@tangle-network/agent-eval 0.144.8 → 0.144.10

package/CHANGELOG.md

@@ -20,6 +20,19 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 - Blind statement-equivalence protocol (`defineEquivalenceCheck`, `buildEquivalenceRecord`, `runEquivalenceCheck`): the two-arm design as a typed primitive with fail-loud refusals (`EquivalenceProtocolError`) — a non-blind arm, a wrong arm count, a refutation without its separating witness, or a mismatched checker strategy throws instead of recording.
 - `docs/verification-strategies.md`: the family, each member's failure mode, and the BCWW (4.6) formalization pilot as the worked example.
 
+## [0.144.10] - 2026-08-10 - Optimizer candidate population
+
+### Added
+
+- `readExternalOptimizerObservationArtifact()` returns every distinct callback-submitted optimizer candidate after it verifies the addressed artifact's digest, canonical rows, sequence, candidate identities, and counts.
+- `decodeExternalTextCandidate()` exposes Eval's existing canonical conversion from external text or named components to a mutable optimization surface.
+
+## [0.144.9] - 2026-08-10 - Token usage completeness
+
+### Fixed
+
+- Campaign cells and run records preserve incomplete token usage as `tokensKnown: false`; their numeric counts remain known subtotals and no token-efficiency ratio is reported.
+
 ## [0.144.8] - 2026-08-10 - Duplicate candidate admission
 
 ### Fixed

package/README.md

@@ -337,6 +337,9 @@ Read `scores` for final-case lift and intervals.
 Read `pairwise` before claiming one method beat another.
 Read `totalCost.accountingComplete` before using the reported dollars as a complete total.
 Each official method score records the optimizer and bridge package versions, source revisions and source-tree hashes, Python runtime, configured optimizer model when present, custom engine module hashes, compatible run ID, exact attempt ID, resume status, evaluation count, artifact directory, and available optimizer token usage in `provenance`.
+Call `readExternalOptimizerObservationArtifact()` with `provenance.observations` to read every distinct callback-submitted candidate.
+The reader verifies the artifact digest, canonical rows, sequence, candidate identities, and summary counts before returning candidates.
+This verification proves that the bytes match the supplied summary; use a summary from trusted method provenance when authenticity matters.
 
 The [optimizer guide](./docs/campaign-proposers.md) covers recipes, budgets, resuming, and data separation.
 The [runnable comparison](./examples/compare-optimization-methods/) can run GEPA, SkillOpt, or both.

package/dist/{agent-profile-CgDTo40f.d.ts → agent-profile-DPi7IZg7.d.ts}

@@ -1,5 +1,5 @@
-import { c as AnalystRunInputs, f as AnalystUsageReceipt, i as AnalystFinding, p as EvidenceRef, w as TraceAnalysisStore } from "./types-DF_Udrp-.js";
-import { E as AnalystRegistry, M as RegistryRunOpts } from "./completion-verifier-foUCLif_.js";
+import { c as AnalystRunInputs, f as AnalystUsageReceipt, i as AnalystFinding, p as EvidenceRef, w as TraceAnalysisStore } from "./types-BvDKaULh.js";
+import { E as AnalystRegistry, M as RegistryRunOpts } from "./completion-verifier-DJA5BhPb.js";
 import { AgentProfile, AgentProfile as AgentProfile$1, HarnessType, HarnessType as HarnessType$1 } from "@tangle-network/agent-interface";
 //#region src/analyst/benchmark-scoring.d.ts
 declare function scoreAnalystFindings(testCase: Pick<AnalystBenchmarkCase, 'id' | 'expectedIssues' | 'labeledEvidence'>, findings: readonly AnalystFinding[]): AnalystFindingScore;
@@ -320,4 +320,4 @@ declare function agentProfileModelId(profile: AgentProfile): string;
 declare function agentProfileHash(profile: AgentProfile): string;
 //#endregion
 export { registryBenchmarkRunner as A, AnalystEvidenceResolution as C, AnalystIssueExpectation as D, AnalystFindingScore as E, traceStoreEvidenceResolver as M, scoreAnalystFindings as N, AnalystLatencyDistribution as O, AnalystEvidenceExpectation as S, AnalystEvidenceResolver as T, AnalystBenchmarkOutput as _, ProfileAxisSpec as a, AnalystBenchmarkRunner as b, agentProfileModelId as c, AnalystBenchmarkCase as d, AnalystBenchmarkDatasetRef as f, AnalystBenchmarkObservation as g, AnalystBenchmarkLabelState as h, HarnessType$1 as i, runAnalystBenchmark as j, RunAnalystBenchmarkOptions as k, expandProfileAxes as l, AnalystBenchmarkError as m, CODING_HARNESSES as n, agentProfileHash as o, AnalystBenchmarkDescriptor as p, HARNESS_NATIVE_MODEL as r, agentProfileId as s, AgentProfile$1 as t, harnessAxisOf as u, AnalystBenchmarkProvenance as v, AnalystEvidenceResolutionError as w, AnalystBenchmarkSummary as x, AnalystBenchmarkResult as y };
-//# sourceMappingURL=agent-profile-CgDTo40f.d.ts.map
+//# sourceMappingURL=agent-profile-DPi7IZg7.d.ts.map

