@tangle-network/agent-eval 0.80.0 → 0.81.0

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 (95) hide show
  1. package/CHANGELOG.md +14 -0
  2. package/README.md +53 -152
  3. package/dist/adapters/http.d.ts +2 -2
  4. package/dist/adapters/langchain.d.ts +2 -2
  5. package/dist/adapters/otel.d.ts +4 -4
  6. package/dist/{agent-profile-aSEaJ9Pl.d.ts → agent-profile-D0PBIWlV.d.ts} +14 -2
  7. package/dist/analyst/index.d.ts +10 -10
  8. package/dist/analyst/index.js +3 -3
  9. package/dist/{analyst-t7zZS3TV.d.ts → analyst-C8HHvfJp.d.ts} +1 -1
  10. package/dist/belief-state/index.d.ts +344 -8
  11. package/dist/belief-state/index.js +1518 -142
  12. package/dist/belief-state/index.js.map +1 -1
  13. package/dist/benchmarks/index.d.ts +2 -2
  14. package/dist/campaign/index.d.ts +40 -120
  15. package/dist/campaign/index.js +129 -238
  16. package/dist/campaign/index.js.map +1 -1
  17. package/dist/{chunk-RPLZ4OIB.js → chunk-BABOZOSN.js} +7 -4
  18. package/dist/{chunk-RPLZ4OIB.js.map → chunk-BABOZOSN.js.map} +1 -1
  19. package/dist/{chunk-IHDHUN2X.js → chunk-CVVHBFGN.js} +3 -3
  20. package/dist/chunk-CVVHBFGN.js.map +1 -0
  21. package/dist/{chunk-B26KI423.js → chunk-FZWAFVAA.js} +2 -2
  22. package/dist/{chunk-ITBRCT73.js → chunk-IDVBLYCY.js} +2 -10
  23. package/dist/chunk-IDVBLYCY.js.map +1 -0
  24. package/dist/{chunk-5LVWPNS5.js → chunk-L5G7OUKD.js} +4 -4
  25. package/dist/{chunk-5LVWPNS5.js.map → chunk-L5G7OUKD.js.map} +1 -1
  26. package/dist/{chunk-GXHLRXDI.js → chunk-OTYQPHPL.js} +4 -4
  27. package/dist/{chunk-6REHLN5J.js → chunk-QS3RBQPI.js} +2 -2
  28. package/dist/{chunk-GWGO2K6Y.js → chunk-RBNA5AZT.js} +2 -2
  29. package/dist/chunk-S42AWHMP.js +697 -0
  30. package/dist/chunk-S42AWHMP.js.map +1 -0
  31. package/dist/chunk-VI2UW6B6.js +162 -0
  32. package/dist/chunk-VI2UW6B6.js.map +1 -0
  33. package/dist/{chunk-CF67I6QY.js → chunk-VIDQF3F5.js} +2 -2
  34. package/dist/{chunk-XXNIODOM.js → chunk-WJL2NJXN.js} +3 -3
  35. package/dist/{chunk-LB2UOI5F.js → chunk-YGYXHNAQ.js} +47 -160
  36. package/dist/chunk-YGYXHNAQ.js.map +1 -0
  37. package/dist/{chunk-KX6F6NCG.js → chunk-Z7VFTS2J.js} +2 -2
  38. package/dist/{chunk-ZPSKPT3V.js → chunk-ZZ2HOPME.js} +5 -2
  39. package/dist/chunk-ZZ2HOPME.js.map +1 -0
  40. package/dist/cli.js +2 -2
  41. package/dist/code-agent-session-BRXmavYv.d.ts +80 -0
  42. package/dist/contract/index.d.ts +16 -15
  43. package/dist/contract/index.js +23 -6
  44. package/dist/contract/index.js.map +1 -1
  45. package/dist/{control-CehLtoET.d.ts → control-GeE8OhpN.d.ts} +1 -1
  46. package/dist/control.d.ts +2 -2
  47. package/dist/hosted/index.d.ts +4 -4
  48. package/dist/{index-B1RKber3.d.ts → index-DE3RXAXD.d.ts} +1 -1
  49. package/dist/index.d.ts +78 -287
  50. package/dist/index.js +87 -410
  51. package/dist/index.js.map +1 -1
  52. package/dist/{insight-report-dlpEzQDi.d.ts → insight-report-3ADTfClO.d.ts} +1 -1
  53. package/dist/{kind-factory-DqV2t1Xk.d.ts → kind-factory-CVecZZG_.d.ts} +2 -2
  54. package/dist/{llm-client-DbjLfz-K.d.ts → llm-client-CuUg2Mn3.d.ts} +1 -1
  55. package/dist/meta-eval/index.d.ts +2 -2
  56. package/dist/openapi.json +1 -1
  57. package/dist/pipelines/index.js +2 -2
  58. package/dist/{provenance-jG-Gngg8.d.ts → provenance-B9Q4886D.d.ts} +4 -4
  59. package/dist/{registry-BK0Zee01.d.ts → registry-DrEQ3Luj.d.ts} +1 -1
  60. package/dist/{release-report-CXXZlR8g.d.ts → release-report-hlNtD12q.d.ts} +2 -2
  61. package/dist/reporting.d.ts +5 -5
  62. package/dist/reporting.js +3 -3
  63. package/dist/{researcher-rInLj9De.d.ts → researcher-BLPHBbNV.d.ts} +3 -3
  64. package/dist/rl.d.ts +7 -7
  65. package/dist/rl.js +4 -4
