@tangle-network/agent-eval 0.146.0 → 0.148.0

package/CHANGELOG.md

@@ -8,6 +8,42 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [0.148.0] — 2026-08-18
+
+### Added
+
+- `@tangle-network/agent-eval/experiment` publishes the evidence receipt: `createEvidenceReceipt`, `verifyEvidenceReceipt`, `isIndependentEvidence`, `EVIDENCE_RECEIPT_VERSION`, `EVIDENCE_AUTHORITY_KINDS`, `INDEPENDENT_EVIDENCE_AUTHORITY_KINDS`, and the `EvidenceReceipt` / `EvidenceBinding` / `EvidenceAuthority` / `EvidenceAuthorityKind` / `EvidenceReceiptVerification` / `CreateEvidenceReceiptInput` types.
+
+  A receipt binds one Runtime execution to the measurement that judged it, without either package importing the other. It carries stable pursuit and run identity, the exact candidate, evaluator, environment, input-set and output content identities, the result digest, and the authority class that made the observation. The payload is attested with the existing canonical report attestation, so mutating any bound field invalidates the receipt.
+
+  The authority vocabulary is closed. An unknown or misspelled kind is never independent, and `candidate-self-report` is never independent, so a candidate cannot certify itself by accident.
+
+- A bounded `SearchHistoryReceipt` over the canonical `SearchLedger`, plus search-history coverage and `searchHistoryPolicy: 'require-complete'` on `compareOptimizationMethods()`. Strict mode refuses missing or denominator-incomplete optimization evidence before untouched-final-test scoring. Rich events remain only in the ledger.
+
+### Fixed
+
+- The packed dependency cohort is read from the manifests instead of a second hand-kept list.
+
+### Changed
+
+- No existing export changed.
+
+---
+
+## [0.147.0] — 2026-08-16
+
+### Removed
+
+- `decideNextUserTurn`, `DecideNextUserTurnOpts` and `buildDriverSystemPrompt`, with `src/driver.ts` and the `user-simulation-driver` example. A role written as a code function cannot be optimized, and a persona driver is an `AgentProfile` on a graph edge, not a packaged function. All five first-party callers now own the role in their own repositories, where the prompt is product data they can change and measure: gtm-agent, legal-agent, insurance-agent, workcomp-agent and creative-agent.
+- `ConvergenceTracker` and `src/convergence.ts`. Its only caller was `AgentDriver`, which 0.145.22 deleted, and it never reached the barrel. `analyzeSeries` in `src/series-convergence.ts` is unaffected — it reads drift across runs, not progress within one.
+- `PersonaConfig.feedbackPatterns`, the `FeedbackPattern` type, and `PersonaConfig.driverModel`. `feedbackPatterns` told `AgentDriver` which product approvals to reject, and `driverModel` picked its driver model; with the class gone nothing reads either, in this package or in any repository that depends on it. A field that advertises behaviour the package no longer has is worse than no field.
+- Nothing else on the public surface changes. `PersonaConfig` and `DriverState` stay: a harness that writes its own driver still describes a persona and a produced state with them.
+
+### Migration
+
+A caller that drove a conversation with `decideNextUserTurn` owns two things now: the system prompt that states what its simulated professional demands, and one priced call that turns the transcript into the next message. Both stay reachable from this package — `CostLedger.runPaidCall` prices and attributes the call, `maximumChargeForLlmRequest` caps it, `costReceiptFromLlm` records it, and `assertServedModel` (published in 0.145.22) holds the transport to the model id it was asked for. gtm-agent's `eval/lib/persona-driver.ts` is the worked example.
+
+A caller pinned below 0.145.22 cannot import `assertServedModel`. Check what the pinned version did before porting: `decideNextUserTurn` did not call the guard before the 0.145.x line, so a port that omits it there matches the pinned behaviour exactly.
 ## [0.146.0] — 2026-08-16
 
 ### Added

package/README.md

@@ -71,6 +71,12 @@ Keep the default whenever real model calls happen.
 