package/dist/{agent-profile-CgDTo40f.d.ts.map → agent-profile-DPi7IZg7.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"agent-profile-CgDTo40f.d.ts","names":[],"sources":["../src/analyst/benchmark-scoring.ts","../src/analyst/benchmark.ts","../src/agent-profile.ts"],"mappings":";;;;iBASgB,qBACd,UAAU,KAAK,oEACf,mBAAmB,mBAClB;;;UCIc;EACf;EACA,OAAO;;UAGQ;EACf;EACA;EACA;EACA;EACA,oBAAoB;EACpB;;EAEA,4BAA4B;;KAGlB;UAEK,qBAAqB;EACpC;;EAEA;;EAEA,YAAY;EACZ,OAAO;EACP,yBAAyB;;EAEzB,2BAA2B;EAC3B;EACA,WAAW;;UAGI;EACf;EACA;EACA;EACA;EACA;EACA,mBAAmB;EACnB;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;EACA;;UAGe;EACf,UAAU;EACV;EACA;;UAGe;EACf;EACA;EACA,oBAAoB;EACpB,QAAQ;;EAER;;KAGU,wBAAwB,qBAAqB;EACvD;EACA,WAAW;EACX,UAAU;EACV,SAAS;gBACK;;;;;iBAMA,2BAA2B,QACzC,WAAW,OAAO,WAAW,qBAC5B,wBAAwB;UAoBV;EACf,mBAAmB;EACnB,QAAQ;EACR,WAAW;;;;;EAKX;;EAEA,QAAQ;;UAGO;EACf;EACA;EACA;EACA;;UAGe,uBAAuB;EACtC;EACA,QACE,OAAO,QACP;IAAW;IAAgB;IAAoB,SAAS;MACvD,yBAAyB,QAAQ;;UAGrB;EACf;EACA;EACA;EACA,YAAY;EACZ;EACA;EACA;EACA;EACA,mBAAmB;EACnB,OAAO;EACP,qBAAqB;EACrB;EACA,eAAe;EACf,QAAQ;EACR,iBAAiB;EACjB,QAAQ;;UAGO;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;EACA,WAAW;EACX;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,UAAU;EACV;EACA,cAAc;EACd,WAAW;;UAGI,mCAAmC;EAClD;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf,YAAY;EACZ,cAAc;EACd,WAAW;;UAGI,2BAA2B;EAC1C,gBAAgB,qBAAqB;EACrC,kBAAkB,uBAAuB;EACzC;EACA;EACA;EACA,kBAAkB,wBAAwB;EAC1C,YAAY;;EAEZ,+BAA+B;EAC/B,iBAAiB,aAAa,uCAAuC;EACrE,SAAS;;iBAGW,oBAAoB,QACxC,SAAS,2BAA2B,UACnC,QAAQ;iBAyDK,wBAAwB;EACtC;EACA,UAAU;EACV,aAAa,KAAK;;EAElB;IACE,uBAAuB;;;;;;;;;;cCpUd,2BAA2B;UAOvB;;;EAGf,MAAM;;EAEN,qBAAqB;;;EAGrB;;;;;;EAMA;;;;;;;cAQW;;;;;;;;;;;;;;;;;;;iBAoBG,kBAAkB,MAAM,kBAAkB;;;;;;;;iBAwD1C,cACd,SAAS,KAAK;EACX,SAAS;EAAa;;;;;;;;;iBAiBX,eAAe,SAAS;;;;;iBASxB,oBAAoB,SAAS;;;;;;;;;;;iBA0C7B,iBAAiB,SAAS"}
+{"version":3,"file":"agent-profile-DPi7IZg7.d.ts","names":[],"sources":["../src/analyst/benchmark-scoring.ts","../src/analyst/benchmark.ts","../src/agent-profile.ts"],"mappings":";;;;iBASgB,qBACd,UAAU,KAAK,oEACf,mBAAmB,mBAClB;;;UCIc;EACf;EACA,OAAO;;UAGQ;EACf;EACA;EACA;EACA;EACA,oBAAoB;EACpB;;EAEA,4BAA4B;;KAGlB;UAEK,qBAAqB;EACpC;;EAEA;;EAEA,YAAY;EACZ,OAAO;EACP,yBAAyB;;EAEzB,2BAA2B;EAC3B;EACA,WAAW;;UAGI;EACf;EACA;EACA;EACA;EACA;EACA,mBAAmB;EACnB;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;EACA;;UAGe;EACf,UAAU;EACV;EACA;;UAGe;EACf;EACA;EACA,oBAAoB;EACpB,QAAQ;;EAER;;KAGU,wBAAwB,qBAAqB;EACvD;EACA,WAAW;EACX,UAAU;EACV,SAAS;gBACK;;;;;iBAMA,2BAA2B,QACzC,WAAW,OAAO,WAAW,qBAC5B,wBAAwB;UAoBV;EACf,mBAAmB;EACnB,QAAQ;EACR,WAAW;;;;;EAKX;;EAEA,QAAQ;;UAGO;EACf;EACA;EACA;EACA;;UAGe,uBAAuB;EACtC;EACA,QACE,OAAO,QACP;IAAW;IAAgB;IAAoB,SAAS;MACvD,yBAAyB,QAAQ;;UAGrB;EACf;EACA;EACA;EACA,YAAY;EACZ;EACA;EACA;EACA;EACA,mBAAmB;EACnB,OAAO;EACP,qBAAqB;EACrB;EACA,eAAe;EACf,QAAQ;EACR,iBAAiB;EACjB,QAAQ;;UAGO;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;EACA,WAAW;EACX;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,UAAU;EACV;EACA,cAAc;EACd,WAAW;;UAGI,mCAAmC;EAClD;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf,YAAY;EACZ,cAAc;EACd,WAAW;;UAGI,2BAA2B;EAC1C,gBAAgB,qBAAqB;EACrC,kBAAkB,uBAAuB;EACzC;EACA;EACA;EACA,kBAAkB,wBAAwB;EAC1C,YAAY;;EAEZ,+BAA+B;EAC/B,iBAAiB,aAAa,uCAAuC;EACrE,SAAS;;iBAGW,oBAAoB,QACxC,SAAS,2BAA2B,UACnC,QAAQ;iBAyDK,wBAAwB;EACtC;EACA,UAAU;EACV,aAAa,KAAK;;EAElB;IACE,uBAAuB;;;;;;;;;;cCpUd,2BAA2B;UAOvB;;;EAGf,MAAM;;EAEN,qBAAqB;;;EAGrB;;;;;;EAMA;;;;;;;cAQW;;;;;;;;;;;;;;;;;;;iBAoBG,kBAAkB,MAAM,kBAAkB;;;;;;;;iBAwD1C,cACd,SAAS,KAAK;EACX,SAAS;EAAa;;;;;;;;;iBAiBX,eAAe,SAAS;;;;;iBASxB,oBAAoB,SAAS;;;;;;;;;;;iBA0C7B,iBAAiB,SAAS"}

