@tangle-network/agent-eval 0.223.0 → 1.0.1

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 (219) hide show
  1. package/CHANGELOG.md +219 -0
  2. package/README.md +2 -1
  3. package/dist/adapters/http.d.ts +2 -2
  4. package/dist/{agreement-irr-BTjDN0i6.js → agreement-irr-w-t3XUTD.js} +2 -2
  5. package/dist/{agreement-irr-BTjDN0i6.js.map → agreement-irr-w-t3XUTD.js.map} +1 -1
  6. package/dist/analyst/index.d.ts +7 -7
  7. package/dist/analyst/index.js +11 -11
  8. package/dist/{analyze-runs-C-pP1sK9.d.ts → analyze-runs-BYyMShsj.d.ts} +2 -2
  9. package/dist/{analyze-runs-C-pP1sK9.d.ts.map → analyze-runs-BYyMShsj.d.ts.map} +1 -1
  10. package/dist/{analyze-runs-Ck68mbgj.js → analyze-runs-Da7P_Mc5.js} +9 -10
  11. package/dist/{analyze-runs-Ck68mbgj.js.map → analyze-runs-Da7P_Mc5.js.map} +1 -1
  12. package/dist/{benchmark-command-CH86twZj.js → benchmark-command-BeDZB3BQ.js} +11 -11
  13. package/dist/{benchmark-command-CH86twZj.js.map → benchmark-command-BeDZB3BQ.js.map} +1 -1
  14. package/dist/benchmarks/index.d.ts +4 -4
  15. package/dist/benchmarks/index.js +5 -5
  16. package/dist/builder-eval/index.js +1 -1
  17. package/dist/{calibration-6usfVYYo.js → calibration-DLzckXnn.js} +2 -2
  18. package/dist/{calibration-6usfVYYo.js.map → calibration-DLzckXnn.js.map} +1 -1
  19. package/dist/campaign/index.d.ts +5 -5
  20. package/dist/campaign/index.js +10 -10
  21. package/dist/{campaign-DdOgQfp8.js → campaign-DKZiYHUq.js} +15 -15
  22. package/dist/{campaign-DdOgQfp8.js.map → campaign-DKZiYHUq.js.map} +1 -1
  23. package/dist/{campaign-evidence-MjCjkb5a.js → campaign-evidence-BICB3a9Z.js} +3 -3
  24. package/dist/{campaign-evidence-MjCjkb5a.js.map → campaign-evidence-BICB3a9Z.js.map} +1 -1
  25. package/dist/{chat-client-CO3uB33i.js → chat-client-D0me8iwq.js} +2 -2
  26. package/dist/{chat-client-CO3uB33i.js.map → chat-client-D0me8iwq.js.map} +1 -1
  27. package/dist/{chat-json-call-8yUv4LFO.js → chat-json-call-C473CwTt.js} +2 -2
  28. package/dist/{chat-json-call-8yUv4LFO.js.map → chat-json-call-C473CwTt.js.map} +1 -1
  29. package/dist/cli.js +7 -7
  30. package/dist/{cluster-bootstrap-SbaeM44s.js → cluster-bootstrap-hNXESoc1.js} +2 -2
  31. package/dist/{cluster-bootstrap-SbaeM44s.js.map → cluster-bootstrap-hNXESoc1.js.map} +1 -1
  32. package/dist/{completion-verifier-rqbMh5-4.js → completion-verifier-ClmJV_Yc.js} +2 -2
  33. package/dist/{completion-verifier-rqbMh5-4.js.map → completion-verifier-ClmJV_Yc.js.map} +1 -1
  34. package/dist/contract/index.d.ts +8 -8
  35. package/dist/contract/index.js +13 -13
  36. package/dist/{decision-point-lhMgODOR.js → decision-point-CErE7GnP.js} +6 -6
  37. package/dist/decision-point-CErE7GnP.js.map +1 -0
  38. package/dist/{default-registry-B1DstPYg.d.ts → default-registry-DKlKVXMx.d.ts} +22 -6
  39. package/dist/default-registry-DKlKVXMx.d.ts.map +1 -0
  40. package/dist/{default-registry-C1tPEjZ4.js → default-registry-gmDeN0KT.js} +38 -7
