@tangle-network/agent-eval 0.200.0 → 0.201.0

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 (231) hide show
  1. package/CHANGELOG.md +8 -0
  2. package/dist/adapters/http.d.ts +7 -8
  3. package/dist/adapters/http.d.ts.map +1 -1
  4. package/dist/adapters/http.js +2 -2
  5. package/dist/adapters/http.js.map +1 -1
  6. package/dist/agent-profile-DDfIjdyS.d.ts.map +1 -1
  7. package/dist/analyst/index.d.ts +76 -76
  8. package/dist/analyst/index.d.ts.map +1 -1
  9. package/dist/analyst/index.js +6 -6
  10. package/dist/{analyze-runs-DFbp2gB8.js → analyze-runs-BrIibNd0.js} +47 -42
  11. package/dist/{analyze-runs-DFbp2gB8.js.map → analyze-runs-BrIibNd0.js.map} +1 -1
  12. package/dist/{ast-CP9ae9B0.js → ast-DJ6Bc7ab.js} +5 -4
  13. package/dist/{ast-CP9ae9B0.js.map → ast-DJ6Bc7ab.js.map} +1 -1
  14. package/dist/authenticity/index.d.ts +14 -15
  15. package/dist/authenticity/index.d.ts.map +1 -1
  16. package/dist/{baseline-BC-eBZ7U.js → baseline-CVKsfWTg.js} +2 -2
  17. package/dist/{baseline-BC-eBZ7U.js.map → baseline-CVKsfWTg.js.map} +1 -1
  18. package/dist/{benchmark-BeQJyrRC.js → benchmark-BywPeAUo.js} +4 -3
  19. package/dist/{benchmark-BeQJyrRC.js.map → benchmark-BywPeAUo.js.map} +1 -1
  20. package/dist/{benchmark-command-EBmuMUBo.js → benchmark-command-DFs_i62N.js} +24 -23
  21. package/dist/{benchmark-command-EBmuMUBo.js.map → benchmark-command-DFs_i62N.js.map} +1 -1
  22. package/dist/benchmarks/index.d.ts +12 -12
  23. package/dist/benchmarks/index.d.ts.map +1 -1
  24. package/dist/benchmarks/index.js +3 -3
  25. package/dist/{bounded-process-BBZob7vl.js → bounded-process-Cj9YjXbE.js} +3 -3
  26. package/dist/{bounded-process-BBZob7vl.js.map → bounded-process-Cj9YjXbE.js.map} +1 -1
  27. package/dist/builder-eval/index.d.ts +16 -17
  28. package/dist/builder-eval/index.d.ts.map +1 -1
  29. package/dist/builder-eval/index.js +12 -10
  30. package/dist/builder-eval/index.js.map +1 -1
  31. package/dist/campaign/index.js +11 -11
  32. package/dist/{campaign-L391bmir.js → campaign-PmTWZi72.js} +30 -25
  33. package/dist/{campaign-L391bmir.js.map → campaign-PmTWZi72.js.map} +1 -1
  34. package/dist/{campaign-evidence-jL_U7Ikv.js → campaign-evidence-Dt_rWPk2.js} +4 -4
  35. package/dist/{campaign-evidence-jL_U7Ikv.js.map → campaign-evidence-Dt_rWPk2.js.map} +1 -1
  36. package/dist/{chat-client-CJORSG_J.js → chat-client-DUhWNQQS.js} +5 -4
  37. package/dist/{chat-client-CJORSG_J.js.map → chat-client-DUhWNQQS.js.map} +1 -1
  38. package/dist/{chat-json-call-DnlDjpco.js → chat-json-call-Dx_sHzqm.js} +2 -2
  39. package/dist/{chat-json-call-DnlDjpco.js.map → chat-json-call-Dx_sHzqm.js.map} +1 -1
  40. package/dist/{claim-V9Zqbq0J.js → claim-BXcZw-jo.js} +2 -2
  41. package/dist/{claim-V9Zqbq0J.js.map → claim-BXcZw-jo.js.map} +1 -1
  42. package/dist/cli.js +12 -11
  43. package/dist/cli.js.map +1 -1
  44. package/dist/contract/index.js +22 -19
  45. package/dist/contract/index.js.map +1 -1
