@tangle-network/agent-eval 0.137.0 → 0.139.0
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 +78 -0
- package/README.md +34 -0
- package/dist/analyst/index.d.ts +485 -104
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +10 -607
- package/dist/analyst/index.js.map +1 -1
- package/dist/{benchmark-YDrpumqB.js → benchmark-CYtcIF2V.js} +299 -159
- package/dist/benchmark-CYtcIF2V.js.map +1 -0
- package/dist/{benchmark-CHX4orG7.d.ts → benchmark-DDVdWcwA.d.ts} +67 -15
- package/dist/benchmark-DDVdWcwA.d.ts.map +1 -0
- package/dist/benchmark-command-BKfjOBJ5.js +4537 -0
- package/dist/benchmark-command-BKfjOBJ5.js.map +1 -0
- package/dist/benchmarks/index.d.ts +1 -1
- package/dist/benchmarks/index.js +1 -1
- package/dist/{benchmarks-DCLkQOmc.js → benchmarks-zxhy1QV3.js} +4 -3
- package/dist/{benchmarks-DCLkQOmc.js.map → benchmarks-zxhy1QV3.js.map} +1 -1
- package/dist/campaign/index.d.ts +5 -5
- package/dist/campaign/index.js +4 -3
- package/dist/{campaign-lgObcHFC.js → campaign-DrS6_hLd.js} +19 -11
- package/dist/campaign-DrS6_hLd.js.map +1 -0
- package/dist/canonical-D011XM8r.js +86 -0
- package/dist/canonical-D011XM8r.js.map +1 -0
- package/dist/cli.js +10 -3
- package/dist/cli.js.map +1 -1
- package/dist/{client-C8L6h6Wf.d.ts → client-BohnDFBq.d.ts} +4 -4
- package/dist/{client-C8L6h6Wf.d.ts.map → client-BohnDFBq.d.ts.map} +1 -1
- package/dist/{completion-verifier-DSyRNVzU.d.ts → completion-verifier-IPoP4fQO.d.ts} +178 -4
- package/dist/completion-verifier-IPoP4fQO.d.ts.map +1 -0
- package/dist/contract/index.d.ts +10 -10
- package/dist/contract/index.js +9 -8
- package/dist/contract/index.js.map +1 -1
- package/dist/control.d.ts +2 -2
- package/dist/{cost-ledger-D-5_-dhi.js → cost-ledger-CZ9diLxY.js} +90 -45
- package/dist/cost-ledger-CZ9diLxY.js.map +1 -0
- package/dist/{cost-ledger-D2o6JOrL.d.ts → cost-ledger-DKgyIWRj.d.ts} +6 -2
- package/dist/cost-ledger-DKgyIWRj.d.ts.map +1 -0
- package/dist/default-registry-B8vf7Rmf.d.ts +118 -0
- package/dist/default-registry-B8vf7Rmf.d.ts.map +1 -0
- package/dist/default-registry-BgJJItGr.js +2364 -0
- package/dist/default-registry-BgJJItGr.js.map +1 -0
- package/dist/dspy-rlm-engine-DTkVyDX-.js +344 -0
- package/dist/dspy-rlm-engine-DTkVyDX-.js.map +1 -0
- package/dist/{eval-campaign-CHqfLnff.js → eval-campaign-BmptJj50.js} +2 -2
- package/dist/{eval-campaign-CHqfLnff.js.map → eval-campaign-BmptJj50.js.map} +1 -1
- package/dist/exact-types-MaaFcllV.d.ts +234 -0
- package/dist/exact-types-MaaFcllV.d.ts.map +1 -0
- package/dist/external-optimizer-contracts-BrxY2Sli.d.ts +32 -0
- package/dist/external-optimizer-contracts-BrxY2Sli.d.ts.map +1 -0
- package/dist/{extract-usage-p-56bh8q.js → extract-usage-DZs601Va.js} +2 -2
- package/dist/{extract-usage-p-56bh8q.js.map → extract-usage-DZs601Va.js.map} +1 -1
- package/dist/{feedback-trajectory-N_F0PwHz.d.ts → feedback-trajectory-BJUWOkJM.d.ts} +3 -2
