fix(#32): surface LLM errors instead of '(no response)'#33
Merged
Conversation
The pi-agent-core framework never throws on LLM errors (rate limits, timeouts, 500s). It creates AssistantMessage objects with stopReason: "error" and an errorMessage field. The code was ignoring these fields, causing users to see "(no response)" in Telegram. - Add extractErrorFromTurn() helper in response.ts - Telegram handler: check for LLM error before "(no response)" fallback, show "LLM error: <reason>" and mark task failed - A2A sync handler: return JSON-RPC error instead of empty success - Worker: post error event instead of complete with empty result - Update test mocks for new extractErrorFromTurn export Closes #32 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
AssistantMessagewithstopReason: "error"anderrorMessage. The code was ignoring these fields, showing "(no response)" to users.extractErrorFromTurn()helper to detect LLM errors in the message streamLLM error: <reason>and mark task failedTest plan
extractErrorFromTurn)Closes #32
🤖 Generated with Claude Code