@tea-agent/loop-agent 0.44.0-next.12 → 0.44.0-next.13

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

@@ -2,7 +2,7 @@
 
 ## Purpose
 
-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。
+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 `.harness/testcase/md/**`，不得生成 pytest 或修改任务源、生产代码和配置。
 
 ## 当前合同
 
@@ -10,7 +10,7 @@
 
 ### 阅读体验
 
-- `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。
+- `.harness/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；`<NNN>` 必须是三位补零序号（`001`，禁止 `01`）。Reviewer 发现两位序号或模块下划线时，必须在标题、README 索引与自动化映射中一致规范化（如 `BE-RESOURCE_NOTES-01` → `BE-RESOURCE-NOTES-001`）。
 - 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。
@@ -22,7 +22,7 @@
 - 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；脚本路径必须等于模块 one-to-one 路径 `testcase/test_<module>.py`，`<module>` 来自当前 Markdown 文件名 stem，不得使用 Case-ID 式模块名（如 `BE-HEALTH.md`）或与模块 stem 不一致的映射。
+- 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；脚本路径必须等于模块 one-to-one 路径 `.harness/testcase/test_<module>.py`，`<module>` 来自当前 Markdown 文件名 stem，不得使用 Case-ID 式模块名（如 `BE-HEALTH.md`）或与模块 stem 不一致的映射。
 
 ## 推荐输出
 

package/docs/templates/frontend-test-case-checklist.md

@@ -15,7 +15,7 @@ LLM review (when `frontendTest.reviewMode=blocking`) must not invent blocking ru
 | `unknown-ac` | When task `sourceBinding.requirementIds` lists ACs, every `acIds` entry must be in that set |
 | `case-id-shape` | `caseId` matches `FE-<FEATURE>-<NNN>-...` (never `AC-FE-*`) |
 | `case-id-is-ac` | Do not use acceptance id as `caseId` / filename |
-| `case-path-mismatch` | `casePath === {casesDir}/{caseId}.md`（默认 `testcase/frontend/cases/{caseId}.md`） |
+| `case-path-mismatch` | `casePath === {casesDir}/{caseId}.md`（默认 `.harness/testcase/frontend/cases/{caseId}.md`） |
 | `case-file-missing` | `casePath` exists |
 
 ## Tool guidance (non-blocking)
@@ -40,5 +40,5 @@ LLM review (when `frontendTest.reviewMode=blocking`) must not invent blocking ru
 
 ## Pipeline vs quality
 
-- **Pipeline acceptance**: final `{reportsDir}/frontend-test-retrospect-*.md` exists after result materialize (default `testcase/frontend/reports/`)
+- **Pipeline acceptance**: final `{reportsDir}/frontend-test-retrospect-*.md` exists after result materialize (default `.harness/testcase/frontend/reports/`)
 - **Quality**: `frontend-test-result-v1.outcome=passed` with 0 blocked/failed (opt-in via `frontendTest.strictOutcomeGate`)

package/docs/templates/frontend-test-dag.generate-cases.prompt.md

@@ -1,6 +1,6 @@
 # Generate frontend functional cases
 
-Use `playwright-cli-case-generator`. Read only `testcase/frontend/rag/context.md`, `coverage-map.md`, and existing `testcase/frontend/cases/`; write only that cases directory. Produce Markdown cases, `index.md`, and schema-version-1 `manifest.draft.json` (materialize promotes to `manifest.json`). Do not generate pytest or Playwright source code.
+Use `playwright-cli-case-generator`. Read only `.harness/testcase/frontend/rag/context.md`, `coverage-map.md`, and existing `.harness/testcase/frontend/cases/`; write only that cases directory. Produce Markdown cases, `index.md`, and schema-version-1 `manifest.draft.json` (materialize promotes to `manifest.json`). Do not generate pytest or Playwright source code.
 
 ## HARD ID contract (frequent failure)
 
@@ -11,12 +11,12 @@ Use `playwright-cli-case-generator`. Read only `testcase/frontend/rag/context.md
 
 - **Never** set `caseId` to `AC-FE-001` or name the file `AC-FE-001.md`.
 - **Never** put `FE-LOGIN-001-core` into `acIds`.
-- `casePath` must be `testcase/frontend/cases/<caseId>.md`.
-- `evidenceDir` must be `testcase/frontend/evidence/<caseId>/`.
+- `casePath` must be `.harness/testcase/frontend/cases/<caseId>.md`.
+- `evidenceDir` must be `.harness/testcase/frontend/evidence/<caseId>/`.
 
 Each case is independently executable and includes AC mapping (`acIds`), preconditions, cleanup, a semantic assertion, and its isolated evidence path. Use dimensions `core`, `boundary`, `flow`, or `backend`. Never guess API fields, constraints, SLA, credentials, or unrecorded data. For passed authority, include a successful `playwright-cli find ...` after `open` and before controller post-execution cleanup; `snapshot`, `goto`, `screenshot`, `request`/`console`, and ordinary interactions are not assertions.
 
