@tangle-network/agent-eval 0.145.6 → 0.145.7

package/CHANGELOG.md

@@ -8,6 +8,16 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [0.145.7] — 2026-08-13
+
+### Fixed
+
+- `runProfileMatrix()` now retains failed moving-model cells when no served model was observed.
+- These rows use explicit unknown model, uncaptured cost, and incomplete usage markers instead of fabricated snapshots or zero measurements.
+- Successful moving-model cells still require one immutable served model snapshot.
+
+---
+
 ## [0.145.6] — 2026-08-13
 
 ### Fixed

package/README.md

@@ -159,6 +159,10 @@ The campaign cell remains failed and unscored, so this protocol penalty is not a
 The failed cell is not cached; a later request retries it with a fresh `ctx.runAttemptId`, while completed cells remain resumable.
 Set `abortOnCellError: true` to keep fail-fast behavior.
 
+`runProfileMatrix()` retains a failed cell when a moving model alias produced no served model snapshot.
+The row carries `model: 'unknown'`, uncaptured cost, and incomplete token usage so downstream reports can count the failure without inventing measurements.
+Successful moving-model cells still require one immutable served snapshot.
+
 ## Adapt Another Text Optimizer
 
 Use `externalTextOptimizationMethod()` when an existing package owns search and selection for a text prompt or named text components.

