@tangle-network/agent-eval 0.161.1 → 0.163.2
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 +42 -0
- package/dist/{active-curriculum-CD5TU2yW.js → active-curriculum-OjIWgrUJ.js} +2 -2
- package/dist/{active-curriculum-CD5TU2yW.js.map → active-curriculum-OjIWgrUJ.js.map} +1 -1
- package/dist/analyst/index.d.ts +2 -2
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +3 -3
- package/dist/{baseline-BhPRQBVn.js → baseline-BC-eBZ7U.js} +2 -2
- package/dist/{baseline-BhPRQBVn.js.map → baseline-BC-eBZ7U.js.map} +1 -1
- package/dist/{benchmark-command-BDC3Gocz.js → benchmark-command-CF-4GEWZ.js} +9 -8
- package/dist/benchmark-command-CF-4GEWZ.js.map +1 -0
- package/dist/benchmarks/index.d.ts +1 -1
- package/dist/benchmarks/index.js +3 -3
- package/dist/builder-eval/index.d.ts.map +1 -1
- package/dist/builder-eval/index.js +22 -8
- package/dist/builder-eval/index.js.map +1 -1
- package/dist/campaign/index.js +8 -8
- package/dist/{campaign-BSmOwskD.js → campaign-DQZmc2Dq.js} +12 -12
- package/dist/{campaign-BSmOwskD.js.map → campaign-DQZmc2Dq.js.map} +1 -1
- package/dist/{chat-json-call-6g5sJobJ.js → chat-json-call-5Jxna-aV.js} +2 -2
- package/dist/{chat-json-call-6g5sJobJ.js.map → chat-json-call-5Jxna-aV.js.map} +1 -1
- package/dist/cli.js +3 -3
- package/dist/contract/index.js +7 -7
- package/dist/{counterfactual-D_VWavVm.js → counterfactual-Bjq1mlUu.js} +2 -2
- package/dist/{counterfactual-D_VWavVm.js.map → counterfactual-Bjq1mlUu.js.map} +1 -1
- package/dist/{define-agent-eval-h-s-sI-v.js → define-agent-eval-D08pWIJb.js} +13 -13
- package/dist/{define-agent-eval-h-s-sI-v.js.map → define-agent-eval-D08pWIJb.js.map} +1 -1
- package/dist/{descriptive-jDOuI6mz.js → descriptive-1V17A-qa.js} +2 -2
- package/dist/{descriptive-jDOuI6mz.js.map → descriptive-1V17A-qa.js.map} +1 -1
- package/dist/{dspy-rlm-engine-DptEII26.js → dspy-rlm-engine-DhA9qKIm.js} +2 -2
- package/dist/{dspy-rlm-engine-DptEII26.js.map → dspy-rlm-engine-DhA9qKIm.js.map} +1 -1
- package/dist/emitter-D_jYSGRd.d.ts.map +1 -1
- package/dist/{emitter-BpYFQPj4.js → emitter-DeQHiDMm.js} +13 -6
- package/dist/emitter-DeQHiDMm.js.map +1 -0
- package/dist/{eval-campaign-BsXWL2-2.js → eval-campaign-BfohKmzx.js} +3 -3
- package/dist/{eval-campaign-BsXWL2-2.js.map → eval-campaign-BfohKmzx.js.map} +1 -1
- package/dist/experiment/index.js +8 -8
- package/dist/{experiment-tracker-Ym6rEQT1.js → experiment-tracker-BKEumQug.js} +2 -2
- package/dist/{experiment-tracker-Ym6rEQT1.js.map → experiment-tracker-BKEumQug.js.map} +1 -1
- package/dist/{external-optimizer-process-WosTBChy.js → external-optimizer-process-BFmh36vW.js} +2 -2
- package/dist/{external-optimizer-process-WosTBChy.js.map → external-optimizer-process-BFmh36vW.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-BIWbHpgD.js → external-optimizer-subprocess-CqLMW3nh.js} +2 -2
