Omniscio

Start a new Claude Code session

Pick a project and hit + New Session (or Ctrl+T / N) — Omniscio spawns a fresh claude CLI inside that project's folder using your active account. Sessions are per-project, persist across restarts, and you can run many at once. Nothing is billed until you send your first message.

On this page

What it is

A session is one chat with Claude Code running inside a specific project's folder, with your back-and-forth living in the session's transcript. You can have many sessions open across many projects at the same time. Starting a new session means: pick a project, hit the launch button (or Ctrl+T / N), and Omniscio spawns a fresh claude CLI process inside that project's folder using your active Claude account.

Omniscio also auto-launches a session for you the first time you switch to a project you've added that has none, so you can start typing without ever clicking the + button. Most built-in tool panes (like the Automation Helper) are the exception — they wait for you to tap +. Two are not: clicking Ask Omniscio or Session Search in the sidebar drops you straight into a session, and if that pane has nothing waiting for you it launches a blank one on the spot, exactly like any other project with no open session. That launch carries no prompt, so nothing is billed — but a session row does appear. This holds on mobile too.

A session is per-project: the folder shown next to the project's name in the sidebar becomes the session's working directory. Anything Claude does (reading files, running tests, writing patches) happens inside that folder. Sessions persist across app restarts — the conversation history, attachments, and any pending state survive a quit.

Starting a session is fire-and-forget (2026-11-03). When you start a session yourself and send its first message, Omniscio takes you back to what you were doing in that hub: the notes, mail or board screen you were on in KMS, Supermail or Mission Control, else the session you were on, else the hub's next session that needs you. The new session keeps running in the sidebar, and Alt+Q jumps back to it. Full rules: send-a-message.md.

Where to find it

The small + icon at the top of the Sessions panel — the middle column in the sidebar that lists a project's sessions — is the most-used entry point. The same action is on a keyboard shortcut and in the project's own menu.

How it behaves

How to use it

  1. Pick a project. Click any project in the left Projects sidebar (the strip with the colored vertical bars). The middle column will switch to that project's session list.
  2. Click the "+" icon at the top right of the Sessions section header (above the session list, next to the count). The icon shows a Plus glyph; the tooltip reads "Launch new session" plus your keyboard shortcut. The session appears at the top of the list, becomes active, and the composer focuses so you can type your first message right away. If the session list was scrolled down — a long Needs You list can push the Live Sessions section below the fold — it scrolls to bring the new session into view, so you always see the one you just started. The session row then follows the session's real state: it reads Starting while the CLI process is still coming up, and only turns green once that process is genuinely up — never ready before it has started.
  3. Or use the keyboard shortcut. Default is Ctrl+T (or just N) — both bound to the newSession action. Works from anywhere in the app. Pressing it twice in a row does NOT create a duplicate empty session — Omniscio reuses the existing blank session if one already exists in this project, so the keyboard shortcut is safe to mash.
  4. Launch it. The + button launches a new session immediately — there is no target dropdown any more. Where the session runs is chosen on the new-session empty state (a Run location picker — pick Cloud and the "Save as default" banner offers to make it your default for Only this project or Everywhere, so new sessions start on Cloud; it applies only where Cloud is offered and after you've confirmed the one-time cloud cost notice, and the Fan-Out, Handoff and phone draft screens keep starting Local), and whether it is isolated in a git worktree follows the project's Isolate by default setting — Shift+click the + button to quick-launch with the opposite isolation. See Session isolation for where that copy is created, what is inside it, and how the work comes back to your project.
  5. Send your first message. The composer placeholder shows "Send your first message to begin..." while the session is ready and still empty (on a phone, a shorter "Your first message..." so the narrow empty box stays one line instead of wrapping the long hint to two). Once a session has messages the box reads the generic "Send a message..." instead — ready is also the idle state a used session rests in, so history, not status alone, decides the wording. Type a prompt and hit Enter (or Ctrl+Enter, depending on your Submit key setting). On the very first send, Omniscio auto-attaches any files in the project's .claude/docs/ folder so the agent has your project conventions on turn one. That first send then follows your Post-send navigation preferences like any other message — the same rule whether the session runs locally, in the cloud, or on one of your saved remotes (2026-10-18), so starting a cloud session does not park you on it.
  6. Or pre-fill the prompt. A few entry points launch a session with an initialPrompt already queued: the Super Prompts picker (Ctrl+Shift+K, only on the auto-created ~/Claude project), recipe and automation runs, and omniscio:// deep links. The prompt sends as soon as the spawn completes — you don't need to press Enter.

