fix(sdk): re-dispatch a single in-flight user on recovery boot - #4768
Merged
Conversation
The recovery-boot smart default spliced the partial assistant plus the user it was answering into the seed chain whenever a partial existed and there was at least one in-flight user. With exactly one in-flight user — the plain OOM / crash-mid-answer shape — that consumed the only message there was to dispatch: `recoveredTurns` came out empty, the boot queue stayed empty, the session.in cursor was advanced past the message anyway, and on a preload or continuation boot (no message on the wire payload) neither dispatch site fired. The interrupted question was never answered and the run idled until its timeout. Require two or more in-flight users for the splice, on both the chain and the recoveredTurns branch. With n >= 2 nothing changes. With n = 1 the orphan partial is dropped and the interrupted user is re-dispatched as a fresh turn, which is what the OOM-resilience docs promise. The submit-message boot is unaffected: the existing dedup skips a queued message identical to the one already on the wire payload. Also corrects the docstrings and the recovery-boot docs, which described the default as "re-dispatch every user" without mentioning the splice. Co-Authored-By: Claude <noreply@anthropic.com>
🦋 Changeset detectedLatest commit: b866cd6 The changes in this PR will be included in the next version bump. This PR includes changesets to release 27 packages
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 |
matt-aitken
marked this pull request as ready for review
August 25, 2026 04:50
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
@trigger.dev/build
trigger.dev
@trigger.dev/core
@trigger.dev/python
@trigger.dev/react-hooks
@trigger.dev/redis-worker
@trigger.dev/rsc
@trigger.dev/schema-to-json
@trigger.dev/sdk
commit: |
ericallam
approved these changes
Aug 27, 2026
Merged
ericallam
pushed a commit
that referenced
this pull request
Aug 28, 2026
## Summary 4 new features, 12 improvements, 5 bug fixes. ## Improvements - `trigger.dev deploy` now asks the server whether to build with Depot or the native build server unless `--native-build`, `--depot-build`, or `--local-build` is passed, so the native build server can be rolled out per organization without a CLI change. `--local-bundle` and `--detach` now require `--native-build`. ([#4803](#4803)) - Add an experimental `--local-bundle` deploy flag that runs the install and bundling steps on your machine and uploads only the build output; the image is still built remotely. Useful when your project's install step needs tooling or credentials that only exist locally. ([#4331](#4331)) - Send the CLI version header on all API requests so deployments are attributable to a CLI version ([#4778](#4778)) - A message that arrives mid-turn and is not injected into that turn is now answered as the next turn, instead of being dropped. This is what the `pendingMessages` docs have always described, and it applies to the default too: configuring `pendingMessages` without a `shouldInject` declines every batch, which previously meant every mid-turn message was lost with no error at either end. ([#4795](#4795)) ```ts chat.agent({ id: "my-chat", pendingMessages: { onReceived: ({ message }) => logger.info("arrived mid-turn", { id: message.id }), // Only interrupt once the agent has started calling tools. shouldInject: ({ steps }) => steps.length > 0, }, run: async ({ messages, signal }) => streamText({ model, messages, abortSignal: signal, // Required for injection. Without it nothing injects, and every // mid-turn message is answered as the next turn instead. ...chat.toStreamTextOptions(), }), }); ``` A declined message keeps its place in the queue, so it survives a crash and is answered by whichever run picks the conversation up. An injected one is consumed at the moment it is injected, so it is never also answered as a later turn. - Browser chats now keep the active turn open across page reloads when older completion records are replayed. ([#4643](#4643)) - Add `chat.endAndContinue()` so fully hand-rolled custom chat agents can hand a conversation off to a fresh run on the latest deployed task version while preserving unconsumed Session input. ([#4647](#4647)) - Custom chat agents now validate and parse client data declared with `chat.withClientData({ schema })` before passing it to agent code. ([#4646](#4646)) ## Bug fixes - Fixes a case where a chat could silently lose a message. If a message arrived while the agent was between turns and a stop arrived after it, the cursor the next boot resumed from could point past that message, so it was never answered and no error was raised. This affected `chat.agent`, not just custom agents. ([#4644](#4644)) Fixes a