@tangle-network/agent-eval 0.211.0 → 0.211.3

package/CHANGELOG.md

@@ -4,6 +4,18 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [0.211.3] — 2026-10-10
+
+- fix(deps): depend on harness-sessions by range, not an exact pin (#972)
+
+## [0.211.2] — 2026-10-10
+
+- fix(analyst): re-pin the benchmark implementation after the gpt-6-luna price (#967)
+
+## [0.211.1] — 2026-10-10
+
+- fix(metrics): price gpt-6-luna at the Tangle Router rate (#965)
+
 ## [0.211.0] — 2026-10-10
 
 - feat(meta-eval): hold veto judges to their false-fail rate on owner passes (#963)

package/dist/analyst/index.d.ts

@@ -1184,11 +1184,11 @@ export declare const ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM = "sha256
  * fields blanked, so a release that only bumps the version keeps the pin. */
 export declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM = "sha256-canonical-file-manifest-without-own-version";
 export declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES: readonly string[];
-export declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "374fcff7d3af677d167be27df41d55c9f5b4005a16c7070a098b8168e55f51d1";
+export declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "78386f0e97ba8692994d6af6b16addd2d027db0e38be8d3ebc1fb586dde796bb";
 export declare const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
 export declare const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
 export declare const ANALYST_BENCHMARK_IMPLEMENTATION_FILES: readonly string[];
-export declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "b749c8adf53ec2d9f8ab40a65d33c1c5742acdb3d52f403e663438e27f8afe93";
+export declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "11b9a5effdd8e9488f13d936335392eefa0a527248529c1099563b30ea5a9e92";
 export declare function analystBenchmarkImplementationDigest(): string;
 export declare function analystBenchmarkDependencyLockDigest(): string;
 //#endregion

package/dist/analyst/index.js

@@ -1,14 +1,14 @@
-import { i as CostLedger } from "../cost-ledger-_IbkejCF.js";
+import { i as CostLedger } from "../cost-ledger-DFOeLeJi.js";
 import { n as isProposalFinding, t as assertProposalFindings } from "../proposal-findings-CXblsskH.js";
-import { B as FINDING_SUBJECT_SYNTAX, F as parseRawFinding, G as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, H as findingSubjectGrammarPromptFor, I as parseTraceSpanEvidenceUri, K as resolveTraceAnalystLimits, L as coerceJson, M as RAW_FINDING_SCHEMA_PROMPT, N as RawAnalystFindingSchema, P as evidenceRefsFromRawFinding, R as stripCodeFences, U as parseFindingSubject, V as KIND_EXPECTED_SUBJECTS, W as renderFindingSubject, i as buildTraceToolsForGroup, n as renderPriorFindings, r as runTraceAnalyst, t as createTraceAnalyst, z as FINDING_SUBJECT_KINDS } from "../kind-factory-ivTx6koH.js";
+import { B as FINDING_SUBJECT_SYNTAX, F as parseRawFinding, G as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, H as findingSubjectGrammarPromptFor, I as parseTraceSpanEvidenceUri, K as resolveTraceAnalystLimits, L as coerceJson, M as RAW_FINDING_SCHEMA_PROMPT, N as RawAnalystFindingSchema, P as evidenceRefsFromRawFinding, R as stripCodeFences, U as parseFindingSubject, V as KIND_EXPECTED_SUBJECTS, W as renderFindingSubject, i as buildTraceToolsForGroup, n as renderPriorFindings, r as runTraceAnalyst, t as createTraceAnalyst, z as FINDING_SUBJECT_KINDS } from "../kind-factory-CMlOx08-.js";
 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-DF4Yp7HQ.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-BhYGMVbV.js";
 import { i as makeProposalFinding, n as computeFindingId, r as makeFinding } from "../types-CW5b90JH.js";
-import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-BpaKVKJA.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-BQxZyXdN.js";
-import { t as createChatClient } from "../chat-client-CydfmLdO.js";
+import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-D7BIsKyZ.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-B4zwq9Uy.js";
+import { t as createChatClient } from "../chat-client-Bnx8NZe4.js";
 import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-BywPeAUo.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-S8tCtkxh.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-B-x91Ly1.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-S8tCtkxh.js → benchmark-command-B-x91Ly1.js}

@@ -1,21 +1,21 @@
 import { s as ValidationError, t as AgentEvalError } from "./errors-Dngq5h35.js";
 import { a as hashCanonical, i as compareCodeUnits, o as jsonDocument, r as canonicalString } from "./canonical-BsZVgBhW.js";
 import { r as pairedBootstrap } from "./paired-tests-jbwPdSz5.js";
-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 { a as resolveModelPricing } from "./metrics-BKaPBtIG.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-DFOeLeJi.js";
 import { d as withLedgerFileLock, f as writeLedgerFileAtomically } from "./journal-DvKCvjty.js";
 import "./ledger-core/index.js";
-import { S as fsCampaignStorage, i as startExternalOptimizerModelProxy, r as runWithCleanup, x as createRunCostLedger, y as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-C0EsxEbI.js";
+import { S as fsCampaignStorage, i as startExternalOptimizerModelProxy, r as runWithCleanup, x as createRunCostLedger, y as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-DitxECD3.js";
 import { f as redactText } from "./redact-Dk1ZdJEm.js";
 import { t as acquireSingleRunLock } from "./single-run-lock-fVu3MZWH.js";
-import { a as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-v968tWw8.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-ivTx6koH.js";
+import { a as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-C_o62yG1.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-CMlOx08-.js";
 import { r as usageReceiptFromCostLedger } from "./usage-receipt-Cx3xNeyB.js";
 import { r as makeFinding } from "./types-CW5b90JH.js";
-import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-BpaKVKJA.js";
-import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-__ebQ6Hn.js";
+import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-D7BIsKyZ.js";
+import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-0AiS29kg.js";
 import { i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver } from "./benchmark-BywPeAUo.js";
-import "./external-optimizer-process-D2Txd-7D.js";
+import "./external-optimizer-process-CB3RGyr7.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";
@@ -1418,7 +1418,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "374fcff7d3af677d167be27df41d55c9f5b4005a16c7070a098b8168e55f51d1";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "78386f0e97ba8692994d6af6b16addd2d027db0e38be8d3ebc1fb586dde796bb";
 const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
 const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
 const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
@@ -1537,7 +1537,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
 	"src/trace/redact.ts",
 	"src/verdict-cache.ts"
 ]);
-const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "b749c8adf53ec2d9f8ab40a65d33c1c5742acdb3d52f403e663438e27f8afe93";
+const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "11b9a5effdd8e9488f13d936335392eefa0a527248529c1099563b30ea5a9e92";
 function analystBenchmarkImplementationDigest() {
 	return ANALYST_BENCHMARK_IMPLEMENTATION_SHA256;
 }
@@ -6324,4 +6324,4 @@ 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-S8tCtkxh.js.map
+//# sourceMappingURL=benchmark-command-B-x91Ly1.js.map