@tangle-network/agent-eval 0.146.0 → 0.147.0

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 (145) hide show
  1. package/CHANGELOG.md +14 -0
  2. package/dist/analyst/index.d.ts +13 -13
  3. package/dist/analyst/index.js +6 -6
  4. package/dist/{backend-integrity-HVmWyOaX.d.ts → backend-integrity-Bz8nSrRE.d.ts} +2 -2
  5. package/dist/{backend-integrity-HVmWyOaX.d.ts.map → backend-integrity-Bz8nSrRE.d.ts.map} +1 -1
  6. package/dist/{benchmark-DTQ1RApl.d.ts → benchmark-Cn7ZMFNW.d.ts} +3 -3
  7. package/dist/{benchmark-DTQ1RApl.d.ts.map → benchmark-Cn7ZMFNW.d.ts.map} +1 -1
  8. package/dist/{benchmark-command-CxLJljS1.js → benchmark-command-BTiysiYU.js} +11 -11
  9. package/dist/{benchmark-command-CxLJljS1.js.map → benchmark-command-BTiysiYU.js.map} +1 -1
  10. package/dist/benchmarks/index.d.ts +4 -4
  11. package/dist/benchmarks/index.js +3 -3
  12. package/dist/campaign/index.d.ts +8 -8
  13. package/dist/campaign/index.js +5 -5
  14. package/dist/{campaign-CbQXcARJ.js → campaign-DCDdhuv2.js} +7 -7
  15. package/dist/{campaign-CbQXcARJ.js.map → campaign-DCDdhuv2.js.map} +1 -1
  16. package/dist/{capture-fetch-BZiO2cEH.d.ts → capture-fetch-BAx3Gntt.d.ts} +2 -2
  17. package/dist/{capture-fetch-BZiO2cEH.d.ts.map → capture-fetch-BAx3Gntt.d.ts.map} +1 -1
  18. package/dist/{chat-client-BJmwfnjN.js → chat-client-BX8Wh3fn.js} +3 -3
  19. package/dist/{chat-client-BJmwfnjN.js.map → chat-client-BX8Wh3fn.js.map} +1 -1
  20. package/dist/cli.js +2 -2
  21. package/dist/{client-YDkU5QST.d.ts → client-BV7icIfy.d.ts} +2 -2
  22. package/dist/{client-YDkU5QST.d.ts.map → client-BV7icIfy.d.ts.map} +1 -1
  23. package/dist/contract/index.d.ts +10 -10
  24. package/dist/contract/index.js +9 -9
  25. package/dist/{cost-ledger-BSe92yAV.js → cost-ledger-B1qx30B4.js} +2 -2
  26. package/dist/{cost-ledger-BSe92yAV.js.map → cost-ledger-B1qx30B4.js.map} +1 -1
  27. package/dist/{default-registry-DONui3mA.d.ts → default-registry-BUtRMRKk.d.ts} +6 -6
  28. package/dist/{default-registry-DONui3mA.d.ts.map → default-registry-BUtRMRKk.d.ts.map} +1 -1
  29. package/dist/{define-agent-eval-BGxmy4W6.js → define-agent-eval-BqWFz3sK.js} +3 -3
  30. package/dist/{define-agent-eval-BGxmy4W6.js.map → define-agent-eval-BqWFz3sK.js.map} +1 -1
  31. package/dist/{define-agent-eval-DrpgTVPp.d.ts → define-agent-eval-D52ClbX2.d.ts} +5 -5
  32. package/dist/{define-agent-eval-DrpgTVPp.d.ts.map → define-agent-eval-D52ClbX2.d.ts.map} +1 -1
  33. package/dist/{dspy-rlm-engine-B2nst4NR.js → dspy-rlm-engine-BmtOl_kP.js} +4 -4
  34. package/dist/{dspy-rlm-engine-B2nst4NR.js.map → dspy-rlm-engine-BmtOl_kP.js.map} +1 -1
  35. package/dist/{engine-Bc3seRPe.d.ts → engine-CIy18RTX.d.ts} +4 -4
  36. package/dist/{engine-Bc3seRPe.d.ts.map → engine-CIy18RTX.d.ts.map} +1 -1
  37. package/dist/{eval-campaign-DeGLwACc.js → eval-campaign-bmZ6NIIP.js} +2 -2
  38. package/dist/{eval-campaign-DeGLwACc.js.map → eval-campaign-bmZ6NIIP.js.map} +1 -1
  39. package/dist/{exact-types-CYFbvA5U.d.ts → exact-types-rdKFzEnK.d.ts} +2 -2
  40. package/dist/{exact-types-CYFbvA5U.d.ts.map → exact-types-rdKFzEnK.d.ts.map} +1 -1
  41. package/dist/experiment/index.d.ts +5 -5
  42. package/dist/experiment/index.js +3 -3
  43. package/dist/{experiment-tracker-DWHZBAYL.d.ts → experiment-tracker-D9VHwRm-.d.ts} +6 -24
  44. package/dist/experiment-tracker-D9VHwRm-.d.ts.map +1 -0
  45. package/dist/{experiment-tracker-C29gXM4B.js → experiment-tracker-Ym6rEQT1.js} +15 -4
  46. package/dist/experiment-tracker-Ym6rEQT1.js.map +1 -0
  47. package/dist/{external-optimizer-contracts-CKEY98bK.d.ts → external-optimizer-contracts-CSjDLLmr.d.ts} +2 -2
  48. package/dist/{external-optimizer-contracts-CKEY98bK.d.ts.map → external-optimizer-contracts-CSjDLLmr.d.ts.map} +1 -1
  49. package/dist/{external-optimizer-process-DYNizz8W.js → external-optimizer-process-C4AyCcQd.js} +2 -2
  50. package/dist/{external-optimizer-process-DYNizz8W.js.map → external-optimizer-process-C4AyCcQd.js.map} +1 -1
  51. package/dist/{external-optimizer-subprocess-r6dP9DAj.js → external-optimizer-subprocess-DU1KM8yV.js} +3 -3
  52. package/dist/{external-optimizer-subprocess-r6dP9DAj.js.map → external-optimizer-subprocess-DU1KM8yV.js.map} +1 -1
  53. package/dist/{feedback-trajectory-Cg9EDxKB.d.ts → feedback-trajectory-niGeR6uJ.d.ts} +3 -3
  54. package/dist/{feedback-trajectory-Cg9EDxKB.d.ts.map → feedback-trajectory-niGeR6uJ.d.ts.map} +1 -1
  55. package/dist/fuzz.js +1 -1
  56. package/dist/hosted/index.d.ts +2 -2
  57. package/dist/{index-DGrcBMbC.d.ts → index-BjBjxiVv.d.ts} +9 -9
  58. package/dist/{index-DGrcBMbC.d.ts.map → index-BjBjxiVv.d.ts.map} +1 -1
  59. package/dist/index-CKblBxtr.d.ts +1 -0
  60. package/dist/{index-CevPFhDT.d.ts → index-gtjtfLEJ.d.ts} +7 -7
  61. package/dist/{index-CevPFhDT.d.ts.map → index-gtjtfLEJ.d.ts.map} +1 -1
  62. package/dist/index.d.ts +21 -51
  63. package/dist/index.d.ts.map +1 -1
  64. package/dist/index.js +16 -125
  65. package/dist/index.js.map +1 -1
  66. package/dist/{integrity-DDoeWibF.d.ts → integrity-CGfpTE5-.d.ts} +2 -2
  67. package/dist/{integrity-DDoeWibF.d.ts.map → integrity-CGfpTE5-.d.ts.map} +1 -1
  68. package/dist/{kind-factory-CPmSd58s.js → kind-factory-DmAa0h3K.js} +7 -7
  69. package/dist/kind-factory-DmAa0h3K.js.map +1 -0
  70. package/dist/{llm-client-_UE4fU7Z.js → llm-client-BMuxYoZy.js} +2 -2
  71. package/dist/{llm-client-_UE4fU7Z.js.map → llm-client-BMuxYoZy.js.map} +1 -1
  72. package/dist/{llm-judge-B7ffRF8w.js → llm-judge-DrzsVS5k.js} +4 -4
  73. package/dist/{llm-judge-B7ffRF8w.js.map → llm-judge-DrzsVS5k.js.map} +1 -1
  74. package/dist/{matrix-su7mIfbB.d.ts → matrix-C-2Qx1Zr.d.ts} +2 -2
  75. package/dist/{matrix-su7mIfbB.d.ts.map → matrix-C-2Qx1Zr.d.ts.map} +1 -1
  76. package/dist/meta-eval/index.d.ts +1 -1
  77. package/dist/{metrics-Cl0L1KUy.js → metrics-Qv-cpptD.js} +15 -8
  78. package/dist/metrics-Qv-cpptD.js.map +1 -0
  79. package/dist/multishot/golden/index.d.ts +1 -1
  80. package/dist/multishot/index.d.ts +2 -2
  81. package/dist/multishot/index.js +1 -1
  82. package/dist/openapi.json +1 -1
  83. package/dist/{produced-state-D3k45S9a.js → produced-state-Dtx60bUQ.js} +4 -4
  84. package/dist/{produced-state-D3k45S9a.js.map → produced-state-Dtx60bUQ.js.map} +1 -1
  85. package/dist/{promotion-policy-BKi5OK5l.d.ts → promotion-policy-CewdjfCJ.d.ts} +2 -2
  86. package/dist/{promotion-policy-BKi5OK5l.d.ts.map → promotion-policy-CewdjfCJ.d.ts.map} +1 -1
  87. package/dist/{provenance-Bb7Zmyj2.d.ts → provenance-LrOEOHQb.d.ts} +6 -6
  88. package/dist/{provenance-Bb7Zmyj2.d.ts.map → provenance-LrOEOHQb.d.ts.map} +1 -1
  89. package/dist/{registry-CZgEmVXb.d.ts → registry-CaqJIDdN.d.ts} +4 -4
  90. package/dist/{registry-CZgEmVXb.d.ts.map → registry-CaqJIDdN.d.ts.map} +1 -1
  91. package/dist/reporting.d.ts +1 -1
  92. package/dist/reporting.js +1 -1
  93. package/dist/{researcher-CC305Ed-.d.ts → researcher-BySlpla_.d.ts} +3 -3
  94. package/dist/{researcher-CC305Ed-.d.ts.map → researcher-BySlpla_.d.ts.map} +1 -1
  95. package/dist/rl.d.ts +3 -3
  96. package/dist/rl.js +2 -2
  97. package/dist/{semantic-concept-judge-BsY2Q0Oq.js → semantic-concept-judge-BI7Rrl5-.js} +3 -3
  98. package/dist/{semantic-concept-judge-BsY2Q0Oq.js.map → semantic-concept-judge-BI7Rrl5-.js.map} +1 -1
