@tangle-network/agent-eval 0.217.1 → 0.218.1
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.
- package/CHANGELOG.md +36 -1
- package/dist/adapters/http.d.ts +2 -2
- package/dist/analyst/index.d.ts +1 -1
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +9 -9
- package/dist/analyst/index.js.map +1 -1
- package/dist/{analyze-runs-DyeNcenW.d.ts → analyze-runs-DjlZOVXx.d.ts} +2 -2
- package/dist/{analyze-runs-DyeNcenW.d.ts.map → analyze-runs-DjlZOVXx.d.ts.map} +1 -1
- package/dist/{benchmark-command-xQK8nOI6.js → benchmark-command-BupdHRyf.js} +661 -562
- package/dist/benchmark-command-BupdHRyf.js.map +1 -0
- package/dist/benchmarks/index.d.ts +4 -4
- package/dist/benchmarks/index.js +3 -3
- package/dist/campaign/index.d.ts +4 -4
- package/dist/campaign/index.js +10 -10
- package/dist/{campaign-CJGkxAQ6.js → campaign-CGvUTnmc.js} +312 -281
- package/dist/{campaign-CJGkxAQ6.js.map → campaign-CGvUTnmc.js.map} +1 -1
- package/dist/{campaign-evidence-CQYw8_0H.js → campaign-evidence-DunzcJGv.js} +2 -2
- package/dist/{campaign-evidence-CQYw8_0H.js.map → campaign-evidence-DunzcJGv.js.map} +1 -1
- package/dist/{chat-client-ldqxYYTN.js → chat-client-B2pXlPdx.js} +2 -2
- package/dist/{chat-client-ldqxYYTN.js.map → chat-client-B2pXlPdx.js.map} +1 -1
- package/dist/{chat-json-call-DavzexSp.js → chat-json-call-Dm9c-b41.js} +2 -2
- package/dist/{chat-json-call-DavzexSp.js.map → chat-json-call-Dm9c-b41.js.map} +1 -1
- package/dist/cli.js +10 -10
- package/dist/{completion-verifier-B_jw6C9p.js → completion-verifier-DbLVf3i8.js} +4 -4
- package/dist/{completion-verifier-B_jw6C9p.js.map → completion-verifier-DbLVf3i8.js.map} +1 -1
- package/dist/contract/index.d.ts +7 -7
- package/dist/contract/index.js +90 -10
- package/dist/contract/index.js.map +1 -1
- package/dist/{default-registry-ClYjq3QE.js → default-registry-BJ-Pq6yL.js} +309 -277
- package/dist/{default-registry-ClYjq3QE.js.map → default-registry-BJ-Pq6yL.js.map} +1 -1
- package/dist/{define-agent-eval-BDxNlP3D.js → define-agent-eval-BGdFKlrc.js} +165 -105
- package/dist/define-agent-eval-BGdFKlrc.js.map +1 -0
- package/dist/{define-agent-eval-BIkH_gAR.d.ts → define-agent-eval-BlH10zEw.d.ts} +6 -6
- package/dist/{define-agent-eval-BIkH_gAR.d.ts.map → define-agent-eval-BlH10zEw.d.ts.map} +1 -1
- package/dist/diagnosis/index.d.ts +1 -1
- package/dist/{dspy-rlm-engine-DhdCr1Dc.js → dspy-rlm-engine-CSMwudLO.js} +2 -2
- package/dist/{dspy-rlm-engine-DhdCr1Dc.js.map → dspy-rlm-engine-CSMwudLO.js.map} +1 -1
- package/dist/eval-campaign-BUMIxKTE.js +393 -0
- package/dist/eval-campaign-BUMIxKTE.js.map +1 -0
- package/dist/{evaluation-jTjC_QQD.d.ts → evaluation-BOZ38vOH.d.ts} +2 -2
- package/dist/{evaluation-jTjC_QQD.d.ts.map → evaluation-BOZ38vOH.d.ts.map} +1 -1
- package/dist/evaluation.d.ts +1 -1
