@tea-agent/loop-agent 0.2.0 → 0.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (77) hide show
  1. package/AGENTS.md +43 -24
  2. package/CHANGELOG.md +72 -44
  3. package/README.md +177 -164
  4. package/bin/loop-agent.js +21 -21
  5. package/dist/application/dag/args.js +6 -0
  6. package/dist/application/dag/generate-task-dag.js +5 -3
  7. package/dist/application/dag/run-dag.js +17 -1
  8. package/dist/application/dag/validate-dag.js +41 -0
  9. package/dist/cli/command-definitions.js +2 -2
  10. package/dist/cli/program.js +24 -4
  11. package/dist/commands/init.js +1036 -461
  12. package/dist/workflows/dag/dynamic-runtime/loop-until.js +2 -1
  13. package/dist/workflows/dag/dynamic-runtime/map.js +1 -0
  14. package/dist/workflows/dag/failure-routing.js +82 -0
  15. package/dist/workflows/dag/init-hybrid.js +3 -3
  16. package/dist/workflows/dag/lifecycle.js +95 -3
  17. package/dist/workflows/dag/report.js +73 -1
  18. package/dist/workflows/dag/skills.js +3 -3
  19. package/dist/workflows/dag/types.js +2 -0
  20. package/dist/workflows/dynamic/compile.js +11 -0
  21. package/dist/workflows/dynamic/spec.js +1 -0
  22. package/docs/README.md +50 -45
  23. package/docs/agent-dag-recovery-playbook.md +32 -6
  24. package/docs/agent-dag-runner.md +19 -17
  25. package/docs/architecture/runtime-boundaries.md +1 -1
  26. package/docs/cursor-executor-usage.md +5 -5
  27. package/docs/decisions/README.md +2 -2
  28. package/docs/design/README.md +24 -24
  29. package/docs/development-principles.md +50 -50
  30. package/docs/dynamic-workflow-dag-engine-roadmap.md +6 -6
  31. package/docs/exec-plans/README.md +4 -4
  32. package/docs/exec-plans/active/README.md +7 -9
  33. package/docs/exec-plans/completed/README.md +10 -8
  34. package/docs/feature-workflow.md +111 -109
  35. package/docs/harness-methodology-verification.md +18 -18
  36. package/docs/init-surface.manifest.json +175 -0
  37. package/docs/loop-agent-harness.md +36 -36
  38. package/docs/production-readiness.md +96 -0
  39. package/docs/progress/README.md +2 -2
  40. package/docs/reports/README.md +4 -2
  41. package/docs/skills/README.md +6 -0
  42. package/docs/skills/vetted-skill-registry.md +26 -0
  43. package/docs/templates/agent-dag-decision-gate-dogfood-report.md +1 -1
  44. package/docs/templates/agent-dag-process-supervisor.prompt.md +2 -2
  45. package/docs/templates/agent-dag-report.schema.json +33 -2
  46. package/docs/templates/agent-dag-review-verdict.prompt.md +1 -1
  47. package/docs/templates/agent-dag.base.json +195 -195
  48. package/docs/templates/agent-dag.final-verification.json +190 -190
  49. package/docs/templates/agent-dag.schema.json +17 -17
  50. package/docs/templates/agent-dag.supervised-implementation.json +500 -500
  51. package/docs/templates/hybrid-dag.json +193 -193
  52. package/docs/templates/init-evolution-review.md +33 -0
  53. package/docs/templates/production-readiness-checklist.md +57 -0
  54. package/docs/templates/progress-log.md +7 -7
  55. package/docs/templates/project-start-checklist.md +8 -8
  56. package/docs/templates/qa-report.md +17 -11
  57. package/docs/templates/sprint-contract.md +19 -19
  58. package/docs/verification-matrix.md +37 -26
  59. package/examples/example-dag.json +51 -51
  60. package/examples/hybrid-loop-agent-dag.json +194 -194
  61. package/harness.json +10 -8
  62. package/package.json +60 -58
  63. package/skills/code-review-core/SKILL.md +20 -0
  64. package/skills/codebase-scout/SKILL.md +19 -0
  65. package/skills/init-capability-evolution/SKILL.md +69 -0
  66. package/skills/loop-agent/SKILL.md +35 -35
  67. package/skills/loop-agent/references/command-reference.md +125 -65
  68. package/skills/loop-agent/references/harness-policy.md +30 -30
  69. package/skills/loop-agent/references/hybrid-dag.md +30 -30
  70. package/skills/loop-agent/references/model-routing.md +1 -1
  71. package/skills/loop-agent/references/orchestrator-and-interventions.md +1 -1
  72. package/skills/loop-agent/references/pi-prompt.md +9 -9
  73. package/skills/loop-agent/references/post-implementation-and-patterns.md +7 -7
  74. package/skills/loop-agent/references/task-workflow.md +19 -19
  75. package/skills/loop-agent/references/verification-and-failure-handling.md +36 -0
  76. package/skills/test-driven-development/SKILL.md +20 -0
  77. package/skills/webapp-testing/SKILL.md +19 -0
@@ -8,7 +8,7 @@
8
8
  - 历史顺序式 `run analyze|plan|spec|implement|verify|auto|loop|continue` workflow 已移除。不要将其作为 fallback path 呈现。
9
9
  - **Long-running `loop`** 是 Agent DAG 之上的 outer state/evidence layer。它记录 rounds、context compression、signals、canonical refs;不得替代 complex work 的 DAG writeSet review、Decision Gate 或 shell verification。
10
10
  - **Main session** 负责 orchestrate:选一个 work chunk、准备 source materials、review DAG/writeSet、monitor failures、跑 final verification、hand off。
11
- - **Executors** 实现 bounded work:Pi 在 DAG nodes 做 read-only planning/review/diagnosis,并在节点声明 `toolProfile: "write"` 时做 bounded implementation/repair;Cursor 是显式启用的可选 bounded writer;shell 产出 deterministic verification facts。
11
+ - **Executors** 实现 bounded work:Pi 在 DAG nodes 做 read-only planning/review/diagnosis,并在节点声明 `toolProfile: "write"` 时做 bounded implementation/repair;Cursor 是显式启用的可选 bounded writer;shell 产出 deterministic verification facts。
12
12
  - **Shell verification 是 completion fact source**。LLM review 或 advisory output 不能替代 command exit codes 与 archived evidence。
13
13
 
14
14
  ## Command surface tiers
@@ -33,13 +33,13 @@ Is this only status, diagnosis, recovery, or closeout?
