@tangle-network/agent-eval 0.181.0 → 0.183.0
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 +30 -0
- package/dist/analyst/index.d.ts +3 -3
- package/dist/analyst/index.js +7 -7
- package/dist/{benchmark-command-B57n9vjz.js → benchmark-command-NBrqNwgy.js} +11 -11
- package/dist/{benchmark-command-B57n9vjz.js.map → benchmark-command-NBrqNwgy.js.map} +1 -1
- package/dist/benchmarks/index.js +3 -3
- package/dist/campaign/index.js +8 -8
- package/dist/{campaign-4_ppJW5X.js → campaign-BwcEBC91.js} +11 -11
- package/dist/{campaign-4_ppJW5X.js.map → campaign-BwcEBC91.js.map} +1 -1
- package/dist/{campaign-evidence-B8oF9xQ6.js → campaign-evidence-PYPUftRy.js} +2 -2
- package/dist/{campaign-evidence-B8oF9xQ6.js.map → campaign-evidence-PYPUftRy.js.map} +1 -1
- package/dist/{chat-client-CkmjYlfB.js → chat-client-DqPqWzVV.js} +2 -2
- package/dist/{chat-client-CkmjYlfB.js.map → chat-client-DqPqWzVV.js.map} +1 -1
- package/dist/{chat-json-call-B_Xv2oJK.js → chat-json-call-C-DnDxEy.js} +2 -2
- package/dist/{chat-json-call-B_Xv2oJK.js.map → chat-json-call-C-DnDxEy.js.map} +1 -1
- package/dist/cli.js +5 -5
- package/dist/contract/index.js +13 -13
- package/dist/{cost-ledger-B1qx30B4.js → cost-ledger-_IbkejCF.js} +2 -2
- package/dist/{cost-ledger-B1qx30B4.js.map → cost-ledger-_IbkejCF.js.map} +1 -1
- package/dist/{default-registry-aL7xUrUz.js → default-registry-C0-N4PkG.js} +3 -3
- package/dist/{default-registry-aL7xUrUz.js.map → default-registry-C0-N4PkG.js.map} +1 -1
- package/dist/{define-agent-eval-Ddu33JH9.js → define-agent-eval-CneiWyuA.js} +8 -8
- package/dist/{define-agent-eval-Ddu33JH9.js.map → define-agent-eval-CneiWyuA.js.map} +1 -1
- package/dist/{dspy-rlm-engine-S53V0HhE.js → dspy-rlm-engine-8pgBSiy7.js} +4 -4
- package/dist/{dspy-rlm-engine-S53V0HhE.js.map → dspy-rlm-engine-8pgBSiy7.js.map} +1 -1
- package/dist/{eval-campaign-aYdtjtJR.js → eval-campaign-CCEkwzoH.js} +2 -2
- package/dist/{eval-campaign-aYdtjtJR.js.map → eval-campaign-CCEkwzoH.js.map} +1 -1
- package/dist/experiment/index.js +5 -5
- package/dist/exporters-D98GPi1n.d.ts +161 -0
- package/dist/exporters-D98GPi1n.d.ts.map +1 -0
- package/dist/{exporters-Df7TgHFv.js → exporters-DEcXbvgO.js} +12 -4
- package/dist/exporters-DEcXbvgO.js.map +1 -0
- package/dist/{external-optimizer-process-QDRURJAM.js → external-optimizer-process-DIB4YWEe.js} +2 -2
- package/dist/{external-optimizer-process-QDRURJAM.js.map → external-optimizer-process-DIB4YWEe.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-D4dzUBZI.js → external-optimizer-subprocess-CjguXN2e.js} +3 -3
- package/dist/{external-optimizer-subprocess-D4dzUBZI.js.map → external-optimizer-subprocess-CjguXN2e.js.map} +1 -1
- package/dist/fuzz.js +1 -1
- package/dist/{hf-dataset-D8_RNIis.js → hf-dataset-CRqtSjnR.js} +2 -2
- package/dist/{hf-dataset-D8_RNIis.js.map → hf-dataset-CRqtSjnR.js.map} +1 -1
- package/dist/{index-CJ3LhKIX.d.ts → index--_8_Nlpn.d.ts} +4 -154
- package/dist/index--_8_Nlpn.d.ts.map +1 -0
- package/dist/{index-DNntP4ch.d.ts → index-DbG8QbH9.d.ts} +2 -2
- package/dist/{index-DNntP4ch.d.ts.map → index-DbG8QbH9.d.ts.map} +1 -1
- package/dist/index.d.ts +2 -2
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +21 -21
- package/dist/{integrity-DH5ng72x.js → integrity-CgQce0FV.js} +2 -2
- package/dist/{integrity-DH5ng72x.js.map → integrity-CgQce0FV.js.map} +1 -1
- package/dist/{kind-factory-D5HOW3R0.js → kind-factory-DxTzg32u.js} +2 -2
- package/dist/{kind-factory-D5HOW3R0.js.map → kind-factory-DxTzg32u.js.map} +1 -1
