@tangle-network/agent-eval 0.220.2 → 0.221.1
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 +64 -0
- package/dist/adapters/http.d.ts +2 -2
- package/dist/{agent-profile-D01Io2Xw.d.ts → agent-profile-Bc7ADJY4.d.ts} +2 -2
- package/dist/{agent-profile-D01Io2Xw.d.ts.map → agent-profile-Bc7ADJY4.d.ts.map} +1 -1
- package/dist/analyst/index.d.ts +77 -78
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +204 -25
- package/dist/analyst/index.js.map +1 -1
- package/dist/{analyze-runs-DqPJaJ4X.js → analyze-runs-CHmsykNJ.js} +4 -4
- package/dist/{analyze-runs-DqPJaJ4X.js.map → analyze-runs-CHmsykNJ.js.map} +1 -1
- package/dist/{analyze-runs-BWAHBDAw.d.ts → analyze-runs-D7In4c3z.d.ts} +2 -2
- package/dist/{analyze-runs-BWAHBDAw.d.ts.map → analyze-runs-D7In4c3z.d.ts.map} +1 -1
- package/dist/{benchmark-command-Dx0E4a6z.js → benchmark-command-DiGqnGUt.js} +13 -11
- package/dist/benchmark-command-DiGqnGUt.js.map +1 -0
- package/dist/benchmarks/index.d.ts +4 -4
- package/dist/benchmarks/index.js +3 -3
- package/dist/calibration-CTwxpJ-t.js +197 -0
- package/dist/calibration-CTwxpJ-t.js.map +1 -0
- package/dist/campaign/index.d.ts +6 -6
- package/dist/campaign/index.js +5 -5
- package/dist/{campaign-BVPC6ODQ.js → campaign-Bt6rbWIU.js} +9 -8
- package/dist/{campaign-BVPC6ODQ.js.map → campaign-Bt6rbWIU.js.map} +1 -1
- package/dist/cli.js +1 -1
- package/dist/{completion-verifier-Cigap8CG.js → completion-verifier-YwoeujPl.js} +2 -2
- package/dist/completion-verifier-YwoeujPl.js.map +1 -0
- package/dist/contract/index.d.ts +10 -10
- package/dist/contract/index.js +7 -7
- package/dist/decision-point-Co3u3W8k.js +831 -0
- package/dist/decision-point-Co3u3W8k.js.map +1 -0
- package/dist/default-registry-BMHqNR6_.d.ts +257 -0
- package/dist/default-registry-BMHqNR6_.d.ts.map +1 -0
- package/dist/{default-registry-ovrIBGmH.js → default-registry-BbFCkqvB.js} +607 -14
- package/dist/default-registry-BbFCkqvB.js.map +1 -0
- package/dist/{define-agent-eval-C2nFhHPu.d.ts → define-agent-eval-Bsoi2GUV.d.ts} +7 -7
- package/dist/{define-agent-eval-C2nFhHPu.d.ts.map → define-agent-eval-Bsoi2GUV.d.ts.map} +1 -1
- package/dist/{define-agent-eval-UQY3VbJ2.js → define-agent-eval-CJhECJNL.js} +4 -4
- package/dist/{define-agent-eval-UQY3VbJ2.js.map → define-agent-eval-CJhECJNL.js.map} +1 -1
- package/dist/diagnosis/index.d.ts +2 -2
- package/dist/diagnosis/index.js +1 -1
- package/dist/{dspy-rlm-engine-Bn_Mt_LW.js → dspy-rlm-engine-BTy7u0jQ.js} +3 -3
- package/dist/{dspy-rlm-engine-Bn_Mt_LW.js.map → dspy-rlm-engine-BTy7u0jQ.js.map} +1 -1
