@tangle-network/agent-eval 0.85.0 → 0.89.0

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 (136) hide show
  1. package/CHANGELOG.md +14 -0
  2. package/dist/adapters/http.d.ts +3 -3
  3. package/dist/adapters/langchain.d.ts +3 -3
  4. package/dist/adapters/otel.d.ts +6 -6
  5. package/dist/adversarial-DIVcDoI_.d.ts +88 -0
  6. package/dist/analyst/index.d.ts +11 -10
  7. package/dist/analyst/index.js +13 -8
  8. package/dist/analyst/index.js.map +1 -1
  9. package/dist/analyze-runs-DwCEkpO_.d.ts +81 -0
  10. package/dist/belief-state/index.d.ts +4 -4
  11. package/dist/belief-state/index.js +1 -1
  12. package/dist/benchmarks/index.d.ts +3 -3
  13. package/dist/campaign/index.d.ts +165 -18
  14. package/dist/campaign/index.js +289 -14
  15. package/dist/campaign/index.js.map +1 -1
  16. package/dist/chunk-45EEMHTC.js +35 -0
  17. package/dist/chunk-45EEMHTC.js.map +1 -0
  18. package/dist/{chunk-FZWAFVAA.js → chunk-4FBZZIYD.js} +2 -2
  19. package/dist/{chunk-YV7J7X5N.js → chunk-5HRORJQY.js} +22 -12
  20. package/dist/chunk-5HRORJQY.js.map +1 -0
  21. package/dist/{chunk-OTYQPHPL.js → chunk-6SOJM3VR.js} +5 -5
  22. package/dist/chunk-BOD4O7OF.js +40 -0
  23. package/dist/chunk-BOD4O7OF.js.map +1 -0
  24. package/dist/{chunk-Z7VFTS2J.js → chunk-CY6U5S3X.js} +2 -2
  25. package/dist/{chunk-VIDQF3F5.js → chunk-D3V5B42D.js} +5 -34
  26. package/dist/chunk-D3V5B42D.js.map +1 -0
  27. package/dist/{chunk-YGYXHNAQ.js → chunk-FIUKOSWI.js} +21 -8
  28. package/dist/chunk-FIUKOSWI.js.map +1 -0
  29. package/dist/{chunk-WJL2NJXN.js → chunk-GSH6QNNS.js} +2 -2
  30. package/dist/{chunk-RBNA5AZT.js → chunk-L3JOU6XM.js} +2 -2
  31. package/dist/{chunk-IDVBLYCY.js → chunk-LMZQ2Z4U.js} +56 -2
  32. package/dist/{chunk-IDVBLYCY.js.map → chunk-LMZQ2Z4U.js.map} +1 -1
  33. package/dist/{chunk-VUINJM5M.js → chunk-QAY5UIJO.js} +2 -193
  34. package/dist/chunk-QAY5UIJO.js.map +1 -0
  35. package/dist/{chunk-XQL22JDG.js → chunk-QG2OVF2D.js} +101 -7
  36. package/dist/chunk-QG2OVF2D.js.map +1 -0
  37. package/dist/chunk-REVYNR6C.js +100 -0
  38. package/dist/chunk-REVYNR6C.js.map +1 -0
  39. package/dist/{chunk-ZZ2HOPME.js → chunk-TWS7AZEY.js} +2 -2
  40. package/dist/chunk-UHMJT4T7.js +200 -0
  41. package/dist/chunk-UHMJT4T7.js.map +1 -0
  42. package/dist/chunk-UMMZHCPB.js +190 -0
  43. package/dist/chunk-UMMZHCPB.js.map +1 -0
  44. package/dist/chunk-VZSRQ272.js +149 -0
  45. package/dist/chunk-VZSRQ272.js.map +1 -0
  46. package/dist/{chunk-L5G7OUKD.js → chunk-XY4DDNEG.js} +8 -190
  47. package/dist/chunk-XY4DDNEG.js.map +1 -0
  48. package/dist/chunk-Y47J2LJ3.js +859 -0
  49. package/dist/chunk-Y47J2LJ3.js.map +1 -0
  50. package/dist/{chunk-BABOZOSN.js → chunk-ZFIBGEOL.js} +3 -3
  51. package/dist/chunk-ZFIBGEOL.js.map +1 -0
  52. package/dist/{code-agent-session-BRXmavYv.d.ts → code-agent-session-BO8nCnv3.d.ts} +1 -1