package/dist/analyst/index.d.ts

@@ -1,15 +1,15 @@
 import { a as MultiLayerVerifier, l as VerifyOptions, o as Severity } from "../multi-layer-verifier-DnAqwl0h.js";
-import { A as parseFindingSubject, C as FINDING_SUBJECT_KINDS, D as FindingSubjectStringSchema, E as FindingSubjectKind, F as DefineExactCustomAnalystOptions, G as SemanticConceptJudgeOptions, I as defineCustomAnalyst, L as defineTraceAnalyst, M as DspyRlmTraceEngineOptions, N as createDspyRlmTraceEngine, O as KIND_EXPECTED_SUBJECTS, P as DefineCustomAnalystOptions, S as FINDING_SUBJECT_GRAMMAR_PROMPT, T as FindingSubject, W as SemanticConceptJudgeInput, Y as RunCritic, Z as RunTrace, _ as FindingsDiff, a as SkillUsageScanConfig, b as defaultIsMaterial, c as DEFAULT_TRACE_ANALYST_KINDS, d as IMPROVEMENT_KIND_SPEC, f as FAILURE_MODE_KIND_SPEC, g as DiffPolicy, h as emitControlIntegrityFindings, i as SkillUsageReport, j as renderFindingSubject, k as findingSubjectGrammarPromptFor, l as KNOWLEDGE_POISONING_KIND_SPEC, m as ControlIntegrityAnalyst, n as SkillUsageAnalyst, o as buildSkillUsageReport, p as CONTROL_INTEGRITY_ANALYST, r as SkillUsageRecord, s as emitSkillUsageFindings, t as SKILL_USAGE_ANALYST, u as KNOWLEDGE_GAP_KIND_SPEC, v as FindingsStore, w as FINDING_SUBJECT_SYNTAX, x as diffFindings, y as PersistedFinding } from "../skill-usage-CJlWEUFt.js";
+import { A as parseFindingSubject, C as FINDING_SUBJECT_KINDS, D as FindingSubjectStringSchema, E as FindingSubjectKind, F as DefineExactCustomAnalystOptions, G as SemanticConceptJudgeOptions, I as defineCustomAnalyst, L as defineTraceAnalyst, M as DspyRlmTraceEngineOptions, N as createDspyRlmTraceEngine, O as KIND_EXPECTED_SUBJECTS, P as DefineCustomAnalystOptions, S as FINDING_SUBJECT_GRAMMAR_PROMPT, T as FindingSubject, W as SemanticConceptJudgeInput, Y as RunCritic, Z as RunTrace, _ as FindingsDiff, a as SkillUsageScanConfig, b as defaultIsMaterial, c as DEFAULT_TRACE_ANALYST_KINDS, d as IMPROVEMENT_KIND_SPEC, f as FAILURE_MODE_KIND_SPEC, g as DiffPolicy, h as emitControlIntegrityFindings, i as SkillUsageReport, j as renderFindingSubject, k as findingSubjectGrammarPromptFor, l as KNOWLEDGE_POISONING_KIND_SPEC, m as ControlIntegrityAnalyst, n as SkillUsageAnalyst, o as buildSkillUsageReport, p as CONTROL_INTEGRITY_ANALYST, r as SkillUsageRecord, s as emitSkillUsageFindings, t as SKILL_USAGE_ANALYST, u as KNOWLEDGE_GAP_KIND_SPEC, v as FindingsStore, w as FINDING_SUBJECT_SYNTAX, x as diffFindings, y as PersistedFinding } from "../skill-usage-CO9OLRBx.js";
 import { b as CustomTokenPricing, c as CostLedgerHandle } from "../cost-ledger-Bv_e8XHY.js";
 import { A as ChatClient, B as SandboxSdkTransportOpts, F as CreateChatClientOpts, I as CustomTransportOpts, L as DirectProviderTransportOpts, M as ChatResponse, N as ChatTransport, P as CliBridgeTransportOpts, R as MockTransportOpts, V as createChatClient, j as ChatRequest, k as ChatCallOpts, m as JudgeInput, p as JudgeFn, z as RouterTransportOpts } from "../types-D216SgwM.js";
-import { I as TraceAnalystSpan, _ as ProposalFinding, a as AnalystInputKind, b as makeFinding, c as AnalystRunInputs, d as AnalystSeverity, f as AnalystUsageReceipt, g as ExecutionProbeRequest, h as ExecutionProbeOutcome, i as AnalystFinding, l as AnalystRunResult, m as ExecutionProbe, n as AnalystContext, o as AnalystRequirements, p as EvidenceRef, r as AnalystCost, s as AnalystRunEvent, t as Analyst, u as AnalystRunSummary, v as ProposalFindingOrigin, w as TraceAnalysisStore, x as makeProposalFinding, y as computeFindingId } from "../types-DF_Udrp-.js";
