Omniscio

Agent Email

Give your agent its own real email address on a shared domain — claiming a name, deciding who may start a session by writing in, holding blocked senders for review, how mail flows in and out, and the quiet arrival notice it raises in your inbox.

On this page

What it is

Give your agent its own real email address. People (or other systems) can email it to start or continue a session, and your agent can reply back out — powered by the Cloudflare-backed email service Omniscio runs.

Who the reply goes to. Back to the person who wrote in, from your agent address — including when that person is you. Emailing your own agent from your account address gets you its answer in your inbox like anyone else's, even if you have a Help Desk ticket open: a customer's answer keeps going onto their ticket, yours does not. One exception on purpose — a message you send as support still goes through the ticket.

What the reply contains. The reply is the agent's final answer to that email, nothing else. If another agent messages the session, or you type into it, after the email turn ends, that later exchange never goes out to the sender. Formatting the agent writes (bold, lists, links) arrives as a properly formatted email, with a plain-text copy alongside for mail apps that want one.

The domain half of the address is server config, not a constant in the app (app_config/agent_email): the panel asks the desktop for it, so the pre-claim preview always shows the real address. On the hosted install that domain is omnisciomail.com.

Where to find it

Where it lives

Agent Email is a sidebar entry nested under Omniscio → Agent Tools (alongside CLI Tools, Skills, MCP Servers, and API Keys). Click the Agent Email row to open its panel.

It is available to everyone and the row is there from the first launch — there is no Lab toggle to reveal it. To hide it, switch Agent Email off in the sidebar item picker. The slim Settings → Agent Email screen is admin-only, and its single on/off toggle neither shows the row nor affects receiving; customers set up through the sidebar wizard, and all claiming and managing happens in the sidebar panel.

Agent Email is the primary, zero-setup way to receive email into Omniscio. The older "Email Inbound" path (forward mail in from your own AgentMail inbox) still exists, but is now framed as an "Advanced — use your own inbox" option under Settings → Email & Summaries — the same capability, for people who want to bring their own inbox.

Setting it up (a guided three-step flow)

Open Agent Tools → Agent Email. Before you have an address the panel walks you through three steps, one thing on each:

Step 1 — Choose your address. Type the name you want — the part before the @. As you type, a live preview shows the full address, e.g. your-agent → your-agent@omnisciomail.com. The preview is exactly what you'll get: letters, numbers, and hyphens only (spaces/punctuation become hyphens, everything lowercases). The domain half is read from the mail service rather than hardcoded, so the preview cannot advertise a domain the service does not use. Validation is instant — the name must be at least 3 characters and not reserved. Reserved covers role words (admin, support, billing, security, no-reply, …), well-known brands (paypal, apple, google, … — also as one word of a longer name, so paypal-billing is refused but pineapple is fine), and anything containing omniscio. Lookalike spellings count too: supp0rt, suport and pay-pal are refused the same way. The Claim this address button stays disabled with a short reason until the name is valid, and the server enforces the same rule (only an Omniscio owner/admin may hold a reserved name). The address is globally unique across everyone on the shared domain: if someone already took that name — or it is still held after its previous owner gave it up (see below) — you get a clean "That name is already taken — please choose another" and pick a different one (it does not silently append random characters). Claiming is idempotent: one address per account. An account may hold a small number of them (five at most) — the server counts what you already hold inside the same transaction that creates a new address, so a script cannot take an unlimited number of names on the shared domain.

Step 2 — Send yourself a test. The address is yours; this step proves it works. Send a test email sends a real message from your agent's address to your own account inbox — the recipient is resolved on the desktop side from your signed-in account, so it can only ever email you, never a stranger. Check your inbox (and spam): replying to that message starts a session, so you can watch the whole round trip. Skip for now moves on without sending one.

Step 3 — Choose who can write in. Only me / People I approve / Anyone, explained in plain words (see below). Finish setup hands over to the management screen.

