@tangle-network/agent-eval 0.174.0 → 0.175.0

package/CHANGELOG.md

@@ -4,6 +4,29 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [0.175.0] — 2026-09-06
+
+### Added
+
+- `agent-eval supervisor-run report <runDir> [--format headline|markdown|json]` prints one run directory's report.
+  It exits 1 when the directory cannot be read and 2 on a usage error.
+- `OutcomeMetrics.supStatusSource`, `supReason`, and `failure` name the record a status came from, Runtime's no-winner reason, and the recorded error.
+  `readTerminalRecord` is the one derivation the analyzer and the rollout minter share.
+
+### Changed
+
+- The supervisor-run reader takes a run's status from Runtime's own settle record.
+  `result.json` is the `SupervisedResult` that `supervise()` returned, and its `kind` is the status (`runtime-result`).
+  The control-plane-era `state.json` `status` and `result.json` `sup_status` remain readable as named legacy sources (`legacy-state`, `legacy-result`).
+- A Runtime `failure.json` without a `result.json` reports status `failed` with the recorded error (`runtime-failure`) instead of an unavailable status.
+  A `failure.json` beside a settled result is reported with `earlierAttempt: true`; the settled result stays the status.
+- A directory holding `observer.jsonl` or `failure.json` is a Runtime run directory before its spawn journal exists.
+  `isRuntimeSupervisorRunDir`, `analyzeSupervisorRun`, and `findSupervisorRunDirs` recognize it, and every journal metric stays a named absence.
+- The Runtime reader no longer copies the result status onto its begin-stamp state document; `SupervisorRunSources.state` for a Runtime run carries `id` and `startedAt` only.
+  It no longer reads `trajectory.json`, which Runtime never wrote.
+
+---
+
 ## [0.174.0] — 2026-09-05
 
 ### Changed

package/README.md

@@ -163,7 +163,7 @@ and [DSPy](./docs/campaign-proposers.md#use-official-dspy-optimizers).
 | `@tangle-network/agent-eval/trajectory-replay` | Re-execute a recorded shell trajectory and check whether its failure reproduces. |
 | `@tangle-network/agent-eval/traces` | Store, replay, and inspect structured traces. |
 | `@tangle-network/agent-eval/reporting` | Statistical comparisons and report rendering. |
-| `@tangle-network/agent-eval/supervisor-run` | Read recursive run directories without collapsing missing measurements to zero. |
+| `@tangle-network/agent-eval/supervisor-run` | Read recursive run directories without collapsing missing measurements to zero; `agent-eval supervisor-run report <runDir>` prints one. |
 | `@tangle-network/agent-eval/meta-eval` | Measure the grader itself: judge calibration, sentinels, and seeded known-wrong plants. |
 | `@tangle-network/agent-eval/profile-cell` | Create and validate portable agent-profile identities. |
 | `@tangle-network/agent-eval/ledger-core` | Append-only hash-chained journal with idempotent append and chain verification. |

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-FfNzaUHV.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-CvW_I72-.js";
 import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-DAe1t6zb.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-Bn-nlnSV.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-BAAiSF3_.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
@@ -1265,7 +1265,7 @@ 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 = "10c77bd9ce4d896811395f8b623216f51bd03dab9ea209cb58e1d8d7b78acb7a";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "4aff818466add5b179dd2308dfa7e9c3ed4b1703c4f135fa2509ac4d47e626ef";
 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

@@ -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 { A as RAW_FINDING_SCHEMA_PROMPT, B as parseFindingSubject, F as stripCodeFences, H as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, I as FINDING_SUBJECT_KINDS, L as FINDING_SUBJECT_SYNTAX, M as evidenceRefsFromRawFinding, N as parseRawFinding, P as coerceJson, R as KIND_EXPECTED_SUBJECTS, U as resolveTraceAnalystLimits, V as renderFindingSubject, i as buildTraceToolsForGroup, j as RawAnalystFindingSchema, n as renderPriorFindings, r as runTraceAnalyst, t as createTraceAnalyst, z as findingSubjectGrammarPromptFor } from "../kind-factory-BLvL-E44.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-CrAp0pYq.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-DBqVI4pq.js";
 import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-Caz2pl4L.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-E3s_fEjB.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-mZIlR-ra.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-D_5xG9LG.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-mZIlR-ra.js → benchmark-command-D_5xG9LG.js}

@@ -1412,7 +1412,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "10c77bd9ce4d896811395f8b623216f51bd03dab9ea209cb58e1d8d7b78acb7a";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "4aff818466add5b179dd2308dfa7e9c3ed4b1703c4f135fa2509ac4d47e626ef";
 const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
 const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
 const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
@@ -6351,4 +6351,4 @@ 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-mZIlR-ra.js.map
+//# sourceMappingURL=benchmark-command-D_5xG9LG.js.map