-Every case must copy the concrete absolute base URL from `testcase/frontend/rag/context.md` only after the environment shell has marked `environmentProbe: reachable`. Do not derive a different origin and do not leave a base-url placeholder.
+Every case must copy the concrete absolute base URL from `.harness/testcase/frontend/rag/context.md` only after the environment shell has marked `environmentProbe: reachable`. Do not derive a different origin and do not leave a base-url placeholder.
 
 Every case must start with `playwright-cli open --browser=chrome` followed by that concrete context URL. Do not copy an angle-bracket URL placeholder into a generated executable case line.
 
@@ -49,15 +49,15 @@ For every executable sub-scenario, state the fixture/reset operation, UI reset o
 
 Each case must require the executor to persist, even when blocked:
 
-- `testcase/frontend/evidence/<case-id>/execution.md`
-- `testcase/frontend/evidence/<case-id>/case-result.json`
+- `.harness/testcase/frontend/evidence/<case-id>/execution.md`
+- `.harness/testcase/frontend/evidence/<case-id>/case-result.json`
 
 `case-result.json` must be valid JSON containing the matching `caseId`, final `status` (`passed`, `failed`, or `blocked`), and an `evidencePaths` array. A rerun must overwrite this same file with its final status and integer `rerunAttempt`; the final report consumes that latest file. A blocked result must include a non-empty `blockedReason`, such as `isolated-test-environment-unavailable` or `token-budget-exhausted`, and must never claim or imply a pass. `execution.md` records attempted or blocked steps, base-URL safety decision, fixture/reset and request-observation availability, timestamps, and the evidence-file list. When available, use fixed headings `### 执行摘要` and `### 实际执行步骤` so the bounded deterministic report extractor can show actual execution facts. Available evidence files are required only when actually produced and must stay under the same case evidence directory.
 
 
 ## Standard scenarios (controller)
 
-- Read `testcase/frontend/rag/standard-scenarios.v1.json` when present.
+- Read `.harness/testcase/frontend/rag/standard-scenarios.v1.json` when present.
 - Cover each `priority=must` scenario with at least one case or record an explicit GAP in coverage-map.
 - Each case Markdown SHOULD include `## 测试点` and `## 测试步骤` sections.
 - Prefer linking cases via `standardScenarioIds` in manifest.draft notes when possible.

