled toggle true | false Reveals the Arij Jira-style issue tracker, which is hidden by default.
arijProjectFolders unknown pipeline Arij backend project id → local working folder. Arij projects live on Omniscio's cloud backend and carry no local path, but spawning an agent on an issue needs a folder to work in — this map supplies it (set via the pick-folder prompt on first agent start per project).
askAboutPageEnabled toggle true | false A toolbar button + Ctrl+J open a popover that asks Claude about whatever is on screen. Reveals the keybinding, the button, and the popover mount.
askPageConsentAckVersion number integer 0..∞ Remembers which version of the privacy notice for the Ask about this page feature you have accepted. The first-use consent screen is skipped once your accepted version is current, and shown again if the notice changes. Starts at 0, meaning not yet accepted. Synonyms: ask page privacy consent, accepted notice version, consent acknowledgment, ask about this page agreement.
askPageConsentGiven toggle true | false Remembers that you accepted the privacy prompt for "Ask about this page" so it is not shown again.
autoNudgeEnabled toggle true | false Nudge a session that reaches its waiting limit, up to three times, instead of surfacing it to you right away.
broadcastEmbedEnabled toggle true | false In-development: a broadcast card can embed a full live web page (a Shares-hosted page with forms + JavaScript) rendered inline in an isolated sandbox, made to look native. A new security surface, so it rolls out deliberately. Hidden until shipped.
broadcastTargetingEnabled toggle true | false In-development: target a broadcast at specific signed-in people, organizations, or custom groups (in addition to the platform / plan / version filters), and manage reusable recipient groups. Hidden until shipped.
browserEnabled toggle true | false Turns on the built-in browser panel and its sidebar entry. Off by default. Your saved logins and cookies survive turning it off and back on.
browserLoginsEnabled toggle true | false Log into a website once and keep that login on this computer. Open a Browser tab already signed in with it, or import it into Agent Web (Settings → Agent Web → Saved logins) so your agents can use it. Local-only; no passwords are stored.
bugIntakeSessionsEnabled toggle true | false In-development: shows the fix sessions Bug Intake spawned inside the Bug Intake panel, and opens a session chat beside the list instead of sending you off to hunt for it in the sidebar. Hidden until shipped.
chatAnswerRetiresQuestionCardsEnabled toggle true | false When you answer an agent's question directly in the chat, the matching question cards waiting in your inbox are marked answered and archived for you. On by default. Turning it off leaves those cards in your inbox until you clear them yourself. Synonyms: auto-clear question cards, answered question cards, retire inbox questions, answer in chat clears inbox.
coachingBridgeDigestEnabled toggle true | false Off by default. When on, sends a weekly AI coaching digest on Sunday evening summarizing the week's coaching sessions.
coachingCategories map map of string → true | false Which categories of AI coaching tips are switched on; each category has its own on/off.
coachingDailyMessageStyle select "motivational" | "coaching" | "mindfulness" | "stoic" | "humor" | "gratitude" | "challenge" Which category of rotating quote shows in the AI Coaching dashboard's daily greeting banner: motivational, coaching, mindfulness, stoic, humor, gratitude, or challenge (default motivational). Chosen from the style picker beside the dashboard's daily greeting.
coachingVaultMirror toggle true | false AI Coaching — when on, coaching artifacts are mirrored as markdown notes in your KMS vault (the knowledge base panel), so each session's coaching output lands in your notes. Opt-in and off by default; requires KMS enabled and a vault configured. Synonyms: coaching notes to vault, mirror coaching artifacts, save coaching to KMS, coaching output as markdown.
composedSessionViewsEnabled toggle true | false In-development: a List / Board / Grid picker above the session list, with board (status columns) and grid views composed from the new session-view primitives. No visible change when off. Hidden by default; enable it in Settings to preview.
composerRichText toggle true | false
contextDockBgRefreshEnabled toggle true | false Keep the Context Dock's content refreshed in the background so it is already up to date when you open it.
continuousSummaryAgentPromptTemplate text string (≤50000) Custom wording for the AI prompt that summarizes agent activity (what it did and asked). Leave empty to use the built-in default.
continuousSummaryDailyCostCapUsd number number 0..100 Daily spending limit in dollars for the continuous session summary. Once today's spend reaches it, live summaries pause until midnight. 0 turns it off.
continuousSummaryEnabled toggle true | false Turns on the Catch-Up Card, a short pinned summary at the top of a session that is waiting for you, so you can see what it was asked and what it did without scrolling. Off by default. Turning it off removes the card and stops the summary calls. Synonyms: catch-up card, session summary, pinned summary, needs you summary.
continuousSummaryLastAskedPromptTemplate text string (≤50000) Custom wording for the AI prompt that summarizes your most recent message. Leave empty to use the built-in default.
continuousSummaryModel text string (≤200) Chooses which Claude model writes the Catch-Up Card summaries. When left unset, the app uses its default Sonnet model. Pick a different model here if you want cheaper or stronger summaries. Synonyms: catch-up card model, summary AI model, summarizer model, which model summarizes.
continuousSummaryOriginallyLengthCap number integer 50..10000 Sets how many characters of your first message are kept as the fallback Originally line on the Catch-Up Card when the AI summary of it fails. Allowed range is 50 to 10,000 characters, and it is 1,000 by default. Synonyms: originally length limit, fallback summary length, first message cap, catch-up card character limit.
continuousSummaryOriginallyPromptTemplate text string (≤50000) Lets you replace the instructions used to summarize your first message into the short Originally line on the Catch-Up Card. When empty, the built-in instructions are used, which is the default. Reset it to go back to the standard wording. Synonyms: originally prompt, summary instructions, catch-up card prompt, custom summary wording.
continuousSummaryRecentTurnsVisible number integer 1..5 Sets how many recent back-and-forth turns the Catch-Up Card shows. A value of 1 shows only the current turn, and larger numbers add earlier turns, up to 5. The default is 1. Synonyms: catch-up card turns, how many turns shown, summary history depth, recent turns count.
continuousSummaryShowAgentSummary toggle true | false Adds Did and Asks rows to the Catch-Up Card that summarize what the agent did and what it is waiting on. This also runs an extra AI call to write them. Off by default, so only the Originally and Last asked rows show. Synonyms: agent summary rows, did and asks, catch-up card agent section, show what agent did.
councilDailyDollarCap number number 0.05..50 Daily spending limit in dollars for AI Council runs; runs stop once the day's council spend reaches it.
councilDefaultModels text string (≤500) The default AI models the AI Council uses, chosen as a comma-separated list.
councilWizardCompleted toggle true | false Remembers that you finished the AI Council setup wizard, so it never interrupts you again.
councilWizardShowWelcome toggle true | false Keep showing the "What is an AI Council?" intro before the setup wizard even after you have completed it. Off by default so the intro stays hidden once you are set up.
customFormatBlock text string (≤10000) The editable text of the Standard Formatting Block — the formatting standard Omniscio injects into the first message of each session so the agent formats its responses to be easy to skim. Leave blank to use the built-in default; edit it in Settings → Questions → Developer. Turn the block on or off with customFormatBlockEnabled. Synonyms: response formatting, formatting standard, scannable output, custom format instructions.
customShareUrlEnabled toggle true | false Everyone can set a memorable custom name for a shared page — e.g. shares.omniscio.com/s/my-report — instead of the random link id, plus an optional short omnisc.io/<code> link.
customSnoozeShortcuts list array of object { enabled: true | false; id: string (≤64); pattern: string (≤200); replacement: string (≤200) } Your own snooze shortcuts: each is a pattern that expands into a phrase when you type it (for example a short code for "tomorrow morning").
dailyJournalEnabled toggle true | false A daily inbox nudge to run a short journaling check-in (and a weekly review) with your AI coach. Entries stay private to coaching and never leak into your other sessions. Requires AI Coaching.
defaultReportStyle text string (≤64)
defaultScreenCapturePresetId unknown catch Which saved recording preset Quick Capture uses. Blank means the built-in default of main screen plus the remembered webcam and default mic.
devinOrgId text string (≤200) Optional Devin organization ID, used when connecting a Devin account. Not a secret.
dismissedPluginCapabilityCards list array of string (≤256) Plugin ids whose read-only Plugin Capability Card the user has permanently dismissed. The card (a one-line "this plugin can act with AI" disclosure that rides on plugin-ai-native-cli) shows once per plugin until its id lands here. Default []. Read as settings.dismissedPluginCapabilityCards ?? [].
featureDiscoveryNudgeEnabled toggle true | false Retired: a daily inbox nudge that pitched an Omniscio feature you had not used yet. Off and hidden for everyone; the code is kept, and only the env reveal turns it back on for testing.
fileConverterEnabled toggle true | false A standalone file converter — drag or pick a file, choose a target format, and convert it on-device (documents, images, audio/video). Free, local, nothing uploaded. Works on desktop and mobile.
fileSearchEnabled toggle true | false A Files tab in the Ctrl+K search that finds any file or folder on this Windows computer by name as you type. Powered by the free Everything app.
fixerOverseerCrew text string (≤100) Names the crew whose overseer answers a background fixer session that ends its turn on a question. The default is Fixer Fleet. If no live crew has that name, nothing is routed and the question is handled as before. Synonyms: fixer question routing, fixer crew name, overseer for fixers, who answers fixer questions.
flowchartEnabled toggle true | false In-development: a standalone visual flowchart editor — shapes and connectors, swimlanes, auto-layout, a saved library, and AI sessions that can read and draw on the board.
foldAutoWaitNoticesEnabled toggle true | false Fold the repeated auto-wait notice rows for one waiting episode into a single count (like "Auto-waited 3x") instead of showing each one.
gauntletLoopEnabled toggle true | false In-development: run a goal through the Gauntlet, where several builder agents each write an attempt, fresh blind critic agents score every attempt against a concrete bar, and it loops until a builder passes or hits the round or cost ceiling. v1 handles text goals (a written artifact); it spawns paid sessions and is cost-capped per run. Off by default; hidden until shipped.
geminiSttEnabled toggle true | false In development: transcribe your voice with Google's Gemini 3.5 Transcribe Live. When it is on, the in-app microphone gains a "Google Gemini 3.5" speech option. It uses your own Gemini API key if you have added one; without one, dictation runs on ours instead, which needs you to be signed in. This flag does NOT gate FlowVoice (OS-wide dictation): its speech engine is chosen in FlowVoice's own settings.
githubCodeSearchEnabled toggle true | false Adds a "Code Search" sidebar tab to search code across your GitHub repositories and open matches in the file viewer.
githubCommitLinkingEnabled toggle true | false Automatically links git commits that reference Mission Control items (e.g. MC-42) to those items, showing commit activity on the item card.
githubIssueCreateEnabled toggle true | false Adds a "New issue" button to the GitHub Issues tab so you can create issues (with labels and assignees) without leaving Omniscio.
githubIssuesEnabled toggle true | false Adds a "GitHub Issues" sidebar tab to browse, comment on, and close or reopen GitHub issues across all your repos.
githubPrLinkingEnabled toggle true | false Automatically links GitHub PRs that reference Mission Control items (e.g. MC-42 in the PR title) and shows live PR status badges on the board.
githubReleasesEnabled toggle true | false Adds a "GitHub Releases" sidebar tab to view a repository's releases and create a release (draft by default) without leaving Omniscio.
grokSttEnabled toggle true | false In development: transcribe your voice with xAI's Grok speech-to-text. When it is on, the voice settings gain a "Grok (xAI)" speech option. It reuses your existing xAI API key (the SAME key as Grok voice output) and bills to your own key.
grokbotBotName text string (≤100) The name Omniscio uses for itself when it hands a task to Grok Bot. It becomes the start of each new Grok Bot conversation's name. The default is Omniscio. Synonyms: grok bot name, grok hand-off name, bot display name, grok conversation prefix.
helpdeskAutopilotEnabled toggle true | false On by default: the legs that write to a REPORTER. A second judge clears a report the safety screen could not read, and the person who reported something is told on their own ticket when their fix lands and again when it ships, with no one typing it. Turning this off puts a person in front of every customer note. It does NOT decide whether a confirmed bug is fixed without asking — that is its own switch, "Fix confirmed bugs without asking".
helpdeskAutopilotJudgeBlocks toggle true | false On by default: the quality check reads every automatic note before it goes out and holds back anything it is unsure about. Left on, a note reaches a reporter only when the check is confident; turned off, the check still reads every note and writes its score to the log, but the note goes out anyway. The checks that always block are unaffected either way: an unfinished draft, an internal name, a release promise we cannot make, a ticket a person already answered, and a thread whose reporter never sees it.
helpdeskAutopilotRepliesEnabled toggle true | false On by default: the note a reporter gets when their fix lands, and again when the release carrying it ships. Turning this off stops ONLY those notes — the autopilot still releases held reports and retries held tickets, which is what the main autopilot switch also stops, and that was the problem this switch exists to fix. The main switch above still turns everything off.
helpdeskAvailability select "online" | "offline" Your manual helpdesk availability for other developers. What they see is this setting combined with a recent heartbeat; if the app is closed it counts as offline.
helpdeskAvailabilityOfflineUntil text string
helpdeskDevConsoleEnabled toggle true | false Developer-only: its own sidebar row for the admin console that lists user-escalated questions, so the developer can reply from inside Omniscio. Separate from the customer Get Help seat — either can be on without the other — and it also needs the admin entitlement. Stays in development even after Helpdesk ships.
helpdeskEmailTicketIntakeEnabled toggle true | false Turns a plain-English inbound support email (no [BUG:]/[FR:] subject marker) into a real Help Desk ticket with its own lifecycle and a two-way email binding, instead of only answering it. Its own switch — separate from the "Get Help" panel above. Claude only ever drafts a reply; a human presses send.
helpdeskEnabled toggle true | false In-app "Get Help" panel: ask a question in plain English and get an AI answer grounded in the app docs.
helpdeskInvestigationModel select "default" | "claude-worker" | "claude-basic" | "deepseek-v4.1-flash" | "deepseek-v4-flash" | "deepseek-v4-pro" | "crofai/deepseek-v4-flash" | "crofai/deepseek-v4-pro" Which engine runs the autonomous investigation Omniscio starts for each incoming ticket — ONE choice covering every intake source: the Help Desk console, an inbound support email, Sentry, an in-app report, and GitHub. Defaults to DeepSeek V4.1 Flash, a cheaper engine chosen for the short, mechanical triage these investigations do; the Claude options need no third-party account, and "Claude — your default model" is what every intake used before this setting existed. If the engine you pick cannot start a session right now — no key saved, or no balance left — the investigation falls back to your account default instead of being dropped, so a ticket is never left uninvestigated. Bug Intake → Intake settings → "Investigation engine". Synonyms: help desk investigation model, which model investigates tickets, ticket investigation engine, deepseek investigations, cheap model for support tickets, intake investigation model, model for help desk tickets, sentry investigation engine.
helpdeskLeadPushEnabled toggle true | false The moment a help desk ticket needs a person — a new report or a reporter follow-up — the app messages the Help Desk crew lead straight away, and again every 15 minutes until the ticket is answered. A crew with no live lead leaves one card in the inbox instead. On by default; switching it off leaves every ticket in the console queue exactly as before.
helpdeskPlanAutopilotEnabled toggle true | false On by default: once a bug report has been confirmed and the fix is small, contained and touches nothing guarded, the plan is approved without waiting for you. Anything risky still waits — database changes, sign-in and security, money and billing, deleting data, cloud deploys and dependency changes — and every feature request waits for you too. This switch only decides plans: it can never send a word to a reporter.
helpdeskResolutionSurveyEnabled toggle true | false On by default: when you resolve a Help Desk ticket, the note the reporter gets carries one line asking them to rate the help from 1 to 5. A reporter with three or more tickets in the last 30 days, or one already asked in the last 30 days, is never asked. Turning this off stops new questions; a rating sent back for a question already asked is still recorded, and nothing else about resolving a ticket changes.
helpdeskTicketAgentLocation select "cloud-first" | "local" Where the agent for each Help Desk ticket runs. "Cloud first" (the default) starts it on a cloud machine when one is free and on this computer when none is. "This computer" always starts it here. Bug Intake → Intake settings → "Where ticket agents run". Synonyms: ticket agents in the cloud, run help desk agents locally, ticket investigation location, cloud or local ticket agent.
helpdeskTicketGroupId text string The mission group every new Help Desk ticket agent reports into, given as the group id (the Missions screen shows it). Leave it empty (the default) and ticket agents stay exactly where they are today. When it names a live group, a ticket agent starts as a member of that group: its finished turn and any question it asks reach whoever leads the group instead of your inbox, it opens with the group name and where it stands, and it is told not to archive itself. The group is looked up fresh for every ticket, so when the overseer is replaced the next ticket follows the new leader with no change here; an id that names no group, or a group that has ended, just starts the ticket as today and says why in the log. A ticket handled by a crew joins that crew and never this group. Set it in Bug Intake → Intake settings, or over the local control API. Synonyms: ticket group, tickets join the mission group, help desk overseer group, route ticket agents to a lead, ticket agents report to my overseer, mission group for tickets.
helpdeskTicketInvestigationEnabled toggle true | false On by default: a ticket that arrives in the Help Desk queue starts ONE read-only investigation session for it — the agent reads the ticket and reports back what it found and what it recommends, and changes nothing until you say go. One per ticket, capped per day. Turning this off stops the automatic start only: the Start session control on a ticket keeps working.
helpdeskTicketRouting select "crew" | "agent" | "human" Who handles each new Help Desk ticket, read fresh for every ticket so a change applies to the next one with no restart. "Help Desk crew" (the default) starts one investigation per ticket inside the Help Desk crew, where its overseer runs it. "One agent per ticket" starts one independent session per ticket on the Investigation engine, in no crew; its finished turn comes to your inbox, and it may answer the customer itself, on its own ticket only, through the agent-reply road (whether that reply waits for you follows "Agent replies wait for my approval"). "A person" starts no agent at all: the ticket waits in the Help Desk console for someone to pick it up. Emailed bug reports, GitHub issues and your own in-app reports keep their crew until they join the ticket inbox. Bug Intake → Intake settings → "Who handles new tickets". Synonyms: help desk routing, one agent per ticket, ticket routing, who handles tickets, no overseer for tickets, route tickets to a person, help desk overseer off, independent ticket agents.
helpdeskVisitorMapEnabled toggle true | false A live city-level map of the people currently in a helpdesk chat, for help admins. No longer behind its own toggle — it lives in the console Insights & Routing menu and is gated by the helpdesk developer console (admin only), like the Routing manager. Visitor consent is enforced backend-side.
hibernationHoldStallExemptEnabled toggle true | false Stops a session that is deliberately asleep, waiting for its scheduled wake, from being flagged as possibly stuck. This avoids false alarms after your computer sleeps for hours. On by default. Turning it off judges a sleeping session like any other waiting one. Synonyms: sleeping session stuck warning, hibernation hold, may be stuck false alarm, idle stall exemption.
hideBackgroundAckEnabled toggle true | false Hide the short "background task finished" status message a session emits when its own background work completes. On by default; "Show system messages" reveals them.
imageStudioNativeEnabled toggle true | false Native image generation panel (replaces the embedded website). Off by default; hidden until shipped.
inboxAutoCheckInEnabled toggle true | false Automatically check in on a session that already surfaced to your inbox and has sat untouched, up to three times.
inboxAutoCheckInMultiple number integer 1..10 The multiple of the waiting period (autoWaitMinutes) a surfaced session must sit UNTOUCHED in your inbox before inboxAutoCheckInEnabled auto-checks-in. Effective dwell = this × autoWaitMinutes (e.g. 2 × 30 = 60 min). Range 1–10, default 2. When no value is saved, 2 is used.
intakeCrewTargetsBySource map map of string → string (≤100) Which crew an intake investigation is born into, keyed by the source the report arrived on: Sentry errors go to the Sentry crew by default, and every Help Desk source — console tickets, the emailed-in ones, in-app reports and GitHub issues — goes to the Help Desk crew. An investigation with no crew has exactly one place its finished turn can land — your Needs-You inbox — so this is what routes a finished investigation to the lead who owns that source instead. The EMAIL lane is rostered too, and safely: a mailed-in ticket is answered by the agent-email reply path, and a crew member normally has its final held as an overseer update — so a member that still owes its reporter an answer is deliberately NOT parked and NOT routed to its lead. It keeps the route its reply needs until the reply is out, and checks in like the others only after that. Your inbox gains no rows from this either way: a mailed-in ticket already landed in Needs-You before this, and now only the ones still owing a reply still do. A source with no entry here is simply never enrolled, which makes this table the on/off switch per source. Synonyms: intake crew, which crew do investigations join, route investigations to a crew lead, sentry crew, help desk crew, keep intake out of my inbox, investigation reporting target.
isolatedComposerEnabled toggle true | false Keep the chat composer's text separate from the session's streamed output, which keeps typing responsive. On by default.
jarvisBriefingPromptOverride text string (≤10000) Optional custom prompt for writing the spoken session briefing. Blank uses the built-in prompt.
jlsImageStudioAppEnabled toggle true | false
jlsMcpGatewayRoutingEnabled toggle true | false In-development: sends JLS Image Studio image requests through Omniscio's shared billing instead of your own personal access key, so they are charged to the credits on your Omniscio account. If forwarding fails for any reason, it falls back to your personal key, so turning it on cannot break anything. Off by default; hidden until shipped.
journalEnabled toggle true | false A private daily journal. Today asks you one question written for your life; answer it, write freely or choose a topic. It sends one gentle nudge a day, at 8:00 PM unless you change it. Entries are stored on this computer, not synced to other devices, and are searchable and taggable. Two switches in Settings → Apps → Journal decide whether your writing is sent to your AI for replies and whether the AI Coaching coach can see your recent entries. An AI agent on this computer can open your entries only after you approve that agent.
journalNudgeAskedAt text string
journalNudgeQuietDays list array of string
journalNudgeQuietSince text string
journalNudgeTimeChangedAt text string
journalNudgeTimeConfirmed toggle true | false
journalOpenedAt text string
journalTrashWindowSince text string
keepWaitingMinutes number integer 5..240 SEPARATE window (minutes) for the inbox "Keep waiting" button — how long one deliberate press re-arms the silent wait AFTER a wait_timeout surfaced the session. Its OWN knob, distinct from autoWaitMinutes (the initial wait + background-task hold + auto-nudge cadence): default 30, range 5–240. The button label and the armed window both read this, so they can't disagree. When no value is saved, 30 is used.
labsBadgeEnabled toggle true | false Example in-development feature: shows a small "🧪 Labs" badge in the app so the gating mechanism can be proven end to end.
lifeInventoryEnabled toggle true | false A structured self-assessment inside AI Coaching — rate yourself across two inventories (Symptoms and Strengths) and Omniscio quietly folds a summary into your coaching profile. Your answers are saved on this computer. A short summary is sent to the AI service with every coaching session you start, and your coach can open the full detail during coaching.
linearIssueSessionIds unknown pipeline
linearTeamProjectIds unknown pipeline
localChatEnabled toggle true | false In-development: chat with a local AI model running on your own PC via Ollama — free, private, offline. Includes a guided setup that detects Ollama, recommends a model for your machine, and downloads it.
localSttEnabled toggle true | false In development: speak to Omniscio with no API key. A small speech model runs on your own computer, free. When it is on, the voice settings gain a "Built-in (free)" speech option, and speaking works out of the box even before you add any key.
masterDebtAutoFixerEnabled toggle true | false In-development: watches the master branch for accumulated debt (failing checks, flagged findings) and either drops an inbox card asking you to fix it, or — when you turn auto-fix on — spawns fix sessions for you. Hidden until shipped.
mcChatBotChannelId text string (≤128) The Team Chat channel id the Mission Control bot posts into. Empty means no target channel is set, so the bot stays silent until one is chosen. Set it over the CLI (/mc/team-chat/bot/config). Synonyms: bot channel, MC bot target channel, where the bot posts.
mcChatBotEnabled toggle true | false Master switch for the Mission Control team-chat bot — when on (and Mission Control is enabled), the bot posts operational alerts and periodic board-health digests from your Mission Control boards into a Team Chat channel. Off by default; configured over the CLI (/mc/team-chat/bot/config), no Settings-UI toggle. Synonyms: mission control bot, MC bot, team chat bot, enable ops alerts, board alerts on/off.
mcChatBotMode select "event-driven" | "digest" | "both" What the Mission Control bot posts: "event-driven" (fire an alert only when something needs attention — a board goes at-risk, a cascade or pattern is detected, or health drops), "digest" (only a periodic board-health summary), or "both". Defaults to event-driven. Synonyms: bot mode, alerts vs digest, event vs summary posting.
mcChatBotSeverityThreshold select "info" | "warning" | "critical" The minimum severity an event must reach before the Mission Control bot posts it: "info" (post everything), "warning" (skip info-level), or "critical" (only the most serious). Defaults to warning. Synonyms: bot severity filter, alert threshold, how noisy the bot is.
mcChatBotWorkspaceId text string (≤128)
mcChatBotWorkspaceKind select "org" | "workspace"
meetingEnhanceModel text string The AI model used to clean up and enhance meeting notes. Leave empty to use the default fast model.
meetingEnhanceOpenAiModel text string The OpenAI model used only when there is no Anthropic key but an OpenAI key is set. Leave empty for the default (gpt-4o-mini).
meetingsAutoEnhance toggle true | false When on, the AI meeting-notes enhancement pipeline runs automatically right after a meeting capture finishes, instead of waiting for you to click 'Enhance'. Off by default. No Settings-UI control yet; set via CLI/PATCH.
meetingsAutoStopOnInactivity toggle true | false On by default. Stops a live meeting recording after 15 minutes of silence and saves the transcript, then shows a Resume alert you click to continue.
meetingsConsentAckVersion number integer 0..∞ Internal bookkeeping: the version of the recording-privacy notice you last accepted. A policy change bumps it to ask for consent again. Not a setting to change by hand.
meetingsConsentAcknowledged toggle true | false Legacy recording-consent flag kept for backward compatibility; an old 'true' counts as consent to version 1. Current consent is tracked by the newer version field.
meetingsEnabled toggle true | false Record meetings (mic + system audio), auto-transcribe, and get AI-enhanced notes. Beta: expect the odd rough edge.
meetingsEnhanceDailyCapUSD number number 0..100 Per-day spending ceiling in US dollars on the PAID AI generation that turns raw meeting notes into enhanced notes (the Anthropic/OpenAI completion). A generous runaway backstop, not a usage limiter: once cumulative enhance spend for the day reaches this amount, a cache-miss or a forced regenerate is refused with a friendly message until tomorrow. Default 5.00; range 0 to 100. Set it to 0 to disable paid note enhancement entirely. Twin of meetingsTranscribeDailyCapUSD (the live meeting-transcription spend cap). Synonyms: meetings enhance daily cap, enhanced notes budget, AI meeting notes spend limit, cap meeting note generation cost.
meetingsJargonTerms text string Comma-separated internal terms (product names, people, codenames) to help meeting transcription and cleanup recognize them. Empty by default.
meetingsMutedDetectApps list array of string Call apps (by name, like 'Zoom') you have silenced from the auto-detect picker, so the detector skips them. Takes effect without a restart.
meetingsMyRecipeIds list array of string The meeting recipes you added to 'My recipes' from the library. They appear as quick recipe chips on Chat home and My notes.
meetingsMyTemplateIds list array of string The shipped meeting-note templates you have hearted into 'My templates'. Seeds the template list in the enhance dropdown.
meetingsRecentRecipeIds list array of string The meeting recipes you ran most recently, newest first, shown in the 'Recent' area. Kept up to date automatically.
meetingsTranscribeDailyCapUSD number number 0..1000 A daily dollar ceiling on live meeting transcription (default $20, 0 = no cap). Once hit, new recordings save notes only. A runaway-cost backstop, not a usage limit.
metaSttEnabled toggle true | false Transcribe your voice with Meta's Muse Voice Transcribe. On by default — the voice settings gain a "Meta Muse Voice Transcribe" speech option. It needs its own Meta Model API key and bills to that key; turn this off to hide the option.
mindmapColorMode select "dark" | "light" | "system" The default light/dark/system theme for a Mind Map that has no per-map color-mode override of its own (default 'system' — follows your OS/app theme). Each map's own toolbar color-mode choice overrides this. No Settings-UI control yet; set via CLI/PATCH. Synonyms: mindmap color mode, mindmap dark mode default, mind map theme default.
mindmapDottedBackground toggle true | false Whether a Mind Map shows a dotted background grid behind its nodes (default off). Toggled from the show/hide dotted-background button in the Mind Map toolbar. Synonyms: mindmap dotted background, mind map grid, dots on mindmap canvas.
mindmapEnabled toggle true | false A standalone mind-mapping canvas — build a tree of ideas with the keyboard and mouse, lay it out automatically, save it to a library, and export it as a picture (PNG), JSON, Markdown or a Mermaid diagram. ON by default; turn it off here to hide Mind Map everywhere.
mindmapFullScreen toggle true | false Whether a Mind Map opens in its full-screen overlay layout instead of docked beside the chat (default off — docked). Toggled from the full-screen header button on an open Mind Map; remembered for next time you open one. Synonyms: mindmap full screen, mind map overlay mode, expand mindmap.
mindmapSessionSplit toggle true | false Whether an open Mind Map shows split-view beside its chat session (default on) or the map alone with chat hidden. Toggled from the split-view button above the Mind Map sidebar tabs; desktop only. Synonyms: mindmap split view, show map and chat together, hide the map chat only.
mindmapSplitWidth number number 320..900 The pixel width of the Mind Map split-view panel, remembered from the last time you dragged its divider (default 460; range 320-900). A remembered layout size, not a toggle you set directly — drag the mind-map/chat divider to change it. Synonyms: mindmap split width, mind map panel width.
mindmapVisualTheme select "app" | "glassmorphism" | "linear" | "warm-charcoal" | "aurora" | "soft-depth" | "neon" | "spotify" | "luxury" | "gradient-sidebar" | "neumorphic" | "frosted-tiers" | "vercel" | "liquid-glass" | "aurora-glass" | "macos" The default visual theme (node/edge color scheme) for a Mind Map that has no per-map theme override of its own (default 'app' — follows the app's own theme). Each map's own Palette menu choice overrides this per map. No Settings-UI control yet; set via CLI/PATCH. Synonyms: mindmap visual theme, mind map color scheme default, mindmap palette default.
mobbinMcpEnabled toggle true | false When on, adds the Mobbin design-research tool to your sessions, with its sign-in handled for you.
mobileCreateOnSendEnabled toggle true | false On your phone, tapping New Session opens a draft composer right away and only creates the real session when you first send. On by default.
mobileMicDiagnosticEnabled toggle true | false In-development: a mobile diagnostic that plays a tone while the mic is open and measures whether the mic stays active, how much it hears the tone itself (self-trigger), and whether it hears your voice — $0, pure client-side. Hidden until shipped.
mobilePortraitLockEnabled toggle true | false Lock the installed mobile app to portrait on Android so it does not rotate. iOS cannot be locked this way.
mobileSessionNavArrowsEnabled toggle true | false Show previous/next session arrows in the mobile session header.
mobileSetupRailEnabled toggle true | false On a phone, show the logo and every new-session setup pick together in one block just above the message box. Turn it off to restore the previous setup card.
modelProxyUrl text string (≤500) Web address of the local model proxy (the base URL the redirected Claude tool connects to). Leave empty if you are not running a proxy.
moreRepliesBelowIndicatorEnabled toggle true | false Show the "N more replies below" scroll hint when real replies are below what you can see.
multiModelCouncilEnabled toggle true | false Ask one question to a panel of AI models; a judge model synthesizes a single best answer.
narrationDailyCapUSD number number 0..100 Daily dollar safety cap for spoken narration audio. Set to 0 to turn narration audio off.
narrationEnabled toggle true | false In-development: a spoken-audio recap of each completed reply — the audio sibling of Plain Speak. When on, the agent writes a short spoken script that plays back per message (optionally auto-playing new replies). Hidden until shipped.
narrationPlaybackRate number number 0.5..2 Playback speed of spoken narration audio, from 0.5x to 2x (1.0 is normal). Does not re-generate the audio.
narrationVoiceReplyEnabled toggle true | false In-development: after the AI reads its spoken recap, a mic button on the message opens a window where you talk, see your words transcribed, and send them back to the session as your reply. Reuses the built-in voice input; requires Voice Input on. Hidden until shipped.
nativeSlashCommandsEnabled toggle true | false Type slash commands like /model, /clear, /cost, /context and /status in the chat composer and have them run for real in Claude Code — switching the model live, clearing context, or showing real cost/usage — instead of being sent to the model as text.
onboardingChecklistCompleted list array of string (≤100) The onboarding checklist items you have completed.
onboardingGuardianEnabled toggle true | false An invisible AI that quietly watches the Setup v2 flow and the interactive tour and offers a gentle hint ONLY when you appear stuck, occasionally acting to help (highlight a control, open a panel). It otherwise stays completely out of the way. On by default; you can turn it off anytime.
onboardingGuardianFreeUserFundingEnabled toggle true | false In-development: lets Omniscio pay for the invisible Onboarding Guardian’s AI when you are on a free plan, so setup help still works before you have connected a provider. Off until it has been tested with real users. Bounded per person.
onboardingTourEnabled toggle true | false A scripted, spotlighted product tour that runs after onboarding — it walks you through sessions, the inbox, replying, reading, and starting new work on a demo workspace. Off by default; the toggle stays live to turn it back on with one setting flip.
overlayFeedbackEnabled toggle true | false Show the "report bad overlay" flag button on the Plain Speak overlay header.
peopleMemoryEnabled toggle true | false In-development: the Mirror's sibling — it reads the full email history of the people you actually write to and builds a running dossier on each one: a short read on who they are, how they are wired, how to work with them, and what is going on with them right now, plus a scannable list of key facts. It appears as a "What I know" panel next to each conversation in Supermail, and one tap forgets a person for good. Bots, newsletters and no-reply senders are never profiled, and someone you have barely written to gets nothing rather than a guess. To write a dossier, the messages it is written from — that person's words in your mail — are sent to our AI provider to be read; the dossier itself is stored on your machine, wipes on Gmail sign-out, and is cost-capped. Off by default; hidden until shipped.
phoneControlEnabled toggle true | false In-development: gives agents a set of mobile_* tools to drive an Android device — tap, swipe, type, take screenshots, install apps, and more — via the @mobilenext/mobile-mcp MCP server. Requires adb (Android Debug Bridge) and the mobile-mcp runtime; both are auto-provisioned on first enable. Off by default; hidden until shipped.
plainSpeakActionEmojisEnabled toggle true | false Show a small emoji before each recommended action label in Plain Speak (for example a box for Archive, an hourglass for Wait).
playwrightMcpEnabled toggle true | false When on, gives your sessions the Playwright browser-automation tool, added to each session for you.
pluginAiDailyCostCapUsd number number 0..1000
pluginAiImagesEnabled toggle true | false Lets a plugin you allowed ask Image Studio for a picture, paid from your credit. You confirm the price of every picture, and each plugin has its own daily limit.
pluginAiNativeCliEnabled toggle true | false Lets the Omniscio AI and CLI invoke an installed app's own actions through its registered CLI endpoints (ctx.cli.handle), including nested multi-segment paths. No UI surface — it gates a control-server route.
pluginCalendarAccessEnabled toggle true | false In-development: lets plugins you approve read and change events on the Google and Outlook calendars you pick.
pluginDocumentsIoEnabled toggle true | false In-development: let an installed app open a normal "choose a file" window, read the file you pick, and add to the end of it — how a PDF viewer would save your notes back into your own PDF. It only ever gets the files you pick yourself, never a folder and never a location on your computer, and each pick is fixed at the time you make it as read-only or read-and-add. An app can also ask to REMEMBER a file you picked, so it can reopen that one file later without asking again — it has to ask your permission once before it may remember anything, you can see every remembered file and take any of them back under Settings → Apps, and turning an app off forgets them all. On by default — every install, new or existing, has it on; turning it off darkens the whole capability in Main, so nothing can read or write your files.
pluginImageDailyCapUsd number number 0..100
pluginInboxReadEnabled toggle true | false In-development: lets plugins you approve see the titles of your open inbox items and sessions waiting on you.
pluginPeopleReadEnabled toggle true | false In-development: lets plugins you approve see when the people in your workspace work and when they are away.
pluginSessionControlEnabled toggle true | false In-development: lets plugins you approve message, pause, unpause, snooze, archive and unarchive the sessions and projects you pick.
pluginSessionsRails map map of string → object { folded: true | false; panelOpen: true | false; width: integer 0..2000 }
pluginTeamChatEnabled toggle true | false In-development: lets plugins you approve read the Team Chat channels and direct messages you pick, and post, reply, react and send direct messages there after you approve each one.
pluginUiContributionsEnabled toggle true | false Lets installed apps add their own buttons to the header toolbar and session menus, and navigate the app to a session, project, or view. App chrome is desktop-only — the phone/WS bridge blocks app navigation and dispatch over the wire.
pluginVaultAccessEnabled toggle true | false In-development: lets plugins you approve read and change the notes in the Vault folders you pick.
pluginWorkDataEnabled toggle true | false In-development: lets plugins you approve read and change the Mission Control boards and task lists you pick.
prVisualEvidenceEnabled toggle true | false Coding-agent sessions attach before/after UI screenshots to their GitHub PR.
