@tea-agent/loop-agent 0.12.0 → 0.13.0-beta.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 (284) hide show
  1. package/AGENTS.md +155 -153
  2. package/CHANGELOG.md +338 -265
  3. package/README.md +345 -298
  4. package/bin/agent-worker.js +22 -22
  5. package/bin/loop-agent.js +21 -21
  6. package/dist/application/dag/generate-task-dag.js +28 -28
  7. package/dist/application/evaluation/candidate-hash.js +75 -0
  8. package/dist/application/evaluation/candidate.js +52 -0
  9. package/dist/application/evaluation/replay.js +289 -0
  10. package/dist/application/evaluation/types.js +130 -0
  11. package/dist/cli/command-definitions.js +27 -7
  12. package/dist/cli/program.js +8 -4
  13. package/dist/commands/cursor-prompt.js +6 -6
  14. package/dist/commands/eval.js +235 -0
  15. package/dist/commands/init.js +544 -506
  16. package/dist/commands/knowledge.js +129 -31
  17. package/dist/commands/loop-benchmark.js +11 -11
  18. package/dist/commands/pi-reuse-benchmark.js +16 -16
  19. package/dist/executors/pi-sdk-executor.js +38 -24
  20. package/dist/executors/shell-executor.js +34 -2
  21. package/dist/executors/shell-presets.js +20 -0
  22. package/dist/executors/shell-verification.js +7 -0
  23. package/dist/governance/manifest-types.js +4 -0
  24. package/dist/infrastructure/evaluation/candidate-store.js +435 -0
  25. package/dist/infrastructure/evaluation/store.js +40 -0
  26. package/dist/sidecars/cursor-prompt/executor.js +1 -1
  27. package/dist/task/config-types.js +28 -1
  28. package/dist/task/runtime.js +27 -27
  29. package/dist/worker/cli.js +96 -1
  30. package/dist/worker/delivery/package.js +3 -3
  31. package/dist/worker/feature/decision-loader.js +37 -6
  32. package/dist/worker/feature/next-action.js +10 -2
  33. package/dist/worker/feature/ready-plan-projection.js +81 -0
  34. package/dist/worker/feature/reducer.js +2 -1
  35. package/dist/worker/feature/review.js +19 -2
  36. package/dist/worker/feature/run.js +27 -2
  37. package/dist/worker/follow-up/approve.js +5 -2
  38. package/dist/worker/follow-up/factory.js +1 -1
  39. package/dist/worker/observability/read-model.js +246 -41
  40. package/dist/worker/observe/routes.js +173 -15
  41. package/dist/worker/observe/spec-evidence.js +281 -0
  42. package/dist/worker/observe/static/api.js +46 -27
  43. package/dist/worker/observe/static/app.js +150 -150
  44. package/dist/worker/observe/static/constants.js +148 -148
  45. package/dist/worker/observe/static/copy.js +67 -67
  46. package/dist/worker/observe/static/dag-helpers.js +172 -172
  47. package/dist/worker/observe/static/dag-layout.d.ts +31 -31
  48. package/dist/worker/observe/static/dag-layout.js +83 -83
  49. package/dist/worker/observe/static/dag-model.js +72 -72
  50. package/dist/worker/observe/static/dom.js +61 -61
  51. package/dist/worker/observe/static/format-pool.js +67 -67
  52. package/dist/worker/observe/static/format.js +292 -292
  53. package/dist/worker/observe/static/index.html +308 -308
  54. package/dist/worker/observe/static/kpi.js +94 -94
  55. package/dist/worker/observe/static/relations.js +133 -128
  56. package/dist/worker/observe/static/router.js +93 -85
  57. package/dist/worker/observe/static/run-processing.js +148 -148
  58. package/dist/worker/observe/static/shell-chrome.js +68 -68
  59. package/dist/worker/observe/static/state.js +253 -253
  60. package/dist/worker/observe/static/styles.css +1902 -1890
  61. package/dist/worker/observe/static/views/batch.js +227 -226
  62. package/dist/worker/observe/static/views/dag-graph.js +172 -172
  63. package/dist/worker/observe/static/views/dag-inspector.js +607 -477
  64. package/dist/worker/observe/static/views/dag.js +362 -362
  65. package/dist/worker/observe/static/views/dashboard.js +445 -442
  66. package/dist/worker/observe/static/views/failures.js +143 -143
  67. package/dist/worker/observe/static/views/feature.js +492 -453
  68. package/dist/worker/observe/static/views/pool.js +350 -347
  69. package/dist/worker/observe/static/views/run.js +453 -453
  70. package/dist/worker/observe/static/views/session-timeline.js +205 -205
  71. package/dist/worker/observe/static/views/shell.js +7 -7
  72. package/dist/worker/observe/static/views/task.js +314 -260
  73. package/dist/worker/observe/static/views/timeline.js +163 -163
  74. package/dist/worker/pool/doctor.js +165 -0
  75. package/dist/worker/pool/migrate-state.js +303 -0
  76. package/dist/worker/pool/run-store.js +205 -17
  77. package/dist/worker/pool/types.js +17 -1
  78. package/dist/worker/pool/validation.js +100 -15
  79. package/dist/worker/report/morning-report.js +12 -2
  80. package/dist/worker/runner/run-ready.js +41 -26
  81. package/dist/worker/task-graph/ready-planner.js +136 -0
