@tangle-network/agent-eval 0.126.4 → 0.126.6

package/dist/{chunk-P6WN2KF5.js → chunk-E3IADPLG.js}

@@ -7,7 +7,7 @@ import {
   pairHoldout,
   recoverTruncatedJson,
   surfaceContentHash
-} from "./chunk-3I74FLK6.js";
+} from "./chunk-BTACVO2W.js";
 import {
   SearchLedgerConflictError,
   SearchLedgerError,
@@ -4634,4 +4634,4 @@ export {
   verifyCodeSurface,
   resolveWorktreePath
 };
-//# sourceMappingURL=chunk-P6WN2KF5.js.map
+//# sourceMappingURL=chunk-E3IADPLG.js.map

package/dist/contract/index.d.ts

@@ -1911,6 +1911,8 @@ interface OptimizationMethodProvenance {
     modules?: OptimizationModuleSource[];
     /** Python implementation used by the bridge process. */
     python?: OptimizationPythonRuntime;
+    /** Exact model identifier configured for optimizer-owned model calls. */
+    optimizerModel?: string;
     runId: string;
     /** Content identity shared by compatible resumptions. */
     compatibleRunId?: string;

package/dist/contract/index.js

@@ -40,7 +40,7 @@ import {
   skillOptOptimizationMethod,
   surfaceContentHash,
   surfaceHash
-} from "../chunk-3I74FLK6.js";
+} from "../chunk-BTACVO2W.js";
 import {
   campaignSplitDigest,
   createRunCostLedger,

package/dist/index.js

@@ -87,7 +87,7 @@ import {
   pairArms,
   parseCorrectnessResponse,
   verifyCompletion
-} from "./chunk-P6WN2KF5.js";
+} from "./chunk-E3IADPLG.js";
 import {
   DEFAULT_MUTATION_PRIMITIVES,
   DEFAULT_RED_TEAM_CORPUS,
@@ -121,7 +121,7 @@ import {
   scoreRedTeamOutput,
   surfaceContentHash,
   toolNamesForRun
-} from "./chunk-3I74FLK6.js";
+} from "./chunk-BTACVO2W.js";
 import {
   BackendIntegrityError,
   assertRealAgentReceipts,

package/dist/openapi.json

@@ -2,7 +2,7 @@
   "openapi": "3.1.0",
   "info": {
     "title": "@tangle-network/agent-eval — wire protocol",
-    "version": "0.126.4",
+    "version": "0.126.6",
     "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

@@ -199,20 +199,25 @@ The runnable version is in [`examples/compare-optimization-methods`](../examples
 
 ## Install Official GEPA
 
-Install the bridge and the source revision tested by this release:
+Install the bridge and the published GEPA package for the standard engine:
 
 ```sh
 python -m pip install agent-eval-rpc
-python -m pip install "gepa[full] @ git+https://github.com/gepa-ai/gepa.git@f919db0a622e2e9f9204779b81fe00cc1b2d808f"
+python -m pip install "gepa[full]==0.1.4"
 ```
 
-The published `gepa==0.1.4` wheel does not contain the required Optimize Anything API.
-The Agent Eval Python package cannot declare a Git dependency in its PyPI metadata, so the GEPA source install is separate.
+Use the tested official source revision for composed recipes and the source-only engines:
+
+```sh
+python -m pip install \
+  "gepa[full] @ git+https://github.com/gepa-ai/gepa.git@f919db0a622e2e9f9204779b81fe00cc1b2d808f"
+```
 
 From this repository:
 
 ```sh
 cd clients/python
+uv sync --frozen --group gepa-release
 uv sync --frozen --group gepa-source
 ```
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.126.4",
+  "version": "0.126.6",
   "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": {
@@ -177,7 +177,8 @@
     "openapi3-ts": "^4.5.0",
     "tsup": "^8.0.0",
     "typescript": "^5.7.0",
-    "vitest": "^3.0.0"
+    "vitest": "^3.0.0",
+    "yaml": "2.9.0"
   },
   "pnpm": {
     "minimumReleaseAge": 4320,