@tangle-network/agent-eval 0.203.0 → 0.203.2

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 (301) hide show
  1. package/CHANGELOG.md +10 -0
  2. package/dist/adapters/http.d.ts +10 -4
  3. package/dist/adapters/http.d.ts.map +1 -1
  4. package/dist/adapters/http.js +43 -38
  5. package/dist/adapters/http.js.map +1 -1
  6. package/dist/{agent-profile-DDfIjdyS.d.ts → agent-profile-EpO0HURy.d.ts} +4 -4
  7. package/dist/{agent-profile-DDfIjdyS.d.ts.map → agent-profile-EpO0HURy.d.ts.map} +1 -1
  8. package/dist/analyst/index.d.ts +12 -12
  9. package/dist/analyst/index.d.ts.map +1 -1
  10. package/dist/analyst/index.js +6 -6
  11. package/dist/{analyze-runs-CPiKLJFs.d.ts → analyze-runs-Q74o4Hfj.d.ts} +2 -2
  12. package/dist/{analyze-runs-CPiKLJFs.d.ts.map → analyze-runs-Q74o4Hfj.d.ts.map} +1 -1
  13. package/dist/{benchmark-command-DFs_i62N.js → benchmark-command-6OBcB0sG.js} +7 -6
  14. package/dist/benchmark-command-6OBcB0sG.js.map +1 -0
  15. package/dist/benchmarks/index.d.ts +4 -4
  16. package/dist/benchmarks/index.js +3 -3
  17. package/dist/campaign/index.d.ts +6 -6
  18. package/dist/campaign/index.js +4 -4
  19. package/dist/{campaign-Btk1yFfw.js → campaign-DYhg4SjN.js} +6 -6
  20. package/dist/{campaign-Btk1yFfw.js.map → campaign-DYhg4SjN.js.map} +1 -1
  21. package/dist/{chat-client-DUhWNQQS.js → chat-client-5LLl4Ctl.js} +2 -2
  22. package/dist/{chat-client-DUhWNQQS.js.map → chat-client-5LLl4Ctl.js.map} +1 -1
  23. package/dist/{chat-json-call-Dx_sHzqm.js → chat-json-call-Digk-pfF.js} +2 -2
  24. package/dist/{chat-json-call-Dx_sHzqm.js.map → chat-json-call-Digk-pfF.js.map} +1 -1
  25. package/dist/cli.js +3 -3
  26. package/dist/contract/index.d.ts +10 -10
  27. package/dist/contract/index.js +7 -7
  28. package/dist/{default-registry-B-utjsmX.d.ts → default-registry-BHEfZHQd.d.ts} +6 -6
  29. package/dist/{default-registry-B-utjsmX.d.ts.map → default-registry-BHEfZHQd.d.ts.map} +1 -1
  30. package/dist/{default-registry-CpswV_S2.js → default-registry-wInsQWlQ.js} +2 -2
  31. package/dist/{default-registry-CpswV_S2.js.map → default-registry-wInsQWlQ.js.map} +1 -1
  32. package/dist/{define-agent-eval-CJN9dTQw.js → define-agent-eval-B25Cc3ki.js} +3 -3
  33. package/dist/{define-agent-eval-CJN9dTQw.js.map → define-agent-eval-B25Cc3ki.js.map} +1 -1
  34. package/dist/{define-agent-eval-MAc6BQrq.d.ts → define-agent-eval-D8bPoBM5.d.ts} +7 -7
  35. package/dist/{define-agent-eval-MAc6BQrq.d.ts.map → define-agent-eval-D8bPoBM5.d.ts.map} +1 -1
  36. package/dist/diagnosis/index.d.ts +2 -2
  37. package/dist/{dspy-rlm-engine-US8YsYGq.js → dspy-rlm-engine-D0h-P2Mz.js} +2 -2
  38. package/dist/{dspy-rlm-engine-US8YsYGq.js.map → dspy-rlm-engine-D0h-P2Mz.js.map} +1 -1
  39. package/dist/{engine-4_Q4oujc.d.ts → engine-F_PvwesR.d.ts} +4 -4
  40. package/dist/{engine-4_Q4oujc.d.ts.map → engine-F_PvwesR.d.ts.map} +1 -1
  41. package/dist/evaluation.d.ts +2 -2
  42. package/dist/{exact-types-KGxBWH4b.d.ts → exact-types-BBMMYk3g.d.ts} +2 -2
  43. package/dist/{exact-types-KGxBWH4b.d.ts.map → exact-types-BBMMYk3g.d.ts.map} +1 -1
  44. package/dist/experiment/index.d.ts +1 -1
  45. package/dist/{external-optimizer-process-KLcw0Vnc.js → external-optimizer-process-CIV4EqiT.js} +2 -2
  46. package/dist/{external-optimizer-process-KLcw0Vnc.js.map → external-optimizer-process-CIV4EqiT.js.map} +1 -1
  47. package/dist/{external-optimizer-subprocess-CkyUUV7h.js → external-optimizer-subprocess-BmKtH3T6.js} +2 -2
  48. package/dist/{external-optimizer-subprocess-CkyUUV7h.js.map → external-optimizer-subprocess-BmKtH3T6.js.map} +1 -1
  49. package/dist/{extract-usage-DFATEuWW.js → extract-usage-BrnzRJ6H.js} +4 -3
  50. package/dist/extract-usage-BrnzRJ6H.js.map +1 -0
  51. package/dist/{feedback-trajectory-BXCGTRkz.d.ts → feedback-trajectory-C6NJxXEa.d.ts} +3 -3
  52. package/dist/{feedback-trajectory-BXCGTRkz.d.ts.map → feedback-trajectory-C6NJxXEa.d.ts.map} +1 -1
  53. package/dist/{index-CAtNOBQY.d.ts → index-B8n12TR2.d.ts} +12 -14
  54. package/dist/index-B8n12TR2.d.ts.map +1 -0
  55. package/dist/{index-DBk_4UPs.d.ts → index-C9l_-23M.d.ts} +7 -7
  56. package/dist/{index-DBk_4UPs.d.ts.map → index-C9l_-23M.d.ts.map} +1 -1
  57. package/dist/{index-Cuhxk05B.d.ts → index-CG7mtu_G.d.ts} +8 -8
  58. package/dist/{index-Cuhxk05B.d.ts.map → index-CG7mtu_G.d.ts.map} +1 -1
  59. package/dist/index.d.ts +19 -19
  60. package/dist/index.js +11 -11
  61. package/dist/{integrity-CaeNeusS.d.ts → integrity-BWO6RPxv.d.ts} +2 -2
  62. package/dist/{integrity-CaeNeusS.d.ts.map → integrity-BWO6RPxv.d.ts.map} +1 -1
  63. package/dist/{jev-review-DX6MI_jq.d.ts → jev-review-Cw06AKuF.d.ts} +2 -2
  64. package/dist/{jev-review-DX6MI_jq.d.ts.map → jev-review-Cw06AKuF.d.ts.map} +1 -1
  65. package/dist/jev.d.ts +3 -3
  66. package/dist/{llm-client-Bhqoglar.js → llm-client-DmCNzrc9.js} +77 -60
  67. package/dist/llm-client-DmCNzrc9.js.map +1 -0
  68. package/dist/{llm-judge-C-0P1WiT.js → llm-judge-DyZdrp6I.js} +57 -15
  69. package/dist/llm-judge-DyZdrp6I.js.map +1 -0
  70. package/dist/{matrix-BucOjLF1.d.ts → matrix-W1lbSx72.d.ts} +2 -2
  71. package/dist/{matrix-BucOjLF1.d.ts.map → matrix-W1lbSx72.d.ts.map} +1 -1
  72. package/dist/meta-eval/index.d.ts +1 -1
  73. package/dist/multishot/golden/index.d.ts +1 -1
  74. package/dist/multishot/index.d.ts +2 -2
  75. package/dist/openapi.json +1 -1
  76. package/dist/{prime-protocol-T0i6xcAs.d.ts → prime-protocol-IoN4Qb6c.d.ts} +2 -2
  77. package/dist/{prime-protocol-T0i6xcAs.d.ts.map → prime-protocol-IoN4Qb6c.d.ts.map} +1 -1
