@tangle-network/agent-eval 0.218.1 → 0.219.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (198) hide show
  1. package/CHANGELOG.md +21 -0
  2. package/dist/adapters/http.d.ts +3 -3
  3. package/dist/adapters/http.d.ts.map +1 -1
  4. package/dist/adapters/http.js +1 -0
  5. package/dist/adapters/http.js.map +1 -1
  6. package/dist/{agent-profile-DTt8uGP9.d.ts → agent-profile-D01Io2Xw.d.ts} +4 -4
  7. package/dist/{agent-profile-DTt8uGP9.d.ts.map → agent-profile-D01Io2Xw.d.ts.map} +1 -1
  8. package/dist/analyst/index.d.ts +13 -13
  9. package/dist/analyst/index.d.ts.map +1 -1
  10. package/dist/analyst/index.js +8 -8
  11. package/dist/analyst/index.js.map +1 -1
  12. package/dist/{analyze-runs-DjlZOVXx.d.ts → analyze-runs-BWAHBDAw.d.ts} +4 -4
  13. package/dist/{analyze-runs-DjlZOVXx.d.ts.map → analyze-runs-BWAHBDAw.d.ts.map} +1 -1
  14. package/dist/{benchmark-command-BupdHRyf.js → benchmark-command-BzmMTnvC.js} +10 -10
  15. package/dist/{benchmark-command-BupdHRyf.js.map → benchmark-command-BzmMTnvC.js.map} +1 -1
  16. package/dist/benchmarks/index.d.ts +5 -5
  17. package/dist/benchmarks/index.js +3 -3
  18. package/dist/benchmarks/index.js.map +1 -1
  19. package/dist/campaign/index.d.ts +8 -8
  20. package/dist/campaign/index.js +8 -8
  21. package/dist/{campaign-CGvUTnmc.js → campaign-BVPC6ODQ.js} +149 -10
  22. package/dist/campaign-BVPC6ODQ.js.map +1 -0
  23. package/dist/campaign-evidence-DunzcJGv.js.map +1 -1
  24. package/dist/{chat-client-B2pXlPdx.js → chat-client-CMQ8_h4J.js} +2 -2
  25. package/dist/{chat-client-B2pXlPdx.js.map → chat-client-CMQ8_h4J.js.map} +1 -1
  26. package/dist/{chat-json-call-Dm9c-b41.js → chat-json-call-BrZKn0L3.js} +2 -2
  27. package/dist/{chat-json-call-Dm9c-b41.js.map → chat-json-call-BrZKn0L3.js.map} +1 -1
  28. package/dist/cli.js +8 -8
  29. package/dist/{completion-verifier-DbLVf3i8.js → completion-verifier-Cigap8CG.js} +4 -4
  30. package/dist/{completion-verifier-DbLVf3i8.js.map → completion-verifier-Cigap8CG.js.map} +1 -1
  31. package/dist/contract/index.d.ts +11 -11
  32. package/dist/contract/index.js +7 -7
  33. package/dist/{cost-ledger-D0352Z4d.js → cost-ledger-BGZB6yY2.js} +75 -2
  34. package/dist/cost-ledger-BGZB6yY2.js.map +1 -0
  35. package/dist/{cost-ledger-Jk62OBfF.d.ts → cost-ledger-C1W3ICmP.d.ts} +26 -2
  36. package/dist/cost-ledger-C1W3ICmP.d.ts.map +1 -0
  37. package/dist/{default-registry-BJ-Pq6yL.js → default-registry-BrKmT01n.js} +3 -3
  38. package/dist/{default-registry-BJ-Pq6yL.js.map → default-registry-BrKmT01n.js.map} +1 -1
  39. package/dist/{default-registry-DXgLmoDI.d.ts → default-registry-Cwg_QN3d.d.ts} +6 -6
  40. package/dist/{default-registry-DXgLmoDI.d.ts.map → default-registry-Cwg_QN3d.d.ts.map} +1 -1
  41. package/dist/{define-agent-eval-BlH10zEw.d.ts → define-agent-eval-C2nFhHPu.d.ts} +8 -8