  46. package/dist/{default-registry-xMLX160E.js → default-registry-D4qXx2aG.js} +2 -2
  47. package/dist/{default-registry-xMLX160E.js.map → default-registry-D4qXx2aG.js.map} +1 -1
  48. package/dist/define-agent-eval-1YuvJpOs.d.ts.map +1 -1
  49. package/dist/{define-agent-eval-7q_UwsTt.js → define-agent-eval-CJN9dTQw.js} +10 -9
  50. package/dist/{define-agent-eval-7q_UwsTt.js.map → define-agent-eval-CJN9dTQw.js.map} +1 -1
  51. package/dist/{descriptive-1V17A-qa.js → descriptive-D9LUFk1-.js} +2 -2
  52. package/dist/{descriptive-1V17A-qa.js.map → descriptive-D9LUFk1-.js.map} +1 -1
  53. package/dist/diagnosis/index.d.ts +7 -7
  54. package/dist/diagnosis/index.d.ts.map +1 -1
  55. package/dist/diagnosis/index.js +2 -2
  56. package/dist/diagnosis/index.js.map +1 -1
  57. package/dist/{dspy-rlm-engine-B5T43BkZ.js → dspy-rlm-engine-US8YsYGq.js} +5 -5
  58. package/dist/{dspy-rlm-engine-B5T43BkZ.js.map → dspy-rlm-engine-US8YsYGq.js.map} +1 -1
  59. package/dist/{eval-campaign-GapmPHIA.js → eval-campaign-ha_aWtk7.js} +14 -12
  60. package/dist/{eval-campaign-GapmPHIA.js.map → eval-campaign-ha_aWtk7.js.map} +1 -1
  61. package/dist/evaluation.d.ts +9 -10
  62. package/dist/evaluation.d.ts.map +1 -1
  63. package/dist/experiment/index.d.ts +29 -29
  64. package/dist/experiment/index.d.ts.map +1 -1
  65. package/dist/experiment/index.js +13 -12
  66. package/dist/experiment/index.js.map +1 -1
  67. package/dist/{exporters-DEcXbvgO.js → exporters-Coiv-qO2.js} +2 -2
  68. package/dist/{exporters-DEcXbvgO.js.map → exporters-Coiv-qO2.js.map} +1 -1
  69. package/dist/{external-optimizer-process-CEXcCKqd.js → external-optimizer-process-KLcw0Vnc.js} +2 -2
  70. package/dist/{external-optimizer-process-CEXcCKqd.js.map → external-optimizer-process-KLcw0Vnc.js.map} +1 -1
  71. package/dist/{external-optimizer-subprocess-laM1-UDV.js → external-optimizer-subprocess-CkyUUV7h.js} +4 -4
  72. package/dist/{external-optimizer-subprocess-laM1-UDV.js.map → external-optimizer-subprocess-CkyUUV7h.js.map} +1 -1
  73. package/dist/fuzz.d.ts +15 -15
  74. package/dist/fuzz.d.ts.map +1 -1
  75. package/dist/{hf-dataset-CRqtSjnR.js → hf-dataset-kjIfIK_e.js} +3 -3
  76. package/dist/{hf-dataset-CRqtSjnR.js.map → hf-dataset-kjIfIK_e.js.map} +1 -1
  77. package/dist/hosted/index.d.ts +8 -8
  78. package/dist/hosted/index.d.ts.map +1 -1
  79. package/dist/hosted/index.js +1 -1
  80. package/dist/{index-D4pC7Tvd2.d.ts → index-D4pC7Tvd.d.ts} +1 -1
  81. package/dist/index-D4pC7Tvd.d.ts.map +1 -0
  82. package/dist/index-DKmrHA02.d.ts.map +1 -1
  83. package/dist/{index-DNgf5gyG2.d.ts → index-DNgf5gyG.d.ts} +1 -1
  84. package/dist/index-DNgf5gyG.d.ts.map +1 -0
  85. package/dist/index.d.ts +124 -124
  86. package/dist/index.d.ts.map +1 -1
  87. package/dist/index.js +52 -42
  88. package/dist/index.js.map +1 -1
  89. package/dist/{integrity-BFP4kjGj.js → integrity-BvnVARVl.js} +30 -29
  90. package/dist/{integrity-BFP4kjGj.js.map → integrity-BvnVARVl.js.map} +1 -1
  91. package/dist/{integrity-BvHANvnp.js → integrity-uwK7XC-8.js} +2 -2