33
33
  yes -> Agent DAG.
34
34
  ```
35
35
 
36
- 在以下任一 signal 适用时用 Agent DAG 而非 broad one-shot execution:
37
-
38
- - loop-agent runtime, DAG schema, run facts, promotion/closeout, scripts/CI, public contract, or shared protocol is touched.
39
- - The change needs multiple files, multiple scouts, review gates, Decision Gate, repair flow, or shell gate.
40
- - `writeSet` is broad, multiple exclusive writers exist, or public interfaces / architecture boundaries change.
41
- - Requirement, architecture, credential, cost, deployment, security, or authority surface is unclear.
42
- - A failure repeats and needs recovery planning rather than blind retry.
36
+ 在以下任一 signal 适用时用 Agent DAG 而非 broad one-shot execution:
37
+
38
+ - loop-agent runtime, DAG schema, run facts, promotion/closeout, scripts/CI, public contract, or shared protocol is touched.
39
+ - The change needs multiple files, multiple scouts, review gates, Decision Gate, repair flow, or shell gate.
40
+ - `writeSet` is broad, multiple exclusive writers exist, or public interfaces / architecture boundaries change.
41
+ - Requirement, architecture, credential, cost, deployment, security, or authority surface is unclear.
42
+ - A failure repeats and needs recovery planning rather than blind retry.
43
43
 
44
44
  ## Agent DAG path
45
45
 
@@ -61,18 +61,18 @@ loop-agent dag validate \
61
61
  --strict-models \
62
62
  --strict-governance
63
63
 
64
- loop-agent run-dag \
65
- --dag <temp-dir>/<task-id>-dag.json \
66
- --cwd <target-repo>
67
- ```
68
-
69
- `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.
70
-
71
- The npm package carries static capability assets: `skills/`, top-level governance docs, `docs/templates/`, `examples/`, `harness.json`, `AGENTS.md`, `README.md`, and `CHANGELOG.md`. Generated or historical task facts under `docs/progress/`, `docs/reports/`, `docs/exec-plans/`, and `docs/decisions/` belong to the target repository; package only their directory README files, not prior run content.
64
+ loop-agent run-dag \
65
+ --dag <temp-dir>/<task-id>-dag.json \
66
+ --cwd <target-repo>
67
+ ```
68
+
69
+ `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.
72
70
 
73
- For arbitrary target repositories, DAG skill instructions must not depend on loop-agent source history being copied into the target repo. Resolve configured, user, or target-local skills when present, then fall back to package-bundled `skills/` as the stable default capability set.
74
-
75
- `<temp-dir>` means the platform-native temp directory. Use native paths for actual `--output`, `--dag`, and `--cwd` values on macOS and Windows; use `/` only for stable repo refs, JSON/Markdown evidence refs, and glob conventions.
71
+ The npm package carries static capability assets: `skills/`, top-level governance docs, `docs/templates/`, `examples/`, `harness.json`, `AGENTS.md`, `README.md`, and `CHANGELOG.md`. Generated or historical task facts under `docs/progress/`, `docs/reports/`, `docs/exec-plans/`, and `docs/decisions/` belong to the target repository; package only their directory README files, not prior run content.
72
+
73
+ For arbitrary target repositories, DAG skill instructions must not depend on loop-agent source history being copied into the target repo. Resolve configured, user, or target-local skills when present, then fall back to package-bundled `skills/` as the stable default capability set.
74
+
75
+ `<temp-dir>` means the platform-native temp directory. Use native paths for actual `--output`, `--dag`, and `--cwd` values on macOS and Windows; use `/` only for stable repo refs, JSON/Markdown evidence refs, and glob conventions.
76
76
 
77
77
  Execution 前 review `dag run-task` JSON / `reviewPacket`:
78
78
 
@@ -168,12 +168,12 @@ Rules:
168
168
  - `dag report --json` 与 markdown 须 expose `convergence.passHistory`。
169
169
  - Final completion authority 仍是 full shell verification;quota/focused commands 仅为 intermediate cost controls。
170
170
 
171
- ## Structured repair, spine audit, and curator gates
172
-
173
- - `shell.repairArtifactGate.fromNodeId` validates the upstream supervisor artifact before repair. Missing/invalid JSON, missing request-revision `fixScope`, or scope outside the downstream repair writer allowedPaths/writeSet fails closed.
174
- - `spine audit <task-id>` is the deterministic minimal spec spine checker for task source, ownership paths, requirement coverage, and final verification commands.
175
- - `dag validate --strict-governance --spine-task <task-id>` may consume the same spine audit as part of strict validation.
176
- - `knowledge curate` reads completed convergence patterns and writes only human-gated proposal Markdown after skill safety preflight.
171
+ ## Structured repair, spine audit, and curator gates
172
+
173
+ - `shell.repairArtifactGate.fromNodeId` validates the upstream supervisor artifact before repair. Missing/invalid JSON, missing request-revision `fixScope`, or scope outside the downstream repair writer allowedPaths/writeSet fails closed.
174
+ - `spine audit <task-id>` is the deterministic minimal spec spine checker for task source, ownership paths, requirement coverage, and final verification commands.
175
+ - `dag validate --strict-governance --spine-task <task-id>` may consume the same spine audit as part of strict validation.
176
+ - `knowledge curate` reads completed convergence patterns and writes only human-gated proposal Markdown after skill safety preflight.
