@tangle-network/agent-eval 0.190.1 → 0.192.0

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 (167) hide show
  1. package/CHANGELOG.md +69 -0
  2. package/dist/adapters/http.d.ts +2 -2
  3. package/dist/{agent-profile-DNV_U6QR.d.ts → agent-profile-DDfIjdyS.d.ts} +3 -3
  4. package/dist/{agent-profile-DNV_U6QR.d.ts.map → agent-profile-DDfIjdyS.d.ts.map} +1 -1
  5. package/dist/analyst/index.d.ts +11 -11
  6. package/dist/analyst/index.js +5 -5
  7. package/dist/{insight-report-CvPkEIcC.d.ts → analyze-runs-CPiKLJFs.d.ts} +73 -3
  8. package/dist/analyze-runs-CPiKLJFs.d.ts.map +1 -0
  9. package/dist/{attribute-vocabulary-DLJ6303h.d.ts → attribute-vocabulary-CcXqHODT.d.ts} +23 -12
  10. package/dist/attribute-vocabulary-CcXqHODT.d.ts.map +1 -0
  11. package/dist/{benchmark-command-BXIr_k8D.js → benchmark-command-C458yEFK.js} +9 -9
  12. package/dist/{benchmark-command-BXIr_k8D.js.map → benchmark-command-C458yEFK.js.map} +1 -1
  13. package/dist/benchmarks/index.d.ts +3 -3
  14. package/dist/benchmarks/index.js +3 -3
  15. package/dist/campaign/index.d.ts +6 -6
  16. package/dist/campaign/index.js +8 -7
  17. package/dist/{campaign-B7q74uIh.js → campaign-BVQVBEfH.js} +13 -325
  18. package/dist/campaign-BVQVBEfH.js.map +1 -0
  19. package/dist/{campaign-evidence-D40-LHIL.js → campaign-evidence-DcQiYhJI.js} +18 -154
  20. package/dist/campaign-evidence-DcQiYhJI.js.map +1 -0
  21. package/dist/claim-V9Zqbq0J.js +54 -0
  22. package/dist/claim-V9Zqbq0J.js.map +1 -0
  23. package/dist/cli.js +99 -2
  24. package/dist/cli.js.map +1 -1
  25. package/dist/client-wFyDisxi.d.ts +236 -0
  26. package/dist/client-wFyDisxi.d.ts.map +1 -0
  27. package/dist/contract/index.d.ts +10 -11
  28. package/dist/contract/index.js +10 -140
  29. package/dist/contract/index.js.map +1 -1
  30. package/dist/{default-registry-B5HrwrPM.d.ts → default-registry-DdqA_-_o.d.ts} +6 -6
  31. package/dist/{default-registry-B5HrwrPM.d.ts.map → default-registry-DdqA_-_o.d.ts.map} +1 -1
  32. package/dist/{default-registry-16I-Bxlf.js → default-registry-xMLX160E.js} +3 -3
  33. package/dist/{default-registry-16I-Bxlf.js.map → default-registry-xMLX160E.js.map} +1 -1
  34. package/dist/{define-agent-eval-DPizhHfy.js → define-agent-eval-DQuos3Aw.js} +30 -113
  35. package/dist/define-agent-eval-DQuos3Aw.js.map +1 -0
  36. package/dist/{define-agent-eval-DblGedQk.d.ts → define-agent-eval-DcludNJS.d.ts} +25 -38
  37. package/dist/define-agent-eval-DcludNJS.d.ts.map +1 -0
  38. package/dist/diagnosis/index.d.ts +2 -2
  39. package/dist/diagnosis/index.js +1 -1
  40. package/dist/{dspy-rlm-engine-Cs5LzJ-f.js → dspy-rlm-engine-BX34vPVY.js} +3 -3
  41. package/dist/{dspy-rlm-engine-Cs5LzJ-f.js.map → dspy-rlm-engine-BX34vPVY.js.map} +1 -1
  42. package/dist/{engine-BkLCnZQX.d.ts → engine-C1DIAEpn.d.ts} +4 -4
