@tangle-network/agent-eval 1.0.20 → 1.0.21
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 +4 -6
- package/dist/adapters/http.d.ts +2 -2
- package/dist/analyst/index.d.ts +5 -5
- package/dist/analyst/index.js +5 -5
- package/dist/{analyze-runs-DicleUI_.d.ts → analyze-runs-DYYe18Gw.d.ts} +3 -3
- package/dist/{analyze-runs-DicleUI_.d.ts.map → analyze-runs-DYYe18Gw.d.ts.map} +1 -1
- package/dist/{analyze-runs-e9vfXY--.js → analyze-runs-jLTRKuoK.js} +5 -5
- package/dist/{analyze-runs-e9vfXY--.js.map → analyze-runs-jLTRKuoK.js.map} +1 -1
- package/dist/app-grade/index.d.ts +2 -2
- package/dist/app-grade/index.js +1 -1
- package/dist/{benchmark-command-BGZD77Un.js → benchmark-command-CoNndRCk.js} +3 -3
- package/dist/{benchmark-command-BGZD77Un.js.map → benchmark-command-CoNndRCk.js.map} +1 -1
- package/dist/benchmarks/index.d.ts +4 -4
- package/dist/benchmarks/index.js +3 -3
- package/dist/builder-eval/index.js +1 -1
- package/dist/{calibration-Ze7SjhT9.js → calibration-Cf-wpqqO.js} +2 -2
- package/dist/{calibration-Ze7SjhT9.js.map → calibration-Cf-wpqqO.js.map} +1 -1
- package/dist/campaign/index.d.ts +5 -5
- package/dist/campaign/index.js +9 -9
- package/dist/{campaign-BfDMncQN.js → campaign-Bl07uIaf.js} +11 -11
- package/dist/{campaign-BfDMncQN.js.map → campaign-Bl07uIaf.js.map} +1 -1
- package/dist/{campaign-evidence-BuKlRzSA.js → campaign-evidence-NtH29ctt.js} +3 -3
- package/dist/{campaign-evidence-BuKlRzSA.js.map → campaign-evidence-NtH29ctt.js.map} +1 -1
- package/dist/cli.js +5 -5
- package/dist/{cluster-bootstrap-BYIW7QJ4.js → cluster-bootstrap-B0MTOBRU.js} +2 -2
- package/dist/{cluster-bootstrap-BYIW7QJ4.js.map → cluster-bootstrap-B0MTOBRU.js.map} +1 -1
- package/dist/contract/index.d.ts +8 -8
- package/dist/contract/index.js +10 -10
- package/dist/{decision-point-DJWievVw.js → decision-point-Di2LATNH.js} +3 -3
- package/dist/{decision-point-DJWievVw.js.map → decision-point-Di2LATNH.js.map} +1 -1
- package/dist/{default-registry-CdMtoY-s.js → default-registry-CdFbxPnr.js} +2 -2
- package/dist/{default-registry-CdMtoY-s.js.map → default-registry-CdFbxPnr.js.map} +1 -1
- package/dist/{default-registry-BpGFsSpZ.d.ts → default-registry-aPvwtzEM.d.ts} +2 -2
- package/dist/{default-registry-BpGFsSpZ.d.ts.map → default-registry-aPvwtzEM.d.ts.map} +1 -1
- package/dist/{define-agent-eval-DuQNZajG.js → define-agent-eval-BROmIwn1.js} +5 -5
- package/dist/{define-agent-eval-DuQNZajG.js.map → define-agent-eval-BROmIwn1.js.map} +1 -1
- package/dist/{define-agent-eval-DcK8mg63.d.ts → define-agent-eval-Bx3b9B01.d.ts} +6 -6
- package/dist/{define-agent-eval-DcK8mg63.d.ts.map → define-agent-eval-Bx3b9B01.d.ts.map} +1 -1
- package/dist/diagnosis/index.d.ts +1 -1
- package/dist/diagnosis/index.js +1 -1
- package/dist/{eval-campaign-LmpC_5fm.js → eval-campaign-Dq8DEKmy.js} +2 -2
- package/dist/{eval-campaign-LmpC_5fm.js.map → eval-campaign-Dq8DEKmy.js.map} +1 -1
- package/dist/{evaluation-BCejQgkV.d.ts → evaluation-CFKj_IlJ.d.ts} +2 -2
- package/dist/{evaluation-BCejQgkV.d.ts.map → evaluation-CFKj_IlJ.d.ts.map} +1 -1
- package/dist/evaluation.d.ts +1 -1
- package/dist/experiment/index.d.ts +2 -2
- package/dist/experiment/index.js +6 -6
- package/dist/fuzz.js +1 -1
- package/dist/{index-CeYLLnfi.d.ts → index-7tWvC0aW.d.ts} +16 -16
- package/dist/{index-CeYLLnfi.d.ts.map → index-7tWvC0aW.d.ts.map} +1 -1