- package/dist/feedback-trajectory-BJUWOkJM.d.ts.map +1 -0
- package/dist/fuzz.d.ts +1 -1
- package/dist/fuzz.js +1 -1
- package/dist/{hf-dataset-DBJXXoY1.js → hf-dataset-XggBupCr.js} +2 -2
- package/dist/{hf-dataset-DBJXXoY1.js.map → hf-dataset-XggBupCr.js.map} +1 -1
- package/dist/hosted/index.d.ts +3 -3
- package/dist/{index-C-Pr4OWg.d.ts → index-BTm_P9aC.d.ts} +12 -11
- package/dist/index-BTm_P9aC.d.ts.map +1 -0
- package/dist/{index-U3RHOShi.d.ts → index-CWOPCJiw.d.ts} +2 -2
- package/dist/{index-U3RHOShi.d.ts.map → index-CWOPCJiw.d.ts.map} +1 -1
- package/dist/{index-DRNl6g_N.d.ts → index-CtR1xh4V.d.ts} +3 -3
- package/dist/{index-DRNl6g_N.d.ts.map → index-CtR1xh4V.d.ts.map} +1 -1
- package/dist/index-DEb46kc6.d.ts.map +1 -1
- package/dist/{index-BnP1QJUv.d.ts → index-_66rVpwN.d.ts} +5 -5
- package/dist/{index-BnP1QJUv.d.ts.map → index-_66rVpwN.d.ts.map} +1 -1
- package/dist/index.d.ts +35 -55
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +55 -514
- package/dist/index.js.map +1 -1
- package/dist/{insight-report-B9ooYH_g.d.ts → insight-report-Bu5Wi9tG.d.ts} +4 -4
- package/dist/{insight-report-B9ooYH_g.d.ts.map → insight-report-Bu5Wi9tG.d.ts.map} +1 -1
- package/dist/{integrity-CKxosZ5Z.d.ts → integrity-COTh3DTH.d.ts} +2 -2
- package/dist/{integrity-CKxosZ5Z.d.ts.map → integrity-COTh3DTH.d.ts.map} +1 -1
- package/dist/kind-factory-CFxA0JQX.js +2133 -0
- package/dist/kind-factory-CFxA0JQX.js.map +1 -0
- package/dist/ledger-core/index.js +2 -1
- package/dist/{ledger-core-t6sItivm.js → ledger-core-Dxz0Rkwa.js} +210 -99
- package/dist/ledger-core-Dxz0Rkwa.js.map +1 -0
- package/dist/{llm-client-DKB25jV8.js → llm-client-bkztEfIx.js} +5 -5
- package/dist/llm-client-bkztEfIx.js.map +1 -0
- package/dist/meta-eval/index.d.ts +2 -2
- package/dist/multishot/index.d.ts +2 -2
- package/dist/openapi.json +1 -1
- package/dist/{proposal-findings-DCawte-y.js → proposal-findings-2GIUo1et.js} +2 -68
- package/dist/proposal-findings-2GIUo1et.js.map +1 -0
- package/dist/{release-report-CofgVNZt.d.ts → release-report-fZarvIm-.d.ts} +3 -3
- package/dist/{release-report-CofgVNZt.d.ts.map → release-report-fZarvIm-.d.ts.map} +1 -1
- package/dist/{replay-K8FaC0CB.d.ts → replay-DjG4IG60.d.ts} +34 -143
- package/dist/replay-DjG4IG60.d.ts.map +1 -0
- package/dist/{replay-Bju0T8Ls.js → replay-SA4OB7O7.js} +48 -136
- package/dist/replay-SA4OB7O7.js.map +1 -0
- package/dist/reporting.d.ts +4 -4
- package/dist/{researcher-Da0Wj-bt.d.ts → researcher-BxhtGfKa.d.ts} +5 -5
- package/dist/{researcher-Da0Wj-bt.d.ts.map → researcher-BxhtGfKa.d.ts.map} +1 -1
- package/dist/{reward-hacking-CQ3hTCO3.d.ts → reward-hacking-CqSLiV51.d.ts} +2 -2
- package/dist/{reward-hacking-CQ3hTCO3.d.ts.map → reward-hacking-CqSLiV51.d.ts.map} +1 -1
- package/dist/rl.d.ts +5 -5
- package/dist/rl.js +1 -1
- package/dist/rollout/index.d.ts +1 -1
- package/dist/rollout/index.js +2 -2
