@tangle-network/agent-eval 0.193.0 → 0.194.0

package/CHANGELOG.md

@@ -6,6 +6,37 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ## Unreleased
 
+## [0.194.0] — 2026-09-25
+
+### Fixed
+
+- A capped search whose cells cost more than their holds could never close: once overspend took committed spend plus the claim reserve past `maxUsd`, the projector refused the `claim` operation, which holds nothing, and every resume failed the same way (`operation claim is not admissible: committed $3.449935 + open $0 + claim reserve $6.5 + hold $0 exceeds the cap $9.6`, with a planted better node already found). The admission rule now admits holds only: an event without a reservation is always recorded, and a claim cell within the unspent claim reserve is admitted however much earlier cells overspent. The same search now runs its 48 claim cells on the reserve, ships the planted node, and ends at $6.31 committed against the $9.60 cap plus $0.79 recorded overspend. `runSearch` also stops expanding once overspend took the search past its cap, even at a zero-dollar lane prior.
+- The shared projector accepted any claim a producer wrote: a `ship` over a finalist whose test interval includes 0, a family-wise confidence of 0.5, rewritten test intervals or estimates, and a fabricated power all replayed and closed. `verifySearchClaim(state)` (`/campaign`) makes the claim again from the closed ledger alone, with no blob, and compares it byte for byte; it detects all five. `runSearch` runs it on every close and on every rerun of a closed ledger, throws on a mismatch, and returns it as `SearchRunResult.claimVerification`. The reference receiver returns it with a closed search.
+
+### Added
+
+- `scripts/search-sim.ts` gains `--binary` (pass/fail cells), `--minimize` (a minimized objective) and `--cost-scale X` (cells cost X times the lane's prior).
+
+## [0.193.2] — 2026-09-25
+
+### Fixed
+
+- 0.193.1's release commit bumped `package.json`, `pyproject.toml` and `__init__.py` but missed `clients/python/uv.lock`'s own `agent-eval-rpc` package entry, so `verifyVersionLock` failed the publish workflow (`uvRoot=0.193.0` against `npm=0.193.1`) before the npm publish step ran. 0.193.1 was never published to any registry — this release carries the same content, correctly locked.
+
+## [0.193.1] — 2026-09-25
+
+### Fixed
+
+- `CREDENTIAL_DETECTORS`' provider-branded prefixes (`sk-ant-`, `AIza`, `ghp_`, `xoxb-`, `AKIA`, `hubcap_`, `eyJ`…) required a leading `\b`, which does not fire between two word characters — a token glued to preceding text by an underscore or letter, in an attribute **key** as well as a value (`env.GITHUB_TOKEN_ghp_<token>`, `BACKUP_AKIA<key>`), passed both `redact()` and `assessShareSafety()` unflagged. Dropped the leading `\b` on the branded prefixes.
+- `walk()`/`scan()` classified an object key only for a CREDENTIAL shape, never `detectPersonalData(key)`, so a key like an email address (`{'alice@corp-example.com': 3}`) passed as SAFE under every profile. Also dropped the same leading-`\b` gap on `huggingface-token`, `npm-token`, `gitlab-token`, `groq-key`, `xai-key` and bare-`sk`-key.
+- `detectCredential` ran on the full string before the size cap applied, and `url-credentials`/`secret-assignment` had unbounded quantifiers, so adversarial text with no real credential could block the exporter/uploader's event loop for tens of seconds (measured ~59s on 256 KiB with no `://` at all). Bounded both regexes and what the value-shape detectors scan.
+- `containsKnownSecret` only matched a known secret's raw/base64/base64url/URL-encoded forms as a substring; `Authorization: Basic <base64(user:key)>` survived as SAFE even with the key passed as a `knownSecret`, because userinfo's 3-byte base64 group alignment means the secret's own base64 form is generally not a substring of the surrounding base64. It now also decodes an embedded base64 span and checks the secret against the decode.
+- `redact()`'s `data:` URI check matched by prefix instead of requiring the whole string to be the URI, so a `data:text/plain;base64,…`/`data:application/json;base64,…` value with a live credential in its decoded payload was always classified as opaque media. The check now requires the whole string to be the URI, and `text/*`/`application/json` payloads are decoded and scanned.
+- `summarizeExecutionMeasurements` counted only `LLM` spans as model calls, so an `EMBEDDING` or `RERANKER` span's own tokens dropped out of the run total whenever a chat call anywhere in the same run also reported tokens — a real undercount (5100 measured as 100 on a trace with one 100-token chat call and one 5000-token embeddings call), not the aggregate-token-loss bug 0.191.0 already fixed. Classify model calls with the contract's `isModelCallKind` (`@tangle-network/agent-trace-contract@^1.3.0`; `LLM`, `EMBEDDING`, `RERANKER`) instead of `kind === 'LLM'`.
+- `never`, `atMost`, `tokensAtMost` and `retrySafe` passed vacuously when a scoped trace had zero TOOL or LLM spans because the exporter never captured any, reading "never captured" as "none happened"; these rules now require capture evidence first and error via `CaptureIntegrityError` otherwise. A malformed `attr` matcher (an incomplete `SerializedRegex`, a bare `oneOf`) was accepted and then compared by reference, so it silently matched nothing; `assertPredicate` now validates every non-primitive `attr` value as a complete matcher shape.
+- `diagnoseSpans`' `NOT_BUILT` reasons for `loop-convergence` and `steering-chain` said only that this engine has no such analysis; they now also name where the capability is built (`@tangle-network/traces`' `loop-analysis.ts`), matching the pattern `tree-comparison`'s reason already used — traces' own conformance table marks all three built, so the two reports no longer read as contradicting each other.
+- `REDACTION_VERSION` → `2.4.0`.
+
 ## [0.193.0] — 2026-09-25
 