- package/dist/experiment/index.d.ts +1 -1
- package/dist/experiment/index.d.ts.map +1 -1
- package/dist/experiment/index.js +110 -71
- package/dist/experiment/index.js.map +1 -1
- package/dist/{exporters-Cl6IeNAu.js → exporters-DWvM16LE.js} +2 -2
- package/dist/{exporters-Cl6IeNAu.js.map → exporters-DWvM16LE.js.map} +1 -1
- package/dist/{external-optimizer-process-KVFGvYX1.js → external-optimizer-process-C3Wm7Vhn.js} +2 -2
- package/dist/{external-optimizer-process-KVFGvYX1.js.map → external-optimizer-process-C3Wm7Vhn.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-XIHBOSKt.js → external-optimizer-subprocess-B5gdLRZv.js} +3 -3
- package/dist/{external-optimizer-subprocess-XIHBOSKt.js.map → external-optimizer-subprocess-B5gdLRZv.js.map} +1 -1
- package/dist/{findings-store-BMVQtEsm.js → findings-store-BtTzPL0d.js} +5 -5
- package/dist/{findings-store-BMVQtEsm.js.map → findings-store-BtTzPL0d.js.map} +1 -1
- package/dist/{hf-dataset-D9f7-oX7.js → hf-dataset-CKxIJQba.js} +3 -3
- package/dist/{hf-dataset-D9f7-oX7.js.map → hf-dataset-CKxIJQba.js.map} +1 -1
- package/dist/hosted/index.js +1 -1
- package/dist/{index-ZuWx52WG.d.ts → index-B16FNdW5.d.ts} +34 -17
- package/dist/index-B16FNdW5.d.ts.map +1 -0
- package/dist/{index-9jJ2fKSX.d.ts → index-CalAsXMR.d.ts} +7 -5
- package/dist/index-CalAsXMR.d.ts.map +1 -0
- package/dist/{index-BiT6RtNH.d.ts → index-DbMOXYnP.d.ts} +6 -6
- package/dist/{index-BiT6RtNH.d.ts.map → index-DbMOXYnP.d.ts.map} +1 -1
- package/dist/index.d.ts +9 -9
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +611 -688
- package/dist/index.js.map +1 -1
- package/dist/{integrity-DOd9Q86O.js → integrity-C8oUeB0g.js} +322 -197
- package/dist/integrity-C8oUeB0g.js.map +1 -0
- package/dist/{journal-CR4QikYp.js → journal-C7om8Gum.js} +48 -38
- package/dist/journal-C7om8Gum.js.map +1 -0
- package/dist/ledger-core/index.d.ts +1 -1
- package/dist/ledger-core/index.js +2 -2
- package/dist/ledger-core/lock-holder.d.ts +2 -0
- package/dist/ledger-core/lock-holder.js +181 -0
- package/dist/ledger-core/lock-holder.js.map +1 -0
- package/dist/{ledger-core-DrJhbms9.js → ledger-core-CAxUdDk0.js} +2 -2
- package/dist/{ledger-core-DrJhbms9.js.map → ledger-core-CAxUdDk0.js.map} +1 -1
- package/dist/{llm-client-BshCREn6.js → llm-client-_Y6ic-tf.js} +238 -248
- package/dist/llm-client-_Y6ic-tf.js.map +1 -0
- package/dist/{llm-judge-C8jMTNNG.js → llm-judge-Djxh-Uhs.js} +646 -458
- package/dist/llm-judge-Djxh-Uhs.js.map +1 -0
- package/dist/lock-holder-DaJbfpci.d.ts +86 -0
- package/dist/lock-holder-DaJbfpci.d.ts.map +1 -0
- package/dist/{matrix-DHe-dwVJ.d.ts → matrix-CCSBna4q.d.ts} +2 -2
- package/dist/{matrix-DHe-dwVJ.d.ts.map → matrix-CCSBna4q.d.ts.map} +1 -1
- package/dist/{mint-zszyYlpA.js → mint-CbdwjTPW.js} +2 -2
