@tea-agent/loop-agent 0.14.0 → 0.16.0

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 (117) hide show
  1. package/AGENTS.md +1 -1
  2. package/CHANGELOG.md +98 -11
  3. package/README.md +24 -5
  4. package/dist/application/evaluation/alias.js +184 -0
  5. package/dist/application/evaluation/budget.js +192 -0
  6. package/dist/application/evaluation/campaign-hash.js +47 -0
  7. package/dist/application/evaluation/campaign-matrix.js +372 -0
  8. package/dist/application/evaluation/campaign-scorecard.js +135 -0
  9. package/dist/application/evaluation/campaign.js +370 -0
  10. package/dist/application/evaluation/candidate.js +23 -6
  11. package/dist/application/evaluation/corpus-hash.js +38 -0
  12. package/dist/application/evaluation/corpus.js +56 -0
  13. package/dist/application/evaluation/experiment.js +294 -0
  14. package/dist/application/evaluation/ignition.js +198 -0
  15. package/dist/application/evaluation/integrity-audit.js +162 -0
  16. package/dist/application/evaluation/outer-loop.js +132 -0
  17. package/dist/application/evaluation/pi-cell-executor.js +39 -0
  18. package/dist/application/evaluation/private-verifier.js +46 -0
  19. package/dist/application/evaluation/promotion-policy.js +151 -0
  20. package/dist/application/evaluation/proposer.js +98 -0
  21. package/dist/application/evaluation/types.js +522 -0
  22. package/dist/cli/command-definitions.js +19 -3
  23. package/dist/commands/eval.js +1176 -13
  24. package/dist/commands/init.js +4 -1
  25. package/dist/infrastructure/evaluation/alias-store.js +199 -0
  26. package/dist/infrastructure/evaluation/campaign-store.js +154 -0
  27. package/dist/infrastructure/evaluation/corpus-store.js +181 -0
  28. package/dist/infrastructure/evaluation/experiment-store.js +124 -0
  29. package/dist/infrastructure/evaluation/ignition-store.js +82 -0
  30. package/dist/infrastructure/evaluation/private-verifier-store.js +145 -0
  31. package/dist/infrastructure/evaluation/proposer-store.js +78 -0
  32. package/dist/worker/cli.js +6 -3
  33. package/dist/worker/delivery/final-verification.js +96 -8
  34. package/dist/worker/delivery/package.js +23 -4
  35. package/dist/worker/delivery/verification-bundle.js +521 -0
  36. package/dist/worker/feature/fullstack-validate.js +337 -0
  37. package/dist/worker/feature/profile-schema.js +44 -0
  38. package/dist/worker/feature/ready-plan-projection.js +1 -0
  39. package/dist/worker/feature/reducer.js +2 -0
  40. package/dist/worker/feature/review.js +106 -11
  41. package/dist/worker/materialize/harness-task-materializer.js +5 -0
  42. package/dist/worker/observability/read-model.js +7 -0
  43. package/dist/worker/observe/static/views/task.js +1 -0
  44. package/dist/worker/outcomes/adapters.js +144 -0
  45. package/dist/worker/outcomes/evidence-tokens.js +29 -0
  46. package/dist/worker/outcomes/gate.js +40 -0
  47. package/dist/worker/outcomes/projector.js +185 -0
  48. package/dist/worker/outcomes/registry.js +1 -0
  49. package/dist/worker/outcomes/store.js +131 -0
  50. package/dist/worker/outcomes/types.js +79 -0
  51. package/dist/worker/report/morning-report.js +4 -3
  52. package/dist/worker/run-task/run-task.js +85 -2
  53. package/dist/worker/runner/run-ready.js +32 -1
  54. package/dist/worker/task-graph/acceptance-schema.js +12 -0
  55. package/dist/worker/task-graph/ready-planner.js +131 -0
  56. package/dist/worker/task-graph/task-graph-schema.js +31 -0
  57. package/dist/worker/task-graph/validate.js +44 -4
  58. package/dist/worker/task-spec/schema.js +9 -0
  59. package/dist/worker/task-spec/validate.js +39 -0
  60. package/dist/worker/task-spec/workflow-routing.js +149 -0
  61. package/dist/workflows/dag/budget-enforcement.js +67 -0
  62. package/dist/workflows/dag/context-policy.js +137 -0
  63. package/dist/workflows/dag/init-hybrid.js +27 -11
  64. package/dist/workflows/dag/knowledge-curator.js +3 -0
  65. package/dist/workflows/dag/node-execution.js +11 -4
  66. package/dist/workflows/dag/prompt.js +1 -1
  67. package/dist/workflows/dag/runner.js +43 -16
  68. package/dist/workflows/dag/skill-snapshot.js +11 -7
  69. package/dist/workflows/dag/types.js +18 -0
  70. package/docs/README.md +1 -0
