@tangle-network/agent-eval 0.216.1 → 0.217.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (521) hide show
  1. package/CHANGELOG.md +102 -57
  2. package/README.md +2 -2
  3. package/dist/adapters/http.d.ts +2 -2
  4. package/dist/{agent-profile-VFcQncbW.d.ts → agent-profile-DTt8uGP9.d.ts} +4 -17
  5. package/dist/agent-profile-DTt8uGP9.d.ts.map +1 -0
  6. package/dist/{agent-profile-cell-BK8mlqlq.js → agent-profile-cell-B1V1gUZs.js} +4 -53
  7. package/dist/agent-profile-cell-B1V1gUZs.js.map +1 -0
  8. package/dist/{agent-profile-cell-BNp-Js9F.d.ts → agent-profile-cell-BcpFbNd5.d.ts} +2 -22
  9. package/dist/agent-profile-cell-BcpFbNd5.d.ts.map +1 -0
  10. package/dist/{agreement-irr-BEWLIF3_.js → agreement-irr-BhAqjluA.js} +5 -5
  11. package/dist/agreement-irr-BhAqjluA.js.map +1 -0
  12. package/dist/analyst/index.d.ts +36 -169
  13. package/dist/analyst/index.d.ts.map +1 -1
  14. package/dist/analyst/index.js +17 -192
  15. package/dist/analyst/index.js.map +1 -1
  16. package/dist/{analyze-runs-C84irm4i.js → analyze-runs-DqPJaJ4X.js} +225 -21
  17. package/dist/analyze-runs-DqPJaJ4X.js.map +1 -0
  18. package/dist/{analyze-runs-D68fd-su.d.ts → analyze-runs-DyeNcenW.d.ts} +5 -5
  19. package/dist/{analyze-runs-D68fd-su.d.ts.map → analyze-runs-DyeNcenW.d.ts.map} +1 -1
  20. package/dist/authenticity/index.d.ts +0 -23
  21. package/dist/authenticity/index.d.ts.map +1 -1
  22. package/dist/authenticity/index.js +1 -34
  23. package/dist/authenticity/index.js.map +1 -1
  24. package/dist/{benchmark-command-By0vh8q7.js → benchmark-command-xQK8nOI6.js} +554 -89
  25. package/dist/benchmark-command-xQK8nOI6.js.map +1 -0
  26. package/dist/benchmarks/index.d.ts +5 -6
  27. package/dist/benchmarks/index.d.ts.map +1 -1
  28. package/dist/benchmarks/index.js +4 -4
  29. package/dist/benchmarks/index.js.map +1 -1
  30. package/dist/builder-eval/index.d.ts +3 -3
  31. package/dist/builder-eval/index.js +2 -2
  32. package/dist/builder-eval/index.js.map +1 -1
  33. package/dist/campaign/index.d.ts +7 -7
  34. package/dist/campaign/index.js +15 -15
  35. package/dist/{campaign-BudZ70zo.js → campaign-CJGkxAQ6.js} +23 -530
  36. package/dist/campaign-CJGkxAQ6.js.map +1 -0
  37. package/dist/{campaign-evidence-Clrn4hBV.js → campaign-evidence-CQYw8_0H.js} +10 -18
  38. package/dist/{campaign-evidence-Clrn4hBV.js.map → campaign-evidence-CQYw8_0H.js.map} +1 -1
  39. package/dist/{canonical-B2RqLofv.js → canonical-Dq2hOQ8L.js} +2 -2
  40. package/dist/{canonical-B2RqLofv.js.map → canonical-Dq2hOQ8L.js.map} +1 -1
  41. package/dist/cell-spend-DEWR3nj-.js +90 -0
  42. package/dist/cell-spend-DEWR3nj-.js.map +1 -0
  43. package/dist/{chat-client-l-MVDlDk.js → chat-client-ldqxYYTN.js} +2 -2
  44. package/dist/{chat-client-l-MVDlDk.js.map → chat-client-ldqxYYTN.js.map} +1 -1
  45. package/dist/{chat-json-call-puMArmtW.js → chat-json-call-DavzexSp.js} +3 -2
  46. package/dist/chat-json-call-DavzexSp.js.map +1 -0
  47. package/dist/{claim-q4HQhK1G.js → claim-BPVuyHuy.js} +3 -3
  48. package/dist/{claim-q4HQhK1G.js.map → claim-BPVuyHuy.js.map} +1 -1
  49. package/dist/cli.js +113 -12
  50. package/dist/cli.js.map +1 -1
  51. package/dist/{client-BzL9niqi.d.ts → client-hwo3cJjR.d.ts} +3 -16
  52. package/dist/client-hwo3cJjR.d.ts.map +1 -0
  53. package/dist/{cluster-bootstrap-qcUWYFl-.js → cluster-bootstrap-DEwwhl0C.js} +3 -3
  54. package/dist/{cluster-bootstrap-qcUWYFl-.js.map → cluster-bootstrap-DEwwhl0C.js.map} +1 -1
  55. package/dist/{produced-state-BsDmnwxc.js → completion-verifier-B_jw6C9p.js} +9 -64
  56. package/dist/completion-verifier-B_jw6C9p.js.map +1 -0
  57. package/dist/contract/index.d.ts +12 -12
  58. package/dist/contract/index.js +25 -401
  59. package/dist/contract/index.js.map +1 -1
  60. package/dist/{cost-ledger-BP8V4kUQ.js → cost-ledger-D0352Z4d.js} +4 -8
  61. package/dist/cost-ledger-D0352Z4d.js.map +1 -0
  62. package/dist/dataset-DQqhOCPt.d.ts.map +1 -1
  63. package/dist/{default-registry-COhk9g36.js → default-registry-ClYjq3QE.js} +8 -11
  64. package/dist/default-registry-ClYjq3QE.js.map +1 -0
  65. package/dist/{default-registry-DzHiGruW.d.ts → default-registry-DXgLmoDI.d.ts} +7 -50
  66. package/dist/default-registry-DXgLmoDI.d.ts.map +1 -0
  67. package/dist/{define-agent-eval-CNTPzIkp.js → define-agent-eval-BDxNlP3D.js} +10 -10
  68. package/dist/{define-agent-eval-CNTPzIkp.js.map → define-agent-eval-BDxNlP3D.js.map} +1 -1
  69. package/dist/{define-agent-eval-WSck0CZJ.d.ts → define-agent-eval-BIkH_gAR.d.ts} +8 -8
  70. package/dist/define-agent-eval-BIkH_gAR.d.ts.map +1 -0
  71. package/dist/{descriptive-DboxPZrG.js → descriptive-CVNy48rR.js} +2 -2
  72. package/dist/{descriptive-DboxPZrG.js.map → descriptive-CVNy48rR.js.map} +1 -1
  73. package/dist/diagnosis/index.d.ts +4 -14
  74. package/dist/diagnosis/index.d.ts.map +1 -1
  75. package/dist/diagnosis/index.js +67 -28
  76. package/dist/diagnosis/index.js.map +1 -1
  77. package/dist/{dspy-rlm-engine-LRCu61m5.js → dspy-rlm-engine-DhdCr1Dc.js} +5 -10
  78. package/dist/dspy-rlm-engine-DhdCr1Dc.js.map +1 -0
  79. package/dist/{emitter-HcCmFQl_.d.ts → emitter-DABYYTcH.d.ts} +5 -5
  80. package/dist/emitter-DABYYTcH.d.ts.map +1 -0
  81. package/dist/emitter-DbMXUIVP.js.map +1 -1
  82. package/dist/{engine-3A_4jOlI.d.ts → engine-BvZ0R-36.d.ts} +17 -21
  83. package/dist/engine-BvZ0R-36.d.ts.map +1 -0
  84. package/dist/{equal-terms-BtdXayCJ.js → equal-terms-DbPGcVtI.js} +2 -2
  85. package/dist/equal-terms-DbPGcVtI.js.map +1 -0
  86. package/dist/{errors-DVZiqS7K.js → errors-BcOs5MKW.js} +2 -8
  87. package/dist/{errors-DVZiqS7K.js.map → errors-BcOs5MKW.js.map} +1 -1
  88. package/dist/{eval-campaign-90jeaCAI.js → eval-campaign-BLEfBGbA.js} +6 -6
  89. package/dist/{eval-campaign-90jeaCAI.js.map → eval-campaign-BLEfBGbA.js.map} +1 -1
  90. package/dist/{evaluation-6Yoi74gM.d.ts → evaluation-jTjC_QQD.d.ts} +7 -7
  91. package/dist/evaluation-jTjC_QQD.d.ts.map +1 -0
  92. package/dist/evaluation.d.ts +2 -2
  93. package/dist/evaluation.js +1 -1
  94. package/dist/evaluation.js.map +1 -1
  95. package/dist/{exact-types-ClugMJfI.d.ts → exact-types-CflbJ9f3.d.ts} +2 -2
  96. package/dist/{exact-types-ClugMJfI.d.ts.map → exact-types-CflbJ9f3.d.ts.map} +1 -1
  97. package/dist/{exec-ChJ6d5if.js → exec-CpbtOXVt.js} +2 -24
  98. package/dist/{exec-ChJ6d5if.js.map → exec-CpbtOXVt.js.map} +1 -1
  99. package/dist/execution-tracks-CpgFPpS5.js.map +1 -1
  100. package/dist/experiment/index.d.ts +9 -112
  101. package/dist/experiment/index.d.ts.map +1 -1
  102. package/dist/experiment/index.js +149 -241
  103. package/dist/experiment/index.js.map +1 -1
  104. package/dist/{exporters-X4xwla8A.js → exporters-Cl6IeNAu.js} +3 -3
  105. package/dist/exporters-Cl6IeNAu.js.map +1 -0
  106. package/dist/{exporters-ChTnR90l.d.ts → exporters-Dk3oEbK_.d.ts} +2 -4
  107. package/dist/{exporters-ChTnR90l.d.ts.map → exporters-Dk3oEbK_.d.ts.map} +1 -1
  108. package/dist/{external-optimizer-process-BjMGUuds.js → external-optimizer-process-KVFGvYX1.js} +4 -3
  109. package/dist/external-optimizer-process-KVFGvYX1.js.map +1 -0
  110. package/dist/{external-optimizer-subprocess-BqW0hHcI.js → external-optimizer-subprocess-XIHBOSKt.js} +9 -11
  111. package/dist/external-optimizer-subprocess-XIHBOSKt.js.map +1 -0
  112. package/dist/{extract-usage-BrnzRJ6H.js → extract-usage-BZLU01kR.js} +2 -23
  113. package/dist/{extract-usage-BrnzRJ6H.js.map → extract-usage-BZLU01kR.js.map} +1 -1
  114. package/dist/{failure-cluster-CbgEDcFJ.d.ts → failure-cluster-DN0t63Z0.d.ts} +4 -43
  115. package/dist/failure-cluster-DN0t63Z0.d.ts.map +1 -0
  116. package/dist/{failure-taxonomy-CjabTATj.js → failure-taxonomy-Bx5oWqaW.js} +2 -19
  117. package/dist/{failure-taxonomy-CjabTATj.js.map → failure-taxonomy-Bx5oWqaW.js.map} +1 -1
  118. package/dist/{feedback-trajectory-C4EG0nNH.d.ts → feedback-trajectory-BWmhRBGu.d.ts} +7 -9
  119. package/dist/feedback-trajectory-BWmhRBGu.d.ts.map +1 -0
  120. package/dist/{semantic-concept-judge-BQF8te0T.js → findings-store-BMVQtEsm.js} +9 -249
  121. package/dist/findings-store-BMVQtEsm.js.map +1 -0
  122. package/dist/fuzz.d.ts +19 -62
  123. package/dist/fuzz.d.ts.map +1 -1
  124. package/dist/fuzz.js +62 -108
  125. package/dist/fuzz.js.map +1 -1
  126. package/dist/{hf-dataset-BR2yhuNn.js → hf-dataset-D9f7-oX7.js} +4 -24
  127. package/dist/hf-dataset-D9f7-oX7.js.map +1 -0
  128. package/dist/hosted/index.d.ts +2 -2
  129. package/dist/hosted/index.js +2 -2
  130. package/dist/{index-DHKEAv3s.d.ts → index-9jJ2fKSX.d.ts} +2 -64
  131. package/dist/index-9jJ2fKSX.d.ts.map +1 -0
  132. package/dist/{index-DV-jSzxF.d.ts → index-BLGqZ81N.d.ts} +10 -15
  133. package/dist/{index-DV-jSzxF.d.ts.map → index-BLGqZ81N.d.ts.map} +1 -1
  134. package/dist/{index-DPcngtwt.d.ts → index-BiT6RtNH.d.ts} +11 -36
  135. package/dist/index-BiT6RtNH.d.ts.map +1 -0
  136. package/dist/{index-BO41eGj5.d.ts → index-CX-GAUpw.d.ts} +3 -7
  137. package/dist/index-CX-GAUpw.d.ts.map +1 -0
  138. package/dist/{index-BFRO6chs.d.ts → index-CiRwLv2R.d.ts} +5 -69
  139. package/dist/index-CiRwLv2R.d.ts.map +1 -0
  140. package/dist/{index-CyszSg4O.d.ts → index-ZuWx52WG.d.ts} +115 -347
  141. package/dist/index-ZuWx52WG.d.ts.map +1 -0
  142. package/dist/index.d.ts +211 -218
  143. package/dist/index.d.ts.map +1 -1
  144. package/dist/index.js +402 -1040
  145. package/dist/index.js.map +1 -1
  146. package/dist/{integrity-dLiDe2kD.js → integrity-DOd9Q86O.js} +7 -9
  147. package/dist/integrity-DOd9Q86O.js.map +1 -0
  148. package/dist/{integrity-BXOsAb3i.js → integrity-W4CADcFc.js} +3 -7
  149. package/dist/{integrity-BXOsAb3i.js.map → integrity-W4CADcFc.js.map} +1 -1
  150. package/dist/{integrity-DAMEDFaC.d.ts → integrity-_qgZLA5p.d.ts} +4 -6
  151. package/dist/{integrity-DAMEDFaC.d.ts.map → integrity-_qgZLA5p.d.ts.map} +1 -1
  152. package/dist/{internal-Epl-YBZW.js → internal-BTK91Bqt.js} +3 -3
  153. package/dist/{internal-Epl-YBZW.js.map → internal-BTK91Bqt.js.map} +1 -1
  154. package/dist/{interval-CELpye1n.js → interval-Dq9gt7jx.js} +3 -3
  155. package/dist/{interval-CELpye1n.js.map → interval-Dq9gt7jx.js.map} +1 -1
  156. package/dist/{journal-DfRz9kps.js → journal-CR4QikYp.js} +110 -110
  157. package/dist/journal-CR4QikYp.js.map +1 -0
  158. package/dist/json-BhdsJaOQ.js +111 -0
  159. package/dist/json-BhdsJaOQ.js.map +1 -0
  160. package/dist/{judge-calibration-BpCy5XQl.js → judge-calibration-BkXMIWA4.js} +3 -3
  161. package/dist/{judge-calibration-BpCy5XQl.js.map → judge-calibration-BkXMIWA4.js.map} +1 -1
  162. package/dist/{judge-gate-iY9s4L44.js → judge-gate-Co5tuh57.js} +4 -27
  163. package/dist/{judge-gate-iY9s4L44.js.map → judge-gate-Co5tuh57.js.map} +1 -1
  164. package/dist/{judge-gate-CE7CQAgt.d.ts → judge-gate-DsL0yFcb.d.ts} +8 -9
  165. package/dist/judge-gate-DsL0yFcb.d.ts.map +1 -0
  166. package/dist/{kind-factory-BobI5Jy3.js → kind-factory-Gy4fXixd.js} +88 -17
  167. package/dist/kind-factory-Gy4fXixd.js.map +1 -0
  168. package/dist/ledger-core/index.d.ts +2 -2
  169. package/dist/ledger-core/index.js +4 -4
  170. package/dist/{ledger-core-Gq7yp8lP.js → ledger-core-DrJhbms9.js} +5 -84
  171. package/dist/ledger-core-DrJhbms9.js.map +1 -0
  172. package/dist/{llm-client-CyBAoYiX.js → llm-client-BshCREn6.js} +6 -108
  173. package/dist/llm-client-BshCREn6.js.map +1 -0
  174. package/dist/{llm-judge-CG12SQJq.js → llm-judge-C8jMTNNG.js} +24 -32
  175. package/dist/llm-judge-C8jMTNNG.js.map +1 -0
  176. package/dist/matrix/index.d.ts +3 -3
  177. package/dist/matrix/index.js +3 -2
  178. package/dist/{matrix-Dm0BQW7U.js → matrix-B8l-Nsxd.js} +3 -88
  179. package/dist/matrix-B8l-Nsxd.js.map +1 -0
  180. package/dist/{matrix-DSrSxjjy.d.ts → matrix-DHe-dwVJ.d.ts} +9 -18
  181. package/dist/matrix-DHe-dwVJ.d.ts.map +1 -0
  182. package/dist/{mean-DHoMiudD.js → mean-BbA_JCzW.js} +39 -5
  183. package/dist/mean-BbA_JCzW.js.map +1 -0
  184. package/dist/meta-eval/index.d.ts +5 -5
  185. package/dist/meta-eval/index.js +10 -10
  186. package/dist/metrics-BKaPBtIG.js.map +1 -1
  187. package/dist/{mint-DNU8QPG4.d.ts → mint-BRZXuwRi.d.ts} +4 -4
  188. package/dist/{mint-DNU8QPG4.d.ts.map → mint-BRZXuwRi.d.ts.map} +1 -1
  189. package/dist/{mint-QaD5cA0u.js → mint-zszyYlpA.js} +4 -4
  190. package/dist/{mint-QaD5cA0u.js.map → mint-zszyYlpA.js.map} +1 -1
  191. package/dist/{multi-layer-verifier-BUaQ4C17.d.ts → multi-layer-verifier-DEgMUk6v.d.ts} +2 -2
  192. package/dist/{multi-layer-verifier-BUaQ4C17.d.ts.map → multi-layer-verifier-DEgMUk6v.d.ts.map} +1 -1
  193. package/dist/{multiplicity-DQUFcbW4.js → multiplicity-Sg0U7h8j.js} +2 -2
  194. package/dist/{multiplicity-DQUFcbW4.js.map → multiplicity-Sg0U7h8j.js.map} +1 -1
  195. package/dist/multishot/golden/index.d.ts +1 -23
  196. package/dist/multishot/golden/index.d.ts.map +1 -1
  197. package/dist/multishot/golden/index.js +3 -3
  198. package/dist/multishot/golden/index.js.map +1 -1
  199. package/dist/multishot/index.d.ts +3 -12
  200. package/dist/multishot/index.d.ts.map +1 -1
  201. package/dist/multishot/index.js +4 -3
  202. package/dist/multishot/index.js.map +1 -1
  203. package/dist/openapi.json +114 -10
  204. package/dist/{otel-spans-B9tUXRHF.js → otel-spans-CdN909k1.js} +3 -3
  205. package/dist/{otel-spans-B9tUXRHF.js.map → otel-spans-CdN909k1.js.map} +1 -1
  206. package/dist/{paired-arms-CwMGJsrS.js → paired-arms-Ct4LTKc1.js} +32 -9
  207. package/dist/paired-arms-Ct4LTKc1.js.map +1 -0
  208. package/dist/{paired-binary-CvpFHfKZ.js → paired-binary-B_nejA44.js} +3 -36
  209. package/dist/paired-binary-B_nejA44.js.map +1 -0
  210. package/dist/{paired-promotion-decision-DPKz8ZnF.d.ts → paired-promotion-decision-CQMJ5xGN.d.ts} +2 -34
  211. package/dist/paired-promotion-decision-CQMJ5xGN.d.ts.map +1 -0
  212. package/dist/{paired-promotion-decision-DsAPYGCm.js → paired-promotion-decision-D0SHb-ZL.js} +3 -3
  213. package/dist/{paired-promotion-decision-DsAPYGCm.js.map → paired-promotion-decision-D0SHb-ZL.js.map} +1 -1
  214. package/dist/{pareto-Cm6ndrWN.js → pareto-BzsxidFD.js} +11 -11
  215. package/dist/pareto-BzsxidFD.js.map +1 -0
  216. package/dist/pipelines/index.d.ts +16 -19
  217. package/dist/pipelines/index.d.ts.map +1 -1
  218. package/dist/pipelines/index.js +4 -68
  219. package/dist/pipelines/index.js.map +1 -1
  220. package/dist/{power-and-mde-Hj2ubb4B.js → power-and-mde-N5nU4_Ly.js} +3 -3
  221. package/dist/{power-and-mde-Hj2ubb4B.js.map → power-and-mde-N5nU4_Ly.js.map} +1 -1
  222. package/dist/{prime-protocol-CHKgA3a6.js → prime-protocol-BFgGrEMP.js} +3 -3
  223. package/dist/prime-protocol-BFgGrEMP.js.map +1 -0
  224. package/dist/{prime-protocol-HiB9HX7E.d.ts → prime-protocol-BWG2DQIk.d.ts} +3 -21
  225. package/dist/prime-protocol-BWG2DQIk.d.ts.map +1 -0
  226. package/dist/profile-cell.d.ts +2 -2
  227. package/dist/profile-cell.js +2 -2
  228. package/dist/{promotion-gate-BawrdPYr.d.ts → promotion-gate-DaY95yU6.d.ts} +7 -8
  229. package/dist/{promotion-gate-BawrdPYr.d.ts.map → promotion-gate-DaY95yU6.d.ts.map} +1 -1
  230. package/dist/{promotion-policy-KO57gbyV.js → promotion-policy-6A8osGr_.js} +4 -4
  231. package/dist/{promotion-policy-KO57gbyV.js.map → promotion-policy-6A8osGr_.js.map} +1 -1
  232. package/dist/{proposal-findings-CY1xKn_a.js → proposal-findings-BbWidvUk.js} +3 -3
  233. package/dist/proposal-findings-BbWidvUk.js.map +1 -0
  234. package/dist/{query-BUCZCK7F.js → query-B_RZ36an.js} +5 -5
  235. package/dist/query-B_RZ36an.js.map +1 -0
  236. package/dist/{query-DK1nWcmp.d.ts → query-Cmv_U8vf.d.ts} +4 -24
  237. package/dist/{query-DK1nWcmp.d.ts.map → query-Cmv_U8vf.d.ts.map} +1 -1
  238. package/dist/{random-ByUSnV9w.js → random-DDDcC7YU.js} +2 -2
  239. package/dist/{random-ByUSnV9w.js.map → random-DDDcC7YU.js.map} +1 -1
  240. package/dist/{raw-provider-sink-DoHz4JNG.js → raw-provider-sink-75w4FWBj.js} +2 -2
  241. package/dist/{raw-provider-sink-DoHz4JNG.js.map → raw-provider-sink-75w4FWBj.js.map} +1 -1
  242. package/dist/{redact-mtCCcT8z.d.ts → redact-DXdlFb_U.d.ts} +2 -3
  243. package/dist/redact-DXdlFb_U.d.ts.map +1 -0
  244. package/dist/{redact-B5xXKqQ3.js → redact-mtkTiJVk.js} +2 -7
  245. package/dist/{redact-B5xXKqQ3.js.map → redact-mtkTiJVk.js.map} +1 -1
  246. package/dist/{registry-D7_hm2fK.d.ts → registry-ssNoHzwD.d.ts} +4 -4
  247. package/dist/{registry-D7_hm2fK.d.ts.map → registry-ssNoHzwD.d.ts.map} +1 -1
  248. package/dist/{release-confidence-CpuP65S5.js → release-confidence-CYIFH-fp.js} +6 -11
  249. package/dist/release-confidence-CYIFH-fp.js.map +1 -0
  250. package/dist/{report-command-SC9nqb4M.js → render-C-w2EZ6p.js} +205 -363
  251. package/dist/render-C-w2EZ6p.js.map +1 -0
  252. package/dist/reporting.d.ts +6 -6
  253. package/dist/reporting.js +8 -8
  254. package/dist/{researcher-CEcfku-T.d.ts → researcher-0ABVIdGa.d.ts} +9 -9
  255. package/dist/{researcher-CEcfku-T.d.ts.map → researcher-0ABVIdGa.d.ts.map} +1 -1
  256. package/dist/{reward-CpCmAM8L.d.ts → reward-DrZ71vnf.d.ts} +3 -26