- package/dist/{mint-zszyYlpA.js.map → mint-CbdwjTPW.js.map} +1 -1
- package/dist/multishot/golden/index.d.ts +1 -1
- package/dist/multishot/index.d.ts +2 -2
- package/dist/openapi.json +1 -1
- package/dist/{pareto-BzsxidFD.js → pareto-CTv8vozZ.js} +4 -4
- package/dist/{pareto-BzsxidFD.js.map → pareto-CTv8vozZ.js.map} +1 -1
- package/dist/{promotion-gate-DaY95yU6.d.ts → promotion-gate-CxEHRsZW.d.ts} +2 -2
- package/dist/{promotion-gate-DaY95yU6.d.ts.map → promotion-gate-CxEHRsZW.d.ts.map} +1 -1
- package/dist/{proposal-findings-BbWidvUk.js → proposal-findings-n-5WBbEx.js} +2 -2
- package/dist/{proposal-findings-BbWidvUk.js.map → proposal-findings-n-5WBbEx.js.map} +1 -1
- package/dist/{render-C-w2EZ6p.js → render-Cs34y0iX.js} +404 -208
- package/dist/render-Cs34y0iX.js.map +1 -0
- package/dist/reporting.d.ts +2 -2
- package/dist/{researcher-0ABVIdGa.d.ts → researcher-GU1tV4dn.d.ts} +2 -2
- package/dist/{researcher-0ABVIdGa.d.ts.map → researcher-GU1tV4dn.d.ts.map} +1 -1
- package/dist/rl.d.ts +2 -2
- package/dist/rl.js +4 -4
- package/dist/rollout/index.js +5 -5
- package/dist/{rollout-D6C50mfA.js → rollout-Dd1ucT_M.js} +5 -5
- package/dist/{rollout-D6C50mfA.js.map → rollout-Dd1ucT_M.js.map} +1 -1
- package/dist/schema-C-ziyJD7.d.ts.map +1 -1
- package/dist/{schema-DxcKTzbi.js → schema-CvhfLjtZ.js} +77 -47
- package/dist/schema-CvhfLjtZ.js.map +1 -0
- package/dist/search/index.d.ts +2 -2
- package/dist/search/index.d.ts.map +1 -1
- package/dist/search/index.js +2 -2
- package/dist/{search-kernel-DxqjBxA-.d.ts → search-kernel-p9JB3SmL.d.ts} +3 -3
- package/dist/{search-kernel-DxqjBxA-.d.ts.map → search-kernel-p9JB3SmL.d.ts.map} +1 -1
- package/dist/{search-ledger-TUvB5gWH.js → search-ledger-ClpN4I3e.js} +4 -4
- package/dist/{search-ledger-TUvB5gWH.js.map → search-ledger-ClpN4I3e.js.map} +1 -1
- package/dist/{search-ledger-file-UKCO2r8a.js → search-ledger-file-Bd5Tioq6.js} +3 -3
- package/dist/{search-ledger-file-UKCO2r8a.js.map → search-ledger-file-Bd5Tioq6.js.map} +1 -1
- package/dist/{search-shipper-Cw2z3-td.js → search-shipper-Bg2HW3Uv.js} +3 -3
- package/dist/{search-shipper-Cw2z3-td.js.map → search-shipper-Bg2HW3Uv.js.map} +1 -1
- package/dist/{search-summary-DQIvJsSB.js → search-summary-CrBuvVnf.js} +3 -3
- package/dist/{search-summary-DQIvJsSB.js.map → search-summary-CrBuvVnf.js.map} +1 -1
- package/dist/{server-DoVbqqtJ.js → server-C6M0qR8h.js} +2 -2
- package/dist/{server-DoVbqqtJ.js.map → server-C6M0qR8h.js.map} +1 -1
- package/dist/{single-run-lock-U58yf8N6.js → single-run-lock-Dekd8_Wv.js} +7 -7
- package/dist/single-run-lock-Dekd8_Wv.js.map +1 -0
- package/dist/{skillopt-optimization-method-kyL94-ri.js → skillopt-optimization-method-5dlex7MJ.js} +1339 -1059
- package/dist/skillopt-optimization-method-5dlex7MJ.js.map +1 -0