  43. package/dist/{engine-BkLCnZQX.d.ts.map → engine-C1DIAEpn.d.ts.map} +1 -1
  44. package/dist/evaluation.d.ts +2 -2
  45. package/dist/{exact-types-CfpP2A4Z.d.ts → exact-types-KGxBWH4b.d.ts} +2 -2
  46. package/dist/{exact-types-CfpP2A4Z.d.ts.map → exact-types-KGxBWH4b.d.ts.map} +1 -1
  47. package/dist/experiment/index.d.ts +1 -1
  48. package/dist/experiment/index.js +2 -1
  49. package/dist/experiment/index.js.map +1 -1
  50. package/dist/{external-optimizer-process-BnSmrkgL.js → external-optimizer-process-D-Sab4v3.js} +3 -62
  51. package/dist/external-optimizer-process-D-Sab4v3.js.map +1 -0
  52. package/dist/{external-optimizer-subprocess-kbcPu5po.js → external-optimizer-subprocess-kbqC-iWf.js} +65 -27
  53. package/dist/external-optimizer-subprocess-kbqC-iWf.js.map +1 -0
  54. package/dist/{extract-usage-BrQ8mCLX.js → extract-usage-DFATEuWW.js} +2 -2
  55. package/dist/{extract-usage-BrQ8mCLX.js.map → extract-usage-DFATEuWW.js.map} +1 -1
  56. package/dist/{feedback-trajectory-BYjh7NEM.d.ts → feedback-trajectory-BXCGTRkz.d.ts} +3 -3
  57. package/dist/{feedback-trajectory-BYjh7NEM.d.ts.map → feedback-trajectory-BXCGTRkz.d.ts.map} +1 -1
  58. package/dist/hosted/index.d.ts +66 -6
  59. package/dist/hosted/index.d.ts.map +1 -1
  60. package/dist/hosted/index.js +2 -2
  61. package/dist/{index-I4UJGRno.d.ts → index-Bj96W0jZ.d.ts} +28 -2
  62. package/dist/{index-I4UJGRno.d.ts.map → index-Bj96W0jZ.d.ts.map} +1 -1
  63. package/dist/{index-2e_MTznj.d.ts → index-DBoXFaz0.d.ts} +6 -6
  64. package/dist/{index-2e_MTznj.d.ts.map → index-DBoXFaz0.d.ts.map} +1 -1
  65. package/dist/{index-CWoIJHmy.d.ts → index-DNVzu9Vv.d.ts} +10 -104
  66. package/dist/index-DNVzu9Vv.d.ts.map +1 -0
  67. package/dist/{index-CJv56rhX.d.ts → index-DwQxdWve.d.ts} +351 -135
  68. package/dist/index-DwQxdWve.d.ts.map +1 -0
  69. package/dist/index.d.ts +16 -17
  70. package/dist/index.d.ts.map +1 -1
  71. package/dist/index.js +11 -11
  72. package/dist/jev.d.ts +2 -2
  73. package/dist/{journal-c3qY0SDP.js → journal-DvKCvjty.js} +94 -2
  74. package/dist/{journal-c3qY0SDP.js.map → journal-DvKCvjty.js.map} +1 -1
  75. package/dist/{kind-factory-ByZeXDqF.js → kind-factory-CdPPHtGZ.js} +10 -26
  76. package/dist/kind-factory-CdPPHtGZ.js.map +1 -0
  77. package/dist/ledger-core/index.d.ts +2 -2
  78. package/dist/ledger-core/index.js +2 -2
  79. package/dist/{llm-judge-BnxAv7ed.js → llm-judge-Z6MkTkd0.js} +1805 -2012
  80. package/dist/llm-judge-Z6MkTkd0.js.map +1 -0
  81. package/dist/{matrix-CNypzP-v.d.ts → matrix-CQMMrEQ5.d.ts} +2 -2
  82. package/dist/{matrix-CNypzP-v.d.ts.map → matrix-CQMMrEQ5.d.ts.map} +1 -1
  83. package/dist/multishot/golden/index.d.ts +1 -1
  84. package/dist/multishot/index.d.ts +2 -2
  85. package/dist/openapi.json +1 -1
