@tangle-network/agent-eval 0.149.0 → 0.150.1
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 +42 -0
- package/README.md +5 -1
- package/dist/analyst/index.d.ts +13 -13
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +4 -4
- package/dist/{backend-integrity-Bz8nSrRE.d.ts → backend-integrity-DOCa_QrR.d.ts} +2 -2
- package/dist/{backend-integrity-Bz8nSrRE.d.ts.map → backend-integrity-DOCa_QrR.d.ts.map} +1 -1
- package/dist/{benchmark-Cn7ZMFNW.d.ts → benchmark-BtAWA8nT.d.ts} +3 -3
- package/dist/{benchmark-Cn7ZMFNW.d.ts.map → benchmark-BtAWA8nT.d.ts.map} +1 -1
- package/dist/{benchmark-command-gufocQ-N.js → benchmark-command-CAFwbH0L.js} +8 -7
- package/dist/benchmark-command-CAFwbH0L.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 +9 -9
- package/dist/campaign/index.js +6 -6
- package/dist/{campaign-BcfXzmPM.js → campaign-CN_7xJdV.js} +90 -8
- package/dist/campaign-CN_7xJdV.js.map +1 -0
- package/dist/{capture-fetch-BAx3Gntt.d.ts → capture-fetch-BBVFzhkk.d.ts} +2 -2
- package/dist/{capture-fetch-BAx3Gntt.d.ts.map → capture-fetch-BBVFzhkk.d.ts.map} +1 -1
- package/dist/{chat-client-BX8Wh3fn.js → chat-client-2bVfrzhN.js} +2 -2
- package/dist/{chat-client-BX8Wh3fn.js.map → chat-client-2bVfrzhN.js.map} +1 -1
- package/dist/cli.js +2 -2
- package/dist/{client-BV7icIfy.d.ts → client-kPQYT_56.d.ts} +2 -2
- package/dist/{client-BV7icIfy.d.ts.map → client-kPQYT_56.d.ts.map} +1 -1
- package/dist/contract/index.d.ts +10 -10
- package/dist/contract/index.js +5 -5
- package/dist/{default-registry-BUtRMRKk.d.ts → default-registry-Cw0Ohdoj.d.ts} +6 -6
- package/dist/{default-registry-BUtRMRKk.d.ts.map → default-registry-Cw0Ohdoj.d.ts.map} +1 -1
- package/dist/{define-agent-eval-BWuk2O_N.d.ts → define-agent-eval-CEQWL9Hy.d.ts} +5 -5
- package/dist/{define-agent-eval-BWuk2O_N.d.ts.map → define-agent-eval-CEQWL9Hy.d.ts.map} +1 -1
- package/dist/{define-agent-eval-CvZQW4u9.js → define-agent-eval-rqNyVhVV.js} +4 -4
- package/dist/{define-agent-eval-CvZQW4u9.js.map → define-agent-eval-rqNyVhVV.js.map} +1 -1
- package/dist/{dspy-rlm-engine-BmtOl_kP.js → dspy-rlm-engine-DHI0WrUU.js} +2 -2
- package/dist/{dspy-rlm-engine-BmtOl_kP.js.map → dspy-rlm-engine-DHI0WrUU.js.map} +1 -1
- package/dist/{engine-CIy18RTX.d.ts → engine-BLzhNzoY.d.ts} +4 -4
- package/dist/{engine-CIy18RTX.d.ts.map → engine-BLzhNzoY.d.ts.map} +1 -1
- package/dist/{eval-campaign-bmZ6NIIP.js → eval-campaign-C4jmuM-b.js} +2 -2
- package/dist/{eval-campaign-bmZ6NIIP.js.map → eval-campaign-C4jmuM-b.js.map} +1 -1
- package/dist/{exact-types-rdKFzEnK.d.ts → exact-types-ccQAyut1.d.ts} +2 -2
- package/dist/{exact-types-rdKFzEnK.d.ts.map → exact-types-ccQAyut1.d.ts.map} +1 -1
- package/dist/experiment/index.d.ts +73 -4
- package/dist/experiment/index.d.ts.map +1 -1
- package/dist/experiment/index.js +175 -1
- package/dist/experiment/index.js.map +1 -1
- package/dist/{experiment-tracker-D9VHwRm-.d.ts → experiment-tracker-0MhuPArU.d.ts} +2 -2
- package/dist/{experiment-tracker-D9VHwRm-.d.ts.map → experiment-tracker-0MhuPArU.d.ts.map} +1 -1