  82. package/dist/workflows/dag/backend-test-analysis-contract.js +120 -0
  83. package/dist/workflows/dag/canvas-observer.js +275 -275
  84. package/dist/workflows/dag/convergence/controller.js +16 -8
  85. package/dist/workflows/dag/dynamic-runtime/map.js +90 -2
  86. package/dist/workflows/dag/failure-routing.js +12 -1
  87. package/dist/workflows/dag/init-hybrid.js +2404 -360
  88. package/dist/workflows/dag/node-execution.js +9 -0
  89. package/dist/workflows/dag/prompt.js +9 -0
  90. package/dist/workflows/dag/report.js +35 -1
  91. package/dist/workflows/dag/runner.js +28 -2
  92. package/dist/workflows/dag/task-demand-routing.js +383 -0
  93. package/dist/workflows/dag/types.js +51 -13
  94. package/dist/workflows/dag/upstream-artifacts.js +1 -0
  95. package/dist/workflows/dag/validate.js +59 -1
  96. package/docs/README.md +106 -104
  97. package/docs/agent-dag-recovery-playbook.md +195 -184
  98. package/docs/agent-dag-runner.md +67 -67
  99. package/docs/architecture/README.md +26 -26
  100. package/docs/architecture/dag-execution.md +140 -140
  101. package/docs/architecture/evolution.md +54 -53
  102. package/docs/architecture/facts-and-state.md +71 -58
  103. package/docs/architecture/runtime-boundaries.md +191 -191
  104. package/docs/architecture/system-overview.md +93 -93
  105. package/docs/architecture/worker-and-feature.md +85 -81
  106. package/docs/cursor-prompt-sidecar.md +36 -36
  107. package/docs/decisions/README.md +18 -15
  108. package/docs/design/README.md +167 -77
  109. package/docs/development-principles.md +73 -73
  110. package/docs/exec-plans/README.md +6 -6
  111. package/docs/exec-plans/active/README.md +15 -9
  112. package/docs/exec-plans/completed/README.md +85 -73
  113. package/docs/feature-workflow.md +389 -261
  114. package/docs/harness-methodology-debugging.md +153 -153
  115. package/docs/harness-methodology-tdd.md +130 -130
  116. package/docs/harness-methodology-verification.md +27 -27
  117. package/docs/init-surface.manifest.json +289 -280
  118. package/docs/loop-agent-harness.md +142 -130
  119. package/docs/production-readiness.md +96 -96
  120. package/docs/progress/README.md +64 -54
  121. package/docs/reports/README.md +117 -94
  122. package/docs/skills/README.md +7 -7
  123. package/docs/skills/vetted-skill-registry.md +29 -27
  124. package/docs/templates/adr.md +60 -60
  125. package/docs/templates/agent-dag-authority-surface-audit.prompt.md +94 -94
  126. package/docs/templates/agent-dag-decision-envelope.schema.json +213 -213
  127. package/docs/templates/agent-dag-decision-gate-dogfood-report.md +117 -117
  128. package/docs/templates/agent-dag-decision-gate.prompt.md +246 -246
  129. package/docs/templates/agent-dag-process-supervisor.prompt.md +98 -98
  130. package/docs/templates/agent-dag-report.schema.json +473 -473
  131. package/docs/templates/agent-dag-review-verdict.prompt.md +68 -68
  132. package/docs/templates/agent-dag.base.json +190 -190
  133. package/docs/templates/agent-dag.final-verification.json +185 -185
  134. package/docs/templates/agent-dag.schema.json +411 -383
  135. package/docs/templates/agent-dag.supervised-implementation.json +501 -501
  136. package/docs/templates/backend-test-analysis.schema.json +44 -0
  137. package/docs/templates/backend-test-dag.generate-pytest.prompt.md +202 -139
  138. package/docs/templates/backend-test-dag.json +311 -276
  139. package/docs/templates/backend-test-dag.retrospect.prompt.md +125 -125
  140. package/docs/templates/backend-test-dag.review-cases.prompt.md +81 -81
  141. package/docs/templates/exec-plan.md +64 -64
  142. package/docs/templates/feature-spec.md +53 -53
  143. package/docs/templates/frontend-design-contract.md +42 -33
  144. package/docs/templates/frontend-task-constraints.md +35 -25
  145. package/docs/templates/frontend-task-requirement.md +70 -61
  146. package/docs/templates/frontend-test-dag.generate-cases.prompt.md +5 -0
  147. package/docs/templates/frontend-test-dag.json +23 -0
  148. package/docs/templates/frontend-test-dag.retrieve-context.prompt.md +3 -0
  149. package/docs/templates/frontend-test-dag.retrospect.prompt.md +3 -0
  150. package/docs/templates/frontend-test-dag.review-cases.prompt.md +3 -0
  151. package/docs/templates/frontend-test-dag.review-execution.prompt.md +3 -0
  152. package/docs/templates/harness.schema.json +221 -221
  153. package/docs/templates/hybrid-dag.json +188 -188
  154. package/docs/templates/init-evolution-review.md +35 -35
  155. package/docs/templates/interactive-ui-round2-experiment.md +66 -66
  156. package/docs/templates/knowledge-graph-bootstrap-dag.json +118 -0
  157. package/docs/templates/knowledge-sync-dag.json +178 -0
  158. package/docs/templates/knowledge-sync-draft.schema.json +71 -0