- package/dist/{engine-BpGGw6cd.d.ts → engine-BF95CWzH.d.ts} +2 -2
- package/dist/{engine-BpGGw6cd.d.ts.map → engine-BF95CWzH.d.ts.map} +1 -1
- package/dist/{eval-campaign-BUMIxKTE.js → eval-campaign-DoX5vz3E.js} +2 -2
- package/dist/{eval-campaign-BUMIxKTE.js.map → eval-campaign-DoX5vz3E.js.map} +1 -1
- package/dist/{evaluation-CBdQt_kr.d.ts → evaluation-D1PGzkPR.d.ts} +3 -3
- package/dist/{evaluation-CBdQt_kr.d.ts.map → evaluation-D1PGzkPR.d.ts.map} +1 -1
- package/dist/evaluation-wdGyZ7jV.js +147 -0
- package/dist/evaluation-wdGyZ7jV.js.map +1 -0
- package/dist/evaluation.d.ts +1 -1
- package/dist/evaluation.js +1 -136
- package/dist/{exact-types-BYFmYq44.d.ts → exact-types-CVn1QxFO.d.ts} +2 -2
- package/dist/{exact-types-BYFmYq44.d.ts.map → exact-types-CVn1QxFO.d.ts.map} +1 -1
- package/dist/experiment/index.d.ts +3 -3
- package/dist/experiment/index.js +2 -2
- package/dist/{external-optimizer-process-wOLfzsCC.js → external-optimizer-process-E5yY2SYS.js} +2 -2
- package/dist/{external-optimizer-process-wOLfzsCC.js.map → external-optimizer-process-E5yY2SYS.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-D670Oxf2.js → external-optimizer-subprocess-DA02c_L6.js} +12 -19
- package/dist/{external-optimizer-subprocess-D670Oxf2.js.map → external-optimizer-subprocess-DA02c_L6.js.map} +1 -1
- package/dist/{feedback-trajectory-DhB9WzYg.d.ts → feedback-trajectory-BZhVCWuz.d.ts} +3 -3
- package/dist/{feedback-trajectory-DhB9WzYg.d.ts.map → feedback-trajectory-BZhVCWuz.d.ts.map} +1 -1
- package/dist/finding-composition-8n0fFgVI.js +131 -0
- package/dist/finding-composition-8n0fFgVI.js.map +1 -0
- package/dist/{findings-store-CvNo712L.js → findings-store-DRiFdoid.js} +4 -4
- package/dist/{findings-store-CvNo712L.js.map → findings-store-DRiFdoid.js.map} +1 -1
- package/dist/{index-CVFStrQD.d.ts → index-BJZ7s-sv.d.ts} +7 -58
- package/dist/index-BJZ7s-sv.d.ts.map +1 -0
- package/dist/{index-Q6DvdcwI.d.ts → index-BvX3CFNS.d.ts} +6 -6
- package/dist/{index-Q6DvdcwI.d.ts.map → index-BvX3CFNS.d.ts.map} +1 -1
- package/dist/index-DWd1gUwR.d.ts +1086 -0
- package/dist/index-DWd1gUwR.d.ts.map +1 -0
- package/dist/{index-DAXfpVf7.d.ts → index-y7i8l6Y_.d.ts} +8 -8
- package/dist/{index-DAXfpVf7.d.ts.map → index-y7i8l6Y_.d.ts.map} +1 -1
- package/dist/index.d.ts +18 -17
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +15 -15
- package/dist/{kind-factory-BhxbtUsQ.js → kind-factory-Dl0PmNQL.js} +2 -2
- package/dist/{kind-factory-BhxbtUsQ.js.map → kind-factory-Dl0PmNQL.js.map} +1 -1
