@piagent/platform 1.5.5 → 1.6.1

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 (323) hide show
  1. package/CHANGELOG.md +166 -0
  2. package/README.md +25 -21
  3. package/README.vi.md +34 -5
  4. package/adapters/web-frontend/profile.json +2 -4
  5. package/architecture/layers.json +18 -3
  6. package/benchmarks/deep-logic-v1/SPECIALIST_PROTOCOL.vi.md +122 -0
  7. package/benchmarks/deep-logic-v1/grade.mjs +272 -10
  8. package/benchmarks/deep-logic-v1/project/apps/admin/src/billing-summary.js +3 -0
  9. package/benchmarks/deep-logic-v1/project/benchmark-contract/public-smoke.test.js +166 -0
  10. package/benchmarks/deep-logic-v1/project/package.json +1 -1
  11. package/benchmarks/deep-logic-v1/project/packages/billing/src/close-period.js +3 -0
  12. package/benchmarks/deep-logic-v1/project/packages/billing/src/plan-timeline.js +3 -0
  13. package/benchmarks/deep-logic-v1/project/test/smoke.test.js +7 -1
  14. package/benchmarks/deep-logic-v1/prompts/budgeted-context-graph.md +2 -0
  15. package/benchmarks/deep-logic-v1/prompts/fair-dependency-scheduler.md +2 -0
  16. package/benchmarks/deep-logic-v1/prompts/layered-policy-resolution.md +2 -0
  17. package/benchmarks/deep-logic-v1/prompts/resumable-stream-assembly.md +3 -1
  18. package/benchmarks/deep-logic-v1/prompts/revision-event-reconciliation.md +2 -0
  19. package/benchmarks/deep-logic-v1/prompts/temporal-usage-billing-close.md +123 -0
  20. package/benchmarks/deep-logic-v1/prompts/transactional-config-merge.md +2 -0
  21. package/benchmarks/deep-logic-v1/suite.json +51 -3
  22. package/benchmarks/deep-logic-v1/variant.mjs +22 -1
  23. package/benchmarks/production-v1/spend-control.v1.json +92 -0
  24. package/benchmarks/production-v1/suite.json +46 -3
  25. package/catalog/capabilities.json +18 -18
  26. package/docs/authority-manifest.md +1 -1
  27. package/docs/auto-delegation-policy.md +38 -73
  28. package/docs/command-reference-vietnamese.md +27 -35
  29. package/docs/context-engine.md +12 -4
  30. package/docs/context-window-policy.md +37 -1
  31. package/docs/distribution-standard.md +7 -7
  32. package/docs/en/architecture.md +27 -13
  33. package/docs/languages.json +4 -4
  34. package/docs/model-options.md +8 -5
  35. package/docs/operator-manual-vietnamese.md +27 -45
  36. package/docs/project-adapters.md +2 -2
  37. package/docs/publishing-for-teams.md +10 -0
  38. package/docs/quality-benchmark.md +427 -62
  39. package/docs/release-install-policy.md +10 -9
  40. package/docs/runtime-harness-standard.md +3 -3
  41. package/docs/runtime-policy-design.md +4 -4
  42. package/docs/runtime-quality-baseline.md +13 -6
  43. package/docs/security-threat-model.md +2 -2
  44. package/docs/subagent-orchestration-capabilities.md +19 -51
  45. package/docs/subagents-and-multiagent.md +21 -47
  46. package/docs/task-implementation-contract.md +3 -3
  47. package/docs/task-lifecycle-vietnamese.md +3 -3
  48. package/docs/team-onboarding.md +2 -2
  49. package/docs/usage-observability.md +7 -2
  50. package/docs/vi/architecture.md +27 -13
  51. package/docs-site/architecture.html +1 -1
  52. package/docs-site/benchmark.html +89 -95
  53. package/docs-site/commands.html +1 -1
  54. package/docs-site/content/benchmark.html +88 -94
  55. package/docs-site/content/en/benchmark.html +134 -90
  56. package/docs-site/content/en/index.html +19 -19
  57. package/docs-site/content/en/runtime.html +4 -4
  58. package/docs-site/content/en/whats-new.html +12 -1
  59. package/docs-site/content/en/workflows.html +2 -2
  60. package/docs-site/content/index.html +19 -19
  61. package/docs-site/content/runtime.html +4 -4
  62. package/docs-site/content/whats-new.html +12 -1
  63. package/docs-site/content/workflows.html +2 -2
  64. package/docs-site/context-engine.html +1 -1
  65. package/docs-site/en/architecture.html +1 -1
  66. package/docs-site/en/benchmark.html +135 -91
  67. package/docs-site/en/commands.html +1 -1
  68. package/docs-site/en/context-engine.html +1 -1
  69. package/docs-site/en/index.html +20 -20
  70. package/docs-site/en/mcp-approval.html +1 -1
  71. package/docs-site/en/mcp-auth.html +1 -1
  72. package/docs-site/en/mcp-servers.html +1 -1
  73. package/docs-site/en/mcp.html +1 -1
  74. package/docs-site/en/permissions.html +1 -1
  75. package/docs-site/en/profiles.html +1 -1
  76. package/docs-site/en/quickstart.html +1 -1
  77. package/docs-site/en/runtime.html +5 -5
  78. package/docs-site/en/scope.html +1 -1
  79. package/docs-site/en/security.html +1 -1
  80. package/docs-site/en/team.html +1 -1
  81. package/docs-site/en/whats-new.html +13 -2
  82. package/docs-site/en/workflows.html +3 -3
  83. package/docs-site/index.html +20 -20
  84. package/docs-site/mcp-approval.html +1 -1
  85. package/docs-site/mcp-auth.html +1 -1
  86. package/docs-site/mcp-servers.html +1 -1
  87. package/docs-site/mcp.html +1 -1