  99. package/dist/{sequential-CYwq6Ff_.d.ts → sequential-BhsrMupG.d.ts} +31 -2
  100. package/dist/sequential-BhsrMupG.d.ts.map +1 -0
  101. package/dist/{sequential-Br0mAPHA.js → sequential-CzK5DarL.js} +48 -6
  102. package/dist/sequential-CzK5DarL.js.map +1 -0
  103. package/dist/series-convergence-CjO2QdRW.js.map +1 -1
  104. package/dist/{series-convergence-C9G-GNYK.d.ts → series-convergence-D2fsoJ2w.d.ts} +4 -7
  105. package/dist/{series-convergence-C9G-GNYK.d.ts.map → series-convergence-D2fsoJ2w.d.ts.map} +1 -1
  106. package/dist/{server-cQXve8i4.js → server-D9wQclzG.js} +3 -3
  107. package/dist/{server-cQXve8i4.js.map → server-D9wQclzG.js.map} +1 -1
  108. package/dist/{skillopt-optimization-method-C9MrMgW9.d.ts → skillopt-optimization-method-BoC1Qccx.d.ts} +5 -5
  109. package/dist/{skillopt-optimization-method-C9MrMgW9.d.ts.map → skillopt-optimization-method-BoC1Qccx.d.ts.map} +1 -1
  110. package/dist/{skillopt-optimization-method-Cv3K4DaS.js → skillopt-optimization-method-C_UrqZs2.js} +4 -4
  111. package/dist/{skillopt-optimization-method-Cv3K4DaS.js.map → skillopt-optimization-method-C_UrqZs2.js.map} +1 -1
  112. package/dist/{statistical-heldout-fvxtHnKQ.d.ts → statistical-heldout-uxSpFEjm.d.ts} +2 -2
  113. package/dist/{statistical-heldout-fvxtHnKQ.d.ts.map → statistical-heldout-uxSpFEjm.d.ts.map} +1 -1
  114. package/dist/{store-otlp-CsptLYpN.js → store-otlp-CDYWW_8N.js} +2 -2
  115. package/dist/{store-otlp-CsptLYpN.js.map → store-otlp-CDYWW_8N.js.map} +1 -1
  116. package/dist/{store-tool-spans-Cq9mFd-q.js → store-tool-spans-CykkbOlv.js} +3 -3
  117. package/dist/{store-tool-spans-Cq9mFd-q.js.map → store-tool-spans-CykkbOlv.js.map} +1 -1
  118. package/dist/{store-tool-spans-CV0hRsUp.d.ts → store-tool-spans-D5FhM0_A.d.ts} +4 -4
  119. package/dist/{store-tool-spans-CV0hRsUp.d.ts.map → store-tool-spans-D5FhM0_A.d.ts.map} +1 -1
  120. package/dist/{task-failure-attributes-CpQ4y5RD.js → task-failure-attributes--ZTP3tYO.js} +2 -2
  121. package/dist/{task-failure-attributes-CpQ4y5RD.js.map → task-failure-attributes--ZTP3tYO.js.map} +1 -1
  122. package/dist/{tool-groups-CDDXNKhd.d.ts → tool-groups-zpufabP8.d.ts} +3 -3
  123. package/dist/tool-groups-zpufabP8.d.ts.map +1 -0
  124. package/dist/trace-repair/index.d.ts +1 -1
  125. package/dist/traces.d.ts +7 -7
  126. package/dist/traces.js +4 -4
  127. package/dist/{types-oAsa-fs4.d.ts → types-BohHewKK.d.ts} +2 -2
  128. package/dist/{types-oAsa-fs4.d.ts.map → types-BohHewKK.d.ts.map} +1 -1
  129. package/dist/{types-DABZgDGV.d.ts → types-C1Bmeb8X.d.ts} +3 -3
  130. package/dist/{types-DABZgDGV.d.ts.map → types-C1Bmeb8X.d.ts.map} +1 -1
  131. package/dist/{types-CWcPguwd.d.ts → types-ColZlZtc.d.ts} +2 -2
  132. package/dist/{types-CWcPguwd.d.ts.map → types-ColZlZtc.d.ts.map} +1 -1
  133. package/dist/{types-XBRdmbj8.d.ts → types-DOhGq4S1.d.ts} +1 -7
  134. package/dist/{types-XBRdmbj8.d.ts.map → types-DOhGq4S1.d.ts.map} +1 -1
  135. package/dist/wire/index.d.ts +2 -2
  136. package/dist/wire/index.js +1 -1
  137. package/package.json +2 -2
  138. package/dist/experiment-tracker-C29gXM4B.js.map +0 -1
  139. package/dist/experiment-tracker-DWHZBAYL.d.ts.map +0 -1
  140. package/dist/index-BgHYx1QG.d.ts +0 -1
  141. package/dist/kind-factory-CPmSd58s.js.map +0 -1
  142. package/dist/metrics-Cl0L1KUy.js.map +0 -1
  143. package/dist/sequential-Br0mAPHA.js.map +0 -1
  144. package/dist/sequential-CYwq6Ff_.d.ts.map +0 -1
  145. package/dist/tool-groups-CDDXNKhd.d.ts.map +0 -1
@@ -1,7 +1,7 @@
1
1
  import { S as PaidCallResult, T as RunPaidCallInput, a as CostChannel, c as CostLedgerHandle, f as CostLedgerSummary, p as CostProvenance } from "./cost-ledger-DbQdN3nO.js";
2
2
  import { u as RunTokenUsage } from "./run-record-DVV82Gwh.js";
3
- import { E as LlmCallMetadata } from "./types-XBRdmbj8.js";
4
- import { _ as ProposalFinding } from "./types-oAsa-fs4.js";
3
+ import { E as LlmCallMetadata } from "./types-DOhGq4S1.js";
4
+ import { _ as ProposalFinding } from "./types-BohHewKK.js";
5
5
  //#region src/campaign/types.d.ts
6
6
  /** Stable identifier + kind tag for any scenario. Consumers
7
7
  * extend with their per-domain payload (persona, task, requirement, ...). */
@@ -626,4 +626,4 @@ interface CampaignResult<TArtifact = unknown, TScenario extends Scenario = Scena
626
626
  }
627
627
  //#endregion
628
628
  export { LabeledScenarioWrite as A, ScoredSurfaceOutcome as B, JudgeDimension as C, LabeledScenarioSampleArgs as D, LabeledScenarioRecord as E, ProposeContext as F, labelTrustRank as G, SurfaceProposer as H, ProposedCandidate as I, RedactionStatus as L, OptimizerConfig as M, ParetoParent as N, LabeledScenarioSource as O, ProposalTrackContext as P, Scenario as R, JudgeConfig as S, LabelTrust as T, TraceSpan as U, SessionScript as V, isProposedCandidate as W, GateDecision as _, CampaignResult as a, GenerationRecord as b, CampaignTraceWriter as c, DispatchContext as d, DispatchFn as f, GateContribution as g, GateContext as h, CampaignCostMeter as i, MutableSurface as j, LabeledScenarioStore as k, CodeSurface as l, GateCheckStatus as m, CampaignArtifactWriter as n, CampaignScenarioIdentity as o, Gate as p, CampaignCellResult as r, CampaignTokenUsage as s, CampaignAggregates as t, ComponentSurface as u, GateResult as v, JudgeScore as w, JudgeAggregate as x, GenerationCandidate as y, ScenarioAggregate as z };
629
- //# sourceMappingURL=types-DABZgDGV.d.ts.map
629
+ //# sourceMappingURL=types-C1Bmeb8X.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"types-DABZgDGV.d.ts","names":[],"sources":["../src/campaign/types.ts"],"mappings":";;;;;;;UAgCiB;EACf;EACA;EACA;;;;;EAKA;;;UAIe,iCAAiC,KAAK;EACrD;;;;;UAMe;EACf;;EAEA;EACA;EACA;EACA;EACA,QAAQ;EACR,OAAO;EACP,WAAW;EACX,MAAM;;EAEN;;EAEA;;;;;;;;EAQA;;;;KAKU,WAAW,kBAAkB,UAAU,cACjD,UAAU,WACV,KAAK,oBACF,QAAQ;;;;UAOI,cAAc,WAAW;EACxC;EACA;EACA;;EAEA;;;EAGA,sBAAsB,UAAU,WAAW,sBAAsB,UAAU,cAAc;;UAK1E;;EAEf;;EAEA;;;;;;;;;UAUe,YAAY,WAAW,kBAAkB,WAAW;EACnE;EACA,YAAY;;;;EAIZ;;;EAGA,MAAM;IACJ,UAAU;IACV,UAAU;IACV,QAAQ;;IAER,aAAa;IACb;IACA,WAAW;MACT,aAAa,QAAQ;EACzB,aAAa,UAAU;;;;;;;;;;;UAYR;EACf,YAAY;EACZ;EACA;;EAEA,UAAU;;;;EAIV;;;EAGA;;EAEA;;EAEA,WAAW,eAAe;;;;;;;UAUX;WACN;;;WAGA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;WAGA;aACE;aACA;aACA;;;WAGF;;;UAIM;WACN;WACA,YAAY,SAAS;;;;;;;;;;;KAYpB,0BAA0B,mBAAmB;;;;;;;UAQxC;EACf,SAAS;;EAET;;;;EAIA;;;;iBAKc,oBACd,OAAO,iBAAiB,oBACvB,SAAS;;;;;;;;;UAkBK;EACf,SAAS;EACT;;;EAGA,YAAY;;;EAGZ;;EAEA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA;;;;;UAMe;;;EAGf;;EAEA;EACA;EACA;EACA,YAAY;;;;;EAKZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;EAC1E;IACE;IACA;;;;;UAMa,eAAe,YAAY;WACjC,gBAAgB;WAChB,SAAS,cAAc;WACvB,UAAU,cAAc;;WAExB;WACA;WACA,QAAQ;;WAER,QAAQ;;;WAGR,kBAAkB;;;WAGlB,mBAAmB;;;;WAInB;;;;;;;WAOA,gBAAgB,cAAc;;WAE9B,aAAa;WACb;;;;;;;;;;;;;;UAeM,gBAAgB,YAAY;EAC3C;;;;;EAKA,QAAQ,KAAK,eAAe,aAAa,QAAQ,MAAM,iBAAiB;;;EAGxE,QAAQ;IAAQ,SAAS,cAAc;;IAAwB;IAAe;;;UAG/D;EACf;EACA;EACA,mBAAmB,qBAAqB;;UAGzB,wBAAwB;EACvC,UAAU;;;KAMA;;KAGA;UAEK;EACf;EACA,QAAQ;EACR;;UAGe,YAAY,WAAW,kBAAkB;EACxD,oBAAoB,YAAY;EAChC,oBAAoB,YAAY;;EAEhC,aAAa,YAAY,eAAe;;;;;EAKxC,sBAAsB,YAAY,eAAe;;;;;;;EAOjD,yBAAyB,YAAY,eAAe;;;EAGpD,uBAAuB,YAAY;EACnC