@tangle-network/agent-eval 0.172.1 → 0.173.0

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 (219) hide show
  1. package/CHANGELOG.md +19 -0
  2. package/README.md +17 -2
  3. package/dist/adapters/http.d.ts +2 -2
  4. package/dist/analyst/index.d.ts +13 -13
  5. package/dist/analyst/index.js +7 -6
  6. package/dist/analyst/index.js.map +1 -1
  7. package/dist/{attestation-CJBGmMVh.d.ts → attestation-c1QvaBdX.d.ts} +2 -2
  8. package/dist/{attestation-CJBGmMVh.d.ts.map → attestation-c1QvaBdX.d.ts.map} +1 -1
  9. package/dist/{backend-integrity-e79K3UPD.d.ts → backend-integrity-CeuTgqsd.d.ts} +3 -4
  10. package/dist/backend-integrity-CeuTgqsd.d.ts.map +1 -0
  11. package/dist/{benchmark-h-h4bfqj.d.ts → benchmark-BjLGkfnN.d.ts} +3 -3
  12. package/dist/{benchmark-h-h4bfqj.d.ts.map → benchmark-BjLGkfnN.d.ts.map} +1 -1
  13. package/dist/{benchmark-command--qeZUHbu.js → benchmark-command-9S20PRel.js} +9 -9
  14. package/dist/{benchmark-command--qeZUHbu.js.map → benchmark-command-9S20PRel.js.map} +1 -1
  15. package/dist/benchmarks/index.d.ts +5 -5
  16. package/dist/benchmarks/index.js +3 -3
  17. package/dist/{bounded-process-VIi0KSL2.js → bounded-process-BBZob7vl.js} +30 -7
  18. package/dist/bounded-process-BBZob7vl.js.map +1 -0
  19. package/dist/builder-eval/index.d.ts +3 -3
  20. package/dist/builder-eval/index.js +2 -2
  21. package/dist/campaign/index.d.ts +9 -9
  22. package/dist/campaign/index.js +6 -6
  23. package/dist/{campaign-Dp35pBbS.js → campaign-pxS0wmo4.js} +8 -8
  24. package/dist/{campaign-Dp35pBbS.js.map → campaign-pxS0wmo4.js.map} +1 -1
  25. package/dist/chat-client-Db4bqYfA.js +115 -0
  26. package/dist/chat-client-Db4bqYfA.js.map +1 -0
  27. package/dist/{chat-json-call-5Jxna-aV.js → chat-json-call-C26igCih.js} +16 -6
  28. package/dist/chat-json-call-C26igCih.js.map +1 -0
  29. package/dist/cli.js +31 -17
  30. package/dist/cli.js.map +1 -1
  31. package/dist/{client-BvwNkIRN.js → client-BlLY6o2w.js} +2 -2
  32. package/dist/{client-BvwNkIRN.js.map → client-BlLY6o2w.js.map} +1 -1
  33. package/dist/{client-Df7wdslk.d.ts → client-DlqdbM7n.d.ts} +4 -4
  34. package/dist/{client-Df7wdslk.d.ts.map → client-DlqdbM7n.d.ts.map} +1 -1
  35. package/dist/contract/index.d.ts +13 -13
  36. package/dist/contract/index.js +202 -10
  37. package/dist/contract/index.js.map +1 -1
  38. package/dist/{counterfactual-Bee5_BIn.d.ts → counterfactual-CLgrwhkY.d.ts} +4 -4
  39. package/dist/{counterfactual-Bee5_BIn.d.ts.map → counterfactual-CLgrwhkY.d.ts.map} +1 -1
  40. package/dist/{chat-client-DI79OPye.js → default-registry-B0bKikCb.js} +3 -39
  41. package/dist/default-registry-B0bKikCb.js.map +1 -0
  42. package/dist/{default-registry-XxedTLwu.d.ts → default-registry-BKwc8bN5.d.ts} +6 -6
  43. package/dist/{default-registry-XxedTLwu.d.ts.map → default-registry-BKwc8bN5.d.ts.map} +1 -1
  44. package/dist/{define-agent-eval-0wW7gFhr.d.ts → define-agent-eval-CY6qdlGV.d.ts} +6 -6