- package/dist/{llm-client-CGlSi8sb.js → llm-client-DDhZ29Vm.js} +2 -2
- package/dist/{llm-client-CGlSi8sb.js.map → llm-client-DDhZ29Vm.js.map} +1 -1
- package/dist/{llm-judge-DEFZeSiu.js → llm-judge-FfaRgz9X.js} +6 -6
- package/dist/{llm-judge-DEFZeSiu.js.map → llm-judge-FfaRgz9X.js.map} +1 -1
- package/dist/{metrics-Qv-cpptD.js → metrics-DOMpkoeb.js} +5 -1
- package/dist/metrics-DOMpkoeb.js.map +1 -0
- package/dist/multishot/index.js +1 -1
- package/dist/openapi.json +1 -1
- package/dist/{paired-arms-D4aeIHUy.js → paired-arms-JSDcs2zx.js} +16 -3
- package/dist/paired-arms-JSDcs2zx.js.map +1 -0
- package/dist/{power-and-mde-B8F2RdcD.js → power-and-mde-BJOpt6pq.js} +2 -2
- package/dist/{power-and-mde-B8F2RdcD.js.map → power-and-mde-BJOpt6pq.js.map} +1 -1
- package/dist/{produced-state-BHboMaab.js → produced-state-CGoVInrl.js} +5 -5
- package/dist/{produced-state-BHboMaab.js.map → produced-state-CGoVInrl.js.map} +1 -1
- package/dist/{promotion-policy-CDMMxzb6.js → promotion-policy-BKFrl7CC.js} +3 -3
- package/dist/{promotion-policy-CDMMxzb6.js.map → promotion-policy-BKFrl7CC.js.map} +1 -1
- package/dist/release-confidence-BcqeQTHW.d.ts.map +1 -1
- package/dist/{report-command-V1ecVgAv.js → report-command-BvqaxlVG.js} +32 -201
- package/dist/report-command-BvqaxlVG.js.map +1 -0
- package/dist/reporting.js +3 -3
- package/dist/rl.d.ts +26 -35
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +61 -57
- package/dist/rl.js.map +1 -1
- package/dist/rollout/index.d.ts +2 -1
- package/dist/rollout/index.js +3 -4
- package/dist/{rollout-B-UF5R6w.js → rollout-D_54FZVu.js} +155 -14
- package/dist/rollout-D_54FZVu.js.map +1 -0
- package/dist/{run-record-Br-Yzt_k.js → run-record-DPa2PeHx.js} +2 -2
- package/dist/{run-record-Br-Yzt_k.js.map → run-record-DPa2PeHx.js.map} +1 -1
- package/dist/{semantic-concept-judge-Bm5JDEKO.js → semantic-concept-judge-_3Fp6Q_3.js} +6 -6
- package/dist/{semantic-concept-judge-Bm5JDEKO.js.map → semantic-concept-judge-_3Fp6Q_3.js.map} +1 -1
- package/dist/{sequential-DAsyV2T9.js → sequential-D_xHrBZe.js} +2 -2
- package/dist/{sequential-DAsyV2T9.js.map → sequential-D_xHrBZe.js.map} +1 -1
- package/dist/{server-D_cjseFN.js → server-BZQR1f0C.js} +3 -3
- package/dist/{server-D_cjseFN.js.map → server-BZQR1f0C.js.map} +1 -1
- package/dist/{skillopt-optimization-method-CL_0aArC.js → skillopt-optimization-method-DY1aQ-aL.js} +6 -6
- package/dist/{skillopt-optimization-method-CL_0aArC.js.map → skillopt-optimization-method-DY1aQ-aL.js.map} +1 -1
- package/dist/statistical-heldout-CpVd6FmY.d.ts.map +1 -1
- package/dist/{store-otlp-DWGUwlyj.js → store-otlp-DAaEbMLf.js} +2 -2
- package/dist/{store-otlp-DWGUwlyj.js.map → store-otlp-DAaEbMLf.js.map} +1 -1
- package/dist/{store-tool-spans-ceJoiUgS.js → store-tool-spans-BZ8MPKFe.js} +3 -3
- package/dist/{store-tool-spans-ceJoiUgS.js.map → store-tool-spans-BZ8MPKFe.js.map} +1 -1
- package/dist/{summary-report-e-MaOAHV.js → summary-report-IGAOtgPd.js} +3 -3
- package/dist/{summary-report-e-MaOAHV.js.map → summary-report-IGAOtgPd.js.map} +1 -1
- package/dist/supervisor-run/index.d.ts +20 -44
- package/dist/supervisor-run/index.d.ts.map +1 -1
- package/dist/supervisor-run/index.js +8 -8
- package/dist/supervisor-run/index.js.map +1 -1
- package/dist/{task-failure-attributes-B072KO_n.js → task-failure-attributes-B_JjrOVo.js} +2 -2
- package/dist/{task-failure-attributes-B072KO_n.js.map → task-failure-attributes-B_JjrOVo.js.map} +1 -1
- package/dist/{terminal-record-BtPwKTSr.js → terminal-record-BHocwFw1.js} +5 -22