- package/dist/{statistical-heldout-C9AbgREN.d.ts → statistical-heldout-BHfLZHrm.d.ts} +2 -2
- package/dist/{statistical-heldout-C9AbgREN.d.ts.map → statistical-heldout-BHfLZHrm.d.ts.map} +1 -1
- package/dist/{summary-report-DM7tlml1.d.ts → summary-report-CkbRcSuu.d.ts} +16 -1
- package/dist/summary-report-CkbRcSuu.d.ts.map +1 -0
- package/dist/supervisor-run/index.d.ts.map +1 -1
- package/dist/supervisor-run/index.js +3 -3
- package/dist/{systemone-Bp_Ac0p1.d.ts → systemone-BMzDJb1i.d.ts} +3 -3
- package/dist/{systemone-Bp_Ac0p1.d.ts.map → systemone-BMzDJb1i.d.ts.map} +1 -1
- package/dist/systemone.d.ts +2 -2
- package/dist/{terminal-record-78g6E4vh.js → terminal-record-D4Rv-j1W.js} +241 -193
- package/dist/{terminal-record-78g6E4vh.js.map → terminal-record-D4Rv-j1W.js.map} +1 -1
- package/dist/trajectory-replay/index.d.ts +4 -1
- package/dist/trajectory-replay/index.d.ts.map +1 -1
- package/dist/trajectory-replay/index.js +834 -824
- package/dist/trajectory-replay/index.js.map +1 -1
- package/dist/{tree-BGRglkKd.js → tree-B5e1uAeL.js} +122 -14
- package/dist/tree-B5e1uAeL.js.map +1 -0
- package/dist/{types-DtMbFw6U.d.ts → types-BKCzzmit.d.ts} +2 -2
- package/dist/{types-DtMbFw6U.d.ts.map → types-BKCzzmit.d.ts.map} +1 -1
- package/dist/{types-D8GhJoHk.d.ts → types-DtkO1G9L.d.ts} +2 -2
- package/dist/{types-D8GhJoHk.d.ts.map → types-DtkO1G9L.d.ts.map} +1 -1
- package/dist/wire/index.js +1 -1
- package/docs/design/statistics-decisions.md +1 -1
- package/docs/eval-surface-map.md +1 -0
- package/docs/profile-json-identity.md +1 -2
- package/docs/public-api.md +27 -16
- package/package.json +7 -2
- package/dist/benchmark-command-xQK8nOI6.js.map +0 -1
- package/dist/define-agent-eval-BDxNlP3D.js.map +0 -1
- package/dist/eval-campaign-BLEfBGbA.js +0 -343
- package/dist/eval-campaign-BLEfBGbA.js.map +0 -1
- package/dist/index-9jJ2fKSX.d.ts.map +0 -1
- package/dist/index-ZuWx52WG.d.ts.map +0 -1
- package/dist/integrity-DOd9Q86O.js.map +0 -1
- package/dist/journal-CR4QikYp.js.map +0 -1
- package/dist/llm-client-BshCREn6.js.map +0 -1
- package/dist/llm-judge-C8jMTNNG.js.map +0 -1
- package/dist/render-C-w2EZ6p.js.map +0 -1
- package/dist/schema-DxcKTzbi.js.map +0 -1
- package/dist/single-run-lock-U58yf8N6.js.map +0 -1
- package/dist/skillopt-optimization-method-kyL94-ri.js.map +0 -1
- package/dist/summary-report-DM7tlml1.d.ts.map +0 -1
- package/dist/tree-BGRglkKd.js.map +0 -1
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
import { o as FailureClass } from "./schema-D6EVKzTB.js";
|
|
2
2
|
import { a as RunRecord, c as RunSplitTag } from "./run-record-CaxbLq6Y.js";
|
|
3
3
|
import { i as DatasetSplit, n as DatasetManifest, r as DatasetScenario } from "./dataset-DQqhOCPt.js";
|
|
4
|
-
import { S as HeldOutGateDecision } from "./summary-report-
