## Summary
Adds **named side channels** to a Session: durable, two-way realtime
streams that outlive a single run and are shared across every run of the
session. Today a Session has exactly one reserved `.in`/`.out` pair (the
chat transcript). This lets a session hold any number of *named*
channels alongside it, each its own `.in`/`.out` pair, so an agent can
stream out-of-band data (a feed of frames, telemetry, a control channel)
on a stream separate from the transcript while many clients read it
live.
The two properties a named channel adds over the reserved pair:
1. It is addressed by a name that outlives a run and is shared across
runs, not welded to the chat turn loop.
2. Writing its `.in` does **not** wake or trigger a run. A run observes
it by subscribing; an external client writes it without spawning
anything.
This is the generalization half of the Momentic ask (stream browser
screenshots from a `chat.agent` to the frontend on a channel separate
from the chat). It builds directly on the start-from-latest /
`useSessionStream` subscribe seam from #4811.
## Usage
Declare the channel's record types once and infer them on both sides:
```ts
// channels.ts (shared, client imports it type-only)
import { sessions } from "@trigger.dev/sdk";
export const screenshots = sessions.defineChannel<{ out: ScreenshotFrame; in: ViewportControl }>(
"screenshots"
);
```
Open a channel from a session handle (`sessions.open(id)` returns one
for a known session id). Writing its `.out` is durable, cross-run, and
wakes nothing; a run observes its `.in` by tailing, without suspending:
```ts
import { sessions } from "@trigger.dev/sdk";
import { screenshots } from "./channels";
const channel = sessions.open(sessionId).channel(screenshots);
await channel.out.append(frame); // frame: ScreenshotFrame (typed from the definition)
channel.in.on((control) => { /* ... */ }); // control: ViewportControl, tail, no suspend
```
Passing the definition types `.out.append` / `.in.on` on the producer
side; a bare name string also works, with records typed `unknown`.
An external client writes the `.in` without waking a run, and reads the
`.out` from React:
```ts
sessions.open(sessionId).channel("screenshots").in.send({ paused: true });
const { records } = useSessionStreamChannel<typeof screenshots>("screenshots", {
sessionId,
accessToken,
io: "out",
from: "latest",
maxRecords: 1,
});
```
`session.channel(name)` returns the same `{ in, out }` handle shape as
the reserved pair, so `append` / `pipe` / `writer` / `read` /
`writeControl` / `trimTo` on `.out` and `send` / `on` / `once` / `peek`
on `.in` all carry over. Passing a name other than the declared one is a
type error; a bare-string call without the generic stays valid with
`records` typed `unknown`.
### With `chat.agent`
This is the motivating case: a `chat.agent` answers on the reserved
transcript as usual, and streams screenshot frames on a side channel in
parallel. `chat.channel(name)` opens a channel on the current run's own
Session, so there's no id to thread:
```ts
import { chat } from "@trigger.dev/sdk/ai";
import { streamText } from "ai";
import { screenshots } from "./channels";
export const browserAgent = chat.agent({
id: "browser-agent",
run: async ({ messages, signal }) => {
const frames = chat.channel(screenshots);
// client pause/resume arrives here without waking a turn
frames.in.on((control: ViewportControl) => applyViewport(control));
// frames stream on their own channel, not the chat transcript
driveBrowser({ signal, onFrame: (frame) => frames.out.append(frame) });
// the assistant reply still goes to the reserved transcript
return streamText({ model: openai("gpt-4o"), messages, abortSignal: signal });
},
});
```
`chat.channel(name)` is a shortcut for `chat.session().channel(name)`;
`chat.session()` returns the current run's full `SessionHandle` if you
need it.
The frontend renders the transcript with `useChat` as before, and the
screenshots with `useSessionStreamChannel<typeof
screenshots>("screenshots", { sessionId: chatId, io: "out", from:
"latest", maxRecords: 1 })`: a live view of the newest frame that
survives across turns (each turn is a new run), because the channel is
keyed on the session, not the run.
### From MCP
An MCP client can observe and write a session's channels with two tools,
built on the same apiClient surface as the hook and the dashboard
viewer:
- `read_session_channel` reads records from a channel (or the reserved
pair). It is a point-in-time drain with cursor pagination
(`afterEventId` / `nextCursor`, `maxRecords`); pass `timeoutInSeconds`
to wait for the next record when none exist yet.
- `write_session_channel` appends one record to a channel's `.in` (an
object or a raw string), so an agent can send control input without
waking a run. `.out` is producer-only, so it is not writable here.