 ### Added
@@ -70,8 +101,8 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ### Changed
 
-- Span classification and the attribute key lists come from `@tangle-network/agent-trace-contract` (`resolveSpanKind`, `declaredSpanKind`, `SPAN_KINDS`); agent-eval's own copies are gone (#823).
-  The analyst shows the declared OpenInference kind, agent-eval's own spans export as `RETRIEVER` and `UNKNOWN` where they wrote `CHAIN` and `SPAN`, and a legacy `SPAN` kind is still accepted on read.
+- **Breaking:** span classification and the attribute key lists come from `@tangle-network/agent-trace-contract` (`resolveSpanKind`, `declaredSpanKind`, `SPAN_KINDS`); agent-eval's own copies are gone (#823).
+  The analyst shows the declared OpenInference kind, agent-eval's own spans export as `RETRIEVER` and `UNKNOWN` where they wrote `CHAIN` and `SPAN`, and a legacy `SPAN` kind is still accepted (and normalized to `UNKNOWN`) on read — but `TraceAnalystSpanKind` (now an alias of the contract's `SpanKind`) no longer has a `'SPAN'` member, so a consumer whose own code returns or type-checks the string `'SPAN'` against `TraceAnalystSpanKind` fails to compile on this version. `Intelligence`'s `pg-trace-analyst-store.ts` `inferKind` and `agent-builder`'s `d1-trace-analysis-store-adapter.ts` mapping both do this today; replace those with the contract's `declaredSpanKind`/`resolveSpanKind` before bumping past 0.190.1.
   Both OTLP intakes decide model calls and aggregates from one span kind, so an undeclared agent or workflow span no longer sums its children's tokens a second time.
 - **Breaking:** the hosted wire ships search ledgers, not eval-run snapshots ([hosted ingest spec](./docs/hosted-ingest-spec.md)).
   A producer uploads each blob an entry names (`PUT /v1/search-blobs/<sha256>`), reads the store's head (`GET /v1/ingest/search-ledger/<searchId>/head`), and posts canonical ledger lines from there (`POST /v1/ingest/search-ledger`, at most 1,000 lines or 1 MiB).

