@tea-agent/loop-agent 0.18.1 → 0.20.0

package/docs/templates/backend-test-dag.review-cases.prompt.md

@@ -2,88 +2,35 @@
 
 ## Purpose
 
-Use this prompt for the single read-only **backend test case review** node: `executor: "pi"`, `role: "reviewer"`, `writePolicy: "read-only"`. The reviewer audits generated backend functional test cases for completeness, format compliance, and traceability to source requirements. The verdict is advisory evidence consumed by canonical context, retrospective, and L-5; it neither authorizes nor blocks the pytest writer.
+供 `review-and-revise-backend-md-cases-pi` 使用。该节点是 `executor: "pi"`、`role: "reviewer"`、`toolProfile: "write"` 的受限 reviewer，只能直接修订 `testcase/md/**`，不得生成 pytest 或修改任务源、生产代码和配置。
 
-Do **not** create `executor: reviewer`. Reviewer is a **role** on `executor: pi`.
+## 当前合同
 
-## Recommended DAG Node Shape
+把 Markdown 用例视为面向测试、研发、产品与评审人员的正式文档，而不是模型中间产物。
 
-```json
-{
-  "id": "review-backend-cases-pi",
-  "depends_on": ["backend-test-case-manifest-shell", "backend-test-analysis-contract-shell"],
-  "complexity": "HIGH",
-  "executor": "pi",
-  "role": "reviewer",
-  "writePolicy": "read-only",
-  "allowedPaths": ["**"],
-  "forbiddenPaths": [".harness/**", "artifacts/**"],
-  "outputContract": "Plain Markdown whose first non-empty line is VERDICT: pass or VERDICT: request-revision; followed by Findings and Coverage Assessment. No file writes.",
-  "subtask_prompt_markdown": "./backend-test-dag.review-cases.prompt.md"
-}
-```
+### 阅读体验
 
-## Prompt Body
+- `testcase/md/README.md` 是简洁入口，包含测试目标、环境、隔离/清理策略、模块汇总和可跳转的用例索引。
+- 模块文件采用中文用例卡片；每条以 `## BE-<MODULE>-<NNN>｜<中文用例名称>` 开始。
+- 新文档优先使用：`测试目的`、`验收标准`、`需求依据`、`前置条件`、`测试数据`、`操作步骤`、`预期结果`、`自动化映射`。
+- validator 同时接受上述中文分节和历史英文分节；机器 ID、HTTP 方法、路径、字段、枚举、文件名、函数名与 source citation 必须保持精确。
+- 步骤和预期可以用紧凑表格，也可以分别使用编号/项目列表；必须可执行、可独立断言。
+- 自动化内部限制应简短或放进 `<details>`，不能淹没人类主要阅读路径。
 
-You are the Backend Test DAG **test case reviewer** (read-only).
+### 正确性
 
-Your job is to audit the generated backend functional test cases for completeness, format compliance, requirement coverage, and traceability. You are **not** an implementer or test generator. Do not edit repository files, including root `artifacts/**`.
+- 对照每条 `需求依据` 和环境报告检查 AC、接口、字段/响应形状、状态码、错误语义、状态转换、正向/异常/边界场景。
+- 删除无依据场景、合并重复用例、补齐有依据的遗漏；无法确认的内容写入中文证据缺口，不猜测行为或凭据。
+- 拒绝“符合预期”“正常工作”等模糊结果，以及无意义的中英双写和大段重复 boilerplate。
+- 若能确定脚本与函数命名，在 `自动化映射` 中写明计划脚本路径与 pytest 函数/方法名。
 
-### Mandatory First Line
+## 推荐输出
 
-The **first non-empty line** of your response must be exactly one of:
+完成文件修订后，仅用简短中文说明：
 
-- `VERDICT: pass`
-- `VERDICT: request-revision`
+- 修订了哪些文档；
+- 用例数与主要模块；
+- 修复了哪些需求一致性或阅读问题；
+- 仍有哪些证据缺口。
 