recovered answer being cut off. After a crash the agent replays the message it had not answered yet, but it was replaying the stop that arrived after that message too, so the turn answering it was aborted the moment it began. A stop is now only applied to the turn that was live when it arrived. That holds however the stop got there: sent after the last completed turn, or sent to a chat whose most recent turn was completed by an older version of the SDK. One limitation to know about: the recovered answer is persisted correctly, but a chat page that stayed open across the crash keeps showing the partial answer it had already received. Reload the page to see the full recovered answer. Also fixes a retried send being answered twice. When a send was retried and its idempotency claim was lost, the agent could consume the same message a second time. Custom agent loops can now inspect pending chat input without consuming it, and consume one record at a time, with `chat.messages.hasPending()` and `chat.messages.next()`. Records carry stable identifiers so a redelivery is recognisable. ```ts if (await chat.messages.hasPending()) { const record = await chat.messages.next({ timeoutInSeconds: 0 }); if (record) handle(record.payload); } ``` `hasPending()` answers for messages alone, so a message sitting behind a stop, or behind a record this version of the SDK does not recognise, still reports as pending and is still delivered. Anything the agent has no consumer for is discarded rather than left where it would make every message queued behind it undeliverable. `chat.messages.next()` returning `undefined` means no message became consumable before the timeout. `chat.writeTurnComplete()`'s `sessionInEventId` is the cursor that is safe to resume from, not the sequence of the record the turn answered. It is held back behind any message still waiting to be handled, so a value below the record you just handled is expected. - Fixed a chat agent hanging after an interrupted turn: when a run was killed mid-answer (out of memory, crash, or eviction) and only the one message it was answering was still outstanding, the new run never replied to it. That message is now re-answered on the new run. ([#4768](#4768)) - Fix chat transport discarding the next turn after stopping generation. `skipToTurnComplete` is now reset when a new message or action is sent, so a message sent after `stopGeneration` streams normally instead of leaving the chat stuck in a streaming state. ([#4744](#4744)) - Fixes a message sent while the agent was mid-answer being lost if the run then crashed. The cursor written at the end of each turn could point past a message that had arrived during that turn but had not been answered yet, so the next boot skipped it and no error was raised anywhere. Such a message is now held until a turn actually takes it. ([#4795](#4795)) This also removes the in-memory buffer those messages used to sit in, on both `chat.agent` and `chat.createSession()`, so a message waiting for its turn is durable rather than only present in the worker that received it. ## Server changes These changes affect the self-hosted Docker image and Trigger.dev Cloud: - Self-hosted instances can now disable the admin dashboard and user impersonation entirely. See the self-hosting docs for the new setting. ([#4774](#4774)) - The dashboard has two new themes, Black and White, plus appearance options for stronger colors and underlined links. ([#4547](#4547)) - Deployment logs no longer jump to the bottom while you are reading earlier output. Scroll up to pause auto-scroll, and scroll back down or use the new scroll-to-bottom button in the log header to resume following. ([#4776](#4776)) - Customize the runs list: show, hide, and reorder columns, and add smart columns that pull a value straight out of a run's payload, metadata, or output. Your column choices are saved in the page URL, so you can share a view, bookmark it, or save it straight to your favorites. ([#4652](#4652)) - Stop the browser offering to autofill or save environment variable values as saved credentials. ([#4777](#4777)) - Cut webapp CPU usage by about a quarter on the routes that workers call most, freeing headroom at the same request rate. Detailed event-loop blocking traces are no longer recorded by default, because producing them was itself a large part of that cost. ([#4746](#4746)) - When a runs list or runs.list API request spans too much data to complete, it now returns a clear, actionable error asking you to narrow the time range, instead of failing with a generic error. ([#4773](#4773)) - Improved the performance and reliability of the runs list and the runs.list API, especially for large projects and filtered views. ([#4763](#4763)) - New Vercel connections