### On the session page
The session detail page lists a session's channels (via an S2 prefix
list in the loader) and shows each as a tab beside `Rendered` and `Raw`.
Selecting a channel renders its records in the same table as the Raw
transcript view, sourced from that channel's `out` and `in` streams.
## How it works
**Addressing.** A channel is a stream name segment:
`sessions/{id}/channels/{name}/{io}`. The reserved pair keeps its
two-part `sessions/{id}/{io}` name for back-compat, and the `channels/`
segment means a user channel named `in`/`out` can never collide with it.
The channel dimension is threaded through the session stream manager
(keyed on `(session, channel, io)`, reserved = absent),
`subscribeToSessionStream`, the session apiClient methods, and the
`realtime.v1.sessions.$session.channels.$channel.$io.{ts,append,records}`
routes. The reserved-pair routes are untouched. The start-from-latest
tail path from #4811 is channel-agnostic, so `from: "latest"` and
`maxRecords` compose unchanged.
**No-wake.** The reserved `.in` append route ensures a run and drains
waitpoints so a chat turn advances. The channel `.in` append route
deliberately does neither: the record lands durably and a run picks it
up when it next subscribes, so writing a side channel can't spawn or
resume a run. A named channel's `.in` is therefore subscribe-only from
the run side (`.on` / `.once` / `.peek`); `.wait()` /
`waitWithIdleTimeout()` throw with a message pointing at the observe
methods.
**Auth.** Channel scope folds into the existing resource id
(`sessions:<key>:channels:<channel>`), so no RBAC grammar change. A
channel route authorizes both the channel-folded id and the bare session
id, which means a session-wide token grants every channel while a
channel-scoped token grants only its own. The per-io rule is preserved
per channel: writing `.out` requires secret-key auth so a browser can't
forge frames; `.in` is writable with the session token.
**Retention.** Channel streams are created on demand on first write and
inherit the org's stream retention (bounded age plus delete-on-empty
from the store's default config), the same as the reserved chat streams.
There is no per-channel control-plane call on the write path. Custom
per-channel retention is deferred until the stream store can set config
inline on the on-demand create, which avoids a control-plane round trip.
**Spans.** Channel writes carry `channel` and `io` attributes, an
accessory chip, and the session icon. Clicking a channel span in the
run's span inspector renders the channel's actual records with the same
viewer the run realtime streams use, rather than the raw properties
JSON.
## Verification
- **Unit (core):** the stream manager isolates channels: two channels on
the same `(session, io)` never cross buffers, and a named channel is
isolated from the reserved pair.
- **Full-stack e2e** against a real stack (webapp, stream store,
Postgres, real runs):
- a named `.out` record is readable back **after the triggering run has
gone terminal** (durable, cross-run);
- a channel `.in` append creates **no** run, while a reserved `.in`
append **does** wake one (the differential is the red/green);
- `from: "latest"` on a named channel delivers the live record and does
**not** replay the backlog from the start;
- the span inspector renders a channel span's records, and the MCP
read/write tools round-trip records on a real session;
- an invalid channel name is rejected.
## Notes
- **Channel listing works on the self-hosted store too.** The stream
store's list operation is available on s2-lite, so the session page's
channel list is an OSS feature. It is a control-plane call made once per
session-page load (best-effort; a failure just hides the tabs), not on
the write path.
- **The ~1 MiB per-record cap is unchanged.** Large payloads (e.g. raw
screenshots) still need object-store pointers on the channel rather than
inline bytes; that's independent of this change.
- Docs ride this branch: the side channels guide, the
`useSessionStreamChannel` reference, and the MCP tools list are all
updated here.
## Screenshots
<img width="3444" height="1870" alt="CleanShot 2026-08-28 at 21 46
27@2x"
src="https://github.com/user-attachments/assets/c192aaee-b946-4824-87b7-ca057514d25e"
/>
## Summary
Realtime streams get a live "last value" mode: subscribe from the latest
record instead of replaying the whole history, keep memory bounded, and
resume across reloads. Plus a new `useSessionStream` hook for reading a
Session's channels from React.
## `useRealtimeStream`: start-from-latest, bounded, resumable
```tsx
const { parts, lastEventId } = useRealtimeStream<Frame>(runId, "frames", {
from: "latest", // skip history, only new records after connect
maxParts: 1, // keep just the most recent (bounded memory)
lastEventId: saved, // resume from a persisted cursor (survives reload)
onParts: (batch) => save(batch.at(-1)?.id), // per-batch event ids
accessToken,
});
```
`from`, `lastEventId` (option and return), and the batching also apply
to `streams.read()` and `fetchStream()`.