-No preamble, heading, or blank lines before the verdict line.
-
-### Inputs to Review
-
-1. **Acceptance criteria / analysis** — from the validated Backend Test Analysis v1 artifact materialized by `backend-test-analysis-contract-shell` (`contracts/backend-test-analysis.json` under the current DAG run). Do not treat free-form Markdown from `analyze-inputs-pi` as the contract.
-2. **Case Manifest v1** — `contracts/backend-test-case-manifest.json` (schemaId `backend-test-case-manifest-v1`). Prefer `coverageSummary` and caseId↔acIds from this artifact; do not invent coverage percentages.
-3. **Generated test cases** — files under `testcase/md/`.
-
-Do NOT re-read source documents. Use the validated analysis artifact, case manifest, and generated cases only.
-
-### Review Checklist
-
-| Area | Check | Severity if Missing |
-|------|-------|---------------------|
-| **ID format** | Every test case ID matches `BE-<MODULE>-<NNN>` (e.g. `BE-ORDER-001`) | Critical |
-| **Positive path coverage** | Happy-path scenarios for each acceptance criterion | Critical |
-| **Negative path coverage** | Error/exception scenarios (invalid input, not found, state violations) | Important |
-| **Boundary conditions** | Edge cases (empty input, max length, edge values) | Important |
-| **State transitions** | Illegal state changes covered | Important |
-| **Requirement traceability** | Each acceptance criterion (AC-xxx) maps to at least one test case ID (manifest coverageSummary or evidenceGaps) | Critical |
-| **Manifest consistency** | Markdown case bodies **and** any AC matrix list the **same full** `BE-*` ids as Case Manifest v1 `caseId`→`acIds`. Never claim "all cases" / "全部用例" cover an AC unless every case maps that AC. | Critical |
-| **Planned automation** | Missing `test_*.py` before generate-pytest is **Informational only**, not Critical | Informational |
-| **Out-of-scope ACs** | Flyway / frontend e2e / `mvn test` etc. already in manifest `evidenceGaps` must not be treated as uncovered Critical | Informational |
-| **Case structure** | Each case has: ID, Title, Precondition, Steps, Expected Result | Important |
-| **No duplicate IDs** | All test case IDs are unique across files | Critical |
-
-### Conditional Coverage (check ONLY if mentioned in upstream analysis)
-
-- **Authentication coverage**: check ONLY if the validated analysis artifact mentions auth mechanism (JWT, OAuth2, API Key, etc.)
-- **Timeout coverage**: check ONLY if the validated analysis artifact mentions timeout handling or degradation strategy
-- If not mentioned in the validated analysis artifact, do NOT flag as missing
-
-### Verdict Rules
-
-| Condition | Verdict |
-|-----------|---------|
-| All Critical checks pass, Important checks have no more than 2 findings | `VERDICT: pass` |
-| Any Critical check fails | `VERDICT: request-revision` |
-| More than 2 Important findings | `VERDICT: request-revision` |
-| Only Informational findings | `VERDICT: pass` (with findings listed) |
-
-### Output Shape (after verdict line)
-
-1. **Coverage Assessment** — table mapping each AC to covering **full** test case IDs (or "uncovered" / gap).
-2. **Findings** — bullet list tagged `Critical`, `Important`, or `Informational`.
-3. **Statistics** — total case count, positive/negative/boundary breakdown, module distribution.
-4. **Required follow-up** (only when `request-revision`) — numbered, concrete MD corrections for a separate follow-up task. These findings do not authorize edits in the current run.
-
-### Fail-fast note
-
-There is no final review or in-run revision writer. Any `request-revision` verdict remains auditable advisory evidence and must be reported downstream; it does not stop pytest generation.
+不得输出 JSON，不得执行测试。