  88. package/docs-site/permissions.html +1 -1
  89. package/docs-site/profiles.html +1 -1
  90. package/docs-site/quickstart.html +1 -1
  91. package/docs-site/runtime.html +5 -5
  92. package/docs-site/scope.html +1 -1
  93. package/docs-site/security.html +1 -1
  94. package/docs-site/team.html +1 -1
  95. package/docs-site/whats-new.html +13 -2
  96. package/docs-site/workflows.html +3 -3
  97. package/evals/fixtures/benchmark-assurance-evidence.invalid.json +1 -1
  98. package/evals/fixtures/benchmark-assurance-evidence.valid.json +1 -1
  99. package/evals/fixtures/codex-relative-efficiency-v1.invalid.json +4 -0
  100. package/evals/fixtures/codex-relative-efficiency-v1.valid.json +94 -0
  101. package/evals/fixtures/helper-request.invalid.json +1 -1
  102. package/evals/fixtures/helper-request.valid.json +1 -1
  103. package/evals/fixtures/piagent-webui/session-live-state-v1.invalid.json +18 -0
  104. package/evals/fixtures/piagent-webui/session-live-state-v1.valid.json +27 -0
  105. package/evals/fixtures/piagent-webui/subagent-tree-v1.valid.json +7 -0
  106. package/evals/fixtures/task-authority-snapshot.valid.json +4 -4
  107. package/evals/fs4-readiness-matrix.v1.json +2 -2
  108. package/evals/fs5-causal-arm.v1.json +3 -3
  109. package/evals/fs5-pilot-protocol.v1.json +3 -3
  110. package/evals/fs5-pilot-protocol.v2.json +8 -8
  111. package/evals/fs5-pilot-protocol.v3.json +8 -8
  112. package/evals/fs5-pilot-protocol.v4.json +7 -6
  113. package/evals/fs5-pilot-protocol.v5.json +9 -7
  114. package/evals/private-holdout-v1/public-exposure.v1.json +1 -1
  115. package/evals/runtime-conformance-v1/README.md +43 -0
  116. package/evals/runtime-conformance-v1/evaluate-paid-canary.mjs +198 -0
  117. package/evals/runtime-conformance-v1/lane.json +57 -0
  118. package/evals/runtime-conformance-v1/paid-canary.json +31 -0
  119. package/evals/runtime-conformance-v1/runner.mjs +456 -0
  120. package/package.json +3 -1
  121. package/packages/piagent-core/README.md +13 -4
  122. package/packages/piagent-core/benchmark/benchmark-assurance.js +4 -1
  123. package/packages/piagent-core/benchmark/benchmark-bootstrap.js +91 -9
  124. package/packages/piagent-core/benchmark/benchmark-claim-restrictions.js +38 -7
  125. package/packages/piagent-core/benchmark/benchmark-cli.js +7 -7
  126. package/packages/piagent-core/benchmark/benchmark-codex-relative-efficiency.js +698 -0
  127. package/packages/piagent-core/benchmark/benchmark-codex.js +3 -1
  128. package/packages/piagent-core/benchmark/benchmark-comparison.js +271 -2
  129. package/packages/piagent-core/benchmark/benchmark-core.js +736 -664
  130. package/packages/piagent-core/benchmark/benchmark-execution-guard.js +7 -5
  131. package/packages/piagent-core/benchmark/benchmark-forensics.js +441 -4
  132. package/packages/piagent-core/benchmark/benchmark-host-readiness.js +639 -0
  133. package/packages/piagent-core/benchmark/benchmark-matrix.js +22 -4
  134. package/packages/piagent-core/benchmark/benchmark-normalized-cost.js +317 -0
  135. package/packages/piagent-core/benchmark/benchmark-preflight.js +5 -1
  136. package/packages/piagent-core/benchmark/benchmark-process.js +6 -5
  137. package/packages/piagent-core/benchmark/benchmark-provider-free-evidence.js +345 -0
  138. package/packages/piagent-core/benchmark/benchmark-provider-wire.js +126 -0
  139. package/packages/piagent-core/benchmark/benchmark-record-validation.js +252 -0
  140. package/packages/piagent-core/benchmark/benchmark-report.js +130 -12
  141. package/packages/piagent-core/benchmark/benchmark-resume-recovery.js +14 -0
  142. package/packages/piagent-core/benchmark/benchmark-runner-policy.js +26 -0
  143. package/packages/piagent-core/benchmark/benchmark-runtime-causal.js +244 -0
  144. package/packages/piagent-core/benchmark/benchmark-stage-diagnostic.js +979 -0
  145. package/packages/piagent-core/benchmark/benchmark-statistics.js +64 -0
  146. package/packages/piagent-core/benchmark/benchmark-stop-policy.js +8 -5
  147. package/packages/piagent-core/benchmark/benchmark-suite-identity.js +31 -0
  148. package/packages/piagent-core/benchmark/benchmark-suite-runtime.js +13 -9
  149. package/packages/piagent-core/benchmark/benchmark-suite.js +149 -2
  150. package/packages/piagent-core/benchmark/benchmark-summary-support.js +380 -0
  151. package/packages/piagent-core/benchmark/benchmark-timing-diagnostics.js +971 -0
  152. package/packages/piagent-core/benchmark/benchmark-usage.js +322 -0
  153. package/packages/piagent-core/benchmark/benchmark-workflow.js +166 -0
  154. package/packages/piagent-core/capabilities/runtime-integrity.js +3 -0
  155. package/packages/piagent-core/docs/context-efficiency-improvement-plan.md +1080 -0
  156. package/packages/piagent-core/extensions/acceptance-behavior-proof.js +806 -0
  157. package/packages/piagent-core/extensions/acceptance-contract-semantics.js +83 -69
