@tangle-network/agent-eval 0.218.1 → 0.220.0
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.
- package/CHANGELOG.md +25 -0
- package/dist/adapters/http.d.ts +3 -3
- package/dist/adapters/http.d.ts.map +1 -1
- package/dist/adapters/http.js +1 -0
- package/dist/adapters/http.js.map +1 -1
- package/dist/{agent-profile-DTt8uGP9.d.ts → agent-profile-D01Io2Xw.d.ts} +4 -4
- package/dist/{agent-profile-DTt8uGP9.d.ts.map → agent-profile-D01Io2Xw.d.ts.map} +1 -1
- package/dist/analyst/index.d.ts +13 -13
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +8 -8
- package/dist/analyst/index.js.map +1 -1
- package/dist/{analyze-runs-DjlZOVXx.d.ts → analyze-runs-BWAHBDAw.d.ts} +4 -4
- package/dist/{analyze-runs-DjlZOVXx.d.ts.map → analyze-runs-BWAHBDAw.d.ts.map} +1 -1
- package/dist/{benchmark-command-BupdHRyf.js → benchmark-command-BzmMTnvC.js} +10 -10
- package/dist/{benchmark-command-BupdHRyf.js.map → benchmark-command-BzmMTnvC.js.map} +1 -1
- package/dist/benchmarks/index.d.ts +5 -5
- package/dist/benchmarks/index.js +3 -3
- package/dist/benchmarks/index.js.map +1 -1
- package/dist/campaign/index.d.ts +8 -8
- package/dist/campaign/index.js +8 -8
- package/dist/{campaign-CGvUTnmc.js → campaign-BVPC6ODQ.js} +149 -10
- package/dist/campaign-BVPC6ODQ.js.map +1 -0
- package/dist/campaign-evidence-DunzcJGv.js.map +1 -1
- package/dist/{chat-client-B2pXlPdx.js → chat-client-CMQ8_h4J.js} +2 -2
- package/dist/{chat-client-B2pXlPdx.js.map → chat-client-CMQ8_h4J.js.map} +1 -1
- package/dist/{chat-json-call-Dm9c-b41.js → chat-json-call-BrZKn0L3.js} +2 -2
- package/dist/{chat-json-call-Dm9c-b41.js.map → chat-json-call-BrZKn0L3.js.map} +1 -1
- package/dist/cli.js +8 -8
- package/dist/{completion-verifier-DbLVf3i8.js → completion-verifier-Cigap8CG.js} +4 -4
- package/dist/{completion-verifier-DbLVf3i8.js.map → completion-verifier-Cigap8CG.js.map} +1 -1
- package/dist/contract/index.d.ts +11 -11
- package/dist/contract/index.js +7 -7
- package/dist/{cost-ledger-D0352Z4d.js → cost-ledger-BGZB6yY2.js} +75 -2
- package/dist/cost-ledger-BGZB6yY2.js.map +1 -0
- package/dist/{cost-ledger-Jk62OBfF.d.ts → cost-ledger-C1W3ICmP.d.ts} +26 -2
- package/dist/cost-ledger-C1W3ICmP.d.ts.map +1 -0
- package/dist/{default-registry-BJ-Pq6yL.js → default-registry-BrKmT01n.js} +3 -3
- package/dist/{default-registry-BJ-Pq6yL.js.map → default-registry-BrKmT01n.js.map} +1 -1
- package/dist/{default-registry-DXgLmoDI.d.ts → default-registry-Cwg_QN3d.d.ts} +6 -6
- package/dist/{default-registry-DXgLmoDI.d.ts.map → default-registry-Cwg_QN3d.d.ts.map} +1 -1
- package/dist/{define-agent-eval-BlH10zEw.d.ts → define-agent-eval-C2nFhHPu.d.ts} +8 -8
