@tangle-network/agent-eval 0.203.2 → 0.205.0
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 +8 -0
- package/dist/analyst/index.d.ts +1 -1
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +5 -5
- package/dist/{analyze-runs-BrIibNd0.js → analyze-runs-d5dcMlxi.js} +9 -9
- package/dist/{analyze-runs-BrIibNd0.js.map → analyze-runs-d5dcMlxi.js.map} +1 -1
- package/dist/baseline-Dm8966du.js +259 -0
- package/dist/baseline-Dm8966du.js.map +1 -0
- package/dist/{benchmark-command-6OBcB0sG.js → benchmark-command-BQhi_BVO.js} +9 -6
- package/dist/benchmark-command-BQhi_BVO.js.map +1 -0
- package/dist/benchmarks/index.js +2 -2
- package/dist/builder-eval/index.js +1 -1
- package/dist/campaign/index.js +9 -9
- package/dist/{campaign-DYhg4SjN.js → campaign-0lmkAMpE.js} +11 -11
- package/dist/{campaign-DYhg4SjN.js.map → campaign-0lmkAMpE.js.map} +1 -1
- package/dist/{campaign-evidence-Dt_rWPk2.js → campaign-evidence-C__cUpCt.js} +2 -2
- package/dist/{campaign-evidence-Dt_rWPk2.js.map → campaign-evidence-C__cUpCt.js.map} +1 -1
- package/dist/cli.js +5 -5
- package/dist/contract/index.js +10 -10
- package/dist/{default-registry-wInsQWlQ.js → default-registry-BthquIoC.js} +2 -2
- package/dist/{default-registry-wInsQWlQ.js.map → default-registry-BthquIoC.js.map} +1 -1
- package/dist/{define-agent-eval-B25Cc3ki.js → define-agent-eval-CeYrXpl7.js} +4 -4
- package/dist/{define-agent-eval-B25Cc3ki.js.map → define-agent-eval-CeYrXpl7.js.map} +1 -1
- package/dist/{descriptive-D9LUFk1-.js → descriptive-CnU8Yq29.js} +2 -2
- package/dist/{descriptive-D9LUFk1-.js.map → descriptive-CnU8Yq29.js.map} +1 -1
- package/dist/diagnosis/index.js +1 -1
- package/dist/{dspy-rlm-engine-D0h-P2Mz.js → dspy-rlm-engine-DCQKNQMn.js} +2 -2
- package/dist/{dspy-rlm-engine-D0h-P2Mz.js.map → dspy-rlm-engine-DCQKNQMn.js.map} +1 -1
- package/dist/{eval-campaign-ha_aWtk7.js → eval-campaign-DsRmYsQI.js} +2 -2
- package/dist/{eval-campaign-ha_aWtk7.js.map → eval-campaign-DsRmYsQI.js.map} +1 -1
- package/dist/experiment/index.js +9 -9
- package/dist/index.d.ts +61 -3
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +102 -25
- package/dist/index.js.map +1 -1
- package/dist/{internal-BOe3zmjQ.js → internal-CRHwS9iz.js} +3 -3
- package/dist/internal-CRHwS9iz.js.map +1 -0
- package/dist/jev.js +1 -1
- package/dist/judge-calibration-DFtEMlde.d.ts.map +1 -1
- package/dist/{judge-calibration-C5zgtiJT.js → judge-calibration-N44V04Se.js} +7 -17
- package/dist/judge-calibration-N44V04Se.js.map +1 -0
- package/dist/{kind-factory-CdPPHtGZ.js → kind-factory-Cn1lbsAd.js} +5 -5
- package/dist/kind-factory-Cn1lbsAd.js.map +1 -0
- package/dist/{llm-judge-DyZdrp6I.js → llm-judge-Bka5q-ds.js} +8 -8
- package/dist/{llm-judge-DyZdrp6I.js.map → llm-judge-Bka5q-ds.js.map} +1 -1
- package/dist/matrix/index.js +1 -1
- package/dist/{matrix-DnlHn5x1.js → matrix-_BV9-Lk5.js} +12 -9
- package/dist/matrix-_BV9-Lk5.js.map +1 -0
- package/dist/meta-eval/index.js +2 -2
- package/dist/multishot/golden/index.js +1 -1
- package/dist/multishot/index.js +1 -1
- package/dist/normal-DsJZtrJc.js +25 -0
- package/dist/normal-DsJZtrJc.js.map +1 -0
- package/dist/openapi.json +1 -1
- package/dist/{paired-arms-DpS_h8ON.js → paired-arms-Dsu-r6xd.js} +6 -27
- package/dist/paired-arms-Dsu-r6xd.js.map +1 -0
- package/dist/{paired-binary-OMBVRtc-.js → paired-binary-DpwwK1fU.js} +2 -2
- package/dist/{paired-binary-OMBVRtc-.js.map → paired-binary-DpwwK1fU.js.map} +1 -1
- package/dist/{paired-promotion-decision-DhrmjdV8.js → paired-promotion-decision-CO0kA0bq.js} +3 -3