-import { a as createTraceAnalyst, c as runTraceAnalyst, d as deriveEfficiencyFindings, i as TraceAnalystDefinition, l as BehavioralAnalystOptions, n as buildDefaultAnalystRegistry, o as renderPriorFindings, r as CreateTraceAnalystOptions, s as renderUpstreamFindings, t as DefaultAnalystRegistryOptions, u as behavioralAnalyst } from "../default-registry-BZhStdjl.js";
-import { a as ExactAnalystRunPolicySnapshot, c as ExactAnalystSnapshot, d as ExactExecutionComponentSnapshot, i as ExactAnalystRunEvent, l as ExactCapableAnalyst, n as ExactAnalystExecutionPlanSnapshot, o as ExactAnalystRunResult, r as ExactAnalystRunCompletion, s as ExactAnalystRunSummary, t as ExactAnalystBudgetSnapshot, u as ExactExecutionComponentIdentity } from "../exact-types-Djvzosly.js";
-import { A as ExactAnalystRunExecutionError, D as AnalystRegistryOptions, E as AnalystRegistry, M as RegistryRunOpts, N as assertExactRegistryRunOpts, O as BudgetPolicy, T as AnalystHooks, j as ExactRegistryRunOpts, k as ExactAnalystBudgetPolicy } from "../completion-verifier-foUCLif_.js";
-import { A as registryBenchmarkRunner, C as AnalystEvidenceResolution, D as AnalystIssueExpectation, E as AnalystFindingScore, M as traceStoreEvidenceResolver, N as scoreAnalystFindings, O as AnalystLatencyDistribution, S as AnalystEvidenceExpectation, T as AnalystEvidenceResolver, _ as AnalystBenchmarkOutput, b as AnalystBenchmarkRunner, d as AnalystBenchmarkCase, f as AnalystBenchmarkDatasetRef, g as AnalystBenchmarkObservation, h as AnalystBenchmarkLabelState, j as runAnalystBenchmark, k as RunAnalystBenchmarkOptions, m as AnalystBenchmarkError, p as AnalystBenchmarkDescriptor, t as AgentProfile, v as AnalystBenchmarkProvenance, w as AnalystEvidenceResolutionError, x as AnalystBenchmarkSummary, y as AnalystBenchmarkResult } from "../agent-profile-CgDTo40f.js";
+import { I as TraceAnalystSpan, _ as ProposalFinding, a as AnalystInputKind, b as makeFinding, c as AnalystRunInputs, d as AnalystSeverity, f as AnalystUsageReceipt, g as ExecutionProbeRequest, h as ExecutionProbeOutcome, i as AnalystFinding, l as AnalystRunResult, m as ExecutionProbe, n as AnalystContext, o as AnalystRequirements, p as EvidenceRef, r as AnalystCost, s as AnalystRunEvent, t as Analyst, u as AnalystRunSummary, v as ProposalFindingOrigin, w as TraceAnalysisStore, x as makeProposalFinding, y as computeFindingId } from "../types-BvDKaULh.js";
+import { a as createTraceAnalyst, c as runTraceAnalyst, d as deriveEfficiencyFindings, i as TraceAnalystDefinition, l as BehavioralAnalystOptions, n as buildDefaultAnalystRegistry, o as renderPriorFindings, r as CreateTraceAnalystOptions, s as renderUpstreamFindings, t as DefaultAnalystRegistryOptions, u as behavioralAnalyst } from "../default-registry-Bf8Woqmq.js";
+import { a as ExactAnalystRunPolicySnapshot, c as ExactAnalystSnapshot, d as ExactExecutionComponentSnapshot, i as ExactAnalystRunEvent, l as ExactCapableAnalyst, n as ExactAnalystExecutionPlanSnapshot, o as ExactAnalystRunResult, r as ExactAnalystRunCompletion, s as ExactAnalystRunSummary, t as ExactAnalystBudgetSnapshot, u as ExactExecutionComponentIdentity } from "../exact-types-DSFFpLLI.js";