## `useSessionStream`: read a Session channel from React (new)
A read-only hook for a Session's `out` (default) or `in` channel, with
the same start / bound / resume options. `useSession` is reserved for
two-way (read and write).
```tsx
const { records, lastEventId } = useSessionStream<Frame>(sessionId, {
io: "out",
from: "latest",
maxRecords: 5,
onRecords: (batch) => {/* each throttled batch, with event ids */},
accessToken,
});
```
## Access-token refresh
Long-lived subscriptions can survive token expiry: pass
`refreshAccessToken` and a 401/403 triggers one re-mint and reconnect.
With no refresher, auth errors stay terminal exactly as before.
```tsx
const { parts } = useRealtimeStream<Frame>(runId, "frames", {
accessToken,
// called on a 401/403 to mint a fresh public token from your backend
refreshAccessToken: async () => {
const res = await fetch("/api/realtime-token");
return (await res.json()).token;
},
});
```
It is also available on `useApiClient` / `TriggerAuthContext`, so every
hook under a provider shares one refresher.
## Notes
Server support (S2 `tail_offset` / Redis `$`, and the start-position
header on the run and session SSE routes) ships here; a client passing
`from: "latest"` against an older server degrades safely to a full
replay. Resume, bounded memory, batched callbacks, and token refresh are
client-only.
Supersedes #4808 and #4809, folded in here. Verified end to end on an
isolated stack: `from: "latest"` on the run and session paths against
real S2, `lastEventId` resume across a reload, bounded memory, batched
callbacks, and a real 401 to token-refresh to reconnect.
## Summary
Lands the full AI Agents documentation surface alongside the v4.5
release candidate of `@trigger.dev/sdk`. Covers `chat.agent` end to end
— defining agents, lifecycle hooks, the frontend transport, sub-agents,
recovery from cancel/crash/OOM, AI Prompts integration — and the
Sessions primitive that backs it.
## Coverage
- **Conceptual**: Overview, Quick Start, How it works.
- **Building agents**: Backend (`chat.agent` / `chat.createSession` /
raw primitives), Lifecycle hooks, Frontend transport, Server-side
`AgentChat`, Sessions reference, `chat.local` state primitive,
TypeScript types.
- **Features**: AI Prompts integration, Fast starts (Preload + Head
Start), Compaction, Pending Messages (steering), Background Injection
(`chat.inject` + `chat.defer`), Actions (undo / regenerate / edit),
Error handling.
- **Patterns (13)**: Sub-agents, Branching conversations, Code sandbox,
Database persistence, Persistence and replay, HITL, Tool result
auditing, Large payloads, Agent skills, OOM resilience, Recovery boot,
Trusted edge signals, Version upgrades.
- **Reference**: API Reference, Client Protocol (wire format), Testing
harness (`mockChatAgent`), MCP server tools, Upgrade guide, Changelog.
## Structure changes
- Top-level nav: AI → **Agents**, with sub-groups for *Building agents /
Features / Patterns / Reference*.
- New RC banner snippet on every page links to the supported AI SDK
versions table on the API Reference.
- All examples use Anthropic with `stopWhen: stepCountIs(15)`.
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Documents the skipColumns option on useRealtimeRun and
useRealtimeRunsWithTag for status-only subscriptions (smaller payloads,
e.g. for progress/completion UI). Adds a troubleshooting section for the
“Failed to index deployment” source-map error when using the Bun
runtime, with a pnpm patch workaround and link to the GitHub issue
* Adds new features table to top of v4 upgrade guide
* Adds wait idempotency to wait-until, wait-for, and wait-for-token pages
* Adds new priority docs page and updates the v4 upgrade guide
* Adds new task lifecycle hooks
* Removes the message about requiring tasks to be exported
* Adds new global lifecycle hooks section
* Moves sections from upgrade guide into the table
* Adds hidden task page
* Improves the global lifecycle hooks section
* Updates middleware and locals section
* Adds new useWaitToken page to the react hooks section
* Adds a new ai.tool section
* Moves Docker (legacy) page into self-hosting section
* Removes known issues from v4 upgrade guide
* Replace “toolTask” with “ai.tool” in the Streams page example
* Renames guide to “Migrating from v3” and adds redirect
* Remove references to v4
* Removes changelog from migration guide
* The installation guide now references `@latest update`
* Changes all references from `/sdk/v3` to `/sdk`
* Updates @v4-beta to @latest
* Fixed broken link
* Fixes broken link
* Adds an upgrade to v4 using AI section
* Fixes 2 broken links
* Adds an entry for targetting preview branches
* Updates the run statuses
* Adds boolean helpers section to the runs and realtime pages
* Updates the concurrency page
* Updates the test page to include the new options
* Adds SDK and curl options for the preview branch targeting