  257. package/dist/reward-DrZ71vnf.d.ts.map +1 -0
  258. package/dist/{reward-hacking-E0d-WVcP.js → reward-hacking-ByuETaIb.js} +3 -3
  259. package/dist/{reward-hacking-E0d-WVcP.js.map → reward-hacking-ByuETaIb.js.map} +1 -1
  260. package/dist/{reward-hacking-RVdZ6Kkt.d.ts → reward-hacking-E52wq86n.d.ts} +5 -18
  261. package/dist/reward-hacking-E52wq86n.d.ts.map +1 -0
  262. package/dist/reward-nw2xZGZG.js.map +1 -1
  263. package/dist/rl.d.ts +117 -295
  264. package/dist/rl.d.ts.map +1 -1
  265. package/dist/rl.js +27 -747
  266. package/dist/rl.js.map +1 -1
  267. package/dist/rollout/index.d.ts +5 -5
  268. package/dist/rollout/index.js +7 -8
  269. package/dist/{rollout-DZV1t2Wg.js → rollout-D6C50mfA.js} +88 -13
  270. package/dist/rollout-D6C50mfA.js.map +1 -0
  271. package/dist/{rubric-predictive-validity-DaFW70y9.js → rubric-predictive-validity-D3_oI72N.js} +3 -3
  272. package/dist/{rubric-predictive-validity-DaFW70y9.js.map → rubric-predictive-validity-D3_oI72N.js.map} +1 -1
  273. package/dist/{rubric-predictive-validity-C03EC7ZE.d.ts → rubric-predictive-validity-DiwT8PbL.d.ts} +2 -2
  274. package/dist/{rubric-predictive-validity-C03EC7ZE.d.ts.map → rubric-predictive-validity-DiwT8PbL.d.ts.map} +1 -1
  275. package/dist/{run-record-C1E24G2A.d.ts → run-record-CaxbLq6Y.d.ts} +4 -10
  276. package/dist/run-record-CaxbLq6Y.d.ts.map +1 -0
  277. package/dist/{run-record-C5e7FjhJ.js → run-record-CysKLB93.js} +3 -3
  278. package/dist/run-record-CysKLB93.js.map +1 -0
  279. package/dist/{run-record-Boc5IUTp.js → run-record-DhEJgoPz.js} +4 -4
  280. package/dist/{run-record-Boc5IUTp.js.map → run-record-DhEJgoPz.js.map} +1 -1
  281. package/dist/sandbox-harness-BlSOu4LX.d.ts.map +1 -1
  282. package/dist/{schema-CSf6qWgZ.js → schema-Bt2vLFm3.js} +2 -14
  283. package/dist/schema-Bt2vLFm3.js.map +1 -0
  284. package/dist/schema-C-ziyJD7.d.ts.map +1 -1
  285. package/dist/{schema-2g7trUwH.d.ts → schema-D6EVKzTB.d.ts} +4 -5
  286. package/dist/schema-D6EVKzTB.d.ts.map +1 -0
  287. package/dist/{schema-BuiujZ-g.js → schema-DxcKTzbi.js} +2 -2
  288. package/dist/schema-DxcKTzbi.js.map +1 -0
  289. package/dist/search/index.d.ts +3 -31
  290. package/dist/search/index.d.ts.map +1 -1
  291. package/dist/search/index.js +4 -4
  292. package/dist/{search-kernel-DyNEa6IU.d.ts → search-kernel-DxqjBxA-.d.ts} +10 -27
  293. package/dist/search-kernel-DxqjBxA-.d.ts.map +1 -0
  294. package/dist/{search-ledger-CVUGLDZp.js → search-ledger-TUvB5gWH.js} +7 -7
  295. package/dist/{search-ledger-CVUGLDZp.js.map → search-ledger-TUvB5gWH.js.map} +1 -1
  296. package/dist/{search-ledger-file-DDQUgvCg.js → search-ledger-file-UKCO2r8a.js} +4 -4
  297. package/dist/search-ledger-file-UKCO2r8a.js.map +1 -0
  298. package/dist/{search-shipper-BOSD46qv.js → search-shipper-Cw2z3-td.js} +4 -4
  299. package/dist/search-shipper-Cw2z3-td.js.map +1 -0
  300. package/dist/{search-summary-BQCSWf1g.js → search-summary-DQIvJsSB.js} +5 -5
  301. package/dist/{search-summary-BQCSWf1g.js.map → search-summary-DQIvJsSB.js.map} +1 -1
  302. package/dist/{sequential-CzK5DarL.js → sequential-BVv1sjsw.js} +2 -32
  303. package/dist/{sequential-CzK5DarL.js.map → sequential-BVv1sjsw.js.map} +1 -1
  304. package/dist/{sequential-Bf_pbE50.js → sequential-CimQrbjv.js} +5 -5
  305. package/dist/sequential-CimQrbjv.js.map +1 -0
  306. package/dist/{sequential-BhsrMupG.d.ts → sequential-KwGspfeR.d.ts} +2 -9
  307. package/dist/{sequential-BhsrMupG.d.ts.map → sequential-KwGspfeR.d.ts.map} +1 -1
  308. package/dist/{sequential-eprocess-DM_qENCl.js → sequential-eprocess-DodI6RoF.js} +2 -2
  309. package/dist/{sequential-eprocess-DM_qENCl.js.map → sequential-eprocess-DodI6RoF.js.map} +1 -1
  310. package/dist/{server-e9oWO_bN.js → server-DoVbqqtJ.js} +101 -101
  311. package/dist/server-DoVbqqtJ.js.map +1 -0
  312. package/dist/{single-run-lock-CV9Eyd_q.js → single-run-lock-U58yf8N6.js} +2 -2
  313. package/dist/{single-run-lock-CV9Eyd_q.js.map → single-run-lock-U58yf8N6.js.map} +1 -1
  314. package/dist/{skillopt-optimization-method-BiwA8nfX.js → skillopt-optimization-method-kyL94-ri.js} +17 -95
  315. package/dist/skillopt-optimization-method-kyL94-ri.js.map +1 -0
  316. package/dist/{spans-BHAUXMGN.d.ts → spans-CVngGij3.d.ts} +2 -2
  317. package/dist/{spans-BHAUXMGN.d.ts.map → spans-CVngGij3.d.ts.map} +1 -1
  318. package/dist/{statistical-heldout-42NlCNDe.js → statistical-heldout-Bksv92Th.js} +3 -3
  319. package/dist/statistical-heldout-Bksv92Th.js.map +1 -0
  320. package/dist/{statistical-heldout-CYpGaoDH.d.ts → statistical-heldout-C9AbgREN.d.ts} +8 -67
  321. package/dist/statistical-heldout-C9AbgREN.d.ts.map +1 -0
  322. package/dist/{steps-Bg5-KVx1.d.ts → steps-DlepJPwD.d.ts} +2 -56
  323. package/dist/steps-DlepJPwD.d.ts.map +1 -0
  324. package/dist/{store-C4avFjIi.d.ts → store-B3nWRy3B.d.ts} +2 -2
  325. package/dist/{store-C4avFjIi.d.ts.map → store-B3nWRy3B.d.ts.map} +1 -1
  326. package/dist/{store-otlp-DJ9dtA5x.js → store-otlp-BteDAbHK.js} +3 -3
  327. package/dist/{store-otlp-DJ9dtA5x.js.map → store-otlp-BteDAbHK.js.map} +1 -1
  328. package/dist/{store-tool-spans-CIX5arAG.js → store-tool-spans-D5l_OfTJ.js} +8 -8
  329. package/dist/store-tool-spans-D5l_OfTJ.js.map +1 -0
  330. package/dist/{store-tool-spans-DdCSPa7C.d.ts → store-tool-spans-DZS0HWVf.d.ts} +9 -18
  331. package/dist/store-tool-spans-DZS0HWVf.d.ts.map +1 -0
  332. package/dist/storyboard/index.d.ts +4 -11
  333. package/dist/storyboard/index.d.ts.map +1 -1
  334. package/dist/storyboard/index.js +1 -16
  335. package/dist/storyboard/index.js.map +1 -1
  336. package/dist/{summary-report-V_JACR4Y.js → summary-report-BsXJoYX5.js} +88 -10
  337. package/dist/summary-report-BsXJoYX5.js.map +1 -0
  338. package/dist/{summary-report-bdFDXq0b.d.ts → summary-report-DM7tlml1.d.ts} +10 -19
  339. package/dist/summary-report-DM7tlml1.d.ts.map +1 -0
  340. package/dist/supervisor-run/index.d.ts +60 -28
  341. package/dist/supervisor-run/index.d.ts.map +1 -1
  342. package/dist/supervisor-run/index.js +4 -458
  343. package/dist/supervisor-run/index.js.map +1 -1
  344. package/dist/{systemone-BomhHr2c.d.ts → systemone-Bp_Ac0p1.d.ts} +5 -5
  345. package/dist/{systemone-BomhHr2c.d.ts.map → systemone-Bp_Ac0p1.d.ts.map} +1 -1
  346. package/dist/systemone-protocol.js +1 -1
  347. package/dist/{systemone-review-CUVcQJu6.d.ts → systemone-review-CwE6JGIp.d.ts} +2 -2
  348. package/dist/{systemone-review-CUVcQJu6.d.ts.map → systemone-review-CwE6JGIp.d.ts.map} +1 -1
  349. package/dist/{systemone-review-D7sXwsqq.js → systemone-review-DzdOJ8I6.js} +3 -3
  350. package/dist/{systemone-review-D7sXwsqq.js.map → systemone-review-DzdOJ8I6.js.map} +1 -1
  351. package/dist/systemone.d.ts +5 -5
  352. package/dist/systemone.js +5 -5
  353. package/dist/systemone.js.map +1 -1
  354. package/dist/{task-failure-attributes-hEmASjix.js → task-failure-attributes-BMsblaDh.js} +3 -3
  355. package/dist/task-failure-attributes-BMsblaDh.js.map +1 -0
  356. package/dist/{terminal-record-DZyQZ3pz.js → terminal-record-78g6E4vh.js} +5 -5
  357. package/dist/terminal-record-78g6E4vh.js.map +1 -0
  358. package/dist/{tool-groups-C3NEcdCM.d.ts → tool-groups-DyNz2JZ_.d.ts} +3 -3
  359. package/dist/tool-groups-DyNz2JZ_.d.ts.map +1 -0
  360. package/dist/{tool-waste-BKgvd-TP.d.ts → tool-waste-CkjzWmeY.d.ts} +25 -28
  361. package/dist/tool-waste-CkjzWmeY.d.ts.map +1 -0
  362. package/dist/{tool-waste-BlesqTqW.js → tool-waste-DLsjS_p-.js} +5 -5
  363. package/dist/{tool-waste-BlesqTqW.js.map → tool-waste-DLsjS_p-.js.map} +1 -1
  364. package/dist/{trace-questions-CM2CAocU.d.ts → trace-questions-xxwgsuMi.d.ts} +4 -9
  365. package/dist/{trace-questions-CM2CAocU.d.ts.map → trace-questions-xxwgsuMi.d.ts.map} +1 -1
  366. package/dist/trace-repair/index.d.ts +14 -211
  367. package/dist/trace-repair/index.d.ts.map +1 -1
  368. package/dist/trace-repair/index.js +865 -981
  369. package/dist/trace-repair/index.js.map +1 -1
  370. package/dist/traces.d.ts +18 -46
  371. package/dist/traces.d.ts.map +1 -1
  372. package/dist/traces.js +13 -13
  373. package/dist/traces.js.map +1 -1
  374. package/dist/trajectory-replay/index.d.ts +3 -117
  375. package/dist/trajectory-replay/index.d.ts.map +1 -1
  376. package/dist/trajectory-replay/index.js +98 -56
  377. package/dist/trajectory-replay/index.js.map +1 -1
  378. package/dist/{tree-C1XYeXvy.js → tree-BGRglkKd.js} +13 -10
  379. package/dist/tree-BGRglkKd.js.map +1 -0
  380. package/dist/{types-B3jzCp0p.js → types-BXgASBCL.js} +2 -2
  381. package/dist/{types-B3jzCp0p.js.map → types-BXgASBCL.js.map} +1 -1
  382. package/dist/{types-C1tnkEgM.d.ts → types-CW8ewATZ.d.ts} +4 -113
  383. package/dist/types-CW8ewATZ.d.ts.map +1 -0
  384. package/dist/{types-BqkVmHfv.d.ts → types-CmXY0PQf.d.ts} +2 -4
  385. package/dist/types-CmXY0PQf.d.ts.map +1 -0
  386. package/dist/{types-C02qtnG8.d.ts → types-D-mgRzlh.d.ts} +7 -28
  387. package/dist/types-D-mgRzlh.d.ts.map +1 -0
  388. package/dist/{types-Cq8mSbq8.d.ts → types-D8GhJoHk.d.ts} +7 -9
  389. package/dist/{types-Cq8mSbq8.d.ts.map → types-D8GhJoHk.d.ts.map} +1 -1
  390. package/dist/{types-IXD2HJzu.js → types-DqFMNTgK.js} +2 -4
  391. package/dist/types-DqFMNTgK.js.map +1 -0
  392. package/dist/{types-Cbe2fWBa.d.ts → types-DtMbFw6U.d.ts} +3 -3
  393. package/dist/{types-Cbe2fWBa.d.ts.map → types-DtMbFw6U.d.ts.map} +1 -1
  394. package/dist/{verdict-Dl0tiT1X.js → verdict-BGQmxQ8A.js} +3 -3
  395. package/dist/verdict-BGQmxQ8A.js.map +1 -0
  396. package/dist/{verdict-E4eRNf7-.d.ts → verdict-C24NELtN.d.ts} +2 -15
  397. package/dist/{verdict-E4eRNf7-.d.ts.map → verdict-C24NELtN.d.ts.map} +1 -1
  398. package/dist/{verdict-cache-Bm8EKL2s.js → verdict-cache-CL_7tePD.js} +2 -2
  399. package/dist/verdict-cache-CL_7tePD.js.map +1 -0
  400. package/dist/wire/index.d.ts +31 -410
  401. package/dist/wire/index.d.ts.map +1 -1
  402. package/dist/wire/index.js +2 -2
  403. package/docs/changes/jev-evidence-review.md +1 -1
  404. package/docs/changes/jev-product-adoption.md +1 -1
  405. package/docs/changes/jev-recorded-evidence.md +1 -1
  406. package/docs/design/statistics-decisions.md +17 -17
  407. package/docs/design.md +1 -1
  408. package/docs/evaluation-integrity.md +1 -1
  409. package/docs/proofs/campaign-attempt-retention-20261001/README.md +2 -2
  410. package/docs/public-api.md +138 -529
  411. package/docs/rollout.md +1 -1
  412. package/docs/trace-repair-admission.md +1 -1
  413. package/docs/wire-protocol.md +1 -1
  414. package/package.json +1 -1
  415. package/dist/active-curriculum-B_Lc9kfO.js +0 -61
  416. package/dist/active-curriculum-B_Lc9kfO.js.map +0 -1
  417. package/dist/agent-profile-VFcQncbW.d.ts.map +0 -1
  418. package/dist/agent-profile-cell-BK8mlqlq.js.map +0 -1
  419. package/dist/agent-profile-cell-BNp-Js9F.d.ts.map +0 -1
  420. package/dist/agreement-irr-BEWLIF3_.js.map +0 -1
  421. package/dist/analyze-runs-C84irm4i.js.map +0 -1
  422. package/dist/baseline-Udi_PLuT.js +0 -259
  423. package/dist/baseline-Udi_PLuT.js.map +0 -1
  424. package/dist/benchmark-CXmVVHH2.js +0 -562
  425. package/dist/benchmark-CXmVVHH2.js.map +0 -1
  426. package/dist/benchmark-command-By0vh8q7.js.map +0 -1
  427. package/dist/campaign-BudZ70zo.js.map +0 -1
  428. package/dist/chat-json-call-puMArmtW.js.map +0 -1
  429. package/dist/claude-jsonl-dZir12m6.js +0 -86
  430. package/dist/claude-jsonl-dZir12m6.js.map +0 -1
  431. package/dist/client-BzL9niqi.d.ts.map +0 -1
  432. package/dist/cost-ledger-BP8V4kUQ.js.map +0 -1
  433. package/dist/counterfactual-CPaWN99-.d.ts +0 -60
  434. package/dist/counterfactual-CPaWN99-.d.ts.map +0 -1
  435. package/dist/counterfactual-Dn3veueY.js +0 -98
  436. package/dist/counterfactual-Dn3veueY.js.map +0 -1
  437. package/dist/default-registry-COhk9g36.js.map +0 -1
  438. package/dist/default-registry-DzHiGruW.d.ts.map +0 -1
  439. package/dist/define-agent-eval-WSck0CZJ.d.ts.map +0 -1
  440. package/dist/dspy-rlm-engine-LRCu61m5.js.map +0 -1
  441. package/dist/effect-sizes-BhzEpXMc.js +0 -82
  442. package/dist/effect-sizes-BhzEpXMc.js.map +0 -1
  443. package/dist/emitter-HcCmFQl_.d.ts.map +0 -1
  444. package/dist/engine-3A_4jOlI.d.ts.map +0 -1
  445. package/dist/equal-terms-BtdXayCJ.js.map +0 -1
  446. package/dist/evaluation-6Yoi74gM.d.ts.map +0 -1
  447. package/dist/exporters-X4xwla8A.js.map +0 -1
  448. package/dist/external-optimizer-process-BjMGUuds.js.map +0 -1
  449. package/dist/external-optimizer-subprocess-BqW0hHcI.js.map +0 -1
  450. package/dist/failure-cluster-CbgEDcFJ.d.ts.map +0 -1
  451. package/dist/feedback-trajectory-C4EG0nNH.d.ts.map +0 -1
  452. package/dist/hf-dataset-BR2yhuNn.js.map +0 -1
  453. package/dist/index-BFRO6chs.d.ts.map +0 -1
  454. package/dist/index-BO41eGj5.d.ts.map +0 -1
  455. package/dist/index-CyszSg4O.d.ts.map +0 -1
  456. package/dist/index-DHKEAv3s.d.ts.map +0 -1
  457. package/dist/index-DPcngtwt.d.ts.map +0 -1
  458. package/dist/integrity-dLiDe2kD.js.map +0 -1
  459. package/dist/journal-DfRz9kps.js.map +0 -1
  460. package/dist/judge-gate-CE7CQAgt.d.ts.map +0 -1
  461. package/dist/kind-factory-BobI5Jy3.js.map +0 -1
  462. package/dist/ledger-core-Gq7yp8lP.js.map +0 -1
  463. package/dist/llm-client-CyBAoYiX.js.map +0 -1
  464. package/dist/llm-judge-CG12SQJq.js.map +0 -1
  465. package/dist/matrix-DSrSxjjy.d.ts.map +0 -1
  466. package/dist/matrix-Dm0BQW7U.js.map +0 -1
  467. package/dist/mean-DHoMiudD.js.map +0 -1
  468. package/dist/normal-DsJZtrJc.js +0 -25
  469. package/dist/normal-DsJZtrJc.js.map +0 -1
  470. package/dist/paired-arms-CwMGJsrS.js.map +0 -1
  471. package/dist/paired-binary-CvpFHfKZ.js.map +0 -1
  472. package/dist/paired-promotion-decision-DPKz8ZnF.d.ts.map +0 -1
  473. package/dist/pareto-Cm6ndrWN.js.map +0 -1
  474. package/dist/prime-protocol-CHKgA3a6.js.map +0 -1
  475. package/dist/prime-protocol-HiB9HX7E.d.ts.map +0 -1
  476. package/dist/produced-state-BsDmnwxc.js.map +0 -1
  477. package/dist/proposal-findings-CY1xKn_a.js.map +0 -1
  478. package/dist/query-BUCZCK7F.js.map +0 -1
  479. package/dist/redact-mtCCcT8z.d.ts.map +0 -1
  480. package/dist/release-confidence-CpuP65S5.js.map +0 -1
  481. package/dist/report-command-SC9nqb4M.js.map +0 -1
  482. package/dist/reward-CpCmAM8L.d.ts.map +0 -1
  483. package/dist/reward-hacking-RVdZ6Kkt.d.ts.map +0 -1
  484. package/dist/rollout-DZV1t2Wg.js.map +0 -1
  485. package/dist/run-record-C1E24G2A.d.ts.map +0 -1
  486. package/dist/run-record-C5e7FjhJ.js.map +0 -1
  487. package/dist/schema-2g7trUwH.d.ts.map +0 -1
  488. package/dist/schema-BuiujZ-g.js.map +0 -1
  489. package/dist/schema-CSf6qWgZ.js.map +0 -1
  490. package/dist/search-kernel-DyNEa6IU.d.ts.map +0 -1
  491. package/dist/search-ledger-file-DDQUgvCg.js.map +0 -1
  492. package/dist/search-shipper-BOSD46qv.js.map +0 -1
  493. package/dist/semantic-concept-judge-BQF8te0T.js.map +0 -1
  494. package/dist/sequential-Bf_pbE50.js.map +0 -1
  495. package/dist/server-e9oWO_bN.js.map +0 -1
  496. package/dist/skillopt-optimization-method-BiwA8nfX.js.map +0 -1
  497. package/dist/statistical-heldout-42NlCNDe.js.map +0 -1
  498. package/dist/statistical-heldout-CYpGaoDH.d.ts.map +0 -1
  499. package/dist/steps-Bg5-KVx1.d.ts.map +0 -1
  500. package/dist/store-tool-spans-CIX5arAG.js.map +0 -1
  501. package/dist/store-tool-spans-DdCSPa7C.d.ts.map +0 -1
  502. package/dist/student-t-DVPW7CdL.js +0 -39
  503. package/dist/student-t-DVPW7CdL.js.map +0 -1
  504. package/dist/summary-report-V_JACR4Y.js.map +0 -1
  505. package/dist/summary-report-bdFDXq0b.d.ts.map +0 -1
  506. package/dist/task-failure-attributes-hEmASjix.js.map +0 -1
  507. package/dist/terminal-record-DZyQZ3pz.js.map +0 -1
  508. package/dist/tool-groups-C3NEcdCM.d.ts.map +0 -1
  509. package/dist/tool-waste-BKgvd-TP.d.ts.map +0 -1
  510. package/dist/trajectory-Y1fmdlw7.d.ts +0 -24
  511. package/dist/trajectory-Y1fmdlw7.d.ts.map +0 -1
  512. package/dist/tree-C1XYeXvy.js.map +0 -1
  513. package/dist/types-BqkVmHfv.d.ts.map +0 -1
  514. package/dist/types-C02qtnG8.d.ts.map +0 -1
  515. package/dist/types-C1tnkEgM.d.ts.map +0 -1
  516. package/dist/types-IXD2HJzu.js.map +0 -1
  517. package/dist/usage-receipt-Cx3xNeyB.js +0 -76
  518. package/dist/usage-receipt-Cx3xNeyB.js.map +0 -1
  519. package/dist/verdict-Dl0tiT1X.js.map +0 -1
  520. package/dist/verdict-cache-Bm8EKL2s.js.map +0 -1
  521. package/docs/design/self-improvement-evidence-audit.md +0 -263
package/docs/public-api.md CHANGED
@@ -7,11 +7,11 @@ Generated by `pnpm api:census` on demand — this is a dated reading, not a gate
7
7
  | measure | count |
8
8
  | --- | --- |
9
9
  | export subpaths | 33 |
10
- | published value exports (subpath x symbol) | 1612 |
11
- | distinct symbols | 1413 |
12
- | production | 1104 |
13
- | planned | 284 |
14
- | none | 224 |
10
+ | published value exports (subpath x symbol) | 1221 |
11
+ | distinct symbols | 1034 |
12
+ | production | 900 |
13
+ | planned | 286 |
14
+ | none | 35 |
15
15
 
