Conversation
…luation mode - Add full_techniques branch in save_evaluation_results() to convert BMAD category scores to sommelier_outputs format - Add BMAD category themes (Problem Definition, Technical Design, Implementation, Documentation) to frontend sommeliers.ts - Add SOMMELIER_ROLES mapping for full_techniques categories in api.ts Fixes issue where all 75-technique results displayed as Jean-Pierre due to missing mode-specific handling
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Summary of ChangesHello @ComBba, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request addresses a critical issue where the 75-technique evaluation mode was failing to display results accurately on the frontend. The changes introduce robust backend logic to correctly parse and format BMAD category scores, which are then seamlessly integrated into the frontend with new, distinct themes and role mappings. This ensures that users receive comprehensive and visually appropriate evaluation feedback for the Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. Walkthrough백엔드 평가 서비스에 새로운 "full_techniques" 평가 모드를 추가하여 카테고리별 점수를 계산하고 상세한 평가 결과를 생성합니다. 프론트엔드는 네 개의 BMAD 카테고리 매핑과 해당 테마 정의를 추가하여 이를 지원합니다. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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 |
… technique details - Change full_techniques result to use 8 tasting note categories instead of 4 BMAD categories - Add TechniqueDetail model to backend and type to frontend - Add expandable technique details section in SommelierCard showing individual technique results - Add 8 tasting note themes (Aroma, Palate, Body, Finish, Balance, Vintage, Terroir, Cellar Notes) - Each category shows success/failed/skipped techniques with expand/collapse UI
![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
🤖 Fix all issues with AI agents
In `@backend/app/services/evaluation_service.py`:
- Around line 371-372: The computed scaled_score can exceed 100 if raw_score >
max_score; update the scaling logic in evaluation_service.py (the raw_score,
max_score, scaled_score computation) to clamp the result into the 0–100 range
(e.g., compute the fraction, multiply by 100, then apply min(max(..., 0), 100)
and convert to int) so UI components like getScoreTier or progress bars never
receive values >100.
🧹 Nitpick comments (2)
backend/app/services/evaluation_service.py (2)
346-347:int()대신round()를 사용하는 것이 더 정확합니다.
int(normalized_score)는 소수점 이하를 버립니다 (예: 84.9 → 84).grand_tasting경로에서는int(aggregate_score * 20)을 사용하므로 비슷한 패턴이지만, 0-100 범위의 점수를 변환할 때는round()가 사용자 기대에 더 부합합니다.♻️ round() 적용 제안
- overall_score = int(normalized_score) + overall_score = round(normalized_score)
358-363:BMAD_CATEGORY_CONFIG를 모듈 수준 상수로 추출하는 것을 고려하세요.대문자 네이밍은 Python에서 모듈 수준 상수 컨벤션입니다. 현재 함수 내부에 정의되어 있어 호출마다 재생성됩니다. 성능에 큰 영향은 없지만, 테스트 용이성과 재사용성을 위해 모듈 상단으로 이동하는 것이 좋습니다.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request effectively addresses a bug where evaluation results for the full_techniques mode were not handled correctly. The changes introduce a new logic branch in the backend to process and format these results, and the frontend is updated accordingly with new themes and mappings to display them. The implementation is clear and follows the existing structure. I've included one suggestion to improve maintainability by defining a configuration dictionary as a module-level constant.
|
|
||
| summary = ( | ||
| f"Comprehensive evaluation using 75 techniques. " | ||
| f"Quality Gate: {quality_gate}. " | ||
| f"Coverage: {coverage * 100:.1f}%." | ||
| ) |
There was a problem hiding this comment.
For better maintainability and performance, consider defining BMAD_CATEGORY_CONFIG as a module-level constant outside of this function. Since it's a static configuration, it doesn't need to be redefined on every function call. This also makes it clearer that this is a fixed configuration for the full_techniques mode.
- Move TASTING_NOTE_CONFIG to module-level constant for maintainability - Use round() instead of int() for normalized_score (more accurate) - Clamp scaled_score to 0-100 range to prevent UI issues
…lier-display fix(full_techniques): add proper result handling for 75-technique evaluation mode
1 participant
Summary
full_techniquesbranch insave_evaluation_results()to convert BMAD category scores tosommelier_outputsformatsommeliers.tsapi.tsProblem
When running 75-technique evaluation mode (
full_techniques), all results were incorrectly displayed as "Jean-Pierre" / "Final Synthesis" because:save_evaluation_results()had no handling forfull_techniquesmode - it fell through tosix_sommelierslogic which found no resultsgetSommelierTheme()returnedjeanpierreas fallback when IDs didn't match any defined sommelierSolution
Backend (
evaluation_service.py):elif is_full_techniques:branch to handle BMAD category scoressommelier_outputsformatFrontend (
sommeliers.ts):Frontend (
api.ts):Files Changed
backend/app/services/evaluation_service.py- Added full_techniques result handlingfrontend/src/lib/sommeliers.ts- Added BMAD category themesfrontend/src/lib/api.ts- Added role mappingsSummary by CodeRabbit
릴리스 노트