- package/dist/{index-CzfdjM6o.d.ts → index-B62BaRzH.d.ts} +2 -2
- package/dist/{index-CzfdjM6o.d.ts.map → index-B62BaRzH.d.ts.map} +1 -1
- package/dist/{index-DYNHOTTB.d.ts → index-BlTbxHlY.d.ts} +2 -2
- package/dist/{index-DYNHOTTB.d.ts.map → index-BlTbxHlY.d.ts.map} +1 -1
- package/dist/{index-D_eAFB3T.d.ts → index-CM12lr9E.d.ts} +3 -3
- package/dist/{index-D_eAFB3T.d.ts.map → index-CM12lr9E.d.ts.map} +1 -1
- package/dist/{index-gSu9DUiw.d.ts → index-DFso1b2W.d.ts} +7 -7
- package/dist/{index-gSu9DUiw.d.ts.map → index-DFso1b2W.d.ts.map} +1 -1
- package/dist/{index-BdLmBInV.d.ts → index-DNXFzSpc.d.ts} +23 -21
- package/dist/{index-BdLmBInV.d.ts.map → index-DNXFzSpc.d.ts.map} +1 -1
- package/dist/{index-Bc8BZfzb.d.ts → index-DfqAy8ct.d.ts} +6 -6
- package/dist/{index-Bc8BZfzb.d.ts.map → index-DfqAy8ct.d.ts.map} +1 -1
- package/dist/index.d.ts +16 -16
- package/dist/index.js +14 -14
- package/dist/{judge-gate-BliY81A0.js → judge-gate-CrN0PaAL.js} +2 -2
- package/dist/{judge-gate-BliY81A0.js.map → judge-gate-CrN0PaAL.js.map} +1 -1
- package/dist/{llm-judge-Bnxuwjxl.js → llm-judge-C813vmpc.js} +9 -9
- package/dist/{llm-judge-Bnxuwjxl.js.map → llm-judge-C813vmpc.js.map} +1 -1
- package/dist/{matrix-D6zEwLvE.d.ts → matrix-C-GxIgeJ.d.ts} +2 -2
- package/dist/{matrix-D6zEwLvE.d.ts.map → matrix-C-GxIgeJ.d.ts.map} +1 -1
- package/dist/meta-eval/index.d.ts +2 -2
- package/dist/meta-eval/index.js +6 -6
- 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/{outcome-observations-BpicIVQi.js → outcome-observations-DPkH-LHQ.js} +2 -2
- package/dist/{outcome-observations-BpicIVQi.js.map → outcome-observations-DPkH-LHQ.js.map} +1 -1
- package/dist/{paired-arms-Dep5tbsw.js → paired-arms-DjMEtYI9.js} +2 -2
- package/dist/{paired-arms-Dep5tbsw.js.map → paired-arms-DjMEtYI9.js.map} +1 -1
- package/dist/{paired-promotion-decision-Nt4CkkOT.js → paired-promotion-decision-Bi9__RQS.js} +2 -2
- package/dist/{paired-promotion-decision-Nt4CkkOT.js.map → paired-promotion-decision-Bi9__RQS.js.map} +1 -1
- package/dist/{paired-promotion-decision-BNzPfXDw.d.ts → paired-promotion-decision-DJU3fZxH.d.ts} +2 -2
- package/dist/{paired-promotion-decision-BNzPfXDw.d.ts.map → paired-promotion-decision-DJU3fZxH.d.ts.map} +1 -1
- package/dist/{pareto-C445lnEH.js → pareto-fJZg8pXm.js} +3 -3
- package/dist/{pareto-C445lnEH.js.map → pareto-fJZg8pXm.js.map} +1 -1
- package/dist/pipelines/index.js +1 -1
- package/dist/{promotion-gate-DjAsmBSZ.d.ts → promotion-gate-Da0xV4sa.d.ts} +2 -2
- package/dist/{promotion-gate-DjAsmBSZ.d.ts.map → promotion-gate-Da0xV4sa.d.ts.map} +1 -1
- package/dist/{promotion-policy-CUWOv01m.js → promotion-policy-DCgftbnd.js} +4 -4
- package/dist/{promotion-policy-CUWOv01m.js.map → promotion-policy-DCgftbnd.js.map} +1 -1
- package/dist/{release-confidence-DDrkmWxT.js → release-confidence-DGtuPDxJ.js} +2 -2
- package/dist/{release-confidence-DDrkmWxT.js.map → release-confidence-DGtuPDxJ.js.map} +1 -1
- package/dist/reporting.d.ts +3 -3
- package/dist/reporting.js +4 -4
- package/dist/{researcher-D35yo0B8.d.ts → researcher-CSlc84Bp.d.ts} +2 -2
- package/dist/{researcher-D35yo0B8.d.ts.map → researcher-CSlc84Bp.d.ts.map} +1 -1
- package/dist/{reward-hacking-DRb8K6N1.js → reward-hacking-BYiDFbIl.js} +2 -2
- package/dist/{reward-hacking-DRb8K6N1.js.map → reward-hacking-BYiDFbIl.js.map} +1 -1