  71. package/docs/init-surface.manifest.json +7 -7
  72. package/docs/templates/branch-merge-report.md +0 -1
  73. package/docs/templates/evaluation/campaign-budget-v1.json +12 -0
  74. package/docs/templates/evaluation/campaign-dogfood-v0.json +24 -0
  75. package/docs/templates/evaluation/campaign-evidence-v1.json +44 -0
  76. package/docs/templates/evaluation/context-policy-baseline-v1.json +17 -0
  77. package/docs/templates/evaluation/context-policy-role-specialized-v1.json +28 -0
  78. package/docs/templates/evaluation/corpus-dogfood-v0.manifest.json +118 -0
  79. package/docs/templates/evaluation/matrix-dag-dry-run-v1.json +21 -0
  80. package/docs/templates/evaluation/matrix-fixture-v1.json +10 -0
  81. package/docs/templates/evaluation/private-verifier-dogfood-v0.json +16 -0
  82. package/docs/templates/product-line/AGENTS.md +1 -0
  83. package/docs/templates/product-line/README.md +17 -0
  84. package/docs/templates/product-line/acceptance.yaml +9 -0
  85. package/docs/templates/product-line/feature.yaml +11 -0
  86. package/docs/templates/product-line/task-graph.yaml +8 -0
  87. package/docs/templates/product-line/task.yaml +4 -0
  88. package/package.json +6 -16
  89. package/skills/browser-tools/SKILL.md +2 -2
  90. package/skills/frontend-design-review/references/review-checklist.md +27 -45
  91. package/skills/frontend-implementation/references/node-contracts.md +4 -4
  92. package/skills/frontend-review/SKILL.md +3 -1
  93. package/skills/frontend-review/references/review-findings.md +2 -1
  94. package/skills/frontend-verification/SKILL.md +3 -1
  95. package/skills/frontend-verification/references/verification-checklist.md +13 -22
  96. package/skills/loop-agent/references/hybrid-dag.md +1 -1
  97. package/docs/agent-dag-recovery-playbook.md +0 -195
  98. package/docs/agent-dag-runner.md +0 -67
  99. package/docs/cursor-prompt-sidecar.md +0 -36
  100. package/docs/decisions/README.md +0 -18
  101. package/docs/design/README.md +0 -167
  102. package/docs/development-principles.md +0 -73
  103. package/docs/exec-plans/README.md +0 -6
  104. package/docs/exec-plans/active/README.md +0 -13
  105. package/docs/exec-plans/completed/README.md +0 -108
  106. package/docs/feature-workflow.md +0 -414
  107. package/docs/loop-agent-harness.md +0 -142
  108. package/docs/production-readiness.md +0 -96
  109. package/docs/progress/README.md +0 -81
  110. package/docs/reports/README.md +0 -163
  111. package/docs/verification-matrix.md +0 -70
  112. package/scripts/check-product-line-docs.sh +0 -29
  113. package/scripts/check-task-pool-root.sh +0 -32
  114. package/scripts/kb-graph-incremental-prepare.sh +0 -5
  115. package/scripts/kb-graph-materialize.sh +0 -4
  116. package/scripts/kb-graph-promote.sh +0 -4
  117. package/scripts/kb-query.sh +0 -5
@@ -1,18 +0,0 @@
1
- # 决策
2
-
3
- 本目录存放架构决策记录(ADR)。模板见 `docs/templates/adr.md`。
4
-
5
- ## 索引
6
-
7
- | ADR | 状态 | 摘要 |
8
- | --- | --- | --- |
9
- | [`0001-pi-only-agent-runtime.md`](0001-pi-only-agent-runtime.md) | accepted | 受治理 Agent 仅 Pi;`cursor-prompt` 为显式 sidecar |
10
- | [`0002-task-pool-runtime-root.md`](0002-task-pool-runtime-root.md) | accepted | Task Pool 唯一根 `.harness/task-pool/`,旧 `.task-pool/` 不兼容 |
11
- | [`0003-docs-dual-tree-converge.md`](0003-docs-dual-tree-converge.md) | accepted | `website/docs/` 用法 vs `docs/` 治理;docs-converge 检查表 |
12
- | [`0004-task-pool-feature-scoped-task-identity.md`](0004-task-pool-feature-scoped-task-identity.md) | accepted | Task Pool 复合身份 `{featureId,taskId}`、state v2、legacy fail-closed、Observe composite route |
13
-
14
- **读者注意(M4)**:ADR 0004 **决策边界**仍有效;正文中「M2+ 未改 consumers/Observe」段落是 M0/M1 当时的切片叙述,现已过时。实现进度以 `docs/progress/2026-07-15-task-pool-v2-feature-scoped-task-identity.md`、最终报告 `docs/reports/2026-07-15-task-pool-v2-feature-scoped-task-identity.md` 与 `CHANGELOG.md [Unreleased]` 为准。本任务 **不修改** ADR 0004 正文(不在 closeout allowedPaths)。
15
-
16
- 新增跨版本架构取舍时:用模板新增 `NNNN-title.md`,并更新本表。不要把 ADR 正文复制进 `website/docs/`。
17
-
18
- 实施细节与证据仍以对应 `docs/exec-plans/completed/` 与 `CHANGELOG.md` 为准;ADR 只固化决策边界。
@@ -1,167 +0,0 @@
1
- # 设计笔记
2
-
3