now get version skew protection turned on automatically, so each run uses the task version its deployment shipped with. Automatic atomic deployments are deprecated and no longer offered when you connect a project, but stay available in your Vercel integration settings. ([#4741](#4741)) - The Staging branch setting now shows an upgrade prompt on plans that don't include a Staging environment, instead of looking editable and then silently doing nothing when saved. ([#4784](#4784)) <details> <summary>Raw changeset output</summary> # Releases ## @trigger.dev/build@4.5.13 ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.5.13` ## trigger.dev@4.5.13 ### Patch Changes - `trigger.dev deploy` now asks the server whether to build with Depot or the native build server unless `--native-build`, `--depot-build`, or `--local-build` is passed, so the native build server can be rolled out per organization without a CLI change. `--local-bundle` and `--detach` now require `--native-build`. ([#4803](#4803)) - Add an experimental `--local-bundle` deploy flag that runs the install and bundling steps on your machine and uploads only the build output; the image is still built remotely. Useful when your project's install step needs tooling or credentials that only exist locally. ([#4331](#4331)) - Send the CLI version header on all API requests so deployments are attributable to a CLI version ([#4778](#4778)) - Updated dependencies: - `@trigger.dev/core@4.5.13` - `@trigger.dev/build@4.5.13` - `@trigger.dev/schema-to-json@4.5.13` ## @trigger.dev/core@4.5.13 ### Patch Changes - `trigger.dev deploy` now asks the server whether to build with Depot or the native build server unless `--native-build`, `--depot-build`, or `--local-build` is passed, so the native build server can be rolled out per organization without a CLI change. `--local-bundle` and `--detach` now require `--native-build`. ([#4803](#4803)) - Add an experimental `--local-bundle` deploy flag that runs the install and bundling steps on your machine and uploads only the build output; the image is still built remotely. Useful when your project's install step needs tooling or credentials that only exist locally. ([#4331](#4331)) - A message that arrives mid-turn and is not injected into that turn is now answered as the next turn, instead of being dropped. This is what the `pendingMessages` docs have always described, and it applies to the default too: configuring `pendingMessages` without a `shouldInject` declines every batch, which previously meant every mid-turn message was lost with no error at either end. ([#4795](#4795)) ```ts chat.agent({ id: "my-chat", pendingMessages: { onReceived: ({ message }) => logger.info("arrived mid-turn", { id: message.id }), // Only interrupt once the agent has started calling tools. shouldInject: ({ steps }) => steps.length > 0, }, run: async ({ messages, signal }) => streamText({ model, messages, abortSignal: signal, // Required for injection. Without it nothing injects, and every // mid-turn message is answered as the next turn instead. ...chat.toStreamTextOptions(), }), }); ``` A declined message keeps its place in the queue, so it survives a crash and is answered by whichever run picks the conversation up. An injected one is consumed at the moment it is injected, so it is never also answered as a later turn. - Fixes a case where a chat could silently lose a message. If a message arrived while the agent was between turns and a stop arrived after it, the cursor the next boot resumed from could point past that message, so it was never answered and no error was raised. This affected `chat.agent`, not just custom agents. ([#4644](#4644)) Fixes a recovered answer being cut off. After a crash the agent replays the message it had not answered yet, but it was replaying the stop that arrived after that message too, so the turn answering it was aborted the moment it began. A stop is now only applied to the turn that was live when it arrived. That holds however the stop got there: sent after the last completed turn, or sent to a chat whose most recent turn was completed by an older version of the SDK. One limitation to know about: the recovered answer is persisted correctly, but a chat page that stayed open across the crash keeps showing the partial answer it had already received. Reload the page to see the full recovered answer. Also fixes a retried send being answered twice. When a send was retried and its idempotency claim was lost, the agent could consume the same message a second time. Custom agent loops can now inspect pending chat input without consuming it, and consume one record at a time, with `chat.messages.hasPending()` and `chat.messages.next()`. Records carry stable identifiers so a redelivery is