  42. package/dist/{define-agent-eval-BlH10zEw.d.ts.map → define-agent-eval-C2nFhHPu.d.ts.map} +1 -1
  43. package/dist/{define-agent-eval-BGdFKlrc.js → define-agent-eval-UQY3VbJ2.js} +4 -4
  44. package/dist/{define-agent-eval-BGdFKlrc.js.map → define-agent-eval-UQY3VbJ2.js.map} +1 -1
  45. package/dist/diagnosis/index.d.ts +2 -2
  46. package/dist/{dspy-rlm-engine-CSMwudLO.js → dspy-rlm-engine-Bn_Mt_LW.js} +3 -3
  47. package/dist/{dspy-rlm-engine-CSMwudLO.js.map → dspy-rlm-engine-Bn_Mt_LW.js.map} +1 -1
  48. package/dist/{engine-BvZ0R-36.d.ts → engine-BpGGw6cd.d.ts} +3 -3
  49. package/dist/{engine-BvZ0R-36.d.ts.map → engine-BpGGw6cd.d.ts.map} +1 -1
  50. package/dist/{evaluation-BOZ38vOH.d.ts → evaluation-CBdQt_kr.d.ts} +4 -4
  51. package/dist/{evaluation-BOZ38vOH.d.ts.map → evaluation-CBdQt_kr.d.ts.map} +1 -1
  52. package/dist/evaluation.d.ts +1 -1
  53. package/dist/evaluation.js +1 -1
  54. package/dist/{exact-types-CflbJ9f3.d.ts → exact-types-BYFmYq44.d.ts} +2 -2
  55. package/dist/{exact-types-CflbJ9f3.d.ts.map → exact-types-BYFmYq44.d.ts.map} +1 -1
  56. package/dist/experiment/index.d.ts +24 -1
  57. package/dist/experiment/index.d.ts.map +1 -1
  58. package/dist/experiment/index.js.map +1 -1
  59. package/dist/{external-optimizer-process-C3Wm7Vhn.js → external-optimizer-process-wOLfzsCC.js} +2 -2
  60. package/dist/{external-optimizer-process-C3Wm7Vhn.js.map → external-optimizer-process-wOLfzsCC.js.map} +1 -1
  61. package/dist/{external-optimizer-subprocess-B5gdLRZv.js → external-optimizer-subprocess-D670Oxf2.js} +3 -3
  62. package/dist/{external-optimizer-subprocess-B5gdLRZv.js.map → external-optimizer-subprocess-D670Oxf2.js.map} +1 -1
  63. package/dist/{feedback-trajectory-BWmhRBGu.d.ts → feedback-trajectory-DhB9WzYg.d.ts} +3 -3
  64. package/dist/{feedback-trajectory-BWmhRBGu.d.ts.map → feedback-trajectory-DhB9WzYg.d.ts.map} +1 -1
  65. package/dist/{findings-store-BtTzPL0d.js → findings-store-CvNo712L.js} +5 -5
  66. package/dist/{findings-store-BtTzPL0d.js.map → findings-store-CvNo712L.js.map} +1 -1
  67. package/dist/fuzz.d.ts +1 -1
  68. package/dist/fuzz.js +1 -1
  69. package/dist/hosted/index.js +1 -1
  70. package/dist/{index-CX-GAUpw.d.ts → index-CHxwfW5g.d.ts} +2 -2
  71. package/dist/{index-CX-GAUpw.d.ts.map → index-CHxwfW5g.d.ts.map} +1 -1
  72. package/dist/{index-BLGqZ81N.d.ts → index-CVFStrQD.d.ts} +8 -8
  73. package/dist/{index-BLGqZ81N.d.ts.map → index-CVFStrQD.d.ts.map} +1 -1
  74. package/dist/{index-CiRwLv2R.d.ts → index-D7fmC-1K.d.ts} +3 -4
  75. package/dist/index-D7fmC-1K.d.ts.map +1 -0
  76. package/dist/{index-DbMOXYnP.d.ts → index-DAXfpVf7.d.ts} +10 -10
  77. package/dist/{index-DbMOXYnP.d.ts.map → index-DAXfpVf7.d.ts.map} +1 -1
  78. package/dist/{index-B16FNdW5.d.ts → index-Q6DvdcwI.d.ts} +37 -11
  79. package/dist/index-Q6DvdcwI.d.ts.map +1 -0
  80. package/dist/index.d.ts +26 -26