- package/dist/{define-agent-eval-BlH10zEw.d.ts.map → define-agent-eval-C2nFhHPu.d.ts.map} +1 -1
- package/dist/{define-agent-eval-BGdFKlrc.js → define-agent-eval-UQY3VbJ2.js} +4 -4
- package/dist/{define-agent-eval-BGdFKlrc.js.map → define-agent-eval-UQY3VbJ2.js.map} +1 -1
- package/dist/diagnosis/index.d.ts +2 -2
- package/dist/{dspy-rlm-engine-CSMwudLO.js → dspy-rlm-engine-Bn_Mt_LW.js} +3 -3
- package/dist/{dspy-rlm-engine-CSMwudLO.js.map → dspy-rlm-engine-Bn_Mt_LW.js.map} +1 -1
- package/dist/{engine-BvZ0R-36.d.ts → engine-BpGGw6cd.d.ts} +3 -3
- package/dist/{engine-BvZ0R-36.d.ts.map → engine-BpGGw6cd.d.ts.map} +1 -1
- package/dist/{evaluation-BOZ38vOH.d.ts → evaluation-CBdQt_kr.d.ts} +4 -4
- package/dist/{evaluation-BOZ38vOH.d.ts.map → evaluation-CBdQt_kr.d.ts.map} +1 -1
- package/dist/evaluation.d.ts +1 -1
- package/dist/evaluation.js +1 -1
- package/dist/{exact-types-CflbJ9f3.d.ts → exact-types-BYFmYq44.d.ts} +2 -2
- package/dist/{exact-types-CflbJ9f3.d.ts.map → exact-types-BYFmYq44.d.ts.map} +1 -1
- package/dist/experiment/index.d.ts +24 -1
- package/dist/experiment/index.d.ts.map +1 -1
- package/dist/experiment/index.js.map +1 -1
- package/dist/{external-optimizer-process-C3Wm7Vhn.js → external-optimizer-process-wOLfzsCC.js} +2 -2
- package/dist/{external-optimizer-process-C3Wm7Vhn.js.map → external-optimizer-process-wOLfzsCC.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-B5gdLRZv.js → external-optimizer-subprocess-D670Oxf2.js} +3 -3
- package/dist/{external-optimizer-subprocess-B5gdLRZv.js.map → external-optimizer-subprocess-D670Oxf2.js.map} +1 -1
- package/dist/{feedback-trajectory-BWmhRBGu.d.ts → feedback-trajectory-DhB9WzYg.d.ts} +3 -3
- package/dist/{feedback-trajectory-BWmhRBGu.d.ts.map → feedback-trajectory-DhB9WzYg.d.ts.map} +1 -1
- package/dist/{findings-store-BtTzPL0d.js → findings-store-CvNo712L.js} +5 -5
- package/dist/{findings-store-BtTzPL0d.js.map → findings-store-CvNo712L.js.map} +1 -1
- package/dist/fuzz.d.ts +1 -1
- package/dist/fuzz.js +1 -1
- package/dist/hosted/index.js +1 -1
- package/dist/{index-CX-GAUpw.d.ts → index-CHxwfW5g.d.ts} +2 -2
- package/dist/{index-CX-GAUpw.d.ts.map → index-CHxwfW5g.d.ts.map} +1 -1
- package/dist/{index-BLGqZ81N.d.ts → index-CVFStrQD.d.ts} +8 -8
- package/dist/{index-BLGqZ81N.d.ts.map → index-CVFStrQD.d.ts.map} +1 -1
- package/dist/{index-CiRwLv2R.d.ts → index-D7fmC-1K.d.ts} +3 -4
- package/dist/index-D7fmC-1K.d.ts.map +1 -0
- package/dist/{index-DbMOXYnP.d.ts → index-DAXfpVf7.d.ts} +10 -10
- package/dist/{index-DbMOXYnP.d.ts.map → index-DAXfpVf7.d.ts.map} +1 -1
- package/dist/{index-B16FNdW5.d.ts → index-Q6DvdcwI.d.ts} +37 -11
