feat(gepa): upgrade engine to 0.1.4

Amp-Thread-ID: https://ampcode.com/threads/T-019ffe40-c240-70bb-8cb2-db33146ed8e6
Co-authored-by: Isaac Miller <isaac@cmpnd.ai>

Author: ampagent

dspy/teleprompt/gepa/gepa.py

@@ -324,6 +324,12 @@ def metric(
               MLflow can be used alongside Weights & Biases (WandB).
             - mlflow_tracking_uri: The tracking URI to use for MLflow (when use_mlflow=True).
             - mlflow_experiment_name: The experiment name to use for MLflow (when use_mlflow=True).
+            - sampling_strategy, selection_strategy, acceptance_criterion: GEPA 0.1.4 proposal controls.
+              DSPy supports these using GEPA's sequential candidate-evaluation fallback.
+            - wandb_attach_existing, mlflow_attach_existing, tracking_key_prefix: GEPA 0.1.4 tracking controls.
+
+            `max_reflection_cost` is not supported yet because DSPy LMs do not expose the cumulative cost
+            interface GEPA requires. Passing it raises an error instead of silently ignoring the budget.
 
             Note: Parameters already handled by DSPy's GEPA class will be overridden by the direct parameters
             and should not be passed through gepa_kwargs.
@@ -451,6 +457,9 @@ def __init__(
         self.component_selector = component_selector
         self.gepa_kwargs = gepa_kwargs or {}
 
+        if "max_reflection_cost" in self.gepa_kwargs:
+            raise ValueError("max_reflection_cost is not supported by dspy.GEPA yet.")
+
         if "reflection_prompt_template" in self.gepa_kwargs:
             raise ValueError(
                 "reflection_prompt_template cannot be passed via gepa_kwargs when using dspy.GEPA. "

dspy/teleprompt/gepa/gepa_utils.py

@@ -268,6 +268,13 @@ def evaluate(self, batch, candidate, capture_traces=False):
             scores = [s["score"] if hasattr(s, "score") else s for s in scores]
             return EvaluationBatch(outputs=outputs, scores=scores, trajectories=None)
 
+    def get_adapter_state(self) -> dict[str, Any]:
+        return {"rng_state": self.rng.getstate()}
+
+    def set_adapter_state(self, state: dict[str, Any]) -> None:
+        if "rng_state" in state:
+            self.rng.setstate(state["rng_state"])
+
     def make_reflective_dataset(
         self, candidate, eval_batch, components_to_update
     ) -> dict[str, list[ReflectiveExample]]:
@@ -415,4 +422,3 @@ def stripped_lm_call(self, x: str) -> list[str]:
                 raise TypeError("Unexpected output type from the base LM! Expected str or dict")
 
         return outputs
-

pyproject.toml

@@ -34,7 +34,7 @@ dependencies = [
     "anyio",
     "cachetools>=5.5.0",
     "cloudpickle>=3.1.2",
-    "gepa[dspy]==0.1.1",
+    "gepa[dspy]==0.1.4",
 ]
 
 [project.optional-dependencies]

tests/teleprompt/test_gepa.py

@@ -1,4 +1,5 @@
 import json
+import random
 import threading
 from typing import Any
 from unittest import mock
@@ -632,3 +633,24 @@ def test_track_best_outputs_result_structure():
         assert isinstance(entries, list)
         for cand_idx, output in entries:
             assert isinstance(cand_idx, int)
+
+
+def test_gepa_rejects_unsupported_reflection_cost_budget():
+    with pytest.raises(ValueError, match="max_reflection_cost"):
+        dspy.GEPA(
+            metric=simple_metric,
+            max_metric_calls=1,
+            reflection_lm=DummyLM([]),
+            gepa_kwargs={"max_reflection_cost": 1.0},
+        )
+
+
+def test_adapter_state_round_trips_rng():
+    from dspy.teleprompt.gepa.gepa_utils import DspyAdapter
+
+    adapter = DspyAdapter(SimpleModule("input -> output"), simple_metric, {}, rng=random.Random(42))
+    state = adapter.get_adapter_state()
+    expected = adapter.rng.random()
+    adapter.rng.random()
+    adapter.set_adapter_state(state)
+    assert adapter.rng.random() == expected