  41. package/dist/default-registry-gmDeN0KT.js.map +1 -0
  42. package/dist/{define-agent-eval-CAffiFbN.d.ts → define-agent-eval-B9zPWFSK.d.ts} +6 -6
  43. package/dist/{define-agent-eval-CAffiFbN.d.ts.map → define-agent-eval-B9zPWFSK.d.ts.map} +1 -1
  44. package/dist/{define-agent-eval-Cc15qGik.js → define-agent-eval-BVhGn7VV.js} +6 -6
  45. package/dist/{define-agent-eval-Cc15qGik.js.map → define-agent-eval-BVhGn7VV.js.map} +1 -1
  46. package/dist/{descriptive-cPwITVfy.js → descriptive-BTzLL-aj.js} +46 -3
  47. package/dist/descriptive-BTzLL-aj.js.map +1 -0
  48. package/dist/diagnosis/index.d.ts +2 -2
  49. package/dist/diagnosis/index.js +2 -2
  50. package/dist/{dspy-rlm-engine-jDiWkul6.js → dspy-rlm-engine-C0zR2xiM.js} +2 -2
  51. package/dist/{dspy-rlm-engine-jDiWkul6.js.map → dspy-rlm-engine-C0zR2xiM.js.map} +1 -1
  52. package/dist/{eval-campaign-C_mNDshv.js → eval-campaign-DVqiBoXR.js} +3 -3
  53. package/dist/{eval-campaign-C_mNDshv.js.map → eval-campaign-DVqiBoXR.js.map} +1 -1
  54. package/dist/{evaluation-BPqUvZ66.d.ts → evaluation-B0-KVXaV.d.ts} +4 -2
  55. package/dist/evaluation-B0-KVXaV.d.ts.map +1 -0
  56. package/dist/{evaluation-B8H3GYej.js → evaluation-BBI37mRe.js} +2 -1
  57. package/dist/evaluation-BBI37mRe.js.map +1 -0
  58. package/dist/evaluation.d.ts +1 -1
  59. package/dist/evaluation.js +1 -1
  60. package/dist/{exact-types-D98BKpxo.d.ts → exact-types-CIViGj98.d.ts} +3 -3
  61. package/dist/{exact-types-D98BKpxo.d.ts.map → exact-types-CIViGj98.d.ts.map} +1 -1
  62. package/dist/experiment/index.d.ts +1 -1
  63. package/dist/experiment/index.js +9 -8
  64. package/dist/experiment/index.js.map +1 -1
  65. package/dist/{exporters-B5Ze_RKh.d.ts → exporters-BYBG9b1n.d.ts} +2 -2
  66. package/dist/{exporters-B5Ze_RKh.d.ts.map → exporters-BYBG9b1n.d.ts.map} +1 -1
  67. package/dist/{external-optimizer-process-BRVmaDFe.js → external-optimizer-process-DKgrrX0J.js} +2 -2
  68. package/dist/{external-optimizer-process-BRVmaDFe.js.map → external-optimizer-process-DKgrrX0J.js.map} +1 -1
  69. package/dist/{external-optimizer-subprocess-U616hV_l.js → external-optimizer-subprocess-wzMaA0oN.js} +2 -2
  70. package/dist/{external-optimizer-subprocess-U616hV_l.js.map → external-optimizer-subprocess-wzMaA0oN.js.map} +1 -1
  71. package/dist/{feedback-trajectory-SBGncrCP.d.ts → feedback-trajectory-Ck7K7AhK.d.ts} +2 -2
  72. package/dist/{feedback-trajectory-SBGncrCP.d.ts.map → feedback-trajectory-Ck7K7AhK.d.ts.map} +1 -1
  73. package/dist/{findings-store-B75Dspaq.js → findings-store-DNSvmy8U.js} +4 -4
  74. package/dist/{findings-store-B75Dspaq.js.map → findings-store-DNSvmy8U.js.map} +1 -1
  75. package/dist/fuzz.js +1 -1
  76. package/dist/{index-CUjeTDPv.d.ts → index-Bn-P_XAl.d.ts} +4 -4
  77. package/dist/{index-CUjeTDPv.d.ts.map → index-Bn-P_XAl.d.ts.map} +1 -1
  78. package/dist/{index-B7v2QHlD.d.ts → index-BwutH5i7.d.ts} +4 -4
  79. package/dist/{index-B7v2QHlD.d.ts.map → index-BwutH5i7.d.ts.map} +1 -1