- package/dist/index-Q6DvdcwI.d.ts.map +1 -0
- package/dist/index.d.ts +26 -26
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +14 -14
- package/dist/index.js.map +1 -1
- package/dist/{integrity-_qgZLA5p.d.ts → integrity-CCwvezWS.d.ts} +2 -2
- package/dist/{integrity-_qgZLA5p.d.ts.map → integrity-CCwvezWS.d.ts.map} +1 -1
- package/dist/judge-gate-Co5tuh57.js.map +1 -1
- package/dist/{judge-gate-DsL0yFcb.d.ts → judge-gate-Dc_mXQsL.d.ts} +2 -2
- package/dist/judge-gate-Dc_mXQsL.d.ts.map +1 -0
- package/dist/{kind-factory-Gy4fXixd.js → kind-factory-BhxbtUsQ.js} +2 -2
- package/dist/{kind-factory-Gy4fXixd.js.map → kind-factory-BhxbtUsQ.js.map} +1 -1
- package/dist/{llm-client-_Y6ic-tf.js → llm-client-DXuOTseU.js} +2 -2
- package/dist/{llm-client-_Y6ic-tf.js.map → llm-client-DXuOTseU.js.map} +1 -1
- package/dist/{llm-judge-Djxh-Uhs.js → llm-judge-Cc8vDJh_.js} +9 -8
- package/dist/llm-judge-Cc8vDJh_.js.map +1 -0
- package/dist/matrix/index.d.ts +2 -2
- package/dist/{matrix-CCSBna4q.d.ts → matrix-Cf-AGxGh.d.ts} +4 -4
- package/dist/{matrix-CCSBna4q.d.ts.map → matrix-Cf-AGxGh.d.ts.map} +1 -1
- package/dist/meta-eval/index.d.ts +2 -2
- package/dist/{mint-BRZXuwRi.d.ts → mint-CkzpVPdz.d.ts} +3 -3
- package/dist/{mint-BRZXuwRi.d.ts.map → mint-CkzpVPdz.d.ts.map} +1 -1
- package/dist/multishot/golden/index.d.ts +1 -1
- package/dist/multishot/index.d.ts +2 -2
- package/dist/multishot/index.js.map +1 -1
- package/dist/openapi.json +1 -1
- package/dist/{pareto-CTv8vozZ.js → pareto-BiBnQXAE.js} +304 -210
- package/dist/pareto-BiBnQXAE.js.map +1 -0
- package/dist/pipelines/index.d.ts.map +1 -1
- package/dist/pipelines/index.js.map +1 -1
- package/dist/{prime-protocol-BWG2DQIk.d.ts → prime-protocol-CckHBxGu.d.ts} +3 -3
- package/dist/{prime-protocol-BWG2DQIk.d.ts.map → prime-protocol-CckHBxGu.d.ts.map} +1 -1
- package/dist/{promotion-gate-CxEHRsZW.d.ts → promotion-gate-CkVZHagC.d.ts} +3 -3
- package/dist/{promotion-gate-CxEHRsZW.d.ts.map → promotion-gate-CkVZHagC.d.ts.map} +1 -1
- package/dist/{proposal-findings-n-5WBbEx.js → proposal-findings-E1aSC_cU.js} +2 -2
- package/dist/{proposal-findings-n-5WBbEx.js.map → proposal-findings-E1aSC_cU.js.map} +1 -1
- package/dist/{registry-ssNoHzwD.d.ts → registry-B_yG-1jh.d.ts} +5 -5
- package/dist/{registry-ssNoHzwD.d.ts.map → registry-B_yG-1jh.d.ts.map} +1 -1
- package/dist/render-Cs34y0iX.js.map +1 -1
- package/dist/reporting.d.ts +3 -3
- package/dist/{researcher-GU1tV4dn.d.ts → researcher-H0p44OYC.d.ts} +5 -5
- package/dist/{researcher-GU1tV4dn.d.ts.map → researcher-H0p44OYC.d.ts.map} +1 -1
- package/dist/{reward-DrZ71vnf.d.ts → reward-BeUgVVC_.d.ts} +2 -2
