docs(mvp): organize mvp documentation

devflow/index.md

@@ -2,32 +2,33 @@
 
 ## 项目
 
-| 日期 | slug | 领域 | 关键词 | 状态 |
+| 日期 | slug | 领域 | 关键词 | 关联 OpenSpec | 状态 |
-|---|---|---|---|---|
+|---|---|---|---|---|---|
-| 2026-07-05 | diagnosis-playbook-skills | Agent Skill/Playbook | read_skill, diagnosis playbook, progressive disclosure, payment timeout, MySQL pool, Redis timeout | openspec/changes/diagnosis-playbook-skills | implemented |
+| 2026-07-09 | interview-demo-quality-audit | Agent eval/demo/Prompt audit | interview demo preflight, prompt_audit, gatekeeper rules, diagnosis baseline, 12 fixtures | openspec/changes/archive/2026-07-09-interview-demo-quality-audit | archived |
+| 2026-07-08 | executor-composer-final-answer | Chat quality gate/evidence attribution | chat_composer, final answer, allowed_claims, allowed_hypotheses, safe fallback, composer_output | openspec/changes/archive/2026-07-08-executor-composer-final-answer | archived |
+| 2026-07-08 | diagnosis-eval-demo-gatekeeper-closure | Agent eval/demo/Gatekeeper | diagnosis eval matrix, stable demo scenarios, Gatekeeper rule set version, audit metadata | openspec/changes/archive/2026-07-08-diagnosis-eval-demo-gatekeeper-closure | archived |
+| 2026-07-08 | verifier-evidence-reference-fidelity | Chat质量门禁/证据归因 | evidence_refs, raw_path, Gatekeeper severity, verifier evidence excerpt, HikariCP mock, no_evidence | openspec/changes/archive/2026-07-08-verifier-evidence-reference-fidelity | archived |
 | 2026-07-07 | executor-evidence-output-contract | Chat质量门禁/证据归因 | Executor structured output, evidence bindings, Verifier structured claims, LOW_CONFID, hallucination | openspec/changes/archive/2026-07-07-executor-evidence-output-contract | archived |
 | 2026-07-07 | executor-v2-output-contract | Chat质量门禁/证据归因 | executor_evidence_v2, user_facing_answer removal, diagnosis_summary removal, structured renderer | openspec/changes/archive/2026-07-07-executor-v2-output-contract | archived |
 | 2026-07-07 | executor-gatekeeper-hook | Chat质量门禁/证据归因 | Gatekeeper, verifier payload, source_invocation_ids, tool_name match, self_evaluation | openspec/changes/archive/2026-07-07-executor-gatekeeper-hook | archived |
 | 2026-07-07 | executor-verifier-claim-checks | Chat质量门禁/证据归因 | Verifier claim_checks, facts_checked compatibility, effective verdict guardrail, malformed output downgrade | openspec/changes/archive/2026-07-07-executor-verifier-claim-checks | archived |
-| 2026-07-08 | executor-composer-final-answer | Chat quality gate/evidence attribution | chat_composer, final answer, allowed_claims, allowed_hypotheses, safe fallback, composer_output | openspec/changes/archive/2026-07-08-executor-composer-final-answer | archived |
-| 2026-07-08 | diagnosis-eval-demo-gatekeeper-closure | Agent eval/demo/Gatekeeper | diagnosis eval matrix, stable demo scenarios, Gatekeeper rule set version, audit metadata | openspec/changes/archive/2026-07-08-diagnosis-eval-demo-gatekeeper-closure | archived |
-| 2026-07-08 | verifier-evidence-reference-fidelity | Chat质量门禁/证据归因 | evidence_refs, raw_path, Gatekeeper severity, verifier evidence excerpt, HikariCP mock, no_evidence | openspec/changes/archive/2026-07-08-verifier-evidence-reference-fidelity | archived |
 | 2026-07-06 | rag-eval-pipeline-closure | RAG/评测/回归闭环 | lookupResult fixture, LookupKnowledgeTool snapshot, evidenceBlocks, contextPack, retrievalTrace, rerankTrace, baseline diff, fallback case | devflow/projects/2026-07-06-rag-eval-pipeline-closure | archived |
 | 2026-07-06 | modular-rag-pipeline | RAG/Agent工具/证据链 | modular RAG, lookup_knowledge, evidenceBlocks, contextPack, rerank, retrievalTrace, L0 hint, unfiltered retry | openspec/changes/archive/2026-07-06-modular-rag-pipeline | archived |
+| 2026-07-05 | diagnosis-playbook-skills | Agent Skill/Playbook | read_skill, diagnosis playbook, progressive disclosure, payment timeout, MySQL pool, Redis timeout | openspec/changes/diagnosis-playbook-skills | implemented |
 | 2026-07-05 | mvp-demo-interview-runbook | MVP Demo/Interview | Plan C, payment timeout, runbook, trace checklist, demo script | openspec/changes/archive/2026-07-05-mvp-demo-interview-runbook | archived |
 | 2026-07-05 | diagnosis-eval-baseline-diff | Agent 评测/回归 Diff | baseline diff, regression detection, evidence coverage, cost signal, markdown report | openspec/changes/archive/2026-07-05-diagnosis-eval-baseline-diff | archived |
 | 2026-07-04 | expand-diagnosis-eval-fixtures | Agent 评测/回归 Baseline | fixture coverage, baseline report, redis timeout, slow response, jvm memory risk | openspec/changes/archive/2026-07-05-expand-diagnosis-eval-fixtures | archived |
 | 2026-07-04 | diagnosis-eval-harness | Agent 评测/回归 Harness | fixed cases, trace validation, evidence coverage, verdict distribution, markdown report | openspec/changes/archive/2026-07-04-diagnosis-eval-harness | archived |
 | 2026-07-04 | evidence-trace-hardening | 证据链/降级契约/离线验证 | ToolInvocationRecorder, ToolTraceSummaryService, lookup_knowledge, query_logs, query_metrics, LOW_CONFID, REJECT | openspec/changes/archive/2026-07-04-evidence-trace-hardening | archived |
-| 2026-07-03 | mvp-demo-trace-acceptance | MVP Demo/trace/acceptance | mvp-demo, trace API, diagnosis_session, agent_step, tool_invocation, feedback | openspec/changes/archive/2026-07-03-mvp-demo-trace-acceptance | archived |
 | 2026-07-04 | aiops-traceable-diagnosis-entry | AIOps/trace/alert diagnosis | ai_ops, SSE, alert input, sessionId, diagnosis_session, trace API | openspec/changes/archive/2026-07-04-aiops-traceable-diagnosis-entry | archived |
 | 2026-07-04 | aiops-alert-scope-control | AIOps/scope/prompt control | payload mode, auto-discovery mode, queryPrometheusAlerts, HighCPUUsage | openspec/changes/archive/2026-07-04-aiops-alert-scope-control | archived |
-| 2026-05-29 | chatmodel-abstraction | 解耦/多模型路由 | ChatModel, EmbeddingModel, DeepSeek, BGE-M3, SiliconFlow, Spring AI | archived |
+| 2026-07-03 | mvp-demo-trace-acceptance | MVP Demo/trace/acceptance | mvp-demo, trace API, diagnosis_session, agent_step, tool_invocation, feedback | openspec/changes/archive/2026-07-03-mvp-demo-trace-acceptance | archived |
-| 2026-06-23 | phase1-infrastructure | 基础设施/文档管理 | MySQL, Redis, Milvus, Flyway, JPA, 向量检索, 类别过滤 | archived |
-| 2026-06-24 | lookup-knowledge-integration | 知识库检索 | L0精确匹配, L1语义检索, frontmatter, 混合检索 | archived |
-| 2026-06-25 | doc-management-ui | 前端开发/文档管理 | 文档管理页面, CRUD, 状态监控, 纯静态页面, API集成 | archived |
-| 2026-06-26 | session-storage | 会话存储/可观测 | diagnosis_session, agent_step, tool_invocation, token追踪, 多Agent路由 | openspec/changes/session-storage | archived |
-| 2026-06-29 | confidence-feedback | 质量评估/反馈机制 | evidence_score, selfEvaluation, feedback, useful, not_useful, case_library, BAD_CASE, tool_invocation规则引擎, 反馈按钮, sessionId回传 | openspec/changes/confidence-feedback | archived |
-| 2026-06-30 | session-dedup-knowledge-map | 去重/知识图谱 | RetrievedDocTracker, KnowledgeDomainService, knowledge_domain, covers, whenToRetrieve, Planner注入, ISS-001 | openspec/changes/archive/2026-06-30-session-dedup-knowledge-map | archived |
-| 2026-07-01 | executor-action-memory-relevance | 检索质量/行动记忆 | relevanceLevel, completenessHint, Min-Max归一化, RetrievedDocTracker域级记录, Executor检索约束, ISS-002 | openspec/changes/archive/2026-07-01-executor-action-memory-relevance | archived |
 | 2026-07-02 | chat-verifier-agent | Chat质量门禁/可追溯验证 | Verifier, groundedness_score, facts_checked, evidence_refs, tool_trace_summary, self_evaluation | openspec/changes/archive/2026-07-03-chat-verifier-agent | archived |
+| 2026-07-01 | executor-action-memory-relevance | 检索质量/行动记忆 | relevanceLevel, completenessHint, Min-Max归一化, RetrievedDocTracker域级记录, Executor检索约束, ISS-002 | openspec/changes/archive/2026-07-01-executor-action-memory-relevance | archived |
+| 2026-06-30 | session-dedup-knowledge-map | 去重/知识图谱 | RetrievedDocTracker, KnowledgeDomainService, knowledge_domain, covers, whenToRetrieve, Planner注入, ISS-001 | openspec/changes/archive/2026-06-30-session-dedup-knowledge-map | archived |
+| 2026-06-29 | confidence-feedback | 质量评估/反馈机制 | evidence_score, selfEvaluation, feedback, useful, not_useful, case_library, BAD_CASE, tool_invocation规则引擎, 反馈按钮, sessionId回传 | openspec/changes/confidence-feedback | archived |
+| 2026-06-26 | session-storage | 会话存储/可观测 | diagnosis_session, agent_step, tool_invocation, token追踪, 多Agent路由 | openspec/changes/session-storage | archived |
+| 2026-06-25 | doc-management-ui | 前端开发/文档管理 | 文档管理页面, CRUD, 状态监控, 纯静态页面, API集成 | archived |
+| 2026-06-24 | lookup-knowledge-integration | 知识库检索 | L0精确匹配, L1语义检索, frontmatter, 混合检索 | archived |
+| 2026-06-23 | phase1-infrastructure | 基础设施/文档管理 | MySQL, Redis, Milvus, Flyway, JPA, 向量检索, 类别过滤 | archived |
+| 2026-05-29 | chatmodel-abstraction | 解耦/多模型路由 | ChatModel, EmbeddingModel, DeepSeek, BGE-M3, SiliconFlow, Spring AI | archived |

devflow/projects/2026-06-30-session-dedup-knowledge-map/acceptance.md

@@ -48,7 +48,7 @@
 
 ## 遗留问题
 
-ISS-002：Executor 无约束重复调用 `lookup_knowledge`（单会话 20+ 次），knowledge map 和检索约束只注入了 Planner 未注入 Executor。详见 `mvp/issues/ISS-002-executor-unconstrained-lookup.md`。
+ISS-002：Executor 无约束重复调用 `lookup_knowledge`（单会话 20+ 次），knowledge map 和检索约束只注入了 Planner 未注入 Executor。详见 `mvp/issues/archived/ISS-002-executor-unconstrained-lookup.md`。
 
 ## 已知限制
 

devflow/projects/2026-07-03-mvp-demo-trace-acceptance/decisions.md

@@ -9,8 +9,8 @@
 ## Context
 
 - `devflow/index.md` was checked. Relevant history includes `session-storage`, `confidence-feedback`, `executor-action-memory-relevance`, and `chat-verifier-agent`.
-- `mvp/notes/agent-engineering-decisions.md` already recommends the next phase as "可复现 MVP Demo", including `mvp-demo` profile, fixed diagnosis case, one-click request, and `GET /api/diagnosis/{sessionId}/trace`.
+- `mvp/archive/2026-07-09-doc-cleanup/notes/agent-engineering-decisions.md` already recommends the next phase as "可复现 MVP Demo", including `mvp-demo` profile, fixed diagnosis case, one-click request, and `GET /api/diagnosis/{sessionId}/trace`.
-- `mvp/issues/ISS-003-mvp-design-implementation-review.md` identifies test stability, session traceability, verifier evidence chain, upload path, and SupervisorAgent consistency as recent MVP concerns. Security cleanup is intentionally deferred by user decision.
+- `mvp/issues/active/ISS-003-mvp-design-implementation-review.md` identifies test stability, session traceability, verifier evidence chain, upload path, and SupervisorAgent consistency as recent MVP concerns. Security cleanup is intentionally deferred by user decision.
 
 ## Question Pool
 

devflow/projects/2026-07-07-executor-evidence-output-contract/acceptance.md

@@ -2,7 +2,7 @@
 
 ## Draft Acceptance
 
-- [x] Issue exists: `mvp/issues/executor-evidence-attribution-hallucination.md`.
+- [x] Issue exists: `mvp/issues/active/executor-evidence-attribution-hallucination.md`.
 - [x] OpenSpec change artifacts exist.
 - [x] devflow tracking files exist.
 - [x] OpenSpec validation passes.

devflow/projects/2026-07-07-executor-v2-output-contract/evidence.md

@@ -5,7 +5,7 @@
 - `devflow/projects/2026-07-07-executor-evidence-output-contract`: V1 evidence-attribution contract kept `user_facing_answer`.
 - `devflow/projects/2026-07-02-chat-verifier-agent`: Verifier consumes explicit inputs and should not see intermediate reasoning.
 - `devflow/projects/2026-07-04-evidence-trace-hardening`: evidence summaries and tool invocation references are the evidence foundation.
-- `mvp/issues/executor-structured-output-v2.md`: staged implementation design; stage one is Executor V2 output contract.
+- `mvp/issues/design-notes/executor-structured-output-v2.md`: staged implementation design; stage one is Executor V2 output contract.
 
 ## Code Evidence
 

devflow/projects/2026-07-08-verifier-evidence-reference-fidelity/brief.md

@@ -41,4 +41,4 @@ Make Executor cite concrete tool evidence, make Gatekeeper validate that citatio
 ## OpenSpec
 
 - Change: `openspec/changes/verifier-evidence-reference-fidelity`
-- Source issue: `mvp/issues/ISS-007-verifier-evidence-summary-fidelity.md`
+- Source issue: `mvp/issues/archived/ISS-007-verifier-evidence-summary-fidelity.md`

devflow/projects/2026-07-09-interview-demo-quality-audit/acceptance.md

@@ -0,0 +1,46 @@
+# Acceptance
+
+## Static Verification
+
+- `openspec validate interview-demo-quality-audit --strict`
+  - Result: passed.
+  - Coverage: OpenSpec proposal/design/spec/tasks consistency.
+- PowerShell parser/runtime readiness check:
+  - Command: `powershell -NoProfile -ExecutionPolicy Bypass -File mvp/demo/scripts/run-interview-demo-check.ps1 -BaseUrl http://127.0.0.1:1 -OutputDir target/demo-check-syntax`
+  - Result: expected failure with actionable readiness message.
+  - Coverage: script parses under Windows PowerShell and fails before issuing diagnosis requests when service is unreachable.
+
+## Script Verification
+
+- `mvn -q "-Dtest=DiagnosisTraceEvaluatorTest" test`
+  - Result: passed.
+  - Coverage: 12/12 fixed eval fixtures, Prompt audit evaluator checks, Gatekeeper rule metadata checks, regenerated baseline reports.
+- `mvn -q "-Dtest=ChatServiceSequentialAgentTest" test`
+  - Result: passed.
+  - Coverage: Chat verifier evaluation persists `prompt_audit`.
+- `mvn -q "-Dtest=DiagnosisTraceEvaluatorTest,DiagnosisEvalBaselineDiffTest,ChatServiceSequentialAgentTest,ExecutorGatekeeperServiceTest,VerifierInputHookTest" test`
+  - Result: passed.
+  - Coverage: broader eval, baseline diff, Chat sequential flow, Gatekeeper, and Verifier input hook regression set.
+- `mvn -q -DskipTests compile`
+  - Result: passed.
+  - Coverage: main source compilation.
+
+## E2E Verification
+
+- Started service with:
+  - `mvn spring-boot:run -Dspring-boot.run.profiles=mvp-demo`
+- Ran:
+  - `powershell -NoProfile -ExecutionPolicy Bypass -File mvp/demo/scripts/run-interview-demo-check.ps1 -BaseUrl http://localhost:9900 -SessionId mvp-demo-interview-quality-audit-001`
+- Result: passed.
+- Summary:
+  - `chatSuccess=true`
+  - `verdict=LOW_CONFID`
+  - `gatekeeperStatus=fail`
+  - `gatekeeperRuleSetVersion=gatekeeper-rules-v1`
+  - `promptAuditVersion=chat-prompts-v1`
+  - tools included `lookup_knowledge`, `query_logs`, `query_metrics`, and `get_available_log_topics`
+- Note: live E2E remains a compatibility check, not the deterministic PASS oracle. The fixed fixture baseline is the regression source of truth.
+
+## Not Verified
+
+- Browser UI inspection was not required for this change because the scope is backend trace/eval/demo script documentation, not frontend behavior.

devflow/projects/2026-07-09-interview-demo-quality-audit/brief.md

@@ -0,0 +1,23 @@
+# Interview Demo Quality Audit Brief
+
+## Background
+
+The MVP already demonstrates traceable Agent diagnosis with Planner, Executor, Gatekeeper, Verifier, Composer, evidence tools, trace persistence, and deterministic eval fixtures. The remaining interview-readiness gap is not a new Agent architecture; it is making the demo easier to run and making prompt/rule changes easier to audit.
+
+## Goal
+
+Stabilize the interview demo path, expand fixture-backed evaluation, and persist prompt/Gatekeeper audit metadata so the project can explain and verify Agent behavior during interviews.
+
+## Scope
+
+- Add prompt audit metadata to Chat verifier evaluation.
+- Extend deterministic eval cases and baseline reports.
+- Add an interview demo preflight/check script.
+- Update MVP demo and architecture documentation.
+
+## Non-goals
+
+- No public API or database schema changes.
+- No new SubAgent split, MCP migration, process isolation, or AIOps LLM Verifier.
+- No guarantee that every live LLM run returns PASS.
+

devflow/projects/2026-07-09-interview-demo-quality-audit/decisions.md

@@ -0,0 +1,111 @@
+# interview-demo-quality-audit Decisions
+
+## Clarify
+
+- Entry summary: stabilize the interview demo, expand deterministic eval coverage, and add Prompt/Gatekeeper version audit.
+- Slug: `interview-demo-quality-audit`.
+- Devflow scale: `standard`.
+- Interface impact: L2 internal contract change because `verifier_evaluation` gains `prompt_audit`; no public HTTP API or database schema change.
+
+## Context
+
+- `devflow/index.md` used: related entries found for `diagnosis-eval-demo-gatekeeper-closure`, `executor-composer-final-answer`, `verifier-evidence-reference-fidelity`, `mvp-demo-interview-runbook`, and `diagnosis-eval-baseline-diff`.
+- Relevant glossary:
+  - Evidence Tools produce incident facts and must be recorded in `tool_invocation`.
+  - Verifier should not use skills/runbooks as incident evidence.
+  - Diagnosis Playbook Skill is workflow guidance, not a fact source.
+- Historical constraints that must enter OpenSpec:
+  - Diagnosis eval is deterministic and fixture-backed; no LLM-as-judge.
+  - Stable demo scenarios are documentation/payloads plus deterministic fixtures; live E2E is a compatibility check, not a guaranteed PASS oracle.
+  - Gatekeeper rule metadata is already metadata-only and should not become dynamic rule execution.
+  - Composer is the final expression layer and must not leak raw Executor JSON.
+
+## Question Pool
+
+| ID | Dimension | Mode | Question | Status |
+|---|---|---|---|---|
+| Q1 | Terminology | evidence-driven | What should the new audit metadata be called? | Resolved |
+| Q2 | Boundary | evidence-driven | Does this require public API or schema changes? | Resolved |
+| Q3 | Acceptance | evidence-driven | Which current assets define deterministic acceptance? | Resolved |
+| Q4 | Technical | evidence-driven | Where should prompt version metadata live with minimal implementation risk? | Resolved |
+| Q5 | Scope | user-interview | Should live E2E be mandatory for all scenarios? | Confirmed by objective as conditional |
+
+## Evidence-driven Conclusions
+
+- Q1 conclusion: use `prompt_audit` for prompt version metadata and keep existing `gatekeeper_result.rule_set_version`.
+- Q2 conclusion: keep this as an internal trace/self-evaluation contract change. Do not add endpoints, tables, or new Agent roles.
+- Q3 conclusion: `DiagnosisTraceEvaluatorTest`, baseline reports, fixed fixtures, and demo scripts define current acceptance style.
+- Q4 conclusion: add a small Chat prompt audit catalog near `ChatService` prompt loading and persist a compact snapshot with verifier evaluation.
+- Q5 conclusion: run live E2E with `mvp-demo` profile if dependencies are available; otherwise record the blocker and rely on deterministic eval/unit evidence.
+
+## Specify / Alignment
+
+| Check | Status | Notes |
+|---|---|---|
+| proposal goals -> proposal | Aligned | Proposal covers demo preflight, eval expansion, prompt audit, and docs. |
+| proposal scope/constraints -> design | Aligned | Design records no public API/schema changes, prompt audit shape, eval fields, and demo script behavior. |
+| design decisions -> specs/tasks | Aligned | Specs cover persisted prompt audit, evaluator checks, baseline, and demo script outputs. |
+| specs observable behavior -> tasks | Aligned | Each requirement has implementation and verification tasks. |
+
+## Audit
+
+Input -> processing -> output chain:
+
+```text
+prompt resource metadata
+  -> ChatService / PromptAudit snapshot
+  -> verifier_evaluation.prompt_audit
+  -> Trace API / eval fixtures
+  -> DiagnosisTraceEvaluator baseline
+
+run-interview-demo-check.ps1
+  -> service readiness
+  -> chat / trace / feedback
+  -> mvp/demo/output summary
+```
+
+Architecture risk assessment:
+
+1. The audit shape is intentionally compact and internal; storing full prompt text would create noisy traces and possible sensitive-content risk.
+2. Eval should assert versions by explicit metadata, not by prompt content hashes that churn during local prompt edits.
+3. Live demo checks may still be LOW_CONFID because LLM output is not deterministic; deterministic fixtures remain the regression source of truth.
+4. No devflow/OpenSpec conflict found.
+
+## Commit Gate
+
+- `openspec validate interview-demo-quality-audit --strict`: passed.
+- File completeness:
+  - `proposal.md`: present.
+  - `design.md`: present.
+  - `specs/`: present for `chat-verifier-agent`, `diagnosis-eval-harness`, and `mvp-demo-trace-acceptance`.
+  - `tasks.md`: present.
+- Consistency:
+  - Proposal goals map to design sections.
+  - Design decisions map to spec requirements and executable tasks.
+  - Task acceptance checks are verifiable.
+- `.committed` marker created.
+
+## Current Checkpoint
+
+- Commit completed.
+- Apply is authorized by the original objective: "完成后归档提交".
+
+## Pre-apply Research
+
+- Capability source: sm-flow built-in apply protocol. `openspec-apply-change` was not invoked directly in this session.
+- Repository semantic search/LSP note: the requested `codebase-retrieval` and LSP tools were not available in the exposed toolset, so impact analysis used `rg`, direct file reads, OpenSpec/devflow artifacts, and targeted tests.
+- Reference implementation and reuse:
+  - `ChatService.persistVerifierEvaluation(...)` is the single persistence point for Chat verifier/composer audit data; prompt audit was added there to cover normal, fallback, and degraded Composer paths.
+  - `DiagnosisTraceEvaluator` and `DiagnosisEvalReportWriter` are the deterministic eval extension points; no LLM judge was introduced.
+  - `mvp/demo/scripts/run-payment-timeout-demo.ps1` provided the request/trace/feedback flow reused by the new interview preflight script.
+- Interface impact remains L2 internal trace contract: `verifier_evaluation.prompt_audit` and eval report fields are added; no public endpoint, table, or request DTO changed.
+
+## Apply Notes
+
+- Added compact Chat prompt audit metadata: `chat-prompts-v1`, with planner/executor/verifier/composer prompt versions and resource paths.
+- Extended diagnosis eval schema, result reporting, baseline fixtures, JSON report, and Markdown report for Prompt audit and Gatekeeper rule metadata.
+- Added two fixture-backed audit cases:
+  - `prompt-gatekeeper-audit-closure`
+  - `audit-metadata-low-confid`
+- Added `mvp/demo/scripts/run-interview-demo-check.ps1` to run service readiness, Chat, Trace, feedback, and summary output.
+- Updated MVP demo/eval/architecture docs to explain `prompt_audit.version`, `gatekeeper_result.rule_set_version`, and deterministic fixture baseline.

