@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
@@ -0,0 +1,461 @@
1
+ import crypto from "node:crypto";
2
+
3
+ import { redactSensitiveText } from "../../extensions/redaction-core.js";
4
+ import {
5
+ CONTEXT_GOVERNOR_PRESSURE_TOKENS,
6
+ CONTEXT_GOVERNOR_SEMANTIC_BOUNDARY_TOKENS,
7
+ CONTEXT_GOVERNOR_TARGET_MESSAGE_TOKENS,
8
+ CONTEXT_GOVERNOR_TOOL_ROUND_LIMIT,
9
+ CONTEXT_PROVIDER_PROMPT_CEILING_TOKENS
10
+ } from "../runtime-limits.ts";
11
+
12
+ export const GOVERNOR_VERSION = "adaptive-context-governor-v2" as const;
13
+ export const CONTEXT_GOVERNOR_MIN_SAVINGS_FLOOR_TOKENS = 8_000;
14
+ export const CONTEXT_GOVERNOR_MIN_SAVINGS_CEILING_TOKENS = 20_000;
15
+ export const CONTEXT_GOVERNOR_MIN_SAVINGS_RATIO = 0.15;
16
+ export const CONTEXT_GOVERNOR_PROTECTED_BOUNDARY_GROUPS = 6;
17
+ const READ_TOOLS = new Set([
18
+ "read",
19
+ "grep",
20
+ "find",
21
+ "ls",
22
+ "glob",
23
+ "search",
24
+ "fetch_content",
25
+ "get_search_content",
26
+ "web_search"
27
+ ]);
28
+ const MUTATION_TOOLS = new Set(["edit", "write", "apply_patch", "patch"]);
29
+ const VERIFIER_PATTERN = /(?:^|\s)(?:test|tests|lint|typecheck|check|verify|build|pytest|vitest|jest|playwright|cargo\s+test|go\s+test)(?:\s|:|$)/i;
30
+ const MUTATION_COMMAND_PATTERN = /(?:^|\s)(?:sed\s+-i|perl\s+-pi|tee\s+|cp\s+|mv\s+|mkdir\s+|touch\s+|npm\s+version|git\s+apply)(?:\s|$)|(?:>>?|2>)\s*[^&]/i;
31
+
32
+ export type MessageLike = Record<string, any> & { role?: string; timestamp?: number };
33
+
34
+ export type SemanticPhase = "scout" | "plan" | "implement" | "verify" | "review" | "release" | "discuss" | "unknown";
35
+ export type SemanticBoundary = {
36
+ kind: "none" | "phase" | "task";
37
+ previousPhase: SemanticPhase;
38
+ currentPhase: SemanticPhase;
39
+ similarity: number;
40
+ };
41
+
42
+ export type ContextResidencyMetrics = {
43
+ estimatedMessageTokens: number;
44
+ toolResults: number;
45
+ readResults: number;
46
+ mutationResults: number;
47
+ verifierResults: number;
48
+ failedResults: number;
49
+ duplicateResults: number;
50
+ duplicateResultRate: number;
51
+ lowValueTokenShare: number;
52
+ userTurns: number;
53
+ };
54
+
55
+ export type ContextGovernorDecision = {
56
+ version: typeof GOVERNOR_VERSION;
57
+ action: "passthrough" | "project";
58
+ reason: "none" | "semantic-boundary" | "residency" | "pressure" | "provider-ceiling";
59
+ reasonCodes: string[];
60
+ reportedTokens: number;
61
+ effectiveTokens: number;
62
+ contextWindow: number;
63
+ percent: number;
64
+ originalMessageTokens: number;
65
+ projectedMessageTokens: number;
66
+ candidateProjectedMessageTokens: number;
67
+ estimatedSavingsTokens: number;
68
+ minimumSavingsTokens: number;
69
+ savingsRatio: number;
70
+ fallback: "none" | "no-safe-boundary" | "insufficient-savings" | "unsafe-tool-protocol";
71
+ originalMessages: number;
72
+ projectedMessages: number;
73
+ accounting: ContextGovernorAccounting;
74
+ boundary: SemanticBoundary;
75
+ residency: ContextResidencyMetrics;
76
+ };
77
+
78
+ export type ContextGovernorAccounting = {
79
+ contextOccupancy: {
80
+ providerReportedTokens: number | null;
81
+ transcriptEstimatedTokens: number;
82
+ projectedTranscriptTokens: number;
83
+ effectivePressureTokens: number;
84
+ contextWindow: number;
85
+ };
86
+ billedTraffic: {
87
+ measured: false;
88
+ inputTokens: null;
89
+ outputTokens: null;