You must be signed in to your Omniscio account (Google) to claim — the address is tied to your account. When signed out, the panel shows a real Sign in with Google button right there (the same Google sign-in the app's sign-in gate uses) on the desktop, or a "sign in on your computer" note on the web/mobile client (the OAuth opens a desktop browser and can't be completed from a phone) — never a dead-end pointer to go find another screen.

When Omniscio takes an address back

The Terms of Service (§15) reserve the right to suspend or reclaim an address. In practice:

  • Suspended — an Omniscio admin (or the automatic spam-complaint limit) stops an address: it cannot send, and mail to it bounces, but you still hold the name. Restoring it brings it back unchanged. Sending shows why: spam reports, a support suspension, or "no longer on your account". You get an email either way.
  • Taken back — for abuse, impersonation, a trademark claim, or other reasons. The address leaves your account and you are emailed. The name is held for 12 months; a name taken back for impersonation is never handed out again.
  • Unused (free accounts only) — an address with no use for 12 months gets two warning emails over 30 days, is then paused, and is released 30 days after that (held 12 months, and you can still claim it back). Sending or receiving mail, or simply having Omniscio open with Agent Email on (it checks in once a day), counts as use and cancels the process. Paid, admin and support addresses are never reclaimed this way.
  • Deleting your account releases its address into the same 12-month hold, with no link back to you.

Admins act from Settings → User Management → a user's ⋯ menu → Agent Email (Suspend Address / Restore Address / Take Back… with a reason), or from the control server (POST /admin/users/agent-email/:action). Taking a name back for Impersonation asks for the evidence it rests on — a ticket, a link or the complaint — and Take Back stays disabled until something is typed; over the control server that is an evidence field in the body. The same menu's Lift Name Block… undoes an impersonation block: type the blocked address or name, and it tells you whether a block was actually lifted.

Managing it afterwards

Once you hold an address, the same panel is the management screen, and everything about the address lives there in one place:

  • Your address, with a Copy button, and Change or release address beneath it.
  • Receiving — the on/off switch for incoming mail.
  • Who can write in — the same three-way control as step 3, plus your approved senders.
  • Mail for you — one-step ways into held mail and Spam, so neither is somewhere you have to remember to look.
  • Send a test email — the connectivity check, available any time.
  • Where email sessions open and Notify me in the inbox — the session destination and the arrival notice.
  • Public support address — the separate public door, always shown here so a first one can be set up (the guided setup only shows it once one already exists).

Changing or releasing your address

There is no in-place rename. Change or release address releases the address, and you then claim a new name — that is how you "change" it. Because releasing is irreversible it asks you to type RELEASE to confirm; then the address stops working at once and any conversation in progress ends. The released name is held for 12 months so nobody else receives your mail: mail to it bounces, nobody else can claim it, and only you can take it back during that time. You can change your address at most 3 times a day.

Who can write in (receiving setup)

Receiving turns on the moment you claim an address — no restart, no extra step. The management screen has a plain Receiving on/off switch (on by default) so you can pause incoming mail at any time and turn it back on later, all live. Pausing keeps your address; it just stops new mail from starting sessions. (This switch is honest — it actually controls the inbound checker, unlike the admin-only feature toggle, which changes nothing a customer can see.)

The "Who can write in" control decides who may start a NEW session by emailing the address. It is the SAME control in both places you meet it — step 3 of the setup and the management screen — so the two can never describe the rule differently. It defaults to the safest choice:

  • Only me (default) — only mail from your own account email starts a session. The control names exactly which address that is.
  • People I approve — add specific email addresses; only those (plus you) get through.
  • Anyone — open intake. Anyone who learns the address can start a session (the AI safety screen still applies, and so does the spam filter if you have turned it on). Shown with a "keep this restricted" caution.

It also closes, in plain words, with what the choice actually does — see the note below.

