@tangle-network/agent-eval 0.181.0 → 0.182.0

package/CHANGELOG.md

@@ -6,6 +6,20 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ## Unreleased
 
+## [0.182.0] — 2026-09-15
+
+### Breaking
+
+- Retire the legacy loops supervisor-run reader and its compatibility exports.
+  Runtime supervisor runs now use the `.agent/supervisor` layout and the runtime journal dialect only.
+- Remove legacy `.loops`, `state.status`, and `result.sup_status` fallback behavior.
+  Missing runtime evidence remains explicitly unavailable.
+
+### Changed
+
+- Reduce paired-score gate work and use the exact shortcut for equal-magnitude Wilcoxon differences.
+- Refresh the analyst benchmark implementation identity after the evaluation changes.
+
 ## [0.181.0] — 2026-09-14
 
 ### Changed

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-BwDSWVzg.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-DS1cysJy.js";
 import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-B2bSNaJB.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-DNntP4ch.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-DbG8QbH9.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/analyst/adapters.d.ts
@@ -1265,11 +1265,11 @@ 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 = "39632afc0f02da9333079d4c6323bab101d1bd0eb47a0ea06fa910ae181b4b40";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "dfee549f65d9965471f1925b1cb8ab2860c74b09f62ea60e49478c0bee16883a";
 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 = "e499ff9c5a3b24104d1a9dbc0c3742ffd08b67ff1b852922b423d38231954254";
+declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "53b4c9f453ed05e46968ed39a8e365f8593163b264c0b1a770f7781005d3aae7";
 declare function analystBenchmarkImplementationDigest(): string;
 declare function analystBenchmarkDependencyLockDigest(): string;
 //#endregion