  53. package/dist/contract/index.d.ts +24 -95
  54. package/dist/contract/index.js +16 -755
  55. package/dist/contract/index.js.map +1 -1
  56. package/dist/{control-GeE8OhpN.d.ts → control-_Qb7skHX.d.ts} +2 -2
  57. package/dist/control.d.ts +5 -5
  58. package/dist/corpus-BoR-041R.d.ts +560 -0
  59. package/dist/cost-ledger-DuSqlw5B.d.ts +113 -0
  60. package/dist/counterfactual-Dwibr5IW.d.ts +85 -0
  61. package/dist/{dataset-B2kL-fSM.d.ts → dataset-BbGkaN2I.d.ts} +1 -1
  62. package/dist/{registry-DrEQ3Luj.d.ts → default-registry-zoGHUQEH.d.ts} +29 -2
  63. package/dist/diagnose.d.ts +251 -0
  64. package/dist/diagnose.js +381 -0
  65. package/dist/diagnose.js.map +1 -0
  66. package/dist/{errors-Dwqw-T_m.d.ts → errors-CzMUYo7b.d.ts} +1 -1
  67. package/dist/{feedback-trajectory-B3rErRsh.d.ts → feedback-trajectory-D9OVLrg9.d.ts} +1 -1
  68. package/dist/fuzz.d.ts +484 -0
  69. package/dist/fuzz.js +613 -0
  70. package/dist/fuzz.js.map +1 -0
  71. package/dist/governance/index.d.ts +4 -4
  72. package/dist/hosted/index.d.ts +6 -6
  73. package/dist/{index-DE3RXAXD.d.ts → index-Bx3gZ8xl.d.ts} +1 -1
  74. package/dist/index.d.ts +1073 -344
  75. package/dist/index.js +2099 -689
  76. package/dist/index.js.map +1 -1
  77. package/dist/{insight-report-3ADTfClO.d.ts → insight-report-BBwvOh6x.d.ts} +2 -2
  78. package/dist/{integrity-CJzrpUua.d.ts → integrity-VJ9A7aST.d.ts} +1 -1
  79. package/dist/{judge-calibration-DilmB3Ml.d.ts → judge-calibration-0p2QcWNE.d.ts} +1 -1
  80. package/dist/{kind-factory-CVecZZG_.d.ts → kind-factory-5b7xXXOr.d.ts} +2 -2
  81. package/dist/{llm-client-CuUg2Mn3.d.ts → llm-client-BeEcAokY.d.ts} +1 -1
  82. package/dist/matrix/index.d.ts +2 -2
  83. package/dist/meta-eval/index.d.ts +177 -3
  84. package/dist/meta-eval/index.js +260 -1
  85. package/dist/meta-eval/index.js.map +1 -1
  86. package/dist/{multi-layer-verifier-DlWCXuxL.d.ts → multi-layer-verifier-DUZXrPDA.d.ts} +7 -1
  87. package/dist/multishot/index.d.ts +25 -11
  88. package/dist/multishot/index.js +36 -7
  89. package/dist/multishot/index.js.map +1 -1
  90. package/dist/openapi.json +1 -1
  91. package/dist/pipelines/index.js +2 -2
  92. package/dist/{agent-profile-D0PBIWlV.d.ts → pre-registration-DELOEJ8v.d.ts} +144 -4
  93. package/dist/{provenance-DPpNIOJD.d.ts → provenance-LnqRT0sS.d.ts} +5 -5
  94. package/dist/{red-team-DW9Ca_tj.d.ts → red-team-BXHil6c8.d.ts} +1 -1
  95. package/dist/{release-report-hlNtD12q.d.ts → release-report-euXIV_Sk.d.ts} +3 -3
  96. package/dist/reporting.d.ts +8 -8
  97. package/dist/reporting.js +3 -3
  98. package/dist/{researcher-BLPHBbNV.d.ts → researcher-DE6Gpnb4.d.ts} +4 -4
  99. package/dist/rl.d.ts +194 -656
  100. package/dist/rl.js +236 -154
  101. package/dist/rl.js.map +1 -1