- package/dist/{llm-judge-Cc8vDJh_.js → llm-judge-3uAeRawE.js} +4 -4
- package/dist/{llm-judge-Cc8vDJh_.js.map → llm-judge-3uAeRawE.js.map} +1 -1
- package/dist/{matrix-Cf-AGxGh.d.ts → matrix-BXo3PSqM.d.ts} +2 -2
- package/dist/{matrix-Cf-AGxGh.d.ts.map → matrix-BXo3PSqM.d.ts.map} +1 -1
- package/dist/meta-eval/index.d.ts +3 -638
- package/dist/meta-eval/index.js +3 -193
- package/dist/meta-eval/index.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/outcome-observations-FLmRpgYa.js +78 -0
- package/dist/outcome-observations-FLmRpgYa.js.map +1 -0
- package/dist/{paired-arms-Ct4LTKc1.js → paired-arms-B2ttLc0_.js} +108 -31
- package/dist/paired-arms-B2ttLc0_.js.map +1 -0
- package/dist/{power-and-mde-N5nU4_Ly.js → power-and-mde-CQX-0weG.js} +2 -2
- package/dist/{power-and-mde-N5nU4_Ly.js.map → power-and-mde-CQX-0weG.js.map} +1 -1
- package/dist/{prime-protocol-CckHBxGu.d.ts → prime-protocol-BEaqBoQE.d.ts} +2 -2
- package/dist/{prime-protocol-CckHBxGu.d.ts.map → prime-protocol-BEaqBoQE.d.ts.map} +1 -1
- package/dist/{proposal-findings-E1aSC_cU.js → proposal-findings-D0_zkQ2l.js} +2 -2
- package/dist/{proposal-findings-E1aSC_cU.js.map → proposal-findings-D0_zkQ2l.js.map} +1 -1
- package/dist/{registry-B_yG-1jh.d.ts → registry-DDKaUrmM.d.ts} +3 -3
- package/dist/{registry-B_yG-1jh.d.ts.map → registry-DDKaUrmM.d.ts.map} +1 -1
- package/dist/reporting.d.ts +1 -1
- package/dist/reporting.js +3 -3
- package/dist/rl.d.ts +4 -5
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +5 -4
- package/dist/rl.js.map +1 -1
- package/dist/{rubric-predictive-validity-noY7uE03.d.ts → rubric-predictive-validity-Cd5SCtAf.d.ts} +58 -3
- package/dist/rubric-predictive-validity-Cd5SCtAf.d.ts.map +1 -0
- package/dist/{rubric-predictive-validity-D3_oI72N.js → rubric-predictive-validity-CeKW2GQN.js} +3 -77
- package/dist/rubric-predictive-validity-CeKW2GQN.js.map +1 -0
- package/dist/search/index.d.ts +2 -2
- package/dist/{search-kernel-Dloxd6gs.d.ts → search-kernel-C6__V0IS.d.ts} +2 -2
- package/dist/{search-kernel-Dloxd6gs.d.ts.map → search-kernel-C6__V0IS.d.ts.map} +1 -1
- package/dist/{skillopt-optimization-method-DLKqdhcR.js → skillopt-optimization-method-D21dH_Bh.js} +4 -4
- package/dist/{skillopt-optimization-method-DLKqdhcR.js.map → skillopt-optimization-method-D21dH_Bh.js.map} +1 -1
- package/dist/{statistical-heldout-3z3I-kJN.d.ts → statistical-heldout-pD1Yah-0.d.ts} +58 -8
- package/dist/statistical-heldout-pD1Yah-0.d.ts.map +1 -0
- package/dist/{store-otlp-dyWE3wAG.js → store-otlp-BVZfR168.js} +2 -2