- package/dist/{paired-promotion-decision-DhrmjdV8.js.map → paired-promotion-decision-CO0kA0bq.js.map} +1 -1
- package/dist/{paired-tests-Ccr16gcW.js → paired-tests-jbwPdSz5.js} +3 -3
- package/dist/{paired-tests-Ccr16gcW.js.map → paired-tests-jbwPdSz5.js.map} +1 -1
- package/dist/pipelines/index.d.ts +1 -1
- package/dist/pipelines/index.js +2 -2
- package/dist/{power-and-mde-bie6i965.js → power-and-mde-fK5Qocwo.js} +3 -3
- package/dist/{power-and-mde-bie6i965.js.map → power-and-mde-fK5Qocwo.js.map} +1 -1
- package/dist/{produced-state-DLToUXrD.js → produced-state-FdbE-88t.js} +3 -3
- package/dist/{produced-state-DLToUXrD.js.map → produced-state-FdbE-88t.js.map} +1 -1
- package/dist/{promotion-policy-BI1RxzwD.js → promotion-policy-BSbTAMtE.js} +4 -4
- package/dist/{promotion-policy-BI1RxzwD.js.map → promotion-policy-BSbTAMtE.js.map} +1 -1
- package/dist/quantile--0yb07pD.js +15 -0
- package/dist/quantile--0yb07pD.js.map +1 -0
- package/dist/{report-command-D0XL2Cvi.js → report-command-JrjiWReS.js} +2 -2
- package/dist/{report-command-D0XL2Cvi.js.map → report-command-JrjiWReS.js.map} +1 -1
- package/dist/reporting.js +4 -4
- package/dist/{reward-hacking-C-a__ShZ.js → reward-hacking-BFcQgkux.js} +2 -2
- package/dist/{reward-hacking-C-a__ShZ.js.map → reward-hacking-BFcQgkux.js.map} +1 -1
- package/dist/rl.js +7 -7
- package/dist/{rubric-predictive-validity-B0Pg-3I5.js → rubric-predictive-validity-BsgkBfT0.js} +3 -3
- package/dist/{rubric-predictive-validity-B0Pg-3I5.js.map → rubric-predictive-validity-BsgkBfT0.js.map} +1 -1
- package/dist/search/index.js +2 -2
- package/dist/{search-kernel-Dpniloks.js → search-kernel-CsISc5t8.js} +5 -5
- package/dist/{search-kernel-Dpniloks.js.map → search-kernel-CsISc5t8.js.map} +1 -1
- package/dist/{search-summary-C1nAHgkB.js → search-summary-BZkoLwbB.js} +4 -4
- package/dist/{search-summary-C1nAHgkB.js.map → search-summary-BZkoLwbB.js.map} +1 -1
- package/dist/{semantic-concept-judge-BgWxa4L_.js → semantic-concept-judge-BbiYuv7U.js} +3 -3
- package/dist/{semantic-concept-judge-BgWxa4L_.js.map → semantic-concept-judge-BbiYuv7U.js.map} +1 -1
- package/dist/{sequential-DWn_np6P.js → sequential-7uxpO0Vm.js} +2 -2
- package/dist/{sequential-DWn_np6P.js.map → sequential-7uxpO0Vm.js.map} +1 -1
- package/dist/{skillopt-optimization-method-Dz5CGZb8.js → skillopt-optimization-method-bEm4jYV4.js} +4 -4
- package/dist/{skillopt-optimization-method-Dz5CGZb8.js.map → skillopt-optimization-method-bEm4jYV4.js.map} +1 -1
- package/dist/{statistical-heldout-CNLOvRq_.js → statistical-heldout-C26hOFWD.js} +3 -3
- package/dist/{statistical-heldout-CNLOvRq_.js.map → statistical-heldout-C26hOFWD.js.map} +1 -1
- package/dist/{store-otlp-yd9lDziN.js → store-otlp-BA7G1Du-.js} +44 -11
- package/dist/store-otlp-BA7G1Du-.js.map +1 -0
- package/dist/{store-tool-spans-CAF3T-BS.d.ts → store-tool-spans-BYIarVrG.d.ts} +17 -8
- package/dist/{store-tool-spans-CAF3T-BS.d.ts.map → store-tool-spans-BYIarVrG.d.ts.map} +1 -1
- package/dist/{store-tool-spans-D5kOU0mr.js → store-tool-spans-DKoVbE-w.js} +3 -3
- package/dist/{store-tool-spans-D5kOU0mr.js.map → store-tool-spans-DKoVbE-w.js.map} +1 -1
- package/dist/{student-t-BBZYka0E.js → student-t-BQeKJx2N.js} +2 -2
- package/dist/{student-t-BBZYka0E.js.map → student-t-BQeKJx2N.js.map} +1 -1
- package/dist/{summary-report-DLzptLSA.js → summary-report-BG6-hOkm.js} +6 -6
- package/dist/{summary-report-DLzptLSA.js.map → summary-report-BG6-hOkm.js.map} +1 -1