  86. package/dist/{otel-spans-CQY1pNiN.js → otel-spans-DS7t1t1J.js} +8 -19
  87. package/dist/otel-spans-DS7t1t1J.js.map +1 -0
  88. package/dist/otlp-attributes-D9ptWaIJ.js +53 -0
  89. package/dist/otlp-attributes-D9ptWaIJ.js.map +1 -0
  90. package/dist/{prime-protocol-Fwvctmhm.d.ts → prime-protocol-T0i6xcAs.d.ts} +2 -2
  91. package/dist/{prime-protocol-Fwvctmhm.d.ts.map → prime-protocol-T0i6xcAs.d.ts.map} +1 -1
  92. package/dist/{produced-state-BXjXJHJT.js → produced-state-CVmCPQDJ.js} +3 -3
  93. package/dist/{produced-state-BXjXJHJT.js.map → produced-state-CVmCPQDJ.js.map} +1 -1
  94. package/dist/{registry-mAQVtuLx.d.ts → registry-Bu3lNole.d.ts} +3 -3
  95. package/dist/{registry-mAQVtuLx.d.ts.map → registry-Bu3lNole.d.ts.map} +1 -1
  96. package/dist/rl.d.ts +1 -1
  97. package/dist/rl.js +1 -1
  98. package/dist/{run-record-DnMFyg_g.js → run-record-tNnlQIrD.js} +2 -10
  99. package/dist/{run-record-DnMFyg_g.js.map → run-record-tNnlQIrD.js.map} +1 -1
  100. package/dist/search-ledger-Ck7tok0h.js +1517 -0
  101. package/dist/search-ledger-Ck7tok0h.js.map +1 -0
  102. package/dist/search-ledger-file-DY0AXX3W.js +27 -0
  103. package/dist/search-ledger-file-DY0AXX3W.js.map +1 -0
  104. package/dist/search-shipper-BG182p-U.js +781 -0
  105. package/dist/search-shipper-BG182p-U.js.map +1 -0
  106. package/dist/{semantic-concept-judge-ClB73cei.js → semantic-concept-judge-Bg-560H0.js} +4 -4
  107. package/dist/{semantic-concept-judge-ClB73cei.js.map → semantic-concept-judge-Bg-560H0.js.map} +1 -1
  108. package/dist/{skillopt-optimization-method-l2vDBtKp.js → skillopt-optimization-method-DoayuM6D.js} +6 -5
  109. package/dist/{skillopt-optimization-method-l2vDBtKp.js.map → skillopt-optimization-method-DoayuM6D.js.map} +1 -1
  110. package/dist/{statistical-heldout-CLpjYffJ.d.ts → statistical-heldout-C1Ej5Ce8.d.ts} +2 -2
  111. package/dist/{statistical-heldout-CLpjYffJ.d.ts.map → statistical-heldout-C1Ej5Ce8.d.ts.map} +1 -1
  112. package/dist/{store-otlp-84DH0OEH.js → store-otlp-BPowgPm6.js} +2 -2
  113. package/dist/{store-otlp-84DH0OEH.js.map → store-otlp-BPowgPm6.js.map} +1 -1
  114. package/dist/{store-tool-spans-DUiqyHvR.js → store-tool-spans-BcC_5ef-.js} +5 -5
  115. package/dist/{store-tool-spans-DUiqyHvR.js.map → store-tool-spans-BcC_5ef-.js.map} +1 -1
  116. package/dist/{store-tool-spans-BBXs8hDP.d.ts → store-tool-spans-ByLdU26j.d.ts} +5 -9
  117. package/dist/store-tool-spans-ByLdU26j.d.ts.map +1 -0
  118. package/dist/{task-failure-attributes-B34TiMBe.js → task-failure-attributes-CEqEfuIY.js} +17 -9
  119. package/dist/task-failure-attributes-CEqEfuIY.js.map +1 -0
  120. package/dist/{tool-groups-W7MJobX_.d.ts → tool-groups-DiBi16ns.d.ts} +3 -3
  121. package/dist/tool-groups-DiBi16ns.d.ts.map +1 -0