  158. package/packages/piagent-core/extensions/acceptance-error-classes.js +160 -0
  159. package/packages/piagent-core/extensions/acceptance-executable-evidence.js +12 -9
  160. package/packages/piagent-core/extensions/acceptance-receipt.js +123 -59
  161. package/packages/piagent-core/extensions/acceptance-state-machine-evidence.js +518 -0
  162. package/packages/piagent-core/extensions/acceptance-test-binding-evidence.js +60 -0
  163. package/packages/piagent-core/extensions/context-efficiency-metrics.js +302 -0
  164. package/packages/piagent-core/extensions/context-efficiency-report.js +167 -0
  165. package/packages/piagent-core/extensions/context-engine.js +149 -156
  166. package/packages/piagent-core/extensions/context-evidence.js +48 -0
  167. package/packages/piagent-core/extensions/context-import-links.js +296 -0
  168. package/packages/piagent-core/extensions/context-index-policy.js +4 -0
  169. package/packages/piagent-core/extensions/context-query-paths.js +57 -0
  170. package/packages/piagent-core/extensions/context-telemetry-integrity.js +65 -0
  171. package/packages/piagent-core/extensions/criterion-context-pack.js +435 -7
  172. package/packages/piagent-core/extensions/criterion-graph.js +82 -9
  173. package/packages/piagent-core/extensions/fallback-base-policy.ts +101 -0
  174. package/packages/piagent-core/extensions/guard-types.ts +6 -0
  175. package/packages/piagent-core/extensions/javascript-regex-evidence.js +32 -0
  176. package/packages/piagent-core/extensions/piagent-guard.ts +420 -260
  177. package/packages/piagent-core/extensions/task-contract-view.js +17 -3
  178. package/packages/piagent-core/extensions/task-lifecycle.js +39 -2
  179. package/packages/piagent-core/extensions/task-state.js +109 -142
  180. package/packages/piagent-core/extensions/verification-intelligence.js +52 -13
  181. package/packages/piagent-core/extensions/workspace-evidence-roots.js +193 -0
  182. package/packages/piagent-core/package.json +1 -1
  183. package/packages/piagent-core/policies/base-policy.json +44 -2
  184. package/packages/piagent-core/policy/authority-manifest.v1.json +3 -3
  185. package/packages/piagent-core/prompts/be-to-fe.md +2 -8
  186. package/packages/piagent-core/prompts/plan.md +1 -1
  187. package/packages/piagent-core/prompts/platform-improve.md +2 -6
  188. package/packages/piagent-core/prompts/review.md +2 -7
  189. package/packages/piagent-core/prompts/scout.md +1 -1
  190. package/packages/piagent-core/prompts/task.md +4 -3
  191. package/packages/piagent-core/runtime/context/context-delivery.ts +103 -0
  192. package/packages/piagent-core/runtime/context/context-delta-shadow.ts +53 -0
  193. package/packages/piagent-core/runtime/context/context-efficiency-format.ts +47 -0
  194. package/packages/piagent-core/runtime/context/context-evidence-qualification.ts +32 -0
  195. package/packages/piagent-core/runtime/context/prefix-telemetry.ts +47 -0
  196. package/packages/piagent-core/runtime/context/repository-memory-hints.ts +27 -0
  197. package/packages/piagent-core/runtime/hooks/agent-prompt-telemetry.ts +56 -0
  198. package/packages/piagent-core/runtime/hooks/agent-start-hook.ts +162 -102
  199. package/packages/piagent-core/runtime/hooks/completion-hook.ts +12 -12
  200. package/packages/piagent-core/runtime/hooks/input-hook.ts +17 -1
  201. package/packages/piagent-core/runtime/hooks/session-hooks.ts +22 -2
  202. package/packages/piagent-core/runtime/hooks/session-start-hook.ts +107 -3
  203. package/packages/piagent-core/runtime/hooks/tool-result-content-guards.ts +95 -0
  204. package/packages/piagent-core/runtime/hooks/tool-result-hook.ts +134 -166
  205. package/packages/piagent-core/runtime/hooks/tool-result-value-helpers.ts +66 -0
  206. package/packages/piagent-core/runtime/inspection/activity-event-adapter.ts +4 -2
  207. package/packages/piagent-core/runtime/inspection/activity-recovery.ts +104 -0
  208. package/packages/piagent-core/runtime/inspection/bounded-emission-guard.ts +286 -0
  209. package/packages/piagent-core/runtime/inspection/runtime-event-store.ts +37 -7
  210. package/packages/piagent-core/runtime/inspection/task-compaction-history.ts +1 -1
  211. package/packages/piagent-core/runtime/inspection/task-handoff-history.ts +1 -1
  212. package/packages/piagent-core/runtime/inspection/task-subagent-tree.ts +27 -4
  213. package/packages/piagent-core/runtime/inspection/tool-failure-classification.ts +70 -0
  214. package/packages/piagent-core/runtime/inspection/webui-snapshot.ts +73 -9
  215. package/packages/piagent-core/runtime/model/authenticated-catalog.ts +17 -9
  216. package/packages/piagent-core/runtime/model/openai-codex-reasoning.ts +83 -0
  217. package/packages/piagent-core/runtime/model/provider-wire-fingerprint.ts +238 -0
  218. package/packages/piagent-core/runtime/orchestration/helper-lifecycle.ts +16 -12