* Updates new bulk actions page
* Remove the releasing concurrency section
* Got rid of some more @v4-beta mentions
* Improved rate limit docs
* Improved migrating docs
* Removed commented sections of the docs
* useWaitToken hook
* Fixed the description
* Fix for missing test image
---------
Co-authored-by: Matt Aitken <matt@mattaitken.com>
Co-authored-by: Dan <8297864+D-K-P@users.noreply.github.com>
* Reordered react hooks + frontend sections
* Updated the overview and nav
* Separated out SWR hooks
* Restructured metadata sections
* Improved backend docs
* Fixed broken link
* Fixed broken links
* Updated the structure
* Restructured overview
* Updated examples cards
* Improved overview
* Updated how it works
* Updated auth
* Added type safety to the run object page
* made the subscribe description clearer
* Fixed links in triggering
* Fixed link
* Removed examples footers
* Copy tweak
* Consolidated metadata and subscribe pages
* moved metadata task examples to metadata
* Fixed links
* Fixing links like zelda
* Removed dead import
* Clearer titles
* Cap R for Realtime
* Fixes broken link
---------
Co-authored-by: James Ritchie <james@trigger.dev>
* Uses image cards for the frameworks
* Removes old snippets
* New AI agents side menu section
* WIP adding new ai agent pages
* Better overview page
* More copy added to the agent example pages
* Copy improvements
* Removes “Creating a project” page and side menu section
* Fixes broken links
* Updates to the latest Mintlify version, fixes issues, changes theme
* Adds descriptions to the main dropdown menu items
* Reformatted Introduction docs ‘landing page’
* Retry heartbeat timeouts by putting back in the queue (#1689)
* If there’s a heartbeat error and no attempts we put it back in the queue to try again
* When nacking, return whether it was put back in the queue or not
* Try and nack, if it fails then fail the run
* Consolidated switch statement
* Fail executing/retrying runs
* OOM retrying on larger machines (#1691)
* OOM retrying on larger machines
* Create forty-windows-shop.md
* Update forty-windows-shop.md
* Only retry again if the machine is different from the original
* Kubernetes OOMs appear as non-zero sigkills, adding support for treating these as OOMs
* Complete the original attempt span if retrying due to an OOM
* Revert "Complete the original attempt span if retrying due to an OOM"
This reverts commit 5f652c6212.
* chore: Update version for release (#1666)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* Release 3.3.14
* Set machine when triggering docs
* Batch queue runs that are waiting for deploy (#1693)
* Detect ffmpeg OOM errors, added manual OutOfMemoryError (#1694)
* Detect ffmpeg OOM errors, added manual OutOfMemoryError
* Create eighty-spies-knock.md
* Improved the machines docs, including the new OutOfMemoryError
* chore: Update version for release (#1695)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* Release 3.3.15
* Create new partitioned TaskEvent table, and switch to it gradually as new runs are created (#1696)
* Create new partitioned TaskEvent table, and switch to it gradually as new runs are created
* Add env var for partition window in seconds
* Make startCreatedAt required in task event store
* Don't create an attempt if the run is final, batchTriggerAndWait bad continue fix (#1698)
* WIP fix for ResumeAttemptService selecting the wrong attempt (which has no error or output)
* Don’t create an attempt if the run is already in a final status
* Don’t get all the columns for the query. Improved the logging.
* Added a log to the batch example
* Filter out the undefined values
* Fix missing logs on child runs by using the root task run createdAt if it exists (#1697)
* Provider changes to support image cache (#1700)
* add env var for additional pull secrets
* make static images configurable
* optional image prefixes
* optional labels with sample rates
* add missing core paths
* remove excessive logs
* Fix run container exits after OOM retries (#1701)
* remove unused imports
* tell run to exit before force requeue
* handle exit for case where we already retried after oom
* improve retry span and add machine props
* don't try to exit run in dev
* Upgrade local dev to use electric beta.15 (#1699)
* Text fixes
* Removed pnpm files
---------
Co-authored-by: Matt Aitken <matt@mattaitken.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Eric Allam <eric@trigger.dev>
Co-authored-by: nicktrn <55853254+nicktrn@users.noreply.github.com>
* Documentation edits made through Mintlify web editor
* Moves files to correct path and improves copy
* Corrects video props to camel case and removes deprecated prop
* Link to the new bulk actions page from the replaying page
---------
Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
Co-authored-by: James Ritchie <james@trigger.dev>
Eric Allam