- package/dist/{rollout-DQFl0UXA.js → rollout-8nj3mYvx.js} +2 -2
- package/dist/{rollout-DQFl0UXA.js.map → rollout-8nj3mYvx.js.map} +1 -1
- package/dist/{rubric-predictive-validity-C4sztLR3.d.ts → rubric-predictive-validity-DQBQj6uV.d.ts} +2 -2
- package/dist/{rubric-predictive-validity-C4sztLR3.d.ts.map → rubric-predictive-validity-DQBQj6uV.d.ts.map} +1 -1
- package/dist/{run-evidence-BDIircdA.d.ts → run-evidence-C4RcRQT5.d.ts} +3 -3
- package/dist/{run-evidence-BDIircdA.d.ts.map → run-evidence-C4RcRQT5.d.ts.map} +1 -1
- package/dist/{run-record-BPCa2rQ8.d.ts → run-record-CztDMXVF.d.ts} +2 -2
- package/dist/{run-record-BPCa2rQ8.d.ts.map → run-record-CztDMXVF.d.ts.map} +1 -1
- package/dist/{semantic-concept-judge-Bz64IckK.js → semantic-concept-judge-BuIJ9IfB.js} +49 -6
- package/dist/semantic-concept-judge-BuIJ9IfB.js.map +1 -0
- package/dist/{server-KjXZZUDX.js → server-DaCpLfi0.js} +3 -3
- package/dist/{server-KjXZZUDX.js.map → server-DaCpLfi0.js.map} +1 -1
- package/dist/single-run-lock-BTTtPZ9N.js +989 -0
- package/dist/single-run-lock-BTTtPZ9N.js.map +1 -0
- package/dist/{skill-usage-CFDLLlhF.d.ts → skill-usage-B-BFS8M2.d.ts} +65 -40
- package/dist/skill-usage-B-BFS8M2.d.ts.map +1 -0
- package/dist/{skillopt-optimization-method-f4o9sUT4.js → skillopt-optimization-method-BbGnCC53.js} +20 -979
- package/dist/skillopt-optimization-method-BbGnCC53.js.map +1 -0
- package/dist/{skillopt-optimization-method-BpbnlvAZ.d.ts → skillopt-optimization-method-_s0Tub7Y.d.ts} +11 -39
- package/dist/skillopt-optimization-method-_s0Tub7Y.d.ts.map +1 -0
- package/dist/{statistics-_7P642CN.d.ts → statistics-B5d0Zd-z.d.ts} +2 -2
- package/dist/{statistics-_7P642CN.d.ts.map → statistics-B5d0Zd-z.d.ts.map} +1 -1
- package/dist/store-otlp-DX4fGIcf.js +757 -0
- package/dist/store-otlp-DX4fGIcf.js.map +1 -0
- package/dist/{summary-report-DHipz9Kx.d.ts → summary-report-Cg7BifAM.d.ts} +3 -3
- package/dist/{summary-report-DHipz9Kx.d.ts.map → summary-report-Cg7BifAM.d.ts.map} +1 -1
- package/dist/tool-groups-CdYq22lX.d.ts +258 -0
- package/dist/tool-groups-CdYq22lX.d.ts.map +1 -0
- package/dist/traces.d.ts +7 -6
- package/dist/traces.js +5 -4
- package/dist/{types-CTGbIm57.d.ts → types-BBFNHxSK.d.ts} +5 -5
- package/dist/{types-CTGbIm57.d.ts.map → types-BBFNHxSK.d.ts.map} +1 -1
- package/dist/{types-CKswbJGO.d.ts → types-DoEYskCd.d.ts} +5 -5
- package/dist/{types-CKswbJGO.d.ts.map → types-DoEYskCd.d.ts.map} +1 -1
- package/dist/{types-CTvKfr5F.d.ts → types-uPrS6mD-.d.ts} +2 -2
- package/dist/{types-CTvKfr5F.d.ts.map → types-uPrS6mD-.d.ts.map} +1 -1
- package/dist/usage-receipt-CgxMEBZq.js +134 -0
- package/dist/usage-receipt-CgxMEBZq.js.map +1 -0
- package/dist/wire/index.d.ts +3 -3
- package/dist/wire/index.js +1 -1
- package/docs/trace-analysis.md +191 -385
- package/package.json +5 -4
- package/dist/analyze-runs-PVtnfjvA.d.ts +0 -72
- package/dist/analyze-runs-PVtnfjvA.d.ts.map +0 -1