- package/dist/{external-optimizer-subprocess-BIWbHpgD.js.map → external-optimizer-subprocess-CqLMW3nh.js.map} +1 -1
- package/dist/fuzz.d.ts +1 -2
- package/dist/fuzz.d.ts.map +1 -1
- package/dist/fuzz.js +4 -10
- package/dist/fuzz.js.map +1 -1
- package/dist/index.d.ts +3 -3
- package/dist/index.js +26 -26
- package/dist/index.js.map +1 -1
- package/dist/{internal-BDHPCnjk.js → internal-BMFSR8Ns.js} +3 -19
- package/dist/internal-BMFSR8Ns.js.map +1 -0
- package/dist/{judge-calibration-zZjLz8hr.js → judge-calibration-BnpVKtnb.js} +3 -13
- package/dist/judge-calibration-BnpVKtnb.js.map +1 -0
- package/dist/judge-calibration-C5CbMYce.d.ts.map +1 -1
- package/dist/{llm-client-hgDieDNN.js → llm-client-BFMRpmqb.js} +8 -11
- package/dist/llm-client-BFMRpmqb.js.map +1 -0
- package/dist/{llm-judge-BhasIPFT.js → llm-judge-Du7WQPh7.js} +7 -7
- package/dist/{llm-judge-BhasIPFT.js.map → llm-judge-Du7WQPh7.js.map} +1 -1
- package/dist/meta-eval/index.d.ts +2 -1
- package/dist/meta-eval/index.d.ts.map +1 -1
- package/dist/meta-eval/index.js +14 -22
- package/dist/meta-eval/index.js.map +1 -1
- package/dist/openapi.json +1 -1
- package/dist/{paired-arms-D-XRF_fy.js → paired-arms-D4aeIHUy.js} +3 -3
- package/dist/{paired-arms-D-XRF_fy.js.map → paired-arms-D4aeIHUy.js.map} +1 -1
- package/dist/{paired-tests-BHIhYVdu.js → paired-tests-C8iCsioC.js} +3 -3
- package/dist/{paired-tests-BHIhYVdu.js.map → paired-tests-C8iCsioC.js.map} +1 -1
- package/dist/pipelines/index.d.ts +3 -2
- package/dist/pipelines/index.d.ts.map +1 -1
- package/dist/pipelines/index.js +4 -19
- package/dist/pipelines/index.js.map +1 -1
- package/dist/{power-and-mde-CHIrXJll.js → power-and-mde-B8F2RdcD.js} +3 -3
- package/dist/{power-and-mde-CHIrXJll.js.map → power-and-mde-B8F2RdcD.js.map} +1 -1
- package/dist/{power-preflight-DEw-uC7q.js → power-preflight-CFXm0Vjo.js} +3 -3
- package/dist/{power-preflight-DEw-uC7q.js.map → power-preflight-CFXm0Vjo.js.map} +1 -1
- package/dist/{produced-state-DZ89riy5.js → produced-state-Be0BK3RN.js} +3 -3
- package/dist/{produced-state-DZ89riy5.js.map → produced-state-Be0BK3RN.js.map} +1 -1
- package/dist/{promotion-policy-xzA40Evo.js → promotion-policy-LY9mVQ7W.js} +3 -3
- package/dist/{promotion-policy-xzA40Evo.js.map → promotion-policy-LY9mVQ7W.js.map} +1 -1
- package/dist/{query-DxPYqpmT.d.ts → query-CwnHlu5p.d.ts} +19 -2
- package/dist/query-CwnHlu5p.d.ts.map +1 -0
- package/dist/{query-CHmMP42p.js → query-_5g6re3_.js} +44 -2
- package/dist/query-_5g6re3_.js.map +1 -0
- package/dist/random-Dn5fPWkt.js +21 -0
- package/dist/random-Dn5fPWkt.js.map +1 -0
- package/dist/record-id-DUgsK5qp.js +17 -0
- package/dist/record-id-DUgsK5qp.js.map +1 -0
- package/dist/{release-confidence-DKfD2RYU.js → release-confidence-nGDJiiwc.js} +2 -2