,WAAW;EACX;IAAQ;IAAmB;;;EAE3B,aAAa;EACb;EACA,QAAQ;;UAGO;EACf,UAAU;EACV;EACA,mBAAmB;EACnB;;;UAIe,KAAK,qBAAqB,kBAAkB,WAAW;EACtE;EACA,OAAO,KAAK,YAAY,WAAW,aAAa,QAAQ;;;;UAOzC;EACf,KAAK,cAAc,aAAa,0BAA0B;EAC1D,SAAS;;UAGM;EACf,IAAI,aAAa;EACjB,aAAa,aAAa;;;;UAKX;EACf,MAAM,cAAc,kBAAkB,aAAa;EACnD,UAAU,cAAc,iBAAiB;;;;;;KAO/B,qBAAqB;;;;;UAMhB;;EAEf,YAAY,GACV,OAAO,KAAK,iBAAiB;IAC3B,UAAU;MAEX,QAAQ,eAAe;;;;;KAQhB;KAOA;;;;;;;;;;;;;;;KAgBA;;iBASI,eAAe,OAAO;;;;UAOrB,qBAAqB,kBAAkB,WAAW,UAAU;EAC3E,UAAU;EACV,UAAU;EACV,aAAa,eAAe;EAC5B,QAAQ;EACR;EACA;EACA,iBAAiB;;;;;EAKjB,aAAa;;EAEb;;UAGe,sBAAsB,kBAAkB,WAAW,UAAU,6BACpE,qBAAqB,WAAW;;EAExC;;;EAGA;;UAGe;EACf;;EAEA;;;;EAIA;EACA;IACE;IACA,SAAS,wBAAwB;IACjC;IACA;;;;;IAKA,WAAW;;;UAIE;EACf,QAAQ,OAAO,uBAAuB;EACtC,OAAO,MAAM,4BAA4B,QAAQ;EACjD,QAAQ;IACN;IACA;IACA,UAAU;;;IAGV,SAAS,OAAO;;;UAMH,mBAAmB;;;EAGlC;EACA;EACA;EACA;EACA;EACA,UAAU;EACV,aAAa,eAAe;;;EAG5B;;EAEA,gBAAgB;;EAEhB;;;EAGA,YAAY;;;EAGZ;;;EAGA;EACA;EACA;EACA;;EAEA;;EAEA;EACA;;UAGe;EACf;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,YAAY;EACZ;;;;;;UAOe;EACf;;EAEA;;EAEA;;EAEA;;EAEA;;;EAGA;;;;EAIA;;;;EAIA;IACE;IACA;IACA,iBAAiB;MAAQ;MAAgB;;;;;EAI3C,YAAY;;;;;;;;;;EAUZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;;;EAG1E;;;;EAIA;;UAGe;EACf,SAAS,eAAe;EACxB,YAAY,eAAe;;EAE3B,MAAM;;EAEN;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe,eAAe,qBAAqB,kBAAkB,WAAW;;EAEhF;;EAEA;EACA;;EAEA;EACA;EACA;EACA;EACA,OAAO,MAAM,mBAAmB;EAChC,YAAY;EACZ;IACE,aAAa;IACb;;EAEF,OAAO;EACP;EACA;EACA,iBAAiB;;;EAGjB,WAAW,MAAM,2BAA2B,KAAK"}
1
+ {"version":3,"file":"types-C1Bmeb8X.d.ts","names":[],"sources":["../src/campaign/types.ts"],"mappings":";;;;;;;UAgCiB;EACf;EACA;EACA;;;;;EAKA;;;UAIe,iCAAiC,KAAK;EACrD;;;;;UAMe;EACf;;EAEA;EACA;EACA;EACA;EACA,QAAQ;EACR,OAAO;EACP,WAAW;EACX,MAAM;;EAEN;;EAEA;;;;;;;;EAQA;;;;KAKU,WAAW,kBAAkB,UAAU,cACjD,UAAU,WACV,KAAK,oBACF,QAAQ;;;;UAOI,cAAc,WAAW;EACxC;EACA;EACA;;EAEA;;;EAGA,sBAAsB,UAAU,WAAW,sBAAsB,UAAU,cAAc;;UAK1E;;EAEf;;EAEA;;;;;;;;;UAUe,YAAY,WAAW,kBAAkB,WAAW;EACnE;EACA,YAAY;;;;EAIZ;;;EAGA,MAAM;IACJ,UAAU;IACV,UAAU;IACV,QAAQ;;IAER,aAAa;IACb;IACA,WAAW;MACT,aAAa,QAAQ;EACzB,aAAa,UAAU;;;;;;;;;;;UAYR;EACf,YAAY;EACZ;EACA;;EAEA,UAAU;;;;EAIV;;;EAGA;;EAEA;;EAEA,WAAW,eAAe;;;;;;;UAUX;WACN;;;WAGA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;WAGA;aACE;aACA;aACA;;;WAGF;;;UAIM;WACN;WACA,YAAY,SAAS;;;;;;;;;;;KAYpB,0BAA0B,mBAAmB;;;;;;;UAQxC;EACf,SAAS;;EAET;;;;EAIA;;;;iBAKc,oBACd,OAAO,iBAAiB,oBACvB,SAAS;;;;;;;;;UAkBK;EACf,SAAS;EACT;;;EAGA,YAAY;;;EAGZ;;EAEA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA;;;;;UAMe;;;EAGf;;EAEA;EACA;EACA;EACA,YAAY;;;;;EAKZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;EAC1E;IACE;IACA;;;;;UAMa,eAAe,YAAY;WACjC,gBAAgB;WAChB,SAAS,cAAc;WACvB,UAAU,cAAc;;WAExB;WACA;WACA,QAAQ;;WAER,QAAQ;;;WAGR,kBAAkB;;;WAGlB,mBAAmB;;;;WAInB;;;;;;;WAOA,gBAAgB,cAAc;;WAE9B,aAAa;WACb;;;;;;;;;;;;;;UAeM,gBAAgB,YAAY;EAC3C;;;;;EAKA,QAAQ,KAAK,eAAe,aAAa,QAAQ,MAAM,iBAAiB;;;EAGxE,QAAQ;IAAQ,SAAS,cAAc;;IAAwB;IAAe;;;UAG/D;EACf;EACA;EACA,mBAAmB,qBAAqB;;UAGzB,wBAAwB;EACvC,UAAU;;;KAMA;;KAGA;UAEK;EACf;EACA,QAAQ;EACR;;UAGe,YAAY,WAAW,kBAAkB;EACxD,oBAAoB,YAAY;EAChC,oBAAoB,YAAY;;EAEhC,aAAa,YAAY,eAAe;;;;;EAKxC,sBAAsB,YAAY,eAAe;;;;;;;EAOjD,yBAAyB,YAAY,eAAe;;;EAGpD,uBAAuB,YAAY;EACnC,WAAW;EACX;IAAQ;IAAmB;;;EAE3B,aAAa;EACb;EACA,QAAQ;;UAGO;EACf,UAAU;EACV;EACA,mBAAmB;EACnB;;;UAIe,KAAK,qBAAqB,kBAAkB,WAAW;EACtE;EACA,OAAO,KAAK,YAAY,WAAW,aAAa,QAAQ;;;;UAOzC;EACf,KAAK,cAAc,aAAa,0BAA0B;EAC1D,SAAS;;UAGM;EACf,IAAI,aAAa;EACjB,aAAa,aAAa;;;;UAKX;EACf,MAAM,cAAc,kBAAkB,aAAa;EACnD,UAAU,cAAc,iBAAiB;;;;;;KAO/B,qBAAqB;;;;;UAMhB;;EAEf,YAAY,GACV,OAAO,KAAK,iBAAiB;IAC3B,UAAU;MAEX,QAAQ,eAAe;;;;;KAQhB;KAOA;;;;;;;;;;;;;;;KAgBA;;iBASI,eAAe,OAAO;;;;UAOrB,qBAAqB,kBAAkB,WAAW,UAAU;EAC3E,UAAU;EACV,UAAU;EACV,aAAa,eAAe;EAC5B,QAAQ;EACR;EACA;EACA,iBAAiB;;;;;EAKjB,aAAa;;EAEb;;UAGe,sBAAsB,kBAAkB,WAAW,UAAU,6BACpE,qBAAqB,WAAW;;EAExC;;;EAGA;;UAGe;EACf;;EAEA;;;;EAIA;EACA;IACE;IACA,SAAS,wBAAwB;IACjC;IACA;;;;;IAKA,WAAW;;;UAIE;EACf,QAAQ,OAAO,uBAAuB;EACtC,OAAO,MAAM,4BAA4B,QAAQ;EACjD,QAAQ;IACN;IACA;IACA,UAAU;;;IAGV,SAAS,OAAO;;;UAMH,mBAAmB;;;EAGlC;EACA;EACA;EACA;EACA;EACA,UAAU;EACV,aAAa,eAAe;;;EAG5B;;EAEA,gBAAgB;;EAEhB;;;EAGA,YAAY;;;EAGZ;;;EAGA;EACA;EACA;EACA;;EAEA;;EAEA;EACA;;UAGe;EACf;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,YAAY;EACZ;;;;;;UAOe;EACf;;EAEA;;EAEA;;EAEA;;EAEA;;;EAGA;;;;EAIA;;;;EAIA;IACE;IACA;IACA,iBAAiB;MAAQ;MAAgB;;;;;EAI3C,YAAY;;;;;;;;;;EAUZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;;;EAG1E;;;;EAIA;;UAGe;EACf,SAAS,eAAe;EACxB,YAAY,eAAe;;EAE3B,MAAM;;EAEN;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe,eAAe,qBAAqB,kBAAkB,WAAW;;EAEhF;;EAEA;EACA;;EAEA;EACA;EACA;EACA;EACA,OAAO,MAAM,mBAAmB;EAChC,YAAY;EACZ;IACE,aAAa;IACb;;EAEF,OAAO;EACP;EACA;EACA,iBAAiB;;;EAGjB,WAAW,MAAM,2BAA2B,KAAK"}
@@ -1,5 +1,5 @@
1
1
  import { s as RunSplitTag } from "./run-record-DVV82Gwh.js";
2
- import { R as Scenario, d as DispatchContext } from "./types-DABZgDGV.js";
2
+ import { R as Scenario, d as DispatchContext } from "./types-C1Bmeb8X.js";
3
3
  //#region src/benchmarks/types.d.ts
4
4
  type BenchmarkTaskKind = 'retrieval' | 'rag-answer' | 'hallucination' | 'kb-improvement' | 'routing' | 'custom';
5
5
  type BenchmarkFamily = 'beir' | 'mteb-retrieval' | 'msmarco' | 'trec-dl' | 'miracl' | 'lotte' | 'bright' | 'crag' | 'hotpotqa' | 'kilt' | 'ragtruth' | 'faithbench' | 'first-party' | 'custom';
@@ -90,4 +90,4 @@ declare const BENCHMARK_SPLIT_SEED = "agent-eval-v1";
90
90
  declare function deterministicSplit(itemId: string, seed?: string): RunSplitTag;
91
91
  //#endregion
92
92
  export { BenchmarkFamily as a, BenchmarkSource as c, BenchmarkEvaluation as i, BenchmarkTaskKind as l, BenchmarkAdapter as n, BenchmarkResponder as o, BenchmarkDatasetItem as r, BenchmarkScenario as s, BENCHMARK_SPLIT_SEED as t, deterministicSplit as u };
93
- //# sourceMappingURL=types-CWcPguwd.d.ts.map
93
+ //# sourceMappingURL=types-ColZlZtc.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"types-CWcPguwd.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;EACA;EACA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}
1
+ {"version":3,"file":"types-ColZlZtc.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;EACA;EACA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}
@@ -767,10 +767,6 @@ interface CompletionCriterion {
767
767
  check: (state: DriverState) => boolean;
768
768
  progress?: (state: DriverState) => number;
769
769
  }
770
- interface FeedbackPattern {
771
- trigger: string;
772
- response: string;
773
- }
774
770
  /**
775
771
  * How hard the simulated user pushes back. The driver LLM scales its tone
776
772
  * and follow-up aggression to this:
@@ -785,9 +781,7 @@ interface PersonaConfig {
785
781
  role: string;
786
782
  goal: string;
787
783
  completionCriteria: CompletionCriterion[];
788
- feedbackPatterns?: FeedbackPattern[];
789
784
  maxTurns: number;
790
- driverModel?: string;
791
785
  /** How adversarial the simulated user is. Defaults to 'demanding'. */
792
786
  rigor?: PersonaRigor;
793
787
  /**
@@ -842,4 +836,4 @@ interface CheckResult {
842
836
  }
843
837
  //#endregion
844
838