16
16
  Type-only exports are not listed: a type binds no runtime surface, and removing one cannot break a caller at run time.
17
17
 
@@ -90,13 +90,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
90
90
 
91
91
  ### `.`
92
92
 
93
- 366 value exports — 291 production, 43 planned, 32 none.
93
+ 321 value exports — 279 production, 41 planned, 1 none.
94
94
 
95
95
  | symbol | consumer | evidence |
96
96
  | --- | --- | --- |
97
97
  | `acquisitionPlansForKnowledgeGaps` | production | agent-builder:src/lib/.server/eval/loops/data-acquisition-engine.ts |
98
98
  | `addCalibrationVerdicts` | planned | doc: docs/concepts.md |
99
- | `admitPolicyEdit` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
100
99
  | `AGENT_PROFILE_KINDS` | production | blueprint-agent:scripts/experiments/lib/agent-profile-cell.ts |
101
100
  | `AgentEvalError` | production | agent-runtime:src/errors.ts |
102
101
  | `agentProfileCellKey` | planned | consumer tests: blueprint-agent:scripts/experiments/lib/__tests__/agent-profile-cell.test.ts |
@@ -104,7 +103,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
104
103
  | `agentProfileId` | production | agent-dev-container:products/intelligence/api/src/lib/project-profile-change-preflight.ts |
105
104
  | `aggregateJudgeVerdicts` | production | agent-app:src/eval-campaign/index.ts |
106
105
  | `aggregateRunScore` | production | agent-dev-container:products/sandbox/evals/src/auto-optimization.ts |
107
- | `analystFindingDigest` | production | this package: src/feedback-trajectory.ts:4 |
108
106
  | `AnalystRegistry` | production | agent-runtime:examples/improve/improve.ts |
109
107
  | `analystRunDigest` | production | this package: src/feedback-trajectory.ts:4 |
110
108
  | `analystRunToFeedbackTrajectory` | planned | doc: docs/feedback-trajectories.md |
@@ -113,14 +111,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
113
111
  | `analyzeRuns` | production | agent-builder:eval/scripts/insight-report.ts |
114
112
  | `analyzeSeries` | production | agent-dev-container:products/sandbox/evals/run.ts |
115
113
  | `analyzeTraces` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
116
- | `applyPolicyEditToSurface` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
117
114
  | `argHash` | production | agent-runtime:src/runtime/supervise/detector-monitor.ts |
118
115
  | `assertCapabilityHeadroom` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
119
116
  | `assertCrossFamily` | production | agent-builder:frontier/judges/artifact-head-to-head.ts |
120
117
  | `assertCrossFamilyServed` | planned | doc: docs/building-doctrine.md |
121
118
  | `assertJudgeMayGate` | planned | doc: docs/concepts.md |
122
119
  | `assertNoHiddenLeak` | planned | doc: docs/design/statistics-decisions.md |
123
- | `assertNoJudgeVerdict` | production | this package: src/analyst/policy-edit.ts:6 |
124
120
  | `assertProductBenchmarkRun` | production | creative-agent:eval/research-package.ts |
125
121
  | `assertRealBackend` | production | creative-agent:eval/canonical-runner.ts |
126
122
  | `assertRunCaptured` | production | creative-agent:eval/canonical-runner.ts |
@@ -143,7 +139,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
143
139
  | `BudgetGuard` | production | creative-agent:scripts/evals/run-driver-soak.ts |
144
140
  | `buildAgentProfileCell` | production | ai-trading-blueprint:evals/src/trading/agent-profile-cell.ts |
145
141
  | `buildDefaultAnalystRegistry` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
146
- | `buildEquivalenceRecord` | none | only this package's tests: src/verification-strategy.test.ts:11 |
147
142
  | `buildReflectionPrompt` | production | ph0ny:products/builder/api/src/eval/evolution.ts |
148
143
  | `buildTraceInsightContext` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html-sections.ts |
149
144
  | `buildTraceInsightPrompt` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/brief.ts |
@@ -169,7 +164,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
169
164
  | `compileTraceContractSpec` | production | traces:src/check.ts |
170
165
  | `completionVerdict` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/scoreboard-core.ts |
171
166
  | `computeFindingId` | production | agent-runtime:src/runtime/index.ts |
172
- | `computePolicyEditId` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
173
167
  | `computeToolUseMetrics` | production | traces:src/pipelines.ts |
174
168
  | `confidenceInterval` | production | agent-runtime:src/runtime/benchmark-report.ts |
175
169
  | `ConfigError` | production | agent-runtime:src/errors.ts |
@@ -179,16 +173,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
179
173
  | `corpusInterRaterAgreement` | planned | doc: docs/design/statistics-decisions.md |
180
174
  | `corpusInterRaterAgreementFromJudgeScores` | planned | consumer tests: tax-agent:tests/eval/lib/judge-irr.ts |
181
175
  | `CostAccountingIncompleteError` | production | agent-runtime:src/improvement/search-executor.ts |
182
- | `CostCallConflictError` | production | this package: src/analyst/benchmark-public-model.ts:8 |
183
176
  | `CostCeilingReachedError` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
184
177
  | `costForTokenPricing` | production | agent-runtime:src/improvement/search-executor.ts |
185
178
  | `costForUsage` | production | agent-builder:src/lib/.server/llm-cost.ts |
186
179
  | `CostLedger` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
187
- | `CostLedgerPersistenceError` | production | this package: src/analyst/benchmark-public-model.ts:8 |
188
- | `CostReceiptCaptureError` | production | this package: src/analyst/benchmark-public-model.ts:8 |
189
180
  | `costReceiptFromLlm` | production | agent-builder:src/lib/.server/eval/router-llm-client.ts |
190
181
  | `costReceiptFromLlmError` | production | agent-builder:src/lib/.server/eval/router-llm-client.ts |
191
- | `CostReservationExceededError` | production | this package: src/analyst/benchmark-public-errors.ts:2 |
192
182
  | `CostTracker` | production | creative-agent:eval/canonical-runner.ts |
193
183
  | `createAntiSlopJudge` | production | ph0ny:products/builder/api/src/eval/judges.ts |
194
184
  | `createBoundedTraceAnalysisStore` | production | braid:src/adapters/analysis/trace-store.ts |
@@ -201,15 +191,11 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
201
191
  | `createTraceAnalyst` | production | agent-runtime:src/runtime/supervise-surface.ts |
202
192
  | `CrossFamilyError` | production | creative-agent:eval/lib/judge-ensemble.ts |
203
193
  | `decidePairedPromotion` | production | discovery-lab:experiments/e1-checker/score.mjs |
204
- | `DECISION_PAIRED_DELTA_STATISTIC` | production | this package: src/campaign/estimate-node.ts:19 |
205
194
  | `DEFAULT_BOUNDED_PROCESS_TIMEOUT_MS` | production | this package: src/command-runner.ts:28 |
206
- | `DEFAULT_FAILURE_REASON_RULES` | none | only this package's tests: tests/failure-taxonomy.test.ts:2 |
207
195
  | `DEFAULT_JUDGE_GATE_POLICY` | none | — |
208
196
  | `DEFAULT_RED_TEAM_CORPUS` | production | starter-foundry:registry/layers/agent-eval/redteam/files/src/eval/redteam/runner.ts |
209
197
  | `DEFAULT_TRACE_ANALYST_BUDGETS` | production | agent-builder:src/lib/.server/eval/stores/d1-trace-analysis-store-adapter.ts |
210
198
  | `DEFAULT_TRACE_ANALYST_KINDS` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
211
- | `DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS` | production | this package: src/analyst/chat-trace-engine.ts:46 |
212
- | `defaultBlendWeights` | none | only this package's tests: src/hidden-criteria-grading.test.ts:4 |
213
199
  | `defineAgentEval` | planned | example: examples/evaluate-a-change/index.ts:10 |
214
200
  | `defineEquivalenceCheck` | planned | example: examples/verify-without-an-answer-key/index.ts:13 |
215
201
  | `deployGateLayer` | production | blueprint-agent:scripts/experiments/lib/deploy-runner.ts |
@@ -239,9 +225,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
239
225
  | `exportRunAsOtlp` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
240
226
  | `extractErrorCount` | production | blueprint-agent:scripts/experiments/lib/error-count-extractor.ts |
241
227
  | `extractProducedState` | production | agent-app:src/eval/index.ts |
242
- | `extractUsage` | production | this package: src/contract/intake/code-agent-session.ts:13 |
228
+ | `extractUsage` | production | this package: src/contract/intake/code-agent-session-metrics.ts:3 |
243
229
  | `extractUsageFromSse` | production | this package: src/trace/capture-fetch.ts:8 |
244
- | `FAILURE_BLAME` | none | only this package's tests: tests/failure-taxonomy.test.ts:2 |
245
230
  | `FAILURE_CLASSES` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
246
231
  | `FAILURE_MODE_KIND_SPEC` | planned | consumer tests: legal-agent:tests/eval/analysts/completion-coverage.ts |
247
232
  | `failureBlame` | production | discovery-lab:experiments/e1-checker/score.mjs |
@@ -256,9 +241,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
256
241
  | `FindingsStore` | production | agent-builder:scripts/run-canonical-analyst-loop.ts |
257
242
  | `fisherExactTwoSided` | production | agent-dev-container:packages/sdk-data/src/analysis/recommendations/statistics.ts |
258
243
  | `formatScorecardDiff` | production | ai-trading-blueprint:evals/src/trading/scorecard-integration.ts |
259
- | `gainHistogram` | planned | doc: docs/research-report-methodology.md |
244
+ | `gainHistogram` | production | this package: src/research-report.ts:18 |
260
245
  | `gateTreatmentApplied` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
261
- | `gradeOnHidden` | none | only this package's tests: src/hidden-criteria-grading.test.ts:4 |
262
246
  | `gradeSemanticStatus` | production | blueprint-agent:scripts/experiments/lib/verification-harness/primitives.ts |
263
247
  | `groupRunsByAgentProfileCell` | planned | consumer tests: legal-agent:tests/eval/matrix-multi.ts |
264
248
  | `HARNESS_NATIVE_MODEL` | production | agent-runtime:src/runtime/supervise/model-policy.ts |
@@ -266,11 +250,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
266
250
  | `hashContent` | production | agent-runtime:bench/src/corpus.ts |
267
251
  | `hashJson` | production | agent-dev-container:products/intelligence/api/src/lib/ingest-optimization-mapping.ts |
268
252
  | `HeldOutGate` | production | agent-builder:src/lib/.server/eval/gates/promotion.ts |
269
- | `hiddenGrade` | none | only this package's tests: src/hidden-criteria-grading.test.ts:4 |
270
- | `holm` | production | this package: src/search/lenses/edit-credit.ts:47 |
271
- | `improvementVerdict` | none | — |
253
+ | `holm` | production | this package: src/search/lenses/edit-credit-statistics.ts:6 |
272
254
  | `inferDomainKeywords` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/suite-projection.ts |
273
- | `INFRA_FAILURE_BLAMES` | none | only this package's tests: tests/failure-taxonomy.test.ts:2 |
274
255
  | `InMemoryFeedbackTrajectoryStore` | production | creative-agent:eval/control/creative-onboarding.ts |
275
256
  | `InMemoryRawProviderSink` | production | agent-builder:src/lib/.server/eval/loops/canonical-campaign.ts |
276
257
  | `inMemoryReviewStore` | production | agent-builder:scripts/propose-review-smoke.ts |
@@ -278,7 +259,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
278
259
  | `interpretCliffs` | production | agent-builder:src/lib/.server/eval/loops/differential-eval.ts |
279
260
  | `interRaterReliability` | production | agent-app:src/eval-campaign/trust-gate.ts |
280
261
  | `iqr` | planned | consumer tests: blueprint-agent:scripts/experiments/lib/__tests__/stats-parity.test.ts |
281
- | `isBinaryOutcomeVector` | none | only this package's tests: src/statistics/paired-binary.test.ts:2 |
282
262
  | `isJudgeSpan` | production | this package: src/trace/query.ts:13 |
283
263
  | `isLlmSpan` | production | agent-runtime:src/candidate-execution/finalize.ts |
284
264
  | `isModelPriced` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-router.ts |
@@ -302,10 +282,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
302
282
  | `llmJudge` | production | agent-runtime:examples/agentic-data-creation/offline-fixtures.ts |
303
283
  | `LlmResponseError` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-router.ts |
304
284
  | `loadScorecard` | production | ai-trading-blueprint:evals/src/trading/scorecard-integration.ts |
305
- | `LOCAL_COMMAND_RUNNER_DEFAULT_CAP_MS` | none | only this package's tests: src/command-runner.test.ts:6 |
306
285
  | `localCommandRunner` | production | blueprint-agent:scripts/experiments/lib/command-runner.ts |
307
286
  | `makeFinding` | production | agent-dev-container:products/intelligence/api/src/lib/consultant/candidates.ts |
308
- | `makePolicyEdit` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
309
287
  | `makePolicyEditCandidateRecord` | planned | doc: docs/campaign-proposers.md |
310
288
  | `makeProposalFinding` | production | agent-lab:projects/playproof/code-surface.ts |
311
289
  | `manifestContentDigest` | production | this package: src/campaign/gates/sequential.ts:36 |
@@ -319,13 +297,11 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
319
297
  | `mintRolloutRows` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
320
298
  | `MODEL_PRICING` | production | supervisor-lab:archive/bench/profile-arena.ts |
321
299
  | `modelHasSnapshot` | production | agent-dev-container:products/intelligence/api/src/lib/project-profile-change-preflight.ts |
322
- | `modelPriceKey` | none | only this package's tests: src/cost-ledger.test.ts:7 |
323
- | `ModelSubstitutionError` | production | this package: src/campaign/external-optimizer-model-proxy.ts:11 |
300
+ | `ModelSubstitutionError` | production | this package: src/campaign/external-optimizer-model-handler.ts:10 |
324
301
  | `mulberry32` | production | agent-knowledge:src/memory/holdout.ts |
325
302
  | `MultiLayerVerifier` | production | agent-builder:src/lib/.server/eval/loops/forge-refinement.ts |
326
303
  | `NoopRawProviderSink` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
327
304
  | `normalTwoSidedPValue` | production | agent-dev-container:packages/sdk-data/src/analysis/recommendations/statistics.ts |
328
- | `notBlocked` | none | only this package's tests: src/oracle.test.ts:2 |
329
305
  | `NotFoundError` | production | agent-runtime:src/errors.ts |
330
306
  | `objectiveEval` | production | agent-knowledge:src/research-loop.ts |
331
307
  | `observeAll` | production | agent-runtime:src/runtime/supervise/detector-monitor.ts |
@@ -333,11 +309,9 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
333
309
  | `otlpTextToTraceAnalysisStore` | production | braid:src/adapters/analysis/trace-store.ts |
334
310
  | `OUTPUT_VALUE` | production | agent-runtime:src/runtime/supervise-surface.ts |
335
311
  | `pairArms` | production | agent-knowledge:src/memory/experiment/learning-pairs.ts |
336
- | `pairedBinaryScale` | production | this package: src/paired-promotion-decision.ts:50 |
337
312
  | `pairedBootstrap` | production | agent-builder:frontier/adapters/fleet-eval-runner.ts |
338
- | `pairedCohensDz` | production | this package: src/contract/analyze-runs.ts:38 |
313
+ | `pairedCohensDz` | production | this package: src/contract/comparison-insight.ts:7 |
339
314
  | `pairedDeltaTest` | production | this package: src/campaign/estimate-node.ts:18 |
340
- | `pairedDeltaTieFraction` | production | this package: src/paired-promotion-decision.ts:50 |
341
315
  | `pairedEvalueSequence` | production | creative-agent:src/lib/experiments/ab-design.ts |
342
316
  | `pairedMde` | production | discovery:research/e1-topology-20260920/gate/gate.mjs |
343
317
  | `pairedPromotionPower` | production | discovery-lab:prereg/continuation-note-v1-tb/gate.mjs |
@@ -345,21 +319,16 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
345
319
  | `pairedRiskDifferenceExact` | production | blueprint-agent:scripts/experiments/lib/publication-decision.ts |
346
320
  | `pairedRiskDifferenceScore` | production | supervisor-lab:src/learn/report.ts |
347
321
  | `pairedSignTest` | production | agent-dev-container:products/intelligence/api/src/lib/paired-stats.ts |
348
- | `pairedTTest` | production | this package: src/contract/analyze-runs.ts:38 |
322
+ | `pairedTTest` | production | this package: src/contract/comparison-insight.ts:7 |
349
323
  | `pairRunRecords` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
350
324
  | `PairwiseSteeringOptimizer` | production | browser-agent-driver:bench/research/webvoyager-agent-eval-loop.mjs |
351
- | `paretoChart` | production | workcomp-agent:eval/benchmark/select.ts |
352
325
  | `paretoFrontier` | production | agent-dev-container:products/sandbox/evals/run.ts |
353
326
  | `parseReflectionResponse` | production | ph0ny:products/builder/api/src/eval/evolution.ts |
354
327
  | `parseRunRecordSafe` | production | gtm-agent:scripts/canonical-completeness/records.ts |
355
328
  | `partialCredit` | planned | doc: docs/design/statistics-decisions.md |
356
329
  | `partitionHeldOut` | production | blueprint-agent:scripts/experiments/calibrate-instrument.ts |
357
- | `partitionTrainSelectionTest` | none | only this package's tests: src/partition-held-out.test.ts:2 |
358
330
  | `passAtK` | planned | doc: docs/design/statistics-decisions.md |
359
331
  | `pearsonR` | production | this package: src/builder-eval/correlation.ts:18 |
360
- | `POLICY_EDIT_CANDIDATE_RECORD_SCHEMA` | none | — |
361
- | `policyEditsFromFindings` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
362
- | `PolicyEditValidationError` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
363
332
  | `preflightModels` | planned | doc: docs/building-doctrine.md |
364
333
  | `productBenchmarkRepoIdentity` | production | creative-agent:eval/research-package.ts |
365
334
  | `ProductClient` | production | creative-agent:eval/e2e/creative-product-harness.ts |
@@ -367,7 +336,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
367
336
  | `projectRuntimeTrajectoryEvidence` | production | agent-dev-container:products/intelligence/api/src/lib/workflow-trace-preflight.ts |
368
337
  | `PromptRegistry` | production | blueprint-agent:scripts/experiments/lib/surface-prompt-registry.ts |
369
338
  | `proposeSynthesisTargets` | production | blueprint-agent:scripts/experiments/researcher/inspect.ts |
370
- | `quotaExhaustedUntil` | none | only this package's tests: src/campaign/transient-failure.test.ts:3 |
371
339
  | `ranks` | production | discovery-lab:tools/evaluators/eval-discrimination/score.mjs |
372
340
  | `readProductBenchmarkManifest` | production | creative-agent:eval/research-package.ts |
373
341
  | `recordRuns` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/analyze.mjs |
@@ -378,7 +346,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
378
346
  | `redactText` | production | agent-dev-container:products/intelligence/api/src/lib/search-ingest.ts |
379
347
  | `redTeamDataset` | production | creative-agent:eval/red-team.ts |
380
348
  | `redTeamReport` | production | creative-agent:eval/red-team.ts |
381
- | `regexMatches` | none | only this package's tests: src/oracle.test.ts:2 |
382
349
  | `registerCalibrationSet` | planned | doc: docs/concepts.md |
383
350
  | `renderPreferenceMemoryMarkdown` | production | agent-builder:src/lib/.server/eval/loops/auto-research-runner.ts |
384
351
  | `repeatedActionDetector` | production | agent-runtime:src/runtime/supervise/detector-monitor.ts |
@@ -387,12 +354,10 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
387
354
  | `requiredSampleSize` | production | agent-dev-container:products/sandbox/evals/src/stats.ts |
388
355
  | `resolveModelPricing` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-primitives.ts |
389
356
  | `resolveSeat` | production | creative-agent:eval/agent.config.ts |
390
- | `routeFields` | none | only this package's tests: src/hidden-criteria-grading.test.ts:4 |
391
357
  | `runAgentControlLoop` | production | agent-runtime:src/run.ts |
392
358
  | `runBoundedProcess` | production | this package: src/command-runner.ts:28 |
393
359
  | `runCampaign` | production | agent-app:src/eval-campaign/index.ts |
394
360
  | `runCanaries` | production | agent-builder:src/lib/.server/eval/loops/canary-cron.ts |
395
- | `runCounterfactual` | production | this package: src/trajectory-replay/batch.ts:30 |
396
361
  | `runEquivalenceCheck` | planned | example: examples/verify-without-an-answer-key/index.ts:13 |
397
362
  | `runEvalCampaign` | production | agent-builder:scripts/eval.ts |
398
363
  | `RunIntegrityError` | production | creative-agent:eval/canonical-runner.ts |
@@ -400,7 +365,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
400
365
  | `runKeywordCoverageJudge` | production | blueprint-agent:scripts/experiments/calibration/scorers.ts |
401
366
  | `runKeywordCoverageJudgeUrl` | production | blueprint-agent:scripts/experiments/lib/completeness-audit.ts |
402
367
  | `runProposeReview` | production | agent-builder:scripts/propose-review-smoke.ts |
403
- | `runProposeReviewAsControlLoop` | none | — |
404
368
  | `RunRecordValidationError` | production | starter-foundry:src/lib/index.ts |
405
369
  | `runSemanticConceptJudge` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-router.ts |
406
370
  | `runsForScenario` | production | ph0ny:products/builder/api/src/eval/gate.ts |
@@ -409,12 +373,9 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
409
373
  | `scoreKnowledgeReadiness` | production | agent-builder:src/lib/.server/runtime/agent-task-readiness.ts |
410
374
  | `scoreRedTeamOutput` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-gate.ts |
411
375
  | `scoreTraceInsightReadiness` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html-sections.ts |
412
- | `searchCellRunId` | production | this package: src/campaign/search-ledger-recording.ts:25 |
413
376
  | `seatPresets` | production | supervisor-lab:archive/bench/comms/judges.ts |
414
377
  | `selfImprove` | production | agent-app:src/eval-campaign/index.ts |
415
378
  | `SEMANTIC_CONCEPT_JUDGE_VERSION` | production | blueprint-agent:scripts/experiments/lib/semantic-audit.ts |
416
- | `ServedCrossFamilyError` | none | only this package's tests: src/integrity/served-model.test.ts:2 |
417
- | `servedModelAcceptable` | production | this package: src/integrity/preflight.ts:33 |
418
379
  | `shareAllowed` | production | agent-dev-container:products/intelligence/api/src/lib/search-blobs.ts |
419
380
  | `snapshotFromJudgeAgreement` | planned | doc: docs/concepts.md |
420
381
  | `spanRecordsToTraceAnalysisStore` | production | agent-dev-container:products/intelligence/api/src/lib/pg-trace-analyst-store.ts |
@@ -426,22 +387,17 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
426
387
  | `summarizeNumberSeries` | production | this package: src/campaign/cell-aggregates.ts:12 |
427
388
  | `summarizePreferenceMemory` | production | agent-builder:src/lib/.server/eval/loops/auto-research-runner.ts |
428
389
  | `summarizeSample` | production | agent-dev-container:products/sandbox/evals/src/stats.ts |
429
- | `summaryTable` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/analyze.mjs |
430
- | `textInSnapshot` | none | only this package's tests: src/oracle.test.ts:2 |
390
+ | `summaryTable` | production | this package: src/research-report.ts:18 |
431
391
  | `toAgentProfileJson` | production | blueprint-agent:scripts/experiments/lib/agent-profile-cell.ts |
432
392
  | `tokenizeDomainWords` | planned | consumer tests: blueprint-agent:scripts/experiments/__tests__/analyze-vb-run.test.ts |
433
393
  | `toolSpansToTraceAnalysisStore` | production | agent-runtime:src/runtime/supervise/run-traces.ts |
434
394
  | `toolWasteView` | production | agent-runtime:src/runtime/supervise/trajectory-recorder.ts |
435
- | `TRACE_ANALYST_TRUNCATION_MARKER_PREFIX` | none | — |
436
395
  | `traceContract` | production | creative-agent:eval/lib/trace-contracts.ts |
437
396
  | `TraceEmitter` | production | agent-builder:src/lib/.server/runtime/trace-runtime.ts |
438
397
  | `transientDispatchFailure` | planned | doc: docs/eval-surface-map.md |
439
398
  | `twoByTwoPValue` | production | agent-dev-container:packages/sdk-data/src/analysis/recommendations/statistics.ts |
440
399
  | `UNKNOWN_MODEL` | production | this package: src/campaign/presets/run-profile-matrix.ts:54 |
441
- | `urlContains` | none | only this package's tests: src/oracle.test.ts:2 |
442
400
  | `userQuestionsForKnowledgeGaps` | production | agent-dev-container:products/intelligence/api/src/routes/project-engines.ts |
443
- | `validatePolicyEdit` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
444
- | `validatePolicyEditCandidateRecord` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
445
401
  | `validateRunRecord` | production | agent-builder:src/lib/.server/eval/stores/run-record-store.ts |
446
402
  | `ValidationError` | production | agent-runtime:src/errors.ts |
447
403
  | `verbosityBias` | production | blueprint-agent:scripts/experiments/calibration/judge-agreement.ts |
@@ -457,7 +413,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
457
413
  | `wilcoxonSignedRank` | production | agent-builder:src/lib/.server/eval/loops/differential-eval.ts |
458
414
  | `wilson` | production | agent-dev-container:packages/sdk-data/src/analysis/recommendations/statistics.ts |
459
415
  | `withAssignedFeedbackSplit` | production | discovery-lab:prereg/factory-portfolio-20260929/sources/phony/products/builder/api/src/feedback/production-trace.ts |
460
- | `withHeldoutBlend` | none | only this package's tests: src/hidden-criteria-grading.test.ts:4 |
461
416
  | `withJudgeRetry` | production | creative-agent:eval/lib/creative-judges.ts |
462
417
  | `wranglerDeployRunner` | production | blueprint-agent:scripts/experiments/lib/deploy-runner.ts |
463
418
 
@@ -472,157 +427,137 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
472
427
 
473
428
  ### `./analyst`
474
429
 
475
- 131 value exports — 81 production, 25 planned, 25 none.
430
+ 113 value exports — 61 production, 37 planned, 15 none.
476
431
 