- `docs/design/` 存放将 `loop-agent` 作为更大产品线 agent 平台内仓库本地 runtime 的规划笔记。这些是设计输入,不是 `src/` 已具备该能力的证明——**除非**页首明确写了实现校准条,且有 `src/` / CHANGELOG / completed plan 旁证。
4
-
5
- **维护日:2026-07-16** — 索引与归档建议按当前代码(`@tea-agent/loop-agent@0.12.0` + 主干 Unreleased)再采样。
6
-
7
- | 文档 | 用途 |
8
- |---|---|
9
- | `taskspec-to-loop-agent-mapping.md` | 将产品线 TaskSpec 适配为 `loop-agent` task 的契约 |
10
- | `taskspec-to-loop-agent-mapping.yaml` | 同上契约的结构化对照表 |
11
- | `state-and-failure-taxonomy.md` | 文档、Task Pool、DAG、Loop 共用的 canonical status 与 failure taxonomy |
12
- | `frontend-implementation-workflow.md` | 前端 DAG 实现 / 评审 / 验证工作流与证据约定 |
13
- | `frontend-mock-data-workflow.md` | 前端任务先读取规范、识别项目 Mock 服务、生成 Mock 合同并做专项验证的已实现设计 |
14
- | `dag-source-binding-and-recovery.md` | 新生成 DAG 的权威任务源绑定、前端需求编号覆盖门禁与中断后完整重生成规则 |
15
- | `full-chain-test-knowledge-base.md` | 全流程测试知识库分层、目录、对象模型、与 backend-test-dag / Feature QA 的读写映射 |
16
- | `full-chain-testing-system-redesign.md` | **综合重设计**:知识库权威层 + I/T/V/K 四类 DAG + knowledge-sync v2 硬化与迁移 |
17
- | `testing-knowledge-base-impl-spec.md` | **知识库实现细节 v1(先冻结)**:目录、schema、ID、读写矩阵、校验规则、MVP 清单 |
18
- | `knowledge-graph-and-query-spec.md` | **业务知识图谱 + 查询协议 v1**:实体/边、knowledge-links、kb-query 分层、索引 materialize |
19
- | `knowledge-graph-ai-bootstrap.md` | **AI 构建图谱 + 初始化 B0–B6**:staging 提案、人审晋升、bootstrap DAG、增量更新 |
20
- | `verification-subdag-plugin.md` | 独立测试全流程 Verification DAG 与三种实现 DAG 的 compose 设计(若分支存在) |
21
- ## 归档策略(何时迁入 `archive/`)
22
-
23
- 满足以下**多数**条件时可归档:
24
-
25
- 1. 对应能力已在 `src/` 落地,且有 `docs/exec-plans/completed/*` 或 dated report / CHANGELOG 版本说明;
26
- 2. 文档主体是**阶段性计划 / 月度 WBS / 已关闭路线图**,不再驱动实现决策;
27
- 3. 继续放在 design 根目录会让新人误判为「未做完」或「下一件必做」。
28
-
29
- **不要归档**(仍放根目录):
30
-
31
- - 仍被代码/CLI/映射表**持续引用**的契约(taxonomy、taskspec mapping、frontend workflow 等);
32
- - 仍有 **active exec-plan** 或大段 **planned/deferred** 的设计真源(如 Eval Lab);
33
- - 长期路线与方法论笔记(六个月规划、腾讯实践、研发模式)——可加校准条,不必塞进 archive;
34
- - 纯视觉 token 参考(`DESIGN-*.md`)。
35
-
36
- ---
37
-
38
- ## 契约与实现映射(优先读 · 仍活)
39
-
40
- | 文档 | 用途 | 归档建议 |
41
- |---|---|---|
42
- | `taskspec-to-loop-agent-mapping.md` / `.yaml` | TaskSpec → loop-agent task 契约 | **保留**(随 schema 更新) |
43
- | `state-and-failure-taxonomy.md` | 状态 / failure taxonomy | **保留** |
44
- | `frontend-implementation-workflow.md` | 前端 DAG 实现/评审/验证约定 | **保留**(活工作流) |
45
- | `full-chain-test-knowledge-base.md` | 测试知识库分层与对象模型 | **保留**(K 族权威设计) |
46
- | `full-chain-testing-system-redesign.md` | I/T/V/K 综合重设计 | **保留**(后续 T/V 与 hardening 仍可能引用;MVP 已部分 ship) |
47
- | `testing-knowledge-base-impl-spec.md` | 知识库实现细节 v1 | **保留**(规格冻结;DAG 细节另文) |
48
- | `knowledge-graph-and-query-spec.md` | 图谱 + 查询协议 v1 | **保留**(Phase A 已实现,规格仍真源) |
49
- | `knowledge-graph-ai-bootstrap.md` | AI bootstrap B0–B6 / staging | **保留**(bootstrap MVP 已实现,增量/产品化仍引用) |
50
-
51
- **执行 Contract(knowledge 已完成归档):** `docs/exec-plans/completed/2026-07-14-knowledge-sync-and-graph.md`
52
-
53
- ---
54
-
55
- ## 实验 / 评测(设计输入 · 进行中)
56
-
57
- | 文档 | 用途 | 归档建议 |
58
- |---|---|---|
59
- | `recursive-self-improvement-eval-lab.md` | Harness Eval Lab 设计真源 | **保留 active**:M1 + M2 W2.1–W2.3 已实现;W2.4 / M3+ 未做。执行计划:`docs/exec-plans/active/2026-07-16-recursive-self-improvement-eval-lab.md` |
60
-
61
- > 设计 README 旧句「W2.3 仍未实现」已过时:W2.3 run association **已合入**(见 active plan 进度与 `CHANGELOG.md [Unreleased]`)。
62
-
63
- ---
64
-
65
- ## 路线与产品线笔记(非实现证明 · 保留 + 校准条)
66
-
67
- | 文档 | 用途 | 归档建议 |
68
- |---|---|---|
69
- | `dynamic-workflow-dag-engine-roadmap.md` | Dynamic Workflow 阶段规划 | **保留**:页首有落地校准;高风险 shard/merge 等仍是 roadmap |
70
- | `六个月规划.md` | 长期路线 | **保留**:页首 **2026-07-16** 已补 0.12.0 / Task Pool v2 / Ready Planner / Eval 指针;第 3–6 月仍有效前瞻 |
71
- | `产品线共享知识库.md` | 产品线文档仓库上游事实源 | **保留**(docs-sync 等仍多为未来) |
72
- | `研发模式.md` | 10 日 Feature 团队工作流 | **保留**(方法论) |
73
- | `腾讯实践对当前项目的指引.md` | 外部实践映射 | **保留**(背景;源文在 website practices) |
74
-
75
- ---
76
-
77
- ## 视觉参考(保留)
78
-
79
- | 文档 | 用途 | 归档建议 |
80
- |---|---|---|
81
- | `DESIGN-cursor.md` | Observe 暖白 / Cursor 风格 token | **保留**(视觉参考) |
82
- | `DESIGN-lovable.md` | Lovable 暖色视觉参考 | **保留** |
83
-
84
- ---
85
-
86
- ## 本次已迁入 `archive/`(2026-07-16)
87
-
88
- | 文档 | 原因 |
89
- |---|---|
90
- | `archive/2026-07-14-loop-agent-self-update-notifier.md` | 自更新提醒 **已实现**(0.11.0 + report/completed plan);设计不再是「尚未实现」 |