proAnnualBillingEnabled toggle true | false In-development: adds a monthly/annual choice to the Pro card on Plan & Usage, so a customer can buy the $192/year plan the Terms advertise (about 20% off the monthly price). ON by default alongside the storefront — the Terms advertise the annual plan, and the choice stays turn-off-able in Settings. It becomes BUYABLE only once the gateway has a live STRIPE_PRO_ANNUAL_PRICE_ID: without it every annual checkout returns "not available", so a customer would see a priced offer they cannot buy. Set that price id on BOTH the gateway and firebase-functions deploys — the gateway sells the plan and firebase grants it, so a partial config would charge someone $192 and leave them on Free.
proSubscriptionEnabled toggle true | false A Plan & Usage screen to see your plan, compare Free vs Pro, upgrade to Pro ($20/mo) via Stripe, bring your own API key, and track your monthly AI allowance.
proactiveSpeechAwayAfterMinutes number integer 0..240 Go quiet once you have been away from the computer this many minutes, so Omniscio is not talking to an empty room. Measured from the operating system's own idle timer, so it keeps counting while the app is in the background. 0 (the default) turns the away rule off entirely; the maximum is 240 minutes. Applies only to speech you did not ask for; anything you explicitly request still plays. Synonyms: stop talking when I am away, idle timeout for speech, do not speak to an empty room, away gate for read-aloud, mute speech when idle, how long before it goes quiet.
proactiveSpeechQuietHoursEnabled toggle true | false When on, Omniscio stays silent during your quiet hours — it will not speak anything you did not ask for (read-aloud, narration, the spoken briefing, voice report-back). Anything you explicitly ask it to say still plays. Off by default, because these settings gate speech that already ships and a non-neutral default would change read-aloud for everyone. Pair it with proactiveSpeechQuietHoursStart and proactiveSpeechQuietHoursEnd. Synonyms: quiet hours for speech, stop talking at night, do not speak after hours, mute read-aloud overnight, silence proactive speech, no talking while I sleep.
proactiveSpeechQuietHoursEnd text string When the speech quiet-hours window ENDS, as a local 24-hour HH:MM time (default 07:00). Only has an effect while proactiveSpeechQuietHoursEnabled is on. The window wraps midnight when the start is later than the end. Setting start and end to the same time means an EMPTY window, not all day. Synonyms: quiet hours end time, when can it talk again, end speech quiet hours, silence speech until, no-talking end time.
proactiveSpeechQuietHoursStart text string When the speech quiet-hours window BEGINS, as a local 24-hour HH:MM time (default 22:00). Only has an effect while proactiveSpeechQuietHoursEnabled is on. The window wraps midnight when the start is later than the end — 22:00 to 07:00 is the usual case. Setting start and end to the same time means an EMPTY window, not all day. Synonyms: quiet hours start time, when should it stop talking, begin speech quiet hours, silence speech from, no-talking start time.
profileMinerEnabled toggle true | false Master switch for the Profile Miner ("The Mirror") — when on (and Supermail is enabled on the amc-gmail path with Google connected), it periodically mines your Gmail (via the Supermail mirror) into typed, evidence-backed profile SIGNALS — facts, preferences, relationships, goals, problems, needs — each with a short supporting quote from the email. Signals land as proposed and can be reviewed / promoted into the AI Coaching profile. Off by default; controlled over the CLI (/profile-miner/* routes), no Settings-UI toggle. Synonyms: profile miner, the mirror, mined signals, contact profile mining, email signal mining, propose contact facts.
projectWorkspaceMoveEnabled toggle true | false When on (default), a hub can be moved between your Personal workspace and the company workspace you are signed into with PATCH /project/:id/workspace {"workspaceId": "personal" or the org id}; the move keeps the hub pin, divider and position. App hubs (the built-in panels) belong to every workspace and are never moved. Off: the route refuses every move with 403 and nothing changes. CLI only for now: PATCH /settings/projectWorkspaceMoveEnabled. Synonyms: move hub to workspace, move project to company workspace, change project workspace, file a hub under the org, workspace of a project.
pullRequestsEnabled toggle true | false Surfaces the GitHub pull requests waiting on you — review requested from you, plus your own with changes requested — as rows in the unified Inbox.
qwCorpusEnabled toggle true | false Turn on the QW full corpus (the training data and classifier pipeline used for triage, calibration, and backfill). Off by default.
realChromeBridgeV2AgentSessionWritesEnabled toggle true | false Whether Omniscio agent sessions may ACT in your real Chrome through "My Real Chrome v2" — open tabs, click, type, fill forms, press keys and navigate — rather than only read it. On by default (owner order, Nov 11 2026). Covers every live session of this install, including crew workers, leads, spawned sessions and scheduled runs; a caller that is not a live session of this install is always refused. Site rules, tab ownership, the on-page banner and the per-session drive log still apply to every write. Turn it off to leave agents read-only. Desktop-only. Synonyms: let agents click and type in chrome, agent writes real chrome, real chrome read only, stop agents typing in my browser.
realChromeBridgeV2DriveAnyTabEnabled toggle true | false Opt-in for the publishable "My Real Chrome v2" that lets Omniscio agents see and drive ANY tab in your real Chrome — including tabs you opened yourself — not just tabs the agent created. Off by default; it WIDENS the data-safety boundary (an agent could then drive your email or banking tab), so turn it on only when you need an agent to reach a pre-existing tab. Every tab an agent drives shows a loud "Omniscio AI is controlling this tab" banner, and turning the setting off immediately releases (never closes) any of your tabs the agent had grabbed. Desktop-only. Synonyms: v2 drive any tab, real chrome v2 any tab, attach an existing tab v2, reach my login tab v2.
realChromeBridgeV2DrivePopupsEnabled toggle true | false Opt-in for the publishable "My Real Chrome v2" that lets Omniscio agents drive a popup opened by a tab the agent itself created — the typical "Sign in with Google" / OAuth popup flow. Off by default. Your existing tabs are never touched by this setting. Desktop-only. Synonyms: v2 drive popups, real chrome v2 oauth popup, agent sign-in popup, drive login popup.
realChromeBridgeV2Enabled toggle true | false In-development: "My Real Chrome — Lite" lets agents work in your everyday, signed-in Chrome, through Agent Web. Its Chrome extension needs no high-risk debugger permission, so it can be approved for the Chrome Web Store and other extensions (LastPass, etc.) do not break it. It has limits: clicks and typing are simulated, it cannot upload files, and screenshots show only the visible tab. By default an agent works only in the new tabs it opens, every tab an agent drives shows a clear banner on the page, and you choose which sites it may use (and can take that back). Desktop-only. Hidden until shipped.
recurringSpecialEventsEnabled toggle true | false Add birthdays, anniversaries, and holidays that create Google Calendar events plus lead-time reminders (day-of, a week before, a month before, or any number of days before).
reflectionNudgeEnabled toggle true | false A once-per-weekday inbox nudge, at a random but timely moment, to reflect on what you just did and how an Omniscio agent could take more of it off your plate. "Let's talk about it" opens a chat that brainstorms and can hand off to the automation builder or Foundry. Off by default.
replayDisconnectSessionNeutralEnabled toggle true | false When a connection drops in the middle of a turn and the app resends that turn, the resend does not use up the turn's limited allowance of replays. On by default. Turning it off counts such resends against the allowance like most other replays. Synonyms: mid-turn disconnect replay, replay budget, reconnect retry limit, dropped connection resend.
reportConversationsEnabled toggle true | false Every report sent from the feedback dialog also opens a Help Desk conversation, so support can reply inside the app. Replies show under "Your reports" even when Get Help is off; the AI assistant never answers them. On by default; you can turn it off anytime.
reportTrackerEnabled toggle true | false In-development: adds a Report Tracker tab inside the Bug Intake panel so you can see the status of every submitted report — triaged, in-flight, or resolved — without leaving the panel. Hidden until shipped.
routeInternalAiThroughGateway toggle true | false Send the app's own AI calls (titles, suggestions, reply drafts, sorting) through the cloud service using your signed-in account instead of built-in keys. On by default; turning it off restores the direct-key path.
screenCapturePresets unknown catch Your saved recording presets: full scenes with sources, positions, sizes, crops and audio that 'Record with this preset' reproduces. Internal stored list; manage it from the recorder.
screenCaptureProjectsEnabled toggle true | false A "Projects" tab in the Screen Capture library for multi-asset compositions: combine clips from many captures into one timeline and export them as one video, instead of editing a single recording at a time.
screenCaptureTemplates unknown catch Your saved recording templates: reusable layouts without sources, where applying one asks you to pick a source for each slot. Internal stored list; manage it from the recorder.
screenRecorderAutoSummaryNoticeShown toggle true | false Whether the one-time notice about the automatic summary has been shown on this machine. It starts false: the first finished take with speech raises that notice instead of sending a summary, so the summary never reaches a cloud model before the person has been told. It does not gate transcription: with the cloud dictation engine selected, the take's audio has already been sent for captions under the setting above. The notice's own button turns the automatic pass off; this marker only records that it was shown. Synonyms: summary notice, cloud AI disclosure, first summary notice.
screenRecorderCamEnabled toggle true | false Record with the camera at all. ON is the shipped default — every road that picks a camera from a REMEMBERED or DEFAULT device id keeps recording it, exactly as it did before this setting existed. OFF means those roads record no camera: a remembered/default camera id is IGNORED (never cleared, so turning this back on brings the same camera back). A scene you built and handed in — the Record composer, a saved preset, an agent request that asked for a webcam — carries its own camera and is untouched by this. Synonyms: camera on, camera off, record with camera, disable webcam, no camera in recordings, privacy, camera privacy.
screenRecorderCaptionFontScale number number 0.5..2 How large the burned-in captions are, as a multiple of normal size (0.5x to 2x). Default 1.
screenRecorderCaptionPosition select "bottom" | "top" Where captions sit on the video, 'bottom' or 'top'. Default bottom.
screenRecorderCaptionsEnabled toggle true | false Show burned-in subtitles on the video, both in the preview and in the saved file. It only works after you have generated a transcript. Off by default.
screenRecorderCaptureEngine select "auto" | "legacy" | "webcodecs-1"
screenRecorderDefaultCamId text string (≤200) The webcam chosen by default in the one-click recording setup. Blank means none chosen yet.
screenRecorderDefaultCanvasPreset select "1080p" | "4k" | "vertical" | "square" The SHAPE a zero-click Quick Record's canvas takes: 1080p (landscape, the shipped default), Vertical or Square. Set once in the Recording-defaults dialog; a recording made from a saved preset uses that preset's own size instead. The PIXELS come from screenRecorderResolution — note '1080p' here no longer means 1080 pixels any more than it means 1080 lines; it means "landscape", and Vertical / Square are the only values that own their canvas. '4k' is accepted so a config that stored it keeps parsing, but nothing writes it: both it and '1080p' read as landscape. Synonyms: recording output size, recording canvas shape, vertical video, square video, quick record size.
screenRecorderDefaultMicId text string (≤200) The microphone chosen by default in the one-click recording setup. Blank means none chosen yet.
screenRecorderDefaultMicMuted toggle true | false Start a recording with the microphone muted (you can unmute it from the recording controls). Set in Recording defaults; New recording opens with it. Off by default. Synonyms: start muted, mic muted at start, begin recording muted.
screenRecorderDefaultScreenCornerRadius number number 0..0.5 How round the screen's corners are when the default screen shape is Rounded, as a fraction of the screen's shorter side. Synonyms: screen roundness, corner radius.
screenRecorderDefaultScreenFit select "fit" | "fill" How a screen sits in the recording when its shape differs from the output size: Fill (cover the frame, cropping the edges — the shipped default) or Fit (show the whole screen with bars). Only visible for Vertical / Square output or an unusual monitor. Synonyms: screen fit, letterbox, crop screen, show whole screen.
screenRecorderDefaultScreenShape select "rect" | "rounded-rect" | "circle" The corner shape of the recorded screen in a Quick Record or a New recording once Recording defaults are saved: Square (a plain full-frame rectangle — the shipped default), Rounded or Circle. Distinct from screenRecorderVideoShape, which only shapes a take that has no scene layout. Synonyms: screen shape, rounded screen, screen corners.
screenRecorderDefaultSourceId text string (≤200) The screen or window chosen by default for one-click recording. Blank means the primary screen is used automatically.
screenRecorderDefaultSourceType select "screen" | "window" Whether the default recording source is a whole 'screen' or a single 'window'. Blank means the primary screen is used automatically.
screenRecorderDefaultSystemAudio toggle true | false Record your computer's system audio by default. On by default.
screenRecorderDefaultSystemAudioMuted toggle true | false Start a recording with system sound captured but muted. Set in Recording defaults; New recording opens with it. Off by default. Synonyms: start with computer sound muted, system audio muted at start.
screenRecorderDefaultWebcamPosition select "top-left" | "top-right" | "bottom-left" | "bottom-right" | "center" Which corner the camera overlay sits in for a zero-click Quick Record: bottom-right (the shipped default), bottom-left, top-right, top-left or Centre. Only applies when a camera is chosen. Synonyms: webcam position, camera corner, where the camera sits, move the webcam overlay, webcam placement in the recording.
screenRecorderDefaultWebcamSize select "small" | "medium" | "large" How large the camera overlay sits in a zero-click Quick Record: Small, Medium (the shipped 240px) or Large. Only applies when a camera is chosen, and it sizes the corner picture-in-picture only — never the camera's own capture resolution. Synonyms: webcam size, camera overlay size, how big the camera is in the recording, webcam PiP size.
screenRecorderDefaultsConfigured toggle true | false Internal flag: whether you have set up your one-click recording defaults yet. It controls the first-run prompt and is not usually changed by hand.
screenRecorderDeviceNames unknown catch Internal memory: the names of the cameras and microphones your recordings have used, so a saved camera or microphone is found again by its name when the computer gives it a new ID. Not a setting to change by hand.
screenRecorderEngineEnabled toggle true | false
screenRecorderFmp4Capture toggle true | false On by default. When on, a screen recording that has no camera or layout is captured straight to fragmented H.264 MP4 instead of VP9 WebM, so pressing Stop only repackages the file (a remux) rather than re-encoding it a second time — Stop finishes several times faster, and the video goes through one lossy encode instead of two. A recording with a camera or layout ignores it, and when this build of the recorder cannot record H.264 the take falls back to the normal WebM path by itself. There is no Settings control for it yet; change it with the CLI settings route. Synonyms: fmp4 capture, h264 screen recording, mp4 capture, remux on stop, faster stop for screen recordings, record straight to mp4, fast recording save.
screenRecorderFrameRate number integer 15..60 Frames per second captured (15, 24, 30 or 60). Higher is smoother but makes larger files. Default 30.
screenRecorderHudAnchor object object { x: number; y: number } Where you last dragged the floating screen-recording bar, saved relative to the work area it was dropped on so it reappears correctly when a monitor changes. Never dragged is the default, and the bar opens centred near the top. Internal display state written as you drag; there is no need to set it by hand. Synonyms: recording hud position, where the recording bar sits, move the recording bar, floating recorder bar location.
screenRecorderLastCamId text string (≤200) Internal memory: the last webcam you used, so Quick Record can reuse it. Not a setting to change by hand.
screenRecorderLastMicId text string (≤200) Internal memory: the last microphone you used, so Quick Record can reuse it. Not a setting to change by hand.
screenRecorderLastMicMuted toggle true | false Remembered flag for whether the microphone was muted in your last screen recording, used to seed the next Record composer. Default false. Part of remember-my-setup. Synonyms: last mic muted, remembered microphone mute.
screenRecorderLastSourceId text string (≤200) Internal memory: the last screen or window you captured, so Quick Record can reuse it. Not a setting to change by hand.
screenRecorderLastSystemAudio toggle true | false Remembered flag for whether system (computer) audio capture was on in your last screen recording, used to seed the next Record composer. Default false. Part of remember-my-setup. Synonyms: last system audio on, remembered computer audio capture.
screenRecorderLastSystemAudioMuted toggle true | false Remembered flag for whether the captured system audio was muted in your last screen recording, used to seed the next Record composer. Default false. Part of remember-my-setup. Synonyms: last system audio muted, remembered computer audio mute.
screenRecorderRegionEnabled toggle true | false Offer Region as a way to record: drag a rectangle on a screen and only that part of it is recorded. ON out of the box. Turning it OFF removes the Region choice from the recorder and refuses every region take — one picked in the recorder, one inside a saved preset, and one an agent asks for — while recording a whole screen or a window carries on exactly as it did before this setting existed. A saved preset that holds a region is kept, not deleted, so switching this back ON brings it back. Synonyms: record part of the screen, record an area, record a selection, region recording, crop recording, partial screen recording.
screenRecorderResolution select "native" | "1440p" | "1080p" | "720p" How many pixels a recording is captured and saved at, shown as the "Output size" row beside Quality: Source resolution (the screen's own pixels — the shipped default, so text stays crisp), 1440p, 1080p or 720p. The chosen resolution is never upscaled past what the display can deliver. Vertical and Square remain separate shape presets and ignore this setting. Synonyms: recording resolution, recording size, capture resolution, output size, native resolution, 1080p recording, 1440p recording, 720p recording.
screenRecorderRetentionDays number integer 1..3650 How many days recordings are kept before auto-deletion when retention is set to delete by age. Default 30.
screenRecorderRetentionMaxGb number number 1..10000 The largest the recording store may grow, in gigabytes, before the oldest recordings are trimmed in size mode. Default 50.
screenRecorderRetentionMode select "off" | "age" | "size" When to auto-delete recordings: 'off' never; 'age' deletes recordings older than a set number of days; 'size' trims the oldest once the store is too big. Off by default, and shared recordings are always kept.
screenRecorderStorePath text string (≤500) Folder where recordings are stored. Blank means the app's default. Only change this through the app's safe move action, never by hand.
screenRecorderUseIndependentHelper toggle true | false On by default (Windows only). When on, screen recordings are captured and saved to disk by a separate helper program that runs outside Omniscio at high priority, so a slow, frozen or crashed Omniscio cannot drop frames or end a recording. If Omniscio closes mid-recording, the helper keeps recording and shows a tray icon and a notification you can use to stop it. Turn it off to record inside Omniscio the old way; Omniscio also falls back to that automatically when the helper cannot start. Find it in the Screen Recording settings gear, on the Advanced tab → Extras → "Record in an independent helper" (shown on Windows only), or change it with the CLI settings route. Synonyms: independent recorder, recorder helper, record outside omniscio, recording survives a crash, high priority recording, separate recording process.
screenshotOcrModel text string (≤120) The AI model used to read text from your screen captures. Defaults to the latest Sonnet.
semanticSearchEnabled toggle true | false Turn on Semantic Search, which finds results by meaning rather than exact words.
senderRunCardsEnabled toggle true | false When several messages land back to back — a burst of gate results, a run of machine wake-ups, a coordinator's inbox — the conversation shows ONE quiet line naming how many and who from, which opens to a single swipeable card deck instead of a stack of bubbles. Every message is still there and readable in full. On by default; you can turn it off anytime.
sessionFilesLinksEnabled toggle true | false In-development: a per-session "Files & Links" panel, opened from a button in the session header, listing every file the agent created or edited in that conversation and every link it handed you — newest first, deduplicated, and clickable. Files come from the session's CLI transcript; links come from its saved messages, so links work on every engine. Read-only and worked out on demand — it stores nothing. Deliberately available on mobile too, where there is no other way to reach a session's files. Off by default; hidden until shipped.
sessionQuoteOnSelect toggle true | false
sessionTagsEnabled toggle true | false Turn on tags for sessions.
sessionToolbarButtons list array of object { action: "prompt" | "recipe"; icon: string (≤40); id: string (≤40); label: string (≤40); promptId: string (≤80); promptKind: "text" | "saved"; promptText: string (≤20000); recipeConfigId: string (≤80) } Your own custom buttons on the open session, up to eight. Each button either sends a saved prompt or plain text into that session, or opens a saved recipe in its project. It never starts a session by itself. The list is empty by default. Synonyms: custom toolbar buttons, session shortcut buttons, one-click prompt buttons, my own buttons.
sessionTrajectoryEnabled toggle true | false In-development: a per-session "Trajectory" view (a new option in a session's view switch, beside All / Agent / You / Events) that shows what the agent did — an ordered list of turns and tool-call steps, a turn-level activity timeline, and a metrics strip (turns, tool calls, tokens, cost, duration). Reads data already stored for every engine, so it works for all harnesses. Read-only; off by default; hidden until shipped.
setupV2Enabled toggle true | false In-development: the redesigned cinematic first-run "Setup" flow — a keyboard-driven, step-sidebar shell (language and look → about you → privacy → your AI → connect → access key → install essentials → permissions). Preview it any time from Settings → Setup Wizards. This entry is the preview toggle for the shell; whether a brand-new install is routed into it is the separate "Setup v2 live first-run onboarding" entry.
setupV2OnboardingEnabled toggle true | false Retired: this toggle chose between Setup v2 and the legacy first-run wizard. The legacy wizard is gone, so Setup v2 is the only first-run onboarding and nothing reads this toggle any more.
sharePageBrandLogoFile text string (≤80)
shareSavedStateEnabled toggle true | false Interactive shares you publish remember what each viewer ticks, types or picks, on that viewer’s own device. Nothing is sent anywhere. Turning this off applies to shares you publish from then on, and the in-app viewer stops remembering.
showEndedSessions toggle true | false Show sessions that have ended.
showHotkeyWhisper toggle true | false Show a brief "(or press X)" hint near the cursor when you click a control that has a keyboard shortcut.
showScreenshotButton toggle true | false Show the camera/screenshot button in the chat composer. Hidden by default; desktop only.
shrinkLargeImages toggle true | false
sidebarGroupOrder list array of string (≤64) Your own order for the sidebar's custom groups, as library-tag ids, most significant first. ORDER ONLY — a tag is a sidebar group because its own "show in sidebar" flag says so, and this list never adds or removes a section. Ids it does not name sort after the named ones, by name. Synonyms: sidebar group order, reorder sidebar groups, arrange my groups, custom sidebar sections order, move a group up.
smartShareReaperEnabled toggle true | false Finds "never expires" shares and screen recordings that are over a year old and unviewed, gives each a 90-day grace expiry, and drops one inbox card asking you to Keep or delete it.
snapShotEnabled toggle true | false Desktop only: a SnapShot button in the message box takes a picture of another app's window and, on Windows, the text that window shows, previews both, and attaches them to your next message only when you press Attach. Omniscio's own windows and password fields are never captured, and nothing leaves this computer before you send.
snoozeSmartOrderEnabled toggle true | false In development: drop the snooze durations you never pick from the menu (after about a month), keeping the rest in the standard order. Off shows the full list.
storyboardWorkflowEnabled toggle true | false AI-powered storyboard generation from a written script. Breaks a script into scenes with camera angle suggestions, character/location metadata, and reference image slots for pre-production visualization. Off by default; hidden until shipped.
stripeCreditTopupsEnabled toggle true | false Buy gateway AI credit with a card via Stripe checkout.
sttDailyCapUSD number number 0..100 Daily dollar safety cap on paid speech-to-text. Set to 0 to turn paid speech-to-text off; the free built-in engine still works.
stuckTaskHelperEnabled toggle true | false In-development: notices when you keep snoozing the same session, email, PR, or message and — after the 3rd time — offers a dismissible inbox nudge to start an AI session that interviews you about the resistance and helps you take a tiny first step.
teachRecorderEnabled toggle true | false In-development: records what you do on Windows — clicks, keystrokes, and screen state — and turns the recording into a reusable AI skill that agents can replay on your behalf. Off by default; hidden until shipped.
teamSubscriptionEnabled toggle true | false In-development: shows the per-seat Team plan card on the Plan & Usage screen — a seat picker, a live $25/seat total, and an "Upgrade to Team" button. Held dark until the gateway has a live STRIPE_TEAM_PRICE_ID: without it every Team checkout returns "not available", so a customer would see a fully-priced offer they cannot buy. Reveal this flag as part of the Team go-live, together with the gateway price wiring. Off by default; hidden until shipped.
timeTrackerAutoCaptureEnabled toggle true | false Turn on the local activity observer that proposes time-tracker draft entries to review. Off by default.
timeTrackerAutoCaptureIdleMinutes number integer 1..60 Auto-capture idle threshold in MINUTES — the gap of no keyboard/mouse activity that closes an activity block (and splits proposals). Default 5; clamped to 1–60.
timeTrackerAutoCaptureTitles toggle true | false Also record the title of the active window during activity capture, not just the app name. A separate opt-in on top of auto-capture.
timeTrackerEnabled toggle true | false Time Tracker
titleEvalDailyDollarCap number number 0..50 Daily spending limit in dollars for the title-quality evaluation test, which runs one paid AI call per sample and model. 0 turns it off.
tryItFreeOnboardingEnabled toggle true | false In-development: an onboarding choice that lets a new user run Claude Code (and later Codex) on company-provided API keys during setup — no personal key needed — with a small capped trial credit and a friendly "add your own key" prompt when it runs out. Off by default; inert until the company gateway keys are live.
ttsDailyCapUSD number number 0..100 Daily dollar safety cap on read-aloud text-to-speech. Set to 0 to turn speech off.
unclaimedCheckEnabled toggle true | false In-development: gives your agents a free "am I owed unclaimed money?" lookup. It installs the bundled unclaimed-check skill and a local search route that proxies each lookup through the Omniscio cloud gateway using your sign-in — no separate key, no cost, just rate-limited. Agent-only (no panel); off by default; hidden until shipped.
unifiedSidebarEngineEnabled toggle true | false Unified sidebar engine (V2)
universalAiSearchEnabled toggle true | false One search box across every surface: type in plain language and get a single relevance-ranked list blending keyword and meaning-based (semantic) matches.
usageModelAliases map map of string → string (≤200)
usageModelPrices map map of string → object { cacheReadPerMillion: number 0..100000; cacheWritePerMillion: number 0..100000; inputPerMillion: number 0..100000; outputPerMillion: number 0..100000 }
userPersona select "founder-fred" | "engineer-ike" | "pm-parker" | "aspiring-amy" Your avatar persona for onboarding and persona-flavored defaults — one of founder-fred, engineer-ike, pm-parker, or aspiring-amy (null = none chosen). Chosen during onboarding; some default settings are flavored by the persona you pick. Synonyms: avatar persona, persona choice, onboarding persona, which persona.
vadThresholdsByDeviceId map map of string → object { silenceFloor: number 0..1; speechThreshold: number 0..1 } Internal: per-microphone voice-activity detection levels the app calibrated. Not a setting to change by hand.
videoPlaybackRate number number 0.5..3 Global video playback speed (VIDEO_SPEED_MIN..MAX, default 1×). Applied to every <VideoPlayer> on load and remembered across plays + restarts (persisted via updateSetting({ silent: true })). Read as settings.videoPlaybackRate ?? 1.
voiceActHighlightEnabled toggle true | false In-development: when voice asks you to confirm an action (like sending a message or ending a thread), highlight the on-screen thread it will act on so you can see what you are confirming.
voiceAttachmentEnabled toggle true | false In-development: a small chip showing whether voice targets Omniscio (app-level) or a specific session, plus a per-utterance receipt of where each voice command actually went.
voiceBargeInLabFlag toggle true | false Experimental flag for voice barge-in, which lets you interrupt the assistant by speaking. Off by default.
voiceBargeInLabVisible toggle true | false In-development: interrupt the spoken AI response by talking over it. Reveals the barge-in controls + mic calibration in Voice settings. Not yet fully wired, so hidden by default.
voiceCustomCommands list array of object { action: "navigate" | "session:send" | "session:interrupt" | "session:archive" | "session:terminate" | "project:select" | "tts:speak" | "tts:stop" | "mute" | "unmute" | "attention"; enabled: true | false; id: string (≤100); label: string (≤200); params: map of string → string (≤500) | number | true | false; triggers: array of string (≤100) } Your custom spoken commands and the actions each one runs.
voiceL2DailyCapUSD number number 0..100 Daily dollar safety cap for the conversational voice feature (Layer 2).
voiceL2Enabled toggle true | false In-development: talk back and forth with an AI assistant that has context about what is on screen, can grab more context, navigate the app, and (later) take actions on your behalf. Read-only in this build.
voiceL2Hotkey unknown string (≤100) | array of string (≤100) The global keyboard shortcut(s) that start a voice conversation.
voiceL2HotkeyEnabled toggle true | false Whether the voice-conversation keyboard shortcut is active.
voiceL3DailyCapUSD number number 0..100 Daily dollar safety cap for the session-voice feature (Layer 3).
voiceL3Model text string (≤100) The AI model used for the session-voice conversation feature (Layer 3).
voiceLlmProvider select "groq" | "claude-haiku" Which AI provider understands your spoken commands: Groq or Claude Haiku.
voicePttCommandEnabled toggle true | false Enable Push to Command: hold a key, speak a command, release to run it.
voicePttCommandKey text string (≤100) The key you hold for Push to Command.
voiceReportBackDailyCapUSD number number 0..100 Daily dollar safety cap for Voice Report Back, which speaks the AI's reply aloud.
voiceWalkEnabled toggle true | false In-development: say "go through my inbox" (or press the button) and the app reads each waiting session aloud, listens once, and acts on the session being read out — reply, follow-up, archive, skip, snooze or repeat — then moves on by itself. Dev builds only.
voiceWalkGeminiVoice toggle true | false Makes the inbox walk speak in one natural Gemini voice at one steady speed, instead of your read-aloud voice and its two different speeds. On by default (the walk itself is in development and stays hidden until it is revealed). It uses your Google (Gemini) key; without one, or once today's live-voice spend limit is used up, the walk uses your regular voice and tells you once. Turn it off to keep the walk on your regular voice.
voiceprintStudioDailyDollarCap number number 0..50 Daily spending limit in dollars for Voiceprint Studio's paid draft and rule generation. 0 turns it off.
waitingDetectorCorpusEnabled toggle true | false Use the full waiting-language detection set, which catches more cases but occasionally misfires. Off by default uses the higher-precision set.
waitingDetectorEnabled toggle true | false When a session describes waiting in plain words without using a proper wait mechanism, hold it back from the "needs you" inbox. On by default.
waitingDetectorModelEnabled toggle true | false Add a second AI check that double-checks unclear "is this session waiting?" cases before it flips to "needs you". Needs an AI key; off by default.
wakeWordFocusOnly toggle true | false Only listen for the wake word while the Omniscio window is focused; listening pauses otherwise.
wakeWordKeywords list array of "computer" | "hey-omniscio" Which wake word(s) you can say (Computer or Hey Omniscio). Note: neither currently triggers reliably on real speech.
wakeWordSensitivity number number 0..1 How easily the wake word fires, from 0 to 1 (higher is more sensitive).
webMediaDownloadEnabled toggle true | false In-development: turns on the File Converter’s "Download from web" tab (desktop only) — paste a YouTube/Vimeo/direct link and yt-dlp saves it to your Downloads as Video (MP4), Audio (MP3), or Best. A SEPARATE opt-in on top of the File Converter, which stays conversion-only until you enable this. Off by default.
workflowCoachDailyDollarCap number number 0.05..5 Daily spending limit in dollars for the AI Workflow Coach's paid suggestions.
workflowCoachDetectors object object { duplicateApproval: true | false; featureGap: true | false; featureUsage: true | false; idleSession: true | false; manualArchive: true | false; repeatedOutgoingText: true | false } Which AI Workflow Coach detectors are switched on (for example repeated approvals, idle sessions, or manual archiving); each can be turned on or off.
workflowCoachEnabled toggle true | false Master on/off for the AI Workflow Coach, which watches your sessions and suggests workflow improvements.
workflowsSessionSplit toggle true | false Show the Workflows build canvas and the AI chat side by side. On by default when you open a build session.
workflowsSplitWidth number number 320..900 Width (px) of the workflow canvas pane in split view. Resizable via the divider; persisted globally. Read as settings.workflowsSplitWidth ?? 460.
writerAutocompleteModel text string (≤100) Which AI model powers Writer's inline autocomplete ghost-text — kept separate from writerModel since autocomplete fires constantly and should stay cheap. Automatic (Luna), Luna, Haiku, Sonnet, or Opus (default Automatic). The Writer's own gear menu (Writer settings) → "Autocomplete model".
writerBookViewEnabled toggle true | false Shows the Write / Book switch in the Writer, for seeing a document laid out as a printed book. On by default; off hides the switch and turns book view off. The Writer's own gear menu (Writer settings) → "Book view". Synonyms: book view, book layout, print preview, typesetting, pages.
writerChaptersEnabled toggle true | false
writerCollapsedFolders list array of string (≤1024) Which folders are collapsed in the Writer sidebar's folder tree, by folder id. Toggled by clicking a folder's collapse arrow; a remembered layout state, not a Settings-page control.
writerCommentsEnabled toggle true | false
writerContextEnabled toggle true | false In-development: attach items from your ContextDock (Local) library to a Writer Studio document, so Writer AI uses only the material attached to that document as reference. Off by default.
writerContextRecentItems list array of string (≤209)
writerContextShortVersionNoticeSeen toggle true | false
writerCostCapUsd number number 0.5..50 RETIRED — ignored. This was the Writer Studio daily AI spending limit. It was removed on 2026-11-19: Writer AI runs only on your own Claude sign-in or your own API keys, so Omniscio no longer sets a Writer-only budget. Nothing reads it, so setting it changes nothing. Synonyms: writer daily budget, writer ai budget, writer cost cap, writer spending limit.
writerCreditsNoticeAccepted toggle true | false RETIRED — ignored. This remembered the answer to the old Writer Studio notice about Omniscio credits as a backup. It was removed on 2026-11-19: Writer AI never uses Omniscio credits, so there is no notice to answer. Nothing reads it, so setting it changes nothing. Synonyms: writer credits notice, writer omniscio credits backup.
writerDefaultCreativity number integer 1..4 The AI creativity level (1=Careful to 4=Bold; default 2=Balanced) a NEW Writer document starts with — set once during the writing-defaults setup step and copied onto each new document; each document can then change its own from there. Setup wizard → Writing Defaults → "AI creativity level".
writerDefaultTone text string (≤200) The default tone (e.g. "professional", "casual", "friendly") a NEW Writer document starts with — set once during the writing-defaults setup step. Blank (the default) lets each document set its own tone. Setup wizard → Writing Defaults → "Default tone".
writerDocViewMode select "list" | "grid" | "compact" How your Writer documents list is displayed: list, grid, or compact (default list). Set from the view-mode switcher above your Writer document list; a remembered display preference.
writerDriveEnabled toggle true | false Kill switch for Writer's Google Drive integration (import from Drive and publish to Google Docs). On by default. No Settings-UI control yet; set via CLI/PATCH.
writerFormatToolbarFrame object object { height: number 0..10000; width: number 0..10000; x: number 0..10000; y: number 0..10000 }
writerFormatToolbarMinimized toggle true | false
writerKmsSyncOnSave toggle true | false When on, saving a Writer document also pushes its content to the Knowledge Vault (KMS) note it's linked to. Off by default; has no effect unless KMS is enabled. Toggled from the sync-on-save control in the Writer header.
writerLocalCopiesEnabled toggle true | false
writerLocalCopiesFolder text string (≤1000)
writerLockAccentRail toggle true | false
writerLockHideMarks toggle true | false
writerMarkAiText toggle true | false
writerModel text string (≤100) Which AI model handles Writer's chat, edits, and rewrite options: Automatic (Sonnet for chat, Luna for edits), Luna, Haiku, Sonnet, or Opus (default Automatic). Kept separate from writerAutocompleteModel, which only covers inline ghost-text. The Writer's own gear menu (Writer settings) → "AI model".
writerOnboardingCompleted toggle true | false Set once you have completed or dismissed the Writer Studio welcome screen.
writerRecentDocsEnabled toggle true | false Shows the Recent list (your three most recently edited documents) at the top of the Writer documents sidebar. On by default; off hides the Recent list so the sidebar shows only your folders and documents. The Writer's own gear menu (Writer settings), "Recent documents". Synonyms: recent documents, recent docs, recently edited, recent list, hide recent, sidebar clutter.
writerRewriteOptionsHintDismissed toggle true | false Remembers that you dismissed the one-time "click any sentence to see alternatives" hint in Rewrite options.
writerSetupComplete toggle true | false Internal bookkeeping: set once you finish or dismiss the Writer Studio setup wizard. It records completion only and does not gate the feature.
writerSidebarCollapsed toggle true | false Whether the Writer document list is folded into a thin strip down the left edge (default off). Switched with the hide button in the Writer document list header or Alt+Ctrl+D, and brought back by clicking the strip. Desktop-width windows only; a phone keeps its list-then-document flow. Synonyms: collapse the sidebar, hide the document list, more room to write, full width page.
writerSpagBubble toggle true | false
writerSpagFont select "page" | "system" | "verdana" | "trebuchet-ms" | "georgia" | "courier-new"
writerSpagOpen toggle true | false
writerSprintGoalWords number integer 0..100000 The word goal last set for a Writer writing sprint, counted from where the sprint started; 0 means no goal. 0 by default. Set in the panel the timer icon in the Writer header opens, and remembered for the next sprint. Synonyms: sprint word goal, writing goal, words this session, word target.
writerSprintHoldAlerts toggle true | false Whether a Writer writing sprint holds every alert until it ends, apart from errors, separately from your Focus Mode settings. On by default. Set with Hold my alerts in the panel the timer icon in the Writer header opens. Synonyms: mute alerts while writing, do not disturb, hold notifications, silence alerts during sprint.
writerSprintHoldUntil text string (≤40) Remembered state: while a Writer writing sprint is holding alerts, the moment the hold ends on its own. Empty when no sprint is holding alerts, and cleared when the sprint ends or the app starts. Synonyms: sprint alert hold, alerts held until, writing sprint hold.
writerSprintMinutes number integer 0..240 The timer length last chosen for a Writer writing sprint, in minutes; 0 means no timer. 30 by default. Set in the panel the timer icon in the Writer header opens, and remembered for the next sprint. Synonyms: sprint timer, writing timer, sprint length, timed writing.
writerTemplateContextDefaults map map of string → array of object { id: string (≤200); kind: "bundle" | "document"; load: "full" | "short" }
writerWidgetPositions object object { dictionary: object { left: number 0..10000; top: number 0..10000 }; storyNames: object { left: number 0..10000; top: number 0..10000 } }