  219. package/packages/piagent-core/runtime/orchestration/minimal-delegation-policy.ts +71 -0
  220. package/packages/piagent-core/runtime/orchestration/owned-work-budget.ts +28 -20
  221. package/packages/piagent-core/runtime/orchestration/role-policy.ts +27 -9
  222. package/packages/piagent-core/runtime/orchestration/subagent-tool-policy.ts +329 -0
  223. package/packages/piagent-core/runtime/policy/block-remedy.ts +0 -4
  224. package/packages/piagent-core/runtime/product/activity-inspector.ts +7 -2
  225. package/packages/piagent-core/runtime/product/efficiency-metrics.ts +7 -2
  226. package/packages/piagent-core/runtime/quality/edit-freshness-guard.ts +102 -0
  227. package/packages/piagent-core/runtime/quality/exact-output-contract.ts +22 -11
  228. package/packages/piagent-core/runtime/quality/performance-assurance-signals.ts +23 -0
  229. package/packages/piagent-core/runtime/quality/performance-assurance.ts +9 -5
  230. package/packages/piagent-core/runtime/recovery/continuation-budget.ts +1 -1
  231. package/packages/piagent-core/runtime/recovery/edit-recovery-context.ts +113 -0
  232. package/packages/piagent-core/runtime/recovery/edit-recovery-delivery.ts +42 -0
  233. package/packages/piagent-core/runtime/recovery/handoff-projection.ts +4 -1
  234. package/packages/piagent-core/runtime/recovery/pristine-task-policy-refresh.ts +91 -0
  235. package/packages/piagent-core/runtime/recovery/recovery-policy.ts +7 -4
  236. package/packages/piagent-core/runtime/recovery/resume-state.ts +112 -14
  237. package/packages/piagent-core/runtime/recovery/semantic-repair-handshake.ts +60 -13
  238. package/packages/piagent-core/runtime/recovery/semantic-repair-runtime.ts +55 -2
  239. package/packages/piagent-core/runtime/recovery/task-evidence-coverage-refresh.ts +217 -0
  240. package/packages/piagent-core/runtime/registration/context-commands.ts +82 -7
  241. package/packages/piagent-core/runtime/registration/knowledge-tools.ts +9 -5
  242. package/packages/piagent-core/runtime/registration/operator-request-intake.ts +49 -0
  243. package/packages/piagent-core/runtime/registration/policy-tools.ts +50 -15
  244. package/packages/piagent-core/runtime/registration/session-commands.ts +1 -1
  245. package/packages/piagent-core/runtime/registration/task-completion-tools.ts +61 -25
  246. package/packages/piagent-core/runtime/registration/task-evidence-tools.ts +21 -12
  247. package/packages/piagent-core/runtime/registration/task-start-guidance.ts +169 -0
  248. package/packages/piagent-core/runtime/registration/task-start-manifest.ts +54 -0
  249. package/packages/piagent-core/runtime/registration/task-start-retry-helpers.ts +37 -0
  250. package/packages/piagent-core/runtime/registration/task-start-tool.ts +108 -103
  251. package/packages/piagent-core/runtime/runtime-limits.ts +16 -2
  252. package/packages/piagent-core/runtime/session/adaptive-context-analysis.ts +461 -0
  253. package/packages/piagent-core/runtime/session/adaptive-context-governor.ts +464 -0
  254. package/packages/piagent-core/runtime/session/adaptive-context-ledger.ts +265 -0
  255. package/packages/piagent-core/runtime/session/message-signals.ts +7 -3
  256. package/packages/piagent-core/runtime/session/operator-request-carry.ts +44 -0
  257. package/packages/piagent-core/runtime/session/runtime-state.ts +161 -5
  258. package/packages/piagent-core/runtime/session/source-checkout-read-grants.ts +35 -0
  259. package/packages/piagent-core/runtime/session/system-prompt.ts +76 -14
  260. package/packages/piagent-core/runtime/session/task-contract-presentation.ts +39 -0
  261. package/packages/piagent-core/runtime/tools/apply-patch-tool.ts +500 -0
  262. package/packages/piagent-core/runtime/tools/phase-tools.ts +8 -8
  263. package/packages/piagent-core/runtime/tools/tool-groups.ts +12 -2
  264. package/packages/piagent-core/runtime/trajectory/trajectory-runtime.ts +2 -1
  265. package/packages/piagent-core/runtime/verification/exact-verifier-reuse.ts +101 -0
  266. package/packages/piagent-core/runtime/workflows/runtime-intake-compaction.ts +164 -0
  267. package/packages/piagent-core/runtime/workflows/task-intake.ts +207 -38
  268. package/packages/piagent-core/security/sensitive-data.js +13 -218
  269. package/packages/piagent-core/security/sensitive-project-file.js +42 -0
  270. package/packages/piagent-core/security/sensitive-source-expression.js +330 -0
  271. package/packages/piagent-core/security/sensitive-source-formats.js +394 -0
  272. package/packages/piagent-core/security/sensitive-text.js +234 -0
  273. package/packages/piagent-core/subagents/piagent-oracle.md +5 -3
  274. package/packages/piagent-core/subagents/piagent-planner.md +6 -4
  275. package/packages/piagent-core/subagents/piagent-reviewer.md +5 -3
  276. package/packages/piagent-core/subagents/piagent-scout.md +4 -2
  277. package/packages/piagent-core/subagents/piagent-worker.md +7 -5