Walk away while it starts — you stay where you went. A new session only opens itself if you are still where you started it: same project, same selected item, same screen. Starting one can take a while — a Cloud session especially, which can spend seconds to minutes before it exists — and if you click into another session, open Settings or switch screens in the meantime, the new session simply appears in the sidebar and your screen stays put. A paste you make there lands where you are, not in the starting session. The same holds for buttons that start and open a session for you (notes, the daily digest's feature ideas, automation presets, the codebase-stats fix, canvas AI builds, "Build this now", Clean Room on a phone). Stay put and you land in the new session exactly as before.

The welcome heading changes from session to session. A brand-new session greets you with a heading above the setup card. Instead of always reading "What are we building?", it draws from 24 built-in lines (translated into every app language), picked at random, and the same line will not come back until about 16 others have shown on this computer, even after a restart. In a project with at least three sessions you opened yourself in the last 30 days (crew and agent sessions never count), lines written for that project join the mix, showing about as often as any built-in line. To write those, Omniscio occasionally (at most once a day per project, only after new work there, and only for projects you open) asks your low-cost Utility AI model to read recent session titles and the start of each opening message, and keeps only short, plain, sentence-case lines of at most 40 characters with no names, numbers or hype words like "tame" or "crush". Each session picks its heading once and keeps it, the heading never waits on the AI, and the lines follow your app language. The spend shows as Welcome Headlines under Stats → Spend. Turn it off under Settings → Sessions → Project-aware welcome headlines; off means no AI call and the built-in lines only. Rules: project-hero-slogans-contract.md.

Picking a tool. The in-session chooser is organized as a Harness → Provider → Model → Thinking picker: you pick the tool (the AI harness) first; under Claude Code a Provider dropdown picks the brain, then a Model within it, then a Thinking / reasoning level if that model has one — each dropdown only offers what the previous pick makes available. All of it is one shared control, the session launcher: on the New Session screen and in a running session's header it stays open, and in dialogs and other settings screens it is a single button showing the current engine and model that opens the same setup in a pop-up. On the collapsed pill that first picker is labeled Harness (so it reads e.g. "Harness Claude Code"), matching the muted label style of the Model and Thinking pills beside it. (Settings still calls these your tools — "Tools in the picker", "Default tool" — so tool and harness are the same thing here.) A tool usually maps one-to-one to a provider (Codex, Gemini, Cursor, OpenCode, Pi, …), but "Claude Code" groups several: the native Claude engine plus the Anthropic-compatible vendors that ARE the Claude binary pointed at a different endpoint (DeepSeek, Kimi). So Claude Code → DeepSeek is the same harness, a different brain.

A tool you have not set up yet still shows in the Harness list, greyed with a short reason ("Install", "Add key", "Set up"). Clicking it opens Settings at the exact row that fixes it — in the main window, including when you are picking from Quick Launch.

By default every session uses Claude, and the New Session button launches a Claude session in one tap. The other tools are already available: Show alternative AI providers (Settings → Accounts) is on by default, so pick the tool from inside the freshly-created session before you send the first message (see the next paragraph) — and turn that setting off if you would rather see Claude only. On desktop the launch button itself also carries a tool menu.

Customize the list, set a default, or hide the picker entirely. Settings → Accounts lets you tailor the picker to how you work:

  • Tools in the picker — a checklist of which tools appear in the chooser (Claude Code is always shown — it's the guaranteed-available engine). Hide the ones you never use to keep the list short.
  • Default tool / model / thinking — the global default a new session starts on (also settable per-project via edit-a-project.md, or straight from a fresh session. For model, thinking, and provider / harness alike: a Project or Session badge on the pill tells you at a glance when the current value isn't your plain global default, and picking something other than your current default surfaces a one-line "Save as default" banner just below the pickers — click it for a scope menu tailored to what changed, spelled out below and in full under "How it works" on part 2.)
  • "Always use my default" — when on, the picker is hidden and every new session just uses your default. The empty session shows a one-line "This session uses your default tool & model" with a "Choose for this session" button that reveals the full picker for that one session if you ever need to override.

