fix(mothership): explain a Chat turn the worker ends without a reason by waleedlatif1 · Pull Request #8478 · simstudioai/sim

waleedlatif1 · 2026-09-30T22:06:40Z

Summary

Problem. When a resume or reattach reaches a Chat run that has already ended (for example at its deadline), the turn failed with the generic "An unexpected error occurred while processing the response." and gave no hint of what happened.

Root cause. When the worker replays an ended run from its log, it sends an error terminal with no error event, because that replay does not carry the run's stored reason. runCopilotLifecycle saw completionStatus === error with an empty context.errors, so no specific message was set and callers fell back to the generic one.

Fix. runCopilotLifecycle now detects that exact shape (error terminal, no reported error, no replay refusal, not aborted) and sets a surface-neutral message: "This run had already ended before it could continue." A reason the worker reports, a replay refusal, and a user Stop all still take precedence. The refusal wins by an explicit guard, not by spread order.

Also:

The Go stream's error text is now logged under errorMessage / detail, so it no longer overwrites the log line's own message field (go/stream.ts, session/buffer.ts).
STREAM_TIMEOUT_MS is renamed CHAT_RUN_DEADLINE_MS and documented as the worker's default run deadline. Sim does not enforce it; it is only the base of USAGE_SETTLE_MS.
The byte-budget doc now says a reader behind the replay-ring trim is re-synced from the worker log, and gets replay_gap only when that log cannot serve it.

Behaviour changes

A turn that reattaches to an already-ended run now shows "This run had already ended before it could continue." instead of the generic unexpected-error message. This applies to Chat, workflow execute, and inbox.
Runs that fail with a worker-reported reason, runs refused on replay, and runs the user stopped behave as before.
Log field names change for two Go-stream error log lines (message → errorMessage / detail).
No change to billing values: USAGE_SETTLE_MS keeps the same number.

Test plan

lib/mothership/request/lifecycle/run.test.ts: new cases for an error terminal with no reason (gets the ended-run message), a replay refusal combined with a reasonless error terminal (refusal wins), and a Stop with a reasonless error terminal (stays a cancellation). Removing the fallback turns the ended-run case red; restoring it turns it green.
lib/mothership/request/lifecycle and lib/mothership/request/go suites pass (185 tests).
bun run type-check in apps/sim
Biome check on changed files
Staging: reattach to a Chat run past its deadline and confirm the new message

When the worker rebuilds an ended run from its log (a resume or reattach that reaches a run that already ended, for example at its deadline), it sends an error terminal with no error event. Sim then fell back to the generic "An unexpected error occurred while processing the response." The turn now says the run had already ended and can be continued by sending a message. A reason the worker reports, a replay refusal, and a Stop all still take precedence. Also: - Log the Go stream's error text under errorMessage/detail so it no longer overwrites the log line's own message (stream.ts, buffer.ts). - Rename STREAM_TIMEOUT_MS to CHAT_RUN_DEADLINE_MS and document it as the worker's default run deadline, now only the base of USAGE_SETTLE_MS. - Update the byte-budget doc: a reader behind the ring trim is re-synced from the worker log; replay_gap is only the fallback.

… a replay refusal The fallback is shared by Chat, workflow execute and inbox, so it no longer tells the reader to send a message. A replay refusal now wins by guard rather than by spread order, with a test that covers the combination.

vercel · 2026-09-30T22:06:45Z

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated
docs	Ready	Preview	Sep 30, 2026 11:19pm UTC

waleedlatif1 · 2026-09-30T22:07:44Z

@greptile

waleedlatif1 · 2026-09-30T22:07:45Z

@cubic-dev-ai review this PR

cubic-dev-ai · 2026-09-30T22:07:53Z

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

cubic-dev-ai

No issues found across 7 files

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Re-trigger cubic}

greptile-apps · 2026-09-30T22:11:44Z

Confidence Score: 5/5

[Medium risk] Adjusts how worker run deadlines and error messages are handled.