devflow/projects/2026-07-09-interview-demo-quality-audit/evidence.md

@@ -0,0 +1,58 @@
+# Evidence
+
+## Context Files Read
+
+- `devflow/index.md`
+- `devflow/glossary/CONTEXT.md`
+- `devflow/projects/2026-07-08-diagnosis-eval-demo-gatekeeper-closure/decisions.md`
+- `devflow/projects/2026-07-08-executor-composer-final-answer/decisions.md`
+- `mvp/architecture/current-mvp-architecture.md`
+- `mvp/architecture/agent-orchestration.md`
+- `mvp/architecture/executor-evidence-pipeline-refactor.md`
+- `mvp/architecture/harness-quality-gates.md`
+- `mvp/demo/README.md`
+- `mvp/demo/ten-minute-interview-demo.md`
+- `mvp/eval/README.md`
+- `mvp/eval/cases/diagnosis-cases.json`
+- `src/main/java/com/superbiz/agent/service/ChatService.java`
+- `src/main/java/com/superbiz/agent/service/ExecutorGatekeeperService.java`
+- `src/main/java/com/superbiz/agent/eval/DiagnosisTraceEvaluator.java`
+- `src/main/resources/gatekeeper/gatekeeper-rules.json`
+
+## Tooling Note
+
+The required `codebase-retrieval` and LSP tools were not exposed in this session. Impact analysis used `rg`, direct file reads, existing OpenSpec/devflow artifacts, and targeted tests instead.
+
+## Implementation Evidence
+
+- `src/main/java/com/superbiz/agent/service/ChatService.java`
+  - Adds `prompt_audit` under `verifier_evaluation` through the shared `persistVerifierEvaluation(...)` path.
+  - Uses compact metadata only: audit version, prompt names, prompt versions, and resource paths.
+- `src/main/java/com/superbiz/agent/eval/DiagnosisTraceEvaluator.java`
+  - Adds deterministic checks for `requirePromptAudit`, `expectedPromptAuditVersion`, `expectedPromptVersions`, and `requireGatekeeperRules`.
+- `src/main/java/com/superbiz/agent/eval/DiagnosisEvalReportWriter.java`
+  - Adds Prompt Audit and Gatekeeper rule count columns to Markdown reports.
+- `mvp/eval/cases/diagnosis-cases.json`
+  - Expands fixed baseline to 12 fixture-backed cases.
+- `mvp/eval/fixtures/prompt-gatekeeper-audit-closure-pass.json`
+  - Positive PASS fixture proving Prompt audit and Gatekeeper rule metadata closure.
+- `mvp/eval/fixtures/audit-metadata-low-confid.json`
+  - LOW_CONFID fixture proving safe answer behavior while audit metadata remains present.
+- `mvp/demo/scripts/run-interview-demo-check.ps1`
+  - Adds service readiness, Chat, Trace, feedback, and summary output for interview preflight.
+
+## Verification Evidence
+
+- OpenSpec:
+  - `openspec validate interview-demo-quality-audit --strict`: passed before archive.
+  - `openspec validate --specs --strict`: 10 specs passed after merging deltas into main specs.
+- Unit/eval:
+  - `mvn -q "-Dtest=DiagnosisTraceEvaluatorTest" test`: passed.
+  - `mvn -q "-Dtest=ChatServiceSequentialAgentTest" test`: passed.
+  - `mvn -q "-Dtest=DiagnosisTraceEvaluatorTest,DiagnosisEvalBaselineDiffTest,ChatServiceSequentialAgentTest,ExecutorGatekeeperServiceTest,VerifierInputHookTest" test`: passed.
+- Compile:
+  - `mvn -q -DskipTests compile`: passed.
+- E2E:
+  - Started `mvn spring-boot:run -Dspring-boot.run.profiles=mvp-demo`.
+  - Ran `mvp/demo/scripts/run-interview-demo-check.ps1` against `http://localhost:9900`.
+  - Summary recorded `chatSuccess=true`, `verdict=LOW_CONFID`, `gatekeeperRuleSetVersion=gatekeeper-rules-v1`, and `promptAuditVersion=chat-prompts-v1`.

mvp/README.md

@@ -1,8 +1,8 @@
 # SuperBizAgent MVP 文档
 
-**更新日期**：2026-07-05
+**更新日期**：2026-07-09
 
-本目录保存 MVP 阶段的架构、问题、演示、评测和数据表说明。当前架构入口已经整理到 `mvp/architecture/`，旧版架构材料已归档，避免继续把历史方案当成当前实现。
+本目录保存 MVP 阶段的架构、问题、演示、评测和数据表说明。当前材料按“当前入口”和“历史归档”拆开，避免把早期设计稿当成当前实现。
 
 ## 当前入口
 
@@ -12,6 +12,7 @@
 | [architecture/current-mvp-architecture.md](architecture/current-mvp-architecture.md) | 当前可运行系统架构 |
 | [architecture/interview-one-pager.md](architecture/interview-one-pager.md) | 面试一页式架构讲解 |
 | [architecture/agent-orchestration.md](architecture/agent-orchestration.md) | Agent 编排架构 |
+| [architecture/executor-evidence-pipeline-refactor.md](architecture/executor-evidence-pipeline-refactor.md) | Executor 证据链路改造记录 |
 | [architecture/harness-quality-gates.md](architecture/harness-quality-gates.md) | Harness 与质量门禁 |
 | [architecture/rag-architecture.md](architecture/rag-architecture.md) | RAG/知识检索新架构 |
 | [architecture/retrieval-observability.md](architecture/retrieval-observability.md) | 检索与可观测性架构 |
@@ -20,11 +21,12 @@
 | [architecture/knowledge-base-authoring.md](architecture/knowledge-base-authoring.md) | 知识库文档编写与维护 |
 | [architecture/data-model.md](architecture/data-model.md) | 数据模型总览 |
 | [architecture/evolution-roadmap.md](architecture/evolution-roadmap.md) | Agent 架构演进路线 |
-| [issues/rag-refactor-plan.md](issues/rag-refactor-plan.md) | RAG 重构计划和阶段拆解 |
+| [issues/README.md](issues/README.md) | MVP issue 索引 |
+| [issues/active/rag-refactor-plan.md](issues/active/rag-refactor-plan.md) | RAG 重构计划和阶段拆解 |
+| [tables/README.md](tables/README.md) | 当前 MySQL 表说明 |
 | [demo/README.md](demo/README.md) | Demo 运行和面试演示材料 |
 | [demo/ten-minute-interview-demo.md](demo/ten-minute-interview-demo.md) | 10 分钟面试演示脚本 |
 | [eval/README.md](eval/README.md) | 诊断评测材料 |
-| [issues/README.md](issues/README.md) | MVP issue 索引 |
 
 ## 当前系统一句话
 
@@ -39,6 +41,7 @@ mvp/
     current-mvp-architecture.md
     interview-one-pager.md
     agent-orchestration.md
+    executor-evidence-pipeline-refactor.md
     harness-quality-gates.md
     rag-architecture.md
     retrieval-observability.md
@@ -47,12 +50,17 @@ mvp/
     knowledge-base-authoring.md
     data-model.md
     evolution-roadmap.md
-    archive/2026-07-05-legacy/
+    archive/
   issues/
     README.md
-    rag-refactor-plan.md
+    active/
-    ISS-*.md
+    archived/
-    rag-*.md
+    design-notes/
+    rag/
+  tables/
+    README.md
+    *表-*.md
+    archive/
   demo/
     README.md
     ten-minute-interview-demo.md
@@ -65,9 +73,7 @@ mvp/
     cases/
     fixtures/
     reports/
-  notes/
+  archive/
-  plan/
-  tables/
 ```
 
 ## 当前核心设计
@@ -107,10 +113,11 @@ RAG
   -> tool_invocation
 ```
 
-## 旧文档说明
+## 归档说明
 
-旧版架构文档已移动到：
+历史材料分两类：
 
-- [architecture/archive/2026-07-05-legacy/](architecture/archive/2026-07-05-legacy/)
+- 旧架构文档：[architecture/archive/2026-07-05-legacy/](architecture/archive/2026-07-05-legacy/)
+- 本次文档清理归档：[archive/2026-07-09-doc-cleanup/](archive/2026-07-09-doc-cleanup/)
 
-归档文档只用于追溯设计历史。当前实现和后续规划以 `architecture/current-mvp-architecture.md` 与 `architecture/rag-architecture.md` 为准。
+归档文档只用于追溯设计历史。当前实现和后续规划以 `architecture/`、`issues/README.md`、`tables/README.md` 和 OpenSpec/devflow 的最新记录为准。

mvp/architecture/archive/2026-07-05-legacy/confidence-feedback.md

@@ -154,4 +154,4 @@ ALTER TABLE diagnosis_session ADD COLUMN answer LONGTEXT COMMENT 'Agent 返回
 
 - **LLM 观点层**：在 `selfEvaluation` 的 `llm_opinion` 字段叠加 LLM 结构化观点（has_root_cause、has_solution 等），作为独立 factors，不改变现有规则逻辑
 - **案例结构化字段**：useful 触发时自动提取 faultCategory / errorCode，替代暂时的 GENERAL
-- **重复召回问题**：Executor Prompt 约束或工具层 session 维度去重（见 [ISS-001](../issues/ISS-001-duplicate-retrieval.md)）
+- **重复召回问题**：Executor Prompt 约束或工具层 session 维度去重（见 [ISS-001](../../../issues/archived/ISS-001-duplicate-retrieval.md)）

mvp/architecture/harness-quality-gates.md

@@ -82,6 +82,23 @@ Prompt 层当前承担的门禁：
 - Chat Composer 不允许补事实，尤其不能把 `$.no_evidence` 表达为“已排除/确认没有”。
 - AIOps payload 模式必须聚焦输入告警。
 
+Chat 链路还会在 `verifier_evaluation.prompt_audit` 中持久化紧凑 Prompt 审计快照：
+
+```json
+{
+  "version": "chat-prompts-v1",
+  "prompts": [
+    {
+      "name": "chat_executor",
+      "version": "chat-executor-v2",
+      "resource": "prompts/chat-executor-prompt.md"
+    }
+  ]
+}
+```
+
+该快照只保存版本和资源路径，不保存完整 Prompt 文本。它用于面试演示、trace 回放和离线 baseline 解释“本次诊断使用了哪套 Prompt 契约”。
+
 ## 4. Trace Hooks
 
 `AgentLoggingHook` 是当前 Agent step 可观测性的核心。
@@ -196,7 +213,7 @@ Verifier 不再逐字核验 excerpt 真伪；这由 Gatekeeper 完成。Verifier
 diagnosis_session.self_evaluation.verifier_evaluation
 ```
 
-其中同时持久化 `executor_structured_output`、`gatekeeper_result`、`tool_trace_summary` 和 `composer_output`，用于 Trace 回放。
+其中同时持久化 `executor_structured_output`、`gatekeeper_result`、`tool_trace_summary`、`prompt_audit` 和 `composer_output`，用于 Trace 回放。
 
 ## 7. AIOps 规则门禁
 
@@ -233,7 +250,7 @@ diagnosis_session.self_evaluation.aiops_rule_evaluation
 - 同一工具调用次数上限。
 - 工具超时的统一熔断。
 - Gatekeeper 规则远程化或三层分离：索引层、元数据层、规则实现层。
-- Prompt 版本记录和回滚。
+- Prompt 版本回滚和更细粒度变更审计。
 - Verifier 对 AIOps 报告的 LLM 级事实校验。
 
 这些应在评测集扩大后逐步加入，避免一次性把诊断流程卡得过死。

mvp/architecture/rag-architecture.md

@@ -2,7 +2,7 @@
 
 **更新日期**：2026-07-06
 **状态**：当前主架构 + 后续演进边界  
-**关联计划**：`mvp/issues/rag-refactor-plan.md`
+**关联计划**：[`mvp/issues/active/rag-refactor-plan.md`](../issues/active/rag-refactor-plan.md)
 
 ## 1. 架构目标
 

mvp/archive/2026-07-09-doc-cleanup/README.md

@@ -0,0 +1,17 @@
+# 2026-07-09 MVP 文档清理归档
+
+本目录保存本次清理中从当前入口移出的历史设计材料。这些文档仍有追溯价值，但不再代表当前可运行实现。
+
+## 归档内容
+
+| 目录 | 内容 | 归档原因 |
+|---|---|---|
+| `discuss/` | 早期 Executor Prompt、L0、RAG 讨论稿 | 已被当前 architecture、OpenSpec change 和 issue 取代 |
+| `plan/` | `session-storage-design.md` | 会话存储已实现，当前表以 Flyway 和 `mvp/tables/` 为准 |
+| `notes/` | 早期工程决策和 Demo Trace 验收笔记 | 相关内容已沉淀到 architecture、demo、eval 和 devflow |
+
+## 使用原则
+
+- 当前架构以 `mvp/architecture/` 为准。
+- 当前表结构以 `mvp/tables/`、Flyway migration 和实体类为准。
+- 当前问题入口以 `mvp/issues/README.md` 为准。

mvp/demo/README.md

@@ -8,7 +8,9 @@
 - `interview-walkthrough.md`：面试讲解话术。
 - `evidence-pipeline-scenarios.md`：PASS / LOW_CONFID / REJECT / no-evidence 场景矩阵。
 - `trace-inspection-checklist.md`：Trace 字段检查清单。
+- `scripts/run-interview-demo-check.ps1`：面试预检脚本，包含服务可达性、Chat、Trace、反馈和 summary 输出。
 - `scripts/run-payment-timeout-demo.ps1`：本地可执行 Demo 脚本。
+- `interview-q-and-a.md`：面试追问回答，覆盖 Agent 工程取舍、审计和评测。
 - `requests/payment-timeout-chat.json`：固定 Chat 请求 payload。
 - `requests/narrow-highcpu-chat.json`：窄范围正向观察请求。
 - `requests/hikari-no-evidence-chat.json`：no-evidence 负向观察请求。
@@ -37,7 +39,7 @@ http://localhost:9900
 最快方式：
 
 ```powershell
-powershell -ExecutionPolicy Bypass -File mvp/demo/scripts/run-payment-timeout-demo.ps1
+powershell -ExecutionPolicy Bypass -File mvp/demo/scripts/run-interview-demo-check.ps1
 ```
 
 脚本会生成：
@@ -46,6 +48,7 @@ powershell -ExecutionPolicy Bypass -File mvp/demo/scripts/run-payment-timeout-de
 mvp/demo/output/chat-response.json
 mvp/demo/output/trace-response.json
 mvp/demo/output/feedback-response.json
+mvp/demo/output/interview-demo-summary.json
 ```
 
 手动请求：
@@ -85,6 +88,8 @@ Invoke-RestMethod `
 - `data.steps` 包含 planner / executor / verifier 等步骤
 - `data.toolInvocations` 包含 `lookup_knowledge`、`query_logs`、`query_metrics` 等证据工具
 - `data.session.selfEvaluation` 包含 verifier 或 rule evaluation
+- Chat V2 链路中，`data.session.selfEvaluation.verifier_evaluation.prompt_audit.version` 记录 Chat Prompt 审计版本
+- Chat V2 链路中，`data.session.selfEvaluation.verifier_evaluation.gatekeeper_result.rule_set_version` 记录 Gatekeeper 规则集版本
 
 ## 5. 提交反馈
 
@@ -176,8 +181,8 @@ AIOps 主线：
 
 面试时不要把所有安全场景都压到 live LLM 现场表现上。建议使用：
 
-- `scripts/run-payment-timeout-demo.ps1` 跑主路径。
+- `scripts/run-interview-demo-check.ps1` 跑主路径和预检 summary。
 - `evidence-pipeline-scenarios.md` 讲解 PASS / LOW_CONFID / REJECT / no-evidence 矩阵。
-- `mvp/eval/reports/baseline-report.md` 证明固定 fixture 10/10 通过。
+- `mvp/eval/reports/baseline-report.md` 证明固定 fixture 12/12 通过。
 
 这样可以同时展示真实链路和确定性回归能力。

mvp/demo/interview-q-and-a.md

@@ -0,0 +1,33 @@
+# 面试追问 Q&A
+
+## 为什么不用普通 Chatbot？
+
+这个项目的重点不是生成一段诊断文本，而是把诊断拆成可审计链路：Planner 拆解问题，Executor 调工具拿证据，Gatekeeper 用代码核验证据引用，Verifier 判断可推导性，Composer 生成最终表达。每次运行都能通过同一个 `sessionId` 回放。
+
+## 为什么 RAG 要做成显式工具？
+
+`lookup_knowledge` 保持显式工具调用，才能在 `tool_invocation` 里看到 Agent 查了什么、命中了什么、相关性等级是什么，以及最终答案是否真的使用了这些证据。隐式 Advisor 更方便，但不利于审计 Agent 决策。
+
+## 怎么防止 Executor 幻觉？
+
+Executor 不直接负责最终用户答案，而是输出 `executor_evidence_v2` 的微观事实和证据引用。Gatekeeper 会校验 `source_invocation_id`、`raw_path`、`evidence_excerpt` 是否真实存在；Verifier 再判断 claim 是否能由已验真的证据推出；Composer 只表达 Verifier 允许输出的内容。
+
+## LOW_CONFID 是失败吗？
+
+不是。`LOW_CONFID` 表示当前证据不足以支撑强结论，但系统仍然可以安全表达已确认事实和缺失信息。面试时可以把它作为“没有证据就不强答”的质量门禁，而不是模型能力失败。
+
+## Prompt 改了怎么审计？
+
+Chat verifier evaluation 里会记录 `prompt_audit.version`，并列出 planner、executor、verifier、composer 的 Prompt 版本和资源路径。它不保存完整 Prompt 文本，只保留用于回放和回归解释的紧凑元数据。
+
+## Gatekeeper 改了怎么审计？
+
+Gatekeeper 结果里记录 `gatekeeper_result.rule_set_version` 和已启用规则元数据摘要。规则执行仍是确定性 Java 代码，版本和规则元数据用于解释“这次引用验真用的是哪套规则”。
+
+## 为什么现在不拆 SubAgent？
+
+当前 MVP 的主要风险不是 Agent 数量不够，而是证据、验证和回归是否稳定。文档里的演进路线把 SubAgent 放在 P2：等故障类型、工具权限和评测集足够明确后再拆，避免只是移动复杂度。
+
+## 为什么 baseline 比 live demo 更重要？
+
+live demo 证明链路在当前环境能跑通，但 LLM 和外部依赖会波动。`mvp/eval` 的固定 fixture baseline 是确定性回归来源，用来判断 Prompt、工具、Gatekeeper、Verifier 或 Composer 的改动有没有让系统退化。