  102. package/dist/{rubric-predictive-validity-CnEl9Jc8.d.ts → rubric-predictive-validity-Cy_W-hWZ.d.ts} +1 -1
  103. package/dist/{run-campaign-4Y5V5CN3.js → run-campaign-RDGAM5KJ.js} +3 -3
  104. package/dist/{run-improvement-loop-CNqQckTj.d.ts → run-improvement-loop-5z_l5zDz.d.ts} +2 -2
  105. package/dist/{run-record-De9VarXR.d.ts → run-record-e7vj1uZQ.d.ts} +1 -1
  106. package/dist/{runtime-trajectory-BLRiaifm.d.ts → runtime-trajectory-BDgfGZSr.d.ts} +1 -1
  107. package/dist/{semantic-concept-judge-DIEgr_6v.d.ts → semantic-concept-judge-Dn8Z6KEG.d.ts} +5 -31
  108. package/dist/series-convergence-D5OWMBg6.d.ts +33 -0
  109. package/dist/{statistics-CnC1FMbx.d.ts → statistics-C7PozGrZ.d.ts} +71 -2
  110. package/dist/{summary-report-Db0dDSWP.d.ts → summary-report-DGmUucwQ.d.ts} +1 -1
  111. package/dist/traces.d.ts +58 -4
  112. package/dist/traces.js +14 -6
  113. package/dist/{types-Cu3u_x59.d.ts → types-2VVIL04s.d.ts} +2 -2
  114. package/dist/{types-D7lLRYe9.d.ts → types-BU-7W85F.d.ts} +21 -1
  115. package/dist/{types-CqPax19X.d.ts → types-mn5Aqk7x.d.ts} +1 -1
  116. package/dist/{verdict-CeEgtjyI.d.ts → verdict-C9MlYujm.d.ts} +3 -0
  117. package/dist/wire/index.d.ts +3 -3
  118. package/dist/workflow/index.d.ts +12 -11
  119. package/dist/workflow/index.js +1 -1
  120. package/package.json +36 -13
  121. package/dist/chunk-BABOZOSN.js.map +0 -1
  122. package/dist/chunk-L5G7OUKD.js.map +0 -1
  123. package/dist/chunk-SHTXZ4O2.js +0 -113
  124. package/dist/chunk-SHTXZ4O2.js.map +0 -1
  125. package/dist/chunk-VIDQF3F5.js.map +0 -1
  126. package/dist/chunk-VUINJM5M.js.map +0 -1
  127. package/dist/chunk-XQL22JDG.js.map +0 -1
  128. package/dist/chunk-YGYXHNAQ.js.map +0 -1
  129. package/dist/chunk-YV7J7X5N.js.map +0 -1
  130. /package/dist/{chunk-FZWAFVAA.js.map → chunk-4FBZZIYD.js.map} +0 -0
  131. /package/dist/{chunk-OTYQPHPL.js.map → chunk-6SOJM3VR.js.map} +0 -0
  132. /package/dist/{chunk-Z7VFTS2J.js.map → chunk-CY6U5S3X.js.map} +0 -0
  133. /package/dist/{chunk-WJL2NJXN.js.map → chunk-GSH6QNNS.js.map} +0 -0
  134. /package/dist/{chunk-RBNA5AZT.js.map → chunk-L3JOU6XM.js.map} +0 -0
  135. /package/dist/{chunk-ZZ2HOPME.js.map → chunk-TWS7AZEY.js.map} +0 -0
  136. /package/dist/{run-campaign-4Y5V5CN3.js.map → run-campaign-RDGAM5KJ.js.map} +0 -0
@@ -1,6 +1,6 @@
1
- import { D as DatasetSplit, c as DatasetManifest, a as DatasetScenario } from './dataset-B2kL-fSM.js';
2
- import { m as GateDecision } from './summary-report-Db0dDSWP.js';
3
- import { R as RunRecord, a as RunSplitTag } from './run-record-De9VarXR.js';
1
+ import { D as DatasetSplit, c as DatasetManifest, a as DatasetScenario } from './dataset-BbGkaN2I.js';
2
+ import { m as GateDecision } from './summary-report-DGmUucwQ.js';
3
+ import { R as RunRecord, a as RunSplitTag } from './run-record-e7vj1uZQ.js';
4
4
 
5
5
  /**
6
6
  * Release confidence gate.