  92. package/dist/{integrity-BvHANvnp.js.map → integrity-uwK7XC-8.js.map} +1 -1
  93. package/dist/{internal-BMFSR8Ns.js → internal-BOe3zmjQ.js} +2 -2
  94. package/dist/{internal-BMFSR8Ns.js.map → internal-BOe3zmjQ.js.map} +1 -1
  95. package/dist/{jev-review-Cu9xtIu4.js → jev-review-DZEjDzlF.js} +7 -5
  96. package/dist/{jev-review-Cu9xtIu4.js.map → jev-review-DZEjDzlF.js.map} +1 -1
  97. package/dist/jev.d.ts +10 -10
  98. package/dist/jev.d.ts.map +1 -1
  99. package/dist/jev.js +2 -2
  100. package/dist/{judge-calibration-DYmaBtJr.js → judge-calibration-C5zgtiJT.js} +2 -2
  101. package/dist/{judge-calibration-DYmaBtJr.js.map → judge-calibration-C5zgtiJT.js.map} +1 -1
  102. package/dist/kind-factory-CdPPHtGZ.js.map +1 -1
  103. package/dist/{llm-client-c_bKHTXz.js → llm-client-Bhqoglar.js} +6 -4
  104. package/dist/{llm-client-c_bKHTXz.js.map → llm-client-Bhqoglar.js.map} +1 -1
  105. package/dist/{llm-judge-CL6f3utD.js → llm-judge-C-0P1WiT.js} +26 -21
  106. package/dist/{llm-judge-CL6f3utD.js.map → llm-judge-C-0P1WiT.js.map} +1 -1
  107. package/dist/matrix/index.d.ts +1 -1
  108. package/dist/matrix/index.js +1 -1
  109. package/dist/{matrix-_NLSWsKM.d.ts → matrix--IZKROxD.d.ts} +2 -2
  110. package/dist/{matrix-_NLSWsKM.d.ts.map → matrix--IZKROxD.d.ts.map} +1 -1
  111. package/dist/{matrix-pWinRMPl.js → matrix-DnlHn5x1.js} +8 -6
  112. package/dist/{matrix-pWinRMPl.js.map → matrix-DnlHn5x1.js.map} +1 -1
  113. package/dist/meta-eval/index.d.ts +55 -55
  114. package/dist/meta-eval/index.d.ts.map +1 -1
  115. package/dist/meta-eval/index.js +4 -4
  116. package/dist/{mint-iCD-W43s.js → mint-vlRckJEX.js} +2 -2
  117. package/dist/{mint-iCD-W43s.js.map → mint-vlRckJEX.js.map} +1 -1
  118. package/dist/multishot/golden/index.d.ts +23 -23
  119. package/dist/multishot/golden/index.d.ts.map +1 -1
  120. package/dist/multishot/golden/index.js +1 -1
  121. package/dist/multishot/index.d.ts +9 -9
  122. package/dist/multishot/index.d.ts.map +1 -1
  123. package/dist/multishot/index.js +1 -1
  124. package/dist/openapi.json +1 -1
  125. package/dist/{otel-spans-CQmSxtcS.js → otel-spans-C8YIJWy1.js} +9 -4
  126. package/dist/{otel-spans-CQmSxtcS.js.map → otel-spans-C8YIJWy1.js.map} +1 -1
  127. package/dist/{outcome-store-BXlkwMPR.js → outcome-store-DUcMj-3D.js} +2 -2
  128. package/dist/{outcome-store-BXlkwMPR.js.map → outcome-store-DUcMj-3D.js.map} +1 -1
  129. package/dist/package-version-D7lQHt_-.js.map +1 -1
  130. package/dist/{paired-arms-DKZFVPt8.js → paired-arms-DpS_h8ON.js} +8 -5
  131. package/dist/{paired-arms-DKZFVPt8.js.map → paired-arms-DpS_h8ON.js.map} +1 -1
  132. package/dist/{paired-binary-fzkwENI4.js → paired-binary-OMBVRtc-.js} +2 -2
  133. package/dist/{paired-binary-fzkwENI4.js.map → paired-binary-OMBVRtc-.js.map} +1 -1
  134. package/dist/{paired-promotion-decision-D5B1Cxc2.js → paired-promotion-decision-DhrmjdV8.js} +5 -4
  135. package/dist/{paired-promotion-decision-D5B1Cxc2.js.map → paired-promotion-decision-DhrmjdV8.js.map} +1 -1