177
177
 
178
178
  ## SePO-lite prompt evolution
179
179
 
@@ -213,11 +213,11 @@ Sidecar output 为 advisory。若须成为 task evidence,通过 loop-agent run
213
213
 
214
214
  - Agent DAG 用 DAG JSON `executorModels` 加 node `executor` / `complexity`;不要从 repo `harness.json.models` 推断 DAG models。
215
215
  - DAG `shell` 与 `static` nodes 不用 models。
216
- - `harness.json.models.<step>` 下 historical step models 是 legacy metadata,不是新 DAG work 的 routing。
217
- - `pi-prompt` / `cursor-prompt` models 来自 CLI flags 或 runtime defaults,须 per intervention 选择。
218
- - Pi DAG nodes 默认 read-only planning/review/diagnosis;声明 `toolProfile: "write"` 时是 bounded writers,须有 explicit write scope。
219
- - Cursor nodes 是显式启用的可选 bounded writers,须有 explicit write scope。
220
- - Shell nodes 产出 deterministic verification facts 与 gates。
216
+ - `harness.json.models.<step>` 下 historical step models 是 legacy metadata,不是新 DAG work 的 routing。
217
+ - `pi-prompt` / `cursor-prompt` models 来自 CLI flags 或 runtime defaults,须 per intervention 选择。
218
+ - Pi DAG nodes 默认 read-only planning/review/diagnosis;声明 `toolProfile: "write"` 时是 bounded writers,须有 explicit write scope。
219
+ - Cursor nodes 是显式启用的可选 bounded writers,须有 explicit write scope。
220
+ - Shell nodes 产出 deterministic verification facts 与 gates。
221
221
 
222
222
  ## Artifacts and facts boundary
223
223
 
@@ -1,6 +1,6 @@
1
1
  # Agent DAG Hybrid Workflow(`run-dag` / `dag init-hybrid`)
2
2
 
3
- 创建或执行 loop-agent 工作的首选 Agent DAG path 时使用本文:Level 2 Agent DAG orchestration、Pi read-only + Pi `toolProfile: "write"` bounded execution、optional Cursor backend、write policy、DAG template、task-to-DAG 生成,或基于 governance-profile 的 template 选择。
3
+ 创建或执行 loop-agent 工作的首选 Agent DAG path 时使用本文:Level 2 Agent DAG orchestration、Pi read-only + Pi `toolProfile: "write"` bounded execution、optional Cursor backend、write policy、DAG template、task-to-DAG 生成,或基于 governance-profile 的 template 选择。
4
4
 
5
5
  ### DAG workflow 优先级
6
6
 
@@ -25,25 +25,25 @@
25
25
 
26
26
  ### Level 2 Agent DAG hybrid(`run-dag`)
27
27
 
28
- ```bash
29
- cp examples/hybrid-loop-agent-dag.json <temp-dir>/hybrid-dag.json
30
- loop-agent dag validate --dag <temp-dir>/hybrid-dag.json # 常规 validation + ranks;无 dag-runs 副作用
31
- loop-agent dag validate --dag <temp-dir>/hybrid-dag.json --strict-models # 非 canonical executorModels 时也失败
32
- loop-agent dag validate --dag <temp-dir>/hybrid-dag.json --strict-governance # governance warning(如 read-only artifact drift)时失败
33
- loop-agent dag validate --dag <temp-dir>/hybrid-dag.json --forbid-executor cursor # offline/CI/no-key 显式 no-Cursor;存在 cursor node 时失败
34
- loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --cwd <repo-root> # 执行(若包含 cursor node 则需 CURSOR_API_KEY)
35
- loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --cwd <repo-root> --no-cursor # 存在 cursor node 时执行前失败
36
- loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --init-only --canvas-path <temp-dir>/hybrid-dag.canvas.tsx # 可选 derived Canvas(无需 CURSOR_API_KEY)
37
- ```
38
-
39
- `<temp-dir>` 表示平台原生临时目录;实际命令中 macOS 与 Windows 都使用本机路径。`/` 只作为 repo refs、JSON/Markdown evidence refs 和 glob 约定的稳定分隔符。
28
+ ```bash
29
+ cp examples/hybrid-loop-agent-dag.json <temp-dir>/hybrid-dag.json
30
+ loop-agent dag validate --dag <temp-dir>/hybrid-dag.json # 常规 validation + ranks;无 dag-runs 副作用
31
+ loop-agent dag validate --dag <temp-dir>/hybrid-dag.json --strict-models # 非 canonical executorModels 时也失败
32
+ loop-agent dag validate --dag <temp-dir>/hybrid-dag.json --strict-governance # governance warning(如 read-only artifact drift)时失败
33
+ loop-agent dag validate --dag <temp-dir>/hybrid-dag.json --forbid-executor cursor # offline/CI/no-key 显式 no-Cursor;存在 cursor node 时失败
34
+ loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --cwd <repo-root> # 执行(若包含 cursor node 则需 CURSOR_API_KEY)
35
+ loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --cwd <repo-root> --no-cursor # 存在 cursor node 时执行前失败
36
+ loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --init-only --canvas-path <temp-dir>/hybrid-dag.canvas.tsx # 可选 derived Canvas(无需 CURSOR_API_KEY)
37
+ ```
38
+
39
+ `<temp-dir>` 表示平台原生临时目录;实际命令中 macOS 与 Windows 都使用本机路径。`/` 只作为 repo refs、JSON/Markdown evidence refs 和 glob 约定的稳定分隔符。
40
40
 
41
41
  完整 schema 与语义:`docs/agent-dag-runner.md`。Workflow 概览:`docs/loop-agent-harness.md`。
42
42
 
43
43
  **v2 字段**(均可选;缺失时行为同 v1):
44
44
 
45
45
  - 顶层:`objective`、`successCriteria`、`globalConstraints`、`defaults`、`skillsByRole`、`executorModels`
46
- - 每 node:`role`、`skills`、`writePolicy`、`writeSet`、`piStep`、`shell`、`outputContract`、`executor`(`cursor` | `pi` | `shell` | `static`);Pi 写入节点额外声明 `toolProfile: "write"`
46
+ - 每 node:`role`、`skills`、`writePolicy`、`writeSet`、`piStep`、`shell`、`outputContract`、`executor`(`cursor` | `pi` | `shell` | `static`);Pi 写入节点额外声明 `toolProfile: "write"`