  122. package/dist/trace-attributes.d.ts +1 -1
  123. package/dist/trace-attributes.js +23 -75
  124. package/dist/trace-attributes.js.map +1 -1
  125. package/dist/trace-repair/index.d.ts +1 -1
  126. package/dist/traces.d.ts +11 -18
  127. package/dist/traces.d.ts.map +1 -1
  128. package/dist/traces.js +16 -16
  129. package/dist/traces.js.map +1 -1
  130. package/dist/{types-Cvqy7asY.d.ts → types-ByZslIlr.d.ts} +2 -2
  131. package/dist/{types-Cvqy7asY.d.ts.map → types-ByZslIlr.d.ts.map} +1 -1
  132. package/dist/{types-BvmWNjjs.d.ts → types-C1CAD70_.d.ts} +15 -16
  133. package/dist/types-C1CAD70_.d.ts.map +1 -0
  134. package/dist/{types-Bay1dh2o.d.ts → types-CeDfCRXp.d.ts} +11 -16
  135. package/dist/types-CeDfCRXp.d.ts.map +1 -0
  136. package/dist/wire/index.d.ts +1 -1
  137. package/docs/campaign-proposers.md +14 -16
  138. package/docs/hosted-ingest-spec.md +92 -133
  139. package/docs/public-api.md +46 -35
  140. package/docs/search-ledger.md +79 -1
  141. package/package.json +2 -2
  142. package/dist/analyze-runs-BvK4-wSs.d.ts +0 -75
  143. package/dist/analyze-runs-BvK4-wSs.d.ts.map +0 -1
  144. package/dist/attribute-vocabulary-DLJ6303h.d.ts.map +0 -1
  145. package/dist/campaign-B7q74uIh.js.map +0 -1
  146. package/dist/campaign-evidence-D40-LHIL.js.map +0 -1
  147. package/dist/client-BhEyAdfe.d.ts +0 -202
  148. package/dist/client-BhEyAdfe.d.ts.map +0 -1
  149. package/dist/client-QwJpsNYU.js +0 -655
  150. package/dist/client-QwJpsNYU.js.map +0 -1
  151. package/dist/define-agent-eval-DPizhHfy.js.map +0 -1
  152. package/dist/define-agent-eval-DblGedQk.d.ts.map +0 -1
  153. package/dist/external-optimizer-process-BnSmrkgL.js.map +0 -1
  154. package/dist/external-optimizer-subprocess-kbcPu5po.js.map +0 -1
  155. package/dist/index-CJv56rhX.d.ts.map +0 -1
  156. package/dist/index-CWoIJHmy.d.ts.map +0 -1
  157. package/dist/insight-report-CvPkEIcC.d.ts.map +0 -1
  158. package/dist/kind-factory-ByZeXDqF.js.map +0 -1
  159. package/dist/llm-judge-BnxAv7ed.js.map +0 -1
  160. package/dist/otel-spans-CQY1pNiN.js.map +0 -1
  161. package/dist/otlp-attributes-BpC_blLF.js +0 -83
  162. package/dist/otlp-attributes-BpC_blLF.js.map +0 -1
  163. package/dist/store-tool-spans-BBXs8hDP.d.ts.map +0 -1
  164. package/dist/task-failure-attributes-B34TiMBe.js.map +0 -1
  165. package/dist/tool-groups-W7MJobX_.d.ts.map +0 -1
  166. package/dist/types-Bay1dh2o.d.ts.map +0 -1
  167. package/dist/types-BvmWNjjs.d.ts.map +0 -1
@@ -1,8 +1,8 @@
1
- import { D as TraceAnalysisStore, i as AnalystFinding, n as AnalystContext } from "./types-Bay1dh2o.js";
2
- import { l as ExactCapableAnalyst } from "./exact-types-CfpP2A4Z.js";
3
- import { n as AnalystRegistry, r as AnalystRegistryOptions } from "./registry-mAQVtuLx.js";
4