- package/dist/{external-optimizer-contracts-CSjDLLmr.d.ts → external-optimizer-contracts-DbLsm4Po.d.ts} +13 -6
- package/dist/{external-optimizer-contracts-CSjDLLmr.d.ts.map → external-optimizer-contracts-DbLsm4Po.d.ts.map} +1 -1
- package/dist/{external-optimizer-process-C4AyCcQd.js → external-optimizer-process-Bhmzngf-.js} +4 -4
- package/dist/{external-optimizer-process-C4AyCcQd.js.map → external-optimizer-process-Bhmzngf-.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-DU1KM8yV.js → external-optimizer-subprocess-Dn90UqN2.js} +572 -25
- package/dist/external-optimizer-subprocess-Dn90UqN2.js.map +1 -0
- package/dist/{feedback-trajectory-niGeR6uJ.d.ts → feedback-trajectory-DpTTjo0q.d.ts} +3 -3
- package/dist/{feedback-trajectory-niGeR6uJ.d.ts.map → feedback-trajectory-DpTTjo0q.d.ts.map} +1 -1
- package/dist/hosted/index.d.ts +2 -2
- package/dist/index-C1ravkGA.d.ts +1 -0
- package/dist/{index-aHDnhBC7.d.ts → index-CTKpu9ry.d.ts} +7 -7
- package/dist/{index-aHDnhBC7.d.ts.map → index-CTKpu9ry.d.ts.map} +1 -1
- package/dist/{index-BCDyf_kT.d.ts → index-IQccV3Ou.d.ts} +47 -11
- package/dist/index-IQccV3Ou.d.ts.map +1 -0
- package/dist/index.d.ts +20 -20
- package/dist/index.js +8 -8
- package/dist/{integrity-CGfpTE5-.d.ts → integrity-B0dZ96EO.d.ts} +2 -2
- package/dist/{integrity-CGfpTE5-.d.ts.map → integrity-B0dZ96EO.d.ts.map} +1 -1
- package/dist/{llm-client-BMuxYoZy.js → llm-client-Bg32RW0j.js} +61 -7
- package/dist/llm-client-Bg32RW0j.js.map +1 -0
- package/dist/{llm-judge-DWq1Ptco.js → llm-judge-CVq33oz1.js} +5 -4
- package/dist/llm-judge-CVq33oz1.js.map +1 -0
- package/dist/{matrix-Bc111FKv.d.ts → matrix-DrVnRp4G.d.ts} +2 -2
- package/dist/{matrix-Bc111FKv.d.ts.map → matrix-DrVnRp4G.d.ts.map} +1 -1
- package/dist/meta-eval/index.d.ts +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/{produced-state-C0oJ4vr-.js → produced-state-jfk8Du3b.js} +3 -3
- package/dist/{produced-state-C0oJ4vr-.js.map → produced-state-jfk8Du3b.js.map} +1 -1
- package/dist/{promotion-policy-CewdjfCJ.d.ts → promotion-policy-DLOUkYhI.d.ts} +2 -2
- package/dist/{promotion-policy-CewdjfCJ.d.ts.map → promotion-policy-DLOUkYhI.d.ts.map} +1 -1
- package/dist/{provenance-DA-Pmyfv.d.ts → provenance-oA4-zUqm.d.ts} +17 -6
- package/dist/{provenance-DA-Pmyfv.d.ts.map → provenance-oA4-zUqm.d.ts.map} +1 -1
- package/dist/{registry-CaqJIDdN.d.ts → registry-BQwrSYpC.d.ts} +4 -4
- package/dist/{registry-CaqJIDdN.d.ts.map → registry-BQwrSYpC.d.ts.map} +1 -1
- package/dist/{researcher-BySlpla_.d.ts → researcher-DJnoUE8c.d.ts} +3 -3
- package/dist/{researcher-BySlpla_.d.ts.map → researcher-DJnoUE8c.d.ts.map} +1 -1
- package/dist/{reward-hacking-DFo2FU5J.js → reward-hacking-DKI9T52l.js} +19 -1
- package/dist/reward-hacking-DKI9T52l.js.map +1 -0
- package/dist/rl.d.ts +2 -2
- package/dist/rl.js +2 -2
- package/dist/{semantic-concept-judge-BI7Rrl5-.js → semantic-concept-judge-laMCnTLn.js} +2 -2
- package/dist/{semantic-concept-judge-BI7Rrl5-.js.map → semantic-concept-judge-laMCnTLn.js.map} +1 -1
