@tangle-network/agent-eval 0.161.0 → 0.161.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -4,6 +4,15 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
4
4
 
5
5
  ---
6
6
 
7
+ ## [0.161.1] — 2026-08-21
8
+
9
+ ### Changed
10
+
11
+ - Declare `@tangle-network/agent-interface` as `^1.4.0` instead of `^1.1.0`. The lockfile resolved 1.1.0, so the packed dist was compiled and tested against 1.1.0 while the range invited a consumer to resolve any later 1.x. The floor is now the copy this release was built against, which is what `verify:package` asserts for every first-party dependency.
12
+ - `ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256` is `657957f8…a0cbdcc8`. The digest covers the four manifests this release changed (`package.json`, `pnpm-lock.yaml`, `clients/python/pyproject.toml`, `clients/python/uv.lock`), so a benchmark artifact produced by this release records the new value. The historical `ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256` is unchanged: it states a fact about already-published evidence.
13
+
14
+ ---
15
+
7
16
  ## [0.161.0] — 2026-08-21
8
17
 
9
18
  ### Added
@@ -1297,7 +1297,7 @@ declare function runAnalystBenchmarkCommand(argv: readonly string[], env?: NodeJ
1297
1297
  declare const ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM = "sha256-canonical-source-manifest";
1298
1298
  declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM = "sha256-canonical-file-manifest";
1299
1299
  declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES: readonly string[];
1300
- declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "6de51aaf48adb3be31601f2e53fbf06a4d407fa16a8c33156caa41bf8c21b09f";
1300
+ declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "657957f896b75dcca9b53a4d0b91d699094bd92d68f8ecaff83c7f74a0cbdcc8";
1301
1301
  declare const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
1302
1302
  declare const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
1303
1303
  declare const ANALYST_BENCHMARK_IMPLEMENTATION_FILES: readonly string[];
@@ -7,7 +7,7 @@ import { a as DEFAULT_TRACE_ANALYST_KINDS, c as IMPROVEMENT_KIND_SPEC, d as Cont
7
7
  import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-DptEII26.js";
8
8
  import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-BSkKKHeq.js";
9
9
  import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-BhT16ep9.js";
10
- import { $ as ANALYST_BENCHMARK_COST_LEDGER_FILE, A as analystInstructionsOverrideFromText, B as appendVerificationArtifactsToOtlp, C as adaptPublicBenchmarkFindings, D as renderCodeTraceCalibrationMarkdown, E as readAnalystBenchmarkArtifact, F as MAX_INCORRECT_BLOCK_STEPS, G as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, H as parseVerificationOutcome, I as publicBenchmarkProtocolSha256, J as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, K as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, L as publicBenchmarkRlmInstructions, M as readAnalystInstructionsOverride, N as CODE_TRACE_BENCH_ANALYST_PROMPT, O as summarizeCodeTraceCalibration, P as MAX_INCORRECT_BLOCKS, Q as analystBenchmarkImplementationDigest, R as publicBenchmarkSystemPrompt, S as analystDefinitionProtocolSha256, T as expandCodeTraceFailureBlocks, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, V as loadCodeTraceVerificationArtifacts, W as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, X as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, Y as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, Z as analystBenchmarkDependencyLockDigest, _ 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_LOCAL_RECEIPT_FILE, f as selectPublicBenchmarkRows, ft as normalizeBenchmarkLabel, g as runReplVariableAnalystDefinition, h as rlmEngineLimits, i as primeAnalystProtocolSha256, it as renderAgentRxCalibrationMarkdown, j as effectiveAnalystProtocolSha256, k as compareAnalystRunners, l as preparePublicAnalystBenchmark, lt as agentRxPredictionsToFindings, m as publicRlmAnalystDefinition, n as renderAnalystBenchmarkMarkdown, nt as ANALYST_BENCHMARK_OBSERVATIONS_FILE, o as runInlineAnalystDefinition, ot as codeTraceBenchCase, p as createPublicBenchmarkRlmRunner, q as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, r as createPrimeBenchmarkRunner, rt as AGENT_RX_UPSTREAM_REVISION, s as nodeHttpPrimeBridgeTransport, st as codeTracerPredictionsToFindings, t as runAnalystBenchmarkCommand, tt as ANALYST_BENCHMARK_MANIFEST_FILE, u as publicBenchmarkDistributions, ut as normalizeAgentRxCategory, v as publicDirectAnalystDefinition, w as emptyPublicBenchmarkRunner, x as analystDefinitionAsymmetries, y as runChunkedAnalystDefinition, z as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES } from "../benchmark-command-BVtaq_ve.js";
10