  45. package/dist/{define-agent-eval-0wW7gFhr.d.ts.map → define-agent-eval-CY6qdlGV.d.ts.map} +1 -1
  46. package/dist/{define-agent-eval-jS8xj_Q_.js → define-agent-eval-D_i_s69h.js} +7 -7
  47. package/dist/{define-agent-eval-jS8xj_Q_.js.map → define-agent-eval-D_i_s69h.js.map} +1 -1
  48. package/dist/{dspy-rlm-engine-CS3qcCEk.js → dspy-rlm-engine-D5byiHn9.js} +5 -6
  49. package/dist/dspy-rlm-engine-D5byiHn9.js.map +1 -0
  50. package/dist/{emitter-Bvnu0VzL.d.ts → emitter-Cs0egaFd.d.ts} +3 -3
  51. package/dist/{emitter-Bvnu0VzL.d.ts.map → emitter-Cs0egaFd.d.ts.map} +1 -1
  52. package/dist/{engine-BfRay1qD.d.ts → engine-DhFir3Ys.d.ts} +23 -8
  53. package/dist/{engine-BfRay1qD.d.ts.map → engine-DhFir3Ys.d.ts.map} +1 -1
  54. package/dist/{eval-campaign-JDTeE6Pl.js → eval-campaign-BeAjdhzC.js} +2 -2
  55. package/dist/{eval-campaign-JDTeE6Pl.js.map → eval-campaign-BeAjdhzC.js.map} +1 -1
  56. package/dist/{exact-types-BEecmnWm.d.ts → exact-types-BKOEILRP.d.ts} +2 -2
  57. package/dist/{exact-types-BEecmnWm.d.ts.map → exact-types-BKOEILRP.d.ts.map} +1 -1
  58. package/dist/experiment/index.d.ts +4 -4
  59. package/dist/{external-optimizer-contracts-szBJ_1vh.d.ts → external-optimizer-contracts-CQCpyrIL.d.ts} +2 -2
  60. package/dist/{external-optimizer-contracts-szBJ_1vh.d.ts.map → external-optimizer-contracts-CQCpyrIL.d.ts.map} +1 -1
  61. package/dist/{external-optimizer-process-CQxylYeG.js → external-optimizer-process-Cq_Pg15r.js} +2 -2
  62. package/dist/{external-optimizer-process-CQxylYeG.js.map → external-optimizer-process-Cq_Pg15r.js.map} +1 -1
  63. package/dist/{external-optimizer-subprocess-Cex8Da2i.js → external-optimizer-subprocess-DgNebftP.js} +2 -2
  64. package/dist/{external-optimizer-subprocess-Cex8Da2i.js.map → external-optimizer-subprocess-DgNebftP.js.map} +1 -1
  65. package/dist/failure-cluster-OldNRoAt.d.ts +154 -0
  66. package/dist/failure-cluster-OldNRoAt.d.ts.map +1 -0
  67. package/dist/{feedback-trajectory-DIqpCyF0.d.ts → feedback-trajectory-CMnv_uYs.d.ts} +6 -6
  68. package/dist/{feedback-trajectory-DIqpCyF0.d.ts.map → feedback-trajectory-CMnv_uYs.d.ts.map} +1 -1
  69. package/dist/{heldout-gate-JgNRDZwZ.d.ts → heldout-gate-Df5hsqmm.d.ts} +7 -7
  70. package/dist/{heldout-gate-JgNRDZwZ.d.ts.map → heldout-gate-Df5hsqmm.d.ts.map} +1 -1
  71. package/dist/hosted/index.d.ts +2 -2
  72. package/dist/hosted/index.js +1 -1
  73. package/dist/{index-DnglhM0A.d.ts → index-BQqOjerE.d.ts} +94 -13
  74. package/dist/index-BQqOjerE.d.ts.map +1 -0
  75. package/dist/{index-_vPrVMRX.d.ts → index-CFDffsKz.d.ts} +11 -11
  76. package/dist/{index-_vPrVMRX.d.ts.map → index-CFDffsKz.d.ts.map} +1 -1
  77. package/dist/{index-DDAPhUJJ.d.ts → index-D0Db5X-4.d.ts} +45 -9
  78. package/dist/index-D0Db5X-4.d.ts.map +1 -0
  79. package/dist/{index-DMoxLG8P.d.ts → index-e7LXeRVa.d.ts} +3 -3