mvp/demo/scripts/run-interview-demo-check.ps1

@@ -0,0 +1,161 @@
+param(
+    [string]$BaseUrl = "http://localhost:9900",
+    [string]$SessionId = "mvp-demo-interview-payment-timeout-001",
+    [string]$RequestFile = "$PSScriptRoot/../requests/payment-timeout-chat.json",
+    [string]$OutputDir = "$PSScriptRoot/../output"
+)
+
+$ErrorActionPreference = "Stop"
+
+function Test-ServiceReachable {
+    param([string]$Url)
+
+    try {
+        $request = [System.Net.WebRequest]::Create($Url)
+        $request.Method = "GET"
+        $request.Timeout = 5000
+        $response = $request.GetResponse()
+        $response.Close()
+        return $true
+    } catch [System.Net.WebException] {
+        if ($_.Exception.Response -ne $null) {
+            $_.Exception.Response.Close()
+            return $true
+        }
+        return $false
+    }
+}
+
+function Get-TraceData {
+    param($TraceResponse)
+
+    if ($TraceResponse.PSObject.Properties.Name -contains "data") {
+        return $TraceResponse.data
+    }
+    return $TraceResponse
+}
+
+function Get-SelfEvaluation {
+    param($TraceData)
+
+    if ($null -eq $TraceData -or $null -eq $TraceData.session) {
+        return $null
+    }
+    return $TraceData.session.selfEvaluation
+}
+
+function Get-ToolNames {
+    param($TraceData)
+
+    if ($null -eq $TraceData -or $null -eq $TraceData.toolInvocations) {
+        return @()
+    }
+    return @($TraceData.toolInvocations | ForEach-Object { $_.toolName } | Where-Object { $_ } | Sort-Object -Unique)
+}
+
+New-Item -ItemType Directory -Force -Path $OutputDir | Out-Null
+
+Write-Host "Running interview demo preflight..."
+Write-Host "BaseUrl: $BaseUrl"
+Write-Host "SessionId: $SessionId"
+
+if (-not (Test-ServiceReachable -Url $BaseUrl)) {
+    throw "Service is not reachable: $BaseUrl. Start the app with mvp-demo profile first: mvn spring-boot:run -Dspring-boot.run.profiles=mvp-demo"
+}
+
+$request = Get-Content -Raw -Encoding UTF8 -Path $RequestFile | ConvertFrom-Json
+$request.Id = $SessionId
+$body = $request | ConvertTo-Json -Depth 8
+
+$chatRequest = @{
+    Method = "Post"
+    Uri = "$BaseUrl/api/chat"
+    ContentType = "application/json; charset=utf-8"
+    Body = $body
+}
+$chat = Invoke-RestMethod @chatRequest
+
+$chatPath = Join-Path $OutputDir "chat-response.json"
+$chat | ConvertTo-Json -Depth 30 | Set-Content -Encoding UTF8 -Path $chatPath
+
+$traceRequest = @{
+    Method = "Get"
+    Uri = "$BaseUrl/api/diagnosis/$SessionId/trace"
+}
+$trace = Invoke-RestMethod @traceRequest
+
+$tracePath = Join-Path $OutputDir "trace-response.json"
+$trace | ConvertTo-Json -Depth 80 | Set-Content -Encoding UTF8 -Path $tracePath
+
+$feedbackBody = @{
+    sessionId = $SessionId
+    feedback = "useful"
+} | ConvertTo-Json
+
+$feedbackRequest = @{
+    Method = "Post"
+    Uri = "$BaseUrl/api/feedback"
+    ContentType = "application/json; charset=utf-8"
+    Body = $feedbackBody
+}
+$feedback = Invoke-RestMethod @feedbackRequest
+
+$feedbackPath = Join-Path $OutputDir "feedback-response.json"
+$feedback | ConvertTo-Json -Depth 30 | Set-Content -Encoding UTF8 -Path $feedbackPath
+
+$traceData = Get-TraceData -TraceResponse $trace
+$selfEvaluation = Get-SelfEvaluation -TraceData $traceData
+$verifierEvaluation = $null
+if ($null -ne $selfEvaluation) {
+    $verifierEvaluation = $selfEvaluation.verifier_evaluation
+}
+
+$gatekeeperResult = $null
+$promptAudit = $null
+if ($null -ne $verifierEvaluation) {
+    $gatekeeperResult = $verifierEvaluation.gatekeeper_result
+    $promptAudit = $verifierEvaluation.prompt_audit
+}
+
+$verdict = $null
+$gatekeeperStatus = $null
+$gatekeeperRuleSetVersion = $null
+$promptAuditVersion = $null
+if ($null -ne $verifierEvaluation) {
+    $verdict = $verifierEvaluation.verdict
+}
+if ($null -ne $gatekeeperResult) {
+    $gatekeeperStatus = $gatekeeperResult.status
+    $gatekeeperRuleSetVersion = $gatekeeperResult.rule_set_version
+}
+if ($null -ne $promptAudit) {
+    $promptAuditVersion = $promptAudit.version
+}
+$toolNames = Get-ToolNames -TraceData $traceData
+$summaryPath = Join-Path $OutputDir "interview-demo-summary.json"
+
+$summary = [ordered]@{
+    sessionId = $SessionId
+    baseUrl = $BaseUrl
+    chatSuccess = $chat.data.success
+    verdict = $verdict
+    gatekeeperStatus = $gatekeeperStatus
+    gatekeeperRuleSetVersion = $gatekeeperRuleSetVersion
+    promptAuditVersion = $promptAuditVersion
+    toolNames = $toolNames
+    paths = [ordered]@{
+        chat = $chatPath
+        trace = $tracePath
+        feedback = $feedbackPath
+        summary = $summaryPath
+    }
+}
+
+$summary | ConvertTo-Json -Depth 20 | Set-Content -Encoding UTF8 -Path $summaryPath
+
+Write-Host ""
+Write-Host "Interview demo preflight completed."
+Write-Host "Verdict: $($summary.verdict)"
+Write-Host "Gatekeeper rules: $($summary.gatekeeperRuleSetVersion)"
+Write-Host "Prompt audit: $($summary.promptAuditVersion)"
+Write-Host "Summary: $summaryPath"

mvp/demo/ten-minute-interview-demo.md

@@ -37,7 +37,7 @@ http://localhost:9900
 推荐使用固定脚本：
 
 ```powershell
-powershell -ExecutionPolicy Bypass -File mvp/demo/scripts/run-payment-timeout-demo.ps1
+powershell -ExecutionPolicy Bypass -File mvp/demo/scripts/run-interview-demo-check.ps1
 ```
 
 脚本会写出：
@@ -46,6 +46,7 @@ powershell -ExecutionPolicy Bypass -File mvp/demo/scripts/run-payment-timeout-de
 mvp/demo/output/chat-response.json
 mvp/demo/output/trace-response.json
 mvp/demo/output/feedback-response.json
+mvp/demo/output/interview-demo-summary.json
 ```
 
 现场话术：
@@ -98,6 +99,8 @@ data.toolInvocations[*].outputPreview
 data.toolInvocations[*].retrievalLayer
 data.toolInvocations[*].relevanceLevel
 data.summary.hasVerifierEvaluation
+data.session.selfEvaluation.verifier_evaluation.prompt_audit.version
+data.session.selfEvaluation.verifier_evaluation.gatekeeper_result.rule_set_version
 ```
 
 现场话术：
@@ -155,6 +158,10 @@ Verifier 不做新检索，只看工具 trace 汇总。
 如果 PASS，就输出原答案。
 如果 LOW_CONFID，可以补证据或加低置信提示。
 如果 REJECT，就降级输出，只保留已确认信息。
+
+Prompt 和 Gatekeeper 的版本也会进入 trace。
+`prompt_audit.version` 用于说明本次 Chat 使用哪套 Prompt 契约，`gatekeeper_result.rule_set_version` 用于说明引用验真的规则版本。
+固定 fixture baseline 是回归判断来源，live demo 主要证明当前环境链路可跑通。
 ```
 
 ## 7. 展示反馈闭环
@@ -226,6 +233,7 @@ AIOps 有两个模式。
 mvp/demo/output/chat-response.json
 mvp/demo/output/trace-response.json
 mvp/demo/output/feedback-response.json
+mvp/demo/output/interview-demo-summary.json
 ```
 
 降级话术：

mvp/demo/trace-inspection-checklist.md

@@ -1,6 +1,6 @@
 # Trace 检查清单
 
-运行 `scripts/run-payment-timeout-demo.ps1` 后，用这份清单检查 `trace-response.json`。
+运行 `scripts/run-interview-demo-check.ps1` 后，用这份清单检查 `trace-response.json` 和 `interview-demo-summary.json`。
 
 ## 1. Session
 
@@ -11,6 +11,8 @@
 | `data.session.answer` | 是否包含最终诊断答案 | 最终答案没有脱离 Trace |
 | `data.session.selfEvaluation` | 是否包含 verifier 或 rule evaluation | 答案经过质量门，不只是模型原始输出 |
 | `data.session.selfEvaluation.verifier_evaluation.gatekeeper_result.rule_set_version` | 如果是 Chat V2 链路，是否记录 Gatekeeper 规则版本 | 安全规则可审计、可回归 |
+| `data.session.selfEvaluation.verifier_evaluation.prompt_audit.version` | 如果是 Chat V2 链路，是否记录 Prompt 审计版本 | Prompt 变更可解释、可回归 |
+| `data.session.selfEvaluation.verifier_evaluation.prompt_audit.prompts[*].version` | 是否记录 planner / executor / verifier / composer 版本 | 便于定位 Prompt 变更影响 |
 | `data.session.feedback` | 提交反馈后是否变为 `useful` | 用户反馈挂在同一次诊断上 |
 
 ## 2. Agent 步骤

mvp/eval/README.md

@@ -29,10 +29,10 @@ The baseline evaluates saved trace fixtures. It does not start the application a
 The committed baseline currently contains:
 
 ```text
-10 fixed cases
+12 fixed cases
-10 passing fixture evaluations
+12 passing fixture evaluations
-4 PASS verdicts
+5 PASS verdicts
-5 LOW_CONFID verdicts
+6 LOW_CONFID verdicts
 1 REJECT verdict
 ```
 
@@ -44,6 +44,8 @@ The V2 evidence-pipeline matrix covers:
 - Unsupported claim filtering before the final answer.
 - Composer fallback rendering without raw Executor JSON leakage.
 - Gatekeeper rule set version audit for new matrix fixtures.
+- Prompt audit version checks for planner, executor, verifier, and composer prompts.
+- Gatekeeper rule metadata checks for enabled rule id and default severity.
 
 ## Verification
 
@@ -80,6 +82,8 @@ Stage 5 adds these V2 checks:
 - `claim_checks` must be structurally auditable.
 - Composer output must record whether normal parsing or fallback rendering was used.
 - Gatekeeper rule set version can be asserted per fixture.
+- Prompt audit version and per-prompt versions can be asserted per fixture.
+- Gatekeeper rule metadata can be required per fixture.
 - Final answers must not leak raw Executor protocol markers such as `executor_evidence_v2`, `answer_version`, `evidence_bindings`, or `claim_id`.
 - Configured unsupported claim keywords must not appear as confirmed final-answer content.
 

mvp/eval/cases/diagnosis-cases.json

@@ -17,6 +17,33 @@
     "expectedComposerStatuses": ["valid"],
     "forbiddenConfirmedClaimKeywords": ["数据库连接池"]
   },
+  {
+    "id": "prompt-gatekeeper-audit-closure",
+    "title": "Prompt and Gatekeeper audit closure",
+    "question": "确认 payment-service 当前是否存在 HighCPUUsage 告警，并检查审计元数据是否完整。",
+    "traceFixture": "prompt-gatekeeper-audit-closure-pass.json",
+    "expectedRootCauseKeywords": ["payment-service", "HighCPUUsage", "92%"],
+    "minKeywordMatches": 2,
+    "requiredEvidenceTools": ["query_metrics"],
+    "allowedVerdicts": ["PASS"],
+    "forbiddenAnswerKeywords": ["根因", "修复建议", "通常情况下"],
+    "requireV2AuditClosure": true,
+    "requireClaimChecks": true,
+    "requireComposerOutput": true,
+    "expectedGatekeeperStatuses": ["pass"],
+    "expectedGatekeeperRuleSetVersion": "gatekeeper-rules-v1",
+    "expectedComposerStatuses": ["valid"],
+    "forbiddenConfirmedClaimKeywords": ["数据库连接池"],
+    "requirePromptAudit": true,
+    "expectedPromptAuditVersion": "chat-prompts-v1",
+    "expectedPromptVersions": {
+      "chat_planner": "chat-planner-v1",
+      "chat_executor": "chat-executor-v2",
+      "chat_verifier": "chat-verifier-v2",
+      "chat_composer": "chat-composer-v1"
+    },
+    "requireGatekeeperRules": true
+  },
   {
     "id": "hikari-no-evidence-negative-observation",
     "title": "Hikari no-evidence negative observation",
@@ -124,6 +151,33 @@
     "expectedComposerStatuses": ["valid"],
     "forbiddenConfirmedClaimKeywords": ["主库故障"]
   },
+  {
+    "id": "audit-metadata-low-confid",
+    "title": "Audit metadata low confidence",
+    "question": "订单超时是否可以确认由数据库主库故障导致，并检查审计元数据是否完整？",
+    "traceFixture": "audit-metadata-low-confid.json",
+    "expectedRootCauseKeywords": ["超时", "证据"],
+    "minKeywordMatches": 2,
+    "requiredEvidenceTools": ["query_logs"],
+    "allowedVerdicts": ["LOW_CONFID"],
+    "forbiddenAnswerKeywords": ["已经确认"],
+    "requireV2AuditClosure": true,
+    "requireClaimChecks": true,
+    "requireComposerOutput": true,
+    "expectedGatekeeperStatuses": ["pass"],
+    "expectedGatekeeperRuleSetVersion": "gatekeeper-rules-v1",
+    "expectedComposerStatuses": ["valid"],
+    "forbiddenConfirmedClaimKeywords": ["主库故障"],
+    "requirePromptAudit": true,
+    "expectedPromptAuditVersion": "chat-prompts-v1",
+    "expectedPromptVersions": {
+      "chat_planner": "chat-planner-v1",
+      "chat_executor": "chat-executor-v2",
+      "chat_verifier": "chat-verifier-v2",
+      "chat_composer": "chat-composer-v1"
+    },
+    "requireGatekeeperRules": true
+  },
   {
     "id": "composer-fallback-no-raw-json",
     "title": "Composer fallback no raw JSON",

mvp/eval/fixtures/audit-metadata-low-confid.json

@@ -0,0 +1,192 @@
+{
+  "session": {
+    "sessionId": "eval-audit-metadata-low-confid",
+    "query": "订单超时是否可以确认由数据库主库故障导致，并检查审计元数据是否完整？",
+    "status": "SUCCESS",
+    "agentFlow": "CHAT",
+    "totalDurationMs": 45000,
+    "toolCallCount": 1,
+    "answer": "以下结论基于当前已获取证据，仍存在部分证据缺口，请谨慎参考。\n\n已确认信息：日志显示订单接口出现超时。\n\n仍需补充信息：目前没有数据库故障日志或主库状态证据，不能把该方向写成确认根因。",
+    "selfEvaluation": {
+      "verifier_evaluation": {
+        "verdict": "LOW_CONFID",
+        "groundedness_score": 0.42,
+        "critical_fact_count": 2,
+        "prompt_audit": {
+          "version": "chat-prompts-v1",
+          "prompts": [
+            {
+              "name": "chat_planner",
+              "version": "chat-planner-v1",
+              "resource": "prompts/chat-planner-prompt.md"
+            },
+            {
+              "name": "chat_executor",
+              "version": "chat-executor-v2",
+              "resource": "prompts/chat-executor-prompt.md"
+            },
+            {
+              "name": "chat_verifier",
+              "version": "chat-verifier-v2",
+              "resource": "prompts/chat-verifier-prompt.md"
+            },
+            {
+              "name": "chat_composer",
+              "version": "chat-composer-v1",
+              "resource": "prompts/chat-composer-prompt.md"
+            }
+          ]
+        },
+        "gatekeeper_result": {
+          "status": "pass",
+          "severity": "none",
+          "rule_set_version": "gatekeeper-rules-v1",
+          "rules": [
+            {
+              "id": "evidence.invocation",
+              "description": "source_invocation_id must reference an existing tool invocation",
+              "enabled": true,
+              "default_severity": "reject"
+            },
+            {
+              "id": "evidence.excerpt",
+              "description": "evidence_excerpt must be supported by recorded evidence text",
+              "enabled": true,
+              "default_severity": "reject"
+            }
+          ],
+          "checked_bindings": [
+            {
+              "claim_id": "claim-timeout",
+              "tool_name": "query_logs",
+              "source_invocation_id": 22,
+              "raw_path": "$.logs[0]",
+              "matched_text": "order api timeout",
+              "status": "pass"
+            }
+          ],
+          "failed_rules": [],
+          "warnings": [],
+          "errors": []
+        },
+        "executor_structured_output": {
+          "answer_version": "executor_evidence_v2",
+          "claims": [
+            {
+              "claim_id": "claim-timeout",
+              "claim_type": "symptom",
+              "claim_text": "订单接口出现超时",
+              "support_level": "direct",
+              "evidence_bindings": [
+                {
+                  "source_type": "tool_trace",
+                  "tool_name": "query_logs",
+                  "source_invocation_id": 22,
+                  "raw_path": "$.logs[0]",
+                  "evidence_excerpt": "order api timeout"
+                }
+              ]
+            },
+            {
+              "claim_id": "claim-db-primary",
+              "claim_type": "root_cause",
+              "claim_text": "数据库主库故障导致订单超时",
+              "support_level": "weak",
+              "evidence_bindings": [
+                {
+                  "source_type": "tool_trace",
+                  "tool_name": "query_logs",
+                  "source_invocation_id": 22,
+                  "raw_path": "$.logs[0]",
+                  "evidence_excerpt": "order api timeout"
+                }
+              ]
+            }
+          ],
+          "hypotheses": [],
+          "recommended_actions": [
+            {
+              "action_text": "补充查询数据库主库状态和错误日志",
+              "reason": "当前只有订单接口超时日志"
+            }
+          ],
+          "missing_info": ["数据库主库状态", "数据库错误日志"]
+        },
+        "claim_checks": [
+          {
+            "claim_id": "claim-timeout",
+            "claim_text": "订单接口出现超时",
+            "claim_type": "symptom",
+            "verification": "direct_observation",
+            "detail": "日志直接记录 order api timeout",
+            "evidence_refs": [
+              {
+                "source_invocation_id": 22,
+                "raw_path": "$.logs[0]"
+              }
+            ]
+          },
+          {
+            "claim_id": "claim-db-primary",
+            "claim_text": "数据库主库故障导致订单超时",
+            "claim_type": "root_cause",
+            "verification": "unsupported",
+            "detail": "日志只能证明订单接口超时，不能证明数据库主库故障",
+            "evidence_refs": [
+              {
+                "source_invocation_id": 22,
+                "raw_path": "$.logs[0]"
+              }
+            ]
+          }
+        ],
+        "facts_checked": [],
+        "composer_output": {
+          "status": "valid",
+          "answer_summary": "日志显示订单接口超时，但数据库方向证据不足。",
+          "recommended_actions": [
+            {
+              "action_text": "补充查询数据库主库状态和错误日志",
+              "reason": "当前只有订单接口超时日志"
+            }
+          ],
+          "user_facing_answer": "以下结论基于当前已获取证据，仍存在部分证据缺口，请谨慎参考。\n\n已确认信息：日志显示订单接口出现超时。\n\n仍需补充信息：目前没有数据库故障日志或主库状态证据，不能把该方向写成确认根因。"
+        },
+        "tool_trace_summary": [
+          {
+            "tool_name": "query_logs",
+            "success": true,
+            "evidence_level": "direct"
+          }
+        ]
+      }
+    }
+  },
+  "steps": [],
+  "toolInvocations": [
+    {
+      "id": 22,
+      "sessionId": "eval-audit-metadata-low-confid",
+      "toolName": "query_logs",
+      "outputPreview": "order api timeout",
+      "retrievalDetails": {
+        "evidence_status": "supported",
+        "evidence_refs": [
+          {
+            "raw_path": "$.logs[0]",
+            "text": "order api timeout"
+          }
+        ]
+      },
+      "success": true
+    }
+  ],
+  "summary": {
+    "persistedStepCount": 3,
+    "returnedStepCount": 3,
+    "persistedToolCallCount": 1,
+    "returnedToolCallCount": 1,
+    "hasVerifierEvaluation": true,
+    "hasFeedback": false
+  }
+}

mvp/eval/fixtures/prompt-gatekeeper-audit-closure-pass.json

@@ -0,0 +1,155 @@
+{
+  "session": {
+    "sessionId": "eval-prompt-gatekeeper-audit-closure",
+    "query": "确认 payment-service 当前是否存在 HighCPUUsage 告警，并检查审计元数据是否完整。",
+    "status": "SUCCESS",
+    "agentFlow": "CHAT",
+    "totalDurationMs": 19000,
+    "toolCallCount": 1,
+    "answer": "payment-service 当前存在 HighCPUUsage 告警，CPU 使用率为 92%。",
+    "selfEvaluation": {
+      "verifier_evaluation": {
+        "verdict": "PASS",
+        "groundedness_score": 1.0,
+        "critical_fact_count": 1,
+        "prompt_audit": {
+          "version": "chat-prompts-v1",
+          "prompts": [
+            {
+              "name": "chat_planner",
+              "version": "chat-planner-v1",
+              "resource": "prompts/chat-planner-prompt.md"
+            },
+            {
+              "name": "chat_executor",
+              "version": "chat-executor-v2",
+              "resource": "prompts/chat-executor-prompt.md"
+            },
+            {
+              "name": "chat_verifier",
+              "version": "chat-verifier-v2",
+              "resource": "prompts/chat-verifier-prompt.md"
+            },
+            {
+              "name": "chat_composer",
+              "version": "chat-composer-v1",
+              "resource": "prompts/chat-composer-prompt.md"
+            }
+          ]
+        },
+        "gatekeeper_result": {
+          "status": "pass",
+          "severity": "none",
+          "rule_set_version": "gatekeeper-rules-v1",
+          "rules": [
+            {
+              "id": "evidence.invocation",
+              "description": "source_invocation_id must reference an existing tool invocation",
+              "enabled": true,
+              "default_severity": "reject"
+            },
+            {
+              "id": "evidence.raw_path",
+              "description": "raw_path must exist in retrieval_details.evidence_refs",
+              "enabled": true,
+              "default_severity": "reject"
+            }
+          ],
+          "checked_bindings": [
+            {
+              "claim_id": "claim-1",
+              "tool_name": "query_metrics",
+              "source_invocation_id": 21,
+              "raw_path": "$.alerts[0]",
+              "matched_text": "HighCPUUsage firing, service=payment-service, current=92%, duration=25m",
+              "status": "pass"
+            }
+          ],
+          "failed_rules": [],
+          "warnings": [],
+          "errors": []
+        },
+        "executor_structured_output": {
+          "answer_version": "executor_evidence_v2",
+          "claims": [
+            {
+              "claim_id": "claim-1",
+              "claim_type": "observation",
+              "claim_text": "payment-service 当前存在 HighCPUUsage 告警，CPU 使用率为 92%。",
+              "support_level": "direct",
+              "evidence_bindings": [
+                {
+                  "source_type": "tool_trace",
+                  "tool_name": "query_metrics",
+                  "source_invocation_id": 21,
+                  "raw_path": "$.alerts[0]",
+                  "evidence_excerpt": "HighCPUUsage firing, service=payment-service, current=92%, duration=25m"
+                }
+              ]
+            }
+          ],
+          "hypotheses": [],
+          "recommended_actions": [],
+          "missing_info": []
+        },
+        "claim_checks": [
+          {
+            "claim_id": "claim-1",
+            "claim_text": "payment-service 当前存在 HighCPUUsage 告警，CPU 使用率为 92%。",
+            "claim_type": "observation",
+            "verification": "direct_observation",
+            "detail": "已核验的指标证据直接包含服务名、告警名和 CPU 当前值。",
+            "evidence_refs": [
+              {
+                "source_invocation_id": 21,
+                "raw_path": "$.alerts[0]"
+              }
+            ]
+          }
+        ],
+        "facts_checked": [],
+        "composer_output": {
+          "status": "valid",
+          "answer_summary": "payment-service 当前存在 HighCPUUsage 告警。",
+          "recommended_actions": [],
+          "user_facing_answer": "payment-service 当前存在 HighCPUUsage 告警，CPU 使用率为 92%。"
+        },
+        "tool_trace_summary": [
+          {
+            "tool_name": "query_metrics",
+            "success": true,
+            "source_invocation_ids": [21],
+            "evidence_level": "direct"
+          }
+        ]
+      }
+    }
+  },
+  "steps": [],
+  "toolInvocations": [
+    {
+      "id": 21,
+      "sessionId": "eval-prompt-gatekeeper-audit-closure",
+      "toolName": "query_metrics",
+      "outputPreview": "HighCPUUsage firing, service=payment-service, current=92%, duration=25m",
+      "retrievalDetails": {
+        "evidence_status": "supported",
+        "evidence_refs": [
+          {
+            "raw_path": "$.alerts[0]",
+            "text": "HighCPUUsage firing, service=payment-service, current=92%, duration=25m"
+          }
+        ]
+      },
+      "success": true
+    }
+  ],
+  "summary": {
+    "persistedStepCount": 3,
+    "returnedStepCount": 3,
+    "persistedToolCallCount": 1,
+    "returnedToolCallCount": 1,
+    "hasVerifierEvaluation": true,
+    "hasFeedback": false
+  }
+}