Integrations (38)

Connecting the other products you use, including the AI providers that run sessions.

Setting Type Accepted values What it does
airtableEnabled toggle true | false Adds an "Airtable" sidebar tab to view and manage your Airtable bases, tables, and records without leaving Omniscio. Connect with your Personal Access Token in Settings. Beta: expect the odd rough edge.
airtableInboxEnabled toggle true | false Show Airtable records assigned to you as rows in the unified Inbox. Works only when the Airtable feature is also on.
airtableSelectedBaseId text string (≤200) Internal: remembers which Airtable base (file) you picked for the board view and inbox poller. Not a setting to change by hand.
airtableSelectedTableId text string (≤200) Internal: remembers which Airtable table you picked inside the selected base, for the board view and inbox poller. Not a setting to change by hand.
airtableSelectedTableName text string (≤200) Internal: remembers the display name of the Airtable table you picked, alongside its id. Not a setting to change by hand.
asanaBoardEnabled toggle true | false Adds an "Asana" sidebar tab to view and work your Asana projects — sections as columns, task detail, comments, assignment — without leaving Omniscio. Connect with an Asana personal access token in Settings. Beta: expect the odd rough edge.
asanaInboxEnabled toggle true | false Show Asana tasks assigned to you in the Omniscio inbox; needs saved Asana credentials and a workspace. Off by default.
asanaWorkspaceGid text string (≤64) The Asana workspace Omniscio should pull your assigned tasks from, identified by its ID. Not set until you connect Asana.
calendarQuickAddDefaultCalendarId text string (≤200) Which calendar a quick-added event goes into when you do not pick one. Empty uses your calendar tool's own default.
clickupEnabled toggle true | false Adds a "ClickUp" sidebar tab to view and manage your ClickUp tasks — board columns, task detail, comments, checklists — without leaving Omniscio. Connect with your Personal API Token in Settings. Beta: expect the odd rough edge.
clickupInboxEnabled toggle true | false Show ClickUp tasks assigned to you as rows in the Inbox. Off by default, and it only shows them when the ClickUp board itself is also on.
cofferAssistantEnabled toggle true | false Opt-in consent for Coffer's natural-language money assistant: ask plain-English questions about your finances ("how much did I spend on restaurants last month?") and get answers grounded in your ledger. Off by default — each question is a small PAID Anthropic round-trip using YOUR OWN API key, and only your question plus small summary figures (totals, budget status) are sent — never your individual transactions. Enabled only by the explicit consent card in the Coffer assistant panel. Synonyms: money assistant, ask about my finances, ledger chat, natural-language finance questions, coffer ai assistant.
cofferBudgetMode select "tracking" | "envelope" Which budgeting style the Coffer Budgets view uses: "tracking" (default) shows classic per-category budgets and spending bars; "envelope" switches to YNAB-style allocation-first budgeting where every dollar is assigned to an envelope and leftovers/overspending carry month to month. Switching modes never deletes data — the other mode's numbers stay saved and reappear if you switch back. Set from the Budgets view's mode switch, not a Settings toggle.
cofferEnabled toggle true | false Adds a "Coffer" sidebar tab — a personal-finance tracker (accounts, transactions, auto-categorization, budgets, net worth) inspired by Mint.com, fully local to Omniscio. Import bank CSV/OFX files or add transactions by hand. In development.
cofferQuotesEnabled toggle true | false Opt-in consent for Coffer's Investments feature to fetch daily closing stock prices from stooq.com (a free quote service) so it can value your manually-tracked holdings and chart them against the S&P 500 benchmark. Off by default; nothing about your balances is ever sent. Set from the Investments view's consent card, not a Settings toggle.
composioConnectedToolkits list array of string (≤100) The list of Composio toolkit slugs currently connected for your account — a local cache of Composio's own server-side connection state, refreshed automatically. Not user-editable; at least one entry is required before the Composio MCP server is added to a session.
composioEnabled toggle true | false Adds a "Composio" sidebar tab to connect your external apps (Gmail, Slack, GitHub, Notion, and 1000+ more) through Composio, then hands those tools to every AI session automatically. It is also a way to connect Google for the built-in Gmail, Calendar and Drive screens. Bring your own free Composio API key.
composioGoogleConnections list array of object { id: string (≤200); status: catch; toolkitSlug: string (≤100) }
composioGoogleDisconnectPending toggle true | false
composioGoogleEmail text string (≤320)
composioUserId text string (≤200) Your auto-generated Composio user id (an opaque "omniscio-<uuid>" string), minted once and reused for every Composio API call. Internal identifier, not user-set and not a credential.
googleMeetEnabled toggle true | false In-development: pull your Google Meet history, cloud recordings, speaker-attributed transcripts, and participant lists from the Google Meet REST API. Requires Google Workspace Business Standard or higher. Off by default.
granolaAuthMode select "apiKey" | "localSession" How Omniscio authenticates to Granola: "apiKey" (the default) uses the Granola API key you paste against Granola's public REST API, while "localSession" is the free-plan path that reads the login of the Granola desktop app already installed on this PC, storing no key. localSession is Windows-only. Synonyms: granola auth mode, granola api key vs local, use granola without a key, granola free plan login.
granolaEnabled toggle true | false Adds a "Granola" sidebar tab to browse your Granola meeting notes — recent meetings, summaries, and full transcripts — and use a transcript as context for a new Claude session, without leaving Omniscio. Connect with a Granola API key in Settings. In development.
granolaInboxEnabled toggle true | false Off by default. When on (and the Granola feature is also on), shows newly created Granola meetings as items in the Inbox.
jiraBoardEnabled toggle true | false Adds a "Jira" sidebar tab to view and work your Jira boards — columns, issue detail, transitions, comments — without leaving Omniscio. Connect with your Atlassian email + API token in Settings. Beta: expect the odd rough edge.
jiraEmail text string (≤320) The Atlassian account email used to sign in to Jira.
jiraSiteUrl text string (≤2000) Your Jira Cloud site address (for example https://acme.atlassian.net). Blank until you connect Jira.
linearBoardEnabled toggle true | false Adds a "Linear" sidebar tab to view and work your Linear teams — workflow-state columns, issue detail, comments, assignment — without leaving Omniscio. Connect with a Linear personal API key in Settings. Beta: expect the odd rough edge.
mondayCloudEnabled toggle true | false Adds a "Monday.com" sidebar tab to view and work your real Monday.com boards — groups, items, column values, updates — without leaving Omniscio. Connect with your personal API token in Settings.
mondayCloudInboxEnabled toggle true | false Show Monday.com items assigned to you as rows in the Inbox. Off by default, and it only shows them when the Monday.com board itself is also on.
notionBoardEnabled toggle true | false Adds a "Notion" sidebar tab to view and work your Notion databases — status/select columns, page detail, properties, page body — without leaving Omniscio. Connect with a Notion internal integration token in Settings. Beta: expect the odd rough edge.
ollertEnabled toggle true | false Master switch for the Ollert sidebar panel. Off by default while it is still in development.
outboundWebhooksLabVisible toggle true | false In-development: deliver curated internal events (agent status, budget alerts, recipe/job completion, inbox alerts) to your own callback URLs. Subscribe by event type, with per-webhook delivery history and a test ping. Off by default.
trelloEnabled toggle true | false Adds a "Trello" sidebar tab to view and manage your Trello boards — kanban columns, card detail, comments, checklists, labels — without leaving Omniscio. Connect with your Trello API key and token in Settings. Beta: expect the odd rough edge.
trelloInboxEnabled toggle true | false Show Trello cards in your inbox (only runs when the Trello connection is set up).
zoomApiEnabled toggle true | false Connect your Zoom account to see meetings, recordings, and transcripts. Beta: expect the odd rough edge.
zoomApiSyncIntervalMin number integer 5..120 Zoom API — how often (in minutes) Omniscio re-syncs your meetings from the Zoom API in the background. 5 to 120 minutes; default 15. Only used when the Zoom integration (zoomApiEnabled) is on. Synonyms: zoom sync interval, zoom poll frequency, how often zoom refreshes.

Plugins & Marketplace (41)

The plugin system, the plugins that ship with it, and where to find more.

Setting Type Accepted values What it does
activeLayoutModBySurface map map of string → string Which layout mod is active on each app surface — a map of surface to mod id (e.g. sidebar to compact-rail), set by the Appearance "Layouts" toggles. Empty means every surface uses its standard built-in layout. Related: layout mods, Compact Rail, sidebar layout.
adStudioEnabled toggle true | false The Ad Studio plugin for advertisers: a Library of competitors' ads, Boards, and Claude-written ad variations and briefs for each Brand. On by default. Turning this off turns the plugin off and removes Ad Studio from the sidebar; your Brands stay for next time.
adsAutopilotEnabled toggle true | false The Ads Autopilot plugin: AI agents run a Meta (Facebook and Instagram) ad account inside hard spending caps. Off by default. Turning this on adds Ads Autopilot to the sidebar; turning it off stops its daily run and removes it from the sidebar.
autohotkeyBuiltinMigrated toggle true | false Internal bookkeeping: remembers that your AutoHotkey entries and settings were moved into the bundled plugin. Not a setting to change.
bundledPluginsDefaultOnBackfilled toggle true | false Internal bookkeeping: remembers a one-time step that turned on two bundled plugins and revealed their group. Not a setting to change.
calendarSchedulerPluginEnabled toggle true | false Booking pages, event types and Google Calendar sync. On by default. Turning this off turns the plugin off and removes Calendar from the sidebar; your bookings, event types and Google link stay for next time.
decksBuiltinMigrated toggle true | false Internal bookkeeping: remembers that your Decks data was moved into the Decks plugin. Not a setting to change.
decksPluginEnabled toggle true | false AI slide decks you can present, publish and export. On by default. Turning this off turns the plugin off and removes Decks from the sidebar; your decks stay for next time.
enabledPlugins list array of string (≤100) The list of plugins currently turned on.
formsPluginEnabled toggle true | false Build forms, share them as public links, and bring the answers home ready to read or send to an agent. On by default; turn it off here to hide Forms everywhere. Your forms and answers are kept, and forms you already published stay open online.
foundryBuiltinMigrated toggle true | false Internal bookkeeping: remembers a one-time install of the Foundry marketplace copy. Not a setting to change.
githubIntegrationPluginEnabled toggle true | false Pull requests, issues, code and releases inside Omniscio. On by default. Turning this off turns the plugin off and removes GitHub from the sidebar; your GitHub connection stays for next time.
layoutOverridesBySurface map map of string → unknown Your own fine-tuning on top of an active layout mod, keyed by app surface (e.g. sidebar, session list). Empty (the default) means no extra tuning beyond the mod's own preset. Set from the Appearance → Layout Mods card; auto-cleared with a warning if a mod errors.
marketplaceBetaNoticeDismissed toggle true | false
marketplaceBuiltinCarryOwed list array of string (≤100) Internal bookkeeping, not a setting you change. It lists built-in features that were swapped for their marketplace plugin copy and still owe a follow-up step, such as carrying your saved data across. It lets the app tell a plugin you switched off from one it rolled back, so unfinished carries can retry. Empty by default. Synonyms: plugin migration marker, builtin to marketplace carry, plugin data carry pending, migration retry list.
marketplaceBuiltinMigrated list array of string (≤100)
marketplaceReEnabledDone toggle true | false Internal bookkeeping: whether the one-time upgrade that re-enabled the plugin marketplace has run. Written by the upgrade, not a setting to change.
marketplaceReviewAlertKinds list array of "plugins" | "automations" | "publishers"
marketplaceReviewAlertsEnabled toggle true | false
marketplaceReviewDesktopAlerts toggle true | false
marketplaceReviewSummaryHour number integer 0..23
marketplaceReviewTargetHours unknown 8 | 24 | 48
modStudioEnabled toggle true | false Design your own session cards out of blocks and restyle any part of the app, with Safe Mode as a one-key escape.
modsPlatformEnabled toggle true | false Layout presets you can tune: reshape the hubs sidebar (a slim icon rail, with or without names) and the session list (row size, status badges), with a Safe Mode that restores the standard layout.
modsSafeMode toggle true | false Safe Mode for layout mods. When on, all layout mods are disabled and every surface falls back to its standard built-in layout no matter what is selected — the recovery kill-switch to use if a mod causes any issue. Synonyms: mods safe mode, disable mods, standard layouts, restore default layout.
newsletterBuilderPluginEnabled toggle true | false Writes your newsletter issues and sends them to your readers. On by default. Turning this off turns the plugin off, removes Newsletter from the sidebar and cancels any scheduled sends; your newsletters, issues and settings stay for next time.
pluginAutoUpdateHolds list array of string (≤100) The plugins you have held back from automatic updates, one plugin id each. Empty by default, so an installed app updates itself in the background whenever a newer version asks for nothing new. A plugin listed here is never updated behind your back, however small the change: its newer version waits in Updates, where installing it is your click, and it stays on the version you have until you do. Turning the hold off lets the next check update it again. The app still tells you when a newer version exists. Marketplace → the app's page → Settings, or Settings → Plugins → the app's card, → "Update automatically". Synonyms: hold a plugin update, keep this version, don't auto update an app, pin a plugin version, ask me before updating, stay on this version.
pluginConsents map map of string → object { allowedCommands: array of string (≤200); cliEndpoints: array of string (≤240); consentedAt: string (≤40); hasBackend: true | false; permissions: array of string (≤100); pinnedPrograms: array of string (≤200); sessionTools: true | false; version: string (≤50) } Internal bookkeeping: records which permissions you approved for each plugin, so it can't be enabled without your consent. Not a setting to change.
pluginEmailScheduleOwed list array of object { action: "cancel" | "hold"; before: string (≤40); pluginId: string (≤100); pluginName: string (≤100); uid: string (≤128) } Internal bookkeeping, not a setting you change. It remembers scheduled emails that still need to be canceled or put on hold after a plugin was removed or turned off, so the cleanup can finish later, for example once you are signed in again. Entries are retried hourly and dropped after about a month. Empty by default. Synonyms: pending plugin email cleanup, scheduled email cancel queue, plugin email hold queue, owed email actions.
pluginEmailScheduleWaiting map map of string → map of string → integer 0..100000 Internal bookkeeping, not a setting you change. For each plugin that schedules emails, it remembers which account the emails are waiting under and how many are still to send, so turning the plugin off while signed out can still stop them once that account signs in. Empty by default. Synonyms: plugin scheduled email accounts, waiting plugin email, plugin email record.
pluginItemFoldersEnabled toggle true | false When on (the default), a plugin you have given the "Item folders" permission keeps one folder per item under a folder named Omniscio in your home folder (or Omniscio and a short code when that name is taken), holding a read-only copy of that item's files. The app writes the folder from its own copy and never reads a change back, so editing a file there never changes the item. Turning it off stops the app writing, reading and refreshing item folders: a chat that already has a folder keeps it and is told once, and no folder is deleted. You or an agent can change it, like any other setting; no plugin can. Synonyms: item folders, plugin item folder, read-only copy in my home folder, turn off item folders, stop item folders.
pluginSessionFullAccess list array of string (≤100) The plugins whose AI agents you have given your own full access, one plugin id each. Empty by default, so every plugin's agents run on the locked-down floor. A plugin listed here starts its agent sessions with your own setup, your trust level and any engine, exactly as before the floor. Not recommended: a plugin hands its agents outside content (form answers, web pages, emails, issues) that could steer them. Takes effect at that plugin's next session launch. You or an agent can change it, like any other setting; no plugin can. Marketplace → the plugin's card → Settings → "Give this plugin's AI agents my full access". Synonyms: plugin full access, trust a plugin's agents, exempt a plugin from the floor, unlock a plugin's agents, plugin agent full permissions.
pluginWidgetsEnabled toggle true | false Shows small live widgets in the app header, from plugins and from your own scripts (via the local API). Omniscio draws each widget from its data — a number, a short label and a status colour — so a plugin or script never draws in the header itself. On by default — turn it off to hide every plugin and script widget.
pluginsGroupCollapsed toggle true | false Whether the Plugins group in the sidebar is folded shut. A display choice only.
pluginsGroupDisplayOrder number integer Where the Plugins group sits among your sidebar groups — a number, and a lower number sorts higher up.
repoguardBuiltinMigrated toggle true | false Internal bookkeeping: remembers a one-time install of the RepoGuard marketplace copy. Not a setting to change.
typingTutorBuiltinMigrated toggle true | false Internal bookkeeping: remembers that your Typing Tutor data was moved into the plugin. Not a setting to change.
userMods list array of unknown The mods you built in Mod Studio — a list of your own layouts and restyles (up to 50). Empty (the default) means you have not built any. Each mod is checked on its own when the app loads, so one broken or outdated mod is skipped without touching your others. Edit them in Mod Studio rather than by hand. Synonyms: my mods, custom mods, saved mods, custom session cards, user-made layouts.
whiteboardBuiltinMigrated toggle true | false Internal bookkeeping: remembers that your Whiteboard data was moved into the bundled plugin. Not a setting to change.
widgetBuilderEnabled toggle true | false A sidebar page where you describe a widget in plain words and press Build. One AI session makes it in your Omniscio Widgets folder, checks it, and it then appears under Your widgets with a Load button. With the widget sidebar on, you choose whether it goes in the top bar or the sidebar. Pressing Build starts a paid AI session, and the page needs the Widget Library and Header Widgets switched on. On by default. Turning this off hides the sidebar row.
widgetLibraryEnabled toggle true | false One Settings page that lists every widget in the app, with one-click add for the top bar and the Control Center, and a way to ask an AI session to build your own. On by default. Turning this off hides the page, its Settings search result, the Browse all widgets button, the More-menu item and the shortcut.

Cloud & Teams (44)

Work that leaves this computer — cloud sessions, teams, sharing and other devices.

Setting Type Accepted values What it does
agentChannelKnockPolicies map map of string → object { knockMode: "all" | "mentions" | "none"; maxPerHour: integer 1..60 } Per-Team-Chat-channel rules for how often a subscribed agent session is told messages are waiting — knock mode (all messages, mentions only, or none) plus a max knocks per hour, keyed by channel id. Agents are told only the count, never the message text. Empty (the default) uses no special rule. Set from a channel's "Interrupting your agents" control; gated behind the agent-channels feature.
agentChannelsEnabled toggle true | false In-development: a session can subscribe to a Team Chat channel and be told, at a natural stopping point rather than mid-task, that messages are waiting there. The notice carries only the channel name and how many messages — never the message text — so the agent reads them only when it deliberately chooses to. Each channel sets its own rule (all messages, only mentions, or none) and how often it may interrupt. Off by default and completely inert until switched on.
aiTeamChatEnabled toggle true | false In-development: AI-powered features for Team Chat including semantic search, channel summarization, and AI-assisted message composition.
channelInvitationsEnabled toggle true | false Invite workspace members to specific channels with per-channel roles (owner, member, read-only), and control who can post (everyone, or owners only).
cloudAutomatedWakeEnabled toggle true | false The one live switch that stops the app from waking cloud machines on its own: with it off, a stopped machine is not started to fetch work back, and the work stays safe on the machine until the switch is back on. On by default. A re-capture you ask for yourself is never blocked. Synonyms: cloud wake switch, stop cloud wakes, automated box wakes, stop auto spawning in the cloud, cloud spend off switch.
cloudOwedCaptureSweepEnabled toggle true | false Runs the periodic background sweep that brings back work still sitting on cloud machines after a session finished, waking a machine when needed to collect it. On by default. Turn it off and each pass is skipped and no machine is woken, but the schedule stays armed and resumes when you turn it back on. Synonyms: cloud work recovery, bring back cloud changes, cloud capture sweep, owed capture sweep, cloud return pass.
cloudReturnOwedAlarmEnabled toggle true | false Raises a warning when a finished cloud session's work has genuinely failed to come back to your computer after repeated attempts. On by default. Turn it off and no crew message or inbox card is raised for these stranded returns, although the work is still tracked. Synonyms: cloud return alarm, stranded cloud work warning, cloud changes not returned, cloud capture failure alert.
cloudZeroTurnAlarmEnabled toggle true | false Raises an alert when a cloud session never produces any reply at all, including a crew session that has not replied, so a silent failure does not go unnoticed. On by default. Turn it off to stop these no-reply alarms and their inbox cards. Synonyms: cloud no reply alarm, silent cloud session alert, zero turn alarm, cloud session never answered.
discordImportEnabled toggle true | false In-development: import channels, messages, threads, reactions, pins, and files from a Discord server into Team Chat. Runs as a guided wizard that maps Discord users to existing accounts and writes to your active workspace via a secure Cloud Function.
firebaseHostingDomain text string (≤200) The custom web address your shared artifacts are served from when Firebase Hosting sharing is used. Empty uses the built-in sharing address.
invitationsEnabled toggle true | false When off, invitations sent to your email address no longer appear as Inbox cards. Anyone can still invite you; turn this back on to see them.
newCloudSessionsUseOrdinaryCompletion toggle true | false Makes newly created cloud sessions finish through the ordinary completion route, so they report done the same way local sessions do. On by default. Turn it off and new cloud sessions use the older recovery-style completion instead; existing sessions keep the route they started with. Synonyms: cloud session completion, ordinary completion, cloud finish behavior, new cloud session protocol.
pmTeamChatEnabled toggle true | false Part of Team Chat: mention Mission Control items in chat with #, send a message to Mission Control as an item, see status updates in linked channels, and see linked chat messages on items. Shows only while Team Chat is on. To turn it off, untick the Mission Control box "Link Team Chat conversations".
selfServeWorkspacesEnabled toggle true | false Create your own workspace, switch between the workspaces you belong to, and see the plan pricing, all from the User Management header.
sharedSessionRequireTurnApproval toggle true | false Off by default. When on, every message from a guest with reply access is held for your approval before it reaches your agent, so guests can suggest but you decide.
showSelfHealNotices toggle true | false Show low-value self-heal notices (like auto-enabled cloud enforcement or cleared worktree locks). Off by default to avoid noise; the healing and its log still happen.
slackImportEnabled toggle true | false Import channels, messages, threads, reactions, pins, and recent files from a Slack workspace into Team Chat. Runs as a guided wizard that maps Slack users to existing accounts and writes to your active workspace via a secure Cloud Function.
teamChatAiTopicTitles toggle true | false When ON, the first message of a new Team Chat topic may be sent to a cloud AI service to suggest a name for the topic. OFF by DEFAULT — while it is off, no chat text ever leaves this computer for titling and the topic keeps the name derived from its opening words. Even when ON, email addresses, phone numbers and other personal details are stripped from the text before it is sent. Applies to every topic, including direct messages. Synonyms: ai topic titles, name my topics with ai, ai channel names, send chat text to ai, cloud topic naming, ai thread titles.
teamChatApiPlatformEnabled toggle true | false In-development: an OAuth2 authorization layer for the Team Chat messaging API, enabling third-party integrations to read and write messages with scoped access tokens. The 13 existing CLI routes (channels, messages, reactions, pins, search, etc.) already have Zod validation, pagination, and idempotency — this feature adds the OAuth2 auth surface for external consumption. Hidden until shipped.
teamChatCallMediaConsent toggle true | false
teamChatDefaultSessionProjectId text string The hub new sessions started from Team Chat default to. Tick "Always start Team Chat sessions in this hub" in the start-session dialog (opened by the Start a session icon on a message, on a phone from the message menu) and press Start to set it; unticking it on your current default and pressing Start clears it. Empty (the default) means no default — the dialog auto-selects a hub only when there is exactly one, otherwise it asks you to pick. Only a real hub can be stored, and a default that has since been deleted is ignored. Synonyms: default hub for team chat sessions, where new sessions start, default repo for sessions started in chat, remember the hub for start a session, team chat session default project.
teamChatDmInboxView toggle true | false Team Chat — when on, the direct-messages area of the Team Chat sidebar becomes a "DM thread inbox": it adds a "Needs Reply" section and a People/Threads toggle so you can triage unanswered direct messages instead of scrolling a flat people list. Off by default. Synonyms: DM thread inbox, direct message inbox view, needs-reply DMs, people vs threads toggle, team chat DM triage.
teamChatDmSort select "recent" | "name" Order of the Team Chat sidebar's Direct Messages list. "recent" (the default) puts conversations where the other person spoke last first, then newest first; "name" sorts people A to Z. Chosen from the "Sort by recent activity" / "Sort by name" items in the ⋯ menu on the Direct Messages heading. Synonyms: sort direct messages, DM order, alphabetical DMs, sort chats by name.
teamChatEnabled toggle true | false In-development: a built-in team chat (channels + direct messages) for your company, delivered in real time to every device via the cloud, built into Omniscio. It stays hidden until the workspace is set up.
teamChatExportEnabled toggle true | false In-development: export Team Chat channel or DM history to a portable format (JSON/CSV). A GDPR data portability requirement for a multi-user cloud product. Adds an export action to the channel settings menu.
teamChatForumFeedEnabled toggle true | false Connect a Discourse forum to a Team Chat channel so new forum topics post there the moment they go up, even when nobody's computer is on. Set up by a workspace admin in the channel's settings. Turning this off hides the Forum feed section on this computer only and does not disconnect a connected forum: it keeps posting until a workspace admin disconnects it in that channel's edit dialog.
teamChatLivePreview toggle true | false Whether the Team Chat composer's markdown live-preview pane is open (default closed). A plain remembered UI preference set by the composer's own preview toggle, not a feature gate or a Settings-page control.
teamChatMessageTranslationEnabled toggle true | false In-development: translate any Team Chat message inline using the existing LLM layer. Adds a translate action to the message hover toolbar for multi-language teams.
teamChatScreenShareFps select "5" | "15" | "30" The frame rate used when you share your screen during a Team Chat video call ("5", "15", or "30" FPS; default "15"). Chosen from the quality-settings popover in the in-call controls bar. A lower FPS stays smooth on slow connections; a higher FPS is better for motion like scrolling or playing video. Synonyms: screen share frame rate, screen sharing FPS, share smoothness, screen share fps.
teamChatShowDmPhotos toggle true | false When on (the default), the Team Chat sidebar's Direct Messages list shows each teammate's profile photo next to their name, with an initials-circle fallback for anyone without one and their online/away presence dot kept as a small corner badge. Off: the DM list shows just the presence dot and the name. A per-user display preference toggled from the "Show profile photos" item in the Team Chat sidebar's overflow (more-actions) menu. Synonyms: team chat DM avatars, show profile pictures next to direct messages, DM photos, hide chat avatars.
teamChatSubmitKeyMode select "enter" | "ctrl_enter" Which key sends a message in Team Chat: Enter sends and Shift+Enter makes a new line, or Ctrl/Cmd+Enter sends.
teamChatSummarizationEnabled toggle true | false In-development: AI-powered summarization for Team Chat channels and threads. Adds a "Summarize" or "Catch me up" button to channel headers and thread panes to generate a concise summary of recent activity.
teamChatSyncDrafts toggle true | false
teamChatVideoBackground select "none" | "blur" | "custom" Which video-call background to show during Team Chat calls ("none", "blur", or "custom"; default "none"). Picked from the in-call backgrounds popover. "none" shows your real surroundings, "blur" soft-focuses them for privacy, and "custom" shows the image you set in teamChatVideoBackgroundImage. Synonyms: call background, virtual background, video background, background effect.
teamChatVideoBackgroundBlurLevel select "light" | "medium" | "heavy" How strong the background blur is when teamChatVideoBackground is "blur" ("light", "medium", or "heavy"; default "medium"). "light" keeps your room mostly recognizable; "heavy" hides nearly everything behind you. Ignored unless the background mode is "blur". Synonyms: blur strength, background blur amount, privacy blur level.
teamChatVideoBackgroundImage text string The custom image shown as your Team Chat video-call background when teamChatVideoBackground is "custom" (a path or stored image reference; default empty). A non-secret user preference like an avatar or theme choice, never a credential. Synonyms: custom background, video background image, call background picture.
teamChatVideoQuality select "auto" | "360p" | "720p" | "1080p" The outgoing video-capture quality for Team Chat video calls ("auto", "360p", "720p", or "1080p"; default "auto"). Chosen from the quality-settings popover in the in-call controls bar. "auto" lets the connection pick and adapt the resolution to available bandwidth; a fixed value caps your camera at that resolution. Synonyms: call video quality, camera quality, video resolution, call quality.
teamLibraryEnabled toggle true | false In-development: a members-only shelf where a teammate publishes a skill or saved prompt once and others install it. Cloud security rules are deployed and tested (org + self-serve workspace roots). Renderer data layer (library-client.ts) and list UI (TeamLibraryList.tsx) wired. Ready for final polish and release.
teamsIntegrationEnabled toggle true | false In-development: connect your Microsoft account to see your Teams meetings, and read and send your Teams chats and channel messages (work or school accounts; some need an IT admin to approve). Off by default.
teamsSyncIntervalMinutes number integer 5..1440 Microsoft Teams — how often (in minutes) Omniscio re-syncs your Teams calendar from Microsoft Graph in the background. The poller ticks on this cadence to pull new and updated meetings. 5 to 1440 minutes; default 15 (every 15 minutes). Only used when the Teams integration (teamsIntegrationEnabled) is on; no dedicated Settings-UI control. Synonyms: teams sync frequency, how often teams refreshes, calendar sync interval, meeting refresh rate, how often it checks for new meetings.
teamsSyncWindowDays number integer 1..90 Microsoft Teams — how large a window of meetings Omniscio keeps in sync from Microsoft Graph, in days both before AND after today (a symmetric window centered on now: default 14 syncs meetings from 14 days ago to 14 days ahead). 1 to 90 days. Only used when the Teams integration (teamsIntegrationEnabled) is on; no dedicated Settings-UI control. Synonyms: teams sync window, how many days of meetings, calendar date range, meeting lookback and lookahead, how far back and ahead teams syncs.
videoCallsEnabled toggle true | false In-development: voice and video calling in Team Chat via LiveKit Cloud
warnInternalLinksInTeamChat toggle true | false Gently warn, without blocking, when a Team Chat message contains a link a teammate can't open (an internal link or a local file path), and offer to publish it.
workspaceHubEnabled toggle true | false Manage everyone in a workspace from one screen: invite people, approve joins, shape what each person can reach, approve risky changes, and remove someone with a live checklist and a receipt. Off by default.

