@tangle-network/agent-eval 0.123.1 → 0.123.2

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 (79) hide show
  1. package/CHANGELOG.md +5 -0
  2. package/README.md +151 -161
  3. package/dist/analyst/index.d.ts +9 -1
  4. package/dist/analyst/index.js +5 -5
  5. package/dist/authenticity/index.js +3 -2
  6. package/dist/authenticity/index.js.map +1 -1
  7. package/dist/benchmarks/index.d.ts +2 -1
  8. package/dist/benchmarks/index.js +6 -6
  9. package/dist/campaign/index.d.ts +29 -33
  10. package/dist/campaign/index.js +6 -6
  11. package/dist/{chunk-A5S77LSE.js → chunk-4SOQ4ND2.js} +2 -2
  12. package/dist/{chunk-VJ7T5WIO.js → chunk-5YMKIFYP.js} +3 -3
  13. package/dist/{chunk-U5CHZ5M3.js → chunk-DNVPOYUS.js} +4 -4
  14. package/dist/{chunk-6WX7CBAR.js → chunk-E3HAD4A3.js} +19 -8
  15. package/dist/chunk-E3HAD4A3.js.map +1 -0
  16. package/dist/{chunk-LBAHQOBI.js → chunk-EBDOTTZJ.js} +37 -11
  17. package/dist/chunk-EBDOTTZJ.js.map +1 -0
  18. package/dist/{chunk-XJYR7XFV.js → chunk-GC4ATIKK.js} +1 -1
  19. package/dist/chunk-GC4ATIKK.js.map +1 -0
  20. package/dist/{chunk-HZJF4IUO.js → chunk-HQY7LBV2.js} +3 -3
  21. package/dist/{chunk-NJC7U437.js → chunk-J7S4YM27.js} +6 -5
  22. package/dist/chunk-J7S4YM27.js.map +1 -0
  23. package/dist/{chunk-S3UZOQ5Y.js → chunk-LOW3U7JZ.js} +2 -2
  24. package/dist/{chunk-OYZAPX5G.js → chunk-R226UZOI.js} +2 -2
  25. package/dist/{chunk-GS3FJGUF.js → chunk-RQP5UTK5.js} +120 -14
  26. package/dist/chunk-RQP5UTK5.js.map +1 -0
  27. package/dist/{chunk-G2GPNLSX.js → chunk-WMJR67FX.js} +3 -3
  28. package/dist/{chunk-FC5NDO3E.js → chunk-WXQTVEKM.js} +3 -3
  29. package/dist/cli.js +100 -10
  30. package/dist/cli.js.map +1 -1
  31. package/dist/contract/index.d.ts +97 -5
  32. package/dist/contract/index.js +9 -7
  33. package/dist/contract/index.js.map +1 -1
  34. package/dist/control.js +3 -3
  35. package/dist/fuzz.js +3 -2
  36. package/dist/fuzz.js.map +1 -1
  37. package/dist/hosted/index.d.ts +8 -2
  38. package/dist/index.d.ts +10 -2
  39. package/dist/index.js +13 -13
  40. package/dist/index.js.map +1 -1
  41. package/dist/openapi.json +1 -1
  42. package/dist/rl.d.ts +9 -1
  43. package/dist/rl.js +4 -4
  44. package/dist/storyboard/index.js +1 -1
  45. package/dist/storyboard/index.js.map +1 -1
  46. package/dist/traces.js +3 -3
  47. package/dist/wire/index.d.ts +61 -4
  48. package/dist/wire/index.js +2 -2
  49. package/docs/adapters-observability.md +6 -6
  50. package/docs/building-doctrine.md +5 -5
  51. package/docs/concepts.md +29 -29
  52. package/docs/customer-journeys.md +80 -155
  53. package/docs/design/loop-taxonomy.md +26 -27
  54. package/docs/design.md +70 -0
  55. package/docs/distributed-driver.md +14 -14
  56. package/docs/eval-surface-map.md +11 -11
  57. package/docs/hosted-ingest-spec.md +4 -4
  58. package/docs/improvement-glossary.md +38 -38
  59. package/docs/insight-report.md +32 -27
  60. package/docs/multi-shot-optimization.md +8 -8
  61. package/docs/research-report-methodology.md +9 -9
  62. package/docs/self-improvement-map.md +13 -13
  63. package/docs/trace-analysis.md +2 -2
  64. package/docs/wire-protocol.md +16 -16
  65. package/package.json +2 -1
  66. package/dist/chunk-6WX7CBAR.js.map +0 -1
  67. package/dist/chunk-GS3FJGUF.js.map +0 -1
  68. package/dist/chunk-LBAHQOBI.js.map +0 -1
  69. package/dist/chunk-NJC7U437.js.map +0 -1
  70. package/dist/chunk-XJYR7XFV.js.map +0 -1
  71. package/docs/auto-research-loop-end-to-end.md +0 -186
  72. /package/dist/{chunk-A5S77LSE.js.map → chunk-4SOQ4ND2.js.map} +0 -0
  73. /package/dist/{chunk-VJ7T5WIO.js.map → chunk-5YMKIFYP.js.map} +0 -0
  74. /package/dist/{chunk-U5CHZ5M3.js.map → chunk-DNVPOYUS.js.map} +0 -0
  75. /package/dist/{chunk-HZJF4IUO.js.map → chunk-HQY7LBV2.js.map} +0 -0
  76. /package/dist/{chunk-S3UZOQ5Y.js.map → chunk-LOW3U7JZ.js.map} +0 -0