90
+ cacheReadTokens: null;
91
+ governorProviderCalls: 0;
92
+ reason: "provider-billing-not-exposed-by-context-hook";
93
+ };
94
+ };
95
+
96
+ export type ToolProtocolAudit = {
97
+ intact: boolean;
98
+ orphanCallIds: string[];
99
+ orphanResultIds: string[];
100
+ };
101
+
102
+ export type ToolObservation = {
103
+ identity: string;
104
+ name: string;
105
+ target: string;
106
+ kind: "read" | "mutation" | "verify" | "other";
107
+ isError: boolean;
108
+ tokens: number;
109
+ };
110
+
111
+ function bounded(value: unknown, maxChars: number): string {
112
+ const compact = String(value ?? "").replace(/\s+/g, " ").trim();
113
+ if (compact.length <= maxChars) return compact;
114
+ const marker = " ... ";
115
+ const available = Math.max(0, maxChars - marker.length);
116
+ const head = Math.floor(available * 0.68);
117
+ return `${compact.slice(0, head).trimEnd()}${marker}${compact.slice(-(available - head)).trimStart()}`;
118
+ }
119
+
120
+ export function safeText(value: unknown, maxChars: number): string {
121
+ return bounded(redactSensitiveText(String(value ?? "")).text, maxChars);
122
+ }
123
+
124
+ function contentTokenEstimate(content: unknown): number {
125
+ if (typeof content === "string") return Math.ceil(content.length / 4);
126
+ if (!Array.isArray(content)) return 0;
127
+ let tokens = 0;
128
+ for (const block of content) {
129
+ if (!block || typeof block !== "object") continue;
130
+ if (block.type === "image") {
131
+ tokens += 1_200;
132
+ continue;
133
+ }
134
+ if (block.type === "text") tokens += Math.ceil(String(block.text ?? "").length / 4);
135
+ else if (block.type === "thinking") tokens += Math.ceil(String(block.thinking ?? block.thinkingSignature ?? "").length / 4);
136
+ else if (block.type === "toolCall") {
137
+ let serialized = "";
138
+ try {
139
+ serialized = JSON.stringify(block.arguments ?? {});
140
+ } catch {
141
+ serialized = String(block.arguments ?? "");
142
+ }
143
+ tokens += Math.ceil((String(block.name ?? "").length + serialized.length) / 4) + 8;
144
+ }
145
+ }
146
+ return tokens;
147
+ }
148
+
149
+ export function estimateGovernorMessageTokens(message: MessageLike): number {
150
+ if (!message || typeof message !== "object") return 0;
151
+ if (message.role === "compactionSummary" || message.role === "branchSummary") {
152
+ return Math.ceil(String(message.summary ?? "").length / 4) + 16;
153
+ }
154
+ if (message.role === "bashExecution") {
155
+ return message.excludeFromContext ? 0 : Math.ceil((String(message.command ?? "").length + String(message.output ?? "").length) / 4) + 16;
156
+ }
157
+ return contentTokenEstimate(message.content) + 8;
158
+ }
159
+
160
+ export function estimateGovernorMessagesTokens(messages: MessageLike[]): number {
161
+ return messages.reduce((sum, message) => sum + estimateGovernorMessageTokens(message), 0);
162
+ }
163
+
164
+ export function messageText(message: MessageLike): string {
165
+ if (typeof message.content === "string") return message.content;
166
+ if (!Array.isArray(message.content)) return "";
167
+ return message.content
168
+ .filter((block: any) => block?.type === "text")
169
+ .map((block: any) => String(block.text ?? ""))
170
+ .join("\n");
171
+ }
172
+
173
+ function fold(value: string): string {
174
+ return value.normalize("NFKD").replace(/[\u0300-\u036f]/g, "").toLowerCase();
175
+ }