Replies from the people in the conversation get through. The policy gates only brand-new conversations — a reply from someone who is part of a thread your agent is in is always accepted, whatever the setting, so the agent can hold a back-and-forth it began. "Part of it" means someone who wrote on the thread OR someone the agent wrote to, which is what makes an answer to a "we have your report" note continue the conversation rather than look like a stranger. Someone who merely knows the thread — a thread's identifier travels in the copy of the mail every recipient receives — is treated as what they are: a new correspondent, subject to the setting above and to the spam filter. That holds even after you archive the session behind it: archiving says you are done with that conversation, not that the person is a stranger, so a participant's next reply starts a fresh session rather than being held for review. Each inbound email that starts a session uses your AI usage like any other session (the panel says so).

What this control does, and what it does not do. For "Only me" and "People I approve", a message only counts if the sending domain proves it really came from there — it has to pass email authentication — so a forged From is refused, not admitted on spelling. What it never does is judge the mail itself: it decides who can START a conversation, and email is still checked by the AI safety screen before a session runs — except for the two narrow cases on Email inbound prescreen (a known sender's mail once the screen's daily budget is spent, and the authenticated bug-report fast path) — with sessions sandboxed besides. The UI says exactly this, in plain words, on both screens that show the control.

Websites your assistant may reach

Next to "Who can write in" is the list of sites a session started by an email may reach. It holds one entry out of the box — a site the owner named — and you can change it, or empty it.

  • Only the sites on the list are reachable, and only over https. An entry covers the site itself and its real subdomains (vimeo.com also allows player.vimeo.com), never a look-alike (vimeo.com.evil.com is a different site).
  • An empty list means no internet access at all beyond the reply the agent sends back. That is a valid and stricter choice; nothing breaks in the panel.
  • This app, and anything on your own network, is never reachable — even if the list names it. The list cannot be used as a way back into Omniscio.
  • It is a person's setting: an agent cannot add a site to it, and it cannot be changed over the command-line control server. Editing it in the panel is the only way.

A session started by an email also works under a set of restrictions that have nothing to do with this list: it reads inside its own workspace plus any attachments the email delivered, it cannot touch credentials (.env, private keys, the secrets store) wherever they live, and its shell is read-only — it can look, not change. It writes only in the Agent Email workspace: if you have pointed incoming email at one of your real projects, the session can read that project to answer a question about it but cannot change a single file in it. It is also launched with its own settings locked down, so those rules hold whatever your personal or project settings allow.

Investigations started by the bug-report machinery are not restricted this way — they exist to set up a worktree, run the tests and commit a fix — and neither is mail you send from your own authenticated address. A Help Desk ticket investigation, which also arrives from public mail, is still on the unrestricted side today; it is the one route here that is not yet narrowed.

How it behaves

Held for review (blocked senders — and the safety screen — are captured, never dropped)

When someone the policy DOESN'T allow (a stranger under "Only me") emails your address, their message is not thrown away — it is held for your review. The same tray also catches any email, on any route, that the built-in safety screen flagged or could not check; those rows carry a "Held by safety screen" badge, the screen's plain-language reason, and which route the mail came in on, so you can tell the two kinds of hold apart at a glance. An email the spam filter caught is held too, but it waits in the Inbox's Spam list instead of here.

The "Held for review" tab in the Agent Email panel lists every held email — sender, subject, and a short preview for a blocked-sender row, plus the badge and reason for a safety-screen row — so you can see exactly what's waiting and decide, instead of the mail vanishing. The queue stays a list down the left; picking one opens that email in the pane beside it, the way a mail app works. A single quiet inbox notice tells you how many blocked-sender emails are waiting (it updates in place — never one ping per email), with a "Review emails" button that opens that Held-for-review tab in one click — on your phone as well as the desktop. Safety-screen holds get their OWN separate "Emails held by the safety screen" card with a "Review held emails" button that opens a standalone review dialog listing just those, laid out the same way — the list with the email beside it, or one at a time on a phone — and because that dialog talks to the held-email list directly, it works even with the Agent Email panel switched off. A message that fails sender authentication (DMARC) — a possible spoofed "from yourself" — is still captured but shown with an "Unverified" badge so it is never mistaken for the real sender.