  78. package/dist/{produced-state-CR2tAPLf.js → produced-state-DLToUXrD.js} +3 -3
  79. package/dist/{produced-state-CR2tAPLf.js.map → produced-state-DLToUXrD.js.map} +1 -1
  80. package/dist/{abort-signal-CtzAM_sJ.js → proposal-findings-CXblsskH.js} +2 -11
  81. package/dist/proposal-findings-CXblsskH.js.map +1 -0
  82. package/dist/{registry-Bu3lNole.d.ts → registry-CT-hMSkR.d.ts} +4 -4
  83. package/dist/{registry-Bu3lNole.d.ts.map → registry-CT-hMSkR.d.ts.map} +1 -1
  84. package/dist/{researcher-DojEMb7E.d.ts → researcher-zTpxNJBy.d.ts} +3 -3
  85. package/dist/{researcher-DojEMb7E.d.ts.map → researcher-zTpxNJBy.d.ts.map} +1 -1
  86. package/dist/rl.d.ts +4 -4
  87. package/dist/search/index.d.ts +2 -2
  88. package/dist/{search-kernel-B8RC6BlK.d.ts → search-kernel-DNpsHb8P.d.ts} +2 -2
  89. package/dist/{search-kernel-B8RC6BlK.d.ts.map → search-kernel-DNpsHb8P.d.ts.map} +1 -1
  90. package/dist/{semantic-concept-judge-BcjYg37z.js → semantic-concept-judge-BgWxa4L_.js} +4 -4
  91. package/dist/{semantic-concept-judge-BcjYg37z.js.map → semantic-concept-judge-BgWxa4L_.js.map} +1 -1
  92. package/dist/{series-convergence-DY7ha0kx.d.ts → series-convergence-DLy0bQMV.d.ts} +2 -2
  93. package/dist/{series-convergence-DY7ha0kx.d.ts.map → series-convergence-DLy0bQMV.d.ts.map} +1 -1
  94. package/dist/{server-B4jMhqQn.js → server-CoBZO1fj.js} +2 -2
  95. package/dist/{server-B4jMhqQn.js.map → server-CoBZO1fj.js.map} +1 -1
  96. package/dist/{skillopt-optimization-method-Bls9t-G_.js → skillopt-optimization-method-Dz5CGZb8.js} +5 -5
  97. package/dist/{skillopt-optimization-method-Bls9t-G_.js.map → skillopt-optimization-method-Dz5CGZb8.js.map} +1 -1
  98. package/dist/{statistical-heldout-DJtQAUZB.d.ts → statistical-heldout-Dq3pnmxd.d.ts} +2 -2
  99. package/dist/{statistical-heldout-DJtQAUZB.d.ts.map → statistical-heldout-Dq3pnmxd.d.ts.map} +1 -1
  100. package/dist/{store-tool-spans-fkNF7Q9Y.d.ts → store-tool-spans-CAF3T-BS.d.ts} +5 -5
  101. package/dist/{store-tool-spans-fkNF7Q9Y.d.ts.map → store-tool-spans-CAF3T-BS.d.ts.map} +1 -1
  102. package/dist/{store-tool-spans-Biio4_Nw.js → store-tool-spans-D5kOU0mr.js} +2 -2
  103. package/dist/{store-tool-spans-Biio4_Nw.js.map → store-tool-spans-D5kOU0mr.js.map} +1 -1
  104. package/dist/{tool-groups-Zm84Pqpk.d.ts → tool-groups-B7_jUPHp.d.ts} +3 -3
  105. package/dist/tool-groups-B7_jUPHp.d.ts.map +1 -0
  106. package/dist/{trace-questions--lnJTaou.d.ts → trace-questions-Dd3AMf-U.d.ts} +3 -3
  107. package/dist/{trace-questions--lnJTaou.d.ts.map → trace-questions-Dd3AMf-U.d.ts.map} +1 -1
  108. package/dist/trace-repair/index.d.ts +1 -1
  109. package/dist/traces.d.ts +5 -5
  110. package/dist/traces.js +2 -2
  111. package/dist/{types-CeDfCRXp.d.ts → types-6VEehmEg.d.ts} +2 -2
  112. package/dist/{types-CeDfCRXp.d.ts.map → types-6VEehmEg.d.ts.map} +1 -1
  113. package/dist/{types-C0bWoSKC.d.ts → types-DLxe96rp.d.ts} +2 -2
  114. package/dist/{types-C0bWoSKC.d.ts.map → types-DLxe96rp.d.ts.map} +1 -1
  115. package/dist/{types-B6JadxWL.d.ts → types-DZQpUJse.d.ts} +2 -2
  116. package/dist/{types-B6JadxWL.d.ts.map → types-DZQpUJse.d.ts.map} +1 -1
  117. package/dist/{types-khIUQ0O5.d.ts → types-ZUy5HGY5.d.ts} +11 -5
  118. package/dist/{types-khIUQ0O5.d.ts.map → types-ZUy5HGY5.d.ts.map} +1 -1
  119. package/dist/wire/index.d.ts +2 -2
  120. package/dist/wire/index.js +1 -1
  121. package/docs/changes/llm-physical-attempts.md +30 -0
  122. package/docs/changes/shared-model-request-lifetime.md +30 -0
  123. package/docs/concepts.md +8 -0
  124. package/docs/eval-surface-map.md +12 -2
  125. package/docs/http-dispatch.md +33 -0
  126. package/docs/proofs/campaign-attempt-retention-20261001/README.md +70 -0
  127. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-judge-attribution/attribution_0/attempts/e7949644-3d60-4ab9-817e-f80d0a48f5d8/attempt-1/artifacts/capture.json +3 -0
  128. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-judge-attribution/attribution_0/attempts/e7949644-3d60-4ab9-817e-f80d0a48f5d8/attempt-1/identity.json +10 -0
  129. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-judge-attribution/attribution_0/attempts/e7949644-3d60-4ab9-817e-f80d0a48f5d8/attempt-1/result.json +1 -0
  130. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-judge-attribution/attribution_0/attempts/e7949644-3d60-4ab9-817e-f80d0a48f5d8/attempt-1/trace/spans.jsonl +0 -0
  131. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-judge-attribution/attribution_0/cached-result.json +1 -0
  132. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-judge-attribution/attribution_0/latest-attempt.json +1 -0
  133. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/attempts/7c7718f6-c85e-4867-9e3a-13ef9513de80/attempt-1/artifacts/captured-response.json +4 -0
  134. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/attempts/7c7718f6-c85e-4867-9e3a-13ef9513de80/attempt-1/identity.json +10 -0
  135. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/attempts/7c7718f6-c85e-4867-9e3a-13ef9513de80/attempt-1/result.json +1 -0
  136. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/attempts/7c7718f6-c85e-4867-9e3a-13ef9513de80/attempt-1/trace/spans.jsonl +1 -0
  137. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/cached-result.json +1 -0
  138. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/captured-response.json +6 -0
  139. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/failure-receipt.json +58 -0
  140. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/latest-attempt.json +1 -0
  141. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/spans.jsonl +1 -0