- package/dist/supervisor-run/index.js +1 -1
- package/dist/{tool-waste-CP5DO383.d.ts → tool-waste-DxlebQkx.d.ts} +42 -2
- package/dist/tool-waste-DxlebQkx.d.ts.map +1 -0
- package/dist/{tool-waste-B-u3rzCz.js → tool-waste-x_E8h9Ih.js} +3 -3
- package/dist/{tool-waste-B-u3rzCz.js.map → tool-waste-x_E8h9Ih.js.map} +1 -1
- package/dist/trace-repair/index.js +1 -1
- package/dist/traces.d.ts +2 -2
- package/dist/traces.js +4 -4
- package/dist/{tree-D48IJUK0.js → tree-CAQflhLR.js} +5 -5
- package/dist/{tree-D48IJUK0.js.map → tree-CAQflhLR.js.map} +1 -1
- package/docs/concepts.md +21 -0
- package/docs/trace-analysis.md +10 -0
- package/package.json +1 -1
- package/dist/baseline-CVKsfWTg.js +0 -150
- package/dist/baseline-CVKsfWTg.js.map +0 -1
- package/dist/benchmark-command-6OBcB0sG.js.map +0 -1
- package/dist/internal-BOe3zmjQ.js.map +0 -1
- package/dist/judge-calibration-C5zgtiJT.js.map +0 -1
- package/dist/kind-factory-CdPPHtGZ.js.map +0 -1
- package/dist/matrix-DnlHn5x1.js.map +0 -1
- package/dist/paired-arms-DpS_h8ON.js.map +0 -1
- package/dist/store-otlp-yd9lDziN.js.map +0 -1
- package/dist/tool-waste-CP5DO383.d.ts.map +0 -1
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { t as AgentEvalError } from "./errors-Dngq5h35.js";
|
|
2
2
|
import { a as hashCanonical, i as compareCodeUnits, r as canonicalString } from "./canonical-BsZVgBhW.js";
|
|
3
|
-
import { n as aggregatePairedHoldout, o as pairHoldout } from "./statistical-heldout-
|
|
3
|
+
import { n as aggregatePairedHoldout, o as pairHoldout } from "./statistical-heldout-C26hOFWD.js";
|
|
4
4
|
import { n as contentHash } from "./verdict-cache-BQEsVy9n.js";
|
|
5
5
|
import { r as projectCampaignCellQuality } from "./run-record-BB290Y9A.js";
|
|
6
6
|
import { t as FileLedgerJournal } from "./journal-DvKCvjty.js";
|
|
@@ -1738,4 +1738,4 @@ function createCampaignEvidenceReceipt(input) {
|
|
|
1738
1738
|
//#endregion
|
|
1739
1739
|
export { openFinalEvidenceLedger as A, assertRealBackend as B, pairedCampaignComposites as C, powerPreflight as D, recoverTruncatedJson as E, surfaceContentHash as F, campaignCoverage as G, assertCampaignDesign as H, surfaceDispatchRef as I, campaignSplitDigestFromIdentities as J, campaignScenarioIdentity as K, surfaceHash as L, codeSurfaceIdentityMaterial as M, componentSurfaceIdentityMaterial as N, FinalEvidenceConflictError as O, renderSurfaceDiff as P, surfaceHashMatches as R, campaignMeanCompositeOrNull as S, parseReflectionResponse as T, assertCampaignSplitIdentity as U, summarizeBackendIntegrity as V, assertCompleteCampaign as W, formatCoverageFailures as Y, provenanceRecordPath as _, createEvidenceReceipt as a, campaignBreakdown as b, ATTESTATION_ALGORITHM as c, buildLoopProvenanceRecord as d, campaignMeasurementDigest as f, loopProvenanceSpans as g, loopProvenanceArgsFromResult as h, INDEPENDENT_EVIDENCE_AUTHORITY_KINDS as i, assertCodeSurfaceIdentity as j, FinalEvidenceError as k, attest as l, emitLoopProvenance as m, EVIDENCE_AUTHORITY_KINDS as n, isIndependentEvidence as o, canonicalDigest as p, campaignSplitDigest as q, EVIDENCE_RECEIPT_VERSION as r, verifyEvidenceReceipt as s, createCampaignEvidenceReceipt as t, verifyAttestation as u, provenanceSpansPath as v, buildReflectionPrompt as w, campaignMeanComposite as x, verifyLoopProvenanceRecord as y, BackendIntegrityError as z };
|
|
1740
1740
|
|
|
1741
|
-
//# sourceMappingURL=campaign-evidence-
|
|
1741
|
+
//# sourceMappingURL=campaign-evidence-C__cUpCt.js.map
|