@tangle-network/agent-eval 0.203.1 → 0.204.0

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 (246) hide show
  1. package/CHANGELOG.md +8 -0
  2. package/dist/adapters/http.d.ts +2 -2
  3. package/dist/analyst/index.d.ts +6 -6
  4. package/dist/analyst/index.js +5 -5
  5. package/dist/{benchmark-command-6OBcB0sG.js → benchmark-command-Jv_puUGM.js} +5 -5
  6. package/dist/{benchmark-command-6OBcB0sG.js.map → benchmark-command-Jv_puUGM.js.map} +1 -1
  7. package/dist/benchmarks/index.d.ts +4 -4
  8. package/dist/benchmarks/index.js +2 -2
  9. package/dist/campaign/index.d.ts +4 -4
  10. package/dist/campaign/index.js +3 -3
  11. package/dist/{campaign-BbObY2c6.js → campaign-DYhg4SjN.js} +4 -4
  12. package/dist/{campaign-BbObY2c6.js.map → campaign-DYhg4SjN.js.map} +1 -1
  13. package/dist/cli.js +1 -1
  14. package/dist/contract/index.d.ts +7 -7
  15. package/dist/contract/index.js +4 -4
  16. package/dist/{default-registry-CxEBVA6W.d.ts → default-registry-BHEfZHQd.d.ts} +3 -3
  17. package/dist/{default-registry-CxEBVA6W.d.ts.map → default-registry-BHEfZHQd.d.ts.map} +1 -1
  18. package/dist/{default-registry-wInsQWlQ.js → default-registry-BthquIoC.js} +2 -2
  19. package/dist/{default-registry-wInsQWlQ.js.map → default-registry-BthquIoC.js.map} +1 -1
  20. package/dist/{define-agent-eval-Da8mHyc7.js → define-agent-eval-B25Cc3ki.js} +2 -2
  21. package/dist/{define-agent-eval-Da8mHyc7.js.map → define-agent-eval-B25Cc3ki.js.map} +1 -1
  22. package/dist/{define-agent-eval-BbEXdM3H.d.ts → define-agent-eval-D8bPoBM5.d.ts} +5 -5
  23. package/dist/{define-agent-eval-BbEXdM3H.d.ts.map → define-agent-eval-D8bPoBM5.d.ts.map} +1 -1
  24. package/dist/{dspy-rlm-engine-D0h-P2Mz.js → dspy-rlm-engine-DCQKNQMn.js} +2 -2
  25. package/dist/{dspy-rlm-engine-D0h-P2Mz.js.map → dspy-rlm-engine-DCQKNQMn.js.map} +1 -1
  26. package/dist/{engine-CaSqEVlL.d.ts → engine-F_PvwesR.d.ts} +2 -2
  27. package/dist/{engine-CaSqEVlL.d.ts.map → engine-F_PvwesR.d.ts.map} +1 -1
  28. package/dist/evaluation.d.ts +1 -1
  29. package/dist/experiment/index.d.ts +1 -1
  30. package/dist/{index-Ce2HACcP.d.ts → index-B8n12TR2.d.ts} +9 -11
  31. package/dist/index-B8n12TR2.d.ts.map +1 -0
  32. package/dist/{index-CIkxRsLS.d.ts → index-C9l_-23M.d.ts} +3 -3
  33. package/dist/{index-CIkxRsLS.d.ts.map → index-C9l_-23M.d.ts.map} +1 -1
  34. package/dist/{index-CGAwP9l3.d.ts → index-CG7mtu_G.d.ts} +6 -6
  35. package/dist/{index-CGAwP9l3.d.ts.map → index-CG7mtu_G.d.ts.map} +1 -1
  36. package/dist/index.d.ts +10 -10
  37. package/dist/index.js +10 -10
  38. package/dist/jev.d.ts +1 -1
  39. package/dist/{kind-factory-CdPPHtGZ.js → kind-factory-Cn1lbsAd.js} +5 -5
  40. package/dist/kind-factory-Cn1lbsAd.js.map +1 -0
  41. package/dist/{llm-judge-EUMHOZOQ.js → llm-judge-DyZdrp6I.js} +54 -12
  42. package/dist/llm-judge-DyZdrp6I.js.map +1 -0
  43. package/dist/{matrix-BqHiMKIj.d.ts → matrix-W1lbSx72.d.ts} +2 -2
  44. package/dist/{matrix-BqHiMKIj.d.ts.map → matrix-W1lbSx72.d.ts.map} +1 -1
  45. package/dist/multishot/golden/index.d.ts +1 -1
  46. package/dist/multishot/index.d.ts +2 -2
  47. package/dist/openapi.json +1 -1
  48. package/dist/{produced-state-g9BPgu4D.js → produced-state-DLToUXrD.js} +2 -2
  49. package/dist/{produced-state-g9BPgu4D.js.map → produced-state-DLToUXrD.js.map} +1 -1
  50. package/dist/rl.d.ts +2 -2
  51. package/dist/search/index.d.ts +2 -2
  52. package/dist/{search-kernel-C5jua_UB.d.ts → search-kernel-DNpsHb8P.d.ts} +2 -2
  53. package/dist/{search-kernel-C5jua_UB.d.ts.map → search-kernel-DNpsHb8P.d.ts.map} +1 -1
  54. package/dist/{semantic-concept-judge-BgWxa4L_.js → semantic-concept-judge-BbiYuv7U.js} +3 -3
  55. package/dist/{semantic-concept-judge-BgWxa4L_.js.map → semantic-concept-judge-BbiYuv7U.js.map} +1 -1
  56. package/dist/{skillopt-optimization-method-DZrdQGZl.js → skillopt-optimization-method-Dz5CGZb8.js} +2 -2
  57. package/dist/{skillopt-optimization-method-DZrdQGZl.js.map → skillopt-optimization-method-Dz5CGZb8.js.map} +1 -1
  58. package/dist/{statistical-heldout-CJYAO-4a.d.ts → statistical-heldout-Dq3pnmxd.d.ts} +2 -2
  59. package/dist/{statistical-heldout-CJYAO-4a.d.ts.map → statistical-heldout-Dq3pnmxd.d.ts.map} +1 -1
  60. package/dist/{store-otlp-yd9lDziN.js → store-otlp-BA7G1Du-.js} +44 -11
  61. package/dist/store-otlp-BA7G1Du-.js.map +1 -0
  62. package/dist/{store-tool-spans-fIE31bU8.d.ts → store-tool-spans-BYIarVrG.d.ts} +19 -10
  63. package/dist/{store-tool-spans-fIE31bU8.d.ts.map → store-tool-spans-BYIarVrG.d.ts.map} +1 -1
  64. package/dist/{store-tool-spans-D5kOU0mr.js → store-tool-spans-DKoVbE-w.js} +3 -3
  65. package/dist/{store-tool-spans-D5kOU0mr.js.map → store-tool-spans-DKoVbE-w.js.map} +1 -1
  66. package/dist/{tool-groups-DP8b5kjF.d.ts → tool-groups-B7_jUPHp.d.ts} +2 -2