- package/dist/rl.d.ts +4 -4
- package/dist/rl.js +7 -7
- package/dist/rollout/index.d.ts +2 -2
- package/dist/{rubric-predictive-validity-BMS7SUyh.js → rubric-predictive-validity-DL7gJ51F.js} +2 -2
- package/dist/{rubric-predictive-validity-BMS7SUyh.js.map → rubric-predictive-validity-DL7gJ51F.js.map} +1 -1
- package/dist/{run-record-CIflWk6i.js → run-record-CFbnkE1K.js} +2 -2
- package/dist/{run-record-CIflWk6i.js.map → run-record-CFbnkE1K.js.map} +1 -1
- package/dist/{runtime-rollouts-CfRyjk60.js → runtime-rollouts-BNrm5nC_.js} +2 -2
- package/dist/{runtime-rollouts-CfRyjk60.js.map → runtime-rollouts-BNrm5nC_.js.map} +1 -1
- package/dist/search/index.d.ts +2 -2
- package/dist/search/index.js +2 -2
- package/dist/{search-kernel-Ds2zILpY.d.ts → search-kernel-CQGLbmgn.d.ts} +3 -3
- package/dist/{search-kernel-Ds2zILpY.d.ts.map → search-kernel-CQGLbmgn.d.ts.map} +1 -1
- package/dist/{search-summary-BSftVrGY.js → search-summary-sPWiYtSl.js} +4 -4
- package/dist/{search-summary-BSftVrGY.js.map → search-summary-sPWiYtSl.js.map} +1 -1
- package/dist/{sequential-CqG6aLWS.js → sequential-9TVb5Nu5.js} +3 -3
- package/dist/{sequential-CqG6aLWS.js.map → sequential-9TVb5Nu5.js.map} +1 -1
- package/dist/{skillopt-optimization-method-DYwEndON.js → skillopt-optimization-method-QO1nU8Kz.js} +6 -6
- package/dist/{skillopt-optimization-method-DYwEndON.js.map → skillopt-optimization-method-QO1nU8Kz.js.map} +1 -1
- package/dist/{statistical-heldout--0b1lgx4.d.ts → statistical-heldout-CvOwNqt9.d.ts} +4 -4
- package/dist/{statistical-heldout--0b1lgx4.d.ts.map → statistical-heldout-CvOwNqt9.d.ts.map} +1 -1
- package/dist/{statistical-heldout-D6i58CJ5.js → statistical-heldout-DLO4Ebos.js} +3 -3
- package/dist/{statistical-heldout-D6i58CJ5.js.map → statistical-heldout-DLO4Ebos.js.map} +1 -1
- package/dist/{statistics-DCZIC-qT.js → statistics-CvvC-MPv.js} +28 -21
- package/dist/statistics-CvvC-MPv.js.map +1 -0
- package/dist/statistics.d.ts +2 -2
- package/dist/statistics.js +2 -2
- package/dist/{summary-report-D_uussI3.js → summary-report-BEhqoxrA.js} +3 -3
- package/dist/{summary-report-D_uussI3.js.map → summary-report-BEhqoxrA.js.map} +1 -1
- package/dist/{summary-report-Cv1AC-iv.d.ts → summary-report-DyZquTaH.d.ts} +2 -2
- package/dist/{summary-report-Cv1AC-iv.d.ts.map → summary-report-DyZquTaH.d.ts.map} +1 -1
- package/dist/supervisor-run/index.d.ts +1 -1
- package/dist/supervisor-run/index.js +1 -1
- package/dist/{systemone-C3xyEKvG.d.ts → systemone-DVk-Crtu.d.ts} +4 -4
- package/dist/{systemone-C3xyEKvG.d.ts.map → systemone-DVk-Crtu.d.ts.map} +1 -1
- package/dist/systemone.d.ts +2 -2
- package/dist/systemone.js +1 -1
- package/dist/{tool-waste-DEhKfiIE.js → tool-waste-BqSmmPUz.js} +2 -2
- package/dist/{tool-waste-DEhKfiIE.js.map → tool-waste-BqSmmPUz.js.map} +1 -1
- package/dist/trace-repair/index.js +1 -1
- package/dist/{tree-B2y1UR8o.js → tree-C-N2kP-8.js} +4 -4
- package/dist/{tree-B2y1UR8o.js.map → tree-C-N2kP-8.js.map} +1 -1
- package/dist/{types-BwF--ZRz.d.ts → types-BsdcSWnf.d.ts} +2 -2
- package/dist/{types-BwF--ZRz.d.ts.map → types-BsdcSWnf.d.ts.map} +1 -1
- package/dist/{types-BAJ2Hb-d.d.ts → types-DUVhW5V1.d.ts} +2 -2
- package/dist/{types-BAJ2Hb-d.d.ts.map → types-DUVhW5V1.d.ts.map} +1 -1
- package/dist/{types-CeMZYsNF.d.ts → types-ip2D3-Ib.d.ts} +2 -2
