@tangle-network/agent-eval 0.95.1 → 0.96.1

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 (65) hide show
  1. package/dist/adapters/http.d.ts +1 -1
  2. package/dist/adapters/langchain.d.ts +1 -1
  3. package/dist/adapters/otel.d.ts +1 -1
  4. package/dist/analyst/index.js +1 -1
  5. package/dist/belief-state/index.js +1 -1
  6. package/dist/builder-eval/index.js +4 -29
  7. package/dist/builder-eval/index.js.map +1 -1
  8. package/dist/campaign/index.d.ts +6 -6
  9. package/dist/campaign/index.js +5 -5
  10. package/dist/{chunk-AQ5WQAIV.js → chunk-3NHEO6ZC.js} +2 -2
  11. package/dist/chunk-3NHEO6ZC.js.map +1 -0
  12. package/dist/{chunk-URWVKRCS.js → chunk-6GT4NI4V.js} +2 -2
  13. package/dist/{chunk-5HRORJQY.js → chunk-AIGWQEME.js} +5 -16
  14. package/dist/{chunk-5HRORJQY.js.map → chunk-AIGWQEME.js.map} +1 -1
  15. package/dist/{chunk-2T4EZACH.js → chunk-HRGTA6U5.js} +2 -2
  16. package/dist/{chunk-56GC6VYO.js → chunk-HRGUJTER.js} +669 -665
  17. package/dist/chunk-HRGUJTER.js.map +1 -0
  18. package/dist/{chunk-NACM5RS7.js → chunk-IH7LYRHL.js} +2 -2
  19. package/dist/{chunk-7QTQKIDD.js → chunk-JMIUM2HE.js} +3 -3
  20. package/dist/{chunk-YRZ4M5GS.js → chunk-NF7OZ4J7.js} +7 -29
  21. package/dist/chunk-NF7OZ4J7.js.map +1 -0
  22. package/dist/{chunk-X74V6ESX.js → chunk-OKQ2LAT7.js} +2 -2
  23. package/dist/{chunk-Z6L6YSU6.js → chunk-QZYXA7ZO.js} +11 -45
  24. package/dist/chunk-QZYXA7ZO.js.map +1 -0
  25. package/dist/{chunk-KKWJD5E6.js → chunk-RPZMBW27.js} +5 -5
  26. package/dist/{chunk-QTMYW64F.js → chunk-VDGPPGE3.js} +2 -2
  27. package/dist/contract/index.d.ts +144 -9
  28. package/dist/contract/index.js +152 -8
  29. package/dist/contract/index.js.map +1 -1
  30. package/dist/diagnose.js +1 -1
  31. package/dist/{gepa-C1NCIZ9o.d.ts → gepa-Dprxvz8r.d.ts} +2 -2
  32. package/dist/hosted/index.d.ts +1 -1
  33. package/dist/index.d.ts +3 -3
  34. package/dist/index.js +15 -9
  35. package/dist/index.js.map +1 -1
  36. package/dist/meta-eval/index.d.ts +1 -1
  37. package/dist/meta-eval/index.js +6 -28
  38. package/dist/meta-eval/index.js.map +1 -1
  39. package/dist/multishot/index.d.ts +1 -1
  40. package/dist/openapi.json +1 -1
  41. package/dist/pipelines/index.js +5 -19
  42. package/dist/pipelines/index.js.map +1 -1
  43. package/dist/{provenance-CncDq9qE.d.ts → provenance-DJ--Jcbg.d.ts} +3 -3
  44. package/dist/reporting.d.ts +1 -1
  45. package/dist/reporting.js +4 -4
  46. package/dist/rl.d.ts +1 -1
  47. package/dist/rl.js +5 -5
  48. package/dist/{run-campaign-WXY7KI67.js → run-campaign-OWCFOEQG.js} +3 -3
  49. package/dist/{statistics-CCJpTGOS.d.ts → statistics-xP-cWc5k.d.ts} +17 -1
  50. package/dist/{types-DQRY8ZT-.d.ts → types-BMahhhio.d.ts} +1 -1
  51. package/dist/workflow/index.d.ts +1 -1
  52. package/dist/workflow/index.js +1 -1
  53. package/package.json +1 -1
  54. package/dist/chunk-56GC6VYO.js.map +0 -1
  55. package/dist/chunk-AQ5WQAIV.js.map +0 -1
  56. package/dist/chunk-YRZ4M5GS.js.map +0 -1
  57. package/dist/chunk-Z6L6YSU6.js.map +0 -1
  58. /package/dist/{chunk-URWVKRCS.js.map → chunk-6GT4NI4V.js.map} +0 -0
  59. /package/dist/{chunk-2T4EZACH.js.map → chunk-HRGTA6U5.js.map} +0 -0
  60. /package/dist/{chunk-NACM5RS7.js.map → chunk-IH7LYRHL.js.map} +0 -0
  61. /package/dist/{chunk-7QTQKIDD.js.map → chunk-JMIUM2HE.js.map} +0 -0