  159. package/docs/templates/product-line/AGENTS.md +8 -8
  160. package/docs/templates/product-line/README.md +9 -9
  161. package/docs/templates/product-line/acceptance.yaml +14 -14
  162. package/docs/templates/product-line/closeout.yaml +9 -9
  163. package/docs/templates/product-line/design.md +13 -13
  164. package/docs/templates/product-line/links.md +10 -10
  165. package/docs/templates/product-line/requirement.md +17 -17
  166. package/docs/templates/product-line/task-graph.yaml +15 -15
  167. package/docs/templates/product-line/task.yaml +64 -64
  168. package/docs/templates/product-line/test-plan.md +7 -7
  169. package/docs/templates/production-readiness-checklist.md +57 -57
  170. package/docs/templates/progress-log.md +17 -17
  171. package/docs/templates/project-start-checklist.md +9 -9
  172. package/docs/templates/qa-report.md +48 -48
  173. package/docs/templates/sprint-contract.md +29 -29
  174. package/docs/templates/worker-dogfood-evidence.md +80 -80
  175. package/docs/templates/worker-dogfood-setup.md +68 -68
  176. package/docs/verification-matrix.md +70 -66
  177. package/examples/decision-gate-agent-dag.json +177 -177
  178. package/examples/example-dag.json +46 -46
  179. package/examples/hybrid-loop-agent-dag.json +189 -189
  180. package/harness.json +66 -66
  181. package/package.json +88 -46
  182. package/scripts/check-product-line-docs.sh +29 -29
  183. package/scripts/check-task-pool-root.sh +32 -32
  184. package/scripts/kb-bootstrap-init-skeleton.sh +240 -0
  185. package/scripts/kb-graph-incremental-prepare.mjs +386 -0
  186. package/scripts/kb-graph-incremental-prepare.sh +5 -0
  187. package/scripts/kb-graph-materialize.mjs +105 -0
  188. package/scripts/kb-graph-materialize.sh +4 -0
  189. package/scripts/kb-graph-promote.mjs +164 -0
  190. package/scripts/kb-graph-promote.sh +4 -0
  191. package/scripts/kb-query.mjs +554 -0
  192. package/scripts/kb-query.sh +5 -0
  193. package/skills/agent-worker/SKILL.md +39 -37
  194. package/skills/agent-worker/references/agent-worker-operator.md +60 -43
  195. package/skills/ai-engineering-context/SKILL.md +48 -48
  196. package/skills/analyze-product-dependencies/SKILL.md +67 -0
  197. package/skills/analyze-product-dependencies/agents/openai.yaml +4 -0
  198. package/skills/analyze-product-dependencies/references/api-documentation-schema.md +30 -0
  199. package/skills/analyze-product-dependencies/references/dependency-analysis-schema.md +28 -0
  200. package/skills/analyze-product-dependencies/references/example.md +76 -0
  201. package/skills/analyze-product-dependencies/references/forward-test-cases.md +35 -0
  202. package/skills/analyze-product-dependencies/references/input-contract.md +11 -0
  203. package/skills/analyze-product-dependencies/references/scouting-rules.md +61 -0
  204. package/skills/analyze-product-dependencies/scripts/test-validators.mjs +267 -0
  205. package/skills/analyze-product-dependencies/scripts/validate-api-documentation.mjs +101 -0
  206. package/skills/analyze-product-dependencies/scripts/validate-dependency-analysis.mjs +142 -0
  207. package/skills/analyze-product-dependencies/scripts/validate-product-requirement-input.mjs +76 -0
  208. package/skills/analyze-product-dependencies/scripts/validation-helpers.mjs +146 -0
  209. package/skills/analyze-product-requirements/SKILL.md +90 -0
  210. package/skills/analyze-product-requirements/agents/openai.yaml +4 -0
  211. package/skills/analyze-product-requirements/references/acceptance-criteria.md +91 -0
  212. package/skills/analyze-product-requirements/references/clarification-and-knowledge.md +56 -0
  213. package/skills/analyze-product-requirements/references/example.md +86 -0
  214. package/skills/analyze-product-requirements/references/forward-test-cases.md +66 -0
  215. package/skills/analyze-product-requirements/references/product-analysis-schema.md +32 -0
  216. package/skills/analyze-product-requirements/references/product-requirement-schema.md +33 -0
  217. package/skills/analyze-product-requirements/references/requirement-clarification-schema.md +35 -0
  218. package/skills/analyze-product-requirements/scripts/test-validators.mjs +193 -0
  219. package/skills/analyze-product-requirements/scripts/validate-product-analysis.mjs +69 -0
  220. package/skills/analyze-product-requirements/scripts/validate-product-requirement.mjs +97 -0
  221. package/skills/analyze-product-requirements/scripts/validate-requirement-clarification.mjs +98 -0
  222. package/skills/analyze-product-requirements/scripts/validation-helpers.mjs +156 -0
  223. package/skills/code-review-core/SKILL.md +20 -20
  224. package/skills/codebase-scout/SKILL.md +19 -19