@@ -1,14 +1,14 @@
1
- export { R as RubricOutcomePair, a as RubricPredictiveValidityInput, b as RubricPredictiveValidityReport, c as RubricRanking, r as rubricPredictiveValidity } from './rubric-predictive-validity-CnEl9Jc8.js';
2
- export { B as BootstrapOptions, a as BootstrapResult, J as JudgeReplayGateArgs, R as ReleaseConfidenceAxis, b as ReleaseConfidenceAxisName, c as ReleaseConfidenceInput, d as ReleaseConfidenceIssue, e as ReleaseConfidenceMetrics, f as ReleaseConfidenceScorecard, g as ReleaseConfidenceStatus, h as ReleaseConfidenceThresholds, i as ReleaseTraceEvidence, j as RenderReleaseReportOptions, V as Verdict, k as assertReleaseConfidence, l as bootstrapCi, m as evaluateReleaseConfidence, n as judgeReplayGate, r as renderReleaseReport } from './release-report-hlNtD12q.js';
1
+ export { R as RubricOutcomePair, a as RubricPredictiveValidityInput, b as RubricPredictiveValidityReport, c as RubricRanking, r as rubricPredictiveValidity } from './rubric-predictive-validity-Cy_W-hWZ.js';
2
+ export { B as BootstrapOptions, a as BootstrapResult, J as JudgeReplayGateArgs, R as ReleaseConfidenceAxis, b as ReleaseConfidenceAxisName, c as ReleaseConfidenceInput, d as ReleaseConfidenceIssue, e as ReleaseConfidenceMetrics, f as ReleaseConfidenceScorecard, g as ReleaseConfidenceStatus, h as ReleaseConfidenceThresholds, i as ReleaseTraceEvidence, j as RenderReleaseReportOptions, V as Verdict, k as assertReleaseConfidence, l as bootstrapCi, m as evaluateReleaseConfidence, n as judgeReplayGate, r as renderReleaseReport } from './release-report-euXIV_Sk.js';
3
3
  export { I as InterimReleaseConfidence, a as InterimReleaseConfidenceInput, P as PairedEvalueOptions, b as PairedEvalueSequence, c as PairedEvalueStep, S as SequentialDecision, e as evaluateInterimReleaseConfidence, p as pairedEvalueSequence } from './sequential-5iSVfzl2.js';
4
- export { P as PairedBootstrapOptions, a as PairedBootstrapResult, b as benjaminiHochberg, p as pairedBootstrap, w as wilcoxonSignedRank } from './statistics-CnC1FMbx.js';
5
- export { G as GainDistributionBin, a as GainDistributionFigureSpec, b as GainDistributionOptions, P as ParetoFigureSpec, c as ParetoPoint, R as RESEARCH_REPORT_HARD_PAIR_FLOOR, d as ResearchReport, e as ResearchReportCandidate, f as ResearchReportDecision, g as ResearchReportMethodology, h as ResearchReportOptions, i as ResearchReportRecommendation, S as SummaryTable, j as SummaryTableOptions, k as SummaryTableRow, l as gainHistogram, p as paretoChart, r as researchReport, s as summaryTable } from './summary-report-Db0dDSWP.js';
6
- import './run-record-De9VarXR.js';
7
- import './errors-Dwqw-T_m.js';
4
+ export { P as PairedBootstrapOptions, a as PairedBootstrapResult, b as benjaminiHochberg, p as pairedBootstrap, w as wilcoxonSignedRank } from './statistics-C7PozGrZ.js';
5