This is the honest middle ground between "Only me" (which used to silently drop everyone else) and "Anyone" (open intake): strangers wait in a review tray you clear, and nothing is ever lost.

When a spending limit stops a spawn (the mail waits, it is not lost)

An inbound message starts a paid session, so your daily spend caps apply to it exactly as they do to a session you start yourself. If a cap refuses the spawn, the email is deferred rather than consumed: nothing is marked as read, so the poller keeps handing the same message back and the session starts by itself as soon as the limit clears (or you raise it). The refusal is quiet — at most one log line per message per window, never an alert on every poll — so a capped inbox does not turn into a notification storm while you are away.

Reading and clearing the tray

Click a held email to open it in the pane beside the list and read the whole message, not just the preview line. On a phone the email takes the screen instead — one half at a time — and carries a Back control to return to the queue, which is also where you land once you have dealt with it. Two buttons then sit under the message:

  • Approve & start session — lets that email through. A session starts from it exactly as if the sender had been allowed all along, your agent works on it and replies by email, and the app jumps you straight to that session. The safety screen does not run a second time on a message you approved, since you've now looked at it yourself — which holds for a blocked-sender email exactly as for one the screen itself held. An email an AGENT approves over the command line is not you looking at it, so that one is still screened. From then on the conversation is a normal thread: their reply continues the same session and is never held again.
  • Dismiss — takes it off the list. For an ordinary blocked-sender hold, nothing is sent to the sender — deliberately, because replying "rejected" would tell a spammer the address is real and read by a person. A safety-screen hold is different: dismissing one asks you to confirm first, then emails the sender that their message couldn't be processed (and tells you if even that notice failed to send). Either way, the message itself is kept, not deleted, until you act.

Agents can only ask, never decide. If an agent working through the command line asks to release or to dismiss an email the safety screen held, it raises an approval card for you instead of doing it — the same as any other high-risk action. Nothing holding the app's own command-line key can release or drop a safety-screen hold except you. One exception, on dismissal only: an email the spam filter caught is refused outright to a command-line caller, with no card, because letting an agent clear a catch would hand it exactly the thing the filter exists to stop. Asking to release one still raises a card, and releasing it runs the safety screen before any session starts.

The "N waiting for review" notice updates itself after each decision and disappears once the tray is empty.

Two things worth knowing:

  • Attachments and reply headers come along. Approving replays the message as it originally arrived — its reply headers and any attachments, not just the text — so the resulting session sees what was actually held and its first reply threads correctly (an email held before this shipped may still replay without its attachments, since no copy of the original was kept for those older rows). The stored text is cut at 256 KB, so an unusually long body is held — and later released — cut at that length; attachments themselves are not shortened.
  • Approving works from the phone too. The review pane on a phone offers the same Approve & start session action as the desktop: it was previously hidden on the reasoning that approving spends money by spawning a session, but the phone already cold-starts paid sessions through Quick Launch, and what actually bounds a phone release is the tunnel's owner sign-in plus the desktop-approval device gate — both unchanged. A CLI caller, by contrast, still cannot release a safety-screen hold on its own.

Approving one email does not add the sender to your approved list — a new, unrelated email from them is held again. If you want someone through permanently, switch "Who can email it" to Approved senders and add their address.

Where each email goes (sorted once, before anything starts)

Every new email to your agent's address is sorted once, right after the spam filter and the safety screen have read it, and goes to exactly one place. Sorting costs nothing extra: the safety screen that already reads every email also says what kind of email it is.