- package/dist/{store-otlp-dyWE3wAG.js.map → store-otlp-BVZfR168.js.map} +1 -1
- package/dist/{store-tool-spans-DIUgZbzu.js → store-tool-spans-CjYiF4fF.js} +3 -3
- package/dist/{store-tool-spans-DIUgZbzu.js.map → store-tool-spans-CjYiF4fF.js.map} +1 -1
- package/dist/{store-tool-spans-DPwXHQkH.d.ts → store-tool-spans-DfnwWMFR.d.ts} +4 -4
- package/dist/{store-tool-spans-DPwXHQkH.d.ts.map → store-tool-spans-DfnwWMFR.d.ts.map} +1 -1
- package/dist/{summary-report-BsXJoYX5.js → summary-report-DHDWxe6p.js} +3 -3
- package/dist/{summary-report-BsXJoYX5.js.map → summary-report-DHDWxe6p.js.map} +1 -1
- package/dist/systemone-D3MrW63C.d.ts +400 -0
- package/dist/systemone-D3MrW63C.d.ts.map +1 -0
- package/dist/{systemone-protocol-DKoi1NdK.d.ts → systemone-protocol-Bl2EI2KQ.d.ts} +4 -2
- package/dist/{systemone-protocol-DKoi1NdK.d.ts.map → systemone-protocol-Bl2EI2KQ.d.ts.map} +1 -1
- package/dist/systemone-protocol.d.ts +2 -2
- package/dist/systemone-protocol.js +7 -7
- package/dist/systemone-protocol.js.map +1 -1
- package/dist/{systemone-review-CUBMuTLi.d.ts → systemone-review-C8DRiT_-.d.ts} +3 -3
- package/dist/{systemone-review-CUBMuTLi.d.ts.map → systemone-review-C8DRiT_-.d.ts.map} +1 -1
- package/dist/{systemone-review-DzdOJ8I6.js → systemone-review-DFGtIUcf.js} +2 -2
- package/dist/{systemone-review-DzdOJ8I6.js.map → systemone-review-DFGtIUcf.js.map} +1 -1
- package/dist/systemone.d.ts +5 -5
- package/dist/systemone.js +5 -343
- package/dist/{tool-groups-LISbBWCg.d.ts → tool-groups-DK1bu5TD.d.ts} +3 -3
- package/dist/tool-groups-DK1bu5TD.d.ts.map +1 -0
- package/dist/{trace-questions-C42fYEE4.d.ts → trace-questions-D_OKYZ6u.d.ts} +3 -3
- package/dist/{trace-questions-C42fYEE4.d.ts.map → trace-questions-D_OKYZ6u.d.ts.map} +1 -1
- package/dist/trace-repair/index.d.ts +1 -1
- package/dist/traces.d.ts +3 -3
- package/dist/traces.js +3 -3
- package/dist/{types-DqFMNTgK.js → types-CnWmj8NW.js} +19 -6
- package/dist/types-CnWmj8NW.js.map +1 -0
- package/dist/{types-CHfn1zg5.d.ts → types-DDKfH-N6.d.ts} +2 -2
- package/dist/{types-CHfn1zg5.d.ts.map → types-DDKfH-N6.d.ts.map} +1 -1
- package/dist/{types-8yQzNm8u.d.ts → types-DGImvHIr.d.ts} +150 -4
- package/dist/types-DGImvHIr.d.ts.map +1 -0
- package/dist/{types-D8GXK9Z5.d.ts → types-IERw_HxR.d.ts} +2 -2
- package/dist/{types-D8GXK9Z5.d.ts.map → types-IERw_HxR.d.ts.map} +1 -1
- package/dist/wire/index.d.ts +1 -1
- package/docs/behavioral-trace-questions.md +99 -0
- package/docs/experiment.md +27 -0
- package/docs/finding-layers.md +54 -1
- package/docs/systemone.md +107 -0