Settings & Customization (244)

Making the app yours — how it looks, how it behaves, and what each setting does.

Setting Type Accepted values What it does
a11yColorBlindSafe toggle true | false Recolors every status dot and badge to a palette that stays easy to tell apart with red-green color blindness, while the shape drawn on each status stays on. Off by default. Turning it off keeps the normal status colors. Synonyms: color blind mode, colorblind friendly, status colors, red green.
a11yHighContrast toggle true | false Switches the app to pure black surfaces, white text and a brighter accent color over whatever theme or look is active. Off by default. Turning it off returns to your normal theme colors. Synonyms: high contrast mode, black and white, easier to read, accessibility contrast.
a11yReduceMotion toggle true | false Stops spinners, slides and fades across the app. The app already follows your computer's own reduce-motion setting; this switch turns it on even when the computer setting is off. Off by default. Synonyms: reduce animations, less motion, no animations, motion sensitivity.
activeSavedPanelLayout text string (≤40) Remembers the name of the saved panel layout that is currently showing, so the app can tell which one is active when you switch or cycle layouts. Empty by default, meaning none is active. It is updated for you when you pick a layout. Synonyms: current layout, selected layout, active layout, current panel arrangement.
activeSavedSidebarView text string (≤40) Remembers which saved sidebar view is applied to the sessions list. Empty by default, meaning the normal sidebar with no saved view. Choosing a view from the sidebar picker or the settings card sets it, and removing the active view clears it. Synonyms: current sidebar view, selected view, active filter view, sidebar preset.
animationSpeedScale number number 0..2 How long the app animations take, as a multiple of their normal length: 1 is normal, 0.5 is twice as quick, 2 is twice as slow, and 0 switches transitions off. It scales the CSS transitions (menus, hover effects, fades and the timing tokens every surface shares). A few components animate with their own fixed timing and keep it between 0.25 and 2; at 0 they stop sliding and zooming, though some may still fade. Spinners keep moving. Settings → Appearance → Motion & Polish → "Animation length". Synonyms: animation speed, faster animations, slower animations, turn off animations, transition duration, reduce motion.
appInstallHistory list array of object { id: string (≤128); installedAt: string (≤40) } The apps you installed most recently, newest first — the ⋯ menu at the end of the top bar lists the five newest that can still be pinned. Recorded automatically; capped at 20.
arabicPilotEnabled toggle true | false Adds Arabic (العربية) to the language picker as a pilot catalog translated by AI. Arabic is right-to-left; any untranslated text falls back to English.
archiveCompactionStartedAt text string (≤64) Internal bookkeeping: ISO time the last archive compaction STARTED. An interrupted rewrite leaves the archive un-compacted, so the automatic request waits a week after this before it asks again. Not user-facing.
archiveIntegrityFailedAt text string (≤64) Internal bookkeeping: ISO time the ARCHIVE was last found CORRUPT; empty = not corrupt. The archive verdict has to outlive the process that made it: both scopes are checked on different schedules, so an in-memory-only archive verdict seeds back OPTIMISTIC on the next launch and the first healthy MAIN pass would then AND to healthy and silently clear the user's corruption card while the archive is still bad. Seeded into the archive health flag at open. Not user-facing.
areaInboxDensity select "compact" | "comfortable" | "spacious" Sets how tightly packed the inbox is: compact, comfortable or spacious. Comfortable by default. This changes only the inbox and leaves the transcript and sidebar alone. Synonyms: inbox spacing, inbox row height, inbox compact mode, inbox padding.
areaInboxTextScale number number 0.8..1.6 Scales the text size in the inbox only, from 0.8 to 1.6 times normal. The default is 1, which is normal size. It is independent of the app-wide font size and of the transcript and sidebar scales. Synonyms: inbox text size, inbox font size, inbox zoom, bigger inbox text.
areaSidebarDensity select "auto" | "compact" | "comfortable" | "spacious" Sets how tightly packed the sessions and projects sidebar is: compact, comfortable or spacious. Automatic by default, which lets the sidebar layout's own spacing stay in charge. Choosing a value overrides it for the sidebar only. Synonyms: sidebar spacing, sidebar row height, compact sidebar, sidebar padding.
areaSidebarTextScale number number 0.8..1.6 Scales the text size in the sessions and projects sidebar only, from 0.8 to 1.6 times normal. The default is 1, which is normal size. It is independent of the app-wide font size and of the transcript and inbox scales. Synonyms: sidebar text size, sidebar font size, sidebar zoom, bigger sidebar text.
areaTranscriptDensity select "compact" | "comfortable" | "spacious" Sets how tightly packed the conversation transcript is: compact, comfortable or spacious. Comfortable by default. This changes only the transcript and leaves the sidebar and inbox alone. Synonyms: transcript spacing, chat spacing, message padding, compact chat.
areaTranscriptTextScale number number 0.8..1.6 Scales the text size in the conversation transcript only, from 0.8 to 1.6 times normal. The default is 1, which is normal size. It is independent of the app-wide font size and of the sidebar and inbox scales. Synonyms: transcript text size, chat font size, chat zoom, bigger chat text.
autoBackupDir text string (≤1024) Absolute path to a custom auto-backup directory, normally on a DIFFERENT volume from the primary database. Empty string = use the default <userData>/backups/auto/ (same-volume). When set to a valid absolute path, the auto-backup ring writes there instead. It survives loss of the DATA volume but NOT loss of the system volume: the ring's AES key lives in <userData>/backup-encryption.key wrapped by the OS keyring (backup-key-store.ts, F015), so an off-volume ring on the same machine is undecryptable after the system disk or the OS account goes. Only the Backup Mirror (passphrase-sealed) survives that. No Settings UI control exists — it is a config/CLI-only field (F137). The getter validates isAbsolute() at runtime — a relative or empty string silently falls through to the default.
autoCapitalizeQuickEmail toggle true | false Auto-capitalize the Quick Email body as you type — the first word, sentence starts (after . ! ?), and the start of each new paragraph/line — while skipping URLs, paths, and abbreviations. Reuses the shared smart-capitalize system (the same one the Tasks input + KMS notes use). FREE local transform, never spends. Default ON (opt-out). Synonyms: quick email auto-capitalize, smart capitalization, capitalize sentences/paragraphs in the quick email body.
autoTidyUnusedCollapsed toggle true | false Internal bookkeeping: whether the automatic tidy has folded away your rarely-used sidebar group. Written by the tidy, not a setting to change.
backupEnabled toggle true | false Automatically save local backup copies of your data on a schedule. On by default.
backupIntervalHours number integer 1..24 How often automatic backups are taken, in hours (1 to 24; default 6).
backupMirrorAutoSyncIntervalMinutes number integer 60..1440 Interval (minutes) for scheduled mode. Floor 60 — a full mirror is ~1–3 GB, so sub-hourly auto-writes are intentionally disallowed. Default 3 h.
backupMirrorAutoSyncMode select "off" | "session" | "scheduled" Automatic-sync mode. off = manual "Sync now" button only (default). session = pull on app launch + pull-then-push on shutdown (once per session). scheduled = also pull-then-push on a timer every …IntervalMinutes. A full snapshot is ~1–3 GB, so the cadence is deliberately coarse.
backupMirrorChunkedFormatEnabled toggle true | false In-development: a content-addressed, chunked incremental on-disk format for the Backup Mirror so a sync ships only the few MB that changed instead of re-uploading the whole archive. Inert until shipped — the mirror keeps writing today’s streamed format, and your existing backups are unaffected. Do NOT enable on a real backup folder until a full backup+restore round-trip has been validated.
backupMirrorEnabled toggle true | false Backup-mirror feature flag. Default: false.
backupMirrorPath text string (≤1024) Absolute path to the user's chosen sync folder (must be writable). Empty string = not configured (UI shows "Pick folder…" affordance).
backupMirrorRetentionCount number integer 1..50 Number of historical mirror bundles to keep on disk. Older ones are pruned after each successful write. Default: 5.
backupMirrorRetentionMaxAgeDays number integer 0..3650 Optional AGE bound (in days) on retained mirror bundles (privacy/erasure). A full-DB mirror is an immutable copy of ALL PII; deletion/ erasure on the live DB never propagates into a prior snapshot, so on a low-cadence device the newest-N snapshots kept by backupMirrorRetentionCount can be arbitrarily old — older than any erasure SLA. When > 0, a snapshot older than this many days is ALSO pruned (additive to the count prune — deleted if beyond-count OR too-old), still honoring cross-device-safe-prune (never deletes a foreign host's single newest snapshot). DEFAULT 0 = disabled / count-only, so existing behavior is UNCHANGED by default — this is a destructive prune of the user's own backups and MUST be opt-in.
backupOffMachineSetupOfferDismissed toggle true | false True once the user has dismissed (or acted on) the first-run "set up an off-machine backup" prompt — never shown again after. A DEFAULT install has no off-machine backup that survives losing the machine: the only default-ON backup is the same-volume local ring, and every off-box copy (setup-to-Gmail / mirror / portable) is opt-in + default-OFF. This one-time, consent-first prompt invites the user to configure one; it changes NO backup default on its own (it routes to the hardened config). Default: false. See OffMachineBackupOffer.tsx + off-machine-backup-offer.ts.
backupRetentionCount number integer 2..50 How many backup copies to keep before the oldest are removed (3 to 50; default 50, about 12.5 days of history at the default 6-hour cadence, plus one older copy from each of the last eight weeks).
bengaliPilotEnabled toggle true | false Adds Bengali (বাংলা) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
bikolPilotEnabled toggle true | false Adds Bikol (Central Bicolano) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
brazilianPortuguesePilotEnabled toggle true | false Adds Brazilian Portuguese (Português do Brasil) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
cebuanoPilotEnabled toggle true | false Adds Cebuano (Bisaya) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
chatFont select "theme" | "system" | "inter" | "serif" | "rounded" | "calibri" | "verdana" | "tahoma" | "trebuchet" Chooses the typeface used for chat text across the app, such as System, Inter, Serif, Rounded, Calibri, Verdana, Tahoma or Trebuchet. The default is the theme's own font, so nothing changes until you pick one. A choice here wins over the theme's font. Synonyms: chat typeface, text font, message font, change font.
chatMathEnabled toggle true | false
codeColorTheme select "github-dark" | "github-light" | "monokai" | "nord" | "dracula" | "solarized-light" Chooses the color palette used inside code blocks: GitHub Dark, GitHub Light, Monokai, Nord, Dracula or Solarized Light. GitHub Dark by default. It changes colors only, not how the code is read or split up. Synonyms: code highlighting, syntax colors, code block theme, syntax highlighting theme.
codeFont select "theme" | "system-mono" | "jetbrains" | "cascadia" | "consolas" | "menlo" | "courier" Chooses the fixed-width typeface used for code, such as System mono, JetBrains Mono, Cascadia Code, Consolas, Menlo or Courier New. The default is the theme's own code font, so nothing changes until you pick one. A choice here wins over the theme's font. Synonyms: monospace font, code typeface, terminal font, coding font.
codeFontFamily text string (≤200) The monospace typeface for code blocks, inline code, diffs, file previews and every other code surface. Empty (the default) uses the system monospace font. Settings → Appearance → Text → Fonts → "Code font". Synonyms: code font, monospace font, mono font, programming font, Fira Code, JetBrains Mono, Cascadia Code.
collapsedQuickReplyFolders list array of string (≤64) Which quick-reply folders you have collapsed, remembered between restarts. A display choice only — an entry for a folder you deleted is ignored.
commandPaletteRecents list array of string (≤64) Most-recently-used command ids for the Command Palette, front = most recent, capped at 10. Persisted so your recents survive restarts. Written automatically as you run commands — remembered usage state, not a setting you configure. Synonyms: recent commands, command palette recents, MRU, recently used.
compactArchiveOnNextStartup toggle true | false When true, the next app launch compacts ONLY the cold-storage archive file (behind the splash screen), leaving the main database alone. Armed automatically, once, when the archive tool-output sweep has freed a large amount of space inside a never-compacted archive; cleared and flushed to disk BEFORE the rewrite starts so it can never boot-loop.
compactOnNextStartup toggle true | false When true, the next app launch runs an in-place VACUUM to compact the database file — and the cold-storage archive too, when it holds enough free space to be worth rewriting. Set by the "Reclaim disk space" action; cleared unconditionally after the attempt (success OR failure) so a VACUUM that errors can never boot-loop. Runs behind the splash screen (exclusive lock).
composerCollapseOnScroll toggle true | false
composerFontFamily text string (≤200) The typeface for the message box you type prompts in. Empty (the default) uses the interface font. Settings → Appearance → Text → Fonts → "Message box font". Synonyms: composer font, typing box font, prompt font, message input font.
conciergeAlwaysAllowKinds list array of "web-lookup" | "note-save" Your Chief of Staff's standing permissions — the kinds of action you have told it not to ask about again. Each entry is one action kind ("web-lookup" = opening a web page or searching the web, "note-save" = saving a quick note). Empty (the default) means it asks about everything. Adding or removing one happens in Chief of Staff itself (the checkbox on its approve card, or the list in its notes dialog); no other setting can grant these, and an action that deletes, spends, changes a setting, starts a paid helper, runs inside one of your real projects or sends any email can never be on the list.
conciergeCustomInstructions text string (≤10000) Your own free-text notes for the Simple Mode concierge — its "steering knob". Appended to the concierge's instructions at the start of every chat, ON TOP of the built-in persona (never replacing it, and the concierge's safety rules always win). Empty (the default) means no custom notes. Up to 10,000 characters. Synonyms: concierge instructions, simple mode notes, concierge steering, my custom concierge notes, guide the concierge.
confirmQuickReplyOnBlankSession toggle true | false When on (the default), sending a quick reply to a session with nothing in it asks you to confirm first, so a reply meant for another session is not sent into the wrong one.
crossDeviceSyncEnabled toggle true | false Cross-Device Sync
crossDeviceSyncMirrorMigrationDismissed toggle true | false True once the user has dismissed (or acted on) the one-time "switch from folder Backup Mirror to Cross-Device Sync" migration offer — never shown again after. Governs BOTH the pre-enroll offer (sync section + the Data Transfer nudge) AND the post-enroll "turn folder Backup Mirror off" hint (they are mutually exclusive by enrollment state). Purely a UI bookkeeping flag — it changes no sync/mirror behavior. Default: false. See mirror-migration.ts + MirrorMigrationCard.tsx.
customHeaderLayoutEnabled toggle true | false In development: add up to four header rows, move any header piece or shortcut icon to any row, and choose what shrinks when space is tight — from Settings → Widgets and the header right-click menu.
customRenderRules list array of object { enabled: true | false; flags: string (≤8); icon: "tag" | "check-circle" | "x-circle" | "alert-circle" | "alert-triangle" | "info" | "git-pull-request" | "git-merge" | "git-branch" | "rocket" | "flag" | "star" | "zap" | "bug" | "clock" | "shield" | "link" | "circle-dot"; id: string; labelTemplate: string (≤200); linkTemplate: string (≤500); name: string (≤100); pattern: string (≤500); tone: "neutral" | "accent" | "success" | "warning" | "danger" | "info" } Your list of Custom Render Rules — each a regex whose matches render as an inline badge in conversation messages, with a color/tone, an optional icon, an optional label built from the match, and an optional clickable http/https link. Add, edit, reorder (first match wins), and delete them in Settings → Sessions → Custom Render Rules. Synonyms: regex render rules, message badges, custom badges, status pill, PR badge.
customRenderRulesEnabled toggle true | false Master switch for Custom Render Rules — your own regex rules that render matching text in conversation messages (both agent output and your own) as inline badges. On (default): your enabled rules render. Off: all custom badge rendering is disabled without deleting your rules. Manage the rules in Settings → Sessions → Custom Render Rules.
darkVisualTheme unknown "glassmorphism" | "linear" | "warm-charcoal" | "aurora" | "soft-depth" | "neon" | "spotify" | "luxury" | "gradient-sidebar" | "neumorphic" | "frosted-tiers" | "vercel" | "liquid-glass" | "aurora-glass" | "macos" | any The visual theme used while the app is in dark mode. Empty (the default) means the same theme as the main Visual Theme setting. With Theme set to System, the app swaps to this theme whenever the computer switches to dark. Settings → Appearance → Theme & Visual → "Separate looks for light and dark". Synonyms: dark mode theme, night theme, different theme for dark mode.
diffColorScheme select "classic" | "colorblind" | "high-contrast"
diffDefaultViewMode select "unified" | "side-by-side" How code changes open by default: 'unified' shows them in one column, 'side-by-side' shows the old and new versions next to each other.
diffIgnoreWhitespace toggle true | false When on, differences that are only spaces, tabs, or blank lines are ignored in code changes.
fileExplorerWidth number integer 180..500 Width in pixels of the file explorer panel (180 to 500).
fileViewerFontSize number integer 10..20 Font size in pixels for the built-in code and file viewer (10 to 20).
focusGuardEnabled toggle true | false When on (the default), Omniscio takes focus back when a stray console window or another app briefly steals it, so what you were typing does not land in the wrong place. Turn it off to let Omniscio stay in the background when something else takes focus.
foldRateSamples list array of object { bytes: number; ms: number } Internal bookkeeping: how long each recent COMPLETED fold took, so the boot trigger prices a fold by what this machine has actually measured itself doing rather than by a constant. One entry per fold that finished, newest last, capped. Each is { bytes, ms } — the store size the fold rewrote and the FOLD step's own elapsed time (never the whole run's, which also contains the optional dead-data step and would poison the rate low on a long scheduled run). The learned rate is floored at the constant, so a slower machine can never make the app LESS willing to tidy up; clear this list to fall straight back to the constant. Not user-facing input, and excluded from settings export — a rate measured on one computer is not a fact about another.
frenchPilotEnabled toggle true | false Adds French (Français) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
friendlyHomeEnabled toggle true | false
georgianPilotEnabled toggle true | false Adds Georgian (ქართული) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
germanPilotEnabled toggle true | false Adds German (Deutsch) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
googleCliFallbackEnabled toggle true | false When on, a Google task that fails on the direct API is retried through the Google command-line tool instead, so the task still finishes.
hardcoreModeEnabled toggle true | false Master switch for Hardcore Mode, which locks an item after a limited number of free looks or snoozes to keep you moving. Off by default.
hardcoreModeForcePastPhrase text string (≤200) The phrase you must type to force past a locked item (used only when the require-phrase toggle is on and the phrase isn't blank).
hardcoreModeForcePastRequirePhrase toggle true | false Require typing the force-past phrase to get past a locked item, adding deliberate friction. Off restores one-click force-past.
hardcoreModeLabRevealed toggle true | false An app-wide discipline mode (the opposite of Focus Mode). Caps how many times you can look at a session or inbox item before it locks. No snooze; you must respond, archive, convert it to a scheduled follow-up, or get AI help. Locking stays off until you turn it on in the Hardcore Mode settings.
hardcoreModeLooksBeforeLock number integer 0..10 How many free looks an item gets before it locks (0 to 10).
hardcoreModeScope select "all" | "selected" Whether Hardcore Mode's locks apply to all projects or only the ones you selected.
hardcoreModeSelectedProjectIds list array of string (≤200) Which projects Hardcore Mode applies to when its scope is set to 'selected'.
hardcoreModeSnoozesBeforeLock number integer 0..10 How many free snoozes an item gets before its snooze option locks (0 to 10).
headerBlockOrder list array of string (≤50) Ordered block ids for the header's right-side drag-to-reorder row (for example account, hardcore, shortcuts). Controls which header blocks appear in that row and their order; written automatically when you drag the blocks into a new arrangement. Synonyms: toolbar block order, header arrangement, reorder header icons, toolbar layout.
helpdeskConsoleRailWidth number integer 240..480 How wide the Help Desk's right-hand details rail is, in pixels — the panel showing the selected conversation's details, remembered at the width you dragged it to. It is stored separately from the left queue column, so the two drags never leak into one another, and it defaults to the fixed width the rail used before the console became resizable. Synonyms: help desk details rail width, ticket details panel width, resize the help desk rail, support console rail size, right panel width in help desk.
helpdeskWidgetPosition select "left" | "right" Which bottom corner the floating Get Help chat bubble sits in (left or right). Changed from the widget's own header.
hiddenToolbarItems list array of string (≤50) Which items you have removed from the top toolbar. A display choice only.
hiligaynonPilotEnabled toggle true | false Adds Hiligaynon (Ilonggo) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
hindiPilotEnabled toggle true | false Adds Hindi (हिन्दी) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
hubDescriptions map map of string → string (≤240) Your own custom description for a hub — a built-in tool/integration, a sidebar category, or a project — keyed by hub id, overriding the AI-written default your Chief of Staff and agents otherwise read. Empty (the default) uses the baked-in descriptions. Settings → Hub Descriptions (edit, regenerate with AI, or reset to default per hub).
hubDescriptionsEnabled toggle true | false A Settings section where you can read and edit the short description of every hub — each built-in tool/integration, each sidebar category, and each of your projects. Your Chief of Staff and agents read these to know what each part of Omniscio is and when it’s relevant; each has an AI-written default you can regenerate or override. On by default; the toggle stays live so you can turn it off with one setting flip.
hungarianPilotEnabled toggle true | false Adds Hungarian (Magyar) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
ilocanoPilotEnabled toggle true | false Adds Ilocano (Ilokano) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
imeHotkeyConflictWarningEnabled toggle true | false Windows only. On by default; warns you when Quick Launch is bound to Ctrl+Space and a Chinese/Japanese/Korean input method is installed, since that key toggles input methods and double-fires. The warning offers to rebind it.
indonesianPilotEnabled toggle true | false Adds Indonesian (Bahasa Indonesia) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
instantFixHotkey unknown string (≤100) | array of string (≤100) The keyboard shortcut for Instant Fix (default Ctrl+Shift+Alt+G): highlight text anywhere, press it, and an AI fixes the spelling and grammar and replaces your selection in place. Rebind it in Settings → Hotkeys. Synonyms: instant fix shortcut, fix selected text hotkey, quick grammar fix key.
instantFixHotkeyEnabled toggle true | false Whether the Instant Fix hotkey (instantFixHotkey) is registered at all (default on). It also needs AI text correction switched on. Turn off to free up the shortcut without losing your saved binding. Synonyms: instant fix on off, fix selected text toggle.
integrationSidebarHidden toggle true | false Whether the integration sub-sidebar (for example the knowledge vault) is collapsed to a thin reopen strip. Applies only to integrations that allow collapsing.
integrityFailedAt text string (≤64)
interfaceCompareLayout select "experimental" | "master"
italianPilotEnabled toggle true | false Adds Italian (Italiano) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
japanesePilotEnabled toggle true | false Adds Japanese (日本語) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
kapampanganPilotEnabled toggle true | false Adds Kapampangan (Pampango) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
keybindings map map of string → array of string (≤50) Your keyboard shortcuts — one entry per action, holding the key combinations you bound to it. Edited from Settings, Keyboard shortcuts; an action with an empty list has no key bound.
kmsQuickFindHotkey unknown string (≤100) | array of string (≤100) The keyboard shortcut that opens Quick Launch straight to the Find Note tab in the knowledge vault. Default Ctrl+Shift+Space. Only active when the vault is enabled.
kmsQuickFindHotkeyEnabled toggle true | false Turns the global shortcut that opens Quick Launch to the vault's Find Note tab on or off.
kmsWindowHotkey unknown string (≤100) | array of string (≤100) The global keyboard shortcut that opens the knowledge vault in its own separate window. Default Ctrl+Alt+N.
kmsWindowHotkeyEnabled toggle true | false Turns the global shortcut that opens the knowledge vault window on or off.
koreanPilotEnabled toggle true | false Adds Korean (한국어) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
languageSettingEnabled toggle true | false Choose the display language for the interface. Omniscio offers English plus its AI-translated pilot catalogs (Spanish, Tagalog, Japanese, German, Hindi and more); further languages appear as their translations complete.
lastArchiveIntegrityCheckAt text string (≤64) Internal bookkeeping: ISO timestamp of the last successful ARCHIVE check (the cold-storage mission-control-archive.db). Deliberately its OWN stamp, never lastIntegrityCheckAt: the main DB is checked boot-adjacent and the archive on a calm-window schedule, so one shared stamp would let either cadence suppress the other. Not user-facing.
lastAutoSyncPulledMirrorId text string (≤256) Internal bookkeeping: the mirror-archive id most recently PULLED by auto-sync. Lets the pull short-circuit skip the expensive decrypt when the newest foreign archive is unchanged. Not user-facing.
lastBackupMirrorAt text string (≤64) ISO timestamp of the last successful mirror write. Empty string = never.
lastBackupMirrorAutoSyncAt text string (≤64) ISO timestamp of the last successful automatic sync. Empty = never.
lastBackupMirrorError text string (≤2000) Last mirror-write error message (for diagnostics). Empty = no failure.
lastGitRepackAt text string (≤64) ISO timestamp of the last startup git compaction that CHANGED a store. Empty = never ran usefully. Distinct from the results clock below on purpose: it answers "when was this store last actually compacted", which a run that found nothing to do cannot answer.
lastGitRepackAttemptsByRepo map map of string → object { afterPacks: number; beforeLoose: number; beforePacks: number; budgetMs: number; observedAt: string; pricedBytes: number; reason: string; runBudgetMs: number; status: "compacted" | "skipped" | "failed" } Internal bookkeeping: THE LAST ATTEMPT ON EACH STORE, keyed by repo path — the durable per-store record the automatic boot trigger reads to decide whether another fold would merely repeat one that already achieved nothing (I-665). Written by every compaction run, upserted per repo, and never cleared by a run that covered other repos. WHY IT IS NOT lastGitRepackResults ABOVE. That one is a RUN's report: recordResults writes it whole, because the Git storage card prints it under lastGitRepackResultsAt as "what the last run did" — so a run covering two of five repos must NOT leave rows from an older run in it. Reading the trigger's evidence out of that key therefore made the evidence as short-lived as the run: a boot that queued store B erased the record of store A's failed fold, A came back with no history, and with two over-threshold stores the back-off alternated forever — one full 15-minute fold per boot, the exact tax the rule exists to remove. A store's own past is a fact about the STORE, so it gets its own key that only a measurement of that store can change. Not user-facing input.
lastGitRepackResults list array of object { afterBytes: number; afterPacks: number; beforeBytes: number; beforePacks: number; reason: string; repoPath: string; status: "compacted" | "skipped" | "failed" } Internal bookkeeping: the outcome of the most recent startup git compaction, surfaced by the Git storage card so the user learns what was reclaimed (or why nothing was). Not user-facing input.
lastGitRepackResultsAt text string (≤64) ISO timestamp of the RUN that produced lastGitRepackResults, written on every run. It exists because those two facts came apart: lastGitRepackAt moves only when a run really compacted something, so after a skipped run the card would have shown results from moments ago under a header naming a run days old. The card renders THIS beside the results.
lastIntegrityCheckAt text string (≤64) ISO timestamp of the last successful PRAGMA quick_check. Empty = never. Gates the deferred startup integrity check to at most once per week (quick_check scales with DB size: ~4.4s on a 950 MB DB).
lastPushedMirrorChangeMarker text string (≤128) Internal bookkeeping: a cheap content token of the DB (message/session counts + max message timestamp) captured at the last auto-PUSH. Lets the push short-circuit skip re-writing a ~1–3 GB archive when nothing changed. Not user-facing.
lastSetupBackupAt text string (≤64) ISO timestamp of the last successful backup send. Empty string = never sent.
lastSetupBackupContentHash text string (≤128) SHA-256 content hash of the last successfully sent bundle. Used for dedup.
lastSetupBackupFailureAt text string (≤64) ISO timestamp of the last failed backup attempt (for diagnostics). Empty string = no failure.
lastSetupBackupFailureMessage text string (≤2000) Last failure error message (for diagnostics in Settings UI). Empty string = no failure.
lightVisualTheme unknown "glassmorphism" | "linear" | "warm-charcoal" | "aurora" | "soft-depth" | "neon" | "spotify" | "luxury" | "gradient-sidebar" | "neumorphic" | "frosted-tiers" | "vercel" | "liquid-glass" | "aurora-glass" | "macos" | any The visual theme used while the app is in light mode. Empty (the default) means the same theme as the main Visual Theme setting. With Theme set to System, the app swaps to this theme whenever the computer switches to light. Settings → Appearance → Theme & Visual → "Separate looks for light and dark". Synonyms: light mode theme, day theme, different theme for light mode.
mobileHeaderLabEnabled toggle true | false In development: pick the mobile header style (frosted glass, seamless, solid, gradient, floating card, or hairline) and a compact row density, from Settings → Appearance on a phone.
motionPolishEnabled toggle true | false Master switch for the app's visual flourishes (Motion and Polish). Turning it off kills every animated effect at once.
panelLayoutEnabled toggle true | false When on (the default), your saved panel layout shows: which of the main window panels are hidden, which side each is docked on, their order and their widths (rearrange the panels, hide the sidebar, dock a panel on the other side, resize a panel). Turn it off to see the standard arrangement (panel sides and order, regions hidden by name, sizes the layout pinned) while keeping everything you arranged; turning it back on brings your arrangement back. A hide or width the layout already wrote into the panel setting itself (the Projects and Sessions lists, the column widths) stays until you use Reset layout. Safe Mode shows the standard arrangement whatever this says. The arrangement itself is changed in Settings, Appearance, Sidebar, Panel layout, or by an agent through the /layout routes; Reset layout (also the Alt+Ctrl+Shift+L shortcut) puts everything back.