477
432
  | symbol | consumer | evidence |
478
433
  | --- | --- | --- |
479
- | `adaptPublicBenchmarkFindings` | production | this package: scripts/gepa-analyst-campaign.ts:59 |
480
434
  | `AGENT_RX_UPSTREAM_REVISION` | production | this package: src/analyst/benchmark-command-result.ts:2 |
481
435
  | `agentRxBenchmarkCase` | production | this package: src/analyst/benchmark-public-data.ts:12 |
482
436
  | `agentRxPredictionsToFindings` | production | this package: src/analyst/benchmark-public-adapters.ts:3 |
483
437
  | `ANALYST_BENCHMARK_COST_LEDGER_FILE` | production | this package: src/analyst/benchmark-command-persistence.ts:9 |
484
- | `ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM` | none | only this package's tests: src/analyst/benchmark-implementation.test.ts:7 |
485
- | `ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES` | none | only this package's tests: src/analyst/benchmark-implementation.test.ts:7 |
486
- | `ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256` | production | this package: src/analyst/benchmark-command-persistence.ts:27 |
487
438
  | `ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256` | planned | doc: .claude/skills/agent-eval/SKILL.md |
488
439
  | `ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256` | planned | doc: .claude/skills/agent-eval/SKILL.md |
489
- | `ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM` | none | only this package's tests: src/analyst/benchmark-implementation.test.ts:7 |
490
440
  | `ANALYST_BENCHMARK_IMPLEMENTATION_FILES` | planned | doc: .claude/skills/agent-eval/SKILL.md |
491
- | `ANALYST_BENCHMARK_IMPLEMENTATION_SHA256` | production | this package: src/analyst/benchmark-command-persistence.ts:27 |
492
441
  | `ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE` | production | this package: src/analyst/benchmark-command-persistence.ts:9 |
493
442
  | `ANALYST_BENCHMARK_MANIFEST_FILE` | production | this package: src/analyst/benchmark-command-persistence.ts:9 |
494
443
  | `ANALYST_BENCHMARK_OBSERVATIONS_FILE` | production | this package: src/analyst/benchmark-command-persistence.ts:9 |
495
- | `analystBenchmarkDependencyLockDigest` | none | only this package's tests: src/analyst/benchmark-implementation.test.ts:7 |
496
- | `analystBenchmarkImplementationDigest` | none | only this package's tests: src/analyst/benchmark-implementation.test.ts:7 |
497
444
  | `analystDefinitionAsymmetries` | planned | doc: docs/trace-analysis.md |
498
445
  | `analystDefinitionProtocolSha256` | planned | doc: docs/trace-analysis.md |
499
446
  | `AnalystExpressivenessError` | production | this package: src/analyst/benchmark-public-model.ts:56 |
500
- | `analystInstructionsOverrideFromText` | none | only this package's tests: src/analyst/benchmark-instructions-override.test.ts:5 |
501
447
  | `AnalystRegistry` | production | agent-runtime:examples/improve/improve.ts |
502
448
  | `analystUsageReceiptFromPrimeUsage` | production | this package: src/analyst/benchmark-runner-prime.ts:19 |
503
- | `appendVerificationArtifactsToOtlp` | production | this package: src/analyst/benchmark-public-data.ts:32 |
504
449
  | `askTraceQuestions` | planned | doc: docs/systemone-behavior-review.md |
505
450
  | `assertProposalFindings` | production | agent-runtime:src/improvement/code-execution.ts |
451
+ | `attachToTaxonomy` | planned | doc: docs/finding-layers.md |
506
452
  | `behavioralAnalyst` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
507
453
  | `bindAnalyst` | planned | doc: docs/trace-analysis.md |
508
454
  | `buildDefaultAnalystRegistry` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
509
455
  | `buildPrimePrompt` | production | this package: src/analyst/benchmark-runner-prime.ts:19 |
510
456
  | `buildPrimeRepairPrompt` | planned | doc: docs/prime-analyst.md |
511
- | `buildSkillUsageReport` | none | only this package's tests: src/analyst/kinds/skill-usage.test.ts:2 |
457
+ | `buildSkillUsageReport` | none | — |
512
458
  | `buildTraceToolsForGroup` | production | this package: src/analyst/kind-factory.ts:15 |
513
- | `citedSpansOnly` | none | only this package's tests: src/analyst/trace-questions.test.ts:7 |
514
- | `CODE_TRACE_BENCH_ANALYST_PROMPT` | production | this package: scripts/gepa-analyst-campaign.ts:60 |
515
- | `codeTraceBenchCase` | production | this package: scripts/gepa-analyst-campaign.ts:58 |
459
+ | `calibrateFailureModes` | planned | doc: docs/finding-layers.md |
460
+ | `classifyTeamShape` | none | only this package's tests: tests/finding-layers.test.ts:16 |
461
+ | `CODE_TRACE_BENCH_ANALYST_PROMPT` | production | this package: scripts/gepa-analyst/configuration.ts:5 |
462
+ | `codeTraceBenchCase` | production | this package: scripts/gepa-analyst/scenarios.ts:5 |
516
463
  | `codeTracerPredictionsToFindings` | production | this package: benchmarks/trace-analysis/codetracebench-glm52-20260730/summarize-codetracer.mjs:6 |
517
- | `coerceJson` | production | this package: src/analyst/finding-codec.ts:19 |
518
- | `compareAnalystRunners` | production | this package: src/analyst/benchmark-command-result.ts:15 |
519
464
  | `computeFindingId` | production | agent-runtime:src/runtime/index.ts |
520
465
  | `CONTROL_INTEGRITY_ANALYST` | planned | named in discovery-lab (bind not in the import graph) |
521
466
  | `ControlIntegrityAnalyst` | planned | named in discovery-lab (bind not in the import graph) |
522
467
  | `createChatClient` | production | agent-builder:src/lib/.server/eval/analysts/forge-deep-analyst.ts |
523
468
  | `createChatTraceEngine` | production | agent-builder:src/lib/.server/eval/analysts/forge-deep-analyst.ts |
524
469
  | `createDspyRlmTraceEngine` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
470
+ | `createFailureModesAnalyst` | planned | doc: docs/finding-layers.md |
525
471
  | `createPrimeBenchmarkRunner` | production | this package: src/analyst/benchmark-command.ts:62 |
526
472
  | `createPublicBenchmarkDirectRunner` | production | this package: src/analyst/benchmark-command.ts:60 |
527
473
  | `createPublicBenchmarkRlmRunner` | production | this package: src/analyst/benchmark-command.ts:61 |
528
- | `createSemanticConceptJudgeAdapter` | none | only this package's tests: src/analyst/adapters.test.ts:2 |
529
474
  | `createTraceAnalyst` | production | agent-runtime:src/runtime/supervise-surface.ts |
530
- | `decodeReplyRows` | production | this package: src/analyst/benchmark-public-model.ts:57 |
531
- | `DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES` | production | this package: src/analyst/benchmark-command.ts:73 |
532
475
  | `DEFAULT_TRACE_ANALYST_KINDS` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
533
- | `DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS` | production | this package: src/analyst/chat-trace-engine.ts:46 |
534
- | `defaultIsMaterial` | none | only this package's tests: src/analyst/analyst.test.ts:8 |
535
476
  | `defineCustomAnalyst` | planned | doc: docs/trace-analysis.md |
477
+ | `defineDomainTaxonomy` | planned | doc: docs/finding-layers.md |
536
478
  | `defineTraceAnalyst` | production | traces:src/ask.ts |
537
- | `deriveEfficiencyFindings` | none | only this package's tests: src/trace-analyst/behavioral-metrics.test.ts:2 |
538
479
  | `diffFindings` | production | agent-runtime:src/analyst-loop/run-analyst-loop.ts |
539
- | `effectiveAnalystProtocolSha256` | production | this package: src/analyst/benchmark-command-persistence.ts:31 |
480
+ | `diffFindingsOverTime` | planned | doc: docs/finding-layers.md |
481
+ | `domainPathOf` | production | this package: src/analyst/promote.ts:28 |
540
482
  | `emitControlIntegrityFindings` | planned | named in discovery-lab (bind not in the import graph) |
541
- | `emitSkillUsageFindings` | none | only this package's tests: src/analyst/kinds/skill-usage.test.ts:2 |
542
- | `emptyPrimeRawUsage` | none | only this package's tests: src/analyst/prime-protocol.test.ts:4 |
543
- | `emptyPublicBenchmarkRunner` | production | this package: src/analyst/benchmark-command.ts:62 |
544
483
  | `evidenceRefsFromRawFinding` | production | agent-dev-container:products/intelligence/api/src/lib/router-trace-analyst.ts |
545
484
  | `ExactAnalystRunExecutionError` | production | discovery-lab:runner/evidence-review.mjs |
546
485
  | `expandCodeTraceFailureBlocks` | production | this package: src/analyst/benchmark-public-model.ts:29 |
547
- | `extractPrimeJsonObject` | none | only this package's tests: src/analyst/prime-protocol.test.ts:4 |
548
486
  | `FAILURE_MODE_KIND_SPEC` | planned | consumer tests: legal-agent:tests/eval/analysts/completion-coverage.ts |
487
+ | `FAILURE_MODE_LABELS` | none | — |
488
+ | `FAILURE_MODES_ANALYST_ID` | none | — |
489
+ | `FAILURE_MODES_MIN_KAPPA` | planned | doc: docs/finding-layers.md |
490
+ | `FAILURE_MODES_QUESTIONS` | none | — |
491
+ | `FAILURE_MODES_VERSION` | none | — |
492
+ | `FINDING_LAYERS` | none | — |
549
493
  | `FINDING_SUBJECT_KINDS` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/compile-and-prove/carrier.test.ts |
550
494
  | `FINDING_SUBJECT_SYNTAX` | planned | named in discovery-lab (bind not in the import graph) |
551
495
  | `FindingsStore` | production | agent-builder:scripts/run-canonical-analyst-loop.ts |
552
496
  | `findingSubjectGrammarPromptFor` | production | this package: src/analyst/kinds/failure-mode.ts:38 |
553
497
  | `IMPROVEMENT_KIND_SPEC` | planned | named in discovery-lab (bind not in the import graph) |
554
- | `isProposalFinding` | none | only this package's tests: src/analyst/proposal-findings.test.ts:2 |
498
+ | `independentUnitCount` | none | — |
555
499
  | `KIND_EXPECTED_SUBJECTS` | production | traces:src/analyst-citations.ts |
556
500
  | `KNOWLEDGE_GAP_KIND_SPEC` | planned | named in discovery-lab (bind not in the import graph) |
557
501
  | `KNOWLEDGE_POISONING_KIND_SPEC` | planned | named in discovery-lab (bind not in the import graph) |
558
- | `loadCodeTraceVerificationArtifacts` | production | this package: src/analyst/benchmark-public-data.ts:32 |
559
- | `loadPublicBenchmarkRows` | production | this package: scripts/gepa-analyst-campaign.ts:64 |
502
+ | `LAB_NODE_ID` | production | this package: src/analyst/promote.ts:28 |
503
+ | `lineageRoots` | production | this package: src/analyst/promote.ts:37 |
504
+ | `loadFailureModeGold` | planned | doc: docs/finding-layers.md |
505
+ | `loadPublicBenchmarkRows` | production | this package: scripts/gepa-analyst/scenarios.ts:6 |
506
+ | `lowestCommonAncestor` | production | this package: src/analyst/promote.ts:28 |
560
507
  | `makeFinding` | production | agent-dev-container:products/intelligence/api/src/lib/consultant/candidates.ts |
561
508
  | `makeProposalFinding` | production | agent-lab:projects/playproof/code-surface.ts |
562
- | `MAX_INCORRECT_BLOCK_STEPS` | production | this package: src/analyst/benchmark-public-adapters.ts:9 |
563
- | `MAX_INCORRECT_BLOCKS` | production | this package: src/analyst/benchmark-public-adapters.ts:9 |
564
509
  | `mergePrimeRawUsage` | planned | doc: docs/prime-analyst.md |
565
510
  | `nodeHttpPrimeBridgeTransport` | production | this package: src/analyst/benchmark-runner-prime.ts:18 |
566
- | `normalizeAgentRxCategory` | none | only this package's tests: src/analyst/benchmark-datasets.test.ts:3 |
567
- | `normalizeBenchmarkLabel` | production | this package: src/analyst/benchmark-dataset-agentrx.ts:10 |
568
511
  | `normalizePrimeUsage` | planned | doc: docs/prime-analyst.md |
512
+ | `NOT_OBSERVABLE` | none | only this package's tests: tests/finding-layers.test.ts:16 |
513
+ | `openFindingsLedger` | planned | doc: docs/finding-layers.md |
514
+ | `parseAnalystFinding` | planned | doc: docs/finding-layers.md |
569
515
  | `parseFindingSubject` | production | agent-dev-container:products/intelligence/api/src/lib/improvement-loop.ts |
570
516
  | `parseRawFinding` | production | this package: src/analyst/kind-factory.ts:7 |
571
- | `parseVerificationOutcome` | production | this package: src/analyst/benchmark-verification-artifacts.ts:8 |
572
- | `preparePublicAnalystBenchmark` | production | this package: scripts/gepa-analyst-campaign.ts:64 |
573
517
  | `primeAnalystProtocolSha256` | planned | doc: docs/prime-analyst.md |
574
518
  | `primeCodeTraceAnalystDefinition` | planned | doc: docs/prime-analyst.md |
575
519
  | `primeProtocolSha256` | production | this package: src/analyst/benchmark-runner-prime.ts:19 |
576
- | `primeReplyDefect` | none | only this package's tests: src/analyst/prime-protocol.test.ts:4 |
577
520
  | `projectPrimeTrajectory` | production | this package: src/analyst/benchmark-runner-prime.ts:19 |
578
- | `publicBenchmarkDistributions` | none | — |
521
+ | `promote` | production | this package: src/analyst/rollup.ts:29 |
522
+ | `ProposalFindingSchema` | production | this package: src/analyst/proposal-findings.ts:1 |
579
523
  | `publicBenchmarkProtocolSha256` | production | this package: src/analyst/benchmark-instructions-override.ts:2 |
580
- | `publicBenchmarkRlmInstructions` | production | this package: scripts/gepa-analyst-campaign.ts:60 |
581
- | `publicBenchmarkSelectionReport` | none | only this package's tests: src/analyst/benchmark-command-public-data.test.ts:13 |
582
- | `publicBenchmarkSystemPrompt` | none | only this package's tests: src/analyst/benchmark-command-public-data.test.ts:13 |
583
524
  | `publicDirectAnalystDefinition` | planned | doc: docs/trace-analysis.md |
584
525
  | `publicRlmAnalystDefinition` | planned | doc: docs/trace-analysis.md |
526
+ | `queryFindings` | planned | doc: docs/finding-layers.md |
585
527
  | `RAW_FINDING_SCHEMA_PROMPT` | production | this package: src/analyst/benchmark-public-rlm.ts:36 |
586
528
  | `RawAnalystFindingSchema` | production | this package: scripts/emit-finding-contract.ts:20 |
587
529
  | `readAnalystBenchmarkArtifact` | production | this package: src/analyst/benchmark-command.ts:42 |
588
- | `readAnalystInstructionsOverride` | production | this package: src/analyst/benchmark-command.ts:52 |
589
- | `registryBenchmarkRunner` | none | only this package's tests: src/analyst/benchmark.test.ts:3 |
590
- | `renderAgentRxCalibrationMarkdown` | production | this package: src/analyst/benchmark-command.ts:19 |
591
- | `renderAnalystBenchmarkMarkdown` | production | this package: src/analyst/benchmark-command.ts:72 |
592
- | `renderCodeTraceCalibrationMarkdown` | production | this package: src/analyst/benchmark-command.ts:56 |
530
+ | `readFindingScope` | planned | doc: docs/finding-layers.md |
593
531
  | `renderFindingSubject` | production | creative-agent:eval/analyst-loop.ts |
594
- | `renderPriorFindings` | none | — |
595
- | `resolveTraceAnalystLimits` | production | this package: src/analyst/kind-factory.ts:5 |
596
- | `rlmEngineLimits` | none | only this package's tests: src/analyst/definition-parity.test.ts:26 |
597
- | `roundAgentRxStep` | production | this package: src/analyst/benchmark-agentrx-calibration.ts:2 |
532
+ | `resolveDomainPath` | none | — |
533
+ | `rollupFindings` | none | only this package's tests: tests/finding-layers.test.ts:16 |
598
534
  | `runAnalystBenchmark` | production | this package: benchmarks/trace-analysis/codetracebench-glm52-20260730/summarize-codetracer.mjs:6 |
599
535
  | `runAnalystBenchmarkCommand` | production | this package: src/cli.ts:19 |
600
536
  | `runPrimeExchange` | production | this package: src/analyst/benchmark-runner-prime.ts:19 |
601
537
  | `runTraceAnalyst` | production | discovery-lab:experiments/axes-screen-r1/review.mjs |
602
- | `scoreAnalystFindings` | production | this package: scripts/gepa-analyst-campaign.ts:57 |
603
- | `selectPublicBenchmarkRows` | none | only this package's tests: src/analyst/benchmark-command-public-data.test.ts:13 |
604
- | `SKILL_USAGE_ANALYST` | none | only this package's tests: src/analyst/kinds/skill-usage.test.ts:2 |
605
538
  | `stripCodeFences` | planned | named in agent-builder (bind not in the import graph) |
606
- | `summarizeAgentRxCalibration` | production | this package: src/analyst/benchmark-command-result.ts:2 |
607
- | `summarizeAnalystBenchmarkRunner` | production | this package: src/analyst/benchmark-command-result.ts:18 |
608
- | `summarizeCodeTraceCalibration` | production | this package: benchmarks/trace-analysis/codetracebench-glm52-20260730/summarize-codetracer.mjs:6 |
539
+ | `taxonomyAncestry` | production | this package: src/analyst/promote.ts:28 |
540
+ | `taxonomyLayerOf` | production | this package: src/analyst/promote.ts:28 |
541
+ | `TEAM_SHAPE_ANALYST_ID` | none | — |
542
+ | `TEAM_SHAPE_CLASSES` | none | — |
543
+ | `TEAM_SHAPE_VERSION` | none | only this package's tests: tests/finding-layers.test.ts:16 |
544
+ | `teamShapeAnalyst` | none | only this package's tests: tests/finding-layers.test.ts:16 |
545
+ | `teamShapeInputFromSources` | planned | doc: docs/finding-layers.md |
609
546
  | `traceStoreEvidenceResolver` | production | this package: src/analyst/benchmark-command.ts:12 |
610
547
 
611
548
  ### `./authenticity`
612
549
 
613
- 5 value exports — 3 production, 0 planned, 2 none.
550
+ 3 value exports — 3 production, 0 planned, 0 none.
614
551
 
615
552
  | symbol | consumer | evidence |
616
553
  | --- | --- | --- |
617
554
  | `gateRealness` | production | blueprint-agent:scripts/experiments/lib/enrich/realness.ts |
618
- | `judgeRealnessLlm` | none | — |
619
555
  | `scoreAuthenticity` | production | blueprint-agent:scripts/experiments/lib/enrich/realness.ts |
620
- | `scoreAuthenticityNuance` | none | only this package's tests: src/authenticity/index.test.ts:3 |
621
556
  | `scoreRealnessBlended` | production | physim:apps/server/src/scripts/agent-eval/investigators/realness.ts |
622
557
 
623
558
  ### `./benchmarks`
624
559
 
625
- 13 value exports — 2 production, 10 planned, 1 none.
560
+ 12 value exports — 2 production, 10 planned, 0 none.
626
561
 
627
562
  | symbol | consumer | evidence |
628
563
  | --- | --- | --- |
@@ -635,7 +570,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
635
570
  | `evaluateStandardRetrieval` | planned | doc: examples/benchmarks/README.md |
636
571
  | `parseBeirCorpusJsonl` | planned | doc: examples/benchmarks/README.md |
637
572
  | `parseBeirQueriesJsonl` | planned | doc: examples/benchmarks/README.md |
638
- | `parseJsonlRows` | none | only this package's tests: tests/benchmarks.test.ts:8 |
639
573
  | `parseQrels` | planned | doc: examples/benchmarks/README.md |
640
574
  | `routing` | planned | doc: docs/building-doctrine.md |
641
575
  | `runBenchmarkAdapter` | planned | doc: examples/benchmarks/README.md |
@@ -655,7 +589,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
655
589
 
656
590
  ### `./campaign`
657
591
 
658
- 170 value exports — 121 production, 25 planned, 24 none.
592
+ 131 value exports — 101 production, 25 planned, 5 none.
659
593
 
