@tangle-network/agent-eval 0.147.0 → 0.148.0

package/CHANGELOG.md

@@ -8,6 +8,28 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [0.148.0] — 2026-08-18
+
+### Added
+
+- `@tangle-network/agent-eval/experiment` publishes the evidence receipt: `createEvidenceReceipt`, `verifyEvidenceReceipt`, `isIndependentEvidence`, `EVIDENCE_RECEIPT_VERSION`, `EVIDENCE_AUTHORITY_KINDS`, `INDEPENDENT_EVIDENCE_AUTHORITY_KINDS`, and the `EvidenceReceipt` / `EvidenceBinding` / `EvidenceAuthority` / `EvidenceAuthorityKind` / `EvidenceReceiptVerification` / `CreateEvidenceReceiptInput` types.
+
+  A receipt binds one Runtime execution to the measurement that judged it, without either package importing the other. It carries stable pursuit and run identity, the exact candidate, evaluator, environment, input-set and output content identities, the result digest, and the authority class that made the observation. The payload is attested with the existing canonical report attestation, so mutating any bound field invalidates the receipt.
+
+  The authority vocabulary is closed. An unknown or misspelled kind is never independent, and `candidate-self-report` is never independent, so a candidate cannot certify itself by accident.
+
+- A bounded `SearchHistoryReceipt` over the canonical `SearchLedger`, plus search-history coverage and `searchHistoryPolicy: 'require-complete'` on `compareOptimizationMethods()`. Strict mode refuses missing or denominator-incomplete optimization evidence before untouched-final-test scoring. Rich events remain only in the ledger.
+
+### Fixed
+
+- The packed dependency cohort is read from the manifests instead of a second hand-kept list.
+
+### Changed
+
+- No existing export changed.
+
+---
+
 ## [0.147.0] — 2026-08-16
 
 ### Removed

package/README.md

@@ -71,6 +71,12 @@ Keep the default whenever real model calls happen.
 
 Runnable copy: [`examples/evaluate-a-change`](./examples/evaluate-a-change/).
 
+## Auditable optimization history
+
+Optimization methods may return a bounded `SearchHistoryReceipt` over Eval's canonical hash-chained `SearchLedger`. Existing callers keep working and see missing-history coverage. Autonomous and publication-grade runs set `searchHistoryPolicy: 'require-complete'` to refuse an incomplete planned denominator before the untouched final cases are opened.
+
+The receipt is a small proof envelope, not another event log. Exact candidates, attempts, failures, decisions, and missing ids remain in the ledger. See [complete optimization search history](./docs/search-history-receipts.md).
+
 ## Which Front Door
 
 Every row is a function you call. Each links to a runnable example.
@@ -188,3 +194,4 @@ uv run --frozen pytest tests/test_dspy_metric.py
 ## License
 
 MIT.
+

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 = "6541250ffe203c50dc685ee65ec25edeba6f63d9d0e769e8d3520373673f0eb5";
+declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "5c7e5561a2ecaa48aaffc52d8a44f582642ed434a92839ae4741ad5556fd9789";
 /** 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

package/dist/analyst/index.js

@@ -7,7 +7,7 @@ import { a as assertExactRegistryRunOpts, c as KNOWLEDGE_GAP_KIND_SPEC, d as CON
 import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-BmtOl_kP.js";
 import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-BI7Rrl5-.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-BTiysiYU.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-Cz4fDmsk.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-BTiysiYU.js → benchmark-command-Cz4fDmsk.js}

@@ -1209,7 +1209,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
 	"package.json",
 	"pnpm-lock.yaml"
 ]);
-const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "6541250ffe203c50dc685ee65ec25edeba6f63d9d0e769e8d3520373673f0eb5";
+const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "5c7e5561a2ecaa48aaffc52d8a44f582642ed434a92839ae4741ad5556fd9789";
 /** 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
@@ -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-BTiysiYU.js.map
+//# sourceMappingURL=benchmark-command-Cz4fDmsk.js.map