  80. package/dist/{index-DMoxLG8P.d.ts.map → index-e7LXeRVa.d.ts.map} +1 -1
  81. package/dist/index.d.ts +130 -42
  82. package/dist/index.d.ts.map +1 -1
  83. package/dist/index.js +64 -41
  84. package/dist/index.js.map +1 -1
  85. package/dist/{insight-report-08F022xN.d.ts → insight-report-DETqPc_A.d.ts} +4 -4
  86. package/dist/{insight-report-08F022xN.d.ts.map → insight-report-DETqPc_A.d.ts.map} +1 -1
  87. package/dist/{integrity-B_EDELom.d.ts → integrity-BKTcA-HP.d.ts} +3 -3
  88. package/dist/{integrity-B_EDELom.d.ts.map → integrity-BKTcA-HP.d.ts.map} +1 -1
  89. package/dist/{kind-factory-DMeEoMQZ.js → kind-factory-gP6lDySe.js} +164 -149
  90. package/dist/kind-factory-gP6lDySe.js.map +1 -0
  91. package/dist/{llm-client-BFMRpmqb.js → llm-client-CxQtdtd6.js} +12 -5
  92. package/dist/llm-client-CxQtdtd6.js.map +1 -0
  93. package/dist/{llm-judge-aQHIk5_-.js → llm-judge-B2YxbAJb.js} +81 -7
  94. package/dist/{llm-judge-aQHIk5_-.js.map → llm-judge-B2YxbAJb.js.map} +1 -1
  95. package/dist/{matrix-Ch8JO1pG.d.ts → matrix-DGu8KhSs.d.ts} +2 -2
  96. package/dist/{matrix-Ch8JO1pG.d.ts.map → matrix-DGu8KhSs.d.ts.map} +1 -1
  97. package/dist/meta-eval/index.d.ts +100 -5
  98. package/dist/meta-eval/index.d.ts.map +1 -1
  99. package/dist/meta-eval/index.js +200 -2
  100. package/dist/meta-eval/index.js.map +1 -1
  101. package/dist/{mint-DjfDUMHr.js → mint-vWOdD8Ae.js} +2 -2
  102. package/dist/{mint-DjfDUMHr.js.map → mint-vWOdD8Ae.js.map} +1 -1
  103. package/dist/multishot/golden/index.d.ts +1 -1
  104. package/dist/multishot/index.d.ts +2 -2
  105. package/dist/openapi.json +1 -1
  106. package/dist/pipelines/index.d.ts +5 -5
  107. package/dist/pipelines/index.js +3 -3
  108. package/dist/{pre-registration-DHz6P_6f.d.ts → pre-registration-BoI4ucR3.d.ts} +2 -2
  109. package/dist/{pre-registration-DHz6P_6f.d.ts.map → pre-registration-BoI4ucR3.d.ts.map} +1 -1
  110. package/dist/{produced-state-CxmbFxFd.js → produced-state-7VYDwtkk.js} +3 -3
  111. package/dist/{produced-state-CxmbFxFd.js.map → produced-state-7VYDwtkk.js.map} +1 -1
  112. package/dist/{promotion-policy-BBBcz5_3.d.ts → promotion-policy-CvMda3kU.d.ts} +2 -2
  113. package/dist/{promotion-policy-BBBcz5_3.d.ts.map → promotion-policy-CvMda3kU.d.ts.map} +1 -1
  114. package/dist/{provenance-Dp-vvyrU.d.ts → provenance-CRY67X50.d.ts} +39 -165
  115. package/dist/provenance-CRY67X50.d.ts.map +1 -0
  116. package/dist/{query-BPGMVlbM.js → query-D1nLIKt7.js} +2 -2
  117. package/dist/{query-BPGMVlbM.js.map → query-D1nLIKt7.js.map} +1 -1
  118. package/dist/{query-Na5gEIGd.d.ts → query-D6W6MaGx.d.ts} +3 -3
  119. package/dist/{query-Na5gEIGd.d.ts.map → query-D6W6MaGx.d.ts.map} +1 -1
  120. package/dist/{registry-xEb_xfns.d.ts → registry-7pOUBrtX.d.ts} +4 -4
  121. package/dist/{registry-xEb_xfns.d.ts.map → registry-7pOUBrtX.d.ts.map} +1 -1
  122. package/dist/{release-confidence-D6lQw_o7.d.ts → release-confidence-BAcNYOf1.d.ts} +4 -4