recognisable. ```ts if (await chat.messages.hasPending()) { const record = await chat.messages.next({ timeoutInSeconds: 0 }); if (record) handle(record.payload); } ``` `hasPending()` answers for messages alone, so a message sitting behind a stop, or behind a record this version of the SDK does not recognise, still reports as pending and is still delivered. Anything the agent has no consumer for is discarded rather than left where it would make every message queued behind it undeliverable. `chat.messages.next()` returning `undefined` means no message became consumable before the timeout. `chat.writeTurnComplete()`'s `sessionInEventId` is the cursor that is safe to resume from, not the sequence of the record the turn answered. It is held back behind any message still waiting to be handled, so a value below the record you just handled is expected. ## @trigger.dev/python@4.5.13 ### Patch Changes - Updated dependencies: - `@trigger.dev/sdk@4.5.13` - `@trigger.dev/core@4.5.13` - `@trigger.dev/build@4.5.13` ## @trigger.dev/react-hooks@4.5.13 ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.5.13` ## @trigger.dev/redis-worker@4.5.13 ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.5.13` ## @trigger.dev/rsc@4.5.13 ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.5.13` ## @trigger.dev/schema-to-json@4.5.13 ### Patch Changes - Updated dependencies: - `@trigger.dev/core@4.5.13` ## @trigger.dev/sdk@4.5.13 ### Patch Changes - Fixed a chat agent hanging after an interrupted turn: when a run was killed mid-answer (out of memory, crash, or eviction) and only the one message it was answering was still outstanding, the new run never replied to it. That message is now re-answered on the new run. ([#4768](#4768)) - Browser chats now keep the active turn open across page reloads when older completion records are replayed. ([#4643](#4643)) - Add `chat.endAndContinue()` so fully hand-rolled custom chat agents can hand a conversation off to a fresh run on the latest deployed task version while preserving unconsumed Session input. ([#4647](#4647)) - Fix chat transport discarding the next turn after stopping generation. `skipToTurnComplete` is now reset when a new message or action is sent, so a message sent after `stopGeneration` streams normally instead of leaving the chat stuck in a streaming state. ([#4744](#4744)) - Custom chat agents now validate and parse client data declared with `chat.withClientData({ schema })` before passing it to agent code. ([#4646](#4646)) - Fixes a message sent while the agent was mid-answer being lost if the run then crashed. The cursor written at the end of each turn could point past a message that had arrived during that turn but had not been answered yet, so the next boot skipped it and no error was raised anywhere. Such a message is now held until a turn actually takes it. ([#4795](#4795)) This also removes the in-memory buffer those messages used to sit in, on both `chat.agent` and `chat.createSession()`, so a message waiting for its turn is durable rather than only present in the worker that received it. - A message that arrives mid-turn and is not injected into that turn is now answered as the next turn, instead of being dropped. This is what the `pendingMessages` docs have always described, and it applies to the default too: configuring `pendingMessages` without a `shouldInject` declines every batch, which previously meant every mid-turn message was lost with no error at either end. ([#4795](#4795)) ```ts chat.agent({ id: "my-chat", pendingMessages: { onReceived: ({ message }) => logger.info("arrived mid-turn", { id: message.id }), // Only interrupt once the agent has started calling tools. shouldInject: ({ steps }) => steps.length > 0, }, run: async ({ messages, signal }) => streamText({ model, messages, abortSignal: signal, // Required for injection. Without it nothing injects, and every // mid-turn message is answered as the next turn instead. ...chat.toStreamTextOptions(), }), }); ``` A declined message keeps its place in the queue, so it survives a crash and is answered by whichever run picks the conversation up. An injected one is consumed at the moment it is injected, so it is never also answered as a later turn. - Fixes a case where a chat could silently lose a message. If a message arrived while the agent was between turns and a stop arrived after it, the cursor the next boot resumed from could point past that message, so it was never answered and no error was raised. This affected `chat.agent`, not just custom agents. ([#4644](#4644)) Fixes a recovered answer being cut off. After a crash the agent replays the message it had not answered yet, but it was replaying the stop that arrived after that message too, so the turn answering it was aborted the