  225. package/skills/frontend-design-review/SKILL.md +66 -59
  226. package/skills/frontend-design-review/references/review-checklist.md +58 -37
  227. package/skills/frontend-implementation/SKILL.md +47 -51
  228. package/skills/frontend-implementation/references/code-standards.md +32 -34
  229. package/skills/frontend-implementation/references/design-spec.md +46 -46
  230. package/skills/frontend-implementation/references/node-contracts.md +76 -32
  231. package/skills/frontend-review/SKILL.md +59 -53
  232. package/skills/frontend-review/references/review-findings.md +47 -42
  233. package/skills/frontend-verification/SKILL.md +53 -40
  234. package/skills/frontend-verification/references/verification-checklist.md +68 -56
  235. package/skills/grill-me/SKILL.md +10 -10
  236. package/skills/grill-with-docs/SKILL.md +88 -88
  237. package/skills/grill-with-docs/adr-format.md +47 -47
  238. package/skills/grill-with-docs/context-format.md +60 -60
  239. package/skills/init-capability-evolution/SKILL.md +70 -70
  240. package/skills/loop-agent/SKILL.md +151 -151
  241. package/skills/loop-agent/references/README.md +67 -67
  242. package/skills/loop-agent/references/command-reference.md +505 -452
  243. package/skills/loop-agent/references/docs-converge.md +126 -126
  244. package/skills/loop-agent/references/harness-policy.md +263 -263
  245. package/skills/loop-agent/references/hybrid-dag.md +238 -233
  246. package/skills/loop-agent/references/learned/README.md +21 -21
  247. package/skills/loop-agent/references/long-running-loop.md +57 -57
  248. package/skills/loop-agent/references/model-routing.md +36 -36
  249. package/skills/loop-agent/references/multi-worktree.md +54 -54
  250. package/skills/loop-agent/references/one-shot-runs.md +85 -85
  251. package/skills/loop-agent/references/orchestrator-and-interventions.md +169 -169
  252. package/skills/loop-agent/references/pi-prompt.md +23 -23
  253. package/skills/loop-agent/references/pi-subagent-assisted-mode.md +84 -84
  254. package/skills/loop-agent/references/post-implementation-and-patterns.md +44 -44
  255. package/skills/loop-agent/references/task-workflow.md +89 -89
  256. package/skills/loop-agent/references/verification-and-failure-handling.md +139 -139
  257. package/skills/playwright-cli/SKILL.md +420 -0
  258. package/skills/playwright-cli/references/element-attributes.md +23 -0
  259. package/skills/playwright-cli/references/playwright-tests.md +39 -0
  260. package/skills/playwright-cli/references/request-mocking.md +87 -0
  261. package/skills/playwright-cli/references/running-code.md +241 -0
  262. package/skills/playwright-cli/references/session-management.md +225 -0
  263. package/skills/playwright-cli/references/storage-state.md +275 -0
  264. package/skills/playwright-cli/references/test-generation.md +433 -0
  265. package/skills/playwright-cli/references/tracing.md +139 -0
  266. package/skills/playwright-cli/references/video-recording.md +143 -0
  267. package/skills/playwright-cli-case-generator/SKILL.md +74 -0
  268. package/skills/requesting-code-review/SKILL.md +101 -101
  269. package/skills/requesting-code-review/code-reviewer.md +168 -168
  270. package/skills/systematic-debugging/CREATION-LOG.md +119 -119
  271. package/skills/systematic-debugging/SKILL.md +296 -296
  272. package/skills/systematic-debugging/condition-based-waiting-example.ts +158 -158
  273. package/skills/systematic-debugging/condition-based-waiting.md +115 -115
  274. package/skills/systematic-debugging/defense-in-depth.md +122 -122
  275. package/skills/systematic-debugging/find-polluter.sh +63 -63
  276. package/skills/systematic-debugging/root-cause-tracing.md +169 -169
  277. package/skills/systematic-debugging/test-academic.md +14 -14
  278. package/skills/systematic-debugging/test-pressure-1.md +58 -58
  279. package/skills/systematic-debugging/test-pressure-2.md +68 -68
  280. package/skills/systematic-debugging/test-pressure-3.md +69 -69
  281. package/skills/test-driven-development/SKILL.md +20 -20
  282. package/skills/using-git-worktrees/SKILL.md +215 -215
  283. package/skills/verification-before-completion/SKILL.md +154 -154
  284. package/skills/webapp-testing/SKILL.md +19 -19
@@ -195,280 +195,280 @@ export function createDagCanvasObserver(opts) {
195
195
  flush: () => writer.flush(),
196
196
  };
197
197
  }
198
- const CANVAS_HEADER = `/* AUTO-GENERATED by . run-dag canvas observer. Derived view only — canonical state lives in .harness/dag-runs/. */
199
- import {
200
- Card,
201
- CardBody,
202
- CardHeader,
203
- Divider,
204
- Grid,
205
- H1,
206
- H2,
207
- Pill,
208
- Row,
209
- Stack,
210
- Stat,
211
- Text,
212
- computeDAGLayout,
213
- useHostTheme,
214
- } from 'cursor/canvas';
215