  81. package/dist/index.d.ts.map +1 -1
  82. package/dist/index.js +14 -14
  83. package/dist/index.js.map +1 -1
  84. package/dist/{integrity-_qgZLA5p.d.ts → integrity-CCwvezWS.d.ts} +2 -2
  85. package/dist/{integrity-_qgZLA5p.d.ts.map → integrity-CCwvezWS.d.ts.map} +1 -1
  86. package/dist/judge-gate-Co5tuh57.js.map +1 -1
  87. package/dist/{judge-gate-DsL0yFcb.d.ts → judge-gate-Dc_mXQsL.d.ts} +2 -2
  88. package/dist/judge-gate-Dc_mXQsL.d.ts.map +1 -0
  89. package/dist/{kind-factory-Gy4fXixd.js → kind-factory-BhxbtUsQ.js} +2 -2
  90. package/dist/{kind-factory-Gy4fXixd.js.map → kind-factory-BhxbtUsQ.js.map} +1 -1
  91. package/dist/{llm-client-_Y6ic-tf.js → llm-client-DXuOTseU.js} +2 -2
  92. package/dist/{llm-client-_Y6ic-tf.js.map → llm-client-DXuOTseU.js.map} +1 -1
  93. package/dist/{llm-judge-Djxh-Uhs.js → llm-judge-Cc8vDJh_.js} +9 -8
  94. package/dist/llm-judge-Cc8vDJh_.js.map +1 -0
  95. package/dist/matrix/index.d.ts +2 -2
  96. package/dist/{matrix-CCSBna4q.d.ts → matrix-Cf-AGxGh.d.ts} +4 -4
  97. package/dist/{matrix-CCSBna4q.d.ts.map → matrix-Cf-AGxGh.d.ts.map} +1 -1
  98. package/dist/meta-eval/index.d.ts +2 -2
  99. package/dist/{mint-BRZXuwRi.d.ts → mint-CkzpVPdz.d.ts} +3 -3
  100. package/dist/{mint-BRZXuwRi.d.ts.map → mint-CkzpVPdz.d.ts.map} +1 -1
  101. package/dist/multishot/golden/index.d.ts +1 -1
  102. package/dist/multishot/index.d.ts +2 -2
  103. package/dist/multishot/index.js.map +1 -1
  104. package/dist/openapi.json +1 -1
  105. package/dist/{pareto-CTv8vozZ.js → pareto-BiBnQXAE.js} +304 -210
  106. package/dist/pareto-BiBnQXAE.js.map +1 -0
  107. package/dist/pipelines/index.d.ts.map +1 -1
  108. package/dist/pipelines/index.js.map +1 -1
  109. package/dist/{prime-protocol-BWG2DQIk.d.ts → prime-protocol-CckHBxGu.d.ts} +3 -3
  110. package/dist/{prime-protocol-BWG2DQIk.d.ts.map → prime-protocol-CckHBxGu.d.ts.map} +1 -1
  111. package/dist/{promotion-gate-CxEHRsZW.d.ts → promotion-gate-CkVZHagC.d.ts} +3 -3
  112. package/dist/{promotion-gate-CxEHRsZW.d.ts.map → promotion-gate-CkVZHagC.d.ts.map} +1 -1
  113. package/dist/{proposal-findings-n-5WBbEx.js → proposal-findings-E1aSC_cU.js} +2 -2
  114. package/dist/{proposal-findings-n-5WBbEx.js.map → proposal-findings-E1aSC_cU.js.map} +1 -1
  115. package/dist/{registry-ssNoHzwD.d.ts → registry-B_yG-1jh.d.ts} +5 -5
  116. package/dist/{registry-ssNoHzwD.d.ts.map → registry-B_yG-1jh.d.ts.map} +1 -1
  117. package/dist/render-Cs34y0iX.js.map +1 -1
  118. package/dist/reporting.d.ts +3 -3
  119. package/dist/{researcher-GU1tV4dn.d.ts → researcher-H0p44OYC.d.ts} +5 -5
  120. package/dist/{researcher-GU1tV4dn.d.ts.map → researcher-H0p44OYC.d.ts.map} +1 -1
  121. package/dist/{reward-DrZ71vnf.d.ts → reward-BeUgVVC_.d.ts} +2 -2
  122. package/dist/{reward-DrZ71vnf.d.ts.map → reward-BeUgVVC_.d.ts.map} +1 -1