|
|
4
|
+
import { S as HeldOutGateDecision } from "./summary-report-CkbRcSuu.js";
|
|
5
5
|
//#region src/statistics/rank-tests.d.ts
|
|
6
6
|
/** How a rank test's p-value was actually computed. */
|
|
7
7
|
type RankTestMethod = 'exact' | 'permutation' | 'asymptotic';
|
|
@@ -301,4 +301,4 @@ declare function judgeReplayGate<TOutput>(args: JudgeReplayGateArgs<TOutput>): P
|
|
|
301
301
|
}>;
|
|
302
302
|
//#endregion
|
|
303
303
|
export { mannWhitneyU as C, WilcoxonSignedRankResult as S, evaluateReleaseConfidence as _, bootstrapCi as a, RankTestMethodRequest as b, ReleaseConfidenceAxis as c, ReleaseConfidenceIssue as d, ReleaseConfidenceMetrics as f, ReleaseTraceEvidence as g, ReleaseConfidenceThresholds as h, Verdict as i, ReleaseConfidenceAxisName as l, ReleaseConfidenceStatus as m, BootstrapResult as n, judgeReplayGate as o, ReleaseConfidenceScorecard as p, JudgeReplayGateArgs as r, ActionableSideInfo as s, BootstrapOptions as t, ReleaseConfidenceInput as u, MannWhitneyResult as v, wilcoxonSignedRank as w, RankTestOptions as x, RankTestMethod as y };
|
|
304
|
-
//# sourceMappingURL=promotion-gate-
|
|
304
|
+
//# sourceMappingURL=promotion-gate-CxEHRsZW.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"promotion-gate-
|
|
1
|
+
{"version":3,"file":"promotion-gate-CxEHRsZW.d.ts","names":[],"sources":["../src/statistics/rank-tests.ts","../src/release-confidence.ts","../src/promotion-gate.ts"],"mappings":";;;;;;KAiCY;;;;;KAMA;UAEK;;EAEf,SAAS;;EAET;;;EAGA;;UAYe;;EAEf;;EAEA;;EAEA;;EAEA,QAAQ;;EAER;;;;;;;;;;;;;;iBAec,aACd,aACA,aACA,OAAM,kBACL;UAuFc;;;EAGf;;EAEA;;EAEA,QAAQ;;EAER;;EAEA;;;;;;;;;;;;;;;iBAgBc,mBACd,kBACA,iBACA,OAAM,kBACL;;;;KCzLE;;UAGY;;EAEf;;EAEA;EACA,WAAW;;EAEX;;EAEA;;EAEA;;EAEA;EACA,WAAW;;KAGD;KACA;UAQK;EACf;EACA;EACA,QAAQ;EACR;EACA;EACA;EACA;EACA;;EAEA,eAAe;EACf,MAAM;EACN,WAAW;;UAGI;;EAEf;EACA;EACA;EACA;;EAEA;EACA;EACA;;EAEA;EACA;EACA;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA;EACA,UAAU;EACV,qBAAqB;EACrB,gBAAgB;EAChB,kBAAkB;EAClB,eAAe;EACf,aAAa;;UAGE;EACf,MAAM;EACN,QAAQ;EACR;EACA;;UAGe;EACf,MAAM;EACN;EACA;EACA;;UAGe;EACf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA,aAAa,OAAO;EACpB,cAAc;EACd,oBAAoB,QAAQ,OAAO;EACnC,0BAA0B;;;;;;;EAO1B;;UAGe;EACf;EACA;EACA;EACA,QAAQ;EACR;EACA,MAAM;EACN,QAAQ;EACR,SAAS;EACT,SAAS;EACT,cAAc;EACd;;iBAkBc,0BACd,OAAO,yBACN;;;;;;;;;;;;;;;;;;;;;;;;;;;KC1JS;UAEK;EACf;EACA;;EAEA;;EAEA;;EAEA;;EAEA;EACA;EACA,SAAS;;UAGM;;EAEf;;EAEA;;;;;;EAMA;;;EAGA;;;;;;;;;iBAUc,YACd,oBACA,qBACA,UAAS,mBACR;;;;;;;;;;;;;;;;UA0Gc,oBAAoB;EACnC,iBAAiB;EACjB,kBAAkB;;EAElB,QAAQ,QAAQ,YAAY;EAC5B;EACA;;EAEA;;EAEA;;;;;iBAMoB,gBAAgB,SACpC,MAAM,oBAAoB,WACzB,QAAQ;EAAoB;EAAyB"}
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
import { S as ProposalFindingSchema } from "./external-optimizer-subprocess-