47
47
 
48
48
  **Model 生成 DAG 的 template 卫生**:
49
49
 
@@ -53,19 +53,19 @@ loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --init-only --canvas-path <t
53
53
  - 输出独立时优先 same-rank parallel read-only scout(`scout-src`、`scout-tests` 等),而非 serial scout chain。
54
54
  - 仅当 child 真正需要 upstream output 时加 `depends_on`;review 时质疑 single-chain topology。
55
55
  - `exclusive` implementer node 需 narrow、disjoint 的 `writeSet` path;勿用 `**` 或 repo root。
56
- - 默认 no-Cursor DAG 使用 `pi` read-only scouts/reviewers 与 `toolProfile: "write"` exclusive implementer;Cursor 是显式启用的可选 scout / writer backend。
56
+ - 默认 no-Cursor DAG 使用 `pi` read-only scouts/reviewers 与 `toolProfile: "write"` exclusive implementer;Cursor 是显式启用的可选 scout / writer backend。
57
57
  - model routing 用 `executorModels`;勿用 `defaults.model` 或 legacy 顶层 `models`。
58
58
 
59
59
  **运维 warning**:
60
60
 
61
- - **常规 validation**:`dag validate --dag <path>` 做 schema/topology/ranks。JSON 输出含 `governanceProfile`(确定性 `minimal|standard|reviewed|supervised` 推断,含 `process` / `delivery` / `codeChange` signal 与 `reasons`),及 model-matrix drift、governance lint(如 read-only artifact-boundary drift 或 DAG 内 `check-repo.sh` shell env drift)的 warnings。手写临时 DAG spec 执行前用 `dag validate --dag <path> --strict-models`;governance warning 应 fail fast 时加 `--strict-governance`。no-Cursor 环境用 `dag validate --dag <path> --forbid-executor cursor` 或 `run-dag --no-cursor` 捕获显式 Cursor 节点;默认生成 DAG 应使用 `pi` read-only / Pi write profile / shell。仅当有意在 `.harness/dag-runs/active/` 要 active run snapshot 时用 `run-dag --dry-run`。
61
+ - **常规 validation**:`dag validate --dag <path>` 做 schema/topology/ranks。JSON 输出含 `governanceProfile`(确定性 `minimal|standard|reviewed|supervised` 推断,含 `process` / `delivery` / `codeChange` signal 与 `reasons`),及 model-matrix drift、governance lint(如 read-only artifact-boundary drift 或 DAG 内 `check-repo.sh` shell env drift)的 warnings。手写临时 DAG spec 执行前用 `dag validate --dag <path> --strict-models`;governance warning 应 fail fast 时加 `--strict-governance`。no-Cursor 环境用 `dag validate --dag <path> --forbid-executor cursor` 或 `run-dag --no-cursor` 捕获显式 Cursor 节点;默认生成 DAG 应使用 `pi` read-only / Pi write profile / shell。仅当有意在 `.harness/dag-runs/active/` 要 active run snapshot 时用 `run-dag --dry-run`。
62
62
  - **Governance profile 推断与 routing(code vs skill 分工)**:`./src/workflows/dag/governance-profile.ts` 从 DAG 结构与 write scope 做 **硬确定性推断**。JSON 输出 **报告** `process` / `delivery` / `codeChange` signal 与人类可读 `reasons`;`profile` tier(`minimal|standard|reviewed|supervised`)仅由该模块 code rule 选择(如多个 exclusive writer、repair node、review-gate topology、`loop-agent-runtime-paths`、`scripts-ci-harness-paths`、weak post-implementation shell verification、supervised topology)。baseline `forbiddenPaths`(`.harness/**`、`.harness/dag-runs/**`、`artifacts/**`)是默认 governance,**本身不是** process-risk signal。skill prompt 与本 reference **解释** tier 并摘要 profile 选择原因;不替代 code 推断。`dag run-task` 转发 embedded validate step 的同一 candidate `governanceProfile`。`dag run-task --profile auto` 先将 candidate profile 经 `harness.json.workflowPolicy.dag.profileRouting` 映射,再在 candidate delivery signal 含 `loop-agent-runtime-paths`、`scripts-ci-harness-paths` 或 `public-contract-paths` 时应用 M4 `supervised-quality-gate` promotion;`profileRouting.routingReasons` 记录确定性 reason。无 profile `dag run-task <task-id>` 仍为 standard-compatible;显式 `--profile minimal|standard|reviewed|supervised` 强制对应 template family(当前 policy 下 minimal/standard 路由到 `standard-dag`),高风险 task 应用 `--profile auto` 或显式 `--profile supervised`,而非显式 `--profile reviewed`。
63
- - **Executor model routing**:DAG spec 选 `executor` 与 `complexity`,可通过 `executorModels` 覆盖 `cursor` / `pi` 的 model 名;不选 provider。默认 routing:Cursor 各 complexity 用 `composer-2.5`;Pi read-only 与 Pi write profile 共用 LOW=`wizard-local/gpt-5.3-codex-spark`、MED=`wizard-local/glm-5.2`、HIGH=`wizard-local/gpt-5.5`。`shell` 不用 model,忽略 `executorModels`。
63
+ - **Executor model routing**:DAG spec 选 `executor` 与 `complexity`,可通过 `executorModels` 覆盖 `cursor` / `pi` 的 model 名;不选 provider。默认 routing:Cursor 各 complexity 用 `composer-2.5`;Pi read-only 与 Pi write profile 共用 LOW=`wizard-local/gpt-5.3-codex-spark`、MED=`wizard-local/glm-5.2`、HIGH=`wizard-local/gpt-5.5`。`shell` 不用 model,忽略 `executorModels`。
64
64
  - **Active visibility**:真实 `run-dag` execution 在 run/node 转换时写 active `state.json`,归档前 core runner 暴露 isolated `DagRunObserver` hook 供 derived view。`.harness/dag-runs/completed/<run-id>/` / `paused/<run-id>/` 仍是 source of truth;observer 输出非 canonical。
65
65
  - **可选 Canvas**:传 `--canvas-path <abs-path>` 或 `--canvas <name>` 输出 derived `.canvas.tsx` live view。省略 flag 行为不变。`--init-only` + Canvas 无需 `CURSOR_API_KEY`。
66
66
 
67
67
  - **Shell node**:`executor: "shell"` 串行跑确定性 `shell.commands`,每 command 有 `timeoutMs`;非零 exit / timeout 标 node `ERROR` 并将 command output 归档到 node result 目录。用于 verification fact,非 code repair。