  142. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/baseline/capture-retention_0/attempts/3652118b-e1dc-4b17-bc15-6b802dc71eb1/attempt-1/artifacts/captured-response.json +4 -0
  143. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/baseline/capture-retention_0/attempts/3652118b-e1dc-4b17-bc15-6b802dc71eb1/attempt-1/identity.json +10 -0
  144. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/baseline/capture-retention_0/attempts/3652118b-e1dc-4b17-bc15-6b802dc71eb1/attempt-1/result.json +1 -0
  145. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/baseline/capture-retention_0/attempts/3652118b-e1dc-4b17-bc15-6b802dc71eb1/attempt-1/trace/spans.jsonl +1 -0
  146. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/baseline/capture-retention_0/cached-result.json +1 -0
  147. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/baseline/capture-retention_0/latest-attempt.json +1 -0
  148. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/42b3fec6b7e55008/capture-retention_0/attempts/40e411fe-ad12-4e6b-a279-2cf07c356a2f/attempt-1/artifacts/captured-response.json +4 -0
  149. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/42b3fec6b7e55008/capture-retention_0/attempts/40e411fe-ad12-4e6b-a279-2cf07c356a2f/attempt-1/failure-receipt.json +62 -0
  150. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/42b3fec6b7e55008/capture-retention_0/attempts/40e411fe-ad12-4e6b-a279-2cf07c356a2f/attempt-1/identity.json +10 -0
  151. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/42b3fec6b7e55008/capture-retention_0/attempts/40e411fe-ad12-4e6b-a279-2cf07c356a2f/attempt-1/result.json +1 -0
  152. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/42b3fec6b7e55008/capture-retention_0/attempts/40e411fe-ad12-4e6b-a279-2cf07c356a2f/attempt-1/trace/spans.jsonl +1 -0
  153. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/42b3fec6b7e55008/capture-retention_0/latest-attempt.json +1 -0
  154. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/87740cc101602a08/capture-retention_0/attempts/9e7da63e-2d19-4ec1-a5ec-ec804e2b0f40/attempt-1/artifacts/captured-response.json +4 -0
  155. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/87740cc101602a08/capture-retention_0/attempts/9e7da63e-2d19-4ec1-a5ec-ec804e2b0f40/attempt-1/identity.json +10 -0
  156. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/87740cc101602a08/capture-retention_0/attempts/9e7da63e-2d19-4ec1-a5ec-ec804e2b0f40/attempt-1/result.json +1 -0
  157. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/87740cc101602a08/capture-retention_0/attempts/9e7da63e-2d19-4ec1-a5ec-ec804e2b0f40/attempt-1/trace/spans.jsonl +1 -0
  158. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/87740cc101602a08/capture-retention_0/cached-result.json +1 -0
  159. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/87740cc101602a08/capture-retention_0/latest-attempt.json +1 -0
  160. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/first-interruption.json +38 -0
  161. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/19147243d263e55b1eaf1c940691947382a7cce17c5f49e4a4da765a473d2a55.json +1 -0
  162. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/5dd0d871d559d1c55b2ac04b3fbd26d62f7c9e25d7632d4542502cd292818fc0.json +1 -0
  163. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/5de45d632937e75ff90fec9f1f2ec425904d3632da71f6b26f83b1e1eb8cde5a.json +1 -0
  164. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/6caba627806e499aa3d9e156aec9d5a731a3ef30e29756d343b85b7217c77c11.json +1 -0
  165. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/ce2770851b3b7651f27cedcbad0372b9191e9a9b016665987e3ddd2ad53012b5.json +1 -0
  166. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/d8ac4ba8d9844afb4defa5cd277fe3cb944d99e58cf41c07d3ae199b6f467966.json +1 -0
  167. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/f59a02035fe96ea2f5582dd715d2e3ad8c184ae959310978962f1ac0780753bd.json +1 -0
  168. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/ledger.jsonl +23 -0
  169. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/ledger.jsonl.head +1 -0
  170. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-path-guard/capture-retention_0/attempts/3c8272d6-d35b-477e-9d08-085261b8dc64/attempt-1/artifacts/capture.json +3 -0
  171. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-path-guard/capture-retention_0/attempts/3c8272d6-d35b-477e-9d08-085261b8dc64/attempt-1/identity.json +10 -0
  172. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-path-guard/capture-retention_0/attempts/3c8272d6-d35b-477e-9d08-085261b8dc64/attempt-1/result.json +1 -0
  173. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-path-guard/capture-retention_0/attempts/3c8272d6-d35b-477e-9d08-085261b8dc64/attempt-1/trace/spans.jsonl +0 -0
  174. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-path-guard/capture-retention_0/cached-result.json +1 -0
  175. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-path-guard/capture-retention_0/latest-attempt.json +1 -0
  176. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/2b022ccb-adb3-4468-8c21-48ee82d0634a/attempt-1/artifacts/captured-response.json +6 -0
  177. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/2b022ccb-adb3-4468-8c21-48ee82d0634a/attempt-1/failure-receipt.json +81 -0
  178. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/2b022ccb-adb3-4468-8c21-48ee82d0634a/attempt-1/identity.json +10 -0
  179. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/2b022ccb-adb3-4468-8c21-48ee82d0634a/attempt-1/result.json +1 -0
