@tangle-network/agent-eval 0.103.0 → 0.103.2

package/dist/index.js

@@ -9,7 +9,7 @@ import {
   checkBehavioralCanary,
   checkCanaries,
   runBehavioralCanaries
-} from "./chunk-U3IDYATS.js";
+} from "./chunk-GDZAWO2I.js";
 import {
   classifyEuAiRisk,
   euAiActReport,
@@ -49,7 +49,7 @@ import {
   validateProductBenchmarkManifest,
   validateProductBenchmarkRecord,
   validateProductBenchmarkRun
-} from "./chunk-RQNOLV3I.js";
+} from "./chunk-FOUG2VVS.js";
 import {
   CODING_HARNESSES,
   HARNESS_NATIVE_MODEL,
@@ -72,7 +72,7 @@ import {
   llmJudge,
   parseCorrectnessResponse,
   verifyCompletion
-} from "./chunk-IXOV77YF.js";
+} from "./chunk-BBQILVBH.js";
 import {
   DEFAULT_MUTATION_PRIMITIVES,
   DEFAULT_RED_TEAM_CORPUS,
@@ -96,7 +96,7 @@ import {
   scoreRedTeamOutput,
   surfaceContentHash,
   toolNamesForRun
-} from "./chunk-NTVWIH24.js";
+} from "./chunk-ZKIL3VOD.js";
 import {
   BackendIntegrityError,
   assertRealBackend,
@@ -106,7 +106,7 @@ import {
   fileVerdictCache,
   inMemoryVerdictCache,
   summarizeBackendIntegrity
-} from "./chunk-XKA6ZGEY.js";
+} from "./chunk-3PFZBGMR.js";
 import {
   MODEL_PRICING,
   MetricsCollector,
@@ -128,7 +128,7 @@ import {
   computeToolUseMetrics,
   iqr,
   welchsTTest
-} from "./chunk-IH7LYRHL.js";
+} from "./chunk-DBDRR6GF.js";
 import {
   analyzeSeries
 } from "./chunk-BOD4O7OF.js";
@@ -145,7 +145,7 @@ import {
   pytestTestParser,
   runTestGradedScenario,
   vitestTestParser
-} from "./chunk-ZOPLCJSY.js";
+} from "./chunk-HZHNRYHK.js";
 import {
   DEFAULT_COMPLEXITY_WEIGHTS,
   FindingsStore,
@@ -159,7 +159,7 @@ import {
   defaultIsMaterial,
   diffFindings,
   runSemanticConceptJudge
-} from "./chunk-JU6ZX3CX.js";
+} from "./chunk-5PK3626Q.js";
 import {
   LockedJsonlAppender,
   Mutex
@@ -167,7 +167,7 @@ import {
 import {
   buildDefaultAnalystRegistry,
   computeTraceMetrics
-} from "./chunk-L5TVEZFT.js";
+} from "./chunk-QRVS7MX4.js";
 import {
   DEFAULT_RUN_SCORE_WEIGHTS,
   POLICY_EDIT_AXES,
@@ -184,7 +184,7 @@ import {
   policyEditsFromFindings,
   scorePolicyEditReadiness,
   validatePolicyEdit
-} from "./chunk-IN3SHQML.js";
+} from "./chunk-LOJ2QVCE.js";
 import {
   AnalystRegistry,
   DEFAULT_TRACE_ANALYST_KINDS,
@@ -194,7 +194,7 @@ import {
   KNOWLEDGE_POISONING_KIND_SPEC,
   createTraceAnalystKind,
   renderPriorFindings
-} from "./chunk-FRI6RG3P.js";
+} from "./chunk-2OGPXHOB.js";
 import {
   controlFailureClassFromVerification,
   controlRunToRunRecord,
@@ -205,7 +205,7 @@ import {
   runProposeReview,
   runProposeReviewAsControlLoop,
   scoreFromEvals
-} from "./chunk-B2TMQM62.js";
+} from "./chunk-K7QEIHHJ.js";
 import {
   allCriticalPassed,
   errorStreakDetector,