- package/dist/benchmark-CHX4orG7.d.ts.map +0 -1
- package/dist/benchmark-YDrpumqB.js.map +0 -1
- package/dist/campaign-lgObcHFC.js.map +0 -1
- package/dist/completion-verifier-DSyRNVzU.d.ts.map +0 -1
- package/dist/concurrency-MUjT7VjM.js +0 -109
- package/dist/concurrency-MUjT7VjM.js.map +0 -1
- package/dist/cost-ledger-D-5_-dhi.js.map +0 -1
- package/dist/cost-ledger-D2o6JOrL.d.ts.map +0 -1
- package/dist/default-registry-CLXbRt0f.js +0 -2594
- package/dist/default-registry-CLXbRt0f.js.map +0 -1
- package/dist/default-registry-Dc5D_Loc.d.ts +0 -202
- package/dist/default-registry-Dc5D_Loc.d.ts.map +0 -1
- package/dist/feedback-trajectory-N_F0PwHz.d.ts.map +0 -1
- package/dist/index-C-Pr4OWg.d.ts.map +0 -1
- package/dist/ledger-core-t6sItivm.js.map +0 -1
- package/dist/llm-client-DKB25jV8.js.map +0 -1
- package/dist/proposal-findings-DCawte-y.js.map +0 -1
- package/dist/registry-BdM7SuTr.d.ts +0 -124
- package/dist/registry-BdM7SuTr.d.ts.map +0 -1
- package/dist/replay-Bju0T8Ls.js.map +0 -1
- package/dist/replay-K8FaC0CB.d.ts.map +0 -1
- package/dist/semantic-concept-judge-Bz64IckK.js.map +0 -1
- package/dist/skill-usage-CFDLLlhF.d.ts.map +0 -1
- package/dist/skillopt-optimization-method-BpbnlvAZ.d.ts.map +0 -1
- package/dist/skillopt-optimization-method-f4o9sUT4.js.map +0 -1
- package/dist/tools-DZk2Jn64.js +0 -1876
- package/dist/tools-DZk2Jn64.js.map +0 -1
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
import { o as FailureClass } from "./schema-BtVldJ3T.js";
|
|
2
|
-
import { l as RunTerminalOutcome } from "./run-record-
|
|
3
|
-
import { bt as ContinuousAgreement } from "./statistics-
|
|
4
|
-
import { i as ParetoFigureSpec, t as GainDistributionBin } from "./summary-report-
|
|
2
|
+
import { l as RunTerminalOutcome } from "./run-record-CztDMXVF.js";
|
|
3
|
+
import { bt as ContinuousAgreement } from "./statistics-B5d0Zd-z.js";
|
|
4
|
+
import { i as ParetoFigureSpec, t as GainDistributionBin } from "./summary-report-Cg7BifAM.js";
|
|
5
5
|
//#region src/contract/insight-report.d.ts
|
|
6
6
|
interface InsightReport {
|
|
7
7
|
/** Number of runs analyzed. */
|
|
@@ -403,4 +403,4 @@ interface Recommendation {
|
|
|
403
403
|
}
|
|
404
404
|
//#endregion
|
|
405
405
|
export { FailureClusterInsight as a, JudgeInsight as c, Recommendation as d, ReleaseSummary as f, FailureClassTally as i, LiftInsight as l, TokenUsageInsight as m, ExecutionErrorOutcomeCell as n, InsightReport as o, ScalarDistribution as p, ExecutionInsight as r, InterRaterInsight as s, CostProvenanceSummary as t, OutcomeCorrelationInsight as u };
|
|
406
|
-
//# sourceMappingURL=insight-report-
|
|
406
|
+
//# sourceMappingURL=insight-report-Bu5Wi9tG.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"insight-report-
|
|
1
|
+