+import { A as ExactAnalystRunExecutionError, D as AnalystRegistryOptions, E as AnalystRegistry, M as RegistryRunOpts, N as assertExactRegistryRunOpts, O as BudgetPolicy, T as AnalystHooks, j as ExactRegistryRunOpts, k as ExactAnalystBudgetPolicy } from "../completion-verifier-DJA5BhPb.js";
+import { A as registryBenchmarkRunner, C as AnalystEvidenceResolution, D as AnalystIssueExpectation, E as AnalystFindingScore, M as traceStoreEvidenceResolver, N as scoreAnalystFindings, O as AnalystLatencyDistribution, S as AnalystEvidenceExpectation, T as AnalystEvidenceResolver, _ as AnalystBenchmarkOutput, b as AnalystBenchmarkRunner, d as AnalystBenchmarkCase, f as AnalystBenchmarkDatasetRef, g as AnalystBenchmarkObservation, h as AnalystBenchmarkLabelState, j as runAnalystBenchmark, k as RunAnalystBenchmarkOptions, m as AnalystBenchmarkError, p as AnalystBenchmarkDescriptor, t as AgentProfile, v as AnalystBenchmarkProvenance, w as AnalystEvidenceResolutionError, x as AnalystBenchmarkSummary, y as AnalystBenchmarkResult } from "../agent-profile-DPi7IZg7.js";
 import { f as ExternalOptimizerModelExecutionObservation, h as ExternalOptimizerRunnerCommand, l as ExternalOptimizerModelCall } from "../external-optimizer-contracts-CZuJNcT5.js";
-import { a as TraceAnalystLimits, c as RAW_FINDING_SCHEMA_PROMPT, d as RawAnalystFinding, f as RawAnalystFindingSchema, i as TraceAnalysisEngineResult, l as RawAnalystEvidence, m as parseRawFinding, n as TraceAnalysisEngine, o as resolveTraceAnalystLimits, p as evidenceRefsFromRawFinding, r as TraceAnalysisEngineRequest, s as ANALYST_SEVERITIES, t as DEFAULT_TRACE_ANALYST_LIMITS, u as RawAnalystEvidenceSchema } from "../engine-nB64f48I.js";
-import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-DIVBnJyl.js";
+import { a as TraceAnalystLimits, c as RAW_FINDING_SCHEMA_PROMPT, d as RawAnalystFinding, f as RawAnalystFindingSchema, i as TraceAnalysisEngineResult, l as RawAnalystEvidence, m as parseRawFinding, n as TraceAnalysisEngine, o as resolveTraceAnalystLimits, p as evidenceRefsFromRawFinding, r as TraceAnalysisEngineRequest, s as ANALYST_SEVERITIES, t as DEFAULT_TRACE_ANALYST_LIMITS, u as RawAnalystEvidenceSchema } from "../engine-3hL-XqwJ.js";
+import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-CZPGGlHf.js";
 import { i as nodeHttpPrimeBridgeTransport, n as PrimeBridgeTransportRequest, r as PrimeBridgeTransportResult, t as PrimeBridgeTransport } from "../prime-bridge-transport-6feEglLf.js";
 import { z } from "zod";
 //#region src/analyst/adapters.d.ts
@@ -1274,7 +1274,7 @@ declare const ANALYST_BENCHMARK_HELP = "agent-eval analyst-benchmark\n\nRun the
 declare const ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM = "sha256-canonical-source-manifest";
 declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM = "sha256-canonical-file-manifest";
 declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES: readonly string[];
-declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "788e0d4e228836e84b4cf31492c9a0f7c884efcce088623988f9c378c768ef7c";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "951c42191f617a9128ac81ed1af189275397c5a2fe965c8a3c694cf91a26c508";
 /** The published benchmark evidence was produced at this package version, by
  * the retired one-shot direct runner, before trace analysts moved to the
  * recursive DSPy RLM engine. Both evidence digests below are historical facts