660
594
  | symbol | consumer | evidence |
661
595
  | --- | --- | --- |
@@ -664,45 +598,35 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
664
598
  | `analyzeCrossSurfaceInteractions` | none | only this package's tests: src/campaign/cross-surface-interaction.test.ts:2 |
665
599
  | `asha` | production | agent-runtime:src/improvement/search-method.ts |
666
600
  | `assertCampaignDesign` | production | tangle-router:lib/auto-policy-lab.ts |
667
- | `assertCampaignSplitIdentity` | production | agent-knowledge:src/memory/experiment/learning-pairs.ts |
668
601
  | `assertCodeSurfaceIdentity` | none | — |
669
- | `assertCompleteSearchHistory` | production | this package: src/campaign/optimization-method.ts:14 |
670
602
  | `assertSearchHistoryMatchesState` | planned | doc: docs/search-ledger.md |
671
- | `autoevalsScorerJudge` | none | only this package's tests: src/campaign/upstream-evaluators.test.ts:6 |
672
603
  | `beam` | production | agent-runtime:src/runtime/strategy-evolution.ts |
673
604
  | `buildCellSchedule` | production | this package: src/campaign/plan-campaign-run.ts:9 |
674
605
  | `buildEvidenceVector` | planned | doc: docs/experiment.md |
675
- | `buildLoopProvenanceRecord` | none | only this package's tests: tests/campaign/candidate-attribution.test.ts:5 |
676
- | `buildTraceAnalystSurfaceDispatch` | none | only this package's tests: src/campaign/analyst-surface.test.ts:4 |
677
606
  | `campaignBreakdown` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-outcome.ts |
678
607
  | `campaignCellSearchResult` | production | agent-runtime:src/improvement/search-method.ts |
679
608
  | `campaignCoverage` | production | tangle-router:lib/auto-policy-lab.ts |
680
609
  | `campaignMeanComposite` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-outcome.ts |
681
- | `campaignMeasurementDigest` | production | this package: src/contract/self-improve-method.ts:14 |
682
610
  | `campaignScenarioIdentity` | production | agent-runtime:src/improvement/method-identity.ts |
683
611
  | `campaignSplitDigest` | production | tangle-router:lib/auto-policy-lab.ts |
684
612
  | `campaignSplitDigestFromIdentities` | production | agent-runtime:src/improvement/method-identity.ts |
685
613
  | `canonicalDigest` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-engine.ts |
686
614
  | `cellCachePath` | production | this package: src/campaign/cell-cache.ts:10 |
687
- | `classifyUngroundedLiterals` | none | only this package's tests: src/campaign/grounded-reflection.test.ts:2 |
688
615
  | `codeSurfaceIdentityMaterial` | none | — |
689
- | `combineComparisonCosts` | production | this package: src/campaign/external-text-optimization.ts:41 |
690
616
  | `compareOptimizationMethods` | production | agent-app:src/eval-campaign/index.ts |
691
617
  | `componentSurfaceIdentityMaterial` | none | only this package's tests: src/campaign/surface-identity.test.ts:4 |
692
618
  | `composeGate` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/evolve.ts |
693
619
  | `costFromLedgerSummary` | production | agent-lab:projects/playproof/profile-improve.mts |
694
620
  | `createProfileMatrixPlan` | planned | doc: docs/eval-surface-map.md |
695
- | `createReferenceEquivalenceJudge` | none | only this package's tests: src/reference-equivalence-judge.test.ts:13 |
696
621
  | `createRetainedDispatch` | production | agent-dev-container:products/intelligence/api/src/lib/measurement-factory.ts |
697
622
  | `createRunCostLedger` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
698
623
  | `createSearchHistoryReceipt` | production | this package: src/campaign/search-ledger-recording.ts:27 |
699
- | `crowdedFrontierParent` | production | this package: scripts/search-sim.ts:146 |
700
- | `decideSearchClaim` | production | this package: src/campaign/search-kernel.ts:42 |
624
+ | `crowdedFrontierParent` | production | this package: scripts/search-sim/policy.ts:3 |
625
+ | `decideSearchClaim` | production | this package: src/campaign/search-kernel-claim.ts:4 |
701
626
  | `decodeExternalTextCandidate` | production | this package: src/campaign/external-text-optimization.ts:20 |
702
627
  | `DEFAULT_EXTERNAL_OPTIMIZER_CALLBACK_LIMITS` | planned | named in discovery-lab (bind not in the import graph) |
703
628
  | `DEFAULT_EXTERNAL_OPTIMIZER_PROCESS_LIMITS` | planned | named in discovery-lab (bind not in the import graph) |
704
629
  | `defaultProductionGate` | production | agent-app:src/eval-campaign/index.ts |
705
- | `detectScale` | production | this package: src/campaign/gates/promotion-policy.ts:25 |
706
630
  | `developmentClaim` | production | agent-dev-container:products/intelligence/api/scripts/search-scale-load.ts |
707
631
  | `dimensionRegressions` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-outcome.ts |
708
632
  | `discoverEvalFixtures` | planned | doc: docs/eval-fixtures.md |
@@ -711,10 +635,9 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
711
635
  | `estimateNodeFromCells` | production | agent-dev-container:products/intelligence/api/src/lib/search-stats.ts |
712
636
  | `externalSurface` | production | agent-runtime:scripts/verify-official-optimizers-consumer.mjs |
713
637
  | `externalTextOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
714
- | `FileSearchLedger` | production | this package: src/campaign/search-kernel.ts:52 |
638
+ | `FileSearchLedger` | production | this package: src/campaign/search-kernel-runner.ts:25 |
715
639
  | `finalizeProfileMatrix` | planned | doc: docs/eval-surface-map.md |
716
640
  | `fsCampaignStorage` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
717
- | `FsLabeledScenarioStore` | none | only this package's tests: src/campaign/presets/run-improvement-loop-capture-integrity.test.ts:5 |
718
641
  | `gepaOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
719
642
  | `gitWorktreeAdapter` | production | agent-runtime:src/improvement/code-execution.ts |
720
643
  | `heldOutGate` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-gate.ts |
@@ -722,51 +645,33 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
722
645
  | `importExternalEvaluations` | planned | doc: docs/search-ledger.md |
723
646
  | `importGepaPopulation` | planned | doc: docs/search-ledger.md |
724
647
  | `incumbent` | production | agent-runtime:examples/improve/search-execution-proof.ts |
725
- | `incumbentWithOperatorBandit` | production | this package: scripts/prove-operator-bandit.mts:18 |
648
+ | `incumbentWithOperatorBandit` | planned | doc: docs/search-ledger.md |
726
649
  | `inMemoryCampaignStorage` | production | agent-dev-container:products/sandbox/evals/src/auto-optimization.ts |
727
650
  | `isProposedCandidate` | production | agent-runtime:src/improvement/search-method.ts |
728
651
  | `isTransientTransportFailure` | production | gtm-agent:eval/suites/persona.ts |
729
- | `LabeledScenarioStoreError` | none | only this package's tests: tests/campaign/run-campaign.test.ts:7 |
730
- | `labelTrustRank` | production | this package: src/campaign/labeled-store/fs-adapter.ts:40 |
731
652
  | `llmJudge` | production | agent-runtime:examples/agentic-data-creation/offline-fixtures.ts |
732
653
  | `loadEvalFixture` | planned | doc: docs/eval-fixtures.md |
733
654
  | `loadEvalFixtureScenarios` | planned | example: examples/eval-fixtures-quickstart/index.ts:11 |
734
- | `loopProvenanceArgsFromResult` | production | this package: src/contract/self-improve.ts:36 |
735
- | `loopProvenanceSpans` | none | only this package's tests: tests/campaign/presets.test.ts:7 |
736
- | `makePlaybackDispatch` | none | only this package's tests: src/campaign/presets/playback.test.ts:6 |
737
655
  | `makeProposalFinding` | production | agent-lab:projects/playproof/code-surface.ts |
738
656
  | `neutralizationGate` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/evolve.ts |
739
657
  | `neutralizeText` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/compile-and-prove/compile-diff.ts |
740
- | `openAutoPr` | production | this package: src/campaign/presets/run-improvement-loop.ts:8 |
741
658
  | `openSearchLedger` | production | agent-runtime:src/durable/pursuit-versions.ts |
742
- | `optimizationTokenUsageFromSummary` | production | this package: src/campaign/external-text-optimization.ts:41 |
743
659
  | `pairHoldout` | production | agent-dev-container:products/intelligence/api/src/lib/run-provenance.ts |
744
660
  | `paretoPolicy` | planned | named in discovery-lab (bind not in the import graph) |
745
661
  | `paretoSignificanceGate` | production | agent-app:src/eval-campaign/index.ts |
746
662
  | `parseSearchLedgerLine` | production | agent-dev-container:products/intelligence/api/src/lib/search-verifier.ts |
747
- | `phoenixEvaluatorJudge` | none | only this package's tests: src/campaign/upstream-evaluators.test.ts:6 |
748
663
  | `planCampaignRun` | production | this package: src/campaign/fixtures.ts:5 |
749
664
  | `planEvalFixtureRun` | planned | example: examples/eval-fixtures-quickstart/index.ts:11 |
750
- | `planSearchClaim` | production | this package: src/campaign/search-kernel.ts:42 |
665
+ | `planSearchClaim` | production | this package: src/campaign/search-kernel-claim.ts:4 |
751
666
  | `powerPreflight` | production | this package: src/contract/self-improve.ts:21 |
752
- | `ProfileMatrixError` | production | this package: src/campaign/presets/segmented-profile-matrix.ts:22 |
753
- | `provenanceRecordPath` | none | only this package's tests: tests/contract-self-improve.test.ts:25 |
754
- | `provenanceSpansPath` | none | only this package's tests: tests/contract-self-improve.test.ts:25 |
755
- | `quotaExhaustedUntil` | none | only this package's tests: src/campaign/transient-failure.test.ts:3 |
756
- | `readCachedCell` | production | this package: src/campaign/execute-cell.ts:11 |
757
667
  | `readExternalOptimizerObservationArtifact` | production | agent-builder:src/lib/.server/eval/loops/method-evidence.ts |
758
668
  | `readGepaCandidatePopulationArtifact` | production | agent-runtime:scripts/verify-official-optimizers-consumer.mjs |
759
- | `recordGepaSearch` | production | this package: scripts/import-vb-climb.ts:35 |
760
- | `recordSkillOptSearch` | production | this package: src/campaign/skillopt-optimization-method.ts:41 |
761
669
  | `renderScoreboardMarkdown` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/run.ts |
762
670
  | `renderSearchSummary` | production | agent-runtime:src/improvement/search-method.ts |
763
671
  | `renderSurfaceDiff` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-evidence-packet.ts |
764
672
  | `replaySearchLedgerText` | production | agent-runtime:scripts/verify-official-optimizers-consumer.mjs |
765
- | `resolveExternalOptimizerCallbackLimits` | production | this package: src/analyst/dspy-rlm-engine.ts:1 |
766
- | `resolveExternalOptimizerProcessLimits` | production | this package: src/analyst/benchmark-command-persistence.ts:6 |
767
673
  | `resolveRunDir` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
768
674
  | `resolveWorktreePath` | none | only this package's tests: tests/campaign/worktree.test.ts:17 |
769
- | `rolloutArgumentDiff` | none | only this package's tests: src/campaign/grounded-reflection.test.ts:2 |
770
675
  | `runCampaign` | production | agent-app:src/eval-campaign/index.ts |
771
676
  | `runEval` | production | agent-dev-container:products/intelligence/api/src/lib/measurement-reference.ts |
772
677
  | `runImprovementLoop` | production | gtm:tools/gtm-doc-eval/improve.mjs |
@@ -778,27 +683,22 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
778
683
  | `scoreboardSummary` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/run.ts |
779
684
  | `scoreDiscrimination` | production | supervisor-lab:archive/bench/comms/seat-discrimination.ts |
780
685
  | `scoreUserStory` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/scoreboard-core.ts |
781
- | `SEARCH_CLAIM_RULE` | production | this package: src/campaign/search-kernel.ts:42 |
686
+ | `SEARCH_CLAIM_RULE` | production | this package: src/campaign/search-kernel-claim.ts:4 |
782
687
  | `SEARCH_ESTIMATOR` | planned | doc: docs/search-ledger.md |
783
- | `SEARCH_KERNEL_SOURCE` | production | this package: src/campaign/presets/run-optimization.ts:57 |
784
688
  | `SEARCH_LEDGER_SCHEMA` | production | agent-dev-container:products/intelligence/api/scripts/search-scale-load.ts |
785
689
  | `searchCellId` | production | agent-dev-container:products/intelligence/api/scripts/search-scale-load.ts |
786
690
  | `searchCellSetDigest` | planned | doc: docs/search-ledger.md |
787
691
  | `searchClaimDecision` | planned | doc: docs/search-ledger.md |
788
692
  | `searchClaimReserveUsd` | production | agent-runtime:src/improvement/search-method.ts |
789
- | `searchDivergence` | planned | doc: docs/search-ledger.md |
693
+ | `searchDivergence` | production | this package: src/campaign/search-kernel-runner.ts:24 |
790
694
  | `searchEdgeId` | production | agent-dev-container:products/intelligence/api/scripts/search-scale-load.ts |
791
- | `searchEstimateMethod` | production | this package: src/search/lenses/edit-credit.ts:34 |
792
- | `searchExpansionIndex` | production | this package: scripts/search-sim.ts:122 |
793
- | `searchHistoryCoverageRow` | production | this package: src/campaign/optimization-method.ts:14 |
794
- | `SearchHistoryRequiredError` | none | — |
795
- | `SearchLedgerConflictError` | production | this package: src/campaign/search-ledger.ts:36 |
695
+ | `searchEstimateMethod` | production | this package: src/search/lenses/edit-credit-statistics.ts:2 |
796
696
  | `SearchLedgerError` | production | agent-dev-container:products/intelligence/api/src/routes/search-ingest.ts |
797
- | `SearchLedgerIntegrityError` | production | this package: src/campaign/search-ledger-file.ts:10 |
697
+ | `SearchLedgerIntegrityError` | production | this package: src/campaign/search-ledger-constraints.ts:3 |
798
698
  | `searchModelIdentity` | production | agent-runtime:src/runtime/strategy-evolution.ts |
799
699
  | `searchNodeId` | production | agent-dev-container:products/intelligence/api/scripts/search-scale-load.ts |
800
- | `searchPolicyView` | production | this package: scripts/prove-operator-bandit.mts:18 |
801
- | `searchPosterior` | production | this package: src/campaign/search-claim.ts:27 |
700
+ | `searchPolicyView` | production | this package: scripts/search-sim/ledger-audit.ts:3 |
701
+ | `searchPosterior` | production | this package: src/campaign/search-claim.ts:28 |
802
702
  | `searchProposalExecution` | production | agent-runtime:src/improvement/search-method.ts |
803
703
  | `searchProposerView` | production | agent-runtime:src/improvement/search-method.ts |
804
704
  | `searchReceiptAccounting` | production | agent-runtime:src/improvement/search-executor.ts |
@@ -807,32 +707,27 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
807
707
  | `SearchStateView` | production | this package: scripts/search-meta-sim.ts:49 |
808
708
  | `searchTaskSetDigest` | production | agent-dev-container:products/intelligence/api/scripts/search-scale-load.ts |
809
709
  | `searchUnitScores` | production | agent-dev-container:products/intelligence/api/src/lib/search-stats.ts |
810
- | `selectDiscriminative` | none | only this package's tests: src/campaign/scenario-selection.test.ts:2 |
811
710
  | `sequentialDecide` | planned | doc: docs/experiment.md |
812
711
  | `sequentialOptimizationMethod` | production | supervisor-lab:src/learn/system-revise.ts |
813
712
  | `sequentialPairedGate` | planned | consumer tests: legal-agent:tests/eval/self-improve.ts |
814
713
  | `skillOptOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
815
714
  | `surfaceContentHash` | production | agent-runtime:scripts/verify-official-optimizers-consumer.mjs |
816
715
  | `surfaceDiff` | production | agent-runtime:src/runtime/strategy-evolution.ts |
817
- | `surfaceDispatchRef` | production | this package: src/campaign/presets/run-final-comparison.ts:11 |
716
+ | `surfaceDispatchRef` | production | this package: src/campaign/presets/optimization-surface-nodes.ts:39 |
818
717
  | `surfaceHash` | production | agent-builder:src/lib/.server/eval/loops/evolution-runner.ts |
819
718
  | `surfaceNode` | production | this package: scripts/synthetic-search-ledger.ts:54 |
820
- | `tangleTracesRoot` | none | only this package's tests: src/campaign/run-dir.test.ts:4 |
821
- | `traceAnalystQualityJudge` | production | this package: scripts/gepa-analyst-campaign.ts:74 |
822
719
  | `transientDispatchFailure` | planned | doc: docs/eval-surface-map.md |
823
720
  | `uniform` | production | agent-runtime:examples/improve/search-execution-proof.ts |
824
721
  | `userStoryScoreboard` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/run.ts |
825
722
  | `validateSearchLedgerEvent` | production | agent-dev-container:products/intelligence/api/scripts/search-scale-load.ts |
826
723
  | `verifyCodeSurface` | production | agent-runtime:src/candidate-execution/builder.ts |
827
- | `verifyLoopProvenanceRecord` | none | — |
828
724
  | `verifySearchClaim` | production | agent-dev-container:products/intelligence/api/src/lib/search-verifier.ts |
829
725
  | `verifySearchHistoryArtifact` | production | agent-runtime:src/improvement/method-execution.ts |
830
726
  | `verifySearchHistoryReceipt` | planned | doc: docs/search-ledger.md |
831
- | `WorktreeAdapterError` | none | only this package's tests: tests/campaign/worktree.test.ts:17 |
832
727
 
833
728
  ### `./contract`
834
729
 
835
- 63 value exports — 41 production, 15 planned, 7 none.
730
+ 55 value exports — 40 production, 15 planned, 0 none.
836
731
 
837
732
  | symbol | consumer | evidence |
838
733
  | --- | --- | --- |
@@ -843,11 +738,9 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
843
738
  | `compareOptimizationMethods` | production | agent-app:src/eval-campaign/index.ts |
844
739
  | `composeGate` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/evolve.ts |
845
740
  | `createChatClient` | production | agent-builder:src/lib/.server/eval/analysts/forge-deep-analyst.ts |
846
- | `createReferenceEquivalenceJudge` | none | only this package's tests: src/reference-equivalence-judge.test.ts:13 |
847
741
  | `defaultProductionGate` | production | agent-app:src/eval-campaign/index.ts |
848
742
  | `defineAgentEval` | planned | example: examples/evaluate-a-change/index.ts:10 |
849
- | `evalReportingSuite` | none | only this package's tests: tests/contract-eval-reporting-suite.test.ts:19 |
850
- | `evaluatePairedMeasurements` | production | this package: src/contract/profile-measured-comparison.ts:26 |
743
+ | `evaluatePairedMeasurements` | production | this package: src/contract/candidate-experiment.ts:35 |
851
744
  | `externalTextOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
852
745
  | `FileSystemOutcomeStore` | production | ph0ny:products/builder/api/src/eval/outcomes.ts |
853
746
  | `fromClaudeCodeSession` | planned | doc: docs/code-agent-intake.md |
@@ -856,9 +749,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
856
749
  | `fromKimiCodeSession` | planned | doc: docs/code-agent-intake.md |
857
750
  | `fromOpenCodeSession` | planned | doc: docs/code-agent-intake.md |
858
751
  | `fromOtelSpans` | production | agent-dev-container:packages/intelligence-kernel/src/deterministic.ts |
859
- | `fromPiGraphSession` | none | only this package's tests: tests/contract-code-agent-intake.test.ts:6 |
860
752
  | `fromPiSession` | planned | doc: docs/code-agent-intake.md |
861
- | `fromRunRecordDir` | production | this package: src/contract/eval-reporting-suite.ts:25 |
862
753
  | `fsCampaignStorage` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
863
754
  | `gepaOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
864
755
  | `heldOutGate` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-gate.ts |
@@ -868,22 +759,18 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
868
759
  | `makeProposalFinding` | production | agent-lab:projects/playproof/code-surface.ts |
869
760
  | `measuredComparisonFromAgentProfileImprovementExperiment` | production | agent-runtime:src/intelligence/authored-profile-improvement.ts |
870
761
  | `measuredComparisonFromCandidateExperiment` | production | agent-runtime:src/intelligence/improvement-cycle.ts |
871
- | `observeCodeAgentSession` | production | this package: src/contract/intake/code-agent-session.ts:14 |
872
- | `observeCodeAgentStore` | none | only this package's tests: tests/contract-code-agent-store.test.ts:5 |
762
+ | `observeCodeAgentSession` | production | this package: src/contract/intake/code-agent-session.ts:28 |
873
763
  | `paretoPolicy` | planned | named in discovery-lab (bind not in the import graph) |
874
764
  | `paretoSignificanceGate` | production | agent-app:src/eval-campaign/index.ts |
875
765
  | `parseAgentTrace` | planned | doc: docs/code-agent-intake.md |
876
766
  | `parseCodeAgentJsonl` | planned | doc: docs/code-agent-intake.md |
877
767
  | `parseCodeAgentJsonlFile` | production | this package: src/contract/intake/code-agent-store.ts:38 |
878
768
  | `partitionRunsByAuthoringModel` | planned | doc: docs/code-agent-intake.md |
879
- | `REFERENCE_EQUIVALENCE_INPUT_LIMITS` | none | only this package's tests: src/reference-equivalence-judge.test.ts:13 |
880
- | `REFERENCE_EQUIVALENCE_JUDGE_VERSION` | none | only this package's tests: src/reference-equivalence-judge.test.ts:13 |
881
769
  | `runAgentProfileImprovementExperiment` | production | agent-runtime:src/intelligence/authored-profile-improvement.ts |
882
770
  | `runCampaign` | production | agent-app:src/eval-campaign/index.ts |
883
771
  | `runCandidateExperiment` | production | agent-runtime:src/intelligence/improvement-cycle.ts |
884
772
  | `runEval` | production | agent-dev-container:products/intelligence/api/src/lib/measurement-reference.ts |
885
773
  | `runImprovementLoop` | production | gtm:tools/gtm-doc-eval/improve.mjs |
886
- | `runReferenceEquivalenceJudge` | none | only this package's tests: src/reference-equivalence-judge.test.ts:13 |
887
774
  | `sealAgentProfileImprovementExperiment` | production | agent-runtime:src/intelligence/authored-profile-improvement.ts |
888
775
  | `sealAgentProfileImprovementSuite` | production | agent-runtime:src/intelligence/profile-improvement-experiment.ts |
889
776
  | `sealAgentProfileImprovementTask` | production | agent-runtime:scripts/fixtures/packed-cohort-consumer.ts |
@@ -902,18 +789,16 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
902
789
 
903
790
  ### `./diagnosis`
904
791
 
905
- 8 value exports — 6 production, 0 planned, 2 none.
792
+ 6 value exports — 5 production, 0 planned, 1 none.
906
793
 
907
794
  | symbol | consumer | evidence |
908
795
  | --- | --- | --- |
909
796
  | `diagnoseSpans` | production | tangle-tools:trace-insights/mine/customer.mjs |
910
- | `DIAGNOSIS_FINDINGS_SCHEMA_ID` | none | — |
911
797
  | `epochMillis` | none | only this package's tests: src/diagnosis/diagnosis.test.ts:4 |
912
798
  | `ingestSpans` | production | traces:src/diff.ts |
913
799
  | `isContentAttribute` | production | traces:diagnosis-kit/checks/metadata-only.ts |
914
800
  | `nodeHttpPrimeBridgeTransport` | production | this package: src/analyst/benchmark-runner-prime.ts:18 |
915
801
  | `rankFirstFailure` | production | traces:src/session-facts.ts |
916
- | `validateDiagnosisFindings` | production | this package: src/diagnosis/engine.ts:23 |
917
802
 
918
803
  ### `./evaluation`
919
804
 
@@ -927,56 +812,42 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
927
812
 
928
813
  ### `./experiment`
929
814
 
930
- 89 value exports — 57 production, 19 planned, 13 none.
815
+ 67 value exports — 46 production, 19 planned, 2 none.
931
816
 
932
817
  | symbol | consumer | evidence |
933
818
  | --- | --- | --- |
934
819
  | `amendExperiment` | planned | doc: docs/experiment.md |
935
820
  | `assertDesignAdequate` | planned | doc: docs/eval-surface-map.md |
936
- | `assertFunnelReconciles` | none | only this package's tests: tests/experiment/funnel.test.ts:7 |
937
821
  | `assertMatchedBudgets` | planned | doc: docs/experiment.md |
938
822
  | `benjaminiHochberg` | production | agent-dev-container:packages/sdk-data/src/analysis/recommendations/statistics.ts |
939
823
  | `bonferroni` | planned | doc: docs/design/statistics-decisions.md |
940
824
  | `BOOTSTRAP_GATE_MIN_N` | production | discovery-lab:prereg/continuation-note-v1-tb/gate.mjs |
941
825
  | `buildEvidenceVector` | planned | doc: docs/experiment.md |
942
826
  | `buildFunnel` | production | blueprint-agent:scripts/experiments/lib/publication-decision.ts |
943
- | `classifyReissue` | none | only this package's tests: tests/experiment/preregistration-acceptance.test.ts:11 |
944
827
  | `clusteredPower` | production | blueprint-agent:scripts/experiments/lib/publication-decision.ts |
945
828
  | `comparePairedArms` | production | agent-knowledge:src/memory/experiment/learning-metrics.ts |
946
829
  | `composeFunnels` | planned | doc: docs/experiment.md |
947
- | `computeEstimand` | production | this package: src/experiment/define.ts:20 |
948
830
  | `computeInterval` | production | blueprint-agent:scripts/experiments/lib/board-record.ts |
949
- | `createCampaignEvidenceReceipt` | production | this package: src/campaign/presets/compare-optimization-methods.ts:11 |
831
+ | `createCampaignEvidenceReceipt` | production | this package: src/campaign/presets/compare-optimization-methods.ts:17 |
950
832
  | `createEvidenceReceipt` | production | this package: src/experiment/campaign-evidence.ts:7 |
951
833
  | `decideRandomizedCanary` | planned | doc: docs/experiment.md |
952
834
  | `defineEvaluationClaim` | production | agent-runtime:src/improvement/search-method.ts |
953
- | `defineExperiment` | production | this package: scripts/tb-gated-stop-ab.ts:55 |
954
- | `DesignRefusalError` | none | only this package's tests: tests/experiment/power.test.ts:10 |
835
+ | `defineExperiment` | production | this package: scripts/tb-gated-stop/design.ts:2 |
955
836
  | `eProcess` | production | this package: src/campaign/gates/sequential.ts:37 |
956
837
  | `evaluateCondition` | planned | named in agent-dev-container (bind not in the import graph) |
957
- | `evaluateHaltRule` | production | this package: src/experiment/define.ts:20 |
958
- | `evaluateHypothesis` | none | only this package's tests: tests/tier2.test.ts:4 |
959
- | `evaluateIdentityGate` | production | this package: src/experiment/define.ts:20 |
960
- | `evaluateOracleDeterminismGate` | production | this package: src/experiment/define.ts:20 |
961
- | `evaluatePopulationReproducibilityGate` | production | this package: src/experiment/define.ts:20 |
962
- | `evaluatePowerFloorGate` | production | this package: src/experiment/define.ts:20 |
963
- | `evaluatePredicate` | production | this package: src/experiment/funnel.ts:17 |
964
- | `evaluateProvenanceGate` | production | this package: src/experiment/define.ts:20 |
965
- | `EVIDENCE_RECEIPT_VERSION` | none | — |
838
+ | `evaluatePowerFloorGate` | production | this package: src/experiment/define.ts:48 |
966
839
  | `EVIDENCE_STATES` | planned | named in discovery-lab (bind not in the import graph) |
967
840
  | `evidenceRegistryRecordSchema` | planned | named in discovery-lab (bind not in the import graph) |
968
- | `executeAdmissionRule` | production | this package: src/experiment/define.ts:65 |
969
- | `executeDecisionRule` | production | this package: src/experiment/define.ts:20 |
841
+ | `executeAdmissionRule` | production | this package: src/experiment/define.ts:66 |
842
+ | `executeDecisionRule` | production | this package: src/experiment/define.ts:31 |
970
843
  | `FinalEvidenceConflictError` | production | this package: src/campaign/final-evidence.ts:7 |
971
844
  | `FinalEvidenceError` | production | this package: src/campaign/final-evidence.ts:7 |
972
- | `FunnelIntegrityError` | none | only this package's tests: tests/experiment/funnel.test.ts:7 |
973
845
  | `hashJson` | production | agent-dev-container:products/intelligence/api/src/lib/ingest-optimization-mapping.ts |
974
846
  | `heldoutSignificance` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
975
- | `holm` | production | this package: src/search/lenses/edit-credit.ts:47 |
847
+ | `holm` | production | this package: src/search/lenses/edit-credit-statistics.ts:6 |
976
848
  | `isIndependentEvidence` | planned | consumer tests: agent-runtime:tests/integration/runtime-eval-pursuit-evidence.test.ts |
977
849
  | `joinProspectiveCanaryReceipts` | planned | doc: docs/experiment.md |
978
850
  | `manifestContentDigest` | production | this package: src/campaign/gates/sequential.ts:36 |
979
- | `MatchedBudgetError` | none | only this package's tests: tests/experiment/budget-and-seal.test.ts:8 |
980
851
  | `mcnemar` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
981
852
  | `mcnemarPower` | production | discovery:research/e1-topology-20260920/gate/gate.mjs |
982
853
  | `mcnemarRequiredN` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
@@ -994,57 +865,44 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
994
865
  | `pairRunRecords` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
995
866
  | `paretoPolicy` | planned | named in discovery-lab (bind not in the import graph) |
996
867
  | `paretoSignificanceGate` | production | agent-app:src/eval-campaign/index.ts |
997
- | `parseEvidenceRegistryRecord` | none | only this package's tests: src/experiment/evidence-record.test.ts:4 |
998
868
  | `powerPreflight` | production | this package: src/contract/self-improve.ts:21 |
999
- | `projectNLadderBudget` | production | this package: src/experiment/define.ts:20 |
1000
869
  | `randomizedCanaryObservationDigest` | none | only this package's tests: src/experiment/prospective-canary-join.test.ts:2 |
1001
870
  | `randomizedCanaryRosterDigest` | none | only this package's tests: src/experiment/prospective-canary-join.test.ts:2 |
1002
- | `readField` | production | this package: src/experiment/claim.ts:4 |
1003
- | `renderEvidenceIndex` | production | this package: scripts/render-evidence-index.ts:15 |
871
+ | `readField` | production | this package: src/experiment/ast/estimand.ts:3 |
1004
872
  | `renderFunnelTable` | planned | example: examples/sealed-experiment/index.ts:12 |
1005
873
  | `requiredPairedSampleSize` | production | discovery:research/e1-topology-20260920/gate/gate.mjs |
1006
874
  | `requiredSampleSize` | production | agent-dev-container:products/sandbox/evals/src/stats.ts |
1007
- | `runSelectionRule` | production | this package: src/experiment/define.ts:20 |
1008
- | `runUniformPassBudget` | production | this package: src/experiment/define.ts:20 |
1009
875
  | `sealExperiment` | production | blueprint-agent:scripts/experiments/lib/__tests__/publication-fixtures.ts |
1010
- | `SealIntegrityError` | none | only this package's tests: tests/experiment/budget-and-seal.test.ts:8 |
1011
876
  | `sealRandomizedCanaryRule` | planned | doc: docs/experiment.md |
1012
- | `sequentialCrossingHorizon` | none | only this package's tests: tests/sequential.test.ts:2 |
1013
877
  | `sequentialDecide` | planned | doc: docs/experiment.md |
1014
878
  | `sequentialPairedGate` | planned | consumer tests: legal-agent:tests/eval/self-improve.ts |
1015
879
  | `signManifest` | production | ph0ny:products/builder/api/src/eval/champion-sign.ts |
1016
880
  | `summarizeEvaluationUnits` | production | agent-runtime:src/improvement/search-method.ts |
1017
- | `validateEvidenceRegistry` | none | only this package's tests: src/experiment/evidence-record.test.ts:4 |
1018
881
  | `verifyEvidenceReceipt` | planned | consumer tests: agent-runtime:tests/integration/runtime-eval-pursuit-evidence.test.ts |
1019
882
  | `verifyManifest` | production | ph0ny:products/builder/api/src/eval/champion-sign.ts |
1020
- | `verifyMatchedBudgets` | production | this package: src/experiment/define.ts:58 |
883
+ | `verifyMatchedBudgets` | production | this package: src/experiment/define.ts:59 |
1021
884
  | `verifySealedExperiment` | production | discovery-lab:experiments/profile-search-h2a/run.mjs |
1022
885
  | `wilson` | production | agent-dev-container:packages/sdk-data/src/analysis/recommendations/statistics.ts |
1023
886
 