  80. package/dist/{index-aDPVYBIM.d.ts → index-ByJ20lyu.d.ts} +7 -7
  81. package/dist/{index-aDPVYBIM.d.ts.map → index-ByJ20lyu.d.ts.map} +1 -1
  82. package/dist/{index-DUn0GNiZ.d.ts → index-CtcCSO1Y.d.ts} +4 -4
  83. package/dist/{index-DUn0GNiZ.d.ts.map → index-CtcCSO1Y.d.ts.map} +1 -1
  84. package/dist/index.d.ts +17 -17
  85. package/dist/index.js +38 -43
  86. package/dist/index.js.map +1 -1
  87. package/dist/{judge-calibration-DGqlfWW8.js → judge-calibration-D93UCm1k.js} +2 -2
  88. package/dist/{judge-calibration-DGqlfWW8.js.map → judge-calibration-D93UCm1k.js.map} +1 -1
  89. package/dist/{judge-gate-Di_6bifh.js → judge-gate-C9sLLJ-v.js} +3 -3
  90. package/dist/{judge-gate-Di_6bifh.js.map → judge-gate-C9sLLJ-v.js.map} +1 -1
  91. package/dist/kind-factory-VKysp1ds.js.map +1 -1
  92. package/dist/{llm-client-kJ9EOqjt.js → llm-client-BdSiZ4qz.js} +2 -2
  93. package/dist/{llm-client-kJ9EOqjt.js.map → llm-client-BdSiZ4qz.js.map} +1 -1
  94. package/dist/{llm-judge-D6JtIqiU.js → llm-judge-BYBLxREr.js} +14 -14
  95. package/dist/{llm-judge-D6JtIqiU.js.map → llm-judge-BYBLxREr.js.map} +1 -1
  96. package/dist/{matrix-CBUzIZs4.d.ts → matrix-4DcRFJ7Q.d.ts} +2 -2
  97. package/dist/{matrix-CBUzIZs4.d.ts.map → matrix-4DcRFJ7Q.d.ts.map} +1 -1
  98. package/dist/{internal-v6XfOeJW.js → mean-DDFhslBt.js} +48 -2
  99. package/dist/mean-DDFhslBt.js.map +1 -0
  100. package/dist/meta-eval/index.js +7 -7
  101. package/dist/multishot/golden/index.d.ts +1 -1
  102. package/dist/multishot/index.d.ts +2 -2
  103. package/dist/openapi.json +1 -1
  104. package/dist/{outcome-observations-D4snOtUb.js → outcome-observations-ahbNtxuP.js} +3 -3
  105. package/dist/{outcome-observations-D4snOtUb.js.map → outcome-observations-ahbNtxuP.js.map} +1 -1
  106. package/dist/{paired-arms-D5H_58e8.js → paired-arms-C0Vd9bGG.js} +4 -4
  107. package/dist/{paired-arms-D5H_58e8.js.map → paired-arms-C0Vd9bGG.js.map} +1 -1
  108. package/dist/{paired-binary-BR0nwHOA.js → paired-binary-B477lksS.js} +2 -2
  109. package/dist/{paired-binary-BR0nwHOA.js.map → paired-binary-B477lksS.js.map} +1 -1
  110. package/dist/{paired-promotion-decision-BiVumgvM.js → paired-promotion-decision-5Pl_qJLX.js} +3 -3
  111. package/dist/{paired-promotion-decision-BiVumgvM.js.map → paired-promotion-decision-5Pl_qJLX.js.map} +1 -1
  112. package/dist/{paired-tests-C2zUqgUW.js → paired-tests-kASEKpc-.js} +3 -37
  113. package/dist/paired-tests-kASEKpc-.js.map +1 -0
  114. package/dist/{pareto-7_LEmYGG.js → pareto-DY_x3HHg.js} +7 -7
  115. package/dist/{pareto-7_LEmYGG.js.map → pareto-DY_x3HHg.js.map} +1 -1
  116. package/dist/pipelines/index.d.ts +1 -1
  117. package/dist/pipelines/index.js +1 -1
  118. package/dist/{power-and-mde-CHvyDO_H.js → power-and-mde-CRxepy8y.js} +3 -3
  119. package/dist/{power-and-mde-CHvyDO_H.js.map → power-and-mde-CRxepy8y.js.map} +1 -1
  120. package/dist/{promotion-policy-D7B4_jEZ.js → promotion-policy-f79oklG_.js} +4 -4