- import { useMemo } from 'react';
216
-
217
- type TaskStatus = 'PENDING' | 'RUNNING' | 'FINISHED' | 'ERROR' | 'SKIPPED';
218
- type Complexity = 'HIGH' | 'MED' | 'LOW';
219
- type Executor = 'cursor' | 'pi' | 'shell' | 'static';
220
-
221
- interface TaskState {
222
- id: string;
223
- depends_on: string[];
224
- complexity: Complexity;
225
- executor: Executor;
226
- subtask_prompt: string;
227
- status: TaskStatus;
228
- model: string;
229
- startedAt?: number;
230
- finishedAt?: number;
231
- resultText?: string;
232
- errorMessage?: string;
233
- inputTokens?: number;
234
- outputTokens?: number;
235
- durationMs?: number;
236
- skippedReason?: string;
237
- }
238
-
239
- interface RunState {
240
- title: string;
241
- runId: string;
242
- startedAt: number;
243
- finishedAt?: number;
244
- runOutcome?: 'SUCCESS' | 'FAILED' | 'INTERRUPTED' | 'PAUSED';
245
- runMessage?: string;
246
- tasks: TaskState[];
198
+ const CANVAS_HEADER = `/* AUTO-GENERATED by . run-dag canvas observer. Derived view only — canonical state lives in .harness/dag-runs/. */
199
+ import {
200
+ Card,
201
+ CardBody,
202
+ CardHeader,
203
+ Divider,
204
+ Grid,
205
+ H1,
206
+ H2,
207
+ Pill,
208
+ Row,
209
+ Stack,
210
+ Stat,
211
+ Text,
212
+ computeDAGLayout,
213
+ useHostTheme,
214
+ } from 'cursor/canvas';
215
+ import { useMemo } from 'react';
216
+
217
+ type TaskStatus = 'PENDING' | 'RUNNING' | 'FINISHED' | 'ERROR' | 'SKIPPED';
218
+ type Complexity = 'HIGH' | 'MED' | 'LOW';
219
+ type Executor = 'cursor' | 'pi' | 'shell' | 'static';
220
+
221
+ interface TaskState {
222
+ id: string;
223
+ depends_on: string[];
224
+ complexity: Complexity;
225
+ executor: Executor;
226
+ subtask_prompt: string;
227
+ status: TaskStatus;
228
+ model: string;
229
+ startedAt?: number;
230
+ finishedAt?: number;
231
+ resultText?: string;
232
+ errorMessage?: string;
233
+ inputTokens?: number;
234
+ outputTokens?: number;
235
+ durationMs?: number;
236
+ skippedReason?: string;
237
+ }
238
+
239
+ interface RunState {
240
+ title: string;
241
+ runId: string;
242
+ startedAt: number;
243
+ finishedAt?: number;
244
+ runOutcome?: 'SUCCESS' | 'FAILED' | 'INTERRUPTED' | 'PAUSED';
245
+ runMessage?: string;
246
+ tasks: TaskState[];
247
247
  }`;
248
- const CANVAS_BODY = String.raw `const NODE_W = 200;
249
- const NODE_H = 72;
250
-
251
- function pillToneFor(status: TaskStatus): 'neutral' | 'info' | 'success' | 'warning' {
252
- switch (status) {
253
- case 'PENDING':
254
- return 'neutral';
255
- case 'RUNNING':
256
- return 'info';
257
- case 'FINISHED':
258
- return 'success';
259
- case 'ERROR':
260
- return 'warning';
261
- case 'SKIPPED':
262
- return 'neutral';
263
- }
264
- }
265
-
266
- function formatDuration(ms?: number): string {
267
- if (ms === undefined) return '—';
268
- if (ms < 1000) return ms + 'ms';
269
- const s = ms / 1000;
270
- if (s < 60) return s.toFixed(1) + 's';
271
- const m = Math.floor(s / 60);
272
- const rem = Math.round(s - m * 60);
273
- return m + 'm ' + rem + 's';
274
- }
275
-
276
- function elapsed(state: RunState): number {
277
- const end = state.finishedAt ?? Date.now();
278
- return end - state.startedAt;
279
- }
280
-
281
- function DAGGraph({ state }: { state: RunState }): JSX.Element {
282
- const theme = useHostTheme();
283
- const layout = computeDAGLayout({
284
- nodes: state.tasks.map((t) => ({ id: t.id })),
285
- edges: state.tasks.flatMap((t) =>
286
- t.depends_on.map((d) => ({ from: d, to: t.id })),
287
- ),
288
- direction: 'vertical',
289
- nodeWidth: NODE_W,
290
- nodeHeight: NODE_H,
291
- rankGap: 72,
292
- nodeGap: 40,
293
- padding: 24,
294
- });
295
- const byId = new Map(state.tasks.map((t) => [t.id, t]));
296
-
297
- return (
298
- <svg width={layout.width} height={layout.height} style={{ display: 'block', maxWidth: '100%' }}>
299
- {layout.edges.map((e, i) => (
300
- <line
301
- key={'e' + i}
302
- x1={e.sourceX}
303
- y1={e.sourceY}
304
- x2={e.targetX}
305
- y2={e.targetY}
306
- stroke={theme.stroke.secondary}
307
- strokeWidth={1.25}
308
- markerEnd="url(#dag-arrow)"
309
- />
310
- ))}
311
- <defs>
312
- <marker id="dag-arrow" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="6" markerHeight="6" orient="auto-start-reverse">
313
- <path d="M 0 0 L 10 5 L 0 10 z" fill={theme.stroke.secondary} />
314
- </marker>
315
- </defs>
316
- {layout.nodes.map((n) => {
317
- const t = byId.get(n.id);
318
- if (!t) return null;
319
- return (
320
- <g key={n.id} transform={'translate(' + n.x + ',' + n.y + ')'}>
321
- <rect
322
- width={NODE_W}
323
- height={NODE_H}
324
- rx={8}
325
- ry={8}
326
- fill={theme.fill.secondary}
327
- stroke={theme.stroke.secondary}
328
- strokeWidth={t.status === 'RUNNING' ? 2 : 1}
329
- />
330