pangasinanPilotEnabled toggle true | false Adds Pangasinan (Pangasinense) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
persianPilotEnabled toggle true | false Adds Persian / Farsi (فارسی) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
pinnedSessionCommandIds list array of string (≤64) Which commands you have pinned to the session header, in order. A display choice from the session-bar customization.
pinnedToolbarItems list array of string (≤50) Which items you have pinned to the top toolbar, in order. A display choice only.
polishAmbient toggle true | false Slow animated gradient on login and empty screens. Part of Motion and Polish, so it needs the master switch on.
polishDashboard toggle true | false Animated count-up numbers and staggered card entrances on the Dashboard/Insights view. Part of Motion and Polish.
polishDepth toggle true | false Gives panels and cards a soft lift shadow. Part of Motion and Polish.
polishGlideReorder toggle true | false Session rows slide to their new position when the sidebar re-sorts. Part of Motion and Polish.
polishInboxZero toggle true | false A calm 'all caught up' moment when the Needs-You count reaches zero. Part of Motion and Polish.
polishInteractive toggle true | false Small hover effects like lifts and sheen on buttons and toolbars. Part of Motion and Polish.
polishPilotEnabled toggle true | false Adds Polish (Polski) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
polishViewCrossfade toggle true | false Fade the transition when switching to or from the Dashboard instead of a hard swap. Part of Motion and Polish.
portableBackupEnabled toggle true | false Export an encrypted backup file you can move to another computer, and import it back.
postRestoreWizardPending toggle true | false Internal bookkeeping: set after a restore so the wizard that re-enters anything unsyncable (like API keys) opens; cleared when done. Not a setting to change.
presentationBlockAutoSpawn toggle true | false While presenting, refuse automatic session starts (scheduled, automation, email, and similar) but still allow your own launches. Held work waits and runs once turned off. Off by default.
presentationContentScrub toggle true | false Optional extra layer that also blurs the CONTENT inside an open session while presenting — message text, file paths, and names — not just the sidebar. Off by default; layered on top of the always-on chrome hiding. Synonyms: blur message content, scrub open session on camera, hide conversation text during a demo.
presentationCustomLabels unknown pipeline Custom placeholder labels for the "placeholder" hide style, keyed by project/session id (e.g. name a hidden client "Acme"). An id with no entry falls back to an auto "Project N" / "Session N" label. Edited inline in the Presentation backstage. Synonyms: custom placeholder names, rename hidden items for a demo, presentation labels.
presentationDemoIdentity object object { avatarDataUrl: string (≤300000); name: string (≤200) } The optional demo identity shown in place of your real account while presenting: a display name plus an optional small avatar image (empty avatar falls back to an initials chip). null (the default) shows a neutral "Presenter" placeholder. Nothing about your real name/email/avatar is shown on camera. Synonyms: demo name, fake account name for a demo, presenter identity, hide my email on screen.
presentationExitStripPosition select "top" | "bottom" Which edge of the screen the "Presentation Mode / Exit" strip anchors to while presenting ('top' or 'bottom'; default 'bottom'). No Settings-UI control yet; set via CLI/PATCH.
presentationHiddenIntegrationIds list array of string (≤200) Which of your built-in Omniscio panels are hidden from camera while presenting, by integration id — a per-integration opt-out on top of the master "Show my integrations on camera" switch. Empty (the default) hides none. Set from the per-integration checkboxes in the Presentation Mode staging panel.
presentationHideAccountWidget toggle true | false Opt-in toggle that hides the header account switcher / balancer widget ENTIRELY while presenting — the account chip plus the balance-scale "N accounts in use" load-balancer count all leave the header, rather than just disguising the name on them. Off by default (the chip stays, showing a demo identity). Synonyms: hide the account widget on camera, hide the account switcher during a demo, hide how many accounts I am running, remove the account pill while presenting.
presentationHideStyle select "remove" | "blur" | "placeholder" How a NON-revealed project or session looks while presenting: "remove" (default, safest) filters it out of the sidebar entirely so it can never leak; "blur" keeps the row but blurs the name in place; "placeholder" swaps a neutral label like "Project 1" / "Session A". Synonyms: presentation hide style, how to hide items on camera, blur vs remove vs placeholder.
presentationModeEnabled toggle true | false Master switch for Presentation Mode (recording-safe / demo mode). When on, Omniscio hides everything private on camera — your projects and sessions, account name/email, and live spend — except the items you explicitly reveal in the Presentation backstage, plus any session you start yourself while it is on. Persists across restarts and only turns off when you exit. Off by default. Synonyms: presentation mode, demo mode, screen-share/recording safe mode, privacy mode, hide everything for a demo, backstage.
presentationQuietInbox toggle true | false While presenting, show nothing in the inbox and a zero badge so no alerts appear on camera. Nothing is lost; everything reappears the moment it is turned off. Off by default.
presentationRevealIntegrations toggle true | false When on (default), your built-in Omniscio panels (Mail, Calendar, Tasks, Mind Map, and so on) show on camera while presenting; turn individual ones off with presentationHiddenIntegrationIds. Off hides them all. Presentation Mode staging panel → "Show my integrations on camera".
presentationRevealedProjectIds list array of string (≤200) The list of project ids you chose to SHOW while presenting (everything else is hidden). Managed from the Presentation backstage reveal toggles; a project the user creates while presenting is auto-added. Synonyms: revealed projects, which projects are visible on camera, presentation allow-list (projects).
presentationRevealedSessionIds list array of string (≤200) The list of session ids shown while presenting — your explicit picks PLUS any session you start yourself while Presentation Mode is on (automation/recipe/background spawns are never added, so they stay hidden). Managed from the Presentation backstage. Synonyms: revealed sessions, which sessions are visible on camera, presentation allow-list (sessions).
presentationShowExitStrip toggle true | false Whether the "Presentation Mode / Exit" strip renders at all while presenting (default on). No Settings-UI control yet; set via CLI/PATCH.
projectLayoutPins map map of string → string (≤40) Stores which saved panel layout is tied to each project, so opening that project's sessions can bring its layout up. Empty by default, meaning no project has a layout. It only takes effect while following project layouts is on. Synonyms: project layouts, pinned layout per project, project panel arrangement, layout by project.
projectLayoutSession unknown unknown Keeps a record, managed by the app, of a project layout that is currently showing and the arrangement to put back afterward. Empty by default. You do not set it yourself. It lets the app return your panels to how they were when you leave the project. Synonyms: project layout in force, restore layout, layout return point, previous layout.
projectLayoutsEnabled toggle true | false When on, switching to a project can bring up the saved panel layout pinned to it, then put your previous layout back when you leave. On by default. Turning it off stops layouts from following the active project. Synonyms: layout per project, follow project layout, project panel layouts, automatic layout switching.
projectLookPresets map map of string → string Stores the ready-made color set you chose for each project, so its look can be recalled when that project is open. Empty by default, meaning no project has a chosen set. It only has an effect while project looks are switched on. Synonyms: project color set, per project theme, project look preset, project accent.
projectsSidebarIconsOnly toggle true | false Collapse the desktop projects sidebar to a narrow strip of icons (name on hover) instead of full labeled rows. Desktop only.
projectsSidebarWidth number integer 120..400 Width in pixels of the projects sidebar (120 to 400).
punjabiPilotEnabled toggle true | false Adds Punjabi (ਪੰਜਾਬੀ) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
quickChatTargets list array of object { hotkey: string (≤100) | array of string (≤100); id: string (≤64); kind: "person" | "channel"; label: string (≤200); refId: string (≤128) } The people and channels you have saved for quick Team Chat messages, each optionally with its own keyboard shortcut. Also seeds the quick-pick list in the message composer.
quickEmailEnabled toggle true | false Master switch for the Quick Email feature. Off by default.
quickEmailHotkeysEnabled toggle true | false Turns on the per-recipient global keyboard shortcuts for Quick Email. Off by default.
quickEmailShowSubjectByDefault toggle true | false Whether the Quick Email composer shows the subject line when it opens. Off by default.
quickLaunchDefaultProjectId text string (≤64) The project Quick Launch sends new work into by default. Leave empty to use the Claude project.
quickLaunchHotkeyEnabled toggle true | false Master switch for the Quick Launch keyboard shortcut. On by default.
quickLaunchPinnedActionIds list array of string (≤64) Internal remembered state: the ordered list of Quick Launch actions you have pinned as tabs. Not usually edited by hand.
quickLaunchTabHotkeys map map of string → string (≤100) | array of string (≤100) The global keyboard shortcuts that open Quick Launch to a specific tab (for example Calendar or Email). Each one only activates when its feature is turned on.
quickLaunchTaskDefaultListId text string (≤64) The Tasks list that a Quick Launch quick-capture files into. Leave empty to use the Inbox list.
quickReplyEnabled toggle true | false When on, quick replies let you send a saved answer to the session you are looking at with one key instead of typing it.
quickReplyNumberKeysDirection select "bottom-up" | "top-down" Quick Replies — how the number badges count in the Alt+S quick-reply picker. bottom-up puts 1 on the bottom row (nearest the send box) and counts up; top-down puts 1 on the top row and counts down. Default bottom-up. Pinned numbers always win either way. Synonyms: numbering direction, number keys order, Alt+S numbering, quick reply badge order.
quickReplyNumberKeysEnabled toggle true | false When on, the number keys pick a quick reply while the quick-reply list is open.
quickReplyText text string (≤500) The saved answer a quick reply sends to the current session. Edit it from the quick-reply settings.
quickSmsRecipients list array of object { id: string (≤64); name: string (≤100); phone: string (≤40) } Your saved SMS favorites for quick-texting from Control Space. The SMS tab also shows recently texted contacts alongside these.
repackOnNextStartupRequestedByUser toggle true | false True when the USER scheduled the pending compaction above. The Git storage card is the only IN-APP path that sets it together with the list, and it clears both on cancel — but a headless or CLI write (PATCH /settings) can set it too, and an import or a restore can CARRY it in alongside the list, since no such path touches either key. It decides the pre-window budget: a marked run keeps the long whole-run budget, an unmarked one gets a minute, so the window is held for at most that. Cleared together with the request at boot.
repackReposOnNextStartup list array of string Absolute paths of git repositories to COMPACT on the next app launch — the git-store twin of compactOnNextStartup. Set by the "Compact git storage" action. Honored behind the splash: before the main window opens, before any session resumes, and before the app runs any git of its own, because that is the only moment in the app's life with no git activity to contend with. The list is cleared and flushed to disk BEFORE the work starts, and the work is ABANDONED if that clear fails, so a compaction can never boot-loop.
romanianPilotEnabled toggle true | false Adds Romanian (Română) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
russianPilotEnabled toggle true | false Adds Russian (Русский) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
savedPanelLayouts list array of unknown Holds your named saved panel layouts, up to 20, each remembering which panels are shown, their order and their sizes. Empty by default. You create them from the saved layouts card, and you can switch, rename or delete them there. Synonyms: saved layouts, panel presets, window arrangements, layout list.
savedPanelLayoutsChangedBy unknown unknown Records who last changed the saved layouts list and what they did, such as saving, switching, renaming or deleting a layout. It is empty until a change happens and is written by the app, not by you. Synonyms: layout change history, last layout change, who changed layouts, layout audit.
savedSidebarViews list array of object { group: "status" | "project" | "tag" | "none"; id: string (≤40); name: string (≤40); onlyRunning: true | false; projectId: string (≤80); sort: "recent" | "name" | "status"; statuses: array of "running" | "needs_you" | "error" | "stalled" | "starting" | "ready" | "terminating" | "ended" | "archived" | "paused" | "waiting"; tag: string (≤60) } Holds your named sidebar views, up to 20. Each view remembers how the session list is grouped and sorted and which statuses, project or tag it shows. Empty by default. You create and manage them from the sidebar views card in settings. Synonyms: saved filters, sidebar presets, session list views, custom views.
scratchpadAutoDeleteEnabled toggle true | false When on, Omniscio deletes scratchpad notes older than your retention window on its own. Off by default — nothing is deleted unless you turn this on.
scratchpadQuickCaptureHotkey unknown string (≤100) | array of string (≤100) System-wide keyboard shortcut(s) that pop a small floating note box OVER whatever app you are using — a dedicated always-on-top capture window that never switches you to Omniscio. Type a note and press Ctrl+Enter or Escape to save and dismiss, returning to what you were doing. Distinct from the "Quick scratchpad" hotkey (Ctrl+Shift+S), which opens the rich in-app overlay and foregrounds the app. NO default binding (owner request 2026-08-25 — the rich Quick scratchpad on Ctrl+Shift+S is the only scratchpad, so this floating variant ships unbound); rebindable in Settings → Keyboard Shortcuts → System-wide. An empty list disables it. Synonyms: floating scratchpad capture, quick note over current app, floating quick-capture hotkey, jot a note without switching apps.
scratchpadQuickCaptureHotkeyEnabled toggle true | false Master on/off toggle for the Floating scratchpad capture system-wide hotkey. On by default, but the floating capture ships UNBOUND (no default key — the rich Quick scratchpad on Ctrl+Shift+S is the single scratchpad), so bind a key in scratchpadQuickCaptureHotkey first for anything to register. Off: the shortcut stops being registered system-wide even when bound. The companion field is scratchpadQuickCaptureHotkey. Synonyms: enable floating scratchpad capture, turn off floating capture shortcut, floating scratchpad global hotkey toggle.
scratchpadRenderMarkdown toggle true | false Style markdown as you type in the scratchpad (bold, headings) while still showing the raw markdown characters.
scratchpadRetentionDays number integer 1..365 How long a scratchpad note is kept before auto-delete removes it, in days (1 to 365). Only used when scratchpad auto-delete is on.
scratchpadWindowHotkey unknown string (≤100) | array of string (≤100) System-wide keyboard shortcut(s) that open the rich Quick scratchpad overlay (the surface with the note list, pop-out, and settings) from any app, even when Omniscio is not the active window. Raises the app, then opens the overlay. Works while the app is running in the background. Default is Ctrl+Shift+S — the SINGLE scratchpad hotkey (owner request 2026-08-25); the stripped-down floating capture below was removed so there is one scratchpad. Rebindable in Settings → Keyboard Shortcuts → System-wide; an empty list disables it. Synonyms: quick scratchpad hotkey, global scratchpad shortcut, open scratchpad from anywhere, launch scratchpad.
scratchpadWindowHotkeyEnabled toggle true | false Master on/off toggle for the Quick scratchpad system-wide hotkey. On (default): the Ctrl+Shift+S shortcut (or whatever you rebound it to) opens the rich Quick scratchpad overlay from any app. Off: the shortcut stops being registered system-wide. The companion field is scratchpadWindowHotkey. Synonyms: enable scratchpad hotkey, turn off scratchpad shortcut, scratchpad global hotkey toggle.
secretHandleEnabled toggle true | false Intercepts clipboard pastes that appear to contain secrets (API keys, tokens, passwords) before they reach a spawned agent session, storing them under an opaque handle so the raw value stays out of your saved history. Off by default; turn it on in Settings → Features.
serbianPilotEnabled toggle true | false Adds Serbian (Српски, Cyrillic script) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
sessionFilterStyle select "panel" | "menu" How you add filters to a sessions sidebar section: "panel" (the default) opens an inline panel of chips under the section header that filter and sort the list the moment you click them, and stays open until Done or Escape; "menu" opens the original pop-up menu where you pick a kind, then its values. The Panel | Menu switch in the filter bar flips it in place. Synonyms: filter style, filter panel, filter menu, inline filters, live filter chips, sidebar filter picker.
sessionMenuCustomizationEnabled toggle true | false In-development: lets each user reorder the items in a session's ⋯ (more actions) menu and hide the ones they don't use — from a drag-to-reorder list in Settings → Sessions and by right-clicking a row in the menu itself. Off by default; hidden until shipped.
sessionMenuHidden list array of string (≤64) Which entries are hidden from a session's ⋯ overflow menu, by entry id. Edit the list in Settings → Sessions → session menu customization; ships with a curated default set of hidden entries.
sessionMenuOrder list array of string (≤64) Your custom display order for entries in a session's ⋯ overflow menu, by entry id. Empty (the default) uses the built-in order. Edit it in Settings → Sessions → session menu customization.
sessionSectionViews map map of string → object { computer: string (≤200); counts: true | false; facets: object { activity: array of string (≤200); owner: array of string (≤200); startedBy: array of string (≤200); where: array of string (≤200) }; filter: string; groupByKind: true | false; hiddenKinds: array of string; overseerShow: "all" | "waiting" | "running"; overseerSort: "mine" | "name" | "needs-you" | "crew"; owner: "overseer" | "solo"; sort: "recent" | "name" | "stale"; where: "cloud" | "local" | "linked"; working: true | false } Your per-section view for the sessions sidebar: which sort each section (Interrupted / Live / Paused) is shown in, and that section's own name filter. An absent entry means untouched, so a section you never opened behaves exactly as before. A filter is a view preference, not a temporary one — it stays until you click Clear, which is why every filtered section says so in its banner. Synonyms: session section view, sort a sidebar section, filter the sessions list, section name filter, interrupted live paused sort.
sessionStateStyles object object { done: object { color: string (≤9); icon: string (≤64); label: string (≤40) }; error: object { color: string (≤9); icon: string (≤64); label: string (≤40) }; needs_you: object { color: string (≤9); icon: string (≤64); label: string (≤40) }; running: object { color: string (≤9); icon: string (≤64); label: string (≤40) }; waiting: object { color: string (≤9); icon: string (≤64); label: string (≤40) } } Holds your custom color, icon and label for each of the five session states: running, waiting, needs you, done and error. Every field is empty by default, which keeps the standard look. They show on sidebar rows, cards and the inbox. Synonyms: status colors, status icons, custom status labels, session state look.
sessionsSidebarWidth number integer 180..500 Width in pixels of the sessions sidebar (180 to 500).
setupBackupConsecutiveFailures number integer 0..10000 Consecutive failure count since last successful send. Resets to 0 on success.
setupBackupEnabled toggle true | false Setup-backup feature flag. Default: false.
showOnlyActiveProjects toggle true | false Hide projects that have no running, needs-you, or errored session, showing only active ones.
sidebarDriftColorsEnabled toggle true | false When on (the default), the sidebar drift chip colours its numbers by severity, so a metric past its warn or critical threshold is coloured to match. Turn it off and the chip still reports every drift number — it just renders in one neutral colour, for when the colour shift reads as noise and you want the numbers without the alarm. Synonyms: sidebar drift colours, colour the drift chip, drift warning colours, turn off drift colouring, sidebar version drift severity colours.
sidebarDriftLevels object object { appAhead: object { critical: integer 0..1000000; warn: integer 0..1000000 }; appBehind: object { critical: integer 0..1000000; warn: integer 0..1000000 }; leaseFailurePercent: object { critical: integer 0..1000000; warn: integer 0..1000000 }; leaseHandoutMinutes: object { critical: integer 0..1000000; warn: integer 0..1000000 }; prLastMergeMinutes: object { critical: integer 0..1000000; warn: integer 0..1000000 }; prOldestOpenHours: object { critical: integer 0..1000000; warn: integer 0..1000000 }; queueAgeMinutes: object { critical: integer 0..1000000; warn: integer 0..1000000 }; queueDepth: object { critical: integer 0..1000000; warn: integer 0..1000000 }; remoteAhead: object { critical: integer 0..1000000; warn: integer 0..1000000 }; remoteBehind: object { critical: integer 0..1000000; warn: integer 0..1000000 }; remoteSyncAgeMinutes: object { critical: integer 0..1000000; warn: integer 0..1000000 }; stuckBranches: object { critical: integer 0..1000000; warn: integer 0..1000000 }; verdict3MissPct: object { critical: integer 0..1000000; warn: integer 0..1000000 } } The warn and critical thresholds the sidebar drift chip colours against, one pair per metric. Every value is a COUNT except queueAgeMinutes, which is in MINUTES. Raise a threshold to make that metric look calmer, lower it to flag drift sooner. Ships with defaults for every metric, so you only need to set the ones you care about. Synonyms: sidebar drift thresholds, drift warn levels, drift critical levels, when does drift go red, tune the drift warning thresholds.
sidebarRarelyUsedCollapsed toggle true | false Whether the rarely-used sidebar group the automatic tidy created is folded shut. A display choice only.
sidebarSortByUsageEnabled toggle true | false When on, your sidebar items are ordered by how often you use them instead of alphabetically, so the ones you reach for most stay near the top.
sidebarUngroupedItems list array of string (≤64) Sidebar items you have chosen not to put into any custom group. A display choice only.
sidebarUsageWindowDays number integer 1..365 How many days of recent use the sidebar's usage ordering counts, in days (1 to 365). Only used when ordering by usage is on.
simpleModeEnabled toggle true | false Chief of Staff Mode gives you one friendly chatbox to run the app in plain words — set a reminder, save a note, check your inbox, ask a question — without learning the rest of the interface. Still an early version, so expect the odd rough edge. Off by default.
simpleModeFullView toggle true | false While you are opted into Simple Mode, which view you are looking at: false (default) = the Simple Mode chatbox (the friendly concierge takeover), true = the normal full Omniscio app. Flipped by the Full <-> Simple switch in the header (and by the Simple Mode hotkey / command bus), NOT a Settings toggle — turning Simple Mode on still enters the Simple view by default, and switching to Full keeps you opted in so the header switch stays available to jump back. Synonyms: simple mode view, which simple mode view, switch to the full app, back to simple mode, full vs simple view, simple mode header switch, am I in simple or full view.
simplifiedChinesePilotEnabled toggle true | false Adds Simplified Chinese (简体中文) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
spanishPilotEnabled toggle true | false Adds Spanish (Español) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
supermailWindowHotkey unknown string (≤100) | array of string (≤100) The global keyboard shortcut that opens Supermail in its own separate window. Default Ctrl+Alt+M. Only active when Supermail is enabled.
supermailWindowHotkeyEnabled toggle true | false Turns the global shortcut that opens the Supermail window on or off.
swahiliPilotEnabled toggle true | false Adds Swahili (Kiswahili) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
tagalogPilotEnabled toggle true | false Adds Tagalog to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
tasksV2OffMachineBackupNoticeDismissed toggle true | false True once the user has dismissed the Tasks/Inbox "your tasks exist only on this computer" notice — the warning's own acknowledgement. Kept SEPARATE from backupOffMachineSetupOfferDismissed on purpose: that flag is also written the moment someone merely CHOOSES a backup route, so reading it here would silence the warning for an install whose backup was started and never finished. Default: false. See TasksV2NoOffMachineBackupNotice.tsx.
tasksV2RailWidth number integer 180..500 Internal: remembers how wide you dragged the Tasks list rail; falls back to the sessions sidebar width until you resize it. Not a setting to change by hand.
teamChatSidebarWidth number integer 180..500 Internal: remembers how wide you dragged the Team Chat channel list; falls back to the sessions sidebar width until you resize it. Not a setting to change by hand.
teamChatWindowHotkey unknown string (≤100) | array of string (≤100) The global hotkey that opens Team Chat in its own separate window. Default Ctrl+Alt+T (mnemonic: Team Chat, completing the Ctrl+Alt+<letter> window family alongside KMS and Supermail). It only registers while Team Chat is enabled, since the window it opens is feature-gated. Synonyms: team chat hotkey, open team chat window, team chat shortcut, global hotkey team chat, pop out team chat.
teamChatWindowHotkeyEnabled toggle true | false Whether the Team Chat window hotkey is registered. On by default. Synonyms: team chat hotkey on off, enable team chat shortcut, disable team chat hotkey, team chat window key.
terminalFontFamily text string (≤200) The typeface for the built-in terminal. Empty (the default) uses the code font, and when that is empty too, the system monospace font. Settings → Appearance → Text → Fonts → "Terminal font". Synonyms: terminal font, console font, shell font, xterm font.
thaiPilotEnabled toggle true | false Adds Thai (ไทย) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
themeDarkAt text string The local time of day when the automatic theme schedule switches the app to dark, written as hours and minutes. 7:00 PM (19:00) by default. It only matters while the theme schedule is on. Synonyms: dark mode start time, night theme time, switch to dark, evening theme.
themeLightAt text string The local time of day when the automatic theme schedule switches the app to light, written as hours and minutes. 7:00 AM (07:00) by default. It only matters while the theme schedule is on. Synonyms: light mode start time, day theme time, switch to light, morning theme.
themeScheduleEnabled toggle true | false When on, the app flips between light and dark at two times you choose each day. Off by default. While it is off, your Dark, Light or System choice works as usual. Turning it on lets the schedule take over the theme. Synonyms: automatic dark mode, scheduled theme, day night theme, auto theme.
traditionalChinesePilotEnabled toggle true | false Adds Traditional Chinese (繁體中文) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
turkishPilotEnabled toggle true | false Adds Turkish (Türkçe) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
uiFontFamily text string (≤200) The typeface for the whole interface — menus, lists, settings and messages. Empty (the default) uses the system font. Takes any font installed on the computer, or a comma-separated list where the first installed one wins; a name the computer does not have falls back to the system font. Settings → Appearance → Text → Fonts → "Interface font". Synonyms: change font, app font, ui font, interface typeface, font family, use Inter.
universalCommandPaletteEnabled toggle true | false In-development: opens a comprehensive, fuzzy-search command palette (Ctrl+Shift+P) that reaches every action, navigation hub, and setting in one keypress. Flag off = today's curated Quick Launch command tab (no regression). DevOnly while the catalog stabilises.
unusedGroupDisplayOrder number integer Where the unused sidebar group sits among your groups — a number, and a lower number sorts higher up.
urduPilotEnabled toggle true | false Adds Urdu (اردو) to the language picker as a pilot catalog translated by AI. Urdu reads right-to-left. Any untranslated text falls back to English.
vietnamesePilotEnabled toggle true | false Adds Vietnamese (Tiếng Việt) to the language picker as a pilot catalog translated by AI. Any untranslated text falls back to English.
warayPilotEnabled toggle true | false Adds Waray (Waray-Waray) to the language picker as a pilot catalog translated by AI. Off by default — English is unaffected, and any untranslated text falls back to English.
winKeyTakeoverEnabled toggle true | false Let a system-wide shortcut use the Windows key (Win+E, Win+V, Win+1-9…). Windows keeps those for itself, so Omniscio takes them for your binding while it runs, and this switch hands every one of them back.
windowSizeLayouts list array of unknown Holds up to six rules that each pair a saved panel layout with a range of window widths. While the main window sits inside a range, that layout shows. Empty by default. Leaving the range puts back what was showing before. Synonyms: layout by window width, responsive layouts, width rules, screen size layouts.
windowSizeLayoutsEnabled toggle true | false When on, the app switches to a saved layout whenever the main window is within a width range you set, for example one for a laptop and one for a big monitor. On by default. Turning it off stops the width rules from changing your layout. Synonyms: follow window width, responsive layout, auto layout by size, width-based layout.
writerAssistantWidth number integer 300..720 Width in pixels of the AI assistant panel in the Writer (300 to 720).
writerFontSize number integer 12..24 The default editor font size in Writer, in points (default 16; choices 12/14/16/18/20/22/24), used by every document that has no size of its own. Writer's own Appearance menu → "Font size". One document's own size is picked from the size dropdown in the Writer formatting toolbar and saved with that document.
writerLineSpacing select "compact" | "normal" | "relaxed" The editor line spacing in Writer: compact, normal, or relaxed (default normal). Writer's own Appearance menu → "Line spacing".
writerPalette select "none" | "parchment" | "midnight-ink" | "candlelight" | "noir" | "velvet" | "frost" | "sage" | "rose" Color palette for the Writer's writing area (parchment, midnight ink, candlelight, and others); 'none' uses the default look. The Writer's own gear menu (Writer settings) → "Palette".
writerShowCharacterCount toggle true | false Shows the live character count in the bar under the Writer editor: the letters, spaces and punctuation you can see, with each emoji counted once and formatting marks not counted. On by default. Writer's own gear menu, Status bar, Character count. Synonyms: character count, characters, letter count, how many characters, tweet length, post length.
writerShowReadTime toggle true | false Shows the estimated reading time in the bar under the Writer editor. On by default. Writer's own gear menu, Status bar, Read time. Synonyms: reading time, read time, minutes to read, how long to read.
writerShowSaved toggle true | false
writerShowWordCount toggle true | false Shows the live word count in the bar under the Writer editor. On by default; when the word count, character count and read time are all off, the bar is hidden. Writer's own gear menu, Status bar, Word count. Synonyms: word count, how many words, hide word count, status bar.
writerShowWordGoal toggle true | false
writerSpagWidth number integer 300..720
writerSplitWidth number integer 320..900
writerTheme select "match-app" | "light" | "dark" Light or dark theme for the Writer: match the app, force light, or force dark. The Writer's own gear menu (Writer settings), at the top.
writerToolbarLayout select "icons-text" | "icons-only" | "compact" | "full-icon" The button style of Writer's own document-header toolbar: icons + labels, icons only, compact, or all icons (default icons only). Writer's own Appearance menu → "Toolbar".
writerVisualEffects toggle true | false

Account & Billing (89)

Your accounts, your keys, and what you are spending.