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tea-agent/loop-agent",
-  "version": "0.18.1",
+  "version": "0.20.0",
   "type": "module",
   "bin": {
     "loop-agent": "bin/loop-agent.js",

package/skills/agent-worker/references/agent-worker-operator.md

@@ -52,8 +52,8 @@ Leaf DAG nodes 不得递归启动 `agent-worker`。Worker 负责 DAG 之外的 s
    ```
 
    doctor 只读；migrate 默认零写入，apply 失败全回滚且不改 JSONL。
-8. Observe（`observe serve|snapshot`）只读；canonical Task 路由为 `/api/features/:featureId/tasks/:taskId` 与 `#/feature/:featureId/task/:taskId`。`GET /api/health` 为 versioned DTO（fingerprint + routeCapabilities）。Console `observeLink` 仅 match 后深链；offline 展示 `agent-worker observe serve --repo . --port 8787`。
-9. Official Console：`agent-worker console serve|doctor`（loopback）。Recovery CTA 为 report/doctor/decision/resume/reconcile/regenerate；无 Cancel、无主 CTA「直接改代码」。主会话 Compatibility Assist 不得替代 Console/CLI 执法。
+8. Inspect（原 Observe）只读：推荐 `agent-worker console serve` 的 `/inspect/#/...`；兼容 `observe serve|snapshot`。canonical Task 路由为 `/api/features/:featureId/tasks/:taskId` 与 `#/feature/:featureId/task/:taskId`。8790 `/api/health` 为 `OperatorSurfaceHealthV1`；8787 仍为 `ObserveHealthV1`。
+9. Official Console：`agent-worker console serve|doctor`（默认 loopback；可 `--host 0.0.0.0` / `--debug`）。Recovery CTA 为 report/doctor/decision/resume/reconcile/regenerate/打开检视；无 Cancel、无主 CTA「直接改代码」。主会话 Compatibility Assist 不得替代 Console/CLI 执法。
 
 ## Versioned Self-Hosting
 

package/skills/frontend-implementation/references/node-contracts.md

@@ -6,22 +6,20 @@ Pre-write nodes are read-only. Preserve IDs, labels, commands, language, require
 
 - **`frontend-contract-pi`**: `Scope`, `Non-goals`, `Acceptance Criteria`, `UI States`, `Target Runtime Environment`, `Risks`, `Verification Expectations`. No guessed requirements.
 - **`frontend-scout-pi`**: routes, components, tokens, data/API/Mock, scripts, tests, assets. Fact vs inference vs gap. Knowledge base first; else search+read `<repoRoot>/openspec/**` before repo fallback. Output stack, routes, components, styling, conventions, state/data, test entry points, reuse, risks.
-- **`frontend-mock-assess-pi` + gate**: declares `firstProtocolLine: "MOCK_STRATEGY:"`; canonical output first line
-  `MOCK_STRATEGY: native|browser-intercept|request-adapter|not-needed|blocked`
-  Pi output mapping promotes the first explicitly labeled Mock strategy line ahead of any preamble, including common bullet, quote, inline-code, fullwidth-colon, `Mock strategy`, and split label/value drift, without inventing or replacing its value; missing, unlabeled, malformed, or blocked strategies still fail closed. Prefer native Mock; browser intercept only with existing e2e; request-adapter only for reversible local preview. Default `auto` may select `not-needed` when contract/scout evidence confirms no project Mock capability, without adding Mock files/deps, while keeping real requests default and recording the Real Integration Gap. Other `not-needed` cases need positive no-remote/stable-backend evidence; invalid when `frontendMock.policy=required`. `blocked` for missing/conflicting contracts, unsafe paths/deps, unread specs, production-default-on, unverifiable entrypoints. Output Mock Decision, API/spec/service evidence, backend readiness, selection evidence, endpoint/fixture matrix, activation, targets, production safety, verification plan, real-integration gap, blocking issues. Never invent fields, store secrets, comment real requests, import test mocks into production, or treat Mock as real integration. Gate uses `first-non-empty` only; never authorizes writes. Unsafe required contracts → no writer.
-- **`frontend-plan-pi` + conditional design loop**: AC → steps, in-bound files, UI states, reuse, deps, activation/rollback, frozen verify entrypoints, real-integration gap. Initial `VERDICT: pass` uses the original plan directly. Only exact `VERDICT: request-revision` runs read-only plan revision plus final review; there is no `frontend-first-design-gate-shell` or pass-path `PASS_NO_REVISION_NEEDED` node. The effective final gate prefers final review when present, otherwise initial review, and only exact pass authorizes writes; malformed/missing/request-revision fails closed → replan/rerun (not dev-fix). The plan-pi prompt includes the complete `frontend-implementation-contract-v1` JSON Schema loaded from the loop-agent package `docs/templates/` path, plus deterministic source binding, risk level, and allowed implementation targets. The model does not need to search or guess contract fields; `schemaId`, `targetFiles`, `requirementCoverage` are explicitly forbidden.
+- **`frontend-plan-pi` + conditional design loop**: AC → steps, in-bound files, UI states, reuse, deps, Mock/API strategy, activation/rollback, frozen verify entrypoints, real-integration gap, and exactly one `frontend-implementation-contract-v1` JSON object. Prefer native Mock; browser intercept only with existing e2e; request-adapter only for a reversible seam. `auto` may select `not-needed` when no project Mock capability exists, while keeping real requests default and recording the gap; `required` cannot. Initial design pass uses the original plan; only exact `request-revision` runs read-only revision plus final review. Small-risk runs one design review only.
+- **`frontend-prewrite-gate-shell`**: the sole write authorization. Resolve effective plan/review, require exact pass, retain every REQ/BR/AC id, enforce Mock policy, validate schema/source binding, and materialize `contracts/frontend-implementation-contract.json`. Fallback is allowed only when a conditional primary is absent; an existing malformed primary fails closed. Generation-time blocked Mock produces one deterministic blocking shell node and no writer.
 - **`frontend-implement-pi`**: sole exclusive writer. Stay in `writeSet`; real requests default-on; Mock reversible, dev/test-only, production-off. Atomic handler/intercept/adapter with consumer+tests. Stop on forbidden paths or guesses. Output changed files, behavior, UI states, styling notes, verification attempted, residual risks. Optional mock-verify when frozen; static+behavior always; behavior must prove page consumption. Skipped-Mock `not-needed` keeps real integration pending unless the real backend path has fresh evidence.
 
