@tea-agent/loop-agent 0.25.6 → 0.26.0

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 (162) hide show
  1. package/AGENTS.md +2 -1
  2. package/CHANGELOG.md +1020 -1006
  3. package/bin/loop-agent.js +21 -21
  4. package/dist/commands/cursor-prompt.js +6 -6
  5. package/dist/commands/loop-benchmark.js +11 -11
  6. package/dist/commands/pi-reuse-benchmark.js +16 -16
  7. package/dist/executors/dag-pi-executor.js +26 -20
  8. package/dist/executors/model-routing.js +34 -18
  9. package/dist/governance/manifest-types.js +33 -5
  10. package/dist/sidecars/cursor-prompt/executor.js +1 -1
  11. package/dist/task/task-demand-routing.js +3 -1
  12. package/dist/worker/console/chat/model-resolver.js +15 -3
  13. package/dist/worker/observe/static/constants.js +3 -2
  14. package/dist/worker/observe/static/copy.js +67 -67
  15. package/dist/worker/observe/static/dag-layout.d.ts +31 -31
  16. package/dist/worker/observe/static/dag-layout.js +83 -83
  17. package/dist/worker/observe/static/dag-model.js +1 -0
  18. package/dist/worker/observe/static/dom.js +220 -220
  19. package/dist/worker/observe/static/relations.js +133 -133
  20. package/dist/worker/observe/static/router.js +93 -93
  21. package/dist/worker/observe/static/run-processing.js +148 -148
  22. package/dist/worker/observe/static/styles.css +182 -42
  23. package/dist/worker/observe/static/views/batch.js +227 -227
  24. package/dist/worker/observe/static/views/dag-graph.js +172 -172
  25. package/dist/worker/observe/static/views/failures.js +143 -143
  26. package/dist/worker/observe/static/views/feature.js +492 -492
  27. package/dist/worker/observe/static/views/run.js +453 -453
  28. package/dist/worker/observe/static/views/shell.js +7 -7
  29. package/dist/worker/observe/static/views/timeline.js +163 -163
  30. package/dist/workflows/dag/canvas-observer.js +275 -275
  31. package/dist/workflows/dag/lifecycle.js +40 -30
  32. package/dist/workflows/dag/node-execution.js +13 -0
  33. package/dist/workflows/dag/types.js +59 -19
  34. package/docs/skills/README.md +7 -7
  35. package/docs/templates/adr.md +60 -60
  36. package/docs/templates/agent-dag-authority-surface-audit.prompt.md +94 -94
  37. package/docs/templates/agent-dag-decision-envelope.schema.json +213 -213
  38. package/docs/templates/agent-dag-decision-gate.prompt.md +246 -246
  39. package/docs/templates/agent-dag-process-supervisor.prompt.md +98 -98
  40. package/docs/templates/agent-dag-report.schema.json +473 -473
  41. package/docs/templates/agent-dag-review-verdict.prompt.md +68 -68
  42. package/docs/templates/backend-test-result.schema.json +99 -99
  43. package/docs/templates/feature-spec.md +53 -53
  44. package/docs/templates/frontend-design-contract.md +42 -42
  45. package/docs/templates/frontend-eval/fixtures/failures/01-type-build-error.md +17 -17
  46. package/docs/templates/frontend-eval/fixtures/failures/02-unit-component-test-fail.md +16 -16
  47. package/docs/templates/frontend-eval/fixtures/failures/03-fixture-schema-drift.md +16 -16
  48. package/docs/templates/frontend-eval/fixtures/failures/04-missing-loading-empty-error-state.md +16 -16
  49. package/docs/templates/frontend-eval/fixtures/failures/05-forbidden-write-writeset-expansion.md +16 -16
  50. package/docs/templates/frontend-eval/fixtures/failures/06-unapproved-dependency-add.md +16 -16