  123. package/dist/{reward-hacking-E52wq86n.d.ts → reward-hacking-WTxUbtbb.d.ts} +2 -2
  124. package/dist/{reward-hacking-E52wq86n.d.ts.map → reward-hacking-WTxUbtbb.d.ts.map} +1 -1
  125. package/dist/rl.d.ts +8 -8
  126. package/dist/rollout/index.d.ts +3 -3
  127. package/dist/rollout-Dd1ucT_M.js.map +1 -1
  128. package/dist/{rubric-predictive-validity-DiwT8PbL.d.ts → rubric-predictive-validity-noY7uE03.d.ts} +2 -2
  129. package/dist/{rubric-predictive-validity-DiwT8PbL.d.ts.map → rubric-predictive-validity-noY7uE03.d.ts.map} +1 -1
  130. package/dist/{run-record-CaxbLq6Y.d.ts → run-record-C3awiXPf.d.ts} +2 -2
  131. package/dist/{run-record-CaxbLq6Y.d.ts.map → run-record-C3awiXPf.d.ts.map} +1 -1
  132. package/dist/schema-CvhfLjtZ.js.map +1 -1
  133. package/dist/search/index.d.ts +2 -2
  134. package/dist/search/index.js +2 -2
  135. package/dist/{search-kernel-p9JB3SmL.d.ts → search-kernel-Dloxd6gs.d.ts} +4 -4
  136. package/dist/{search-kernel-p9JB3SmL.d.ts.map → search-kernel-Dloxd6gs.d.ts.map} +1 -1
  137. package/dist/{search-ledger-ClpN4I3e.js → search-ledger-CZRqtFbW.js} +249 -242
  138. package/dist/search-ledger-CZRqtFbW.js.map +1 -0
  139. package/dist/{search-shipper-Bg2HW3Uv.js → search-shipper-Dn3NLsuH.js} +2 -2
  140. package/dist/{search-shipper-Bg2HW3Uv.js.map → search-shipper-Dn3NLsuH.js.map} +1 -1
  141. package/dist/{search-summary-CrBuvVnf.js → search-summary-D4bwYnAE.js} +2 -2
  142. package/dist/{search-summary-CrBuvVnf.js.map → search-summary-D4bwYnAE.js.map} +1 -1
  143. package/dist/{server-C6M0qR8h.js → server-8TS8XCvg.js} +3 -3
  144. package/dist/{server-C6M0qR8h.js.map → server-8TS8XCvg.js.map} +1 -1
  145. package/dist/{skillopt-optimization-method-5dlex7MJ.js → skillopt-optimization-method-DLKqdhcR.js} +106 -61
  146. package/dist/skillopt-optimization-method-DLKqdhcR.js.map +1 -0
  147. package/dist/{statistical-heldout-BHfLZHrm.d.ts → statistical-heldout-3z3I-kJN.d.ts} +3 -3
  148. package/dist/{statistical-heldout-BHfLZHrm.d.ts.map → statistical-heldout-3z3I-kJN.d.ts.map} +1 -1
  149. package/dist/{store-otlp-BteDAbHK.js → store-otlp-dyWE3wAG.js} +2 -2
  150. package/dist/{store-otlp-BteDAbHK.js.map → store-otlp-dyWE3wAG.js.map} +1 -1
  151. package/dist/{store-tool-spans-D5l_OfTJ.js → store-tool-spans-DIUgZbzu.js} +3 -3
  152. package/dist/{store-tool-spans-D5l_OfTJ.js.map → store-tool-spans-DIUgZbzu.js.map} +1 -1
  153. package/dist/{store-tool-spans-DZS0HWVf.d.ts → store-tool-spans-DPwXHQkH.d.ts} +7 -7
  154. package/dist/{store-tool-spans-DZS0HWVf.d.ts.map → store-tool-spans-DPwXHQkH.d.ts.map} +1 -1
  155. package/dist/{summary-report-CkbRcSuu.d.ts → summary-report-C8V49Jt3.d.ts} +3 -3
  156. package/dist/{summary-report-CkbRcSuu.d.ts.map → summary-report-C8V49Jt3.d.ts.map} +1 -1
  157. package/dist/{systemone-BMzDJb1i.d.ts → systemone-DVA7t76V.d.ts} +6 -6