  export { checkServedModel as $, LlmClientOptions as A, isTransientLlmError as B, SandboxSdkTransportOpts as C, LlmCallRequest as D, LlmCallMetadata as E, assertLlmRoute as F, AssertServedModelOptions as G, probeLlm as H, callLlm as I, ServedModelCheck as J, ModelSubstitutionError as K, callLlmJson as L, LlmResponseError as M, LlmRouteRequirements as N, LlmCallResult as O, LlmUsage as P, assertServedModels as Q, costReceiptFromLlm as R, RouterTransportOpts as S, LlmCallError as T, stripFencedJson as U, maximumChargeForLlmRequest as V, AssertCrossFamilyServedOptions as W, assertCrossFamilyServed as X, ServedModelVerdict as Y, assertServedModel as Z, CliBridgeTransportOpts as _, providerFromBaseUrl as _t, JudgeInput as a, judgeFamily as at, DirectProviderTransportOpts as b, PersonaConfig as c, InMemoryRawProviderSink as ct, Scenario as d, ProviderRedactor as dt, servedModelAcceptable as et, ChatCallOpts as f, RawProviderDirection as ft, ChatTransport as g, defaultProviderRedactor as gt, ChatResponse as h, RawProviderSinkFilter as ht, JudgeFn as i, assertCrossFamily as it, LlmMessage as j, LlmClient as k, ProductClientConfig as l, InMemoryRawProviderSinkOptions as lt, ChatRequest as m, RawProviderSink as mt, CompletionCriterion as n, CrossFamilyError as nt, JudgeRubric as o, FileSystemRawProviderSink as ot, ChatClient as p, RawProviderEvent as pt, ServedCrossFamilyError as q, DriverState as r, JudgeFamily as rt, JudgeScore as s, FileSystemRawProviderSinkOptions as st, CheckResult as t, AssertCrossFamilyOptions as tt, RouteMap as u, NoopRawProviderSink as ut, CreateChatClientOpts as v, createChatClient as w, MockTransportOpts as x, CustomTransportOpts as y, costReceiptFromLlmError as z };
845
- //# sourceMappingURL=types-XBRdmbj8.d.ts.map
839
+ //# sourceMappingURL=types-DOhGq4S1.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"types-XBRdmbj8.d.ts","names":[],"sources":["../src/trace/raw-provider-sink.ts","../src/judge-families.ts","../src/integrity/served-model.ts","../src/llm-client.ts","../src/analyst/chat-client.ts","../src/types.ts"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;KA8BY;UAEK;;EAEf;;EAEA;EACA;;;;;;EAMA;EACA;;EAEA;;EAEA;;EAEA;EACA,WAAW;;EAEX;;EAEA;EACA;EACA,iBAAiB;EACjB;EACA,kBAAkB;EAClB;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA,YAAY;EACZ;;UAGe;EACf,OAAO,OAAO,mBAAmB;;EAEjC,MAAM,SAAS,wBAAwB,QAAQ;;EAE/C,UAAU;;KAGA,oBAAoB,OAAO,qBAAqB;;;;;;iBAmB5C,wBAAwB,OAAO,mBAAmB;UA8CjD;EACf,WAAW;;cAGA,mCAAmC;UACtC;UACA;EAER,YAAY,OAAM;EAIZ,OAAO,OAAO,mBAAmB;EAIjC,KAAK,SAAQ,wBAA6B,QAAQ;EAUxD;;cAKW,+BAA+B;EACpC,UAAU;;;;;;;EASV,QAAQ,QAAQ;;UAOP;;EAEf;;EAEA;;EAEA;EACA,WAAW;;cAGA,qCAAqC;UACxC;UACA;UACA;UACA;UACA;UACA;UACA;EAER,YAAY,MAAM;UAOJ;UAON;EAKF,OAAO,OAAO,mBAAmB;EAYjC,KAAK,SAAQ,wBAA6B,QAAQ;;;;;;iBAkC1C,oBAAoB;;;;;;;;;;;;;KC5QxB;;;;;;;iBAkEI,YAAY,kBAAkB;UAc7B;;EAEf;;;;EAIA;;cAGW,yBAAyB;WAGlB,UAAU;WACV;EAHlB,YACE,iBACgB,UAAU,eACV;;;;;;;;;;;;;;;iBAoBJ,kBACd,kBACA,OAAM,2BACL;;;;KCnFS;;;;;;;;;;;UAYK;;EAEf;;EAEA;EACA,iBAAiB;;EAEjB,cAAc;EACd,SAAS;;EAET;;;;;;;;;;;;iBA4Cc,iBACd,mBACA,oCACC;cA4CU,+BAA+B;WAGxB,QAAQ,cAAc;EAFxC,YACE,iBACgB,QAAQ,cAAc;;UAOzB;;;;;;EAMf;;;;;EAKA;;EAEA;;;;;;;iBAQc,sBACd,OAAO,kBACP,OAAM;;;;;;iBA6BQ,kBACd,mBACA,mCACA,OAAM,2BACL;;;;;iBAea,mBACd,OAAO;EAAgB;EAAmB;IAC1C,OAAM,2BACL;UAec,uCAAuC;;EAEtD;;EAEA;;cAGW,+BAA+B;WAGxB,UAAU;WACV,QAAQ,cAAc;EAHxC,YACE,iBACgB,UAAU,eACV,QAAQ,cAAc;;;;;;;;;;;iBAgB1B,wBACd,OAAO;EAAgB;EAAmB;IAC1C,OAAM,iCACL;;;UCjPc;EACf;;;;;EAKA,kBAEI;IACM;IAAc;;IACd;IAAmB;MAAa;MAAa;;;;KAI7C;UAEK;EACf;EACA,UAAU;;EAEV;;EAEA;IAAe;IAAc,QAAQ;;EACrC;EACA;;EAEA,WAAW;;EAEX;;;;;;iBAOc,2BACd,SAAS,KAAK,iFACd,UAAS,mBACR;UAgCc;EACf;EACA;EACA;;EAEA;;EAEA;;EAEA;;UAGe;;EAEf;EACA,OAAO;;;;;EAKP;;;;;;;;;EASA;;;;;;;;;;;;EAYA;;EAEA;;;;;;;;;EASA;;;;;;;EAOA;;EAEA,KAAK;;KAGK,kBAAkB,KAAK;;iBAGnB,mBACd,QAAQ,eACR,qBAAqB,qBACpB;;iBA2Ba,wBACd,OAAO,OACP,qBAAqB,qBACpB;cAMU,qBAAqB;WAGd;WACA;WACA;EAJlB,YACE,iBACgB,gBACA,cACA;;;;;cASP,yBAAyB;WAGlB,QAAQ;EAF1B,YACE,iBACgB,QAAQ,eACxB;IAAY;;;UAMC;;EAEf;;EAEA;EACA;;EAEA;IAAe;IAAc;;;EAE7B;;EAEA;;;;;;;EAOA,SAAS;;;;;;;;EAQT;;EAEA;;EAEA,qBAAqB;;;;;;;EAOrB;;;;;;EAMA;;EAEA,WAAW;;EAEX,eAAe;;;;;;;;EAQf,UAAU;;;;;EAKV;;EAEA;IAAiB;IAAgB;;;EAEjC,WAAW;;;;;;;;;;EAUX,8BAA8B;;;;;;;;;;;;;iBAsEhB,oBAAoB;;;;;;iBA6IpB,gBAAgB;;;;;;iBA6EV,QACpB,KAAK,gBACL,OAAM,mBACL,QAAQ;;;;;;;iBAoVW,YAAY,aAChC,KAAK,gBACL,OAAM,mBACL;EAAU,OAAO;EAAG,QAAQ;;UA6Ed;;;;;;;EAOf;;;;;EAKA,kBAAkB,eAAe;;EAEjC,kBAAkB,eAAe;;EAEjC;;;;;EAKA;;;;;;;;;;;iBAYc,eAAe,MAAM,kBAAkB,MAAK;;;;;;;;;;;;;;;;;;iBA6EtC,SACpB,eACA,OAAM;EAAqB;IAC1B;EACD;EACA;EACA;;EAEA;;EAEA;;;;;;;cAoCW;WACF;mBACQ;EAEjB,YAAY,OAAM;EAKlB,KAAK,KAAK,gBAAgB,MAAM,mBAAmB,QAAQ;EAK3D,SAAS,aACP,KAAK,gBACL,MAAM,mBACL;IAAU,OAAO;IAAG,QAAQ;;;;;;;;UCjqChB;;WAEN,WAAW;;WAEX;;WAEA;;EAGT,KAAK,KAAK,aAAa,OAAO,eAAe,QAAQ;;KAG3C;UAQK,oBAAoB,KAAK;;EAExC;;KAGU,eAAe;UAEV;;EAEf,SAAS;;EAET;;EAEA;;EAEA;;KAKU,uBACR,sBACA,yBACA,8BACA,0BACA,sBACA;UAEM;EACR;;EAEA;;UAGe,4BAA4B;EAC3C;EACA;EACA;;UAGe,+BAA+B;EAC9C;EACA;EACA;;UAGe,oCAAoC;EACnD;EACA;EACA;;;;;;UAOe,gCAAgC;EAC/C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;UAI1C,4BAA4B;EAC3C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;UAO1C,0BAA0B;EACzC;EACA,UAAU,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;iBAO9C,iBAAiB,MAAM,uBAAuB;;;UCjH7C;EACf;EACA;EACA;EACA;EACA;EACA,OAAO;EACP,gBAAgB;EAChB;;UAGe;EACf;EACA;EACA;EACA;;UAKe;EACf;EAQA;EACA;EACA;EACA;;UAKe;EACf;EACA;EACA,YAAY;;UAGG;EACf;EACA;EACA;EACA;EACA;;UAmBe;EACf;EACA;EACA;EACA;EACA;IAAmB;IAAc;;EACjC;EACA;;UASe;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;IAAc;IAAc;;EAC5B;IAAmB;IAAc,QAAQ;;EACzC;IAAc;IAAkB;;EAChC;;UAKe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;GACC;;UAGc;EACf;EACA,QAAQ;;EAER;;UAyBe;EACf;EACA,QAAQ,OAAO;EACf,YAAY,OAAO;;UAGJ;EACf;EACA;;;;;;;;;;KAWU;UAEK;EACf;EACA;EACA;EACA,oBAAoB;EACpB,mBAAmB;EACnB;EACA;;EAEA,QAAQ;;;;;;;EAOR;;;;;;;EAOA;;;;;;EAMA;;UAGe;EACf;EACA;EACA;IAAa;IAAiB;IAAkB;;EAChD;EACA;EACA;;UAGe;EACf,UAAU;EACV,OAAO;EACP,WAAW;;EAEX,aAAa;EACb;EACA,WAAW;EACX,SAAS;;KAGC,WAAW,MAAM,YAAY,OAAO,eAAe,QAAQ;UAYtD;EACf;EACA;EACA;EACA"}
1
+ {"version":3,"file":"types-DOhGq4S1.d.ts","names":[],"sources":["../src/trace/raw-provider-sink.ts","../src/judge-families.ts","../src/integrity/served-model.ts","../src/llm-client.ts","../src/analyst/chat-client.ts","../src/types.ts"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;KA8BY;UAEK;;EAEf;;EAEA;EACA;;;;;;EAMA;EACA;;EAEA;;EAEA;;EAEA;EACA,WAAW;;EAEX;;EAEA;EACA;EACA,iBAAiB;EACjB;EACA,kBAAkB;EAClB;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA,YAAY;EACZ;;UAGe;EACf,OAAO,OAAO,mBAAmB;;EAEjC,MAAM,SAAS,wBAAwB,QAAQ;;EAE/C,UAAU;;KAGA,oBAAoB,OAAO,qBAAqB;;;;;;iBAmB5C,wBAAwB,OAAO,mBAAmB;UA8CjD;EACf,WAAW;;cAGA,mCAAmC;UACtC;UACA;EAER,YAAY,OAAM;EAIZ,OAAO,OAAO,mBAAmB;EAIjC,KAAK,SAAQ,wBAA6B,QAAQ;EAUxD;;cAKW,+BAA+B;EACpC,UAAU;;;;;;;EASV,QAAQ,QAAQ;;UAOP;;EAEf;;EAEA;;EAEA;EACA,WAAW;;cAGA,qCAAqC;UACxC;UACA;UACA;UACA;UACA;UACA;UACA;EAER,YAAY,MAAM;UAOJ;UAON;EAKF,OAAO,OAAO,mBAAmB;EAYjC,KAAK,SAAQ,wBAA6B,QAAQ;;;;;;iBAkC1C,oBAAoB;;;;;;;;;;;;;KC5QxB;;;;;;;iBAkEI,YAAY,kBAAkB;UAc7B;;EAEf;;;;EAIA;;cAGW,yBAAyB;WAGlB,UAAU;WACV;EAHlB,YACE,iBACgB,UAAU,eACV;;;;;;;;;;;;;;;iBAoBJ,kBACd,kBACA,OAAM,2BACL;;;;KCnFS;;;;;;;;;;;UAYK;;EAEf;;EAEA;EACA,iBAAiB;;EAEjB,cAAc;EACd,SAAS;;EAET;;;;;;;;;;;;iBA4Cc,iBACd,mBACA,oCACC;cA4CU,+BAA+B;WAGxB,QAAQ,cAAc;EAFxC,YACE,iBACgB,QAAQ,cAAc;;UAOzB;;;;;;EAMf;;;;;EAKA;;EAEA;;;;;;;iBAQc,sBACd,OAAO,kBACP,OAAM;;;;;;iBA6BQ,kBACd,mBACA,mCACA,OAAM,2BACL;;;;;iBAea,mBACd,OAAO;EAAgB;EAAmB;IAC1C,OAAM,2BACL;UAec,uCAAuC;;EAEtD;;EAEA;;cAGW,+BAA+B;WAGxB,UAAU;WACV,QAAQ,cAAc;EAHxC,YACE,iBACgB,UAAU,eACV,QAAQ,cAAc;;;;;;;;;;;iBAgB1B,wBACd,OAAO;EAAgB;EAAmB;IAC1C,OAAM,iCACL;;;UCjPc;EACf;;;;;EAKA,kBAEI;IACM;IAAc;;IACd;IAAmB;MAAa;MAAa;;;;KAI7C;UAEK;EACf;EACA,UAAU;;EAEV;;EAEA;IAAe;IAAc,QAAQ;;EACrC;EACA;;EAEA,WAAW;;EAEX;;;;;;iBAOc,2BACd,SAAS,KAAK,iFACd,UAAS,mBACR;UAgCc;EACf;EACA;EACA;;EAEA;;EAEA;;EAEA;;UAGe;;EAEf;EACA,OAAO;;;;;EAKP;;;;;;;;;EASA;;;;;;;;;;;;EAYA;;EAEA;;;;;;;;;EASA;;;;;;;EAOA;;EAEA,KAAK;;KAGK,kBAAkB,KAAK;;iBAGnB,mBACd,QAAQ,eACR,qBAAqB,qBACpB;;iBA2Ba,wBACd,OAAO,OACP,qBAAqB,qBACpB;cAMU,qBAAqB;WAGd;WACA;WACA;EAJlB,YACE,iBACgB,gBACA,cACA;;;;;cASP,yBAAyB;WAGlB,QAAQ;EAF1B,YACE,iBACgB,QAAQ,eACxB;IAAY;;;UAMC;;EAEf;;EAEA;EACA;;EAEA;IAAe;IAAc;;;EAE7B;;EAEA;;;;;;;EAOA,SAAS;;;;;;;;EAQT;;EAEA;;EAEA,qBAAqB;;;;;;;EAOrB;;;;;;EAMA;;EAEA,WAAW;;EAEX,eAAe;;;;;;;;EAQf,UAAU;;;;;EAKV;;EAEA;IAAiB;IAAgB;;;EAEjC,WAAW;;;;;;;;;;EAUX,8BAA8B;;;;;;;;;;;;;iBAsEhB,oBAAoB;;;;;;iBA6IpB,gBAAgB;;;;;;iBA6EV,QACpB,KAAK,gBACL,OAAM,mBACL,QAAQ;;;;;;;iBAoVW,YAAY,aAChC,KAAK,gBACL,OAAM,mBACL;EAAU,OAAO;EAAG,QAAQ;;UA6Ed;;;;;;;EAOf;;;;;EAKA,kBAAkB,eAAe;;EAEjC,kBAAkB,eAAe;;EAEjC;;;;;EAKA;;;;;;;;;;;iBAYc,eAAe,MAAM,kBAAkB,MAAK;;;;;;;;;;;;;;;;;;iBA6EtC,SACpB,eACA,OAAM;EAAqB;IAC1B;EACD;EACA;EACA;;EAEA;;EAEA;;;;;;;cAoCW;WACF;mBACQ;EAEjB,YAAY,OAAM;EAKlB,KAAK,KAAK,gBAAgB,MAAM,mBAAmB,QAAQ;EAK3D,SAAS,aACP,KAAK,gBACL,MAAM,mBACL;IAAU,OAAO;IAAG,QAAQ;;;;;;;;UCjqChB;;WAEN,WAAW;;WAEX;;WAEA;;EAGT,KAAK,KAAK,aAAa,OAAO,eAAe,QAAQ;;KAG3C;UAQK,oBAAoB,KAAK;;EAExC;;KAGU,eAAe;UAEV;;EAEf,SAAS;;EAET;;EAEA;;EAEA;;KAKU,uBACR,sBACA,yBACA,8BACA,0BACA,sBACA;UAEM;EACR;;EAEA;;UAGe,4BAA4B;EAC3C;EACA;EACA;;UAGe,+BAA+B;EAC9C;EACA;EACA;;UAGe,oCAAoC;EACnD;EACA;EACA;;;;;;UAOe,gCAAgC;EAC/C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;UAI1C,4BAA4B;EAC3C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;UAO1C,0BAA0B;EACzC;EACA,UAAU,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;iBAO9C,iBAAiB,MAAM,uBAAuB;;;UCjH7C;EACf;EACA;EACA;EACA;EACA;EACA,OAAO;EACP,gBAAgB;EAChB;;UAGe;EACf;EACA;EACA;EACA;;UAKe;EACf;EAQA;EACA;EACA;EACA;;UAKe;EACf;EACA;EACA,YAAY;;UAGG;EACf;EACA;EACA;EACA;EACA;;UAmBe;EACf;EACA;EACA;EACA;EACA;IAAmB;IAAc;;EACjC;EACA;;UASe;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;IAAc;IAAc;;EAC5B;IAAmB;IAAc,QAAQ;;EACzC;IAAc;IAAkB;;EAChC;;UAKe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;GACC;;UAGc;EACf;EACA,QAAQ;;EAER;;UAyBe;EACf;EACA,QAAQ,OAAO;EACf,YAAY,OAAO;;;;;;;;;;KAWT;UAEK;EACf;EACA;EACA;EACA,oBAAoB;EACpB;;EAEA,QAAQ;;;;;;;EAOR;;;;;;;EAOA;;;;;;EAMA;;UAGe;EACf;EACA;EACA;IAAa;IAAiB;IAAkB;;EAChD;EACA;EACA;;UAGe;EACf,UAAU;EACV,OAAO;EACP,WAAW;;EAEX,aAAa;EACb;EACA,WAAW;EACX,SAAS;;KAGC,WAAW,MAAM,YAAY,OAAO,eAAe,QAAQ;UAYtD;EACf;EACA;EACA;EACA"}
@@ -1,7 +1,7 @@
1
1
  import { c as CostLedgerHandle } from "../cost-ledger-DbQdN3nO.js";
2
- import { A as LlmClientOptions, N as LlmRouteRequirements } from "../types-XBRdmbj8.js";
2
+ import { A as LlmClientOptions, N as LlmRouteRequirements } from "../types-DOhGq4S1.js";
3
3
  import { s as TraceStore } from "../store-CT9YIIve.js";
4
- import { m as FeedbackTrajectoryStore } from "../feedback-trajectory-Cg9EDxKB.js";
4
+ import { m as FeedbackTrajectoryStore } from "../feedback-trajectory-niGeR6uJ.js";
5
5
  import { z } from "zod";
6
6
  import { ServerType } from "@hono/node-server";
7
7
  import { Hono } from "hono";
@@ -1,2 +1,2 @@
1
- import { A as TraceEventSchema, C as HealthResponseSchema, D as RubricDimensionSchema, E as ListRubricsResponseSchema, F as hashRubric, M as TracesIngestResponseSchema, N as VersionResponseSchema, O as RubricInfoSchema, P as WIRE_VERSION, S as FeedbackTrajectorySchema, T as JudgeResultSchema, _ as ErrorResponseSchema, a as runRpcBatch, b as FeedbackIngestResponseSchema, c as WireError, d as handleListRubrics, f as handleTracesIngest, g as listBuiltinRubrics, h as getBuiltinRubric, i as dispatchRpc, j as TracesIngestRequestSchema, k as RubricSchema, l as handleFeedbackIngest, m as BUILTIN_RUBRICS, n as startServer, o as runRpcOnce, p as handleVersion, r as startServerAsync, s as buildOpenApi, t as createApp, u as handleJudge, v as FailureModeSchema, w as JudgeRequestSchema, x as FeedbackLabelSchema, y as FeedbackAttemptSchema } from "../server-cQXve8i4.js";
1
+ import { A as TraceEventSchema, C as HealthResponseSchema, D as RubricDimensionSchema, E as ListRubricsResponseSchema, F as hashRubric, M as TracesIngestResponseSchema, N as VersionResponseSchema, O as RubricInfoSchema, P as WIRE_VERSION, S as FeedbackTrajectorySchema, T as JudgeResultSchema, _ as ErrorResponseSchema, a as runRpcBatch, b as FeedbackIngestResponseSchema, c as WireError, d as handleListRubrics, f as handleTracesIngest, g as listBuiltinRubrics, h as getBuiltinRubric, i as dispatchRpc, j as TracesIngestRequestSchema, k as RubricSchema, l as handleFeedbackIngest, m as BUILTIN_RUBRICS, n as startServer, o as runRpcOnce, p as handleVersion, r as startServerAsync, s as buildOpenApi, t as createApp, u as handleJudge, v as FailureModeSchema, w as JudgeRequestSchema, x as FeedbackLabelSchema, y as FeedbackAttemptSchema } from "../server-D9wQclzG.js";
2
2
  export { BUILTIN_RUBRICS, ErrorResponseSchema, FailureModeSchema, FeedbackAttemptSchema, FeedbackIngestResponseSchema, FeedbackLabelSchema, FeedbackTrajectorySchema, HealthResponseSchema, JudgeRequestSchema, JudgeResultSchema, ListRubricsResponseSchema, RubricDimensionSchema, RubricInfoSchema, RubricSchema, TraceEventSchema, TracesIngestRequestSchema, TracesIngestResponseSchema, VersionResponseSchema, WIRE_VERSION, WireError, buildOpenApi, createApp, dispatchRpc, getBuiltinRubric, handleFeedbackIngest, handleJudge, handleListRubrics, handleTracesIngest, handleVersion, hashRubric, listBuiltinRubrics, runRpcBatch, runRpcOnce, startServer, startServerAsync };
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@tangle-network/agent-eval",
3
- "version": "0.146.0",
3
+ "version": "0.147.0",
4
4
  "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
5
5
  "homepage": "https://github.com/tangle-network/agent-eval#readme",
6
6
  "repository": {
@@ -185,7 +185,7 @@
185
185
  "dependencies": {
186
186
  "@asteasolutions/zod-to-openapi": "^9.1.0",
187
187
  "@hono/node-server": "^2.0.12",
188
- "@tangle-network/agent-core": "0.9.4",
188
+ "@tangle-network/agent-core": "^0.9.4",
189
189
  "@tangle-network/agent-interface": "^1.0.0",
190
190
  "@tangle-network/agent-trace-contract": "^1.0.2",
191
191
  "hono": "^4.12.32",
@@ -1 +0,0 @@
1