+ export { G as GainDistributionBin, a as GainDistributionFigureSpec, b as GainDistributionOptions, P as ParetoFigureSpec, c as ParetoPoint, R as RESEARCH_REPORT_HARD_PAIR_FLOOR, d as ResearchReport, e as ResearchReportCandidate, f as ResearchReportDecision, g as ResearchReportMethodology, h as ResearchReportOptions, i as ResearchReportRecommendation, S as SummaryTable, j as SummaryTableOptions, k as SummaryTableRow, l as gainHistogram, p as paretoChart, r as researchReport, s as summaryTable } from './summary-report-DGmUucwQ.js';
6
+ import './run-record-e7vj1uZQ.js';
7
+ import './errors-CzMUYo7b.js';
8
8
  import './schema-m0gsnbt3.js';
9
9
  import './outcome-store-rnXLEqSn.js';
10
- import './dataset-B2kL-fSM.js';
11
- import './judge-calibration-DilmB3Ml.js';
10
+ import './dataset-BbGkaN2I.js';
11
+ import './judge-calibration-0p2QcWNE.js';
12
12
  import './types-Croy5h7V.js';
13
13
  import '@tangle-network/tcloud';
14
14
  import './failure-cluster-CL7IVgkJ.js';
package/dist/reporting.js CHANGED
@@ -4,7 +4,7 @@ import {
4
4
  evaluateReleaseConfidence,
5
5
  judgeReplayGate,
6
6
  renderReleaseReport
7
- } from "./chunk-FZWAFVAA.js";
7
+ } from "./chunk-4FBZZIYD.js";
8
8
  import {
9
9
  rubricPredictiveValidity
10
10
  } from "./chunk-YRZ4M5GS.js";
@@ -18,12 +18,12 @@ import {
18
18
  paretoChart,
19
19
  researchReport,
20
20
  summaryTable
21
- } from "./chunk-Z7VFTS2J.js";
21
+ } from "./chunk-CY6U5S3X.js";
22
22
  import {
23
23
  benjaminiHochberg,
24
24
  pairedBootstrap,
25
25
  wilcoxonSignedRank
26
- } from "./chunk-IDVBLYCY.js";
26
+ } from "./chunk-LMZQ2Z4U.js";
27
27
  import "./chunk-VSMTAMNK.js";
28
28
  import "./chunk-3BFEG2F6.js";
29
29
  import "./chunk-PZ5AY32C.js";
@@ -1,8 +1,8 @@
1
- import { a as RunSplitTag, b as RunTokenUsage, c as RunJudgeMetadata, J as JudgeScoresRecord, A as AgentProfileCell, d as AgentProfileCellInput, R as RunRecord } from './run-record-De9VarXR.js';
2
- import { L as LlmClientOptions, a as LlmRouteRequirements } from './llm-client-CuUg2Mn3.js';
3
- import { h as ResearchReportOptions, d as ResearchReport, m as GateDecision } from './summary-report-Db0dDSWP.js';
1
+ import { a as RunSplitTag, b as RunTokenUsage, c as RunJudgeMetadata, J as JudgeScoresRecord, A as AgentProfileCell, d as AgentProfileCellInput, R as RunRecord } from './run-record-e7vj1uZQ.js';
2
+ import { L as LlmClientOptions, a as LlmRouteRequirements } from './llm-client-BeEcAokY.js';
3
+ import { h as ResearchReportOptions, d as ResearchReport, m as GateDecision } from './summary-report-DGmUucwQ.js';
4
4
  import { T as TraceEmitter, R as RunCompleteHook } from './emitter-DEZwY14K.js';
5
- import { R as RunIntegrityExpectations, a as RunIntegrityReport } from './integrity-CJzrpUua.js';
5
+ import { R as RunIntegrityExpectations, a as RunIntegrityReport } from './integrity-VJ9A7aST.js';
6
6
  import { R as RawProviderSink } from './raw-provider-sink-C46HDghv.js';
7
7
  import { F as FailureClass } from './schema-m0gsnbt3.js';
8
8
  import { T as TraceStore } from './store-CKUAgsJz.js';