 ## Contract / trace / stages (M1–M2)
 
-- Contract shell: `jsonArtifactGate` → `contracts/frontend-implementation-contract.json` from the effective plan (one fenced JSON or pure JSON); schemaId `frontend-implementation-contract-v1`. Revision is primary and original plan is fallback only when the conditional revision output is absent. Requirement coverage uses the same primary/fallback rule. An existing malformed/schema-invalid/incomplete primary fails closed; fallback never masks it. Final design + implement depend on the artifact; `MOCK_STRATEGY: blocked` not implementable.
-- Trace shell: `frontend-verification-trace-gate` binds contract `verificationTargets` to static/behavior records (`commandLabels`, file exists, optional symbol). Assess `MOCK_STRATEGY:` must match `mockApi.strategy` when present. Writes `contracts/frontend-verification-trace.json`. Browser/visual always `not-run`.
+- `frontend-verify-assess-shell` runs Mock/static/behavior command groups, binds contract `verificationTargets` to command labels and file/symbol evidence, then writes `frontend-verification-trace.json` and `frontend-repair-assessment.json`. Browser/visual remain `not-run`.
+- `frontend-review-context-shell` captures the real diff and combines contract, effective trace, repair assessment, and diff into `contracts/frontend-review-context.json`.
 - Implement stages: (1) contract confirm (2) tests sync (3) component/UI (4) API/Mock (5) frozen checks (6) diff cleanup. Summary: Contract Ref, Changed Files, Requirements, UI States, Tests, Verification Attempts, Deviations, Residual Risks.
 
 ## Repair (M3)
 
-static/behavior/trace may `nonZeroExitPolicy: record`. Assess emits pure JSON and writes `contracts/frontend-repair-assessment.json`. Only `eligible=true` runs `frontend-repair-pi` (same writeSet as implement; no re-spec; max 1 attempt), reverify, and retrace. No-failure condition-skips that branch, while diff/review/read-only `frontend-closeout-pi` continue on initial evidence. Repair-contract fails closed on non-repairable (contract/path/dependency/credential/deploy/spec-unclear), writeSet expansion, ERROR, or hard skip; `all-or-condition-skip` never softens those failures.
+Only `eligible=true` runs `frontend-repair-pi` (same writeSet as implement; no re-spec; max 1 attempt) and `frontend-reverify-shell`. No failure condition-skips both. Non-repairable contract/path/dependency/credential/deploy/spec-unclear failures fail closed.
 
