feat(ai): 인성·자소서 평가위원 (회의적 리뷰 D)#141
Merged
Merged
Conversation
임원면접 품질 감사에서 3/3로 확인된 갭: PERSONALITY/INTEGRATED 면접의 인성·자소서
답변이 기술 축(기술/논리/전달)으로만 채점되어 평가에서 빠짐.
- chain/prompts/personality_evaluation.py(신규): 자소서 경험의 소유·진정성, 지원동기·
가치관·성장 서사 일관성, 표준 인성 주제 답변의 구체성·STAR를 평가.
- feedback_generation_chain: PERSONALITY_EVALUATOR_LABEL="인성·자소서", PersonalityEvaluator
Protocol + LlmPersonalityEvaluator + build 체인(첫인상 평가위원 미러).
- feedback_consumer: _evaluate_personality(req) — mode∈{PERSONALITY,INTEGRATED} + 실질
경험형 답변 있을 때만. 첫인상·직무적합도와 동일하게 panel_breakdown 에 가산(비집계) →
종합 점수(overall/기술/논리/전달) 불변(저위험). BEHAVIORAL 우선, 없으면 폴백/스킵.
- runner: LlmPersonalityEvaluator 주입.
- 테스트 3건(패널 추가/미해당 스킵/overall_score 불변). 전체 308 passed, flake8 clean.
프론트는 비-SPECIAL 라벨을 '면접관 패널 평가'로 렌더하므로 자동 노출(무변경).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
|
좋네요 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
변경 사항
#140 머지 전 회의적 max 리뷰에서 3/3로 확인된 최대 깊이갭: PERSONALITY/INTEGRATED 면접의 인성·자소서 답변이 기술 축(기술/논리/전달)으로만 채점되어 평가에서 빠짐 → 인성·자소서 평가위원 추가.
chain/prompts/personality_evaluation.py(신규): 자소서 경험의 소유·진정성, 지원동기·가치관·성장 서사 일관성, 표준 인성 주제 답변의 구체성·STAR 평가.EvaluatorResult스키마(점수 0~100/null + strength/weakness/detail/rationale) 재사용.feedback_generation_chain:PERSONALITY_EVALUATOR_LABEL="인성·자소서",PersonalityEvaluatorProtocol +LlmPersonalityEvaluator+ build 체인 — 첫인상 평가위원 미러.feedback_consumer:_evaluate_personality(req)—mode ∈ {PERSONALITY, INTEGRATED}+ 실질 경험형(비자기소개) 답변이 있을 때만. 첫인상·직무적합도와 동일하게panel_breakdown에 가산(비집계) →overall_score/기술·논리·전달 불변(저위험). BEHAVIORAL 우선, PERSONALITY 무태깅이면 전체 폴백, INTEGRATED 무 BEHAVIORAL이면 스킵. TECHNICAL/JOB_TAILORED엔 미실행.runner:LlmPersonalityEvaluator주입.검증
overall_score불변 assert), 전체 308 passed, flake8 clean.FeedbackReport는 비-SPECIAL 라벨을 '면접관 패널 평가'로 렌더 → 자동 노출(프론트 무변경).비고
🤖 Generated with Claude Code