176
+
177
+ export function classifySemanticPhase(value: string): SemanticPhase {
178
+ const text = fold(value);
179
+ if (/\b(commit|push|merge|publish|release|tag|deploy|phat hanh|trien khai)\b/.test(text)) return "release";
180
+ if (/\b(verify|verification|run tests?|test lai|kiem thu|typecheck|lint|ci|closeout)\b/.test(text)) return "verify";
181
+ if (/\b(implement|implementation|fix|repair|code|sua code|tien hanh sua|lam di|build it)\b/.test(text)) return "implement";
182
+ if (/\b(plan|planning|ke hoach|len plan|proposal|design approach)\b/.test(text)) return "plan";
183
+ if (/\b(review|reviewer|cross-check|double-check|danh gia lai)\b/.test(text)) return "review";
184
+ if (/\b(scout|audit|inspect|investigate|read-only|read only|mapping|map logic|kiem tra logic|xem xet)\b/.test(text)) return "scout";
185
+ if (/\b(explain|why|discuss|question|tai sao|vi sao|nghi sao|phan tich)\b/.test(text)) return "discuss";
186
+ return "unknown";
187
+ }
188
+
189
+ const SEMANTIC_STOP_WORDS = new Set([
190
+ "about", "after", "agent", "anh", "before", "cho", "code", "continue", "cua", "em", "file", "fix", "giup",
191
+ "implement", "kiem", "lam", "logic", "please", "project", "sua", "task", "test", "tiep", "tuc", "that", "the",
192
+ "this", "them", "then", "there", "these", "update", "verify", "viec", "with", "xem"
193
+ ]);
194
+
195
+ function semanticTerms(value: string): Set<string> {
196
+ const terms = fold(value).match(/[a-z0-9_.\/-]{3,}/g) ?? [];
197
+ return new Set(terms.filter((term) => !SEMANTIC_STOP_WORDS.has(term)));
198
+ }
199
+
200
+ function semanticSimilarity(left: string, right: string): number {
201
+ const a = semanticTerms(left);
202
+ const b = semanticTerms(right);
203
+ if (a.size === 0 || b.size === 0) return 0;
204
+ let intersection = 0;
205
+ for (const term of a) if (b.has(term)) intersection += 1;
206
+ return intersection / new Set([...a, ...b]).size;
207
+ }
208
+
209
+ export function operatorMessages(messages: MessageLike[]): MessageLike[] {
210
+ return messages.filter((message) => message.role === "user" && messageText(message).trim());
211
+ }
212
+
213
+ export function detectSemanticBoundary(messages: MessageLike[]): SemanticBoundary {
214
+ const users = operatorMessages(messages);
215
+ const currentText = messageText(users.at(-1) ?? {});
216
+ const previousText = messageText(users.at(-2) ?? {});
217
+ const currentPhase = classifySemanticPhase(currentText);
218
+ const previousPhase = classifySemanticPhase(previousText);
219
+ const similarity = semanticSimilarity(previousText, currentText);
220
+ if (!previousText || !currentText) return { kind: "none", previousPhase, currentPhase, similarity };
221
+
222
+ const phaseChanged = currentPhase !== "unknown"
223
+ && previousPhase !== "unknown"
224
+ && currentPhase !== previousPhase
225
+ && ["plan", "implement", "verify", "review", "release"].includes(currentPhase);
226
+ if (phaseChanged) return { kind: "phase", previousPhase, currentPhase, similarity };
227
+
228
+ const continuation = /\b(continue|tiep tuc|proceed|carry on|oke|ok|do it|lam tiep|sua tiep)\b/.test(fold(currentText));
229
+ if (!continuation && currentText.length >= 24 && previousText.length >= 24 && similarity < 0.12) {
230
+ return { kind: "task", previousPhase, currentPhase, similarity };
231
+ }
232
+ return { kind: "none", previousPhase, currentPhase, similarity };