What arrives Where it goes
Mail from a sender a session subscribed to Straight into that session
A customer bug report, feature request or question A Help Desk ticket — its investigation runs in the Omniscio project, not the Agent Email hub
Automated or vendor mail nobody subscribed to (codes, receipts, confirmations) The one Mail Room session
A thank-you on a conversation you already archived Kept in Held with a Thank-you badge — no session
Everything else, and every email from you A new session, exactly as before
  • Subscriptions. An agent that is about to sign up for something — and expects a code by email — can subscribe to that sender first. The sender's next email then goes straight into that session, even if your "who can write in" setting would otherwise hold it. It still passes the spam filter and the safety screen, it is never answered automatically, and a sender's follow-ups stop arriving the moment the subscription ends (7 days at most). A session started by an email can never subscribe, nobody can subscribe to you or to an approved sender, and a whole public mail provider (all of gmail.com) can't be subscribed to. Every active subscription is listed on the management screen under Listening for mail, with a Remove button.
  • The Mail Room. One standing session, locked down like any session a stranger's email starts. It reads each piece of automated mail and decides where it belongs. It can only hand an email to a session that recently emailed that sender's company — so a stranger's email can never be steered into one of your own working sessions — and otherwise it leaves the email as a card in your inbox with its note (the code, the link). The Mail Room never sends mail. If you archive it, the next notice simply starts a fresh one.
  • Thank-yous. A reply that only says thanks on a conversation you already closed no longer starts a session. It waits in the Held tab with a Thank-you badge; Approve & start session turns it into one if it needs an agent after all. It never counts toward the "waiting for review" badge.
  • The Emails tab shows where each email went with a small label (Notice, Thank-you, Subscribed, Support).
  • Fail-safe. If the sorting can't tell, or anything about it fails, the email starts a new session exactly as it did before this existed.

One address, several destinations (the + in your address)

Your agent's address takes a plus tag, the way a Gmail address does. Hand out you+invoices@… to a supplier, you+support@… to a customer, and keep you@… for yourself — all of them are the same address and the same mailbox, and you decide where each version's mail opens.

  • Set it up on the management screen, under Where email sessions open → Route mail by tag: one row per tag. Each row can name the project mail to it should open in, give the agent standing instructions for that mail, or both — then press Save tag.
  • A tag you have not listed changes nothing. Mail to you+anythingelse@… opens wherever you chose for the whole address, exactly as it does today. Nothing is ever lost to a tag you forgot to set up.
  • A tag never lets anyone past who can write in — unless you open that one tag. It cannot change who the email is from, and the sender has to pass the same checks as any other email. The one exception is a tag you deliberately open to anyone (below).
  • A tag only routes mail sent to your own address. Mail to your public support address keeps going to the Help Desk exactly as before, so nobody can guess a word and drop their mail into a project of yours.
  • If the sender drops the + word, the mail still arrives — it just opens where everything else does.
  • This works because the + word is part of the address, not a separate mailbox: nobody can claim you+invoices@… as their own name, and the word never appears as a second address you hold.

Plus aliases: sending, standing instructions, and opening one alias

Each + version of your address is an alias: a label on your one mailbox, never a second identity.

  • Replies keep the alias. When mail arrives at you+travel@…, the agent's reply goes out from you+travel@…, so the conversation stays on that alias. That holds for the automatic reply when a session finishes AND for your agent's own reply sent through POST /agent/email/send: if it names no alias, the app looks at the mail that session received from the person it is answering and uses the alias that mail arrived at. Naming an alias yourself always wins, and a message to someone who never wrote to that session goes from you@…. A few words can never be sent from — support, brand names, and lookalikes of them — so mail to you+support@… is answered from you@….
  • Your agent can send from an alias. POST /agent/email/send takes an optional alias (just the word, like "alias": "receipts"); the app builds you+receipts@… itself. A word that cannot be used, or an alias combined with identity: "support", is refused with a plain message.
  • Limits and complaints follow your address, not the alias. Your daily sending limit counts every alias together, a recipient who marked you@… as spam is never mailed from any of its aliases, and a complaint about an alias counts against you@….
  • Standing instructions (a routine). Give a tag instructions — for example "add the receipt total to my expenses sheet and reply with the amount" — and every new email to that alias starts a session with your instructions placed above the email. The email itself can never add to or change them, and that mail is never filed away as a notice or a thank-you or turned into a Help Desk ticket.
  • Anyone can write to this alias. A tag's switch opens that alias only to people outside your who-can-write-in list — useful for a newsletter or sign-up address. Your main address and every other alias stay exactly as locked as before. Strangers must still pass the spam filter, the safety screen and the sender check (their mail has to be genuinely from the domain it claims), and their session runs locked in Agent Email, never in one of your projects.
  • Only you change these. An agent — including one started by an email — cannot edit the tag list on its own; asking to raises your approval card.
  • Going live. The receiving side works as soon as the app updates. Sending from an alias needs the cloud sendEmail function deployed; until then, mail asked to go out from an alias goes out from you@… instead, and the app logs a warning once.