  51. package/docs/templates/frontend-eval/fixtures/failures/07-mock-production-on.md +21 -21
  52. package/docs/templates/frontend-eval/fixtures/functional/01-simple-component-style.md +29 -29
  53. package/docs/templates/frontend-eval/fixtures/functional/02-form-validation.md +28 -28
  54. package/docs/templates/frontend-eval/fixtures/functional/03-list-detail-page.md +28 -28
  55. package/docs/templates/frontend-eval/fixtures/functional/04-api-mock.md +29 -29
  56. package/docs/templates/frontend-eval/fixtures/functional/05-permission-auth-gated-ui.md +27 -27
  57. package/docs/templates/frontend-eval/fixtures/functional/06-ssr-server-client-boundary.md +28 -28
  58. package/docs/templates/frontend-eval/fixtures/functional/07-shared-public-component-api.md +28 -28
  59. package/docs/templates/frontend-eval/fixtures/functional/08-pure-local-no-remote.md +27 -27
  60. package/docs/templates/frontend-eval/metrics.md +138 -138
  61. package/docs/templates/frontend-eval/smoke-targets.md +53 -53
  62. package/docs/templates/frontend-task-constraints.md +35 -35
  63. package/docs/templates/frontend-task-requirement.md +70 -70
  64. package/docs/templates/harness.schema.json +29 -7
  65. package/docs/templates/init-evolution-review.md +35 -35
  66. package/docs/templates/interactive-ui-round2-experiment.md +66 -66
  67. package/docs/templates/knowledge-graph-bootstrap-dag.json +118 -118
  68. package/docs/templates/knowledge-sync-dag.json +178 -178
  69. package/docs/templates/knowledge-sync-draft.schema.json +71 -71
  70. package/docs/templates/product-line/closeout.yaml +9 -9
  71. package/docs/templates/product-line/design.md +13 -13
  72. package/docs/templates/product-line/links.md +10 -10
  73. package/docs/templates/product-line/requirement.md +17 -17
  74. package/docs/templates/product-line/test-plan.md +7 -7
  75. package/docs/templates/production-readiness-checklist.md +57 -57
  76. package/docs/templates/project-start-checklist.md +9 -9
  77. package/docs/templates/qa-report.md +48 -48
  78. package/docs/templates/sprint-contract.md +29 -29
  79. package/docs/templates/worker-dogfood-evidence.md +80 -80
  80. package/docs/templates/worker-dogfood-setup.md +68 -68
  81. package/harness.json +1 -2
  82. package/package.json +1 -1
  83. package/scripts/kb-bootstrap-init-skeleton.sh +0 -0
  84. package/scripts/kb-graph-incremental-prepare.mjs +386 -386
  85. package/scripts/kb-graph-materialize.mjs +105 -105
  86. package/scripts/kb-graph-promote.mjs +164 -164
  87. package/scripts/kb-query.mjs +554 -554
  88. package/skills/ai-engineering-context/SKILL.md +48 -48
  89. package/skills/analyze-product-dependencies/SKILL.md +67 -67
  90. package/skills/analyze-product-dependencies/agents/openai.yaml +4 -4
  91. package/skills/analyze-product-dependencies/references/api-documentation-schema.md +30 -30
  92. package/skills/analyze-product-dependencies/references/dependency-analysis-schema.md +28 -28
  93. package/skills/analyze-product-dependencies/references/example.md +76 -76
  94. package/skills/analyze-product-dependencies/references/forward-test-cases.md +35 -35
  95. package/skills/analyze-product-dependencies/references/input-contract.md +11 -11
  96. package/skills/analyze-product-dependencies/references/scouting-rules.md +61 -61