1024
887
  ### `./fuzz`
1025
888
 
1026
- 14 value exports — 11 production, 1 planned, 2 none.
889
+ 9 value exports — 8 production, 1 planned, 0 none.
1027
890
 
1028
891
  | symbol | consumer | evidence |
1029
892
  | --- | --- | --- |
1030
- | `adversarialObjective` | production | this package: src/fuzz/explorer.ts:23 |
1031
- | `BehaviorExplorer` | production | this package: src/fuzz/fuzz-agent.ts:9 |
1032
- | `buildCapsule` | production | this package: src/fuzz/explorer.ts:20 |
1033
893
  | `buildCoverage` | production | this package: src/fuzz/capsule.ts:12 |
1034
894
  | `cellId` | planned | consumer tests: tax-agent:tests/eval/lib/fuzz-space.ts |
1035
895
  | `composeGates` | production | creative-agent:eval/lib/fuzz-wiring.ts |
1036
896
  | `enumerateCells` | production | this package: src/fuzz/explorer.ts:22 |
1037
897
  | `fuzzAgent` | production | creative-agent:eval/fuzz.ts |
1038
- | `makeExploreTools` | none | only this package's tests: src/fuzz/fuzz-agent.test.ts:8 |
1039
898
  | `mutationProposer` | production | creative-agent:eval/fuzz.ts |
1040
- | `noveltyObjective` | none | only this package's tests: src/fuzz/fuzz-agent.test.ts:7 |
1041
899
  | `perturbationStabilityGate` | production | creative-agent:eval/lib/fuzz-wiring.ts |
1042
900
  | `renderCapsuleHtml` | production | creative-agent:eval/fuzz.ts |
1043
901
  | `severityFloorGate` | production | creative-agent:eval/lib/fuzz-wiring.ts |
1044
902
 
1045
903
  ### `./hosted`
1046
904
 
1047
- 24 value exports — 21 production, 2 planned, 1 none.
905
+ 18 value exports — 16 production, 2 planned, 0 none.
1048
906
 
1049
907
  | symbol | consumer | evidence |
1050
908
  | --- | --- | --- |
@@ -1052,21 +910,15 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1052
910
  | `createHostedClient` | production | traces:src/index.ts |
1053
911
  | `HOSTED_WIRE_VERSION` | production | agent-dev-container:packages/sdk-data/src/sink/intelligence-sink.ts |
1054
912
  | `hostedClientFromEnv` | production | traces:src/index.ts |
1055
- | `HostedRequestError` | none | — |
1056
913
  | `hostedTenantFromEnv` | production | blueprint-agent:scripts/experiments/vb-climb-definer.ts |
1057
914
  | `IngestResponseSchema` | production | this package: src/hosted/client.ts:22 |
1058
915
  | `IngestSearchLedgerRequestSchema` | production | agent-dev-container:products/intelligence/api/src/routes/search-ingest.ts |
1059
916
  | `IngestTracesRequestSchema` | production | this package: src/hosted/client.ts:22 |
1060
917
  | `SEARCH_LEDGER_BATCH_MAX_BYTES` | production | agent-dev-container:products/intelligence/api/src/routes/search-ingest.ts |
1061
- | `SEARCH_LEDGER_BATCH_MAX_LINES` | production | this package: src/hosted/search-shipper.ts:18 |
1062
918
  | `SEARCH_LEDGER_INGEST_PATH` | production | agent-dev-container:products/intelligence/api/src/routes/search-ingest.ts |
1063
- | `searchBlobPath` | production | this package: src/hosted/client.ts:23 |
1064
919
  | `SearchBlobPutResponseSchema` | production | this package: src/hosted/client.ts:23 |
1065
- | `searchLedgerArtifactRefs` | production | this package: src/hosted/search-shipper.ts:18 |
1066
920
  | `SearchLedgerConflictSchema` | production | this package: src/hosted/client.ts:23 |
1067
- | `searchLedgerHeadPath` | production | this package: src/hosted/client.ts:23 |
1068
921
  | `SearchLedgerHeadSchema` | production | this package: src/hosted/client.ts:23 |
1069
- | `SearchRunKindSchema` | production | this package: src/search-command.ts:37 |
1070
922
  | `SearchShipConflictError` | production | this package: src/search-command.ts:38 |
1071
923
  | `shipSearchLedger` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
1072
924
  | `startSearchShipper` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
@@ -1075,52 +927,37 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1075
927
 
1076
928
  ### `./ledger-core`
1077
929
 
1078
- 28 value exports — 19 production, 1 planned, 8 none.
930
+ 14 value exports — 9 production, 1 planned, 4 none.
1079
931
 
1080
932
  | symbol | consumer | evidence |
1081
933
  | --- | --- | --- |
1082
- | `appendLedgerLine` | production | this package: src/campaign/search-ledger-file.ts:3 |
1083
- | `AtomicFileLockError` | production | this package: src/ledger-core/journal-file.ts:16 |
1084
934
  | `canonicalString` | production | agent-dev-container:products/intelligence/api/scripts/search-scale-load.ts |
1085
935
  | `FileLedgerJournal` | production | discovery-lab:runner/evidence-review.mjs |
1086
936
  | `hashCanonical` | production | agent-dev-container:products/intelligence/api/scripts/prove-measurement.ts |
1087
937
  | `jsonDocument` | production | blueprint-agent:scripts/experiments/lib/__tests__/customer-evidence-fixtures.ts |
1088
938
  | `LEDGER_HASH_PATTERN` | production | blueprint-agent:scripts/experiments/lib/causal-analytics.ts |
1089
939
  | `LedgerCanonicalizationError` | planned | named in blueprint-agent (bind not in the import graph) |
1090
- | `MemoryLedgerJournal` | production | this package: src/campaign/search-ledger.ts:23 |
1091
- | `MERKLE_EMPTY_ROOT` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
1092
- | `merkleConsistencyProof` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
1093
- | `merkleInclusionProof` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
1094
- | `merkleLeafHash` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
1095
- | `merkleRoot` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
1096
- | `merkleSalt` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
1097
- | `probeAtomicFileLock` | production | this package: src/campaign/single-run-lock.ts:17 |
1098
- | `projectorSnapshotPathFor` | production | this package: src/ledger-core/journal.ts:48 |
1099
- | `readProjectorSnapshotFile` | production | this package: src/ledger-core/journal.ts:48 |
1100
- | `readTrustedHeadFile` | production | this package: src/ledger-core/journal.ts:55 |
1101
- | `replayLedgerText` | production | this package: src/campaign/search-ledger.ts:23 |
1102
- | `trustedHeadPathFor` | production | this package: src/ledger-core/journal.ts:55 |
940
+ | `merkleInclusionProof` | none | — |
941
+ | `merkleLeafHash` | none | — |
942
+ | `merkleRoot` | production | this package: src/analyst/findings-ledger.ts:18 |
943
+ | `merkleSalt` | none | — |
1103
944
  | `tryAcquireAtomicFileLock` | production | discovery-lab:runner/evidence-review.mjs |
1104
945
  | `tryWithLedgerFileLock` | production | discovery-lab:experiments/diu-campaign-v1/launch-wave-cloud.mjs |
1105
- | `verifyEntriesAgainstTrustedHead` | production | this package: src/ledger-core/journal.ts:55 |
1106
- | `verifyMerkleConsistency` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
1107
- | `verifyMerkleInclusion` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
1108
- | `withLedgerFileLock` | production | this package: src/analyst/benchmark-response-cache.ts:6 |
946
+ | `verifyMerkleInclusion` | none | — |
1109
947
  | `writeLedgerFileAtomically` | production | discovery-lab:experiments/diu-campaign-v1/launch-wave-cloud.mjs |
1110
948
 
1111
949
  ### `./matrix`
1112
950
 
1113
- 3 value exports — 3 production, 0 planned, 0 none.
951
+ 2 value exports — 2 production, 0 planned, 0 none.
1114
952
 
1115
953
  | symbol | consumer | evidence |
1116
954
  | --- | --- | --- |
1117
- | `readCellSpend` | production | this package: src/matrix/runner.ts:15 |
1118
955
  | `runAgentMatrix` | production | blueprint-agent:scripts/experiments/lib/vb-matrix.ts |
1119
956
  | `withCellSpend` | production | gtm-agent:eval/lib/multishot-graph.ts |
1120
957
 
1121
958
  ### `./meta-eval`
1122
959
 
1123
- 43 value exports — 27 production, 14 planned, 2 none.
960
+ 42 value exports — 27 production, 14 planned, 1 none.
1124
961
 
1125
962
  | symbol | consumer | evidence |
1126
963
  | --- | --- | --- |
@@ -1145,7 +982,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1145
982
  | `fileSentinelStore` | production | creative-agent:eval/lib/judge-sentinel.ts |
1146
983
  | `FileSystemOutcomeStore` | production | ph0ny:products/builder/api/src/eval/outcomes.ts |
1147
984
  | `InMemoryOutcomeStore` | planned | consumer tests: ph0ny:products/builder/api/src/eval/outcomes-correlate.test.ts |
1148
- | `inMemorySentinelStore` | none | only this package's tests: src/meta-eval/judge-gate.test.ts:2 |
1149
985
  | `judgeGateDecision` | planned | doc: docs/concepts.md |
1150
986
  | `JudgeGateRefusedError` | planned | doc: docs/concepts.md |
1151
987
  | `judgeSentinelReport` | production | creative-agent:eval/lib/judge-sentinel.ts |
@@ -1170,7 +1006,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1170
1006
 
1171
1007
  ### `./multishot`
1172
1008
 
1173
- 18 value exports — 10 production, 4 planned, 4 none.
1009
+ 14 value exports — 10 production, 4 planned, 0 none.
1174
1010
 
1175
1011
  | symbol | consumer | evidence |
1176
1012
  | --- | --- | --- |
@@ -1179,23 +1015,19 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1179
1015
  | `DEFAULT_CODER_MODEL` | planned | named in blueprint-agent (bind not in the import graph) |
1180
1016
  | `DEFAULT_JUDGE_MODEL` | planned | named in agent-builder (bind not in the import graph) |
1181
1017
  | `defaultDelegationTools` | production | gtm-agent:eval/lib/multishot-graph.ts |
1182
- | `defaultMultishotDriverSystemPrompt` | none | only this package's tests: tests/multishot/shape-defaults.test.ts:10 |
1183
- | `defaultMultishotOpener` | none | only this package's tests: tests/multishot/shape-defaults.test.ts:10 |
1184
1018
  | `defaultShapeFromProfile` | production | gtm-agent:eval/lib/multishot-graph.ts |
1185
1019
  | `estimateMultishotCost` | production | gtm-agent:eval/lib/multishot-graph.ts |
1186
1020
  | `MultishotDriverEmptyError` | production | gtm-agent:eval/lib/multishot-graph.ts |
1187
1021
  | `MultishotFatalToolError` | production | gtm-agent:eval/lib/multishot-graph.ts |
1188
- | `MultishotShotResultError` | none | only this package's tests: tests/multishot/matrix-shot-seam.test.ts:18 |
1189
1022
  | `renderDimensions` | planned | consumer tests: tax-agent:tests/eval/multishot.ts |
1190
1023
  | `renderJsonFooter` | production | gtm-agent:eval/scoring/multishot-judges.ts |
1191
- | `renderPersonaFacts` | none | only this package's tests: tests/multishot/shape-defaults.test.ts:10 |
1192
1024
  | `runJudge` | production | gtm-agent:eval/monitoring/live-soak.ts |
1193
1025
  | `runMultishot` | production | agent-runtime:examples/p1-parity/arms.ts |
1194
1026
  | `runMultishotMatrix` | production | gtm-agent:eval/lib/multishot-matrix-graph.ts |
1195
1027
 
1196
1028
  ### `./multishot/golden`
1197
1029
 
1198
- 21 value exports — 11 production, 8 planned, 2 none.
1030
+ 15 value exports — 7 production, 8 planned, 0 none.
1199
1031
 
1200
1032
  | symbol | consumer | evidence |
1201
1033
  | --- | --- | --- |
@@ -1204,26 +1036,20 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1204
1036
  | `checkMultishotGolden` | planned | doc: docs/multishot-golden-records.md |
1205
1037
  | `checkMultishotGoldenScenario` | planned | doc: docs/multishot-golden-records.md |
1206
1038
  | `checkMultishotMatrixGoldenScenario` | planned | doc: docs/multishot-golden-records.md |
1207
- | `compareJson` | production | this package: scripts/record-multishot-golden.ts:32 |
1208
1039
  | `CURRENT_MULTISHOT_GOLDEN_VERSION` | planned | doc: docs/multishot-golden-records.md |
1209
- | `goldenRecords` | production | this package: src/multishot/golden/harness.ts:23 |
1210
- | `maskVolatileMarkdown` | none | only this package's tests: src/multishot/golden/golden.test.ts:20 |
1040
+ | `goldenRecords` | production | this package: src/multishot/golden/harness.ts:24 |
1211
1041
  | `MultishotGoldenMismatchError` | planned | doc: docs/multishot-golden-records.md |
1212
1042
  | `multishotGoldenScenarios` | production | this package: scripts/record-multishot-golden.ts:49 |
1213
- | `multishotGoldenVersions` | none | — |
1214
1043
  | `multishotMatrixGoldenScenarios` | production | this package: scripts/record-multishot-golden.ts:38 |
1215
- | `readRunDir` | production | this package: scripts/record-multishot-golden.ts:42 |
1216
1044
  | `recordError` | production | this package: scripts/record-multishot-golden.ts:42 |
1217
- | `recordJudgeRequest` | production | this package: src/multishot/golden/matrix-scenarios.ts:21 |
1218
1045
  | `recordMessage` | planned | named in agent-dev-container (bind not in the import graph) |
1219
1046
  | `recordRequest` | production | this package: src/multishot/golden/matrix-scenarios.ts:21 |
1220
1047
  | `recordResult` | production | this package: scripts/record-multishot-golden.ts:42 |
1221
- | `sortJudgeRequests` | production | this package: scripts/record-multishot-golden.ts:42 |
1222
1048
  | `stripVolatile` | production | this package: scripts/record-multishot-golden.ts:42 |
1223
1049
 
1224
1050
  ### `./pipelines`
1225
1051
 
1226
- 10 value exports — 8 production, 0 planned, 2 none.
1052
+ 8 value exports — 8 production, 0 planned, 0 none.
1227
1053
 
1228
1054
  | symbol | consumer | evidence |
1229
1055
  | --- | --- | --- |
@@ -1232,261 +1058,190 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1232
1058
  | `diffSteps` | production | traces:src/diff.ts |
1233
1059
  | `diffStepsFromSpans` | production | traces:src/diff.ts |
1234
1060
  | `failureClusterView` | production | insurance-agent:scripts/analyze-agent-eval-evidence.ts |
1235
- | `firstDivergenceView` | none | only this package's tests: tests/pipelines.test.ts:2 |
1236
1061
  | `judgeAgreementView` | production | insurance-agent:scripts/analyze-agent-eval-evidence.ts |
1237
- | `regressionView` | none | only this package's tests: src/pipelines/regression.test.ts:4 |
1238
1062
  | `stuckLoopView` | production | agent-runtime:src/runtime/supervise/trajectory-recorder.ts |
1239
1063
  | `toolWasteView` | production | agent-runtime:src/runtime/supervise/trajectory-recorder.ts |
1240
1064
 
1241
1065
  ### `./profile-cell`
1242
1066
 
1243
- 11 value exports — 5 production, 3 planned, 3 none.
1067
+ 8 value exports — 5 production, 3 planned, 0 none.
1244
1068
 
1245
1069
  | symbol | consumer | evidence |
1246
1070
  | --- | --- | --- |
1247
1071
  | `AGENT_PROFILE_KINDS` | production | blueprint-agent:scripts/experiments/lib/agent-profile-cell.ts |
1248
1072
  | `agentProfileCellKey` | planned | consumer tests: blueprint-agent:scripts/experiments/lib/__tests__/agent-profile-cell.test.ts |
1249
1073
  | `AgentProfileCellValidationError` | planned | doc: docs/profile-json-identity.md |
1250
- | `assertRunAgentProfileCell` | none | only this package's tests: tests/agent-profile-cell.test.ts:3 |
1251
- | `buildAgentInterfaceProfileCell` | none | only this package's tests: tests/agent-profile-cell.test.ts:3 |
1252
1074
  | `buildAgentProfileCell` | production | ai-trading-blueprint:evals/src/trading/agent-profile-cell.ts |
1253
1075
  | `groupRunsByAgentProfileCell` | planned | consumer tests: legal-agent:tests/eval/matrix-multi.ts |
1254
- | `requireAgentProfileCell` | none | only this package's tests: tests/agent-profile-cell.test.ts:3 |
1255
1076
  | `toAgentProfileJson` | production | blueprint-agent:scripts/experiments/lib/agent-profile-cell.ts |
1256
1077
  | `validateAgentProfileCell` | production | blueprint-agent:apps/web/src/lib/.server/services/leaderboards/submission-profile-config.ts |
1257
1078
  | `verifyAgentProfileCell` | production | this package: src/eval-campaign.ts:39 |
1258
1079
 
1259
1080
  ### `./reporting`
1260
1081
 
1261
- 15 value exports — 10 production, 4 planned, 1 none.
1082
+ 13 value exports — 12 production, 1 planned, 0 none.
1262
1083
 
1263
1084
  | symbol | consumer | evidence |
1264
1085
  | --- | --- | --- |
1265
- | `assertReleaseConfidence` | none | only this package's tests: tests/release-confidence.test.ts:4 |
1266
1086
  | `benjaminiHochberg` | production | agent-dev-container:packages/sdk-data/src/analysis/recommendations/statistics.ts |
1267
1087
  | `bootstrapCi` | production | agent-dev-container:products/intelligence/api/src/lib/auto-improve/measure-online-rewards.ts |
1268
1088
  | `evaluateInterimReleaseConfidence` | production | agent-builder:scripts/eval.ts |
1269
1089
  | `evaluateReleaseConfidence` | production | agent-knowledge:src/release.ts |
1270
- | `gainHistogram` | planned | doc: docs/research-report-methodology.md |
1090
+ | `gainHistogram` | production | this package: src/research-report.ts:18 |
1271
1091
  | `judgeReplayGate` | planned | named in physim (bind not in the import graph) |
1272
1092
  | `pairedBootstrap` | production | agent-builder:frontier/adapters/fleet-eval-runner.ts |
1273
1093
  | `pairedEvalueSequence` | production | creative-agent:src/lib/experiments/ab-design.ts |
1274
- | `paretoChart` | production | workcomp-agent:eval/benchmark/select.ts |
1275
- | `RESEARCH_REPORT_HARD_PAIR_FLOOR` | planned | doc: docs/research-report-methodology.md |
1094
+ | `RESEARCH_REPORT_HARD_PAIR_FLOOR` | production | this package: src/research-report.ts:7 |
1276
1095
  | `researchReport` | production | this package: src/eval-campaign.ts:58 |
1277
1096
  | `rubricPredictiveValidity` | production | physim:apps/server/src/scripts/agent-eval/validate-rubrics.ts |
1278
- | `summaryTable` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/analyze.mjs |
1097
+ | `summaryTable` | production | this package: src/research-report.ts:18 |
1279
1098
  | `wilcoxonSignedRank` | production | agent-builder:src/lib/.server/eval/loops/differential-eval.ts |
1280
1099
 
1281
1100
  ### `./rl`
1282
1101
 
1283
- 79 value exports — 19 production, 32 planned, 28 none.
1102
+ 48 value exports — 14 production, 32 planned, 2 none.
1284
1103
 
1285
1104
  | symbol | consumer | evidence |
1286
1105
  | --- | --- | --- |
1287
- | `ABSENT_CATEGORY` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
1288
- | `appendToCorpus` | none | only this package's tests: src/rl/corpus.test.ts:6 |
1289
- | `applyEloUpdate` | none | only this package's tests: tests/rl-tournament.test.ts:2 |
1290
1106
  | `bestOfN` | production | supervisor-lab:src/learn/retry.ts |
1291
1107
  | `bucketLabel` | planned | named in agent-dev-container (bind not in the import graph) |
1292
- | `buildDatasetFromCorpus` | none | only this package's tests: src/rl/corpus.test.ts:6 |
1293
- | `buildPairwiseFromCampaign` | none | only this package's tests: tests/rl-tournament.test.ts:2 |
1294
1108
  | `buildRlDataset` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
1295
- | `buildVerifiedFindingRow` | none | only this package's tests: src/rl/verified-findings-dataset.test.ts:5 |
1296
1109
  | `campaignToRunRecords` | production | agent-builder:src/lib/.server/kb/optimization.ts |
1297
1110
  | `checkerReadSignal` | planned | doc: docs/systemone-behavior-review.md |
1298
- | `CLAIM_INTEGRITY_VERSION` | none | — |
1299
1111
  | `claimIntegrityDigest` | planned | named in discovery-lab (bind not in the import graph) |
1300
1112
  | `claimIntegritySystemOneReview` | planned | doc: docs/systemone-behavior-review.md |
1301
1113
  | `claimIntegrityTraceQuestions` | planned | doc: docs/systemone-behavior-review.md |
1302
1114
  | `claimIntegrityVerdict` | planned | doc: docs/systemone-behavior-review.md |
1303
1115
  | `compareAdaptationCurves` | planned | doc: docs/design/statistics-decisions.md |
1304
- | `datasheetToMarkdown` | none | only this package's tests: src/rl/dataset.test.ts:7 |
1305
- | `defaultBehaviorFeatures` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
1306
1116
  | `detectRewardHacking` | production | agent-builder:scripts/eval.ts |
1307
1117
  | `doublyRobust` | planned | consumer tests: agent-knowledge:tests/memory-holdout.test.ts |
1308
- | `easyModeCheck` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
1309
1118
  | `extractPreferences` | production | creative-agent:eval/canonical-export.ts |
1310
- | `extractStepRewards` | none | only this package's tests: tests/rl-process-reward.test.ts:3 |
1311
1119
  | `extractVerifiableReward` | planned | named in gtm-agent (bind not in the import graph) |
1312
1120
  | `extractVerifiableRewardsFromRecords` | production | creative-agent:eval/canonical-export.ts |
1313
1121
  | `farmingSignal` | planned | doc: docs/systemone-behavior-review.md |
1314
1122
  | `FileSystemOutcomeStore` | production | ph0ny:products/builder/api/src/eval/outcomes.ts |
1315
- | `filterDeterministicallyRewarded` | production | this package: src/rl/reward-hacking.ts:43 |
1316
1123
  | `firstPassK` | planned | doc: docs/statistical-evidence.md |
1317
1124
  | `fitBradleyTerry` | none | only this package's tests: tests/rl-tournament.test.ts:2 |
1318
1125
  | `GRADER_REFERENCE_PHRASES` | planned | named in discovery-lab (bind not in the import graph) |
1319
1126
  | `graderReferenceSignal` | planned | doc: docs/systemone-behavior-review.md |
1320
- | `injectIrrelevantClause` | none | only this package's tests: tests/rl-contamination.test.ts:2 |
1321
1127
  | `InMemoryOutcomeStore` | planned | consumer tests: ph0ny:products/builder/api/src/eval/outcomes-correlate.test.ts |
1322
1128
  | `inverseProbabilityWeighting` | planned | consumer tests: agent-knowledge:tests/memory-holdout.test.ts |
1323
- | `jsDivergence` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
1324
1129
  | `loadVerifiedFindingsDataset` | planned | doc: docs/verified-labels-flywheel.md |
1325
1130
  | `monitorSignal` | planned | doc: docs/systemone-behavior-review.md |
1326
- | `offPolicyEstimateAll` | none | only this package's tests: tests/rl-off-policy.test.ts:3 |
1327
- | `paretoFrontier` | production | agent-dev-container:products/sandbox/evals/run.ts |
1131
+ | `paretoCostScoreFrontier` | none | only this package's tests: tests/rl-adversarial-and-compute.test.ts:2 |
1328
1132
  | `parseSourceScopeReferee` | planned | doc: docs/systemone-behavior-review.md |
1329
1133
  | `PredictiveValidityResearcher` | planned | doc: docs/design/mlbenchmarks-book-review.md |
1330
1134
  | `prmTrainingPairs` | planned | doc: examples/fine-tune-with-prime-rl/README.md |
1331
- | `quantileEdges` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
1332
1135
  | `readCorpus` | planned | named in agent-runtime (bind not in the import graph) |
1333
1136
  | `refereeSignal` | planned | doc: docs/systemone-behavior-review.md |
1334
- | `renameVariables` | none | only this package's tests: tests/rl-contamination.test.ts:2 |
1335
1137
  | `ruleHolds` | planned | consumer tests: discovery-lab:experiments/factory-test-2/null-certificate.test.mjs |
1336
1138
  | `runAdaptationCurve` | planned | doc: docs/statistical-evidence.md |
1337
- | `runComputeCurve` | none | only this package's tests: tests/rl-adversarial-and-compute.test.ts:2 |
1338
1139
  | `runContaminationProbe` | planned | doc: docs/statistical-evidence.md |
1339
1140
  | `runEvalCampaign` | production | agent-builder:scripts/eval.ts |
1340
1141
  | `runRLCampaign` | planned | doc: docs/outcome-validity.md |
1341
- | `runwiseStepRewardSummary` | none | only this package's tests: tests/rl-process-reward.test.ts:3 |
1342
1142
  | `scopeSignals` | planned | doc: docs/systemone-behavior-review.md |
1343
- | `selfConsistency` | none | only this package's tests: tests/rl-adversarial-and-compute.test.ts:2 |
1344
1143
  | `selfNormalizedImportanceWeighting` | planned | consumer tests: agent-knowledge:tests/memory-holdout.test.ts |
1345
- | `shuffleOrder` | none | — |
1346
- | `simFidelityReport` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
1347
1144
  | `sourceScopeRefereeMessages` | planned | doc: docs/systemone-behavior-review.md |
1348
- | `stepRewardsToJsonl` | none | only this package's tests: src/rollout/gate-properties.test.ts:38 |
1349
- | `summarizeVerifiedFindings` | none | only this package's tests: src/rl/verified-findings-dataset.test.ts:5 |
1350
1145
  | `systemOneSignal` | planned | doc: docs/changes/systemone-provider-neutral.md |
1351
1146
  | `toAnthropicFormat` | production | blueprint-agent:scripts/experiments/lib/steering-dataset.ts |
1352
- | `toDpoJsonl` | production | this package: src/rl/dataset.ts:27 |
1353
1147
  | `toDpoRows` | production | this package: src/rl/dataset.ts:27 |
1354
- | `toGrpoJsonl` | production | this package: src/rl/dataset.ts:27 |
1355
1148
  | `toGrpoRows` | production | this package: src/rl/dataset.ts:27 |
1356
- | `toPrmJsonl` | none | only this package's tests: tests/rl-exporters.test.ts:2 |
1357
1149
  | `toPrmRows` | planned | doc: docs/rollout.md |
1358
1150
  | `toSftJsonl` | production | this package: src/rl/dataset.ts:27 |
1359
- | `toSftRows` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
1151
+ | `toSftRowsWithLookups` | production | this package: src/rl/dataset.ts:27 |
1360
1152
  | `toTRLFormat` | production | blueprint-agent:scripts/experiments/lib/steering-dataset.ts |
1361
1153
  | `validateDatasetFormats` | planned | example: examples/publish-rl-dataset/build-dataset.ts:30 |
1362
- | `varianceBasedCurriculum` | production | this package: src/fuzz/explorer.ts:18 |
1363
- | `verificationReportToRunRecord` | none | — |
1364
- | `VERIFIED_FINDING_SCHEMA` | none | only this package's tests: src/rl/verified-findings-dataset.test.ts:5 |
1365
- | `verifiedFindingsToJsonl` | none | only this package's tests: src/rl/verified-findings-dataset.test.ts:5 |
1366
1154
 