- <text x={12} y={22} fontSize={13} fontWeight={600} fill={theme.text.primary}>
331
- {t.id.length > 22 ? t.id.slice(0, 21) + '…' : t.id}
332
- </text>
333
- <text x={12} y={42} fontSize={10.5} fill={theme.text.secondary}>
334
- {t.executor} · {t.complexity} · {t.status}
335
- </text>
336
- <text x={12} y={58} fontSize={10.5} fill={theme.text.tertiary}>
337
- {formatDuration(t.durationMs)}
338
- </text>
339
- </g>
340
- );
341
- })}
342
- </svg>
343
- );
344
- }
345
-
346
- export default function DagRun(): JSX.Element {
347
- const counts = useMemo(
348
- () =>
349
- STATE.tasks.reduce(
350
- (acc, t) => {
351
- acc.total += 1;
352
- const key = t.status.toLowerCase() as 'pending' | 'running' | 'finished' | 'error' | 'skipped';
353
- if (key in acc) acc[key] += 1;
354
- return acc;
355
- },
356
- { total: 0, pending: 0, running: 0, finished: 0, error: 0, skipped: 0 },
357
- ),
358
- [],
359
- );
360
- const isFinal = STATE.finishedAt !== undefined;
361
- const statusLabel =
362
- STATE.runOutcome === 'PAUSED'
363
- ? 'PAUSED'
364
- : STATE.runOutcome === 'FAILED'
365
- ? 'FAILED'
366
- : isFinal
367
- ? 'COMPLETE'
368
- : 'RUNNING';
369
- const statusTone =
370
- STATE.runOutcome === 'FAILED'
371
- ? 'danger'
372
- : STATE.runOutcome === 'PAUSED'
373
- ? 'warning'
374
- : isFinal
375
- ? 'success'
376
- : 'info';
377
-
378
- return (
379
- <Stack gap={20}>
380
- <Stack gap={6}>
381
- <H1>{STATE.title}</H1>
382
- <Text tone="secondary" size="small">
383
- run {STATE.runId}
384
- </Text>
385
- <Row gap={10} align="center">
386
- <Pill tone={statusTone} active size="sm">
387
- {statusLabel}
388
- </Pill>
389
- <Text tone="secondary" size="small">
390
- {counts.total} tasks · elapsed {formatDuration(elapsed(STATE))}
391
- </Text>
392
- </Row>
393
- {STATE.runMessage ? (
394
- <Text tone="secondary" size="small">
395
- {STATE.runMessage}
396
- </Text>
397
- ) : null}
398
- </Stack>
399
-
400
- <Grid columns={6} gap={12}>
401
- <Stat value={String(counts.total)} label="Total" />
402
- <Stat value={String(counts.pending)} label="Pending" />
403
- <Stat value={String(counts.running)} label="Running" tone={counts.running > 0 ? 'info' : undefined} />
404
- <Stat value={String(counts.finished)} label="Finished" tone={counts.finished > 0 ? 'success' : undefined} />
405
- <Stat value={String(counts.error)} label="Errored" tone={counts.error > 0 ? 'danger' : undefined} />
406
- <Stat value={String(counts.skipped)} label="Skipped" />
407
- </Grid>
408
-
409
- <Divider />
410
-
411
- <Stack gap={12}>
412
- <H2>Graph</H2>
413
- <DAGGraph state={STATE} />
414
- </Stack>
415
-
416
- <Divider />
417
-
418
- <Stack gap={12}>
419
- <H2>Tasks</H2>
420
- <Stack gap={10}>
421
- {STATE.tasks.map((t) => (
422
- <Card key={t.id} collapsible defaultOpen={t.status !== 'PENDING'}>
423
- <CardHeader
424
- trailing={
425
- <Row gap={6} align="center">
426
- <Pill tone="neutral" size="sm">
427
- {t.executor}
428
- </Pill>
429
- <Pill tone={pillToneFor(t.status)} active={t.status !== 'PENDING'} size="sm">
430
- {t.status}
431
- </Pill>
432
- </Row>
433
- }
434
- >
435
- {t.id}
436
- </CardHeader>
437
- <CardBody>
438
- <Stack gap={8}>
439
- <Text tone="secondary" size="small">
440
- Model {t.model}
441
- {t.depends_on.length > 0 ? ' · depends on ' + t.depends_on.join(', ') : ''}
442
- {t.durationMs !== undefined ? ' · ' + formatDuration(t.durationMs) : ''}
443
- </Text>
444
- <Text size="small">
445
- <Text as="span" weight="semibold">
446
- Prompt:{' '}
447
- </Text>
448
- {t.subtask_prompt}
449
- </Text>
450
- {t.resultText ? (
451
- <pre style={{ margin: 0, whiteSpace: 'pre-wrap', wordBreak: 'break-word' }}>
452
- {t.resultText}
453
- {t.status === 'RUNNING' ? '\u2588' : ''}
454
- </pre>
455
- ) : null}
456
- {t.skippedReason ? (
457
- <Text size="small" tone="secondary">
458
- Skipped: {t.skippedReason}
459
- </Text>
460
- ) : null}
461
- {t.errorMessage ? (
462
- <Text size="small" tone="secondary">
463
- {t.errorMessage}
464
- </Text>
465
- ) : null}
466
- </Stack>
467
- </CardBody>
468
- </Card>
469
- ))}
470
- </Stack>
471
- </Stack>
472
- </Stack>
473
- );
248
+ const CANVAS_BODY = String.raw `const NODE_W = 200;
249
+ const NODE_H = 72;
250
+
251
+ function pillToneFor(status: TaskStatus): 'neutral' | 'info' | 'success' | 'warning' {
252
+ switch (status) {
253
+ case 'PENDING':
254
+ return 'neutral';
255
+ case 'RUNNING':
256
+ return 'info';
257
+ case 'FINISHED':
258
+ return 'success';
259
+ case 'ERROR':
260
+ return 'warning';
261
+ case 'SKIPPED':
262
+ return 'neutral';
263
+ }
264
+ }
265
+
266
+ function formatDuration(ms?: number): string {
267
+ if (ms === undefined) return '—';
268
+ if (ms < 1000) return ms + 'ms';
269
+ const s = ms / 1000;
270
+ if (s < 60) return s.toFixed(1) + 's';
271