 Runnable copy: [`examples/evaluate-a-change`](./examples/evaluate-a-change/).
 
+## Auditable optimization history
+
+Optimization methods may return a bounded `SearchHistoryReceipt` over Eval's canonical hash-chained `SearchLedger`. Existing callers keep working and see missing-history coverage. Autonomous and publication-grade runs set `searchHistoryPolicy: 'require-complete'` to refuse an incomplete planned denominator before the untouched final cases are opened.
+
+The receipt is a small proof envelope, not another event log. Exact candidates, attempts, failures, decisions, and missing ids remain in the ledger. See [complete optimization search history](./docs/search-history-receipts.md).
+
 ## Which Front Door
 
 Every row is a function you call. Each links to a runnable example.
@@ -188,3 +194,4 @@ uv run --frozen pytest tests/test_dspy_metric.py
 ## License
 
 MIT.
+

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-CevPFhDT.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-gtjtfLEJ.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-XBRdmbj8.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-DOhGq4S1.js";
 import { s as TraceStore } from "../store-CT9YIIve.js";
-import "../index-BgHYx1QG.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-oAsa-fs4.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-DONui3mA.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-CYFbvA5U.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-CZgEmVXb.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-DTQ1RApl.js";
-import { f as ExternalOptimizerModelExecutionObservation, h as ExternalOptimizerRunnerCommand, l as ExternalOptimizerModelCall } from "../external-optimizer-contracts-CKEY98bK.js";
+import "../index-CKblBxtr.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-BohHewKK.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-BUtRMRKk.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-rdKFzEnK.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-CaqJIDdN.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-Cn7ZMFNW.js";
+import { f as ExternalOptimizerModelExecutionObservation, h as ExternalOptimizerRunnerCommand, l as ExternalOptimizerModelCall } from "../external-optimizer-contracts-CSjDLLmr.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-Bc3seRPe.js";
-import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-CDDXNKhd.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-CIy18RTX.js";
+import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-zpufabP8.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 = "67f8190cb923ea20fec9b45e66e26673a140e02df082b4132d174a14fcbace54";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "5c7e5561a2ecaa48aaffc52d8a44f582642ed434a92839ae4741ad5556fd9789";
 /** 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
@@ -1311,7 +1311,7 @@ declare const ANALYST_BENCHMARK_EVIDENCE_PACKAGE_VERSION = "0.137.0";
 declare const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
 declare const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
 declare const ANALYST_BENCHMARK_IMPLEMENTATION_FILES: readonly string[];
-declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "e5af51a8ca6f0f3a11c645980a7dd1506835c03ee64c3db80616da420a00cdbf";
+declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "6fe839500ca54d707265f11d6cd0bf8cbca55b9087d1b7d6ae751dc6960bfb1b";
 declare function analystBenchmarkImplementationDigest(): string;
 declare function analystBenchmarkDependencyLockDigest(): string;
 //#endregion