- package/dist/{release-confidence-DKfD2RYU.js.map → release-confidence-nGDJiiwc.js.map} +1 -1
- package/dist/reporting.js +6 -6
- package/dist/{reward-hacking-t4lB1yt8.js → reward-hacking-O5zKDANP.js} +2 -2
- package/dist/{reward-hacking-t4lB1yt8.js.map → reward-hacking-O5zKDANP.js.map} +1 -1
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +9 -15
- package/dist/rl.js.map +1 -1
- package/dist/{rubric-predictive-validity-CK8SCOg-.js → rubric-predictive-validity-2D5Gw9z9.js} +3 -3
- package/dist/{rubric-predictive-validity-CK8SCOg-.js.map → rubric-predictive-validity-2D5Gw9z9.js.map} +1 -1
- package/dist/{semantic-concept-judge-BSkKKHeq.js → semantic-concept-judge-BsDMOwJr.js} +2 -2
- package/dist/{semantic-concept-judge-BSkKKHeq.js.map → semantic-concept-judge-BsDMOwJr.js.map} +1 -1
- package/dist/{sequential-rYW-Ophm.js → sequential-BLMbdrD7.js} +3 -3
- package/dist/{sequential-rYW-Ophm.js.map → sequential-BLMbdrD7.js.map} +1 -1
- package/dist/{server-BtFd4uzB.js → server-BjYiJHoJ.js} +2 -2
- package/dist/{server-BtFd4uzB.js.map → server-BjYiJHoJ.js.map} +1 -1
- package/dist/{skillopt-optimization-method-DbaekMcn.js → skillopt-optimization-method-UArRo-nr.js} +6 -6
- package/dist/{skillopt-optimization-method-DbaekMcn.js.map → skillopt-optimization-method-UArRo-nr.js.map} +1 -1
- package/dist/{store-tool-spans-Dlh9vkFK.js → store-tool-spans-BVga3c37.js} +21 -17
- package/dist/store-tool-spans-BVga3c37.js.map +1 -0
- package/dist/store-tool-spans-DPUG7UUY.d.ts.map +1 -1
- package/dist/{student-t-CvBq2mve.js → student-t-BA-Uy51p.js} +2 -2
- package/dist/{student-t-CvBq2mve.js.map → student-t-BA-Uy51p.js.map} +1 -1
- package/dist/{summary-report-BI5hUtvK.js → summary-report-BXeQ5Ues.js} +6 -6
- package/dist/{summary-report-BI5hUtvK.js.map → summary-report-BXeQ5Ues.js.map} +1 -1
- package/dist/supervisor-run/index.js +1 -1
- package/dist/{tool-waste-BqzmVdJk.js → tool-waste-8BQiUc8K.js} +4 -4
- package/dist/{tool-waste-BqzmVdJk.js.map → tool-waste-8BQiUc8K.js.map} +1 -1
- package/dist/{tool-waste-Dro0gJi3.d.ts → tool-waste-CKc7bYIg.d.ts} +2 -2
- package/dist/{tool-waste-Dro0gJi3.d.ts.map → tool-waste-CKc7bYIg.d.ts.map} +1 -1
- package/dist/trace-repair/index.js +1 -1
- package/dist/traces.d.ts +2 -2
- package/dist/traces.d.ts.map +1 -1
- package/dist/traces.js +8 -17
- package/dist/traces.js.map +1 -1
- package/dist/trajectory-replay/index.d.ts.map +1 -1
- package/dist/trajectory-replay/index.js +3 -13
- package/dist/trajectory-replay/index.js.map +1 -1
- package/dist/{types-BPb2Kf_C2.d.ts → types-BPb2Kf_C.d.ts} +1 -1
- package/dist/types-BPb2Kf_C.d.ts.map +1 -0
- package/dist/types-Bfk0uxRj.d.ts.map +1 -1
- package/dist/wire/index.js +1 -1
- package/package.json +1 -1
- package/dist/benchmark-command-BDC3Gocz.js.map +0 -1
- package/dist/emitter-BpYFQPj4.js.map +0 -1