  123. package/dist/{release-confidence-D6lQw_o7.d.ts.map → release-confidence-BAcNYOf1.d.ts.map} +1 -1
  124. package/dist/{release-confidence-CzUHc4z4.js → release-confidence-BsGEg_xg.js} +3 -3
  125. package/dist/{release-confidence-CzUHc4z4.js.map → release-confidence-BsGEg_xg.js.map} +1 -1
  126. package/dist/reporting.d.ts +3 -3
  127. package/dist/reporting.js +1 -1
  128. package/dist/{researcher-CMUTQXD7.d.ts → researcher-jsW1X94L.d.ts} +7 -8
  129. package/dist/researcher-jsW1X94L.d.ts.map +1 -0
  130. package/dist/{reward-hacking-SkxYgT0x.js → reward-hacking-CKW4teig.js} +2 -2
  131. package/dist/{reward-hacking-SkxYgT0x.js.map → reward-hacking-CKW4teig.js.map} +1 -1
  132. package/dist/{reward-hacking-CgPRUesA.d.ts → reward-hacking-ZXEi9VCq.d.ts} +2 -2
  133. package/dist/{reward-hacking-CgPRUesA.d.ts.map → reward-hacking-ZXEi9VCq.d.ts.map} +1 -1
  134. package/dist/rl.d.ts +7 -7
  135. package/dist/rl.js +4 -4
  136. package/dist/rollout/index.d.ts +1 -1
  137. package/dist/rollout/index.js +2 -2
  138. package/dist/{rollout-Crypdx8s.js → rollout-C-znbbYg.js} +2 -2
  139. package/dist/{rollout-Crypdx8s.js.map → rollout-C-znbbYg.js.map} +1 -1
  140. package/dist/{rubric-predictive-validity-DluJLCKQ.d.ts → rubric-predictive-validity-Dl1dvKCv.d.ts} +2 -2
  141. package/dist/{rubric-predictive-validity-DluJLCKQ.d.ts.map → rubric-predictive-validity-Dl1dvKCv.d.ts.map} +1 -1
  142. package/dist/{run-record-DQjRcYwA.d.ts → run-record-DTv1MdjK.d.ts} +2 -2
  143. package/dist/{run-record-DQjRcYwA.d.ts.map → run-record-DTv1MdjK.d.ts.map} +1 -1
  144. package/dist/{run-record-DLORoL7t.js → run-record-ZIsR9Fif.js} +2 -2
  145. package/dist/{run-record-DLORoL7t.js.map → run-record-ZIsR9Fif.js.map} +1 -1
  146. package/dist/{schema-DID1Cqct.d.ts → schema-CR5cpjQ3.d.ts} +57 -2
  147. package/dist/{schema-DID1Cqct.d.ts.map → schema-CR5cpjQ3.d.ts.map} +1 -1
  148. package/dist/{schema-CdIX2aHu.js → schema-CSf6qWgZ.js} +35 -1
  149. package/dist/{schema-CdIX2aHu.js.map → schema-CSf6qWgZ.js.map} +1 -1
  150. package/dist/semantic-concept-judge-Ct3QU7t5.js +780 -0
  151. package/dist/semantic-concept-judge-Ct3QU7t5.js.map +1 -0
  152. package/dist/{series-convergence-D9WgpXGi.d.ts → series-convergence-DeG33RpC.d.ts} +2 -2
  153. package/dist/{series-convergence-D9WgpXGi.d.ts.map → series-convergence-DeG33RpC.d.ts.map} +1 -1
  154. package/dist/{server-CCEnywOR.js → server-BR6onwZB.js} +2 -2
  155. package/dist/{server-CCEnywOR.js.map → server-BR6onwZB.js.map} +1 -1
  156. package/dist/{skillopt-optimization-method-LHi02MzH.js → skillopt-optimization-method-BzdphODy.js} +6 -6
  157. package/dist/{skillopt-optimization-method-LHi02MzH.js.map → skillopt-optimization-method-BzdphODy.js.map} +1 -1
  158. package/dist/{statistical-heldout-Yldkntvy.d.ts → statistical-heldout-DTyB_6-1.d.ts} +3 -3