mvp/eval/reports/baseline-report.json

@@ -1,14 +1,14 @@
 {
-  "totalCases" : 10,
+  "totalCases" : 12,
-  "passedCases" : 10,
+  "passedCases" : 12,
   "passRate" : 1.0,
   "verdictDistribution" : {
-    "PASS" : 4,
+    "PASS" : 5,
-    "LOW_CONFID" : 5,
+    "LOW_CONFID" : 6,
     "REJECT" : 1
   },
-  "averageToolCallCount" : 1.5,
+  "averageToolCallCount" : 1.4166666666666667,
-  "averageDurationMs" : 39800.0,
+  "averageDurationMs" : 38500.0,
   "results" : [ {
     "caseId" : "narrow-highcpu-observation",
     "title" : "Narrow HighCPU observation",
@@ -22,10 +22,31 @@
     },
     "gatekeeperStatus" : "pass",
     "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "promptAuditVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 1,
+    "gatekeeperRuleCount" : 1,
     "toolCallCount" : 1,
     "durationMs" : 18000
+  }, {
+    "caseId" : "prompt-gatekeeper-audit-closure",
+    "title" : "Prompt and Gatekeeper audit closure",
+    "passed" : true,
+    "failedChecks" : [ ],
+    "verdict" : "PASS",
+    "matchedKeywordCount" : 3,
+    "requiredKeywordCount" : 3,
+    "evidenceCoverage" : {
+      "query_metrics" : true
+    },
+    "gatekeeperStatus" : "pass",
+    "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "promptAuditVersion" : "chat-prompts-v1",
+    "composerStatus" : "valid",
+    "claimCheckCount" : 1,
+    "gatekeeperRuleCount" : 2,
+    "toolCallCount" : 1,
+    "durationMs" : 19000
   }, {
     "caseId" : "hikari-no-evidence-negative-observation",
     "title" : "Hikari no-evidence negative observation",
@@ -39,8 +60,10 @@
     },
     "gatekeeperStatus" : "pass",
     "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "promptAuditVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 1,
+    "gatekeeperRuleCount" : 1,
     "toolCallCount" : 1,
     "durationMs" : 21000
   }, {
@@ -58,8 +81,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 3,
     "durationMs" : 42000
   }, {
@@ -76,8 +101,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 2,
     "durationMs" : 51000
   }, {
@@ -93,8 +120,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 1,
     "durationMs" : 36000
   }, {
@@ -111,8 +140,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 2,
     "durationMs" : 47000
   }, {
@@ -129,8 +160,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 2,
     "durationMs" : 53000
   }, {
@@ -146,8 +179,10 @@
     },
     "gatekeeperStatus" : "fail",
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 1,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 1,
     "durationMs" : 39000
   }, {
@@ -163,10 +198,31 @@
     },
     "gatekeeperStatus" : "pass",
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 2,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 1,
     "durationMs" : 44000
+  }, {
+    "caseId" : "audit-metadata-low-confid",
+    "title" : "Audit metadata low confidence",
+    "passed" : true,
+    "failedChecks" : [ ],
+    "verdict" : "LOW_CONFID",
+    "matchedKeywordCount" : 2,
+    "requiredKeywordCount" : 2,
+    "evidenceCoverage" : {
+      "query_logs" : true
+    },
+    "gatekeeperStatus" : "pass",
+    "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "promptAuditVersion" : "chat-prompts-v1",
+    "composerStatus" : "valid",
+    "claimCheckCount" : 2,
+    "gatekeeperRuleCount" : 2,
+    "toolCallCount" : 1,
+    "durationMs" : 45000
   }, {
     "caseId" : "composer-fallback-no-raw-json",
     "title" : "Composer fallback no raw JSON",
@@ -180,8 +236,10 @@
     },
     "gatekeeperStatus" : "pass",
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : "composer_malformed",
     "claimCheckCount" : 2,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 1,
     "durationMs" : 47000
   } ]

mvp/eval/reports/baseline-report.md

@@ -1,28 +1,30 @@
 # Diagnosis Eval Report
 
-- Total cases: 10
+- Total cases: 12
-- Passed cases: 10
+- Passed cases: 12
 - Pass rate: 100.00%
-- Average tool calls: 1.50
+- Average tool calls: 1.42
-- Average duration ms: 39800.00
+- Average duration ms: 38500.00
 
 ## Verdict Distribution
 
-- PASS: 4
+- PASS: 5
-- LOW_CONFID: 5
+- LOW_CONFID: 6
 - REJECT: 1
 
 ## Cases
 
-| Case | Result | Verdict | Gatekeeper | Rule Set | Composer | Claim Checks | Keywords | Tool Calls | Duration ms | Failed Checks |
+| Case | Result | Verdict | Gatekeeper | Rule Set | Prompt Audit | Composer | Claim Checks | Rules | Keywords | Tool Calls | Duration ms | Failed Checks |
-| --- | --- | --- | --- | --- | --- | ---: | --- | ---: | ---: | --- |
+| --- | --- | --- | --- | --- | --- | --- | ---: | ---: | --- | ---: | ---: | --- |
-| narrow-highcpu-observation | PASS | PASS | pass | gatekeeper-rules-v1 | valid | 1 | 3/3 | 1 | 18000 | - |
+| narrow-highcpu-observation | PASS | PASS | pass | gatekeeper-rules-v1 | - | valid | 1 | 1 | 3/3 | 1 | 18000 | - |
-| hikari-no-evidence-negative-observation | PASS | PASS | pass | gatekeeper-rules-v1 | valid | 1 | 3/3 | 1 | 21000 | - |
+| prompt-gatekeeper-audit-closure | PASS | PASS | pass | gatekeeper-rules-v1 | chat-prompts-v1 | valid | 1 | 2 | 3/3 | 1 | 19000 | - |
-| payment-timeout | PASS | PASS | - | - | - | - | 3/3 | 3 | 42000 | - |
+| hikari-no-evidence-negative-observation | PASS | PASS | pass | gatekeeper-rules-v1 | - | valid | 1 | 1 | 3/3 | 1 | 21000 | - |
-| mysql-pool-exhausted | PASS | LOW_CONFID | - | - | - | - | 3/3 | 2 | 51000 | - |
+| payment-timeout | PASS | PASS | - | - | - | - | - | - | 3/3 | 3 | 42000 | - |
-| redis-timeout | PASS | LOW_CONFID | - | - | - | - | 2/2 | 1 | 36000 | - |
+| mysql-pool-exhausted | PASS | LOW_CONFID | - | - | - | - | - | - | 3/3 | 2 | 51000 | - |
-| slow-response | PASS | PASS | - | - | - | - | 2/2 | 2 | 47000 | - |
+| redis-timeout | PASS | LOW_CONFID | - | - | - | - | - | - | 2/2 | 1 | 36000 | - |
-| jvm-memory-risk | PASS | LOW_CONFID | - | - | - | - | 3/3 | 2 | 53000 | - |
+| slow-response | PASS | PASS | - | - | - | - | - | - | 2/2 | 2 | 47000 | - |
-| gatekeeper-fabricated-invocation | PASS | REJECT | fail | - | valid | 1 | 3/3 | 1 | 39000 | - |
+| jvm-memory-risk | PASS | LOW_CONFID | - | - | - | - | - | - | 3/3 | 2 | 53000 | - |
-| unsupported-claim-filtering | PASS | LOW_CONFID | pass | - | valid | 2 | 2/2 | 1 | 44000 | - |
+| gatekeeper-fabricated-invocation | PASS | REJECT | fail | - | - | valid | 1 | - | 3/3 | 1 | 39000 | - |
-| composer-fallback-no-raw-json | PASS | LOW_CONFID | pass | - | composer_malformed | 2 | 2/2 | 1 | 47000 | - |
+| unsupported-claim-filtering | PASS | LOW_CONFID | pass | - | - | valid | 2 | - | 2/2 | 1 | 44000 | - |
+| audit-metadata-low-confid | PASS | LOW_CONFID | pass | gatekeeper-rules-v1 | chat-prompts-v1 | valid | 2 | 2 | 2/2 | 1 | 45000 | - |
+| composer-fallback-no-raw-json | PASS | LOW_CONFID | pass | - | - | composer_malformed | 2 | - | 2/2 | 1 | 47000 | - |