Once you're inside a brand-new session — on desktop or mobile — you can pick its tool/model/thinking before sending. A brand-new session opens on a welcome screen: the Omniscio orb (it swirls while you are using the window and stays still if you've asked for less motion, turned the Animated logo off, or are in Low Power Mode — on Safari and iPhones it is always the still logo), the heading "What are we building?" in the brand gradient with a thin line under it, a line naming the project the session is in, and a framed "Session setup" card in the main panel holding the launch-config pickers (Tool picker plus Model + reasoning-effort pickers for the engines that offer them — see below). The card only appears when the pickers are in it. Click or tap to pick Codex, Gemini, or another enabled tool — the choice is remembered instantly and nothing actually starts up yet; it's applied in one step when you send your first message, so you can flip between tools freely. The pickers disappear once you send the first message, because the choices lock in then, and the header shows a small static provider badge instead. (If you pick something but never send, the choice is simply forgotten.) You can set a per-project default in edit-a-project.md. ("Always use my default", above, hides this whole block behind the one-tap "Choose for this session" reveal.)

On a phone, tapping the message box opens the soft keyboard, which shrinks the screen. The launch-config pickers scroll into view just above the keyboard so they stay reachable, not hidden behind it, while you type your first message.

Pick the model — and, on some engines, the reasoning effort. In those same launch-config pickers, a fresh session shows a Model picker for every engine that offers a choice, plus a second picker (Thinking on Claude, Reasoning effort on Codex) where the engine has one:

  • Claude — Model: the current lineup (Fable 5.1, Fable 5, Opus 5.5, Opus 5, Sonnet 5.5, Sonnet 5, Haiku 5.5, Haiku 4.5) shows at the top; the older versions (Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 4.6, Sonnet 4.5) tuck behind an "Older versions" row you expand in place — nothing is removed, every model stays pickable (and if a session is already running on an older one, the row opens expanded so you still see your pick). Plus Thinking (Auto / Low / Medium / High / Max). One exception to “nothing is removed”: a model that needs a newer Claude Code than you have installed is hidden from the list, and a single grey line takes its place naming the version it needs — e.g. “Claude Fable 5.1 needs Claude Code 2.1.251+ (you have 2.1.236)”. Nothing is lost: it reappears on its own the moment you update Claude Code (Settings → Connected Tools). It is hidden because the installed Claude Code doesn’t know that model id, so a session started on it would fail on every single turn with nothing on screen explaining why. If Omniscio can’t read your Claude Code version at all, it hides nothing.
  • Codex — Model (GPT-6.1 Sol — the default, runs on a ChatGPT-plan login / GPT-6 Astra / GPT-6 Sol / GPT-6 Luna / GPT-5.6 Sol / GPT-5.6 Terra / GPT-5.6 Luna / GPT-5.5) + Reasoning effort (Low / Medium / High / Extra High / Max / Ultra).
  • DeepSeek — Model (DeepSeek V4 Flash / V4 Pro / V4 Flash Vision — experimental, image input). Gemini — Model (3.6 Flash — the default / 3.5 Flash / 3.5 Flash-Lite / 3.1 Pro / 2.5 Flash).
  • Kimi — Model (Kimi K3 + Kimi K2.7 Code). Cursor — Model (a curated 10-model list across the Anthropic / OpenAI / Gemini / Grok families plus Cursor's own Composer and Auto; the model picker doubles as the reasoning-effort picker, since Cursor bakes effort into the model id — see cursor-provider.md).
  • OpenCode — Model (Claude Sonnet 4.5, plus GPT-4o / Kimi K2 / DeepSeek via OpenRouter). Pi — Model (Claude Sonnet 4.5 / GPT-4o / Gemini 2.5 Pro / Kimi K2 — Pi is model-agnostic and runs whichever you've configured a key for). Both now take a per-session model pick (your choice wins over the global OpenCode/Pi model setting); previously they only followed that one global setting.
  • Anti-Gravity — a model picker with the models your Google plan offers, plus an effort picker once a model is chosen (antigravity-provider.md).
  • Hermes — no model picker (it runs a model-agnostic local CLI), so the block shows just the tool chooser. Hermes is a first-class pickable tool, so it appears in the Tool chooser alongside the others.

Under Claude Code, the brains it spans — Claude / DeepSeek / Kimi / GLM / MiniMax — are listed in a separate Provider dropdown, each shown with its brand icon. The Model dropdown then shows only the chosen provider's models (a flat list — no company headings, since it's single-provider). Resellers (DeepInfra, RunInfra, InferX) are never listed as a provider and their copies of these models never appear; which company serves a GLM, DeepSeek, Kimi or MiniMax model, and who pays, is that family's supply list. See model-vendors.md.