  121. package/dist/{promotion-policy-D7B4_jEZ.js.map → promotion-policy-f79oklG_.js.map} +1 -1
  122. package/dist/{proposal-findings-WFQrxnfe.js → proposal-findings-duV5flPv.js} +2 -2
  123. package/dist/{proposal-findings-WFQrxnfe.js.map → proposal-findings-duV5flPv.js.map} +1 -1
  124. package/dist/{raw-provider-sink-DDLkP_eF.js → raw-provider-sink-RbaEv2vB.js} +2 -2
  125. package/dist/{raw-provider-sink-DDLkP_eF.js.map → raw-provider-sink-RbaEv2vB.js.map} +1 -1
  126. package/dist/{redact-C_wzC4c_.d.ts → redact-jrT0APTU.d.ts} +50 -35
  127. package/dist/redact-jrT0APTU.d.ts.map +1 -0
  128. package/dist/{redact-D6APJS1d.js → redact-zp_ILC4l.js} +92 -33
  129. package/dist/redact-zp_ILC4l.js.map +1 -0
  130. package/dist/redaction.d.ts +2 -0
  131. package/dist/redaction.js +1 -0
  132. package/dist/{registry-dhdDoAV8.d.ts → registry-CMtGAxOw.d.ts} +2 -2
  133. package/dist/{registry-dhdDoAV8.d.ts.map → registry-CMtGAxOw.d.ts.map} +1 -1
  134. package/dist/{release-confidence-CTUJz5mM.js → release-confidence--1iP-d3x.js} +2 -2
  135. package/dist/{release-confidence-CTUJz5mM.js.map → release-confidence--1iP-d3x.js.map} +1 -1
  136. package/dist/{render-pfAZ7IR4.js → render-aB58Be3N.js} +2 -2
  137. package/dist/{render-pfAZ7IR4.js.map → render-aB58Be3N.js.map} +1 -1
  138. package/dist/reporting.js +5 -5
  139. package/dist/{reward-hacking-Bjk3MAjh.js → reward-hacking-D-Vi9-fE.js} +3 -3
  140. package/dist/{reward-hacking-Bjk3MAjh.js.map → reward-hacking-D-Vi9-fE.js.map} +1 -1
  141. package/dist/rl.d.ts +3 -3
  142. package/dist/rl.js +9 -9
  143. package/dist/rollout/index.d.ts +4 -4
  144. package/dist/rollout/index.js +1 -1
  145. package/dist/{rollout-BhkMpAJT.js → rollout-BC4u-d_I.js} +3 -3
  146. package/dist/{rollout-BhkMpAJT.js.map → rollout-BC4u-d_I.js.map} +1 -1
  147. package/dist/{rubric-predictive-validity-CQp_M0vy.js → rubric-predictive-validity-BdxXDN6h.js} +2 -2
  148. package/dist/{rubric-predictive-validity-CQp_M0vy.js.map → rubric-predictive-validity-BdxXDN6h.js.map} +1 -1
  149. package/dist/{run-record-BUm-Jggo.js → run-record-B-G2Tu11.js} +2 -2
  150. package/dist/{run-record-BUm-Jggo.js.map → run-record-B-G2Tu11.js.map} +1 -1
  151. package/dist/{schema-DkFJr3Y8.d.ts → schema-CfoA9U_U.d.ts} +28 -2
  152. package/dist/schema-CfoA9U_U.d.ts.map +1 -0
  153. package/dist/search/index.d.ts +2 -2
  154. package/dist/search/index.js +2 -2
  155. package/dist/{search-kernel-CBdwFZ05.d.ts → search-kernel-BjR2Sr7w.d.ts} +2 -2
  156. package/dist/{search-kernel-CBdwFZ05.d.ts.map → search-kernel-BjR2Sr7w.d.ts.map} +1 -1
  157. package/dist/{search-summary-Bt3uuK53.js → search-summary-DedyTdiM.js} +4 -4
  158. package/dist/{search-summary-Bt3uuK53.js.map → search-summary-DedyTdiM.js.map} +1 -1
  159. package/dist/{sequential-De7BTAlV.js → sequential-Zp1tsxqI.js} +2 -2
  160. package/dist/{sequential-De7BTAlV.js.map → sequential-Zp1tsxqI.js.map} +1 -1