mvp/eval/schema.md

@@ -34,7 +34,16 @@ baseline report：整套固定集当前认可的结果
   "expectedGatekeeperStatuses": ["pass"],
   "expectedGatekeeperRuleSetVersion": "gatekeeper-rules-v1",
   "expectedComposerStatuses": ["valid"],
-  "forbiddenConfirmedClaimKeywords": ["主库故障"]
+  "forbiddenConfirmedClaimKeywords": ["主库故障"],
+  "requirePromptAudit": true,
+  "expectedPromptAuditVersion": "chat-prompts-v1",
+  "expectedPromptVersions": {
+    "chat_planner": "chat-planner-v1",
+    "chat_executor": "chat-executor-v2",
+    "chat_verifier": "chat-verifier-v2",
+    "chat_composer": "chat-composer-v1"
+  },
+  "requireGatekeeperRules": true
 }
 ```
 
@@ -58,6 +67,10 @@ baseline report：整套固定集当前认可的结果
 | `expectedGatekeeperRuleSetVersion` | 期望的 Gatekeeper 规则集版本 | 配置后校验 `gatekeeper_result.rule_set_version` |
 | `expectedComposerStatuses` | 允许的 Composer 状态 | 实际 `composer_output.status` 不在列表中则失败 |
 | `forbiddenConfirmedClaimKeywords` | 不得进入最终答案的未支持结论关键词 | 用于证明 unsupported/external_unknown claim 被过滤 |
+| `requirePromptAudit` | 是否要求 Prompt 审计元数据 | 要求 `prompt_audit.version` 存在 |
+| `expectedPromptAuditVersion` | 期望的 Prompt 审计目录版本 | 配置后校验 `prompt_audit.version` |
+| `expectedPromptVersions` | 期望的各角色 Prompt 版本 | 校验 `prompt_audit.prompts[*].name/version` |
+| `requireGatekeeperRules` | 是否要求 Gatekeeper 规则元数据 | 要求 `gatekeeper_result.rules` 非空，且每条规则有 `id`、`enabled`、`default_severity` |
 
 ## 2. Trace Fixture
 
@@ -72,6 +85,9 @@ fixture 是一次 Agent 运行后的 trace 快照。评测器只读取当前规
 | `session.selfEvaluation.verifier_evaluation.verdict` | Verifier 判定 | 必须存在并符合 case 的 `allowedVerdicts` |
 | `session.selfEvaluation.verifier_evaluation.gatekeeper_result.status` | Gatekeeper 结果 | V2 case 必须存在；`fail` 不允许搭配 `PASS` |
 | `session.selfEvaluation.verifier_evaluation.gatekeeper_result.rule_set_version` | Gatekeeper 规则集版本 | 新矩阵 case 可显式断言该版本 |
+| `session.selfEvaluation.verifier_evaluation.gatekeeper_result.rules` | Gatekeeper 规则元数据摘要 | 审计 case 可要求规则列表非空且字段完整 |
+| `session.selfEvaluation.verifier_evaluation.prompt_audit.version` | Chat Prompt 审计目录版本 | 审计 case 可显式断言该版本 |
+| `session.selfEvaluation.verifier_evaluation.prompt_audit.prompts` | 各 Chat Prompt 名称、版本和资源路径 | 审计 case 可断言 planner、executor、verifier、composer 版本 |
 | `session.selfEvaluation.verifier_evaluation.claim_checks` | Verifier V2 claim 级校验 | V2 case 必须存在；每项需要 `claim_id`、`verification`、`detail` |
 | `session.selfEvaluation.verifier_evaluation.composer_output.status` | Composer 渲染状态 | V2 case 必须存在；记录 `valid`、`composer_malformed` 等 |
 | `session.selfEvaluation.verifier_evaluation.executor_structured_output.claims[*].evidence_bindings` | Executor claim 证据绑定 | 如果结构化输出存在，每条 claim 需要证据绑定 |
@@ -95,8 +111,10 @@ Java 类型：`DiagnosisEvalResult`
 | `evidenceCoverage` | 每个必需工具是否出现 |
 | `gatekeeperStatus` | 读到的 `gatekeeper_result.status` |
 | `gatekeeperRuleSetVersion` | 读到的 `gatekeeper_result.rule_set_version` |
+| `promptAuditVersion` | 读到的 `prompt_audit.version` |
 | `composerStatus` | 读到的 `composer_output.status` |
 | `claimCheckCount` | `claim_checks` 数量 |
+| `gatekeeperRuleCount` | `gatekeeper_result.rules` 数量 |
 | `toolCallCount` | trace 中工具调用总数 |
 | `durationMs` | trace 总耗时 |
 
@@ -130,6 +148,10 @@ Executor structured output
 - V2 case 必须有 `gatekeeper_result`、`claim_checks`、`composer_output`。
 - `gatekeeper_result.status = fail` 时，Verifier verdict 不能是 `PASS`。
 - 配置 `expectedGatekeeperRuleSetVersion` 的 case 必须匹配 `gatekeeper_result.rule_set_version`。
+- 配置 `requirePromptAudit` 的 case 必须包含 `prompt_audit.version`。
+- 配置 `expectedPromptAuditVersion` 的 case 必须匹配 `prompt_audit.version`。
+- 配置 `expectedPromptVersions` 的 case 必须能在 `prompt_audit.prompts` 中找到对应角色和版本。
+- 配置 `requireGatekeeperRules` 的 case 必须包含非空 `gatekeeper_result.rules`，且每条规则有 `id`、`enabled`、`default_severity`。
 - `claim_checks[*].verification` 只能是 `direct_observation`、`reasonable_inference`、`overstated`、`unsupported`、`external_unknown`、`contradicted`。
 - Composer 输出必须记录 `status`。
 - 最终答案不能泄漏 `executor_evidence_v2`、`answer_version`、`evidence_bindings`、`claim_id`。

mvp/issues/README.md

@@ -1,47 +1,64 @@
-# 已知问题记录
+# MVP Issues 索引
 
-| # | 标题 | 严重程度 | 状态 | 文件 |
+**更新日期**：2026-07-09  
-|---|---|---|---|---|
+**状态**：按活跃问题、设计笔记、RAG 问题集和已归档问题整理
-| ISS-001 | Executor 重复召回同一文档 | 中 | 已修复 | [ISS-001-duplicate-retrieval.md](ISS-001-duplicate-retrieval.md) |
-| ISS-002 | Executor 无约束重复调用 lookup_knowledge | 中 | 已修复 | [ISS-002-executor-unconstrained-lookup.md](ISS-002-executor-unconstrained-lookup.md) |
-| ISS-003 | MVP 设计与实现 Review 收敛 | 高 | 待规划 | [ISS-003-mvp-design-implementation-review.md](ISS-003-mvp-design-implementation-review.md) |
-| ISS-004 | Executor 域级检索水位控制（Phase 2） | 低 | 待规划 | [ISS-004-executor-domain-hard-limit.md](ISS-004-executor-domain-hard-limit.md) |
-| ISS-005 | 证据链补齐与降级契约收敛 | 高 | 已归档 | [ISS-005-evidence-trace-hardening.md](ISS-005-evidence-trace-hardening.md) |
-| ISS-006 | 固定诊断评测集与回归 Harness | 高 | 已归档 | [ISS-006-diagnosis-eval-harness.md](ISS-006-diagnosis-eval-harness.md) |
-| ISS-007 | Verifier 证据摘要保真与工具命中质量问题 | 高 | 已实施 | [ISS-007-verifier-evidence-summary-fidelity.md](ISS-007-verifier-evidence-summary-fidelity.md) |
-| ISS-008 | Executor 窄范围查询越界 | 中 | 已修复 | [ISS-008-executor-narrow-scope-overreach.md](ISS-008-executor-narrow-scope-overreach.md) |
-| ISS-009 | negative_observation 精确引用 no-evidence 结果 | 中 | 已修复 | [ISS-009-negative-observation-no-evidence-reference.md](ISS-009-negative-observation-no-evidence-reference.md) |
-| executor-evidence-attribution-hallucination | Executor 证据归因幻觉 | 高 | 待规划 | [executor-evidence-attribution-hallucination.md](executor-evidence-attribution-hallucination.md) |
-| executor-self-evidence-loop-design-note | Executor 自证循环与证据摘要链路设计记录 | 高 | 已形成方向 | [executor-self-evidence-loop-design-note.md](executor-self-evidence-loop-design-note.md) |
-| expand-diagnosis-eval-fixtures | 补齐固定诊断评测 fixture 与 baseline | 中 | 已归档 | [expand-diagnosis-eval-fixtures.md](expand-diagnosis-eval-fixtures.md) |
-| diagnosis-eval-baseline-diff | 诊断评测 baseline diff 与回归判断 | 中 | 已归档 | [diagnosis-eval-baseline-diff.md](diagnosis-eval-baseline-diff.md) |
-| mvp-demo-interview-runbook | Plan C 面试可复现 Demo 包 | 中 | 已归档 | [mvp-demo-interview-runbook.md](mvp-demo-interview-runbook.md) |
 
-## RAG 重构计划
+## 目录约定
+
+| 目录 | 用途 |
+|---|---|
+| [active/](active/) | 仍需要规划或实现的问题 |
+| [design-notes/](design-notes/) | 已形成方向、用于指导后续实现的设计记录 |
+| [rag/](rag/) | RAG 子问题集合；多数已合并到 RAG 重构计划 |
+| [archived/](archived/) | 已修复、已实施或已归档的问题 |
+
+## 活跃问题
 
 | 名称 | 标题 | 严重程度 | 状态 | 文件 |
 |---|---|---|---|---|
-| rag-refactor-plan | RAG 检索重构计划 | 高 | 待规划 | [rag-refactor-plan.md](rag-refactor-plan.md) |
+| ISS-003 | MVP 设计与实现 Review 收敛 | 高 | 待规划 | [active/ISS-003-mvp-design-implementation-review.md](active/ISS-003-mvp-design-implementation-review.md) |
+| ISS-004 | Executor 域级检索水位控制 | 低 | 待规划 | [active/ISS-004-executor-domain-hard-limit.md](active/ISS-004-executor-domain-hard-limit.md) |
+| executor-evidence-attribution-hallucination | Executor 证据归因幻觉 | 高 | 待规划 | [active/executor-evidence-attribution-hallucination.md](active/executor-evidence-attribution-hallucination.md) |
+| rag-refactor-plan | RAG 检索重构计划 | 高 | 待规划 | [active/rag-refactor-plan.md](active/rag-refactor-plan.md) |
 
-## RAG 检索问题
+## 设计笔记
 
-| 名称 | 标题 | 严重程度 | 状态 | 文件 |
+| 名称 | 标题 | 状态 | 文件 |
-|---|---|---|---|---|
+|---|---|---|---|
-| chunk-context-reconstruction | RAG 切片上下文重建缺失 | 高 | 已合并到重构计划 | [rag-chunk-context-reconstruction.md](rag-chunk-context-reconstruction.md) |
+| executor-self-evidence-loop-design-note | Executor 自证循环与证据摘要链路设计记录 | 已形成方向 | [design-notes/executor-self-evidence-loop-design-note.md](design-notes/executor-self-evidence-loop-design-note.md) |
-| breadcrumb-embedding-gap | RAG breadcrumb 未参与向量语义 | 高 | 已合并到重构计划 | [rag-breadcrumb-embedding-gap.md](rag-breadcrumb-embedding-gap.md) |
+| executor-structured-output-v2 | Executor 结构化输出 V2 阶段设计 | 部分已实施，保留为后续改造参考 | [design-notes/executor-structured-output-v2.md](design-notes/executor-structured-output-v2.md) |
-| l0-l1-fusion-ranking | RAG L0 和 L1 未真正融合排序 | 中 | 已合并到重构计划 | [rag-l0-l1-fusion-ranking.md](rag-l0-l1-fusion-ranking.md) |
-| l0-keyword-matching-quality | RAG L0 关键词匹配质量不足 | 中 | 已合并到重构计划 | [rag-l0-keyword-matching-quality.md](rag-l0-keyword-matching-quality.md) |
-| l1-score-calibration | RAG L1 分数阈值未校准 | 中 | 已合并到重构计划 | [rag-l1-score-calibration.md](rag-l1-score-calibration.md) |
-| context-packing-and-reranking | RAG 缺少上下文打包和 Rerank | 中 | 已合并到重构计划 | [rag-context-packing-and-reranking.md](rag-context-packing-and-reranking.md) |
-| upload-chunk-parameter-drift | RAG 上传切片参数未真正生效 | 低 | 已合并到重构计划 | [rag-upload-chunk-parameter-drift.md](rag-upload-chunk-parameter-drift.md) |
-| query-rewrite-gap | RAG 查询改写能力薄弱 | 中 | 已合并到重构计划 | [rag-query-rewrite-gap.md](rag-query-rewrite-gap.md) |
 
-## RAG 框架化改造
+## RAG 问题集
 
-| 名称 | 标题 | 严重程度 | 状态 | 文件 |
+这些问题已经收敛到 [active/rag-refactor-plan.md](active/rag-refactor-plan.md)，单个文件保留用于追溯原始问题和设计背景。
-|---|---|---|---|---|
+
-| spring-ai-vectorstore-migration | RAG 迁移到 Spring AI VectorStore 检索抽象 | 高 | 已合并到重构计划 | [rag-spring-ai-vectorstore-migration.md](rag-spring-ai-vectorstore-migration.md) |
+| 名称 | 标题 | 状态 | 文件 |
-| spring-ai-query-transformer | RAG 接入 Spring AI Query Transformer | 中 | 已合并到重构计划 | [rag-spring-ai-query-transformer.md](rag-spring-ai-query-transformer.md) |
+|---|---|---|---|
-| spring-ai-document-postprocessor | RAG 使用 DocumentPostProcessor 做后处理 | 中 | 已合并到重构计划 | [rag-spring-ai-document-postprocessor.md](rag-spring-ai-document-postprocessor.md) |
+| breadcrumb-embedding-gap | RAG breadcrumb 未参与向量语义 | 已合并到重构计划 | [rag/rag-breadcrumb-embedding-gap.md](rag/rag-breadcrumb-embedding-gap.md) |
-| l0-domain-entity-hint | RAG 将 L0 降级为领域和实体 Hint | 中 | 已合并到重构计划 | [rag-l0-domain-entity-hint.md](rag-l0-domain-entity-hint.md) |
+| chunk-context-reconstruction | RAG 切片上下文重建缺失 | 已合并到重构计划 | [rag/rag-chunk-context-reconstruction.md](rag/rag-chunk-context-reconstruction.md) |
-| spring-ai-advisor-boundary | RAG 明确 Spring AI Advisor 与 Agent Tool 的边界 | 中 | 已合并到重构计划 | [rag-spring-ai-advisor-boundary.md](rag-spring-ai-advisor-boundary.md) |
+| context-packing-and-reranking | RAG 缺少上下文打包和 Rerank | 已合并到重构计划 | [rag/rag-context-packing-and-reranking.md](rag/rag-context-packing-and-reranking.md) |
+| l0-domain-entity-hint | RAG 将 L0 降级为领域和实体 Hint | 已合并到重构计划 | [rag/rag-l0-domain-entity-hint.md](rag/rag-l0-domain-entity-hint.md) |
+| l0-keyword-matching-quality | RAG L0 关键词匹配质量不足 | 已合并到重构计划 | [rag/rag-l0-keyword-matching-quality.md](rag/rag-l0-keyword-matching-quality.md) |
+| l0-l1-fusion-ranking | RAG L0 和 L1 未真正融合排序 | 已合并到重构计划 | [rag/rag-l0-l1-fusion-ranking.md](rag/rag-l0-l1-fusion-ranking.md) |
+| l1-score-calibration | RAG L1 分数阈值未校准 | 已合并到重构计划 | [rag/rag-l1-score-calibration.md](rag/rag-l1-score-calibration.md) |
+| query-rewrite-gap | RAG 查询改写能力薄弱 | 已合并到重构计划 | [rag/rag-query-rewrite-gap.md](rag/rag-query-rewrite-gap.md) |
+| spring-ai-advisor-boundary | Spring AI Advisor 与 Agent Tool 边界 | 已合并到重构计划 | [rag/rag-spring-ai-advisor-boundary.md](rag/rag-spring-ai-advisor-boundary.md) |
+| spring-ai-document-postprocessor | 使用 DocumentPostProcessor 做后处理 | 已合并到重构计划 | [rag/rag-spring-ai-document-postprocessor.md](rag/rag-spring-ai-document-postprocessor.md) |
+| spring-ai-query-transformer | 接入 Spring AI Query Transformer | 已合并到重构计划 | [rag/rag-spring-ai-query-transformer.md](rag/rag-spring-ai-query-transformer.md) |
+| spring-ai-vectorstore-migration | 迁移到 Spring AI VectorStore 检索抽象 | 已合并到重构计划 | [rag/rag-spring-ai-vectorstore-migration.md](rag/rag-spring-ai-vectorstore-migration.md) |
+| upload-chunk-parameter-drift | 上传切片参数未真正生效 | 已合并到重构计划 | [rag/rag-upload-chunk-parameter-drift.md](rag/rag-upload-chunk-parameter-drift.md) |
+
+## 已归档问题
+
+| 名称 | 标题 | 状态 | 文件 |
+|---|---|---|---|
+| ISS-001 | Executor 重复召回同一文档 | 已修复 | [archived/ISS-001-duplicate-retrieval.md](archived/ISS-001-duplicate-retrieval.md) |
+| ISS-002 | Executor 无约束重复调用 lookup_knowledge | 已修复 | [archived/ISS-002-executor-unconstrained-lookup.md](archived/ISS-002-executor-unconstrained-lookup.md) |
+| ISS-005 | 证据链补齐与降级契约收敛 | 已归档 | [archived/ISS-005-evidence-trace-hardening.md](archived/ISS-005-evidence-trace-hardening.md) |
+| ISS-006 | 固定诊断评测集与回归 Harness | 已归档 | [archived/ISS-006-diagnosis-eval-harness.md](archived/ISS-006-diagnosis-eval-harness.md) |
+| ISS-007 | Verifier 证据摘要保真与工具命中质量问题 | 已实施 | [archived/ISS-007-verifier-evidence-summary-fidelity.md](archived/ISS-007-verifier-evidence-summary-fidelity.md) |
+| ISS-008 | Executor 窄范围查询越界 | 已修复 | [archived/ISS-008-executor-narrow-scope-overreach.md](archived/ISS-008-executor-narrow-scope-overreach.md) |
+| ISS-009 | negative_observation 精确引用 no-evidence 结果 | 已修复 | [archived/ISS-009-negative-observation-no-evidence-reference.md](archived/ISS-009-negative-observation-no-evidence-reference.md) |
+| diagnosis-eval-baseline-diff | 诊断评测 baseline diff 与回归判断 | 已归档 | [archived/diagnosis-eval-baseline-diff.md](archived/diagnosis-eval-baseline-diff.md) |
+| expand-diagnosis-eval-fixtures | 补齐固定诊断评测 fixture 与 baseline | 已归档 | [archived/expand-diagnosis-eval-fixtures.md](archived/expand-diagnosis-eval-fixtures.md) |
+| mvp-demo-interview-runbook | Plan C 面试可复现 Demo 包 | 已归档 | [archived/mvp-demo-interview-runbook.md](archived/mvp-demo-interview-runbook.md) |

mvp/issues/active/rag-refactor-plan.md

@@ -347,19 +347,19 @@ RAG、Agent、AIOps、数据库记录互相关联，必须分阶段推进，每
 
 本计划合并以下问题和改造方向：
 
-- [rag-chunk-context-reconstruction.md](rag-chunk-context-reconstruction.md)
+- [rag-chunk-context-reconstruction.md](../rag/rag-chunk-context-reconstruction.md)
-- [rag-breadcrumb-embedding-gap.md](rag-breadcrumb-embedding-gap.md)
+- [rag-breadcrumb-embedding-gap.md](../rag/rag-breadcrumb-embedding-gap.md)
-- [rag-l0-l1-fusion-ranking.md](rag-l0-l1-fusion-ranking.md)
+- [rag-l0-l1-fusion-ranking.md](../rag/rag-l0-l1-fusion-ranking.md)
-- [rag-l0-keyword-matching-quality.md](rag-l0-keyword-matching-quality.md)
+- [rag-l0-keyword-matching-quality.md](../rag/rag-l0-keyword-matching-quality.md)
-- [rag-l1-score-calibration.md](rag-l1-score-calibration.md)
+- [rag-l1-score-calibration.md](../rag/rag-l1-score-calibration.md)
-- [rag-context-packing-and-reranking.md](rag-context-packing-and-reranking.md)
+- [rag-context-packing-and-reranking.md](../rag/rag-context-packing-and-reranking.md)
-- [rag-upload-chunk-parameter-drift.md](rag-upload-chunk-parameter-drift.md)
+- [rag-upload-chunk-parameter-drift.md](../rag/rag-upload-chunk-parameter-drift.md)
-- [rag-query-rewrite-gap.md](rag-query-rewrite-gap.md)
+- [rag-query-rewrite-gap.md](../rag/rag-query-rewrite-gap.md)
-- [rag-spring-ai-vectorstore-migration.md](rag-spring-ai-vectorstore-migration.md)
+- [rag-spring-ai-vectorstore-migration.md](../rag/rag-spring-ai-vectorstore-migration.md)
-- [rag-spring-ai-query-transformer.md](rag-spring-ai-query-transformer.md)
+- [rag-spring-ai-query-transformer.md](../rag/rag-spring-ai-query-transformer.md)
-- [rag-spring-ai-document-postprocessor.md](rag-spring-ai-document-postprocessor.md)
+- [rag-spring-ai-document-postprocessor.md](../rag/rag-spring-ai-document-postprocessor.md)
-- [rag-l0-domain-entity-hint.md](rag-l0-domain-entity-hint.md)
+- [rag-l0-domain-entity-hint.md](../rag/rag-l0-domain-entity-hint.md)
-- [rag-spring-ai-advisor-boundary.md](rag-spring-ai-advisor-boundary.md)
+- [rag-spring-ai-advisor-boundary.md](../rag/rag-spring-ai-advisor-boundary.md)
 
 ---
 

mvp/issues/archived/ISS-001-duplicate-retrieval.md

@@ -4,7 +4,7 @@
 **严重程度**：中（影响 token 消耗和上下文质量，不影响功能正确性）
 **发现时间**：2026-06-30
 **修复版本**：session-dedup-knowledge-map
-**历史架构文档**：[会话级去重与知识域地图](../architecture/archive/2026-07-05-legacy/session-dedup-knowledge-map.md)
+**历史架构文档**：[会话级去重与知识域地图](../../architecture/archive/2026-07-05-legacy/session-dedup-knowledge-map.md)
 
 ---
 

mvp/tables/Agent步骤表-agent_step.md

@@ -0,0 +1,41 @@
+# Agent 步骤表：agent_step
+
+**状态**：当前表  
+**来源**：`V005__create_session_storage.sql`、`V006__fix_agent_step_json_to_text.sql`、`AgentStep`
+
+## 定位
+
+`agent_step` 记录一次诊断过程中每个 Agent 步骤的模型输入、输出、耗时和 Token 消耗。页面展示执行链路时应优先按 `step_index` 排序。
+
+## 字段
+
+| 字段 | 类型 | 必填 | 说明 |
+|---|---|---|---|
+| `id` | BIGINT | 是 | 自增主键 |
+| `session_id` | VARCHAR(64) | 是 | 关联 `diagnosis_session.session_id` |
+| `step_index` | INT | 是 | 步骤序号，从 0 开始 |
+| `agent_name` | VARCHAR(32) | 是 | Agent 名称，例如 planner、executor、verifier、composer |
+| `model_input` | TEXT | 否 | 模型输入摘要；`V006` 已从 JSON 改为 TEXT |
+| `model_output` | TEXT | 否 | 模型输出摘要；`V006` 已从 JSON 改为 TEXT |
+| `thought` | TEXT | 否 | Agent 思考过程或调试摘要 |
+| `has_tool_call` | BOOLEAN | 否 | 本步骤是否触发工具调用 |
+| `duration_ms` | INT | 否 | 本步骤耗时 |
+| `token_count` | INT | 否 | 本步骤 Token 消耗 |
+| `created_at` | DATETIME | 是 | 创建时间 |
+
+## 索引
+
+| 索引 | 字段 | 用途 |
+|---|---|---|
+| `idx_session_step` | `session_id, step_index` | Trace 页面按会话和步骤顺序查询 |
+| `idx_agent_name` | `agent_name` | 按 Agent 类型筛选 |
+
+## 关系
+
+- `agent_step.session_id` 逻辑关联 `diagnosis_session.session_id`。
+- `tool_invocation.step_id` 可关联 `agent_step.id`，但当前允许为空且不强制外键。
+
+## 注意点
+
+- 前端展示步骤时应按 `step_index` 排序，而不是按 `created_at` 或数据库返回顺序。
+- Verifier 应在 Executor 循环完成后出现；如果 `step_index` 中 Verifier 提前，通常意味着编排或记录顺序有问题。

mvp/tables/README.md

@@ -0,0 +1,40 @@
+# MVP 数据表索引
+
+**更新日期**：2026-07-09  
+**状态**：当前表文档入口
+
+本目录保存当前 MVP 使用的数据表说明。详细结构以 Flyway migration 和实体类为准；本目录用于面试讲解、排查索引和快速理解数据流。
+
+## 当前表
+
+| 表 | 用途 | 文档 |
+|---|---|---|
+| `diagnosis_session` | 会话级主记录，保存 query、状态、最终答案和自评估 | [诊断会话表-diagnosis_session.md](诊断会话表-diagnosis_session.md) |
+| `agent_step` | Agent 步骤记录，按 `step_index` 回放执行链路 | [Agent步骤表-agent_step.md](Agent步骤表-agent_step.md) |
+| `tool_invocation` | 工具调用记录，支撑 Trace、Verifier 和评测 | [工具调用表-tool_invocation.md](工具调用表-tool_invocation.md) |
+| `api_document` | 知识库文档元数据，和向量库 chunk 通过 `doc_id` 关联 | [文档元数据表-api_document.md](文档元数据表-api_document.md) |
+| `knowledge_domain` | 知识域元数据，支撑 RAG domain hint 和检索策略 | [知识域表-knowledge_domain.md](知识域表-knowledge_domain.md) |
+| `case_library` | 用户反馈沉淀出的高质量诊断案例 | [案例库表-case_library.md](案例库表-case_library.md) |
+
+## 已归档表
+
+| 表 | 归档原因 | 文档 |
+|---|---|---|
+| `diagnosis_record` | 已由 `V007` 删除，被 `diagnosis_session + agent_step + tool_invocation` 替代 | [archive/2026-07-09-doc-cleanup/旧诊断记录表-diagnosis_record.md](archive/2026-07-09-doc-cleanup/旧诊断记录表-diagnosis_record.md) |
+
+## 核心关系
+
+```text
+diagnosis_session.session_id
+  -> agent_step.session_id
+  -> tool_invocation.session_id
+  -> case_library.diagnosis_id
+
+api_document.doc_id
+  -> vector chunk metadata.docId / doc_id
+
+knowledge_domain.domain_id
+  -> api_document metadata.category / vector chunk metadata.category
+```
+
+当前实现主要使用逻辑关联，不依赖数据库外键。

mvp/tables/api_document.md

@@ -1,332 +0,0 @@
-# api_document - 文档元数据表
-
-## 表定位
-
-**文档管理表**：管理接口文档的元信息，不负责文档检索（检索由 Milvus 负责）
-
-## 设计理念
-
-### 文档管理，不是文档检索
-
-**核心定位**：
-- MySQL 负责文档元数据管理（状态、版本、去重）
-- Milvus 负责文档内容存储和检索
-- 通过 doc_id 关联两者
-
-**MVP版本原则**：
-- ✅ 最简字段，满足基本管理需求
-- ✅ 文件去重（基于 file_hash）
-- ✅ 状态追踪（索引进度）
-- ✅ 硬删除（同步删除 Milvus 数据）
-- ❌ 暂不支持：软删除、启用开关、版本管理（Phase 2）
-
----
-
-## 表结构（MVP版）
-
-```sql
-CREATE TABLE api_document (
-    -- 主键
-    id BIGINT PRIMARY KEY AUTO_INCREMENT,
-    doc_id VARCHAR(64) UNIQUE NOT NULL COMMENT '文档唯一ID（UUID），关联Milvus',
-    
-    -- 文档分类
-    fault_category VARCHAR(32) DEFAULT 'EXTERNAL_API' COMMENT '文档类别',
-    fault_source VARCHAR(128) COMMENT '文档归属（省份/服务名）',
-    api_name VARCHAR(128) COMMENT '接口名称',
-    version VARCHAR(32) DEFAULT 'v1.0' COMMENT '文档版本',
-    
-    -- 文件信息
-    file_name VARCHAR(256) NOT NULL COMMENT '原始文件名',
-    file_path VARCHAR(512) COMMENT '文件存储路径',
-    file_hash VARCHAR(64) COMMENT '文件MD5 hash（用于去重）',
-    file_size BIGINT COMMENT '文件大小（字节）',
-    
-    -- 索引状态
-    status VARCHAR(16) DEFAULT 'PENDING' COMMENT '索引状态（PENDING/PROCESSING/INDEXED/FAILED）',
-    chunk_count INT DEFAULT 0 COMMENT '分块数量',
-    error_message TEXT COMMENT '失败原因',
-    
-    -- 时间字段
-    indexed_at DATETIME COMMENT '索引完成时间',
-    created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
-    updated_at DATETIME DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
-    
-    -- 索引
-    UNIQUE INDEX uk_file_hash (file_hash),
-    INDEX idx_doc_id (doc_id),