91
- | `archive/2026-07-16-priority-ready-planner-contract.md` | Ready Planner **已实现并 closeout**;原 M0 RED「未实现」状态条会误导 |
92
-
93
- ---
94
-
95
- ## 已归档(历史)
96
-
97
- | 文档 | 用途 |
98
- |---|---|
99
- | `archive/2026-07-07-agent-worker-plan.md` | Worker 落地计划(已实现于 `src/worker/`) |
100
- | `archive/2026-07-07-taskspec-plan.md` | TaskSpec v0.1 设计(已实现) |
101
- | `archive/2026-07-10-下一阶段任务-功能开发完成.md` | 样本/失败硬化完成记录 |
102
- | `archive/2026-07-10-observe-ui.md` | Observe UI v0(OBS-001~010) |
103
- | `archive/2026-07-10-observe-ui-optimization.md` | 中文 DAG-first / 过程时间线 |
104
- | `archive/2026-07-10-observe-ui-goal.md` | OBS 进度看板(全部 done) |
105
- | `archive/2026-07-14-observe-ui-roadmap.md` | Observe R1–R5 路线图(已完成) |
106
- | `archive/2026-07-11-第一月规划.md` / `第一月wbs.md` | 首月闭环历史 |
107
- | `archive/2026-07-12-第二月规划.md` | 第二月 Feature 闭环历史 |
108
- | `archive/2026-07-14-loop-agent-self-update-notifier.md` | CLI 自更新提醒设计(已实现) |
109
- | `archive/2026-07-16-priority-ready-planner-contract.md` | Ready Planner M0 合同(已实现) |
110
-
111
- ---
112
-
113
- ## 根目录文件 — 归档建议一览(2026-07-16)
114
-
115
- | 文件 | 建议 | 说明 |
116
- |---|---|---|
117
- | `README.md` | 保留 | 本索引 |
118
- | `taskspec-to-loop-agent-mapping.*` | 保留 | 活契约 |
119
- | `state-and-failure-taxonomy.md` | 保留 | 活契约 |
120
- | `frontend-implementation-workflow.md` | 保留 | 活工作流 |
121
- | `full-chain-test-knowledge-base.md` | 保留 | K 族设计真源 |
122
- | `full-chain-testing-system-redesign.md` | 保留(可选日后拆「已落地摘要」) | 综合草案;部分已 ship |
123
- | `testing-knowledge-base-impl-spec.md` | 保留 | 规格冻结 |
124
- | `knowledge-graph-and-query-spec.md` | 保留 | 协议真源 |
125
- | `knowledge-graph-ai-bootstrap.md` | 保留 | bootstrap 设计真源 |
126
- | `recursive-self-improvement-eval-lab.md` | **保留 active** | Eval Lab 真源 |
127
- | `dynamic-workflow-dag-engine-roadmap.md` | 保留 | roadmap + 校准 |
128
- | `六个月规划.md` | 保留 | 路线;校准条已含 0.12 / Unreleased |
129
- | `产品线共享知识库.md` | 保留 | 上游知识库愿景 |
130
- | `研发模式.md` | 保留 | 方法论 |
131
- | `腾讯实践对当前项目的指引.md` | 保留 | 实践映射 |
132
- | `DESIGN-cursor.md` / `DESIGN-lovable.md` | 保留 | 视觉 |
133
- | ~~`2026-07-14-loop-agent-self-update-notifier.md`~~ | **已归档** | 见上 |
134
- | ~~`2026-07-16-priority-ready-planner-contract.md`~~ | **已归档** | 见上 |
135
-
136
- ### 暂不建议归档(但可标注「部分落地」)
137
-
138
- - **knowledge 四件套 + full-chain\***:exec-plan 已 complete,但设计文仍是目录/schema/增量协议的权威;归档会切断引用习惯。若未来拆出「实现状态」短页,可把**纯进度段落**迁 archive,规格正文仍留根。
139
- - **六个月规划 / Dynamic Workflow roadmap**:含未来月与未完成 primitive;只做页首校准,整篇归档会丢前瞻。
140
-
141
- ---
142
-
143
- ## 命名约定(2026-07-09 起)
144
-
145
- | 名称 | 含义 | 状态 |
146
- |---|---|---|
147
- | `loop-agent` | 仓库本地 runtime / 治理控制器 CLI | 已发布 |
148
- | `agent-worker` | 产品线 TaskSpec 批处理适配层 CLI | 已发布 |
149
- | `agent-platform` | 早期规划设想名;**不是**当前 CLI | 仅未来 monorepo/上层服务语境 |
150
-
151
- ```text
152
- 产品线 docs / TaskSpec / TaskGraph
153
- → agent-worker(本地批处理适配)
154
- → loop-agent(runtime kernel)
155
- → Pi(受治理 Agent) / shell / static
156
- → cursor-prompt(显式手工 one-shot sidecar,非受治理 writer)
157
- ```
158
-
159
- ## 维护规则
160
-
161
- 1. 保持 TaskSpec 字段、status、failure category、命令示例与契约文档一致。
162
- 2. 未来平台组件标为目标架构,除非已存在于 `src/` 或 `scripts/`。
163
- 3. 命令示例只用 `agent-worker` / `loop-agent`。
164
- 4. `config-types` / profile routing 变更时更新 mapping 文档。
165
- 5. failure / Task Pool state 变更时更新 taxonomy。
166
- 6. **过期月规划 / 已关闭实现合同**迁入 `archive/`,并更新本 README。
167
- 7. 运行 `bash scripts/check-repo.sh`(或至少 check-doc-index / check-doc-links)。
@@ -1,73 +0,0 @@
1
- # 开发原则
2
-
3
- loop-agent 是面向 agentic coding 的工作流 runtime。仓库应保持小而显式、可验证。
4
-
5
- ## 操作立场
6
-
7
- 项目采用「人类掌舵、智能体执行」的工程模型。Agent 可实现、验证与总结,但持久意图与完成证据必须落在仓库中。
8
-
9
- 这个模型吸收了 Anthropic 长时运行 agent harness、OpenAI Codex harness engineering、腾讯端到端 Harness Engineering 和社区 agent harness 实践中的共同经验:用短入口文档导航长期知识,用结构化任务状态和 handoff artifact 跨 session 传递事实,用独立验证和评审回路约束 agent 输出,并把人类注意力集中在意图、边界、架构和反馈系统上。面向使用者的背景资料收录在 `website/docs/practices/`。
10
-
11
- - 仓库是记录系统。决策、契约、计划、测试、报告与交接属于 tracked files。
12
- - `AGENTS.md` 是操作地图,不是知识 dump。长期方法论与决策属于 `ai_workspace/loop-agent/`。
13
- - 工作以小步、可逆、可验证的增量推进。
14
- - 状态不确定时,先跑基线验证再开新工。
15
- - 完成由新鲜证据定义,而非意图或信心。
16
-
17
- ## 原则
18
-
19
- 1. 一次任务只推进一个有边界的工作块。
20
- 2. 设计新行为前先搜索现有代码、文档、脚本与测试。
21
- 3. Shell 验证是完成权威。
22