package/dist/analyst/index.js

@@ -1,12 +1,12 @@
 import { i as CostLedger } from "../cost-ledger-DMFxsLKr.js";
-import { C as createChatClient, _ as CONTROL_INTEGRITY_ANALYST, b as behavioralAnalyst, f as DEFAULT_TRACE_ANALYST_KINDS, g as FAILURE_MODE_KIND_SPEC, h as IMPROVEMENT_KIND_SPEC, i as assertExactRegistryRunOpts, m as KNOWLEDGE_GAP_KIND_SPEC, n as AnalystRegistry, p as KNOWLEDGE_POISONING_KIND_SPEC, r as ExactAnalystRunExecutionError, t as buildDefaultAnalystRegistry, v as ControlIntegrityAnalyst, x as deriveEfficiencyFindings, y as emitControlIntegrityFindings } from "../default-registry-BaQXW1Ow.js";
-import { A as coerceJson, B as renderFindingSubject, D as RawAnalystFindingSchema, E as RawAnalystEvidenceSchema, F as FINDING_SUBJECT_SYNTAX, G as resolveTraceAnalystLimits, I as FindingSubjectStringSchema, L as KIND_EXPECTED_SUBJECTS, M as stripCodeFences, N as FINDING_SUBJECT_GRAMMAR_PROMPT, O as evidenceRefsFromRawFinding, P as FINDING_SUBJECT_KINDS, R as findingSubjectGrammarPromptFor, T as RAW_FINDING_SCHEMA_PROMPT, W as DEFAULT_TRACE_ANALYST_LIMITS, a as buildTraceToolsForGroup, i as runTraceAnalyst, j as coerceToFindingRows, k as parseRawFinding, n as renderPriorFindings, r as renderUpstreamFindings, t as createTraceAnalyst, w as ANALYST_SEVERITIES, z as parseFindingSubject } from "../kind-factory-BHIgPmzS.js";
-import { a as computeFindingId, i as validateUsageSettlementTimeout, n as settleUsageReceiptFromCostLedger, o as makeFinding, s as makeProposalFinding } from "../usage-receipt-EVI8B8Xu.js";
+import { C as createChatClient, _ as CONTROL_INTEGRITY_ANALYST, b as behavioralAnalyst, f as DEFAULT_TRACE_ANALYST_KINDS, g as FAILURE_MODE_KIND_SPEC, h as IMPROVEMENT_KIND_SPEC, i as assertExactRegistryRunOpts, m as KNOWLEDGE_GAP_KIND_SPEC, n as AnalystRegistry, p as KNOWLEDGE_POISONING_KIND_SPEC, r as ExactAnalystRunExecutionError, t as buildDefaultAnalystRegistry, v as ControlIntegrityAnalyst, x as deriveEfficiencyFindings, y as emitControlIntegrityFindings } from "../default-registry-BmktKy8r.js";
+import { A as coerceJson, B as renderFindingSubject, D as RawAnalystFindingSchema, E as RawAnalystEvidenceSchema, F as FINDING_SUBJECT_SYNTAX, I as FindingSubjectStringSchema, L as KIND_EXPECTED_SUBJECTS, M as stripCodeFences, N as FINDING_SUBJECT_GRAMMAR_PROMPT, O as evidenceRefsFromRawFinding, P as FINDING_SUBJECT_KINDS, R as findingSubjectGrammarPromptFor, T as RAW_FINDING_SCHEMA_PROMPT, U as DEFAULT_TRACE_ANALYST_LIMITS, W as resolveTraceAnalystLimits, a as buildTraceToolsForGroup, i as runTraceAnalyst, j as coerceToFindingRows, k as parseRawFinding, n as renderPriorFindings, r as renderUpstreamFindings, t as createTraceAnalyst, w as ANALYST_SEVERITIES, z as parseFindingSubject } from "../kind-factory-B8-r8-y8.js";
+import { c as makeProposalFinding, i as validateUsageSettlementTimeout, n as settleUsageReceiptFromCostLedger, o as computeFindingId, s as makeFinding } from "../usage-receipt-t7vAzCRQ.js";
 import { n as isProposalFinding, t as assertProposalFindings } from "../proposal-findings-2GIUo1et.js";
-import { a as RunCritic, c as buildSkillUsageReport, d as defaultIsMaterial, f as diffFindings, h as defineTraceAnalyst, i as runSemanticConceptJudge, l as emitSkillUsageFindings, m as defineCustomAnalyst, n as SEMANTIC_CONCEPT_JUDGE_VERSION, o as SKILL_USAGE_ANALYST, s as SkillUsageAnalyst, u as FindingsStore } from "../semantic-concept-judge-Bmrq6yqU.js";
-import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-BiN49gK6.js";
-import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-B181aMF9.js";
-import { $ as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, A as summarizeCodeTraceCalibration, B as publicBenchmarkSystemPrompt, C as analystDefinitionAsymmetries, D as expandCodeTraceFailureBlocks, E as emptyPublicBenchmarkRunner, F as CODE_TRACE_BENCH_ANALYST_PROMPT, G as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, H as appendVerificationArtifactsToOtlp, I as MAX_INCORRECT_BLOCKS, J as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, K as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, L as MAX_INCORRECT_BLOCK_STEPS, M as analystInstructionsOverrideFromText, N as effectiveAnalystProtocolSha256, O as readAnalystBenchmarkArtifact, P as readAnalystInstructionsOverride, Q as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, R as publicBenchmarkProtocolSha256, S as AnalystExpressivenessError, T as adaptPublicBenchmarkFindings, U as loadCodeTraceVerificationArtifacts, V as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, W as parseVerificationOutcome, X as ANALYST_BENCHMARK_EVIDENCE_PACKAGE_VERSION, Y as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, Z as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, _ as runReplVariableAnalystDefinition, a as primeAnalystProtocolSha256, at as ANALYST_BENCHMARK_OBSERVATIONS_FILE, b as runChunkedAnalystDefinition, c as nodeHttpPrimeBridgeTransport, ct as