-    INDEX idx_fault_source (fault_source),
-    INDEX idx_status (status),
-    INDEX idx_created_at (created_at)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COMMENT='文档元数据表（MVP版）';
-```
-
----
-
-## 字段说明
-
-| 字段 | 类型 | 必填 | 说明 |
-|------|------|------|------|
-| doc_id | VARCHAR(64) | 是 | **核心**：文档唯一ID，关联 Milvus |
-| fault_category | VARCHAR(32) | 否 | 文档类别 |
-| fault_source | VARCHAR(128) | 否 | 文档归属（省份/服务名）|
-| api_name | VARCHAR(128) | 否 | 接口名称 |
-| version | VARCHAR(32) | 否 | 文档版本 |
-| file_name | VARCHAR(256) | 是 | 原始文件名 |
-| file_path | VARCHAR(512) | 否 | 文件存储路径 |
-| file_hash | VARCHAR(64) | 否 | **去重关键**：文件MD5 |
-| file_size | BIGINT | 否 | 文件大小 |
-| status | VARCHAR(16) | 是 | **状态追踪**：PENDING/PROCESSING/INDEXED/FAILED |
-| chunk_count | INT | 否 | 分块数量 |
-| error_message | TEXT | 否 | 失败原因 |
-| indexed_at | DATETIME | 否 | 索引完成时间 |
-
----
-
-## 核心设计决策
-
-### 1. doc_id：MySQL 与 Milvus 的桥梁
-
-```
-作用：
-- MySQL：通过 doc_id 管理文档元数据
-- Milvus：每个 chunk 的 metadata 中携带 doc_id
-
-关联关系：
-api_document (MySQL)
-    doc_id: doc-001
-    ↓ 1:N
-Milvus chunks
-    chunk_1: {doc_id: 'doc-001', text: '...', vector: [...]}
-    chunk_2: {doc_id: 'doc-001', text: '...', vector: [...]}
-
-管理操作：
-- 删除文档：
-  DELETE FROM milvus_collection WHERE metadata["doc_id"] == 'doc-001';
-  DELETE FROM api_document WHERE doc_id = 'doc-001';
-```
-
-### 2. file_hash：文件去重
-
-```
-去重流程：
-1. 用户上传文件
-   ↓
-2. 计算文件 MD5
-   file_hash = md5(file_content)
-   ↓
-3. 检查是否已存在
-   SELECT * FROM api_document WHERE file_hash = 'abc123...';
-   ↓
-4a. 如果存在 → 提示"文档已存在"
-4b. 如果不存在 → 继续导入
-
-唯一约束：UNIQUE INDEX uk_file_hash (file_hash)
-```
-
-### 3. status：状态追踪
-
-```
-状态流转：
-PENDING (待处理)
-    ↓
-PROCESSING (处理中)
-    ↓ 成功
-INDEXED (已索引)
-    ↓ 失败
-FAILED (失败)
-
-用途：
-- 批量导入时监控进度
-- 失败重试
-- 统计索引成功率
-```
-
-### 4. 硬删除策略（MVP）
-
-```
-删除文档时：
-1. 删除 Milvus 中的所有分块
-2. 删除 MySQL 元数据
-3. 可选：删除原始文件
-
-特点：
-- 简单直接
-- 数据彻底删除
-- 不可恢复（需谨慎）
-
-Phase 2 可增强：
-- 软删除（archived_at）
-- 启用开关（enabled）
-```
-
----
-
-## 数据流
-
-### 场景1：导入新文档
-
-```
-1. 用户上传文件
-   ↓
-2. 计算 hash
-   ↓
-3. 检查去重（MySQL）
-   ↓
-4. 插入元数据（status=PROCESSING）
-   ↓
-5. 后台处理：解析 → 分块 → 向量化 → 存入 Milvus
-   ↓
-6. 更新状态（status=INDEXED, chunk_count=15）
-```
-
-### 场景2：删除文档
-
-```
-1. 用户删除文档
-   ↓
-2. 删除 Milvus 数据（WHERE metadata["doc_id"] == 'xxx'）
-   ↓
-3. 删除 MySQL 元数据
-   ↓
-4. 可选：删除原始文件
-```
-
-### 场景3：重新索引
-
-```
-1. 删除旧数据（Milvus + MySQL）
-   ↓
-2. 重新导入（同场景1）
-```
-
----
-
-## 典型查询
-
-```sql
--- 查看文档列表
-SELECT doc_id, file_name, version, status, chunk_count, indexed_at
-FROM api_document
-WHERE fault_source = '广东'
-  AND status = 'INDEXED'
-ORDER BY indexed_at DESC;
-
--- 查询失败的文档
-SELECT doc_id, file_name, error_message
-FROM api_document
-WHERE status = 'FAILED';
-
--- 统计各状态文档数量
-SELECT status, COUNT(*) as count
-FROM api_document
-GROUP BY status;
-```
-
----
-
-## 与 Milvus 的协作
-
-### Milvus Collection Schema
-
-```python
-{
-  "collection_name": "api_doc_collection",
-  "fields": [
-    {"name": "id", "type": "VARCHAR", "is_primary": true},
-    {"name": "content", "type": "VARCHAR"},
-    {"name": "vector", "type": "FLOAT_VECTOR", "dim": 1536},
-    {"name": "metadata", "type": "JSON"}
-  ]
-}
-
-# metadata 结构
-{
-  "doc_id": "doc-001",           # 关联 MySQL
-  "_source": "/path/to/file",
-  "_file_name": "xxx.docx",
-  "chunkIndex": 0,
-  "totalChunks": 15
-}
-```
-
-### Java 代码示例
-
-```java
-// 插入时携带 doc_id
-Map<String, Object> metadata = new HashMap<>();
-metadata.put("doc_id", docId);  // 关联 MySQL
-metadata.put("_source", filePath);
-metadata.put("chunkIndex", chunkIndex);
-
-// 删除文档的所有分块
-String expr = String.format("metadata[\"doc_id\"] == \"%s\"", docId);
-milvusClient.delete(DeleteParam.newBuilder()
-    .withCollectionName(COLLECTION_NAME)
-    .withExpr(expr)
-    .build());
-```
-
----
-
-## 数据示例
-
-```sql
--- 外部接口文档
-INSERT INTO api_document VALUES
-(1, 'doc-001', 'EXTERNAL_API', '广东', '社保查询', 'v2.1',
- '广东社保查询v2.1.docx', '/docs/guangdong/social-v2.1.docx',
- 'abc123...', 1048576,
- 'INDEXED', 15, NULL, '2024-06-15 10:30:00', NOW(), NOW());
-
--- 内部服务文档
-INSERT INTO api_document VALUES
-(2, 'doc-002', 'INTERNAL_ERROR', 'order-service', '订单服务API', 'v1.0',
- '订单服务API文档.pdf', '/docs/internal/order-service-api.pdf',
- 'def456...', 2097152,
- 'INDEXED', 20, NULL, '2024-06-14 15:20:00', NOW(), NOW());
-
--- 处理失败的文档
-INSERT INTO api_document VALUES
-(3, 'doc-003', 'EXTERNAL_API', '江苏', '公积金查询', 'v1.5',
- '江苏公积金查询.html', '/docs/jiangsu/fund-v1.5.html',
- 'ghi789...', 512000,
- 'FAILED', 0, '不支持HTML格式', NULL, NOW(), NOW());
-```
-
----
-
-## 数据量预估
-
-```
-预估：100-200 条
-- 外部接口文档：50-100 条
-- 内部服务文档：20-50 条
-- 其他文档：30-50 条
-
-存储：
-- 单条记录：约 1KB
-- 200 条：约 200KB
-
-结论：数据量很小
-```
-
----
-
-## MVP 版本的简化
-
-```
-Phase 1（当前）：
-✅ 基础字段和表结构
-✅ 文件去重（file_hash）
-✅ 状态追踪（status）
-✅ 硬删除
-✅ 通过 doc_id 关联 Milvus
-
-Phase 2（未来增强）：
-❌ enabled（启用开关）
-❌ archived_at（软删除）
-❌ batch_id（批次管理）
-❌ status 细化
-❌ tags（标签分类）
-```

mvp/tables/archive/2026-07-09-doc-cleanup/旧诊断记录表-diagnosis_record.md

@@ -1,4 +1,6 @@
-# diagnosis_record - 诊断记录表
+# diagnosis_record - 旧诊断记录表
+
+> 归档说明：`diagnosis_record` 已在 `V007__drop_diagnosis_record.sql` 中删除，当前主模型是 `diagnosis_session + agent_step + tool_invocation`。本文只用于追溯早期设计。
 
 ## 表定位
 

mvp/tables/case_library.md

@@ -1,265 +0,0 @@
-# case_library - 案例库表
-
-## 表定位
-
-**知识沉淀表**：存储高质量诊断案例，支持相似案例推荐
-
-## 设计理念
-
-### 知识沉淀，系统越用越智能
-
-**核心价值**：
-- 质量过滤：只存储高质量案例（成功诊断 + 用户反馈有用）
-- 知识沉淀：历史诊断经验可复用
-- 提升准确率：相似问题提供历史参考
-- 加速诊断：快速推荐相似案例
-
-**MVP版本设计原则**：
-- ✅ 能用：满足基本案例推荐功能
-- ✅ 简单：字段不多，逻辑清晰
-- ✅ 可扩展：后续可增加字段
-
----
-
-## 表结构（MVP版）
-
-```sql
-CREATE TABLE case_library (
-    -- 主键
-    id BIGINT PRIMARY KEY AUTO_INCREMENT,
-    case_id VARCHAR(64) UNIQUE NOT NULL COMMENT '案例唯一ID（UUID）',
-    
-    -- 来源关联
-    diagnosis_id VARCHAR(64) COMMENT '关联诊断记录（可选，人工录入时为空）',
-    source_type VARCHAR(16) DEFAULT 'AUTO' COMMENT '来源类型（AUTO:自动生成/MANUAL:人工录入）',
-    
-    -- 案例分类
-    fault_category VARCHAR(32) COMMENT '故障类别（EXTERNAL_API/INTERNAL_ERROR/DATABASE...）',
-    fault_source VARCHAR(128) COMMENT '故障源（省份/服务名/类名...）',
-    fault_target VARCHAR(256) COMMENT '故障目标（接口URL/方法名/SQL...）',
-    error_code VARCHAR(64) COMMENT '错误码',
-    
-    -- 案例内容
-    title VARCHAR(256) NOT NULL COMMENT '案例标题（简短描述）',
-    root_cause TEXT NOT NULL COMMENT '根因分析',
-    solution TEXT NOT NULL COMMENT '解决方案',
-    
-    -- 简单统计
-    reference_count INT DEFAULT 0 COMMENT '引用次数（被推荐的次数）',
-    
-    -- 元数据
-    created_by VARCHAR(64) COMMENT '创建人',
-    created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
-    updated_at DATETIME DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
-    
-    -- 索引
-    INDEX idx_fault_category (fault_category),
-    INDEX idx_error_code (error_code),
-    INDEX idx_fault_source (fault_source),
-    INDEX idx_fault_target (fault_target(100)),
-    INDEX idx_diagnosis_id (diagnosis_id),
-    INDEX idx_reference_count (reference_count),
-    INDEX idx_created_at (created_at)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COMMENT='案例库表（MVP版）';
-```
-
----
-
-## 字段说明
-
-| 字段 | 类型 | 必填 | 说明 |
-|------|------|------|------|
-| case_id | VARCHAR(64) | 是 | 案例唯一标识（UUID）|
-| diagnosis_id | VARCHAR(64) | 否 | 关联诊断记录（人工录入时为空）|
-| source_type | VARCHAR(16) | 是 | 来源：AUTO（自动）/MANUAL（人工）|
-| fault_category | VARCHAR(32) | 否 | 故障类别 |
-| fault_source | VARCHAR(128) | 否 | 故障源 |
-| fault_target | VARCHAR(256) | 否 | 故障目标（与 diagnosis_record 一致）|
-| error_code | VARCHAR(64) | 否 | 错误码 |
-| title | VARCHAR(256) | 是 | 案例标题 |
-| root_cause | TEXT | 是 | 根因分析（核心内容）|
-| solution | TEXT | 是 | 解决方案（核心内容）|
-| reference_count | INT | 是 | 引用次数（用于排序）|
-
----
-
-## 核心设计决策
-
-### 1. 案例来源
-
-```
-来源1：自动生成（source_type=AUTO）
-├─ 触发条件：诊断成功 + 用户反馈"有用"
-├─ 关联诊断：diagnosis_id 不为空
-└─ 质量保证：用户验证过
-
-来源2：人工录入（source_type=MANUAL）
-├─ 运维团队总结的经典案例
-├─ diagnosis_id 为空
-└─ 质量最高
-
-注意：诊断失败或用户反馈"无用"的不自动生成案例
-```
-
-### 2. 简化的评分机制（MVP）
-
-```
-MVP版本：只按 reference_count 排序
-- 引用次数多的排前面
-- 简单有效
-
-Phase 2 可增强：
-- 增加 useful_count（用户反馈有用次数）
-- 增加 score（综合评分）
-- 增加 is_featured（人工标记的经典案例）
-```
-
-### 3. 与 diagnosis_record 的关系
-
-```
-关系：一对一（可选）
-- 一次诊断 → 可以生成一个案例
-- 通过 diagnosis_id 关联
-- diagnosis_id 可为空（人工录入案例）
-
-流程：
-diagnosis_record（成功）
-    ↓
-用户反馈"有用"
-    ↓
-自动生成 case_library
-    ↓
-后续可人工修正、合并相似案例
-```
-
----
-
-## 数据示例
-
-### 示例1：外部接口故障案例
-```sql
-INSERT INTO case_library VALUES
-(1, 'case-001', 'diag-001', 'AUTO', 'EXTERNAL_API', '广东', '/api/v1/guangdong/social-security', '40003', 
- '广东社保查询idCard字段缺失', 
- '请求报文中未传入idCard字段，导致参数校验失败', 
- '前端表单增加idCard必填校验；后端增加参数校验提示', 
- 15, 'system', NOW(), NOW());
-```
-
-### 示例2：内部错误案例
-```sql
-INSERT INTO case_library VALUES
-(2, 'case-002', 'diag-045', 'AUTO', 'INTERNAL_ERROR', 'order-service', 'OrderController.createOrder()', 'NullPointerException',
- '订单服务创建订单空指针异常',
- 'OrderController.createOrder()方法中user对象为null，未做空判断',
- '在第45行添加空判断：if (user == null) throw new BizException("用户信息不存在")',
- 8, 'system', NOW(), NOW());
-```
-
-### 示例3：人工录入案例
-```sql
-INSERT INTO case_library VALUES
-(3, 'case-003', NULL, 'MANUAL', 'DATABASE', 'mysql-master-01', 'UPDATE orders SET status=? WHERE order_id=?', '1213',
- '订单库存更新死锁通用处理',
- '两个事务互相等待对方释放锁',
- '调整事务加锁顺序：统一先锁订单，再锁库存；或使用乐观锁',
- 3, 'admin', NOW(), NOW());
-```
-
----
-
-## 典型查询
-
-### 精确匹配查询
-```sql
--- 按错误码查询
-SELECT * FROM case_library
-WHERE error_code = '40003'
-ORDER BY reference_count DESC
-LIMIT 5;
-
--- 按故障类别 + 错误码 + 故障目标查询
-SELECT * FROM case_library
-WHERE fault_category = 'INTERNAL_ERROR'
-  AND error_code = 'NullPointerException'
-  AND fault_target = 'OrderController.createOrder()'
-ORDER BY reference_count DESC
-LIMIT 5;
-```
-
-### 统计分析
-```sql
--- 统计案例分布
-SELECT 
-  fault_category,
-  COUNT(*) as count,
-  AVG(reference_count) as avg_reference
-FROM case_library
-GROUP BY fault_category
-ORDER BY count DESC;
-
--- Top 引用案例
-SELECT title, reference_count, created_at
-FROM case_library
-ORDER BY reference_count DESC
-LIMIT 10;
-```
-
----
-
-## 与 Milvus 的配合
-
-### 混合检索策略
-
-```
-1. 精确匹配（MySQL）
-   - 按 error_code 查询
-   - 按 fault_category + fault_source 查询
-   - 优点：快速、准确
-
-2. 语义检索（Milvus）
-   - 将案例内容向量化
-   - 按语义相似度查询
-   - 优点：能找到相似但不同错误码的案例
-
-3. 混合策略（推荐）
-   Step 1: 先精确匹配（MySQL）
-   Step 2: 如果结果 < 3 个，补充语义检索（Milvus）
-   Step 3: 合并去重，按 reference_count 排序
-   Step 4: 返回 Top 5
-```
-
----
-
-## 数据量预估
-
-```
-预估：500-1000 条
-- 初期：每月新增 10-20 条
-- 稳定期：每月新增 5-10 条
-- 总量：1-2 年达到稳定
-
-存储：
-- 单条记录：约 2KB
-- 1000 条：约 2MB
-
-结论：数据量很小
-```
-
----
-
-## MVP 版本的简化
-
-```
-Phase 1（当前）：
-✅ 基础字段和表结构
-✅ 自动生成案例
-✅ 人工录入案例
-✅ 按 reference_count 简单排序
-
-Phase 2（未来增强）：
-❌ useful_count + score（复杂评分）
-❌ 版本管理
-❌ 标签分类（tags）
-❌ 案例合并功能
-```

mvp/tables/工具调用表-tool_invocation.md

@@ -0,0 +1,66 @@
+# 工具调用表：tool_invocation
+
+**状态**：当前表  
+**来源**：`V005__create_session_storage.sql`、`V010__add_relevance_level_to_tool_invocation.sql`、`ToolInvocation`
+
+## 定位
+
+`tool_invocation` 记录 Agent 显式调用工具的事实，包括工具名、入参、输出摘要、检索层级、证据引用和失败信息。它是 Trace、Verifier、评测和人工排查的共同数据源。
+
+## 字段
+
+| 字段 | 类型 | 必填 | 说明 |
+|---|---|---|---|
+| `id` | BIGINT | 是 | 自增主键 |
+| `session_id` | VARCHAR(64) | 是 | 关联 `diagnosis_session.session_id` |
+| `step_id` | BIGINT | 否 | 可关联 `agent_step.id` |
+| `tool_name` | VARCHAR(64) | 是 | 工具名称，例如 `lookup_knowledge`、日志查询、指标查询 |
+| `input_params` | JSON | 是 | 工具入参 |
+| `output_preview` | TEXT | 否 | 工具输出摘要或前缀 |
+| `output_length` | INT | 否 | 工具输出字符数 |
+| `retrieval_layer` | VARCHAR(8) | 否 | 检索层级，例如 `L0`、`L1`、`L0+L1` |
+| `l0_match_count` | INT | 否 | L0 命中数量 |
+| `l1_match_count` | INT | 否 | L1 命中数量 |
+| `is_truncated` | BOOLEAN | 否 | 输出是否被截断 |
+| `relevance_level` | VARCHAR(20) | 否 | 归一化质量等级：`PRECISE`、`HIGHLY_RELEVANT`、`REFERENCE`、`DEDUPED` |
+| `dedup_reason` | VARCHAR(32) | 否 | 去重原因，例如 `doc_retrieved`、`domain_retrieved` |
+| `retrieval_details` | JSON | 否 | 检索明细、证据引用、Gatekeeper 可用导航信息 |
+| `duration_ms` | INT | 否 | 工具耗时 |
+| `success` | BOOLEAN | 否 | 工具是否成功 |
+| `error_message` | TEXT | 否 | 失败原因 |
+| `created_at` | DATETIME | 是 | 创建时间 |
+
+## 索引
+
+| 索引 | 字段 | 用途 |
+|---|---|---|
+| `idx_session_id` | `session_id` | 按会话查询工具调用 |
+| `idx_tool_name` | `tool_name` | 按工具类型排查 |
+| `idx_retrieval_layer` | `retrieval_layer` | 观察 RAG L0/L1 行为 |
+
+## 关系
+
+- `tool_invocation.session_id` 逻辑关联 `diagnosis_session.session_id`。
+- `tool_invocation.step_id` 可关联 `agent_step.id`，但当前不强制。
+
+## 关键 JSON
+
+`retrieval_details` 是扩展字段。当前重要结构包括：
+
+```json
+{
+  "evidence_status": "supported",
+  "evidence_refs": [
+    {
+      "raw_path": "$.logs[0]",
+      "text": "工具返回中可核对的最小证据文本"
+    }
+  ]
+}
+```
+
+## 注意点
+
+- Verifier 不应只信任 RAG 证据；所有工具只要能提供 `evidence_refs`，都应该进入可校验证据链。
+- `output_preview` 只适合展示和排查，不应被当成完整原始输出。
+- `$.no_evidence` 只代表“本次工具未命中证据”，不能推导为“故障不存在”。

mvp/tables/文档元数据表-api_document.md

@@ -0,0 +1,51 @@
+# 文档元数据表：api_document
+
+**状态**：当前表  
+**来源**：`V003__create_api_document.sql`、`V004__add_metadata_to_api_document.sql`、`ApiDocument`
+
+## 定位
+
+`api_document` 是知识库文档的 MySQL 元数据表。它不保存向量正文，正文切片和向量检索由 Milvus/Zilliz collection 承担；两侧通过 `doc_id` 和 chunk metadata 逻辑关联。
+
+## 字段
+
+| 字段 | 类型 | 必填 | 说明 |
+|---|---|---|---|
+| `id` | BIGINT | 是 | 自增主键 |
+| `doc_id` | VARCHAR(64) | 是 | 文档唯一 ID，关联向量库 chunk metadata |
+| `fault_category` | VARCHAR(32) | 否 | 文档类别，默认 `EXTERNAL_API`；实体侧使用 `FaultCategory` |
+| `fault_source` | VARCHAR(128) | 否 | 文档归属，例如服务名、省份或系统来源 |
+| `api_name` | VARCHAR(128) | 否 | 接口或文档主题名称 |
+| `version` | VARCHAR(32) | 否 | 文档版本，默认 `v1.0` |
+| `file_name` | VARCHAR(256) | 是 | 原始文件名 |
+| `file_path` | VARCHAR(512) | 否 | 文件存储路径 |
+| `file_hash` | VARCHAR(64) | 否 | 文件 MD5，用于去重 |
+| `file_size` | BIGINT | 否 | 文件大小，单位字节 |
+| `status` | VARCHAR(16) | 否 | 索引状态：`PENDING`、`PROCESSING`、`INDEXED`、`FAILED` |
+| `chunk_count` | INT | 否 | 向量库切片数量 |
+| `error_message` | TEXT | 否 | 索引失败原因 |
+| `metadata` | TEXT | 否 | frontmatter 元数据 JSON 字符串 |
+| `indexed_at` | DATETIME | 否 | 索引完成时间 |
+| `created_at` | DATETIME | 是 | 创建时间 |
+| `updated_at` | DATETIME | 是 | 更新时间 |
+
+## 索引
+
+| 索引 | 字段 | 用途 |
+|---|---|---|
+| `uk_file_hash` | `file_hash` | 文件去重 |
+| `idx_doc_id` | `doc_id` | 按文档 ID 查询 |
+| `idx_fault_source` | `fault_source` | 按来源筛选 |
+| `idx_status` | `status` | 查看索引状态 |
+| `idx_created_at` | `created_at` | 按上传时间排序 |
+
+## 关系
+
+- `api_document.doc_id` 与向量库 chunk metadata 中的 `docId` / `doc_id` 逻辑关联。
+- `knowledge_domain.domain_id` 与文档 metadata 中的 `category` 形成领域聚合关系；当前没有数据库外键。
+
+## 注意点
+
+- 删除文档时需要同时处理 MySQL 元数据和向量库 chunk。
+- `metadata` 是 JSON 字符串，不是 MySQL JSON 列。
+- 表字段以 Flyway 为准；实体默认值和枚举可能与迁移脚本的 SQL 默认值存在历史差异，排查时优先看实际迁移和数据库结构。

mvp/tables/案例库表-case_library.md

@@ -0,0 +1,50 @@
+# 案例库表：case_library
+
+**状态**：当前表  
+**来源**：`V002__create_case_library.sql`、`CaseLibrary`
+
+## 定位
+
+`case_library` 保存高质量诊断案例，用于后续相似案例推荐和知识沉淀。当前自动沉淀路径来自 `useful` 用户反馈：系统把 `diagnosis_session` 中的 query 和 answer 映射为案例内容。
+
+## 字段
+
+| 字段 | 类型 | 必填 | 说明 |
+|---|---|---|---|
+| `id` | BIGINT | 是 | 自增主键 |
+| `case_id` | VARCHAR(64) | 是 | 案例唯一 ID |
+| `diagnosis_id` | VARCHAR(64) | 否 | 关联诊断会话；当前自动生成时存 `diagnosis_session.session_id` |
+| `source_type` | VARCHAR(16) | 否 | 来源类型：`AUTO` 或 `MANUAL` |
+| `fault_category` | VARCHAR(32) | 否 | 故障类别，实体侧使用 `FaultCategory` |
+| `fault_source` | VARCHAR(128) | 否 | 故障源，例如服务、系统或省份 |
+| `fault_target` | VARCHAR(256) | 否 | 故障目标，例如接口、方法、SQL 或组件 |
+| `error_code` | VARCHAR(64) | 否 | 错误码或异常类型 |
+| `title` | VARCHAR(256) | 是 | 案例标题 |
+| `root_cause` | TEXT | 是 | 根因分析 |
+| `solution` | TEXT | 是 | 解决方案 |
+| `reference_count` | INT | 否 | 被推荐次数 |
+| `created_by` | VARCHAR(64) | 否 | 创建人 |
+| `created_at` | DATETIME | 是 | 创建时间 |
+| `updated_at` | DATETIME | 是 | 更新时间 |
+
+## 索引
+
+| 索引 | 字段 | 用途 |
+|---|---|---|
+| `idx_fault_category` | `fault_category` | 按故障类别筛选 |
+| `idx_error_code` | `error_code` | 按错误码精确匹配 |
+| `idx_fault_source` | `fault_source` | 按故障源筛选 |
+| `idx_fault_target` | `fault_target(100)` | 按故障目标筛选 |
+| `idx_diagnosis_id` | `diagnosis_id` | 追溯来源会话 |
+| `idx_reference_count` | `reference_count` | 推荐排序 |
+| `idx_created_at` | `created_at` | 时间排序 |
+
+## 关系
+
+- `case_library.diagnosis_id` 当前逻辑关联 `diagnosis_session.session_id`，不是旧的 `diagnosis_record`。
+- 人工录入案例可以不填写 `diagnosis_id`。
+
+## 注意点
+
+- 旧文档里提到的 `diagnosis_record` 已被 `V007` 删除，不再是当前主模型。
+- 当前自动沉淀仍比较粗：`root_cause` 和 `solution` 都可能来自完整 answer。后续可从结构化结论中拆分根因、证据和修复建议。

mvp/tables/知识域表-knowledge_domain.md

@@ -0,0 +1,36 @@
+# 知识域表：knowledge_domain
+
+**状态**：当前表  
+**来源**：`V009__add_knowledge_domain.sql`、`KnowledgeDomain`
+
+## 定位
+
+`knowledge_domain` 保存知识库领域级元数据，用来帮助 Planner/Executor 判断什么时候检索某一类知识，并为 RAG 的 domain hint、去重和可观测性提供基础信息。
+
+## 字段
+
+| 字段 | 类型 | 必填 | 说明 |
+|---|---|---|---|
+| `id` | BIGINT | 是 | 自增主键 |
+| `domain_id` | VARCHAR(64) | 是 | 领域 ID，通常对应文档 category，例如 `payment`、`infrastructure` |
+| `description` | VARCHAR(256) | 否 | 领域描述 |
+| `when_to_retrieve` | TEXT | 否 | 何时检索该领域的提示说明 |
+| `document_count` | INT | 是 | 当前领域文档数量 |
+| `created_at` | DATETIME | 是 | 创建时间 |
+| `updated_at` | DATETIME | 是 | 更新时间 |
+
+## 索引
+
+| 索引 | 字段 | 用途 |
+|---|---|---|
+| unique | `domain_id` | 保证领域 ID 唯一 |
+
+## 关系
+
+- `knowledge_domain.domain_id` 与 `api_document.metadata` 或向量库 chunk metadata 中的 `category` 逻辑关联。
+- 当前没有数据库外键，领域文档数量由服务逻辑维护。
+
+## 注意点
+
+- `when_to_retrieve` 是检索策略提示，不是事实证据。
+- Executor / Verifier 不能把领域描述当作诊断结论依据；事实仍应来自工具返回的证据块或证据引用。

mvp/tables/诊断会话表-diagnosis_session.md

@@ -0,0 +1,47 @@
+# 诊断会话表：diagnosis_session
+
+**状态**：当前主表  
+**来源**：`V005__create_session_storage.sql`、`V008__add_answer_to_diagnosis_session.sql`、`DiagnosisSession`
+
+## 定位
+
+`diagnosis_session` 是一次 Chat 或 AIOps 诊断的会话级主记录，负责保存用户问题、执行状态、最终答案、总体统计和自评估结果。
+
+## 字段
+
+| 字段 | 类型 | 必填 | 说明 |
+|---|---|---|---|
+| `id` | BIGINT | 是 | 自增主键 |
+| `session_id` | VARCHAR(64) | 是 | 会话唯一 ID，Trace API 和反馈接口使用它 |
+| `query` | TEXT | 是 | 用户原始问题或 AIOps 输入摘要 |
+| `status` | VARCHAR(16) | 否 | `PENDING`、`RUNNING`、`SUCCESS`、`FAILED` |
+| `agent_flow` | VARCHAR(32) | 否 | `CHAT` 或 `AI_OPS` |
+| `total_duration_ms` | INT | 否 | 总耗时，单位毫秒 |
+| `total_token_count` | INT | 否 | 总 Token 消耗 |
+| `step_count` | INT | 否 | Agent 步骤数 |
+| `tool_call_count` | INT | 否 | 工具调用次数 |
+| `answer` | LONGTEXT | 否 | 返回给用户的最终答案 |
+| `self_evaluation` | JSON | 否 | rule、verifier、aiops 等自评估结果容器 |
+| `feedback` | VARCHAR(16) | 否 | 用户反馈：`useful`、`not_useful` 或空 |
+| `created_at` | DATETIME | 是 | 创建时间 |
+| `updated_at` | DATETIME | 是 | 更新时间 |
+
+## 索引
+
+| 索引 | 字段 | 用途 |
+|---|---|---|
+| `session_id` unique | `session_id` | 会话唯一约束 |
+| `idx_created_at` | `created_at` | 按时间查询 |
+| `idx_status` | `status` | 按状态筛选 |
+| `idx_agent_flow` | `agent_flow` | 区分 Chat / AIOps |
+
+## 关系
+
+- `agent_step.session_id` 逻辑关联 `diagnosis_session.session_id`。
+- `tool_invocation.session_id` 逻辑关联 `diagnosis_session.session_id`。
+- `case_library.diagnosis_id` 在自动生成案例时保存 `diagnosis_session.session_id`。
+
+## 注意点
+
+- 当前没有数据库外键，Trace 聚合依赖 `session_id`。
+- `self_evaluation` 是扩展容器，里面可能包含 `rule_evaluation`、`verifier_evaluation`、`aiops_rule_evaluation`。

openspec/changes/archive/2026-07-08-executor-composer-final-answer/decisions.md

@@ -30,7 +30,7 @@
 
 | Source | Alignment |
 |---|---|
-| Issue objective | Stage four in `mvp/issues/executor-structured-output-v2.md` requires Composer output final answer from Verifier-allowed material. Covered by proposal, design, specs, and tasks. |
+| Issue objective | Stage four in `mvp/issues/design-notes/executor-structured-output-v2.md` requires Composer output final answer from Verifier-allowed material. Covered by proposal, design, specs, and tasks. |
 | Proposal -> design | Proposal says Composer owns final expression; design defines input filtering, output parsing, fallback, and audit. |
 | Design -> specs | Design decisions are reflected in `chat-composer-agent` requirements and modified `chat-verifier-agent` routing requirements. |
 | Specs -> tasks | Each required behavior has implementation and test tasks, including malformed fallback and no raw output leakage. |

openspec/changes/archive/2026-07-08-verifier-evidence-reference-fidelity/decisions.md

@@ -2,7 +2,7 @@
 
 ## Discover Context
 
-- Source issue: `mvp/issues/ISS-007-verifier-evidence-summary-fidelity.md`.