package/dist/adapters/http.d.ts

@@ -1,6 +1,6 @@
 import { m as CostReceipt } from "../cost-ledger-DbQdN3nO.js";
-import { R as Scenario, d as DispatchContext, f as DispatchFn } from "../types-BWwRXofp.js";
-import "../index-DWQNDqPd.js";
+import { R as Scenario, d as DispatchContext, f as DispatchFn } from "../types-DLtLe21j.js";
+import "../index-DKUIMOst.js";
 //#region src/adapters/http.d.ts
 interface HttpDispatchOptions<TScenario extends Scenario, _TArtifact> {
   /** Static endpoint URL. Mutually exclusive with `resolveUrl`. */

package/dist/analyst/index.d.ts

@@ -4,10 +4,10 @@ import { A as createChatClient, C as ChatResponse, D as MockTransportOpts, E as
 import { A as runAnalystBenchmark, C as AnalystEvidenceResolutionError, D as AnalystLatencyDistribution, E as AnalystIssueExpectation, M as scoreAnalystFindings, O as RunAnalystBenchmarkOptions, S as AnalystEvidenceResolution, T as AnalystFindingScore, V as ExternalOptimizerModelCall, W as ExternalOptimizerModelExecutionObservation, _ as AnalystBenchmarkProvenance, b as AnalystBenchmarkSummary, d as AnalystBenchmarkDatasetRef, f as AnalystBenchmarkDescriptor, g as AnalystBenchmarkOutput, h as AnalystBenchmarkObservation, j as traceStoreEvidenceResolver, k as registryBenchmarkRunner, m as AnalystBenchmarkLabelState, p as AnalystBenchmarkError, q as ExternalOptimizerRunnerCommand, t as AgentProfile, u as AnalystBenchmarkCase, v as AnalystBenchmarkResult, w as AnalystEvidenceResolver, x as AnalystEvidenceExpectation, y as AnalystBenchmarkRunner } from "../agent-profile-DDfIjdyS.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-KGxBWH4b.js";
 import { a as ExactAnalystBudgetPolicy, c as RegistryRunOpts, i as BudgetPolicy, n as AnalystRegistry, o as ExactAnalystRunExecutionError, r as AnalystRegistryOptions, s as ExactRegistryRunOpts, t as AnalystHooks } from "../registry-Bu3lNole.js";
-import { a as createTraceAnalyst, c as BehavioralAnalystOptions, i as TraceAnalystDefinition, l as behavioralAnalyst, n as buildDefaultAnalystRegistry, o as renderPriorFindings, r as CreateTraceAnalystOptions, s as runTraceAnalyst, t as DefaultAnalystRegistryOptions, u as deriveEfficiencyFindings } from "../default-registry-C3HTE08O.js";
-import { a as TraceAnalystLimits, c as RawAnalystEvidence, d as evidenceRefsFromRawFinding, f as parseRawFinding, i as TraceAnalysisEngineResult, l as RawAnalystFinding, n as TraceAnalysisEngine, o as resolveTraceAnalystLimits, r as TraceAnalysisEngineRequest, s as RAW_FINDING_SCHEMA_PROMPT, t as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, u as RawAnalystFindingSchema } from "../engine-DjRV55F9.js";
-import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-BC9O7Epn.js";
-import { A as SemanticConceptJudgeInput, C as DspyRlmTraceEngineOptions, E as createChatTraceEngine, S as renderFindingSubject, T as ChatTraceEngineOptions, _ as FindingSubject, a as FAILURE_MODE_KIND_SPEC, b as findingSubjectGrammarPromptFor, c as emitControlIntegrityFindings, d as FindingsStore, f as PersistedFinding, g as FINDING_SUBJECT_SYNTAX, h as FINDING_SUBJECT_KINDS, 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 FindingSubjectKind, w as createDspyRlmTraceEngine, x as parseFindingSubject, y as KIND_EXPECTED_SUBJECTS } from "../index-0jEtpSM7.js";