summarizeAgentRxCalibration, d as publicBenchmarkDistributions, dt as agentRxBenchmarkCase, et as analystBenchmarkDependencyLockDigest, f as publicBenchmarkSelectionReport, ft as agentRxPredictionsToFindings, g as rlmEngineLimits, h as publicRlmAnalystDefinition, ht as normalizeBenchmarkLabel, i as createPrimeBenchmarkRunner, it as ANALYST_BENCHMARK_MANIFEST_FILE, j as compareAnalystRunners, k as renderCodeTraceCalibrationMarkdown, l as loadPublicBenchmarkRows, lt as codeTraceBenchCase, m as createPublicBenchmarkRlmRunner, mt as roundAgentRxStep, n as runAnalystBenchmarkCommand, nt as ANALYST_BENCHMARK_COST_LEDGER_FILE, o as primeCodeTraceAnalystDefinition, ot as AGENT_RX_UPSTREAM_REVISION, p as selectPublicBenchmarkRows, pt as normalizeAgentRxCategory, q as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, r as renderAnalystBenchmarkMarkdown, rt as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, s as runInlineAnalystDefinition, st as renderAgentRxCalibrationMarkdown, t as ANALYST_BENCHMARK_HELP, tt as analystBenchmarkImplementationDigest, u as preparePublicAnalystBenchmark, ut as codeTracerPredictionsToFindings, v as createPublicBenchmarkDirectRunner, w as analystDefinitionProtocolSha256, x as decodeReplyRows, y as publicDirectAnalystDefinition, z as publicBenchmarkRlmInstructions } from "../benchmark-command-BKENp2s5.js";
+import { a as RunCritic, c as buildSkillUsageReport, d as defaultIsMaterial, f as diffFindings, h as defineTraceAnalyst, i as runSemanticConceptJudge, l as emitSkillUsageFindings, m as defineCustomAnalyst, n as SEMANTIC_CONCEPT_JUDGE_VERSION, o as SKILL_USAGE_ANALYST, s as SkillUsageAnalyst, u as FindingsStore } from "../semantic-concept-judge-D1z-KepS.js";
+import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-DbTk4JdR.js";
+import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-CWeqGl7x.js";
+import { $ as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, A as summarizeCodeTraceCalibration, B as publicBenchmarkSystemPrompt, C as analystDefinitionAsymmetries, D as expandCodeTraceFailureBlocks, E as emptyPublicBenchmarkRunner, F as CODE_TRACE_BENCH_ANALYST_PROMPT, G as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, H as appendVerificationArtifactsToOtlp, I as MAX_INCORRECT_BLOCKS, J as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, K as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, L as MAX_INCORRECT_BLOCK_STEPS, M as analystInstructionsOverrideFromText, N as effectiveAnalystProtocolSha256, O as readAnalystBenchmarkArtifact, P as readAnalystInstructionsOverride, Q as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, R as publicBenchmarkProtocolSha256, S as AnalystExpressivenessError, T as adaptPublicBenchmarkFindings, U as loadCodeTraceVerificationArtifacts, V as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, W as parseVerificationOutcome, X as ANALYST_BENCHMARK_EVIDENCE_PACKAGE_VERSION, Y as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, Z as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, _ as runReplVariableAnalystDefinition, a as primeAnalystProtocolSha256, at as ANALYST_BENCHMARK_OBSERVATIONS_FILE, b as runChunkedAnalystDefinition, c as nodeHttpPrimeBridgeTransport, ct as summarizeAgentRxCalibration, d as publicBenchmarkDistributions, dt as agentRxBenchmarkCase, et as analystBenchmarkDependencyLockDigest, f as publicBenchmarkSelectionReport, ft as agentRxPredictionsToFindings, g as rlmEngineLimits, h as publicRlmAnalystDefinition, ht as normalizeBenchmarkLabel, i as createPrimeBenchmarkRunner, it as ANALYST_BENCHMARK_MANIFEST_FILE, j as compareAnalystRunners, k as renderCodeTraceCalibrationMarkdown, l as loadPublicBenchmarkRows, lt as codeTraceBenchCase, m as createPublicBenchmarkRlmRunner, mt as roundAgentRxStep, n as runAnalystBenchmarkCommand, nt as ANALYST_BENCHMARK_COST_LEDGER_FILE, o as primeCodeTraceAnalystDefinition, ot as AGENT_RX_UPSTREAM_REVISION, p as selectPublicBenchmarkRows, pt as normalizeAgentRxCategory, q as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, r as renderAnalystBenchmarkMarkdown, rt as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, s as runInlineAnalystDefinition, st as renderAgentRxCalibrationMarkdown, t as ANALYST_BENCHMARK_HELP, tt as analystBenchmarkImplementationDigest, u as preparePublicAnalystBenchmark, ut as codeTracerPredictionsToFindings, v as createPublicBenchmarkDirectRunner, w as analystDefinitionProtocolSha256, x as decodeReplyRows, y as publicDirectAnalystDefinition, z as publicBenchmarkRlmInstructions } from "../benchmark-command-D3fEnKdf.js";
 import { a as extractPrimeJsonObject, c as primeProtocolSha256, d as runPrimeExchange, i as emptyPrimeRawUsage, l as primeReplyDefect, n as buildPrimePrompt, o as mergePrimeRawUsage, r as buildPrimeRepairPrompt, s as normalizePrimeUsage, t as analystUsageReceiptFromPrimeUsage, u as projectPrimeTrajectory } from "../prime-protocol-BfSalTfR.js";
 //#region src/analyst/adapters.ts
 /**