package/dist/analyst/index.d.ts

@@ -1,19 +1,19 @@
 import { a as MultiLayerVerifier, c as VerifyOptions, o as Severity } from "../multi-layer-verifier-DIguZc8Z.js";
-import { A as SemanticConceptJudgeInput, C as parseFindingSubject, E as createDspyRlmTraceEngine, F as RunScoreWeights, P as RunScore, S as findingSubjectGrammarPromptFor, T as DspyRlmTraceEngineOptions, _ as FINDING_SUBJECT_SYNTAX, a as FAILURE_MODE_KIND_SPEC, b as FindingSubjectStringSchema, c as emitControlIntegrityFindings, d as FindingsStore, f as PersistedFinding, g as FINDING_SUBJECT_KINDS, h as FINDING_SUBJECT_GRAMMAR_PROMPT, i as IMPROVEMENT_KIND_SPEC, j as SemanticConceptJudgeOptions, l as DiffPolicy, m as diffFindings, n as KNOWLEDGE_POISONING_KIND_SPEC, o as CONTROL_INTEGRITY_ANALYST, p as defaultIsMaterial, r as KNOWLEDGE_GAP_KIND_SPEC, s as ControlIntegrityAnalyst, t as DEFAULT_TRACE_ANALYST_KINDS, u as FindingsDiff, v as FindingSubject, w as renderFindingSubject, x as KIND_EXPECTED_SUBJECTS, y as FindingSubjectKind } from "../index-PgqfwhsM.js";
+import { A as SemanticConceptJudgeInput, C as parseFindingSubject, E as createDspyRlmTraceEngine, F as RunScoreWeights, P as RunScore, S as findingSubjectGrammarPromptFor, T as DspyRlmTraceEngineOptions, _ as FINDING_SUBJECT_SYNTAX, a as FAILURE_MODE_KIND_SPEC, b as FindingSubjectStringSchema, c as emitControlIntegrityFindings, d as FindingsStore, f as PersistedFinding, g as FINDING_SUBJECT_KINDS, h as FINDING_SUBJECT_GRAMMAR_PROMPT, i as IMPROVEMENT_KIND_SPEC, j as SemanticConceptJudgeOptions, l as DiffPolicy, m as diffFindings, n as KNOWLEDGE_POISONING_KIND_SPEC, o as CONTROL_INTEGRITY_ANALYST, p as defaultIsMaterial, r as KNOWLEDGE_GAP_KIND_SPEC, s as ControlIntegrityAnalyst, t as DEFAULT_TRACE_ANALYST_KINDS, u as FindingsDiff, v as FindingSubject, w as renderFindingSubject, x as KIND_EXPECTED_SUBJECTS, y as FindingSubjectKind } from "../index-YrUFx3FU.js";
 import { b as CustomTokenPricing, c as CostLedgerHandle } from "../cost-ledger-DbQdN3nO.js";
 import { C as TraceEvent, _ as Span, f as Run, n as BudgetLedgerEntry, t as Artifact } from "../schema-BtVldJ3T.js";
 import { C as SandboxSdkTransportOpts, S as RouterTransportOpts, _ as CliBridgeTransportOpts, a as JudgeInput, b as DirectProviderTransportOpts, f as ChatCallOpts, g as ChatTransport, h as ChatResponse, i as JudgeFn, m as ChatRequest, p as ChatClient, v as CreateChatClientOpts, w as createChatClient, x as MockTransportOpts, y as CustomTransportOpts } from "../types-Cx3YUh2r.js";
 import { s as TraceStore } from "../store-CT9YIIve.js";
-import "../index-Ba3YrbAL.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-DLQx4mKU.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-CgzxnJsj.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-BH1twmAJ.js";
-import { a as ExactAnalystBudgetPolicy, c as RegistryRunOpts, i as BudgetPolicy, l as assertExactRegistryRunOpts, n as AnalystRegistry, o as ExactAnalystRunExecutionError, r as AnalystRegistryOptions, s as ExactRegistryRunOpts, t as AnalystHooks } from "../registry-oJeeI4-a.js";
-import { C as scoreAnalystFindings, S as traceStoreEvidenceResolver, _ as AnalystIssueExpectation, a as AnalystBenchmarkLabelState, b as registryBenchmarkRunner, c as AnalystBenchmarkProvenance, d as AnalystBenchmarkSummary, f as AnalystEvidenceExpectation, g as AnalystFindingScore, h as AnalystEvidenceResolver, i as AnalystBenchmarkError, l as AnalystBenchmarkResult, m as AnalystEvidenceResolutionError, n as AnalystBenchmarkDatasetRef, o as AnalystBenchmarkObservation, p as AnalystEvidenceResolution, r as AnalystBenchmarkDescriptor, s as AnalystBenchmarkOutput, t as AnalystBenchmarkCase, u as AnalystBenchmarkRunner, v as AnalystLatencyDistribution, x as runAnalystBenchmark, y as RunAnalystBenchmarkOptions } from "../benchmark-Ceoan7vk.js";
+import "../index-BKShPTwZ.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-vXyshMwx.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-cpHtP2Og.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-CzbhVDr2.js";
+import { a as ExactAnalystBudgetPolicy, c as RegistryRunOpts, i as BudgetPolicy, l as assertExactRegistryRunOpts, n as AnalystRegistry, o as ExactAnalystRunExecutionError, r as AnalystRegistryOptions, s as ExactRegistryRunOpts, t as AnalystHooks } from "../registry-B_1Frl8a.js";
+import { C as scoreAnalystFindings, S as traceStoreEvidenceResolver, _ as AnalystIssueExpectation, a as AnalystBenchmarkLabelState, b as registryBenchmarkRunner, c as AnalystBenchmarkProvenance, d as AnalystBenchmarkSummary, f as AnalystEvidenceExpectation, g as AnalystFindingScore, h as AnalystEvidenceResolver, i as AnalystBenchmarkError, l as AnalystBenchmarkResult, m as AnalystEvidenceResolutionError, n as AnalystBenchmarkDatasetRef, o as AnalystBenchmarkObservation, p as AnalystEvidenceResolution, r as AnalystBenchmarkDescriptor, s as AnalystBenchmarkOutput, t as AnalystBenchmarkCase, u as AnalystBenchmarkRunner, v as AnalystLatencyDistribution, x as runAnalystBenchmark, y as RunAnalystBenchmarkOptions } from "../benchmark-DbiZbPdH.js";
 import { f as ExternalOptimizerModelExecutionObservation, h as ExternalOptimizerRunnerCommand, l as ExternalOptimizerModelCall } from "../external-optimizer-contracts-lixrOZdX.js";
 import { t as AgentProfile } from "../agent-profile-B9_GGsG8.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-FRZ3RLvT.js";
-import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-BdcoEgtV.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-DJqRKbhs.js";
+import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-CZotz-e_.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/run-critic.d.ts
@@ -1299,7 +1299,7 @@ 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 = "34a180bb19abb605cd8190bc854f7ff1574fb3a5951706cccc49261dd32e96e6";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "599faa767a84b62fd8ffcb085175a643d88f040c45ed24bed0cf9b5f501e257b";
 /** 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