  278. package/packages/piagent-webui/dist/client/assets/{MarkdownMessage-rD9WJKxs.js → MarkdownMessage-B4XehTCU.js} +1 -1
  279. package/packages/piagent-webui/dist/client/assets/index-CgOEyRPG.js +176 -0
  280. package/packages/piagent-webui/dist/client/index.html +1 -1
  281. package/packages/piagent-webui/extension/piagent-webui.ts +3 -1
  282. package/packages/piagent-webui/extension/same-session-bridge.ts +1 -1
  283. package/packages/piagent-webui/extension/session-stream-adapter.ts +33 -10
  284. package/packages/piagent-webui/gateway/gateway-events.ts +109 -5
  285. package/packages/piagent-webui/gateway/gateway-service.ts +3 -0
  286. package/packages/piagent-webui/gateway/gateway-session-stream.ts +122 -20
  287. package/packages/piagent-webui/gateway/session-command-controller.ts +18 -3
  288. package/packages/piagent-webui/gateway/session-effective-options.ts +47 -0
  289. package/packages/piagent-webui/gateway/session-live-state.ts +21 -0
  290. package/packages/piagent-webui/gateway/session-operation-lifecycle.ts +237 -0
  291. package/packages/piagent-webui/gateway/session-operation-retry-control.ts +38 -0
  292. package/packages/piagent-webui/gateway/session-operation-start.ts +5 -1
  293. package/packages/piagent-webui/gateway/session-operation-watchdog.ts +165 -0
  294. package/packages/piagent-webui/gateway/session-runtime-factory.ts +45 -0
  295. package/packages/piagent-webui/gateway/session-runtime-supervisor.ts +141 -125
  296. package/packages/piagent-webui/ownership/session-lease-store.ts +5 -2
  297. package/packages/piagent-webui/server/core-inspection-provider.ts +2 -1
  298. package/packages/piagent-webui/server/loopback-server.ts +8 -0
  299. package/packages/piagent-webui/server/transcript-projection.ts +113 -9
  300. package/packages/piagent-webui/shared/text-visibility.ts +10 -0
  301. package/schemas/codex-relative-efficiency-v1.schema.json +155 -0
  302. package/schemas/piagent-webui/catalog-v1.json +9 -0
  303. package/schemas/piagent-webui/gateway-protocol-v1.schema.json +53 -3
  304. package/schemas/piagent-webui/runtime-event-v2.schema.json +15 -5
  305. package/schemas/piagent-webui/session-live-state-v1.schema.json +76 -0
  306. package/schemas/piagent-webui/subagent-tree-v1.schema.json +11 -1
  307. package/schemas/project-profile.schema.json +1 -1
  308. package/schemas/task-contract.schema.json +27 -1
  309. package/scripts/benchmark-runner-core.mjs +367 -363
  310. package/scripts/benchmark-runner-finalization.mjs +313 -0
  311. package/scripts/benchmark-runner-host-readiness.mjs +94 -0
  312. package/scripts/benchmark-runner-support.mjs +200 -0
  313. package/scripts/benchmark-session.mjs +95 -41
  314. package/scripts/configure-model-scope.sh +4 -3
  315. package/scripts/configure-subagents.sh +42 -34
  316. package/scripts/helper-evaluation.mjs +2 -2
  317. package/scripts/install-global.sh +2 -2
  318. package/scripts/pi-usage-history.mjs +37 -10
  319. package/scripts/setup.sh +2 -2
  320. package/scripts/team-doctor.sh +1 -1
  321. package/scripts/verify-local.sh +10 -1
  322. package/templates/global/settings.json +2 -1
  323. package/packages/piagent-webui/dist/client/assets/index-BZRFw1u6.js +0 -174
@@ -1,18 +1,32 @@
1
1
  import type { TaskContract } from "../../extensions/guard-types.ts";
2
2
  import { SEMANTIC_COMPACTION_MAX_CHARS } from "../runtime-limits.ts";
3
- import { criterionGraphGuidance } from "../../extensions/criterion-graph.js";
3
+ import {
4
+ losslessOperatorRequestFitsWithin,
5
+ operatorRequestCarryLines
6
+ } from "./operator-request-carry.ts";
7
+ import { presentedAcceptanceCriteria, presentedCriterionGraphGuidance } from "./task-contract-presentation.ts";
4
8
 
5
9
  const LEGACY_PROJECT_INSTRUCTIONS_START = "Before implementation:\n\n1. Load `.pi/piagent-profile.json` with `piagent_context`.";
6
10
  const LEGACY_PROJECT_INSTRUCTIONS_END = "18. If the bundled `pi-subagents` parent skill is available, use it for delegation patterns, review loops, native supervisor coordination, and safety boundaries.";
7
11
  const RUNTIME_MANAGED_PROJECT_INSTRUCTIONS = [
8
12
  "Piagent runtime-managed task flow:",
9
13
  "1. Runtime creates the task contract automatically for a bounded source-changing request before the model starts.",
10
- "2. Only when runtime intake pauses for broad, high-risk, or ambiguous scope, call `piagent_task_start` exactly once with project-relative path/glob scope; reuse an active contract.",
11
- "3. Read the narrow target and nearest relevant test, then use ordinary read/edit/bash tools.",
12
- "4. Run every exact runtime-provided verifier after the latest mutation. Automatic tasks need no management calls.",
13
- "5. Runtime hooks enforce policy and record context, changes, current-tree verification, trace and final gate. Diagnostic groups appear only for explicit requests or manual high-risk checkpoints."
