[waleedlatif1]

Summary

• history search --chats from a workflow's copilot chat is refused by design (other chats are read back from home chats only), but the refusal said Chat not found about the caller's own, existing chat
• The agent read that as a transient lookup failure and retried the identical command, up to three times in one chat
• The refusal is now forbidden with the reason: "Reading other chats is available in home chats, not in a workflow's copilot chat", matching the neighboring "requires an agent chat" refusal. No concealment is lost: it is the caller's own chat, refused after authorization
• What is listed, and for whom, is unchanged; the worker already surfaces Sim's refusal text and status for any non-OK answer

Type of Change

• Bug fix

Testing

• lib/mothership/chat/application/read-recall-chats.test.ts: the workflow-chat case now asserts the forbidden code and reason; 13/13 pass, and it fails against the previous not_found
• bun run lint, check:api-validation:strict, check:comment-hygiene, check:test-patterns, check:utils, check:source-conventions
• Type-check, full check:audits and the test suites run in CI

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing (new tests pass the test-audit authoring gate)
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

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

1 Skipped Deployment

Project	Deployment	Actions	Updated
docs	Skipped		Oct 31, 2026 9:06am UTC

[greptile-apps]

Confidence Score: 5/5

[Low impact] This PR appears safe to merge.

Summary

Changes the workflow-chat refusal from not_found to forbidden and explains that reading other chats is available only from home chats.

• Workflow copilot chats get a clear reason when they cannot read other chats.

_{Reviews (1) · Last reviewed commit: "fix(mothership): say why a workflow copi..." · Reviewed by Greptile}

[cubic-dev-ai]

No issues found across 2 files

Confidence score: 5/5

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

_{Turn on auto-fix | Re-trigger cubic}