@tangle-network/agent-eval 0.145.2 → 0.145.4

package/CHANGELOG.md

@@ -8,6 +8,28 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [0.145.4] — 2026-08-12
+
+### Added
+
+- Consumers that split one profile matrix across bounded external grants can
+  create one Eval-owned plan, pass disjoint rows to each segment, reuse the
+  same segment identity to resume failed cells, and call finalization only
+  after every declared row is claimed.
+- Finalization preserves the ordinary `runProfileMatrix` result and reports
+  missing, failed, and zero-score rows separately.
+
+---
+
+## [0.145.3] — 2026-08-12
+
+### Fixed
+
+- Accept and preserve a provider-qualified snapshot when an optimizer callback reports the requested model.
+- Reject true model substitution and conflicting response and receipt identities.
+
+---
+
 ## [0.145.2] — 2026-08-12
 
 ### Changed

package/dist/analyst/index.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 = "653ca1243a688124c0e879e0c59fce8e869c97a31ab81d2b0f56fcbfa5675de4";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "45a5c51773d54898165ee5d6ab339f0b5b20c028378f6ea52350797a778da092";
 /** 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 = "81709d08fb59b31296fed615bddcc1fa5cef1dc2c09579f5002d39e29d8c0315";
+declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "4a960df94935a8177be12a64d20083510ca4afbfa050533a9356447f39c6f846";
 declare function analystBenchmarkImplementationDigest(): string;
 declare function analystBenchmarkDependencyLockDigest(): string;
 //#endregion

package/dist/analyst/index.js

@@ -4,10 +4,10 @@ import { i as isProposalFinding, n as clamp01, r as assertProposalFindings, t as
 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-Bp4Ebuuc.js";
-import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-B_qhSc21.js";
+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-mJSa_4zd.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-BANo4dTm.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/{benchmark-command-mJSa_4zd.js → benchmark-command-BANo4dTm.js}

@@ -4,14 +4,14 @@ 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 { c as writeLedgerFileAtomically, s as withLedgerFileLock } from "./ledger-core-BmZt19oQ.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-DrJ9hR8u.js";
+import { b as createRunCostLedger, i as startExternalOptimizerModelProxy, r as runWithCleanup, v as resolveExternalOptimizerProcessLimits, x as fsCampaignStorage } from "./external-optimizer-subprocess-BhKYK0Jv.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-d0-2TT1g.js";
-import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-B_qhSc21.js";
+import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-BZ2aMZEd.js";
 import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-CsptLYpN.js";
 import { i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver } from "./benchmark-BhT16ep9.js";
-import { n as acquireSingleRunLock } from "./external-optimizer-process-BTiNB-RH.js";
+import { n as acquireSingleRunLock } from "./external-optimizer-process-BRE56woM.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 = "653ca1243a688124c0e879e0c59fce8e869c97a31ab81d2b0f56fcbfa5675de4";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "45a5c51773d54898165ee5d6ab339f0b5b20c028378f6ea52350797a778da092";
 /** 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 = "81709d08fb59b31296fed615bddcc1fa5cef1dc2c09579f5002d39e29d8c0315";
+const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "4a960df94935a8177be12a64d20083510ca4afbfa050533a9356447f39c6f846";
 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-mJSa_4zd.js.map
+//# sourceMappingURL=benchmark-command-BANo4dTm.js.map