  67. package/dist/tool-groups-B7_jUPHp.d.ts.map +1 -0
  68. package/dist/{trace-questions-Cd0Fyhbv.d.ts → trace-questions-Dd3AMf-U.d.ts} +2 -2
  69. package/dist/{trace-questions-Cd0Fyhbv.d.ts.map → trace-questions-Dd3AMf-U.d.ts.map} +1 -1
  70. package/dist/trace-repair/index.d.ts +1 -1
  71. package/dist/traces.d.ts +3 -3
  72. package/dist/traces.js +4 -4
  73. package/dist/{types-hH9APahd.d.ts → types-DZQpUJse.d.ts} +2 -2
  74. package/dist/{types-hH9APahd.d.ts.map → types-DZQpUJse.d.ts.map} +1 -1
  75. package/dist/{types-Duc6xOoW.d.ts → types-ZUy5HGY5.d.ts} +9 -3
  76. package/dist/{types-Duc6xOoW.d.ts.map → types-ZUy5HGY5.d.ts.map} +1 -1
  77. package/docs/eval-surface-map.md +12 -2
  78. package/docs/proofs/campaign-attempt-retention-20261001/README.md +70 -0
  79. 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
  80. 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
  81. 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
  82. 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
  83. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-judge-attribution/attribution_0/cached-result.json +1 -0
  84. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-judge-attribution/attribution_0/latest-attempt.json +1 -0
  85. 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
  86. 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
  87. 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
  88. 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
  89. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/cached-result.json +1 -0
  90. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/captured-response.json +6 -0
  91. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/failure-receipt.json +58 -0
  92. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/latest-attempt.json +1 -0
  93. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-legacy/capture-retention_0/spans.jsonl +1 -0
  94. 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
  95. 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
  96. 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
  97. 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
  98. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/baseline/capture-retention_0/cached-result.json +1 -0
  99. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/baseline/capture-retention_0/latest-attempt.json +1 -0
  100. 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
  101. 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
  102. 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
  103. 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
  104. 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
  105. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/42b3fec6b7e55008/capture-retention_0/latest-attempt.json +1 -0
  106. 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
  107. 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
  108. 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
  109. 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
  110. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/87740cc101602a08/capture-retention_0/cached-result.json +1 -0
  111. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/candidates/87740cc101602a08/capture-retention_0/latest-attempt.json +1 -0
  112. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/first-interruption.json +38 -0
  113. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/19147243d263e55b1eaf1c940691947382a7cce17c5f49e4a4da765a473d2a55.json +1 -0
  114. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/5dd0d871d559d1c55b2ac04b3fbd26d62f7c9e25d7632d4542502cd292818fc0.json +1 -0
  115. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/5de45d632937e75ff90fec9f1f2ec425904d3632da71f6b26f83b1e1eb8cde5a.json +1 -0
  116. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/6caba627806e499aa3d9e156aec9d5a731a3ef30e29756d343b85b7217c77c11.json +1 -0
  117. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/ce2770851b3b7651f27cedcbad0372b9191e9a9b016665987e3ddd2ad53012b5.json +1 -0
  118. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/d8ac4ba8d9844afb4defa5cd277fe3cb944d99e58cf41c07d3ae199b6f467966.json +1 -0
  119. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/blobs/f59a02035fe96ea2f5582dd715d2e3ad8c184ae959310978962f1ac0780753bd.json +1 -0
  120. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/ledger.jsonl +23 -0
  121. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-optimization/search/ledger.jsonl.head +1 -0
  122. 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
  123. 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
  124. 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