- package/dist/{types-CeMZYsNF.d.ts.map → types-ip2D3-Ib.d.ts.map} +1 -1
- package/dist/wire/index.d.ts +2 -2
- package/docs/design/statistics-decisions.md +7 -0
- package/package.json +1 -1
- package/dist/statistics-DCZIC-qT.js.map +0 -1
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { c as RunSplitTag } from "./run-record-D2BFMPGl.js";
|
|
2
|
-
import { R as Scenario, d as DispatchContext } from "./types-
|
|
2
|
+
import { R as Scenario, d as DispatchContext } from "./types-ip2D3-Ib.js";
|
|
3
3
|
type BenchmarkTaskKind = 'retrieval' | 'rag-answer' | 'hallucination' | 'kb-improvement' | 'routing' | 'custom';
|
|
4
4
|
type BenchmarkFamily = 'beir' | 'mteb-retrieval' | 'msmarco' | 'trec-dl' | 'miracl' | 'lotte' | 'bright' | 'crag' | 'hotpotqa' | 'kilt' | 'ragtruth' | 'faithbench' | 'first-party' | 'custom';
|
|
5
5
|
interface BenchmarkDatasetItem<TPayload = unknown> {
|
|
@@ -97,4 +97,4 @@ declare const BENCHMARK_SPLIT_SEED = "agent-eval-v1";
|
|
|
97
97
|
*/
|
|
98
98
|
declare function deterministicSplit(itemId: string, seed?: string): RunSplitTag;
|
|
99
99
|
export { BenchmarkFamily as a, BenchmarkSource as c, BenchmarkEvaluation as i, BenchmarkTaskKind as l, BenchmarkAdapter as n, BenchmarkResponder as o, BenchmarkDatasetItem as r, BenchmarkScenario as s, BENCHMARK_SPLIT_SEED as t, deterministicSplit as u };
|
|
100
|
-
//# sourceMappingURL=types-
|
|
100
|
+
//# sourceMappingURL=types-BsdcSWnf.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types-
|
|
1
|
+
{"version":3,"file":"types-BsdcSWnf.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;;EAEA;EACA;EACA;;EAEA;;;;;EAKA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
import {
|
|
1
|
+
import { ht as SeriesDistribution } from "./index-DNXFzSpc.js";
|
|
2
2
|
import { C as RolloutWorkspaceCapture, h as RolloutLine } from "./schema-PDKQ_iNE.js";
|
|
3
3
|
/** A metric that could not be computed, with the reason its artifact was missing. */
|
|
4
4
|
interface Unavailable {
|
|
@@ -563,4 +563,4 @@ interface SupervisorRunTreeGap {
|
|
|
563
563
|
readonly count?: number;
|
|
564
564
|
}
|
|
565
565
|
export { WorkerTurnCoverage as A, SupervisorRunTreeGapCode as C, WallDistribution as D, Unavailable as E, showMeasured as M, unavailable as N, WorkerLogSource as O, SupervisorRunTreeGap as S, TerminalFailure as T, SupervisorRunReader as _, OrchestrationMetrics as a, SupervisorRunSources as b, PerWorkerRow as c, RollupCellRow as d, SourceLimits as f, SupervisorRunNodeRole as g, SteerBreakdown as h, NamedResourceReceipt as i, isUnavailable as j, WorkerNativeSession as k, ResourceSpendRecord as l, SpendMeasurements as m, EconomicsMetrics as n, OutcomeMetrics as o, SpendMeasurement as p, Measured as r, PatchStats as s, DecisionMetrics as t, RoleSpend as u, SupervisorRunReport as v, SupervisorStatusSource as w, SupervisorRunTree as x, SupervisorRunRollup as y };
|
|
566
|
-
//# sourceMappingURL=types-
|
|
566
|
+
//# sourceMappingURL=types-DUVhW5V1.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types-
|
|
1
|
+