@@ -7,7 +7,7 @@ import { a as assertExactRegistryRunOpts, c as KNOWLEDGE_GAP_KIND_SPEC, d as CON
 import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-BZ2aMZEd.js";
 import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-BiJxScqe.js";
 import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-BhT16ep9.js";
-import { $ as analystBenchmarkDependencyLockDigest, A as compareAnalystRunners, B as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, C as analystDefinitionProtocolSha256, D as readAnalystBenchmarkArtifact, E as expandCodeTraceFailureBlocks, F as MAX_INCORRECT_BLOCKS, G as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, H as loadCodeTraceVerificationArtifacts, I as MAX_INCORRECT_BLOCK_STEPS, J as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, K as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, L as publicBenchmarkProtocolSha256, M as effectiveAnalystProtocolSha256, N as readAnalystInstructionsOverride, O as renderCodeTraceCalibrationMarkdown, P as CODE_TRACE_BENCH_ANALYST_PROMPT, Q as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, R as publicBenchmarkRlmInstructions, S as analystDefinitionAsymmetries, T as emptyPublicBenchmarkRunner, U as parseVerificationOutcome, V as appendVerificationArtifactsToOtlp, W as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, X as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, Y as ANALYST_BENCHMARK_EVIDENCE_PACKAGE_VERSION, Z as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, _ as runReplVariableAnalystDefinition, a as primeAnalystProtocolSha256, at as AGENT_RX_UPSTREAM_REVISION, b as runChunkedAnalystDefinition, c as nodeHttpPrimeBridgeTransport, ct as codeTraceBenchCase, d as publicBenchmarkDistributions, dt as agentRxPredictionsToFindings, et as analystBenchmarkImplementationDigest, f as publicBenchmarkSelectionReport, ft as normalizeAgentRxCategory, g as rlmEngineLimits, h as publicRlmAnalystDefinition, i as createPrimeBenchmarkRunner, it as ANALYST_BENCHMARK_OBSERVATIONS_FILE, j as analystInstructionsOverrideFromText, k as summarizeCodeTraceCalibration, l as loadPublicBenchmarkRows, lt as codeTracerPredictionsToFindings, m as createPublicBenchmarkRlmRunner, mt as normalizeBenchmarkLabel, n as runAnalystBenchmarkCommand, nt as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, o as primeCodeTraceAnalystDefinition, ot as renderAgentRxCalibrationMarkdown, p as selectPublicBenchmarkRows, pt as roundAgentRxStep, q as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, r as renderAnalystBenchmarkMarkdown, rt as ANALYST_BENCHMARK_MANIFEST_FILE, s as runInlineAnalystDefinition, st as summarizeAgentRxCalibration, t as ANALYST_BENCHMARK_HELP, tt as ANALYST_BENCHMARK_COST_LEDGER_FILE, u as preparePublicAnalystBenchmark, ut as agentRxBenchmarkCase, v as createPublicBenchmarkDirectRunner, w as adaptPublicBenchmarkFindings, x as AnalystExpressivenessError, y as publicDirectAnalystDefinition, z as publicBenchmarkSystemPrompt } from "../benchmark-command-DspwA7cv.js";
+import { $ as analystBenchmarkDependencyLockDigest, A as compareAnalystRunners, B as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, C as analystDefinitionProtocolSha256, D as readAnalystBenchmarkArtifact, E as expandCodeTraceFailureBlocks, F as MAX_INCORRECT_BLOCKS, G as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, H as loadCodeTraceVerificationArtifacts, I as MAX_INCORRECT_BLOCK_STEPS, J as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, K as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, L as publicBenchmarkProtocolSha256, M as effectiveAnalystProtocolSha256, N as readAnalystInstructionsOverride, O as renderCodeTraceCalibrationMarkdown, P as CODE_TRACE_BENCH_ANALYST_PROMPT, Q as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, R as publicBenchmarkRlmInstructions, S as analystDefinitionAsymmetries, T as emptyPublicBenchmarkRunner, U as parseVerificationOutcome, V as appendVerificationArtifactsToOtlp, W as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, X as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, Y as ANALYST_BENCHMARK_EVIDENCE_PACKAGE_VERSION, Z as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, _ as runReplVariableAnalystDefinition, a as primeAnalystProtocolSha256, at as AGENT_RX_UPSTREAM_REVISION, b as runChunkedAnalystDefinition, c as nodeHttpPrimeBridgeTransport, ct as codeTraceBenchCase, d as publicBenchmarkDistributions, dt as agentRxPredictionsToFindings, et as analystBenchmarkImplementationDigest, f as publicBenchmarkSelectionReport, ft as normalizeAgentRxCategory, g as rlmEngineLimits, h as publicRlmAnalystDefinition, i as createPrimeBenchmarkRunner, it as ANALYST_BENCHMARK_OBSERVATIONS_FILE, j as analystInstructionsOverrideFromText, k as summarizeCodeTraceCalibration, l as loadPublicBenchmarkRows, lt as codeTracerPredictionsToFindings, m as createPublicBenchmarkRlmRunner, mt as normalizeBenchmarkLabel, n as runAnalystBenchmarkCommand, nt as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, o as primeCodeTraceAnalystDefinition, ot as renderAgentRxCalibrationMarkdown, p as selectPublicBenchmarkRows, pt as roundAgentRxStep, q as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, r as renderAnalystBenchmarkMarkdown, rt as ANALYST_BENCHMARK_MANIFEST_FILE, s as runInlineAnalystDefinition, st as summarizeAgentRxCalibration, t as ANALYST_BENCHMARK_HELP, tt as ANALYST_BENCHMARK_COST_LEDGER_FILE, u as preparePublicAnalystBenchmark, ut as agentRxBenchmarkCase, v as createPublicBenchmarkDirectRunner, w as adaptPublicBenchmarkFindings, x as AnalystExpressivenessError, y as publicDirectAnalystDefinition, z as publicBenchmarkSystemPrompt } from "../benchmark-command-C7L0rQsD.js";
 import { a as extractPrimeJsonObject, c as primeProtocolSha256, d as runPrimeExchange, f as decodeReplyRows, 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-6tZTVsWm.js";
 import { existsSync, readFileSync, readdirSync, statSync } from "node:fs";
 import { join } from "node:path";