14
+ "2. Only when runtime intake pauses for a broad, high-risk, or ambiguous task, call `piagent_task_start` exactly once with project-relative focus paths/globs; reuse an active contract.",
15
+ "3. Use complete runtime-delivered source directly; do not reread it normally. On edit drift/oldText mismatch, use attached recovery; otherwise reread the affected region once. Never retry guessed anchors. Otherwise read only missing source or a concrete criterion-linked focused test. Task scope seeds retrieval and review; it does not limit source mutation. Follow repository evidence across packages or child repos while preserving explicit user constraints. When creating an explicitly requested new path, do not probe that destination with read first; create it, then read back or verify it. If existence matters, use a non-erroring existence check.",
16
+ "4. Preserve every runtime-provided verifier exactly and keep commands separate. Run the exact verifier set once on the final tree; rerun only after a later mutation, an explicit operator request, or a runtime-authorized same-tree infrastructure retry. Before any repeat, use piagent_task_gate_check and run only commands reported missing for the current tree; Piagent reuses a durable exact pass on an unchanged tree. Automatic tasks need no other management calls.",
17
+ "5. Treat the current source, the operator request, and the durable Task Contract as authoritative. The parent model reasons and implements directly. Helpers are off unless explicitly enabled; even then, allow at most one fresh read-only helper only when runtime evidence proves two independent lanes and at least 30% projected net token saving. Never delegate writes, inherit parent history, fan out, or retry a deterministic helper failure. Preserve explicit user constraints and report unresolved risk. Runtime-derived scope is only the initial focus and may expand when implementation evidence requires FE, BE, tests, configuration, or another child repo. Runtime hooks enforce protected paths and approvals and record context, changes, current-tree verification, trace and final gate. Diagnostic groups appear only for explicit requests or manual high-risk checkpoints."
14
18
  ].join("\n");
15
19
 
20
+ export const SEMANTIC_COMPACTION_CANCELLED_PREFIX = "[Piagent semantic compaction cancelled:";
21
+
22
+ export function semanticCompactionCancelled(value: unknown): boolean {
23
+ return String(value ?? "").startsWith(SEMANTIC_COMPACTION_CANCELLED_PREFIX);
24
+ }
25
+
26
+ function semanticCompactionCancellation(task?: TaskContract): string {
27
+ return `${SEMANTIC_COMPACTION_CANCELLED_PREFIX} authoritative durable task truth and exact verifiers exceed the ${SEMANTIC_COMPACTION_MAX_CHARS}-character carry target. Keep the current session context unchanged; do not summarize, hash, truncate, or reconstruct authoritative task truth.${task?.operatorRequestDigest ? ` Contract digest: ${task.operatorRequestDigest}.` : ""}]`;
28
+ }
29
+
16
30
  export function rewriteLegacyProjectInstructions(systemPrompt: string): {
17
31
  systemPrompt: string;
18
32
  rewritten: boolean;
@@ -34,7 +48,7 @@ export function compactManagedProjectInstructions(
34
48
  ): { systemPrompt: string; compacted: boolean } {
35
49
  const concise = mode === "protected"
36
50
  ? "Piagent protected-path policy: do not read, disclose, or mutate protected content. Refuse without tool calls."