moment it began. A stop is now only applied to the turn that was live when it arrived. That holds however the stop got there: sent after the last completed turn, or sent to a chat whose most recent turn was completed by an older version of the SDK. One limitation to know about: the recovered answer is persisted correctly, but a chat page that stayed open across the crash keeps showing the partial answer it had already received. Reload the page to see the full recovered answer. Also fixes a retried send being answered twice. When a send was retried and its idempotency claim was lost, the agent could consume the same message a second time. Custom agent loops can now inspect pending chat input without consuming it, and consume one record at a time, with `chat.messages.hasPending()` and `chat.messages.next()`. Records carry stable identifiers so a redelivery is recognisable. ```ts if (await chat.messages.hasPending()) { const record = await chat.messages.next({ timeoutInSeconds: 0 }); if (record) handle(record.payload); } ``` `hasPending()` answers for messages alone, so a message sitting behind a stop, or behind a record this version of the SDK does not recognise, still reports as pending and is still delivered. Anything the agent has no consumer for is discarded rather than left where it would make every message queued behind it undeliverable. `chat.messages.next()` returning `undefined` means no message became consumable before the timeout. `chat.writeTurnComplete()`'s `sessionInEventId` is the cursor that is safe to resume from, not the sequence of the record the turn answered. It is held back behind any message still waiting to be handled, so a value below the record you just handled is expected. - Updated dependencies: - `@trigger.dev/core@4.5.13` </details> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Requested by Matt Aitken · Slack thread
Before: a
chat.agentrun is killed mid-answer (OOM, crash, eviction) while the message it was answering is the only one still outstanding. The new run boots, puts that message and the half-written reply into its context, and then waits for a message that already arrived. Nobody ever answers the user; the run sits idle until it times out.After: the new run re-runs that message as a fresh turn and replies to it. The half-written reply is dropped. When two or more messages are outstanding, nothing changes — the interrupted one still goes into context and the newer ones are re-run, exactly as before.
✅ Checklist
Testing
New regression test in
packages/trigger-sdk/test/recovery-boot.test.ts— seeds a partial assistant plus exactly one in-flight user, noonRecoveryBoot, and asserts one turn fires for that user with the orphan partial dropped from the chain. It fails onmain(turnCount0, no turn at all) and passes with this change.pnpm exec vitest runinpackages/trigger-sdk— 373 passed, 1 skipped (31 files passed, 1 skipped)pnpm exec oxfmt --checkon the changed files — cleanpnpm exec oxlint packages/trigger-sdk/src packages/trigger-sdk/test— cleanpnpm run build --filter @trigger.dev/sdk— cleanWhat it does: with exactly one in-flight user on a recovery boot, re-dispatch that user as a fresh turn instead of splicing it into the seed chain, where it was never answered.
How: the recovery-boot smart default made one decision in two halves — the seed chain and the recovered-turn list — both gated on
partialAssistant !== undefined && inFlightUsers.length > 0. The splice consumesinFlightUsers[0]into the chain as "the question the partial was answering" and dispatches the rest. That only works when there is a rest: at n=1recoveredTurnscame out empty, the boot-injected queue stayed empty, thesession.incursor was advanced past the message anyway, and on apreloador continuation boot (nomessageon the wire payload) neither dispatch site fired. Both branches now requirelength > 1, so n=1 falls through to the documented default — chain =settledMessages, re-dispatch every in-flight user. The submit-message boot is unaffected: the existing dedup still drops a queued message identical to the one already on the wire payload.Also corrected alongside it: the two SDK docstrings and the
docs/ai-chat/patterns/recovery-boot.mdxdefaults section, which described the default as "re-dispatch every user" and never mentioned the splice.Follow-up (not in this PR): the webapp e2e OOM helper never streams a token before throwing, so it exercises the no-partial path only and would not have caught this. Worth a variant that emits a token first.
Changelog
Fixed a chat agent hanging after an interrupted turn: when a run was killed mid-answer and only the one message it was answering was still outstanding, the new run never replied to it. That message is now re-answered on the new run.