package/docs/templates/frontend-test-dag.json

@@ -14,7 +14,7 @@
     "Every generated browser start command uses playwright-cli open --browser=chrome followed by the concrete URL selected by retrieve-frontend-test-context-pi from bound task source/config and written to context.md; the environment shell must mark that URL reachable before generation/execution; executable case lines never retain an angle-bracket URL/ref placeholder; subsequent commands stay in that default session and must not use unverified named-session flags.",
     "Case children execute serially. Persist each case result, logs and browser evidence before the next child starts.",
     "A token threshold is a post-case stop check, not a model hard token cap; unstarted cases must be recorded as blocked: token-budget-exhausted.",
-    "Default pipeline acceptance is the final frontend-test-result-v1 plus testcase/frontend/reports/frontend-test-report.html",
+    "Default pipeline acceptance is the final frontend-test-result-v1 plus .harness/testcase/frontend/reports/frontend-test-report.html",
     "Default frontendTest.reviewMode=off uses mechanical checklist-shell before materialize; set reviewMode=blocking for legacy dual LLM review gate.",
     "playwright-cli-only: generators and executors may call only skill-declared playwright-cli commands; bare playwright / npx playwright / @playwright/test / Playwright source are forbidden with no native Playwright fallback.",
     "Browser-tool preflight (preflight-frontend-browser-tool-shell) must reject CODE_AGENT_PI_BACKEND=cli-only, verify the Pi SDK structured custom-tool surface, and confirm the verified playwright-cli launcher + --help open/close/find/snapshot/click contract before any frontend-test Pi node; it does not select or freeze the tested URL; missing capability/CLI fails with zero Pi calls.",
@@ -57,16 +57,16 @@
       "complexity": "LOW",
       "writePolicy": "exclusive",
       "writeSet": [
-        "testcase/frontend/rag/**"
+        ".harness/testcase/frontend/rag/**"
       ],
       "allowedPaths": [
-        "testcase/frontend/rag/**"
+        ".harness/testcase/frontend/rag/**"
       ],
       "forbiddenPaths": [
         ".harness/**",
         "artifacts/**"
       ],
-      "outputContract": "Write testcase/frontend/rag/standard-scenarios.v1.json for generate-time standard scenario coverage. Copy docs/templates or harness.json governanceRoot templates (including ai_workspace/loop-agent/templates) when present; otherwise write the minimal STD-FE-SMOKE-ENTRY fallback.",
+      "outputContract": "Write .harness/testcase/frontend/rag/standard-scenarios.v1.json for generate-time standard scenario coverage. Copy docs/templates or harness.json governanceRoot templates (including ai_workspace/loop-agent/templates) when present; otherwise write the minimal STD-FE-SMOKE-ENTRY fallback.",
       "subtask_prompt": "Prepare frontend-test package: materialize standard-scenarios.v1.json into the RAG package from docs/templates, governanceRoot/templates, or the init-projected ai_workspace/loop-agent/templates path.",
       "shell": {
         "commands": [],
@@ -86,11 +86,11 @@
       "complexity": "MED",
       "writePolicy": "exclusive",
       "writeSet": [
-        "testcase/frontend/rag/**"
+        ".harness/testcase/frontend/rag/**"
       ],
       "allowedPaths": [
         "REPLACE/WITH/SOURCE/PATH/**",
-        "testcase/frontend/rag/**"
+        ".harness/testcase/frontend/rag/**"
       ],
       "forbiddenPaths": [
         ".harness/**",
@@ -110,17 +110,17 @@
       "complexity": "LOW",
       "writePolicy": "exclusive",
       "writeSet": [
-        "testcase/frontend/rag/**"
+        ".harness/testcase/frontend/rag/**"
       ],
       "allowedPaths": [
-        "testcase/frontend/rag/**"
+        ".harness/testcase/frontend/rag/**"
       ],
       "forbiddenPaths": [
         ".harness/**",
         "artifacts/**"
       ],
       "outputContract": "Fail-closed environment preflight: absolute non-production baseUrl + curl HTTP reachability; writes environmentProbe facts; unreachable => blockedReason frontend-base-url-unreachable with errorClass (connection-refused / dns-unresolved / connect-timeout / http-N). Node ERROR so generate/map do not run. Does not start the app.",
-      "subtask_prompt": "Parse the concrete baseUrl selected by retrieve-frontend-test-context-pi from testcase/frontend/rag/context.md. Reject production, non-http(s), credentials, query and fragment. Probe with curl (HEAD then GET fallback; connect/max-time; no auth/cookie). 2xx/3xx => reachable and continue. Connection refused records errorClass=connection-refused and tells the operator to start the local app then rerun from this node. 4xx/5xx/DNS/timeout/TLS => blockedReason frontend-base-url-unreachable. Missing curl => blockedReason curl-unavailable. Do not start the app.",
+      "subtask_prompt": "Parse the concrete baseUrl selected by retrieve-frontend-test-context-pi from .harness/testcase/frontend/rag/context.md. Reject production, non-http(s), credentials, query and fragment. Probe with curl (HEAD then GET fallback; connect/max-time; no auth/cookie). 2xx/3xx => reachable and continue. Connection refused records errorClass=connection-refused and tells the operator to start the local app then rerun from this node. 4xx/5xx/DNS/timeout/TLS => blockedReason frontend-base-url-unreachable. Missing curl => blockedReason curl-unavailable. Do not start the app.",
       "shell": {
         "commands": [],
         "frontendTestEnvironmentProbe": {},
@@ -139,13 +139,13 @@
       "complexity": "HIGH",
       "writePolicy": "exclusive",
       "writeSet": [
-        "testcase/frontend/cases/FE-*.md",
-        "testcase/frontend/cases/index.md",
-        "testcase/frontend/cases/manifest.draft.json"
+        ".harness/testcase/frontend/cases/FE-*.md",
+        ".harness/testcase/frontend/cases/index.md",
+        ".harness/testcase/frontend/cases/manifest.draft.json"
       ],
       "allowedPaths": [
-        "testcase/frontend/rag/**",
-        "testcase/frontend/cases/**"
+        ".harness/testcase/frontend/rag/**",
+        ".harness/testcase/frontend/cases/**"
       ],
       "forbiddenPaths": [
         ".harness/**",
@@ -165,11 +165,11 @@
       "complexity": "LOW",
       "writePolicy": "exclusive",
       "writeSet": [
-        "testcase/frontend/cases/**"
+        ".harness/testcase/frontend/cases/**"
       ],
       "allowedPaths": [
-        "testcase/frontend/rag/**",
-        "testcase/frontend/cases/**"
+        ".harness/testcase/frontend/rag/**",
+        ".harness/testcase/frontend/cases/**"
       ],
       "forbiddenPaths": [
         ".harness/**",
@@ -233,17 +233,17 @@
           "outputContract": "Compact JSON <=1200 chars. Browser actions must use structured playwright_cli tool.",
           "writePolicy": "exclusive",
           "allowedPaths": [
-            "testcase/frontend/cases/{{case.caseId}}.md",