{"version":3,"file":"types-DUVhW5V1.d.ts","names":[],"sources":["../src/supervisor-run/types.ts"],"mappings":";;;UAkCiB;WACN;;;KAIC,SAAS,KAAK,IAAI;iBAEd,YAAY,iBAAiB;iBAI7B,cAAc,aAAa,KAAK;;iBAKhC,aAAa,GAAG;;KAWpB;;UAGK;WACN;WACA;;;KAIC;WAEG;WACA;;;WAGA;;;;WAIA;;WAEA;WAAgC;;;;;;UAM9B;;;;;WAKN;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;;;;WAMA,QAAQ;;;;;;WAMR,gBAAgB;;WAEhB,6BAA6B;;WAE7B;;WAEA;WACA;WACA;WACA;;;;;;;;;;;;;UAcM;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;;;;;;;;;;;UAqBM;;WAEN;WACA;;WAEA;;WAEA;;;;;;WAMA;;;;;;WAMA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA,kBAAkB;;WAElB;;;;WAIA;;;;;;WAMA;;;;;;;WAOA;;WAEA;;WAEA;;WAEA;;;;;;WAMA;;;;;WAKA;IACP;IACA;IACA;IACA;;IAEA;IACA;;WAEO;;WAEA,QAAQ;;;;;WAKR;;WAEA,iCAAiC;;;;;WAKjC;;;;;;UAOM;;WAEN;EACT,QAAQ,QAAQ;;cAOL;cACA;UAEI;;WAEN;WACA;;WAEA;;WAEA;;UAGM;WACN,gBAAgB;WAChB,gBAAgB;WAChB,kBAAkB;;WAElB,QAAQ;WACR,iBAAiB;WACjB,gBAAgB,kBAAkB;;WAElC,kBAAkB;;;;;;WAMlB,OAAO;WACP,WAAW;WACX,gBAAgB;;WAEhB,UAAU;;WAEV,gBAAgB;;WAEhB,iBAAiB;WACjB,oBAAoB;WACpB,kBAAkB;;;;;;;;;WASlB,sBAAsB;;WAEtB,QAAQ;WACR,SAAS;;WAET,mBAAmB;;UAGb;WACN,iBAAiB,SAAS;WAC1B,iBAAiB,SAAS;;;;;;;WAO1B,UAAU;;WAEV,UAAU;;WAEV,WAAW;;WAEX,oBAAoB;;WAEpB,wBAAwB;;WAExB,eAAe;WACf,qBAAqB;;UAGf;WACN,UAAU;WACV,WAAW;;;;;;WAMX,WAAW;WACX,YAAY;WACZ,KAAK;WACL;;UAGM;;WAEN;WACA;;WAEA,MAAM;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;WACA;;WAEA;WACA;WACA;WACA;WACA;;WAEA;;WAEA,4BAA4B;;;;;;;KAQ3B,mBAAmB;;UAGd;WACN,KAAK;;WAEL;;;;;;;WAOA;;WAEA;;WAEA;;;;;;;;;;;;;UAcM;WACN,gBAAgB;WAChB,aAAa;;;UAIP;WACN,MAAM;WACN,MAAM;WACN,QAAQ;WACR,OAAO;;;UAID;WACN;WACA;WACA;WACA,WAAW,kBAAkB;;UAGvB;;WAEN,kBAAkB,kBAAkB;;WAEpC,OAAO;;;;;;;;WAQP,kBAAkB;;WAElB,SAAS;;WAET,OAAO;;;;;;;;WAQP,UAAU;;;;;;WAMV;WACA,yBAAyB;WACzB,0BAA0B,SAAS;WACnC,WAAW,kBAAkB;;UAGvB;WACN;WACA;WACA;WACA;;;KAIC;;;;;;UAOK;;;;;WAKN;;WAEA;;WAEA;;WAEA;;;;;;;;WAQA;;UAGM;;;;;;WAMN,WAAW;WACX,iBAAiB,SAAS;;;;;;WAM1B,WAAW;;;;;;;WAOX,SAAS,SAAS;WAClB,YAAY;WACZ,WAAW;WACX,eAAe;WACf,YAAY;WACZ,aAAa;WACb,YAAY;WACZ,YAAY;WACZ,UAAU;WACV,OAAO,SAAS;;WAEhB;;UAGM;WACN,eAAe;;WAEf;WACA;WACA;WACA,cAAc;WACd,yBAAyB;WACzB;WACA,eAAe;WACf,UAAU;WACV,WAAW;WACX,SAAS;;WAET,gCAAgC;;WAEhC;;WAEA;;UAGM;;WAEN,kBAAkB,kBAAkB;WACpC;WACA;WACA,QAAQ;WACR,OAAO;WACP,aAAa;WACb,SAAS;WACT,UAAU;WACV,KAAK;;UAGC;WACN,eAAe;WACf;WACA,aAAa;WACb,iBAAiB;WACjB;WACA,WAAW;WACX,mBAAmB;WACnB,iBAAiB;WACjB,aAAa;WACb,qBAAqB;WACrB,eAAe;;;;;WAKf,UAAU;;;;;;;WAOV;aACE;eAA2B,OAAO;eAA2B;;aAC7D;eAAwB,OAAO;eAA2B;;;WAE5D,eAAe;WACf,kBAAkB;;;;;;;;UASZ;WACN;WACA,gBAAgB;;WAEhB,eAAe;;;KAId;UAWK;WACN,MAAM;WACN;WACA;WACA"}
|
|
@@ -2,7 +2,7 @@ import { g as PaidCallResult, i as CostChannel, l as CostLedgerSummary, o as Cos
|
|
|
2
2
|
import { a as RunRecord, d as RunTokenUsage, s as RunSearchCoordinates } from "./run-record-D2BFMPGl.js";
|
|
3
3
|
import { v as ProposalFinding } from "./types-kBMNdo1X.js";
|
|
4
4
|
import { R as LlmCallMetadata } from "./cluster-Cd0MRbr9.js";
|
|
5
|
-
import {
|
|
5
|
+
import { ht as SeriesDistribution } from "./index-DNXFzSpc.js";
|
|
6
6
|
import { A as SearchLedgerHash, F as SearchNodeRegisteredEvent, G as SearchSplit, I as SearchNodeStatus, L as SearchOpenedEvent, N as SearchNodeDecision, O as SearchLedgerEntry, P as SearchNodeRef, Q as SearchTaskOutcome, R as SearchOperationKind, U as SearchReservation, Z as SearchTask, b as SearchClosedEvent, d as SearchCellCancelledEvent, i as SearchArtifactRef, l as SearchCandidateSurface, o as SearchAudit, p as SearchCellStage, t as NodeEstimate, w as SearchEdgeRecordedEvent, z as SearchOperationRecordedEvent } from "./search-ledger-types-qiYRUo_N.js";
|
|
7
7
|