  158. package/dist/{systemone-BMzDJb1i.d.ts.map → systemone-DVA7t76V.d.ts.map} +1 -1
  159. package/dist/{systemone-review-CwE6JGIp.d.ts → systemone-review-CUBMuTLi.d.ts} +2 -2
  160. package/dist/{systemone-review-CwE6JGIp.d.ts.map → systemone-review-CUBMuTLi.d.ts.map} +1 -1
  161. package/dist/systemone.d.ts +3 -3
  162. package/dist/{tool-groups-DyNz2JZ_.d.ts → tool-groups-LISbBWCg.d.ts} +3 -3
  163. package/dist/tool-groups-LISbBWCg.d.ts.map +1 -0
  164. package/dist/{trace-questions-xxwgsuMi.d.ts → trace-questions-C42fYEE4.d.ts} +4 -4
  165. package/dist/{trace-questions-xxwgsuMi.d.ts.map → trace-questions-C42fYEE4.d.ts.map} +1 -1
  166. package/dist/trace-repair/index.d.ts +3 -3
  167. package/dist/traces.d.ts +6 -6
  168. package/dist/traces.js +3 -3
  169. package/dist/trajectory-replay/index.js +24 -3
  170. package/dist/trajectory-replay/index.js.map +1 -1
  171. package/dist/{tree-B5e1uAeL.js → tree-DSqwJpL9.js} +3 -3
  172. package/dist/{tree-B5e1uAeL.js.map → tree-DSqwJpL9.js.map} +1 -1
  173. package/dist/{types-CW8ewATZ.d.ts → types-8yQzNm8u.d.ts} +4 -4
  174. package/dist/{types-CW8ewATZ.d.ts.map → types-8yQzNm8u.d.ts.map} +1 -1
  175. package/dist/{types-DtkO1G9L.d.ts → types-CHfn1zg5.d.ts} +69 -71
  176. package/dist/types-CHfn1zg5.d.ts.map +1 -0
  177. package/dist/{types-BKCzzmit.d.ts → types-D8GXK9Z5.d.ts} +3 -3
  178. package/dist/{types-BKCzzmit.d.ts.map → types-D8GXK9Z5.d.ts.map} +1 -1
  179. package/dist/{types-D-mgRzlh.d.ts → types-eMhdacVp.d.ts} +2 -2
  180. package/dist/{types-D-mgRzlh.d.ts.map → types-eMhdacVp.d.ts.map} +1 -1
  181. package/dist/wire/index.d.ts +3 -3
  182. package/dist/wire/index.js +1 -1
  183. package/docs/campaign-proposers.md +16 -0
  184. package/docs/concepts.md +31 -0
  185. package/docs/public-api.md +76 -75
  186. package/package.json +2 -5
  187. package/dist/campaign-CGvUTnmc.js.map +0 -1
  188. package/dist/cost-ledger-D0352Z4d.js.map +0 -1
  189. package/dist/cost-ledger-Jk62OBfF.d.ts.map +0 -1
  190. package/dist/index-B16FNdW5.d.ts.map +0 -1
  191. package/dist/index-CiRwLv2R.d.ts.map +0 -1
  192. package/dist/judge-gate-DsL0yFcb.d.ts.map +0 -1
  193. package/dist/llm-judge-Djxh-Uhs.js.map +0 -1
  194. package/dist/pareto-CTv8vozZ.js.map +0 -1
  195. package/dist/search-ledger-ClpN4I3e.js.map +0 -1
  196. package/dist/skillopt-optimization-method-5dlex7MJ.js.map +0 -1
  197. package/dist/tool-groups-DyNz2JZ_.d.ts.map +0 -1
  198. package/dist/types-DtkO1G9L.d.ts.map +0 -1
@@ -1025,9 +1025,9 @@ async function runFixPhase(run, selected, rows, verdicts) {
1025
1025
  function pct(value) {
1026
1026
  return value === null ? "—" : `${(value * 100).toFixed(1)}%`;
1027
1027
  }
1028
- function renderBatchReport(report) {
1029
- const lines = [];
1030
- const { headline, totals } = report;
1028
+ /** The title and the headline rates, prefix divergence and fix-flip numbers. */