 ## Risk & capability (M4–M6)
 
-Deterministic risk (no model); high-risk beats small; supervised never small. Small may drop the initial design review + conditional revision branch; its retained final review audits `frontend-plan-pi`, and contract shell retargets to that plan without fallback. Capability seed injects adapters; openspec/task sources outrank. A11y: static/component tools only when present; Browser a11y always not-run.
+Deterministic risk (no model); high-risk beats small; supervised never small. Standard/high-risk contain 15 top-level nodes; small contains 13 by omitting revision and final review. Capability seed injects adapters; openspec/task sources outrank. A11y: static/component tools only when present; Browser a11y always not-run.

package/skills/frontend-review/SKILL.md

@@ -10,14 +10,11 @@ references:
 # Frontend Review
 
 Use for `frontend-review-pi`; read the findings guide first. Required inputs are
-original task/reference material, contract/constraints, Mock assessment, original and
-revised/confirmed plan, final design verdict, implementation summary, actual diff,
-and static/behavior/optional Mock shell evidence. The actual diff is the run-owned
-`frontend-worktree-diff-shell` artifacts: `contracts/frontend-worktree-diff.json` and
-`artifacts/diff_patch.patch` under the current DAG run directory. When those artifacts
-exist, treat them as the authoritative actual diff—do not request revision solely for
-"missing diff". Only force revision for a missing actual diff when both artifacts are
-absent; never invent a diff from an implementation summary alone.
+original task/reference material, effective plan/design branch, implementation summary,
+and `contracts/frontend-review-context.json`. That canonical context binds the validated
+implementation contract, effective initial-or-post-repair verification trace, repair
+assessment, and run-owned actual diff. Treat its diff as authoritative; never invent a
+diff from an implementation summary alone.
 