37
- : "Piagent runtime task is injected below. Root project instructions are already loaded; do not re-read root AGENTS.md. Use task-relevant source/tests and ordinary tools, run the exact verifier after final edits, and make no task-management calls.";
51
+ : "Piagent runtime task is injected below. Root project instructions are already loaded; do not re-read root AGENTS.md. Treat current source, the operator request, and the durable Task Contract as authoritative; preserve explicit user constraints and report unresolved risk. The parent reasons and implements directly. Helpers are opt-in and limited to one fresh read-only helper only with two independent lanes and at least 30% projected net token saving; never delegate writes, inherit parent history, fan out, or retry a deterministic helper failure. Runtime-derived scope is an initial retrieval/review focus, not a mutation boundary; follow repository evidence across packages and child repos. Use complete runtime-delivered source directly without rereading it normally. On edit drift/oldText mismatch, use attached recovery; otherwise reread the affected region once. Never retry guessed anchors. Otherwise read only missing source or a concrete criterion-linked focused test. For an explicitly requested new path, create it without a speculative read, then read back or verify it. Preserve every runtime verifier exactly and keep commands separate. Run the exact verifier set once on the final tree; rerun only after a later mutation or a runtime-authorized same-tree infrastructure retry. Make no task-management calls.";
38
52
  const markerStart = "<!-- piagent-managed:start -->";
39
53
  const markerEnd = "<!-- piagent-managed:end -->";
40
54
  const start = systemPrompt.indexOf(markerStart);
@@ -70,27 +84,75 @@ function compactCarryOverList(values: unknown[], limit: number, itemChars: numbe
70
84
  return selected.join(", ") || "none recorded";
71
85
  }
72
86
 
73
- function boundedCarryOver(value: string): string {
87
+ function boundedCarryOver(value: string, task?: TaskContract): string {
74
88
  if (value.length <= SEMANTIC_COMPACTION_MAX_CHARS) return value;
75
- const marker = "\n\n[Piagent carry-over shortened; the durable Task Contract remains authoritative.]\n\n";
89
+ const operatorTruth = operatorRequestCarryLines(task);
90
+ if (task && operatorTruth.length > 0) {
91
+ const fallback = [
92
+ "Create a structured Piagent carry-over summary.",
93
+ `Current task: ${compactCarryOverText(task.taskId, 160)} (${task.riskLane})`,
94
+ ...operatorTruth,
95
+ "Acceptance criteria:",
96
+ ...presentedAcceptanceCriteria(task).slice(0, 8).map((criterion, index) => `- ${index + 1}. ${compactCarryOverText(criterion, 160)}`),
97
+ `Changed files: ${compactCarryOverList(task.changedFiles, 6, 80)}`,
98
+ ...(task.verifyCommands.length > 0 ? ["Exact verify commands:", ...task.verifyCommands.map((command, index) => `${index + 1}. ${command}`)] : ["Exact verify commands: not recorded"]),
99
+ `Outcome/blocker: ${task.trace.outcome}${task.trace.friction ? `; ${compactCarryOverText(task.trace.friction, 240)}` : ""}`,
100
+ "Preserve the authoritative operator request and every atomic acceptance criterion, plus current repository facts, task progress, exact verifier evidence, blockers, and next action.",
101
+ "Discard stale tool logs and speculative reasoning. Do not convert assumptions into facts."
102
+ ].join("\n");
103
+ if (fallback.length <= SEMANTIC_COMPACTION_MAX_CHARS) return fallback;
104
+ const minimal = [
105
+ "Create a structured Piagent carry-over summary.",
106
+ `Current task: ${compactCarryOverText(task.taskId, 120)} (${task.riskLane})`,
107
+ ...operatorTruth,
108
+ "Exact verify commands:", ...task.verifyCommands.map((command, index) => `${index + 1}. ${command}`),
109
+ `Outcome/blocker: ${task.trace.outcome}${task.trace.friction ? `; ${compactCarryOverText(task.trace.friction, 200)}` : ""}`,
110
+ "The complete operator request above is the acceptance source of truth. Continue only from current source and these exact verifiers."
111
+ ].join("\n");
112
+ return minimal.length <= SEMANTIC_COMPACTION_MAX_CHARS ? minimal : semanticCompactionCancellation(task);
113
+ }
114
+ if (task) {
115
+ const manual = [
116
+ "Create a structured Piagent carry-over summary.",
117
+ `Current task: ${compactCarryOverText(task.taskId, 120)} (${task.riskLane})`,
118
+ `Goal: ${task.summary}`,
119
+ `Expected output: ${task.expectedOutput}`,
120
+ "Acceptance criteria:", ...presentedAcceptanceCriteria(task).map((criterion, index) => `${index + 1}. ${criterion}`),
121
+ "Exact verify commands:", ...task.verifyCommands.map((command, index) => `${index + 1}. ${command}`),
122
+ "Continue only from current source and every durable task clause above."