  97. package/skills/analyze-product-dependencies/scripts/test-validators.mjs +267 -267
  98. package/skills/analyze-product-dependencies/scripts/validate-api-documentation.mjs +101 -101
  99. package/skills/analyze-product-dependencies/scripts/validate-dependency-analysis.mjs +142 -142
  100. package/skills/analyze-product-dependencies/scripts/validate-product-requirement-input.mjs +76 -76
  101. package/skills/analyze-product-dependencies/scripts/validation-helpers.mjs +146 -146
  102. package/skills/analyze-product-requirements/SKILL.md +90 -90
  103. package/skills/analyze-product-requirements/agents/openai.yaml +4 -4
  104. package/skills/analyze-product-requirements/references/acceptance-criteria.md +91 -91
  105. package/skills/analyze-product-requirements/references/clarification-and-knowledge.md +56 -56
  106. package/skills/analyze-product-requirements/references/example.md +86 -86
  107. package/skills/analyze-product-requirements/references/forward-test-cases.md +66 -66
  108. package/skills/analyze-product-requirements/references/product-analysis-schema.md +32 -32
  109. package/skills/analyze-product-requirements/references/product-requirement-schema.md +33 -33
  110. package/skills/analyze-product-requirements/references/requirement-clarification-schema.md +35 -35
  111. package/skills/analyze-product-requirements/scripts/test-validators.mjs +193 -193
  112. package/skills/analyze-product-requirements/scripts/validate-product-analysis.mjs +69 -69
  113. package/skills/analyze-product-requirements/scripts/validate-product-requirement.mjs +97 -97
  114. package/skills/analyze-product-requirements/scripts/validate-requirement-clarification.mjs +98 -98
  115. package/skills/analyze-product-requirements/scripts/validation-helpers.mjs +156 -156
  116. package/skills/browser-tools/browser-content.js +103 -103
  117. package/skills/browser-tools/browser-cookies.js +35 -35
  118. package/skills/browser-tools/browser-eval.js +53 -53
  119. package/skills/browser-tools/browser-hn-scraper.js +108 -108
  120. package/skills/browser-tools/browser-nav.js +44 -44
  121. package/skills/browser-tools/browser-pick.js +162 -162
  122. package/skills/browser-tools/browser-screenshot.js +34 -34
  123. package/skills/browser-tools/browser-start.js +86 -86
  124. package/skills/browser-tools/package-lock.json +2556 -2556
  125. package/skills/browser-tools/package.json +19 -19
  126. package/skills/code-review-core/SKILL.md +20 -20
  127. package/skills/codebase-scout/SKILL.md +19 -19
  128. package/skills/grill-me/SKILL.md +10 -10
  129. package/skills/loop-agent/references/README.md +67 -67
  130. package/skills/loop-agent/references/docs-converge.md +126 -126
  131. package/skills/loop-agent/references/hybrid-dag.md +2 -2
  132. package/skills/loop-agent/references/learned/README.md +21 -21
  133. package/skills/loop-agent/references/long-running-loop.md +57 -57
  134. package/skills/loop-agent/references/model-routing.md +2 -0
  135. package/skills/loop-agent/references/one-shot-runs.md +85 -85
  136. package/skills/loop-agent/references/pi-prompt.md +23 -23
  137. package/skills/loop-agent/references/pi-subagent-assisted-mode.md +84 -84
  138. package/skills/playwright-cli/SKILL.md +420 -420
  139. package/skills/playwright-cli/references/element-attributes.md +23 -23