-            "testcase/frontend/rag/context.md",
-            "testcase/frontend/rag/coverage-map.md",
-            "testcase/frontend/evidence/{{case.caseId}}/**"
+            ".harness/testcase/frontend/cases/{{case.caseId}}.md",
+            ".harness/testcase/frontend/rag/context.md",
+            ".harness/testcase/frontend/rag/coverage-map.md",
+            ".harness/testcase/frontend/evidence/{{case.caseId}}/**"
           ],
           "forbiddenPaths": [
             ".harness/**",
             "artifacts/**"
           ],
           "writeSet": [
-            "testcase/frontend/evidence/{{case.caseId}}/**"
+            ".harness/testcase/frontend/evidence/{{case.caseId}}/**"
           ],
           "writeGuardPolicy": "tools-only"
         }
@@ -259,11 +259,11 @@
       "complexity": "LOW",
       "writePolicy": "exclusive",
       "writeSet": [
-        "testcase/frontend/evidence/**"
+        ".harness/testcase/frontend/evidence/**"
       ],
       "allowedPaths": [
-        "testcase/frontend/cases/**",
-        "testcase/frontend/evidence/**"
+        ".harness/testcase/frontend/cases/**",
+        ".harness/testcase/frontend/evidence/**"
       ],
       "forbiddenPaths": [
         ".harness/**",
@@ -273,7 +273,7 @@
       "subtask_prompt": "Select frontend-test cases eligible for bounded rerun.",
       "shell": {
         "commands": [
-          "node -e \"const fs=require('fs'),path=require('path');const manifestPath='testcase/frontend/cases/manifest.json';if(!fs.existsSync(manifestPath)){process.stdout.write(JSON.stringify({cases:[]}));process.exit(0);}const manifest=JSON.parse(fs.readFileSync(manifestPath,'utf8'));const cases=[];for(const c of (manifest.cases||[])){const evidenceDir=(c.evidenceDir||('testcase/frontend/evidence/'+c.caseId+'/')).replace(/\\/+$/,'')+'/';const resultPath=path.join(evidenceDir,'case-result.json');const execPath=path.join(evidenceDir,'execution.md');let reason=null;let attempt=0;let missing=false;if(!fs.existsSync(resultPath)){missing=true;reason='missing-result-files';}else{try{const r=JSON.parse(fs.readFileSync(resultPath,'utf8'));attempt=Number(r.rerunAttempt||0)||0;if(r.status==='blocked')reason='blocked';if(!r.status){missing=true;reason='missing-result-files';}}catch(e){missing=true;reason='missing-result-files';}}if(!fs.existsSync(execPath)){const st=reason;if(st!=='blocked'){missing=true;reason=reason||'missing-result-files';}}const should=(reason==='blocked'||missing)&&attempt<1;if(should){cases.push({caseId:c.caseId,casePath:c.casePath||('testcase/frontend/cases/'+c.caseId+'.md'),evidenceDir,dimension:c.dimension||'core',acIds:c.acIds||[],rerunAttempt:attempt+1,reason:reason||'blocked'});}}const out={schemaVersion:1,cases};fs.mkdirSync('testcase/frontend/evidence',{recursive:true});fs.writeFileSync('testcase/frontend/evidence/rerun-candidates.json',JSON.stringify(out,null,2)+'\\n');process.stdout.write(JSON.stringify({cases}));"
+          "node -e \"const fs=require('fs'),path=require('path');const manifestPath='.harness/testcase/frontend/cases/manifest.json';if(!fs.existsSync(manifestPath)){process.stdout.write(JSON.stringify({cases:[]}));process.exit(0);}const manifest=JSON.parse(fs.readFileSync(manifestPath,'utf8'));const cases=[];for(const c of (manifest.cases||[])){const evidenceDir=(c.evidenceDir||('.harness/testcase/frontend/evidence/'+c.caseId+'/')).replace(/\\/+$/,'')+'/';const resultPath=path.join(evidenceDir,'case-result.json');const execPath=path.join(evidenceDir,'execution.md');let reason=null;let attempt=0;let missing=false;if(!fs.existsSync(resultPath)){missing=true;reason='missing-result-files';}else{try{const r=JSON.parse(fs.readFileSync(resultPath,'utf8'));attempt=Number(r.rerunAttempt||0)||0;if(r.status==='blocked')reason='blocked';if(!r.status){missing=true;reason='missing-result-files';}}catch(e){missing=true;reason='missing-result-files';}}if(!fs.existsSync(execPath)){const st=reason;if(st!=='blocked'){missing=true;reason=reason||'missing-result-files';}}const should=(reason==='blocked'||missing)&&attempt<1;if(should){cases.push({caseId:c.caseId,casePath:c.casePath||('.harness/testcase/frontend/cases/'+c.caseId+'.md'),evidenceDir,dimension:c.dimension||'core',acIds:c.acIds||[],rerunAttempt:attempt+1,reason:reason||'blocked'});}}const out={schemaVersion:1,cases};fs.mkdirSync('.harness/testcase/frontend/evidence',{recursive:true});fs.writeFileSync('.harness/testcase/frontend/evidence/rerun-candidates.json',JSON.stringify(out,null,2)+'\\n');process.stdout.write(JSON.stringify({cases}));"
         ],
         "cwd": ".",
         "timeoutMs": 120000
@@ -328,17 +328,17 @@
           "outputContract": "Compact JSON <=1200 chars. Browser actions must use structured playwright_cli tool.",
           "writePolicy": "exclusive",
           "allowedPaths": [
-            "testcase/frontend/cases/{{case.caseId}}.md",
-            "testcase/frontend/rag/context.md",
-            "testcase/frontend/rag/coverage-map.md",
-            "testcase/frontend/evidence/{{case.caseId}}/**"
+            ".harness/testcase/frontend/cases/{{case.caseId}}.md",
+            ".harness/testcase/frontend/rag/context.md",
+            ".harness/testcase/frontend/rag/coverage-map.md",
+            ".harness/testcase/frontend/evidence/{{case.caseId}}/**"
           ],
           "forbiddenPaths": [
             ".harness/**",
             "artifacts/**"
           ],
           "writeSet": [
-            "testcase/frontend/evidence/{{case.caseId}}/**"
+            ".harness/testcase/frontend/evidence/{{case.caseId}}/**"
           ],
           "writeGuardPolicy": "tools-only"
         }
@@ -354,11 +354,11 @@
       "complexity": "LOW",
       "writePolicy": "exclusive",
       "writeSet": [
-        "testcase/frontend/evidence/**"
+        ".harness/testcase/frontend/evidence/**"
       ],
       "allowedPaths": [
-        "testcase/frontend/cases/**",
-        "testcase/frontend/evidence/**"
+        ".harness/testcase/frontend/cases/**",
+        ".harness/testcase/frontend/evidence/**"
       ],
       "forbiddenPaths": [
         ".harness/**",
@@ -383,10 +383,10 @@
       "complexity": "LOW",
       "writePolicy": "exclusive",
       "writeSet": [
-        "testcase/frontend/reports/**"
+        ".harness/testcase/frontend/reports/**"
       ],
       "allowedPaths": [
-        "testcase/frontend/**"
+        ".harness/testcase/frontend/**"
       ],
       "forbiddenPaths": [
         ".harness/**",
@@ -403,5 +403,14 @@
         "timeoutMs": 120000
       }
     }
-  ]
+  ],
+  "frontendTestLayout": {
+    "testRoot": ".harness/testcase/frontend",
+    "ragDir": ".harness/testcase/frontend/rag",
+    "casesDir": ".harness/testcase/frontend/cases",
+    "evidenceDir": ".harness/testcase/frontend/evidence",
+    "reportsDir": ".harness/testcase/frontend/reports",
+    "fixturesDir": ".harness/testcase/frontend/fixtures",
+    "isDefault": true
+  }
 }