The PR appears safe to merge, with a non-blocking Slack callback recovery-message regression.

Summary

The PR gives reasonless, already-ended runs a specific lifecycle error and clarifies the worker deadline, replay-ring behavior, and Go-stream log fields. Changes since the previous review also add a desktop system-browser source-connection flow. The Slack callback’s new failure redirect loses actionable recovery guidance when the browser session has expired.

Diagram

sequenceDiagram
  participant Desktop
  participant Sim
  participant Browser
  Desktop->>Sim: Store one-use source request
  Desktop->>Browser: Open source connection
  Browser->>Sim: Consume request and start authorization
  Sim-->>Browser: Provider completion
  Browser->>Desktop: Return result through loopback

_{Reviews (3) · Last reviewed commit: "Merge remote-tracking branch 'origin/sta..."}

waleedlatif1 · 2026-09-30T22:31:28Z

@greptile

waleedlatif1 · 2026-09-30T22:31:29Z

@cubic-dev-ai review this PR

cubic-dev-ai · 2026-09-30T22:31:35Z

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

cubic-dev-ai

No issues found across 7 files

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Re-trigger cubic}

…e stream-abort test helper

…-terminal-message

waleedlatif1 · 2026-09-30T23:16:59Z

@greptile

waleedlatif1 · 2026-09-30T23:17:01Z

@cubic-dev-ai review this PR

cubic-dev-ai · 2026-09-30T23:17:07Z

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

cubic-dev-ai

No issues found across 7 files

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Re-trigger cubic}

waleedlatif1 added 2 commits September 30, 2026 15:04

vercel Bot temporarily deployed to Preview September 30, 2026 22:06 Inactive

cubic-dev-ai Bot reviewed Sep 30, 2026

View reviewed changes

greptile-apps Bot reviewed Sep 30, 2026

View reviewed changes

Comment thread apps/sim/lib/mothership/request/lifecycle/run.test.ts Outdated

cubic-dev-ai Bot reviewed Sep 30, 2026

View reviewed changes

waleedlatif1 added 2 commits September 30, 2026 16:09

refactor(mothership): drop the unreachable refusal guard and reuse th…

5a34b3e

…e stream-abort test helper

Merge remote-tracking branch 'origin/staging' into fix/chat-ended-run…

183d321

…-terminal-message

vercel Bot deployed to Preview September 30, 2026 23:19 View deployment

cubic-dev-ai Bot reviewed Sep 30, 2026

View reviewed changes

waleedlatif1 merged commit 2178d6e into staging Oct 1, 2026
32 checks passed

icecrasher321 mentioned this pull request Oct 1, 2026

v0.9.8: search cleanup recovery, new search providers, billing and chat reliability #8494

Open

waleedlatif1 deleted the fix/chat-ended-run-terminal-message branch October 1, 2026 01:24

Conversation

waleedlatif1 commented Sep 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Behaviour changes

Test plan

Uh oh!

vercel Bot commented Sep 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

waleedlatif1 commented Sep 30, 2026

Uh oh!

waleedlatif1 commented Sep 30, 2026

Uh oh!

cubic-dev-ai Bot commented Sep 30, 2026

Uh oh!

cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

greptile-apps Bot commented Sep 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Confidence Score: 5/5

Summary

Uh oh!

Uh oh!

waleedlatif1 commented Sep 30, 2026

Uh oh!

waleedlatif1 commented Sep 30, 2026

Uh oh!

cubic-dev-ai Bot commented Sep 30, 2026

Uh oh!

cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

waleedlatif1 commented Sep 30, 2026

Uh oh!

waleedlatif1 commented Sep 30, 2026

Uh oh!

cubic-dev-ai Bot commented Sep 30, 2026

Uh oh!

cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

This branch was successfully deployed

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

waleedlatif1 commented Sep 30, 2026 •

edited

Loading

vercel Bot commented Sep 30, 2026 •

edited

Loading

greptile-apps Bot commented Sep 30, 2026 •

edited

Loading