233
+ }
234
+
235
+ function toolCalls(message: MessageLike): any[] {
236
+ if (message.role !== "assistant" || !Array.isArray(message.content)) return [];
237
+ return message.content.filter((block: any) => block?.type === "toolCall");
238
+ }
239
+
240
+ function toolCallId(block: any): string {
241
+ return String(block?.id ?? block?.toolCallId ?? "").trim();
242
+ }
243
+
244
+ export function auditToolProtocol(messages: MessageLike[]): ToolProtocolAudit {
245
+ const calls = new Map<string, number>();
246
+ const results = new Map<string, number>();
247
+ for (const message of messages) {
248
+ for (const call of toolCalls(message)) {
249
+ const id = toolCallId(call);
250
+ if (id) calls.set(id, (calls.get(id) ?? 0) + 1);
251
+ }
252
+ if (message.role !== "toolResult") continue;
253
+ const id = String(message.toolCallId ?? "").trim();
254
+ if (id) results.set(id, (results.get(id) ?? 0) + 1);
255
+ }
256
+ const orphanCallIds = [...calls]
257
+ .filter(([id, count]) => (results.get(id) ?? 0) !== count)
258
+ .map(([id]) => id)
259
+ .sort();
260
+ const orphanResultIds = [...results]
261
+ .filter(([id, count]) => (calls.get(id) ?? 0) !== count)
262
+ .map(([id]) => id)
263
+ .sort();
264
+ return {
265
+ intact: orphanCallIds.length === 0 && orphanResultIds.length === 0,
266
+ orphanCallIds,
267
+ orphanResultIds
268
+ };
269
+ }
270
+
271
+ function canonicalToolArguments(value: unknown): string {
272
+ const canonical = (item: unknown): unknown => {
273
+ if (Array.isArray(item)) return item.map(canonical);
274
+ if (!item || typeof item !== "object") return item;
275
+ return Object.fromEntries(
276
+ Object.entries(item as Record<string, unknown>)
277
+ .filter(([, child]) => child !== undefined)
278
+ .sort(([left], [right]) => left < right ? -1 : left > right ? 1 : 0)
279
+ .map(([key, child]) => [key, canonical(child)])
280
+ );
281
+ };
282
+ try {
283
+ return JSON.stringify(canonical(value));
284
+ } catch {
285
+ return String(value ?? "");
286
+ }
287
+ }
288
+
289
+ function toolTarget(name: string, input: Record<string, unknown>): string {
290
+ const candidate = input.url ?? input.path ?? input.file_path ?? input.filePath ?? input.target ?? input.query ?? input.pattern
291
+ ?? input.command ?? input.cmd ?? input.script ?? "";
292
+ if (candidate) return safeText(candidate, name === "bash" ? 320 : 180);
293
+ if (Array.isArray(input.queries) && input.queries.length > 0) {
294
+ return safeText(input.queries.join(" | "), 180);
295
+ }
296
+ const selector = [
297
+ input.responseId ?? input.response_id,
298
+ input.urlIndex ?? input.url_index,
299
+ input.offset,
300
+ input.limit
301
+ ];
302
+ if (selector.some((value) => value !== undefined && value !== null && value !== "")) {
303
+ return safeText([
304
+ selector[0] === undefined ? "" : `responseId=${String(selector[0])}`,
305
+ selector[1] === undefined ? "" : `urlIndex=${String(selector[1])}`,
306
+ selector[2] === undefined ? "" : `offset=${String(selector[2])}`,
307
+ selector[3] === undefined ? "" : `limit=${String(selector[3])}`
308
+ ].filter(Boolean).join(" "), 180);
309
+ }
310
+ return safeText(candidate, name === "bash" ? 320 : 180);
311
+ }
312
+
313
+ function toolKind(name: string, target: string): ToolObservation["kind"] {
314
+ const normalized = name.toLowerCase();
315