1367
1155
  ### `./rollout`
1368
1156
 
1369
- 69 value exports — 45 production, 13 planned, 11 none.
1157
+ 46 value exports — 33 production, 13 planned, 0 none.
1370
1158
 
1371
1159
  | symbol | consumer | evidence |
1372
1160
  | --- | --- | --- |
1373
- | `addScrubCounts` | production | this package: src/rollout/release/hf-dataset.ts:34 |
1374
1161
  | `appendRolloutLines` | production | super-agent:evals/conversation-rollout.ts |
1375
1162
  | `assertGateReport` | production | this package: src/rollout/release/card.ts:12 |
1376
1163
  | `assertMinted` | production | blueprint-agent:scripts/experiments/lib/steering-dataset.ts |
1377
1164
  | `assertMintedLines` | planned | doc: docs/rollout.md |
1378
1165
  | `assertRolloutLine` | production | this package: src/rollout/interchange/harbor.ts:60 |
1379
- | `ATIF_SCHEMA_VERSION` | none | only this package's tests: src/rollout/interchange/harbor.test.ts:6 |
1380
1166
  | `buildDatasetCard` | production | this package: src/rollout/release/hf-dataset.ts:25 |
1381
1167
  | `buildHfDataset` | production | supervisor-lab:archive/bench/vertical-rollout-package.ts |
1382
- | `claudeProjectSlug` | none | only this package's tests: src/rollout/readers/claude-jsonl.test.ts:11 |
1383
1168
  | `DEFAULT_CLAUDE_PROJECTS_DIR` | planned | named in discovery-lab (bind not in the import graph) |
1384
1169
  | `DEFAULT_OPENCODE_DB` | planned | named in discovery-lab (bind not in the import graph) |
1385
1170
  | `defaultRolloutScrubber` | production | supervisor-lab:archive/bench/vertical-rollout-package.ts |
1386
- | `emptyScrubCounts` | production | this package: src/rollout/release/hf-dataset.ts:34 |
1387
1171
  | `findClaudeTranscripts` | planned | doc: docs/rollout.md |
1388
- | `findOpencodeSessionsByDirectory` | none | only this package's tests: src/rollout/readers/opencode-sqlite.test.ts:7 |
1389
- | `FORMAT_FILES` | production | this package: src/rollout/release/hf-dataset.ts:25 |
1390
- | `FORMAT_GATE_DISPOSITION` | production | this package: src/rollout/release/card.ts:12 |
1391
1172
  | `fromHarborTrajectory` | planned | doc: docs/rollout.md |
1392
1173
  | `GATE_CHECK_IDS` | production | this package: src/rollout/release/gate-report.ts:47 |
1393
1174
  | `GATE_CHECKS` | planned | doc: docs/rollout.md |
1394
1175
  | `GATE_POLICIES` | production | this package: src/rollout/release/gate-report.ts:47 |
1395
1176
  | `gatedEvidenceOf` | production | this package: src/rollout/schema.ts:50 |
1396
- | `gatedRolloutIds` | production | this package: src/rollout/release/hf-dataset.ts:26 |
1397
1177
  | `gateErrors` | production | this package: src/rollout/schema.ts:50 |
1398
1178
  | `gateGamedOutcome` | planned | named in discovery-lab (bind not in the import graph) |
1399
- | `HARBOR_IMPORT_GAP` | none | only this package's tests: src/rollout/interchange/harbor.test.ts:6 |
1400
1179
  | `isRealnessGated` | production | starter-foundry:src/lib/held-out-gate.ts |
1401
1180
  | `isRolloutLine` | production | this package: src/supervisor-run/rollout-nodes.ts:27 |
1402
1181
  | `isTrainableSplit` | production | this package: src/rollout/release/hf-dataset.ts:24 |
1403
- | `measureFormatGate` | production | this package: src/rollout/release/hf-dataset.ts:26 |
1404
1182
  | `mintRolloutRows` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
1405
- | `observedScore` | production | this package: src/rl/reward-hacking.ts:40 |
1406
1183
  | `observedSplitScore` | production | starter-foundry:src/lib/held-out-gate.ts |
1407
1184
  | `parseClaudeTranscript` | planned | doc: docs/rollout.md |
1408
- | `parseRolloutReleaseArgs` | none | only this package's tests: src/rollout/release/hf-dataset.test.ts:9 |
1409
- | `planPushCommand` | none | only this package's tests: src/rollout/release/hf-dataset.test.ts:9 |
1410
1185
  | `readClaudeTranscript` | production | blueprint-agent:scripts/experiments/lib/vb-climb-coder.ts |
1411
- | `readOpencodeSession` | none | only this package's tests: src/rollout/readers/opencode-sqlite.test.ts:7 |
1412
1186
  | `readOpencodeSessionMessages` | production | super-agent:evals/conversation-application.ts |
1413
- | `readRolloutJournal` | none | only this package's tests: src/rollout/ledger.test.ts:6 |
1414
1187
  | `readRolloutLedger` | production | this package: src/rollout/release/hf-dataset.ts:23 |
1415
1188
  | `relabelImportedSplit` | planned | doc: docs/rollout.md |
1416
- | `RELEASE_FORMATS` | production | this package: src/rollout/release/hf-dataset.ts:25 |
1417
- | `releaseRowRefs` | production | this package: src/rollout/release/hf-dataset.ts:26 |
1418
1189
  | `ROLLOUT_CAPTURES` | production | this package: src/rollout/interchange/harbor.ts:60 |
1419
1190
  | `ROLLOUT_ROLES` | production | this package: src/rollout/interchange/harbor.ts:60 |
1420
1191
  | `ROLLOUT_SCHEMA` | production | this package: src/rollout/interchange/harbor.ts:60 |
1421
1192
  | `ROLLOUT_SPLITS` | production | this package: src/rollout/interchange/harbor.ts:60 |
1422
- | `runRolloutReleaseCli` | production | this package: src/cli.ts:21 |
1423
- | `scoreOrigin` | production | this package: src/rollout/mint.ts:39 |
1424
1193
  | `scrubLines` | production | supervisor-lab:archive/bench/vertical-rollout-package.ts |
1425
- | `scrubRolloutLine` | none | only this package's tests: src/rollout/release/scrub.test.ts:4 |
1426
1194
  | `scrubText` | planned | named in tangle-tools (bind not in the import graph) |
1427
1195
  | `toHarborTrajectories` | planned | doc: docs/rollout.md |
1428
1196
  | `toHarborTrajectory` | planned | doc: docs/rollout.md |
1429
1197
  | `toJsonl` | production | supervisor-lab:archive/bench/vertical-rollout-package.ts |
1430
1198
  | `toRewardRows` | planned | doc: docs/rollout.md |
1431
- | `toRftItem` | none | only this package's tests: src/rollout/mint.test.ts:9 |
1432
1199
  | `toRftItems` | production | this package: src/rollout/release/hf-dataset.ts:22 |
1433
1200
  | `toSftRows` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
1434
- | `toVerifiersRolloutOutput` | none | only this package's tests: src/rollout/exporters.test.ts:2 |
1435
1201
  | `toVerifiersRolloutOutputs` | production | this package: src/rollout/release/hf-dataset.ts:22 |
1436
1202
  | `trainingReward` | production | supervisor-lab:archive/bench/vertical-gate-proof.ts |
1437
- | `trainingScore` | production | this package: src/eval-trace-store.ts:20 |
1438
- | `transcriptFromSession` | production | this package: src/supervisor-run/claude-code-reader.ts:67 |
1203
+ | `trainingScore` | production | this package: src/rl/corpus.ts:21 |
1439
1204
  | `unmintableReasons` | production | supervisor-lab:archive/bench/mint-audit.ts |
1440
1205
  | `validateRolloutLine` | production | this package: src/supervisor-run/integrity-tree.ts:1 |
1441
1206
  | `writeRolloutLedger` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
1442
1207
 
1443
1208
  ### `./search`
1444
1209
 
1445
- 32 value exports — 26 production, 6 planned, 0 none.
1210
+ 24 value exports — 19 production, 5 planned, 0 none.
1446
1211
 
1447
1212
  | symbol | consumer | evidence |
1448
1213
  | --- | --- | --- |
1449
- | `draftOnPlateau` | production | this package: scripts/search-sim.ts:162 |
1214
+ | `draftOnPlateau` | production | this package: scripts/search-sim/policy.ts:5 |
1450
1215
  | `editCredit` | production | this package: scripts/synthetic-search-ledger.ts:70 |
1451
1216
  | `editCreditText` | production | this package: src/search-command.ts:39 |
1452
- | `EXPANSION_OPERATORS` | production | this package: src/campaign/search-policy.ts:18 |
1453
- | `formatLandscape` | production | this package: src/search-command.ts:41 |
1454
- | `formatSkillManifold` | production | this package: src/search-command.ts:45 |
1455
1217
  | `front` | production | this package: src/search-command.ts:40 |
1456
- | `landscape` | production | this package: scripts/search-sim.ts:156 |
1457
- | `lineageEdits` | planned | doc: docs/search-ledger.md |
1458
- | `lineEditDistance` | production | this package: scripts/search-sim.ts:156 |
1218
+ | `landscape` | production | this package: scripts/search-sim/geometry.ts:1 |
1219
+ | `lineageEdits` | production | this package: src/search/lenses/landscape.ts:45 |
1459
1220
  | `META_SEARCH_SCORE_SOURCE` | production | this package: scripts/search-meta-sim.ts:52 |
1460
1221
  | `metaSearch` | production | this package: scripts/search-meta-sim.ts:52 |
1461
1222
  | `metaSearchScore` | production | this package: src/search/nested-search.ts:46 |
1462
1223
  | `MIN_OUTCOMES_FOR_WEIGHT` | planned | doc: docs/search-ledger.md |
1463
1224
  | `nestedSearchId` | planned | doc: docs/search-ledger.md |
1464
- | `nextUnitExtension` | production | this package: scripts/search-sim.ts:163 |
1465
- | `objectiveKey` | production | this package: scripts/search-meta-sim.ts:52 |
1466
- | `operatorYield` | production | this package: scripts/prove-operator-bandit.mts:24 |
1467
- | `rankingSplit` | production | this package: src/search/lenses/edit-credit.ts:53 |
1468
- | `renderMetaSearchText` | production | this package: scripts/search-meta-sim.ts:52 |
1225
+ | `nextUnitExtension` | production | this package: scripts/search-sim/policy.ts:6 |
1226
+ | `operatorYield` | production | this package: src/campaign/search-kernel-policy-view.ts:2 |
1227
+ | `renderMetaSearchText` | production | this package: scripts/search-meta-sim.ts:57 |
1469
1228
  | `runNestedSearch` | production | this package: scripts/search-meta-sim.ts:58 |
1470
- | `screenedNodes` | production | this package: src/search/lenses/landscape.ts:38 |
1471
1229
  | `searchConfigCodec` | planned | doc: docs/search-ledger.md |
1472
- | `searchPlateau` | production | this package: src/search/lenses/landscape.ts:49 |
1473
1230
  | `searchPolicyGenome` | planned | doc: docs/search-ledger.md |
1474
- | `skillCalibration` | production | this package: scripts/search-sim.ts:163 |
1475
- | `skillManifold` | production | this package: scripts/search-sim.ts:163 |
1476
- | `summarizeSamples` | production | this package: src/search/lenses/meta-search.ts:55 |
1231
+ | `skillCalibration` | production | this package: scripts/search-sim/geometry.ts:2 |
1232
+ | `skillManifold` | production | this package: scripts/search-sim/geometry.ts:2 |
1233
+ | `summarizeSamples` | production | this package: src/search/lenses/meta-search.ts:56 |
1477
1234
  | `surfaceTextEdits` | production | this package: src/search-command.ts:41 |
1478
1235
  | `taskMatrix` | production | this package: scripts/prove-task-matrix.mts:19 |
1479
- | `tree` | production | this package: src/search-command.ts:47 |
1236
+ | `tree` | production | this package: src/search-command.ts:48 |
1480
1237
  | `vectorEmbedding` | planned | doc: docs/search-ledger.md |
1481
1238
 
1482
1239
  ### `./storyboard`
1483
1240
 
1484
- 9 value exports — 5 production, 2 planned, 2 none.
1241
+ 7 value exports — 5 production, 2 planned, 0 none.
1485
1242
 
1486
1243
  | symbol | consumer | evidence |
1487
1244
  | --- | --- | --- |
1488
- | `codeEditFromSpan` | none | only this package's tests: src/storyboard/code-edit.test.ts:4 |
1489
- | `codeEditsForStoryboard` | none | only this package's tests: src/storyboard/code-edit.test.ts:4 |
1490
1245
  | `compileStoryboard` | production | run-capsule:src/index.ts |
1491
1246
  | `editAnimationText` | planned | named in run-capsule (bind not in the import graph) |
1492
1247
  | `extractCodeEdits` | production | run-capsule:src/index.ts |
@@ -1497,43 +1252,34 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1497
1252
 
1498
1253
  ### `./supervisor-run`
1499
1254
 
1500
- 29 value exports — 20 production, 4 planned, 5 none.
1255
+ 20 value exports — 17 production, 3 planned, 0 none.
1501
1256
 
1502
1257
  | symbol | consumer | evidence |
1503
1258
  | --- | --- | --- |
1504
1259
  | `analyzeSupervisorRun` | production | discovery-lab:pursuits/agent-authored-runtime-control-deepseek-20260812h/workspaces/runtime-control-deps/runtime-control.mjs |
1505
1260
  | `analyzeSupervisorRunIntegrity` | production | discovery-lab:pursuits/final-agent-authored-campaign-20260810/materialize-candidates.mjs |
1506
1261
  | `analyzeSupervisorRunSources` | production | discovery-lab:experiments/0005-run-visibility/probe.mjs |
1507
- | `claudeCodeSupervisorRunReader` | none | only this package's tests: src/supervisor-run/claude-code-reader.test.ts:6 |
1508
1262
  | `findSupervisorRunDirs` | production | traces:src/cli.ts |
1509
1263
  | `isRuntimeSupervisorRunDir` | production | discovery-lab:runner/observations-rollup.mjs |
1510
- | `isUnavailable` | production | this package: src/supervisor-run/analyze.ts:19 |
1511
- | `NO_SOURCE_LIMITS` | production | this package: src/supervisor-run/fixtures.ts:7 |
1264
+ | `isUnavailable` | production | this package: src/supervisor-run/analyze.ts:21 |
1512
1265
  | `NO_TERMINAL_RECORD` | planned | named in discovery-lab (bind not in the import graph) |
1513
- | `parsePatch` | planned | named in browser-agent-driver (bind not in the import graph) |
1266
+ | `parsePatch` | production | this package: src/supervisor-run/analyze.ts:10 |
1514
1267
  | `parseSupervisorTree` | production | discovery-lab:experiments/0005-run-visibility/probe.mjs |
1515
- | `readClaudeCodeSupervisorRun` | none | only this package's tests: src/supervisor-run/claude-code-reader.test.ts:6 |
1516
1268
  | `readRuntimeSupervisorRun` | production | discovery-lab:pursuits/final-agent-authored-campaign-20260810/materialize-candidates.mjs |
1517
- | `readTerminalRecord` | production | this package: src/supervisor-run/analyze.ts:18 |
1269
+ | `readTerminalRecord` | production | this package: src/supervisor-run/analyze.ts:20 |
1518
1270
  | `renderSupervisorRollupMarkdown` | production | traces:src/cli.ts |
1519
1271
  | `renderSupervisorRunHeadline` | production | discovery-lab:experiments/0005-run-visibility/probe.mjs |
1520
1272
  | `renderSupervisorRunMarkdown` | production | discovery-lab:experiments/0005-run-visibility/render-run.mjs |
1521
1273
  | `rollupSupervisorRuns` | production | traces:src/cli.ts |
1522
- | `runSupervisorRunCommand` | production | this package: src/cli.ts:23 |
1523
1274
  | `RUNTIME_FAILED_STATUS` | planned | named in discovery-lab (bind not in the import graph) |
1524
- | `runtimeSupervisorRunReader` | none | only this package's tests: src/supervisor-run/index.test.ts:2 |
1525
1275
  | `showMeasured` | production | discovery-lab:runner/readback.mjs |
1526
1276
  | `SUPERVISOR_RUN_INTEGRITY_SCHEMA` | production | this package: src/supervisor-run/integrity.ts:4 |
1527
- | `SUPERVISOR_RUN_ROLLUP_SCHEMA` | production | this package: src/supervisor-run/analyze.ts:19 |
1528
- | `SUPERVISOR_RUN_SCHEMA` | production | this package: src/supervisor-run/analyze.ts:19 |
1529
1277
  | `supervisorRunRolloutLines` | planned | doc: docs/rollout.md |
1530
- | `unavailable` | production | this package: src/supervisor-run/analyze.ts:19 |
1531
- | `writeSupervisorRunReport` | none | — |
1532
- | `writeSupervisorRunReportSafe` | none | — |
1278
+ | `unavailable` | production | this package: src/supervisor-run/analyze.ts:21 |
1533
1279
 
1534
1280
  ### `./systemone`
1535
1281
 
1536
- 20 value exports — 10 production, 10 planned, 0 none.
1282
+ 19 value exports — 10 production, 9 planned, 0 none.
1537
1283
 
1538
1284
  | symbol | consumer | evidence |
1539
1285
  | --- | --- | --- |
@@ -1544,13 +1290,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1544
1290
  | `createEvaluator` | production | blueprint-agent:scripts/experiments/app-grade/drive.ts |
1545
1291
  | `normalizedSystemOneScore` | planned | doc: docs/changes/systemone-provider-neutral.md |
1546
1292
  | `normalizeSystemOneResult` | production | tangle-router:lib/systemone.ts |
1547
- | `parseSystemOneQuestions` | production | this package: src/systemone.ts:14 |
1548
1293
  | `parseSystemOneRecordedRequest` | planned | example: examples/systemone-replay.ts:7 |
1549
1294
  | `parseSystemOneRequest` | production | discovery-lab:experiments/diu-campaign-v1/jev-review.mjs |
1550
1295
  | `parseSystemOneResult` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
1551
1296
  | `prepareSystemOneDomainMatch` | planned | doc: docs/systemone-integrations.md |
1552
1297
  | `prepareSystemOneReview` | production | this package: src/rl/claim-integrity.ts:47 |
1553
- | `systemOneAnalyst` | planned | example: examples/systemone-behavior-review.ts:3 |
1298
+ | `systemOneAnalyst` | production | this package: src/analyst/failure-modes.ts:20 |
1554
1299
  | `systemOneConfidence` | planned | doc: docs/changes/systemone-provider-neutral.md |
1555
1300
  | `systemOneEvaluator` | planned | doc: docs/changes/systemone-provider-neutral.md |
1556
1301
  | `systemOneJudge` | planned | example: examples/systemone-product-integrity.ts:4 |
@@ -1610,20 +1355,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1610
1355
 
1611
1356
  ### `./trace-repair`
1612
1357
 
1613
- 95 value exports — 51 production, 23 planned, 21 none.
1358
+ 42 value exports — 18 production, 24 planned, 0 none.
1614
1359
 
