@tangle-network/agent-eval 0.122.8 → 0.122.9

package/dist/contract/index.js

@@ -36,7 +36,7 @@ import {
   runReferenceEquivalenceJudge,
   surfaceContentHash,
   surfaceHash
-} from "../chunk-S6IL3R5I.js";
+} from "../chunk-4EDDIK77.js";
 import {
   campaignSplitDigest,
   createRunCostLedger,
@@ -48,9 +48,9 @@ import {
 import {
   buildDefaultAnalystRegistry,
   createChatClient
-} from "../chunk-BVMWQDC5.js";
+} from "../chunk-VJ7T5WIO.js";
 import "../chunk-HHWE3POT.js";
-import "../chunk-MUS5DOH7.js";
+import "../chunk-FC5NDO3E.js";
 import {
   FileSystemOutcomeStore,
   InMemoryOutcomeStore
@@ -70,7 +70,7 @@ import {
 import "../chunk-PXE2VKMX.js";
 import "../chunk-ZET2UAYW.js";
 import "../chunk-GGE4NNQT.js";
-import "../chunk-PXD6ZFNY.js";
+import "../chunk-IR3KBHOY.js";
 import "../chunk-PC4UYEBM.js";
 import {
   parseRunRecordSafe

package/dist/index.js

@@ -53,7 +53,7 @@ import {
   pairArms,
   parseCorrectnessResponse,
   verifyCompletion
-} from "./chunk-ZDAKRZG5.js";
+} from "./chunk-CWF6SCBK.js";
 import {
   DEFAULT_MUTATION_PRIMITIVES,
   DEFAULT_RED_TEAM_CORPUS,
@@ -91,7 +91,7 @@ import {
   scoreRedTeamOutput,
   surfaceContentHash,
   toolNamesForRun
-} from "./chunk-S6IL3R5I.js";
+} from "./chunk-4EDDIK77.js";
 import {
   BackendIntegrityError,
   assertRealAgentReceipts,
@@ -116,12 +116,12 @@ import {
   defaultIsMaterial,
   diffFindings,
   runSemanticConceptJudge
-} from "./chunk-MI2H23RV.js";
+} from "./chunk-G2GPNLSX.js";
 import {
   buildDefaultAnalystRegistry,
   computeTraceMetrics,
   createChatClient
-} from "./chunk-BVMWQDC5.js";
+} from "./chunk-VJ7T5WIO.js";
 import "./chunk-HHWE3POT.js";
 import {
   AnalystRegistry,
@@ -156,7 +156,7 @@ import {
   scorePolicyEditReadiness,
   validatePolicyEdit,
   validatePolicyEditCandidateRecord
-} from "./chunk-MUS5DOH7.js";
+} from "./chunk-FC5NDO3E.js";
 import {
   allCriticalPassed,
   controlFailureClassFromVerification,
@@ -305,7 +305,7 @@ import {
   scoreTraceInsightReadiness,
   tokenizeDomainWords,
   traceAnalystOnRunComplete
-} from "./chunk-ULOKLHIQ.js";
+} from "./chunk-A5S77LSE.js";
 import "./chunk-H5UD2323.js";
 import {
   extractUsage,
@@ -327,7 +327,7 @@ import {
   TRACE_ANALYST_ACTOR_DESCRIPTION,
   TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION,
   analyzeTraces
-} from "./chunk-WW2A73HW.js";
+} from "./chunk-NUKSVU3W.js";
 import {
   DEFAULT_REDACTION_RULES,
   REDACTION_VERSION,
@@ -352,7 +352,7 @@ import {
   stringField,
   traceAnalystFunctionGroup,
   traceSpanKindToOpenInferenceKind
-} from "./chunk-PXD6ZFNY.js";
+} from "./chunk-IR3KBHOY.js";
 import {
   RunIntegrityError,
   assertRunCaptured,

package/dist/openapi.json

@@ -2,7 +2,7 @@
   "openapi": "3.1.0",
   "info": {
     "title": "@tangle-network/agent-eval — wire protocol",
-    "version": "0.122.8",
+    "version": "0.122.9",
     "description": "HTTP and stdio RPC interface to agent-eval. The TypeScript runtime is the source of truth; this spec is the contract that cross-language clients (Python, Rust, Go) generate from.\n\nWire-protocol version: 1.0.0. Bumps on breaking changes to request/response schemas.",
     "contact": {
       "name": "Tangle Network",

package/dist/traces.js

@@ -27,7 +27,7 @@ import {
   scoreTraceInsightReadiness,
   tokenizeDomainWords,
   traceAnalystOnRunComplete
-} from "./chunk-ULOKLHIQ.js";
+} from "./chunk-A5S77LSE.js";
 import "./chunk-H5UD2323.js";
 import {
   extractUsage,
@@ -49,7 +49,7 @@ import {
   TRACE_ANALYST_ACTOR_DESCRIPTION,
   TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION,
   analyzeTraces
-} from "./chunk-WW2A73HW.js";
+} from "./chunk-NUKSVU3W.js";
 import {
   DEFAULT_REDACTION_RULES,
   REDACTION_VERSION,
@@ -74,7 +74,7 @@ import {
   stringField,
   traceAnalystFunctionGroup,
   traceSpanKindToOpenInferenceKind
-} from "./chunk-PXD6ZFNY.js";
+} from "./chunk-IR3KBHOY.js";
 import {
   RunIntegrityError,
   assertRunCaptured,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.122.8",
+  "version": "0.122.9",
   "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
   "homepage": "https://github.com/tangle-network/agent-eval#readme",
   "repository": {