  136. package/dist/{paired-tests-C8iCsioC.js → paired-tests-Ccr16gcW.js} +3 -3
  137. package/dist/{paired-tests-C8iCsioC.js.map → paired-tests-Ccr16gcW.js.map} +1 -1
  138. package/dist/pipelines/index.d.ts +19 -19
  139. package/dist/pipelines/index.d.ts.map +1 -1
  140. package/dist/pipelines/index.js +5 -4
  141. package/dist/pipelines/index.js.map +1 -1
  142. package/dist/{power-and-mde-K_CmO3dc.js → power-and-mde-bie6i965.js} +9 -6
  143. package/dist/{power-and-mde-K_CmO3dc.js.map → power-and-mde-bie6i965.js.map} +1 -1
  144. package/dist/{produced-state-DZMW8cuF.js → produced-state-CR2tAPLf.js} +8 -5
  145. package/dist/{produced-state-DZMW8cuF.js.map → produced-state-CR2tAPLf.js.map} +1 -1
  146. package/dist/{promotion-policy-C6FAJvmZ.js → promotion-policy-BI1RxzwD.js} +4 -4
  147. package/dist/{promotion-policy-C6FAJvmZ.js.map → promotion-policy-BI1RxzwD.js.map} +1 -1
  148. package/dist/{raw-provider-sink-CXuOhLvT.js → raw-provider-sink-rB2DYxr6.js} +2 -2
  149. package/dist/{raw-provider-sink-CXuOhLvT.js.map → raw-provider-sink-rB2DYxr6.js.map} +1 -1
  150. package/dist/{release-confidence-XQm_xjhR.js → release-confidence-CiFg1EPq.js} +3 -2
  151. package/dist/{release-confidence-XQm_xjhR.js.map → release-confidence-CiFg1EPq.js.map} +1 -1
  152. package/dist/{report-command-DKJ_yAIj.js → report-command-DzPpFgjB.js} +20 -18
  153. package/dist/{report-command-DKJ_yAIj.js.map → report-command-DzPpFgjB.js.map} +1 -1
  154. package/dist/reporting.js +5 -5
  155. package/dist/{reward-hacking-D0XwhVWE.js → reward-hacking-C-a__ShZ.js} +5 -3
  156. package/dist/{reward-hacking-D0XwhVWE.js.map → reward-hacking-C-a__ShZ.js.map} +1 -1
  157. package/dist/rl.d.ts +199 -202
  158. package/dist/rl.d.ts.map +1 -1
  159. package/dist/rl.js +48 -49
  160. package/dist/rl.js.map +1 -1
  161. package/dist/rollout/index.d.ts +1 -1
  162. package/dist/rollout/index.js +5 -5
  163. package/dist/{rollout-B-XBReTC.js → rollout-BUQixCoc.js} +5 -5
  164. package/dist/{rollout-B-XBReTC.js.map → rollout-BUQixCoc.js.map} +1 -1
  165. package/dist/{rubric-predictive-validity-CCK-1B7w.js → rubric-predictive-validity-B0Pg-3I5.js} +3 -3
  166. package/dist/{rubric-predictive-validity-CCK-1B7w.js.map → rubric-predictive-validity-B0Pg-3I5.js.map} +1 -1
  167. package/dist/{run-record-tNnlQIrD.js → run-record-BB290Y9A.js} +5 -3
  168. package/dist/{run-record-tNnlQIrD.js.map → run-record-BB290Y9A.js.map} +1 -1
  169. package/dist/{schema-C1aaAxTf.js → schema-DAMp77zB.js} +24 -20
  170. package/dist/{schema-C1aaAxTf.js.map → schema-DAMp77zB.js.map} +1 -1
  171. package/dist/search/index.d.ts +34 -34
  172. package/dist/search/index.d.ts.map +1 -1
  173. package/dist/search/index.js +2 -2
  174. package/dist/{search-kernel-AVgIjXaI.js → search-kernel-Dpniloks.js} +33 -26
  175. package/dist/{search-kernel-AVgIjXaI.js.map → search-kernel-Dpniloks.js.map} +1 -1
  176. package/dist/{search-ledger-CL0-mXQ8.js → search-ledger-CXQPwdWz.js} +4 -3
