Conversation
6 tasks
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughAdds feedback-driven refinement: two POST endpoints (/refine and /weekly/refine) accept previous response + feedback, build initial agent state, and run new LangGraph agents (coach_refine_graph and weekly_coach_refine_graph) to produce validated refined SkillLab or WeeklyRoutine responses. Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant API as /refine Endpoint
participant Agent as coach_refine_graph
participant LLM1 as OpenAI (gpt-4o-mini)
participant Retriever as retrieve_drills
participant LLM2 as OpenAI (gpt-4o)
Client->>API: POST /refine (original_request + previous_response + feedback)
API->>Agent: invoke graph with initial_state
Agent->>LLM1: classify_feedback (re_retrieve | regenerate_only)
LLM1-->>Agent: feedback_type
alt feedback_type == "re_retrieve"
Agent->>Retriever: re_retrieve (update context)
Retriever-->>Agent: updated context
end
Agent->>LLM2: refine_generate (profile + previous_response + feedback + context)
LLM2-->>Agent: refined JSON
Agent->>Agent: validate JSON -> final_response
Agent-->>API: final_response
API->>Client: SuccessResponse[SkillLabResponse]
sequenceDiagram
participant Client
participant API as /weekly/refine Endpoint
participant Agent as weekly_coach_refine_graph
participant LLM1 as OpenAI (gpt-4o-mini)
participant Retriever as retrieve_drills
participant LLM2 as OpenAI (gpt-4o)
Client->>API: POST /weekly/refine (original_request + previous_response + feedback)
API->>Agent: invoke graph with initial_state (week_plan from previous_response.days)
Agent->>LLM1: classify_feedback (re_retrieve | regenerate_only)
LLM1-->>Agent: feedback_type
alt feedback_type == "re_retrieve"
Agent->>Retriever: re_retrieve (per-day drill retrieval)
Retriever-->>Agent: updated per-day context
end
Agent->>Agent: refine_generate (aggregate per-day context + available_time)
Agent->>LLM2: prompt for WeeklyRoutineResponse JSON
LLM2-->>Agent: refined weekly routine JSON
Agent->>Agent: validate JSON -> final_response
Agent-->>API: final_response
API->>Client: SuccessResponse[WeeklyRoutineResponse]
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 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 |
zweadfx
changed the title
![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 the current code and only fix it if needed.
Inline comments:
In `@src/api/v1/endpoints/skill.py`:
- Around line 205-210: In the except asyncio.TimeoutError handler, suppress the
original exception chain by re-raising the HTTPException with "from None" so the
traceback doesn't include the TimeoutError; update the raise HTTPException(...)
in the block that catches asyncio.TimeoutError (the endpoint's timeout handler)
to use "raise HTTPException(... ) from None" referencing asyncio.TimeoutError
and HTTPException to locate the change.
🪄 Autofix (Beta)
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: defaults
Review profile: CHILL
Plan: Pro
Run ID: 2570895b-4f47-4631-8e89-7932c85464ca
📒 Files selected for processing (4)
src/api/v1/endpoints/skill.pysrc/models/refine_schema.pysrc/services/agents/coach_refine_agent.pysrc/services/agents/weekly_coach_refine_agent.py
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.
어떤 변경사항인가요?
작업 상세 내용
체크리스트
관련 이슈
리뷰 포인트
참고사항 및 스크린샷(선택)
피드백 루프 그래프 구조:
classify_feedback ──조건분기──┬── re_retrieve → refine_generate → END
└─────────────→ refine_generate → END
Summary by CodeRabbit