  159. package/dist/{statistical-heldout-Yldkntvy.d.ts.map → statistical-heldout-DTyB_6-1.d.ts.map} +1 -1
  160. package/dist/{store-Cq9oOrI1.d.ts → store-BErPvYBr.d.ts} +2 -2
  161. package/dist/{store-Cq9oOrI1.d.ts.map → store-BErPvYBr.d.ts.map} +1 -1
  162. package/dist/{store-otlp-CHjBvWQY.js → store-otlp-Dow0pk_5.js} +2 -2
  163. package/dist/{store-otlp-CHjBvWQY.js.map → store-otlp-Dow0pk_5.js.map} +1 -1
  164. package/dist/{store-tool-spans-BvdUbeOB.d.ts → store-tool-spans-CCZNsihA.d.ts} +8 -8
  165. package/dist/{store-tool-spans-BvdUbeOB.d.ts.map → store-tool-spans-CCZNsihA.d.ts.map} +1 -1
  166. package/dist/{store-tool-spans-B9o6tU8f.js → store-tool-spans-CeNj_m2L.js} +3 -3
  167. package/dist/{store-tool-spans-B9o6tU8f.js.map → store-tool-spans-CeNj_m2L.js.map} +1 -1
  168. package/dist/storyboard/index.d.ts +1 -1
  169. package/dist/{summary-report-DRstQNBX.d.ts → summary-report-gMrbYawB.d.ts} +3 -3
  170. package/dist/{summary-report-DRstQNBX.d.ts.map → summary-report-gMrbYawB.d.ts.map} +1 -1
  171. package/dist/{task-failure-attributes-CBGtLS_H.js → task-failure-attributes-CZjZeBsY.js} +3 -3
  172. package/dist/{task-failure-attributes-CBGtLS_H.js.map → task-failure-attributes-CZjZeBsY.js.map} +1 -1
  173. package/dist/{tool-groups-DjwlMBvW.d.ts → tool-groups-Cp4Xdzrp.d.ts} +3 -3
  174. package/dist/tool-groups-Cp4Xdzrp.d.ts.map +1 -0
  175. package/dist/{tool-waste-CwGHzBzX.js → tool-waste-B9tdWV6g.js} +253 -6
  176. package/dist/tool-waste-B9tdWV6g.js.map +1 -0
  177. package/dist/{tool-waste-BrmLKxMw.d.ts → tool-waste-D23I0zWm.d.ts} +4 -4
  178. package/dist/{tool-waste-BrmLKxMw.d.ts.map → tool-waste-D23I0zWm.d.ts.map} +1 -1
  179. package/dist/trace-repair/index.d.ts +2 -2
  180. package/dist/traces.d.ts +10 -10
  181. package/dist/traces.js +7 -7
  182. package/dist/{trajectory-r1bQqvBQ.d.ts → trajectory-D7qrNvaN.d.ts} +3 -3
  183. package/dist/{trajectory-r1bQqvBQ.d.ts.map → trajectory-D7qrNvaN.d.ts.map} +1 -1
  184. package/dist/trajectory-replay/index.d.ts +3 -3
  185. package/dist/{types-CCZ34qmV.d.ts → types-BDV4PiMR.d.ts} +3 -3
  186. package/dist/{types-CCZ34qmV.d.ts.map → types-BDV4PiMR.d.ts.map} +1 -1
  187. package/dist/{types-nokrtr7M.d.ts → types-Ba5UQyVD.d.ts} +4 -4
  188. package/dist/{types-nokrtr7M.d.ts.map → types-Ba5UQyVD.d.ts.map} +1 -1
  189. package/dist/{types-DMoNFDWi.d.ts → types-DN2WdT5S.d.ts} +3 -3
  190. package/dist/{types-DMoNFDWi.d.ts.map → types-DN2WdT5S.d.ts.map} +1 -1
  191. package/dist/types-gvRsyJLh.d.ts +831 -0
  192. package/dist/types-gvRsyJLh.d.ts.map +1 -0
  193. package/dist/wire/index.d.ts +3 -3
  194. package/dist/wire/index.js +1 -1
  195. package/docs/plants.md +69 -1
  196. package/docs/public-api.md +6 -4
  197. package/docs/trace-analysis.md +55 -8
  198. package/package.json +1 -1
  199. package/dist/backend-integrity-e79K3UPD.d.ts.map +0 -1
  200. package/dist/bounded-process-VIi0KSL2.js.map +0 -1
  201. package/dist/chat-client-DI79OPye.js.map +0 -1