68
- - **Pi node**:`executor: "pi"` 默认仅用 read-only tool(当前 DAG Pi executor 中 `read`、`grep`、`find`、`ls`),返回 Markdown 结论供 downstream node。声明 `toolProfile: "write"` 后同一个 Pi executor 使用 writer tools 并在执行后跑 write guard;必须配合 `writePolicy=exclusive`、`allowedPaths`、`forbiddenPaths`、`writeSet`。
68
+ - **Pi node**:`executor: "pi"` 默认仅用 read-only tool(当前 DAG Pi executor 中 `read`、`grep`、`find`、`ls`),返回 Markdown 结论供 downstream node。声明 `toolProfile: "write"` 后同一个 Pi executor 使用 writer tools 并在执行后跑 write guard;必须配合 `writePolicy=exclusive`、`allowedPaths`、`forbiddenPaths`、`writeSet`。
69
69
  - **Root `artifacts/` boundary**:root `artifacts/修改记录.md` 与 `artifacts/验证结果.md` 是 legacy / explicit-write 摘要,不是 Agent DAG read-only scratchpad,也不是新工作流默认 handoff。read-only DAG node 须在 node output 返回发现;runner-owned node artifacts 于 `.harness/dag-runs/<run-id>/` 是 per-run source of truth。
70
70
  - **Upstream output artifacts**:直接 `depends_on` 上游 stdout 超过 2000 字符时,runner 写 `<runDir>/<node-id>/stdout.md` 并在下游 `<upstream_context>` 提供 preview + artifact pointer map(绝对路径、`chars`、`sha256`)。下游 agent 可读 runner evidence,但 read-only node 仍不得编辑 `.harness/dag-runs/**`。
71
71
  - **`writePolicy=exclusive`** 要求非空 `writeSet`;same-rank exclusive node 的 `writeSet` 条目须 **disjoint**,否则 validation fail fast。v1 DAG 中声明 `writePolicy` 或 `writeSet` 任一即 opt-in write validation。
@@ -74,7 +74,7 @@ loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --init-only --canvas-path <t
74
74
  - **Defaults caveat**:`defaults.skills` / `defaults.writePolicy` 生效。对 `cursor` / `pi` node,resolved skill 名亦由 DAG runner 映射为有界 inline `SKILL.md` instruction,审计于 `<node>/skills.json`;Pi 仍以 `noSkills` / `--no-skills` 运行,故非 Pi ResourceLoader loading。`defaults.executor`、`defaults.model`、`defaults.piBackend`、`defaults.contextProfile` 接受/保留但尚非 runtime default。runtime execution 用 node `executor` + node `complexity`;各 executor 内部自选 model。live contract 已移除 `models`;executor-specific routing 用 `executorModels`。
75
75
  - **默认无**跨 node Pi runtime reuse;各 Pi node 是独立 `executePiStep()` call。
76
76
  - **Prompt source**:每个 task 仅用一种 prompt source。v1-compatible DAG 用 inline `subtask_prompt`;markdown-backed prompt 用 canonical `subtask_prompt_markdown`。同时提供两字段、皆不提供、或用连字符 alias `subtask_prompt-markdown` 均 fail fast。
77
- - **勿宣称 live smoke 已通过**,除非真实 `run-dag` execution 中 Pi read-only、Pi writer、显式 Cursor 或 shell node 均按 DAG 完成。
77
+ - **勿宣称 live smoke 已通过**,除非真实 `run-dag` execution 中 Pi read-only、Pi writer、显式 Cursor 或 shell node 均按 DAG 完成。
78
78
 
79
79
  可复用 template:`docs/templates/agent-dag.base.json`(model 生成 DAG 的首选 base template)、`docs/templates/agent-dag.schema.json`(JSON Schema)、`docs/templates/agent-dag.supervised-implementation.json`(supervised implementation:writeSet audit、soft/hard verify、process supervisor、repair、review verdict gate)、`docs/templates/agent-dag-process-supervisor.prompt.md`、`docs/templates/agent-dag-review-verdict.prompt.md`、`docs/templates/agent-dag-authority-surface-audit.prompt.md`(可选 authority surface verifier;authority signal 或显式 enablement 匹配时由 `dag init-hybrid` 插入)、`examples/hybrid-loop-agent-dag.json`、`docs/templates/hybrid-dag.json`。
80
80
 
@@ -87,9 +87,9 @@ loop-agent run-dag --dag <temp-dir>/hybrid-dag.json --init-only --canvas-path <t
87
87
  **Supervised topology**(执行前替换所有 `REPLACE/WITH/...` placeholder):
88
88
 
89
89
  ```text
90
- contract-pi → scout-src ∥ scout-tests → plan-pi → write-set-audit-pi
91
- → write-set-gate-shell → implement-pi → soft-verify-shell → process-supervisor-pi → process-gate-shell
92
- → repair-pi → hard-verify-shell
90
+ contract-pi → scout-src ∥ scout-tests → plan-pi → write-set-audit-pi
91
+ → write-set-gate-shell → implement-pi → soft-verify-shell → process-supervisor-pi → process-gate-shell
92
+ → repair-pi → hard-verify-shell
93
93
  → [authority-surface-audit-pi → authority-surface-gate-shell] # 可选
94
94
  → review-pi → review-gate-shell → decision-pi → closeout-pi
95
95
  ```
@@ -101,7 +101,7 @@ contract-pi → scout-src ∥ scout-tests → plan-pi → write-set-audit-pi
101
101
  | `soft-verify-shell` | supervision 前归档 focused test exit code |
102
102
  | `process-supervisor-pi` | read-only audit coverage、boundary drift、verify gap、repair scope;应 prominently 输出 `VERDICT: pass` 或 `VERDICT: request-revision` |
103
103
  | `process-gate-shell` | supervisor node JSON 上 runtime `shell.verdictGate`(仅 `pass` 或 `request-revision`) |
104
- | `repair-pi` / optional `repair-cursor` | supervisor 请求 revision 时在 repair `writeSet` 内 bounded exclusive fix |
104
+ | `repair-pi` / optional `repair-cursor` | supervisor 请求 revision 时在 repair `writeSet` 内 bounded exclusive fix |
105
105
  | `hard-verify-shell` | lint/typecheck + `HARNESS_ALLOW_ACTIVE_DAG_RUNS=1 check-repo.sh` fact |
106
106