- package/package.json +4 -4
- package/dist/benchmark-command-Dx0E4a6z.js.map +0 -1
- package/dist/completion-verifier-Cigap8CG.js.map +0 -1
- package/dist/default-registry-Cwg_QN3d.d.ts +0 -70
- package/dist/default-registry-Cwg_QN3d.d.ts.map +0 -1
- package/dist/default-registry-ovrIBGmH.js.map +0 -1
- package/dist/evaluation.js.map +0 -1
- package/dist/index-CVFStrQD.d.ts.map +0 -1
- package/dist/judge-gate-Dc_mXQsL.d.ts +0 -453
- package/dist/judge-gate-Dc_mXQsL.d.ts.map +0 -1
- package/dist/meta-eval/index.d.ts.map +0 -1
- package/dist/outcome-store-CNt4iZ67.d.ts +0 -58
- package/dist/outcome-store-CNt4iZ67.d.ts.map +0 -1
- package/dist/paired-arms-Ct4LTKc1.js.map +0 -1
- package/dist/rubric-predictive-validity-D3_oI72N.js.map +0 -1
- package/dist/rubric-predictive-validity-noY7uE03.d.ts.map +0 -1
- package/dist/statistical-heldout-3z3I-kJN.d.ts.map +0 -1
- package/dist/systemone-DVA7t76V.d.ts +0 -135
- package/dist/systemone-DVA7t76V.d.ts.map +0 -1
- package/dist/systemone.js.map +0 -1
- package/dist/tool-groups-LISbBWCg.d.ts.map +0 -1
- package/dist/types-8yQzNm8u.d.ts.map +0 -1
- package/dist/types-DqFMNTgK.js.map +0 -1
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { u as CostProvenance } from "./cost-ledger-C1W3ICmP.js";
|
|
2
|
-
import { C as JudgeDimension, w as JudgeScore } from "./types-
|
|
2
|
+
import { C as JudgeDimension, w as JudgeScore } from "./types-DDKfH-N6.js";
|
|
3
3
|
import { o as MatrixResult } from "./index-CHxwfW5g.js";
|
|
4
4
|
import { AgentProfile } from "@tangle-network/agent-interface";
|
|
5
5
|
//#region src/multishot/types.d.ts
|
|
@@ -389,4 +389,4 @@ interface RunMultishotMatrixResult {
|
|
|
389
389
|
declare function runMultishotMatrix<TPersona extends MultishotPersona>(opts: RunMultishotMatrixOptions<TPersona>): Promise<RunMultishotMatrixResult>;
|
|
390
390
|
//#endregion
|
|
391
391
|
export { MultishotTransportRequest as A, MultishotMessage as C, MultishotToolDefinition as D, MultishotShape as E, MultishotTransportToolCall as M, assertMultishotShotResult as N, MultishotToolExecutor as O, MultishotFatalToolError as S, MultishotResult as T, renderDimensions as _, MultishotCellOutput as a, MultishotArtifact as b, RunMultishotMatrixResult as c, MultishotShot as d, RunMultishotOptions as f, MultishotJudgeConfig as g, JudgeRunResult as h, ConversationJudgeInput as i, MultishotTransportResponse as j, MultishotTransport as k, computeCellComposite as l, DEFAULT_JUDGE_MODEL as m, CellCompositeInput as n, MultishotJudges as o, runMultishot as p, CellCompositeScore as r, RunMultishotMatrixOptions as s, ArtifactJudgeInput as t, runMultishotMatrix as u, renderJsonFooter as v, MultishotPersona as w, MultishotDriverEmptyError as x, runJudge as y };
