feat(extract): add timeout for LLM extraction step#604
Merged
Conversation
LLM extraction previously ran with an unbounded context, so a slow model (e.g. qwen3:0.6b on an image) could hang indefinitely with no way to bail out other than manually cancelling the overlay. Add a configurable `extraction.llm_timeout` (env: MICASA_EXTRACTION_LLM_TIMEOUT, default: 2m) that wraps the ChatStream context with a deadline. On timeout the overlay shows an actionable message pointing users to the config key. The timeout context is properly cleaned up on completion, cancellation, and rerun. closes #486
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #604 +/- ##
==========================================
- Coverage 76.13% 76.06% -0.08%
==========================================
Files 63 63
Lines 18579 18673 +94
==========================================
+ Hits 14145 14203 +58
- Misses 3757 3790 +33
- Partials 677 680 +3 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
cpcloud
added a commit
that referenced
this pull request
Mar 19, 2026
## Summary - Add configurable `extraction.llm_timeout` (env: `MICASA_EXTRACTION_LLM_TIMEOUT`, default: 2m) to bound LLM extraction inference time - On timeout, the overlay shows an actionable message: `timed out after Xs -- increase extraction.llm_timeout in config` - Non-timeout errors preserve their original message unchanged - Timeout context is properly cleaned up on completion, user cancellation, and rerun closes #486
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
extraction.llm_timeout(env:MICASA_EXTRACTION_LLM_TIMEOUT, default: 2m) to bound LLM extraction inference timetimed out after Xs -- increase extraction.llm_timeout in configcloses #486