+import { a as createTraceAnalyst, c as BehavioralAnalystOptions, i as TraceAnalystDefinition, l as behavioralAnalyst, n as buildDefaultAnalystRegistry, o as renderPriorFindings, r as CreateTraceAnalystOptions, s as runTraceAnalyst, t as DefaultAnalystRegistryOptions, u as deriveEfficiencyFindings } from "../default-registry-D44M_E4Q.js";
+import { a as TraceAnalystLimits, c as RawAnalystEvidence, d as evidenceRefsFromRawFinding, f as parseRawFinding, i as TraceAnalysisEngineResult, l as RawAnalystFinding, n as TraceAnalysisEngine, o as resolveTraceAnalystLimits, r as TraceAnalysisEngineRequest, s as RAW_FINDING_SCHEMA_PROMPT, t as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, u as RawAnalystFindingSchema } from "../engine-LkP-rfp1.js";
+import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-CiFSpk6C.js";
+import { A as SemanticConceptJudgeInput, C as DspyRlmTraceEngineOptions, E as createChatTraceEngine, S as renderFindingSubject, T as ChatTraceEngineOptions, _ as FindingSubject, a as FAILURE_MODE_KIND_SPEC, b as findingSubjectGrammarPromptFor, c as emitControlIntegrityFindings, d as FindingsStore, f as PersistedFinding, g as FINDING_SUBJECT_SYNTAX, h as FINDING_SUBJECT_KINDS, 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 FindingSubjectKind, w as createDspyRlmTraceEngine, x as parseFindingSubject, y as KIND_EXPECTED_SUBJECTS } from "../index-cWnRlQLW.js";
 import { A as ReplyRowDecoded, C as primeProtocolSha256, D as DecodedReply, E as runPrimeExchange, M as decodeReplyRows, O as ReplyContract, S as normalizePrimeUsage, T as projectPrimeTrajectory, _ as buildPrimePrompt, a as PrimeProjectionOutcome, b as extractPrimeJsonObject, c as PrimeProtocolIdentity, d as PrimeRepairPromptSpec, f as PrimeRepairState, g as analystUsageReceiptFromPrimeUsage, h as PrimeTurnRecord, i as PrimeProjectionDelivery, j as ReplyRowRejection, k as ReplyEnvelope, l as PrimeRawUsage, m as PrimeRowDecoded, n as PrimeExchangeOutcome, o as PrimeProjectionSource, p as PrimeReplyContract, r as PrimeFailure, s as PrimePromptSpec, t as PrimeExchangeOptions, u as PrimeRejectedRow, v as buildPrimeRepairPrompt, w as primeReplyDefect, x as mergePrimeRawUsage, y as emptyPrimeRawUsage } from "../prime-protocol-T0i6xcAs.js";
 import { i as nodeHttpPrimeBridgeTransport, n as PrimeBridgeTransportRequest, r as PrimeBridgeTransportResult, t as PrimeBridgeTransport } from "../prime-bridge-transport-6feEglLf.js";
 import { z } from "zod";
@@ -1181,11 +1181,11 @@ declare function runAnalystBenchmarkCommand(argv: readonly string[], env?: NodeJ
 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 = "0ff3eda790af1c3811ac4e084fe57c9d64254966fd0ebf53374f40e504bc28be";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "ae1aa0c627f55852e9710693f2b0f043c250bdd692ee4fa4979d6020215aa13d";
 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 = "00002cbbc8a749281287418f0abc03e4fc6a78ef3c1b4f21e33f2452629283da";
+declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "8bb4bdae57e4c5596ffe77d80c7a16e67eef7b2fc5087c2af369a417ed423a26";
 declare function analystBenchmarkImplementationDigest(): string;
 declare function analystBenchmarkDependencyLockDigest(): string;
 //#endregion