  140. package/skills/playwright-cli/references/playwright-tests.md +39 -39
  141. package/skills/playwright-cli/references/request-mocking.md +87 -87
  142. package/skills/playwright-cli/references/running-code.md +241 -241
  143. package/skills/playwright-cli/references/session-management.md +225 -225
  144. package/skills/playwright-cli/references/storage-state.md +275 -275
  145. package/skills/playwright-cli/references/test-generation.md +433 -433
  146. package/skills/playwright-cli/references/tracing.md +139 -139
  147. package/skills/playwright-cli/references/video-recording.md +143 -143
  148. package/skills/requesting-code-review/SKILL.md +101 -101
  149. package/skills/requesting-code-review/code-reviewer.md +168 -168
  150. package/skills/systematic-debugging/CREATION-LOG.md +119 -119
  151. package/skills/systematic-debugging/condition-based-waiting-example.ts +158 -158
  152. package/skills/systematic-debugging/condition-based-waiting.md +115 -115
  153. package/skills/systematic-debugging/defense-in-depth.md +122 -122
  154. package/skills/systematic-debugging/find-polluter.sh +63 -63
  155. package/skills/systematic-debugging/root-cause-tracing.md +169 -169
  156. package/skills/systematic-debugging/test-academic.md +14 -14
  157. package/skills/systematic-debugging/test-pressure-1.md +58 -58
  158. package/skills/systematic-debugging/test-pressure-2.md +68 -68
  159. package/skills/systematic-debugging/test-pressure-3.md +69 -69
  160. package/skills/using-git-worktrees/SKILL.md +215 -215
  161. package/skills/verification-before-completion/SKILL.md +154 -154
  162. package/skills/webapp-testing/SKILL.md +19 -19
package/AGENTS.md CHANGED
@@ -25,6 +25,7 @@
25
25
  - 用 loop-agent 迭代本仓库时,控制器必须来自已发布 npm 包(记录实际版本);启动后不要中途升级;不要用工作区 `npm link` / `npm run dev` 控制可能改 CLI/runtime/package 的任务。
26
26
  - 反复出现的约束固化为文档、脚本、检查、测试或模板;禁止占位实现(除非 contract 标明脚手架)。
27
27
  - 非微小实现:`exec-plan` 不能替代 Agent DAG;除非用户要求 one-shot 或计划记录 escape hatch,否则改实现前完成 `new-task`、结构化路径、`dag run-task`、`dag validate` 与 writeSet 审查。
28
+ - **实现默认 DAG,主会话不直接改代码**:只要是实现/修复/行为或展示语义变更(含 observe 文案映射、runtime status、schema、executor、CLI 等),主会话只做 Orient / 建 task / dry-run / validate / writeSet 审查 / 执行与监视 DAG,**不得**自己改 `src/**`、`test/**` 等交付面。仅当用户**明确授权**主会话直接处理(例如「直接改」「主会话改」「one-shot」「不用 DAG」)时,才允许主会话写入;授权后仍须记录边界、allowedPaths 与验证证据。纯答疑、读代码、查状态、提交/推送已有 diff、或用户点名的文档微调(如本文件规则)不在此限。
28
29
  - 不要自行引入外部 SDD/spec-first 等强制平行治理树;以本文件与 `docs/` 为准(ADR 0006)。
29
30
 
30
31
  ## 开始顺序
@@ -44,7 +45,7 @@
44
45
 
45
46
  1. Orient → 2. Select(一块)→ 3. Contract → 4. Implement → 5. Verify → 6. Converge Docs → 7. Handoff。
46
47
 
47
- 这不是 DAG 节点序列。复杂实现默认 Agent DAG;主 agent 拆任务、写 contract、结构化路径、审查 DAG/writeSet/profile/shell verification。微小任务可用 one-shot escape hatch 并记录边界与验证证据。
48
+ 这不是 DAG 节点序列。实现默认 Agent DAG;主 agent 拆任务、写 contract、结构化路径、审查 DAG/writeSet/profile/shell verification,**不自行 implement**。主会话 one-shot 仅在用户明确授权时可用,并记录边界与验证证据;「看起来很小」或「只是展示文案」不构成授权——若改动触及 runtime/status/映射语义,仍走 DAG。
48
49
 
49
50
  启动 loop-agent DAG 流程后,主 agent 应自主推进到整个流程结束,不要中途请求无谓的人工确认(如“要我现在执行 DAG 吗?”)。只要 dry-run / validate / writeSet 审查通过就应直接执行并跑完全部 ranks;遇到真问题(契约不一致、writeSet 越界、verify 失败且超出 maxFixLoops、用户明显未授权的高风险动作)才停。即便 profile 是 supervised/reviewed,也不默认在 review-gate 主动停下等人——控制器会在需要人工 approve 时自行提示,主 agent 的职责是推动流程跑完。
50
51