  | `authority-surface-audit-pi` + `authority-surface-gate-shell` | 可选 permission/state/tool-exposure audit;仅 authority signal 或显式 `authority-surface-audit` marker 时插入;gate 仅接受 `VERDICT: pass` |
107
107
  | `review-pi` + `review-gate-shell` | Critical/Important → `request-revision`;node JSON 上 `shell.verdictGate` block,除非 extracted verdict 行为 `VERDICT: pass` |
@@ -114,16 +114,16 @@ Prompt invariant:`docs/templates/agent-dag-process-supervisor.prompt.md`、`do
114
114
 
115
115
  ### Level 3 task-to-DAG(`dag init-hybrid` / `dag run-task`)
116
116
 
117
- ```bash
118
- loop-agent dag init-hybrid <task-id> [--output <temp-dir>/<task-id>-hybrid-dag.json]
119
- loop-agent dag run-task <task-id> [--output <temp-dir>/<task-id>-hybrid-dag.json] # 安全默认:仅 generate + validate,standard-compatible
117
+ ```bash
118
+ loop-agent dag init-hybrid <task-id> [--output <temp-dir>/<task-id>-hybrid-dag.json]
119
+ loop-agent dag run-task <task-id> [--output <temp-dir>/<task-id>-hybrid-dag.json] # 安全默认:仅 generate + validate,standard-compatible
120
120
  loop-agent dag run-task <task-id> --profile auto # 推断 candidate governanceProfile,再经 workflowPolicy 路由
121
121
  loop-agent dag run-task <task-id> --profile minimal # 强制当前 minimal 路由(standard-dag)
122
122
  loop-agent dag run-task <task-id> --profile standard # 强制 standard-dag
123
123
  loop-agent dag run-task <task-id> --profile reviewed # 强制 review-gated DAG
124
124
  loop-agent dag run-task <task-id> --profile supervised # 强制 supervised implementation DAG
125
125
  loop-agent dag run-task <task-id> --strict-models # 非 canonical executorModels 时失败
126
- loop-agent dag run-task <task-id> --no-cursor # 显式 no-Cursor 校验;generated cursor node 时失败
126
+ loop-agent dag run-task <task-id> --no-cursor # 显式 no-Cursor 校验;generated cursor node 时失败
127
127
  loop-agent dag run-task <task-id> --execute --cwd <repo-root> # 要求 narrowed implement writeSet
128
128
  loop-agent dag run-task <task-id> --dry-run --cwd <repo-root> # active snapshot 于 .harness/dag-runs/active/
129
129
  loop-agent dag run-task <task-id> --init-only --cwd <repo-root> # pending active snapshot,不执行 node
@@ -135,7 +135,7 @@ loop-agent dag run-task <task-id> --init-only --cwd <repo-root>
135
135
 
136
136
  ### DAG 与 artifacts source-of-truth 规则
137
137
 
138
- - 临时 DAG input spec 放平台原生临时目录(例如 `<temp-dir>/<topic>-dag.json`);可复用 template 放 `examples/` 或 `docs/templates/`。
138
+ - 临时 DAG input spec 放平台原生临时目录(例如 `<temp-dir>/<topic>-dag.json`);可复用 template 放 `examples/` 或 `docs/templates/`。
139
139
  - **不要**在 `.harness/dag-runs/active/` root 保留手写 DAG input 副本。
140
140
  - **不要**把 `.harness/dag-runs/` 内容 commit 到 git。
141
141
  - canonical per-run DAG 历史是 `.harness/dag-runs/completed/<run-id>/run.json` 及该 run 目录的 `state.json`、`executor.jsonl`、node artifacts;新建 run directory 使用 `YYYYMMDD-<slug>`。
@@ -161,7 +161,7 @@ loop-agent dag doctor
161
161
  loop-agent dag status --run-id <run-id>
162
162
  loop-agent dag report --paused-latest [--json|--markdown] # 最新 paused run;勿与 --lifecycle 并用
163
163
  loop-agent dag report [--run-id <run-id>] [--lifecycle active|paused|completed|all] [--json|--markdown] [--failed-only] [--latest] [--action <recovery-action>] # derived per-node report(只读);JSON schema: docs/templates/agent-dag-report.schema.json;仅 advisory — 见 docs/agent-dag-recovery-playbook.md
164
- loop-agent dag closeout-draft [--run-id <run-id>] [--output <path>] # M5:从 completed run facts 生成确定性 closeout draft;默认平台临时目录;仅 advisory;不 mutate completed facts
164
+ loop-agent dag closeout-draft [--run-id <run-id>] [--output <path>] # M5:从 completed run facts 生成确定性 closeout draft;默认平台临时目录;仅 advisory;不 mutate completed facts
165
165
  loop-agent promote-run <task-id> --run-id <run-id> # 从 completed DAG/one-shot evidence 汇总 task artifacts;不 mutate completed facts
166
166
  loop-agent closeout task <task-id> # 从 task artifacts 生成 docs/progress closeout
167
167
  loop-agent dag reconcile-tasks --glob '<pattern>' [--json|--markdown] # 仅报告的 task/run/artifact/verify drift audit
@@ -211,6 +211,6 @@ review-heavy DAG 中长 shell stdout 可能掩盖 proof 时,用 **evidence-sum
211
211
  | 10 | writeSet planning | scout 应列出链接的 `./skill/references/**` 为 **writeSet expansion candidates**(P2:遗漏链接 skill ref 迫使 main-session patch) |
212
212
  | 11 | Evidence summary | `evidence-summary-shell` / leading `EVIDENCE:` 行是 **practice convention**,非 runtime executor、schema field 或 parser |
213
213
  | 12 | Featureization | 除非 repeated real-run failure 证明 checklist guidance 不够,勿加 runtime/schema/validator/CLI/executor feature |
214
- | 13 | writeSet / writer backend | `exclusive` node 用 narrow、disjoint path;无 `**`;默认用 Pi write profile,仅在显式启用且 task-fit 时用 Cursor |
214
+ | 13 | writeSet / writer backend | `exclusive` node 用 narrow、disjoint path;无 `**`;默认用 Pi write profile,仅在显式启用且 task-fit 时用 Cursor |
215
215
  | 14 | Placeholders | 执行前将 `REPLACE/WITH/...` 换为具体 path |