package/docs/templates/frontend-test-dag.retrieve-context.prompt.md

@@ -1,6 +1,6 @@
 # Retrieve frontend test context
 
-Write only `testcase/frontend/rag/context.md` and `coverage-map.md`. Record traceable facts from the task source, routes, components, API/Mock contracts, existing tests and execution contract. Do not invent fields, credentials, limits or test data.
+Write only `.harness/testcase/frontend/rag/context.md` and `coverage-map.md`. Record traceable facts from the task source, routes, components, API/Mock contracts, existing tests and execution contract. Do not invent fields, credentials, limits or test data.
 
 ## Runtime Base URL resolution (required)
 
@@ -17,5 +17,5 @@ Do not claim the environment is reachable until preflight completes. Preflight d
 
 ## Standard scenario coverage
 
-- Copy or reference `docs/templates/frontend-test-standard-scenarios.v1.json`, `harness.json` `governanceRoot`/templates, or the init-projected `ai_workspace/loop-agent/templates/frontend-test-standard-scenarios.v1.json` into `testcase/frontend/rag/standard-scenarios.v1.json` when available.
+- Copy or reference `docs/templates/frontend-test-standard-scenarios.v1.json`, `harness.json` `governanceRoot`/templates, or the init-projected `ai_workspace/loop-agent/templates/frontend-test-standard-scenarios.v1.json` into `.harness/testcase/frontend/rag/standard-scenarios.v1.json` when available.
 - Add `## Standard scenario coverage` to coverage-map.md with planned/n/a for each must scenario.

package/docs/templates/frontend-test-dag.retrospect.prompt.md

@@ -1,5 +1,5 @@
 # Frontend test retrospective
 
-Write a dated report under `testcase/frontend/reports/` (for example `frontend-test-retrospect-<date>.md`) after `frontend-test-result-v1` materialization. Do **not** require outcome=pass; failed, incomplete, and blocked runs still need a report.
+Write a dated report under `.harness/testcase/frontend/reports/` (for example `frontend-test-retrospect-<date>.md`) after `frontend-test-result-v1` materialization. Do **not** require outcome=pass; failed, incomplete, and blocked runs still need a report.
 