package/dist/{analyze-runs-BNNK7irB.js → analyze-runs-C30yljDJ.js}

@@ -1,7 +1,7 @@
 import { r as observedSplitScore } from "./reward-nw2xZGZG.js";
 import { D as pairedCohensDz, E as pairedBootstrap, L as pearsonR, P as pairedTTest, V as spearmanR, Z as continuousAgreement, k as pairedMde, z as requiredPairedSampleSize } from "./statistics-ByxzSiOM.js";
 import { r as pairRunRecords } from "./paired-arms-iZ08VFMN.js";
-import { s as validateRunRecord } from "./run-record-DqOw5X6_.js";
+import { s as validateRunRecord } from "./run-record-BmSPWXJR.js";
 import { r as welchsTTest } from "./baseline-C-GocmIW.js";
 import { o as llmSpans } from "./query-Di7eEQ79.js";
 import { r as paretoChart } from "./summary-report-Lf-5I7xh.js";
@@ -1079,4 +1079,4 @@ function buildRecommendations(ctx) {
 //#endregion
 export { checkBehavioralCanary as a, canaryLeakView as i, summarizeExecution as n, checkCanaries as o, HoldoutAuditor as r, runBehavioralCanaries as s, analyzeRuns as t };
 
-//# sourceMappingURL=analyze-runs-BNNK7irB.js.map
+//# sourceMappingURL=analyze-runs-C30yljDJ.js.map