Repository navigation
[bot] Merge master/c3c5284a into rel/dev - #1842
Merged
Merged
Conversation
#1789) * feat(gooddata-eval): record why an agentic simulated-user loop stopped metric_created=False alone cannot separate a run that ran out of turns, one where the agent went silent, one where the harness's own simulated user failed, and one that was refused. Each run now records which of those ended it, so a failing item can be diagnosed without replaying it, and a chat or simulated-user fault is recorded against the run rather than aborting the whole item. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(gooddata-eval): process ChatError.partial_result so created objects cannot leak A stream that broke AFTER create_metric or create_metric_alert had already succeeded left the object behind in the workspace, where the next run found it and scored against it. The partial result carries what the call managed to do, so it is read and cleaned up instead of discarded with the error. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(gooddata-eval): rebase a partial result onto the shared timeline The success path shifts and indexes a turn's events before anything reads them; the ChatError branch extended the conversation lists with the raw partial. Each turn's SSE stream times from ~0 and indexes from 0, so a partial on a later turn landed at call_ts 0.5 beside the first turn's events, with indexes restarting at 0 -- `timeline_detail` then reported two turns overlapping, with duplicate indexes pointing at the wrong call. Its reasoning steps were dropped from `total_steps` for the same reason. What the stream delivered before it died is still that turn's work, so it is accumulated exactly as a completed turn's is. The TurnIncompleteError branch was already correct -- it assigns the partial to `chat_result` and falls through to the shared path -- which is what made the asymmetry easy to miss. Found in review by CodeRabbit. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configuration
You can disable this status message by setting the Use the checkbox below for a quick retry:
Comment |
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## rel/dev #1842 +/- ##
===========================================
+ Coverage 83.62% 83.69% +0.06%
===========================================
Files 331 331
Lines 22338 22447 +109
===========================================
+ Hits 18681 18787 +106
- Misses 3657 3660 +3 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
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
2 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.
🚀 Automated PR to perform merge from master into rel/dev with changes up to c3c5284 (created by https://github.com/gooddata/gooddata-python-sdk/actions/runs/37293680431).