- 4. Runtime 状态在 `.harness/`;持久决策在 `ai_workspace/loop-agent/`。
23
- 5. Pi writer 节点必须由显式 allowed/forbidden paths 与 writeSet 约束;Cursor 仅可作为 `cursor-prompt` one-shot sidecar,不进入受治理 DAG/Loop 写入路径。
24
- 6. Pi review/planning 路径是 advisory,除非后跟确定性验证。
25
- 7. 反复出现的约束应固化为文档、测试、脚本、检查或模板。
26
- 8. 不要把隐藏流程状态只留在聊天里。
27
- 9. 不要把占位实现当作已完成交付。
28
- 10. 新增抽象前先沿用现有局部模式。
29
-
30
- ## 仓库结构
31
-
32
- - 源码:`src/`
33
- - 测试:`test/`
34
- - Skill 指令:源码仓库和 npm 包内置在 `.agents/skills/`,目标项目 repo-local skills 在 `.agents/skills/`
35
- - 验证与维护脚本:`scripts/`
36
- - 治理与交接产物:`ai_workspace/loop-agent/`
37
-
38
- ## 变更纪律
39
-
40
- 行为变更要更新测试;工作流或命令变更要更新文档与示例;治理变更要更新 `harness.json` 与相关检查脚本。
41
-
42
- 当工作影响需求、行为、跨命令契约或 harness 规则时,更新对应持久产物:
43
-
44
- - 设计/契约文档 — 变更后的预期
45
- - 测试或验证脚本 — 变更后的行为
46
- - progress log 或 report — 非平凡交接证据
47
- - ADR — 架构或公开契约决策
48
- - 模板 — 重复流程可复用时
49
-
50
- 除非 contract 明确说明必须一起移动,否则不要在一个工作块里混合无关重构、新功能与大规模文档迁移。
51
-
52
- ## 搜索与复用
53
-
54
- 实现前先检视现有系统:
55
-
56
- - 仓库已索引且任务需要理解代码时,优先用 CodeGraph。
57
- - 可用时用 `rg` 做文本搜索、`fd` 找文件。
58
- - 引入新 helper 前先读邻近测试与 helper。
59
- - 优先结构化 parser 与现有本地 API,避免 ad hoc 字符串处理。
60
-
61
- 在搜索证明否则之前,假设系统可能已有部分解法。
62
-
63
- ## 完成纪律
64
-
65
- 完成声明必须回答:
66
-
67
- - 改了什么
68
- - 为何选此方案
69
- - 哪条命令验证、结果如何
70
- - 是否影响契约、文档、测试或脚本
71
- - 剩余风险或后续项
72
-
73
- 验证失败时,报告失败命令与观察到的状态,而不是软化完成定义。
@@ -1,6 +0,0 @@
1
- # 执行计划
2
-
3
- - `active/README.md` — 当前进行中的计划
4
- - `completed/README.md` — 已完成的计划
5
-
6
- 影响多文件、公开命令行为或仓库治理的变更应使用 execution plan。
@@ -1,13 +0,0 @@
1
- # 进行中的执行计划
2
-
3
- 本目录存放当前进行中的 execution plan。
4
-
5
- 源码仓库可在本 README 旁保留具体 active plan 文件。npm 包只携带本 README 作为目录契约,不复制 loop-agent 源码历史的 active plan;目标仓库自行生成 active plan。
6
-
7
- 当前 active execution plan:
8
-
9
- - [`2026-07-18-nightly-auto-release.md`](2026-07-18-nightly-auto-release.md) — 夜间自动发布:距上次 tag ≥3 commits → GitHub Release + npm(内部测试阶段复用人工发布规则;全自动执行、次日上午人工核对;**active**)
10
- - [`2026-07-16-recursive-self-improvement-eval-lab.md`](2026-07-16-recursive-self-improvement-eval-lab.md) — Eval Lab:**M0+M1+M2(W2.1–W2.3) done**;W2.4 alias/promotion 与 M3+ live campaign 仍 todo(设计真源 `docs/design/recursive-self-improvement-eval-lab.md`;CHANGELOG `[Unreleased]`)
11
- - [`2026-07-16-frontend-mock-node.md`](2026-07-16-frontend-mock-node.md) — 前端 DAG Mock 策略节点与安全验证
12
-
13
- - 已归档:`../completed/2026-07-18-observe-ops-surface-and-rich-timeline.md`、`../completed/2026-07-16-fe-test-dag.md`、`../completed/2026-07-17-frontend-implementation-capability-deepening.md`、`../completed/2026-07-17-backend-test-capability-deepening.md`、`../completed/2026-07-16-backend-test-remediation.md`、`../completed/2026-07-16-frontend-demand-auto-routing.md`、`../completed/2026-07-16-frontend-mock-data-workflow.md`、`../completed/2026-07-14-knowledge-sync-and-graph.md`、`../completed/2026-07-15-repair-artifact-gate-runtime-contract.md`、`../completed/2026-07-14-observe-ui-r5.md`、`../completed/2026-07-14-observe-ui-r4.md`、`../completed/2026-07-14-observe-ui-r3.md`、`../completed/2026-07-14-observe-ui-r2.md`、`../completed/2026-07-14-observe-ui-r1.md`、`../completed/2026-07-14-init-canonical-layout.md`、`../completed/2026-07-12-observe-warm-console-redesign.md`、`../completed/2026-07-14-website-docs-ia-and-converge.md`、`../completed/2026-07-13-versioned-self-hosting-bootstrap.md`、`../completed/2026-07-12-pi-only-agent-runtime.md`、第二月 M2-01~M2-08、`../completed/2026-07-11-observe-dashboard-page-system.md`、`../completed/2026-07-11-observe-dashboard-detail-refinement.md`、`../completed/2026-07-11-observe-terminal-dag-kpi.md`、`../completed/2026-07-11-observe-polling-efficiency.md`、`../completed/2026-07-11-command-performance-guardrails.md` 及更早计划。
@@ -1,108 +0,0 @@
1
- # 已完成的执行计划
2
-
3
- 实现与验证结束后,已完成计划移入此目录。
4
-
5
- npm 包携带本 README 作为目录契约。具体 completed plan 属于目标仓库历史,不从 loop-agent 源码历史复制。
6
-
7
- - [`2026-07-18-observe-ops-surface-and-rich-timeline.md`](2026-07-18-observe-ops-surface-and-rich-timeline.md) — Observe 资源池运营面、总览执行面重排、检查器半屏宽度与富执行过程时间线(含 `recordedAt`)
8
- - [`2026-07-16-fe-test-dag.md`](2026-07-16-fe-test-dag.md) — FE-test RAG:`taskKind: "frontend-test"` 串行浏览器用例/证据 DAG(MVP + PR #25;prompt 深度 / 真实 browser smoke 等 residual 另开)
9