216
216
  | 15 | Governance | in-flight shell:`HARNESS_ALLOW_ACTIVE_DAG_RUNS=1 bash scripts/check-repo.sh`;archive 后:裸 `bash scripts/check-repo.sh` |
@@ -17,7 +17,7 @@
17
17
 
18
18
  Agent DAG node 的模型来自 DAG JSON 中的 `executorModels`,并由 `dag validate --strict-models` 检查 canonical matrix 漂移。若变更模型配置,须同步更新 `harness.json`、相关测试、repo docs 与本 skill。
19
19
 
20
- `pi-prompt` 是独立 one-shot helper,不使用 `harness.json.models` 或 DAG `executorModels`。当前默认是 `wizard-local/glm-5.2`;高复杂度 one-shot 显式传 `--model gpt-5.5`。Agent DAG `pi` executor 的 canonical matrix 保持;读写 profile 共用同一矩阵:
20
+ `pi-prompt` 是独立 one-shot helper,不使用 `harness.json.models` 或 DAG `executorModels`。当前默认是 `wizard-local/glm-5.2`;高复杂度 one-shot 显式传 `--model gpt-5.5`。Agent DAG `pi` executor 的 canonical matrix 保持;读写 profile 共用同一矩阵:
21
21
 
22
22
  ```json
23
23
  {
@@ -98,7 +98,7 @@ main session 编排;不是默认 implementer。in-flight run 期间:
98
98
  | Inspect status / node artifacts | 始终允许 | progress 或 sidecar output 中的 notes |
99
99
  | Sidecar read-only Pi/Cursor prompt | 诊断、plan critique、log 解读 | resume 前的 findings |
100
100
  | Surgical patch | small、obvious、可 verify;无 active `writeSet` 冲突 | `docs/reports/` 或 exec plan,含 scope + verification |
101
- | DAG/source repair | topology、writeSet 或 prompt contract 错误 | 编辑平台临时目录中的 DAG 或 plan;re-validate;rerun |
101
+ | DAG/source repair | topology、writeSet 或 prompt contract 错误 | 编辑平台临时目录中的 DAG 或 plan;re-validate;rerun |
102
102
  | Approve/reject/resume | Decision Gate `pause-on-human` | 仅 CLI artifacts |
103
103
  | Post-DAG closeout | promotion、report、plan archive、indexes | `promote-run`、`closeout task`、`docs/reports/`、`docs/progress`、exec-plan indexes — 非 root `artifacts/`,除非 explicit narrow writeSet |
104
104
 
@@ -1,22 +1,22 @@
1
1
  # One-shot Pi SDK Prompt Helper(`pi-prompt`)
2
2
 
3
- 短时 Pi SDK task、不需要完整 `.harness/tasks/<id>` workflow 时使用本文。替代 ad-hoc 临时代码脚本导入 `executeSingleSdkAttempt` 的做法。
3
+ 短时 Pi SDK task、不需要完整 `.harness/tasks/<id>` workflow 时使用本文。替代 ad-hoc 临时代码脚本导入 `executeSingleSdkAttempt` 的做法。
4
4
 
5
5
  ### One-shot Pi SDK prompt helper
6
6
 
7
- 短时 Pi SDK task、不需要完整 `.harness/tasks/<id>` workflow 时,用 `loop-agent pi-prompt`,勿创建 ad-hoc 临时代码脚本导入 `executeSingleSdkAttempt`。`pi-prompt` 是一次性 full-capability helper;是否只读由本次调用的 prompt 与 `--tools` 决定。
7
+ 短时 Pi SDK task、不需要完整 `.harness/tasks/<id>` workflow 时,用 `loop-agent pi-prompt`,勿创建 ad-hoc 临时代码脚本导入 `executeSingleSdkAttempt`。`pi-prompt` 是一次性 full-capability helper;是否只读由本次调用的 prompt 与 `--tools` 决定。
8
8
 
9
9
  ```bash
10
- loop-agent pi-prompt "Reply with exactly OK."
11
- loop-agent pi-prompt --stdin < <temp-dir>/task.md
12
- loop-agent pi-prompt --file <temp-dir>/task.md
13
- loop-agent pi-prompt --cwd ~/go/src/loop-agent --tools read,grep,find,ls "Review the current diff. Do not edit files."
10
+ loop-agent pi-prompt "Reply with exactly OK."
11
+ loop-agent pi-prompt --stdin < <temp-dir>/task.md
12
+ loop-agent pi-prompt --file <temp-dir>/task.md
13
+ loop-agent pi-prompt --cwd ~/go/src/loop-agent --tools read,grep,find,ls "Review the current diff. Do not edit files."
14
14
  loop-agent pi-prompt --cwd ~/go/src/loop-agent --tools subagent,read --timeout 2400000 "Use subagent exactly once ..."
15
15
  loop-agent pi-prompt --model gpt-5.5 --cwd ~/go/src/loop-agent "Deeply diagnose this failure."
16
16
  loop-agent pi-prompt "Reply with exactly OK."
17
- ```
18
-
19
- `<temp-dir>` 表示平台原生临时目录;实际命令中使用本机路径。
17
+ ```
18
+
19
+ `<temp-dir>` 表示平台原生临时目录;实际命令中使用本机路径。
20
20
 
21
21
  默认:`--provider wizard-local --model glm-5.2`;高复杂度 one-shot 可显式 `--model gpt-5.5`。按需用 `--provider`、`--model`、`--thinking`、`--tools`、`--timeout` 覆盖。
22
22
 
@@ -22,13 +22,13 @@ DAG run、promotion、closeout 和最终验证完成后:
22
22
  ```
23
23
  1. new-task <id>
24
24
  2. 写 source/需求.md + source/执行约束.md
25
- 3. dag run-task <id> --profile auto --strict-models --output <temp-dir>/<id>-dag.json
26
- 4. dag validate --dag <temp-dir>/<id>-dag.json --strict-models --strict-governance
27
- 5. run-dag --dag <temp-dir>/<id>-dag.json --cwd <repo-root>
28
- 6. promote-run / closeout / final verification
29
- ```
30
-
31
- `<temp-dir>` 表示平台原生临时目录;实际命令中使用 macOS/Windows 本机路径。
25
+ 3. dag run-task <id> --profile auto --strict-models --output <temp-dir>/<id>-dag.json
26
+ 4. dag validate --dag <temp-dir>/<id>-dag.json --strict-models --strict-governance
27
+ 5. run-dag --dag <temp-dir>/<id>-dag.json --cwd <repo-root>
28
+ 6. promote-run / closeout / final verification
29
+ ```
30
+
31
+ `<temp-dir>` 表示平台原生临时目录;实际命令中使用 macOS/Windows 本机路径。
32
32
 
33
33
  **关键**:实现 work 由 DAG node 和 executor 执行;main session 负责审 DAG、审 writeSet、跑验证和 handoff。
34
34
 
@@ -6,18 +6,18 @@
6
6
 
7
7
  所有需要可恢复、可验证、可交接的实现工作都走 DAG 路径:
8
8
 
9
- ```bash
10
- loop-agent new-task <task-id> "Task Title"
11
- loop-agent dag run-task <task-id> --profile auto --strict-models --output <temp-dir>/<task-id>-dag.json