package/dist/analyst/index.js

@@ -2,12 +2,12 @@ import { i as CostLedger } from "../cost-ledger-B1qx30B4.js";
 import { n as assertProposalFindings, r as isProposalFinding } from "../abort-signal-CtzAM_sJ.js";
 import { c as validateUsageSettlementTimeout, i as makeProposalFinding, n as computeFindingId, o as settleUsageReceiptFromCostLedger, r as makeFinding } from "../types-DQ0e2E7y.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-D5HOW3R0.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-aL7xUrUz.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-DHWwIwa8.js";
 import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-S53V0HhE.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-Bm5JDEKO.js";
 import { t as createChatClient } from "../chat-client-CkmjYlfB.js";
 import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-DQKzykkO.js";
-import { $ as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, A as effectiveAnalystProtocolSha256, B as loadCodeTraceVerificationArtifacts, C as adaptPublicBenchmarkFindings, D as renderCodeTraceCalibrationMarkdown, E as readAnalystBenchmarkArtifact, F as publicBenchmarkProtocolSha256, G as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, H as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, I as publicBenchmarkRlmInstructions, J as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, K as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, L as publicBenchmarkSystemPrompt, M as CODE_TRACE_BENCH_ANALYST_PROMPT, N as MAX_INCORRECT_BLOCKS, O as summarizeCodeTraceCalibration, P as MAX_INCORRECT_BLOCK_STEPS, Q as ANALYST_BENCHMARK_COST_LEDGER_FILE, R as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, S as analystDefinitionProtocolSha256, T as expandCodeTraceFailureBlocks, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, V as parseVerificationOutcome, W as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, X as analystBenchmarkDependencyLockDigest, Y as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, Z as analystBenchmarkImplementationDigest, _ as createPublicBenchmarkDirectRunner, a as primeCodeTraceAnalystDefinition, at as summarizeAgentRxCalibration, b as AnalystExpressivenessError, c as loadPublicBenchmarkRows, ct as agentRxBenchmarkCase, d as publicBenchmarkSelectionReport, dt as roundAgentRxStep, et as ANALYST_BENCHMARK_MANIFEST_FILE, f as selectPublicBenchmarkRows, ft as normalizeBenchmarkLabel, g as runReplVariableAnalystDefinition, h as rlmEngineLimits, i as primeAnalystProtocolSha256, it as renderAgentRxCalibrationMarkdown, j as readAnalystInstructionsOverride, k as analystInstructionsOverrideFromText, l as preparePublicAnalystBenchmark, lt as agentRxPredictionsToFindings, m as publicRlmAnalystDefinition, n as renderAnalystBenchmarkMarkdown, nt as compareAnalystRunners, o as runInlineAnalystDefinition, ot as codeTraceBenchCase, p as createPublicBenchmarkRlmRunner, q as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, r as createPrimeBenchmarkRunner, rt as AGENT_RX_UPSTREAM_REVISION, s as nodeHttpPrimeBridgeTransport, st as codeTracerPredictionsToFindings, t as runAnalystBenchmarkCommand, tt as ANALYST_BENCHMARK_OBSERVATIONS_FILE, u as publicBenchmarkDistributions, ut as normalizeAgentRxCategory, v as publicDirectAnalystDefinition, w as emptyPublicBenchmarkRunner, x as analystDefinitionAsymmetries, y as runChunkedAnalystDefinition, z as appendVerificationArtifactsToOtlp } from "../benchmark-command-B57n9vjz.js";
+import { $ as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, A as effectiveAnalystProtocolSha256, B as loadCodeTraceVerificationArtifacts, C as adaptPublicBenchmarkFindings, D as renderCodeTraceCalibrationMarkdown, E as readAnalystBenchmarkArtifact, F as publicBenchmarkProtocolSha256, G as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, H as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, I as publicBenchmarkRlmInstructions, J as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, K as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, L as publicBenchmarkSystemPrompt, M as CODE_TRACE_BENCH_ANALYST_PROMPT, N as MAX_INCORRECT_BLOCKS, O as summarizeCodeTraceCalibration, P as MAX_INCORRECT_BLOCK_STEPS, Q as ANALYST_BENCHMARK_COST_LEDGER_FILE, R as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, S as analystDefinitionProtocolSha256, T as expandCodeTraceFailureBlocks, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, V as parseVerificationOutcome, W as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, X as analystBenchmarkDependencyLockDigest, Y as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, Z as analystBenchmarkImplementationDigest, _ as createPublicBenchmarkDirectRunner, a as primeCodeTraceAnalystDefinition, at as summarizeAgentRxCalibration, b as AnalystExpressivenessError, c as loadPublicBenchmarkRows, ct as agentRxBenchmarkCase, d as publicBenchmarkSelectionReport, dt as roundAgentRxStep, et as ANALYST_BENCHMARK_MANIFEST_FILE, f as selectPublicBenchmarkRows, ft as normalizeBenchmarkLabel, g as runReplVariableAnalystDefinition, h as rlmEngineLimits, i as primeAnalystProtocolSha256, it as renderAgentRxCalibrationMarkdown, j as readAnalystInstructionsOverride, k as analystInstructionsOverrideFromText, l as preparePublicAnalystBenchmark, lt as agentRxPredictionsToFindings, m as publicRlmAnalystDefinition, n as renderAnalystBenchmarkMarkdown, nt as compareAnalystRunners, o as runInlineAnalystDefinition, ot as codeTraceBenchCase, p as createPublicBenchmarkRlmRunner, q as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, r as createPrimeBenchmarkRunner, rt as AGENT_RX_UPSTREAM_REVISION, s as nodeHttpPrimeBridgeTransport, st as codeTracerPredictionsToFindings, t as runAnalystBenchmarkCommand, tt as ANALYST_BENCHMARK_OBSERVATIONS_FILE, u as publicBenchmarkDistributions, ut as normalizeAgentRxCategory, v as publicDirectAnalystDefinition, w as emptyPublicBenchmarkRunner, x as analystDefinitionAsymmetries, y as runChunkedAnalystDefinition, z as appendVerificationArtifactsToOtlp } from "../benchmark-command-7X7HPNHh.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-B57n9vjz.js → benchmark-command-7X7HPNHh.js}