package/dist/{backend-integrity-CsVin_Wb.d.ts → backend-integrity-BffcHGdm.d.ts}

@@ -1,7 +1,7 @@
 import { t as AgentEvalError } from "./errors-DEE6u6ot.js";
 import { a as CheckerIdentity, n as VerdictCertification, t as DefaultVerdict, x as VerificationStrategySource } from "./verdict-E4eRNf7-.js";
 import { c as CostLedgerHandle } from "./cost-ledger-DbQdN3nO.js";
-import { a as RunRecord } from "./run-record-CKiihE6f.js";
+import { a as RunRecord } from "./run-record-DVV82Gwh.js";
 import { it as RawProviderSink, p as ChatClient } from "./types-Cx3YUh2r.js";
 //#region src/artifact-validator.d.ts
 /**
@@ -277,4 +277,4 @@ declare function assertRealBackend(records: ReadonlyArray<RunRecord>, opts?: {
 }): BackendIntegrityReport;
 //#endregion
 export { SatisfiedBy as _, ArtifactEventLike as a, createLlmCorrectnessChecker as b, ToolCallEventLike as c, CompletionVerdict as d, CorrectnessChecker as f, RequirementCheck as g, ProducedState as h, summarizeBackendIntegrity as i, extractProducedState as l, ProducedProposal as m, BackendIntegrityReport as n, ProposalEventLike as o, LlmCorrectnessCheckerOpts as p, assertRealBackend as r, RuntimeEventLike as s, BackendIntegrityError as t, CompletionRequirement as u, TaskGold as v, verifyCompletion as x, completionVerdict as y };
-//# sourceMappingURL=backend-integrity-CsVin_Wb.d.ts.map
+//# sourceMappingURL=backend-integrity-BffcHGdm.d.ts.map

