feat: 給訪談 bot 共用的 interview briefing(purpose + 累積 context)#27
Open
MakiDevelop wants to merge 1 commit into
Open
feat: 給訪談 bot 共用的 interview briefing(purpose + 累積 context)#27MakiDevelop wants to merge 1 commit into
MakiDevelop wants to merge 1 commit into
Conversation
根因修法。pilot 連續 4 個 bug(EVASION 誤判 / resume 把控制訊息當題目 / PII 誤 redact / follow-up 咬語氣詞)的共同根因:每個 LLM call 只拿到 當前問題、沒有訪談目的、沒有累積的對話脈絡 —— bot 沒頭沒尾,不知道 為何問、不知道前面聊過什麼、不知道怎麼接話。 Codex + Gemini 雙審設計、Chair 拍板: - 新模組 briefing.py:build_interview_briefing 組裝 purpose(訪談目的, 明示困惑/痛苦是材料不是迴避)+ 進度 + durable summary(anchors/ triples)+ coverage gaps + 最近逐字 - InterviewBriefing dataclass + 4 種 render mode(full / follow_up / classifier / anchor),各 LLM call 拿到適量 context - process_turn 每 turn 組裝一次,注入 evaluate_depth / extract_anchors / _final_reply / generate_follow_up - 全部 briefing 參數 optional(=None),向後相容、零行為改變 Constraint: 在既有 pipeline 上加 context 層;不重寫成 LLM-driven、 不改 DB schema、不擴張 ontology Directive: classifier mode 只給 purpose + 近期逐字 — EVASION 誤判的根因 修法;anchor mode 不給完整舊 anchors,避免 confirmation bias Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Owner
Author
Gemini 獨立 code review — 無 blockerGemini(Analyst)對 結論:無 blocker,可 commit/merge。 6 個檢查點:
review chain 完整:設計 Codex+Gemini 雙審 → Codex 實作 → Claude 獨立驗證(287 全綠 + 逐行)→ Gemini 獨立 review(本則)。 follow-up(非 blocker): |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
摘要
根因修法。 一場真人 pilot 連續踩了 4 個 bug(#23 EVASION 誤判、#24 resume 把控制訊息當題目、#25 PII 誤 redact、#26 follow-up 咬語氣詞)。四個都是症狀,根因同一個:
修法(Codex + Gemini 雙審設計,Chair 拍板)
新增「共用 interview briefing」層,注入到每個 LLM call:
briefing.py:INTERVIEW_PURPOSE常數 —— 訪談目的陳述(明示「困惑/懷疑/痛苦是材料,不是迴避」)。build_interview_briefing()—— 每 turn 組裝:purpose + 進度(第幾週)+ durable summary(anchors ≤12 / triples ≤12)+ coverage gaps(≤8)+ 最近逐字(≤8 turns)。純 deterministic,原料全來自既有 DB。InterviewBriefingdataclass + 4 種render(mode):full/follow_up/classifier/anchor—— 各 LLM call 拿到適量 context。evaluate_depth(classifier mode —— EVASION 誤判的根因修法)、extract_anchors(anchor mode)、_final_reply(full)、generate_follow_up(follow_up)。process_turn每 turn 組裝一次、傳遍所有下游。briefing參數 optional(=None) → 向後相容、零行為改變。範圍
本 slice = 在既有 pipeline 上加一層共用 context。不是重寫成 LLM-driven 訪談、不改 DB schema、不擴張 ontology。
驗證
review chain
設計:Codex + Gemini 雙審收斂 → Chair 拍板。實作:Codex。驗證:Claude 獨立(287 全綠 + briefing.py 逐行 + 整合 diff 逐行)。Gemini 獨立 code review 進行中,結果會補在本 PR comment。
注意
🤖 Generated with Claude Code