- - [`2026-07-17-frontend-implementation-capability-deepening.md`](2026-07-17-frontend-implementation-capability-deepening.md) — frontend-implementation Contract/trace/repair、风险裁剪、React/Next/Vue capability、a11y/openSpec seed(M0–M6 核心完成;W2.7/W3.8/W6.8 residual)
10
- - [`2026-07-17-backend-test-capability-deepening.md`](2026-07-17-backend-test-capability-deepening.md) — backend-test 执行合同、结果分类、Case Manifest/Traceability 与 M4 docs/init/tmpdir smoke 收敛(M0–M4 全完成)
11
- - [`2026-07-17-review-findings-remediation.md`](2026-07-17-review-findings-remediation.md) — 收敛主干 review findings
12
- - [`2026-07-16-frontend-mock-data-workflow.md`](2026-07-16-frontend-mock-data-workflow.md) — 前端 Mock 数据治理链
13
- - [`2026-07-16-frontend-demand-auto-routing.md`](2026-07-16-frontend-demand-auto-routing.md) — 前端需求确定性自动路由
14
- - [`2026-07-16-dag-source-binding-recovery.md`](2026-07-16-dag-source-binding-recovery.md) — DAG 任务源绑定与恢复门禁
15
- - [`2026-07-16-backend-test-remediation.md`](2026-07-16-backend-test-remediation.md) — backend-test 报告、writeSet 与 prompt 修复
16
- - [`2026-07-14-knowledge-sync-and-graph.md`](2026-07-14-knowledge-sync-and-graph.md) — knowledge-sync 与知识图谱 MVP 完成归档
17
- - [`2026-07-16-target-agents-routing-observe.md`](2026-07-16-target-agents-routing-observe.md) — 让根与初始化目标 AGENTS 正确路由后端测试,并提供本地只读看板入口和安全更新回归
18
- - [`2026-07-16-init-upgrade-continuity.md`](2026-07-16-init-upgrade-continuity.md) — 修复 apply-safe 降级 recorded state、补齐 knowledge taskKind/公共 CLI 指引,并将 kb runtime scripts 纳入 packageRequired
19
- - [`2026-07-15-repair-artifact-gate-runtime-contract.md`](2026-07-15-repair-artifact-gate-runtime-contract.md) — 显式 `repairNodeId` + 严格 repair writer 契约、DagSpec `runtimeContract` capability preflight,以及 run-owned controller identity(resume 漂移 fail-closed)
20
- - [`2026-07-14-backend-test-dag-template.md`](2026-07-14-backend-test-dag-template.md) — 通过 `taskKind: "backend-test"` 生成需求分析、功能用例、pytest 自动化、执行与复盘的 Pi-only 专用 DAG
21
- - [`2026-07-14-observe-ui-r5.md`](2026-07-14-observe-ui-r5.md) — Observe 原生 ES module 拆分、四态 helper、Pool hash 筛选与入口 re-export
22
- - [`2026-07-14-observe-ui-r4.md`](2026-07-14-observe-ui-r4.md) — Observe Batch/Pool 有界事件时间线、cursor/limit、JSONL 容量与投影 fault-first
23
- - [`2026-07-14-observe-ui-r2.md`](2026-07-14-observe-ui-r2.md) — Observe Batch / Worker Run 证据化详情、三层只读结构与安全 artifact preview
24
- - [`2026-07-14-observe-ui-r3.md`](2026-07-14-observe-ui-r3.md) — Observe Feature 决策详情、copy-only 建议命令与 canonical 对象关系导航
25
- - [`2026-07-14-observe-ui-r1.md`](2026-07-14-observe-ui-r1.md) — Observe 资源池总览、Task 下钻、精确对象关联与有界 run history
26
- - [`2026-07-14-init-canonical-layout.md`](2026-07-14-init-canonical-layout.md) — 目标项目治理资料统一到 `ai_workspace/loop-agent/` 与 `.agents/skills/`,并为旧布局提供保守安全迁移
27
- - [`2026-07-14-self-update-notifier-implementation.md`](2026-07-14-self-update-notifier-implementation.md) — 实现 loop-agent CLI 自更新提醒,覆盖拒绝版本、精确安装、npm global 来源证明和验证收口
28
- - [`2026-07-12-observe-warm-console-redesign.md`](2026-07-12-observe-warm-console-redesign.md) — 以暖白、细边界和高密度信息架构重构 Observe Dashboard;多轮细节调整后按用户确认收口归档。
29
- - [`2026-07-14-website-docs-ia-and-converge.md`](2026-07-14-website-docs-ia-and-converge.md) — Website 文档信息架构、双树边界与 `docs-converge` 同步机制
30
- - [`2026-07-14-frontend-spec-source-fallback.md`](2026-07-14-frontend-spec-source-fallback.md) — 统一前端规范来源为知识库优先、失败后强制检索当前项目 `openSpec/`
31
- - [`2026-07-13-test-environment-stability.md`](2026-07-13-test-environment-stability.md) — 修复 Windows Git Bash、npm CLI 启动与 Git/Delivery 测试资源分类,避免验证节点反复失败并跳过 DAG 收口
32
- - [`2026-07-13-sdd-embedded-skills.md`](2026-07-13-sdd-embedded-skills.md) — 目标项目 repo-local SDD skills 的可选 DAG 节点嵌入增强,loop-agent 保持流程、状态与写边界控制
33
- - [`2026-07-13-frontend-skill-contracts.md`](2026-07-13-frontend-skill-contracts.md) — 补齐前端节点 Skill 的输入、输出、证据与阻断契约,并预留组件/设计知识库接入 TODO
34
- - [`2026-07-13-versioned-self-hosting-bootstrap.md`](2026-07-13-versioned-self-hosting-bootstrap.md) — 固定已发布 controller identity、冻结 run-owned skills,并由隔离候选包完成 deterministic self-hosting takeover canary
35
- - [`2026-07-12-pi-only-agent-runtime.md`](2026-07-12-pi-only-agent-runtime.md) — 将 DAG、Loop、Delegate 和 Worker 收敛为 Pi-only 受治理 runtime,仅保留独立的 one-shot `cursor-prompt` sidecar
36
- - [`2026-07-11-m2-01-feature-review-model.md`](2026-07-11-m2-01-feature-review-model.md) — 第二月首个纵向切片:严格派生 Feature 状态、AC/Delivery/Closeout 证据与只读 `feature review`