 ## Verdict Contract
 

package/skills/loop-agent/references/command-reference.md

@@ -531,7 +531,9 @@ agent-worker batch run-ready \
   [--quiet] \
   [--pi-model <model>]                           # smoke 覆盖：所有 pi 节点强制用该模型
 agent-worker report morning --repo <repo-root> [--batch-run-id <id>] [--output <path>]
-agent-worker observe serve --repo <repo-root> [--port 8787] [--host 127.0.0.1]
+agent-worker console serve --repo <repo-root> [--port 8790] [--host 127.0.0.1]
+agent-worker console doctor --repo <repo-root> [--json] [--console-url <url>]
+agent-worker observe serve --repo <repo-root> [--port 8787] [--host 127.0.0.1]  # 兼容入口；stderr 会提示 OBSERVE_SERVE_DEPRECATED
 agent-worker observe snapshot --repo <repo-root>  # 输出 GlobalSnapshot JSON 到 stdout
 ```
 
@@ -552,7 +554,7 @@ agent-worker observe snapshot --repo <repo-root>  # 输出 GlobalSnapshot JSON
 - `report metrics` 按 UTC 月去重投影 Feature/Failure/Follow-up/Delivery/AC/decision/recovery/boundary 指标，同时写 JSON 与 Markdown；每项保留 numerator、denominator、sampleSize 和 missingData。
 - `task draft-followup` 会按全部 failure category 生成 TaskDraft 或人工行动卡：ProductBug/TestBug/FlakyTest/DependencyFailure 可批准；EnvFailure 连续两次后才生成 ENV-CHECK；Spec/Contract/Risk/Human/Unknown 只给行动卡。人工以 `feature approve-followup --dry-run` 预览，再带非空 `--owner` 批准 TaskDraft；行动卡不能批准。批准在 staging validation 后写 TaskSpec、graph、Ready/approval/event，原失败事实不改写，并有 rename/state/approval/index/event 回滚门禁。
 - `task retry` 是失败 Task 的唯一重试入口。它会保留原有运行记录和 failure handoff，并让下一次 `batch run-ready` 使用新的 `workerRunId`；不要删除运行态文件或手动修改状态来重试。
-- `observe serve` 是独立于执行过程的本地只读看板，默认监听 `127.0.0.1:8787`；`observe snapshot` 只输出同一份运行态快照 JSON。两者都不会启动、暂停或重试 Task / Worker / DAG。
+- **推荐** `console serve`（默认 `127.0.0.1:8790`）提供 Operate + Inspect；Inspect 路径为 `/inspect/#/...`，API 仍为根 `/api/**`。`observe serve` 为兼容入口（默认 `8787`，启动时 stderr 输出 `OBSERVE_SERVE_DEPRECATED`）；`observe snapshot` 保留。两者都不会启动、暂停或重试 Task / Worker / DAG。
 - 当前 Worker 仍是 v0（库 + CLI + dogfood），未接入定时/CI 驱动；`report morning` 只能从已有 Task Pool runs 汇总。
 
 ### 查看 duration statistics

package/skills/loop-agent/references/harness-policy.md

@@ -17,7 +17,7 @@
 | Tier | Default purpose | Commands |
 |---|---|---|
 | Primary | Normal autonomous implementation（经 CLI） | `new-task` -> `dag run-task --profile auto` -> `dag validate --strict-models --strict-governance` -> `run-dag` |
-| Operator | Diagnose, recover, close out, inspect facts | `status`, `instructions`, `dag status`, `dag doctor`, `dag report`, `dag reconcile-run`, `dag closeout-draft`, `dag reconcile-tasks`, `dag final-verification`, `inspect`, `doctor`, `spine audit`, `knowledge curate`, `docs audit`, `handoff check`, `loop-benchmark`；Observe：`agent-worker observe serve\|snapshot` |
+| Operator | Diagnose, recover, close out, inspect facts | `status`, `instructions`, `dag status`, `dag doctor`, `dag report`, `dag reconcile-run`, `dag closeout-draft`, `dag reconcile-tasks`, `dag final-verification`, `inspect`, `doctor`, `spine audit`, `knowledge curate`, `docs audit`, `handoff check`, `loop-benchmark`；Inspect：`agent-worker console serve`（`/inspect/`）与兼容 `observe serve\|snapshot` |
 | Compatibility (CLI helpers) | Legacy task metadata and feature-study helpers | `goal`, `reference`, `study` |
 | Escape hatch | Isolated delegation, one-shot diagnosis or **显式** bounded repair | `delegate`, `worktree`, `harvest`, `pi-prompt`, `cursor-prompt`（不得作失败默认恢复） |