  125. 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
  126. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-path-guard/capture-retention_0/cached-result.json +1 -0
  127. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-path-guard/capture-retention_0/latest-attempt.json +1 -0
  128. 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
  129. 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
  130. 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
  131. 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
  132. 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
  133. 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
  134. 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
  135. 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
  136. 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
  137. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/cached-result.json +1 -0
  138. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/capture-retention_0/latest-attempt.json +1 -0
  139. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-resume/observation.json +608 -0
  140. 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
  141. 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
  142. 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
  143. 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
  144. 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
  145. 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
  146. 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
  147. 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
  148. 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
  149. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/cached-result.json +1 -0
  150. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/capture-retention_0/latest-attempt.json +1 -0
  151. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-retry/observation.json +514 -0
  152. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/after-summary.json +1853 -0
  153. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/judge-attribution.json +140 -0
  154. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/qualification.log +1 -0
  155. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/qualify.mjs +165 -0
  156. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduce.mjs +39 -0
  157. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/capture-retention_0/cached-result.json +1 -0
  158. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/capture-retention_0/captured-response.json +5 -0
  159. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/capture-retention_0/failure-receipt.json +58 -0
  160. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/capture-retention_0/spans.jsonl +1 -0
  161. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-resume/observer-retained-captures.json +20 -0
  162. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/capture-retention_0/cached-result.json +1 -0
  163. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/capture-retention_0/captured-response.json +5 -0
  164. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/capture-retention_0/failure-receipt.attempt-1.json +58 -0
  165. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/capture-retention_0/spans.jsonl +1 -0
  166. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-retry/observer-retained-captures.json +20 -0
  167. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction-summary.json +315 -0
  168. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/reproduction.log +1 -0
  169. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/source-and-build.json +2409 -0
  170. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/typecheck.log +1 -0
  171. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/current/verify-package.log +340 -0
  172. 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
  173. 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
  174. 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
  175. 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
  176. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/cached-result.json +1 -0
  177. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/captured-response.json +6 -0
  178. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/failure-receipt.json +58 -0
  179. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/latest-attempt.json +1 -0
  180. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-legacy/capture-retention_0/spans.jsonl +1 -0
  181. 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
  182. 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
  183. 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
  184. 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