package/dist/analyst/index.js

@@ -4,11 +4,11 @@ import { B as FINDING_SUBJECT_SYNTAX, F as parseRawFinding, G as DEFAULT_TRACE_A
 import { i as validateUsageSettlementTimeout, n as settleUsageReceiptFromCostLedger } from "../usage-receipt-Cx3xNeyB.js";
 import { a as KNOWLEDGE_POISONING_KIND_SPEC, c as FAILURE_MODE_KIND_SPEC, d as emitControlIntegrityFindings, f as behavioralAnalyst, i as DEFAULT_TRACE_ANALYST_KINDS, l as CONTROL_INTEGRITY_ANALYST, n as AnalystRegistry, o as KNOWLEDGE_GAP_KIND_SPEC, p as deriveEfficiencyFindings, r as ExactAnalystRunExecutionError, s as IMPROVEMENT_KIND_SPEC, t as buildDefaultAnalystRegistry, u as ControlIntegrityAnalyst } from "../default-registry-xMLX160E.js";
 import { i as makeProposalFinding, n as computeFindingId, r as makeFinding } from "../types-CW5b90JH.js";
-import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-BX34vPVY.js";
-import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, o as createChatTraceEngine, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-Bg-560H0.js";
-import { t as createChatClient } from "../chat-client-B_ItsSBw.js";
+import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-k_QdEBZo.js";
+import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, o as createChatTraceEngine, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-Bh5lvKGg.js";
+import { t as createChatClient } from "../chat-client-CJORSG_J.js";
 import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-BeQJyrRC.js";
-import { $ as ANALYST_BENCHMARK_MANIFEST_FILE, A as readAnalystInstructionsOverride, B as parseVerificationOutcome, C as emptyPublicBenchmarkRunner, D as summarizeCodeTraceCalibration, E as renderCodeTraceCalibrationMarkdown, F as publicBenchmarkRlmInstructions, G as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, H as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, I as publicBenchmarkSystemPrompt, J as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, K as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, L as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, M as MAX_INCORRECT_BLOCKS, N as MAX_INCORRECT_BLOCK_STEPS, O as analystInstructionsOverrideFromText, P as publicBenchmarkProtocolSha256, Q as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, R as appendVerificationArtifactsToOtlp, S as adaptPublicBenchmarkFindings, T as readAnalystBenchmarkArtifact, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, V as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, W as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, X as analystBenchmarkImplementationDigest, Y as analystBenchmarkDependencyLockDigest, Z as ANALYST_BENCHMARK_COST_LEDGER_FILE, _ as publicDirectAnalystDefinition, a as primeCodeTraceAnalystDefinition, at as codeTraceBenchCase, b as analystDefinitionAsymmetries, c as preparePublicAnalystBenchmark, ct as agentRxPredictionsToFindings, d as selectPublicBenchmarkRows, dt as normalizeBenchmarkLabel, et as ANALYST_BENCHMARK_OBSERVATIONS_FILE, f as createPublicBenchmarkRlmRunner, g as createPublicBenchmarkDirectRunner, h as runReplVariableAnalystDefinition, i as primeAnalystProtocolSha256, it as summarizeAgentRxCalibration, j as CODE_TRACE_BENCH_ANALYST_PROMPT, k as effectiveAnalystProtocolSha256, l as publicBenchmarkDistributions, lt as normalizeAgentRxCategory, m as rlmEngineLimits, n as renderAnalystBenchmarkMarkdown, nt as AGENT_RX_UPSTREAM_REVISION, o as