feat(chatbi): §5-3 低置信 RAG 方案预览与 plan_execution_token#100
Merged
Conversation
明确 Ink 模块、FE 验收、Harness 跨仓节奏与 5-2 差异；更新 RECENT/backlog/母单 5-3 指针。 Co-authored-by: Cursor <cursoragent@cursor.com>
task in_progress；C1 契约与阶段表；invoke_00 供 semi_auto 22→30→40。 Co-authored-by: Cursor <cursoragent@cursor.com>
…eview 放行 22-R1 与 30 开工；HG-REINSPECT 仍 pending 至 50 后。 Co-authored-by: Cursor <cursoragent@cursor.com>
扩展 clarify 至 rag_search：preview_only 检索方案、clarify_plan_once 令牌按工具校验；契约增量 rewrite_query 等键；Harness 22/30/40 invoke 与 R1 审查落盘。 Co-authored-by: Cursor <cursoragent@cursor.com>
KPI 100% pass；母单/SPEC 同步；reinspect v1；diary 样本索引；task→done。 Co-authored-by: Cursor <cursoragent@cursor.com>
浏览器 E2E 截图、round1/round2 Timeline JSON、NOTES 记录 LLM 缺日期提示词； README 对齐路线 A 联调 env；附 TestClient 导出脚本供 stub 再生。 Co-authored-by: Cursor <cursoragent@cursor.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
rag_search路径输出agent.plan.preview（rewrite_query、plan_execution_token等），clarify_plan_once通用化；确认后带 token 跳过agent.clarify并执行检索（api/agent.py、api/chatbi_plan_token.py、api/tools.py）。_contract_manifest.json增补 RAG 预览键；pytesttest_v3_rag_plan_*/ plan token 用例。docs/tasks/done/、50 reinspect、invoke 链；母单 SPEC §5-3 / §6 RAG 项已勾选。docs/diary/samples/chatbi-v3-lowconf-rag-preview/真机截图、E2E Timeline、NOTES-future-diary-llm-date.md（答案质量 / LLM 缺日期提示词，非闸门缺陷）。依赖：Ink FE 已在
main@72f8f0c（确认卡「按预览执行」）；本 PR 仅后端仓。Test plan
pytest tests -m "not intent_eval and not intent_benchmark"python tools/tech_graph_contract_check.py（若 CI 要求）CHATBI_V3_LOW_CONFIDENCE_CLARIFY=1、CHATBI_V3_PLAN_PREVIEW_CONFIRM=1、INTENT_MIN_CONFIDENCE=1.0→ 问「2026-04-28日记的大致内容」→ 14 条 preview+clarify → 按预览执行 → 无 clarify、执行rag_search（见 diary 样本 README）Out of scope / follow-up
docs/diary/samples/chatbi-v3-lowconf-rag-preview/NOTES-future-diary-llm-date.md，建议单独 task 注入 wall-clock 日期与 KB 边界 prompt。jsonPKmermaidfixture 变更不在本 PR 内。CI 状态（自动 · pr-post-ci）
Required 全绿：是
变更范围（自动统计）
文件数：30
docs/api/tests/scripts/⚠ automerge 路径闸：含
api/、tests/、.github/workflows/等 — 勿打automerge或须人审 merge。命中路径
api/agent.pyapi/chatbi_plan_token.pyapi/tools.pytests/test_chatbi_plan_token.pytests/test_unified_chat_backend_v2_agent.py