  62. /package/dist/{chunk-X74V6ESX.js.map → chunk-OKQ2LAT7.js.map} +0 -0
  63. /package/dist/{chunk-KKWJD5E6.js.map → chunk-RPZMBW27.js.map} +0 -0
  64. /package/dist/{chunk-QTMYW64F.js.map → chunk-VDGPPGE3.js.map} +0 -0
  65. /package/dist/{run-campaign-WXY7KI67.js.map → run-campaign-OWCFOEQG.js.map} +0 -0
package/dist/index.js CHANGED
@@ -9,7 +9,7 @@ import {
9
9
  checkBehavioralCanary,
10
10
  checkCanaries,
11
11
  runBehavioralCanaries
12
- } from "./chunk-Z6L6YSU6.js";
12
+ } from "./chunk-QZYXA7ZO.js";
13
13
  import {
14
14
  classifyEuAiRisk,
15
15
  euAiActReport,
@@ -67,12 +67,12 @@ import {
67
67
  scoreRedTeamOutput,
68
68
  surfaceContentHash,
69
69
  toolNamesForRun
70
- } from "./chunk-7QTQKIDD.js";
70
+ } from "./chunk-JMIUM2HE.js";
71
71
  import {
72
72
  BackendIntegrityError,
73
73
  assertRealBackend,
74
74
  summarizeBackendIntegrity
75
- } from "./chunk-2T4EZACH.js";
75
+ } from "./chunk-HRGTA6U5.js";
76
76
  import {
77
77
  MODEL_PRICING,
78
78
  MetricsCollector,
@@ -94,7 +94,7 @@ import {
94
94
  computeToolUseMetrics,
95
95
  iqr,
96
96
  welchsTTest
97
- } from "./chunk-NACM5RS7.js";
97
+ } from "./chunk-IH7LYRHL.js";
98
98
  import {
99
99
  analyzeSeries
100
100
  } from "./chunk-BOD4O7OF.js";
@@ -132,7 +132,7 @@ import {
132
132
  import {
133
133
  buildDefaultAnalystRegistry,
134
134
  computeTraceMetrics
135
- } from "./chunk-AQ5WQAIV.js";
135
+ } from "./chunk-3NHEO6ZC.js";
136
136
  import {
137
137
  LockedJsonlAppender,
138
138
  Mutex
@@ -176,10 +176,10 @@ import {
176
176
  evaluateReleaseConfidence,
177
177
  judgeReplayGate,
178
178
  renderReleaseReport
179
- } from "./chunk-QTMYW64F.js";
179
+ } from "./chunk-VDGPPGE3.js";
180
180
  import {
181
181
  runEvalCampaign
182
- } from "./chunk-X74V6ESX.js";
182
+ } from "./chunk-OKQ2LAT7.js";
183
183
  import {
184
184
  LlmCallError,
185
185
  LlmClient,
@@ -202,7 +202,7 @@ import {
202
202
  paretoChart,
203
203
  researchReport,
204
204
  summaryTable
205
- } from "./chunk-URWVKRCS.js";
205
+ } from "./chunk-6GT4NI4V.js";
206
206
  import {
207
207
  attributeCounterfactuals,
208
208
  runCounterfactual
@@ -240,15 +240,18 @@ import {
240
240
  pairedTTest,
241
241
  partialCredit,
242
242
  passAtK,
243
+ pearsonR,
243
244
  positionalBias,
245
+ ranks,
244
246
  requiredSampleSize,
245
247
  selfPreference,
248
+ spearmanR,
246
249
  verbosityBias,
247
250
  weightedComposite,
248
251
  weightedMean,
249
252
  wilcoxonSignedRank,
250
253
  wilson
251
- } from "./chunk-56GC6VYO.js";
254
+ } from "./chunk-HRGUJTER.js";
252
255
  import {
253
256
  FileSystemTraceStore,
254
257
  InMemoryTraceStore,
@@ -10509,6 +10512,7 @@ export {
10509
10512
  partitionHeldOut,
10510
10513
  passAtK,
10511
10514
  passOrthogonality,
10515
+ pearsonR,
10512
10516
  pixelDeltaRatio,
10513
10517
  planTraceInsightQuestions,
10514
10518
  politenessPrefixMutator,
@@ -10524,6 +10528,7 @@ export {
10524
10528
  proposeSynthesisTargets,
10525
10529
  providerFromBaseUrl,
10526
10530
  pytestTestParser,
10531
+ ranks,
10527
10532
  readOtlpStatus,
10528
10533
  recordRuns,
10529
10534
  recordRunsToScorecard,
@@ -10598,6 +10603,7 @@ export {
10598
10603
  serializeFeedbackTrajectoriesJsonl,
10599
10604
  signManifest,
10600
10605
  soc2Report,
10606
+ spearmanR,
10601
10607
  splitGold,
10602
10608
  statusAdvanced,
10603
10609
  stopOnNoProgress,