+ const m = Math.floor(s / 60);
272
+ const rem = Math.round(s - m * 60);
273
+ return m + 'm ' + rem + 's';
274
+ }
275
+
276
+ function elapsed(state: RunState): number {
277
+ const end = state.finishedAt ?? Date.now();
278
+ return end - state.startedAt;
279
+ }
280
+
281
+ function DAGGraph({ state }: { state: RunState }): JSX.Element {
282
+ const theme = useHostTheme();
283
+ const layout = computeDAGLayout({
284
+ nodes: state.tasks.map((t) => ({ id: t.id })),
285
+ edges: state.tasks.flatMap((t) =>
286
+ t.depends_on.map((d) => ({ from: d, to: t.id })),
287
+ ),
288
+ direction: 'vertical',
289
+ nodeWidth: NODE_W,
290
+ nodeHeight: NODE_H,
291
+ rankGap: 72,
292
+ nodeGap: 40,
293
+ padding: 24,
294
+ });
295
+ const byId = new Map(state.tasks.map((t) => [t.id, t]));
296
+
297
+ return (
298
+ <svg width={layout.width} height={layout.height} style={{ display: 'block', maxWidth: '100%' }}>
299
+ {layout.edges.map((e, i) => (
300
+ <line
301
+ key={'e' + i}
302
+ x1={e.sourceX}
303
+ y1={e.sourceY}
304
+ x2={e.targetX}
305
+ y2={e.targetY}
306
+ stroke={theme.stroke.secondary}
307
+ strokeWidth={1.25}
308
+ markerEnd="url(#dag-arrow)"
309
+ />
310
+ ))}
311
+ <defs>
312
+ <marker id="dag-arrow" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="6" markerHeight="6" orient="auto-start-reverse">
313
+ <path d="M 0 0 L 10 5 L 0 10 z" fill={theme.stroke.secondary} />
314
+ </marker>
315
+ </defs>
316
+ {layout.nodes.map((n) => {
317
+ const t = byId.get(n.id);
318
+ if (!t) return null;
319
+ return (
320
+ <g key={n.id} transform={'translate(' + n.x + ',' + n.y + ')'}>
321
+ <rect
322
+ width={NODE_W}
323
+ height={NODE_H}
324
+ rx={8}
325
+ ry={8}
326
+ fill={theme.fill.secondary}
327
+ stroke={theme.stroke.secondary}
328
+ strokeWidth={t.status === 'RUNNING' ? 2 : 1}
329
+ />
330
+ <text x={12} y={22} fontSize={13} fontWeight={600} fill={theme.text.primary}>
331
+ {t.id.length > 22 ? t.id.slice(0, 21) + '…' : t.id}
332
+ </text>
333
+ <text x={12} y={42} fontSize={10.5} fill={theme.text.secondary}>
334
+ {t.executor} · {t.complexity} · {t.status}
335
+ </text>
336
+ <text x={12} y={58} fontSize={10.5} fill={theme.text.tertiary}>
337
+ {formatDuration(t.durationMs)}
338
+ </text>
339
+ </g>
340
+ );
341
+ })}
342
+ </svg>
343
+ );
344
+ }
345
+
346
+ export default function DagRun(): JSX.Element {
347
+ const counts = useMemo(
348
+ () =>
349
+ STATE.tasks.reduce(
350
+ (acc, t) => {
351
+ acc.total += 1;
352
+ const key = t.status.toLowerCase() as 'pending' | 'running' | 'finished' | 'error' | 'skipped';
353
+ if (key in acc) acc[key] += 1;
354
+ return acc;
355
+ },
356
+ { total: 0, pending: 0, running: 0, finished: 0, error: 0, skipped: 0 },
357
+ ),
358
+ [],
359
+ );
360
+ const isFinal = STATE.finishedAt !== undefined;
361
+ const statusLabel =
362
+ STATE.runOutcome === 'PAUSED'
363
+ ? 'PAUSED'
364
+ : STATE.runOutcome === 'FAILED'
365
+ ? 'FAILED'
366
+ : isFinal
367
+ ? 'COMPLETE'
368
+ : 'RUNNING';
369
+ const statusTone =
370
+ STATE.runOutcome === 'FAILED'
371
+ ? 'danger'
372
+ : STATE.runOutcome === 'PAUSED'
373
+ ? 'warning'
374
+ : isFinal
375
+ ? 'success'
376
+ : 'info';
377
+
378
+ return (
379
+ <Stack gap={20}>
380
+ <Stack gap={6}>
381
+ <H1>{STATE.title}</H1>
382
+ <Text tone="secondary" size="small">
383
+ run {STATE.runId}
384
+ </Text>
385
+ <Row gap={10} align="center">
386
+ <Pill tone={statusTone} active size="sm">
387
+ {statusLabel}
388
+ </Pill>
389
+ <Text tone="secondary" size="small">
390
+ {counts.total} tasks · elapsed {formatDuration(elapsed(STATE))}
391
+ </Text>
392
+ </Row>
393
+ {STATE.runMessage ? (
394
+ <Text tone="secondary" size="small">
395
+ {STATE.runMessage}
396
+ </Text>
397
+ ) : null}
398
+ </Stack>
399
+
400
+ <Grid columns={6} gap={12}>
401
+ <Stat value={String(counts.total)} label="Total" />
402
+ <Stat value={String(counts.pending)} label="Pending" />
403
+ <Stat value={String(counts.running)} label="Running" tone={counts.running > 0 ? 'info' : undefined} />
404
+ <Stat value={String(counts.finished)} label="Finished" tone={counts.finished > 0 ? 'success' : undefined} />
405
+ <Stat value={String(counts.error)} label="Errored" tone={counts.error > 0 ? 'danger' : undefined} />
406
+ <Stat value={String(counts.skipped)} label="Skipped" />
407
+ </Grid>
408
+
409
+ <Divider />
410
+
411
+ <Stack gap={12}>
412
+ <H2>Graph</H2>
413
+ <DAGGraph state={STATE} />
414
+ </Stack>
415
+
416
+ <Divider />
417
+
418
+ <Stack gap={12}>
419
+ <H2>Tasks</H2>
420
+ <Stack gap={10}>
421
+ {STATE.tasks.map((t) => (
422
+ <Card key={t.id} collapsible defaultOpen={t.status !== 'PENDING'}>
423
+ <CardHeader
424
+ trailing={
425
+ <Row gap={6} align="center">
426
+ <Pill tone="neutral" size="sm">
427
+ {t.executor}