How mail flows

  • Inbound: mail sent to your agent address (on the shared mail domain) arrives via Cloudflare Email Routing → an email worker → a Firebase function that drops it into an inbound queue Mission Control picks up. The inbound checker runs whenever you have a claimed address AND the Receiving switch is on — claiming (or flipping the switch) starts/stops it immediately, with no restart. A message to a known address starts or continues a session; mail to a random/unknown address on the domain is rejected with a bounce by design. Before a NEW session spawns, the "who can write in" policy (above) is applied — a sender it blocks is held for your review (captured in full, not silently dropped — see "Held for review" below; no session, no reply is sent); a reply on an existing thread skips the check.
  • Outbound: your agent can reply in a thread it's already in, OR compose a brand-new email to anyone from its address (the latter via the POST /agent/email/send CLI route — the Omniscio-native replacement for a third-party outbound sender like AgentMail). Outbound has abuse guards — per-account daily limits, a distinct-recipient-per-day cap, no spoofing (the from is always your own agent address, set server-side), and auto-suppression of recipients that bounce or complain (to protect the shared domain's reputation).
  • The shared address is protected as a whole: every customer's agent mail leaves from the same domain, so no single account is allowed to exhaust it. Two of those protections can pause you: a brand-new free account may only email its own address for the first week (confirm your email address and the restriction lifts straight away), and if the service ever nears a whole-day safety ceiling, new sending pauses for everybody until midnight UTC. Neither one affects a reply to someone you already correspond with.
  • Mailing-list mail gets a one-click unsubscribe: a send marked as list mail (a Newsletter issue, for example) carries the standard unsubscribe headers, which most mail apps show as an Unsubscribe button next to the sender. The link is made by Omniscio's email service for that one recipient. When someone uses it, they stop getting list mail from you through Omniscio; ordinary one-to-one email to them still works, and other people's mail to them is not affected. The record keeps no email address, only a one-way code, for up to two years.
  • Plugins can schedule an issue: a plugin you allowed to send email (Newsletter, for example) can hand an issue and its readers to Omniscio's cloud with a send time, so it goes out on time even with your computer off, and the plugin can cancel it until then. Plugins may use at most 80% of your daily sending allowance (on the free plan, 80 emails and 20 new readers a day), and at most 500 a day each; if a limit stops an issue part-way, the rest goes out the next day and the plugin tells you. The issue and the readers' addresses stay in the cloud only until it is sent, then are deleted automatically.

When the agent's answer is held (a reply written for someone else)

One email in, one reply out. So before Omniscio mails anything back, it asks who the agent's finished turn was actually written for — and a turn can be written for an internal reader rather than the person who wrote in: a crew member's report back to a coordinator, a dev-pipeline gate report, an overseer status update, a mission summary. Those are real, finished pieces of writing, but mailing one to your correspondent would spend their single reply on text addressed to somebody else.

Omniscio holds it instead, and tells you — a card in your inbox: "A reply is being held, and someone is still waiting." It names the session, says plainly that the person who wrote in has been sent nothing, and stays there until a reply actually reaches them; it clears itself the moment one goes out. One card per session, so a second correspondent waiting on a second agent does not get hidden behind the first card you dismiss. Nothing is lost by the hold: the agent's next finished turn that IS written for the correspondent goes out normally.