  180. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/2b022ccb-adb3-4468-8c21-48ee82d0634a/attempt-1/trace/spans.jsonl +2 -0
  181. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/c4859951-1e7c-4d23-b89a-0ca8fa79e2cf/attempt-1/artifacts/captured-response.json +6 -0
  182. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/c4859951-1e7c-4d23-b89a-0ca8fa79e2cf/attempt-1/identity.json +10 -0
  183. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/c4859951-1e7c-4d23-b89a-0ca8fa79e2cf/attempt-1/result.json +1 -0
  184. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/attempts/c4859951-1e7c-4d23-b89a-0ca8fa79e2cf/attempt-1/trace/spans.jsonl +2 -0
  185. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/cached-result.json +1 -0
  186. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/latest-attempt.json +1 -0
  187. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/observation.json +608 -0
  188. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-1/artifacts/captured-response.json +6 -0
  189. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-1/failure-receipt.json +81 -0
  190. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-1/identity.json +10 -0
  191. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-1/result.json +1 -0
  192. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-1/trace/spans.jsonl +2 -0
  193. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-2/artifacts/captured-response.json +6 -0
  194. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-2/identity.json +10 -0
  195. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-2/result.json +1 -0
  196. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/attempts/74c13884-d47e-4b6d-a823-5bd44ee0e6cb/attempt-2/trace/spans.jsonl +2 -0
  197. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/cached-result.json +1 -0
  198. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/latest-attempt.json +1 -0
  199. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/observation.json +514 -0
  200. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-summary.json +1853 -0
  201. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/judge-attribution.json +140 -0
  202. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/qualification.log +1 -0
  203. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/qualify.mjs +165 -0
  204. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduce.mjs +39 -0
  205. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/capture-retention_0/cached-result.json +1 -0
  206. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/capture-retention_0/captured-response.json +5 -0
  207. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/capture-retention_0/failure-receipt.json +58 -0
  208. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/capture-retention_0/spans.jsonl +1 -0
  209. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/observer-retained-captures.json +20 -0
  210. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/capture-retention_0/cached-result.json +1 -0
  211. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/capture-retention_0/captured-response.json +5 -0
  212. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/capture-retention_0/failure-receipt.attempt-1.json +58 -0
  213. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/capture-retention_0/spans.jsonl +1 -0
  214. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/observer-retained-captures.json +20 -0
  215. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-summary.json +315 -0
  216. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction.log +1 -0
  217. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/source-and-build.json +2409 -0
  218. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/typecheck.log +1 -0
  219. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/verify-package.log +340 -0
  220. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/attempts/33d57ccb-d4d8-4c23-92e3-c1ddf7db6058/attempt-1/artifacts/captured-response.json +4 -0
  221. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/attempts/33d57ccb-d4d8-4c23-92e3-c1ddf7db6058/attempt-1/identity.json +10 -0
  222. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/attempts/33d57ccb-d4d8-4c23-92e3-c1ddf7db6058/attempt-1/result.json +1 -0
  223. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/attempts/33d57ccb-d4d8-4c23-92e3-c1ddf7db6058/attempt-1/trace/spans.jsonl +1 -0
  224. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/cached-result.json +1 -0
  225. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/captured-response.json +6 -0
  226. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/failure-receipt.json +58 -0
  227. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/latest-attempt.json +1 -0
  228. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/spans.jsonl +1 -0
  229. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/baseline/capture-retention_0/attempts/6b25a1d2-5324-445b-b59d-bdc7381cd4b4/attempt-1/artifacts/captured-response.json +4 -0
  230. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/baseline/capture-retention_0/attempts/6b25a1d2-5324-445b-b59d-bdc7381cd4b4/attempt-1/identity.json +10 -0
  231. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/baseline/capture-retention_0/attempts/6b25a1d2-5324-445b-b59d-bdc7381cd4b4/attempt-1/result.json +1 -0
  232. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/baseline/capture-retention_0/attempts/6b25a1d2-5324-445b-b59d-bdc7381cd4b4/attempt-1/trace/spans.jsonl +1 -0