- import { a as TraceAnalystLimits, i as TraceAnalysisEngineResult, l as RawAnalystFinding, n as TraceAnalysisEngine } from "./engine-BkLCnZQX.js";
5
- import { t as TraceToolGroupName } from "./tool-groups-W7MJobX_.js";
1
+ import { O as TraceAnalysisStore, i as AnalystFinding, n as AnalystContext } from "./types-CeDfCRXp.js";
2
+ import { l as ExactCapableAnalyst } from "./exact-types-KGxBWH4b.js";
3
+ import { n as AnalystRegistry, r as AnalystRegistryOptions } from "./registry-Bu3lNole.js";
4
+ import { a as TraceAnalystLimits, i as TraceAnalysisEngineResult, l as RawAnalystFinding, n as TraceAnalysisEngine } from "./engine-C1DIAEpn.js";
5
+ import { t as TraceToolGroupName } from "./tool-groups-DiBi16ns.js";
6
6
  //#region src/trace-analyst/behavioral-metrics.d.ts
7
7
  type SuboptimalCode = 'monotonic-input-growth' | 'output-length-decay' | 'single-tool-dependency' | 'no-self-verification';
8
8
  interface SuboptimalSignal {
@@ -110,4 +110,4 @@ interface DefaultAnalystRegistryOptions {
110
110
  declare function buildDefaultAnalystRegistry(options?: DefaultAnalystRegistryOptions): AnalystRegistry;
111
111
  //#endregion
112
112
  export { createTraceAnalyst as a, BehavioralAnalystOptions as c, TraceAnalystDefinition as i, behavioralAnalyst as l, buildDefaultAnalystRegistry as n, renderPriorFindings as o, CreateTraceAnalystOptions as r, runTraceAnalyst as s, DefaultAnalystRegistryOptions as t, deriveEfficiencyFindings as u };
113
- //# sourceMappingURL=default-registry-B5HrwrPM.d.ts.map
113
+ //# sourceMappingURL=default-registry-DdqA_-_o.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"default-registry-B5HrwrPM.d.ts","names":[],"sources":["../src/trace-analyst/behavioral-metrics.ts","../src/analyst/behavioral-analyst.ts","../src/analyst/kind-factory.ts","../src/analyst/default-registry.ts"],"mappings":";;;;;;KAoBY;UAMK;EACf,MAAM;EACN;;EAEA;;EAEA,UAAU;;UAGK;;EAEf;EACA;;EAEA,gBAAgB;;EAEhB;EACA;EACA,eAAe;EACf;EACA;;EAEA;EACA;EACA,SAAS;;UAGM;EACf;EACA;EACA,sBAAsB;EACtB,uBAAuB;;;;UC1BR;;EAEf;;EAEA;;;;;;iBA+Dc,yBACd,SAAS,mBACT;EAAQ;EAAoB;IAC3B;;iBAkCa,kBACd,UAAS,2BACR,oBAAoB;;;;UCrHN;EACf;EACA;EACA;EACA;;EAEA,sBAAsB,SAAS;;EAE/B;;EAEA,WAAW;;EAEX,kBACE,OAAO,oBACP,SAAS,wCACe;EAC1B,SAAS,QAAQ;EACjB,eAAe,KAAK,mBAAmB,SAAS,mBAAmB;EACnE;EACA;;UAGe;EACf,QAAQ;;EAER;EACA;;;iBAIoB,gBAAgB;EACpC,YAAY;EACZ,QAAQ;EACR,OAAO;EACP,SAAS;EACT;IACE,QAAQ;;iBAgHI,mBACd,YAAY,wBACZ,SAAS,4BACR,oBAAoB;iBA2RP,oBAAoB,OAAO;;;UChc1B;;;;;;EAMf,SAAS;EACT,uBAAuB;;EAEvB;EACA,aAAa;EACb,WAAW;;iBAGG,4BACd,UAAS,gCACR"}
1