428
+ </Pill>
429
+ <Pill tone={pillToneFor(t.status)} active={t.status !== 'PENDING'} size="sm">
430
+ {t.status}
431
+ </Pill>
432
+ </Row>
433
+ }
434
+ >
435
+ {t.id}
436
+ </CardHeader>
437
+ <CardBody>
438
+ <Stack gap={8}>
439
+ <Text tone="secondary" size="small">
440
+ Model {t.model}
441
+ {t.depends_on.length > 0 ? ' · depends on ' + t.depends_on.join(', ') : ''}
442
+ {t.durationMs !== undefined ? ' · ' + formatDuration(t.durationMs) : ''}
443
+ </Text>
444
+ <Text size="small">
445
+ <Text as="span" weight="semibold">
446
+ Prompt:{' '}
447
+ </Text>
448
+ {t.subtask_prompt}
449
+ </Text>
450
+ {t.resultText ? (
451
+ <pre style={{ margin: 0, whiteSpace: 'pre-wrap', wordBreak: 'break-word' }}>
452
+ {t.resultText}
453
+ {t.status === 'RUNNING' ? '\u2588' : ''}
454
+ </pre>
455
+ ) : null}
456
+ {t.skippedReason ? (
457
+ <Text size="small" tone="secondary">
458
+ Skipped: {t.skippedReason}
459
+ </Text>
460
+ ) : null}
461
+ {t.errorMessage ? (
462
+ <Text size="small" tone="secondary">
463
+ {t.errorMessage}
464
+ </Text>
465
+ ) : null}
466
+ </Stack>
467
+ </CardBody>
468
+ </Card>
469
+ ))}
470
+ </Stack>
471
+ </Stack>
472
+ </Stack>
473
+ );
474
474
  }`;
@@ -2,7 +2,7 @@ import { access, appendFile, cp, mkdir } from "node:fs/promises";
2
2
  import path from "node:path";
3
3
  import { parseProcessVerdict } from "../node-execution.js";
4
4
  import { freshNodeRecord } from "../dynamic-runtime/shared.js";
5
- const CONVERGENCE_CHAIN_NODE_IDS = [
5
+ const DEFAULT_CONVERGENCE_CHAIN_NODE_IDS = [
6
6
  "process-supervisor-pi",
7
7
  "process-gate-shell",
8
8
  "repair-pi",
@@ -29,7 +29,7 @@ export async function runConvergencePassController(input) {
29
29
  convergence.terminalReason = "feature-flag-off";
30
30
  return { retry: false };
31
31
  }
32
- if (!hasConvergenceChain(input.tasksById)) {
32
+ if (!hasConvergenceChain(input.tasksById, input.spec)) {
33
33
  convergence.terminalReason = "unsupported-dag-shape";
34
34
  return { retry: false };
35
35
  }
@@ -54,6 +54,7 @@ export async function runConvergencePassController(input) {
54
54
  reason: "hard-verify-failed",
55
55
  state: input.state,
56
56
  runDir: input.runDir,
57
+ spec: input.spec,
57
58
  });
58
59
  if (CONVERGENCE_NON_RETRY_FAILURES.has(hardFailure)) {
59
60
  passRecord.status = "terminal";
@@ -96,8 +97,12 @@ export async function runConvergencePassController(input) {
96
97
  await input.persistState();
97
98
  return { retry: true };
98
99
  }
99
- function hasConvergenceChain(tasksById) {
100
- return CONVERGENCE_CHAIN_NODE_IDS.every((id) => tasksById.has(id));
100
+ function getConvergenceChain(spec) {
101
+ return spec.convergence?.chainNodeIds ?? DEFAULT_CONVERGENCE_CHAIN_NODE_IDS;
102
+ }
103
+ function hasConvergenceChain(tasksById, spec) {
104
+ const chain = getConvergenceChain(spec);
105
+ return chain.every((id) => tasksById.has(id));
101
106
  }
102
107
  async function buildConvergencePassRecord(input) {
103
108
  const hardVerify = input.state.nodes["hard-verify-shell"];
@@ -122,13 +127,14 @@ async function buildConvergencePassRecord(input) {
122
127
  pass: input.pass,
123
128
  state: input.state,
124
129
  runDir: input.runDir,
130
+ spec: input.spec,
125
131
  }),
126
132
  };
127
133
  }
128
134
  async function preserveConvergencePassArtifacts(input) {
129
135
  const passDir = path.join(input.runDir, "convergence", `pass-${input.pass}`);
130
136
  await mkdir(passDir, { recursive: true });
131
- const nodeIds = nodesToPreserveForConvergence(input.state);
137
+ const nodeIds = nodesToPreserveForConvergence(input.state, input.spec);
132
138
  const refs = [];
133
139
  for (const nodeId of nodeIds) {
134
140
  const node = input.state.nodes[nodeId];
@@ -151,8 +157,9 @@ async function preserveConvergencePassArtifacts(input) {
151
157
  }
152
158
  return refs;
153
159
  }
154
- function nodesToPreserveForConvergence(state) {
155
- return CONVERGENCE_CHAIN_NODE_IDS.filter((nodeId) => state.nodes[nodeId]);
160
+ function nodesToPreserveForConvergence(state, spec) {
161
+ const chain = getConvergenceChain(spec);
162
+ return chain.filter((nodeId) => state.nodes[nodeId]);
156
163
  }
157
164
  async function copyIfExists(from, to) {
158
165
  try {
@@ -242,7 +249,8 @@ function extractSupervisorStructuredBlock(node) {
242
249
  return block;
243
250
  }
244
251
  async function resetConvergenceNodesForNextPass(input) {
245
- const resetIds = new Set(CONVERGENCE_CHAIN_NODE_IDS);
252
+ const chain = getConvergenceChain(input.spec);
253
+ const resetIds = new Set(chain);
246
254
  for (const id of collectTransitiveDescendantTaskIds(input.spec, "hard-verify-shell")) {
247
255
  const node = input.state.nodes[id];
248
256
  if (node?.status === "SKIPPED")