  161. package/dist/{server-DA6h3co5.js → server-CPKyf3bz.js} +2 -2
  162. package/dist/{server-DA6h3co5.js.map → server-CPKyf3bz.js.map} +1 -1
  163. package/dist/{skillopt-optimization-method-BKFbJEyz.js → skillopt-optimization-method-DmfZz-2d.js} +9 -9
  164. package/dist/{skillopt-optimization-method-BKFbJEyz.js.map → skillopt-optimization-method-DmfZz-2d.js.map} +1 -1
  165. package/dist/{spans-vZoW__3q.d.ts → spans-CGjHouKM.d.ts} +2 -2
  166. package/dist/{spans-vZoW__3q.d.ts.map → spans-CGjHouKM.d.ts.map} +1 -1
  167. package/dist/{statistical-heldout-C9hz_AF9.js → statistical-heldout-DYF5f10K.js} +3 -3
  168. package/dist/{statistical-heldout-C9hz_AF9.js.map → statistical-heldout-DYF5f10K.js.map} +1 -1
  169. package/dist/{statistical-heldout-Cei036nE.d.ts → statistical-heldout-bU7FBNjR.d.ts} +2 -2
  170. package/dist/{statistical-heldout-Cei036nE.d.ts.map → statistical-heldout-bU7FBNjR.d.ts.map} +1 -1
  171. package/dist/{store-tool-spans-C2g8UYm-.js → store-tool-spans-GGaCijFy.js} +19 -62
  172. package/dist/store-tool-spans-GGaCijFy.js.map +1 -0
  173. package/dist/{store-tool-spans-B3i3fl0A.d.ts → store-tool-spans-lWf6INTH.d.ts} +3 -44
  174. package/dist/store-tool-spans-lWf6INTH.d.ts.map +1 -0
  175. package/dist/{summary-report-BLnTyQKH.js → summary-report-BstMpOfy.js} +6 -7
  176. package/dist/{summary-report-BLnTyQKH.js.map → summary-report-BstMpOfy.js.map} +1 -1
  177. package/dist/supervisor-run/index.d.ts +2 -2
  178. package/dist/supervisor-run/index.js +1 -1
  179. package/dist/{systemone-Cw2txK5m.d.ts → systemone-BDVgb6XV.d.ts} +7 -9
  180. package/dist/systemone-BDVgb6XV.d.ts.map +1 -0
  181. package/dist/systemone.d.ts +2 -2
  182. package/dist/systemone.js +2 -2
  183. package/dist/{tool-waste-CLJ46AbT.js → tool-waste-CRJqOASv.js} +3 -3
  184. package/dist/{tool-waste-CLJ46AbT.js.map → tool-waste-CRJqOASv.js.map} +1 -1
  185. package/dist/trace-repair/index.js +2 -2
  186. package/dist/traces.d.ts +18 -39
  187. package/dist/traces.d.ts.map +1 -1
  188. package/dist/traces.js +51 -57
  189. package/dist/traces.js.map +1 -1
  190. package/dist/{tree-DnBkWXun.js → tree-C2N31CoI.js} +5 -6
  191. package/dist/{tree-DnBkWXun.js.map → tree-C2N31CoI.js.map} +1 -1
  192. package/dist/{types-C54Uk_a1.d.ts → types-BF-xQGQn.d.ts} +2 -2
  193. package/dist/{types-C54Uk_a1.d.ts.map → types-BF-xQGQn.d.ts.map} +1 -1
  194. package/dist/{types-C-aOqgt2.d.ts → types-DNB9hIXa.d.ts} +2 -2
  195. package/dist/{types-C-aOqgt2.d.ts.map → types-DNB9hIXa.d.ts.map} +1 -1
  196. package/dist/{types-0oMg7zee.d.ts → types-yofaDmQa.d.ts} +2 -2
  197. package/dist/{types-0oMg7zee.d.ts.map → types-yofaDmQa.d.ts.map} +1 -1
  198. package/dist/wire/index.d.ts +7 -7
  199. package/dist/wire/index.js +1 -1
  200. package/docs/design/statistics-decisions.md +1 -0
  201. package/docs/redaction.md +24 -1
  202. package/docs/systemone.md +6 -0
  203. package/package.json +10 -5
  204. package/dist/decision-point-lhMgODOR.js.map +0 -1