package/dist/analyst/index.js

@@ -1,13 +1,13 @@
 import { o as NotFoundError } from "../errors-Dngq5h35.js";
-import { i as CostLedger } from "../cost-ledger-BSe92yAV.js";
+import { i as CostLedger } from "../cost-ledger-B1qx30B4.js";
 import { i as isProposalFinding, n as clamp01, r as assertProposalFindings, t as aggregateRunScore } from "../run-score-lDzV0X8j.js";
 import { a as settleUsageReceiptFromCostLedger, n as makeFinding, r as makeProposalFinding, s as validateUsageSettlementTimeout, t as computeFindingId } from "../types-BI4fT3HN.js";
-import { A as coerceJson, B as renderFindingSubject, D as RawAnalystFindingSchema, E as RawAnalystEvidenceSchema, F as FINDING_SUBJECT_SYNTAX, H 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, V 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-CPmSd58s.js";
-import { a as assertExactRegistryRunOpts, c as KNOWLEDGE_GAP_KIND_SPEC, d as CONTROL_INTEGRITY_ANALYST, f as ControlIntegrityAnalyst, h as deriveEfficiencyFindings, i as ExactAnalystRunExecutionError, l as IMPROVEMENT_KIND_SPEC, m as behavioralAnalyst, n as buildDefaultAnalystRegistry, o as DEFAULT_TRACE_ANALYST_KINDS, p as emitControlIntegrityFindings, r as AnalystRegistry, s as KNOWLEDGE_POISONING_KIND_SPEC, t as createChatClient, u as FAILURE_MODE_KIND_SPEC } from "../chat-client-BJmwfnjN.js";
-import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-B2nst4NR.js";
-import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-BsY2Q0Oq.js";
+import { A as coerceJson, B as renderFindingSubject, D as RawAnalystFindingSchema, E as RawAnalystEvidenceSchema, F as FINDING_SUBJECT_SYNTAX, H 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, V 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-DmAa0h3K.js";
+import { a as assertExactRegistryRunOpts, c as KNOWLEDGE_GAP_KIND_SPEC, d as CONTROL_INTEGRITY_ANALYST, f as ControlIntegrityAnalyst, h as deriveEfficiencyFindings, i as ExactAnalystRunExecutionError, l as IMPROVEMENT_KIND_SPEC, m as behavioralAnalyst, n as buildDefaultAnalystRegistry, o as DEFAULT_TRACE_ANALYST_KINDS, p as emitControlIntegrityFindings, r as AnalystRegistry, s as KNOWLEDGE_POISONING_KIND_SPEC, t as createChatClient, u as FAILURE_MODE_KIND_SPEC } from "../chat-client-BX8Wh3fn.js";
+import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-BmtOl_kP.js";
+import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-BI7Rrl5-.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-CxLJljS1.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-Cz4fDmsk.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-HVmWyOaX.d.ts → backend-integrity-Bz8nSrRE.d.ts}

@@ -2,7 +2,7 @@ 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-DVV82Gwh.js";
-import { mt as RawProviderSink, p as ChatClient } from "./types-XBRdmbj8.js";
+import { mt as RawProviderSink, p as ChatClient } from "./types-DOhGq4S1.js";
 //#region src/artifact-validator.d.ts
 /**
  * Artifact validators.
@@ -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-HVmWyOaX.d.ts.map
+//# sourceMappingURL=backend-integrity-Bz8nSrRE.d.ts.map

package/dist/{backend-integrity-HVmWyOaX.d.ts.map → backend-integrity-Bz8nSrRE.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"backend-integrity-HVmWyOaX.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-Bz8nSrRE.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-DTQ1RApl.d.ts → benchmark-Cn7ZMFNW.d.ts}

@@ -1,5 +1,5 @@
-import { c as AnalystRunInputs, f as AnalystUsageReceipt, i as AnalystFinding, p as EvidenceRef, w as TraceAnalysisStore } from "./types-oAsa-fs4.js";
-import { c as RegistryRunOpts, n as AnalystRegistry } from "./registry-CZgEmVXb.js";
+import { c as AnalystRunInputs, f as AnalystUsageReceipt, i as AnalystFinding, p as EvidenceRef, w as TraceAnalysisStore } from "./types-BohHewKK.js";
+import { c as RegistryRunOpts, n as AnalystRegistry } from "./registry-CaqJIDdN.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-DTQ1RApl.d.ts.map
+//# sourceMappingURL=benchmark-Cn7ZMFNW.d.ts.map

package/dist/{benchmark-DTQ1RApl.d.ts.map → benchmark-Cn7ZMFNW.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"benchmark-DTQ1RApl.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-Cn7ZMFNW.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-CxLJljS1.js → benchmark-command-Cz4fDmsk.js}