12
- loop-agent dag validate --dag <temp-dir>/<task-id>-dag.json --strict-models --strict-governance
13
- loop-agent run-dag --dag <temp-dir>/<task-id>-dag.json --cwd <repo-root>
14
- ```
15
-
16
- `<temp-dir>` 表示平台原生临时目录。实际文件路径必须兼容 macOS 和 Windows;只有 repo refs、JSON/Markdown 证据 refs 和 glob 约定默认使用 `/`。
17
-
18
- 当目标仓库是 loop-agent 本仓库时,`loop-agent` 命令必须来自 npm 上已发布的安装包。首次安装或有意升级可用 `@tea-agent/loop-agent@latest`,但一次自举任务启动后不要中途升级控制器,并记录 `npm list -g @tea-agent/loop-agent --depth=0` 显示的实际版本。不要用当前工作区的 `npm link` 或 `npm run dev` 控制会改动 CLI、DAG runtime、executor、package metadata 或 build output 的任务;源码开发和 focused debugging 才使用 `npm run dev -- <args>`。
19
-
20
- 低风险的一行修正文档或配置时,可以由 main session 做 surgical patch,但仍必须记录 scope 并运行对应验证命令。
9
+ ```bash
10
+ loop-agent new-task <task-id> "Task Title"
11
+ loop-agent dag run-task <task-id> --profile auto --strict-models --output <temp-dir>/<task-id>-dag.json
12
+ loop-agent dag validate --dag <temp-dir>/<task-id>-dag.json --strict-models --strict-governance
13
+ loop-agent run-dag --dag <temp-dir>/<task-id>-dag.json --cwd <repo-root>
14
+ ```
15
+
16
+ `<temp-dir>` 表示平台原生临时目录。实际文件路径必须兼容 macOS 和 Windows;只有 repo refs、JSON/Markdown 证据 refs 和 glob 约定默认使用 `/`。
17
+
18
+ 当目标仓库是 loop-agent 本仓库时,`loop-agent` 命令必须来自 npm 上已发布的安装包。首次安装或有意升级可用 `@tea-agent/loop-agent@latest`,但一次自举任务启动后不要中途升级控制器,并记录 `npm list -g @tea-agent/loop-agent --depth=0` 显示的实际版本。不要用当前工作区的 `npm link` 或 `npm run dev` 控制会改动 CLI、DAG runtime、executor、package metadata 或 build output 的任务;源码开发和 focused debugging 才使用 `npm run dev -- <args>`。
19
+
20
+ 低风险的一行修正文档或配置时,可以由 main session 做 surgical patch,但仍必须记录 scope 并运行对应验证命令。
21
21
 
22
22
  ## Source Materials
23
23
 
@@ -75,10 +75,10 @@ loop-agent --repo-root /path/to/target-repo <command>
75
75
  完成声明必须来自新鲜验证证据。按目标 repo 的 `docs/verification-matrix.md` 选择最小证明命令;loop-agent 自身常用:
76
76
 
77
77
  ```bash
78
- npm run typecheck
79
- npm test
80
- bash scripts/check-repo.sh
81
- bash scripts/ci.sh
82
- ```
83
-
84
- Windows 上通过 Git Bash 或配置好的兼容 Bash 运行 `scripts/*.sh`;不要把 POSIX 路径假设写入 CLI、模板或 task source。
78
+ npm run typecheck
79
+ npm test
80
+ bash scripts/check-repo.sh
81
+ bash scripts/ci.sh
82
+ ```
83
+
84
+ Windows 上通过 Git Bash 或配置好的兼容 Bash 运行 `scripts/*.sh`;不要把 POSIX 路径假设写入 CLI、模板或 task source。
@@ -4,6 +4,40 @@
4
4
 
5
5
  ## Verify strategy 与 completion audit
6
6
 
7
+ ## Production Readiness v0.1
8
+
9
+ 低/中风险单 repo DAG 任务如果声明 production-ready v0.1,必须按 `docs/production-readiness.md` 和 `docs/templates/production-readiness-checklist.md` 收口。
10
+
11
+ 支持范围:
12
+
13
+ - single repo
14
+ - bounded task
15
+ - explicit task source
16
+ - explicit `allowedPaths` / `forbiddenPaths` / write scope
17
+ - shell verification
18
+ - report / doctor / closeout handoff
19
+
20
+ 非目标:
21
+
22
+ - automatic merge
23
+ - automatic release
24
+ - production secrets
25
+ - production database
26
+ - high-risk migration
27
+ - online Worker Pool
28
+ - writable Dynamic Workflow sharded migration
29
+
30
+ 失败分类是路由字段,不是主状态;不要覆盖 `.harness/dag-runs/completed/**` 的原始事实。报告和 handoff 应保留:
31
+
32
+ ```text
33
+ raw_failure_category
34
+ dag_normalized_failure_category
35
+ product_line_failure_category
36
+ recommended_follow_up
37
+ ```
38
+
39
+ product-line taxonomy 的事实源是 `docs/design/state-and-failure-taxonomy.md`。
40
+
7
41
  ### Verify 始终在本地跑
8
42
  `verify` step 跑确定性命令(check-repo.sh + tests + typecheck)。**不**调用 pi。因此快且可靠。
9
43
 
@@ -90,3 +124,5 @@ loop-agent handoff check <task-id>
90
124
  ```
91
125
 
92
126
  active exec plan 实质完成时,用 `docs archive` 归档并更新 active/completed 索引,勿留 stale active status。
127
+
128
+ failed DAG run 不应生成成功式 closeout。它应该生成 failure handoff,至少包含 what failed、evidence、classification、recommended follow-up、safe retry conditions 和 human decision needed。
@@ -0,0 +1,20 @@
1
+ ---
2
+ name: test-driven-development
3
+ description: 用于需要回归覆盖的行为变更与 bug 修复。保持小循环:写失败测试 → 变绿 → 仅在 green 后 refactor。
4
+ ---
5
+
6
+ # Test-Driven Development
7
+
8
+ 本 skill 用于会改变 runtime 行为的 implementation 节点。
9
+
10
+ ## 规则
11
+
12
+ - 行为是新增或已损坏时,在 production code 之前写或更新聚焦测试。
13
+ - 运行聚焦测试,确认因预期原因失败。
14
+ - 做最小实现变更使测试变绿。
15
+ - refactor 仅在 green 之后,且仍在同一 bounded write set 内。
16
+ - 能测真实本地 module 时,不要用 broad mock。
17
+
18
+ ## Output
19
+
20
+ 报告 red 命令、green 命令,以及仍需要的 broader verification。
@@ -0,0 +1,19 @@
1
+ ---
2
+ name: webapp-testing
3
+ description: 任务明确涉及 browser 渲染行为时,用于前端或本地 web UI 验证。
4
+ ---
5
+
6
+ # Webapp Testing
7
+
8
+ 仅当任务包含 browser UI 或本地 web app 时使用本 skill。
9
+
10
+ ## 规则
11
+
12
+ - 优先使用项目现有的 dev server 与 test tooling。
13
+ - 当 visual 或 interaction 行为重要时,用 browser 或文档化的 UI test 命令验证渲染行为。
14
+ - UI 有变更时,检查 desktop 与 mobile 布局的 overlap、clipping、blank state。
15
+ - 默认不添加 networked services 或第三方 scan。
16
+
17
+ ## Output
18
+
19
+ 报告确切的 server 命令、URL、browser/test 命令与观察结果。