  185. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/baseline/capture-retention_0/cached-result.json +1 -0
  186. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/baseline/capture-retention_0/latest-attempt.json +1 -0
  187. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/first-interruption.json +5 -0
  188. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/search/blobs/5de45d632937e75ff90fec9f1f2ec425904d3632da71f6b26f83b1e1eb8cde5a.json +1 -0
  189. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/search/ledger.jsonl +7 -0
  190. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-optimization/search/ledger.jsonl.head +1 -0
  191. 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
  192. 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
  193. 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
  194. 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
  195. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-path-guard/capture-retention_0/cached-result.json +1 -0
  196. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-path-guard/capture-retention_0/latest-attempt.json +1 -0
  197. 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
  198. 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
  199. 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
  200. 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
  201. 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
  202. 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
  203. 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
  204. 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
  205. 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
  206. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/cached-result.json +1 -0
  207. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/capture-retention_0/latest-attempt.json +1 -0
  208. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-resume/observation.json +458 -0
  209. 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
  210. 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
  211. 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
  212. 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
  213. 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
  214. 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
  215. 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
  216. 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
  217. 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
  218. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/cached-result.json +1 -0
  219. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/capture-retention_0/latest-attempt.json +1 -0
  220. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/after-retry/observation.json +380 -0
  221. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/capture-retention_0/cached-result.json +1 -0
  222. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/capture-retention_0/captured-response.json +6 -0
  223. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/capture-retention_0/failure-receipt.json +58 -0
  224. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/capture-retention_0/spans.jsonl +1 -0
  225. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-resume/observation.json +198 -0
  226. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/capture-retention_0/cached-result.json +1 -0
  227. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/capture-retention_0/captured-response.json +6 -0
  228. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/capture-retention_0/failure-receipt.attempt-1.json +58 -0
  229. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/capture-retention_0/spans.jsonl +1 -0
  230. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-retry/observation.json +121 -0
  231. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/before-summary.json +321 -0
  232. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/build.attribution.log +491 -0
  233. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/build.final.log +491 -0
  234. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/build.log +495 -0
  235. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/qualification.log +18 -0
  236. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/qualification.wrong-root.log +9 -0
  237. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/qualify.mjs +148 -0
  238. package/docs/proofs/campaign-attempt-retention-20261001/artifacts/predecessor/qualify.wrong-root.mjs +148 -0
  239. package/docs/proofs/campaign-attempt-retention-20261001/manifest.json +808 -0
  240. package/docs/trace-analysis.md +10 -0
  241. package/package.json +1 -1
  242. package/dist/index-Ce2HACcP.d.ts.map +0 -1