package/dist/{backend-integrity-CsVin_Wb.d.ts.map → backend-integrity-BffcHGdm.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"backend-integrity-CsVin_Wb.d.ts","names":[],"sources":["../src/artifact-validator.ts","../src/completion-verifier.ts","../src/produced-state.ts","../src/integrity/backend-integrity.ts"],"mappings":";;;;;;;;;;;;;;;;;;UAaiB;;EAEf;;EAEA;;EAEA;;EAEA,QAAQ;;EAER,WAAW;;;;;KCsBD;UAEK;;EAEf;;EAEA;;EAEA;;EAEA,cAAc;;UAGC;EACf;EACA,cAAc;;UAGC;EACf;EACA;EACA;;EAEA;;;UAIe;;EAEf,WAAW;;EAEX,WAAW;;EAEX;;UAGe;EACf;EACA;;EAEA;;;;;;EAMA;;EAEA;;;;;;;;;EASA;;EAEA;;EAEA;;;;;UAMe,0BAA0B;EACzC;EACA,cAAc;;EAEd;;EAEA;;EAEA;;;;;;;;;iBAUc,kBAAkB;EAChC;EACA,cAAc;;;EAGd,gBAAgB;IACd;;;;;;UAqCa;EACf,UAAU;EACV,SAAS;EACT;;;;;;;;;;;;UAae;GAEb,aAAa,uBACb,kBACC;IAAU;IAAkB;;EAC/B,cAAc;;;;;;;;;iBAsLM,iBACpB,MAAM,UACN,OAAO,eACP,kBAAkB,qBACjB,QAAQ;UAyGM;EACf;;EAEA,aAAa;EACb;EACA,WAAW;EACX,SAAS;;EAET;;;;;;EAMA;;;;;;EAMA,UAAU;;;;;;;;iBA2CI,4BACd,MAAM,YACN,OAAM,4BACL;;;;UCnhBc;EACf;EACA;;;;;;;UAQe;EACf;EACA;EACA;EACA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EAIA;;;;;;;;KASU,mBACR,oBACA,oBACA;EACE;;;;;;;;;;;;iBAmBU,qBAAqB,iBAAiB,qBAAqB;;;UCpD1D;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;;;;;;cAQW,8BAA8B;WAGvB,QAAQ;EAF1B,YACE,iBACgB,QAAQ;;;;;;;iBAWZ,0BACd,SAAS,cAAc,aACtB;;;;;;;;iBAuHa,kBACd,SAAS,cAAc,YACvB;EAAQ;IACP"}
+{"version":3,"file":"backend-integrity-BffcHGdm.d.ts","names":[],"sources":["../src/artifact-validator.ts","../src/completion-verifier.ts","../src/produced-state.ts","../src/integrity/backend-integrity.ts"],"mappings":";;;;;;;;;;;;;;;;;;UAaiB;;EAEf;;EAEA;;EAEA;;EAEA,QAAQ;;EAER,WAAW;;;;;KCsBD;UAEK;;EAEf;;EAEA;;EAEA;;EAEA,cAAc;;UAGC;EACf;EACA,cAAc;;UAGC;EACf;EACA;EACA;;EAEA;;;UAIe;;EAEf,WAAW;;EAEX,WAAW;;EAEX;;UAGe;EACf;EACA;;EAEA;;;;;;EAMA;;EAEA;;;;;;;;;EASA;;EAEA;;EAEA;;;;;UAMe,0BAA0B;EACzC;EACA,cAAc;;EAEd;;EAEA;;EAEA;;;;;;;;;iBAUc,kBAAkB;EAChC;EACA,cAAc;;;EAGd,gBAAgB;IACd;;;;;;UAqCa;EACf,UAAU;EACV,SAAS;EACT;;;;;;;;;;;;UAae;GAEb,aAAa,uBACb,kBACC;IAAU;IAAkB;;EAC/B,cAAc;;;;;;;;;iBAsLM,iBACpB,MAAM,UACN,OAAO,eACP,kBAAkB,qBACjB,QAAQ;UAyGM;EACf;;EAEA,aAAa;EACb;EACA,WAAW;EACX,SAAS;;EAET;;;;;;EAMA;;;;;;EAMA,UAAU;;;;;;;;iBA2CI,4BACd,MAAM,YACN,OAAM,4BACL;;;;UCnhBc;EACf;EACA;;;;;;;UAQe;EACf;EACA;EACA;EACA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EAIA;;;;;;;;KASU,mBACR,oBACA,oBACA;EACE;;;;;;;;;;;;iBAmBU,qBAAqB,iBAAiB,qBAAqB;;;UCpD1D;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;;;;;;cAQW,8BAA8B;WAGvB,QAAQ;EAF1B,YACE,iBACgB,QAAQ;;;;;;;iBAWZ,0BACd,SAAS,cAAc,aACtB;;;;;;;;iBAuHa,kBACd,SAAS,cAAc,YACvB;EAAQ;IACP"}