+ if (READ_TOOLS.has(normalized)) return "read";
316
+ if ((normalized === "bash" || normalized === "exec" || normalized === "exec_command") && VERIFIER_PATTERN.test(target)) return "verify";
317
+ if (MUTATION_TOOLS.has(normalized) || (normalized === "bash" && MUTATION_COMMAND_PATTERN.test(target))) return "mutation";
318
+ return "other";
319
+ }
320
+
321
+ export function toolObservations(messages: MessageLike[]): ToolObservation[] {
322
+ const calls = new Map<string, { name: string; input: Record<string, unknown> }>();
323
+ const observations: ToolObservation[] = [];
324
+ for (const message of messages) {
325
+ for (const call of toolCalls(message)) {
326
+ calls.set(String(call.id ?? ""), {
327
+ name: String(call.name ?? "tool"),
328
+ input: call.arguments && typeof call.arguments === "object" ? call.arguments : {}
329
+ });
330
+ }
331
+ if (message.role !== "toolResult") continue;
332
+ const call = calls.get(String(message.toolCallId ?? ""));
333
+ const name = String(message.toolName ?? call?.name ?? "tool").toLowerCase();
334
+ const input = call?.input ?? {};
335
+ const target = toolTarget(name, input);
336
+ const identitySource = `${name}\u0000${canonicalToolArguments(input)}`;
337
+ observations.push({
338
+ identity: crypto.createHash("sha256").update(identitySource).digest("hex").slice(0, 16),
339
+ name,
340
+ target,
341
+ kind: toolKind(name, target),
342
+ isError: message.isError === true,
343
+ tokens: estimateGovernorMessageTokens(message)
344
+ });
345
+ }
346
+ return observations;
347
+ }
348
+
349
+ export function analyzeContextResidency(messages: MessageLike[]): ContextResidencyMetrics {
350
+ const observations = toolObservations(messages);
351
+ const seen = new Set<string>();
352
+ let duplicateResults = 0;
353
+ let lowValueTokens = 0;
354
+ for (const observation of observations) {
355
+ if (seen.has(observation.identity)) duplicateResults += 1;
356
+ seen.add(observation.identity);
357
+ if (observation.kind === "read" && !observation.isError) lowValueTokens += observation.tokens;
358
+ }
359
+ const estimatedMessageTokens = estimateGovernorMessagesTokens(messages);
360
+ return {
361
+ estimatedMessageTokens,
362
+ toolResults: observations.length,
363
+ readResults: observations.filter((item) => item.kind === "read").length,
364
+ mutationResults: observations.filter((item) => item.kind === "mutation").length,
365
+ verifierResults: observations.filter((item) => item.kind === "verify").length,
366
+ failedResults: observations.filter((item) => item.isError).length,
367
+ duplicateResults,
368
+ duplicateResultRate: observations.length > 0 ? duplicateResults / observations.length : 0,
369
+ lowValueTokenShare: estimatedMessageTokens > 0 ? lowValueTokens / estimatedMessageTokens : 0,
370
+ userTurns: operatorMessages(messages).length
371
+ };
372
+ }
373
+
374
+ export function reasonForProjection(
375
+ effectiveTokens: number,
376
+ contextWindow: number,
377
+ boundary: SemanticBoundary,
378
+ residency: ContextResidencyMetrics
379
+ ): { reason: ContextGovernorDecision["reason"]; codes: string[] } {
380
+ const percent = contextWindow > 0 ? (effectiveTokens / contextWindow) * 100 : 0;
381
+ if (effectiveTokens >= CONTEXT_PROVIDER_PROMPT_CEILING_TOKENS || percent >= 68) {
382
+ return { reason: "provider-ceiling", codes: ["provider-prompt-headroom", "preserve-output-budget"] };
383
+ }