import { y as LedgerProjector } from "./index-lRKqfyg4.js";
|
|
8
8
|
import { s as TraceStore } from "./store-CMs5wGXP.js";
|
|
@@ -1078,4 +1078,4 @@ interface CampaignResult<TArtifact = unknown, TScenario extends Scenario = Scena
|
|
|
1078
1078
|
scenarios: Array<CampaignScenarioIdentity & Pick<TScenario, 'id' | 'kind'>>;
|
|
1079
1079
|
}
|
|
1080
1080
|
export { MintRolloutResult as $, LabeledScenarioWrite as A, ScoredSurfaceOutcome as B, JudgeDimension as C, LabeledScenarioSampleArgs as D, LabeledScenarioRecord as E, ProposeContext as F, SearchProposerView as G, SurfaceProposer as H, ProposedCandidate as I, searchProposerView as J, SearchSummaryOptions as K, RedactionStatus as L, OptimizerConfig as M, ParetoParent as N, LabeledScenarioSource as O, ProposalTrackContext as P, MintRolloutOptions as Q, Scenario as R, JudgeConfig as S, LabelTrust as T, TraceSpan as U, SessionScript as V, isProposedCandidate as W, SearchStateView as X, SearchState as Y, searchUnitScores as Z, GateDecision as _, CampaignResult as a, SearchCompletion as at, GenerationRecord as b, CampaignTraceWriter as c, SearchOperation as ct, DispatchContext as d, SearchUnitScore as dt, RolloutScrubber as et, DispatchFn as f, searchCellId as ft, GateContribution as g, GateContext as h, CampaignCostMeter as i, SearchCell as it, MutableSurface as j, LabeledScenarioStore as k, CodeSurface as l, SearchScoredCell as lt, GateCheckStatus as m, searchTaskSetDigest as mt, CampaignArtifactWriter as n, mintRolloutRows as nt, CampaignScenarioIdentity as o, SearchDecisionRecord as ot, Gate as p, searchNodeId as pt, renderSearchSummary as q, CampaignCellResult as r, unmintableReasons as rt, CampaignTokenUsage as s, SearchNode as st, CampaignAggregates as t, RolloutSearchLineage as tt, ComponentSurface as u, SearchSpend as ut, GateResult as v, JudgeScore as w, JudgeAggregate as x, GenerationCandidate as y, ScenarioAggregate as z };
|
|
1081
|
-
//# sourceMappingURL=types-
|
|
1081
|
+
//# sourceMappingURL=types-ip2D3-Ib.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types-
|
|
1
|
+
{"version":3,"file":"types-ip2D3-Ib.d.ts","names":[],"sources":["../src/campaign/search-state-identity.ts","../src/campaign/search-state-types.ts","../src/campaign/search-state-indexes.ts","../src/rollout/mint.ts","../src/campaign/search-state-view.ts","../src/campaign/search-state-projection.ts","../src/campaign/search-summary.ts","../src/campaign/types.ts"],"mappings":";;;;;;;;;;;iBAOgB,aAAa,kBAAkB;;iBAK/B,aACd,kBACA,gBACA,gBACA,OAAO,aACP;;iBAMc,oBAAoB,gBAAgB,eAAe;UCHlD;EACf;EACA,UAAU;EACV,OAAO;EACP;EACA;;UAGe;EACf;EACA;EACA;EACA;;;;UAKe;EACf;EACA;EACA;EACA;;;UAIe;EACf;EACA;;EAEA;EACA;;UAGe;EACf;;EAEA;EACA,gBAAgB;EAChB,UAAU;EACV,mBAAmB;;;EAGnB;;EAEA;;;;EAIA,kBAAkB;EAClB;EACA;EACA,QAAQ;EACR;;EAEA;EACA,oBAAoB;EACpB;EACA,OAAO;EACP;EACA;;UAGe;EACf;EACA;EACA;EACA;EACA,OAAO;EACP;EACA,OAAO;EACP;EACA,aAAa;EACb;EACA;EACA,SAAS;;EAET;;EAEA;EACA,WAAW;;EAEX;;EAEA;EACA;EACA;EACA;;UAGe;EACf;EACA,eAAe;EACf,aAAa;EACb;;EAEA,SAAS;;;EAGT,WAAW;;;EAGX,oBAAoB;;EAEpB;;EAEA;;UAGe;EACf;EACA;;UAGe;EACf,OAAO;EACP;EACA;EACA;EACA;EACA,SAAS;EACT,YAAY;EACZ;EACA;EACA;EACA,WAAW;EACX;EACA;EACA;EACA,OAAO;;cCvII;WACF,OAAK;IAA4B,OAAA;IAAqB;;WACtD,OAAK,YAAA;WACL;WACA,cAAY;WACZ,OAAK,YAAA;WACL;WACA,OAAK,YAAA;WACL,YAAU,YAAA;EAEnB,KAAK,iBAAiB;EAKtB;EAIA,QAAQ;EAIR,gBAAgB;EAIhB,KAAK,iBAAiB;