  243. package/dist/kind-factory-CdPPHtGZ.js.map +0 -1
  244. package/dist/llm-judge-EUMHOZOQ.js.map +0 -1
  245. package/dist/store-otlp-yd9lDziN.js.map +0 -1
  246. package/dist/tool-groups-DP8b5kjF.d.ts.map +0 -1
@@ -0,0 +1,380 @@
1
+ {
2
+ "invocations": 2,
3
+ "observed": [
4
+ {
5
+ "invocation": 1,
6
+ "path": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/artifacts/captured-response.json",
7
+ "sha256": "8385bfc8995c60edfbac91635b6e5e7378d47bb66c3ae84ae0aa72ec0c50f687",
8
+ "value": {
9
+ "cellId": "capture-retention:0",
10
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
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/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/artifacts/captured-response.json",
18
+ "sha256": "88f9bc5b401b30755b797e0461a55ea3d2c13e199fe7ecfeb82d7a647909730a",
19
+ "value": {
20
+ "cellId": "capture-retention:0",
21
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
22
+ "invocation": 2,
23
+ "content": "Actual filesystem capture from invocation 2"
24
+ }
25
+ }
26
+ ],
27
+ "attempts": [
28
+ {
29
+ "identity": {
30
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
31
+ "number": 1,
32
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
33
+ "cellId": "capture-retention:0",
34
+ "scenarioId": "capture-retention",
35
+ "rep": 0,
36
+ "seed": 42,
37
+ "startedAt": "2026-10-01T17:09:52.218Z"
38
+ },
39
+ "result": {
40
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
41
+ "attempt": {
42
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
43
+ "number": 1
44
+ },
45
+ "cellId": "capture-retention:0",
46
+ "scenarioId": "capture-retention",
47
+ "rep": 0,
48
+ "artifact": null,
49
+ "judgeScores": {},
50
+ "costUsd": 0,
51
+ "costProvenance": {
52
+ "kind": "observed",
53
+ "usd": 0
54
+ },
55
+ "costCallIds": [],
56
+ "tokenUsage": {
57
+ "input": 0,
58
+ "output": 0
59
+ },
60
+ "durationMs": 1,
61
+ "seed": 42,
62
+ "cached": false,
63
+ "errorStage": "dispatch",
64
+ "error": "Operational interruption after native artifact capture"
65
+ },
66
+ "trace": [
67
+ {
68
+ "name": "native.callback.capture",
69
+ "cellId": "capture-retention:0",
70
+ "startMs": 1790874592218,
71
+ "invocation": 1,
72
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
73
+ "durationMs": 0
74
+ }
75
+ ],
76
+ "path": "after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1"
77
+ },
78
+ {
79
+ "identity": {
80
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
81
+ "number": 2,
82
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
83
+ "cellId": "capture-retention:0",
84
+ "scenarioId": "capture-retention",
85
+ "rep": 0,
86
+ "seed": 42,
87
+ "startedAt": "2026-10-01T17:09:52.220Z"
88
+ },
89
+ "result": {
90
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
91
+ "attempt": {
92
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
93
+ "number": 2
94
+ },
95
+ "cellId": "capture-retention:0",
96
+ "scenarioId": "capture-retention",
97
+ "rep": 0,
98
+ "artifact": {
99
+ "cellId": "capture-retention:0",
100
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
101
+ "invocation": 2,
102
+ "content": "Actual filesystem capture from invocation 2"
103
+ },
104
+ "judgeScores": {},
105
+ "costUsd": 0,
106
+ "costProvenance": {
107
+ "kind": "observed",
108
+ "usd": 0
109
+ },
110
+ "costCallIds": [],
111
+ "tokenUsage": {
112
+ "input": 0,
113
+ "output": 0
114
+ },
115
+ "durationMs": 0,
116
+ "seed": 42,
117
+ "cached": false,
118
+ "retryAttempts": 1
119
+ },
120
+ "trace": [
121
+ {
122
+ "name": "native.callback.capture",
123
+ "cellId": "capture-retention:0",
124
+ "startMs": 1790874592220,
125
+ "invocation": 2,
126
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
127
+ "durationMs": 0
128
+ }
129
+ ],
130
+ "path": "after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2"
131
+ }
132
+ ],
133
+ "receipt": {
134
+ "schemaVersion": 1,
135
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
136
+ "recordedAt": "2026-10-01T17:09:52.219Z",
137
+ "failure": {
138
+ "stage": "dispatch",
139
+ "error": {
140
+ "name": "Error",
141
+ "message": "Operational interruption after native artifact capture",
142
+ "stack": "Error: Operational interruption after native artifact capture\n at Object.dispatch (file:///mnt/traces/eval-attempt-artifacts-20261001/qualify.mjs:28:33)\n at async executeCell (file:///home/drew/code/_wt/eval-router-cache-usage-20261001/dist/llm-judge-BGJ-FcTy.js:487:19)\n at async file:///home/drew/code/_wt/eval-router-cache-usage-20261001/dist/llm-judge-BGJ-FcTy.js:919:15\n at async Promise.allSettled (index 0)\n at async runCampaign (file:///home/drew/code/_wt/eval-router-cache-usage-20261001/dist/llm-judge-BGJ-FcTy.js:966:22)\n at async qualify (file:///mnt/traces/eval-attempt-artifacts-20261001/qualify.mjs:32:38)\n at async file:///mnt/traces/eval-attempt-artifacts-20261001/qualify.mjs:70:96"
