@tangle-network/agent-eval 0.173.0 → 0.173.1

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
+ ## [0.173.1] — 2026-09-01
8
+
9
+ ### Fixed
10
+
11
+ - A malformed string in `findings_json` now uses the existing bounded repair turn instead of aborting the trace analysis.
12
+ Non-string values still stop the run because they are adapter contract defects, not recoverable model output.
13
+
14
+ ---
15
+
7
16
  ## [0.173.0] — 2026-09-01
8
17
 
9
18
  ### Added
@@ -1267,11 +1267,11 @@ declare function runAnalystBenchmarkCommand(argv: readonly string[], env?: NodeJ
1267
1267
  declare const ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM = "sha256-canonical-source-manifest";
1268
1268
  declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM = "sha256-canonical-file-manifest";
1269
1269
  declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES: readonly string[];
1270
- declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "8e4b431bbba1d1d485847fd21acea07ce78bde91f43b9f64750046d70b7373b1";
1270
+ declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "e859e07e195eb64386e00c81b67a49cc627a5d138ed90a1fac537aa956085b17";
1271
1271
  declare const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
1272
1272
  declare const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
1273
1273
  declare const ANALYST_BENCHMARK_IMPLEMENTATION_FILES: readonly string[];
1274
- declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "d099d13e08710074eeced469aea8220ef50acf41738372a5c17cb26155628cf7";
1274
+ declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "fffa485899aa8f8e95213f56fb2aaefd2a244874165cee4e7dc09b81b872b94e";
1275
1275
  declare function analystBenchmarkImplementationDigest(): string;
1276
1276
  declare function analystBenchmarkDependencyLockDigest(): string;
1277
1277
  //#endregion
@@ -7,7 +7,7 @@ import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-D5byiHn9.js";
7
7
  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-Ct3QU7t5.js";
8
8
  import { t as createChatClient } from "../chat-client-Db4bqYfA.js";
9
9
  import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-C4wk_Sjr.js";
10
- 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-9S20PRel.js";
10
+ 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-k-fOGzt8.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";
@@ -1412,7 +1412,7 @@ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
1412
1412
  "package.json",
1413
1413
  "pnpm-lock.yaml"
1414
1414
  ]);
1415
- const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "8e4b431bbba1d1d485847fd21acea07ce78bde91f43b9f64750046d70b7373b1";
1415
+ const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "e859e07e195eb64386e00c81b67a49cc627a5d138ed90a1fac537aa956085b17";
1416
1416
  const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
1417
1417
  const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
1418
1418
  const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
@@ -1525,7 +1525,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
1525
1525
  "src/trace/raw-provider-sink.ts",
1526
1526
  "src/verdict-cache.ts"
1527
1527
  ]);
1528
- const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "d099d13e08710074eeced469aea8220ef50acf41738372a5c17cb26155628cf7";
1528
+ const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "fffa485899aa8f8e95213f56fb2aaefd2a244874165cee4e7dc09b81b872b94e";
1529
1529
  function analystBenchmarkImplementationDigest() {
1530
1530
  return ANALYST_BENCHMARK_IMPLEMENTATION_SHA256;
1531
1531
  }
@@ -6351,4 +6351,4 @@ function shellQuote(value) {
6351
6351
  //#endregion
6352
6352
  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 };
6353
6353
 
6354
- //# sourceMappingURL=benchmark-command-9S20PRel.js.map
6354
+ //# sourceMappingURL=benchmark-command-k-fOGzt8.js.map