fix(reasoning): detect bare READY markers and honor the last decision - #6882
Open
CountClaw wants to merge 2 commits into
Open
fix(reasoning): detect bare READY markers and honor the last decision#6882CountClaw wants to merge 2 commits into
CountClaw wants to merge 2 commits into
Conversation
Planning readiness only matched the full instructional phrase "READY: I am ready to execute the task.", so models that conclude with a short-form READY line (common with Ollama/local models) were stuck in endless refine loops. Introduce response_indicates_ready() that accepts the full phrase and line-anchored READY / NOT READY markers, with the last marker winning. Closes crewAIInc#6204
📝 WalkthroughWalkthroughThe change adds shared readiness detection for full phrases and line-start ChangesReadiness detection
Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment Warning |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@lib/crewai/src/crewai/utilities/reasoning_handler.py`:
- Line 71: Update the full-phrase check in reasoning_handler.py at lines 71-71
to compare response.casefold() against _READY_FULL_PHRASE.casefold(), preserving
the existing matching behavior. Add a regression assertion in
test_response_indicates_ready.py at lines 14-20 covering an embedded lowercase
full phrase.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 751c3f04-878b-4708-a335-e6d4ca27b3d8
📒 Files selected for processing (2)
lib/crewai/src/crewai/utilities/reasoning_handler.pylib/crewai/tests/utilities/test_response_indicates_ready.py
| if last_decision is not None: | ||
| return last_decision | ||
|
|
||
| return _READY_FULL_PHRASE in response |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
Make full-phrase matching case-insensitive.
Line 71 uses a case-sensitive containment check. A lowercase full phrase that is not at line start does not match the short-marker regex and returns False. Normalize both strings with casefold(). Add a regression test for an embedded lowercase full phrase.
lib/crewai/src/crewai/utilities/reasoning_handler.py#L71-L71: compareresponse.casefold()with_READY_FULL_PHRASE.casefold().lib/crewai/tests/utilities/test_response_indicates_ready.py#L14-L20: add an assertion for an embedded lowercase full phrase.
Proposed fix
- return _READY_FULL_PHRASE in response
+ return _READY_FULL_PHRASE.casefold() in response.casefold()📍 Affects 2 files
lib/crewai/src/crewai/utilities/reasoning_handler.py#L71-L71(this comment)lib/crewai/tests/utilities/test_response_indicates_ready.py#L14-L20
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@lib/crewai/src/crewai/utilities/reasoning_handler.py` at line 71, Update the
full-phrase check in reasoning_handler.py at lines 71-71 to compare
response.casefold() against _READY_FULL_PHRASE.casefold(), preserving the
existing matching behavior. Add a regression assertion in
test_response_indicates_ready.py at lines 14-20 covering an embedded lowercase
full phrase.
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.
What
Detect bare READY markers and honor the last readiness decision in planning responses.
Why
Supersedes Kyou12138#6754 after rebasing onto latest
main(original PR branch could not be force-updated from this environment due to missingworkflowOAuth scope on that account).Closes the same issue intent as #6754 / original fix for ready-marker detection.