143
+ }
144
+ },
145
+ "cell": {
146
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
147
+ "attempt": {
148
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
149
+ "number": 1
150
+ },
151
+ "cellId": "capture-retention:0",
152
+ "scenarioId": "capture-retention",
153
+ "rep": 0,
154
+ "artifact": null,
155
+ "judgeScores": {},
156
+ "costUsd": 0,
157
+ "costProvenance": {
158
+ "kind": "observed",
159
+ "usd": 0
160
+ },
161
+ "costCallIds": [],
162
+ "tokenUsage": {
163
+ "input": 0,
164
+ "output": 0
165
+ },
166
+ "durationMs": 1,
167
+ "seed": 42,
168
+ "cached": false,
169
+ "errorStage": "dispatch",
170
+ "error": "Operational interruption after native artifact capture"
171
+ },
172
+ "cost": {
173
+ "totalCalls": 0,
174
+ "pendingCalls": 0,
175
+ "unresolvedCalls": 0,
176
+ "reservedCostUsd": 0,
177
+ "inputTokens": 0,
178
+ "outputTokens": 0,
179
+ "reasoningTokens": 0,
180
+ "cachedTokens": 0,
181
+ "cacheWriteTokens": 0,
182
+ "totalCostUsd": 0,
183
+ "costProvenance": {
184
+ "kind": "observed",
185
+ "usd": 0
186
+ },
187
+ "byChannel": [],
188
+ "unpricedModels": [],
189
+ "fullyPriced": true,
190
+ "usageComplete": true,
191
+ "accountingComplete": true,
192
+ "incompleteReasons": []
193
+ }
194
+ },
195
+ "pointer": {
196
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
197
+ "number": 2
198
+ },
199
+ "reports": [
200
+ {
201
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
202
+ "splitDigest": "sha256:23ea149e81be5435966bd1d185776c7d2e119739830f98a47d4738bdbd46ade6",
203
+ "seed": 42,
204
+ "reps": 1,
205
+ "startedAt": "2026-10-01T17:09:52.217Z",
206
+ "endedAt": "2026-10-01T17:09:52.220Z",
207
+ "durationMs": 3,
208
+ "cells": [
209
+ {
210
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
211
+ "attempt": {
212
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
213
+ "number": 2
214
+ },
215
+ "cellId": "capture-retention:0",
216
+ "scenarioId": "capture-retention",
217
+ "rep": 0,
218
+ "artifact": {
219
+ "cellId": "capture-retention:0",
220
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
221
+ "invocation": 2,
222
+ "content": "Actual filesystem capture from invocation 2"
223
+ },
224
+ "judgeScores": {},
225
+ "costUsd": 0,
226
+ "costProvenance": {
227
+ "kind": "observed",
228
+ "usd": 0
229
+ },
230
+ "costCallIds": [],
231
+ "tokenUsage": {
232
+ "input": 0,
233
+ "output": 0
234
+ },
235
+ "durationMs": 0,
236
+ "seed": 42,
237
+ "cached": false,
238
+ "retryAttempts": 1
239
+ }
240
+ ],
241
+ "aggregates": {
242
+ "byJudge": {},
243
+ "byScenario": {},
244
+ "cost": {
245
+ "totalCalls": 0,
246
+ "pendingCalls": 0,
247
+ "unresolvedCalls": 0,
248
+ "reservedCostUsd": 0,
249
+ "inputTokens": 0,
250
+ "outputTokens": 0,
251
+ "reasoningTokens": 0,
252
+ "cachedTokens": 0,
253
+ "cacheWriteTokens": 0,
254
+ "totalCostUsd": 0,
255
+ "costProvenance": {
256
+ "kind": "observed",
257
+ "usd": 0
258
+ },
259
+ "byChannel": [],
260
+ "unpricedModels": [],
261
+ "fullyPriced": true,
262
+ "usageComplete": true,
263
+ "accountingComplete": true,
264
+ "incompleteReasons": []
265
+ },
266
+ "cellsExecuted": 1,
267
+ "cellsSkipped": 0,
268
+ "cellsCached": 0,
269
+ "cellsFailed": 0,
270
+ "cellsDispatchFailed": 0,
271
+ "cellsJudgeFailed": 0,
272
+ "cellsUnclassifiedFailed": 0
273
+ },
274
+ "runDir": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry",
275
+ "artifactsByPath": {
276
+ "capture-retention:0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/identity.json": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/identity.json",
277
+ "capture-retention:0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/artifacts/captured-response.json": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/artifacts/captured-response.json",
278
+ "capture-retention:0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/failure-receipt.json": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/failure-receipt.json",
279
+ "capture-retention:0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/result.json": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-1/result.json",
280
+ "capture-retention:0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/identity.json": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/identity.json",
281
+ "capture-retention:0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/artifacts/captured-response.json": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/artifacts/captured-response.json",
282
+ "capture-retention:0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/result.json": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry/capture-retention_0/attempts/cf34f352-67e5-4e8b-a510-0e896bcc96fc/attempt-2/result.json"