37
- - [`2026-07-12-m2-02-feature-run-orchestration.md`](2026-07-12-m2-02-feature-run-orchestration.md) — Feature 级 dry-run 与复用现有 Worker pipeline 的薄编排入口
38
- - [`2026-07-12-m2-03-follow-up-tracer-bullet.md`](2026-07-12-m2-03-follow-up-tracer-bullet.md) — ProductBug 失败到人工批准 FIX、依赖重连、Ready 与 verified lineage 的纵向闭环
39
- - [`2026-07-12-m2-04-follow-up-hardening.md`](2026-07-12-m2-04-follow-up-hardening.md) — 全 failure-category ActionCard/TaskDraft、EnvFailure 阈值、supersede 与审批事务故障回滚
40
- - [`2026-07-12-m2-05-git-transaction.md`](2026-07-12-m2-05-git-transaction.md) — Feature branch checkpoint、失败证据/恢复、ignored 隔离与事务完整性
41
- - [`2026-07-12-m2-06-delivery-closeout-preview.md`](2026-07-12-m2-06-delivery-closeout-preview.md) — Delivery Package、canonical AC evidence 与只读 Closeout gates
42
- - [`2026-07-12-m2-07-feature-decision-metrics.md`](2026-07-12-m2-07-feature-decision-metrics.md) — 共享 Feature Decision Summary、Observe 层级、corruption 降级与月度 metrics
43
- - [`2026-07-12-m2-08-closeout-dogfood-release.md`](2026-07-12-m2-08-closeout-dogfood-release.md) — Closeout apply、第二真实 Feature、真实 Follow-up 恢复、package/init/browser 与月度收口证据
44
- - [`2026-07-11-observe-dashboard-page-system.md`](2026-07-11-observe-dashboard-page-system.md) — 完成 Observe 全页面信息层级与桌面布局优化,按用户确认收口归档。
45
- - [`2026-07-11-observe-dashboard-detail-refinement.md`](2026-07-11-observe-dashboard-detail-refinement.md) — 完成 DAG 详情输出、依赖图与执行过程的轮询状态保持和桌面节点布局优化,按用户确认收口归档。
46
- - [`2026-07-11-observe-terminal-dag-kpi.md`](2026-07-11-observe-terminal-dag-kpi.md) — 修复终态 DAG 因遗留未执行节点被误计为活跃的问题。
47
- - [`2026-07-11-observe-polling-efficiency.md`](2026-07-11-observe-polling-efficiency.md) — 完成详情页终态停轮询、非重叠调度和后台降频。
48
- - [`2026-07-11-command-performance-guardrails.md`](2026-07-11-command-performance-guardrails.md) — 完成命令并发参数、串行验证与 Observe SSE 的资源峰值护栏。
49
- - [`2026-07-11-command-performance-followups.md`](2026-07-11-command-performance-followups.md) — 完成 Observe 快照复用、命令输出有界缓冲和 reference index 遍历优化。
50
- - [`2026-07-02-loop-agent-subject-restructure.md`](2026-07-02-loop-agent-subject-restructure.md) — 将原 `tools/code-agent` runtime 提升到仓库根、重命名为 `loop-agent`,移除旧 memory plugin 产品线
51
- - [`2026-07-04-remove-level1-fallback.md`](2026-07-04-remove-level1-fallback.md) — 移除历史顺序 Level 1 fallback,runtime、文档与 command surface 收敛到 DAG 执行
52
- - [`2026-07-04-runtime-boundary-remediation.md`](2026-07-04-runtime-boundary-remediation.md) — 整合 CLI/skill/runtime 边界,抽出 DAG/Loop runtime seam,集中 harness store/guard 策略
53
- - [`2026-07-10-next-stage-worker-evidence.md`](2026-07-10-next-stage-worker-evidence.md) — Worker retry、EnvFailure、边界治理、初始化投影与真实 BE/FE/QA dogfood evidence 闭环
54
- - [`2026-07-10-release-0.6.0-nightly-drill.md`](2026-07-10-release-0.6.0-nightly-drill.md) — 发布 0.6.0、首轮夜间演练(6 worker runs / 3 success)、Observe 过程时间线验证;C6 owner gate 由 Round 3 morning decision 满足后正式关闭
55
- - [`2026-07-10-harness-json-schema.md`](2026-07-10-harness-json-schema.md) — 新增 `harness.json` IDE JSON Schema、初始化投影、旧项目 update 修复和漂移防护
56
- - [`2026-07-11-interactive-ui-writer-routing.md`](2026-07-11-interactive-ui-writer-routing.md) — 新增 interactive-ui writer-only HIGH 路由、UI 交付契约、真实 React dogfood fixture 与 Round-2 A/B/C 实验入口
57
- - [`2026-07-11-round-2-interactive-ui-productization.md`](2026-07-11-round-2-interactive-ui-productization.md) — 完成 owner gate、0.7.0–0.7.4 发布、React A/B/C、20 个 Worker runs、外部 nightly、产品线模板与 docs CI
58
- - [`2026-07-11-observe-dag-visualization.md`](2026-07-11-observe-dag-visualization.md) — Observe 投影 canonical DAG edges,新增确定性 SVG 依赖图、节点交互、视觉 tokens、可访问性与真实 Chrome smoke
59
- - [`2026-07-04-dag-role-skill-alignment.md`](2026-07-04-dag-role-skill-alignment.md) — 对齐 DAG/Dynamic Workflow role 与 repo-local vetted skills,新增 strict skill audit
60
- - [`2026-07-06-production-readiness-hardening.md`](2026-07-06-production-readiness-hardening.md) — 冻结 Production Readiness v0.1,打磨 DAG 主路径 next steps、failure routing、doctor/report/failure handoff 与 dogfood 验证
61
- - [`2026-07-08-taskspec-schema-validate.md`](2026-07-08-taskspec-schema-validate.md) — 新增 TaskSpec v0.1 schema、三层校验器、risk→complexity 映射和 5 个 dogfood TaskSpec 样例
62