package/dist/{benchmark-Ceoan7vk.d.ts → benchmark-DbiZbPdH.d.ts}

@@ -1,5 +1,5 @@
-import { c as AnalystRunInputs, f as AnalystUsageReceipt, i as AnalystFinding, p as EvidenceRef, w as TraceAnalysisStore } from "./types-DLQx4mKU.js";
-import { c as RegistryRunOpts, n as AnalystRegistry } from "./registry-oJeeI4-a.js";
+import { c as AnalystRunInputs, f as AnalystUsageReceipt, i as AnalystFinding, p as EvidenceRef, w as TraceAnalysisStore } from "./types-vXyshMwx.js";
+import { c as RegistryRunOpts, n as AnalystRegistry } from "./registry-B_1Frl8a.js";
 //#region src/analyst/benchmark-scoring.d.ts
 declare function scoreAnalystFindings(testCase: Pick<AnalystBenchmarkCase, 'id' | 'expectedIssues' | 'labeledEvidence'>, findings: readonly AnalystFinding[]): AnalystFindingScore;
 //#endregion
@@ -233,4 +233,4 @@ declare function registryBenchmarkRunner(options: {
 }): AnalystBenchmarkRunner<AnalystRunInputs>;
 //#endregion
 export { scoreAnalystFindings as C, traceStoreEvidenceResolver as S, AnalystIssueExpectation as _, AnalystBenchmarkLabelState as a, registryBenchmarkRunner as b, AnalystBenchmarkProvenance as c, AnalystBenchmarkSummary as d, AnalystEvidenceExpectation as f, AnalystFindingScore as g, AnalystEvidenceResolver as h, AnalystBenchmarkError as i, AnalystBenchmarkResult as l, AnalystEvidenceResolutionError as m, AnalystBenchmarkDatasetRef as n, AnalystBenchmarkObservation as o, AnalystEvidenceResolution as p, AnalystBenchmarkDescriptor as r, AnalystBenchmarkOutput as s, AnalystBenchmarkCase as t, AnalystBenchmarkRunner as u, AnalystLatencyDistribution as v, runAnalystBenchmark as x, RunAnalystBenchmarkOptions as y };
-//# sourceMappingURL=benchmark-Ceoan7vk.d.ts.map
+//# sourceMappingURL=benchmark-DbiZbPdH.d.ts.map