runInlineAnalystDefinition, ot as codeTracerPredictionsToFindings, p as publicRlmAnalystDefinition, q as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, r as createPrimeBenchmarkRunner, rt as renderAgentRxCalibrationMarkdown, s as loadPublicBenchmarkRows, st as agentRxBenchmarkCase, t as runAnalystBenchmarkCommand, tt as compareAnalystRunners, u as publicBenchmarkSelectionReport, ut as roundAgentRxStep, v as runChunkedAnalystDefinition, w as expandCodeTraceFailureBlocks, x as analystDefinitionProtocolSha256, y as AnalystExpressivenessError, z as loadCodeTraceVerificationArtifacts } from "../benchmark-command-DVhUPU7H.js";
+import { $ as ANALYST_BENCHMARK_MANIFEST_FILE, A as readAnalystInstructionsOverride, B as parseVerificationOutcome, C as emptyPublicBenchmarkRunner, D as summarizeCodeTraceCalibration, E as renderCodeTraceCalibrationMarkdown, F as publicBenchmarkRlmInstructions, G as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, H as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, I as publicBenchmarkSystemPrompt, J as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, K as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, L as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, M as MAX_INCORRECT_BLOCKS, N as MAX_INCORRECT_BLOCK_STEPS, O as analystInstructionsOverrideFromText, P as publicBenchmarkProtocolSha256, Q as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, R as appendVerificationArtifactsToOtlp, S as adaptPublicBenchmarkFindings, T as readAnalystBenchmarkArtifact, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, V as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, W as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, X as analystBenchmarkImplementationDigest, Y as analystBenchmarkDependencyLockDigest, Z as ANALYST_BENCHMARK_COST_LEDGER_FILE, _ as publicDirectAnalystDefinition, a as primeCodeTraceAnalystDefinition, at as codeTraceBenchCase, b as analystDefinitionAsymmetries, c as preparePublicAnalystBenchmark, ct as agentRxPredictionsToFindings, d as selectPublicBenchmarkRows, dt as normalizeBenchmarkLabel, et as ANALYST_BENCHMARK_OBSERVATIONS_FILE, f as createPublicBenchmarkRlmRunner, g as createPublicBenchmarkDirectRunner, h as runReplVariableAnalystDefinition, i as primeAnalystProtocolSha256, it as summarizeAgentRxCalibration, j as CODE_TRACE_BENCH_ANALYST_PROMPT, k as effectiveAnalystProtocolSha256, l as publicBenchmarkDistributions, lt as normalizeAgentRxCategory, m as rlmEngineLimits, n as renderAnalystBenchmarkMarkdown, nt as AGENT_RX_UPSTREAM_REVISION, o as runInlineAnalystDefinition, ot as codeTracerPredictionsToFindings, p as publicRlmAnalystDefinition, q as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, r as createPrimeBenchmarkRunner, rt as renderAgentRxCalibrationMarkdown, s as loadPublicBenchmarkRows, st as agentRxBenchmarkCase, t as runAnalystBenchmarkCommand, tt as compareAnalystRunners, u as publicBenchmarkSelectionReport, ut as roundAgentRxStep, v as runChunkedAnalystDefinition, w as expandCodeTraceFailureBlocks, x as analystDefinitionProtocolSha256, y as AnalystExpressivenessError, z as loadCodeTraceVerificationArtifacts } from "../benchmark-command-Boqtfx4Z.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-DcAK9pC8.js";
 import { t as nodeHttpPrimeBridgeTransport } from "../prime-bridge-transport-Z3cpKGoV.js";
 import { existsSync, readFileSync, readdirSync, statSync } from "node:fs";