  233. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/baseline/capture-retention_0/cached-result.json +1 -0
  234. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/baseline/capture-retention_0/latest-attempt.json +1 -0
  235. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/first-interruption.json +5 -0
  236. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/search/blobs/5de45d632937e75ff90fec9f1f2ec425904d3632da71f6b26f83b1e1eb8cde5a.json +1 -0
  237. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/search/ledger.jsonl +7 -0
  238. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/search/ledger.jsonl.head +1 -0
  239. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-path-guard/capture-retention_0/attempts/723fa9c6-099e-437c-bddf-a4cbd28a8508/attempt-1/artifacts/capture.json +3 -0
  240. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-path-guard/capture-retention_0/attempts/723fa9c6-099e-437c-bddf-a4cbd28a8508/attempt-1/identity.json +10 -0
  241. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-path-guard/capture-retention_0/attempts/723fa9c6-099e-437c-bddf-a4cbd28a8508/attempt-1/result.json +1 -0
  242. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-path-guard/capture-retention_0/attempts/723fa9c6-099e-437c-bddf-a4cbd28a8508/attempt-1/trace/spans.jsonl +0 -0
  243. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-path-guard/capture-retention_0/cached-result.json +1 -0
  244. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-path-guard/capture-retention_0/latest-attempt.json +1 -0
  245. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/06db3429-c5c6-42c1-8623-08e2da1f563e/attempt-1/artifacts/captured-response.json +6 -0
  246. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/06db3429-c5c6-42c1-8623-08e2da1f563e/attempt-1/failure-receipt.json +62 -0
  247. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/06db3429-c5c6-42c1-8623-08e2da1f563e/attempt-1/identity.json +10 -0
  248. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/06db3429-c5c6-42c1-8623-08e2da1f563e/attempt-1/result.json +1 -0
  249. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/06db3429-c5c6-42c1-8623-08e2da1f563e/attempt-1/trace/spans.jsonl +1 -0
  250. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/d49f7e40-c4d2-4cb6-98d1-5e49f45c6e2c/attempt-1/artifacts/captured-response.json +6 -0
  251. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/d49f7e40-c4d2-4cb6-98d1-5e49f45c6e2c/attempt-1/identity.json +10 -0
  252. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/d49f7e40-c4d2-4cb6-98d1-5e49f45c6e2c/attempt-1/result.json +1 -0
  253. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/attempts/d49f7e40-c4d2-4cb6-98d1-5e49f45c6e2c/attempt-1/trace/spans.jsonl +1 -0
  254. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/cached-result.json +1 -0
  255. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/latest-attempt.json +1 -0
  256. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/observation.json +458 -0
  257. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/artifacts/captured-response.json +6 -0
  258. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/failure-receipt.json +62 -0
  259. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/identity.json +10 -0
  260. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/result.json +1 -0
  261. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/trace/spans.jsonl +1 -0
  262. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/artifacts/captured-response.json +6 -0
  263. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/identity.json +10 -0
  264. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/result.json +1 -0
  265. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/trace/spans.jsonl +1 -0
  266. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/cached-result.json +1 -0
  267. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/latest-attempt.json +1 -0
  268. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/observation.json +380 -0
  269. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/capture-retention_0/cached-result.json +1 -0
  270. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/capture-retention_0/captured-response.json +6 -0
  271. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/capture-retention_0/failure-receipt.json +58 -0
  272. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/capture-retention_0/spans.jsonl +1 -0
  273. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/observation.json +198 -0
  274. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/capture-retention_0/cached-result.json +1 -0
  275. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/capture-retention_0/captured-response.json +6 -0
  276. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/capture-retention_0/failure-receipt.attempt-1.json +58 -0
  277. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/capture-retention_0/spans.jsonl +1 -0
  278. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/observation.json +121 -0
  279. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-summary.json +321 -0
  280. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/build.attribution.log +491 -0
  281. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/build.final.log +491 -0
  282. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/build.log +495 -0
  283. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/qualification.log +18 -0
  284. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/qualification.wrong-root.log +9 -0
