feat(sdk,core,webapp): transcript storage for chat.agent - #4896

ericallam · 2026-09-05T19:08:10Z

Adds a pluggable TranscriptStorage seam so a chat.agent run can own its conversation history across continuations:

Version 2 transcript snapshot + dual-version dashboard reader
The storage option, a read API, and a conformance suite
Run-tail recovery for every chat.agent
Compaction and injected-context persistence
A dashboard TranscriptStorage over the agent's message rows

This collapses the former 5-PR review stack (#4904, #4893, #4894, #4895) into a single PR after rebasing onto main and migrating to zod v4 (the stack was on zod v3 and conflicted with the zod v4 upgrade #4039). All prior review threads were addressed on the stack branches.

🤖 Generated with Claude Code

coderabbitai · 2026-09-05T19:08:17Z

Note

Reviews paused

It looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the reviews.auto_review.auto_pause_after_reviewed_commits setting.

Use the following commands to manage reviews:

@coderabbitai resume to resume automatic reviews.
@coderabbitai review to trigger a single review.

Use the checkboxes below for quick actions:

▶️ Resume reviews
🔍 Trigger review

Walkthrough

Adds a TranscriptStorage adapter for chat.agent, including default and custom storage, incremental changesets, transcript state, cursors, and context loading. Adds paginated transcript APIs, server and React loading helpers, and storage conformance tests. Adds dashboard-agent database persistence with migrations. Updates snapshot handling, crash recovery, injection and compaction persistence, deprecates hydrateMessages, and documents the new APIs and migration path.

Merge Risk: 🟡 Moderate · up to 3ddfb

This change adds persisted chat transcripts, loading, paging, and recovery behavior. The remaining documentation issues could cause users to implement incompatible action handling or incomplete recovery flows, so they should be corrected before merge.

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 47.06% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 17 functions across 17 files. (2 skipped:…	Write docstrings for the functions missing them to satisfy the coverage threshold.
Description check	⚠️ Warning	The description accurately summarizes the feature, implementation scope, and review history, but it does not follow the repository template. It omits the issue reference, checklist, testing steps, cha…	Add the required template sections. Include a Closes # reference, complete the checklist, describe the tests that were run and their results, add a short changelog entry, and include screenshots or state that they are not applicable.

✅ Passed checks (3 passed)

Check name	Status	Explanation
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Title check	✅ Passed	The title clearly and concisely identifies the main change: adding transcript storage for chat.agent across the SDK, core, and webapp.

Full details: Docstring Coverage

Explanation

Docstring coverage is 47.06% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 17 functions across 17 files. (2 skipped: 2 unsupported.)

Full details: Description check

Explanation

The description accurately summarizes the feature, implementation scope, and review history, but it does not follow the repository template. It omits the issue reference, checklist, testing steps, changelog, and screenshots sections.

✨ Finishing Touches 💡 1

📝 Generate docstrings 💡

Create stacked PR
Commit on current branch

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch feat/transcript-storage-tri-13667

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands.}

changeset-bot · 2026-09-05T19:08:19Z

🦋 Changeset detected

Latest commit: ed95a9e

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 27 packages

Name	Type
@trigger.dev/sdk	Minor
@trigger.dev/core	Minor
@trigger.dev/python	Minor
@internal/dashboard-agent	Patch
@trigger.dev/build	Minor
trigger.dev	Minor
@trigger.dev/redis-worker	Minor
@trigger.dev/schema-to-json	Minor
@internal/clickhouse	Patch
@internal/llm-model-catalog	Patch
@internal/metrics-pipeline	Patch
@trigger.dev/rbac	Minor
@internal/redis	Patch
@internal/replication	Patch
@internal/run-engine	Patch
@internal/run-store	Patch
@internal/schedule-engine	Patch
@internal/tracing	Patch
@internal/webhook-engine	Patch
@internal/webhook-sources	Patch
@internal/cache	Patch
@trigger.dev/react-hooks	Minor
@trigger.dev/rsc	Minor
@trigger.dev/database	Minor
@trigger.dev/otlp-importer	Minor
@trigger.dev/sso	Minor
@internal/testcontainers	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

github-actions · 2026-09-05T19:10:30Z

Observability map

As of ed95a9e.

19/100 over 457 measured of 475 entry points (base 19, no change)

What this PR changed

route	base	head	now failing
/resources/preferences/chat-open-mode	new	0	request-context
/api/v1/sessions/:sessionId/transcript	new	50	request-context

FIX FIRST

/api/v1/projects/:projectRef/envvars (sensitive) - auth-boundary, request-context
/auth/sso (sensitive) - auth-boundary, request-context
/_app/orgs/:organizationSlug/settings/team (sensitive) - error-classification, auth-scope, request-context

AUDIT 3 of 50 sensitive mutations record an actor. 47 without one.
CONTEXT 23 of 457 entry points name a tenant on a failure path. 354 appear only here, 39 of them sensitive, in the JSON rather than the fix list.

What the score is made of

CHECKS
  error-classification  186 applicable, 107 pass,   0 sole, global without it 11
  auth-boundary          62 applicable,  57 pass,   0 sole, global without it 16
  auth-scope             19 applicable,  17 pass,   0 sole, global without it 19
  request-context       457 applicable,  23 pass, 249 sole, global without it 64
  audit-trail            50 applicable,   3 pass,   0 sole, not in the score

The score and findings here are report-only and never gate the merge. Separately, a required test suite keeps this tool's symbol and route lists in sync with the code they name, and can fail a pull request that renames or removes a symbol they reference, or that adds the first route with a segment they anticipate. Each failure names the list to edit. The rules and their reasons: internal-packages/observability-map/README.md.

pkg-pr-new · 2026-09-05T20:32:30Z

Open in StackBlitz

@trigger.dev/build

npm i https://pkg.pr.new/@trigger.dev/build@ed95a9e

trigger.dev

npm i https://pkg.pr.new/trigger.dev@ed95a9e

@trigger.dev/core

npm i https://pkg.pr.new/@trigger.dev/core@ed95a9e

@trigger.dev/python

npm i https://pkg.pr.new/@trigger.dev/python@ed95a9e

@trigger.dev/react-hooks

npm i https://pkg.pr.new/@trigger.dev/react-hooks@ed95a9e

@trigger.dev/redis-worker

npm i https://pkg.pr.new/@trigger.dev/redis-worker@ed95a9e

@trigger.dev/rsc

npm i https://pkg.pr.new/@trigger.dev/rsc@ed95a9e

@trigger.dev/schema-to-json

npm i https://pkg.pr.new/@trigger.dev/schema-to-json@ed95a9e

@trigger.dev/sdk

npm i https://pkg.pr.new/@trigger.dev/sdk@ed95a9e

commit: ed95a9e

Give chat.agent a pluggable TranscriptStorage seam so a run can own its conversation history across continuations: the version 2 transcript snapshot and dual-version dashboard reader, the storage option with a read API and conformance suite, run-tail recovery, compaction and injected-context persistence, and a dashboard TranscriptStorage over the agent's message rows. Includes the continuation-boot recovery hardening and the compaction/injection persistence fix. Rebased onto main and migrated to zod v4. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VG39FXXkFFU24U5EtJMwPi

devin-ai-integration

Devin Review found 1 new potential issue.