- {"version":3,"file":"experiment-tracker-C29gXM4B.js","names":[],"sources":["../src/experiment-tracker.ts"],"sourcesContent":["/**\n * Experiment tracker — git-provenanced experiment log with N-rep stats and a\n * KEEP / REGRESSION / NOISE verdict against a parent.\n *\n * Every loop the fleet runs reduces to the same question: \"I ran the candidate\n * N times — is the median measurably better than the parent, or is the delta\n * inside the noise band?\" The hand-rolled copies bake a fixed score scale\n * (percentage points), a fixed store path (`.evolve/experiments-v2.json`), and\n * `execSync('git …')` straight into the module. This is the canonical version:\n * provenance and persistence are injected, thresholds are configurable, and the\n * stats + verdict are pure functions you can unit-test without a git repo or a\n * filesystem.\n *\n * Stats per experiment: median / mean / min / max / iqr / stddev / passRate /\n * n, plus a `stable` flag (`iqr < iqrUnstableAbove && stddev < stddevUnstableAbove`).\n *\n * Verdict against a parent (both must have `n >= minRepsForVerdict`):\n * - NOISE — the candidate is too unstable to judge (`!stable`)\n * - KEEP — `medianDelta > keepThreshold`\n * - REGRESSION — `medianDelta < -regressionThreshold`\n * - NOISE — otherwise (delta inside the band)\n * With no parent (or insufficient reps) the verdict is the neutral ITERATE.\n */\n\nimport { execSync } from 'node:child_process'\nimport { iqr } from './baseline'\nimport { ValidationError } from './errors'\n\n/** Verdict for one experiment relative to its parent. ITERATE is the neutral\n * \"keep collecting reps / no parent to compare against\" state. */\nexport type ExperimentVerdict = 'KEEP' | 'ITERATE' | 'NOISE' | 'REGRESSION'\n\n/** Git provenance for the working tree an experiment was run from. */\nexport interface ExperimentProvenance {\n /** Commit sha (short or full — the tracker does not interpret it). */\n commit: string\n /** First line of the commit message. */\n message: string\n /** Files changed vs the parent commit, or a marker like 'uncommitted'. */\n changedFiles: string[]\n}\n\n/** A single repetition of an experiment, carrying the score the verdict is\n * computed on plus any free-form per-rep metrics the consumer wants kept. */\nexport interface ExperimentRep {\n /** 0-indexed repetition number within the experiment. */\n rep: number\n /** The score this rep is judged on (same scale as the thresholds). */\n score: number\n /** ISO timestamp the rep completed. */\n timestamp: string\n /** Whether this rep passed the consumer's own gate — folded into `passRate`. */\n passed?: boolean\n /** Free-form numeric metrics retained for later analysis. */\n metrics?: Record<string, number>\n}\n\nexport interface ExperimentStats {\n median: number\n mean: number\n min: number\n max: number\n /** Inter-quartile range of the rep scores. */\n iqr: number\n /** Population standard deviation of the rep scores. */\n stddev: number\n /** Fraction of reps with `passed === true`, over reps that set `passed`.\n * null when no rep declared a pass/fail outcome. */\n passRate: number | null\n /** Number of reps. */\n n: number\n /** True when the sample is tight enough to trust for a verdict. */\n stable: boolean\n}\n\nexport interface Experiment {\n /** Stable id for the experiment. */\n id: string\n /** Free-form label / config descriptor. */\n label: string\n /** Git provenance captured when the experiment was created. */\n provenance: ExperimentProvenance\n /** Parent experiment id this candidate is compared against, if any. */\n parentId?: string\n /** One-line summary of what changed from the parent. */\n changeSummary: string\n reps: ExperimentRep[]\n stats: ExperimentStats\n verdict: ExperimentVerdict\n /** ISO timestamp the experiment was created. */\n createdAt: string\n}\n\nexport interface ImprovementThresholds {\n /** medianDelta strictly above this ⇒ KEEP. Default 5. */\n keepThreshold?: number\n /** medianDelta strictly below the negative of this ⇒ REGRESSION. Default 5. */\n regressionThreshold?: number\n /** iqr at or above this ⇒ unstable. Default 10. */\n iqrUnstableAbove?: number\n /** stddev at or above this ⇒ unstable. Default Infinity (iqr-only stability). */\n stddevUnstableAbove?: number\n /** Reps required on BOTH candidate and parent before a verdict is rendered.\n * Default 3. */\n minRepsForVerdict?: number\n}\n\nexport interface ImprovementVerdictResult {\n verdict: ExperimentVerdict\n /** candidate.median − parent.median; null when no parent or insufficient reps. */\n medianDelta: number | null\n /** Human-readable reason for the verdict — for dashboards and logs. */\n reason: string\n}\n\nconst DEFAULTS: Required<ImprovementThresholds> = {\n keepThreshold: 5,\n regressionThreshold: 5,\n iqrUnstableAbove: 10,\n stddevUnstableAbove: Number.POSITIVE_INFINITY,\n minRepsForVerdict: 3,\n}\n\nfunction resolveThresholds(t: ImprovementThresholds | undefined): Required<ImprovementThresholds> {\n const r = { ...DEFAULTS, ...(t ?? {}) }\n if (r.keepThreshold < 0) {\n throw new ValidationError(\n `experiment-tracker: keepThreshold must be >= 0, got ${r.keepThreshold}`,\n )\n }\n if (r.regressionThreshold < 0) {\n throw new ValidationError(\n `experiment-tracker: regressionThreshold must be >= 0, got ${r.regressionThreshold}`,\n )\n }\n if (r.minRepsForVerdict < 1) {\n throw new ValidationError(\n `experiment-tracker: minRepsForVerdict must be >= 1, got ${r.minRepsForVerdict}`,\n )\n }\n return r\n}\n\nfunction median(sorted: number[]): number {\n const n = sorted.length\n if (n === 0) return 0\n const mid = Math.floor(n / 2)\n return n % 2 === 0 ? (sorted[mid - 1]! + sorted[mid]!) / 2 : sorted[mid]!\n}\n\n/** Population standard deviation (÷n). 0 for fewer than 2 values. */\nfunction stddev(values: number[], mean: number): number {\n if (values.length < 2) return 0\n const variance = values.reduce((acc, v) => acc + (v - mean) ** 2, 0) / values.length\n return Math.sqrt(variance)\n}\n\n/**\n * Compute the N-rep statistics for a set of reps. Pure — no I/O. The `stable`\n * flag is the trust gate the verdict depends on: a sample whose spread exceeds\n * the configured bounds can't distinguish a real delta from run-to-run noise.\n */\nexport function computeExperimentStats(\n reps: ExperimentRep[],\n thresholds?: ImprovementThresholds,\n): ExperimentStats {\n const t = resolveThresholds(thresholds)\n const n = reps.length\n if (n === 0) {\n return {\n median: 0,\n mean: 0,\n min: 0,\n max: 0,\n iqr: 0,\n stddev: 0,\n passRate: null,\n n: 0,\n stable: false,\n }\n }\n const scores = reps.map((r) => {\n if (!Number.isFinite(r.score)) {\n throw new ValidationError(`experiment-tracker: rep ${r.rep} has non-finite score ${r.score}`)\n }\n return r.score\n })\n const sorted = [...scores].sort((a, b) => a - b)\n const mean = scores.reduce((s, v) => s + v, 0) / n\n const sd = stddev(scores, mean)\n const spread = iqr(scores)\n const rated = reps.filter((r) => typeof r.passed === 'boolean')\n const passRate = rated.length === 0 ? null : rated.filter((r) => r.passed).length / rated.length\n const stable = spread < t.iqrUnstableAbove && sd < t.stddevUnstableAbove\n return {\n median: median(sorted),\n mean,\n min: sorted[0]!,\n max: sorted[n - 1]!,\n iqr: spread,\n stddev: sd,\n passRate,\n n,\n stable,\n }\n}\n\n/**\n * Verdict for a candidate against its parent. Pure — operates on already-computed\n * stats. KEEP/REGRESSION require both sides to have `>= minRepsForVerdict` reps\n * AND the candidate to be `stable`; otherwise the result is NOISE (unstable) or\n * ITERATE (not enough reps / no parent).