  202. package/dist/chat-json-call-5Jxna-aV.js.map +0 -1
  203. package/dist/dspy-rlm-engine-CS3qcCEk.js.map +0 -1
  204. package/dist/failure-cluster-6YSvsKlp.d.ts +0 -58
  205. package/dist/failure-cluster-6YSvsKlp.d.ts.map +0 -1
  206. package/dist/index-DDAPhUJJ.d.ts.map +0 -1
  207. package/dist/index-DnglhM0A.d.ts.map +0 -1
  208. package/dist/kind-factory-DMeEoMQZ.js.map +0 -1
  209. package/dist/llm-client-BFMRpmqb.js.map +0 -1
  210. package/dist/provenance-Dp-vvyrU.d.ts.map +0 -1
  211. package/dist/raw-provider-sink-BU29Sh8h.d.ts +0 -134
  212. package/dist/raw-provider-sink-BU29Sh8h.d.ts.map +0 -1
  213. package/dist/researcher-CMUTQXD7.d.ts.map +0 -1
  214. package/dist/semantic-concept-judge-I36eejJx.js +0 -382
  215. package/dist/semantic-concept-judge-I36eejJx.js.map +0 -1
  216. package/dist/tool-groups-DjwlMBvW.d.ts.map +0 -1
  217. package/dist/tool-waste-CwGHzBzX.js.map +0 -1
  218. package/dist/types-Bfk0uxRj.d.ts +0 -443
  219. package/dist/types-Bfk0uxRj.d.ts.map +0 -1
@@ -2,7 +2,7 @@ import { s as ValidationError } from "./errors-Dngq5h35.js";
2
2
  import { t as canonicalJson } from "./verdict-cache-B3eCVQtY.js";
3
3
  import { c as costForTokenPricing, i as CostLedger } from "./cost-ledger-B1qx30B4.js";
4
4
  import { a as appendLedgerLine, o as tryWithLedgerFileLock } from "./ledger-core-PIfjCbKn.js";
5
- import { f as ModelSubstitutionError, g as assertServedModelPolicy, h as assertServedModel } from "./llm-client-BFMRpmqb.js";
5
+ import { f as ModelSubstitutionError, g as assertServedModelPolicy, h as assertServedModel } from "./llm-client-CxQtdtd6.js";
6
6
  import { createRequire } from "node:module";
7
7
  import { randomBytes } from "node:crypto";
8
8
  import { isAbsolute, join, resolve } from "node:path";
@@ -1915,4 +1915,4 @@ function summarizeProcessOutput(capture, max = 4e3) {
1915
1915
  //#endregion
1916
1916
  export { inMemoryCampaignStorage as C, SearchLedgerIntegrityError as D, SearchLedgerError as E, fsCampaignStorage as S, SearchLedgerConflictError as T, removeCredentialEnvironment as _, closeServer as a, safePathComponent as b, waitForActiveHandlers as c, assertExternalOptimizerModelBudget as d, assertJsonValue as f, isRecord as g, isExternalTextCandidate as h, startExternalOptimizerModelProxy as i, DEFAULT_EXTERNAL_OPTIMIZER_CALLBACK_LIMITS as l, isCandidateText as m, closeExternalOptimizerResources as n, listenLocal as o, assertNoCredentialValues as p, runWithCleanup as r, sendJsonIfOpen as s, runExternalOptimizerProcess as t, DEFAULT_EXTERNAL_OPTIMIZER_PROCESS_LIMITS as u, resolveExternalOptimizerCallbackLimits as v, SEARCH_LEDGER_FILE_CONTEXT as w, createRunCostLedger as x, resolveExternalOptimizerProcessLimits as y };
1917
1917
 
1918
- //# sourceMappingURL=external-optimizer-subprocess-Cex8Da2i.js.map
1918
+ //# sourceMappingURL=external-optimizer-subprocess-DgNebftP.js.map