Follow-ups to the transcript storage feature (triggerdotdev#4896), surfaced by dogfooding it in the durable-chat example. ## Changes - **Drop the compaction prefix fingerprint.** A compacted lane is reused while its `throughId` still exists in the transcript. A rollback that crosses the compaction point rebuilds from the transcript; an in-place edit of a summarized message is tolerated (unsupported by design). This removes the implicit requirement that a custom `TranscriptStorage` preserve exact message JSON — no more "store as TEXT not JSONB / canonicalize keys" trap. - **Skip persisting a content-less assistant response.** A turn that errors before the model writes anything no longer leaves an empty assistant bubble in the transcript or the next turn's context. - **Non-empty error fallback.** A thrown error with no message now surfaces a generic message instead of a blank error to the client. - **Test harness:** `seedSessionInTail` stamps the harness `clientData` onto seeded records (matching how production carries each record's metadata), so recovery re-dispatch is testable for `clientDataSchema` agents. ## Verification - `@trigger.dev/sdk` + `@trigger.dev/core` typecheck clean - Full `@trigger.dev/sdk` suite: 633 passing (includes new tests for the throughId-boundary compaction behavior, the empty-response skip, and clientData-scoped recovery re-dispatch) - oxfmt + oxlint clean --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

## Summary 5 new features, 37 improvements, 12 bug fixes. ## Breaking changes - Reading a session's `.in` channel (`GET /realtime/v1/sessions/{id}/in` and `/in/records`) now requires a secret key. Public tokens, including `read:sessions:{id}`, get a 403; they can still read `.out` and append to `.in`. ## Highlights - A failed write to a realtime or chat session stream no longer crashes the process running it, and a dropped chat session output write is now logged instead of swallowed. ([`fb25c0149`](https://github.com/triggerdotdev/trigger.dev/commit/fb25c0149c6c734f942f6f41210b197ed4b1f736)) ## Improvements - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. - The `playwright` build extension now works with Playwright 1.58 and later. 1.58 changed the `playwright install --dry-run` output, which made deploy image builds fail while downloading the browsers. ([#4881](https://github.com/triggerdotdev/trigger.dev/pull/4881)) - Rename the dev error link to "Ask Trigger about this error" ([`f999516a0`](https://github.com/triggerdotdev/trigger.dev/commit/f999516a0d8ae2f3a19c76e11aae935e60c81d2c)) - Automatically archive up to three inactive development branches when creating a branch at the plan limit. Connected and recently active branches remain protected, and the CLI reports which branches were archived. ([`dd55fdb5b`](https://github.com/triggerdotdev/trigger.dev/commit/dd55fdb5b821b7cb51d15cd102481c87659985ef)) - When the build log stream cannot be opened or disconnects during a build server deploy, the CLI now explains that the deployment itself is unaffected and exits immediately with a non-zero code, since it can no longer confirm the outcome. Previously a disconnect printed the raw stream error and left the process hanging. ([#4887](https://github.com/triggerdotdev/trigger.dev/pull/4887)) - Build logs no longer include docker's registry login output, most notably the credential-storage warning on failed builds. ([#4909](https://github.com/triggerdotdev/trigger.dev/pull/4909)) - Reduce sensitive values in CLI and SDK diagnostics, secure files created by `trigger env pull`, and remove credentials from collected Git remote metadata. ([`ff05824c1`](https://github.com/triggerdotdev/trigger.dev/commit/ff05824c1bdf1c2276d202ed84328c948cc290a3)) - `chat.agent` persists a conversation through a `TranscriptStorage`: an adapter with `load` and `save` that the runtime drives after every turn, failed turn and history-changing action. The platform snapshot stays the default; bring your own to write the conversation to your database as it happens. Each save carries both the changes since the last one (so a row store writes only what changed, and an undo is one `truncateAfter`) and the whole transcript as it now stands (so a document store writes it as-is with no state of its own). ([#4896](https://github.com/triggerdotdev/trigger.dev/pull/4896)) ```ts chat.agent({ id: "my-chat", storage: myTranscriptStorage, run: async ({ messages, signal, streamText }) => streamText({ model, messages, abortSignal: signal }), }); ``` `chat.createLoadTranscriptAction(storage)` and `useLoadTranscript` read the conversation back the same way for every storage, and `runTranscriptStorageTests` from `@trigger.dev/sdk/ai/test` checks an implementation against the contract. Compaction summaries and `chat.inject` context now survive a continuation run, and crash recovery runs for every agent, including one that owns its own context. `hydrateMessages` is deprecated in favour of `loadContext` on a storage. The snapshot format is now version 2, which older SDK versions cannot read. - `chat.agent`: a run that recovers a session with more than one in-flight user message no longer drops the unanswered ones if it restarts mid-recovery. Recovered messages now hold the resume cursor until each has been answered, so a restart re-answers the rest instead of resuming past them. Previously the cursor could advance past messages that were only held in memory, so a crash before they were dispatched lost them. ([#4907](https://github.com/triggerdotdev/trigger.dev/pull/4907)) - End a chat conversation from inside the agent with `chat.close({ reason })`. The session row is closed, further sends are refused with HTTP 409, and the run exits without scheduling a continuation, so a budget cap, a completed goal, or a signed-out user can stop the conversation rather than only the current run. ([`0a23814a0`](https://github.com/triggerdotdev/trigger.dev/commit/0a23814a0896205da227520bd417bd490a017379)) ```ts chat.agent({ id: "budgeted-agent", run: async ({ messages, signal }) => streamText({ model: openai("gpt-4o"), messages, abortSignal: signal }), onBeforeTurnComplete: async ({ chatId }) => { if (await overBudget(chatId)) { chat.close({ reason: "Monthly budget reached" }); } }, }); ``` The current turn still streams in full. Decide the close before the turn ends (`run()`, `prepareStep`, `onBeforeTurnComplete`) so the closed state rides out on that turn's final record and the user sees it as soon as the answer finishes. `TriggerChatTransport` picks the close up from the response stream or from a refused send, exposes it as `transport.sessionStatus(chatId)` plus `transport.sessionClosedReason(chatId)`, and stops sending and reconnecting. Closing a session from outside with `sessions.close()` now also reaches a live run, so an idle or suspended agent exits on its next wake instead of waiting out its idle timeout. Writes to a closed session's named side channels are refused with the same 409. - Reading a page of a chat agent's conversation no longer downloads the whole conversation. The saved transcript now carries an index, so asking for the most recent messages fetches only those messages, and history loads in roughly constant time however long the chat gets. ([`b7e86f2af`](https://github.com/triggerdotdev/trigger.dev/commit/b7e86f2afe1b1b4e38f1f2f00222eb172e2d0ee3)) A paged read also returns only the conversation itself. The model-side context an agent keeps, its compacted history and any injected context, is no longer included, so it cannot reach a browser through a load-transcript server action. The built-in storage is deliberately basic about long conversations: once an agent has compacted, it keeps roughly the last hundred messages and drops the rest, so what it rewrites each turn stops growing. A conversation that never compacts is kept whole. If your app renders history further back than that, give the agent your own transcript storage. The saved format has changed and an older SDK cannot read it, so a deployment rolled back to an earlier version will not find a readable transcript for conversations the newer version already saved, and those conversations continue from the live stream tail instead. Roll forward rather than back, or keep your own transcript storage. - Adds the `GetDeploymentArtifactUrlResponseBody` schema for the deployment artifact download URL endpoint. ([`1a5ad1e5f`](https://github.com/triggerdotdev/trigger.dev/commit/1a5ad1e5fbc54efbc1c61077ed966477e94a9849)) - Deployments now return the `--external-id` they were deployed under as `externalId`, and a run can read its own from `ctx.deployment.externalId`. Also fixes the deployments list failing when one deployment had no git metadata. ([`879e8975b`](https://github.com/triggerdotdev/trigger.dev/commit/879e8975b13605fd7607c87bd906e640fca90755)) - Add an optional `appliedSchedulePolicy` field to the schedule API response. It is present only when a non-overridable plan policy applies a minimum window to a schedule (e.g. a free-plan schedule's minimum run interval); the configured `window` continues to be returned separately and unchanged. ([`2991bb48a`](https://github.com/triggerdotdev/trigger.dev/commit/2991bb48a284f8b0c140b7a3890f1e4ee73e224d)) - Triggering a task whose id cannot be represented in a URL (for example an id containing an unpaired surrogate) now fails with a clear error naming the task id, instead of a cryptic URI error. ([`ad821eaea`](https://github.com/triggerdotdev/trigger.dev/commit/ad821eaead317bfe60e6d4ca10c00b6fdcbbc5fd)) - Actions can now become turns. `onAction` edits history with `chat.history`; to answer after the edit, return `chat.turn()` and a turn runs on the edited history with everything a turn has: the agent's system prompt and tools, steering, compaction, injected instructions, `onTurnStart` and `onTurnComplete`, and persistence. A regenerate is `chat.history.slice(0, -1); return chat.turn();`. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) ```ts onAction: async ({ action }) => { if (action.type === "regenerate") { chat.history.slice(0, -1); return chat.turn(); } if (action.type === "undo") chat.history.slice(0, -2); // edit only }, ``` Returning a `StreamTextResult`, `string` or `UIMessage` from `onAction` is no longer supported and now fails with an error pointing to `chat.turn()`. A response produced that way skipped every turn guarantee, and its delivery to the browser was unreliable: the frontend never read the stream `transport.sendAction` returned, so a regenerate that appeared to work on the server did not render. History edits made by an action are still persisted as before: platform-managed snapshots are written after the edit, and apps with their own store mirror the edit themselves. - `run()` now receives a `streamText` with your agent's managed options already applied, so they cannot be lost by leaving out the spread: ([#4884](https://github.com/triggerdotdev/trigger.dev/pull/4884)) ```ts run: async ({ messages, signal, streamText }) => streamText({ model, messages, abortSignal: signal }); ``` Spreading `chat.toStreamTextOptions()` still works and is equivalent. The difference is what happens when your options collide with the managed ones. Passing `tools` after the spread replaces the skill tools, and passing your own `prepareStep` replaces the managed one, which silently switches off steering, compaction and injected context. The managed `streamText` merges tools and composes `prepareStep` instead, so neither can be turned off by accident. `system` can be set at the call site, on `chat.agent({ system })`, or through `chat.prompt.set()`, but only in one of them: setting it in two places throws, because no single shape merges two system values across every supported AI SDK version, and dropping one silently is the failure this seam exists to prevent. Injected instructions append to whichever one is in play. `chat.agent()` also takes `registry`, `cacheControl` and `systemProviderOptions` now, so a managed prompt's model and its cache breakpoint no longer have to be passed at the call site. `chat.toStreamTextOptions()` applies them as well, so spreading it into the `streamText` imported from `ai` stays equivalent to the one `run()` receives. `chat.headStart` and `chat.startHeadStart` hand their `run` the same thing, carrying the options the handover protocol depends on. There it matters more: re-setting `messages`, `prompt`, `stopWhen` or `abortSignal` after a spread breaks the handover rather than degrading a feature, and nothing caught it. On the managed one those four keys are a type error; `tools` is yours to pass. - Actions are sent through `useChat` so a turn that follows one renders like any turn. `TriggerChatTransport` recognises `body.action` on a `useChat` request and sends it as an action, so `sendMessage(undefined, { body: { action } })` or `regenerate({ body: { action } })` sends the action and `useChat` owns the response: it streams into the message list, `status` and `error` behave as for a message, and `stop` works. `useChatActions({ sendMessage })` in `@trigger.dev/sdk/chat/react` is a two-line convenience over that. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) ```tsx const { sendMessage } = useChat({ id: chatId, transport }); const { sendAction } = useChatActions({ sendMessage }); sendAction({ type: "regenerate" }); ``` Previously the frontend docs said `useChat` consumed the stream `transport.sendAction` returns; it never did, so an action's answer was never rendered by an app following them. `transport.sendAction` still returns a stream that callers outside `useChat` must read, and now accepts `{ abortSignal, metadata }`, with per-action metadata merged over the transport's `clientData`. - Chat sessions can now be pinned to a deployment, so a conversation keeps talking to the agent version its release shipped with, and follows the pin on its own when your app redeploys. Opt out with `triggerConfig: { externalDeploymentId: null }` or `versionSkew: "hold"`. Also fixes `AgentChat` ignoring `maxDuration`, `region` and `lockToVersion`, and a restored `AgentChat` session never picking up a new deployment id. ([`1133ad45e`](https://github.com/triggerdotdev/trigger.dev/commit/1133ad45e7c1edbc2ff053678e37146c155521ef)) - `chat.agent`: a `chat.history` edit made in `onTurnComplete` after a failed turn is now kept. Previously the edit was applied only when the turn succeeded, so a failure record or a card the hook closed on the error path never reached the transcript. ([`3f67c71c0`](https://github.com/triggerdotdev/trigger.dev/commit/3f67c71c0c68ea53ba1859b4e31054cc5d52293a)) - `chat.agent`: after a Head Start turn whose handed-over tool call was followed by more tool steps, the next turn no longer fails with `tool_use ids must be unique`. The runtime kept the warm step's pending tool call in the model context alongside the completed response that already contained it. ([`8b72e6c06`](https://github.com/triggerdotdev/trigger.dev/commit/8b72e6c0616b1570d57f35b5e2a736791ad3c6f0)) - `chat.agent`: a continuation boot no longer re-dispatches the message that resumed it, and a turn with no new user message no longer calls the model. Previously a resumed run could answer the same message twice, and the second attempt failed against providers that reject a trailing assistant message, overwriting an answer that had already completed. ([`35e57e785`](https://github.com/triggerdotdev/trigger.dev/commit/35e57e785c6c80ee22329c597287ff88a3486e4e)) - `useTriggerChatTransport` now picks up changes to `accessToken`, `startSession` and `fetch` on re-render, so a chat that stays mounted while the surrounding page changes no longer keeps sending to the endpoint captured on first render. ([`9ae9c1ae4`](https://github.com/triggerdotdev/trigger.dev/commit/9ae9c1ae43a91e21afcc6e2c97c4b63b9b0bff71)) - Steering messages are now kept in the conversation when you drive turns yourself with `chat.createSession()` or `chat.MessageAccumulator`. Previously a message that arrived mid-answer shaped that answer and then existed nowhere: it was missing from `turn.uiMessages`, so an app persisting from there never stored it, missing from `turn.messages`, so every later turn answered as though it had never been sent, and it was not queued as its own turn either. It now lands in both, the same way it does on `chat.agent`. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) - Injected system context is merged into a single instruction block, so it works on every supported AI SDK version. Note that a cached system prompt gives up its cache entry for as long as an injection is live, since the cached prefix has changed. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) - `chat.inject()` with `role: "system"` now works. It previously put the system message into the conversation, which AI SDK 7 rejects for every provider: the next turn died with a generic "An error occurred." and persisted an empty assistant message, so the agent looked like it had stopped answering. System-role context is now appended to the model's instructions, which is also the only way to inject context the agent treats as trusted. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) Two things to know. Instructions are delivered by `chat.toStreamTextOptions()`, so a `run()` that calls `streamText` without spreading it does not receive a system-role injection. The conversational lane has no such requirement. And an injection applies to the next turn only, rather than repeating on every turn that follows it. Every inference call in that turn sees it, so a `run()` that builds options more than once gets the same instructions each time. An instruction injected after an action has run, and before the next message, reaches that next turn rather than the one after it. - Undo, edit and regenerate now survive a run ending. History rolled back from `onAction` was only kept in the running worker's memory, so the rollback held while that worker stayed warm and then reverted on the next continuation. The undone messages came back, minutes later, with no error. This also holds when the turn before the action failed: the rollback used to be written against the cursor from before that turn, so a continuation could replay output the failed turn had already superseded. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) - Server-side `AgentChat` streams now reconnect when the connection drops mid-turn instead of ending with a truncated reply, and a turn that still cannot be resumed ends with an error rather than a silent truncation. ([`8bf27a629`](https://github.com/triggerdotdev/trigger.dev/commit/8bf27a62937b5858f4963d65a9d7802982f1724e)) - Session public tokens can now be narrowed to one stream: `read: { sessions: "chat_123:out" }` grants read access to that session's `.out` channel only, without access to the session record or its other channels. ([`33cf5701b`](https://github.com/triggerdotdev/trigger.dev/commit/33cf5701b4536012d45e365761c4a36067ea5f1d)) - Steering messages injected mid-answer are now part of the conversation, both for your hooks and for the model on later turns. Previously they reached the model for the answer they steered and reached the browser, but nothing else: `onTurnComplete` never saw them, so an app storing its own transcript lost the instruction the answer was shaped by, and it vanished from the conversation on reload. The model also forgot the instruction from the next turn onwards, answering as though the message had never been sent, while the chat UI still showed it. This holds when the steered turn fails part-way, and when `pendingMessages.prepare` reshapes the message: later turns now see the same form the steered turn did, not the original message. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) Approving a tool call no longer undoes compaction. A tool-approval continuation used to rebuild the model's context from the full conversation, so a chat that had been summarised to fit the context window was sent the whole transcript again on the next call, and could go over the limit it had just been compacted to avoid. If you worked around this by saving steering messages as they arrive, in `pendingMessages.onReceived` for example, that write now duplicates the one you get from `newUIMessages`. Drop it, or skip messages you have already stored. - Reloading a chat while the agent is still answering now shows the message being answered. Previously the incoming message was only persisted once the turn finished, so a refresh mid-answer showed the reply arriving with no question above it. ([`986811008`](https://github.com/triggerdotdev/trigger.dev/commit/9868110089cb08817801bc4e1026dd6c781be1be)) Adds `chat.deferBeforeOutput()` for app-owned writes that the next page load has to see. Like `chat.defer()` the work is not awaited by the hook that registers it, so it runs alongside the model and costs no time to first token, but the answer is held until it lands. Use it for the conversation or message write you previously had to `await` in `onTurnStart`, as long as nothing else in the turn reads that write back: it orders the write against what the frontend can see, not against the model, so a tool that reads the same row still needs an awaited write. - chat.agent transcript fixes: a turn that errors before the model produces any content no longer stores an empty assistant message, an error thrown without a message now shows a generic error instead of a blank one, and a custom transcript storage no longer needs to preserve exact message JSON for a compaction to survive a continuation. ([#4910](https://github.com/triggerdotdev/trigger.dev/pull/4910)) ## Bug fixes - Fixes storage of large trigger payloads for task ids containing a slash, which could fail the trigger with an "Invalid packet storage path" error. It affected ids that started or ended with a slash, contained two slashes in a row, or contained a `.` or `..` path component. The storage path is now built from a generated id rather than from the task id, so no task id can produce an unusable one, and payloads that are already stored are still read from where they were written. ([`ed37e19c9`](https://github.com/triggerdotdev/trigger.dev/commit/ed37e19c9f70495ba2a067245f8a4a83aaace2c3)) ## Server changes These changes affect the self-hosted Docker image and Trigger.dev Cloud: - Projects that need a Node.js runtime update can now be handed to a coding agent: the organization Projects settings page has a button that copies a ready-to-paste prompt listing every project to update. - Additional API keys are now enabled by default. New environments no longer display root API keys, and existing environments can permanently disable their visibility - New schedules use a default CRON spread window when none is set, distributing runs after their scheduled time instead of starting them all at once. Set an explicit window to override the default. - Schedules now support a configurable minimum spread window that applies even when a smaller window is requested. - The "Cancel in-progress runs when this limit is reached" option on the billing limit form is now enabled by default when you first configure a limit, so already-executing runs stop instead of continuing past the limit. Organizations that have already saved a billing limit keep their existing choice. - Creating and archiving Development and Preview branches now requires the branch management permission, which the Developer role has by default. - The assistant in the dashboard no longer has a monthly message limit, so you can chat with it as much as you like. Asking it to keep an eye on something and tell you when it happens is rolling out gradually, so it isn't offered in every organization yet. - Ask Trigger now opens as a floating window you can drag anywhere and resize, and the chat header lets you switch it to a right-side panel or fullscreen. Choose the position it opens in from your account settings. - The Queues page Allocated tile now explains that it is the sum of your queue concurrency limits, and no longer shows a warning color when those add up to more than the environment limit, which is expected. - Deleting a project now stops its pending runs. Runs that were waiting on a `delay` or sitting in the queue are cancelled instead of executing later, and a deleted project no longer sends task failure alerts. - Fixes an intermittent "Invalid access token" failure caused by the deployment log stream token expiring while a deploy was still in flight. - Dashboard pages no longer keep polling for updates while their browser tab is hidden, which could leave a tab you came back to showing a connection error instead of your data. Pages refresh when you return to the tab. - Stop counting agent LLM calls twice. An agent framework emits a wrapper span around the inference span that did the work, and both were priced, so LLM cost aggregates and the AI metrics page reported roughly double for agent workloads. Per-call figures in the run view were always correct and are unchanged. - Retried trigger and batch trigger requests are deduplicated again: when the SDK automatically retries a request that the server had in fact already accepted, you get the original run or batch back instead of a duplicate one. - Fix the Queues page showing "No activity" on the queue-metrics charts for some organizations even though their metrics were being collected. Those charts now display the collected data. - The queue page's "Oldest wait" card now shows a single clear number (how long the oldest waiting run has been waiting) with an explanatory tooltip, and no longer shows a second "worst" figure that could confusingly read lower than the headline. - Run replication now recovers on its own after a Redis restart or outage, in place of logging "Cannot extend an already-expired lock" and holding the replication slot open until the server is restarted. Deployments running under a process supervisor can set `RUN_REPLICATION_MAX_RESUBSCRIBE_ATTEMPTS` to exit and be restarted when a stream cannot recover. - Reject waitpoint registrations that target a run outside the authenticated environment - Switching environments now keeps you on the current page when a task's id contains a slash, instead of dropping you back to the list. The test page for a webhook task whose id contains a slash also opens correctly now. - GitHub App installations are now linked only after the installing GitHub user authorizes the App and is verified to have access to the installation. <details> <summary>Raw changeset output</summary> # Releases ## @trigger.dev/build@4.6.0 ### Minor Changes - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. ### Patch Changes - The `playwright` build extension now works with Playwright 1.58 and later. 