|
|
1
|
+
import { S as ProposalFindingSchema } from "./external-optimizer-subprocess-B5gdLRZv.js";
|
|
2
2
|
//#region src/analyst/proposal-findings.ts
|
|
3
3
|
/** True when a finding names a source candidate generation may learn from. */
|
|
4
4
|
function isProposalFinding(finding) {
|
|
@@ -23,4 +23,4 @@ function findingLabel(finding, index) {
|
|
|
23
23
|
//#endregion
|
|
24
24
|
export { assertProposalFindings as t };
|
|
25
25
|
|
|
26
|
-
//# sourceMappingURL=proposal-findings-
|
|
26
|
+
//# sourceMappingURL=proposal-findings-n-5WBbEx.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"proposal-findings-
|
|
1
|
+
{"version":3,"file":"proposal-findings-n-5WBbEx.js","names":[],"sources":["../src/analyst/proposal-findings.ts"],"sourcesContent":["import { ProposalFindingSchema } from './finding-scope'\nimport type { ProposalFinding } from './types'\n\n/** True when a finding names a source candidate generation may learn from. */\nfunction isProposalFinding(finding: unknown): finding is ProposalFinding {\n return ProposalFindingSchema.safeParse(finding).success\n}\n\n/**\n * Reject findings whose source has not been explicitly admitted for candidate\n * generation. Search feedback and observed production behavior are allowed;\n * final evaluation data has no allowed origin.\n */\nexport function assertProposalFindings(\n findings: unknown,\n context = 'proposal findings',\n): ReadonlyArray<ProposalFinding> {\n if (!Array.isArray(findings)) {\n throw new TypeError(`${context}: expected an array`)\n }\n const rejected = findings.flatMap((finding, index) =>\n isProposalFinding(finding) ? [] : [findingLabel(finding, index)],\n )\n if (rejected.length > 0) {\n throw new Error(\n `${context}: every finding must match AnalystFinding and declare ` +\n `proposal_origin as search or production. ` +\n `Rejected findings: [${rejected.join(', ')}].`,\n )\n }\n return findings as ReadonlyArray<ProposalFinding>\n}\n\nfunction findingLabel(finding: unknown, index: number): string {\n if (typeof finding !== 'object' || finding === null) return `index ${index}`\n const id = (finding as { finding_id?: unknown }).finding_id\n return typeof id === 'string' && id.length > 0 ? id : `index ${index}`\n}\n"],"mappings":";;;AAIA,SAAS,kBAAkB,SAA8C;CACvE,OAAO,sBAAsB,UAAU,OAAO,CAAC,CAAC;AAClD;;;;;;AAOA,SAAgB,uBACd,UACA,UAAU,qBACsB;CAChC,IAAI,CAAC,MAAM,QAAQ,QAAQ,GACzB,MAAM,IAAI,UAAU,GAAG,QAAQ,oBAAoB;CAErD,MAAM,WAAW,SAAS,SAAS,SAAS,UAC1C,kBAAkB,OAAO,IAAI,CAAC,IAAI,CAAC,aAAa,SAAS,KAAK,CAAC,CACjE;CACA,IAAI,SAAS,SAAS,GACpB,MAAM,IAAI,MACR,GAAG,QAAQ,qHAEc,SAAS,KAAK,IAAI,EAAE,GAC/C;CAEF,OAAO;AACT;AAEA,SAAS,aAAa,SAAkB,OAAuB;CAC7D,IAAI,OAAO,YAAY,YAAY,YAAY,MAAM,OAAO,SAAS;CACrE,MAAM,KAAM,QAAqC;CACjD,OAAO,OAAO,OAAO,YAAY,GAAG,SAAS,IAAI,KAAK,SAAS;AACjE"}
|