283
+ },
284
+ "scenarios": [
285
+ {
286
+ "id": "capture-retention",
287
+ "kind": "operational",
288
+ "scenarioDigest": "sha256:70a52f79806918ce9e4833c4ed81360245988fced43a4605ab703d7afacb20a3"
289
+ }
290
+ ]
291
+ }
292
+ ],
293
+ "cacheReuse": {
294
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
295
+ "splitDigest": "sha256:23ea149e81be5435966bd1d185776c7d2e119739830f98a47d4738bdbd46ade6",
296
+ "seed": 42,
297
+ "reps": 1,
298
+ "startedAt": "2026-10-01T17:09:52.221Z",
299
+ "endedAt": "2026-10-01T17:09:52.221Z",
300
+ "durationMs": 0,
301
+ "cells": [
302
+ {
303
+ "manifestHash": "6d4d16fdd6cbaa1119fc301e329b128e6485461e9bc013bdbeaea9ec0270b19c",
304
+ "attempt": {
305
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
306
+ "number": 2
307
+ },
308
+ "cellId": "capture-retention:0",
309
+ "scenarioId": "capture-retention",
310
+ "rep": 0,
311
+ "artifact": {
312
+ "cellId": "capture-retention:0",
313
+ "runAttemptId": "cf34f352-67e5-4e8b-a510-0e896bcc96fc",
314
+ "invocation": 2,
315
+ "content": "Actual filesystem capture from invocation 2"
316
+ },
317
+ "judgeScores": {},
318
+ "costUsd": 0,
319
+ "costProvenance": {
320
+ "kind": "observed",
321
+ "usd": 0
322
+ },
323
+ "costCallIds": [],
324
+ "tokenUsage": {
325
+ "input": 0,
326
+ "output": 0
327
+ },
328
+ "durationMs": 0,
329
+ "seed": 42,
330
+ "cached": true,
331
+ "retryAttempts": 1
332
+ }
333
+ ],
334
+ "aggregates": {
335
+ "byJudge": {},
336
+ "byScenario": {},
337
+ "cost": {
338
+ "totalCalls": 0,
339
+ "pendingCalls": 0,
340
+ "unresolvedCalls": 0,
341
+ "reservedCostUsd": 0,
342
+ "inputTokens": 0,
343
+ "outputTokens": 0,
344
+ "reasoningTokens": 0,
345
+ "cachedTokens": 0,
346
+ "cacheWriteTokens": 0,
347
+ "totalCostUsd": 0,
348
+ "costProvenance": {
349
+ "kind": "observed",
350
+ "usd": 0
351
+ },
352
+ "byChannel": [],
353
+ "unpricedModels": [],
354
+ "fullyPriced": true,
355
+ "usageComplete": true,
356
+ "accountingComplete": true,
357
+ "incompleteReasons": []
358
+ },
359
+ "cellsExecuted": 1,
360
+ "cellsSkipped": 0,
361
+ "cellsCached": 1,
362
+ "cellsFailed": 0,
363
+ "cellsDispatchFailed": 0,
364
+ "cellsJudgeFailed": 0,
365
+ "cellsUnclassifiedFailed": 0
366
+ },
367
+ "runDir": "/mnt/traces/eval-attempt-artifacts-20261001/after-retry",
368
+ "artifactsByPath": {},
369
+ "scenarios": [
370
+ {
371
+ "id": "capture-retention",
372
+ "kind": "operational",
373
+ "scenarioDigest": "sha256:70a52f79806918ce9e4833c4ed81360245988fced43a4605ab703d7afacb20a3"
374
+ }
375
+ ]
376
+ },
377
+ "firstContentStillPresent": true,
378
+ "modelInference": false,
379
+ "researchUnits": 0
380
+ }
@@ -0,0 +1 @@
1
+ {"manifestHash":"6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7","cellId":"capture-retention:0","scenarioId":"capture-retention","rep":0,"artifact":{"cellId":"capture-retention:0","runAttemptId":"cc7546fa-7b18-4a50-8444-204439c84bae","invocation":2,"content":"Actual filesystem capture from invocation 2"},"judgeScores":{},"costUsd":0,"costProvenance":{"kind":"observed","usd":0},"costCallIds":[],"tokenUsage":{"input":0,"output":0},"durationMs":256,"seed":42,"cached":false}
@@ -0,0 +1,6 @@
1
+ {
2
+ "cellId": "capture-retention:0",
3
+ "runAttemptId": "cc7546fa-7b18-4a50-8444-204439c84bae",
4
+ "invocation": 2,
5
+ "content": "Actual filesystem capture from invocation 2"
6
+ }
@@ -0,0 +1,58 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "runAttemptId": "08005dbd-35ff-488f-8942-22732fc5f036",
4
+ "recordedAt": "2026-10-01T16:47:43.723Z",
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":1790873263979,"invocation":2,"durationMs":0}
@@ -0,0 +1,198 @@
1
+ {
2
+ "invocations": 2,
3
+ "observed": [
4
+ {
5
+ "invocation": 1,
6
+ "path": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/captured-response.json",
7
+ "sha256": "36f08e9a29651e4506af2c01fa13df81fff0711f1c53f3f4633f79397b90c569",
8
+ "value": {
9
+ "cellId": "capture-retention:0",
10
+ "runAttemptId": "08005dbd-35ff-488f-8942-22732fc5f036",
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-resume/capture-retention_0/captured-response.json",
18
+ "sha256": "bd867bf7291384d653ab799dc2eebf768878ca3a8681fa869684d6da0808cfd7",
19
+ "value": {
20
+ "cellId": "capture-retention:0",
21
+ "runAttemptId": "cc7546fa-7b18-4a50-8444-204439c84bae",
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": "cc7546fa-7b18-4a50-8444-204439c84bae",
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": "2026-10-01T16:47:43.722Z",
41
+ "endedAt": "2026-10-01T16:47:43.723Z",
42
+ "durationMs": 1,
43
+ "cells": [
44
+ {
45
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
46
+ "cellId": "capture-retention:0",
47
+ "scenarioId": "capture-retention",
48
+ "rep": 0,
49
+ "artifact": null,
50
+ "judgeScores": {},
51
+ "costUsd": 0,
52