package/dist/{benchmark-Ceoan7vk.d.ts.map → benchmark-DbiZbPdH.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"benchmark-Ceoan7vk.d.ts","names":[],"sources":["../src/analyst/benchmark-scoring.ts","../src/analyst/benchmark.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"}
+{"version":3,"file":"benchmark-DbiZbPdH.d.ts","names":[],"sources":["../src/analyst/benchmark-scoring.ts","../src/analyst/benchmark.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"}

package/dist/{benchmark-command-DspwA7cv.js → benchmark-command-C7L0rQsD.js}

@@ -1209,7 +1209,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "34a180bb19abb605cd8190bc854f7ff1574fb3a5951706cccc49261dd32e96e6";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "599faa767a84b62fd8ffcb085175a643d88f040c45ed24bed0cf9b5f501e257b";
 /** 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
@@ -6369,4 +6369,4 @@ function shellQuote(value) {
 //#endregion
 export { analystBenchmarkDependencyLockDigest as $, compareAnalystRunners as A, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as B, analystDefinitionProtocolSha256 as C, readAnalystBenchmarkArtifact as D, expandCodeTraceFailureBlocks as E, MAX_INCORRECT_BLOCKS as F, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as G, loadCodeTraceVerificationArtifacts as H, MAX_INCORRECT_BLOCK_STEPS as I, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as J, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as K, publicBenchmarkProtocolSha256 as L, effectiveAnalystProtocolSha256 as M, readAnalystInstructionsOverride as N, renderCodeTraceCalibrationMarkdown as O, CODE_TRACE_BENCH_ANALYST_PROMPT as P, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as Q, publicBenchmarkRlmInstructions as R, analystDefinitionAsymmetries as S, emptyPublicBenchmarkRunner as T, parseVerificationOutcome as U, appendVerificationArtifactsToOtlp as V, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as W, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as X, ANALYST_BENCHMARK_EVIDENCE_PACKAGE_VERSION as Y, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as Z, runReplVariableAnalystDefinition as _, primeAnalystProtocolSha256 as a, AGENT_RX_UPSTREAM_REVISION as at, runChunkedAnalystDefinition as b, nodeHttpPrimeBridgeTransport as c, codeTraceBenchCase as ct, publicBenchmarkDistributions as d, agentRxPredictionsToFindings as dt, analystBenchmarkImplementationDigest as et, publicBenchmarkSelectionReport as f, normalizeAgentRxCategory as ft, rlmEngineLimits as g, publicRlmAnalystDefinition as h, createPrimeBenchmarkRunner as i, ANALYST_BENCHMARK_OBSERVATIONS_FILE as it, analystInstructionsOverrideFromText as j, summarizeCodeTraceCalibration as k, loadPublicBenchmarkRows as l, codeTracerPredictionsToFindings as lt, createPublicBenchmarkRlmRunner as m, normalizeBenchmarkLabel as mt, runAnalystBenchmarkCommand as n, ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as nt, primeCodeTraceAnalystDefinition as o, renderAgentRxCalibrationMarkdown as ot, selectPublicBenchmarkRows as p, roundAgentRxStep as pt, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as q, renderAnalystBenchmarkMarkdown as r, ANALYST_BENCHMARK_MANIFEST_FILE as rt, runInlineAnalystDefinition as s, summarizeAgentRxCalibration as st, ANALYST_BENCHMARK_HELP as t, ANALYST_BENCHMARK_COST_LEDGER_FILE as tt, preparePublicAnalystBenchmark as u, agentRxBenchmarkCase as ut, createPublicBenchmarkDirectRunner as v, adaptPublicBenchmarkFindings as w, AnalystExpressivenessError as x, publicDirectAnalystDefinition as y, publicBenchmarkSystemPrompt as z };
 
-//# sourceMappingURL=benchmark-command-DspwA7cv.js.map
+//# sourceMappingURL=benchmark-command-C7L0rQsD.js.map