@tangle-network/agent-eval 0.126.4 → 0.126.6

package/CHANGELOG.md

@@ -4,6 +4,19 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [0.126.6] - 2026-07-24 - optimizer model provenance
+
+### Added
+
+- Proxied GEPA and SkillOpt runs now record the configured optimizer model in `OptimizationMethodProvenance.optimizerModel`; GEPA engines without a configured optimizer omit it.
+
+## [0.126.5] - 2026-07-24 - published GEPA compatibility
+
+### Fixed
+
+- The standard GEPA engine now runs against the published `gepa[full]==0.1.4` package instead of requiring an unreleased source API.
+- GEPA source-only engines and composition functions still fail explicitly unless the documented official source revision is installed.
+
 ## [0.126.4] - 2026-07-24 - train-only GEPA optimization
 
 ### Fixed

package/README.md

@@ -33,16 +33,21 @@ python -m pip install agent-eval-rpc
 python -m pip install \
   "skillopt @ git+https://github.com/microsoft/SkillOpt.git@61735e3922efc2b90c6d6cab561e62e98452ca90"
 
-# GEPA Optimize Anything at the source revision tested by this release
+# Standard GEPA engine from the published package
 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"
+
+# GEPA Omni and source-only engines
+python -m pip install \
+  "gepa[full] @ git+https://github.com/gepa-ai/gepa.git@f919db0a622e2e9f9204779b81fe00cc1b2d808f"
 
 # DSPy 3.2.1 with Agent Eval metrics
 python -m pip install "agent-eval-rpc[dspy]"
 ```
 
-The published `gepa==0.1.4` wheel does not contain the Optimize Anything API used here.
-The Git revision is intentional and should move only after compatibility tests pass.
+The published GEPA package supports the standard `gepa` engine.
+Sequential, adaptive, best-of, vote, Omni, AutoResearch, Meta Harness, and Best-of-N currently require the tested official source revision.
+Move that revision only after both release and source compatibility tests pass.
 The published `skillopt==0.2.0` wheel omits the prompt files required by `ReflACTTrainer`, so the tested SkillOpt source revision is also intentional.
 DSPy 3.2.1 requires GEPA 0.0.27, while the general bridge requires GEPA 0.1.4.
 Install the DSPy adapter and the general GEPA bridge in separate Python environments.
@@ -278,7 +283,7 @@ console.table(result.scores)
 Read `scores` for final-case lift and intervals.
 Read `pairwise` before claiming one method beat another.
 Read `totalCost.accountingComplete` before using the reported dollars as a complete total.
-Each official method score records the 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 in `provenance`.
+Each official method score records the optimizer and bridge package versions, source revisions and source-tree hashes, Python runtime, configured optimizer model when present, custom engine module hashes, compatible run ID, exact attempt ID, resume status, evaluation count, artifact directory, and available optimizer token usage in `provenance`.
 
 The [optimizer guide](./docs/campaign-proposers.md) covers recipes, budgets, resuming, and data separation.
 The [runnable comparison](./examples/compare-optimization-methods/) can run GEPA, SkillOpt, or both.
@@ -373,6 +378,11 @@ Python compatibility tests use the locked dependencies:
 
 ```sh
 cd clients/python
+uv sync --frozen --extra dev --group gepa-release
+AGENT_EVAL_EXPECT_GEPA_RELEASE=1 \
+  uv run --frozen --extra dev --group gepa-release \
+  pytest tests/test_gepa_release_compatibility.py tests/test_gepa_bridge.py
+
 uv sync --frozen --extra dev --group skillopt-source --group gepa-source
 uv run --frozen pytest
 

package/dist/benchmarks/index.js

@@ -17,8 +17,8 @@ import {
   runBenchmarkAdapter,
   summarizeBenchmarkCampaign
 } from "../chunk-CGG5SLH3.js";
-import "../chunk-P6WN2KF5.js";
-import "../chunk-3I74FLK6.js";
+import "../chunk-E3IADPLG.js";
+import "../chunk-BTACVO2W.js";
 import "../chunk-ZVCHKKOP.js";
 import "../chunk-WGXIEX7P.js";
 import "../chunk-ARU2PZFM.js";

package/dist/campaign/index.d.ts

@@ -2556,6 +2556,8 @@ 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/campaign/index.js

@@ -32,7 +32,7 @@ import {
   userStoryScoreboard,
   validateSearchLedgerEvent,
   verifyCodeSurface
-} from "../chunk-P6WN2KF5.js";
+} from "../chunk-E3IADPLG.js";
 import {
   acquireSingleRunLock,
   assertCodeSurfaceIdentity,
@@ -79,7 +79,7 @@ import {
   surfaceContentHash,
   surfaceHash,
   verifyLoopProvenanceRecord
-} from "../chunk-3I74FLK6.js";
+} from "../chunk-BTACVO2W.js";
 import {
   SearchLedgerConflictError,
   SearchLedgerError,

package/dist/{chunk-3I74FLK6.js → chunk-BTACVO2W.js}

@@ -1991,6 +1991,9 @@ function assertOptimizationProvenance(methodName, value) {
     if (entry !== void 0 && (typeof entry !== "string" || !entry.trim())) fail(`source.${field}`);
   }
   if (typeof value.runId !== "string" || !value.runId.trim()) fail("runId");
+  if (value.optimizerModel !== void 0 && (typeof value.optimizerModel !== "string" || !value.optimizerModel.trim() || value.optimizerModel.trim() !== value.optimizerModel)) {
+    fail("optimizerModel");
+  }
   if (typeof value.resumed !== "boolean") fail("resumed");
   if (!Number.isSafeInteger(value.evaluationCount) || value.evaluationCount < 0) {
     fail("evaluationCount");
@@ -5718,6 +5721,7 @@ function gepaOptimizationMethod(config) {
         durationMs: Date.now() - started,
         provenance: {
           ...runtime,
+          ...config.optimizer ? { optimizerModel: config.optimizer.model } : {},
           compatibleRunId,
           runId,
           resumed: result.resumed,
@@ -7251,6 +7255,7 @@ function skillOptOptimizationMethod(config) {
         durationMs: Date.now() - started,
         provenance: {
           ...runtime,
+          optimizerModel: config.optimizer.model,
           compatibleRunId,
           runId,
           resumed: result.resumed,
@@ -7341,4 +7346,4 @@ export {
   emitLoopProvenance,
   skillOptOptimizationMethod
 };
-//# sourceMappingURL=chunk-3I74FLK6.js.map
+//# sourceMappingURL=chunk-BTACVO2W.js.map