An email the agent writes by hand counts as the reply. When a session emails the person itself (its own send, or a message added to that person's Help Desk ticket), Omniscio marks everything that person sent the session as answered and clears the card — so a correspondent the agent already answered is never shown as still waiting, and is never mailed a second, stray reply later. A newsletter-style mailing does not count, and an email to someone else leaves this person's reply owed.

A turn that only paused — the agent stopped to wait on something and has not finished — sends nothing and raises no card: no answer is owed yet, and the reply slot is deliberately left untouched so the real answer can go out when the turn actually finishes.

Your agent's answer is never held up by a wait it didn't ask for. That "it hasn't finished" rule is what keeps a half-finished note out of your correspondent's inbox, so it only holds when the agent itself says it is waiting to be checked on — its standard "I'm waiting on a background process to finish, I'll continue once it completes" sign-off, or the same sentence with a timeframe on it. A turn that merely reads like waiting — a friendly "I'm online and standing by" at the end of a complete answer, or "on hold until…" in passing — is answered straight away instead. Without that distinction a finished answer could be parked for the whole wait window and then set aside as if nothing had been written, so the person who wrote in heard nothing back and nothing in the app said a reply was owed.

Seeing your mail + arrival alerts

The Agent Email panel's Emails tab is a real inbox view: each row shows the sender, the subject, a short preview of the message, and the date it arrived (older emails that predate this fall back gracefully to the session name). Click a row to open the session it started.

When an email arrives and starts or continues a session, a quiet entry also appears in your main Omniscio inbox — "New email from <sender>" with the subject and the full message — so you can read the email right there instead of opening the session to find out what it said. Quoted reply history and signatures are stripped, and very long mail is capped, but the message itself arrives whole. Lines the sender's mail program wrapped are flowed back into full paragraphs, so a wrapped paragraph reads as one line, while the lines the sender typed — a greeting, a sign-off under a finished sentence, a list, a forwarded message's header, a pasted log or code block — keep their own line; mail that was never wrapped is normally left exactly as sent. It is a calm inbox row, not an OS pop-up or a sound, and it links straight to the session. Bug reports / feedback emails do not raise it (they have their own triage flow). A "Notify me in the inbox" switch in the panel turns it off (default on), and your global notification setting still gates it.

Reading a conversation

A conversation is drawn by who sent what, so someone else's words are never mistaken for yours:

  • Mail from the other person arrives on the right, inside the same indented violet channel Omniscio uses for messages agents send each other, headed "emailed by <sender>" with the subject underneath. It is not drawn as one of your own messages.
  • Your agent's own messages stay ordinary agent messages, on the left and unchanged.
  • A reply that actually went out as email is not repeated in the session: it shows one line — "Emailed <recipient>" — and clicking it opens the full exchange. That line appears only when Omniscio can point at the record of the send, so it never claims a delivery that did not happen.
  • Anything you type keeps the accent-coloured bubble, so the accent colour always means you.

An email conversation opens on its Email tab — the mail both ways and nothing else, with a line naming the address as your agent's and stating that a reply on that thread reaches your agent, not a person. The Session tab beside it is the full working transcript: the agent's thinking, its tool calls, and everything else.

The developer-facing reference — every route, file and setting behind the feature — is on part 2.

The other built-in Agent Tools integrations are described in Agent tools, and the bearer-token contract behind every route above lives in CLI Control. An agent that wants to email someone other than you is the same command-line pattern Agent-driven sessions uses to drive a session over HTTP. Bug reports and feedback emails deliberately take a different path (Bug report intake) and never raise the arrival notice described above. What the safety screen reads before any of this, why it holds rather than bounces, and how its picture/attachment limits work is covered in Email inbound prescreen. The developer-facing reference — the sidebar registration, the captured-inbox columns, the relay, the sender and screen-hold rules and the outbound routes — is on part 2.

Last verified 2026-10-25