Setting Type Accepted values What it does
accountTierModelDefaultsEnabled toggle true | false Opt-in, default OFF. When on, a Claude session spawned with no explicit model gets a default model stamped from the picked account's plan tier (Max to Opus, Pro to Sonnet, and so on). Off means no behaviour change. Affects which model — and therefore what a turn costs — when you do not choose one. Synonyms: account tier model defaults, pick model from my plan, default model per account, max account uses opus.
acpAgentsEnabled toggle true | false Install coding agents from the open Agent Client Protocol list — Copilot, Goose, Cline, Qwen Code and more — and run them as session engines. Only fingerprint-checked downloads and pinned npm packages install. On by default; turn it off to hide the card and every installed agent.
allowAbliterationSessionSpawn toggle true | false Opt-in toggle to expose Abliteration as a session provider in the new-session menu / spawn ladder. Abliteration serves abliterated (refusal-stripped, uncensored) models inside the Claude Code harness, configured via your own Abliteration API key. Off by default: no Abliteration sessions can be started until this is enabled. Synonyms: abliteration, abliterated, allow abliteration sessions, abliteration provider, enable abliteration, allow abliteration spawn, uncensored.
allowApiKeySessionSpawn toggle true | false The API-key session-spawn guard. When OFF (the default), API-key accounts can power AI features but CANNOT start sessions — a spawn falls through to a login account, or surfaces the all-exhausted banner if no login account has capacity. Turn it ON to let sessions run on the API key, which means Anthropic bills you per token for that session. Off by default precisely so a pasted key cannot silently start costing money. Enforced in three layers at spawn time. Synonyms: let api keys run sessions, allow api key spawn, run sessions on my api key, api key session guard, stop api keys starting sessions.
allowCrofaiSessionSpawn toggle true | false Retired: the CrofAI reseller lane. CrofAI is shutting down, so the provider is hidden from every model picker and from Settings → Accounts & Providers. Its catalog entry, models and pricing stay in place so existing sessions and recorded spend still resolve.
allowCursorSessionSpawn toggle true | false
allowDeepinfraSessionSpawn toggle true | false Allow starting sessions on cheap DeepInfra-hosted open models (DeepSeek, Qwen, Llama, GLM, Kimi); needs a saved DeepInfra key. Off by default.
allowDeepseekSessionSpawn toggle true | false
allowDshSessionSpawn toggle true | false
allowEngySessionSpawn toggle true | false Opt-in toggle to expose Engy as a session provider in the new-session menu / spawn ladder. Engy serves DeepSeek V4.1 Flash, V4.1 Flash 1017 and V4 Flash inside the Claude Code harness, straight to its own Claude-compatible endpoint, configured via your own Engy API key. Off by default: no Engy sessions can be started until this is enabled. Synonyms: engy, allow engy sessions, engy provider, enable engy, allow engy spawn, deepseek reseller.
allowGeminiccSessionSpawn toggle true | false Allow starting sessions on Google Gemini models (Pro, Flash, Flash-Lite) inside Omniscio; uses your saved Gemini key. Off by default.
allowGlmSessionSpawn toggle true | false
allowGrokSessionSpawn toggle true | false
allowHermesSessionSpawn toggle true | false
allowHighRiskCredentialKinds toggle true | false The high-risk credential gate. When OFF (the default), Omniscio refuses to hand agents the credential kinds with broad access or outbound-abuse potential. Turn it ON only if you deliberately want those credential kinds available. Default false — this one is a security posture setting, not a convenience toggle. Synonyms: allow high risk credentials, broad access credentials, dangerous credential kinds, let agents use risky keys.
allowInferxSessionSpawn toggle true | false Opt-in toggle to expose InferX as a session provider in the new-session menu / spawn ladder. InferX serves DeepSeek V4 Flash — a serverless, pay-per-token OpenAI-compatible endpoint — inside the Claude Code harness, configured via its own API key. Off by default: no InferX sessions can be started until this is enabled. Synonyms: inferx, allow inferx sessions, inferx provider, enable inferx, allow inferx spawn.
allowKimiSessionSpawn toggle true | false
allowKimicodeSessionSpawn toggle true | false
allowMetaSessionSpawn toggle true | false
allowMinimaxSessionSpawn toggle true | false
allowMusecodeSessionSpawn toggle true | false
allowOpencodeSessionSpawn toggle true | false
allowOpenrouterSessionSpawn toggle true | false
allowPiSessionSpawn toggle true | false
allowQwenSessionSpawn toggle true | false
allowRefuselessSessionSpawn toggle true | false Opt-in toggle to expose Refuseless as a session provider in the new-session menu / spawn ladder. Refuseless serves abliterated (refusal-removed) open weights — GLM 5.3 Abliterated, its Flash tier, DeepSeek V4.1 Flash and MiniMax M3.1 Flash, 1M context — inside the Claude Code harness, configured via your own Refuseless API key. Off by default: no Refuseless sessions can be started until this is enabled. Synonyms: refuseless, abliterated, allow refuseless sessions, refuseless provider, enable refuseless, allow refuseless spawn, uncensored.
allowRuninfraSessionSpawn toggle true | false Opt-in toggle to expose RunInfra as a session provider in the new-session menu / spawn ladder. RunInfra serves full-precision (BF16) open models — DeepSeek V4 Flash/Pro, Qwen, Nemotron — inside the Claude Code harness at pay-per-token prices (NOT quantized), configured via its own API key. Off by default: no RunInfra sessions can be started until this is enabled. Synonyms: runinfra, allow runinfra sessions, runinfra provider, enable runinfra, allow runinfra spawn.
allowT3codeSessionSpawn toggle true | false
allowUltramarineSessionSpawn toggle true | false
allowUnverifiedPluginBackends toggle true | false A retired switch that once let plugin backends from unverified sources run. It is off by default, is kept only so older settings are not lost, and is no longer read or written. A plugin's saved consent now decides whether its backend may run. Synonyms: unverified plugin backends, plugin backend override, unsandboxed plugin permission, plugin trust switch.
allowVeniceSessionSpawn toggle true | false Opt-in toggle to expose Venice as a session provider in the new-session menu / spawn ladder. Venice serves uncensored (refusal-stripped) models — GLM 4.7 Flash Heretic and Abliterated Large V2, with a cached-input discount — inside the Claude Code harness, configured via its own API key. Off by default: no Venice sessions can be started until this is enabled. Synonyms: venice, allow venice sessions, venice provider, enable venice, allow venice spawn, uncensored.
antigravityAcpEnabled toggle true | false
antigravitySignInGateEnabled toggle true | false
autoPlacementMaxWorking map map of string → integer 1..500
budgetCapHardUSD number number 0..10000 PER-SESSION HARD cap, in US dollars: a session is force-KILLED when its own accumulated cost crosses this. Default $100. This is the per-session stop; budgetCapSoftUSD only warns. It does NOT bound a fan-out of many sessions — that is what dailyBudgetCapHardUSD is for. Nighty Tidy AUDIT sessions are exempt (an audit legitimately outspends a normal session and carries its own ceiling), but they remain subject to the daily caps. null or 0 disables it. Synonyms: per session hard cap, kill a session that costs too much, max dollars per session, session spend limit, stop a runaway session.
budgetCapSoftUSD number number 0..10000 PER-SESSION SOFT cap, in US dollars: when one session's own accumulated cost crosses this, Omniscio shows a ONE-TIME warning for that session and keeps going — nothing is stopped. Default $20, on. This is the early signal that fires well before the $100 hard kill. Not the same as budgetCapHardUSD (which stops the session) and not the same as the dailyBudgetCap* pair (which measure a whole DAY across all sessions on an account). null or 0 disables it. Synonyms: per session soft cap, warn me when a session costs, session spend warning, soft budget limit, session cost warning threshold.
capacityLedgerPlacement toggle true | false In-development, default OFF, and NOT yet switchable: nothing writes it today — there is no Settings control and no CLI seed — so the only value any install can reach is off. When it IS wired up, turning it on will make the load-balancing picker rank and refuse accounts using the capacity ledger's LIVE projected utilization rather than the stale usage poll, adding proactive refusal and soft affinity; it stays off until shadow-validated. NOTE: AMC_DISABLE_CAPACITY_LEDGER=1 is NOT an off-ramp for it — that env var is read trough the settings-gated shape, so it can only ever disable a feature that this still-off setting has already disabled. Synonyms: capacity ledger placement, live capacity placement, smarter account picking, projected utilization routing.
dailyBudgetCapHardUSD number number 0..10000 PER-ACCOUNT DAILY HARD cap, in US dollars: once TODAY's spend on an account crosses this, Omniscio STOPS the running session AND blocks new spawns on that account until tomorrow. Default $25, on. This is the aggregate backstop the per-session cap cannot provide against a fan-out of many sessions. Applies ONLY to pay-per-use API-key sessions (Anthropic apikey accounts + anthropic-compat vendor keys) — never flat-fee subscription (login) sessions. If someone asks to "lower my spending limit" and means a per-day ceiling, this is usually the one. null or 0 disables it. Synonyms: daily hard cap, stop spending after, max per day, daily spend limit, block new sessions when I hit my daily budget.
dailyBudgetCapSoftUSD number number 0..10000 PER-ACCOUNT DAILY SOFT cap, in US dollars: when TODAY's spend on an account crosses this, Omniscio warns once per session and keeps going. Default $10, on. Applies ONLY to pay-per-use API-key sessions (Anthropic apikey accounts + anthropic-compat vendor keys) — never to flat-fee subscription (login) sessions, which cost nothing extra per turn. Note the axis: this measures a whole DAY across all sessions on the account, where budgetCapSoftUSD measures ONE session. null or 0 disables it. Synonyms: daily soft cap, warn me at a daily spend, per day spend warning, account daily budget warning.
dailyMeteredCompatCapUSD number number 0..10000 PER-PROVIDER DAILY HARD cap, in US dollars, for the metered anthropic-compat vendors (Kimi/Moonshot, DeepSeek, GLM, MiniMax, Meta). Once today's recorded spend for ONE of those vendors crosses this, NEW spawns on that vendor are blocked until tomorrow (a pre-spawn gate). Each vendor is capped separately. It exists because those vendors authenticate with their own vendor key and record no account id, so the per-account daily cap above cannot attribute their spend — this meters by provider instead. Opt-in and OFF by default; null or 0 disables. Synonyms: kimi daily cap, deepseek spend limit, glm daily cap, per vendor daily limit, metered vendor cap, compat vendor spend limit.
defaultProvider text string
defaultThinkingLevel select "auto" | "minimal" | "low" | "medium" | "high" | "max" | "xhigh" | "ultra" How much thinking effort new sessions use by default. Higher levels are smarter but slower and cost more; 'auto' lets the model decide.
devinProviderEnabled toggle true | false Run Cognition's Devin cloud coding agent as a session provider alongside Claude. Devin runs remotely and is billed in ACUs on your own Devin account, so you add a Devin API key to use it.
dismissedDecryptFailureAccountIds list array of string Remembers the accounts you've silenced the 'couldn't unlock your saved login' warning for, so it stops nagging; a newly broken account still warns.
enableBundledApiKeys toggle true | false When on, Omniscio-hosted ("bundled") keys proxy OpenAI, Gemini and Perplexity so those features work without you pasting your own key. Feature-flagged OFF by default. ElevenLabs and Deepgram are deliberately NOT covered — their SDKs ignore the base-URL env var the proxy relies on, so they would need CLI wrappers. Synonyms: bundled api keys, use omniscio hosted keys, built-in api keys, do I need my own openai key.
glmActiveAccountId text string Which GLM account new sessions use by default: a specific saved account, or the shared 'AMC GLM credits' entry. Blank means auto-balance across your personal accounts.
grokbotProviderEnabled toggle true | false Run xAI's Grok Bot desktop agent as a session provider alongside Claude, and let any session hand it a task such as X research. Grok Bot uses the sign-in already saved by the Grok Bot app on this computer, and its usage counts against your own Grok or Cursor plan.
harnessDefaultThinkingLevels map map of string → "auto" | "minimal" | "low" | "medium" | "high" | "max" | "xhigh" | "ultra" Default thinking effort per tool, used whenever that tool runs (e.g. your general sessions). Empty means each tool falls back to the global default.
limitResetsEnabled toggle true | false When a Claude Pro or Max login holds a free limit reset from Anthropic, offer a button beside a session stuck on that limit to use one, after a confirm. Never buys usage credits.
linkedComputersEnabled toggle true | false Your own desktops on your Tailscale network, signed into the same Omniscio account, link with no codes. Pick one in the Run chip and the session runs there while you drive it from here. On by default; turn it off with one setting flip.
linkedComputersFollowed list array of string (≤200)
linkedComputersMirrorSpawned toggle true | false
linkedComputersReleasedSessions list array of string (≤200)
linkedWorkHomeOwnFinish list array of string (≤200)
managedProvidersEnabled toggle true | false Paid-plan users run non-Anthropic sessions on Omniscio's own gateway keys, drawing down prepaid credits — no personal provider key needed. The gateway 402s at zero. DeepSeek is live; GLM is coming.
managedSessionKeysOptIn toggle true | false Run native Claude coding sessions on Omniscio's pooled API key via the gateway — draining your prepaid credits instead of bringing your own key.
meteredVendorSpendAlertUSD number number 0..10000 The ALERT MINIMUM, in US dollars, for those same metered vendors: the daily spend at which Omniscio starts raising the 'spend today is unusually high' inbox card for one of them, with a runaway card at 4x this. It NOTIFIES only — it never blocks a session, which is what the per-provider daily cap above does, and the two are independent. Default $25. Raise it if your own ordinary day on a vendor is already above that, or the card will keep reporting a normal day as an anomaly; lower it to hear about smaller spikes. Leave empty for the default, which ALSO warns when one vendor spikes far above its own usual — setting a number turns that extra warning off, so the number you enter is the whole bar for that vendor. Synonyms: alert threshold, spend alert minimum, when to warn me about spend, metered vendor alert level, kimi alert threshold, deepseek alert threshold, stop alerting me on normal days.
modelDefaultThinkingLevels map map of string → "auto" | "minimal" | "low" | "medium" | "high" | "max" | "xhigh" | "ultra" Default thinking effort for individual models (e.g. max for Opus, low for Haiku), applied whenever that model is used. Empty means models fall back to the global default.
modelVendorOverrides map map of string → any RETIRED — ignored, and removed in a later release. It used to pin which company serves a model that more than one company offers (GLM, DeepSeek, Kimi, MiniMax). Which company serves a model, and who pays for it, is now decided by that model family's Who pays & who serves list (Settings → Accounts → Who pays & who serves): to use a company, put its row where you want it tried. This value was read only once, to build those lists the first time, and is kept for one release so a revert loses nothing. Changing it does nothing. Synonyms: model vendor, serving provider, auto vendor, cheapest vendor, provider pin, vendor override, preferred vendor, model routing, which provider serves this model.
museCodeProviderEnabled toggle true | false In-development: run Meta's Muse Code coding agent as a session provider alongside Claude. Muse Code runs on your computer through the muse program and is billed to your own Meta account — through your saved Meta API key, or Muse's own sign-in.
onboardingOfferAccountSignIn toggle true | false Show the "sign in with your account" option on first run. Off by default — new users run on their own key or a managed pool, with no account required; flip it ON to bring the account-based sign-in option back into the first-run flow. Synonyms: offer account sign in, show account option on first run, sign in with account, account onboarding.
openrouterPresetModels list array of string (≤100) The model list shown in the OpenRouter provider preset's picker — the "good coding models" shortlist, not every model OpenRouter carries. Normally maintained for you: OpenRouter is an aggregator with hundreds of models and several added a week, so a background watcher refreshes this from its live catalog. Empty means "not derived yet" and the built-in shipped snapshot is used instead, so a failed refresh can never leave you with an empty picker. Edit it yourself in Settings → Custom Providers (which also sets openrouterPresetModelsCustomized). Synonyms: openrouter model list, which openrouter models show up, openrouter picker models, customize openrouter models, openrouter preset shortlist.
openrouterPresetModelsCustomized toggle true | false Set to true once you edit the OpenRouter model list yourself. While it is true the automatic catalog refresh stops writing that list, so a nightly poll can never overwrite a choice you made deliberately. Clear it to hand the list back to automatic refresh. Set for you when you edit the list in Settings → Custom Providers — you rarely set this directly. Synonyms: openrouter list is customized, stop auto-updating my openrouter models, lock the openrouter model list, openrouter manual model list, reset openrouter models to automatic.
pluginBackendPermissions map map of string → true | false Which marketplace plugins you've allowed to run behind-the-scenes access, keyed by plugin. Set when you grant or revoke access at install time or later.
projectDefaultModels map map of string → string (≤100) The default model and thinking level each project starts new Claude sessions with; a session's own pick overrides it.
projectDefaultProviders map map of string → any Which provider (Claude, Codex, Gemini, DeepSeek, and so on) each project uses by default for new sessions.
projectDefaultThinkingLevels map map of string → "auto" | "minimal" | "low" | "medium" | "high" | "max" | "xhigh" | "ultra" The default thinking effort each project uses for new sessions, unless a session or model sets its own.
projectMcpDefaults map map of string → map of string → true | false Which MCP tools/servers are on or off by default for each project, overriding the global on/off choice per project.
projectProviderDefaultModels map map of string → map of string → string (≤100) Per project, the default model and effort for non-Claude engines (e.g. Codex, Gemini) when that project runs that engine.
projectProviderDefaultThinkingLevels map map of string → map of string → "auto" | "minimal" | "low" | "medium" | "high" | "max" | "xhigh" | "ultra" Per project, the default thinking effort for each non-Claude engine, unless a session overrides it.
promptRateLimitWarningPct number number 1..100 Rate-limit utilization percent (1–100) at which the pre-send "This prompt may be expensive" confirmation ALSO warns about your 5-hour usage: when your current bucket utilization is at or above this percent, the danger confirm adds a rate-limit line before you send. Null disables the rate-limit warning (the dollar-cap warning can still fire independently). Synonyms: rate limit warning threshold, 5-hour usage warning, utilization percent alert, bandwidth warning percent.
promptSpendWarningCapsUSD map map of string → number 0..10000 Per-model dollar caps (in USD) for the pre-send spend warning: a map of model name (or "_default") to a dollar amount — when the estimated cost of a prompt you are about to send reaches that cap, a "This prompt may be expensive" confirmation appears before the send. Null or empty disables the spend warning entirely. Estimates are approximate (input + draft + a fixed output estimate) and use each model's catalog price. Synonyms: spend warning threshold, expensive-prompt warning, cost cap before send, per-model dollar limit, prompt price alert.
promptSpendWarningEnabled toggle true | false Warns you before sending a prompt that is estimated to cost more than your threshold. API-key users set a per-model dollar cap; subscription users set a 5-hour rate-limit percentage.
providerBalanceAutoResumeEnabled toggle true | false When an API-key provider account (DeepSeek, Kimi) runs out of balance, automatically resume its parked sessions once the account is funded again.
providerConfigSyncCursorProjectDirs list array of string (≤500) Folders where Cursor's skills get installed (Cursor has no single skills folder). Empty means Cursor gets no skills.
providerConfigSyncSkillBudgets map map of string → integer 0..100000 Provider Config Sync — the per-engine skill-count budget: engine id (codex, gemini, cursor) → the max number of skills to sync to that engine before the Skill Budget alert fires. 0 (or absent) = the code default (Codex has a real strict-loader limit; other engines default OFF). User-tunable, so the alert never depends on reverse-engineering an engine internal limit. Synonyms: skill budget, per-engine skill cap, codex skill limit, how many skills per engine.
providerConfigSyncSkillExclusions map map of string → array of string (≤200) Provider Config Sync — the per-engine skill exclusions you chose: engine id (codex, gemini, cursor — the COPYING engines) → skill folder names to hold back from THAT engine fan-out. An excluded skill stays fully installed and usable everywhere else; it is only kept out of that one engine (its already-synced copy is swept on the next sync). Populated via the Skill Budget alert / its settings, never an automatic cut. Synonyms: skill exclusions, per-engine skip list, do not sync these skills, hold back skill.
providerDefaultModels map map of string → string (≤100) Global default model for engines that lack their own setting (gemini, codex, cursor, deepseek, kimi); set from a session's 'Set as default'. Empty means each engine uses its built-in default.
providerDefaultThinkingLevels map map of string → "auto" | "minimal" | "low" | "medium" | "high" | "max" | "xhigh" | "ultra" Global default thinking effort per provider - 'use this effort whenever I use this provider'. Empty means the global default applies.
providerFunding map map of string → array of "own-key" | "omniscio" Per provider, how it's paid for: your own vendor key ('own-key') or Omniscio-managed credits ('omniscio'). A provider with no entry is treated as own-key-first (the money-safe default).
providerKeyExhausted map map of string → string RETIRED — ignored, and removed in a later release. It used to record which of your own provider keys were out of balance. Omniscio now remembers an account that runs out of credit while the app is running: every session skips it and uses the next row of its Who pays & who serves list, and it is tried again every 10 minutes, or as soon as a balance check sees money there. Nothing reads this setting any more, so editing it changes nothing. Synonyms: provider key out of balance, my api key ran out of credit, why is it using company credits, exhausted provider key, unfunded key fallback, key balance cache.
providerRouteOverrides map map of string → any Per-AI connection route: for each AI that can be reached more than one way — today Codex, natively, through Claude, or through a custom provider — pins which one to use. Empty means each AI uses its own default. Your pick applies to sessions you start from then on; sessions that already exist keep the connection they started with. If the one you pick is not set up, the app falls back to one that is. The session page carries no route picker — this is the only route editor. It never decides who pays: that is supplyLists (Settings → Accounts → Who pays & who serves). Settings → Sessions → How each AI connects. Synonyms: route, connection route, transport, gateway, claude via codex, custom provider via codex.
proxyModelsEnabled toggle true | false Run GPT, xAI Grok, CrofAI, or DeepInfra (cheap open-weight DeepSeek/Qwen/Llama/GLM/Kimi/MiniMax) inside the Claude Code harness by pointing it at a local model-translating proxy. On by default — the CLIProxyAPI model-proxy binary ships in the installer (with a runtime download-on-first-use fallback). Turn it off to hide these providers.
rateLimitDowngradeEnabled toggle true | false Opt-in auto-downgrade: when enabled and your 5-hour or 7-day rate-limit utilization reaches the downgrade threshold, active sessions automatically switch to a cheaper fallback model to protect your usage bucket, and switch back once utilization drops. Off by default. The fallback model (rateLimitDowngradeFallbackModel) must be in the model catalog, and the threshold (rateLimitDowngradeThresholdPct) defaults to 80%. Synonyms: auto downgrade model, rate limit fallback, cheaper model when limited, tier-down protection.
rateLimitDowngradeFallbackModel text string The model active sessions fall back to while the rate-limit auto-downgrade is active — set it to a cheaper model in the catalog (e.g. a fast mid-tier model) so usage is preserved during a utilization spike. Must be a valid catalog model; an unknown value is rejected. Only used when rateLimitDowngradeEnabled is on and the threshold is reached. Synonyms: fallback model, downgrade model, cheaper model, backup model.
rateLimitDowngradeThresholdPct number number 50..99 The rate-limit utilization percent (50–99, default 80) that triggers the auto-downgrade when rateLimitDowngradeEnabled is on: when your 5-hour or 7-day bucket utilization is at or above this percent, sessions switch to the fallback model, and clear again once utilization falls ~10% below it. Synonyms: downgrade threshold percent, utilization trigger, rate limit cutoff percent, when to tier down.
remoteMachinesLeastBusy toggle true | false
tunnelEnabled toggle true | false Makes your mobile web-access server reachable from anywhere on the internet (true) instead of only your own Tailscale devices (false). Off by default.
webAccessPort number integer 1024..65535 The TCP port Omniscio's own web-access server listens on — the port the phone-side web view, the mobile pairing link and any device on your local network connect to. It is shared by the local address and, when the Tailscale tunnel is on, the same port on the tunnel address. Default 9876; the accepted range is 1024-65535. It cannot be changed while the server is running (stop it first), and it is the only web-access key saved through the ordinary settings path — webAccessEnabled, webAccessToken and tunnelEnabled each go through their own start/stop handlers. Settings → Remote Access → Advanced → "Server Port". Synonyms: web access port, remote access port, server port, websocket server port, which port is omniscio on, change the mobile port, port 9876, lan port, local network port, port already in use.

Troubleshooting (4)

When something is wrong — recovering it, diagnosing it, or making it fast again.

Setting Type Accepted values What it does
crawlerWatchProjectBuildFolders toggle true | false
logTimeBasedRetentionEnabled toggle true | false Lets the app keep a little extra log history so it always covers at least a few hours, instead of a fixed number of log files. On by default.
perfStatusEnabled toggle true | false Whether anything is slowing this computer right now, and what the app is doing about it. Opens on a one-line plain-language verdict, then the readout it comes from — box counters, the app's main-thread stall share, the external-memory pool, fleet + process-birth rate, per-volume disk runway, cloud verdict share, the auto-lander pulse and where your agents' time goes — and finally every agent-load governor grouped by the plain-English mechanism it belongs to, with a switch on the ones where turning it off is a sane thing to do. Read from the app's own tapes in process; it starts no probes. Governor switches go through the ordinary settings path.
resourceLedgerEnabled toggle true | false A tab in the Performance Monitor that shows which of your sessions, programs and background jobs are using how much of the computer right now or a few minutes ago, adding up to how busy it is.

Terms, privacy and the other policy pages.

Setting Type Accepted values What it does
aiBrowserHistoryRetentionDays number integer 0..3650 How long the AI browser keeps the pages it visited, in days — the page text and its searchable index. The default is 180 days, so anything older than the horizon is aged out automatically; set it to 0 to keep them forever.
browserLoginAutoExpireDays number integer 0..365 How many days a saved browser login is kept before it is aged out. 0 (the default) switches the age-out off and keeps every saved login until you remove it yourself.
communicationsRetentionDays number integer How long your messages are kept, in days. 0 (the default) keeps them forever; otherwise choose a window between 30 and 3650 days.
communicationsRetentionEnabledAt text string (≤40) Internal bookkeeping: when the message-retention window was switched on, used as the grace anchor. Written by Omniscio, not a setting to change.
consentLedger map map of string → object { granted: true | false; purpose: "crash-autosend" | "cloud-intake" | "email-remote-images" | "voice-stt" | "web-bridge-message-transit" | "wake-word-listening" | "sync" | "voiceprint-training" | "flowvoice-dictation" | "flowvoice-dictation-audio" | "behavioral-profiling" | "ai-browser-memory" | "pipeline-cloud-offload" | "pipeline-fleet-identity" | "share-publish" | "marketing-attribution" | "outside-memory-copies" | "outside-memory-conversations" | "person-memory" | "tasks-ai" | "supermail-ai-summary" | "supermail-ai-plain-speak" | "supermail-ai-filter" | "supermail-video-summary" | "supermail-archive-digest"; recordedAt: string (≤40); source: "backfill" | "settings-change" | "user-acceptance"; version: integer 0..∞ } Internal record of which data-use consents you have granted or withdrawn, with the version and time of each. Written by Omniscio; nothing is gated on it.
dataRetentionDays number integer 1..365 How long your data is kept before it is cleared away, in days (30 by default; 1 to 365).

General (299)