@@ -1,17 +1,17 @@
 import { s as ValidationError, t as AgentEvalError } from "./errors-Dngq5h35.js";
 import { r as pairedBootstrap } from "./paired-tests-BHIhYVdu.js";
-import { a as resolveModelPricing } from "./metrics-Cl0L1KUy.js";
-import { a as CostLedgerPersistenceError, i as CostLedger, n as CostCallConflictError, o as CostReceiptCaptureError, r as CostCeilingReachedError, s as CostReservationExceededError, t as CostAccountingIncompleteError } from "./cost-ledger-BSe92yAV.js";
+import { a as resolveModelPricing } from "./metrics-Qv-cpptD.js";
+import { a as CostLedgerPersistenceError, i as CostLedger, n as CostCallConflictError, o as CostReceiptCaptureError, r as CostCeilingReachedError, s as CostReservationExceededError, t as CostAccountingIncompleteError } from "./cost-ledger-B1qx30B4.js";
 import { c as writeLedgerFileAtomically, s as withLedgerFileLock } from "./ledger-core-DTae9rv_.js";
 import { i as hashCanonical, r as canonicalString } from "./canonical-D-XsTQ6_.js";
-import { b as createRunCostLedger, i as startExternalOptimizerModelProxy, r as runWithCleanup, v as resolveExternalOptimizerProcessLimits, x as fsCampaignStorage } from "./external-optimizer-subprocess-r6dP9DAj.js";
+import { b as createRunCostLedger, i as startExternalOptimizerModelProxy, r as runWithCleanup, v as resolveExternalOptimizerProcessLimits, x as fsCampaignStorage } from "./external-optimizer-subprocess-DU1KM8yV.js";
 import { n as makeFinding, o as usageReceiptFromCostLedger } from "./types-BI4fT3HN.js";
-import { D as RawAnalystFindingSchema, O as evidenceRefsFromRawFinding, T as RAW_FINDING_SCHEMA_PROMPT, h as TRACE_ANALYSIS_LIMITS, i as runTraceAnalyst } from "./kind-factory-CPmSd58s.js";
-import { c as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-_UE4fU7Z.js";
-import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-B2nst4NR.js";
-import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-CsptLYpN.js";
+import { D as RawAnalystFindingSchema, O as evidenceRefsFromRawFinding, T as RAW_FINDING_SCHEMA_PROMPT, h as TRACE_ANALYSIS_LIMITS, i as runTraceAnalyst } from "./kind-factory-DmAa0h3K.js";
+import { c as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-BMuxYoZy.js";
+import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-BmtOl_kP.js";
+import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-CDYWW_8N.js";
 import { i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver } from "./benchmark-BhT16ep9.js";
-import { n as acquireSingleRunLock } from "./external-optimizer-process-DYNizz8W.js";
+import { n as acquireSingleRunLock } from "./external-optimizer-process-C4AyCcQd.js";
 import { c as primeProtocolSha256, d as runPrimeExchange, f as decodeReplyRows, n as buildPrimePrompt, p as assertEqualDeclarativeTerms, t as analystUsageReceiptFromPrimeUsage, u as projectPrimeTrajectory } from "./prime-protocol-6tZTVsWm.js";
 import { createHash, randomUUID } from "node:crypto";
 import { constants, existsSync, lstatSync, readFileSync } from "node:fs";
@@ -1209,7 +1209,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "67f8190cb923ea20fec9b45e66e26673a140e02df082b4132d174a14fcbace54";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "5c7e5561a2ecaa48aaffc52d8a44f582642ed434a92839ae4741ad5556fd9789";
 /** 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
@@ -1327,7 +1327,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
 	"src/trace/raw-provider-sink.ts",
 	"src/verdict-cache.ts"
 ]);
-const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "e5af51a8ca6f0f3a11c645980a7dd1506835c03ee64c3db80616da420a00cdbf";
+const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "6fe839500ca54d707265f11d6cd0bf8cbca55b9087d1b7d6ae751dc6960bfb1b";
 function analystBenchmarkImplementationDigest() {
 	return ANALYST_BENCHMARK_IMPLEMENTATION_SHA256;
 }
@@ -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-CxLJljS1.js.map
+//# sourceMappingURL=benchmark-command-Cz4fDmsk.js.map