1615
1360
  | symbol | consumer | evidence |
1616
1361
  | --- | --- | --- |
1617
1362
  | `ADMISSION_CONFIG_DEFAULTS` | planned | doc: docs/trace-repair-admission.md |
1618
- | `ADMISSION_EXCLUSION_MEANING` | production | this package: src/trace-repair/admission-report.ts:11 |
1619
- | `ADMISSION_EXCLUSION_ORDER` | production | this package: src/trace-repair/admission-report.ts:11 |
1620
- | `ADMISSION_STRATA` | production | this package: src/trace-repair/admission-report.ts:11 |
1621
1363
  | `admissionArtifact` | planned | doc: docs/trace-repair-admission.md |
1622
- | `AdmissionDenominatorError` | production | this package: src/trace-repair/admission.ts:36 |
1623
- | `AdmissionIndependenceError` | none | only this package's tests: src/trace-repair/admission.test.ts:19 |
1624
- | `admitRow` | production | this package: scripts/tb-repair-milestone1.ts:41 |
1625
- | `admittedCount` | planned | named in agent-knowledge (bind not in the import graph) |
1626
- | `admittedRowIds` | none | only this package's tests: src/trace-repair/admission.test.ts:3 |
1364
+ | `admitRow` | production | this package: tests/trace-repair/fixtures.ts:11 |
1627
1365
  | `askRepairArm` | planned | doc: docs/trace-repair-analyst-arms.md |
1628
1366
  | `assertAnalystIndependent` | production | this package: src/trace-repair/admission.ts:36 |
1629
1367
  | `assertArmSymmetry` | production | this package: src/trace-repair/admission.ts:52 |
@@ -1631,92 +1369,45 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1631
1369
  | `assertControlCalibrated` | production | this package: src/trace-repair/admission-contract.ts:39 |
1632
1370
  | `assertDenominatorIntact` | planned | doc: docs/design/statistics-decisions.md |
1633
1371
  | `assertDeterministicOracle` | planned | doc: docs/design/statistics-decisions.md |
1634
- | `assertDspyRepairEngine` | none | only this package's tests: tests/trace-repair/arm-dspy.test.ts:19 |
1635
- | `BLINDED_FIELDS` | none | only this package's tests: tests/trace-repair/admission.test.ts:3 |
1636
1372
  | `blindTrajectory` | production | this package: src/trace-repair/analyst-arm.ts:41 |
1637
1373
  | `buildDenominatorChain` | production | this package: src/trace-repair/admission.ts:36 |
1638
- | `checkInterventionBudget` | production | this package: src/trace-repair/analyst-arm.ts:33 |
1639
- | `classifyActionPayload` | production | this package: scripts/tb-repair-milestone1.ts:41 |
1640
1374
  | `continuationPolicyDigest` | production | this package: src/trace-repair/admission.ts:52 |
1641
- | `ContinuationPolicyViolationError` | none | only this package's tests: src/trace-repair/continuation-policy.test.ts:11 |
1642
1375
  | `continuationSeed` | planned | doc: docs/trace-repair-continuation.md |
1643
- | `ContinuationSymmetryError` | none | only this package's tests: src/trace-repair/continuation-policy.test.ts:11 |
1644
- | `CONTROL_SCREENING_MODES` | production | this package: src/trace-repair/admission.ts:58 |
1645
- | `controlCanRescue` | none | only this package's tests: tests/trace-repair/control-policy.test.ts:4 |
1646
- | `countFunnel` | production | this package: src/trace-repair/delta-repair.ts:27 |
1647
1376
  | `createCompletionRepairArm` | planned | doc: docs/trace-repair-analyst-arms.md |
1648
1377
  | `createDockerContinuationEnvironment` | production | this package: scripts/tb-repair-freelunch.ts:32 |
1649
1378
  | `createDspyRepairArm` | planned | doc: docs/trace-repair-analyst-arms.md |
1650
- | `CREDIT_TERMS` | none | only this package's tests: tests/trace-repair/degenerate-strategies.test.ts:8 |
1651
- | `defineControlPolicy` | production | this package: scripts/tb-repair-milestone1.ts:41 |
1379
+ | `defineControlPolicy` | production | this package: tests/trace-repair/fixtures.ts:16 |
1652
1380
  | `definePinnedContinuationPolicy` | production | this package: scripts/tb-repair-freelunch.ts:32 |
1653
1381
  | `DEGENERATE_STRATEGIES` | planned | doc: docs/trace-repair-grader.md |
1654
- | `deltaRepair` | production | this package: scripts/tb-repair-milestone1.ts:41 |
1655
- | `dockerRunArgs` | none | only this package's tests: src/trace-repair/docker-environment.test.ts:3 |
1382
+ | `deltaRepair` | planned | doc: docs/trace-repair-grader.md |
1656
1383
  | `DSPY_REPAIR_SIGNATURE` | planned | doc: docs/trace-repair-analyst-arms.md |
1657
- | `DSPY_REPAIR_TASK_TOKEN` | none | only this package's tests: tests/trace-repair/arm-dspy.test.ts:19 |
1658
- | `dspyRepairInstructions` | none | only this package's tests: tests/trace-repair/arm-dspy.test.ts:19 |
1659
- | `gradeRepairRow` | production | this package: scripts/tb-repair-milestone1.ts:41 |
1660
- | `injectedTestOracle` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1661
- | `isRecordedTimeout` | production | this package: scripts/tb-repair-milestone1.ts:68 |
1662
- | `MINI_SWE_SYSTEM_MESSAGE` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1663
- | `NO_DECISIVE_FAILURE` | none | only this package's tests: tests/trace-repair/analyst-response.test.ts:2 |
1384
+ | `gradeRepairRow` | planned | doc: docs/trace-repair-analyst-arms.md |
1385
+ | `injectedTestOracle` | production | this package: scripts/tb-gated-stop/row.ts:1 |
1664
1386
  | `nodeProcessRunner` | production | this package: scripts/tb-repair-freelunch.ts:32 |
1665
- | `NondeterministicOracleError` | none | only this package's tests: tests/trace-repair/oracle-determinism.test.ts:4 |
1666
- | `noOpInjectionStep` | none | only this package's tests: src/trace-repair/admission.test.ts:3 |
1667
- | `normalizeActionForComparison` | production | this package: src/trace-repair/grade.ts:31 |
1668
- | `oracleDeterminism` | production | this package: scripts/tb-oracle-determinism.ts:17 |
1669
- | `OUTPUT_ELISION_THRESHOLD` | none | only this package's tests: src/trace-repair/mini-swe-scaffold.test.ts:2 |
1670
- | `parseAction` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1387
+ | `parseAction` | production | this package: scripts/tb-gated-stop/row.ts:1 |
1671
1388
  | `parseAnalystResponse` | planned | doc: docs/trace-repair-grader.md |
1672
1389
  | `parseTaskOracleRegistry` | production | this package: scripts/tb-corpus-rows.ts:28 |
1673
1390
  | `renderAdmissionReport` | planned | doc: docs/trace-repair-admission.md |
1674
1391
  | `renderDeltaRepairReport` | planned | doc: docs/trace-repair-grader.md |
1675
- | `renderFormatErrorObservation` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1676
- | `renderInstanceMessage` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1677
- | `renderObservation` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1678
- | `renderRepairTrajectory` | production | this package: src/trace-repair/arm-completion.ts:37 |
1679
- | `renderTimeoutObservation` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1680
- | `REPAIR_CONTRACT_LINES` | production | this package: src/trace-repair/arm-completion.ts:37 |
1681
- | `REPAIR_QUESTION` | production | this package: src/trace-repair/arm-completion.ts:37 |
1682
- | `REPAIR_REPAIR_CONTRACT_LINES` | production | this package: src/trace-repair/arm-completion.ts:37 |
1683
1392
  | `repairArmAsymmetries` | planned | doc: docs/trace-repair-analyst-arms.md |
1684
1393
  | `repairArmPromptSha256` | production | this package: src/trace-repair/analyst-arm.ts:42 |
1685
1394
  | `repairArmResponse` | planned | doc: docs/trace-repair-analyst-arms.md |
1686
- | `repairCredit` | production | this package: src/trace-repair/grade.ts:40 |
1687
- | `repairFinding` | production | this package: scripts/tb-repair-milestone1.ts:41 |
1688
1395
  | `repairQuestionSha256` | production | this package: src/trace-repair/analyst-arm.ts:42 |
1689
- | `repairTaskDefinition` | production | this package: src/trace-repair/arm-completion.ts:37 |
1690
- | `repairTaskPolicy` | production | this package: src/trace-repair/arm-dspy.ts:48 |
1691
- | `repairTrajectoryHeader` | production | this package: src/trace-repair/arm-completion.ts:37 |
1692
- | `resolveAdmissionConfig` | none | only this package's tests: src/trace-repair/admission.test.ts:3 |
1693
1396
  | `rolloutDigest` | planned | doc: docs/trace-repair-continuation.md |
1694
1397
  | `rolloutRecordedSteps` | planned | doc: docs/trace-repair-continuation.md |
1695
1398
  | `runAdmission` | planned | doc: docs/trace-repair-admission.md |
1696
1399
  | `runContinuation` | production | this package: scripts/tb-repair-freelunch.ts:32 |
1697
- | `SCAFFOLD_INTERVENTION_BUDGET` | production | this package: src/trace-repair/arm-completion.ts:27 |
1698
- | `scanShellAction` | none | only this package's tests: tests/trace-repair/action-budget.test.ts:2 |
1699
- | `stratumOf` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1700
- | `submissionOf` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1701
- | `SUBMIT_SENTINEL` | production | this package: src/trace-repair/action-budget.ts:19 |
1702
- | `SUITE_REWARD_UNIT` | none | only this package's tests: tests/trace-repair/oracle-determinism.test.ts:4 |
1703
- | `taskOracleRegistry` | none | only this package's tests: src/trace-repair/admission-report.test.ts:7 |
1704
- | `TB_REPAIR_ADMISSION_CRITERIA` | production | this package: scripts/tb-repair-milestone1.ts:41 |
1705
- | `TestOracleError` | none | only this package's tests: tests/trace-repair/test-oracle.test.ts:4 |
1706
- | `testSuiteDigest` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
1707
1400
  | `TestSuiteTamperedError` | planned | doc: docs/trace-repair-grader.md |
1708
- | `toRecordedSteps` | none | only this package's tests: src/trace-repair/continuation-policy.test.ts:25 |
1709
1401
  | `totalCost` | planned | doc: examples/adapt-a-text-optimizer/README.md |
1710
1402
  | `totalUsage` | planned | named in agent-builder (bind not in the import graph) |
1711
1403
  | `UncalibratedControlError` | planned | doc: docs/trace-repair-admission.md |
1712
1404
 
1713
1405
  ### `./traces`
1714
1406
 
1715
- 122 value exports — 101 production, 8 planned, 13 none.
1407
+ 97 value exports — 88 production, 6 planned, 3 none.
1716
1408
 
1717
1409
  | symbol | consumer | evidence |
1718
1410
  | --- | --- | --- |
1719
- | `aggregateLlm` | none | only this package's tests: src/trace/query.test.ts:3 |
1720
1411
  | `analyzeTraces` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
1721
1412
  | `applyLlmSpanOtlpAttributes` | production | traces:src/adapters/claude.ts |
1722
1413
  | `applyToolSpanOtlpAttributes` | production | braid:src/adapters/analysis/trace-store.ts |
@@ -1729,23 +1420,18 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1729
1420
  | `buildTraceInsightContext` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html-sections.ts |
1730
1421
  | `buildTraceInsightPrompt` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/brief.ts |
1731
1422
  | `captureFetchToRawSink` | production | creative-agent:eval/canonical-runner.ts |
1732
- | `classifyKey` | planned | doc: docs/redaction.md |
1423
+ | `classifyKey` | production | this package: src/trace/redact.ts:38 |
1733
1424
  | `combineVerdicts` | production | run-capsule:src/run-to-video.ts |
1734
1425
  | `contextInputTokens` | none | only this package's tests: tests/trace-otel.test.ts:3 |
1735
1426
  | `convertTraceStoresToOtlp` | planned | consumer tests: legal-agent:tests/eval/lib/traces-to-otlp.ts |
1736
1427
  | `createBoundedTraceAnalysisStore` | production | braid:src/adapters/analysis/trace-store.ts |
1737
1428
  | `DEFAULT_TRACE_ANALYST_BUDGETS` | production | agent-builder:src/lib/.server/eval/stores/d1-trace-analysis-store-adapter.ts |
1738
- | `defaultProviderRedactor` | production | this package: src/llm-client.ts:54 |
1739
- | `defaultTraceInsightPanel` | none | only this package's tests: src/trace-analyst/insights.test.ts:3 |
1740
1429
  | `describeTraceInsightScope` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html.ts |
1741
1430
  | `detectCredential` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
1742
- | `detectPersonalData` | production | this package: scripts/redaction-corpus.ts:9 |
1743
1431
  | `domainEvidencePattern` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/session-loader.ts |
1744
1432
  | `emptyRedactionReport` | production | agent-runtime:src/candidate-execution/protected-redaction.ts |
1745
1433
  | `exportRunAsOtlp` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
1746
- | `extractOtlpAttributes` | production | this package: src/trace-analyst/store-otlp.ts:40 |
1747
- | `extractUsage` | production | this package: src/contract/intake/code-agent-session.ts:13 |
1748
- | `extractUsageFromResponse` | none | only this package's tests: src/trace/extract-usage.test.ts:2 |
1434
+ | `extractUsage` | production | this package: src/contract/intake/code-agent-session-metrics.ts:3 |
1749
1435
  | `extractUsageFromSse` | production | this package: src/trace/capture-fetch.ts:8 |
1750
1436
  | `FAILURE_CLASSES` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
1751
1437
  | `FileSystemRawProviderSink` | production | agent-builder:scripts/eval.ts |
@@ -1754,7 +1440,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1754
1440
  | `firstStringAttr` | production | this package: src/trace-analyst/otlp-to-run-records.ts:60 |
1755
1441
  | `flattenOtlpExportToNdjson` | production | creative-agent:eval/trace-analyst-runner.ts |
1756
1442
  | `groupBy` | production | this package: src/tool-use-metrics.ts:10 |
1757
- | `hasCapturedToolArgs` | production | this package: src/pipelines/failure-cluster.ts:10 |
1758
1443
  | `inferDomainKeywords` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/suite-projection.ts |
1759
1444
  | `InMemoryRawProviderSink` | production | agent-builder:src/lib/.server/eval/loops/canonical-campaign.ts |
1760
1445
  | `InMemoryTraceStore` | production | agent-builder:src/lib/.server/eval/loops/canonical-campaign.ts |
@@ -1785,148 +1470,72 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
1785
1470
  | `NoopRawProviderSink` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
1786
1471
  | `normalizeKey` | planned | named in agent-app (bind not in the import graph) |
1787
1472
  | `OPENINFERENCE_SPAN_KIND` | production | braid:src/adapters/analysis/trace-event-projection.ts |
1788
- | `OTEL_AGENT_EVAL_SCOPE` | none | — |
1789
1473
  | `OtlpFileTraceStore` | production | agent-builder:scripts/run-canonical-analyst-loop.ts |
1790
1474
  | `otlpRowsToRunRecords` | production | traces:src/execution.ts |
1791
1475
  | `otlpTextToTraceAnalysisStore` | production | braid:src/adapters/analysis/trace-store.ts |
1792
1476
  | `otlpToRunRecords` | production | traces:src/execution.ts |
1793
- | `otlpToTraceRunRecords` | none | only this package's tests: src/trace-analyst/otlp-to-run-records.test.ts:3 |
1794
1477
  | `OUTPUT_VALUE` | production | agent-runtime:src/runtime/supervise-surface.ts |
1795
- | `planTraceInsightQuestions` | none | only this package's tests: src/trace-analyst/insights.test.ts:3 |
1796
1478
  | `projectOtlpFlatLine` | production | this package: src/trace-analyst/otlp-to-run-records.ts:60 |
1797
- | `providerFromBaseUrl` | production | this package: src/llm-client.ts:54 |
1798
1479
  | `redact` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
1799
1480
  | `redactForShare` | production | chatgpt-plugins:plugins/agents/inspection/src/index.ts |
1800
- | `REDACTION_PROFILES` | production | this package: scripts/redaction-corpus.ts:9 |
1801
1481
  | `REDACTION_VERSION` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
1802
1482
  | `redactText` | production | agent-dev-container:products/intelligence/api/src/lib/search-ingest.ts |
1803
- | `RUN_COST_ATTR_KEYS` | production | this package: src/trace/execution-measurements.ts:3 |
1804
- | `RUN_METRICS` | none | — |
1805
1483
  | `runFailureClass` | production | starter-foundry:registry/layers/agent-eval/redteam/files/src/eval/redteam/runner.ts |
1806
1484
  | `RunIntegrityError` | production | creative-agent:eval/canonical-runner.ts |
1807
- | `runMetricExtractor` | production | this package: src/meta-eval/calibration.ts:10 |
1808
1485
  | `runsForScenario` | production | ph0ny:products/builder/api/src/eval/gate.ts |
1809
1486
  | `scoreTraceInsightReadiness` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html-sections.ts |
1810
1487
  | `shareAllowed` | production | agent-dev-container:products/intelligence/api/src/lib/search-blobs.ts |
1811
1488
  | `SPAN_KIND_ATTR_KEYS` | production | traces:src/run-span-tree.ts |
1812
1489
  | `SpanNotFoundError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
1813
1490
  | `spanRecordsToTraceAnalysisStore` | production | agent-dev-container:products/intelligence/api/src/lib/pg-trace-analyst-store.ts |
1814
- | `stringField` | planned | named in agent-dev-container (bind not in the import graph) |
1815
- | `throwIfRunIncomplete` | none | only this package's tests: tests/run-integrity.test.ts:3 |
1816
1491
  | `tokenizeDomainWords` | planned | consumer tests: blueprint-agent:scripts/experiments/__tests__/analyze-vb-run.test.ts |
1817
- | `TOOL_ARGS_CAPTURED` | production | this package: src/trace/otlp-attributes.ts:4 |
1818
- | `TOOL_LATENCY_MS` | production | this package: src/trace/otlp-attributes.ts:4 |
1819
1492
  | `TOOL_NAME` | production | supervisor-lab:archive/bench/analyst/rewrite-views.mts |
1820
1493
  | `TOOL_NAME_ATTR_KEYS` | production | this package: src/trace-analyst/behavioral-metrics.ts:13 |
1821
1494
  | `toolSpans` | production | this package: src/pipelines/failure-cluster.ts:10 |
1822
1495
  | `toolSpansToTraceAnalysisStore` | production | agent-runtime:src/runtime/supervise/run-traces.ts |
1823
- | `ToolTraceMissingError` | none | only this package's tests: src/trace-analyst/store-tool-spans.test.ts:10 |
1496
+ | `ToolTraceMissingError` | none | — |
1824
1497
  | `TRACE_ANALYSIS_LIMITS` | production | this package: src/analyst/benchmark-evidence-validation.ts:1 |
1825
- | `TRACE_ANALYST_ACTOR_DESCRIPTION` | production | this package: src/trace-analyst/analyst.ts:11 |
1826
- | `TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION` | production | this package: src/trace-analyst/analyst.ts:11 |
1827
1498
  | `TRACE_ANALYST_TOOL_NAMESPACE` | none | — |
1828
- | `TRACE_ANALYST_TRUNCATION_MARKER_PREFIX` | none | — |
1829
- | `TRACE_SCHEMA_VERSION` | none | — |
1830
1499
  | `TraceAnalysisLimitError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
1831
1500
  | `TraceAnalysisStoreContractError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
1832
1501
  | `TraceAnalysisValidationError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
1833
1502
  | `traceAnalystOnRunComplete` | planned | named in creative-agent (bind not in the import graph) |
1834
1503
  | `TraceEmitter` | production | agent-builder:src/lib/.server/runtime/trace-runtime.ts |
1835
- | `TraceFileMalformedError` | production | this package: src/trace-analyst/store-otlp.ts:31 |
1836
- | `TraceFileMissingError` | production | this package: src/trace-analyst/store-otlp.ts:31 |
1837
- | `TraceFileTooLargeError` | production | this package: src/trace-analyst/store-otlp.ts:31 |
1504
+ | `TraceFileMissingError` | production | this package: src/trace-analyst/store-otlp.ts:30 |
1505
+ | `TraceFileTooLargeError` | production | this package: src/trace-analyst/store-otlp.ts:30 |
1838
1506
  | `TraceNotFoundError` | production | agent-dev-container:products/intelligence/api/src/lib/pg-trace-analyst-store.ts |
1839
- | `traceSpanKindToOpenInferenceKind` | production | this package: src/trace/otel.ts:12 |
1840
1507
  | `UNTRUSTED_TRACE_TEXT` | production | traces:src/mcp.ts |
1841
1508
 
1842
1509
  ### `./trajectory-replay`
1843
1510
 
1844
- 47 value exports — 34 production, 4 planned, 9 none.
1511
+ 11 value exports — 8 production, 3 planned, 0 none.
1845
1512
 
1846
1513
  | symbol | consumer | evidence |
1847
1514
  | --- | --- | --- |
1848
- | `assertReplayableTrajectory` | none | only this package's tests: tests/trajectory-replay/steps.test.ts:7 |
1849
- | `buildFixPrompt` | production | this package: src/trajectory-replay/fix-loop.ts:17 |
1850
- | `buildRetryFixPrompt` | production | this package: src/trajectory-replay/fix-loop.ts:17 |
1851
1515
  | `classifyObservation` | production | this package: scripts/tb-corpus-rows.ts:29 |
1852
- | `classifyPrefixStep` | none | only this package's tests: tests/trajectory-replay/verify.test.ts:14 |
1853
1516
  | `classifyVerdict` | planned | named in agent-builder (bind not in the import graph) |
1854
- | `clipText` | production | this package: src/trajectory-replay/fix-loop.ts:17 |
1855
- | `countScriptCommands` | production | this package: src/trajectory-replay/fix-loop.ts:17 |
1856
1517
  | `decodeRecordedTurns` | production | this package: scripts/tb-corpus-rows.ts:29 |
1857
- | `derivedImageTag` | none | only this package's tests: tests/trajectory-replay/batch.test.ts:13 |
1858
- | `deriveFailureSignature` | production | this package: src/trace-repair/grade.ts:25 |
1859
1518
  | `dockerImagePreparer` | production | this package: src/trajectory-replay/batch.ts:43 |
1860
- | `enumerateReplayableCases` | production | traces:src/replay.ts |
1861
- | `extractFixCommand` | production | this package: src/trajectory-replay/fix-loop.ts:17 |
1862
1519
  | `finalRecordedOutcome` | production | this package: scripts/tb-corpus-rows.ts:29 |
1863
- | `findingReplayStep` | none | only this package's tests: tests/trajectory-replay/findings.test.ts:5 |
1864
- | `findingTrajectoryId` | none | only this package's tests: tests/trajectory-replay/findings.test.ts:5 |
1865
- | `FORMAT_ERROR_OBSERVATION_PREFIX` | production | this package: src/trace-repair/mini-swe-scaffold.ts:17 |
1866
- | `generateFixCommand` | production | this package: src/trajectory-replay/batch.ts:41 |
1867
- | `goldIncorrectSteps` | planned | named in traces (bind not in the import graph) |
1868
- | `ingestRecordedTrajectory` | production | this package: src/trajectory-replay/batch.ts:44 |
1869
- | `isElidedField` | none | only this package's tests: tests/trajectory-replay/steps.test.ts:7 |
1870
- | `isRecordedTimeout` | production | this package: scripts/tb-repair-milestone1.ts:68 |
1871
- | `isSubmitAction` | production | this package: src/trajectory-replay/findings.ts:39 |
1872
- | `isSubmitOnlyAction` | production | this package: src/trajectory-replay/corpus.ts:19 |
1873
- | `parseCorpusFlag` | production | traces:src/cli.ts |
1874
- | `parseIncorrectStepsSubject` | production | this package: src/trajectory-replay/findings.ts:41 |
1875
- | `parseObservationOutput` | production | this package: src/trajectory-replay/corpus.ts:19 |
1876
- | `parseRecordedReturncode` | production | this package: scripts/tb-gated-stop-ab.ts:77 |
1877
1520
  | `PREFIX_DIVERGENCE_TOLERANCE_PCT` | production | this package: src/trajectory-replay/batch.ts:44 |
1878
- | `readFindingsFile` | production | traces:src/replay.ts |
1879
- | `renderVerifiedFindingsSection` | production | traces:src/cli.ts |
1880
1521
  | `replayVerify` | production | traces:src/replay.ts |
1881
1522
  | `replayVerifyFinding` | planned | doc: docs/trajectory-replay.md |
1882
- | `resolveCaseResources` | production | this package: src/trajectory-replay/findings.ts:36 |
1883
- | `resolveFindingInvocation` | none | only this package's tests: tests/trajectory-replay/wire.test.ts:6 |
1884
- | `resolveFindingReplayability` | none | only this package's tests: tests/trajectory-replay/findings.test.ts:5 |
1885
- | `runFixLoop` | production | this package: src/trajectory-replay/batch.ts:42 |
1886
1523
  | `runReplayBatch` | production | traces:src/replay.ts |
1887
- | `SandboxCounterfactualRunner` | production | this package: src/trajectory-replay/batch.ts:44 |
1888
1524
  | `seededSample` | planned | named in discovery-lab (bind not in the import graph) |
1889
- | `SUBMIT_ACTION_SIGNATURE` | production | this package: src/trace-repair/mini-swe-scaffold.ts:17 |
1890
- | `summarizePrefixReplay` | none | only this package's tests: tests/trajectory-replay/verify.test.ts:14 |
1891
- | `TIMEOUT_OBSERVATION_MARKER` | production | this package: src/trace-repair/mini-swe-scaffold.ts:17 |
1892
- | `unreadableExitCount` | production | this package: scripts/tb-corpus-rows.ts:29 |
1893
1525
  | `verifyFindings` | production | traces:src/replay.ts |
1894
- | `wrapActionForExec` | production | this package: src/trace-repair/grade.ts:24 |
1895
1526
 
1896
1527
  ### `./wire`
1897
1528
 
1898
- 31 value exports — 25 production, 3 planned, 3 none.
1529
+ 9 value exports — 6 production, 3 planned, 0 none.
1899
1530
 
1900
1531
  | symbol | consumer | evidence |
1901
1532
  | --- | --- | --- |
1902
- | `buildOpenApi` | production | this package: src/cli.ts:25 |
1903
1533
  | `createApp` | planned | doc: docs/wire-protocol.md |
1904
1534
  | `dispatchRpc` | planned | doc: docs/wire-protocol.md |
1905
1535
  | `ErrorResponseSchema` | production | this package: src/wire/openapi.ts:15 |
1906
- | `FeedbackIngestResponseSchema` | production | this package: src/wire/openapi.ts:15 |
1907
1536
  | `FeedbackTrajectorySchema` | production | insurance-agent:src/routes/api.feedback.ts |
1908
- | `getBuiltinRubric` | production | this package: src/wire/handlers.ts:21 |
1909
- | `handleFeedbackIngest` | production | this package: src/wire/server.ts:20 |
1910
- | `handleJudge` | production | this package: src/wire/rpc.ts:15 |
1911
- | `handleListRubrics` | production | this package: src/wire/rpc.ts:15 |
1912
- | `handleTracesIngest` | production | this package: src/wire/server.ts:20 |
1913
- | `handleVersion` | production | this package: src/cli.ts:24 |
1914
- | `hashRubric` | production | this package: src/wire/handlers.ts:22 |
1915
- | `HealthResponseSchema` | production | this package: src/wire/openapi.ts:15 |
1916
- | `JudgeRequestSchema` | production | this package: src/wire/openapi.ts:15 |
1917
- | `JudgeResultSchema` | production | this package: src/wire/openapi.ts:15 |
1918
- | `listBuiltinRubrics` | production | this package: src/wire/handlers.ts:21 |
1919
- | `ListRubricsResponseSchema` | production | this package: src/wire/openapi.ts:15 |
1920
- | `RUBRIC_VERSION_SCHEME` | none | — |
1921
- | `RubricDimensionSchema` | none | only this package's tests: tests/wire/schemas.test.ts:12 |
1922
- | `RubricSchema` | none | only this package's tests: tests/wire/schemas.test.ts:12 |
1923
- | `runRpcBatch` | production | this package: src/cli.ts:26 |
1924
- | `runRpcOnce` | production | this package: src/cli.ts:26 |
1925
1537
  | `startServer` | production | creative-agent:eval/ingestion-server.ts |
1926
1538
  | `startServerAsync` | production | this package: src/cli.ts:27 |
1927
1539
  | `TraceEventSchema` | planned | named in insurance-agent (bind not in the import graph) |
1928
- | `TracesIngestRequestSchema` | production | this package: src/wire/openapi.ts:15 |
1929
- | `TracesIngestResponseSchema` | production | this package: src/wire/openapi.ts:15 |
1930
- | `VersionResponseSchema` | production | this package: src/wire/openapi.ts:15 |
1931
1540
  | `WIRE_VERSION` | production | this package: src/wire/handlers.ts:22 |
1932
1541
  | `WireError` | production | this package: src/wire/rpc.ts:15 |