123
+ ].join("\n");
124
+ return manual.length <= SEMANTIC_COMPACTION_MAX_CHARS ? manual : semanticCompactionCancellation(task);
125
+ }
126
+ const marker = "\n\n[Piagent carry-over shortened; no durable task contract was available.]\n\n";
76
127
  const available = SEMANTIC_COMPACTION_MAX_CHARS - marker.length;
77
128
  const head = Math.floor(available * 0.72);
78
129
  return `${value.slice(0, head).trimEnd()}${marker}${value.slice(-(available - head)).trimStart()}`;
79
130
  }
80
131
 
81
132
  export function buildSemanticCompactionInstructions(task?: TaskContract): string {
133
+ if (!losslessOperatorRequestFitsWithin(task, SEMANTIC_COMPACTION_MAX_CHARS)) {
134
+ return semanticCompactionCancellation(task);
135
+ }
136
+ const criteria = task ? presentedAcceptanceCriteria(task) : [];
137
+ const executionMap = task ? presentedCriterionGraphGuidance(task, 8) : [];
138
+ const operatorTruth = operatorRequestCarryLines(task);
139
+ const criteriaLimit = operatorTruth.length > 0 ? 8 : criteria.length;
140
+ const criterionChars = operatorTruth.length > 0 ? 180 : 280;
82
141
  const taskState = task
83
142
  ? [
84
143
  `Current task: ${compactCarryOverText(task.taskId, 160)} (${task.riskLane})`,
85
144
  `Session: ${compactCarryOverText(task.sessionName ?? task.sessionId, 160)}`,
86
- `Goal: ${compactCarryOverText(task.summary, 600)}`,
145
+ `Goal: ${operatorTruth.length > 0 ? compactCarryOverText(task.summary, 600) : task.summary}`,
146
+ ...operatorTruth,
147
+ `Expected output: ${operatorTruth.length > 0 ? compactCarryOverText(task.expectedOutput, 500) : task.expectedOutput}`,
87
148
  "Acceptance criteria:",
88
- ...task.acceptanceCriteria.slice(0, 12).map((criterion, index) => `- ${index + 1}. ${compactCarryOverText(criterion, 280)}`),
89
- `Scope: ${compactCarryOverList(task.scope, 8, 80)}`,
90
- ...(criterionGraphGuidance(task.criterionGraph, 8).length > 0 ? ["Execution map (planning only):", ...criterionGraphGuidance(task.criterionGraph, 8).map((line: string) => `- ${line}`)] : []),
149
+ ...criteria.slice(0, criteriaLimit).map((criterion, index) => `- ${index + 1}. ${operatorTruth.length > 0 ? compactCarryOverText(criterion, criterionChars) : criterion}`),
150
+ `Initial focus (advisory): ${compactCarryOverList(task.scope, 8, 80)}`,
151
+ "Initial focus guides retrieval/review and neither authorizes nor forbids mutation.",
152
+ ...(executionMap.length > 0 ? ["Execution map (planning only):", ...executionMap.map((line: string) => `- ${line}`)] : []),
91
153
  `Changed files: ${compactCarryOverList(task.changedFiles, 8, 100)}`,
92
154
  task.verifyCommands.length > 0
93
- ? ["Exact verify commands:", ...task.verifyCommands.slice(0, 8).map((command, index) => `${index + 1}. ${compactCarryOverText(command, 180)}`)].join("\n")
155
+ ? ["Exact verify commands:", ...task.verifyCommands.map((command, index) => `${index + 1}. ${command}`)].join("\n")
94
156
  : "Exact verify commands: not recorded",
95
157
  `Outcome/blocker: ${task.trace.outcome}${task.trace.friction ? `; ${compactCarryOverText(task.trace.friction, 320)}` : ""}`,
96
158
  "Full task truth is file-backed by the durable Task Contract; do not inspect private Piagent state directly."
@@ -105,5 +167,5 @@ export function buildSemanticCompactionInstructions(task?: TaskContract): string
105
167
  "- superseded plans, repeated reads, raw tool logs, successful intermediate output, and speculative reasoning",
106
168
  "- full source excerpts that can be re-read from the repository", "",
107
169
  "Do not convert assumptions into facts. Mark unknowns explicitly. After compaction, re-read current files before editing."
108
- ].join("\n"));
170
+ ].join("\n"), task);
109
171
  }
@@ -0,0 +1,39 @@
1
+ import type { TaskContract } from "../../extensions/guard-types.ts";
2
+ import { criterionGraphGuidance } from "../../extensions/criterion-graph.js";
3
+
4
+ export const LEGACY_RUNTIME_SCOPE_CRITERION = "Changes stay within the runtime-derived task scope.";
5
+
6
+ function isLegacyRuntimeScopeCriterion(value: unknown): boolean {
7
+ return typeof value === "string" && value.trim() === LEGACY_RUNTIME_SCOPE_CRITERION;
8
+ }
9
+
10
+ export function presentedAcceptanceCriteria(
11
+ task: Pick<TaskContract, "acceptanceCriteria">
12
+ ): string[] {
13
+ return task.acceptanceCriteria.filter((criterion) => !isLegacyRuntimeScopeCriterion(criterion));
14
+ }
15
+
16
+ export function presentedCriterionGraphGuidance(
17
+ task: Pick<TaskContract, "criterionGraph">,
18
+ maximumLines = 12
19
+ ): string[] {
20
+ const graph = task.criterionGraph;
21
+ if (!graph) return [];
22
+ const removedNodeIds = new Set(
23
+ graph.nodes
24
+ .filter((node) => isLegacyRuntimeScopeCriterion(node.obligation))
25
+ .map((node) => node.id)
26
+ );
27
+ if (removedNodeIds.size === 0) return criterionGraphGuidance(graph, maximumLines);
28
+ const presentedGraph = {
29
+ ...graph,
30
+ nodes: graph.nodes
31
+ .filter((node) => !removedNodeIds.has(node.id))
32
+ .map((node) => ({
33
+ ...node,
34
+ dependsOn: node.dependsOn.filter((dependency) => !removedNodeIds.has(dependency))
35
+ })),
36
+ order: graph.order.filter((nodeId) => !removedNodeIds.has(nodeId))
37
+ };
38
+ return criterionGraphGuidance(presentedGraph, maximumLines);
39
+ }