- package/dist/internal-BDHPCnjk.js.map +0 -1
- package/dist/judge-calibration-zZjLz8hr.js.map +0 -1
- package/dist/llm-client-hgDieDNN.js.map +0 -1
- package/dist/query-CHmMP42p.js.map +0 -1
- package/dist/query-DxPYqpmT.d.ts.map +0 -1
- package/dist/store-tool-spans-Dlh9vkFK.js.map +0 -1
- package/dist/types-BPb2Kf_C2.d.ts.map +0 -1
|
@@ -90,4 +90,4 @@ declare const BENCHMARK_SPLIT_SEED = "agent-eval-v1";
|
|
|
90
90
|
declare function deterministicSplit(itemId: string, seed?: string): RunSplitTag;
|
|
91
91
|
//#endregion
|
|
92
92
|
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 };
|
|
93
|
-
//# sourceMappingURL=types-
|
|
93
|
+
//# sourceMappingURL=types-BPb2Kf_C.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"types-BPb2Kf_C.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;EACA;EACA;;;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 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types-Bfk0uxRj.d.ts","names":[],"sources":["../src/llm-client.ts","../src/analyst/chat-client.ts","../src/types.ts"],"mappings":";;;
|
|
1
|
+
{"version":3,"file":"types-Bfk0uxRj.d.ts","names":[],"sources":["../src/llm-client.ts","../src/analyst/chat-client.ts","../src/types.ts"],"mappings":";;;UAuDiB;EACf;;;;;EAKA,kBAEI;IACM;IAAc;;IACd;IAAmB;MAAa;MAAa;;;;EAGvD,YAAY;;EAEZ;;KAGU;;UAGK;EACf;EACA;IACE;IACA;IACA,YAAY;;;;KAKJ;EAIN;EAAkB;IAAY;;;;UAGnB;EACf;EACA;;EAEA;;UAGe;EACf;EACA,UAAU;;EAEV;;EAEA;IAAe;IAAc,QAAQ;;;EAErC,QAAQ;;EAER,aAAa;EACb;EACA;;;;;EAKA;IAAa;;;EAEb,WAAW;;EAEX;;;;;;UAOe;;EAEf;;EAEA;;EAEA,WAAW;;EAEX,qBAAqB;;iBAGP,2BACd,SAAS,KACP,0GAGF,UAAS,kBACR;UAgCc;EACf;EACA;EACA;;EAEA;;EAEA;;EAEA;;;;UAKe;EACf;EACA;EACA,KAAK;IAAgB;IAAe;;;UAGrB;;EAEf;;EAEA,YAAY;EACZ,OAAO;;;;;EAKP;;;;;;;;;EASA;;;;;;;;;;;;EAYA;;EAEA;;;;;;;;;EASA;;;;;;;EAOA;;;;;;;;EAQA,WAAW,cAAc;;EAEzB,KAAK;;KAGK,kBAAkB,KAAK;;;;;;iBAOnB,mBACd,QAAQ,eACR,qBAAqB,qBACpB;;iBA6Ba,wBACd,OAAO,OACP,qBAAqB,qBACpB;cAMU,qBAAqB;WAGd;WACA;WACA;EAJlB,YACE,iBACgB,gBACA,cACA;;;;;cASP,yBAAyB;WAGlB,QAAQ;EAF1B,YACE,iBACgB,QAAQ,eACxB;IAAY;;;;;;;;;;;;;;iBA2IA,oBAAoB;;;;;;iBA6PpB,gBAAgB;;;;;;UC/rBf;;WAEN,WAAW;;WAEX;;WAEA;;EAGT,KAAK,KAAK,aAAa,OAAO,eAAe,QAAQ;;KAG3C;UAKK,oBAAoB,KAAK;;EAExC;;KAGU,eAAe;UAEV;;EAEf,SAAS;;EAET;;EAEA;;EAEA;;KAKU,uBAAuB,0BAA0B,sBAAsB;UAEzE;EACR;;EAEA;;;;;;UAOe,gCAAgC;EAC/C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;UAI1C,4BAA4B;EAC3C;EACA,OAAO,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;UAO1C,0BAA0B;EACzC;EACA,UAAU,KAAK,aAAa,OAAO,iBAAiB,QAAQ;;;;;;iBAO9C,iBAAiB,MAAM,uBAAuB;;;UClF7C;EACf;EACA;EACA;EACA;EACA;EACA,OAAO;EACP,gBAAgB;EAChB;;UAGe;EACf;EACA;EACA;EACA;;UAKe;EACf;EAQA;EACA;EACA;EACA;;UAKe;EACf;EACA;EACA,YAAY;;UAGG;EACf;EACA;EACA;EACA;EACA;;UAmBe;EACf;EACA;EACA;EACA;EACA;IAAmB;IAAc;;EACjC;EACA;;UASe;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;IAAc;IAAc