1.58 changed the `playwright install --dry-run` output, which made deploy image builds fail while downloading the browsers. ([#4881](https://github.com/triggerdotdev/trigger.dev/pull/4881)) - Updated dependencies: - `@trigger.dev/core@4.6.0` ## trigger.dev@4.6.0 ### Minor Changes - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. ### Patch Changes - Rename the dev error link to "Ask Trigger about this error" ([`f999516a0`](https://github.com/triggerdotdev/trigger.dev/commit/f999516a0d8ae2f3a19c76e11aae935e60c81d2c)) - Automatically archive up to three inactive development branches when creating a branch at the plan limit. Connected and recently active branches remain protected, and the CLI reports which branches were archived. ([`dd55fdb5b`](https://github.com/triggerdotdev/trigger.dev/commit/dd55fdb5b821b7cb51d15cd102481c87659985ef)) - When the build log stream cannot be opened or disconnects during a build server deploy, the CLI now explains that the deployment itself is unaffected and exits immediately with a non-zero code, since it can no longer confirm the outcome. Previously a disconnect printed the raw stream error and left the process hanging. ([#4887](https://github.com/triggerdotdev/trigger.dev/pull/4887)) - Build logs no longer include docker's registry login output, most notably the credential-storage warning on failed builds. ([#4909](https://github.com/triggerdotdev/trigger.dev/pull/4909)) - Reduce sensitive values in CLI and SDK diagnostics, secure files created by `trigger env pull`, and remove credentials from collected Git remote metadata. ([`ff05824c1`](https://github.com/triggerdotdev/trigger.dev/commit/ff05824c1bdf1c2276d202ed84328c948cc290a3)) - Updated dependencies: - `@trigger.dev/core@4.6.0` - `@trigger.dev/build@4.6.0` - `@trigger.dev/schema-to-json@4.6.0` ## @trigger.dev/core@4.6.0 ### Minor Changes - `chat.agent` persists a conversation through a `TranscriptStorage`: an adapter with `load` and `save` that the runtime drives after every turn, failed turn and history-changing action. The platform snapshot stays the default; bring your own to write the conversation to your database as it happens. Each save carries both the changes since the last one (so a row store writes only what changed, and an undo is one `truncateAfter`) and the whole transcript as it now stands (so a document store writes it as-is with no state of its own). ([#4896](https://github.com/triggerdotdev/trigger.dev/pull/4896)) ```ts chat.agent({ id: "my-chat", storage: myTranscriptStorage, run: async ({ messages, signal, streamText }) => streamText({ model, messages, abortSignal: signal }), }); ``` `chat.createLoadTranscriptAction(storage)` and `useLoadTranscript` read the conversation back the same way for every storage, and `runTranscriptStorageTests` from `@trigger.dev/sdk/ai/test` checks an implementation against the contract. Compaction summaries and `chat.inject` context now survive a continuation run, and crash recovery runs for every agent, including one that owns its own context. `hydrateMessages` is deprecated in favour of `loadContext` on a storage. The snapshot format is now version 2, which older SDK versions cannot read. - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. ### Patch Changes - Automatically archive up to three inactive development branches when creating a branch at the plan limit. Connected and recently active branches remain protected, and the CLI reports which branches were archived. ([`dd55fdb5b`](https://github.com/triggerdotdev/trigger.dev/commit/dd55fdb5b821b7cb51d15cd102481c87659985ef)) - `chat.agent`: a run that recovers a session with more than one in-flight user message no longer drops the unanswered ones if it restarts mid-recovery. Recovered messages now hold the resume cursor until each has been answered, so a restart re-answers the rest instead of resuming past them. Previously the cursor could advance past messages that were only held in memory, so a crash before they were dispatched lost them. ([#4907](https://github.com/triggerdotdev/trigger.dev/pull/4907)) - End a chat conversation from inside the agent with `chat.close({ reason })`. The session row is closed, further sends are refused with HTTP 409, and the run exits without scheduling a continuation, so a budget cap, a completed goal, or a signed-out user can stop the conversation rather than only the current run. ([`0a23814a0`](https://github.com/triggerdotdev/trigger.dev/commit/0a23814a0896205da227520bd417bd490a017379)) ```ts chat.agent({ id: "budgeted-agent", run: async ({ messages, signal }) => streamText({ model: openai("gpt-4o"), messages, abortSignal: signal }), onBeforeTurnComplete: async ({ chatId }) => { if (await overBudget(chatId)) { chat.close({ reason: "Monthly budget reached" }); } }, }); ``` The current turn still streams in full. Decide the close before the turn ends (`run()`, `prepareStep`, `onBeforeTurnComplete`) so the closed state rides out on that turn's final record and the user sees it as soon as the answer finishes. `TriggerChatTransport` picks the close up from the response stream or from a refused send, exposes it as `transport.sessionStatus(chatId)` plus `transport.sessionClosedReason(chatId)`, and stops sending and reconnecting. Closing a session from outside with `sessions.close()` now also reaches a live run, so an idle or suspended agent exits on its next wake instead of waiting out its idle timeout. Writes to a closed session's named side channels are refused with the same 409. - Reading a page of a chat agent's conversation no longer downloads the whole conversation. The saved transcript now carries an index, so asking for the most recent messages fetches only those messages, and history loads in roughly constant time however long the chat gets. ([`b7e86f2af`](https://github.com/triggerdotdev/trigger.dev/commit/b7e86f2afe1b1b4e38f1f2f00222eb172e2d0ee3)) A paged read also returns only the conversation itself. The model-side context an agent keeps, its compacted history and any injected context, is no longer included, so it cannot reach a browser through a load-transcript server action. The built-in storage is deliberately basic about long conversations: once an agent has compacted, it keeps roughly the last hundred messages and drops the rest, so what it rewrites each turn stops growing. A conversation that never compacts is kept whole. If your app renders history further back than that, give the agent your own transcript storage. The saved format has changed and an older SDK cannot read it, so a deployment rolled back to an earlier version will not find a readable transcript for conversations the newer version already saved, and those conversations continue from the live stream tail instead. Roll forward rather than back, or keep your own transcript storage. - Adds the `GetDeploymentArtifactUrlResponseBody` schema for the deployment artifact download URL endpoint. ([`1a5ad1e5f`](https://github.com/triggerdotdev/trigger.dev/commit/1a5ad1e5fbc54efbc1c61077ed966477e94a9849)) - Deployments now return the `--external-id` they were deployed under as `externalId`, and a run can read its own from `ctx.deployment.externalId`. Also fixes the deployments list failing when one deployment had no git metadata. ([`879e8975b`](https://github.com/triggerdotdev/trigger.dev/commit/879e8975b13605fd7607c87bd906e640fca90755)) - Add an optional `appliedSchedulePolicy` field to the schedule API response. It is present only when a non-overridable plan policy applies a minimum window to a schedule (e.g. a free-plan schedule's minimum run interval); the configured `window` continues to be returned separately and unchanged. ([`2991bb48a`](https://github.com/triggerdotdev/trigger.dev/commit/2991bb48a284f8b0c140b7a3890f1e4ee73e224d)) - A failed write to a realtime or chat session stream no longer crashes the process running it, and a dropped chat session output write is now logged instead of swallowed. ([`fb25c0149`](https://github.com/triggerdotdev/trigger.dev/commit/fb25c0149c6c734f942f6f41210b197ed4b1f736)) - Triggering a task whose id cannot be represented in a URL (for example an id containing an unpaired surrogate) now fails with a clear error naming the task id, instead of a cryptic URI error. ([`ad821eaea`](https://github.com/triggerdotdev/trigger.dev/commit/ad821eaead317bfe60e6d4ca10c00b6fdcbbc5fd)) ## @trigger.dev/react-hooks@4.6.0 ### Minor Changes - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.6.0` ## @trigger.dev/redis-worker@4.6.0 ### Minor Changes - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.6.0` ## @trigger.dev/rsc@4.6.0 ### Minor Changes - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.6.0` ## @trigger.dev/schema-to-json@4.6.0 ### Minor Changes - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.6.0` ## @trigger.dev/sdk@4.6.0 ### Minor Changes - Actions can now become turns. `onAction` edits history with `chat.history`; to answer after the edit, return `chat.turn()` and a turn runs on the edited history with everything a turn has: the agent's system prompt and tools, steering, compaction, injected instructions, `onTurnStart` and `onTurnComplete`, and persistence. A regenerate is `chat.history.slice(0, -1); return chat.turn();`. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) ```ts onAction: async ({ action }) => { if (action.type === "regenerate") { chat.history.slice(0, -1); return chat.turn(); } if (action.type === "undo") chat.history.slice(0, -2); // edit only }, ``` Returning a `StreamTextResult`, `string` or `UIMessage` from `onAction` is no longer supported and now fails with an error pointing to `chat.turn()`. A response produced that way skipped every turn guarantee, and its delivery to the browser was unreliable: the frontend never read the stream `transport.sendAction` returned, so a regenerate that appeared to work on the server did not render. History edits made by an action are still persisted as before: platform-managed snapshots are written after the edit, and apps with their own store mirror the edit themselves. - End a chat conversation from inside the agent with `chat.close({ reason })`. The session row is closed, further sends are refused with HTTP 409, and the run exits without scheduling a continuation, so a budget cap, a completed goal, or a signed-out user can stop the conversation rather than only the current run. ([`0a23814a0`](https://github.com/triggerdotdev/trigger.dev/commit/0a23814a0896205da227520bd417bd490a017379)) ```ts chat.agent({ id: "budgeted-agent", run: async ({ messages, signal }) => streamText({ model: openai("gpt-4o"), messages, abortSignal: signal }), onBeforeTurnComplete: async ({ chatId }) => { if (await overBudget(chatId)) { chat.close({ reason: "Monthly budget reached" }); } }, }); ``` The current turn still streams in full. Decide the close before the turn ends (`run()`, `prepareStep`, `onBeforeTurnComplete`) so the closed state rides out on that turn's final record and the user sees it as soon as the answer finishes. `TriggerChatTransport` picks the close up from the response stream or from a refused send, exposes it as `transport.sessionStatus(chatId)` plus `transport.sessionClosedReason(chatId)`, and stops sending and reconnecting. Closing a session from outside with `sessions.close()` now also reaches a live run, so an idle or suspended agent exits on its next wake instead of waiting out its idle timeout. Writes to a closed session's named side channels are refused with the same 409. - `run()` now receives a `streamText` with your agent's managed options already applied, so they cannot be lost by leaving out the spread: ([#4884](https://github.com/triggerdotdev/trigger.dev/pull/4884)) ```ts run: async ({ messages, signal, streamText }) => streamText({ model, messages, abortSignal: signal }); ``` Spreading `chat.toStreamTextOptions()` still works and is equivalent. The difference is what happens when your options collide with the managed ones. Passing `tools` after the spread replaces the skill tools, and passing your own `prepareStep` replaces the managed one, which silently switches off steering, compaction and injected context. The managed `streamText` merges tools and composes `prepareStep` instead, so neither can be turned off by accident. `system` can be set at the call site, on `chat.agent({ system })`, or through `chat.prompt.set()`, but only in one of them: setting it in two places throws, because no single shape merges two system values across every supported AI SDK version, and dropping one silently is the failure this seam exists to prevent. Injected instructions append to whichever one is in play. `chat.agent()` also takes `registry`, `cacheControl` and `systemProviderOptions` now, so a managed prompt's model and its cache breakpoint no longer have to be passed at the call site. `chat.toStreamTextOptions()` applies them as well, so spreading it into the `streamText` imported from `ai` stays equivalent to the one `run()` receives. `chat.headStart` and `chat.startHeadStart` hand their `run` the same thing, carrying the options the handover protocol depends on. There it matters more: re-setting `messages`, `prompt`, `stopWhen` or `abortSignal` after a spread breaks the handover rather than degrading a feature, and nothing caught it. On the managed one those four keys are a type error; `tools` is yours to pass. - `chat.agent` persists a conversation through a `TranscriptStorage`: an adapter with `load` and `save` that the runtime drives after every turn, failed turn and history-changing action. The platform snapshot stays the default; bring your own to write the conversation to your database as it happens. Each save carries both the changes since the last one (so a row store writes only what changed, and an undo is one `truncateAfter`) and the whole transcript as it now stands (so a document store writes it as-is with no state of its own). ([#4896](https://github.com/triggerdotdev/trigger.dev/pull/4896)) ```ts chat.agent({ id: "my-chat", storage: myTranscriptStorage, run: async ({ messages, signal, streamText }) => streamText({ model, messages, abortSignal: signal }), }); ``` `chat.createLoadTranscriptAction(storage)` and `useLoadTranscript` read the conversation back the same way for every storage, and `runTranscriptStorageTests` from `@trigger.dev/sdk/ai/test` checks an implementation against the contract. Compaction summaries and `chat.inject` context now survive a continuation run, and crash recovery runs for every agent, including one that owns its own context. `hydrateMessages` is deprecated in favour of `loadContext` on a storage. The snapshot format is now version 2, which older SDK versions cannot read. - Actions are sent through `useChat` so a turn that follows one renders like any turn. `TriggerChatTransport` recognises `body.action` on a `useChat` request and sends it as an action, so `sendMessage(undefined, { body: { action } })` or `regenerate({ body: { action } })` sends the action and `useChat` owns the response: it streams into the message list, `status` and `error` behave as for a message, and `stop` works. `useChatActions({ sendMessage })` in `@trigger.dev/sdk/chat/react` is a two-line convenience over that. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) ```tsx const { sendMessage } = useChat({ id: chatId, transport }); const { sendAction } = useChatActions({ sendMessage }); sendAction({ type: "regenerate" }); ``` Previously the frontend docs said `useChat` consumed the stream `transport.sendAction` returns; it never did, so an action's answer was never rendered by an app following them. `transport.sendAction` still returns a stream that callers outside `useChat` must read, and now accepts `{ abortSignal, metadata }`, with per-action metadata merged over the transport's `clientData`. - Trigger.dev now uses Zod 4 by default. Projects using Zod 3.25.56 or later 3.x releases remain supported. ([#4039](https://github.com/triggerdotdev/trigger.dev/pull/4039)) Zod remains a runtime dependency of packages that execute schemas, so existing and new installations continue to receive it automatically. The matching peer dependency range allows package managers to reuse either a compatible Zod 3 or Zod 4 installation from your project. ### Patch Changes - Chat sessions can now be pinned to a deployment, so a conversation keeps talking to the agent version its release shipped with, and follows the pin on its own when your app redeploys. Opt out with `triggerConfig: { externalDeploymentId: null }` or `versionSkew: "hold"`. Also fixes `AgentChat` ignoring `maxDuration`, `region` and `lockToVersion`, and a restored `AgentChat` session never picking up a new deployment id. ([`1133ad45e`](https://github.com/triggerdotdev/trigger.dev/commit/1133ad45e7c1edbc2ff053678e37146c155521ef)) - `chat.agent`: a `chat.history` edit made in `onTurnComplete` after a failed turn is now kept. Previously the edit was applied only when the turn succeeded, so a failure record or a card the hook closed on the error path never reached the transcript. ([`3f67c71c0`](https://github.com/triggerdotdev/trigger.dev/commit/3f67c71c0c68ea53ba1859b4e31054cc5d52293a)) - `chat.agent`: after a Head Start turn whose handed-over tool call was followed by more tool steps, the next turn no longer fails with `tool_use ids must be unique`. The runtime kept the warm step's pending tool call in the model context alongside the completed response that already contained it. ([`8b72e6c06`](https://github.com/triggerdotdev/trigger.dev/commit/8b72e6c0616b1570d57f35b5e2a736791ad3c6f0)) - `chat.agent`: a continuation boot no longer re-dispatches the message that resumed it, and a turn with no new user message no longer calls the model. Previously a resumed run could answer the same message twice, and the second attempt failed against providers that reject a trailing assistant message, overwriting an answer that had already completed. ([`35e57e785`](https://github.com/triggerdotdev/trigger.dev/commit/35e57e785c6c80ee22329c597287ff88a3486e4e)) - `chat.agent`: a run that recovers a session with more than one in-flight user message no longer drops the unanswered ones if it restarts mid-recovery. Recovered messages now hold the resume cursor until each has been answered, so a restart re-answers the rest instead of resuming past them. Previously the cursor could advance past messages that were only held in memory, so a crash before they