 | Experimental | Long-running outer task state | `loop init\|status\|run\|record-round\|add-signal\|closeout` |

package/skills/loop-agent/references/hybrid-dag.md

@@ -16,10 +16,10 @@
 
 对于默认 `standard` 任务，生成器根据标题、`source/需求.md` 和结构化 `allowedPaths` 做保守、确定性的需求分类。只有高置信的前端实现需求自动选择 `frontend-implementation` DAG；后端、前后端混合、明确排除前端或证据不足的需求继续使用 governance profile 选出的模板。分类不会把普通后端实现路由到 `backend-test`，也不会替换由显式 profile、`workflowPolicy` 或 supervised quality gate 选中的 supervised 模板。
 
-前端专用链在 `frontend-scout-pi` 后加入只读 `frontend-mock-assess-pi` 和确定性 contract gate，根据接口契约、后端就绪度、生成期能力 seed 与固化验证入口选择 `native|browser-intercept|request-adapter|not-needed|blocked`。策略直接传给 plan、条件 design review、唯一 writer、实现 review 和 closeout；真实请求保持默认，缺少契约、生产隔离、注释真实请求或显式 required 合同不完整时 gate 阻塞。standard/full 拓扑的 initial design pass 直接使用 original plan，只有 request-revision 才运行 plan revision 和 final review；small-risk 拓扑保留 final review 作为对 original plan 的单一审查。已删除 `frontend-first-design-gate-shell`，保留的 final gate 只接受生效 initial/final verdict 的 pass。可选 `frontendMock` 配置声明 `auto|required|disabled`、既有服务目录与专项命令；默认 `auto` 下没有已确认 Mock 能力时跳过 Mock 继续实现并保留真实联调缺口，不安全或不完整的显式 required 合同只生成无 writer 的评估链，有可信命令时才增加 `frontend-mock-verify-shell`。Mock-backed 证据只证明前端状态；跳过 Mock 且未调用后端时 closeout 报告 `Frontend status: locally-validated` 与 `Real integration: pending`。初始验证后的 assessment 输出 JSON，只有 `eligible=true` 才运行 repair/reverify/retrace；绿色路径跳过该分支后仍继续 diff/review/只读 `frontend-closeout-pi`，non-repairable 或 `ERROR` 仍硬阻断。
+前端专用链保留独立 contract/scout；plan 同时选择 Mock/API 策略并输出结构化 implementation contract。design initial pass 直接使用原计划，只有 request-revision 才运行 revision/final review；small-risk 只执行一次 design review。`frontend-prewrite-gate-shell` 合并生效 verdict、REQ/BR/AC 覆盖、Mock policy 和 contract 物化，是唯一写入授权。实现后 `frontend-verify-assess-shell` 合并 Mock/static/behavior/trace/assessment；只有 `eligible=true` 才运行同 writeSet 的 repair 和 `frontend-reverify-shell`。`frontend-review-context-shell` 绑定真实 diff 与有效验证证据后再 review/closeout。standard/high-risk 为 15 个顶层节点，small-risk 为 13；绿色路径执行 11 个节点、7 次 Pi。生成期 blocked Mock 只生成一个确定性阻塞节点且没有 writer。
 
 
-> Backend-test Markdown-first：先由确定性环境 Shell 检查 clean env 中 Python/pytest、常见配置、conftest/fixture、test root、server entry 和 HTML renderer，失败时不消耗模型调用。随后 Pi 生成并独立 Review `testcase/md/**`，Shell 校验 Case ID、AC/source traceability、章节、步骤、可断言预期与 secret 安全；pytest writer 仅转换最终 Markdown，不重读 `source/**`。traceability 是执行前唯一资产硬门；pytest 只运行一次，生成 JUnit，并从同一 JUnit 生成 self-contained HTML 与 Markdown facts。最终 Pi 只解释事实并生成 Markdown 报告和 L-5 结论。active 流程不要求模型生成 backend-test 业务 JSON。
+> Backend-test Markdown-first：先由确定性环境 Shell 检查 clean env 中 Python/pytest、常见配置、conftest/fixture、test root、server entry 和 HTML renderer，失败时不消耗模型调用。随后 Pi 生成中文 README 索引与模块用例卡片并独立 Review `testcase/md/**`，Shell 校验 Case ID、AC/source traceability、中文或历史英文分节、步骤、可断言预期与 secret 安全；pytest writer 仅转换最终 Markdown，不重读 `source/**`。traceability 同时支持模块级函数和 pytest 测试类方法；pytest 只运行一次，生成 JUnit，并把 Markdown 名称/场景/脚本映射与同一 JUnit 合成为逐条中文 self-contained HTML 主报告和 Markdown facts。最终 Pi 只解释事实并生成 Markdown 报告和 L-5 结论。active 流程不要求模型生成 backend-test 业务 JSON。
 
 显式专用 `taskKind` 保持兼容并优先于任务源分类。`backend-test` 选择固定 **8 个真实顶层节点**的 Markdown-first DAG：环境硬门、Markdown cases、独立 Review/修订、Markdown gate、pytest 转换、确定性 traceability、单次 pytest + JUnit/HTML/facts、最终 Markdown 报告与 L-5。历史 JSON contract/materializer 可继续读取旧 DAG，但新 runtime/template 不再生成模型业务 JSON。`knowledge-sync` 与 `knowledge-graph-bootstrap` 继续通过各自显式 taskKind 选择知识回写/图谱开荒 DAG。治理等级仍由 `minimal|standard|reviewed|supervised` 推断。