EAItB;EAIA,KAAK,iBAAiB;EAKtB,QAAQ;EAKR,UAAU,sBAAsB;EAKhC,YAAY,gBAAgB,OAAO,cAAc;;;KCZvC,mBAAmB;;UAGd;;EAEf;;EAEA;;EAEA;;;EAGA;;UAGe;EACf,QAAQ;;;;;;;EAOR,cACE,2BACY,4BAA4B,iBAAiB;;EAE3D,cACE;IAEI;IAAe,mBAAmB;kBAEpC;IAAU;IAAe,mBAAmB;;;EAEhD;;EAEA,OAAO;;EAEP;;EAEA,YAAY;;;;;;;;EAQZ,iBACE,QAAQ,yBACL,uBAAuB,QAAQ;;UAGrB;EACf,MAAM;;EAEN;;;;;;;;;;;;;;iBA4Pc,kBAAkB,QAAQ;;;;;;;iBAsMpB,gBACpB,SAAS,aACT,OAAO,YACP,UAAS,qBACR,QAAQ;;;;;;;iBClhBK,iBAAiB,gBAAgB,qBAAqB;;;;;;cAyBzD;WACF;WACA,QAAQ;WACR,QAAQ;WACR;IAAQ;IAAkB,WAAW;;;WAErC;WACA,OAAO;WACP,YAAY;;;;;;;WAOZ;IAAU;IAA4B;;mBAC9B;mBACA;EAEL,YAAA,OAAO,aAAa;;MAiB5B;EAIJ,KAAK,iBAAiB;EAItB,QAAQ;;EAKR;;EAKA,SAAS;EAKT,gBAAgB;EAIhB,KAAK,iBAAiB;;EAKtB,SAAS;EAKT,KAAK,iBAAiB;;EAKtB,MAAM;IAAU;MAAyB;EAKzC,UAAU,sBAAsB;;;EAMhC,YAAY,gBAAgB,OAAO,cAAc;;EAKjD,WAAW,gBAAgB,OAAO,cAAc;;EAKhD,QAAQ,aAAa,uBAAuB;UAmCpC;;;;;;;cCnJG,uBAAuB,gBAAgB,mBAAmB;WAC5D;UACD;UACA;UACA;UACA;UACA;UACA;UACA;;mBAES;;UAET;mBACS;mBACA;;WAER,OAAK;EAEF,YAAA;EAiCZ,MAAM,OAAO,mBAAmB;EA6BhC,YAAY;;EAKZ,KAAK;UAIG;UAgCA;UA6CA;UA2BA;UA8BA;UA8CA;UAsHA;UAwEA;UAyEA;UAiBA;UAmDA;UAaA;;;UA2EA;;EASR;;;EAmBA;IACE,QAAQ;IACR,QAAQ;IACR;MAAQ;MAAkB,WAAW;;IACrC;IACA,OAAO;IACP;MAAU;MAA4B;;;;;;UCjuBzB;WACN;WACA;;;EAGT,YAAY,0BAA0B;;EAEtC,WAAW,0BAA0B;;;iBAIvB,mBAAmB,OAAO,kBAAkB;UAW3C;;;;;;;;EAQf,OAAO;;EAEP;;;;;;;;;;;iBAYc,oBAAoB,OAAO,iBAAiB,SAAS;;;UCrCpD;EACf;EACA;EACA;;;;;EAKA;;;UAIe,iCAAiC,KAAK;EACrD;;;;;UAMe;EACf;;EAEA;EACA;EACA;EACA;EACA,QAAQ;EACR,OAAO;EACP,WAAW;EACX,MAAM;;EAEN;;EAEA;;;;;;;;EAQA;;;;KAKU,WAAW,kBAAkB,UAAU,cACjD,UAAU,WACV,KAAK,oBACF,QAAQ;;;;UAOI,cAAc,WAAW;EACxC;EACA;EACA;;EAEA;;;EAGA,sBAAsB,UAAU,WAAW,sBAAsB,UAAU,cAAc;;UAK1E;;EAEf;;EAEA;;;;;;;;;UAUe,YAAY,WAAW,kBAAkB,WAAW;EACnE;EACA,YAAY;;;;EAIZ;;;EAGA,MAAM;IACJ,UAAU;IACV,UAAU;IACV,QAAQ;;IAER,aAAa;IACb;IACA,WAAW;MACT,aAAa,QAAQ;EACzB,aAAa,UAAU;;;;;;;;;;;UAYR;EACf,YAAY;EACZ;EACA;;EAEA,UAAU;;;;;;;EAOV;;;;EAIA,eAAe,eAAe;IAAQ;IAAe;;;;;EAIrD;;;EAGA;;EAEA;;EAEA,WAAW,eAAe;;;;;;;UAUX;WACN;;;WAGA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;WAGA;aACE;aACA;aACA;;;WAGF;;;UAIM;WACN;WACA,YAAY,SAAS;;;;;;;;;;;KAYpB,0BAA0B,mBAAmB;;;;;;;UAQxC;EACf,SAAS;;EAET;;;;EAIA;;;;;;EAMA,cAAc,SAAS;;;;iBAKT,oBACd,OAAO,iBAAiB,oBACvB,SAAS;;;;;;;;;UAkBK;EACf,SAAS;EACT;;;EAGA,YAAY;;;EAGZ;;EAEA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA;;;;;UAMe;;;EAGf;;EAEA;EACA;EACA;EACA,YAAY;;;;;EAKZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;EAC1E;IACE;IACA;;;;;UAMa,eAAe,YAAY;;;;WAIjC,gBAAgB;;;;;WAKhB;;;;WAIA,UAAU;IAAgB;IAAgB,UAAU;;;;WAGpD,QAAQ;;;;WAIR;;;WAGA,SAAS,cAAc;WACvB,UAAU,cAAc;;WAExB;WACA;WACA,QAAQ;;WAER,QAAQ;;;WAGR,kBAAkB;;;WAGlB,mBAAmB;;;;WAInB,gBAAgB;;;;WAIhB;;;;;;;WAOA,gBAAgB,cAAc;;WAE9B,aAAa;WACb;;;;;;;;;;;;;;UAeM,gBAAgB,YAAY;EAC3C;;;;;EAKA,QAAQ,KAAK,eAAe,aAAa,QAAQ,MAAM,iBAAiB;;;EAGxE,QAAQ;IAAQ,SAAS,cAAc;;IAAwB;IAAe;;;UAGtE;EACR;EACA;EACA,mBAAmB,qBAAqB;;UAGzB,wBAAwB;EACvC,UAAU;;;KAMA;;KAGA;UAEK;EACf;EACA,QAAQ;EACR;;UAGe,YAAY,WAAW,kBAAkB;EACxD,oBAAoB,YAAY;EAChC,oBAAoB,YAAY;;EAEhC,aAAa,YAAY,eAAe;;;;;EAKxC,sBAAsB,YAAY,eAAe;;;;;;;EAOjD,yBAAyB,YAAY,eAAe;;;EAGpD,uBAAuB,YAAY;EACnC,WAAW;EACX;IAAQ;IAAmB;;;EAE3B,aAAa;EACb;EACA,QAAQ;;UAGO;EACf,UAAU;EACV;EACA,mBAAmB;EACnB;;;UAIe,KAAK,qBAAqB,kBAAkB,WAAW;EACtE;EACA,OAAO,KAAK,YAAY,WAAW,aAAa,QAAQ;;;;UAOzC;EACf,KAAK,cAAc,aAAa,0BAA0B;EAC1D,SAAS;;UAGM;EACf,IAAI,aAAa;EACjB,aAAa,aAAa;;;;;UAMX;EACf,MAAM,cAAc,kBAAkB,aAAa;EACnD,UAAU,cAAc,iBAAiB;;;;;;KAO/B,qBAAqB;;;;;UAMhB;;EAEf,YAAY,GACV,OAAO,KAAK,iBAAiB;IAC3B,UAAU;MAEX,QAAQ,eAAe;;;;;KAQhB;KAOA;;;;;;;;;;;;;;;KAgBA;;;;UAgBK,qBAAqB,kBAAkB,WAAW,UAAU;EAC3E,UAAU;EACV,UAAU;EACV,aAAa,eAAe;EAC5B,QAAQ;EACR;EACA;EACA,iBAAiB;;;;;EAKjB,aAAa;;EAEb;;UAGe,sBAAsB,kBAAkB,WAAW,UAAU,6BACpE,qBAAqB,WAAW;;EAExC;;;EAGA;;UAGe;EACf;;EAEA;;;;EAIA;EACA;IACE;IACA,SAAS,wBAAwB;IACjC;IACA;;;;;IAKA,WAAW;;;UAIE;EACf,QAAQ,OAAO,uBAAuB;EACtC,OAAO,MAAM,4BAA4B,QAAQ;EACjD,QAAQ;IACN;IACA;IACA,UAAU;;;IAGV,SAAS,OAAO;;;UAMH,mBAAmB;;EAElC,gBAAgB;;;EAGhB;EACA;;EAEA;IAAY;IAAsB;;EAClC;EACA;EACA;EACA,UAAU;EACV,aAAa,eAAe;;;EAG5B;;EAEA,gBAAgB;;EAEhB;;;EAGA,YAAY;;;EAGZ;;;EAGA;EACA;EACA;EACA;;;;EAIA;;EAEA;;EAEA;EACA;;UAGe;EACf;EACA;EACA;EACA;;;;;;EAMA,cAAc;;UAGC;EACf;EACA;EACA;;;EAGA,cAAc;;UAGC;EACf;EACA,YAAY;EACZ;;;;;;UAOe;EACf;;;;EAIA;;;;EAIA;;;;EAIA;IACE;IACA;IACA,iBAAiB;MAAQ;MAAgB;;;;;EAI3C,YAAY;;;;;;;;;;EAUZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;;;EAG1E;;;;EAIA;;;;EAIA,cAAc,SAAS;;UAGR;EACf,SAAS,eAAe;EACxB,YAAY,eAAe;;EAE3B,MAAM;;EAEN;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe,eAAe,qBAAqB,kBAAkB,WAAW;;EAEhF;;EAEA;EACA;;EAEA;EACA;EACA;EACA;EACA,OAAO,MAAM,mBAAmB;EAChC,YAAY;EACZ;IACE,aAAa;IACb;;EAEF,OAAO;EACP;EACA;EACA,iBAAiB;;;EAGjB,WAAW,MAAM,2BAA2B,KAAK"}
|
package/dist/wire/index.d.ts
CHANGED
|
@@ -267,10 +267,10 @@ export declare const FeedbackTrajectorySchema: z.ZodObject<{
|
|
|
267
267
|
metadata: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
|
|
268
268
|
}, z.core.$strip>>;
|
|
269
269
|
split: z.ZodOptional<z.ZodEnum<{
|
|
270
|
-
train: "train";
|
|
271
270
|
dev: "dev";
|
|
272
|
-
test: "test";
|
|
273
271
|
holdout: "holdout";
|
|
272
|
+
train: "train";
|
|
273
|
+
test: "test";
|
|
274
274
|
}>>;
|
|
275
275
|
tags: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
|
|
276
276
|
createdAt: z.ZodString;
|
|
@@ -38,3 +38,10 @@ including winsorization and failure scoring. Hourly windows exclude sealed steps
|
|
|
38
38
|
72 hours or 39 eligible boundaries yields `uncalibrated` with null bounds. It returns K, n,
|
|
39
39
|
boundaries and deltas; bounds invert as `[delta - q975, delta - q025]`.
|
|
40
40
|
The [recorded contract](../../tests/cluster-recorded.integration.test.ts) labels constructed replay; callers validate cadence, cell, coverage, clusters and estimator.
|
|
41
|
+
|
|
42
|
+
`independentRiskDifference(beforeSuccesses, beforeN, afterSuccesses, afterN, confidence)`
|
|
43
|
+
combines the existing Wilson limits with Newcombe's method 10 (no continuity correction).
|
|
44
|
+
It returns after-minus-before `delta`, `lower`, `upper`, confidence and both counted arms;
|
|
45
|
+
either empty arm gives a null delta and full difference support. This interval assumes
|
|
46
|
+
independent binomial observations; repeated attempts do not become independent trials.
|
|
47
|
+
Reference: [Newcombe (1998), method 10 and Table II](https://doi.org/10.1002/(SICI)1097-0258(19980430)17:8%3C873::AID-SIM779%3E3.0.CO;2-I).
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@tangle-network/agent-eval",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.21",
|
|
4
4
|
"description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
|
|
5
5
|
"homepage": "https://github.com/tangle-network/agent-eval#readme",
|
|
6
6
|
"repository": {
|