;;EAC5B;IAAmB;IAAc,QAAQ;;EACzC;IAAc;IAAkB;;EAChC;;UAKe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;GACC;;UAGc;EACf;EACA,QAAQ;;EAER;;UAyBe;EACf;EACA,QAAQ,OAAO;EACf,YAAY,OAAO;;;;;;;;;;KAWT;UAEK;EACf;EACA;EACA;EACA,oBAAoB;EACpB;;EAEA,QAAQ;;;;;;;EAOR;;;;;;;EAOA;;;;;;EAMA;;UAGe;EACf;EACA;EACA;IAAa;IAAiB;IAAkB;;EAChD;EACA;EACA;;UAGe;EACf,UAAU;EACV,OAAO;EACP,WAAW;;EAEX,aAAa;EACb;EACA,WAAW;EACX,SAAS;;KAGC,WAAW,MAAM,YAAY,OAAO,eAAe,QAAQ;UAYtD;EACf;EACA;EACA;EACA"}
|
package/dist/wire/index.js
CHANGED
|
@@ -1,2 +1,2 @@
|
|
|
1
|
-
import { A as hashRubric, C as RubricDimensionSchema, D as TracesIngestResponseSchema, E as TracesIngestRequestSchema, O as VersionResponseSchema, S as ListRubricsResponseSchema, T as TraceEventSchema, _ as FeedbackIngestResponseSchema, a as runRpcBatch, b as JudgeRequestSchema, c as WireError, d as handleListRubrics, f as handleTracesIngest, g as ErrorResponseSchema, h as listBuiltinRubrics, i as dispatchRpc, k as WIRE_VERSION, l as handleFeedbackIngest, m as getBuiltinRubric, n as startServer, o as runRpcOnce, p as handleVersion, r as startServerAsync, s as buildOpenApi, t as createApp, u as handleJudge, v as FeedbackTrajectorySchema, w as RubricSchema, x as JudgeResultSchema, y as HealthResponseSchema } from "../server-
|
|
1
|
+
import { A as hashRubric, C as RubricDimensionSchema, D as TracesIngestResponseSchema, E as TracesIngestRequestSchema, O as VersionResponseSchema, S as ListRubricsResponseSchema, T as TraceEventSchema, _ as FeedbackIngestResponseSchema, a as runRpcBatch, b as JudgeRequestSchema, c as WireError, d as handleListRubrics, f as handleTracesIngest, g as ErrorResponseSchema, h as listBuiltinRubrics, i as dispatchRpc, k as WIRE_VERSION, l as handleFeedbackIngest, m as getBuiltinRubric, n as startServer, o as runRpcOnce, p as handleVersion, r as startServerAsync, s as buildOpenApi, t as createApp, u as handleJudge, v as FeedbackTrajectorySchema, w as RubricSchema, x as JudgeResultSchema, y as HealthResponseSchema } from "../server-BjYiJHoJ.js";
|
|
2
2
|
export { ErrorResponseSchema, FeedbackIngestResponseSchema, FeedbackTrajectorySchema, HealthResponseSchema, JudgeRequestSchema, JudgeResultSchema, ListRubricsResponseSchema, RubricDimensionSchema, RubricSchema, TraceEventSchema, TracesIngestRequestSchema, TracesIngestResponseSchema, VersionResponseSchema, WIRE_VERSION, WireError, buildOpenApi, createApp, dispatchRpc, getBuiltinRubric, handleFeedbackIngest, handleJudge, handleListRubrics, handleTracesIngest, handleVersion, hashRubric, listBuiltinRubrics, runRpcBatch, runRpcOnce, startServer, startServerAsync };
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@tangle-network/agent-eval",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.163.2",
|
|
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": {
|