Setting Type Accepted values What it does
agentConversationsEnabled toggle true | false In-development: one screen listing every conversation your agents are having — with a teammate, across your own other computers, with another organisation over an accepted connection, and between two sessions on this computer. Each thread carries a name the agent that started it chose and you can change, a summary that is only made when you click Summarize (so it only costs money then), and one search box over names and messages. It lists and names; it never sends, and it never opens a connection. Off by default; hidden until shipped.
agentGitThrottleEnabled toggle true | false Retired control for pacing an agent's git operations. Hard-off now and kept only for compatibility.
agentHostEnabled unknown true | false | object { mode: "named"; sessions: array of string } | object { mode: "share"; percent: integer 1..100 } Off by default. Starts new agent sessions inside the separate agent host instead of directly under the app, as a step toward agents that keep running through an app restart. For testing only; until the restart-survival work is finished, host agents are still ended whenever the app closes or starts.
agentInstallThrottleEnabled toggle true | false Retired control for pacing agent package installs. Hard-off now and kept only for compatibility.
agentPermissionDenyRules list array of string (≤200) The never-allow rules: commands and paths an agent is always refused, at every permission level including Full trust and Smart, with no approval card. A command rule is the command typed out, and a rule ending in * matches anything that starts the same way (git push --force* refuses every force-push); a rule starting with path: refuses a file or folder (path:~/secrets/**). Up to 100 rules of 200 characters each, empty by default. Only the person can write them, in Settings, Workflow, Agent permissions, while the Safety checks Lab switch is on: no agent, control-server route or phone request can add one. Codex receives only command rules written as a prefix ending in *. Synonyms: deny rules, never allow list, blocked commands, forbidden commands, refuse command always, block path, safety rules.
agentSearchThrottleEnabled toggle true | false Retired control for pacing agent search operations. Hard-off now and kept only for compatibility.
agentShellHandBlockRemovalEnabled toggle true | false Allows the app to remove two older hand-written guard blocks from your shell startup file once its managed shell routing block replaces them. Off by default. It refuses to touch the file unless both blocks are found exactly as expected, and it makes a backup first. In development. Synonyms: remove old shell guard blocks, bashrc cleanup, shell shim cleanup, agent shell startup tidy.
agentShellThrottleEnabled toggle true | false Retired control for pacing agent shell commands. Hard-off now and kept only for compatibility.
agentWebCloudBrowsersEnabled toggle true | false Let Agent Web use a browser that runs on Browserbase or Browser Use instead of Chrome on this computer. Off by default. A cloud browser never receives your saved passwords or saved logins, and it is reached only on that vendor's own address.
agentsApiEnabled toggle true | false Publish chosen agents so other tools on this computer can call them like an OpenAI model, with keys you make here and can revoke at any time. It never uses your Claude or ChatGPT subscriptions: a published agent runs only on a key you pay for by use. It never answers from outside this computer unless you turn on Tailscale yourself. Off by default.
agentsApiPort number integer 1024..65535
agentsApiTailnetEnabled toggle true | false
aiTextCorrectionEnabled toggle true | false Proofread or expand the text you have selected, straight from the Omniscio quick launcher — the corrected text comes back ready to copy. Fully native; it needs no AutoHotkey script.
anthropicPromptCacheEnabled toggle true | false
archilMcpEnabled toggle true | false When on, every session runs its file, search and command tools in Archil cloud microVMs instead of on this computer, with each change synced back to the session folder (needs archilApiKey). Usually switched on per project or per session from the MCP Servers controls rather than for every session. Synonyms: archil workspace, run tools on archil, archil sandbox, cloud microvm tools, offload agent tools.
archilRegion select "aws-us-east-1" | "aws-us-west-2" | "aws-eu-west-1" | "gcp-us-central1" The Archil region the workspace disk lives in (aws-us-east-1 by default). Synonyms: archil region, where archil runs.
autoArchiveOnLand toggle true | false When on (default), a session whose branch successfully lands (is merged to master by the auto-lander) is automatically archived off your board — with a safety guard that leaves a session alone if it still needs you. Off: a landed session stays visible until you archive it. It's the "landed sessions clear themselves" backstop.
autoDeployFirestoreIndexes toggle true | false Retired control for auto-deploying Firestore indexes after a land. Nothing reads it and nothing deploys on a land any more; kept only for config compatibility.
autoDeployFirestoreRules toggle true | false Retired control for publishing database security rules after a land. Nothing reads it and nothing deploys on a land any more; kept only for config compatibility.
autoDeployFunctions toggle true | false Retired control for running a Cloud Functions drift check after a land. Nothing reads it and nothing runs on a land any more; kept only for config compatibility.
autoLanderDeadGateDeferEnabled toggle true | false On by default. Re-sends a check whose run came back with no result, so a dead run recovers instead of being lost. Flips live without a restart.
autoLanderDisarmedAtMs number integer 0..∞
autoLanderFreeze object object { agentLease: true | false; by: string (≤200); rearmOnExpiry: true | false; reason: string (≤500); until: string (≤64) } A RESTART FREEZE on record — who asked for it, why, and until when — as { by, reason, until, rearmOnExpiry? } (ISO-8601), or null for none. It exists because "the lander is off" has two causes that need opposite answers: the machine must hold still while the app is rebuilt and checked, or it simply keeps its lander off by design and landing by hand is the intended behaviour. Only the first is recorded, so only it refuses a hand-land; a plain off needs nothing set by hand. Persisted rather than held in memory because the window it guards spans an app restart. Synonyms: restart freeze, why is landing refused, hand-land refused.
autoLanderMaxConcurrentRemediations number integer 1..12 Max concurrent auto-lander remediation sessions (the paid rescue sessions that rebase + re-gate + re-tag a stranded branch). Higher drains the stranded backlog several-at-a-time instead of ~2 per 30 min; bounded so a churn storm cannot spawn a swarm, and the spawn-admission pacer still paces the actual starts. Default 4.
autoLanderReadyParkEnabled toggle true | false On by default. Automatically re-dispatches and finalizes a merge request that got parked, instead of leaving it waiting. Flips live without a restart.
autoLanderRemediationModel select "default" | "claude-worker" | "claude-basic" | "deepseek-v4.1-flash" | "deepseek-v4-flash" | "deepseek-v4-pro" | "crofai/deepseek-v4-flash" | "crofai/deepseek-v4-pro" Which AI model the auto-lander's PAID rescue sessions run on — the sessions that rebase, re-gate and re-tag a stranded branch. The default is the cheap Claude WORKER tier (claude-worker), not your Claude default model: a rescue does the most mechanical work in the product against a fully-specified prompt, so the cheap tier drains the same backlog for far less money. Choosing default instead runs rescues on whatever your Claude default model is — on a normal install the flagship, which costs materially more per attempt. A stronger model is more likely to succeed on a genuinely hard conflict, so it may produce fewer attempts at a higher cost each. Read at spawn, with a Claude fallback if the chosen tier is unavailable. Synonyms: auto-lander rescue model, which model fixes stranded branches, remediation model, rescue session cost, cheap model for rescues.
autoLanderReturnedDroppedWorkRescueEnabled toggle true | false Allows the automatic rescue for a returned cloud branch that the auto-lander is holding because it would have dropped work. Off by default, so no such rescue is started or approved. Turn it on only if you want those rescues to run. Synonyms: dropped work rescue, returned cloud branch rescue, auto-lander rescue, rescue held branch.
autoTidyDemoted list array of string (≤200) Internal bookkeeping: the sidebar items the automatic tidy decided to demote. Written by the tidy, not a setting to change.
autoTidyFirstSeen map map of string → string (≤40) Internal bookkeeping: when the automatic tidy first saw each sidebar item. Written by the tidy, not a setting to change.
autoTidyFirstSeenRepaired toggle true | false Internal bookkeeping: whether the automatic tidy's first-seen record has been repaired after an upgrade. Written by the tidy, not a setting to change.
autoTidyKept list array of string (≤200) Internal bookkeeping: the sidebar items the automatic tidy deliberately kept. Written by the tidy, not a setting to change.
autoTidyLastSweep text string (≤40) Internal bookkeeping: when the automatic sidebar tidy last ran. Written by the tidy, not a setting to change.
backendGenerationStaging toggle true | false Build backend edits into a staged, immutable generation instead of restarting the whole app during development. Off by default — the ordinary dev launch is untouched, and a backend edit behaves exactly as it always has until this is switched on.
backupArchiveUserHarmGateEnabled toggle true | false Not switched on yet. When on, backup and archive work waits only while the app is actually struggling for you, instead of whenever the processor is merely busy — so it runs more often on a busy machine. Off until its own evidence is reviewed.
baselineCloudCutoverEnabled toggle true | false Which producer's test baseline the app trusts. Off (the default) = the cloud producer publishes only a shadow result no consumer adopts, and the local road's baseline stays the live one; on = the cloud result becomes live and the local road is paused. The flip is one-way and slow: the cloud road is cut over only after two consecutive shadow fires published good results beside the local one's.
baselineV2Enabled toggle true | false Which system answers "is this test failure mine?" — the existing baseline, or Baseline V2, which re-runs the failing tests in the cloud at the exact revision the branch forked from. OFF by default, and off means every existing baseline result is unchanged: no extra job, no local work, no spend. An unreadable value counts as off, so V2 never starts on a guess, and an agent session cannot flip this one — the switch belongs to you. Synonyms: baseline v2, which baseline, new attribution system, how is a red judged, is this failure mine, switch attribution system, baselineV2.
baselineV2WarmerEnabled toggle true | false Whether Baseline V2 keeps evidence for current master warm, so a comparison answers from what was already measured instead of running a fresh replay. It does nothing unless Baseline V2 itself is on, ships off, and counts an unreadable value as off. Attribution still works with it off — it is only slower. Synonyms: baseline v2 warmer, keep evidence warm, pre-build master evidence, faster baseline answers, warm the baseline cache, baselineV2 warmer.
bashSessionShell toggle true | false Windows only. When on, each agent session keeps ONE shell alive for its whole life and runs every Bash tool command in a copy of it, instead of starting a brand-new shell for each command and re-loading the session setup every time (thousands of file lookups and up to a few hundred ms per command, far more when the machine is busy). Nothing an agent can see changes: same output, same exit code, same clean slate between commands, and any command the resident shell cannot answer runs exactly as before. On by default (Windows). Takes effect on the NEXT session you start; to stop an ALREADY-running session using it, set AMC_DISABLE_BASH_SESSION_SHELL=1 for that session. Fail-open: if anything is wrong the call just runs the old way and it is recorded. No effect on macOS or Linux. Synonyms: persistent shell, resident shell, one shell per session, faster bash tool calls, session shell.
boxWideShellHost toggle true | false Windows only. When on, ONE resident tool shell serves the whole box instead of one per session. It changes how EVERY session starts its tool shells, and the box-wide host is not yet proven, so it ships OFF — off is byte-for-byte today's road, one host per session. Flip it on for a session cohort, measure the shell-host process count, their memory, and box faults per second, and only then default it on. Depends on the persistent session shell (bashSessionShell): with that off there is no resident shell to host, so this is a no-op. The environment kill switch AMC_DISABLE_BOX_WIDE_SHELL_HOST=1 wins over it. Synonyms: box-wide shell host, one shell host for the whole box, shared shell host, fewer resident shells, shell host rollout.
branchOwnerEscalationEnabled toggle true | false Lets the app start sessions to take over troubled branches that have no active owner, moving up from the owner to the crew lead to the lead seat, within daily limits. Off by default, so the sweep only watches and records. Synonyms: branch owner escalation, ownerless branch takeover, branch ownership sweep, escalate stuck branch.
branchSweepEnabled toggle true | false Runs the no-branch-left-behind sweep every 10 minutes: branches already on master are retired, every other stuck branch is messaged once to the session that can settle it, and one that stays stuck is retired after 48 hours with its work saved so it can be brought back. On by default. Turning it off stops the sweep; nothing it already did is undone. Synonyms: branch sweep, stuck branch cleanup, needs-you branches, no branch left behind.
burstAllUntil number integer 0..9007199254740991 Internal bookkeeping: the time until which every session is temporarily given a burst of extra processing (or empty when no burst is running). Set by the CPU burst control, not a setting to change.
calendarQuickAddBackfilledAt text string (≤64) Internal bookkeeping: when the one-time upgrade that filled in the quick-add calendar finished. Written by the upgrade, not a setting to change.
chatGatewayAllowAllSenders toggle true | false
chatGatewayEnabled toggle true | false Talk to your agents from Telegram, Slack, Discord, Mattermost, Matrix, Signal, iMessage, Home Assistant, SMS, WhatsApp, Teams and Google Chat through named bots. Only people you allow can drive a bot, tool approvals never override your safety checks, and the built-in Telegram bot is unchanged. Off by default.
chatGatewayKeepRunning toggle true | false
chatGatewayWebhookPort number integer 1024..65535
checkoutDeferredNoticeEnabled toggle true | false Show the hourly 'updates are waiting for your restart' notice while the main app folder cannot be updated because an app is running from it. Off by default; updates still wait correctly, just silently.
checkoutKeeperReportedAt text string ISO timestamp the main-checkout keeper stamps after its ONE report-only cycle — the run that reports what it WOULD put back without changing a file. Null means that cycle has not happened yet and the next tick is a dry run. Persisted rather than held in memory so it happens once ever, not once per app restart.
chromeExtensionDevEnabled toggle true | false Chrome extension dev (Autopilot)
chromeExtensionDevNudgeSeen toggle true | false Remembers that the one-time prompt about installing the companion Chrome extension in developer mode has been shown.
claudeCodeBinaryPath text string (≤1000) Full path of the Claude Code CLI used to launch sessions. Leave empty to auto-detect. A leading ~ is expanded to your home folder, so the path a terminal prints works as-is.
cliProxyHealthUserHarmGateEnabled toggle true | false Not switched on yet. When on, CLI proxy health checks keep their normal wait while the app is fine, instead of stretching the wait whenever the processor is merely busy. Off until its own evidence is reviewed.
cliSpawnPacerUserHarmGateEnabled toggle true | false Not switched on yet. When on, agent restarts are paced only while the app is actually struggling for you, instead of whenever the processor is merely busy. Off until its own evidence is reviewed.
cloudBrokerSecretManagerVault toggle true | false Read cloud tenants' provider credentials from Google Secret Manager instead of the in-memory development vault. On by default; it only engages once a vault project is set. Turn it off to keep the in-memory vault.
cloudBrokerVaultProject text string The Google Cloud project holding the cloud tenants' provider credentials. Empty means the Secret Manager vault does not engage yet, so cloud sessions keep using the in-memory development vault.
cloudCredentialBrokerEnabled toggle true | false Send a cloud session's own-key model calls straight to the provider instead of relayed through this computer, so uploads for cloud work do not ride on your connection. On by default.
cloudGlmGatewayPassEnabled toggle true | false
codeHostProvidersEnabled toggle true | false Lets the app work with projects hosted outside GitHub. GitLab gets linked and detected merge requests, opening one from the git button and merging; Bitbucket Cloud, Azure DevOps and Forgejo or Gitea are read-only. Add a host and its token under Settings → Integrations → Code hosts. GitHub is not affected by this switch.
coldStorageUserHarmHoldEnabled toggle true | false Let old-data storage cleanup pause itself when the app is under heavy load, to keep the interface responsive. On.
composerCommandsEnabled toggle true | false Makes the app commands (/new, /clear, /compact, /model, /cost, /context, /status, /stop, /help and /rollback) work on every engine, and lets you type @ to attach a file, a folder, your changes so far or a web page to a message. It needs the native slash commands that are already on. Commands that change or discard a session run only when you send them yourself. Off by default.
conversionHoldUserHarmGateEnabled toggle true | false Not switched on yet. When on, agent-triggered conversions hold only while the app is actually struggling for you, instead of whenever the processor is merely busy. Off until its own evidence is reviewed.
crewMigrationAutoRun toggle true | false
cronDispatchUserHarmGateEnabled toggle true | false Not switched on yet. When on, scheduled jobs wait only while the app is actually struggling for you, instead of whenever the processor is merely busy. Off until its own evidence is reviewed.
customUiEnabled toggle true | false Master switch. OFF returns the stock interface immediately, panel and full-window alike.
customUiFullWindow toggle true | false Whether the user's own interface fills the whole window in place of ours. Full-window is the mode that can leave someone staring at a broken custom UI, so it is OFF by default and every way back out of it is deliberate: the always-visible exit affordance, the keyboard escape, and POST /custom-ui/exit. See the escape invariants in the contract.
customVoiceCommand object object { args: array of string (≤1024); executable: string (≤1024) }
dbPrivateCacheAutoArmed toggle true | false Internal bookkeeping: records that the database was auto-moved to private storage once, so it never does so again. Not a setting to change.
dedicateUiCoreEnabled toggle true | false Retired control for reserving a CPU core for the app's interface. Ignored now even if set to true; kept only so older settings still load.
defaultPersonalityId text string (≤120) Which personality every new agent session starts with, or none when empty. The value is the id of one of your saved personalities or of a built-in one; a session can still pick a different personality, or no personality at all, for itself. If the chosen personality is deleted, sessions that relied on it run with no added personality. Only has an effect while the Personalities Lab switch is on. Changed in Settings, Personalities, "Default personality". Synonyms: default personality, default tone, default persona, which personality do my agents use, change the agent tone for every session, personality for new sessions.
demoLookEnabled toggle true | false One switch that makes the app look like a brand-new install: it swaps in the fresh-install appearance, quietens Presentation Mode, and hides any plugin panels you had enabled, then restores your own look when you turn it off. Persisted, so the demo survives a restart until you switch it back. Settings → Appearance → Demo Look. Synonyms: demo look, make it look new, fresh install look, screen-share clean look, reset the appearance for a demo, hide my plugins for a demo.
depPropagationUserHarmGateEnabled toggle true | false Whether a dependency change may propagate while the machine is measurably hurting you — one of the family of load gates that defer heavy work while something on the box is being harmed. Ships OFF (dark): no disagreement tape has been gathered for this site yet, so it preserves the existing calm-hold until the data exists, rather than guessing. Turn it on to apply the user-harm verdict at this site. Synonyms: dependency propagation harm gate, user harm gate for dep updates, hold dep propagation while hurt, load gate for dependency propagation.
desktopNotificationOptOutTipSeen toggle true | false Remembers that the one-time tip about turning off desktop notifications has been shown.
developerGuardrailsEnabled toggle true | false Machine-wide git safety: installs ONE master-safety guard hook into your GLOBAL ~/.claude/settings.json, so every Claude Code session Omniscio starts — subagents included — is guarded however it was launched. The git rules stand down for a session Omniscio never started, though it still cannot print the full-trust key or switch the gcloud account. Blocks direct commits/pushes to a protected branch (master/main), a destructive git stash, and edits while on a protected branch (reusing the git-guardrails engine + its per-repo exclusion + time-boxed approval escape hatches). Cross-platform; OFF by default (opt-in), it edits your global config so it stays opt-in. Turn it on in Settings → Features.
developerModelSubsidyEnabled toggle true | false Route an enrolled developer's non-Claude sessions through the company service instead of their own account so the company pays. Turned on automatically by setup for enrolled developers; off by default.
dockerSessionCpus number number 0.5..64
dockerSessionMemoryMb number integer 256..65536
dockerSessionNetwork select "model-and-app" | "open"
dockerSessionPidsLimit number integer 64..32768
dockerSessionsEnabled toggle true | false Run a session inside a locked-down Docker container that can see only its own folder, with limits on memory, CPUs and processes. It needs Docker Desktop, which you install yourself; Omniscio never installs it. By default the container can reach only the model and this app. Your sign-in files never enter a container. Off by default.
dockerSessionsImageTag unknown "" | string (≤128)
emptyInboxTipSeen toggle true | false Remembers that the one-time "your inbox is empty" tip has been shown.
externalAgentGovernorUserHarmGateEnabled toggle true | false Not switched on yet. When on, outside agents are slowed only while the app is actually struggling for you, instead of whenever the processor is merely busy. Off until its own evidence is reviewed.
fathomInboxEnabled toggle true | false Shows your recent Fathom meetings as items in your inbox by checking Fathom in the background with your saved Fathom key. Off by default, and it needs the Fathom meetings feature to be set up. Turn it off to stop the checks. Synonyms: Fathom inbox, meetings in inbox, Fathom meeting alerts, Fathom polling.
fathomMcpEnabled toggle true | false When on, adds the Fathom meeting-notes tool to your sessions, with its API key stored beside it (fathomApiKey). It is a per-session tool-server toggle, so it only affects sessions you start after turning it on. Synonyms: fathom MCP, fathom meeting notes tool, add fathom to sessions, fathom integration toggle.
fathomMeetingsEnabled toggle true | false Groundwork for a Fathom meetings tab that is not in Omniscio yet: turning this on shows nothing new today. Your Fathom transcripts already reach "What should I do next?" through the Fathom API key in Settings > Mission Control. In development.
featureRoadmapAutoActivityEnabled toggle true | false Record each day's commits onto the roadmap features their commit tags name. On by default.
featureRoadmapAutoAddEnabled toggle true | false Automatically add cards to the feature roadmap board to match the unreleased-features list, without duplicating. Off by default.
featureRoadmapAutoSyncEnabled toggle true | false Automatically sync the feature roadmap board to the cloud. Off by default (turned on for launch).
featureRoadmapDriftWatchdogEnabled toggle true | false Watch for the feature roadmap board drifting out of sync with the source list and alert you; it never changes the board itself. Off by default.
featureRoadmapEodCheckInEnabled toggle true | false In-development: at the end of a day you actually landed work, reads your own commits and opens a short session that PROPOSES roadmap updates for the features you own. It only ever proposes — nothing it finds reaches the board unattended, it never overwrites your words, and it never moves a feature's phase without you. Routing a commit to a feature is a separate, automatic record (the autoActivity field); this half is the part that asks. Silent on a day with nothing to report. Off by default.
featureRoadmapEodCheckInOwnWorkOnlyEnabled toggle true | false Show a developer only their OWN work in the nightly roadmap check-in: the feature cards they own, plus any card their own commits named with a Roadmap trailer. A card that merely looks related by file path, and the neglected-cards section, are limited to their own cards too, so nobody is asked to describe a feature they did not build. On by default. It only narrows what the night session OFFERS — anyone may still edit any card, and a commit still counts against the card it belongs to, so no work is lost. Turn it off to get the old whole-board agenda back. Synonyms: own work only, roadmap check-in shows only my features, stop reviewing other people features, scope the check-in to my cards.
featureRoadmapHealthWatchdogEnabled toggle true | false Warn when a developer is behind on roadmap check-ins (an overdue ETA or 14+ days without an update). Off by default.
featureRoadmapNudgeDevelopersEnabled toggle true | false Send a developer a targeted in-app nudge (repeated about every 3 days) while they're behind on roadmap check-ins, cleared when they catch up. Off by default.
fleetGovernorBirthLoopEnabled toggle true | false Let the fleet governor pace how fast new agent processes are started, so a burst cannot overwhelm the machine. On by default.
fleetGovernorUserInteractiveEnabled toggle true | false Never slow down pacing for the session you are actively looking at. On by default.
fleetSafetyGovernorEnabled toggle true | false Pace agents' tool calls and scheduled maintenance when the app is under real strain. Only agents are paced, never something you started. On by default.
forceOffFeaturesMigrationDone toggle true | false Internal bookkeeping: whether the one-time upgrade that switched a set of optional features off has run. Written by the upgrade, not a setting to change.
foregroundAppPriorityFloorEnabled toggle true | false Keeps the app you are using from being slowed down by your agents. Omniscio holds its agents at below-normal CPU priority; if the app you are working in (Chrome, say) ever starts at that same level — which can happen after a restart — it has to share the CPU equally with every agent and feels sluggish. When on (the default), Omniscio notices that and raises the app, plus its own helper processes, back to normal priority. It never raises anything above normal, never touches an app you set to Efficiency mode, and never touches an agent. Windows only. Kill switch AMC_DISABLE_FOREGROUND_APP_PRIORITY_FLOOR. Synonyms: foreground app priority, Chrome slow when agents run, protect my browser, computer slow outside Omniscio, below normal priority app, raise my app priority.
gitPollLimiterUserHarmGateEnabled toggle true | false Not switched on yet. When on, background git reads slow down only while the app is actually struggling for you, instead of whenever the processor is merely busy. Off until its own evidence is reviewed.
gitReadCacheEnabled toggle true | false Temporarily cache repeated git reads so a burst of identical lookups hits the disk only once. Off by default.
gitShellIntegrityCheckEnabled toggle true | false Every fifteen minutes on Windows, checks that the shell Git relies on still works and raises an alert if it is blocked. On by default. Turn it off and the check stops and any open alert about it is cleared. Synonyms: git shell check, git health check, git bash integrity, shell blocked alert.
gitStoreMaintenanceUserHarmGateEnabled toggle true | false Let git storage maintenance pause itself when the app is under heavy load, to keep the interface responsive. On.
gitStoreStormAlarmEnabled toggle true | false When on (the default), an agent is told when the git object store starts failing silently — a storm of single-object packs, a pack count over the consolidation trigger, a maintenance tier gone dark, or residue outliving its retention. It only silences the alert card; the store upkeep and the readout keep running either way. Turn it off to stop the card on a machine whose store is being misjudged. Synonyms: git object store alarm, git pack storm alert, silent git failure warning, git store health card, stop git store alerts, git maintenance alarm.
gitWriteBrokerEnabled toggle true | false Let the app perform an agent's git commit or rebase itself, one at a time per repository, instead of the agent running git directly. On by default.
githubReadToolEnabled toggle true | false Gives your sessions a built-in read-only GitHub tool for looking things up. On by default. Turning it off stops adding the tool to sessions and makes the app's GitHub lookup door refuse requests. Synonyms: GitHub read tool, github lookup for agents, read-only github access, github MCP tool.
googleWorkspaceMcpEnabled toggle true | false When on, adds the Google Workspace tool server (Gmail, Calendar, and Drive) to your sessions. It is a per-session tool-server toggle, so it only affects sessions you start after turning it on. Synonyms: google workspace MCP, gmail calendar drive tool, add google workspace to sessions, google workspace integration toggle.
guardChainDedupeEnabled toggle true | false When developer guardrails are on, removes duplicate entries from the chain of safety hooks so each guard runs only once. Off by default. Turn it on only if you use the developer guardrails and see the same guard run more than once. Synonyms: guard dedupe, duplicate guard hooks, developer guardrails cleanup, hook chain dedupe.
hangSentinelEnabled toggle true | false Watch the main thread from a worker thread and write one report when it stops turning for 30 s. On by default — a silent hang otherwise leaves no evidence of what the app was doing. Off starts no worker and writes nothing.
headerLayout object object { collapse: map of string → "auto" | "never" | "always"; iconBars: map of string → string (≤20); rows: array of object { end: array of string (≤120); start: array of string (≤120) } }
heavyJobBrokerEnabled toggle true | false Retired setting kept for compatibility; always off and it enables nothing.
hermesImportEnabled toggle true | false Bring your memories, skills, scheduled jobs, MCP servers and personalities over from a Hermes install on this computer, after a preview of exactly what will be added. Secrets stay in Hermes. Off by default.
inboxKeepListFocusEnabled toggle true | false In-development: the inverted bulk snooze, for an intentional focus block. Today you select what to HIDE, so the work scales with how noisy your inbox is - exactly backwards when you are trying to focus. This adds 'Snooze everything else...' to the inbox right-click menu and a 'Snooze others' button on a project hub's header: you pick the few things worth keeping, choose a duration, and everything else leaves in one action and comes back on its own. It sweeps everything, including task reminders and pending approvals, so it asks once and states the real count - and the whole sweep is undoable. Off by default.
inbuiltTerminalBlocksEnabled toggle true | false Show visual command boundaries (check / cross per exit code) with fold, copy, and re-run per block. Requires the inbuilt terminal to be on.
ioSweepTimeBudgetEnabled toggle true | false Limit how long the background task that adjusts session priorities may run in one pass. On by default.
jlsImageStudioEnabled toggle true | false When on, adds the JLS Image Studio tool server to your sessions so an agent can generate images with it; its API key is stored separately (jlsImageStudioApiKey). It is a per-session tool-server toggle, so it only affects sessions you start after turning it on. Synonyms: jls image studio MCP, image generation tool, add image studio to sessions, image studio integration toggle.
keybindingWhen map map of string → string (≤300)
keyboardDemoTourEnabled toggle true | false In-development: a keystroke-driven copy of the Interactive Demo. Each step shows a key to press (the app’s real shortcuts), so the walkthrough doubles as hands-on keyboard practice on safe sample data. Reveals a "Keyboard Demo" card in Settings → Setup Wizards.
kmsSaveHoldsEditAlertSeen toggle true | false
kmsWizardAlertSeen toggle true | false Remembers that the one-time "new KMS quick reference guide" alert has been raised for you.
labsNotifiedFeatureIds list array of string (≤200) Internal bookkeeping: which Labs features you have already been told about. Written by Omniscio, not a setting to change.
landedArchiveRefPruneReportedAt text string ISO timestamp the landed-branch archive-ref prune stamps after its ONE report-only cycle — the run that reports which refs/auto-lander-archive/* it WOULD retire without deleting one. Null means that cycle has not happened yet and the next pass is a dry run. Persisted rather than held in memory so it happens once ever, not once per app restart. Job-written bookkeeping; the on/off lever is the lander-archive-ref-prune switch, never this field. See auto-lander/landed-archive-ref-prune.ts.
landerGitExecUserHarmGateEnabled toggle true | false Whether the auto-lander's own git steps decide "is the machine too busy to run this right now?" from the USER-HARM verdict — is anything here about to hurt you? — instead of from raw CPU busy-ness. On by default. On a machine running many sessions at once, CPU busy-ness reads as heavy nearly all the time, which pinned the lander's load-responsive git steps to their slow setting; keying on the harm verdict lets them run whenever nothing is actually at risk. A verdict that cannot be read falls back to the CPU signal rather than guessing. Read live, so turning it off needs no restart. Master kill: AMC_DISABLE_HARM_KEYED_LOAD_GATES=1. Synonyms: lander git exec user harm gate, harm keyed load gate, why is the lander waiting, auto-lander load gate, busy machine landing.
landerRepairUnderLoadEnabled toggle true | false When on (the default), the auto-lander still runs its PAID repair session — the one that rebases and re-tags a stranded branch — even when the machine reads as loaded. Normally that repair is deferred so it cannot pile more work onto a busy machine, but on a machine that reads busy most of the day the defer becomes a permanent stall: a stranded branch waits on a veto that only a repair clears. Since a repair is the only thing that clears most vetoes, letting it through is worth the load it adds. Turn it OFF to restore the old defer-under-load pacing. Synonyms: repair under load, let the lander repair while busy, deferred repair session, stranded branch repair under load, auto-lander repair throttling.
landerServiceOwnsLanding toggle true | false Compatibility field: the independent service is the sole landing owner. Legacy app-managed landing is OFF regardless of saved false values. Re-enabling requires new explicit owner authorization and a reviewed code change.
lastActiveProjectId text string (≤200) Internal bookkeeping: the project you had open when you last left the app, so it reopens where you left off. Written by the app, not a setting to change.
lastActiveSessionId text string (≤200) Internal bookkeeping: the session you had open when you last left the app, so it reopens where you left off. Written by the app, not a setting to change.
lastReleaseNotesVersion text string (≤50) Internal marker (not a user setting, no UI): the app version the post-update "What's new" inbox card was last evaluated for. Compared against the running version at launch — only an UPGRADE posts a card. Starts null (a fresh install records the baseline with no card). See services/app/release-notes-inbox.ts.
lastWhatsNewSeenVersion text string (≤50) Internal marker (not a user setting, no UI): the app version the first-launch-after- update "What's new" TOAST was last shown for. Independent of lastReleaseNotesVersion (the inbox card's marker) because the two surfaces are dismissed independently. Starts null (a fresh install baselines silently, no toast).
lazyCompileTraceEnabled toggle true | false
leadDirectReportCap number integer 1..50
liteModeSnapshot map map of string → true | false | number Internal bookkeeping: the settings saved when Lite mode was turned on, so they can be restored when it is turned off. Written automatically — not a setting to change.
localAgentRelayEnabled toggle true | false Sends the model calls of the agents running on this computer through the relay built into the app, which compresses large requests before they leave and, while the upload line is being measured, shares the same upload budget as cloud agents, so many agents at once cannot saturate your connection. On by default. Turning it off makes every agent started afterwards dial its model company directly, as before; agents already running keep the route they started with. AMC_DISABLE_LOCAL_AGENT_RELAY=1 also turns it off and outranks this. Synonyms: local agent upload relay, route local agents through relay, compress agent requests, agents saturating upload, phone cannot load because of agents.
localSessionCeiling number integer 0..2000 How many agent sessions may run on this computer at once. On by default at 150; set it to 0 to switch the limit off. Once that many are running, a session the app starts on its own (a code review, a recipe, a scheduled job, a restart after the app reopens) waits in line and begins by itself the moment a place frees up. Nothing is dropped or failed. Sessions you start yourself, a message you send to a waiting one, and a crew lead are never held. Takes effect on the very next start, no restart needed. The live count, the limit and the line are on the performance readout (npm run perf:status). Synonyms: session limit, max concurrent sessions, cap on running sessions, session ceiling, how many sessions at once, too many sessions, queue new sessions.
masterAutoSyncEnabled toggle true | false SUPERSEDED by masterSyncEnabled — no longer read by the master-sync cron. Used to let a background check bring your local master branch up to date with the remote on its own; that job is now the one master-sync cron (see masterSyncEnabled), off by default. Kept in the settings schema for compatibility only.
masterSyncCatchUpEnabled toggle true | false Whether the small sync engine's automatic catch-up is allowed to fire. Off by default. When on, a computer that has been behind GitHub for the whole catch-up window (two hours by default) parks all of its own commits on a named branch, moves master to GitHub's tip, and replays the parked work as pull requests. That is the largest thing this engine does, so it stays off until the road is proven. Synonyms: automatic catch-up, turn off catch-up, catch-up switch, park and replay, small engine catch-up, minimal catch-up.
masterSyncCoordinatorModel text string Which model the master-sync escalator buys for the COORDINATOR — the single session that actually resolves the conflicts, commits, and lands the merge onto your local master. Leave blank (the default) to use the model this computer already uses for its own new sessions. A model is only sent together with masterSyncProvider, because the engine is what decides which models it serves; with no provider set this key is ignored and the sync says so in its run log. Set it with PATCH /settings/masterSyncCoordinatorModel; it takes effect on the next 15-minute tick with no restart, and a refused pick retries once with no engine or model named rather than stalling the sync. Does not change HOW MANY sessions are bought — that is the escalation cap. Synonyms: master sync model, sync coordinator model, which model resolves sync conflicts, change the sync model, master sync engine, sync resolver model, conflict resolver model.
masterSyncEnabled toggle true | false
masterSyncEscalateEnabled toggle true | false Internal bookkeeping / superseded: this old switch for paying a session to finish a blocked master sync is no longer read; a newer master-sync setting replaces it. Not a setting to change.
masterSyncFallbackWindowHours number integer 0..24 How long GitHub may hold a newer master this computer has not caught up with before the automatic repair takes over, in hours (default 2; range 0-24). When the window passes, the repair saves every commit of yours that GitHub does not have onto a catch-up branch, publishes those commits as pull requests, and only then puts your local master on GitHub's exact version — it never resets over unpublished work. Set it to 0 to keep master sync switched on while the automatic repair never runs, so nothing moves your master except the ordinary sync. Lives beside "Merge agents per day" in the Dev Pipeline panel → Setup → Master sync. Synonyms: automatic recovery window, when does master reset itself, catch-up fallback hours, how long before the automatic repair, master sync recovery window, stop the automatic master reset, 0 disables the fallback.
masterSyncFollowGitHubTip toggle true | false Whether THIS computer keeps its master level with GitHub by moving it straight to GitHub's tip, instead of merging GitHub into it. Off in the code, and on for every developer computer through the team setup, so every computer except the operator follows GitHub and sends its work as pull requests. When on, the 15-minute sync saves any commits master holds that GitHub lacks on a new amc-backup/master-<time> branch, moves master to GitHub's tip in one step, and raises a card naming the saved commit so the work can be sent as a pull request; an uncommitted edit to a tracked file skips that run and changes nothing. It has no effect on the main computer, and none while the role of this computer cannot be read. Turning it off needs the owner. CLI/agent-set; no Settings-UI control. Synonyms: follow GitHub tip, follow to tip, park local commits and follow, master follows GitHub, no merge sync, backup branch sync.
masterSyncOverseerEnabled toggle true | false Gives this computer its own Master Sync overseer: when this computer runs the simple master sync from the Omniscio source checkout and no Master Sync crew is live, the app starts one overseer session whose heartbeat opens with the full sync status. On by default; off starts no new overseer and leaves a running one alone. Each heartbeat is a paid agent turn. Read at every crew sweep. Dev Pipeline -> Setup -> Master sync. Synonyms: master sync overseer, sync overseer, sync heartbeat, master sync crew, sync lead.
masterSyncProvider text string Which engine the master-sync coordinator and its analysis workers run on. Leave blank (the default) to let each computer decide: the sync spawns the way any new session would there, on that project's default engine, then its global default, then Claude — so a computer with an engine switched off is never handed an engine it cannot run. Set it to pin the whole sync to one engine; the model keys beside it must then name models that engine actually serves, or the pickup is refused and the sync retries with nothing named. Set it with PATCH /settings/masterSyncProvider. Synonyms: master sync provider, sync engine, which provider runs the sync, change sync engine, sync vendor, master sync backend.
masterSyncStallWatchdogEnabled toggle true | false
masterSyncWorkerModel text string Which model the master-sync escalator buys for its ANALYSIS WORKERS — the up-to-ten read-only helpers that each study one packet of conflicted files and report proposed resolutions back to the coordinator. They never edit, commit, or land, so a cheaper model is the normal choice. Leave blank (the default) to use the model this computer already uses for its own new sessions. A model is only sent together with masterSyncProvider; with no provider set this key is ignored and the sync says so in its run log. Set it with PATCH /settings/masterSyncWorkerModel; it takes effect on the next 15-minute tick with no restart. Synonyms: sync worker model, master sync helper model, analysis worker model, cheap model for sync workers, sync fan-out model, conflict analysis model.
mcpServersComposedMigrationDone toggle true | false Internal bookkeeping: whether the one-time upgrade that composes each session's tool servers has run. Written by the upgrade, not a setting to change.
mcpToolControlsEnabled toggle true | false Switch single tools of an MCP server off, make a server always ask before it is used, and cap how many times one session may call it. Off by default. Switching a tool off works for Claude and Codex sessions and the tool is never offered to the agent; always ask and the call limit work for Claude sessions only.