  205. package/dist/default-registry-B1DstPYg.d.ts.map +0 -1
  206. package/dist/default-registry-C1tPEjZ4.js.map +0 -1
  207. package/dist/descriptive-cPwITVfy.js.map +0 -1
  208. package/dist/evaluation-B8H3GYej.js.map +0 -1
  209. package/dist/evaluation-BPqUvZ66.d.ts.map +0 -1
  210. package/dist/internal-v6XfOeJW.js.map +0 -1
  211. package/dist/mean-BPuUNznQ.js +0 -16
  212. package/dist/mean-BPuUNznQ.js.map +0 -1
  213. package/dist/paired-tests-C2zUqgUW.js.map +0 -1
  214. package/dist/redact-C_wzC4c_.d.ts.map +0 -1
  215. package/dist/redact-D6APJS1d.js.map +0 -1
  216. package/dist/schema-DkFJr3Y8.d.ts.map +0 -1
  217. package/dist/store-tool-spans-B3i3fl0A.d.ts.map +0 -1
  218. package/dist/store-tool-spans-C2g8UYm-.js.map +0 -1
  219. package/dist/systemone-Cw2txK5m.d.ts.map +0 -1
@@ -1,9 +1,9 @@
1
1
  import { t as AgentEvalError } from "./errors-DeEEV9Vx.js";
2
2
  import { a as hashCanonical, i as compareCodeUnits, r as canonicalString } from "./canonical-CicJlINA.js";
3
- import { n as aggregatePairedHoldout, o as pairHoldout } from "./statistical-heldout-C9hz_AF9.js";
3
+ import { n as aggregatePairedHoldout, o as pairHoldout } from "./statistical-heldout-DYF5f10K.js";
4
4
  import { t as FileLedgerJournal } from "./journal-C1uLJi0w.js";
5
5
  import { n as contentHash } from "./verdict-cache-BVH-fl18.js";
6
- import { r as projectCampaignCellQuality } from "./run-record-BUm-Jggo.js";
6
+ import { r as projectCampaignCellQuality } from "./run-record-B-G2Tu11.js";
7
7
  import { l as surfaceHash, o as renderSurfaceDiff, s as surfaceContentHash, t as autoCloseTruncatedJson, u as surfaceHashMatches } from "./json-recovery-DK4MDm5r.js";
8
8
  import { t as defineEvaluationClaim } from "./claim-Dod_mjk3.js";
9
9
  import { createHash } from "node:crypto";
@@ -1428,4 +1428,4 @@ function createCampaignEvidenceReceipt(input) {
1428
1428
  }
1429
1429
  export { campaignSplitDigest as A, assertRealBackend as C, assertCompleteCampaign as D, assertCampaignSplitIdentity as E, formatCoverageFailures as M, campaignCoverage as O, BackendIntegrityError as S, assertCampaignDesign as T, parseReflectionResponse as _, ATTESTATION_ALGORITHM as a, FinalEvidenceError as b, campaignMeasurementDigest as c, loopProvenanceArgsFromResult as d, campaignBreakdown as f, buildReflectionPrompt as g, pairedCampaignComposites as h, verifyEvidenceReceipt as i, campaignSplitDigestFromIdentities as j, campaignScenarioIdentity as k, canonicalDigest as l, campaignMeanCompositeOrNull as m, createEvidenceReceipt as n, attest as o, campaignMeanComposite as p, isIndependentEvidence as r, verifyAttestation as s, createCampaignEvidenceReceipt as t, emitLoopProvenance as u, powerPreflight as v, summarizeBackendIntegrity as w, openFinalEvidenceLedger as x, FinalEvidenceConflictError as y };
1430
1430
 
1431
- //# sourceMappingURL=campaign-evidence-MjCjkb5a.js.map
1431
+ //# sourceMappingURL=campaign-evidence-BICB3a9Z.js.map