+- Source issue: `mvp/issues/archived/ISS-007-verifier-evidence-summary-fidelity.md`.
 - Related existing specs: `chat-verifier-agent`, `evidence-trace-hardening`.
 - Related devflow records: `executor-gatekeeper-hook`, `executor-verifier-claim-checks`, `executor-composer-final-answer`, `evidence-trace-hardening`.
 - Current repo instruction requested semantic code search and LSP confirmation before code changes; those tools are not exposed in this environment, so implementation will use `rg`, direct code reading, and focused tests as fallback evidence.

openspec/changes/archive/2026-07-09-interview-demo-quality-audit/.archive-ready

@@ -0,0 +1 @@
+ready

openspec/changes/archive/2026-07-09-interview-demo-quality-audit/.committed

@@ -0,0 +1 @@
+committed

openspec/changes/archive/2026-07-09-interview-demo-quality-audit/design.md

@@ -0,0 +1,117 @@
+# Design: Interview Demo Quality Audit
+
+## Overview
+
+The change adds auditability and demo readiness without changing Agent routing.
+
+```text
+ChatService prompt resources
+  -> PromptAuditService
+  -> verifier_evaluation.prompt_audit
+  -> Trace API
+  -> DiagnosisTraceEvaluator
+  -> baseline report
+
+mvp/demo/scripts/run-interview-demo-check.ps1
+  -> health/readiness check
+  -> payment timeout chat
+  -> trace fetch
+  -> feedback
+  -> demo output bundle
+```
+
+## Prompt Audit
+
+Add a compact `prompt_audit` object under:
+
+```text
+diagnosis_session.self_evaluation.verifier_evaluation.prompt_audit
+```
+
+Shape:
+
+```json
+{
+  "version": "chat-prompts-v1",
+  "prompts": [
+    {
+      "name": "chat_planner",
+      "version": "chat-planner-v1",
+      "resource": "prompts/chat-planner-prompt.md"
+    }
+  ]
+}
+```
+
+Design choices:
+
+- Use explicit local metadata, not full prompt hashes, because the interview goal is explainable version audit rather than cryptographic integrity.
+- Keep this metadata in code or a small resource catalog near prompt loading.
+- Persist prompt audit with every Chat verifier evaluation, including fallback/degraded paths.
+- Do not include full prompt text in trace.
+
+## Eval Expansion
+
+Extend `DiagnosisEvalCase` with optional fields:
+
+- `requirePromptAudit`
+- `expectedPromptAuditVersion`
+- `expectedPromptVersions`
+- `requireGatekeeperRules`
+
+Evaluator behavior:
+
+- If `requirePromptAudit=true`, `verifier_evaluation.prompt_audit.version` must exist.
+- If `expectedPromptAuditVersion` is set, it must match.
+- If `expectedPromptVersions` is set, each listed prompt name/version pair must exist.
+- If `requireGatekeeperRules=true`, `gatekeeper_result.rules` must be a non-empty list and each item must include `id`, `enabled`, and `default_severity`.
+
+Add at least two fixture-backed cases:
+
+- A positive audit closure case that requires prompt audit + Gatekeeper rules.
+- A metadata-gap negative case represented as `LOW_CONFID`/safe final answer, used to prove the evaluator catches missing audit metadata when configured.
+
+The baseline must remain fully passing after fixtures are updated.
+
+## Demo Stabilization
+
+Add a PowerShell script:
+
+```text
+mvp/demo/scripts/run-interview-demo-check.ps1
+```
+
+Responsibilities:
+
+- Accept base URL and session id parameters.
+- Check that the service is reachable.
+- Run the existing payment-timeout chat request.
+- Fetch trace for the same session id.
+- Submit useful feedback.
+- Write outputs under `mvp/demo/output/`.
+- Emit a concise summary with session id, verdict, Gatekeeper rule version, prompt audit version, and output paths.
+
+The script should fail fast with actionable messages when the service is unavailable.
+
+## Documentation
+
+Add/update:
+
+- `mvp/demo/README.md`: mention the preflight script.
+- `mvp/demo/ten-minute-interview-demo.md`: use the preflight script as the recommended path.
+- `mvp/demo/interview-q-and-a.md`: concise interview answers for Agent engineering tradeoffs.
+- `mvp/architecture/harness-quality-gates.md`: record prompt audit as part of the quality gate.
+
+## Verification
+
+Required:
+
+- Targeted unit/eval tests for prompt audit persistence and evaluator checks.
+- Regenerated baseline JSON/Markdown reports.
+- OpenSpec validation.
+
+E2E:
+
+- If local dependencies are available, run Spring Boot with `mvp-demo` profile and execute the new preflight script.
+- If unavailable, record the reason and rely on deterministic unit/eval evidence.
+

openspec/changes/archive/2026-07-09-interview-demo-quality-audit/proposal.md

@@ -0,0 +1,58 @@
+# Change: Interview Demo Quality Audit
+
+## Problem
+
+SuperBizAgent MVP is now strong enough to demonstrate traceable Agent engineering, but the interview path still has three gaps:
+
+- The live demo has a run script, but no preflight command that checks service readiness and produces a concise interview evidence bundle.
+- The diagnosis eval baseline covers the V2 evidence pipeline, but it does not yet assert prompt-version audit data and has limited coverage for audit metadata gaps.
+- Gatekeeper already exposes `rule_set_version`, but prompt versions are not persisted with the verifier evaluation, making prompt changes harder to explain, compare, and roll back in an interview.
+
+This change stabilizes the MVP as an interview artifact rather than adding a new diagnosis architecture.
+
+## Proposed Solution
+
+Implement a small internal quality/audit increment:
+
+1. Add prompt version audit metadata to Chat verifier evaluation.
+2. Extend deterministic diagnosis eval cases/fixtures to assert prompt audit metadata and audit-metadata failures.
+3. Add an interview demo preflight script and documentation that can be run before or during a demo to verify service readiness, execute the payment timeout path, fetch trace, and record key audit fields.
+4. Add/update MVP documentation for interview Q&A and the new audit/preflight workflow.
+
+## Scope
+
+In scope:
+
+- Internal `diagnosis_session.self_evaluation.verifier_evaluation` audit JSON.
+- Diagnosis eval case schema, evaluator checks, fixtures, and baseline reports.
+- MVP demo scripts/docs.
+- Architecture/demo documentation for prompt and Gatekeeper version audit.
+
+Out of scope:
+
+- Public HTTP API changes.
+- Database schema changes.
+- New Agent roles, MCP tool server migration, process isolation, or AIOps LLM Verifier.
+- Replacing existing `Planner -> Executor -> Gatekeeper -> Verifier -> Composer` orchestration.
+- Guaranteeing live LLM `PASS` for every demo run. Live demo compatibility and deterministic fixture regression are separate acceptance paths.
+
+## Context Constraints From devflow
+
+- Evidence Tools produce incident facts and must be recorded in `tool_invocation`.
+- Chat quality gates are layered: Gatekeeper verifies evidence references, Verifier judges derivability, Composer controls expression.
+- `diagnosis eval` is deterministic and fixture-backed; no LLM-as-judge.
+- Demo assets should be runnable, but interview safety should not depend solely on live LLM behavior.
+- Gatekeeper rule metadata is metadata-only; dynamic rule execution is out of scope.
+
+## Interface Impact
+
+Level: L2 internal contract change.
+
+Reason: `verifier_evaluation` gains a compact `prompt_audit` object. Existing public API shape remains the same, and the value is exposed only through already-existing trace/self-evaluation JSON.
+
+## Risks
+
+- Baseline report churn is expected when adding cases; JSON and Markdown reports must be regenerated together.
+- Prompt audit must be deterministic and stable enough for eval fixtures; avoid hashing full prompt text with environment-specific content.
+- Demo preflight must not hardcode secrets and must tolerate local service unavailability with clear failure messages.
+

openspec/changes/archive/2026-07-09-interview-demo-quality-audit/specs/chat-verifier-agent/spec.md

@@ -0,0 +1,16 @@
+## MODIFIED Requirements
+
+### Requirement: Verifier SHALL be observable
+The Verifier's verdict SHALL be persisted for observability.
+
+#### Scenario: prompt audit written to verifier evaluation
+- **WHEN** the Chat verifier evaluation is persisted
+- **THEN** the system SHALL include a `prompt_audit` object under `diagnosis_session.self_evaluation.verifier_evaluation`
+- **AND** `prompt_audit.version` SHALL identify the Chat prompt audit catalog version
+- **AND** `prompt_audit.prompts` SHALL include the planner, executor, verifier, and composer prompt names and versions
+- **AND** full prompt text SHALL NOT be persisted in `prompt_audit`
+
+#### Scenario: prompt audit available on fallback paths
+- **WHEN** Chat verifier parsing fails, Composer parsing fails, or Chat produces a degraded answer
+- **THEN** the persisted verifier evaluation SHALL still include `prompt_audit`
+

openspec/changes/archive/2026-07-09-interview-demo-quality-audit/specs/diagnosis-eval-harness/spec.md

@@ -0,0 +1,21 @@
+## MODIFIED Requirements
+
+### Requirement: Diagnosis eval SHALL validate trace fixtures deterministically
+The diagnosis eval harness SHALL evaluate saved trace fixtures without invoking an LLM judge.
+
+#### Scenario: prompt audit assertions are enforced
+- **WHEN** an eval case sets `requirePromptAudit=true`
+- **THEN** the evaluator SHALL require `verifier_evaluation.prompt_audit.version`
+- **AND** when `expectedPromptAuditVersion` is configured, it SHALL match exactly
+- **AND** when `expectedPromptVersions` is configured, each configured prompt name SHALL appear with the expected version
+
+#### Scenario: Gatekeeper rule metadata assertions are enforced
+- **WHEN** an eval case sets `requireGatekeeperRules=true`
+- **THEN** the evaluator SHALL require `verifier_evaluation.gatekeeper_result.rules` to be non-empty
+- **AND** each rule item SHALL include `id`, `enabled`, and `default_severity`
+
+#### Scenario: expanded baseline remains passing
+- **WHEN** the committed fixture set is evaluated
+- **THEN** every case SHALL pass
+- **AND** baseline JSON and Markdown reports SHALL reflect the expanded case count and verdict distribution
+

openspec/changes/archive/2026-07-09-interview-demo-quality-audit/specs/mvp-demo-trace-acceptance/spec.md

@@ -0,0 +1,22 @@
+## MODIFIED Requirements
+
+### Requirement: MVP demo SHALL be reproducible for interviews
+The MVP demo SHALL provide a repeatable way to show a diagnosis answer, trace, verifier evaluation, and feedback.
+
+#### Scenario: interview demo check script records an evidence bundle
+- **WHEN** the user runs the interview demo check script against a running `mvp-demo` service
+- **THEN** the script SHALL submit a fixed Chat diagnosis request
+- **AND** it SHALL fetch the trace for the same session id
+- **AND** it SHALL submit useful feedback for that session
+- **AND** it SHALL write chat, trace, feedback, and summary outputs under `mvp/demo/output/`
+
+#### Scenario: interview demo check fails with actionable readiness output
+- **WHEN** the target service is not reachable
+- **THEN** the script SHALL fail before issuing diagnosis requests
+- **AND** the failure message SHALL name the base URL and the expected startup profile
+
+#### Scenario: interview documentation explains audit fields
+- **WHEN** an interviewer asks how prompt or Gatekeeper changes are audited
+- **THEN** the demo documentation SHALL point to `prompt_audit.version` and `gatekeeper_result.rule_set_version`
+- **AND** it SHALL explain that deterministic eval fixtures are the regression source of truth
+

openspec/changes/archive/2026-07-09-interview-demo-quality-audit/tasks.md

@@ -0,0 +1,32 @@
+## 1. OpenSpec And devflow
+
+- [x] 1.1 Create OpenSpec proposal/design/spec/tasks for `interview-demo-quality-audit`.
+- [x] 1.2 Record context, question pool, interface impact, audit, and verification plan in devflow decisions.
+- [x] 1.3 Pass OpenSpec validation and create `.committed`.
+
+## 2. Prompt/Gatekeeper Version Audit
+
+- [x] 2.1 Add compact Chat prompt audit metadata for planner, executor, verifier, and composer prompts.
+- [x] 2.2 Persist `prompt_audit` under `verifier_evaluation` for Chat verifier/composer outcomes.
+- [x] 2.3 Add focused tests proving prompt audit appears in persisted verifier evaluation.
+- [x] 2.4 Extend eval checks for prompt audit and Gatekeeper rule metadata.
+
+## 3. Eval Expansion
+
+- [x] 3.1 Extend diagnosis eval case/result schema for prompt audit fields.
+- [x] 3.2 Add fixture-backed cases for audit closure coverage.
+- [x] 3.3 Regenerate baseline JSON and Markdown reports.
+- [x] 3.4 Update eval docs/schema.
+
+## 4. Interview Demo Stabilization
+
+- [x] 4.1 Add `run-interview-demo-check.ps1` with service preflight, chat, trace, feedback, and summary output.
+- [x] 4.2 Update demo README and 10-minute script to use the preflight path.
+- [x] 4.3 Add interview Q&A documentation focused on Agent engineering tradeoffs.
+
+## 5. Verification And Archive
+
+- [x] 5.1 Run targeted tests for ChatService/prompt audit and diagnosis eval.
+- [x] 5.2 Run relevant broader regression tests.
+- [x] 5.3 Run E2E demo check with `mvp-demo` profile if dependencies are available; otherwise record the blocker.
+- [x] 5.4 Archive the OpenSpec change, update devflow artifacts, and commit implementation + archive.

openspec/specs/chat-verifier-agent/spec.md

@@ -145,6 +145,17 @@ The Verifier's verdict and downstream final-answer composition SHALL be persiste
 - **THEN** `diagnosis_session.self_evaluation.verifier_evaluation` SHALL include `gatekeeper_result`
 - **AND** existing verifier fields such as `verdict`, `facts_checked`, `executor_output_parse_status`, and `tool_trace_summary` SHALL be preserved
 
+#### Scenario: prompt audit written to verifier evaluation
+- **WHEN** the Chat verifier evaluation is persisted
+- **THEN** the system SHALL include a `prompt_audit` object under `diagnosis_session.self_evaluation.verifier_evaluation`
+- **AND** `prompt_audit.version` SHALL identify the Chat prompt audit catalog version
+- **AND** `prompt_audit.prompts` SHALL include the planner, executor, verifier, and composer prompt names and versions
+- **AND** full prompt text SHALL NOT be persisted in `prompt_audit`
+
+#### Scenario: prompt audit available on fallback paths
+- **WHEN** Chat verifier parsing fails, Composer parsing fails, or Chat produces a degraded answer
+- **THEN** the persisted verifier evaluation SHALL still include `prompt_audit`
+
 ### Requirement: self_evaluation SHALL be a container object
 The `diagnosis_session.self_evaluation` field SHALL store multiple evaluation channels in one JSON object.
 

openspec/specs/diagnosis-eval-harness/spec.md

@@ -195,3 +195,22 @@ The evaluation harness SHALL be able to assert the Gatekeeper rule set version r
 - **WHEN** an evaluation case declares `expectedGatekeeperRuleSetVersion`
 - **AND** the fixture has a different or missing rule set version
 - **THEN** the case SHALL fail with a clear failed check
+
+### Requirement: Diagnosis eval SHALL validate trace fixtures deterministically
+The diagnosis eval harness SHALL evaluate saved trace fixtures without invoking an LLM judge.
+
+#### Scenario: prompt audit assertions are enforced
+- **WHEN** an eval case sets `requirePromptAudit=true`
+- **THEN** the evaluator SHALL require `verifier_evaluation.prompt_audit.version`
+- **AND** when `expectedPromptAuditVersion` is configured, it SHALL match exactly
+- **AND** when `expectedPromptVersions` is configured, each configured prompt name SHALL appear with the expected version
+
+#### Scenario: Gatekeeper rule metadata assertions are enforced
+- **WHEN** an eval case sets `requireGatekeeperRules=true`
+- **THEN** the evaluator SHALL require `verifier_evaluation.gatekeeper_result.rules` to be non-empty
+- **AND** each rule item SHALL include `id`, `enabled`, and `default_severity`
+
+#### Scenario: expanded baseline remains passing
+- **WHEN** the committed fixture set is evaluated
+- **THEN** every case SHALL pass
+- **AND** baseline JSON and Markdown reports SHALL reflect the expanded case count and verdict distribution

openspec/specs/mvp-demo-trace-acceptance/spec.md

@@ -56,6 +56,26 @@ The MVP demo SHALL provide scripts and request payloads for running the payment-
 - **WHEN** the demo script finishes successfully
 - **THEN** it SHALL write chat, trace, and feedback responses under a demo output directory
 
+### Requirement: MVP demo SHALL be reproducible for interviews
+The MVP demo SHALL provide a repeatable way to show a diagnosis answer, trace, verifier evaluation, and feedback.
+
+#### Scenario: interview demo check script records an evidence bundle
+- **WHEN** the user runs the interview demo check script against a running `mvp-demo` service
+- **THEN** the script SHALL submit a fixed Chat diagnosis request
+- **AND** it SHALL fetch the trace for the same session id
+- **AND** it SHALL submit useful feedback for that session
+- **AND** it SHALL write chat, trace, feedback, and summary outputs under `mvp/demo/output/`
+
+#### Scenario: interview demo check fails with actionable readiness output
+- **WHEN** the target service is not reachable
+- **THEN** the script SHALL fail before issuing diagnosis requests
+- **AND** the failure message SHALL name the base URL and the expected startup profile
+
+#### Scenario: interview documentation explains audit fields
+- **WHEN** an interviewer asks how prompt or Gatekeeper changes are audited
+- **THEN** the demo documentation SHALL point to `prompt_audit.version` and `gatekeeper_result.rule_set_version`
+- **AND** it SHALL explain that deterministic eval fixtures are the regression source of truth
+
 ### Requirement: MVP demo SHALL provide a trace inspection checklist
 The MVP demo SHALL document which trace fields to inspect for evidence, verifier behavior, and session-level auditability.
 

src/main/java/com/superbiz/agent/eval/DiagnosisEvalCase.java

@@ -6,6 +6,7 @@ import lombok.Data;
 import lombok.NoArgsConstructor;
 
 import java.util.List;
+import java.util.Map;
 
 @Data
 @Builder
@@ -29,4 +30,8 @@ public class DiagnosisEvalCase {
     private String expectedGatekeeperRuleSetVersion;
     private List<String> expectedComposerStatuses;
     private List<String> forbiddenConfirmedClaimKeywords;
+    private Boolean requirePromptAudit;
+    private String expectedPromptAuditVersion;
+    private Map<String, String> expectedPromptVersions;
+    private Boolean requireGatekeeperRules;
 }

src/main/java/com/superbiz/agent/eval/DiagnosisEvalReportWriter.java

@@ -46,8 +46,8 @@ public class DiagnosisEvalReportWriter {
         }
 
         builder.append("## Cases\n\n");
-        builder.append("| Case | Result | Verdict | Gatekeeper | Rule Set | Composer | Claim Checks | Keywords | Tool Calls | Duration ms | Failed Checks |\n");
+        builder.append("| Case | Result | Verdict | Gatekeeper | Rule Set | Prompt Audit | Composer | Claim Checks | Rules | Keywords | Tool Calls | Duration ms | Failed Checks |\n");
-        builder.append("| --- | --- | --- | --- | --- | --- | ---: | --- | ---: | ---: | --- |\n");
+        builder.append("| --- | --- | --- | --- | --- | --- | --- | ---: | ---: | --- | ---: | ---: | --- |\n");
         for (DiagnosisEvalResult result : report.getResults()) {
             builder.append("| ")
                     .append(result.getCaseId())
@@ -60,10 +60,14 @@ public class DiagnosisEvalReportWriter {
                     .append(" | ")
                     .append(valueOrDash(result.getGatekeeperRuleSetVersion()))
                     .append(" | ")
+                    .append(valueOrDash(result.getPromptAuditVersion()))
+                    .append(" | ")
                     .append(valueOrDash(result.getComposerStatus()))
                     .append(" | ")
                     .append(result.getClaimCheckCount() == null ? "-" : result.getClaimCheckCount())
                     .append(" | ")
+                    .append(result.getGatekeeperRuleCount() == null ? "-" : result.getGatekeeperRuleCount())
+                    .append(" | ")