- package/dist/{series-convergence-D2fsoJ2w.d.ts → series-convergence-BxKEgBwA.d.ts} +2 -2
- package/dist/{series-convergence-D2fsoJ2w.d.ts.map → series-convergence-BxKEgBwA.d.ts.map} +1 -1
- package/dist/{server-D9wQclzG.js → server-dIWwF3j_.js} +2 -2
- package/dist/{server-D9wQclzG.js.map → server-dIWwF3j_.js.map} +1 -1
- package/dist/{skillopt-optimization-method-ChCTN4FD.d.ts → skillopt-optimization-method-BDD_o1xE.d.ts} +19 -13
- package/dist/{skillopt-optimization-method-ChCTN4FD.d.ts.map → skillopt-optimization-method-BDD_o1xE.d.ts.map} +1 -1
- package/dist/{skillopt-optimization-method-Donmq4sq.js → skillopt-optimization-method-DLeUcK-K.js} +92 -14
- package/dist/skillopt-optimization-method-DLeUcK-K.js.map +1 -0
- package/dist/{statistical-heldout-uxSpFEjm.d.ts → statistical-heldout-_woZ9q9j.d.ts} +2 -2
- package/dist/{statistical-heldout-uxSpFEjm.d.ts.map → statistical-heldout-_woZ9q9j.d.ts.map} +1 -1
- package/dist/{store-tool-spans-D5FhM0_A.d.ts → store-tool-spans-Br2_IUhm.d.ts} +4 -4
- package/dist/{store-tool-spans-D5FhM0_A.d.ts.map → store-tool-spans-Br2_IUhm.d.ts.map} +1 -1
- package/dist/{tool-groups-zpufabP8.d.ts → tool-groups-B4tqh8jB.d.ts} +3 -3
- package/dist/tool-groups-B4tqh8jB.d.ts.map +1 -0
- package/dist/trace-repair/index.d.ts +1 -1
- package/dist/traces.d.ts +7 -7
- package/dist/{types-BohHewKK.d.ts → types-B2NsbrNy.d.ts} +2 -2
- package/dist/{types-BohHewKK.d.ts.map → types-B2NsbrNy.d.ts.map} +1 -1
- package/dist/{types-ColZlZtc.d.ts → types-CLAwnY-L.d.ts} +2 -2
- package/dist/{types-ColZlZtc.d.ts.map → types-CLAwnY-L.d.ts.map} +1 -1
- package/dist/{types-C1Bmeb8X.d.ts → types-DdFNuyxQ.d.ts} +3 -3
- package/dist/{types-C1Bmeb8X.d.ts.map → types-DdFNuyxQ.d.ts.map} +1 -1
- package/dist/{types-DOhGq4S1.d.ts → types-jUBXJ7Iz.d.ts} +50 -5
- package/dist/types-jUBXJ7Iz.d.ts.map +1 -0
- package/dist/wire/index.d.ts +2 -2
- package/dist/wire/index.js +1 -1
- package/docs/campaign-proposers.md +67 -3
- package/docs/experiment.md +2 -0
- package/docs/multishot-golden-records.md +3 -0
- package/package.json +4 -2
- package/dist/benchmark-command-gufocQ-N.js.map +0 -1
- package/dist/campaign-BcfXzmPM.js.map +0 -1
- package/dist/external-optimizer-subprocess-DU1KM8yV.js.map +0 -1
- package/dist/index-BCDyf_kT.d.ts.map +0 -1
- package/dist/index-CKblBxtr.d.ts +0 -1
- package/dist/llm-client-BMuxYoZy.js.map +0 -1
- package/dist/llm-judge-DWq1Ptco.js.map +0 -1
- package/dist/reward-hacking-DFo2FU5J.js.map +0 -1
- package/dist/skillopt-optimization-method-Donmq4sq.js.map +0 -1
- package/dist/tool-groups-zpufabP8.d.ts.map +0 -1
- package/dist/types-DOhGq4S1.d.ts.map +0 -1
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { u as RunTokenUsage } from "./run-record-DVV82Gwh.js";
|
|
2
|
-
import {
|
|
2
|
+
import { ft as ProviderRedactor, ht as RawProviderSink } from "./types-jUBXJ7Iz.js";
|
|
3
3
|
//#region src/trace/extract-usage.d.ts
|
|
4
4
|
type ExtractedUsage = RunTokenUsage;
|
|
5
5
|
type SseUsageMode = 'cumulative' | 'delta';
|
|
@@ -65,4 +65,4 @@ interface CaptureFetchOptions {