  285. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/qualify.mjs +148 -0
  286. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/qualify.wrong-root.mjs +148 -0
  287. package/docs/proofs/campaign-attempt-retention-20261001/manifest.json +808 -0
  288. package/docs/proofs/router-cache-usage-20261001/after.json +2058 -0
  289. package/docs/proofs/router-cache-usage-20261001/component-projections.json +584 -0
  290. package/docs/proofs/router-cache-usage-20261001/component-projections.nested-only.json +306 -0
  291. package/docs/proofs/router-cache-usage-20261001/manifest.json +32 -0
  292. package/docs/proofs/router-cache-usage-20261001/summary.json +49 -0
  293. package/docs/proofs/router-cache-usage-20261001/summary.nested-only.json +29 -0
  294. package/package.json +1 -1
  295. package/dist/abort-signal-CtzAM_sJ.js.map +0 -1
  296. package/dist/benchmark-command-DFs_i62N.js.map +0 -1
  297. package/dist/extract-usage-DFATEuWW.js.map +0 -1
  298. package/dist/index-CAtNOBQY.d.ts.map +0 -1
  299. package/dist/llm-client-Bhqoglar.js.map +0 -1
  300. package/dist/llm-judge-C-0P1WiT.js.map +0 -1
  301. package/dist/tool-groups-Zm84Pqpk.d.ts.map +0 -1
@@ -0,0 +1,58 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
4
+ "recordedAt": "2026-10-01T16:47:43.515Z",
5
+ "failure": {
6
+ "stage": "dispatch",
7
+ "error": {
8
+ "name": "Error",
9
+ "message": "Operational interruption after native artifact capture",
10
+ "stack": "Error: Operational interruption after native artifact capture\n at Object.dispatch (file:///home/drew/webb/_wt/lab-autoroute-campaign-20261001/[eval1]:16:22)\n at async executeCell (file:///home/drew/webb/_wt/lab-evidence-unified/node_modules/.pnpm/@tangle-network+agent-eval@0.203.0/node_modules/@tangle-network/agent-eval/dist/llm-judge-C-0P1WiT.js:459:19)\n at async file:///home/drew/webb/_wt/lab-evidence-unified/node_modules/.pnpm/@tangle-network+agent-eval@0.203.0/node_modules/@tangle-network/agent-eval/dist/llm-judge-C-0P1WiT.js:888:15\n at async Promise.allSettled (index 0)\n at async runCampaign (file:///home/drew/webb/_wt/lab-evidence-unified/node_modules/.pnpm/@tangle-network+agent-eval@0.203.0/node_modules/@tangle-network/agent-eval/dist/llm-judge-C-0P1WiT.js:935:22)\n at async file:///home/drew/webb/_wt/lab-autoroute-campaign-20261001/[eval1]:19:17"
11
+ }
12
+ },
13
+ "cell": {
14
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
15
+ "cellId": "capture-retention:0",
16
+ "scenarioId": "capture-retention",
17
+ "rep": 0,
18
+ "artifact": null,
19
+ "judgeScores": {},
20
+ "costUsd": 0,
21
+ "costProvenance": {
22
+ "kind": "observed",
23
+ "usd": 0
24
+ },
25
+ "costCallIds": [],
26
+ "tokenUsage": {
27
+ "input": 0,
28
+ "output": 0
29
+ },
30
+ "durationMs": 1,
31
+ "seed": 42,
32
+ "cached": false,
33
+ "errorStage": "dispatch",
34
+ "error": "Operational interruption after native artifact capture"
35
+ },
36
+ "cost": {
37
+ "totalCalls": 0,
38
+ "pendingCalls": 0,
39
+ "unresolvedCalls": 0,
40
+ "reservedCostUsd": 0,
41
+ "inputTokens": 0,
42
+ "outputTokens": 0,
43
+ "reasoningTokens": 0,
44
+ "cachedTokens": 0,
45
+ "cacheWriteTokens": 0,
46
+ "totalCostUsd": 0,
47
+ "costProvenance": {
48
+ "kind": "observed",
49
+ "usd": 0
50
+ },
51
+ "byChannel": [],
52
+ "unpricedModels": [],
53
+ "fullyPriced": true,
54
+ "usageComplete": true,
55
+ "accountingComplete": true,
56
+ "incompleteReasons": []
57
+ }
58
+ }
@@ -0,0 +1 @@
1
+ {"name":"capture-invocation","cellId":"capture-retention:0","startMs":1790873263516,"invocation":2,"durationMs":0}
@@ -0,0 +1,121 @@
1
+ {
2
+ "invocations": 2,
3
+ "observed": [
4
+ {
5
+ "invocation": 1,
6
+ "path": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry/capture-retention_0/captured-response.json",
7
+ "sha256": "b5485b0030654d9ca660401cc07d42e16decdbe5bdc4d8a059eb20045202656b",
8
+ "value": {
9
+ "cellId": "capture-retention:0",
10
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
11
+ "invocation": 1,
12
+ "content": "Actual filesystem capture from invocation 1"
13
+ }
14
+ },
15
+ {
16
+ "invocation": 2,
17
+ "path": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry/capture-retention_0/captured-response.json",
18
+ "sha256": "6b0ce0b4eac76fbfdbdf88be21f5d73939d6949b23a7a5579253d74541232ebc",
19
+ "value": {
20
+ "cellId": "capture-retention:0",
21
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
22
+ "invocation": 2,
23
+ "content": "Actual filesystem capture from invocation 2"
24
+ }
25
+ }
26
+ ],
27
+ "firstContentStillPresent": false,
28
+ "finalBytes": {
29
+ "cellId": "capture-retention:0",
30
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
31
+ "invocation": 2,
32
+ "content": "Actual filesystem capture from invocation 2"
33
+ },
34
+ "reports": [
35
+ {
36
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
37
+ "splitDigest": "sha256:4a729491b198148335bdd5b8f6429d48611d3b44480f1982e77f3a91e4cf2a5f",
38
+ "seed": 42,
39
+ "reps": 1,
40
+ "startedAt": "2026-10-01T16:47:43.512Z",
41
+ "endedAt": "2026-10-01T16:47:43.721Z",
42
+ "durationMs": 209,
43
+ "cells": [
44
+ {
45
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
46
+ "cellId": "capture-retention:0",
47
+ "scenarioId": "capture-retention",
48
+ "rep": 0,
49
+ "artifact": {
50
+ "cellId": "capture-retention:0",
51
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
52
+ "invocation": 2,
53
+ "content": "Actual filesystem capture from invocation 2"
54
+ },
55
+ "judgeScores": {},
56
+ "costUsd": 0,
57
+ "costProvenance": {
58
+ "kind": "observed",
59
+ "usd": 0
60
+ },
61
+ "costCallIds": [],