\n */\nexport function improvementVerdict(\n candidate: ExperimentStats,\n parent: ExperimentStats | null,\n thresholds?: ImprovementThresholds,\n): ImprovementVerdictResult {\n const t = resolveThresholds(thresholds)\n if (!parent) {\n return {\n verdict: 'ITERATE',\n medianDelta: null,\n reason: 'no parent experiment to compare against',\n }\n }\n if (candidate.n < t.minRepsForVerdict || parent.n < t.minRepsForVerdict) {\n return {\n verdict: 'ITERATE',\n medianDelta: null,\n reason: `need >= ${t.minRepsForVerdict} reps on both sides (candidate n=${candidate.n}, parent n=${parent.n})`,\n }\n }\n if (!candidate.stable) {\n return {\n verdict: 'NOISE',\n medianDelta: candidate.median - parent.median,\n reason: `candidate unstable (iqr=${candidate.iqr}, stddev=${candidate.stddev.toFixed(2)})`,\n }\n }\n const medianDelta = candidate.median - parent.median\n if (medianDelta > t.keepThreshold) {\n return { verdict: 'KEEP', medianDelta, reason: `median +${medianDelta} > +${t.keepThreshold}` }\n }\n if (medianDelta < -t.regressionThreshold) {\n return {\n verdict: 'REGRESSION',\n medianDelta,\n reason: `median ${medianDelta} < -${t.regressionThreshold}`,\n }\n }\n return {\n verdict: 'NOISE',\n medianDelta,\n reason: `median delta ${medianDelta} inside noise band [-${t.regressionThreshold}, +${t.keepThreshold}]`,\n }\n}\n\n// ── Provenance + persistence seams ───────────────────────────────────\n\n/** Reads git provenance for the working tree. Inject a fake in tests; the\n * default implementation shells out to `git`. */\nexport type ProvenanceReader = () => ExperimentProvenance | Promise<ExperimentProvenance>\n\n/** Persistence seam for the experiment log. Inject in-memory in tests; the\n * filesystem implementation is `fileExperimentStore`. */\nexport interface ExperimentStore {\n load(): Promise<Experiment[]>\n save(experiments: Experiment[]): Promise<void>\n}\n\n/**\n * Default provenance reader: `git rev-parse HEAD`, the subject line, and the\n * files changed vs `HEAD~1`. Fail-loud — a tracker that silently logs\n * `commit: 'unknown'` corrupts the provenance the whole point of the log is to\n * carry. When the working tree genuinely has no parent commit, pass an override.\n */\nexport const gitProvenanceReader: ProvenanceReader = () => {\n const run = (cmd: string): string => execSync(cmd, { encoding: 'utf8' }).trim()\n const commit = run('git rev-parse --short HEAD')\n const message = run('git log -1 --format=%s')\n const changedRaw = run('git diff --name-only HEAD~1')\n const changedFiles = changedRaw.length === 0 ? [] : changedRaw.split('\\n').filter(Boolean)\n return { commit, message, changedFiles }\n}\n\n/** In-memory store — the default when no persistence is wanted (tests, ephemeral\n * runs). State lives on the instance. */\nexport function inMemoryExperimentStore(initial: Experiment[] = []): ExperimentStore {\n let state = initial.map((e) => structuredClone(e))\n return {\n async load() {\n return state.map((e) => structuredClone(e))\n },\n async save(experiments) {\n state = experiments.map((e) => structuredClone(e))\n },\n }\n}\n\n/** Filesystem store — a single JSON array at `path`, created on first save. */\nexport function fileExperimentStore(path: string): ExperimentStore {\n return {\n async load() {\n const fs = await import('node:fs/promises')\n try {\n const raw = await fs.readFile(path, 'utf8')\n const parsed = JSON.parse(raw)\n if (!Array.isArray(parsed)) {\n throw new ValidationError(`experiment-tracker: store at ${path} is not a JSON array`)\n }\n return parsed as Experiment[]\n } catch (err) {\n if ((err as NodeJS.ErrnoException).code === 'ENOENT') return []\n throw err\n }\n },\n async save(experiments) {\n const fs = await import('node:fs/promises')\n const pathMod = await import('node:path')\n await fs.mkdir(pathMod.dirname(path), { recursive: true })\n await fs.writeFile(path, JSON.stringify(experiments, null, 2), 'utf8')\n },\n }\n}\n\nexport interface ExperimentTrackerOptions {\n store?: ExperimentStore\n provenanceReader?: ProvenanceReader\n thresholds?: ImprovementThresholds\n /** Clock seam for deterministic timestamps in tests. Default `Date.now`. */\n now?: () => number\n}\n\nexport interface CreateExperimentInput {\n id: string\n label: string\n changeSummary: string\n parentId?: string\n /** Override provenance instead of reading from git (e.g. CI metadata). */\n provenance?: ExperimentProvenance\n}\n\n/**\n * Stateful tracker over an `ExperimentStore`. Create an experiment (provenance\n * is captured once), append reps as they complete (stats + verdict recompute on\n * every append), and read the log back for a dashboard. All persistence and git\n * access flow through the injected seams, so the tracker is fully testable\n * without a repo or disk.\n */\nexport class ExperimentTracker {\n private readonly store: ExperimentStore\n private readonly provenanceReader: ProvenanceReader\n private readonly thresholds: Required<ImprovementThresholds>\n private readonly now: () => number\n\n constructor(options: ExperimentTrackerOptions = {}) {\n this.store = options.store ?? inMemoryExperimentStore()\n this.provenanceReader = options.provenanceReader ?? gitProvenanceReader\n this.thresholds = resolveThresholds(options.thresholds)\n this.now = options.now ?? Date.now\n }\n\n async create(input: CreateExperimentInput): Promise<Experiment> {\n const experiments = await this.store.load()\n if (experiments.some((e) => e.id === input.id)) {\n throw new ValidationError(`experiment-tracker: experiment id \"${input.id}\" already exists`)\n }\n if (input.parentId && !experiments.some((e) => e.id === input.parentId)) {\n throw new ValidationError(\n `experiment-tracker: parent experiment \"${input.parentId}\" not found`,\n )\n }\n const provenance = input.provenance ?? (await this.provenanceReader())\n const experiment: Experiment = {\n id: input.id,\n label: input.label,\n provenance,\n parentId: input.parentId,\n changeSummary: input.changeSummary,\n reps: [],\n stats: computeExperimentStats([], this.thresholds),\n verdict: 'ITERATE',\n createdAt: new Date(this.now()).toISOString(),\n }\n experiments.push(experiment)\n await this.store.save(experiments)\n return structuredClone(experiment)\n }\n\n /** Append a rep (its `rep` index defaults to the current rep count) and\n * recompute stats + verdict. Returns the updated experiment. */\n async addRep(\n experimentId: string,\n rep: Omit<ExperimentRep, 'rep' | 'timestamp'> & { rep?: number; timestamp?: string },\n ): Promise<Experiment> {\n const experiments = await this.store.load()\n const exp = experiments.find((e) => e.id === experimentId)\n if (!exp)\n throw new ValidationError(`experiment-tracker: experiment \"${experimentId}\" not found`)\n const fullRep: ExperimentRep = {\n rep: rep.rep ?? exp.reps.length,\n score: rep.score,\n passed: rep.passed,\n metrics: rep.metrics,\n timestamp: rep.timestamp ?? new Date(this.now()).toISOString(),\n }\n exp.reps.push(fullRep)\n exp.stats = computeExperimentStats(exp.reps, this.thresholds)\n const parent = exp.parentId ? experiments.find((e) => e.id === exp.parentId) : undefined\n exp.verdict = improvementVerdict(exp.stats, parent?.stats ?? null, this.thresholds).verdict\n await this.store.save(experiments)\n return structuredClone(exp)\n }\n\n async get(experimentId: string): Promise<Experiment | undefined> {\n const experiments = await this.store.load()\n const found = experiments.find((e) => e.id === experimentId)\n return found ? structuredClone(found) : undefined\n }\n\n async list(): Promise<Experiment[]> {\n return this.store.load()\n }\n\n /** Full verdict (not just the enum) for an experiment vs its parent. */\n async verdictFor(experimentId: string): Promise<ImprovementVerdictResult> {\n const experiments = await this.store.load()\n const exp = experiments.find((e) => e.id === experimentId)\n if (!exp)\n throw new ValidationError(`experiment-tracker: experiment \"${experimentId}\" not found`)\n const parent = exp.parentId ? experiments.find((e) => e.id === exp.parentId) : undefined\n return improvementVerdict(exp.stats, parent?.stats ?? null, this.thresholds)\n }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;AAmHA,MAAM,WAA4C;CAChD,eAAe;CACf,qBAAqB;CACrB,kBAAkB;CAClB,qBAAqB,OAAO;CAC5B,mBAAmB;AACrB;AAEA,SAAS,kBAAkB,GAAuE;CAChG,MAAM,IAAI;EAAE,GAAG;EAAU,GAAI,KAAK,CAAC;CAAG;CACtC,IAAI,EAAE,gBAAgB,GACpB,MAAM,IAAI,gBACR,uDAAuD,EAAE,eAC3D;CAEF,IAAI,EAAE,sBAAsB,GAC1B,MAAM,IAAI,gBACR,6DAA6D,EAAE,qBACjE;CAEF,IAAI,EAAE,oBAAoB,GACxB,MAAM,IAAI,gBACR,2DAA2D,EAAE,mBAC/D;CAEF,OAAO;AACT;AAEA,SAAS,OAAO,QAA0B;CACxC,MAAM,IAAI,OAAO;CACjB,IAAI,MAAM,GAAG,OAAO;CACpB,MAAM,MAAM,KAAK,MAAM,IAAI,CAAC;CAC5B,OAAO,IAAI,MAAM,KAAK,OAAO,MAAM,KAAM,OAAO,QAAS,IAAI,OAAO;AACtE;;AAGA,SAAS,OAAO,QAAkB,MAAsB;CACtD,IAAI,OAAO,SAAS,GAAG,OAAO;CAC9B,MAAM,WAAW,OAAO,QAAQ,KAAK,MAAM,OAAO,IAAI,SAAS,GAAG,CAAC,IAAI,OAAO;CAC9E,OAAO,KAAK,KAAK,QAAQ;AAC3B;;;;;;AAOA,SAAgB,uBACd,MACA,YACiB;CACjB,MAAM,IAAI,kBAAkB,UAAU;CACtC,MAAM,IAAI,KAAK;CACf,IAAI,MAAM,GACR,OAAO;EACL,QAAQ;EACR,MAAM;EACN,KAAK;EACL,KAAK;EACL,KAAK;EACL,QAAQ;EACR,UAAU;EACV,GAAG;EACH,QAAQ;CACV;CAEF,MAAM,SAAS,KAAK,KAAK,MAAM;EAC7B,IAAI,CAAC,OAAO,SAAS,EAAE,KAAK,GAC1B,MAAM,IAAI,gBAAgB,2BAA2B,EAAE,IAAI,wBAAwB,EAAE,OAAO;EAE9F,OAAO,EAAE;CACX,CAAC;CACD,MAAM,SAAS,CAAC,GAAG,MAAM,CAAC,CAAC,MAAM,GAAG,MAAM,IAAI,CAAC;CAC/C,MAAM,OAAO,OAAO,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI;CACjD,MAAM,KAAK,OAAO,QAAQ,IAAI;CAC9B,MAAM,SAAS,IAAI,MAAM;CACzB,MAAM,QAAQ,KAAK,QAAQ,MAAM,OAAO,EAAE,WAAW,SAAS;CAC9D,MAAM,WAAW,MAAM,WAAW,IAAI,OAAO,MAAM,QAAQ,MAAM,EAAE,MAAM,CAAC,CAAC,SAAS,MAAM;CAC1F,MAAM,SAAS,SAAS,EAAE,oBAAoB,KAAK,EAAE;CACrD,OAAO;EACL,QAAQ,OAAO,MAAM;EACrB;EACA,KAAK,OAAO;EACZ,KAAK,OAAO,IAAI;EAChB,KAAK;EACL,QAAQ;EACR;EACA;EACA;CACF;AACF;;;;;;;AAQA,SAAgB,mBACd,WACA,QACA,YAC0B;CAC1B,MAAM,IAAI,kBAAkB,UAAU;CACtC,IAAI,CAAC,QACH,OAAO;EACL,SAAS;EACT,aAAa;EACb,QAAQ;CACV;CAEF,IAAI,UAAU,IAAI,EAAE,qBAAqB,OAAO,IAAI,EAAE,mBACpD,OAAO;EACL,SAAS;EACT,aAAa;EACb,QAAQ,WAAW,EAAE,kBAAkB,mCAAmC,UAAU,EAAE,aAAa,OAAO,EAAE;CAC9G;CAEF,IAAI,CAAC,UAAU,QACb,OAAO;EACL,SAAS;EACT,aAAa,UAAU,SAAS,OAAO;EACvC,QAAQ,2BAA2B,UAAU,IAAI,WAAW,UAAU,OAAO,QAAQ,CAAC,EAAE;CAC1F;CAEF,MAAM,cAAc,UAAU,SAAS,OAAO;CAC9C,IAAI,cAAc,EAAE,eAClB,OAAO;EAAE,SAAS;EAAQ;EAAa,QAAQ,WAAW,YAAY,MAAM,EAAE;CAAgB;CAEhG,IAAI,cAAc,CAAC,EAAE,qBACnB,OAAO;EACL,SAAS;EACT;EACA,QAAQ,UAAU,YAAY,MAAM,EAAE;CACxC;CAEF,OAAO;EACL,SAAS;EACT;EACA,QAAQ,gBAAgB,YAAY,uBAAuB,EAAE,oBAAoB,KAAK,EAAE,cAAc;CACxG;AACF;;;;;;;AAqBA,MAAa,4BAA8C;CACzD,MAAM,OAAO,QAAwB,SAAS,KAAK,EAAE,UAAU,OAAO,CAAC,CAAC,CAAC,KAAK;CAC9E,MAAM,SAAS,IAAI,4BAA4B;CAC/C,MAAM,UAAU,IAAI,wBAAwB;CAC5C,MAAM,aAAa,IAAI,6BAA6B;CAEpD,OAAO;EAAE;EAAQ;EAAS,cADL,WAAW,WAAW,IAAI,CAAC,IAAI,WAAW,MAAM,IAAI,CAAC,CAAC,OAAO,OAAO;CAClD;AACzC;;;AAIA,SAAgB,wBAAwB,UAAwB,CAAC,GAAoB;CACnF,IAAI,QAAQ,QAAQ,KAAK,MAAM,gBAAgB,CAAC,CAAC;CACjD,OAAO;EACL,MAAM,OAAO;GACX,OAAO,MAAM,KAAK,MAAM,gBAAgB,CAAC,CAAC;EAC5C;EACA,MAAM,KAAK,aAAa;GACtB,QAAQ,YAAY,KAAK,MAAM,gBAAgB,CAAC,CAAC;EACnD;CACF;AACF;;AAGA,SAAgB,oBAAoB,MAA+B;CACjE,OAAO;EACL,MAAM,OAAO;GACX,MAAM,KAAK,MAAM,OAAO;GACxB,IAAI;IACF,MAAM,MAAM,MAAM,GAAG,SAAS,MAAM,MAAM;IAC1C,MAAM,SAAS,KAAK,MAAM,GAAG;IAC7B,IAAI,CAAC,MAAM,QAAQ,MAAM,GACvB,MAAM,IAAI,gBAAgB,gCAAgC,KAAK,qBAAqB;IAEtF,OAAO;GACT,SAAS,KAAK;IACZ,IAAK,IAA8B,SAAS,UAAU,OAAO,CAAC;IAC9D,MAAM;GACR;EACF;EACA,MAAM,KAAK,aAAa;GACtB,MAAM,KAAK,MAAM,OAAO;GACxB,MAAM,UAAU,MAAM,OAAO;GAC7B,MAAM,GAAG,MAAM,QAAQ,QAAQ,IAAI,GAAG,EAAE,WAAW,KAAK,CAAC;GACzD,MAAM,GAAG,UAAU,MAAM,KAAK,UAAU,aAAa,MAAM,CAAC,GAAG,MAAM;EACvE;CACF;AACF;;;;;;;;AA0BA,IAAa,oBAAb,MAA+B;CAC7B;CACA;CACA;CACA;CAEA,YAAY,UAAoC,CAAC,GAAG;EAClD,KAAK,QAAQ,QAAQ,SAAS,wBAAwB;EACtD,KAAK,mBAAmB,QAAQ,oBAAoB;EACpD,KAAK,aAAa,kBAAkB,QAAQ,UAAU;EACtD,KAAK,MAAM,QAAQ,OAAO,KAAK;CACjC;CAEA,MAAM,OAAO,OAAmD;EAC9D,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,IAAI,YAAY,MAAM,MAAM,EAAE,OAAO,MAAM,EAAE,GAC3C,MAAM,IAAI,gBAAgB,sCAAsC,MAAM,GAAG,iBAAiB;EAE5F,IAAI,MAAM,YAAY,CAAC,YAAY,MAAM,MAAM,EAAE,OAAO,MAAM,QAAQ,GACpE,MAAM,IAAI,gBACR,0CAA0C,MAAM,SAAS,YAC3D;EAEF,MAAM,aAAa,MAAM,cAAe,MAAM,KAAK,iBAAiB;EACpE,MAAM,aAAyB;GAC7B,IAAI,MAAM;GACV,OAAO,MAAM;GACb;GACA,UAAU,MAAM;GAChB,eAAe,MAAM;GACrB,MAAM,CAAC;GACP,OAAO,uBAAuB,CAAC,GAAG,KAAK,UAAU;GACjD,SAAS;GACT,WAAW,IAAI,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,YAAY;EAC9C;EACA,YAAY,KAAK,UAAU;EAC3B,MAAM,KAAK,MAAM,KAAK,WAAW;EACjC,OAAO,gBAAgB,UAAU;CACnC;;;CAIA,MAAM,OACJ,cACA,KACqB;EACrB,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,MAAM,MAAM,YAAY,MAAM,MAAM,EAAE,OAAO,YAAY;EACzD,IAAI,CAAC,KACH,MAAM,IAAI,gBAAgB,mCAAmC,aAAa,YAAY;EACxF,MAAM,UAAyB;GAC7B,KAAK,IAAI,OAAO,IAAI,KAAK;GACzB,OAAO,IAAI;GACX,QAAQ,IAAI;GACZ,SAAS,IAAI;GACb,WAAW,IAAI,aAAa,IAAI,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,YAAY;EAC/D;EACA,IAAI,KAAK,KAAK,OAAO;EACrB,IAAI,QAAQ,uBAAuB,IAAI,MAAM,KAAK,UAAU;EAC5D,MAAM,SAAS,IAAI,WAAW,YAAY,MAAM,MAAM,EAAE,OAAO,IAAI,QAAQ,IAAI,KAAA;EAC/E,IAAI,UAAU,mBAAmB,IAAI,OAAO,QAAQ,SAAS,MAAM,KAAK,UAAU,CAAC,CAAC;EACpF,MAAM,KAAK,MAAM,KAAK,WAAW;EACjC,OAAO,gBAAgB,GAAG;CAC5B;CAEA,MAAM,IAAI,cAAuD;EAE/D,MAAM,SAAQ,MADY,KAAK,MAAM,KAAK,EAAA,CAChB,MAAM,MAAM,EAAE,OAAO,YAAY;EAC3D,OAAO,QAAQ,gBAAgB,KAAK,IAAI,KAAA;CAC1C;CAEA,MAAM,OAA8B;EAClC,OAAO,KAAK,MAAM,KAAK;CACzB;;CAGA,MAAM,WAAW,cAAyD;EACxE,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,MAAM,MAAM,YAAY,MAAM,MAAM,EAAE,OAAO,YAAY;EACzD,IAAI,CAAC,KACH,MAAM,IAAI,gBAAgB,mCAAmC,aAAa,YAAY;EACxF,MAAM,SAAS,IAAI,WAAW,YAAY,MAAM,MAAM,EAAE,OAAO,IAAI,QAAQ,IAAI,KAAA;EAC/E,OAAO,mBAAmB,IAAI,OAAO,QAAQ,SAAS,MAAM,KAAK,UAAU;CAC7E;AACF"}
@@ -1 +0,0 @@
1
- {"version":3,"file":"experiment-tracker-DWHZBAYL.d.ts","names":[],"sources":["../src/statistics/power-and-mde.ts","../src/statistics/random.ts","../src/experiment-tracker.ts"],"mappings":";;;;;;;iBAWgB,mBAAmB;EACjC;EACA;EACA;EACA;;;;;;;;;;;iBAsBc,yBAAyB;EACvC;EACA;EACA;EACA;;;;;;;;iBAkBc,UAAU;EACxB;EACA;EACA;EACA;;;;;;;;;;;;;;;;iBAyBc,iBAAiB;EAC/B;EACA;EACA;EACA;EACA;;;;;;;iBAyBc,aAAa;EAC3B;EACA;EACA;EACA;EACA;;;;;;;;iBCrHc,WAAW;;;;;;;;;;;;;;;;;;;;;;;;;;;;KCwBf;;UAGK;;EAEf;;EAEA;;EAEA;;;;UAKe;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA,UAAU;;UAGK;EACf;EACA;EACA;EACA;;EAEA;;EAEA;;;EAGA;;EAEA;;EAEA;;UAGe;;EAEf;;EAEA;;EAEA,YAAY;;EAEZ;;EAEA;EACA,MAAM;EACN,OAAO;EACP,SAAS;;EAET;;UAGe;;EAEf;;EAEA;;EAEA;;EAEA;;;EAGA;;UAGe;EACf,SAAS;;EAET;;EAEA;;;;;;;iBAkDc,uBACd,MAAM,iBACN,aAAa,wBACZ;;;;;;;iBAgDa,mBACd,WAAW,iBACX,QAAQ,wBACR,aAAa,wBACZ;;;KA6CS,yBAAyB,uBAAuB,QAAQ;;;UAInD;EACf,QAAQ,QAAQ;EAChB,KAAK,aAAa,eAAe;;;;iBAoBnB,wBAAwB,UAAS,eAAoB;;iBAarD,oBAAoB,eAAe;UAyBlC;EACf,QAAQ;EACR,mBAAmB;EACnB,aAAa;;EAEb;;UAGe;EACf;EACA;EACA;EACA;;EAEA,aAAa;;;;;;;;;cAUF;mBACM;mBACA;mBACA;mBACA;EAEjB,YAAY,UAAS;EAOf,OAAO,OAAO,wBAAwB,QAAQ;;;EA6B9C,OACJ,sBACA,KAAK,KAAK;IAAwC;IAAc;MAC/D,QAAQ;EAoBL,IAAI,uBAAuB,QAAQ;EAMnC,QAAQ,QAAQ;;EAKhB,WAAW,uBAAuB,QAAQ"}
@@ -1 +0,0 @@
1
- import "./capture-fetch-BZiO2cEH.js";