  66. package/dist/{rubric-predictive-validity-CLPuwiUw.d.ts → rubric-predictive-validity-CnEl9Jc8.d.ts} +1 -1
  67. package/dist/{run-campaign-OVEZF24D.js → run-campaign-4Y5V5CN3.js} +3 -3
  68. package/dist/{run-improvement-loop-BAl_aVOZ.d.ts → run-improvement-loop-D6PZOoQL.d.ts} +2 -2
  69. package/dist/{run-record-sItO5ftF.d.ts → run-record-De9VarXR.d.ts} +1 -1
  70. package/dist/{semantic-concept-judge-qXEUV2w7.d.ts → semantic-concept-judge-DIEgr_6v.d.ts} +6 -6
  71. package/dist/{statistics-B7yCbi9i.d.ts → statistics-CnC1FMbx.d.ts} +3 -7
  72. package/dist/{store-GmBE2pZZ.d.ts → store-C1YxJDEK.d.ts} +1 -1
  73. package/dist/{summary-report-BTaXq1TS.d.ts → summary-report-Db0dDSWP.d.ts} +1 -1
  74. package/dist/traces.d.ts +5 -5
  75. package/dist/{types-DRvV0zRo.d.ts → types-Cu3u_x59.d.ts} +3 -3
  76. package/dist/{types-4mm2msnR.d.ts → types-D7lLRYe9.d.ts} +1 -1
  77. package/dist/wire/index.js +2 -2
  78. package/dist/workflow/index.d.ts +7 -7
  79. package/dist/workflow/index.js +1 -1
  80. package/docs/concepts.md +1 -0
  81. package/docs/research/belief-state-agent-eval-roadmap.md +39 -7
  82. package/docs/self-improvement-map.md +111 -0
  83. package/package.json +2 -2
  84. package/dist/chunk-IHDHUN2X.js.map +0 -1
  85. package/dist/chunk-ITBRCT73.js.map +0 -1
  86. package/dist/chunk-LB2UOI5F.js.map +0 -1
  87. package/dist/chunk-ZPSKPT3V.js.map +0 -1
  88. /package/dist/{chunk-B26KI423.js.map → chunk-FZWAFVAA.js.map} +0 -0
  89. /package/dist/{chunk-GXHLRXDI.js.map → chunk-OTYQPHPL.js.map} +0 -0
  90. /package/dist/{chunk-6REHLN5J.js.map → chunk-QS3RBQPI.js.map} +0 -0
  91. /package/dist/{chunk-GWGO2K6Y.js.map → chunk-RBNA5AZT.js.map} +0 -0
  92. /package/dist/{chunk-CF67I6QY.js.map → chunk-VIDQF3F5.js.map} +0 -0
  93. /package/dist/{chunk-XXNIODOM.js.map → chunk-WJL2NJXN.js.map} +0 -0
  94. /package/dist/{chunk-KX6F6NCG.js.map → chunk-Z7VFTS2J.js.map} +0 -0
  95. /package/dist/{run-campaign-OVEZF24D.js.map → run-campaign-4Y5V5CN3.js.map} +0 -0
@@ -1,10 +1,10 @@
1
1
  import {
2
2
  runCampaign,
3
3
  summarizeBackendIntegrity
4
- } from "./chunk-ZPSKPT3V.js";
4
+ } from "./chunk-ZZ2HOPME.js";
5
5
  import {
6
6
  callLlm
7
- } from "./chunk-IHDHUN2X.js";
7
+ } from "./chunk-CVVHBFGN.js";
8
8
  import {
9
9
  DEFAULT_REDACTION_RULES
10
10
  } from "./chunk-GGE4NNQT.js";
@@ -1252,6 +1252,9 @@ function labelTrustRank(trust) {
1252
1252
  import { createHash } from "crypto";
1253
1253
  async function runOptimization(opts) {
1254
1254
  const promoteTopK = opts.promoteTopK ?? 2;
1255
+ if (typeof opts.runDir !== "string" || opts.runDir.trim().length === 0) {
1256
+ throw new Error("runOptimization: runDir is required and must be a non-empty string");
1257
+ }
1255
1258
  const baselineCampaign = await runCampaign({
1256
1259
  ...opts,
1257
1260
  dispatch: (scenario, ctx) => opts.dispatchWithSurface(opts.baselineSurface, scenario, ctx),
@@ -1440,7 +1443,7 @@ async function runImprovementLoop(opts) {
1440
1443
  const dispatchTimeoutMs = opts.dispatchTimeoutMs ?? DEFAULT_DISPATCH_TIMEOUT_MS;
1441
1444
  const optimization = await runOptimization({ ...opts, dispatchTimeoutMs });
1442
1445
  const winnerIsBaseline = optimization.winnerSurfaceHash === surfaceHash(opts.baselineSurface);
1443
- const { runCampaign: runCampaign2 } = await import("./run-campaign-OVEZF24D.js");
1446
+ const { runCampaign: runCampaign2 } = await import("./run-campaign-4Y5V5CN3.js");
1444
1447
  const baselineOnHoldout = await runCampaign2({
1445
1448
  ...opts,
1446
1449
  dispatchTimeoutMs,
@@ -1841,4 +1844,4 @@ export {
1841
1844
  provenanceSpansPath,
1842
1845
  emitLoopProvenance
1843
1846
  };
1844
- //# sourceMappingURL=chunk-RPLZ4OIB.js.map
1847
+ //# sourceMappingURL=chunk-BABOZOSN.js.map