They behave exactly like the provider chooser: editable only before your first message (each pick is staged locally and applied when you send), then locked in. The pill names the model the session will actually use — e.g. "Gemini 3.6 Flash", "Opus 4.8" — whether that's the inherited default or a pick of your own. To see whether it's the default, open the dropdown: the "Use default (…)" row is highlighted and marked Current — so "default" lives in the menu, not as clutter on the collapsed pill. Click to pick a model for this session, or Use default to clear the override and inherit again. The dropdown rows are clean single-tap picks (just like the Thinking menu beside it). To make a model your standing default, pick it for this session and use the "Save as default" banner below the pickers. There's no separate "clear without replacing" action in the session picker — to revert a project back to inheriting the engine-wide default, clear its default model field in edit-a-project.md instead. (On the built-in virtual projects, which can't carry their own default, only the engine-wide row shows.) After the first message a session you customized keeps a small read-only badge in the header — the engine's logo plus the model name (e.g. the Claude mark + "Claude Fable 5"; for non-Claude engines the provider badge already carries the logo, so the pill shows just the model name — the word "Model" is no longer shown) — so you can see what it's running. A Claude session you never picked a model for shows it too: once the engine starts, its own report of the model it is running is stored on the session, so you always see what a running session is really using, not only when you chose it. Only a session whose engine has not yet reported keeps a bare header. For Claude the precedence is this session's pick → the project's default → your global default (Settings → Sessions → Default engine & model — the same Session Launcher, always open — sets the global default for every engine, and edit-a-project.md sets a per-project default); other engines resolve this session's pick → that engine's own default ("Make it my default" writes that per-engine default; Gemini/Codex/Cursor ship with a sensible one seeded so the picker always names a model). Each engine reads only its own default — non-Claude sessions never inherit Claude's model list.

Thinking / reasoning effort inherits the same way — and can default per model. The Thinking picker (Claude) / Reasoning-effort picker (Codex) resolves a default just like the model does: this session's pick → the project's default → the per-model default → your single global Thinking Level (Codex has no single global, so its per-model default is the lowest layer). Thinking's same "Save as default" banner covers the fullest set of scopes when it appears: This model sets the level for that model everywhere (so bumping Opus to Max never touches Haiku); All (engine) sessions / All (harness) sessions set it whenever you use that engine / harness (named for the actual one, e.g. "All Codex sessions" / "All Claude Code sessions"); Only this project for this project only; Everywhere is Claude's single flat level. Promoting to Only this project or broader clears any narrower shadow so the new default takes effect right away. (On a single-engine tool like Codex, "This harness" is dropped — it would duplicate "This provider" — and Codex has no flat "Everywhere" thinking.) You can still set per-model defaults in bulk in Settings → Session → Per-model thinking level so, e.g., Opus starts on Max and Haiku on Low without you setting it each time — a level a model's engine doesn't support is validated out, so it never reaches a session. Full behavior: per-model-thinking-level.md.

Save a setup as a preset and pick it in one click. The Preset button at the top right of the Session setup card holds your saved setups. Pick one and every chip changes at once — harness and provider, model, thinking level, where it runs (Local or Cloud), and MCP servers. Nothing starts until you send your first message, exactly as if you had clicked each chip yourself.

