@tea-agent/loop-agent 0.28.12-beta.1 → 0.28.13

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

@@ -42,7 +42,7 @@ loop-agent doctor
      --accept-recommendations DIGEST \
      --allowed-path "src/**" \
      --forbidden-path ".harness/**" \
-     --verify "typecheck:npm run typecheck" \
+     --verify "<label>:<command>" \
      --json
 
    # 审查 gate.writeSet / gate.digest 后
@@ -55,6 +55,8 @@ loop-agent doctor
    loop-agent plan complete PLAN_ID --summary "..."
    ```
 
+   `--verify` 命令应取项目 `AGENTS.md` / `docs/governance/verification-matrix.md` 登记的验证命令（不要假定 `npm run typecheck` 存在）；`--verify` 可选，省略时自动从 package.json scripts 或既有 managed `task.json.verifyCommands` 推导建议。
+
    首次 `task advance` 内部完成 create、PRD 归档、managed contract 投影、DAG 生成与 strict validate，并停在 writeSet gate；批准后同一命令长跑到稳定终态并做确定性 promotion/closeout。决策表与反模式见 `source-and-plan-practice.md`。
 2. **Operator 工具**，用于 recovery、诊断、评测重放：
 
@@ -166,7 +168,7 @@ loop-agent examples copy <name> --output examples/<name>
 loop-agent task advance <task-id> "Task Title" \
   --prd path/to-prd.md \
   --allowed-path "src/**" \
-  --verify "typecheck:npm run typecheck" \
+  --verify "<label>:<command>" \
   --json
 loop-agent task advance <task-id> --approve-gate "write-set-review:<digest>" --json
 loop-agent task status <task-id> --json
@@ -218,7 +220,7 @@ loop-agent task advance <task-id> "标题" \
   --prd <path-to-original-prd.md> \
   --allowed-path "<glob>" \
   --forbidden-path ".harness/**" \
-  --verify "typecheck:npm run typecheck" \
+  --verify "<label>:<command>" \
   --json
 ```
 
@@ -566,6 +568,9 @@ agent-worker scheduler cancel <schedule-id> --repo <repo-root> [--reason <text>]
 agent-worker scheduler harvest <schedule-id> --repo <repo-root> [--json]
 agent-worker scheduler discard <schedule-id> --repo <repo-root> --reason <text> [--force] [--json]
 agent-worker scheduler tick --repo <repo-root> [--json]  # daemon/clock; not Operator Chat
+agent-worker scheduler clock install --repo <repo-root> [--interval-sec 60] [--loop-agent-bin <path>] [--json]  # OS timer; CLI-only
+agent-worker scheduler clock status --repo <repo-root> [--json]  # CLI-only
+agent-worker scheduler clock uninstall --repo <repo-root> [--json]  # CLI-only
 agent-worker scheduler submit --repo <repo-root> --feature-id <id> --task-id <id> ...  # low-level planning fact
 agent-worker scheduler transition <schedule-id> --repo <repo-root> --to <status> ...  # internal lifecycle
 agent-worker console [--repo <repo-root>] [--port 8790] [--host 127.0.0.1]  # Official 裸入口；repo 默认当前目录
@@ -596,7 +601,7 @@ agent-worker observe snapshot --repo <repo-root>  # 输出 GlobalSnapshot JSON
 - `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。
 - **推荐**裸入口 `agent-worker console`（repo 默认当前目录，默认 `127.0.0.1:8790`）提供 Operate + Inspect；`console serve` 是等价兼容入口。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。Inspect/Observe 本身不会启动、暂停或重试 Task / Worker / DAG。
-- Night Scheduler（本地夜间自治）：白天 `admission prepare` 冻结 worktree + DAG writeSet gate；`scheduler add` 消费 gate 并预约 Task Pool `Queued`（不立即执行）；`scheduler tick` 作为 Worker 时钟 claim/dispatch（CLI/cron，不进 Operator Chat）；成功后 `pending-harvest`，早晨 `scheduler harvest`（exact-base FF）或 `scheduler discard`；`report morning --window night` 与 Inspect `#/night` / Operate 夜间面板读取同一套 facts。
+- Night Scheduler（本地夜间自治）：白天 `admission prepare` 冻结 worktree + DAG writeSet gate；`scheduler add` 消费 gate 并预约 Task Pool `Queued`（不立即执行）；`scheduler clock install` 安装本机 user-level OS timer（launchd / systemd --user / schtasks）周期调用 `scheduler tick`；tick 写统一 Clock receipt，doctor/morning/status 可解释 missing/stale/error/busy/drift；成功后 `pending-harvest`，早晨 `scheduler harvest`（exact-base FF）或 `scheduler discard`；`report morning --window night` 与 Inspect `#/night` / Operate 夜间面板读取同一套 facts。Clock install/status/uninstall 为 CLI-only。
 - 当前 Worker 仍是 v0（库 + CLI + dogfood）；日间批处理未强制定时/CI 驱动；`report morning` 默认可从 Task Pool runs 汇总，并支持 `--window night` 投影 Scheduler facts。
 
 ### 查看 duration statistics / context usage

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

@@ -57,7 +57,7 @@ Minimum governed path：
 loop-agent task advance <task-id> "Task Title" \
   --prd <path-to-original-prd.md> \
   --allowed-path "<glob>" \
-  --verify "typecheck:npm run typecheck" \
+  --verify "<label>:<command>" \
   --json \
   [--repo-root <target-repo>]
 
@@ -70,6 +70,8 @@ loop-agent task advance <task-id> \
 loop-agent task status <task-id> --json [--repo-root <target-repo>]
 ```
 
+The `--verify` command should reference verification commands registered in the project's `AGENTS.md` or its governance verification-matrix.md; do not assume `npm run typecheck` exists. `--verify` is optional; when omitted, suggestions are auto-derived from `package.json` scripts or existing managed `task.json.verifyCommands`.
+
 `loop-agent` is the preferred global CLI. For self-hosting loop-agent development, the controller must be an installed npm-published package. Use `npm install -g @tea-agent/loop-agent@latest` for first install or intentional upgrades, then treat the installed version as frozen for the current task and record `npm list -g @tea-agent/loop-agent --depth=0`. Do not repeatedly fetch `npx @latest` inside DAG nodes, and do not use the current working tree's `npm link` or `npm run dev` to control tasks that may edit CLI, DAG runtime, executors, package metadata, or build output. Use `npm run dev -- <args>` only for source debugging and focused CLI development.
 
 The npm package carries static capability assets: `skills/` (bundled in-package, containing `loop-agent` and `agent-worker`; `loop-agent init` mirrors them into the target project's `.agents/skills/`), `docs/templates/`, `docs/architecture/`, `docs/skills/`, `examples/`, `harness.json`, `AGENTS.md`, `README.md`, and `CHANGELOG.md`. `loop-agent init` creates `ai_workspace/loop-agent/` (the default governanceRoot) in the target project with `progress/`, `reports/`, `exec-plans/`, and `decisions/` directories plus their README files; the actual files under those directories belong to the target repository and are not shipped by the npm package.