@tangle-network/agent-eval 0.126.0 → 0.126.2

package/dist/index.js

@@ -87,7 +87,7 @@ import {
   pairArms,
   parseCorrectnessResponse,
   verifyCompletion
-} from "./chunk-KO2PZOGP.js";
+} from "./chunk-Y5CLI4PY.js";
 import {
   DEFAULT_MUTATION_PRIMITIVES,
   DEFAULT_RED_TEAM_CORPUS,
@@ -121,7 +121,7 @@ import {
   scoreRedTeamOutput,
   surfaceContentHash,
   toolNamesForRun
-} from "./chunk-NTOV7RU5.js";
+} from "./chunk-7AN2E7BU.js";
 import {
   BackendIntegrityError,
   assertRealAgentReceipts,
@@ -146,7 +146,7 @@ import {
   defaultIsMaterial,
   diffFindings,
   runSemanticConceptJudge
-} from "./chunk-4B7ZZHPX.js";
+} from "./chunk-KE2VWPZX.js";
 import {
   AnalystRegistry,
   DEFAULT_TRACE_ANALYST_KINDS,
@@ -163,7 +163,7 @@ import {
   makeFinding,
   renderPriorFindings,
   renderUpstreamFindings
-} from "./chunk-CM4OILD2.js";
+} from "./chunk-LUNF2SEL.js";
 import "./chunk-HHWE3POT.js";
 import {
   DEFAULT_RUN_SCORE_WEIGHTS,
@@ -171,7 +171,7 @@ import {
   aggregateRunScore,
   clamp01,
   mapConcurrent
-} from "./chunk-UI4YMIN2.js";
+} from "./chunk-WGXIEX7P.js";
 import {
   allCriticalPassed,
   controlFailureClassFromVerification,

package/dist/openapi.json

@@ -2,7 +2,7 @@
   "openapi": "3.1.0",
   "info": {
     "title": "@tangle-network/agent-eval — wire protocol",
-    "version": "0.126.0",
+    "version": "0.126.2",
     "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/docs/campaign-proposers.md

@@ -183,13 +183,13 @@ const comparison = await compareOptimizationMethods({
   runDir: '.agent-eval/optimizer-comparison',
   optimizationRunOptions: {
     maxConcurrency: 4,
-    costCeiling: 10,
   },
-  costCeiling: 3,
+  costCeiling: 23,
   confidence: 0.95,
 })
 ```
 
+`costCeiling` is one limit shared by optimizer-model calls, train and selection evaluations, and final test scoring.
 `comparison.scores` contains the final-case baseline score, selected score, lift, simultaneous interval, cost status, duration, and selected surface for each method.
 Official method scores contain optimizer and bridge package versions, source revisions and source-tree hashes, Python runtime, custom engine module hashes, compatible run ID, exact attempt ID, resume status, evaluation count, artifact directory, and available optimizer token usage.
 `comparison.pairwise` compares the highest-ranked method with every other method.
@@ -203,7 +203,7 @@ Install the bridge and the source revision tested by this release:
 
 ```sh
 python -m pip install agent-eval-rpc
-python -m pip install "gepa @ git+https://github.com/gepa-ai/gepa.git@f919db0a622e2e9f9204779b81fe00cc1b2d808f"
+python -m pip install "gepa[full] @ git+https://github.com/gepa-ai/gepa.git@f919db0a622e2e9f9204779b81fe00cc1b2d808f"
 ```
 
 The published `gepa==0.1.4` wheel does not contain the required Optimize Anything API.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.126.0",
+  "version": "0.126.2",
   "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": {