384
+ if (boundary.kind !== "none" && (
385
+ effectiveTokens >= CONTEXT_GOVERNOR_SEMANTIC_BOUNDARY_TOKENS
386
+ || residency.toolResults >= 8
387
+ )) {
388
+ return { reason: "semantic-boundary", codes: [`${boundary.kind}-boundary`, "fresh-working-set"] };
389
+ }
390
+ if (residency.toolResults >= CONTEXT_GOVERNOR_TOOL_ROUND_LIMIT && (
391
+ residency.duplicateResultRate >= 0.12
392
+ || residency.readResults >= Math.ceil(CONTEXT_GOVERNOR_TOOL_ROUND_LIMIT * 0.5)
393
+ || effectiveTokens >= CONTEXT_GOVERNOR_TARGET_MESSAGE_TOKENS
394
+ )) {
395
+ return { reason: "residency", codes: ["tool-round-residency", residency.duplicateResults > 0 ? "duplicate-delta" : "stale-read-residency"] };
396
+ }
397
+ if ((effectiveTokens >= CONTEXT_GOVERNOR_PRESSURE_TOKENS || percent >= 52)
398
+ && residency.toolResults >= 8) {
399
+ return { reason: "pressure", codes: ["context-pressure", "value-density"] };
400
+ }
401
+ return { reason: "none", codes: [] };
402
+ }
403
+
404
+ export function minimumContextSavingsTokens(occupancyTokens: number): number {
405
+ const proportional = Math.ceil(Math.max(0, occupancyTokens) * CONTEXT_GOVERNOR_MIN_SAVINGS_RATIO);
406
+ return Math.max(
407
+ CONTEXT_GOVERNOR_MIN_SAVINGS_FLOOR_TOKENS,
408
+ Math.min(CONTEXT_GOVERNOR_MIN_SAVINGS_CEILING_TOKENS, proportional)
409
+ );
410
+ }
411
+
412
+ function toolProtocolSafeCuts(messages: MessageLike[]): number[] {
413
+ const callIndexes = new Map<string, number>();
414
+ const pairSpans: Array<{ call: number; result: number }> = [];
415
+ for (let index = 0; index < messages.length; index += 1) {
416
+ const message = messages[index]!;
417
+ for (const call of toolCalls(message)) {
418
+ const id = toolCallId(call);
419
+ if (id && !callIndexes.has(id)) callIndexes.set(id, index);
420
+ }
421
+ if (message.role !== "toolResult") continue;
422
+ const id = String(message.toolCallId ?? "").trim();
423
+ const call = callIndexes.get(id);
424
+ if (call !== undefined) pairSpans.push({ call, result: index });
425
+ }
426
+
427
+ const blockedDeltas = new Int32Array(messages.length + 2);
428
+ for (const span of pairSpans) {
429
+ blockedDeltas[span.call + 1] += 1;
430
+ blockedDeltas[span.result + 1] -= 1;
431
+ }
432
+ const cuts: number[] = [];
433
+ let blocked = 0;
434
+ for (let cut = 0; cut <= messages.length; cut += 1) {
435
+ blocked += blockedDeltas[cut] ?? 0;
436
+ if (blocked > 0) continue;
437
+ cuts.push(cut);
438
+ }
439
+ return cuts;
440
+ }
441
+
442
+ export function safeSuffixStart(
443
+ messages: MessageLike[],
444
+ recentTokenBudget: number,
445
+ protectedBoundaryGroups = CONTEXT_GOVERNOR_PROTECTED_BOUNDARY_GROUPS
446
+ ): number {
447
+ if (!auditToolProtocol(messages).intact) return 0;
448
+ let tokens = 0;
449
+ let rawStart = messages.length;
450
+ while (rawStart > 0 && tokens < recentTokenBudget) {
451
+ rawStart -= 1;
452
+ tokens += estimateGovernorMessageTokens(messages[rawStart]!);
453
+ }
454
+
455
+ const safeCuts = toolProtocolSafeCuts(messages);
456
+ const budgetStart = [...safeCuts].reverse().find((cut) => cut <= rawStart) ?? 0;
457
+ const protectedGroups = Math.max(0, Math.floor(protectedBoundaryGroups));
458
+ const protectedIndex = Math.max(0, safeCuts.length - 1 - protectedGroups);
459
+ const protectedStart = safeCuts[protectedIndex] ?? 0;
460
+ return Math.min(budgetStart, protectedStart);
461
+ }