|
|
392
|
-
//# sourceMappingURL=matrix-
|
|
392
|
+
//# sourceMappingURL=matrix-BXo3PSqM.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"matrix-
|
|
1
|
+
{"version":3,"file":"matrix-BXo3PSqM.d.ts","names":[],"sources":["../src/multishot/types.ts","../src/multishot/judges.ts","../src/multishot/multishot.ts","../src/multishot/matrix.ts"],"mappings":";;;;;UAIiB;EACf;EACA;EACA;EACA,YAAY;IAAQ;IAAY;IAAc,MAAM;;;UAGrC;EACf;EACA;EACA;IAAc;IAAc,MAAM;;EAClC;;UAGe;EACf,YAAY;EACZ,WAAW;EACX;EACA;;;EAGA;;;;;;;;EAQA,iBAAiB;;UAGF;EACf;EACA;IACE;IACA;IACA,YAAY;;;;;;UAOC;EACf;EACA,UAAU,MAAM;EAChB,QAAQ;EACR;EACA;EACA,SAAS;;UAGM;EACf;EACA;EACA;IAAY;IAAc;;;UAGX;EACf;IAAW;IAAyB,aAAa;;EACjD;IAAU;IAAwB;;;;EAGlC;;;;EAIA;;;;;;;;KASU,sBACV,KAAK,8BACF,QAAQ;KAED,yBACV,MAAM,yBACN;;EAEE,WAAW;EACX,SAAS;MAER;EAAU;EAAiB;;UAEf;;EAEf;;GAEC;;;;;;;;UASc,eAAe,iBAAiB;;EAE/C,eAAe,SAAS;;;EAGxB,2BAA2B,SAAS;;cAGzB,kCAAkC;WACjB;EAA5B,YAA4B;;cAMjB,gCAAgC;EAC3C,YAAY;;;;;;;;;;;;;;;;;;;iBAgCE,0BAA0B,yBAAyB,SAAS;;;cCvI/D;UAEI,qBAAqB;;EAEpC;;;EAGA,WAAW;;EAEX;;EAEA,YAAY;;EAEZ;;;EAGA,cAAc,OAAO;;EAErB;;UAGe;;EAEf,OAAO;;EAEP,MAAM;;iBAGc,SAAS,QAC7B,OAAO,qBAAqB,SAC5B,OAAO,SACN,QAAQ;;;iBAsIK,iBAAiB,eAAe;;iBAKhC,iBAAiB,eAAe;;;UCjK/B,oBAAoB,iBAAiB;EACpD,SAAS;EACT,SAAS;;;EAGT,QAAQ,eAAe;;EAEvB,QAAQ;;EAER,gBAAgB,eAAe;;;;EAI/B,mBAAmB;EACnB;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;;EAGA,gBAAgB;;;;EAIhB,iBAAiB;;;EAGjB,gBAAgB;EAChB,SAAS;;;;;;;;;;;KAYC,cAAc,iBAAiB,qBACzC,MAAM,oBAAoB,cACvB,QAAQ;;;;;;;;;;;;;;;;;iBA2BS,aAAa,iBAAiB,kBAClD,MAAM,oBAAoB,YACzB,QAAQ;;;UClFM,uBAAuB,iBAAiB;EACvD,YAAY;EACZ,SAAS;;UAGM,mBAAmB,iBAAiB;EACnD,UAAU;EACV,SAAS;;UAGM,gBAAgB,iBAAiB;;EAEhD,cAAc,qBAAqB,uBAAuB;;EAE1D,aAAa,qBAAqB,mBAAmB;;EAErD,iBAAiB,qBAAqB,mBAAmB;;EAEzD;;EAEA;;UAGe;EACf;EACA,cAAc;EACd;IACE,aAAa,MAAM;MAAe;MAAc;;IAChD;;EAEF;IACE,aAAa,MAAM;MAAe;MAAc;;IAChD;;;UAIa,0BAA0B,iBAAiB;;EAE1D,UAAU;IAAQ;IAAY,OAAO;;;EAErC,UAAU;;;EAGV,QAAQ,eAAe;;EAEvB,QAAQ,gBAAgB;;EAExB,QAAQ;;EAER,gBAAgB,eAAe;;EAE/B,mBAAmB;;EAEnB;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;;;EAIA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;;;EAIA,gBAAgB;;EAEhB,iBAAiB;;;EAGjB,gBAAgB;;;;;;;;;;;;;;;EAehB,UAAU,cAAc;;;;;UAMT;EACf;EACA;EACA;;UAoBe;EACf,cAAc;;EAEd,cAAc,cAAc;;EAE5B,iBAAiB,cAAc;;;;;;;iBAQjB,qBAAqB,OAAO;EAC1C;EACA;EACA;EACA;;UAuBe;EACf,QAAQ,aAAa;;iBAGD,mBAAmB,iBAAiB,kBACxD,MAAM,0BAA0B,YAC/B,QAAQ"}
|