+ import { $ as ANALYST_BENCHMARK_COST_LEDGER_FILE, A as analystInstructionsOverrideFromText, B as appendVerificationArtifactsToOtlp, C as adaptPublicBenchmarkFindings, D as renderCodeTraceCalibrationMarkdown, E as readAnalystBenchmarkArtifact, F as MAX_INCORRECT_BLOCK_STEPS, G as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, H as parseVerificationOutcome, I as publicBenchmarkProtocolSha256, J as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, K as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, L as publicBenchmarkRlmInstructions, M as readAnalystInstructionsOverride, N as CODE_TRACE_BENCH_ANALYST_PROMPT, O as summarizeCodeTraceCalibration, P as MAX_INCORRECT_BLOCKS, Q as analystBenchmarkImplementationDigest, R as publicBenchmarkSystemPrompt, S as analystDefinitionProtocolSha256, T as expandCodeTraceFailureBlocks, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, V as loadCodeTraceVerificationArtifacts, W as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, X as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, Y as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, Z as analystBenchmarkDependencyLockDigest, _ 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_LOCAL_RECEIPT_FILE, f as selectPublicBenchmarkRows, ft as normalizeBenchmarkLabel, g as runReplVariableAnalystDefinition, h as rlmEngineLimits, i as primeAnalystProtocolSha256, it as renderAgentRxCalibrationMarkdown, j as effectiveAnalystProtocolSha256, k as compareAnalystRunners, l as preparePublicAnalystBenchmark, lt as agentRxPredictionsToFindings, m as publicRlmAnalystDefinition, n as renderAnalystBenchmarkMarkdown, nt as ANALYST_BENCHMARK_OBSERVATIONS_FILE, o as runInlineAnalystDefinition, ot as codeTraceBenchCase, p as createPublicBenchmarkRlmRunner, q as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, r as createPrimeBenchmarkRunner, rt as AGENT_RX_UPSTREAM_REVISION, s as nodeHttpPrimeBridgeTransport, st as codeTracerPredictionsToFindings, t as runAnalystBenchmarkCommand, tt as ANALYST_BENCHMARK_MANIFEST_FILE, u as publicBenchmarkDistributions, ut as normalizeAgentRxCategory, v as publicDirectAnalystDefinition, w as emptyPublicBenchmarkRunner, x as analystDefinitionAsymmetries, y as runChunkedAnalystDefinition, z as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES } from "../benchmark-command-BDC3Gocz.js";
11
11
  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";
12
12
  import { existsSync, readFileSync, readdirSync, statSync } from "node:fs";
13
13
  import { join } from "node:path";
@@ -1211,7 +1211,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
1211
1211
  "package.json",
1212
1212
  "pnpm-lock.yaml"
1213
1213
  ]);
1214
- const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "6de51aaf48adb3be31601f2e53fbf06a4d407fa16a8c33156caa41bf8c21b09f";
1214
+ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "657957f896b75dcca9b53a4d0b91d699094bd92d68f8ecaff83c7f74a0cbdcc8";
1215
1215
  const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
1216
1216
  const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
1217
1217
  const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
@@ -6365,4 +6365,4 @@ function shellQuote(value) {
6365
6365
  //#endregion
6366
6366
  export { ANALYST_BENCHMARK_COST_LEDGER_FILE as $, analystInstructionsOverrideFromText as A, appendVerificationArtifactsToOtlp as B, adaptPublicBenchmarkFindings as C, renderCodeTraceCalibrationMarkdown as D, readAnalystBenchmarkArtifact as E, MAX_INCORRECT_BLOCK_STEPS as F, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as G, parseVerificationOutcome as H, publicBenchmarkProtocolSha256 as I, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as J, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as K, publicBenchmarkRlmInstructions as L, readAnalystInstructionsOverride as M, CODE_TRACE_BENCH_ANALYST_PROMPT as N, summarizeCodeTraceCalibration as O, MAX_INCORRECT_BLOCKS as P, analystBenchmarkImplementationDigest as Q, publicBenchmarkSystemPrompt as R, analystDefinitionProtocolSha256 as S, expandCodeTraceFailureBlocks as T, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as U, loadCodeTraceVerificationArtifacts as V, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as W, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as X, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as Y, analystBenchmarkDependencyLockDigest 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_LOCAL_RECEIPT_FILE as et, selectPublicBenchmarkRows as f, normalizeBenchmarkLabel as ft, runReplVariableAnalystDefinition as g, rlmEngineLimits as h, primeAnalystProtocolSha256 as i, renderAgentRxCalibrationMarkdown as it, effectiveAnalystProtocolSha256 as j, compareAnalystRunners as k, preparePublicAnalystBenchmark as l, agentRxPredictionsToFindings as lt, publicRlmAnalystDefinition as m, renderAnalystBenchmarkMarkdown as n, ANALYST_BENCHMARK_OBSERVATIONS_FILE as nt, runInlineAnalystDefinition as o, codeTraceBenchCase as ot, createPublicBenchmarkRlmRunner as p, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as q, createPrimeBenchmarkRunner as r, AGENT_RX_UPSTREAM_REVISION as rt, nodeHttpPrimeBridgeTransport as s, codeTracerPredictionsToFindings as st, runAnalystBenchmarkCommand as t, ANALYST_BENCHMARK_MANIFEST_FILE as tt, publicBenchmarkDistributions as u, normalizeAgentRxCategory as ut, publicDirectAnalystDefinition as v, emptyPublicBenchmarkRunner as w, analystDefinitionAsymmetries as x, runChunkedAnalystDefinition as y, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as z };
6367
6367
 
6368
- //# sourceMappingURL=benchmark-command-BVtaq_ve.js.map
6368
+ //# sourceMappingURL=benchmark-command-BDC3Gocz.js.map