were dispatched lost them. ([#4907](https://github.com/triggerdotdev/trigger.dev/pull/4907)) - Reading a page of a chat agent's conversation no longer downloads the whole conversation. The saved transcript now carries an index, so asking for the most recent messages fetches only those messages, and history loads in roughly constant time however long the chat gets. ([`b7e86f2af`](https://github.com/triggerdotdev/trigger.dev/commit/b7e86f2afe1b1b4e38f1f2f00222eb172e2d0ee3)) A paged read also returns only the conversation itself. The model-side context an agent keeps, its compacted history and any injected context, is no longer included, so it cannot reach a browser through a load-transcript server action. The built-in storage is deliberately basic about long conversations: once an agent has compacted, it keeps roughly the last hundred messages and drops the rest, so what it rewrites each turn stops growing. A conversation that never compacts is kept whole. If your app renders history further back than that, give the agent your own transcript storage. The saved format has changed and an older SDK cannot read it, so a deployment rolled back to an earlier version will not find a readable transcript for conversations the newer version already saved, and those conversations continue from the live stream tail instead. Roll forward rather than back, or keep your own transcript storage. - `useTriggerChatTransport` now picks up changes to `accessToken`, `startSession` and `fetch` on re-render, so a chat that stays mounted while the surrounding page changes no longer keeps sending to the endpoint captured on first render. ([`9ae9c1ae4`](https://github.com/triggerdotdev/trigger.dev/commit/9ae9c1ae43a91e21afcc6e2c97c4b63b9b0bff71)) - Steering messages are now kept in the conversation when you drive turns yourself with `chat.createSession()` or `chat.MessageAccumulator`. Previously a message that arrived mid-answer shaped that answer and then existed nowhere: it was missing from `turn.uiMessages`, so an app persisting from there never stored it, missing from `turn.messages`, so every later turn answered as though it had never been sent, and it was not queued as its own turn either. It now lands in both, the same way it does on `chat.agent`. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) - Injected system context is merged into a single instruction block, so it works on every supported AI SDK version. Note that a cached system prompt gives up its cache entry for as long as an injection is live, since the cached prefix has changed. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) - `chat.inject()` with `role: "system"` now works. It previously put the system message into the conversation, which AI SDK 7 rejects for every provider: the next turn died with a generic "An error occurred." and persisted an empty assistant message, so the agent looked like it had stopped answering. System-role context is now appended to the model's instructions, which is also the only way to inject context the agent treats as trusted. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) Two things to know. Instructions are delivered by `chat.toStreamTextOptions()`, so a `run()` that calls `streamText` without spreading it does not receive a system-role injection. The conversational lane has no such requirement. And an injection applies to the next turn only, rather than repeating on every turn that follows it. Every inference call in that turn sees it, so a `run()` that builds options more than once gets the same instructions each time. An instruction injected after an action has run, and before the next message, reaches that next turn rather than the one after it. - A failed write to a realtime or chat session stream no longer crashes the process running it, and a dropped chat session output write is now logged instead of swallowed. ([`fb25c0149`](https://github.com/triggerdotdev/trigger.dev/commit/fb25c0149c6c734f942f6f41210b197ed4b1f736)) - Undo, edit and regenerate now survive a run ending. History rolled back from `onAction` was only kept in the running worker's memory, so the rollback held while that worker stayed warm and then reverted on the next continuation. The undone messages came back, minutes later, with no error. This also holds when the turn before the action failed: the rollback used to be written against the cursor from before that turn, so a continuation could replay output the failed turn had already superseded. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) - Reduce sensitive values in CLI and SDK diagnostics, secure files created by `trigger env pull`, and remove credentials from collected Git remote metadata. ([`ff05824c1`](https://github.com/triggerdotdev/trigger.dev/commit/ff05824c1bdf1c2276d202ed84328c948cc290a3)) - Server-side `AgentChat` streams now reconnect when the connection drops mid-turn instead of ending with a truncated reply, and a turn that still cannot be resumed ends with an error rather than a silent truncation. ([`8bf27a629`](https://github.com/triggerdotdev/trigger.dev/commit/8bf27a62937b5858f4963d65a9d7802982f1724e)) - Session public tokens can now be narrowed to one stream: `read: { sessions: "chat_123:out" }` grants read access to that session's `.out` channel only, without access to the session record or its other channels. ([`33cf5701b`](https://github.com/triggerdotdev/trigger.dev/commit/33cf5701b4536012d45e365761c4a36067ea5f1d)) - Fixes storage of large trigger payloads for task ids containing a slash, which could fail the trigger with an "Invalid packet storage path" error. It affected ids that started or ended with a slash, contained two slashes in a row, or contained a `.` or `..` path component. The storage path is now built from a generated id rather than from the task id, so no task id can produce an unusable one, and payloads that are already stored are still read from where they were written. ([`ed37e19c9`](https://github.com/triggerdotdev/trigger.dev/commit/ed37e19c9f70495ba2a067245f8a4a83aaace2c3)) - Steering messages injected mid-answer are now part of the conversation, both for your hooks and for the model on later turns. Previously they reached the model for the answer they steered and reached the browser, but nothing else: `onTurnComplete` never saw them, so an app storing its own transcript lost the instruction the answer was shaped by, and it vanished from the conversation on reload. The model also forgot the instruction from the next turn onwards, answering as though the message had never been sent, while the chat UI still showed it. This holds when the steered turn fails part-way, and when `pendingMessages.prepare` reshapes the message: later turns now see the same form the steered turn did, not the original message. ([#4816](https://github.com/triggerdotdev/trigger.dev/pull/4816)) Approving a tool call no longer undoes compaction. A tool-approval continuation used to rebuild the model's context from the full conversation, so a chat that had been summarised to fit the context window was sent the whole transcript again on the next call, and could go over the limit it had just been compacted to avoid. If you worked around this by saving steering messages as they arrive, in `pendingMessages.onReceived` for example, that write now duplicates the one you get from `newUIMessages`. Drop it, or skip messages you have already stored. - Reloading a chat while the agent is still answering now shows the message being answered. Previously the incoming message was only persisted once the turn finished, so a refresh mid-answer showed the reply arriving with no question above it. ([`986811008`](https://github.com/triggerdotdev/trigger.dev/commit/9868110089cb08817801bc4e1026dd6c781be1be)) Adds `chat.deferBeforeOutput()` for app-owned writes that the next page load has to see. Like `chat.defer()` the work is not awaited by the hook that registers it, so it runs alongside the model and costs no time to first token, but the answer is held until it lands. Use it for the conversation or message write you previously had to `await` in `onTurnStart`, as long as nothing else in the turn reads that write back: it orders the write against what the frontend can see, not against the model, so a tool that reads the same row still needs an awaited write. - chat.agent transcript fixes: a turn that errors before the model produces any content no longer stores an empty assistant message, an error thrown without a message now shows a generic error instead of a blank one, and a custom transcript storage no longer needs to preserve exact message JSON for a compaction to survive a continuation. ([#4910](https://github.com/triggerdotdev/trigger.dev/pull/4910)) - Updated dependencies: - `@trigger.dev/core@4.6.0` ## @trigger.dev/python@4.6.0 ### Patch Changes - Updated dependencies: - `@trigger.dev/sdk@4.6.0` - `@trigger.dev/core@4.6.0` - `@trigger.dev/build@4.6.0` </details> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from c5e1f5d to bac2a16 Compare September 5, 2026 20:29