+ {"version":3,"file":"default-registry-DdqA_-_o.d.ts","names":[],"sources":["../src/trace-analyst/behavioral-metrics.ts","../src/analyst/behavioral-analyst.ts","../src/analyst/kind-factory.ts","../src/analyst/default-registry.ts"],"mappings":";;;;;;KAoBY;UAMK;EACf,MAAM;EACN;;EAEA;;EAEA,UAAU;;UAGK;;EAEf;EACA;;EAEA,gBAAgB;;EAEhB;EACA;EACA,eAAe;EACf;EACA;;EAEA;EACA;EACA,SAAS;;UAGM;EACf;EACA;EACA,sBAAsB;EACtB,uBAAuB;;;;UC1BR;;EAEf;;EAEA;;;;;;iBA+Dc,yBACd,SAAS,mBACT;EAAQ;EAAoB;IAC3B;;iBAkCa,kBACd,UAAS,2BACR,oBAAoB;;;;UCrHN;EACf;EACA;EACA;EACA;;EAEA,sBAAsB,SAAS;;EAE/B;;EAEA,WAAW;;EAEX,kBACE,OAAO,oBACP,SAAS,wCACe;EAC1B,SAAS,QAAQ;EACjB,eAAe,KAAK,mBAAmB,SAAS,mBAAmB;EACnE;EACA;;UAGe;EACf,QAAQ;;EAER;EACA;;;iBAIoB,gBAAgB;EACpC,YAAY;EACZ,QAAQ;EACR,OAAO;EACP,SAAS;EACT;IACE,QAAQ;;iBAgHI,mBACd,YAAY,wBACZ,SAAS,4BACR,oBAAoB;iBA2RP,oBAAoB,OAAO;;;UChc1B;;;;;;EAMf,SAAS;EACT,uBAAuB;;EAEvB;EACA,aAAa;EACb,WAAW;;iBAGG,4BACd,UAAS,gCACR"}
@@ -1,10 +1,10 @@
1
1
  import { a as hashCanonical, r as canonicalString } from "./canonical-BsZVgBhW.js";
2
2
  import { t as deepFreezeCanonicalJson } from "./deep-freeze-CurcOQg3.js";
3
3
  import { t as combineAbortSignals } from "./abort-signal-CtzAM_sJ.js";
4
- import { A as spanEpochMillis, H as findingSubjectGrammarPromptFor, J as snapshotExactExecutionPlan, q as snapshotExactExecutionComponentIdentity, t as createTraceAnalyst } from "./kind-factory-ByZeXDqF.js";
4
+ import { A as spanEpochMillis, H as findingSubjectGrammarPromptFor, J as snapshotExactExecutionPlan, q as snapshotExactExecutionComponentIdentity, t as createTraceAnalyst } from "./kind-factory-CdPPHtGZ.js";
5
5
  import { i as validateUsageSettlementTimeout, t as assertValidAnalystUsageReceipt } from "./usage-receipt-Cx3xNeyB.js";
6
6
  import { LLM_CONTEXT_TOKENS, LLM_INPUT_TOKEN_ATTR_KEYS, LLM_OUTPUT_TOKEN_ATTR_KEYS, TOOL_NAME_ATTR_KEYS } from "./trace-attributes.js";
7
- import "./otlp-attributes-BpC_blLF.js";
7
+ import "./otlp-attributes-D9ptWaIJ.js";
8
8
  import { r as makeFinding } from "./types-CW5b90JH.js";
9
9
  import { t as executionTrackByLane } from "./execution-tracks-CpgFPpS5.js";
10
10
  import { t as analyzeSupervisorRunIntegrity } from "./integrity-BvHANvnp.js";
@@ -2366,4 +2366,4 @@ function buildDefaultAnalystRegistry(options = {}) {
2366
2366
  //#endregion
2367
2367
  export { completedAnalystReviewQuality as _, KNOWLEDGE_POISONING_KIND_SPEC as a, validateAnalystReviewDecisions as b, FAILURE_MODE_KIND_SPEC as c, emitControlIntegrityFindings as d, behavioralAnalyst as f, assertUniqueFindingIds as g, analystRunDigest as h, DEFAULT_TRACE_ANALYST_KINDS as i, CONTROL_INTEGRITY_ANALYST as l, analystFindingDigest as m, AnalystRegistry as n, KNOWLEDGE_GAP_KIND_SPEC as o, deriveEfficiencyFindings as p, ExactAnalystRunExecutionError as r, IMPROVEMENT_KIND_SPEC as s, buildDefaultAnalystRegistry as t, ControlIntegrityAnalyst as u, readAnalystReview as v, snapshotAnalystRun as y };
2368
2368
 
2369
- //# sourceMappingURL=default-registry-16I-Bxlf.js.map
2369
+ //# sourceMappingURL=default-registry-xMLX160E.js.map