  • Open it by clicking Preset, or press Alt+P (rebindable in Settings → Keybindings). With the menu open, 1–9 apply the first nine presets.
  • Save one with Save current setup as preset… — give it a name and, if you like, an icon (an emoji or a symbol). Turn on Use this for every new session to make it your default. Saving under a name you already use asks before replacing it.
  • Each row shows the preset's icon, name and a one-line summary ("Opus 5.5 · High thinking · Cloud"), a check beside the name of the one in use, and a Default badge. The ⋯ on a row offers Edit preset…, Make default (or Stop using as default), Move up, Move down, and Delete — a delete can be undone from the toast.
  • Put the presets in your own order. Hold a row for a moment and drag it up or down — the order is saved, and it is also the order the 1–9 keys follow. Move up / Move down in the ⋯ do the same without dragging, and a normal click still just applies the preset.
  • Edit one from Edit preset…: change its name, its icon and whether it is used for every new session. Tick Also save the chips I have now to also store the model, thinking level, run location and MCP choice you have picked right now into that preset — leave it unticked and the preset keeps applying exactly what it did before.
  • Tweak after picking. Change any chip and the button shows edited, with a bar offering Reset (put the preset's picks back), Save as new (keep the original), and Update preset (save your changes into it — it stays your default if it was).
  • The default preset fills in each new blank session once, before you pick anything. It never overrides a pick you already made, and it never picks Cloud on the phone's new-session screen.
  • A Hub's own defaults win. If the Hub you are starting in has its own default saved — the engine, the model, the thinking level, or where its sessions run — the default preset leaves that Hub alone, so new sessions there start the way the Hub says. Picking a preset by hand still works in that Hub, and a Hub with no defaults of its own keeps filling in from the default preset as before.
  • What it won't do. A preset whose AI isn't set up yet (or whose custom provider was removed) is greyed with the reason and can't be picked. A Cloud preset only applies where Cloud is actually available to this session — otherwise nothing changes and a message tells you, so a Cloud preset can never quietly run on your computer; the Run chip's own greyed row says why. A preset whose model was later retired uses that engine's default model and says so. On a paired phone, a preset sets everything except MCP servers, which a phone isn't allowed to change.
  • Turn it off in Settings → Lab → Session Setup Presets. Presets are saved with your settings, so they survive restarts, and are readable over the CLI as sessionSetupPresets / defaultSessionSetupPresetId.

Pick the MCP servers — at launch. That same block also carries an "MCP servers" button next to the model/thinking pickers. Click it to choose which MCP servers this session gets (Default / On / Off per server) before you send the first message — the choice applies on the session's first launch. It opens the same editor as the session's ⋯ menu → MCP servers, just up front. The button appears on real projects only (it's hidden on virtual/inbox projects, where MCP doesn't apply). Full behavior: mcp-servers.md.

What happens if no account exists yet: the spawn returns an error and a system message in the chat says you need to add a Claude account before sessions can run. Open Settings → Accounts and use Log In with Anthropic to add one. See add-a-claude-account.md.

What happens when every account is at its rate limit: the session row shows the amber "Needs You" / "Rate Limited" sub-state, the chat surfaces a banner with the absolute reset time, and a sidebar-wide "All accounts are at their usage limit" banner appears at the top of the Sessions panel. Omniscio auto-resumes when the first account regains capacity, so you can usually leave the session alone. See account-pool.md and session-stuck-in-needs-you.md.

What happens if the project's folder no longer exists on disk: the session lands in error and a red "Project folder is missing" banner offers a "Recreate Folder" button. See project-folder-missing.md.

What happens if a launch fails: an error toast appears carrying a Try again button that re-runs the same launch for you. When the app can tell what went wrong, the toast says so — no account yet, the project folder moved, the Claude Code binary path, a permission failure, a full disk, a remote/SSH problem, a busy system, a busy database — and the right move is to fix that cause and press Try again; many other launch failures are simply transient and clear on a second try. The button is offered on both launch paths — the + button and Ctrl+T — because they run the same launch and the same error handling. Where to look when the toast names no cause covers the rest.

When the toast names no cause

Not every failure classifies. When the app cannot attribute the failure to anything it recognises, the toast reads:

Couldn't launch the session — please try again. If it keeps happening, open Settings → Diagnostics and send the diagnostic bundle with your report.

That sentence is deliberate: it does not guess at a cause it does not know, and it points at the two things that do help — a retry, and the evidence. Press Try again once; if it fails again, open Settings → Diagnostics, click Export diagnostic bundle, and attach the ZIP to a bug report (see logs-and-debugging.md). The reason the app could not classify is written to the log, which that bundle carries. This is the text most launch failures actually show, so a report that quotes it is expected rather than unusual.

Two more launch-time messages that do name their own cause:

  • "The system was busy and the session couldn't start — please try again." The computer was momentarily out of process slots (too many processes starting at once, or extremely low memory). Nothing is wrong with the project or your account; retry, and if it repeats, close some running sessions first.
  • "The app's database on this computer was busy, so the session couldn't start — please try again." A local write was momentarily blocked. Retry — this one clears on its own.

"Sessions are starting slower than usual" (spawn queue backed up)

Under a burst of launches Omniscio paces new sessions so the computer stays responsive. If the queue backs up it raises a single inbox card with that title, telling you how many launches are waiting. It is not caused by how many sessions you have running, it needs nothing from you, and it clears itself as sessions finish starting. Try again is not the answer here — the launch is already queued.