                     .append(result.getMatchedKeywordCount()).append("/").append(result.getRequiredKeywordCount())
                     .append(" | ")
                     .append(result.getToolCallCount() == null ? "-" : result.getToolCallCount())

src/main/java/com/superbiz/agent/eval/DiagnosisEvalResult.java

@@ -24,8 +24,10 @@ public class DiagnosisEvalResult {
     private Map<String, Boolean> evidenceCoverage;
     private String gatekeeperStatus;
     private String gatekeeperRuleSetVersion;
+    private String promptAuditVersion;
     private String composerStatus;
     private Integer claimCheckCount;
+    private Integer gatekeeperRuleCount;
     private Integer toolCallCount;
     private Integer durationMs;
 }

src/main/java/com/superbiz/agent/eval/DiagnosisTraceEvaluator.java

@@ -67,8 +67,10 @@ public class DiagnosisTraceEvaluator {
                         .evidenceCoverage(emptyCoverage(evalCase.getRequiredEvidenceTools()))
                         .gatekeeperStatus(null)
                         .gatekeeperRuleSetVersion(null)
+                        .promptAuditVersion(null)
                         .composerStatus(null)
                         .claimCheckCount(null)
+                        .gatekeeperRuleCount(null)
                         .toolCallCount(null)
                         .durationMs(null)
                         .build());
@@ -123,10 +125,13 @@ public class DiagnosisTraceEvaluator {
         String gatekeeperStatus = extractNestedString(trace, "verifier_evaluation", "gatekeeper_result", "status");
         String gatekeeperRuleSetVersion = extractNestedString(trace, "verifier_evaluation",
                 "gatekeeper_result", "rule_set_version");
+        String promptAuditVersion = extractNestedString(trace, "verifier_evaluation",
+                "prompt_audit", "version");
         String composerStatus = extractNestedString(trace, "verifier_evaluation", "composer_output", "status");
         Integer claimCheckCount = countList(trace, "verifier_evaluation", "claim_checks");
+        Integer gatekeeperRuleCount = countNestedList(trace, "verifier_evaluation", "gatekeeper_result", "rules");
         failedChecks.addAll(validateV2AuditClosure(evalCase, trace, normalizedAnswer, verdict,
-                gatekeeperStatus, gatekeeperRuleSetVersion, composerStatus));
+                gatekeeperStatus, gatekeeperRuleSetVersion, promptAuditVersion, composerStatus));
 
         Integer toolCallCount = trace.getToolInvocations() == null ? 0 : trace.getToolInvocations().size();
         Integer durationMs = trace.getSession() == null ? null : trace.getSession().getTotalDurationMs();
@@ -142,8 +147,10 @@ public class DiagnosisTraceEvaluator {
                 .evidenceCoverage(evidenceCoverage)
                 .gatekeeperStatus(gatekeeperStatus)
                 .gatekeeperRuleSetVersion(gatekeeperRuleSetVersion)
+                .promptAuditVersion(promptAuditVersion)
                 .composerStatus(composerStatus)
                 .claimCheckCount(claimCheckCount)
+                .gatekeeperRuleCount(gatekeeperRuleCount)
                 .toolCallCount(toolCallCount)
                 .durationMs(durationMs)
                 .build();
@@ -237,6 +244,7 @@ public class DiagnosisTraceEvaluator {
                                                 String verdict,
                                                 String gatekeeperStatus,
                                                 String gatekeeperRuleSetVersion,
+                                                String promptAuditVersion,
                                                 String composerStatus) {
         List<String> failedChecks = new ArrayList<>();
         boolean requireV2AuditClosure = Boolean.TRUE.equals(evalCase.getRequireV2AuditClosure());
@@ -259,6 +267,10 @@ public class DiagnosisTraceEvaluator {
             failedChecks.add("gatekeeper rule set version not expected: "
                     + valueOrMissing(gatekeeperRuleSetVersion));
         }
+        if (Boolean.TRUE.equals(evalCase.getRequireGatekeeperRules())) {
+            failedChecks.addAll(validateGatekeeperRules(trace));
+        }
+        failedChecks.addAll(validatePromptAudit(evalCase, trace, promptAuditVersion));
 
         failedChecks.addAll(validateClaimChecks(trace, requireClaimChecks));
 
@@ -290,6 +302,78 @@ public class DiagnosisTraceEvaluator {
         return failedChecks;
     }
 
+    private List<String> validatePromptAudit(DiagnosisEvalCase evalCase,
+                                             DiagnosisTraceResponse trace,
+                                             String promptAuditVersion) {
+        List<String> failedChecks = new ArrayList<>();
+        Object promptAudit = nestedValue(trace, "verifier_evaluation", "prompt_audit");
+        if (Boolean.TRUE.equals(evalCase.getRequirePromptAudit()) && !(promptAudit instanceof Map<?, ?>)) {
+            failedChecks.add("missing prompt_audit");
+            return failedChecks;
+        }
+        if (!isBlank(evalCase.getExpectedPromptAuditVersion())
+                && !evalCase.getExpectedPromptAuditVersion().equals(promptAuditVersion)) {
+            failedChecks.add("prompt audit version not expected: " + valueOrMissing(promptAuditVersion));
+        }
+        if (evalCase.getExpectedPromptVersions() == null || evalCase.getExpectedPromptVersions().isEmpty()) {
+            return failedChecks;
+        }
+        if (!(promptAudit instanceof Map<?, ?> audit)) {
+            failedChecks.add("missing prompt_audit");
+            return failedChecks;
+        }
+        Object promptsValue = audit.get("prompts");
+        if (!(promptsValue instanceof List<?> prompts)) {
+            failedChecks.add("prompt_audit missing prompts");
+            return failedChecks;
+        }
+        Map<String, String> actualVersions = new LinkedHashMap<>();
+        for (Object promptValue : prompts) {
+            if (promptValue instanceof Map<?, ?> prompt) {
+                String name = stringValue(prompt.get("name"));
+                String version = stringValue(prompt.get("version"));
+                if (!isBlank(name)) {
+                    actualVersions.put(name, version);
+                }
+            }
+        }
+        for (Map.Entry<String, String> expected : evalCase.getExpectedPromptVersions().entrySet()) {
+            String actual = actualVersions.get(expected.getKey());
+            if (!expected.getValue().equals(actual)) {
+                failedChecks.add("prompt version not expected: "
+                        + expected.getKey() + "=" + valueOrMissing(actual));
+            }
+        }
+        return failedChecks;
+    }
+
+    private List<String> validateGatekeeperRules(DiagnosisTraceResponse trace) {
+        Object rulesValue = nestedNestedValue(trace, "verifier_evaluation", "gatekeeper_result", "rules");
+        if (!(rulesValue instanceof List<?> rules) || rules.isEmpty()) {
+            return List.of("gatekeeper_result missing rules");
+        }
+        List<String> failedChecks = new ArrayList<>();
+        for (Object item : rules) {
+            if (!(item instanceof Map<?, ?> rule)) {
+                failedChecks.add("gatekeeper rule metadata is not an object");
+                continue;
+            }
+            String id = stringValue(rule.get("id"));
+            Object enabled = rule.get("enabled");
+            String severity = stringValue(rule.get("default_severity"));
+            if (isBlank(id)) {
+                failedChecks.add("gatekeeper rule metadata missing id");
+            }
+            if (!(enabled instanceof Boolean)) {
+                failedChecks.add("gatekeeper rule metadata missing enabled: " + valueOrMissing(id));
+            }
+            if (isBlank(severity)) {
+                failedChecks.add("gatekeeper rule metadata missing default_severity: " + valueOrMissing(id));
+            }
+        }
+        return failedChecks;
+    }
+
     private List<String> validateClaimChecks(DiagnosisTraceResponse trace, boolean required) {
         Object claimChecks = nestedValue(trace, "verifier_evaluation", "claim_checks");
         if (!(claimChecks instanceof List<?> claimCheckList)) {
@@ -347,6 +431,19 @@ public class DiagnosisTraceEvaluator {
         return value instanceof List<?> list ? list.size() : null;
     }
 
+    private Integer countNestedList(DiagnosisTraceResponse trace, String firstKey, String secondKey, String thirdKey) {
+        Object value = nestedNestedValue(trace, firstKey, secondKey, thirdKey);
+        return value instanceof List<?> list ? list.size() : null;
+    }
+
+    private Object nestedNestedValue(DiagnosisTraceResponse trace, String firstKey, String secondKey, String thirdKey) {
+        Object value = nestedValue(trace, firstKey, secondKey);
+        if (!(value instanceof Map<?, ?> map)) {
+            return null;
+        }
+        return map.get(thirdKey);
+    }
+
     private int countMatches(String normalizedAnswer, List<String> keywords) {
         int count = 0;
         for (String keyword : safeList(keywords)) {

src/main/java/com/superbiz/agent/service/ChatService.java

@@ -60,6 +60,7 @@ public class ChatService {
     private static final Logger logger = LoggerFactory.getLogger(ChatService.class);
     private static final String LOW_CONFID_DISCLAIMER = "以下结论基于当前已获取证据，仍存在部分证据缺口，请谨慎参考。";
     private static final String DEGRADED_PREFIX = "当前无法基于已获取证据生成可靠结论，建议人工介入。";
+    private static final String CHAT_PROMPT_AUDIT_VERSION = "chat-prompts-v1";
 
     /** 封装 answer + 后端生成的 sessionId，用于 feedback 关联 */
     public record ChatResult(String answer, String sessionId) {}
@@ -884,6 +885,7 @@ public class ChatService {
         verifierEvaluation.put("rationale", decision.rationale());
         verifierEvaluation.put("round", round);
         verifierEvaluation.put("traceability_version", "v1");
+        verifierEvaluation.put("prompt_audit", promptAuditSnapshot());
         verifierEvaluation.put("executor_output_parse_status",
                 Optional.ofNullable(VerifierContextHolder.getExecutorOutputParseStatus())
                         .orElse(Map.of("status", "missing", "detail", "executor parse status unavailable")));
@@ -902,6 +904,26 @@ public class ChatService {
         diagnosisSessionRepository.save(session);
     }
 
+    private Map<String, Object> promptAuditSnapshot() {
+        Map<String, Object> audit = new LinkedHashMap<>();
+        audit.put("version", CHAT_PROMPT_AUDIT_VERSION);
+        audit.put("prompts", List.of(
+                promptAuditItem("chat_planner", "chat-planner-v1", "prompts/chat-planner-prompt.md"),
+                promptAuditItem("chat_executor", "chat-executor-v2", "prompts/chat-executor-prompt.md"),
+                promptAuditItem("chat_verifier", "chat-verifier-v2", "prompts/chat-verifier-prompt.md"),
+                promptAuditItem("chat_composer", "chat-composer-v1", "prompts/chat-composer-prompt.md")
+        ));
+        return audit;
+    }
+
+    private Map<String, Object> promptAuditItem(String name, String version, String resource) {
+        Map<String, Object> item = new LinkedHashMap<>();
+        item.put("name", name);
+        item.put("version", version);
+        item.put("resource", resource);
+        return item;
+    }
+
     private Map<String, Object> defaultGatekeeperPass() {
         GatekeeperRuleCatalog catalog = GatekeeperRuleCatalog.fallback();
         return Map.of(

src/test/java/com/superbiz/agent/eval/DiagnosisEvalBaselineDiffTest.java

@@ -100,13 +100,13 @@ class DiagnosisEvalBaselineDiffTest {
     }
 
     private void degradeRedisCase(DiagnosisEvalReport report) {
-        report.setPassedCases(9);
+        report.setPassedCases(11);
-        report.setPassRate(0.9);
+        report.setPassRate(11.0 / 12.0);
         report.setAverageToolCallCount(3.0);
-        report.setAverageDurationMs(39800.0);
+        report.setAverageDurationMs(38500.0);
         report.setVerdictDistribution(new LinkedHashMap<>());
-        report.getVerdictDistribution().put("PASS", 4L);
+        report.getVerdictDistribution().put("PASS", 5L);
-        report.getVerdictDistribution().put("LOW_CONFID", 4L);
+        report.getVerdictDistribution().put("LOW_CONFID", 5L);
         report.getVerdictDistribution().put("REJECT", 2L);
 
         DiagnosisEvalResult redis = result(report, "redis-timeout");

src/test/java/com/superbiz/agent/eval/DiagnosisTraceEvaluatorTest.java

@@ -24,11 +24,11 @@ class DiagnosisTraceEvaluatorTest {
 
         DiagnosisEvalReport report = evaluator.evaluate(cases, Path.of("mvp/eval/fixtures"));
 
-        assertEquals(10, report.getTotalCases());
+        assertEquals(12, report.getTotalCases());
-        assertEquals(10, report.getPassedCases());
+        assertEquals(12, report.getPassedCases());
         assertEquals(1.0, report.getPassRate(), 0.001);
-        assertEquals(4L, report.getVerdictDistribution().get("PASS"));
+        assertEquals(5L, report.getVerdictDistribution().get("PASS"));
-        assertEquals(5L, report.getVerdictDistribution().get("LOW_CONFID"));
+        assertEquals(6L, report.getVerdictDistribution().get("LOW_CONFID"));
         assertEquals(1L, report.getVerdictDistribution().get("REJECT"));
 
         DiagnosisEvalResult narrowHighCpu = result(report, "narrow-highcpu-observation");
@@ -36,6 +36,12 @@ class DiagnosisTraceEvaluatorTest {
         assertEquals("gatekeeper-rules-v1", narrowHighCpu.getGatekeeperRuleSetVersion());
         assertEquals("pass", narrowHighCpu.getGatekeeperStatus());
 
+        DiagnosisEvalResult promptGatekeeperAudit = result(report, "prompt-gatekeeper-audit-closure");
+        assertTrue(promptGatekeeperAudit.isPassed());
+        assertEquals("chat-prompts-v1", promptGatekeeperAudit.getPromptAuditVersion());
+        assertEquals("gatekeeper-rules-v1", promptGatekeeperAudit.getGatekeeperRuleSetVersion());
+        assertEquals(2, promptGatekeeperAudit.getGatekeeperRuleCount());
+
         DiagnosisEvalResult hikariNoEvidence = result(report, "hikari-no-evidence-negative-observation");
         assertTrue(hikariNoEvidence.isPassed());
         assertEquals("gatekeeper-rules-v1", hikariNoEvidence.getGatekeeperRuleSetVersion());
@@ -60,6 +66,12 @@ class DiagnosisTraceEvaluatorTest {
         DiagnosisEvalResult composerFallback = result(report, "composer-fallback-no-raw-json");
         assertTrue(composerFallback.isPassed());
         assertEquals("composer_malformed", composerFallback.getComposerStatus());
+
+        DiagnosisEvalResult auditMetadataLowConfid = result(report, "audit-metadata-low-confid");
+        assertTrue(auditMetadataLowConfid.isPassed());
+        assertEquals("LOW_CONFID", auditMetadataLowConfid.getVerdict());
+        assertEquals("chat-prompts-v1", auditMetadataLowConfid.getPromptAuditVersion());
+        assertEquals(2, auditMetadataLowConfid.getGatekeeperRuleCount());
     }
 
     @Test
@@ -195,6 +207,76 @@ class DiagnosisTraceEvaluatorTest {
                 "gatekeeper rule set version not expected: old-rules"));
     }
 
+    @Test
+    void evaluateFailsWhenPromptAuditMissingOrMismatches() {
+        DiagnosisEvalCase evalCase = DiagnosisEvalCase.builder()
+                .id("prompt-audit")
+                .title("Prompt audit")
+                .expectedRootCauseKeywords(List.of())
+                .requiredEvidenceTools(List.of())
+                .allowedVerdicts(List.of("PASS"))
+                .requirePromptAudit(true)
+                .expectedPromptAuditVersion("chat-prompts-v1")
+                .expectedPromptVersions(java.util.Map.of("chat_executor", "chat-executor-v2"))
+                .build();
+        DiagnosisTraceResponse trace = DiagnosisTraceResponse.builder()
+                .session(DiagnosisTraceResponse.SessionTrace.builder()
+                        .answer("安全回答")
+                        .selfEvaluation(java.util.Map.of(
+                                "verifier_evaluation", java.util.Map.of(
+                                        "verdict", "PASS",
+                                        "prompt_audit", java.util.Map.of(
+                                                "version", "old-prompts",
+                                                "prompts", java.util.List.of(java.util.Map.of(
+                                                        "name", "chat_executor",
+                                                        "version", "chat-executor-v1"
+                                                ))
+                                        )
+                                )))
+                        .build())
+                .toolInvocations(List.of())
+                .build();
+
+        DiagnosisEvalResult result = evaluator.evaluate(evalCase, trace);
+
+        assertFalse(result.isPassed());
+        assertTrue(result.getFailedChecks().contains(
+                "prompt audit version not expected: old-prompts"));
+        assertTrue(result.getFailedChecks().contains(
+                "prompt version not expected: chat_executor=chat-executor-v1"));
+    }
+
+    @Test
+    void evaluateFailsWhenGatekeeperRulesAreMissing() {
+        DiagnosisEvalCase evalCase = DiagnosisEvalCase.builder()
+                .id("gatekeeper-rules")
+                .title("Gatekeeper rules")
+                .expectedRootCauseKeywords(List.of())
+                .requiredEvidenceTools(List.of())
+                .allowedVerdicts(List.of("PASS"))
+                .requireGatekeeperRules(true)
+                .build();
+        DiagnosisTraceResponse trace = DiagnosisTraceResponse.builder()
+                .session(DiagnosisTraceResponse.SessionTrace.builder()
+                        .answer("安全回答")
+                        .selfEvaluation(java.util.Map.of(
+                                "verifier_evaluation", java.util.Map.of(
+                                        "verdict", "PASS",
+                                        "gatekeeper_result", java.util.Map.of(
+                                                "status", "pass",
+                                                "rule_set_version", "gatekeeper-rules-v1"
+                                        )
+                                )))
+                        .build())
+                .toolInvocations(List.of())
+                .build();
+
+        DiagnosisEvalResult result = evaluator.evaluate(evalCase, trace);
+
+        assertFalse(result.isPassed());
+        assertTrue(result.getFailedChecks().contains("gatekeeper_result missing rules"));
+    }
+
 
     @Test
     void evaluateFailsWhenUnsupportedClaimLeaksIntoFinalAnswer() {

src/test/java/com/superbiz/agent/service/ChatServiceSequentialAgentTest.java

@@ -394,10 +394,20 @@ class ChatServiceSequentialAgentTest {
         verify(mergeService).mergeVerifierEvaluation(isNull(), captor.capture());
         Map<String, Object> verifierEvaluation = captor.getValue();
         assertTrue(verifierEvaluation.containsKey("gatekeeper_result"));
+        assertTrue(verifierEvaluation.containsKey("prompt_audit"));
         @SuppressWarnings("unchecked")
         Map<String, Object> gatekeeperResult = (Map<String, Object>) verifierEvaluation.get("gatekeeper_result");
         assertEquals("pass", gatekeeperResult.get("status"));
         assertEquals("none", gatekeeperResult.get("severity"));
+        @SuppressWarnings("unchecked")
+        Map<String, Object> promptAudit = (Map<String, Object>) verifierEvaluation.get("prompt_audit");
+        assertEquals("chat-prompts-v1", promptAudit.get("version"));
+        @SuppressWarnings("unchecked")
+        List<Map<String, Object>> prompts = (List<Map<String, Object>>) promptAudit.get("prompts");
+        assertEquals(4, prompts.size());
+        assertTrue(prompts.stream().anyMatch(prompt ->
+                "chat_executor".equals(prompt.get("name"))
+                        && "chat-executor-v2".equals(prompt.get("version"))));
     }
 
     @Test