62
+ "tokenUsage": {
63
+ "input": 0,
64
+ "output": 0
65
+ },
66
+ "durationMs": 0,
67
+ "seed": 42,
68
+ "cached": false,
69
+ "retryAttempts": 1
70
+ }
71
+ ],
72
+ "aggregates": {
73
+ "byJudge": {},
74
+ "byScenario": {},
75
+ "cost": {
76
+ "totalCalls": 0,
77
+ "pendingCalls": 0,
78
+ "unresolvedCalls": 0,
79
+ "reservedCostUsd": 0,
80
+ "inputTokens": 0,
81
+ "outputTokens": 0,
82
+ "reasoningTokens": 0,
83
+ "cachedTokens": 0,
84
+ "cacheWriteTokens": 0,
85
+ "totalCostUsd": 0,
86
+ "costProvenance": {
87
+ "kind": "observed",
88
+ "usd": 0
89
+ },
90
+ "byChannel": [],
91
+ "unpricedModels": [],
92
+ "fullyPriced": true,
93
+ "usageComplete": true,
94
+ "accountingComplete": true,
95
+ "incompleteReasons": []
96
+ },
97
+ "cellsExecuted": 1,
98
+ "cellsSkipped": 0,
99
+ "cellsCached": 0,
100
+ "cellsFailed": 0,
101
+ "cellsDispatchFailed": 0,
102
+ "cellsJudgeFailed": 0,
103
+ "cellsUnclassifiedFailed": 0
104
+ },
105
+ "runDir": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry",
106
+ "artifactsByPath": {
107
+ "capture-retention:0/captured-response.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry/capture-retention_0/captured-response.json",
108
+ "capture-retention:0/failure-receipt.attempt-1.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry/capture-retention_0/failure-receipt.attempt-1.json"
109
+ },
110
+ "scenarios": [
111
+ {
112
+ "id": "capture-retention",
113
+ "kind": "operational",
114
+ "scenarioDigest": "sha256:955e060f603d0f2e9cd84b8426b05de1faab5b9dbbefdc5d494834afdcb56fc9"
115
+ }
116
+ ]
117
+ }
118
+ ],
119
+ "modelInference": false,
120
+ "researchUnits": 0
121
+ }
@@ -0,0 +1,321 @@
1
+ {
2
+ "retry": {
3
+ "invocations": 2,
4
+ "observed": [
5
+ {
6
+ "invocation": 1,
7
+ "path": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry/capture-retention_0/captured-response.json",
8
+ "sha256": "b5485b0030654d9ca660401cc07d42e16decdbe5bdc4d8a059eb20045202656b",
9
+ "value": {
10
+ "cellId": "capture-retention:0",
11
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
12
+ "invocation": 1,
13
+ "content": "Actual filesystem capture from invocation 1"
14
+ }
15
+ },
16
+ {
17
+ "invocation": 2,
18
+ "path": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry/capture-retention_0/captured-response.json",
19
+ "sha256": "6b0ce0b4eac76fbfdbdf88be21f5d73939d6949b23a7a5579253d74541232ebc",
20
+ "value": {
21
+ "cellId": "capture-retention:0",
22
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
23
+ "invocation": 2,
24
+ "content": "Actual filesystem capture from invocation 2"
25
+ }
26
+ }
27
+ ],
28
+ "firstContentStillPresent": false,
29
+ "finalBytes": {
30
+ "cellId": "capture-retention:0",
31
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
32
+ "invocation": 2,
33
+ "content": "Actual filesystem capture from invocation 2"
34
+ },
35
+ "reports": [
36
+ {
37
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
38
+ "splitDigest": "sha256:4a729491b198148335bdd5b8f6429d48611d3b44480f1982e77f3a91e4cf2a5f",
39
+ "seed": 42,
40
+ "reps": 1,
41
+ "startedAt": "2026-10-01T16:47:43.512Z",
42
+ "endedAt": "2026-10-01T16:47:43.721Z",
43
+ "durationMs": 209,
44
+ "cells": [
45
+ {
46
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
47
+ "cellId": "capture-retention:0",
48
+ "scenarioId": "capture-retention",
49
+ "rep": 0,
50
+ "artifact": {
51
+ "cellId": "capture-retention:0",
52
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
53
+ "invocation": 2,
54
+ "content": "Actual filesystem capture from invocation 2"
55
+ },
56
+ "judgeScores": {},
57
+ "costUsd": 0,
58
+ "costProvenance": {
59
+ "kind": "observed",
60
+ "usd": 0
61
+ },
62
+ "costCallIds": [],
63
+ "tokenUsage": {
64
+ "input": 0,
65
+ "output": 0
66
+ },
67
+ "durationMs": 0,
68
+ "seed": 42,
69
+ "cached": false,
70
+ "retryAttempts": 1
71
+ }
72
+ ],
73
+ "aggregates": {
74
+ "byJudge": {},
75
+ "byScenario": {},
76
+ "cost": {
77
+ "totalCalls": 0,
78
+ "pendingCalls": 0,
79
+ "unresolvedCalls": 0,
80
+ "reservedCostUsd": 0,
81
+ "inputTokens": 0,
82
+ "outputTokens": 0,
83
+ "reasoningTokens": 0,
84
+ "cachedTokens": 0,
85
+ "cacheWriteTokens": 0,
86
+ "totalCostUsd": 0,
87
+ "costProvenance": {
88
+ "kind": "observed",
89
+ "usd": 0
90
+ },
91
+ "byChannel": [],
92
+ "unpricedModels": [],
93
+ "fullyPriced": true,
94
+ "usageComplete": true,
95
+ "accountingComplete": true,
96
+ "incompleteReasons": []
97
+ },
98
+ "cellsExecuted": 1,
99
+ "cellsSkipped": 0,
100
+ "cellsCached": 0,
101
+ "cellsFailed": 0,
102
+ "cellsDispatchFailed": 0,
103
+ "cellsJudgeFailed": 0,
104
+ "cellsUnclassifiedFailed": 0
105
+ },
106
+ "runDir": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry",
107
+ "artifactsByPath": {
108
+ "capture-retention:0/captured-response.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry/capture-retention_0/captured-response.json",
109
+ "capture-retention:0/failure-receipt.attempt-1.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-retry/capture-retention_0/failure-receipt.attempt-1.json"
110
+ },
111
+ "scenarios": [
112
+ {
113
+ "id": "capture-retention",
114
+ "kind": "operational",
115
+ "scenarioDigest": "sha256:955e060f603d0f2e9cd84b8426b05de1faab5b9dbbefdc5d494834afdcb56fc9"
116
+ }
117
+ ]
118
+ }
119
+ ],
120
+ "modelInference": false,
121
+ "researchUnits": 0
122
+ },
123
+ "resume": {
124
+ "invocations": 2,
125
+ "observed": [
126
+ {
127
+ "invocation": 1,
128
+ "path": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/captured-response.json",
129
+ "sha256": "36f08e9a29651e4506af2c01fa13df81fff0711f1c53f3f4633f79397b90c569",
