@tangle-network/agent-eval 0.187.0 → 0.187.1

package/CHANGELOG.md

@@ -6,6 +6,24 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ## Unreleased
 
+## [0.187.1] — 2026-09-24
+
+### Added
+
+- `/benchmarks` `createHarborBenchmarkAdapter()` and `readHarborTask()` import a Harbor dataset checkout (Terminal-Bench and others) as a `BenchmarkAdapter`.
+  Items carry each task's instruction, timeouts, requested resources and declared artifacts.
+  `evaluate` delegates to the caller's `grade` callback, which runs the dataset's own verifier; a verifier that did not run throws rather than scoring zero.
+- `BenchmarkSource` gains `revision`, `rules` and `contamination`, so an adapter reports the exact upstream commit, the rules a result must follow, and its known training-data exposure.
+- `/supervisor-run` reads the transcripts Runtime retained.
+  The Runtime reader names the root stream, each worker's retained turn outputs (`turns`) and its native-session receipt (`nativeSession`), and checks each named blob on disk.
+  The integrity report adds `transcript-incomplete` (closed workers that lost dispatched turns) and `native-session-unavailable` (closed workers without a native harness session, by Runtime's reason).
+
+### Changed
+
+- `transcript-unavailable` counts only rows with neither inlined messages nor a transcript reference, and reports the rows retained by reference.
+  Before this, every Runtime node was counted, whatever Runtime had kept.
+- Supervisor-run rollout rows carry only the patch and transcript artifacts a reader declares; they no longer derive paths from the run directory.
+
 ## [0.187.0] — 2026-09-23
 
 ### Added

package/dist/analyst/index.d.ts

@@ -7,7 +7,7 @@ import { a as ExactAnalystBudgetPolicy, c as RegistryRunOpts, i as BudgetPolicy,
 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-DMxeb4GD.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-DNlKhIm0.js";
 import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-veQYPiTy.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-C8jCAOTT.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-vYNHCV2G.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-CDBcL9NM.js";
 import { i as nodeHttpPrimeBridgeTransport, n as PrimeBridgeTransportRequest, r as PrimeBridgeTransportResult, t as PrimeBridgeTransport } from "../prime-bridge-transport-6feEglLf.js";
 import { z } from "zod";
@@ -1181,7 +1181,7 @@ 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 = "f638fe34d62cc17bb28901e04051c74d3a16e8193070f27ab7e2afe8ce032df3";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "b0fdbd5a581299cc5c72e27dc13ed0856805db5ad2975323d657518b5095c4ab";
 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[];

package/dist/analyst/index.js

@@ -3,12 +3,12 @@ import { n as assertProposalFindings, r as isProposalFinding } from "../abort-si
 import { i as makeProposalFinding, n as computeFindingId, r as makeFinding } from "../types-C8VBbiw6.js";
 import { B as findingSubjectGrammarPromptFor, F as coerceJson, H as renderFindingSubject, I as stripCodeFences, L as FINDING_SUBJECT_KINDS, M as RawAnalystFindingSchema, N as evidenceRefsFromRawFinding, P as parseRawFinding, R as FINDING_SUBJECT_SYNTAX, U as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, V as parseFindingSubject, W as resolveTraceAnalystLimits, i as buildTraceToolsForGroup, j as RAW_FINDING_SCHEMA_PROMPT, n as renderPriorFindings, r as runTraceAnalyst, t as createTraceAnalyst, z as KIND_EXPECTED_SUBJECTS } from "../kind-factory-V79Hw0AU.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-xiHrldW8.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-Ca2IWH1X.js";
 import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-BE9lCzzL.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-Cnt0TWp0.js";
 import { t as createChatClient } from "../chat-client-DqPqWzVV.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-j1YV50m1.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-CERRH0E6.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-j1YV50m1.js → benchmark-command-CERRH0E6.js}

@@ -1414,7 +1414,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "f638fe34d62cc17bb28901e04051c74d3a16e8193070f27ab7e2afe8ce032df3";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "b0fdbd5a581299cc5c72e27dc13ed0856805db5ad2975323d657518b5095c4ab";
 const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
 const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
 const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
@@ -6315,4 +6315,4 @@ 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-j1YV50m1.js.map
+//# sourceMappingURL=benchmark-command-CERRH0E6.js.map