1029
+ function pushHeadline(report, lines) {
1030
+ const { headline } = report;
1031
1031
  lines.push("# Replay-verify batch report");
1032
1032
  lines.push("");
1033
1033
  lines.push(`Generated ${report.generatedAt}.`);
@@ -1045,6 +1045,10 @@ function renderBatchReport(report) {
1045
1045
  const parts = Object.entries(headline.flipsByAttempt).sort((a, b) => Number(a[0]) - Number(b[0])).map(([attempt, count]) => `attempt ${attempt}: ${count}`);
1046
1046
  lines.push(`- Flips by attempt: ${parts.join(", ")}.`);
1047
1047
  }
1048
+ }
1049
+ /** How many label entries were replayable, executed and excluded, and why. */
1050
+ function pushEnumeration(report, lines) {
1051
+ const { totals } = report;
1048
1052
  lines.push("");
1049
1053
  lines.push("## Enumeration");
1050
1054
  lines.push("");
@@ -1062,6 +1066,9 @@ function renderBatchReport(report) {
1062
1066
  lines.push("| --- | --- | --- |");
1063
1067
  for (const [corpus, stats] of submitEntries.sort((a, b) => a[0].localeCompare(b[0]))) lines.push(`| ${corpus} | ${stats.submitOnlyCases} | ${stats.goldsSkippedWithinReplayable} |`);
1064
1068
  }
1069
+ }
1070
+ /** The images that could not be pulled or built. */
1071
+ function pushPullFailures(report, lines) {
1065
1072
  if (report.pullFailures.length > 0) {
1066
1073
  lines.push("");
1067
1074
  lines.push("## Image pull/build failures");
@@ -1070,6 +1077,9 @@ function renderBatchReport(report) {
1070
1077
  lines.push("| --- | --- | --- | --- |");
1071
1078
  for (const failure of report.pullFailures) lines.push(`| ${failure.corpus} | ${failure.trajId} | \`${failure.image}\` | ${failure.error.replaceAll("|", "\\|")} |`);
1072
1079
  }
1080
+ }
1081
+ /** One row per replayed case. */
1082
+ function pushCaseResults(report, lines) {
1073
1083
  lines.push("");
1074
1084
  lines.push("## Per-case results");
1075
1085
  lines.push("");
@@ -1100,12 +1110,23 @@ function renderBatchReport(report) {
1100
1110
  (row.wallMs / 1e3).toFixed(1)
1101
1111
  ].join(" | "));
1102
1112
  }
1113
+ }
1114
+ /** The model, calls and tokens spent generating fixes. */
1115
+ function pushLlmUsage(report, lines) {
1103
1116
  if (report.llm) {
1104
1117
  lines.push("");
1105
1118
  lines.push("## LLM fix generation");
1106
1119
  lines.push("");
1107
1120
  lines.push(`Model ${report.llm.model}: ${report.llm.calls} calls (${report.llm.failures} failed), ${report.llm.promptTokens} prompt + ${report.llm.completionTokens} completion tokens.`);
1108
1121
  }
1122
+ }
1123
+ function renderBatchReport(report) {
1124
+ const lines = [];
1125
+ pushHeadline(report, lines);
1126
+ pushEnumeration(report, lines);
1127
+ pushPullFailures(report, lines);
1128
+ pushCaseResults(report, lines);
1129
+ pushLlmUsage(report, lines);
1109
1130
  lines.push("");
1110
1131
  return lines.join("\n");
1111
1132
  }