When the session can't be isolated (worktree creation fails)

With Isolate by default on, launching a session creates a git worktree first. Creating one can fail, and when the failure looks retryable the app retries on its own — up to three attempts with a short backoff — before giving up. What you see after that depends on one setting:

  • Require worktree isolation is OFF — the session still never runs in your project folder: the start step tries again to give it a working folder of its own, and if none can be made the session waits instead of starting, with a notice saying it never got a working folder of its own. The older warning "This session couldn't be isolated in its own worktree and is running directly in your project folder" is shown only when the session really is about to run there. See session-isolation.md.
  • Require worktree isolation is ON — the app will not put the session in your real project folder. It copies the project into the fallback directory instead (a shallow git clone, or a plain file copy if the clone fails), and the session runs there. If no fallback directory is configured, or another fallback copy is already running, the session lands in error with a message telling you to configure a fallback directory in Settings or turn Require worktree isolation off.

When a launch finally gives up on getting a working folder, its message now tells you what this project's worktree pool held at that moment — for example "0 ready and 27 leased of 27". A busy project usually looks like that: the folders it keeps are out with other sessions. The counts are added to the refusal the app already gives; they never cause one, so a launch that would have got a folder by waiting still waits.

Repeated failures also raise the inbox card "Workspace creation keeps failing", naming the most recent problem — that is the signal to look, rather than a fact about this one launch.

The reasons a create is refused, and what each one means for you:

What was in the way What to do
The branch is already in use — another worktree has it checked out Finish or archive the session holding that worktree, or launch with a different branch/session name
The directory already exists and isn't yours to reuse Pick a different session name, or retire the stale worktree that owns the folder
Protected branch — the target is master / main An integration branch is never a worktree target; pick a working branch
Cap reached — too many worktrees exist Retire finished worktrees from the Work in Flight screen, then retry
Git is unavailable — the check couldn't run (a spawn fault or a busy drive) Transient; retry. If it keeps happening, check that git runs in a terminal for that project
Not enough disk space Free space on the drive the worktrees live on, then retry
The repository's git store is lost or being restored Wait for the restore to finish — creating worktrees is refused on purpose until it does

What happens if the app closes while a new session is starting: the request survives. Once Omniscio has accepted your New Session click, closing or losing the app before the process came up does not lose it — on the next start Omniscio brings that session up again, with the opening message you had already given it if there was one, or as an empty session if there wasn't. It is never turned into a broken/error session while it waits, and it is never resumed with a generic "please continue" in place of what you asked for. A request that has not started is kept until it starts or you cancel it — it is not dropped for being old. See durable-new-session-request-contract.md.

Choosing the model from an inbox card's Start session

The Start session dialog on an inbox card — an alert, the weekly summary, the daily digest, a scheduled message, a cron failure, a Help Desk ticket — offers the same choices as a new session, but keeps them out of the way. Under the prompt sits one small launcher button showing the engine the session will use. Click it and the full New Session setup opens in a pop-up: harness, provider, model, thinking, run location and MCP servers, each already on that repo's defaults. Anything you changed stays set after you close it, and a small dot on the button reminds you. Leave it alone and the session starts exactly as it always did, on the repo's defaults and on this computer. Changing the repo in the dialog clears earlier choices, because a model picked for one repo's engine may not suit another's. Every dialog that chooses what runs a session uses this same launcher button (the New Session screen and a running session's header keep it open instead of behind a button); the pieces are SessionLauncher and useProjectStartConfig, and the rules are in session-launcher-contract.md and alert-start-session-optimistic-contract.md.

Which hub a session starts in when you don’t pick one

Most entry points use the hub you are already in, and the Start session button on an alert resolves a smarter one — the repo the alert names, then your Start alert sessions in setting, then an automatic Omniscio checkout, and ~/Claude last. That resolution, and the dialogs that deliberately keep the plain Claude default, have their own page: alert-session-hub.md.

Ctrl+T from the inbox starts the session in the hub of the card you are looking at. On a session card that is the session's hub; on an alert card — an Overseer's message, say — it is the hub the card is filed under in the inbox, else the hub of the session that sent it. A card filed somewhere that cannot host sessions leaves Ctrl+T doing nothing, as before. The lookup is resolveActiveProjectId in navigation.ts.

Naming the worktree branch

When the Start session dialog shows Base branch, it also has an optional Worktree branch name box and a Suggest (paid AI) button that writes a name from your first message and shows what it cost. Leave it empty for the usual name. See worktree-branch-naming.md.

Last verified 2026-11-03