 Combine a short AC → case → browser-evidence review with the closeout: case coverage, passed/failed/blocked results (including `token-budget-exhausted`), evidence gaps, browser anomalies, residual risks, and an A/B/C/D maturity rating. Cite the deterministic case-evidence validation outcome. Passed cases should reference the successful `find` assertion plus screenshot or equivalent browser evidence and the ordered post-execution cleanup receipt when available; failed/blocked cases need explicit reasons. Blocked cases never count as passed; a missing or malformed `execution.md` / `case-result.json` is a verification gap, not a pass. Do not write under `docs/**`.

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

@@ -2,4 +2,4 @@
 
 Read the RAG files and Markdown cases only. First line must be `VERDICT: pass` or `VERDICT: request-revision`. Report AC coverage, case independence, evidence completeness, unsafe environment/data dependencies, and manifest issues. This verdict is a deterministic safety gate: `request-revision` blocks manifest materialization and browser execution.
 
-Every case must retain the exact browser-start command prefix with the resolved absolute baseUrl from `testcase/frontend/rag/context.md` (prefer task source `config.md`, else `http://localhost:5173`): `playwright-cli open --browser=chrome <resolved-base-url>`; session flags must not precede `open`, and subsequent commands must remain in its default session without `-s=` or assumed named-session binding. Verify every executable sub-scenario specifies fixture/reset, UI reset, fresh snapshot before element refs, a successful `playwright-cli find ...` semantic assertion after `open`, and an evidence write point. `snapshot`, `goto`, `screenshot`, `request`/`console`, and ordinary interactions cannot independently authorize passed. Verify each case requires both `execution.md` and `case-result.json` under its own evidence directory. The JSON result must contain matching `caseId`, `status` (`passed`, `failed`, or `blocked`) and `evidencePaths`; blocked cases must name a non-empty `blockedReason` and cannot count as passed.
+Every case must retain the exact browser-start command prefix with the resolved absolute baseUrl from `.harness/testcase/frontend/rag/context.md` (prefer task source `config.md`, else `http://localhost:5173`): `playwright-cli open --browser=chrome <resolved-base-url>`; session flags must not precede `open`, and subsequent commands must remain in its default session without `-s=` or assumed named-session binding. Verify every executable sub-scenario specifies fixture/reset, UI reset, fresh snapshot before element refs, a successful `playwright-cli find ...` semantic assertion after `open`, and an evidence write point. `snapshot`, `goto`, `screenshot`, `request`/`console`, and ordinary interactions cannot independently authorize passed. Verify each case requires both `execution.md` and `case-result.json` under its own evidence directory. The JSON result must contain matching `caseId`, `status` (`passed`, `failed`, or `blocked`) and `evidencePaths`; blocked cases must name a non-empty `blockedReason` and cannot count as passed.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tea-agent/loop-agent",
-  "version": "0.44.0-next.12",
+  "version": "0.44.0-next.13",
   "type": "module",
   "bin": {
     "loop-agent": "bin/loop-agent.js",
@@ -79,19 +79,23 @@
     "@deepseek-ai/dsh-invariants": "0.1.1-rc.2",
     "@earendil-works/pi-ai": "0.84.4",
     "@earendil-works/pi-coding-agent": "0.84.4",
+    "@mozilla/readability": "^0.6.0",
+    "@playwright/cli": "0.1.20",
     "@xterm/addon-fit": "^0.11.0",
     "@xterm/xterm": "^6.0.0",
     "commander": "^12.1.0",
     "katex": "^0.16.47",
+    "linkedom": "^0.18.13",
     "mermaid": "^11.16.1",
     "mysql2": "^3.24.4",
     "node-pty": "^1.2.0-beta.15",
     "pg": "^8.23.0",
-    "playwright-core": "^1.63.0",
+    "playwright-core": "1.64.0-alpha-2026-09-14",
     "rehype-highlight": "^7.0.2",
     "rehype-katex": "^7.0.1",
     "remark-math": "^6.0.0",
     "semver": "^7.8.5",
+    "turndown": "^7.2.4",
     "typebox": "1.3.7",
     "yaml": "^2.9.0",
     "zod": "^3.25.76",
@@ -107,6 +111,7 @@
     "@types/react": "^19.1.8",
     "@types/react-dom": "^19.1.6",
     "@types/semver": "^7.7.1",
+    "@types/turndown": "^5.0.6",
     "@vitest/coverage-v8": "^4.1.11",
     "fast-check": "^4.10.0",
     "react": "^19.1.0",