package/dist/{benchmark-command-DVhUPU7H.js → benchmark-command-Boqtfx4Z.js}

@@ -5,16 +5,16 @@ import { a as resolveModelPricing } from "./metrics-DOMpkoeb.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-_IbkejCF.js";
 import { d as withLedgerFileLock, f as writeLedgerFileAtomically } from "./journal-DvKCvjty.js";
 import "./ledger-core/index.js";
-import { C as fsCampaignStorage, S as createRunCostLedger, i as startExternalOptimizerModelProxy, r as runWithCleanup, x as acquireSingleRunLock, y as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-kbqC-iWf.js";
-import { f as redactText } from "./redact-B7rt9Zot.js";
+import { C as fsCampaignStorage, S as createRunCostLedger, i as startExternalOptimizerModelProxy, r as runWithCleanup, x as acquireSingleRunLock, y as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-BrghTvEp.js";
+import { f as redactText } from "./redact-Dk1ZdJEm.js";
 import { M as RAW_FINDING_SCHEMA_PROMPT, N as RawAnalystFindingSchema, P as evidenceRefsFromRawFinding, g as TRACE_ANALYSIS_LIMITS, r as runTraceAnalyst } from "./kind-factory-CdPPHtGZ.js";
 import { r as usageReceiptFromCostLedger } from "./usage-receipt-Cx3xNeyB.js";
-import { a as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-KYQBh9C8.js";
+import { a as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-c_bKHTXz.js";
 import { r as makeFinding } from "./types-CW5b90JH.js";
-import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-BX34vPVY.js";
+import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-k_QdEBZo.js";
 import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-BPowgPm6.js";
 import { i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver } from "./benchmark-BeQJyrRC.js";
-import "./external-optimizer-process-D-Sab4v3.js";
+import "./external-optimizer-process-_YIECYJ7.js";
 import { t as assertEqualDeclarativeTerms } from "./equal-terms-Blx9Zk5I.js";
 import { c as primeProtocolSha256, d as runPrimeExchange, f as decodeReplyRows, n as buildPrimePrompt, t as analystUsageReceiptFromPrimeUsage, u as projectPrimeTrajectory } from "./prime-protocol-DcAK9pC8.js";
 import { t as nodeHttpPrimeBridgeTransport } from "./prime-bridge-transport-Z3cpKGoV.js";
@@ -1415,7 +1415,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "0ff3eda790af1c3811ac4e084fe57c9d64254966fd0ebf53374f40e504bc28be";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "ae1aa0c627f55852e9710693f2b0f043c250bdd692ee4fa4979d6020215aa13d";
 const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
 const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
 const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
@@ -1530,7 +1530,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
 	"src/trace/redact.ts",
 	"src/verdict-cache.ts"
 ]);
-const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "00002cbbc8a749281287418f0abc03e4fc6a78ef3c1b4f21e33f2452629283da";
+const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "8bb4bdae57e4c5596ffe77d80c7a16e67eef7b2fc5087c2af369a417ed423a26";
 function analystBenchmarkImplementationDigest() {
 	return ANALYST_BENCHMARK_IMPLEMENTATION_SHA256;
 }
@@ -6316,4 +6316,4 @@ function shellQuote(value) {
 //#endregion
 export { ANALYST_BENCHMARK_MANIFEST_FILE as $, readAnalystInstructionsOverride as A, parseVerificationOutcome as B, emptyPublicBenchmarkRunner as C, summarizeCodeTraceCalibration as D, renderCodeTraceCalibrationMarkdown as E, publicBenchmarkRlmInstructions as F, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as G, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as H, publicBenchmarkSystemPrompt as I, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as J, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as K, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as L, MAX_INCORRECT_BLOCKS as M, MAX_INCORRECT_BLOCK_STEPS as N, analystInstructionsOverrideFromText as O, publicBenchmarkProtocolSha256 as P, ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as Q, appendVerificationArtifactsToOtlp as R, adaptPublicBenchmarkFindings as S, readAnalystBenchmarkArtifact as T, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as U, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as V, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as W, analystBenchmarkImplementationDigest as X, analystBenchmarkDependencyLockDigest as Y, ANALYST_BENCHMARK_COST_LEDGER_FILE as Z, publicDirectAnalystDefinition as _, primeCodeTraceAnalystDefinition as a, codeTraceBenchCase as at, analystDefinitionAsymmetries as b, preparePublicAnalystBenchmark as c, agentRxPredictionsToFindings as ct, selectPublicBenchmarkRows as d, normalizeBenchmarkLabel as dt, ANALYST_BENCHMARK_OBSERVATIONS_FILE as et, createPublicBenchmarkRlmRunner as f, createPublicBenchmarkDirectRunner as g, runReplVariableAnalystDefinition as h, primeAnalystProtocolSha256 as i, summarizeAgentRxCalibration as it, CODE_TRACE_BENCH_ANALYST_PROMPT as j, effectiveAnalystProtocolSha256 as k, publicBenchmarkDistributions as l, normalizeAgentRxCategory as lt, rlmEngineLimits as m, renderAnalystBenchmarkMarkdown as n, AGENT_RX_UPSTREAM_REVISION as nt, runInlineAnalystDefinition as o, codeTracerPredictionsToFindings as ot, publicRlmAnalystDefinition as p, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as q, createPrimeBenchmarkRunner as r, renderAgentRxCalibrationMarkdown as rt, loadPublicBenchmarkRows as s, agentRxBenchmarkCase as st, runAnalystBenchmarkCommand as t, compareAnalystRunners as tt, publicBenchmarkSelectionReport as u, roundAgentRxStep as ut, runChunkedAnalystDefinition as v, expandCodeTraceFailureBlocks as w, analystDefinitionProtocolSha256 as x, AnalystExpressivenessError as y, loadCodeTraceVerificationArtifacts as z };
 
-//# sourceMappingURL=benchmark-command-DVhUPU7H.js.map
+//# sourceMappingURL=benchmark-command-Boqtfx4Z.js.map