  177. package/dist/{search-ledger-CL0-mXQ8.js.map → search-ledger-CXQPwdWz.js.map} +1 -1
  178. package/dist/{search-shipper-Cs6K4km9.js → search-shipper-DhhofkDX.js} +3 -6
  179. package/dist/{search-shipper-Cs6K4km9.js.map → search-shipper-DhhofkDX.js.map} +1 -1
  180. package/dist/{search-summary-DvWk0hb3.js → search-summary-C1nAHgkB.js} +4 -4
  181. package/dist/{search-summary-DvWk0hb3.js.map → search-summary-C1nAHgkB.js.map} +1 -1
  182. package/dist/{semantic-concept-judge-2SE_kXGF.js → semantic-concept-judge-BcjYg37z.js} +4 -4
  183. package/dist/{semantic-concept-judge-2SE_kXGF.js.map → semantic-concept-judge-BcjYg37z.js.map} +1 -1
  184. package/dist/{sequential-Yz3OSskl.js → sequential-DWn_np6P.js} +2 -3
  185. package/dist/{sequential-Yz3OSskl.js.map → sequential-DWn_np6P.js.map} +1 -1
  186. package/dist/{server-D56r1lhp.js → server-B4jMhqQn.js} +2 -2
  187. package/dist/{server-D56r1lhp.js.map → server-B4jMhqQn.js.map} +1 -1
  188. package/dist/{skillopt-optimization-method-B2syNik0.js → skillopt-optimization-method-Bls9t-G_.js} +9 -9
  189. package/dist/{skillopt-optimization-method-B2syNik0.js.map → skillopt-optimization-method-Bls9t-G_.js.map} +1 -1
  190. package/dist/{statistical-heldout-BAFDCo07.js → statistical-heldout-CNLOvRq_.js} +3 -3
  191. package/dist/{statistical-heldout-BAFDCo07.js.map → statistical-heldout-CNLOvRq_.js.map} +1 -1
  192. package/dist/statistical-heldout-HswMvzbP.d.ts.map +1 -1
  193. package/dist/{store-DNe_Uv1Q.js → store-BhNuLdJw.js} +3 -5
  194. package/dist/{store-DNe_Uv1Q.js.map → store-BhNuLdJw.js.map} +1 -1
  195. package/dist/store-C4avFjIi.d.ts.map +1 -1
  196. package/dist/{store-otlp-BPowgPm6.js → store-otlp-yd9lDziN.js} +2 -2
  197. package/dist/{store-otlp-BPowgPm6.js.map → store-otlp-yd9lDziN.js.map} +1 -1
  198. package/dist/{store-tool-spans-BaGakFc2.js → store-tool-spans-Biio4_Nw.js} +4 -4
  199. package/dist/{store-tool-spans-BaGakFc2.js.map → store-tool-spans-Biio4_Nw.js.map} +1 -1
  200. package/dist/storyboard/index.d.ts +20 -21
  201. package/dist/storyboard/index.d.ts.map +1 -1
  202. package/dist/{student-t-BA-Uy51p.js → student-t-BBZYka0E.js} +4 -3
  203. package/dist/{student-t-BA-Uy51p.js.map → student-t-BBZYka0E.js.map} +1 -1
  204. package/dist/{summary-report-BeYnvddy.js → summary-report-DLzptLSA.js} +8 -7
  205. package/dist/{summary-report-BeYnvddy.js.map → summary-report-DLzptLSA.js.map} +1 -1
  206. package/dist/supervisor-run/index.d.ts +25 -25
  207. package/dist/supervisor-run/index.d.ts.map +1 -1
  208. package/dist/supervisor-run/index.js +2 -2
  209. package/dist/{tool-waste-CJDfxH45.js → tool-waste-B-u3rzCz.js} +11 -6
  210. package/dist/{tool-waste-CJDfxH45.js.map → tool-waste-B-u3rzCz.js.map} +1 -1
  211. package/dist/trace-repair/index.d.ts +96 -96
  212. package/dist/trace-repair/index.d.ts.map +1 -1
  213. package/dist/trace-repair/index.js +1 -1
  214. package/dist/trace-repair/index.js.map +1 -1