- package/dist/{reward-DrZ71vnf.d.ts.map → reward-BeUgVVC_.d.ts.map} +1 -1
- package/dist/{reward-hacking-E52wq86n.d.ts → reward-hacking-WTxUbtbb.d.ts} +2 -2
- package/dist/{reward-hacking-E52wq86n.d.ts.map → reward-hacking-WTxUbtbb.d.ts.map} +1 -1
- package/dist/rl.d.ts +9 -8
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +35 -1
- package/dist/rl.js.map +1 -1
- package/dist/rollout/index.d.ts +3 -3
- package/dist/rollout-Dd1ucT_M.js.map +1 -1
- package/dist/{rubric-predictive-validity-DiwT8PbL.d.ts → rubric-predictive-validity-noY7uE03.d.ts} +2 -2
- package/dist/{rubric-predictive-validity-DiwT8PbL.d.ts.map → rubric-predictive-validity-noY7uE03.d.ts.map} +1 -1
- package/dist/{run-record-CaxbLq6Y.d.ts → run-record-C3awiXPf.d.ts} +2 -2
- package/dist/{run-record-CaxbLq6Y.d.ts.map → run-record-C3awiXPf.d.ts.map} +1 -1
- package/dist/schema-CvhfLjtZ.js.map +1 -1
- package/dist/search/index.d.ts +2 -2
- package/dist/search/index.js +2 -2
- package/dist/{search-kernel-p9JB3SmL.d.ts → search-kernel-Dloxd6gs.d.ts} +4 -4
- package/dist/{search-kernel-p9JB3SmL.d.ts.map → search-kernel-Dloxd6gs.d.ts.map} +1 -1
- package/dist/{search-ledger-ClpN4I3e.js → search-ledger-CZRqtFbW.js} +249 -242
- package/dist/search-ledger-CZRqtFbW.js.map +1 -0
- package/dist/{search-shipper-Bg2HW3Uv.js → search-shipper-Dn3NLsuH.js} +2 -2
- package/dist/{search-shipper-Bg2HW3Uv.js.map → search-shipper-Dn3NLsuH.js.map} +1 -1
- package/dist/{search-summary-CrBuvVnf.js → search-summary-D4bwYnAE.js} +2 -2
- package/dist/{search-summary-CrBuvVnf.js.map → search-summary-D4bwYnAE.js.map} +1 -1
- package/dist/{server-C6M0qR8h.js → server-8TS8XCvg.js} +3 -3
- package/dist/{server-C6M0qR8h.js.map → server-8TS8XCvg.js.map} +1 -1
- package/dist/{skillopt-optimization-method-5dlex7MJ.js → skillopt-optimization-method-DLKqdhcR.js} +106 -61
- package/dist/skillopt-optimization-method-DLKqdhcR.js.map +1 -0
- package/dist/{statistical-heldout-BHfLZHrm.d.ts → statistical-heldout-3z3I-kJN.d.ts} +3 -3
- package/dist/{statistical-heldout-BHfLZHrm.d.ts.map → statistical-heldout-3z3I-kJN.d.ts.map} +1 -1
- package/dist/{store-otlp-BteDAbHK.js → store-otlp-dyWE3wAG.js} +2 -2
- package/dist/{store-otlp-BteDAbHK.js.map → store-otlp-dyWE3wAG.js.map} +1 -1
- package/dist/{store-tool-spans-D5l_OfTJ.js → store-tool-spans-DIUgZbzu.js} +3 -3
- package/dist/{store-tool-spans-D5l_OfTJ.js.map → store-tool-spans-DIUgZbzu.js.map} +1 -1
- package/dist/{store-tool-spans-DZS0HWVf.d.ts → store-tool-spans-DPwXHQkH.d.ts} +7 -7
- package/dist/{store-tool-spans-DZS0HWVf.d.ts.map → store-tool-spans-DPwXHQkH.d.ts.map} +1 -1
