@tea-agent/loop-agent 0.28.13 → 0.29.1

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

@@ -10,6 +10,12 @@ The preflight controller resolves and freezes one absolute browser base URL from
 - Never use production hosts or credentials.
 - Write `environmentProbe: pending`. The environment preflight shell will replace this with `reachable`, `unreachable`, or `curl-unavailable` plus a structured `blockedReason` (for example `frontend-base-url-unreachable`).
 - Include the exact browser start prefix using the supplied controller-frozen URL:
-  `playwright-cli open --browser=chrome --headed <controller-frozen-base-url>`.
+  `playwright-cli open --browser=chrome --headless <controller-frozen-base-url>`.
 
 Do not claim the environment is reachable until preflight completes. Preflight does not start the application.
+
+
+## Standard scenario coverage
+
+- Copy or reference `docs/templates/frontend-test-standard-scenarios.v1.json` into `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.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 --headed <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 `testcase/frontend/rag/context.md` (prefer task source `config.md`, else `http://localhost:5173`): `playwright-cli open --browser=chrome --headless <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/docs/templates/frontend-test-standard-scenarios.v1.json

@@ -0,0 +1,114 @@
+{
+  "schemaVersion": 1,
+  "id": "frontend-test-standard-scenarios-v1",
+  "scenarios": [
+    {
+      "id": "STD-FE-SMOKE-ENTRY",
+      "title": "入口可打开与壳层可见",
+      "category": "smoke",
+      "priority": "must",
+      "dimensionHint": "core",
+      "testPoints": ["冻结 baseUrl 可 open", "关键导航或页面壳可见"],
+      "minCases": 1
+    },
+    {
+      "id": "STD-FE-EMPTY-STATE",
+      "title": "列表空态",
+      "category": "empty",
+      "priority": "must",
+      "dimensionHint": "boundary",
+      "testPoints": ["无数据时空态文案或引导", "不白屏"],
+      "minCases": 1
+    },
+    {
+      "id": "STD-FE-LIST-PAGE",
+      "title": "列表渲染",
+      "category": "list",
+      "priority": "must",
+      "dimensionHint": "core",
+      "testPoints": ["表头/列或卡片列表可见", "有数据时行可渲染"],
+      "minCases": 1
+    },
+    {
+      "id": "STD-FE-PAGINATION",
+      "title": "分页或加载更多",
+      "category": "pagination",
+      "priority": "should",
+      "dimensionHint": "boundary",
+      "testPoints": ["翻页或加载更多可观察", "数据不足可 blocked 并写原因"],
+      "minCases": 0
+    },
+    {
+      "id": "STD-FE-CREATE-FORM-VALIDATION",
+      "title": "创建表单校验",
+      "category": "form",
+      "priority": "must",
+      "dimensionHint": "boundary",
+      "testPoints": ["必填/格式校验", "不提交明显脏数据"],
+      "minCases": 1
+    },
+    {
+      "id": "STD-FE-CREATE-SUCCESS",
+      "title": "创建成功反馈",
+      "category": "create",
+      "priority": "must",
+      "dimensionHint": "flow",
+      "testPoints": ["成功提示", "列表或详情可见新数据或等价反馈"],
+      "minCases": 1
+    },
+    {
+      "id": "STD-FE-VIEW-DETAIL",
+      "title": "详情查看",
+      "category": "detail",
+      "priority": "must",
+      "dimensionHint": "core",
+      "testPoints": ["从列表进入详情", "关键字段可读"],
+      "minCases": 1
+    },
+    {
+      "id": "STD-FE-UPDATE-OWNED",
+      "title": "更新归属数据",
+      "category": "update",
+      "priority": "should",
+      "dimensionHint": "flow",
+      "testPoints": ["仅可证明归属数据", "否则 blocked"],
+      "minCases": 0
+    },
+    {
+      "id": "STD-FE-DELETE-CONFIRM",
+      "title": "删除确认",
+      "category": "delete",
+      "priority": "should",
+      "dimensionHint": "flow",
+      "testPoints": ["确认框或等价保护", "归属规则"],
+      "minCases": 0
+    },
+    {
+      "id": "STD-FE-SEARCH-FILTER",
+      "title": "搜索筛选",
+      "category": "filter",
+      "priority": "must",
+      "dimensionHint": "core",
+      "testPoints": ["关键字或状态筛选结果变化"],
+      "minCases": 1
+    },
+    {
+      "id": "STD-FE-API-ERROR-TOAST",
+      "title": "后端错误可见反馈",
+      "category": "error",
+      "priority": "should",
+      "dimensionHint": "backend",
+      "testPoints": ["错误提示可观察", "可用 Mock"],
+      "minCases": 0
+    },
+    {
+      "id": "STD-FE-LOADING-DISABLED",
+      "title": "提交中防重复",
+      "category": "interaction",
+      "priority": "should",
+      "dimensionHint": "boundary",
+      "testPoints": ["loading 或按钮禁用"],
+      "minCases": 0
+    }
+  ]
+}

package/docs/templates/init-managed-agents.md

@@ -136,7 +136,7 @@ agent-worker console serve --repo . --port 8790   # 兼容入口，等价于上
 
 live run 先用 `loop-agent dag status --run-id <run-id>` 看 lifecycle 与 liveness；用 `loop-agent dag report --run-id <run-id> --markdown` 读 facts；失败/paused 用 `loop-agent dag doctor --run-id <run-id> --markdown`。生命周期对齐先只读运行 `loop-agent dag reconcile-run --run-id <run-id>`；只有 runner 已停止且 operator 明确提供 `--action supersede|abandon --reason "..."` 时才允许变更。失败 run 用 `loop-agent dag closeout-draft --run-id <run-id>` 生成 failure handoff，不要写成成功 closeout。
 