  77. /package/dist/{chunk-OYZAPX5G.js.map → chunk-R226UZOI.js.map} +0 -0
  78. /package/dist/{chunk-G2GPNLSX.js.map → chunk-WMJR67FX.js.map} +0 -0
  79. /package/dist/{chunk-FC5NDO3E.js.map → chunk-WXQTVEKM.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-6WX7CBAR.js";
12
+ } from "./chunk-E3HAD4A3.js";
13
13
  import {
14
14
  BENCHMARK_SPLIT_SEED,
15
15
  benchmarks_exports,
@@ -53,7 +53,7 @@ import {
53
53
  pairArms,
54
54
  parseCorrectnessResponse,
55
55
  verifyCompletion
56
- } from "./chunk-GS3FJGUF.js";
56
+ } from "./chunk-RQP5UTK5.js";
57
57
  import {
58
58
  DEFAULT_MUTATION_PRIMITIVES,
59
59
  DEFAULT_RED_TEAM_CORPUS,
@@ -91,7 +91,7 @@ import {
91
91
  scoreRedTeamOutput,
92
92
  surfaceContentHash,
93
93
  toolNamesForRun
94
- } from "./chunk-HZJF4IUO.js";
94
+ } from "./chunk-HQY7LBV2.js";
95
95
  import {
96
96
  BackendIntegrityError,
97
97
  assertRealAgentReceipts,
@@ -116,12 +116,12 @@ import {
116
116
  defaultIsMaterial,
117
117
  diffFindings,
118
118
  runSemanticConceptJudge
119
- } from "./chunk-G2GPNLSX.js";
119
+ } from "./chunk-WMJR67FX.js";
120
120
  import {
121
121
  buildDefaultAnalystRegistry,
122
122
  computeTraceMetrics,
123
123
  createChatClient
124
- } from "./chunk-VJ7T5WIO.js";
124
+ } from "./chunk-5YMKIFYP.js";
125
125
  import "./chunk-HHWE3POT.js";
126
126
  import {
127
127
  AnalystRegistry,
@@ -156,7 +156,7 @@ import {
156
156
  scorePolicyEditReadiness,
157
157
  validatePolicyEdit,
158
158
  validatePolicyEditCandidateRecord
159
- } from "./chunk-FC5NDO3E.js";
159
+ } from "./chunk-WXQTVEKM.js";
160
160
  import {
161
161
  allCriticalPassed,
162
162
  controlFailureClassFromVerification,
@@ -177,7 +177,7 @@ import {
177
177
  stopOnNoProgress,
178
178
  stopOnRepeatedAction,
179
179
  subjectiveEval
180
- } from "./chunk-OYZAPX5G.js";
180
+ } from "./chunk-R226UZOI.js";
181
181
  import {
182
182
  assertReleaseConfidence,
183
183
  bootstrapCi,
@@ -187,7 +187,7 @@ import {
187
187
  } from "./chunk-MOXWMGPC.js";
188
188
  import {
189
189
  runEvalCampaign
190
- } from "./chunk-U5CHZ5M3.js";
190
+ } from "./chunk-DNVPOYUS.js";
191
191
  import "./chunk-ARU2PZFM.js";
192
192
  import {
193
193
  LlmCallError,
@@ -204,7 +204,7 @@ import {
204
204
  maximumChargeForLlmRequest,
205
205
  probeLlm,
206
206
  stripFencedJson
207
- } from "./chunk-NJC7U437.js";
207
+ } from "./chunk-J7S4YM27.js";
208
208
  import {
209
209
  evaluateInterimReleaseConfidence,
210
210
  pairedEvalueSequence
@@ -305,7 +305,7 @@ import {
305
305
  scoreTraceInsightReadiness,
306
306
  tokenizeDomainWords,
307
307
  traceAnalystOnRunComplete
308
- } from "./chunk-A5S77LSE.js";
308
+ } from "./chunk-4SOQ4ND2.js";
309
309
  import "./chunk-H5UD2323.js";
310
310
  import {
311
311
  extractUsage,
@@ -377,7 +377,7 @@ import {
377
377
  resolveRunCostProvenance,
378
378
  roundTripRunRecord,
379
379
  validateRunRecord
380
- } from "./chunk-S3UZOQ5Y.js";
380
+ } from "./chunk-LOW3U7JZ.js";
381
381
  import {
382
382
  FAILURE_CLASSES,
383
383
  TRACE_SCHEMA_VERSION,
@@ -400,7 +400,7 @@ import {
400
400
  toAgentProfileJson,
401
401
  validateAgentProfileCell,
402
402
  verifyAgentProfileCell
403
- } from "./chunk-XJYR7XFV.js";
403
+ } from "./chunk-GC4ATIKK.js";
404
404
  import {
405
405
  canonicalize,
406
406
  evaluateHypothesis,
@@ -10800,7 +10800,7 @@ function expectRunRecordShape(value, path) {
10800
10800
  throw new ValidationError(`${path}: run record tokenUsage.input/output must be numbers`);
10801
10801
  }
10802
10802
  const outcome = obj.outcome;
10803
- if (!outcome || !outcome.raw || typeof outcome.raw !== "object") {
10803
+ if (!outcome?.raw || typeof outcome.raw !== "object") {
10804
10804
  throw new ValidationError(`${path}: run record outcome.raw must be an object`);
10805
10805
  }
10806
10806
  return value;