130
+ "value": {
131
+ "cellId": "capture-retention:0",
132
+ "runAttemptId": "08005dbd-35ff-488f-8942-22732fc5f036",
133
+ "invocation": 1,
134
+ "content": "Actual filesystem capture from invocation 1"
135
+ }
136
+ },
137
+ {
138
+ "invocation": 2,
139
+ "path": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/captured-response.json",
140
+ "sha256": "bd867bf7291384d653ab799dc2eebf768878ca3a8681fa869684d6da0808cfd7",
141
+ "value": {
142
+ "cellId": "capture-retention:0",
143
+ "runAttemptId": "cc7546fa-7b18-4a50-8444-204439c84bae",
144
+ "invocation": 2,
145
+ "content": "Actual filesystem capture from invocation 2"
146
+ }
147
+ }
148
+ ],
149
+ "firstContentStillPresent": false,
150
+ "finalBytes": {
151
+ "cellId": "capture-retention:0",
152
+ "runAttemptId": "cc7546fa-7b18-4a50-8444-204439c84bae",
153
+ "invocation": 2,
154
+ "content": "Actual filesystem capture from invocation 2"
155
+ },
156
+ "reports": [
157
+ {
158
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
159
+ "splitDigest": "sha256:4a729491b198148335bdd5b8f6429d48611d3b44480f1982e77f3a91e4cf2a5f",
160
+ "seed": 42,
161
+ "reps": 1,
162
+ "startedAt": "2026-10-01T16:47:43.722Z",
163
+ "endedAt": "2026-10-01T16:47:43.723Z",
164
+ "durationMs": 1,
165
+ "cells": [
166
+ {
167
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
168
+ "cellId": "capture-retention:0",
169
+ "scenarioId": "capture-retention",
170
+ "rep": 0,
171
+ "artifact": null,
172
+ "judgeScores": {},
173
+ "costUsd": 0,
174
+ "costProvenance": {
175
+ "kind": "observed",
176
+ "usd": 0
177
+ },
178
+ "costCallIds": [],
179
+ "tokenUsage": {
180
+ "input": 0,
181
+ "output": 0
182
+ },
183
+ "durationMs": 1,
184
+ "seed": 42,
185
+ "cached": false,
186
+ "errorStage": "dispatch",
187
+ "error": "Operational interruption after native artifact capture"
188
+ }
189
+ ],
190
+ "aggregates": {
191
+ "byJudge": {},
192
+ "byScenario": {},
193
+ "cost": {
194
+ "totalCalls": 0,
195
+ "pendingCalls": 0,
196
+ "unresolvedCalls": 0,
197
+ "reservedCostUsd": 0,
198
+ "inputTokens": 0,
199
+ "outputTokens": 0,
200
+ "reasoningTokens": 0,
201
+ "cachedTokens": 0,
202
+ "cacheWriteTokens": 0,
203
+ "totalCostUsd": 0,
204
+ "costProvenance": {
205
+ "kind": "observed",
206
+ "usd": 0
207
+ },
208
+ "byChannel": [],
209
+ "unpricedModels": [],
210
+ "fullyPriced": true,
211
+ "usageComplete": true,
212
+ "accountingComplete": true,
213
+ "incompleteReasons": []
214
+ },
215
+ "cellsExecuted": 0,
216
+ "cellsSkipped": 0,
217
+ "cellsCached": 0,
218
+ "cellsFailed": 1,
219
+ "cellsDispatchFailed": 1,
220
+ "cellsJudgeFailed": 0,
221
+ "cellsUnclassifiedFailed": 0
222
+ },
223
+ "runDir": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume",
224
+ "artifactsByPath": {
225
+ "capture-retention:0/captured-response.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/captured-response.json",
226
+ "capture-retention:0/failure-receipt.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/failure-receipt.json"
227
+ },
228
+ "scenarios": [
229
+ {
230
+ "id": "capture-retention",
231
+ "kind": "operational",
232
+ "scenarioDigest": "sha256:955e060f603d0f2e9cd84b8426b05de1faab5b9dbbefdc5d494834afdcb56fc9"
233
+ }
234
+ ]
235
+ },
236
+ {
237
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
238
+ "splitDigest": "sha256:4a729491b198148335bdd5b8f6429d48611d3b44480f1982e77f3a91e4cf2a5f",
239
+ "seed": 42,
240
+ "reps": 1,
241
+ "startedAt": "2026-10-01T16:47:43.723Z",
242
+ "endedAt": "2026-10-01T16:47:43.979Z",
243
+ "durationMs": 256,
244
+ "cells": [
245
+ {
246
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
247
+ "cellId": "capture-retention:0",
248
+ "scenarioId": "capture-retention",
249
+ "rep": 0,
250
+ "artifact": {
251
+ "cellId": "capture-retention:0",
252
+ "runAttemptId": "cc7546fa-7b18-4a50-8444-204439c84bae",
253
+ "invocation": 2,
254
+ "content": "Actual filesystem capture from invocation 2"
255
+ },
256
+ "judgeScores": {},
257
+ "costUsd": 0,
258
+ "costProvenance": {
259
+ "kind": "observed",
260
+ "usd": 0
261
+ },
262
+ "costCallIds": [],
263
+ "tokenUsage": {
264
+ "input": 0,
265
+ "output": 0
266
+ },
267
+ "durationMs": 256,
268
+ "seed": 42,
269
+ "cached": false
270
+ }
271
+ ],
272
+ "aggregates": {
273
+ "byJudge": {},
274
+ "byScenario": {},
275
+ "cost": {
276
+ "totalCalls": 0,
277
+ "pendingCalls": 0,
278
+ "unresolvedCalls": 0,
279
+ "reservedCostUsd": 0,
280
+ "inputTokens": 0,
281
+ "outputTokens": 0,
282
+ "reasoningTokens": 0,
283
+ "cachedTokens": 0,
284
+ "cacheWriteTokens": 0,
285
+ "totalCostUsd": 0,
286
+ "costProvenance": {
287
+ "kind": "observed",
288
+ "usd": 0
289
+ },
290
+ "byChannel": [],
291
+ "unpricedModels": [],
292
+ "fullyPriced": true,
293
+ "usageComplete": true,
294
+ "accountingComplete": true,
295
+ "incompleteReasons": []
296
+ },
297
+ "cellsExecuted": 1,
298
+ "cellsSkipped": 0,
299
+ "cellsCached": 0,
300
+ "cellsFailed": 0,
301
+ "cellsDispatchFailed": 0,
302
+ "cellsJudgeFailed": 0,
303
+ "cellsUnclassifiedFailed": 0
304
+ },
305
+ "runDir": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume",
306
+ "artifactsByPath": {
307
+ "capture-retention:0/captured-response.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/captured-response.json"
308
+ },
309
+ "scenarios": [
310
+ {
311
+ "id": "capture-retention",
312
+ "kind": "operational",
313
+ "scenarioDigest": "sha256:955e060f603d0f2e9cd84b8426b05de1faab5b9dbbefdc5d494834afdcb56fc9"
314
+ }
315
+ ]
316
+ }
317
+ ],
318
+ "modelInference": false,
319
+ "researchUnits": 0
320
+ }
321
+ }