package/skills/fe-test-ui-scout/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: fe-test-ui-scout
-description: 在写 frontend-test Wave PRD/回归目录之前，对真实运行的被测页面做只读锚点侦察，产出并维护 {testRoot}/rag/ui-anchors.md 锚点台账（默认 testcase/frontend/rag/ui-anchors.md）。用 playwright-cli snapshot/find 逐字面验证命中数与唯一性，防止 PRD 验收标准引用不存在或不唯一的文案。触发词：frontend-test、锚点、台账、ui-anchors、侦察、写 PRD 前、snapshot/find 校准、Wave PRD。
+description: 在写 frontend-test Wave PRD/回归目录之前，对真实运行的被测页面做只读锚点侦察，产出并维护 {testRoot}/rag/ui-anchors.md 锚点台账（默认 .harness/testcase/frontend/rag/ui-anchors.md）。用 playwright-cli snapshot/find 逐字面验证命中数与唯一性，防止 PRD 验收标准引用不存在或不唯一的文案。触发词：frontend-test、锚点、台账、ui-anchors、侦察、写 PRD 前、snapshot/find 校准、Wave PRD。
 references:
   - path: references/ledger-schema.md
     required: true
@@ -13,7 +13,7 @@ references:
 ## 定位
 
 写 Wave PRD / 校准回归目录 AC **之前**的前置侦察。产出锚点台账
-`{testRoot}/rag/ui-anchors.md`（默认 `testcase/frontend/rag/ui-anchors.md`）：每个「页面 × 状态」下真实可见、
+`{testRoot}/rag/ui-anchors.md`（默认 `.harness/testcase/frontend/rag/ui-anchors.md`）：每个「页面 × 状态」下真实可见、
 `find` 可命中的字面清单。PRD 的每条 `find "..."` 断言必须能在台账找到对应行；
 台账没有的字面禁止写进验收标准。
 
@@ -23,7 +23,7 @@ references:
 
 ## 输入
 
-- 被测 baseUrl（来自 `{testRoot}/rag/context.md` 的 `environmentProbe=reachable` URL；默认 `testcase/frontend/rag/context.md`）
+- 被测 baseUrl（来自 `{testRoot}/rag/context.md` 的 `environmentProbe=reachable` URL；默认 `.harness/testcase/frontend/rag/context.md`）
 - 目标 Wave 的 AC 清单（回归目录中本 Wave 范围的行）
 - 既有台账（增量更新，不整表重写）
 
@@ -56,7 +56,7 @@ references:
 
 ## 输出
 
-- `{testRoot}/rag/ui-anchors.md`（增量更新；默认 `testcase/frontend/rag/ui-anchors.md`）
+- `{testRoot}/rag/ui-anchors.md`（增量更新；默认 `.harness/testcase/frontend/rag/ui-anchors.md`）
 - 侦察小结（对话内输出，不落盘；结论回写 PRD 草稿的锚点引用）
 
 ## References

package/skills/fe-test-ui-scout/references/ledger-schema.md

@@ -2,7 +2,7 @@
 
 ## 文件位置与命名
 
-- 路径：`{testRoot}/rag/ui-anchors.md`（默认 `testcase/frontend/rag/ui-anchors.md`）
+- 路径：`{testRoot}/rag/ui-anchors.md`（默认 `.harness/testcase/frontend/rag/ui-anchors.md`）
 - 编码：UTF-8，LF；表格用 GitHub Flavored Markdown。
 - 台账是**增量账本**：修订不删除历史行；失效行改状态列并注明原因。
 

