@tangle-network/agent-eval 0.126.3 → 0.126.5

package/CHANGELOG.md

@@ -4,6 +4,19 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [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
+
+- Official GEPA optimization accepts an empty selection set, reuses the non-empty training set for candidate comparison, and labels that comparison as a training-set fallback.
+
 ## [0.126.3] - 2026-07-24 - execution-bound optimizer resume
 
 ### Added

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.
@@ -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/openapi.json

@@ -2,7 +2,7 @@
   "openapi": "3.1.0",
   "info": {
     "title": "@tangle-network/agent-eval — wire protocol",
-    "version": "0.126.3",
+    "version": "0.126.5",
     "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": "0.126.3",
+  "version": "0.126.5",
   "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,