- package/dist/terminal-record-BHocwFw1.js.map +1 -0
- package/dist/traces.js +4 -4
- package/dist/{types-lPkDQNqJ.d.ts → types-BlIJ5URG.d.ts} +17 -26
- package/dist/types-BlIJ5URG.d.ts.map +1 -0
- package/dist/wire/index.js +1 -1
- package/docs/public-api.md +111 -98
- package/package.json +1 -1
- package/dist/exporters-Df7TgHFv.js.map +0 -1
- package/dist/index-CJ3LhKIX.d.ts.map +0 -1
- package/dist/metrics-Qv-cpptD.js.map +0 -1
- package/dist/opencode-sqlite-CNw3vubS.js +0 -145
- package/dist/opencode-sqlite-CNw3vubS.js.map +0 -1
- package/dist/paired-arms-D4aeIHUy.js.map +0 -1
- package/dist/report-command-V1ecVgAv.js.map +0 -1
- package/dist/rollout-B-UF5R6w.js.map +0 -1
- package/dist/terminal-record-BtPwKTSr.js.map +0 -1
- package/dist/types-lPkDQNqJ.d.ts.map +0 -1
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
import { s as ValidationError, t as AgentEvalError } from "./errors-Dngq5h35.js";
|
|
2
2
|
import { a as hashCanonical, i as compareCodeUnits, r as canonicalString } from "./canonical-DPyQ_rpt.js";
|
|
3
3
|
import { r as pairedBootstrap } from "./paired-tests-C8iCsioC.js";
|
|
4
|
-
import { n as campaignCellExecutionEvidence, o as projectCampaignCellQuality, s as decidePairedPromotion } from "./run-record-
|
|
4
|
+
import { n as campaignCellExecutionEvidence, o as projectCampaignCellQuality, s as decidePairedPromotion } from "./run-record-DPa2PeHx.js";
|
|
5
5
|
import { n as contentHash } from "./verdict-cache-B3eCVQtY.js";
|
|
6
6
|
import { t as FileLedgerJournal } from "./journal-Cs9f7385.js";
|
|
7
7
|
import { g as readField } from "./ast-CP9ae9B0.js";
|
|
@@ -2124,4 +2124,4 @@ function createCampaignEvidenceReceipt(input) {
|
|
|
2124
2124
|
//#endregion
|
|
2125
2125
|
export { formatCoverageFailures as $, FinalEvidenceConflictError as A, surfaceDispatchRef as B, campaignMeanCompositeOrNull as C, parseReflectionResponse as D, buildReflectionPrompt as E, assertCodeSurfaceIdentity as F, summarizeBackendIntegrity as G, surfaceHashMatches as H, codeSurfaceIdentityMaterial as I, assertCompleteCampaign as J, assertCampaignDesign as K, componentSurfaceIdentityMaterial as L, openFinalEvidenceLedger as M, defineEvaluationClaim as N, recoverTruncatedJson as O, summarizeEvaluationUnits as P, campaignSplitDigestFromIdentities as Q, renderSurfaceDiff as R, campaignMeanComposite as S, pairedCampaignComposites as T, BackendIntegrityError as U, surfaceHash as V, assertRealBackend as W, campaignScenarioIdentity as X, campaignCoverage as Y, campaignSplitDigest as Z, provenanceRecordPath as _, createEvidenceReceipt as a, pairHoldout as at, assertFiniteRankKey as b, ATTESTATION_ALGORITHM as c, buildLoopProvenanceRecord as d, TIE_WARN_FRACTION as et, campaignMeasurementDigest as f, loopProvenanceSpans as g, loopProvenanceArgsFromResult as h, INDEPENDENT_EVIDENCE_AUTHORITY_KINDS as i, heldoutSignificance as it, FinalEvidenceError as j, powerPreflight as k, attest as l, emitLoopProvenance as m, EVIDENCE_AUTHORITY_KINDS as n, detectScale as nt, isIndependentEvidence as o, canonicalDigest as p, assertCampaignSplitIdentity as q, EVIDENCE_RECEIPT_VERSION as r, dimensionRegressions as rt, verifyEvidenceReceipt as s, createCampaignEvidenceReceipt as t, aggregatePairedHoldout as tt, verifyAttestation as u, provenanceSpansPath as v, compareRankKeys as w, campaignBreakdown as x, verifyLoopProvenanceRecord as y, surfaceContentHash as z };
|
|
2126
2126
|
|
|
2127
|
-
//# sourceMappingURL=campaign-evidence-
|
|
2127
|
+
//# sourceMappingURL=campaign-evidence-PYPUftRy.js.map
|