-Operator 须持续监控 live run，直到 controller 报告 run 已结束（节点/流程终态如 `FINISHED`、`FAILED` 或 `partial_failed`），或 Decision Gate **需要 approve**；不要在节点仍运行时假定完成。判活须组合 runner heartbeat、session events 与 `dag doctor` liveness/provider meaningful progress；Runner heartbeat 只证明 lease，alone ≠ progress，不得仅凭运行时长结束节点。exclusive writer（如 `implement-pi` / `repair-pi`）运行期间：主会话与其他 writer **不得并发修改工作区**，以免 write-guard 错误归因；只读 status/doctor/report/observe 与 approve/reject/resume CLI 仍允许。恢复：status/doctor/report → classify → reconcile/replan → CLI 重跑 → shell verify。**禁止**把主会话直接 Edit 业务代码当作恢复手段。
+Operator 须持续监控 live run，直到 controller 报告 run 已结束（节点/流程终态如 `FINISHED`、`FAILED` 或 `partial_failed`），或 Decision Gate **需要 approve**；不要在节点仍运行时假定完成。持续监视过程中，主会话可在合适节点（例如节点/rank 状态变化、进入 verify/closeout、出现 stall 嫌疑或需要 approve 时）向用户做简短进度汇报（当前节点、状态、是否有风险），避免长时间静默；汇报是告知，不是请求确认，不得因此停下流程。判活须组合 runner heartbeat、session events 与 `dag doctor` liveness/provider meaningful progress；Runner heartbeat 只证明 lease，alone ≠ progress，不得仅凭运行时长结束节点。exclusive writer（如 `implement-pi` / `repair-pi`）运行期间：主会话与其他 writer **不得并发修改工作区**，以免 write-guard 错误归因；只读 status/doctor/report/observe 与 approve/reject/resume CLI 仍允许。恢复：status/doctor/report → classify → reconcile/replan → CLI 重跑 → shell verify。**禁止**把主会话直接 Edit 业务代码当作恢复手段。
 
 ### 运行态与验证
 

package/harness.json

@@ -81,8 +81,8 @@
     "pi": {
       "description": "Pi planning, review, diagnosis, and bounded writing when DAG toolProfile=write",
       "LOW": "minimax-m3",
-      "MED": "gpt-5.6-terra",
-      "HIGH": "gpt-5.6-sol"
+      "MED": { "model": "deepseek/deepseek-v4-flash", "thinking": "max" },
+      "HIGH": "grok-4.5"
     }
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tea-agent/loop-agent",
-  "version": "0.28.13",
+  "version": "0.29.1",
   "type": "module",
   "bin": {
     "loop-agent": "bin/loop-agent.js",
@@ -51,6 +51,7 @@
     "lint": "tsc --noEmit",
     "typecheck": "tsc --noEmit",
     "test": "node scripts/run-tests.mjs",
+    "test:host": "vitest run test/init-upgrade.test.ts --maxWorkers=1 -t \"records and reuses|controller-authorized semantic merge|authority-sensitive\"",
     "test:fast": "vitest run --config vitest.fast.config.ts",
     "test:integration": "vitest run --config vitest.integration.config.ts",
     "docs:dev": "npm --prefix website start",

package/skills/playwright-cli/SKILL.md

@@ -58,7 +58,7 @@ request
 获取 snapshot，并只使用 snapshot 中可见的 ref 或已知安全 locator。
 
 ```text
-playwright-cli open --browser=chrome --headed http://localhost:5173
+playwright-cli open --browser=chrome --headless http://localhost:5173
 playwright-cli snapshot
 playwright-cli find "Sign in"
 playwright-cli fill e1 "user@example.com"

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

@@ -41,7 +41,7 @@ description: 根据 FE-test RAG 知识包生成可由受限 playwright_cli runti
    `-s=<case-id>` 建立 named session。
 3. 可独立执行的命令序列：使用 RAG `context.md` 中已解析的绝对 `baseUrl`（优先来自任务源
    `config.md`；缺失时默认 `http://localhost:5173`），必须以
-   `playwright-cli open --browser=chrome --headed` 后接解析出的具体 base URL 开始；不得保留
+   `playwright-cli open --browser=chrome --headless` 后接解析出的具体 base URL 开始；不得保留
    base-url 占位符，也不得使用 `-s=<case-id>` 或其他 named session；再按需登录、数据准备、
    `snapshot` 后优先使用元素引用和操作。每个拟通过场景必须在 `open` 后以成功的 `find` 作为
    唯一结构化 UI 语义断言，再由 controller 执行 post-execution cleanup。`snapshot`、`goto`、