|
|
|
65
65
|
declare function captureFetchToRawSink(fetch: typeof globalThis.fetch, sink: RawProviderSink, ctx: CaptureFetchContext, opts?: CaptureFetchOptions): typeof globalThis.fetch;
|
|
66
66
|
//#endregion
|
|
67
67
|
export { ExtractedUsage as a, extractUsageFromResponse as c, ExtractUsageFromSseOptions as i, extractUsageFromSse as l, CaptureFetchOptions as n, SseUsageMode as o, captureFetchToRawSink as r, extractUsage as s, CaptureFetchContext as t };
|
|
68
|
-
//# sourceMappingURL=capture-fetch-
|
|
68
|
+
//# sourceMappingURL=capture-fetch-BBVFzhkk.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"capture-fetch-
|
|
1
|
+
{"version":3,"file":"capture-fetch-BBVFzhkk.d.ts","names":[],"sources":["../src/trace/extract-usage.ts","../src/trace/capture-fetch.ts"],"mappings":";;;KAgBY,iBAAiB;KACjB;UAEK;;EAEf,OAAO;;;;;;;iBAuDO,aAAa,gBAAgB;;;;;;iBA6C7B,oBACd,cACA,UAAS,6BACR;;;;;;;iBA4DmB,yBACpB,UAAU,UACV,aAAa,6BACZ,QAAQ;;;UCrKM;;;EAGf;;EAEA;;;EAGA;;EAEA;;EAEA;;UAGe;;EAEf,WAAW;;;EAGX;;;EAGA;;;;;;;;EAQA,WAAW,OAAO,gBAAgB,KAAK;;EAEvC,eAAe;;iBAkDD,sBACd,cAAc,WAAW,OACzB,MAAM,iBACN,KAAK,qBACL,OAAM,6BACE,WAAW"}
|
|
@@ -3,7 +3,7 @@ import { a as combineAbortSignals } from "./run-score-lDzV0X8j.js";
|
|
|
3
3
|
import { c as deepFreezeCanonicalJson, i as assertValidAnalystUsageReceipt, n as makeFinding, s as validateUsageSettlementTimeout } from "./types-BI4fT3HN.js";
|
|
4
4
|
import { R as findingSubjectGrammarPromptFor, X as spanEpochMillis, nt as snapshotExactExecutionComponentIdentity, rt as snapshotExactExecutionPlan, t as createTraceAnalyst } from "./kind-factory-DmAa0h3K.js";
|
|
5
5
|
import { LLM_CONTEXT_TOKENS, LLM_INPUT_TOKEN_ATTR_KEYS, LLM_OUTPUT_TOKEN_ATTR_KEYS, TOOL_NAME_ATTR_KEYS } from "./trace-attributes.js";
|
|
6
|
-
import { n as LlmClient } from "./llm-client-
|
|
6
|
+
import { n as LlmClient } from "./llm-client-Bg32RW0j.js";
|
|
7
7
|
import { t as executionTrackByLane } from "./execution-tracks-CpgFPpS5.js";
|
|
8
8
|
import { t as analyzeSupervisorRunIntegrity } from "./integrity-DysDBWDu.js";
|
|
9
9
|
import { randomUUID } from "node:crypto";
|
|
@@ -2449,4 +2449,4 @@ function resolveModel(req, defaultModel) {
|
|
|
2449
2449
|
//#endregion
|
|
2450
2450
|
export { validateAnalystReviewDecisions as S, analystRunDigest as _, assertExactRegistryRunOpts as a, readAnalystReview as b, KNOWLEDGE_GAP_KIND_SPEC as c, CONTROL_INTEGRITY_ANALYST as d, ControlIntegrityAnalyst as f, analystFindingDigest as g, deriveEfficiencyFindings as h, ExactAnalystRunExecutionError as i, IMPROVEMENT_KIND_SPEC as l, behavioralAnalyst as m, buildDefaultAnalystRegistry as n, DEFAULT_TRACE_ANALYST_KINDS as o, emitControlIntegrityFindings as p, AnalystRegistry as r, KNOWLEDGE_POISONING_KIND_SPEC as s, createChatClient as t, FAILURE_MODE_KIND_SPEC as u, assertUniqueFindingIds as v, snapshotAnalystRun as x, completedAnalystReviewQuality as y };
|
|
2451
2451
|
|
|
2452
|
-
//# sourceMappingURL=chat-client-
|
|
2452
|
+
//# sourceMappingURL=chat-client-2bVfrzhN.js.map
|