{"version":3,"file":"insight-report-Bu5Wi9tG.d.ts","names":[],"sources":["../src/contract/insight-report.ts"],"mappings":";;;;;UAqCiB;;EAEf;;;;EAKA,WAAW;;EAGX,WAAW;;;EAIX,cAAc,eAAe;;EAG7B;IACE,MAAM;IACN,QAAQ;;;;IAIR,aAAa;;;;;IAKb;MAAa;MAAe;;;;;;EAM9B,QAAQ,eAAe;;;;EAKvB,aAAa;;;;EAKb,OAAO;;;EAIP,kBAAkB;;;EAIlB,gBAAgB;;;;;EAMhB,qBAAqB;;;;;EAMrB,SAAS;;;;;;EAOT,wBAAwB;;;;EAKxB,iBAAiB;;;EAIjB,iBAAiB;;UAGF;EACf;IAAY;IAAW;;EACvB;IAAa;IAAW;;EACxB;IAAc;;EACd;;UAGe;;EAEf,YAAY;;EAEZ,SAAS;;;EAGT,YAAY;;;EAGZ;IACE;IACA,YAAY;IACZ,SAAS;IACT;;;EAGF,QAAQ;IAAQ;IAAe;;;;;EAI/B;IACE;IACA;IACA;;;;;EAKF;IACE;;;IAGA;;IAEA;;IAEA;;IAEA;;IAEA;;;;;IAKA,mBAAmB,OAAO,oBAAoB;;;;EAIhD;IACE;IACA;IACA;IACA;IACA;;;UAIa;;EAEf;;EAEA;;EAEA;;UAGe;EACf,OAAO;EACP,QAAQ;EACR,WAAW;EACX,QAAQ;EACR,YAAY;EACZ;IACE;IACA;IACA;IACA;IACA;;;;UAOa;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA,WAAW;;;;;EAKX,WAAW;IAAQ;IAAe;;;UAGnB;;EAEf;;EAEA;;;EAGA,cAAc;;;EAGd;;;EAGA;;;EAGA;;UAGe;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA,SAAS;;EAET,mBAAmB;IACjB;IACA,SAAS;MAAQ;MAAe;;IAChC;;;UAIa;EACf;EACA;;EAEA;;EAEA;;;EAGA;;EAEA;;EAEA;;;;;;;;;;;EAWA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe;;EAEf,UAAU;IACR;IACA;;IAEA;;IAEA;;IAEA;;EAEF;;;;;UAMe;;EAEf,cAAc;;EAEd;;EAEA;;UAGe;;EAEf;;;EAGA;EACA,UAAU;IAAQ;IAAe;IAAgB;;;UAGlC;;;EAGf;;EAEA;;EAEA;;EAEA;;EAEA;IACE;IACA;IACA;;;UAIa;;;EAGf;EACA,MAAM;IACJ;IACA;IACA;;;;EAIF;;UAGQ;;EAER;;EAEA;;;;EAIA;;EAEA;EACA;;KAGU,eACP;EACC;;EAEA;;EAEA;;EAEA;;EAEA;MAED;EACC;;EAEA;EACA;EACA;EACA;;UAGW;;EAEf;EACA;;EAEA;;;;EAIA,SAAS,eAAe;;;EAGxB;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA;EACA;;EAEA"}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { r as CaptureIntegrityError } from "./errors-DkfjIDvD.js";
|
|
2
|
-
import { _t as RawProviderSink } from "./types-
|
|
2
|
+
import { _t as RawProviderSink } from "./types-uPrS6mD-.js";
|
|
3
3
|
import { s as TraceStore } from "./store-CT9YIIve.js";
|
|
4
4
|
//#region src/trace/integrity.d.ts
|
|
5
5
|
interface RunIntegrityExpectations {
|
|
@@ -58,4 +58,4 @@ declare function assertRunCaptured(store: TraceStore, runId: string, expectation
|
|
|
58
58
|
declare function throwIfRunIncomplete(report: RunIntegrityReport): void;
|
|
59
59
|
//#endregion
|
|
60
60
|
export { RunIntegrityReport as a, RunIntegrityIssueCode as i, RunIntegrityExpectations as n, assertRunCaptured as o, RunIntegrityIssue as r, throwIfRunIncomplete as s, RunIntegrityError as t };
|
|
61
|
-
//# sourceMappingURL=integrity-
|
|
61
|
+
//# sourceMappingURL=integrity-COTh3DTH.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"integrity-
|
|
1
|
+
{"version":3,"file":"integrity-COTh3DTH.d.ts","names":[],"sources":["../src/trace/integrity.ts"],"mappings":";;;;UAyBiB;;EAEf;;EAEA;;EAEA;;;;;EAKA,UAAU;;EAEV;;;;;;EAMA;;EAEA;;KAGU;UAUK;EACf,MAAM;EACN;EACA,SAAS;;UAGM;EACf;EACA;EACA;EACA;EACA;EACA;;;;;;EAMA;IAAmB;IAAiB;;EACpC,QAAQ;;cAGG,0BAA0B;WACT,QAAQ;EAApC,YAA4B,QAAQ;;iBAOhB,kBACpB,OAAO,YACP,eACA,eAAc,2BACb,QAAQ;;iBA6GK,qBAAqB,QAAQ"}
|