- package/dist/{summary-report-CkbRcSuu.d.ts → summary-report-C8V49Jt3.d.ts} +3 -3
- package/dist/{summary-report-CkbRcSuu.d.ts.map → summary-report-C8V49Jt3.d.ts.map} +1 -1
- package/dist/{systemone-BMzDJb1i.d.ts → systemone-DVA7t76V.d.ts} +6 -6
- package/dist/{systemone-BMzDJb1i.d.ts.map → systemone-DVA7t76V.d.ts.map} +1 -1
- package/dist/{systemone-review-CwE6JGIp.d.ts → systemone-review-CUBMuTLi.d.ts} +2 -2
- package/dist/{systemone-review-CwE6JGIp.d.ts.map → systemone-review-CUBMuTLi.d.ts.map} +1 -1
- package/dist/systemone.d.ts +3 -3
- package/dist/{tool-groups-DyNz2JZ_.d.ts → tool-groups-LISbBWCg.d.ts} +3 -3
- package/dist/tool-groups-LISbBWCg.d.ts.map +1 -0
- package/dist/{trace-questions-xxwgsuMi.d.ts → trace-questions-C42fYEE4.d.ts} +4 -4
- package/dist/{trace-questions-xxwgsuMi.d.ts.map → trace-questions-C42fYEE4.d.ts.map} +1 -1
- package/dist/trace-repair/index.d.ts +3 -3
- package/dist/traces.d.ts +6 -6
- package/dist/traces.js +3 -3
- package/dist/trajectory-replay/index.js +24 -3
- package/dist/trajectory-replay/index.js.map +1 -1
- package/dist/{tree-B5e1uAeL.js → tree-DSqwJpL9.js} +3 -3
- package/dist/{tree-B5e1uAeL.js.map → tree-DSqwJpL9.js.map} +1 -1
- package/dist/{types-CW8ewATZ.d.ts → types-8yQzNm8u.d.ts} +4 -4
- package/dist/{types-CW8ewATZ.d.ts.map → types-8yQzNm8u.d.ts.map} +1 -1
- package/dist/{types-DtkO1G9L.d.ts → types-CHfn1zg5.d.ts} +69 -71
- package/dist/types-CHfn1zg5.d.ts.map +1 -0
- package/dist/{types-BKCzzmit.d.ts → types-D8GXK9Z5.d.ts} +3 -3
- package/dist/{types-BKCzzmit.d.ts.map → types-D8GXK9Z5.d.ts.map} +1 -1
- package/dist/{types-D-mgRzlh.d.ts → types-eMhdacVp.d.ts} +2 -2
- package/dist/{types-D-mgRzlh.d.ts.map → types-eMhdacVp.d.ts.map} +1 -1
- package/dist/wire/index.d.ts +3 -3
- package/dist/wire/index.js +1 -1
- package/docs/campaign-proposers.md +16 -0
- package/docs/concepts.md +31 -0
- package/docs/public-api.md +76 -75
- package/package.json +2 -5
- package/dist/campaign-CGvUTnmc.js.map +0 -1
- package/dist/cost-ledger-D0352Z4d.js.map +0 -1
- package/dist/cost-ledger-Jk62OBfF.d.ts.map +0 -1
- package/dist/index-B16FNdW5.d.ts.map +0 -1
- package/dist/index-CiRwLv2R.d.ts.map +0 -1
- package/dist/judge-gate-DsL0yFcb.d.ts.map +0 -1
- package/dist/llm-judge-Djxh-Uhs.js.map +0 -1
- package/dist/pareto-CTv8vozZ.js.map +0 -1
- package/dist/search-ledger-ClpN4I3e.js.map +0 -1
- package/dist/skillopt-optimization-method-5dlex7MJ.js.map +0 -1
- package/dist/tool-groups-DyNz2JZ_.d.ts.map +0 -1
- 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
|
-
|
|
1029
|
-
|
|
1030
|
-
const { headline
|
|
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
|
}
|