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 2b2ea99 to be72173 Compare September 5, 2026 20:29

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from bac2a16 to bb1acb8 Compare September 5, 2026 20:38

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from be72173 to 5dc4365 Compare September 5, 2026 20:38

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from bb1acb8 to 8bb1a1c Compare September 6, 2026 05:42

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 5dc4365 to 3bdfd45 Compare September 6, 2026 05:42

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from 8bb1a1c to 10a1d68 Compare September 6, 2026 05:55

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 3bdfd45 to db561bb Compare September 6, 2026 05:55

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from 10a1d68 to f2a1179 Compare September 6, 2026 06:17

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from db561bb to 185360a Compare September 6, 2026 06:17

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from f2a1179 to 860969d Compare September 6, 2026 06:18

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 185360a to 461a6d2 Compare September 6, 2026 06:18

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from 860969d to 0b4aa77 Compare September 6, 2026 06:39

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 461a6d2 to 1a3b477 Compare September 6, 2026 06:39

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from 0b4aa77 to b12a0b7 Compare September 6, 2026 08:05

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 1a3b477 to d06408f Compare September 6, 2026 08:06

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from b12a0b7 to dce7b9b Compare September 6, 2026 08:43

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from d06408f to a4f1bfe Compare September 6, 2026 08:43

ericallam marked this pull request as ready for review September 6, 2026 16:36

This comment was marked as resolved.

Sign in to view

ericallam force-pushed the feat/transcript-storage-tri-13667 branch 6 times, most recently from 39a00da to bf8496f Compare September 7, 2026 07:48

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from 1e23c34 to d627683 Compare September 7, 2026 10:22

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 7a6c3fd to 0a10002 Compare September 7, 2026 10:22

This comment was marked as resolved.

Sign in to view

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 3ddfb85 to bca2b92 Compare September 8, 2026 09:48

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from d627683 to 8292d10 Compare September 8, 2026 09:48

This comment was marked as resolved.

Sign in to view

ericallam force-pushed the feat/transcript-storage-gate-split-tri-13667 branch from 8292d10 to 70a6e1d Compare September 8, 2026 17:53

ericallam force-pushed the feat/transcript-storage-tri-13667 branch 2 times, most recently from af81d57 to 5f06b37 Compare September 8, 2026 18:07

ericallam added this pull request to the merge queue Sep 8, 2026

github-merge-queue Bot removed this pull request from the merge queue because a pull request earlier in the stack was removed Sep 8, 2026

ericallam changed the base branch from feat/transcript-storage-gate-split-tri-13667 to main September 9, 2026 06:20

ericallam force-pushed the feat/transcript-storage-tri-13667 branch from 5f06b37 to ed95a9e Compare September 9, 2026 06:21

ericallam enabled auto-merge September 9, 2026 06:22

devin-ai-integration Bot reviewed Sep 9, 2026

View reviewed changes

ericallam added this pull request to the merge queue Sep 9, 2026

Merged via the queue into main with commit df6972c Sep 9, 2026
86 of 97 checks passed

ericallam deleted the feat/transcript-storage-tri-13667 branch September 9, 2026 06:42

github-actions Bot mentioned this pull request Sep 9, 2026

chore: release v4.6.0 #4883

Merged

ericallam mentioned this pull request Sep 9, 2026

fix(sdk): chat.agent transcript follow-ups #4910

Merged

Navigation Menu

Uh oh!

Uh oh!

feat(sdk,core,webapp): transcript storage for chat.agent - #4896