@@ -224,10 +224,10 @@ import {
   evaluateReleaseConfidence,
   judgeReplayGate,
   renderReleaseReport
-} from "./chunk-VDGPPGE3.js";
+} from "./chunk-6HFYGEZ3.js";
 import {
   runEvalCampaign
-} from "./chunk-6FIAJHCU.js";
+} from "./chunk-LIEJUH2I.js";
 import {
   LlmCallError,
   LlmClient,
@@ -239,7 +239,7 @@ import {
   isTransientLlmError,
   probeLlm,
   stripFencedJson
-} from "./chunk-CWNP4DV4.js";
+} from "./chunk-FUCQVFMU.js";
 import {
   evaluateInterimReleaseConfidence,
   pairedEvalueSequence
@@ -250,11 +250,11 @@ import {
   paretoChart,
   researchReport,
   summaryTable
-} from "./chunk-6GT4NI4V.js";
+} from "./chunk-6MFFKPZ4.js";
 import {
   attributeCounterfactuals,
   runCounterfactual
-} from "./chunk-REVYNR6C.js";
+} from "./chunk-6SK5VFYK.js";
 import {
   buildTrajectory
 } from "./chunk-RZTMDUO7.js";
@@ -299,7 +299,7 @@ import {
   weightedMean,
   wilcoxonSignedRank,
   wilson
-} from "./chunk-HRGUJTER.js";
+} from "./chunk-XMSYF4A7.js";
 import {
   FileSystemTraceStore,
   InMemoryTraceStore,
@@ -330,13 +330,13 @@ import {
   scoreTraceInsightReadiness,
   tokenizeDomainWords,
   traceAnalystOnRunComplete
-} from "./chunk-7RBJANJD.js";
+} from "./chunk-V7HNA47Z.js";
 import {
   TRACE_ANALYST_ACTOR_DESCRIPTION,
   TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION,
   TRACE_ANALYST_SUBAGENT_DESCRIPTION,
   analyzeTraces
-} from "./chunk-2MLIEQSN.js";
+} from "./chunk-RPDDVKI7.js";
 import {
   DEFAULT_REDACTION_RULES,
   REDACTION_VERSION,
@@ -352,7 +352,7 @@ import {
   runFailureClass,
   runsForScenario,
   toolSpans
-} from "./chunk-UFSG7ACU.js";
+} from "./chunk-JZXGWLK5.js";
 import {
   FAILURE_CLASSES,
   TRACE_SCHEMA_VERSION,
@@ -395,12 +395,12 @@ import {
   stringField,
   traceAnalystFunctionGroup,
   traceSpanKindToOpenInferenceKind
-} from "./chunk-YBIGNSCZ.js";
+} from "./chunk-LNQEP766.js";
 import {
   RunIntegrityError,
   assertRunCaptured,
   throwIfRunIncomplete
-} from "./chunk-SBCB6VZY.js";
+} from "./chunk-TT4KNT67.js";
 import {
   FileSystemRawProviderSink,
   InMemoryRawProviderSink,
@@ -415,7 +415,7 @@ import {
   parseRunRecordSafe,
   roundTripRunRecord,
   validateRunRecord
-} from "./chunk-2NSLDY4B.js";
+} from "./chunk-VK6HBGAE.js";
 import {
   TraceEmitter,
   llmSpanFromProvider
@@ -433,7 +433,7 @@ import {
   toAgentProfileJson,
   validateAgentProfileCell,
   verifyAgentProfileCell
-} from "./chunk-ABOIVNXL.js";
+} from "./chunk-XJYR7XFV.js";
 import {
   canonicalize,
   evaluateHypothesis,
@@ -450,7 +450,7 @@ import {
   ReplayError,
   ValidationError,
   VerificationError
-} from "./chunk-3BFEG2F6.js";
+} from "./chunk-ONWEPEDO.js";
 import {
   __export
 } from "./chunk-PZ5AY32C.js";