  215. package/dist/traces.d.ts +29 -29
  216. package/dist/traces.d.ts.map +1 -1
  217. package/dist/traces.js +9 -7
  218. package/dist/traces.js.map +1 -1
  219. package/dist/trajectory-replay/index.d.ts +35 -35
  220. package/dist/trajectory-replay/index.d.ts.map +1 -1
  221. package/dist/trajectory-replay/index.js +5 -5
  222. package/dist/trajectory-replay/index.js.map +1 -1
  223. package/dist/{tree-Ki_gW7z8.js → tree-D48IJUK0.js} +39 -31
  224. package/dist/{tree-Ki_gW7z8.js.map → tree-D48IJUK0.js.map} +1 -1
  225. package/dist/wire/index.d.ts +48 -48
  226. package/dist/wire/index.d.ts.map +1 -1
  227. package/dist/wire/index.js +1 -1
  228. package/docs/jev-behavior-review.md +4 -3
  229. package/package.json +18 -36
  230. package/dist/index-D4pC7Tvd2.d.ts.map +0 -1
  231. package/dist/index-DNgf5gyG2.d.ts.map +0 -1
@@ -3,7 +3,7 @@ import { i as modelHasSnapshot, l as searchCellRunId } from "./run-record-BRlM99
3
3
  import { n as MemoryLedgerJournal, r as replayLedgerText, t as FileLedgerJournal } from "./journal-DvKCvjty.js";
4
4
  import "./ledger-core/index.js";
5
5
  import { a as SearchLedgerError, i as SearchLedgerConflictError, o as SearchLedgerIntegrityError, t as SEARCH_LEDGER_FILE_CONTEXT } from "./search-ledger-file-DY0AXX3W.js";
6
- import { n as evaluationClaimSchema } from "./claim-V9Zqbq0J.js";
6
+ import { n as evaluationClaimSchema } from "./claim-BXcZw-jo.js";
7
7
  import { createHash } from "node:crypto";
8
8
  import { z } from "zod";
9
9
  //#region src/campaign/search-ledger-ordering.ts
@@ -1535,7 +1535,8 @@ function parseSearchLedgerEntry(raw, context) {
1535
1535
  const parsed = EntrySchema.safeParse(raw);
1536
1536
  if (!parsed.success) throw new SearchLedgerIntegrityError(`search ledger ${context.path} has a malformed entry at line ${context.line}: ${formatZodError(parsed.error)}`);
1537
1537
  const entry = parsed.data;
1538
- if (canonicalString(validateSearchLedgerEvent(entry.event)) !== canonicalString(entry.event)) throw new SearchLedgerIntegrityError(`search ledger ${context.path} has non-canonical event ordering at line ${context.line}`);
1538
+ const normalizedEvent = validateSearchLedgerEvent(entry.event);
1539
+ if (canonicalString(normalizedEvent) !== canonicalString(entry.event)) throw new SearchLedgerIntegrityError(`search ledger ${context.path} has non-canonical event ordering at line ${context.line}`);
1539
1540
  return entry;
1540
1541
  }
1541
1542
  function normalizeEvent(event) {
@@ -1591,4 +1592,4 @@ function formatZodError(error) {
1591
1592
  //#endregion
1592
1593
  export { validateSearchLedgerEvent as a, SearchStateView as c, searchTaskSetDigest as d, searchUnitScores as f, replaySearchLedgerText as i, searchCellId as l, openSearchLedger as n, SEARCH_LEDGER_SCHEMA as o, parseSearchLedgerLine as r, SearchState as s, FileSearchLedger as t, searchNodeId as u };
1593
1594
 
1594
- //# sourceMappingURL=search-ledger-CL0-mXQ8.js.map
1595
+ //# sourceMappingURL=search-ledger-CXQPwdWz.js.map