memoryReclaimAdvancedEnabled toggle true | false In-development: on deep free-RAM pressure, run a Windows-only system-wide reclaim (empty all working sets + purge the standby list) via a one-time admin-approved helper. May briefly reduce performance. Hidden until shipped.
memoryReclaimAdvancedFreePercent number integer 1..90 Free physical RAM %, at/below which Tier-2 system-wide reclaim fires. Range 1-90. Default 25 (~16 GB free on a 64 GB box).
mintChangedLintGuardRunEnabled toggle true | false Let the ready-to-merge check run the repo lint guards a branch's own change concerns and report what it finds, so a branch cannot break a shared guard nobody runs on its path. Off by default: it only reports, and an unarmed run must not slow a merge down. Report-only — nothing is refused.
mintTestsReceiptRequired toggle true | false When on (the default), a branch cannot be marked ready to merge unless its tests actually ran at the exact commit the tag names. It is the TAG-TIME half of the tests-receipt rule, and it has its own switch on purpose: the lander has separate switches, and turning those off does not turn this one off. It is a PRESENCE rule - the receipt has to exist and cover that commit, it does not have to be green (a failure already on your main branch is not the branch's fault), and a branch that changed no code, or only docs, or only end-to-end tests owes no test lane at all. It also refuses a receipt that records a failure the runner attributes to this branch. When the answer is missing or stale it re-runs the check instead of stamping the tag. Turn it OFF to let a tag stand without test proof - that is the one-click way back, and it is what to reach for while the check system itself cannot produce receipts. A suspended cloud check lane is the usual reason. Takes effect on the next tag with no restart. Synonyms: tag-time test proof, require a tests receipt to tag, ready tag without tests, mint gate, why will my branch not tag.
missionControl2Accent select "ocean" | "emerald" | "violet" | "rose" | "amber" | "teal" | "indigo" | "fuchsia" | "sky" | "lime" Which accent color Mission Control (new) uses while missionControl2MatchTheme is off: ocean (the default), emerald, violet, rose, amber, teal, indigo, fuchsia, sky or lime. It colors the accent-colored controls inside the Mission Control (new) panel only. Set from the Look button on the Mission Control (new) panel. Synonyms: accent color, mission control accent, panel color, button color, pick a color for mission control.
missionControl2Background select "none" | "ember" | "dusk" | "forest" | "ocean" | "amethyst" | "meadow" | "vermilion" | "indigo" | "pine" | "graphite" | "sunrise" | "cobalt" What is painted behind the open Mission Control (new) board: none (the default), or one of the current Mission Control board backgrounds, the gradients ember, dusk, forest, ocean, amethyst and meadow, and the solid colors vermilion, indigo, pine, graphite, sunrise and cobalt. Saved for you only and applied to every board you open in Mission Control (new). Set from the Look button on the Mission Control (new) panel. Synonyms: board background, board wallpaper, background color, background gradient, make the board a color, remove the board background.
missionControl2Density select "compact" | "normal" | "comfortable" How tall a row of a Mission Control (new) board is: compact, normal (the default) or comfortable. Saved for you only and applied to every board you open in Mission Control (new); the current Mission Control keeps its own density. Set from the Look button on the Mission Control (new) panel. Synonyms: board density, row height, compact rows, comfortable spacing, make the board denser, rows too tall, rows too tight.
missionControl2Enabled toggle true | false Adds a "Mission Control (new)" row beside Mission Control in the sidebar. It is an in-progress rebuild of Mission Control, for testing only, and it starts empty. Your current Mission Control and its boards are not touched. Off by default.
missionControl2MatchTheme toggle true | false When on (the default), Mission Control (new) uses your Omniscio theme color as its accent color. Turn it off to use the accent color in missionControl2Accent instead. It changes how accent-colored controls inside the Mission Control (new) panel are drawn and nothing outside it. Set from the Look button on the Mission Control (new) panel. Synonyms: match my theme, use my theme color, follow the app color, mission control colors, accent follows theme.
missionControl2PostLinkedUpdates toggle true | false When on (the default), Omni posts one short plain line on a Mission Control (new) item when a session you linked to that item yourself ends or is archived, saying what the session got done. Only links you made in the app count; sessions linked by an agent or started from an item never post. It stays silent while Mission Control (new) is off, Omni is off or your AI comfort level is low, uses one small AI check per finished session under a 0.25 dollar daily cap, and posts again only after you type something new in that session. Set from the Omni settings section on the Mission Control (new) panel. Synonyms: post an update on linked items, linked session updates, omni recap on item, session summary on item, keep the item up to date, stop omni posting updates.
mobileDiffReviewEnabled toggle true | false On by default: a touch-native version of the Review-Changes surface, so you can read what a session changed and act on it from your phone. Lists the changed files, renders each file's diff as tappable chunks, and lets you accept or reject a single chunk or a whole file, then commit. The desktop reviewer is built on VSCode's editor engine, which is unusable by touch — this is a separate, lightweight renderer over the same data. The toggle stays live: this is the one surface that reaches destructive git commands from a paired phone, so turning it off is also how you close that door.
mobileSavedInboxEnabled toggle true | false On by default. Lets a phone show its inbox instantly from a saved local copy, then replace it with live data. Off shows nothing from the saved copy and deletes it.
mobileUrgentPanelMountEnabled toggle true | false On by default. On a phone, opens the tapped session's detail panel immediately instead of deferring it. A server-side switch that flips every phone at once.
newSessionSpawnPacingEnabled toggle true | false Paces the rate at which brand-new sessions are spawned, so a burst of starts cannot storm the machine. Off by default, and arming it is deliberately governed — one pacing lever is turned on at a time, each behind a crash matrix, a latency benchmark and a soak, never as a side effect of unrelated work. Synonyms: new session spawn pacing, pace session starts, don't spawn a storm, throttle new sessions, spawn pacer.
newSettingsLayoutEnabled toggle true | false Reorganizes Settings into clearer, better-named "rooms" without changing any individual setting.
objectDbMaintenanceEnabled toggle true | false When on, a quiet-window background job keeps each of your git projects' SHARED object database (the git-common-dir every worktree points at) fast by writing and refreshing its commit-graph (git maintenance run --task=commit-graph), so concurrent git operations across many worktrees (log, merge-base, history traversal) stay quick instead of slowing down as the loose object store grows. It runs ONLY when your computer is in a quiet window (it skips while the CPU is busy or still settling), runs demoted at low priority, is time-bounded and killed the instant the box gets busy, does at most one project per tick, and fails open (any problem simply means no maintenance ran, exactly like today). It deliberately does NOT repack loose objects — that stays the separate git object-store maintenance service's job — and never runs an aggressive full git gc/repack. Off by default (opt-in). Env kill switch AMC_DISABLE_OBJECTDB_MAINTENANCE=1. Synonyms: git maintenance, commit graph, git object database compaction, keep git fast across worktrees, git housekeeping, quiet-window maintenance.
objectDbMaintenanceUserHarmGateEnabled toggle true | false Not switched on yet. When on, object-database maintenance pauses only while the app is actually struggling for you, instead of whenever the processor is merely busy — so it runs more often on a busy machine. Off until its own evidence is reviewed.
omniscioCliEnabled toggle true | false Adds an omniscio command to your terminal so you can chat with an agent, run a one-off prompt, or connect an editor that speaks ACP, all through the running app. The command is added to your own PATH only while this is on and is removed when you turn it off; nothing system-wide changes, and it works only while Omniscio is running. Off by default.
optInToggleMigrationDone toggle true | false Internal bookkeeping: whether the one-time upgrade that added the sidebar opt-in switches has run. Written by the upgrade, not a setting to change.
orphanReaperEnabled toggle true | false When on (the default), Omniscio cleans up Claude processes left behind when it crashes or restarts, so a dead run never keeps eating memory and CPU in the background. Turn it off to leave every leftover process alone, for when you suspect the cleanup is stopping something it should not. Synonyms: orphan reaper, kill leftover claude processes, clean up orphaned sessions, stop the orphan cleanup, leftover process cleanup.
orphanReaperWmiStormHoldEnabled toggle true | false When on (the default), the orphaned-process reaper holds back its WMI command-line fallback — a full-machine process walk that would add CPU load — while the machine is in a kernel-bound storm. The reaper keeps sweeping; it just stops reaching for the expensive fallback until the storm passes, so a box that is already struggling is not made worse by the reaper itself. Turn it off to always allow the fallback. Synonyms: orphan reaper wmi storm hold, pause the wmi fallback while busy, reaper hold during a storm, kernel storm hold, wmi walk hold.
orphanToolTreeReaperEnforce toggle true | false Whether the reaper for orphaned tool-call process trees actually KILLS the processes it finds, or only writes down what it would have killed. Off by default — it ships in shadow mode, so you can read its findings before letting it act. Master kill: AMC_DISABLE_ORPHAN_TOOL_TREE_REAP=1. Synonyms: orphan tool tree reaper enforce, kill orphaned processes, shadow mode reaper, leftover tool processes, stray child processes.
overseerCardSubscriptionByMission map map of string → "decisions" | "decisions-and-reports" | "everything"
overseerSystem select "classic" | "missions"
overseerUpdateLevels select "both" | "big-only" | "small-only" | "none"
overseerUpdateLevelsBySession map map of string → "both" | "big-only" | "small-only" | "none"
panelActsOnItsOwn toggle true | false
panelChairOrder list array of string (≤120)
panelEveryHours number integer 1..24
panelMembers list array of object { model: string (≤120); provider: string (≤60) }
persistentAgentSecretsEnabled toggle true | false Keeps the secret that signs agent session tokens saved in an encrypted file, so agents keep working across app restarts instead of getting a fresh secret every launch. On by default, and it also needs Windows built-in data protection to be available; otherwise per-startup secrets are used. Switching it off deletes the saved secret at the next start. Synonyms: durable agent secrets, keep agent tokens across restart, persistent agent token secret, agent login survives restart.
personalitiesEnabled toggle true | false Pick a personality for your agents, such as concise, friendly or formal, as a default for every session or for a single session. Off by default.
personalityPresets list array of object { createdAt: string; id: string (≤120); mode: "add" | "replace"; name: string (≤60); source: "user" | "hermes"; text: string (≤4000) } The personalities you have saved, up to 50: each has a name, a short text of up to 4000 characters, a mode (add = the text is added after the built-in persona, replace = the text takes its place for the session) and where it came from (you wrote it, or the Import from Hermes tool brought it across). Omniscio's built-in personalities are not stored here. Only has an effect while the Personalities Lab switch is on. Changed in Settings, Personalities, where you can write, edit and delete presets, or by the Import from Hermes tool. Synonyms: saved personalities, custom personalities, my personalities, tone presets, persona presets, agent tone list, personalities imported from Hermes.
picovoiceWakeWordEnabled toggle true | false Retired: the paid Picovoice wake-word engine. Its proprietary models are no longer bundled and it is hidden from the wake-word engine picker — the free built-in engine recognizes the same wake words. Retirement outranks this entry’s toggle, so switching it on cannot bring the engine back; only the AMC_SHOW_PICOVOICE_WAKE_WORD=1 developer setting re-reveals it, for testing.
pinnedSidebarHeaderItemIds list array of string (≤64) Which project-header actions (e.g. terminal, collapse, new session, search) show as bar icons versus being tucked into the ⋮ menu, by action id. Set by right-clicking a header icon and choosing "Pin to header" / "Move to ⋮ menu"; desktop only.
piperExecutablePath text string (≤1024)
piperModelPath text string (≤1024)
postLandBuildHarmYieldEnabled toggle true | false Let the post-land build step step aside when the app is under real strain. On by default.
powershellChainRetireEnabled toggle true | false Retire the machine-local PowerShell guard chain. When on, the app stops fronting the chain and removes ~/.claude/hooks/guard-host.ps1, pretooluse-guards.ps1, every guards/*.ps1 and hookguard*.exe plus the *.bak* files beside them, after writing one archive copy and one record of what it removed; the hook entries that named those files are unwired in the same pass. Off by default, and AMC_DISABLE_POWERSHELL_CHAIN_RETIRE=1 keeps today's chain regardless.
preLockReplySeatRetireMigrationDone toggle true | false
processReaperDryRunLaunches number integer 0..1000 How many more launches the orphan-process cleaner runs in practice-only mode before it starts actually closing leftover processes (default 5).
processReaperMode select "dry-run" | "active" Whether the orphan-process cleaner only logs what it would close ('dry-run', default) or actually closes leftover processes ('active').
providerFallbackChainEnabled toggle true | false When a provider keeps failing, move that session down your own fallback list to the next provider you already switched on. Off by default. It only reorders choices you made: it never adds a provider, never turns one on and never raises a cap. Claude sessions move only if you also allow that.
providerKeyPoolsEnabled toggle true | false Add more than one key for a provider and the app rotates to the next one when a key is rate limited, out of credit or refused. Off by default. Never used for Anthropic or Claude accounts, and keys never leave this computer.
quickLaunchTabsBackfilledAt text string (≤64) Internal bookkeeping: when the one-time upgrade that filled in the Quick Launch tabs finished. Written by the upgrade, not a setting to change.
quitConfirmation select "direct" | "hold" | "double-click"
readyMintV2Enabled toggle true | false Reserved switch for the second ready-to-merge mint, shipped off. Nothing selects the second mint yet: with this on or off, every run takes the first mint exactly as it always has, and every ledger row records the pipeline it ran on as v1. The switch exists now so the rows, the settings catalog and the scorecard name it once, in one place; the wave that builds the second mint is the one that makes this setting change what runs, and until then turning it on is safe and changes nothing. No restart and no environment variable are involved. Synonyms: second mint, v2 pipeline, ready mint v2, new ready gate, switch the ready mint over, compare the ready mint pipelines.
readyMintVerdict3Evidence toggle true | false Whether the ready-to-merge check also accepts a Verdict 3 result. When a branch's test receipt has no matching record on this computer, the check asks Verdict 3 whether it passed this exact version of the code, and accepts the branch only on a clear "passed". Ships off; off means nothing is asked and nothing changes HERE. It does NOT cover the folder-less row (a branch registered with no checkout, e.g. a carry:cloud re-cut): that row has no receipt of its own to be corroborated, so its mint always asks Verdict 3 for the owed lanes and records what it answers — otherwise the branch could never be tagged at all. Synonyms: verdict 3 evidence, accept verdict 3 results, ready mint verdict 3, tree verdict, evidence uncorroborated, readyMintVerdict3Evidence.
readyOperationEnabled toggle true | false In development. When on, handing in a finished branch becomes a durable job the app owns and retries when a machine or server cannot answer, instead of failing the author. Off by default, and the existing ready-to-merge route is used. Synonyms: readiness operation, ready to merge v2, durable merge hand-off, branch ready retry.
relayUploadCapEnabled toggle true | false Pace what the cloud key relay sends out of this computer to its share of the measured upload line — 80% of it less what other traffic is already sending and less the loss the line is running, or 768 KiB/s while the line cannot be read — shared across every relayed call, so a cloud agent never saturates your upload. On by default.
relayUploadMobileCapKiBps number integer 0..∞ Sets the upload speed limit, in kilobytes per second, that the cloud relay uses while your computer is on a mobile network. The default of 0 means no special mobile limit beyond the normal automatic pacing. It only matters when the relay upload cap itself is on. Synonyms: mobile upload cap, cellular upload limit, relay upload speed on phone network, tethering bandwidth limit.
remoteSessionsEnabled toggle true | false Shows the Remote sessions controls on the Remotes tab of SSH Remotes settings: the kill switch, the four limits, standing OKs and the log of every request. Still in development; it is hidden until you switch it on, and it always shows once a machine lets agents start sessions or a remote session is running.
rendererLoadRetryEnabled toggle true | false When on (the default), a window whose page fails to load is reloaded a few times on its own, which clears the brief blank screen you can see while the app is rebuilding. Turn it off to show the failure at once with no retry. Synonyms: renderer load retry, retry blank window, auto reload white screen, retry failed window load, stop auto reloading windows.
requireMobileAccountLogin toggle true | false Require signing in to your account to use the mobile/web view. Forced on; only a developer setting can turn it off.
reserveUiCoreCount number integer 1..8 How many performance (P) cores to set aside for Omniscio's window when the reserve setting above is on. One is enough for a responsive window on most machines; raise it if Omniscio's own window, its graphics process and its helpers together need more than a single core to stay smooth under a heavy swarm. Your sessions share every core that is left, and they are never squeezed onto fewer than one performance core no matter how high you set this — on a smaller CPU the reservation quietly lands lower than you asked. Only takes effect while the reserve setting is on. No effect on non-hybrid CPUs or non-Windows systems.
runawayCommandAutoStopEnabled toggle true | false When on (the default), the runaway-command watch also stops a READ-ONLY search or listing on its own — only one that has run 20 minutes or more, is still busy, and is slowing the other agents, and at most two per check. Anything that writes, installs, builds or tests is never stopped without you. Turn it off to keep the inbox cards and their Stop button but stop nothing automatically. Synonyms: runaway command auto stop, stop runaway searches automatically, auto stop long searches, automatic command stop, stop slow read-only commands.
runawayCommandWatchEnabled toggle true | false When on (the default), Omniscio watches every command your agents are running and raises ONE inbox card with a Stop button when a search or listing has run 10 minutes or more and is still busy while the other agents slow, or when a command looks like an unbounded search — a build, test run, install or merge gate never gets it just for being busy. Stop ends only that command — the agent sees it fail and its session keeps running. Turn it off to stop the cards and the automatic stops entirely. Synonyms: runaway command watch, long running agent command, stop a stuck agent command, agent command slowing everything, has run minutes card.
runawayMemoryReapEnforce toggle true | false Lets the app end a process that is using runaway amounts of memory and still climbing, including one of its own agent sessions. On by default. Turning it off makes the app only report what it would have ended and end nothing. Synonyms: runaway memory killer, memory hog reaper, kill runaway process, out of memory protection.
safetyChecksEnabled toggle true | false Extra protections for agents: a Smart approval level, never-allow rules, an optional approval timeout, credential and secret protection, private-network and site blocking, injection scanning and package advisories. Off by default.
safetyEnvPassthrough list array of string (≤128) Names of environment variables that stay visible to agent processes even while Keep secrets out of agent processes is on, for example MY_API_TOKEN. Normally every variable whose name looks like a key, token, secret, password or credential is removed before an agent command, tool process or scheduled script starts; list a name here only when a tool you run really needs it. Exact names only, made of letters, digits and underscores and not starting with a digit, up to 50 names, empty by default. Edit it in Settings, Safety checks (Lab switch on). Synonyms: env var allow list, let environment variable through, keep token visible to scripts, secrets scrub exceptions, scrub passthrough.
scheduledJobsPlusEnabled toggle true | false Scheduled jobs that report back: send a job's result to your inbox, a file, email or a chat, pass output to the next job, skip a run with a script, pause every job at once, check jobs with the doctor, type schedules in plain words, and run prompts as a batch. Off by default.
scratchTierEnabled toggle true | false Let agent pipelines build scratch worktrees that hold only the files they open, instead of a full checkout. On by default; turn off to give every agent a full worktree again.
sessionCheckpointsEnabled toggle true | false Take a private snapshot of a session's folder before and after every turn, so you can undo what one turn changed. The snapshots live in a hidden store inside Omniscio's own data folder, never in your project, and they never change your own git history, branches, index or stash. They also work in folders that are not git projects. Off by default.
sessionIoPriorityUserHarmGateEnabled toggle true | false Not switched on yet. When on, the session disk-priority sweep keeps its normal cadence while the app is fine, instead of speeding up whenever the processor is merely busy. Off until its own evidence is reviewed.
sessionTreeEcoQosEnabled toggle true | false
settingsDrilldownNavEnabled toggle true | false Reorganizes Settings into a multi-level drill-down — pick a category, then a page, instead of one long list. It also enables the room grouping.
settingsGuidedStepsEnabled toggle true | false When an agent needs you to do something by hand, it offers Give me guided steps. Choosing it opens a steps window attached beside every screen that ticks steps off as you go and returns you to the chat when you finish. On by default; switch it off and the link still opens the place for the first step, just without the window.
settingsQuickPresetsEnabled toggle true | false In-development: a "Quick setup" card on the Settings Home page offering three one-click presets (Minimal, Balanced, Power user) that each apply a batch of benign settings in one action and show which preset is currently active. Off by default; hidden until shipped.
settingsRedesignEnabled toggle true | false The settings redesign: per-page tab strips (Appearance / Sessions / Voice) with aggressive Basic/Advanced splitting and live previews. Shipped — on by default for everyone; the enable/disable toggle is retired. The settingKey is kept only so older persisted configs still parse; visibility no longer reads it (a shipped feature is always on). Quick-setup presets remain a separate in-development feature.
setupToolsAppliedAt text string ISO timestamp set when the "Your tools" selection was applied, so it is never applied twice and a completion can be counted.
setupV2ChosenProvider select "claude" | "codex" | "gemini" | "antigravity" | "deepseek" | "kimi" | "glm" | "minimax" | "meta" | "qwen" | "openrouter" | "cursor" | "hermes" | "grok" | "gpt" | "xai" | "pi" | "devin" | "grokbot" | "reason" | "kimicode" | "dsh" | "musecode" | "ultramarine" | "t3code" | "crofai" | "deepinfra" | "geminicc" | "runinfra" | "inferx" | "venice" | "abliteration" | "engy" | "refuseless" Remembers which AI provider you picked on the first-run setup question about which AI you use. It lets setup return to your own provider's sign-in options after a quit or crash. Empty when no setup run is unfinished. It holds no credential. Synonyms: setup chosen AI, first-run provider pick, onboarding provider choice, which AI do you use.
setupV2PendingClaudeLogin toggle true | false Marks that you chose to sign in with your Claude account during first-run setup but Claude Code was not installed yet, so the sign-in is waiting for the install step. It survives a quit so setup can still offer it. Off by default, and cleared when done. Synonyms: pending Claude sign-in, queued claude login, setup login waiting, onboarding sign-in queued.
setupV2RoleToolsEnabled toggle true | false First-run setup asks what you do (developer, writer, photographer…) and offers a starter set of tools and plugins for that role, which you can add to or trim before they are added to your side nav. On by default for every new install; the toggle stays live so it reverts with one setting flip.
sharedNodeModulesEnabled toggle true | false In-development: point a new worktree's node_modules at a single shared base via one junction instead of copying every dependency file, cutting a worktree's file count by about 89% — so worktrees create and delete faster and churn far less disk. Hidden until shipped.
simpleMasterSyncEnabled toggle true | false Keeps this computer's local master level with GitHub's master by running the simple master sync every 15 minutes: a fast-forward when this computer has nothing of its own, otherwise one merge that keeps this computer's copy of any clashing file. It never pushes, and it runs on every computer, packaged installs included. On by default; off stands the sync down at its next tick, and the environment variable AMC_DISABLE_SIMPLE_MASTER_SYNC=1 also turns it off. Read at each tick. Dev Pipeline -> Setup -> Master sync.
smrzzEnabled toggle true | false
smrzzLabExitHeld toggle true | false
smrzzShown toggle true | false
sourceCheckoutPath text string The folder of the Omniscio source checkout this computer should run its background jobs from, when Omniscio itself is the installed app rather than a checkout you started with npm run dev. Leave it empty and Omniscio uses a checkout it can already find; set it and that folder is used first. Without one, an installed Omniscio cannot start its scheduled maintenance jobs or the Verdict broker that answers your test gates, and a gate tells you so by name. Set it in the Dev Pipeline panel → Setup → "Source checkout folder". Synonyms: source checkout, my omniscio checkout folder, repo path for background jobs, ops jobs cannot run, no-runner, where is my checkout.
sourceControlFollowPullRequestTemplates toggle true | false
sourceControlWritingInstructions text string (≤2000)
sourceControlWritingMode select "conventional-commits" | "repo-conventions" | "custom"
spawnOomHoldEnabled toggle true | false On by default. When the machine is low on memory, pauses new agent sessions instead of letting them pile up and crash the computer.
spawnPacerUserHarmGateEnabled toggle true | false Not switched on yet. When on, new session starts are paced only while the app is actually struggling for you, instead of whenever the processor is merely busy. Off until its own evidence is reviewed.
stayAliveHandOverTokens number integer 20000..2000000
stayAliveNoteTokens number integer 20000..2000000
streamingThrottleMs number integer 16..200 How often (in milliseconds) streamed AI output is refreshed on screen. A larger number is smoother but less responsive.
supplyControlEnabled toggle true | false Adds a "Supply Control" tab to the sidebar: a workspace for buying from suppliers, from sourcing to purchase orders. It runs on demonstration data and is still in development.
syncReadoutEnabled toggle true | false After each sync, this computer sends your other computers one short status line: how far behind and ahead it is, whether it follows another computer, and the last error in plain words. On by default. Turning it off stops sending and showing that line. Synonyms: sync status report, report sync position, sync readout, computer sync status line.
tasksKeyboardTourPromptShown toggle true | false
terminalEnabled toggle true | false Inbuilt terminal
thinSessionProcs toggle true | false Windows only. When on, each agent session and every tool command it runs (bash, git, powershell) share ONE genuinely-hidden console window, so Windows no longer creates a separate conhost.exe console window per command — the fix for hundreds of terminal windows flashing on screen and a pile of conhost.exe processes. It routes a session spawn through a tiny bundled launcher (amc-hidden-launch.exe) — a direct-executable engine directly, and a .cmd / .bat shim engine (an npm-global install, for example) through the launcher's hiding gate, so the cmd.exe that runs it gets the same hidden console instead of a visible one of its own. On by default (Windows). Fail-open: if off, or on any problem finding the launcher, sessions start exactly as before. Takes effect on the next session you start. No effect on macOS or Linux. Legacy enable env var AMC_HIDDEN_CONSOLE_LAUNCHER=1; kill switch env var AMC_DISABLE_THIN_SESSION_PROCS=1. Synonyms: thin session processes, hidden console, stop the flashing terminal windows, fewer conhost processes, no console window per tool command.
toolCallTimingTapeEnabled toggle true | false Record how long agent tool calls take, for diagnostics. A measurement only, not a limit. On by default.
trainingHubEnabled toggle true | false In-development: one sidebar hub (Insights group) for learning Omniscio — every tutorial video playing in the app, the docs in a clean reader that works offline, and links to keyboard shortcuts, Get Help and the online guide. ON by default; turn it off here to remove the hub from the sidebar.
trainingHubWatchedVideos list array of string (≤500) Internal bookkeeping: the Training Hub tutorial videos you have watched at least halfway, so the hub can show them as Watched. Written by Omniscio when a video reaches its halfway point, not a setting to change. Synonyms: watched tutorials, seen videos, tutorial progress.
trainingTracksJoined list array of string
tutorialVideosInInboxEnabled toggle true | false Sends tutorial videos to your inbox, one at a time, as you become ready for them. On by default. Turning it off keeps the videos in the Training Hub only and sends none to your inbox. Synonyms: tutorial videos in inbox, training video cards, send videos to inbox, onboarding video drip.
tutorialVideosPace select "as-ready" | "daily" | "weekly" | "monthly" Chooses how often a new tutorial video arrives in your inbox: as soon as you are ready, one a day, one a week, or one a month. The default is as soon as ready. Only matters while tutorial videos in the inbox are on. Synonyms: tutorial video frequency, video drip speed, how often new videos, training video cadence.
updateInterfaceEnabled toggle true | false Lets a new interface build be applied to the running app without restarting it: the renderer is built into a fresh folder, checked against the running main, and swapped in only when you reload (POST /app/reload, the Hard reload action, or the tray). Off by default — with it off, every reload behaves exactly as it always has and the app keeps showing the build it launched with.
usageCascadeOnErrors toggle true | false
usageCascadeOnErrorsIncludeClaude toggle true | false
usageCascadeRouting select "priority" | "cheapest"
userRoleId select "developer" | "writer" | "photographer" | "designer" | "founder" | "product-manager" | "student" | "other" The role chip picked on "About you" (userRole keeps the free text / label for anything that reads it today). Written only after the privacy disclosure (F196), like userRole.
verdict3AgentQaAccountId text string (≤200)
verdict3MasterSendEnabled toggle true | false Whether the Verdict 3 test fleet's copy of master is kept up to date after each land. When on, the newest master is sent to the fleet's git server shortly after lands (several lands share one send), and only ever as a forward move. Ships off; off means nothing is sent. Synonyms: verdict 3 master send, send master to the fleet, fleet git master, keep fleet master current, verdict3MasterSendEnabled.
verdict3OldRoadFallback toggle true | false Since the Verdict 3 switch-off the agent gates never re-run a Verdict 3 no-answer on the older road: a no-answer stays a no-answer. This switch is now read only when the nightly master baseline picks its road, and it goes away with the older road. On by default. Synonyms: test service fallback, old test road, no answer fallback, cloud test fallback.
verdict3RecentPassWindowMinutes number integer 0..60 On by default, at 10 minutes. When you re-run the same test, lint, typecheck or end-to-end check on the same commit and the same files within this many minutes of a PASS, Verdict 3 hands you that PASS straight from this computer's own attempt ledger, printed as "served from cache at <age>" with the original request id, instead of asking the test fleet again. Only an accepted PASS is ever served: never a FAIL or a no-answer, never another commit, file list, typecheck program or lane, never over a working tree with uncommitted changes (untracked files included), and never over a landing proof that already holds a failing entry for that check. 0 turns it off and 60 is the most. A value the app cannot read, or an app too old to know this setting, means no cache. Read live on every ask with no restart; change it with PATCH /settings/verdict3RecentPassWindowMinutes. Synonyms: recent pass cache, serve a cached verdict, repeat ask cache, skip a repeat test run, verdict 3 cache window, served from cache.
verdictRouteCutoverMoved toggle true | false Internal bookkeeping: written true when the app-start migration moves this install from "v1" to "v3-all". Nothing reads it any more (the rollback it served is retired). Written by the upgrade, not a setting to change.
verdictV1Off toggle true | false On by default: the old V1 test queue is switched off. Every check goes to Verdict 3, and a job that would have gone to V1 ends as a named no-answer that says which program sent it. The one exception is a short list of end-to-end test shapes Verdict 3 cannot run yet (specs that need a signed-in account and the internet, and old-road staging asks); each entry names the task that retires it. While this is on, the V1 fleet alarms stay quiet. Turn it off to put every V1 road back at once, or set AMC_VERDICT_V1_OFF=0 for a single run.
videoStudioAppEnabled toggle true | false
videoStudioEnabled toggle true | false Video Studio panel in the Creative group: make short AI video clips and fix any part of them. Also needs Video Studio switched on in Settings → Built-in Apps. Off by default; hidden until shipped.
voiceLiveEnabled toggle true | false In-development: hold a real conversation during an inbox walk — ask about the session you just heard, change your mind, cut in mid-sentence, and hear a natural voice answer. It does only what the walk already does — reply, follow-up, archive, skip, snooze, repeat — and sending still needs your spoken yes. Needs the inbox walk turned on too; if the live voice or its key is missing, the ordinary walk runs as before.
watchdogReconnectWifiOnOutage toggle true | false
webAppVerifyNudgeSeen toggle true | false Web-app verification (Obscura) is retired as of 2026-09-19 — the verify_web_app tool no longer composes into a session, so there is nothing to turn on and no tool to advertise; the engine stays in the tree, unwired. This key is only the one-shot marker that the old "install Obscura" nudge has been seen, and it is now read by nothing.
whatNextFathomEnabled toggle true | false
whatNextFirefliesEnabled toggle true | false
widgetSidebar unknown unknown
windowForegroundHarmYieldEnabled toggle true | false When on (the default), a window raise Omniscio starts ON ITS OWN takes the cheap path — no always-on-top toggle — while the machine is measurably hurting you. A raise YOU asked for is never gated by this, so clicking a session always brings it forward normally. Turn it off to let every machine-initiated raise use the full path regardless of load. Synonyms: window foreground harm yield, dont steal focus while busy, cheap window raise when hurt, machine window raise gating, foreground harm yield.
wmiHydrationBackoffEnabled toggle true | false When on (the default), the command-line hydrator backs off its FULL-TABLE WMI walk: a walk that resolves nothing doubles the wait, up to 15 minutes, and any walk that resolves something resets it; off restores one walk per batch, unconditionally. It exists for a measured reason — 44 consecutive full-table WMI walks at the reaper's 2-minute cadence, over ~155 processes the walk never resolved, burned a core in wmiprvse.exe on every tick, forever. Synonyms: wmi hydration backoff, slow down the wmi walk, wmi fallback backoff, command line hydration backoff, stop the wmi CPU burn.
worktreeBranchNaming object object { instructions: string (≤1000); mode: "session" | "prefix" | "ai"; prefix: string (≤40) }
worktreeBuildLimitMinutes number integer 1..600
worktreeCreateCalmHoldEnabled toggle true | false Makes each new worktree wait, for a bounded time, until the drive it is created on is no longer busy. Off by default: on a computer whose system drive is also the worktree drive that drive never reads calm, so every create sat out the full wait for nothing. With it off, busy-drive creates are still taken one at a time. Armed under the same one-at-a-time rule as the pacing levers. Synonyms: worktree calm hold, wait for the disk to calm, create queue calm wait, hold worktree creates on a busy drive.
worktreeCreateOutageAlarmEnabled toggle true | false Raises an alert when several attempts to create a session workspace fail within a short time, which suggests something such as a full disk or stuck git is broken. On by default. Turning it off silences that alert. Synonyms: workspace create failure alert, worktree creation outage, cannot create workspace alarm, create failure warning.
worktreeCreatePacingEnabled toggle true | false Paces the rate at which new worktrees are created, so a burst of creates cannot storm the disk. Off by default, and armed under the same one-at-a-time rule as the other pacing levers (crash matrix, latency benchmark and soak before it is switched on). Synonyms: worktree create pacing, pace worktree creation, throttle worktree creates, worktree create storm, disk pressure from worktrees.
worktreeDefaultSparseEnabled toggle true | false Give each new worktree only the folders most work needs (big test, video and side-project folders stay out until a session asks for them), so worktrees are smaller and git is faster. On by default.
worktreeDeleteEnabled toggle true | false
worktreeDeleteWindow object object { endHour: integer 0..23; startHour: integer 0..23 }
worktreeDepsInstallByRepo map map of string → string (≤500) Per-repository choice of how a new workspace gets its dependencies, keyed by the repository folder. Empty by default, which means the app installs with the package manager the repo's lockfile names (npm ci, yarn install --frozen-lockfile or pnpm install --frozen-lockfile, or npm install --no-package-lock when there is no lockfile). A value of off means the app does not install for that repo and the agent installs itself; any other value is the install command to run instead, split on spaces with no quoting, so a single argument cannot contain a space, and run without a shell. Read each time a workspace is prepared. Synonyms: custom install command, skip dependency install, no install for this repo, per repo install, workspace install command.
worktreeFullCopyRepeatCapEnabled toggle true | false Limit worktrees to one full large dependency copy per day, so a repeated copy cannot fill the disk. On by default.
worktreeHandOutLimitSeconds number integer 1..600
worktreeHomes list array of string (≤260)
worktreeIdleLeaseEnabled toggle true | false Automatically give an idle session's work folder back after six hours, saving its unsaved work first. On by default; turn off to keep folders indefinitely.
worktreeInstallLimitMinutes number integer 1..120 How many minutes the app lets a repo's own dependency install run in a new workspace before it stops it and marks the workspace as failed, from 1 to 120 with 15 by default. It applies to repositories that are not set up for Omniscio's own shared dependency folder, where the app installs with the repo's own package manager. Read each time an install starts. Synonyms: install timeout, dependency install time limit, npm install timeout, workspace install minutes.
worktreeLeaseCanaryVolume text string
worktreeLeaseEngine select "v1" | "shadow" | "canary" | "v2" | "v5-shadow" | "v5-canary" | "v5"
worktreeLeftoverKeepMax number integer 0..8 While spare work folders are switched off, keep at most this many finished folders (0 to 8) for new sessions to reuse; extra ones are deleted at the next cleanup, branches kept. 0 deletes every finished folder. Default 8.
worktreeLifecycleCore select "auto" | "legacy" | "core"
worktreeLifecycleCoreBornAs object object { decidedAt: string (≤300); engine: "legacy" | "core"; reason: string (≤300) }
worktreePinLapseArchivedLandedEnabled toggle true | false When on (the default), one case skips the usual wait before an agent-set pin lapses: a pin whose session is already archived and whose branch is already on your integration branch is released straight away, so finished work never holds a slot through the grace period. Turn it off and every agent-set pin waits the full grace period as before. Separate from worktreePinLapseEnabled on purpose — that one turns the whole lapse pass off; this one turns off only the immediate release for finished work. It acts on this repository's worktree ledger, never on your own changes. Synonyms: release a pin whose work already landed, skip the pin grace period, finished agent pin release, fast pin lapse.
worktreePinLapseEnabled toggle true | false When on (the default), a pin an agent set on a worktree ledger row lapses once both the agent that set it and the row owner are gone, so a claimed slot is never held for ever by a dead agent. Turn it off to keep agent-set pins in place indefinitely. A separate environment kill switch exists for operators. Synonyms: worktree pin lapse, let stale pins expire, dead agent holds a worktree, release abandoned worktree pins, pin never held forever.
worktreePinLifetimeDays number integer 0..90 How many days a kept workspace stays kept after it was kept or last renewed. A day before it ends you get a reminder with Keep and Let go. The default is 7 days, the range is 0 to 90, and 0 keeps pins forever. Synonyms: pin lifetime, kept workspace expiry, worktree pin days, keep workspace duration.
worktreePoolSize number integer 0..50
worktreePoolSizeByRepo map map of string → integer 0..50
worktreePoolSpareFloor number integer 0..50 On this computer, keep at least this many spare work folders ready for each project (0 to 50), even while the project already has spares to reuse or repair. 0 keeps the current behaviour. Growth still stops at the limit of the folder permit and at every disk safety floor. Default 0.
worktreePoolV2Enabled toggle true | false
worktreeReapUserHarmGateEnabled toggle true | false On by default. Cleanup is maintenance work: it proceeds through agent-only CPU pressure, but yields to a positive user-interactive harm verdict. Saturated target volumes do not hold the drain; cleanup runs gently to keep disk I/O reduced. If the harm reading is blind or unavailable, it falls back to the CPU verdict and its bounded retry. Read live, so switching it needs no restart. Master kill: AMC_DISABLE_HARM_KEYED_LOAD_GATES=1. Synonyms: worktree reap user harm gate, harm keyed load gate, worktree cleanup load gate, reap worktrees when busy.
worktreeRegistryFileReadsEnabled toggle true | false When on (the default), Omniscio lists a repository's worktrees by reading the files under its .git folder instead of running git for each listing — on a checkout with hundreds of worktrees that turns a multi-second git command into a few milliseconds with no process at all. Any doubt falls back to git automatically. Turn it off to make every listing run git exactly as before; the AMC_DISABLE_WORKTREE_REGISTRY_FILE_READS environment variable is the operator's kill switch for the same thing.
worktreeRepairLimitMinutes number integer 1..600
worktreeRepairOnlyLeasing toggle true | false
worktreeSlotPoolEnabled toggle true | false Reuse an already-prepared work folder for a new session instead of building a fresh one each time. On by default.
worktreeStaleInstallRefusalEnabled toggle true | false Refuse to use a worktree whose dependency install is out of date compared to its setup. On by default.
worktreeSubmodules select "none" | "top-level" | "recursive"

Every "What it does" is the setting's own description — this page is rebuilt whenever a setting changes, so it is always current.