@@ -1413,7 +1413,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "39632afc0f02da9333079d4c6323bab101d1bd0eb47a0ea06fa910ae181b4b40";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "dfee549f65d9965471f1925b1cb8ab2860c74b09f62ea60e49478c0bee16883a";
 const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
 const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
 const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
@@ -1526,7 +1526,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
 	"src/trace/raw-provider-sink.ts",
 	"src/verdict-cache.ts"
 ]);
-const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "e499ff9c5a3b24104d1a9dbc0c3742ffd08b67ff1b852922b423d38231954254";
+const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "53b4c9f453ed05e46968ed39a8e365f8593163b264c0b1a770f7781005d3aae7";
 function analystBenchmarkImplementationDigest() {
 	return ANALYST_BENCHMARK_IMPLEMENTATION_SHA256;
 }
@@ -6352,4 +6352,4 @@ function shellQuote(value) {
 //#endregion
 export { ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as $, effectiveAnalystProtocolSha256 as A, loadCodeTraceVerificationArtifacts as B, adaptPublicBenchmarkFindings as C, renderCodeTraceCalibrationMarkdown as D, readAnalystBenchmarkArtifact as E, publicBenchmarkProtocolSha256 as F, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as G, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as H, publicBenchmarkRlmInstructions as I, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as J, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as K, publicBenchmarkSystemPrompt as L, CODE_TRACE_BENCH_ANALYST_PROMPT as M, MAX_INCORRECT_BLOCKS as N, summarizeCodeTraceCalibration as O, MAX_INCORRECT_BLOCK_STEPS as P, ANALYST_BENCHMARK_COST_LEDGER_FILE as Q, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as R, analystDefinitionProtocolSha256 as S, expandCodeTraceFailureBlocks as T, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as U, parseVerificationOutcome as V, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as W, analystBenchmarkDependencyLockDigest as X, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as Y, analystBenchmarkImplementationDigest as Z, createPublicBenchmarkDirectRunner as _, primeCodeTraceAnalystDefinition as a, summarizeAgentRxCalibration as at, AnalystExpressivenessError as b, loadPublicBenchmarkRows as c, agentRxBenchmarkCase as ct, publicBenchmarkSelectionReport as d, roundAgentRxStep as dt, ANALYST_BENCHMARK_MANIFEST_FILE as et, selectPublicBenchmarkRows as f, normalizeBenchmarkLabel as ft, runReplVariableAnalystDefinition as g, rlmEngineLimits as h, primeAnalystProtocolSha256 as i, renderAgentRxCalibrationMarkdown as it, readAnalystInstructionsOverride as j, analystInstructionsOverrideFromText as k, preparePublicAnalystBenchmark as l, agentRxPredictionsToFindings as lt, publicRlmAnalystDefinition as m, renderAnalystBenchmarkMarkdown as n, compareAnalystRunners as nt, runInlineAnalystDefinition as o, codeTraceBenchCase as ot, createPublicBenchmarkRlmRunner as p, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as q, createPrimeBenchmarkRunner as r, AGENT_RX_UPSTREAM_REVISION as rt, nodeHttpPrimeBridgeTransport as s, codeTracerPredictionsToFindings as st, runAnalystBenchmarkCommand as t, ANALYST_BENCHMARK_OBSERVATIONS_FILE as tt, publicBenchmarkDistributions as u, normalizeAgentRxCategory as ut, publicDirectAnalystDefinition as v, emptyPublicBenchmarkRunner as w, analystDefinitionAsymmetries as x, runChunkedAnalystDefinition as y, appendVerificationArtifactsToOtlp as z };
 
-//# sourceMappingURL=benchmark-command-B57n9vjz.js.map
+//# sourceMappingURL=benchmark-command-7X7HPNHh.js.map