+ "costProvenance": {
53
+ "kind": "observed",
54
+ "usd": 0
55
+ },
56
+ "costCallIds": [],
57
+ "tokenUsage": {
58
+ "input": 0,
59
+ "output": 0
60
+ },
61
+ "durationMs": 1,
62
+ "seed": 42,
63
+ "cached": false,
64
+ "errorStage": "dispatch",
65
+ "error": "Operational interruption after native artifact capture"
66
+ }
67
+ ],
68
+ "aggregates": {
69
+ "byJudge": {},
70
+ "byScenario": {},
71
+ "cost": {
72
+ "totalCalls": 0,
73
+ "pendingCalls": 0,
74
+ "unresolvedCalls": 0,
75
+ "reservedCostUsd": 0,
76
+ "inputTokens": 0,
77
+ "outputTokens": 0,
78
+ "reasoningTokens": 0,
79
+ "cachedTokens": 0,
80
+ "cacheWriteTokens": 0,
81
+ "totalCostUsd": 0,
82
+ "costProvenance": {
83
+ "kind": "observed",
84
+ "usd": 0
85
+ },
86
+ "byChannel": [],
87
+ "unpricedModels": [],
88
+ "fullyPriced": true,
89
+ "usageComplete": true,
90
+ "accountingComplete": true,
91
+ "incompleteReasons": []
92
+ },
93
+ "cellsExecuted": 0,
94
+ "cellsSkipped": 0,
95
+ "cellsCached": 0,
96
+ "cellsFailed": 1,
97
+ "cellsDispatchFailed": 1,
98
+ "cellsJudgeFailed": 0,
99
+ "cellsUnclassifiedFailed": 0
100
+ },
101
+ "runDir": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume",
102
+ "artifactsByPath": {
103
+ "capture-retention:0/captured-response.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/captured-response.json",
104
+ "capture-retention:0/failure-receipt.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/failure-receipt.json"
105
+ },
106
+ "scenarios": [
107
+ {
108
+ "id": "capture-retention",
109
+ "kind": "operational",
110
+ "scenarioDigest": "sha256:955e060f603d0f2e9cd84b8426b05de1faab5b9dbbefdc5d494834afdcb56fc9"
111
+ }
112
+ ]
113
+ },
114
+ {
115
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
116
+ "splitDigest": "sha256:4a729491b198148335bdd5b8f6429d48611d3b44480f1982e77f3a91e4cf2a5f",
117
+ "seed": 42,
118
+ "reps": 1,
119
+ "startedAt": "2026-10-01T16:47:43.723Z",
120
+ "endedAt": "2026-10-01T16:47:43.979Z",
121
+ "durationMs": 256,
122
+ "cells": [
123
+ {
124
+ "manifestHash": "6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7",
125
+ "cellId": "capture-retention:0",
126
+ "scenarioId": "capture-retention",
127
+ "rep": 0,
128
+ "artifact": {
129
+ "cellId": "capture-retention:0",
130
+ "runAttemptId": "cc7546fa-7b18-4a50-8444-204439c84bae",
131
+ "invocation": 2,
132
+ "content": "Actual filesystem capture from invocation 2"
133
+ },
134
+ "judgeScores": {},
135
+ "costUsd": 0,
136
+ "costProvenance": {
137
+ "kind": "observed",
138
+ "usd": 0
139
+ },
140
+ "costCallIds": [],
141
+ "tokenUsage": {
142
+ "input": 0,
143
+ "output": 0
144
+ },
145
+ "durationMs": 256,
146
+ "seed": 42,
147
+ "cached": false
148
+ }
149
+ ],
150
+ "aggregates": {
151
+ "byJudge": {},
152
+ "byScenario": {},
153
+ "cost": {
154
+ "totalCalls": 0,
155
+ "pendingCalls": 0,
156
+ "unresolvedCalls": 0,
157
+ "reservedCostUsd": 0,
158
+ "inputTokens": 0,
159
+ "outputTokens": 0,
160
+ "reasoningTokens": 0,
161
+ "cachedTokens": 0,
162
+ "cacheWriteTokens": 0,
163
+ "totalCostUsd": 0,
164
+ "costProvenance": {
165
+ "kind": "observed",
166
+ "usd": 0
167
+ },
168
+ "byChannel": [],
169
+ "unpricedModels": [],
170
+ "fullyPriced": true,
171
+ "usageComplete": true,
172
+ "accountingComplete": true,
173
+ "incompleteReasons": []
174
+ },
175
+ "cellsExecuted": 1,
176
+ "cellsSkipped": 0,
177
+ "cellsCached": 0,
178
+ "cellsFailed": 0,
179
+ "cellsDispatchFailed": 0,
180
+ "cellsJudgeFailed": 0,
181
+ "cellsUnclassifiedFailed": 0
182
+ },
183
+ "runDir": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume",
184
+ "artifactsByPath": {
185
+ "capture-retention:0/captured-response.json": "/mnt/traces/eval-attempt-artifacts-20261001/before-resume/capture-retention_0/captured-response.json"
186
+ },
187
+ "scenarios": [
188
+ {
189
+ "id": "capture-retention",
190
+ "kind": "operational",
191
+ "scenarioDigest": "sha256:955e060f603d0f2e9cd84b8426b05de1faab5b9dbbefdc5d494834afdcb56fc9"
192
+ }
193
+ ]
194
+ }
195
+ ],
196
+ "modelInference": false,
197
+ "researchUnits": 0
198
+ }
@@ -0,0 +1 @@
1
+ {"manifestHash":"6e492a4dc01bf06d2f7e169cdde455d0b0416e34bd4396c1ec7f72f795d57fa7","cellId":"capture-retention:0","scenarioId":"capture-retention","rep":0,"artifact":{"cellId":"capture-retention:0","runAttemptId":"64928c35-e5f2-4ae6-a4c1-266088c5ecf9","invocation":2,"content":"Actual filesystem capture from invocation 2"},"judgeScores":{},"costUsd":0,"costProvenance":{"kind":"observed","usd":0},"costCallIds":[],"tokenUsage":{"input":0,"output":0},"durationMs":0,"seed":42,"cached":false,"retryAttempts":1}
@@ -0,0 +1,6 @@
1
+ {
2
+ "cellId": "capture-retention:0",
3
+ "runAttemptId": "64928c35-e5f2-4ae6-a4c1-266088c5ecf9",
4
+ "invocation": 2,
5
+ "content": "Actual filesystem capture from invocation 2"
6
+ }