- - [`2026-07-08-acceptance-taskgraph-ready.md`](2026-07-08-acceptance-taskgraph-ready.md) — 新增 AcceptanceSpec / TaskGraphSpec schema、Feature graph 校验、环检测和 Ready 队列计算
63
- - [`2026-07-08-profile-mapping-agent-worker-cli.md`](2026-07-08-profile-mapping-agent-worker-cli.md) — 新增 business profile 到 loop-agent profile 映射、独立 `agent-worker` CLI 和 package bin surface
64
- - [`2026-07-08-loop-agent-client-contract-smoke.md`](2026-07-08-loop-agent-client-contract-smoke.md) — 新增 LoopAgentClient、command artifact、JSON parse failure、repo resolver/preflight 与 Ring 0 CLI contract smoke
65
- - [`2026-07-08-materializer-ring1-dag.md`](2026-07-08-materializer-ring1-dag.md) — 新增 TaskSpec materializer、materialize manifest、coverage-safe source 输出与 Ring 1 DAG generate/validate/dry-run smoke
66
- - [`2026-07-08-run-task-pipeline-ring2.md`](2026-07-08-run-task-pipeline-ring2.md) — 新增 Worker run-task pipeline、task-local run record、成功/失败分流与 Ring 2 shell-only DAG success/failure smoke
67
- - [`2026-07-08-task-pool-morning-report.md`](2026-07-08-task-pool-morning-report.md) — 新增 Worker Task Pool JSONL/state store、failure routing、串行 batch run-ready 和 morning report
68
- - [`2026-07-08-taskspec-worker-master.md`](2026-07-08-taskspec-worker-master.md) — 完成 TaskSpec + Worker 7 步 master 编排,覆盖 schema、graph、profile、client、materialize、run-task、Task Pool 和 morning report
69
- - [`2026-07-10-obs-001.md`](2026-07-10-obs-001.md) — WorkerEvent schema 与 append-only event/snapshot store
70
- - [`2026-07-10-obs-002.md`](2026-07-10-obs-002.md) — LoopAgentClient 流式输出、heartbeat 与实时 artifact
71
- - [`2026-07-10-obs-003.md`](2026-07-10-obs-003.md) — composite progress 与 Worker pipeline 事件打点
72
- - [`2026-07-10-obs-004.md`](2026-07-10-obs-004.md) — observability snapshot read model
73
- - [`2026-07-10-obs-005.md`](2026-07-10-obs-005.md) — 本地只读 observe HTTP/SSE server
74
- - [`2026-07-10-obs-006.md`](2026-07-10-obs-006.md) — Dashboard、Batch Detail 与 Run Detail UI
75
- - [`2026-07-10-obs-007.md`](2026-07-10-obs-007.md) — run-dag JSONL events 与 composite observer
76
- - [`2026-07-10-obs-008.md`](2026-07-10-obs-008.md) — Worker DAG events 接线与 DAG Detail UI
77
- - [`2026-07-10-obs-009.md`](2026-07-10-obs-009.md) — stale、quiet 与 timeout-risk 诊断
78
- - [`2026-07-10-obs-010.md`](2026-07-10-obs-010.md) — Failure Inbox、文档、package surface 与 smoke 验证
79
- - [`2026-07-10-observe-ui-review-remediation.md`](2026-07-10-observe-ui-review-remediation.md) — 修复 Observe UI 事件链路、历史 run 投影、artifact 安全边界与失败状态展示
80
-
81
- - [`2026-07-13-exec-plan-lifecycle.md`](2026-07-13-exec-plan-lifecycle.md)
82
-
83
- - [`2026-07-15-task-pool-priority-aware-ready-planner.md`](2026-07-15-task-pool-priority-aware-ready-planner.md)
84
- - [`2026-07-15-task-pool-v2-feature-scoped-task-identity.md`](2026-07-15-task-pool-v2-feature-scoped-task-identity.md)
85
- - [`2026-07-15-init-update-surface-coverage.md`](2026-07-15-init-update-surface-coverage.md)
86
- - [`2026-07-15-readonly-node-retry.md`](2026-07-15-readonly-node-retry.md)
87
-
88
- - [`2026-07-16-init-natural-language-routing.md`](2026-07-16-init-natural-language-routing.md)
89
-
90
- - [`2026-07-16-observe-inspector-node-consistency.md`](2026-07-16-observe-inspector-node-consistency.md)
91
-
92
- - [`2026-07-16-repair-artifact-pass-normalization.md`](2026-07-16-repair-artifact-pass-normalization.md)
93
-
94
- - [`2026-07-16-decision-envelope-fence-tolerance.md`](2026-07-16-decision-envelope-fence-tolerance.md)
95
-
96
- - [`2026-07-16-decision-envelope-prompt-contract.md`](2026-07-16-decision-envelope-prompt-contract.md)
97
-
98
- - [`2026-07-17-source-target-structure-alignment.md`](2026-07-17-source-target-structure-alignment.md)
99
-
100
- - [`2026-07-17-review-findings-remediation.md`](2026-07-17-review-findings-remediation.md)
101
-
102
- - [`2026-07-16-backend-test-analysis-contract-artifact.md`](2026-07-16-backend-test-analysis-contract-artifact.md)
103
-
104
- - [`2026-07-17-release-0130-reconcile.md`](2026-07-17-release-0130-reconcile.md)
105
-
106
- - [`2026-07-17-observe-dashboard-incremental-polling.md`](2026-07-17-observe-dashboard-incremental-polling.md)
107
-
108
- - [`2026-07-18-origin-main-merge-43e86ad.md`](2026-07-18-origin-main-merge-43e86ad.md)