package/skills/playwright-cli/SKILL.md

@@ -55,7 +55,7 @@ request
 
 ## 推荐执行流程
 
-使用 `{testRoot}/rag/context.md`（默认 `testcase/frontend/rag/context.md`）中已由 environment shell 标记为 `reachable` 的非生产 `baseUrl` 和默认浏览器 session；不得创建 named session。交互前先获取 snapshot，并只使用 snapshot 中可见的 ref 或已知安全 locator。截图写入当前 case 的 `{evidenceDir}/<caseId>/`，canonical 文件名仍是 `final.png`。
+使用 `{testRoot}/rag/context.md`（默认 `.harness/testcase/frontend/rag/context.md`）中已由 environment shell 标记为 `reachable` 的非生产 `baseUrl` 和默认浏览器 session；不得创建 named session。交互前先获取 snapshot，并只使用 snapshot 中可见的 ref 或已知安全 locator。截图写入当前 case 的 `{evidenceDir}/<caseId>/`，canonical 文件名仍是 `final.png`。
 
 ```text
 playwright-cli open --browser=chrome http://localhost:5173

package/skills/playwright-cli-case-generator/SKILL.md

@@ -13,7 +13,7 @@ description: 根据 FE-test RAG 知识包生成可由受限 playwright_cli runti
 
 ## 输入与边界
 
-默认产物根是 `testcase/frontend/`。若任务配置了 `frontendTest.testRoot`，把下列路径中的 `testcase/frontend/` 整段替换为该根（不要只替换 `testcase/`）。
+默认产物根是 `.harness/testcase/frontend/`。若任务配置了 `frontendTest.testRoot`，把下列路径中的 `.harness/testcase/frontend/` 整段替换为该根（不要只替换 `.harness/testcase/`）。
 
 - 只读取 `{testRoot}/rag/context.md`、`coverage-map.md` 与已有 `{testRoot}/cases/`。
 - 若存在 `{testRoot}/rag/ui-anchors.md` 锚点台账，必须一并读取并作为 UI 断言的唯一事实源；台账缺失时按 RAG 知识包生成，但不得引用台账外的具体控件字面（缺失信息标 `blocked`）。
@@ -40,8 +40,8 @@ description: 根据 FE-test RAG 知识包生成可由受限 playwright_cli runti
     （例：`FE-LOGIN-001-core`）。禁止把验收标准写成 caseId。
   - `acIds` = **验收标准 ID 列表**，形态 `AC-FE-*` / `AC-*`
     （例：`["AC-FE-001"]`）。禁止把用例 ID 放进 acIds。
-  - `casePath` 必须等于 `{casesDir}/<caseId>.md`（默认 `testcase/frontend/cases/<caseId>.md`）；
-    `evidenceDir` 必须等于 `{evidenceDir}/<caseId>/`（默认 `testcase/frontend/evidence/<caseId>/`）。
+  - `casePath` 必须等于 `{casesDir}/<caseId>.md`（默认 `.harness/testcase/frontend/cases/<caseId>.md`）；
+    `evidenceDir` 必须等于 `{evidenceDir}/<caseId>/`（默认 `.harness/testcase/frontend/evidence/<caseId>/`）。
 - `manifest` 使用 `schemaVersion: 1`，每项只含 `caseId`、`casePath`、`dimension`、`acIds`、
   `evidenceDir`。所有 ID、路径和 evidenceDir 必须唯一，并位于 `{testRoot}/` 内。
 - `index.md` 按功能点列出 case、维度、AC、数据依赖、API 映射和预期执行状态。
@@ -75,7 +75,7 @@ description: 根据 FE-test RAG 知识包生成可由受限 playwright_cli runti
 7. 明确的 UI/API 预期与数据清理结果；无法满足的环境或数据依赖必须写为 `blocked`。
 
 所有文件型输出均由 controller 绑定到执行节点提供的
-`{evidenceDir}/<case-id>/` 工作目录（默认 `testcase/frontend/evidence/<case-id>/`）。截图一律使用 canonical 语法
+`{evidenceDir}/<case-id>/` 工作目录（默认 `.harness/testcase/frontend/evidence/<case-id>/`）。截图一律使用 canonical 语法
 `playwright-cli screenshot --filename final.png`；如确有从最新 snapshot 解析出的真实元素 ref，写为
 `playwright-cli screenshot e5 --filename final.png`。`pdf` 必须写为
 `playwright-cli pdf --filename final.pdf`。`snapshot` 无 filename 时仅返回响应；需要文件时使用

package/dist/worker/console/static/assets/channel-CyBY_yGk.js

@@ -1 +0,0 @@
-import{ag as o,ah as n}from"./mermaid.core-4P9yPC9c.js";const t=(a,r)=>o.lang.round(n.parse(a)[r]);export{t as c};

package/dist/worker/console/static/assets/classDiagram-JCYQIIEL-D5lN4E_E.js

@@ -1 +0,0 @@
-import{s as a,c as s,a as e,C as t}from"./chunk-GF5L2VYU-C3uE-yc2.js";import{_ as i}from"./mermaid.core-4P9yPC9c.js";import"./chunk-5VM5RSS4-BNAuTOLE.js";import"./chunk-XXDRQBXY-CTQDmJcp.js";import"./chunk-KBJHAD2P-D_AtEYQL.js";import"./chunk-2GRJ4B5K-B9fh0IkF.js";import"./index-CTMZsDmh.js";var n={parser:e,get db(){return new t},renderer:s,styles:a,init:i(r=>{r.class||(r.class={}),r.class.arrowMarkerAbsolute=r.arrowMarkerAbsolute},"init")};export{n as diagram};

package/dist/worker/console/static/assets/classDiagram-v2-OCEON4UE-D5lN4E_E.js

@@ -1 +0,0 @@
-import{s as a,c as s,a as e,C as t}from"./chunk-GF5L2VYU-C3uE-yc2.js";import{_ as i}from"./mermaid.core-4P9yPC9c.js";import"./chunk-5VM5RSS4-BNAuTOLE.js";import"./chunk-XXDRQBXY-CTQDmJcp.js";import"./chunk-KBJHAD2P-D_AtEYQL.js";import"./chunk-2GRJ4B5K-B9fh0IkF.js";import"./index-CTMZsDmh.js";var n={parser:e,get db(){return new t},renderer:s,styles:a,init:i(r=>{r.class||(r.class={}),r.class.arrowMarkerAbsolute=r.arrowMarkerAbsolute},"init")};export{n as diagram};