Initial commit: PROMETHEUS v0.1.0 - Prompt optimizer

- Clean architecture (domain/application/infrastructure)
- DSPy-based evolution engine with scoring
- CLI via pyproject.toml entry point
- Unit + integration tests (~300 tests)
- Configs for glm-5.1 and glm-4.5-air models
- Z.AI endpoint integration

tests/unit/test_evolution.py

@@ -0,0 +1,147 @@
+"""Unit tests for the evolution loop — with full mocking."""
+from __future__ import annotations
+
+from unittest.mock import MagicMock, patch
+
+from prometheus.application.bootstrap import SyntheticBootstrap
+from prometheus.application.evaluator import PromptEvaluator
+from prometheus.application.evolution import EvolutionLoop
+from prometheus.domain.entities import EvalResult, Prompt, SyntheticExample, Trajectory
+
+
+class TestEvolutionLoop:
+    def test_accepts_improvement(
+        self,
+        seed_prompt: Prompt,
+        synthetic_pool: list[SyntheticExample],
+        task_description: str,
+        mock_llm_port: MagicMock,
+        mock_judge_port: MagicMock,
+        mock_proposer_port: MagicMock,
+    ) -> None:
+        """When the new prompt improves the score, the best candidate is updated."""
+        evaluator = PromptEvaluator(mock_llm_port, mock_judge_port)
+        bootstrap = MagicMock(spec=SyntheticBootstrap)
+        bootstrap.sample_minibatch.return_value = synthetic_pool[:5]
+
+        initial_eval = EvalResult(
+            scores=[0.3, 0.4, 0.3, 0.5, 0.2],
+            feedbacks=["bad"] * 5,
+            trajectories=[
+                Trajectory(f"input{i}", f"output{i}", s, "bad", "prompt")
+                for i, s in enumerate([0.3, 0.4, 0.3, 0.5, 0.2])
+            ],
+        )
+        old_eval = EvalResult(
+            scores=[0.3, 0.4, 0.3, 0.5, 0.2],
+            feedbacks=["bad"] * 5,
+            trajectories=[
+                Trajectory(f"input{i}", f"output{i}", s, "bad", "prompt")
+                for i, s in enumerate([0.3, 0.4, 0.3, 0.5, 0.2])
+            ],
+        )
+        new_eval = EvalResult(
+            scores=[0.8, 0.9, 0.7, 0.8, 0.9],
+            feedbacks=["good"] * 5,
+            trajectories=[],
+        )
+        evaluator.evaluate = MagicMock(side_effect=[initial_eval, old_eval, new_eval])
+
+        loop = EvolutionLoop(
+            evaluator=evaluator,
+            proposer=mock_proposer_port,
+            bootstrap=bootstrap,
+            max_iterations=1,
+            minibatch_size=5,
+        )
+        with patch.object(loop, "_log"):
+            state = loop.run(seed_prompt, synthetic_pool, task_description)
+
+        assert state.best_candidate is not None
+        assert state.best_candidate.best_score > 0
+
+    def test_rejects_regression(
+        self,
+        seed_prompt: Prompt,
+        synthetic_pool: list[SyntheticExample],
+        task_description: str,
+        mock_llm_port: MagicMock,
+        mock_judge_port: MagicMock,
+        mock_proposer_port: MagicMock,
+    ) -> None:
+        """When the new prompt degrades the score, the best candidate stays unchanged."""
+        evaluator = PromptEvaluator(mock_llm_port, mock_judge_port)
+        bootstrap = MagicMock(spec=SyntheticBootstrap)
+        bootstrap.sample_minibatch.return_value = synthetic_pool[:5]
+
+        initial_eval = EvalResult(
+            scores=[0.7, 0.8, 0.7, 0.8, 0.9],
+            feedbacks=["ok"] * 5,
+            trajectories=[
+                Trajectory(f"input{i}", f"output{i}", s, "ok", "prompt")
+                for i, s in enumerate([0.7, 0.8, 0.7, 0.8, 0.9])
+            ],
+        )
+        old_eval = EvalResult(
+            scores=[0.7, 0.8, 0.7, 0.8, 0.9],
+            feedbacks=["ok"] * 5,
+            trajectories=[
+                Trajectory(f"input{i}", f"output{i}", s, "ok", "prompt")
+                for i, s in enumerate([0.7, 0.8, 0.7, 0.8, 0.9])
+            ],
+        )
+        new_eval = EvalResult(
+            scores=[0.2, 0.1, 0.3, 0.2, 0.1],
+            feedbacks=["bad"] * 5,
+            trajectories=[],
+        )
+        evaluator.evaluate = MagicMock(side_effect=[initial_eval, old_eval, new_eval])
+
+        loop = EvolutionLoop(
+            evaluator=evaluator,
+            proposer=mock_proposer_port,
+            bootstrap=bootstrap,
+            max_iterations=1,
+            minibatch_size=5,
+        )
+        with patch.object(loop, "_log"):
+            state = loop.run(seed_prompt, synthetic_pool, task_description)
+
+        assert state.best_candidate is not None
+        assert state.best_candidate.prompt.text == seed_prompt.text
+
+    def test_skips_perfect_scores(
+        self,
+        seed_prompt: Prompt,
+        synthetic_pool: list[SyntheticExample],
+        task_description: str,
+        mock_llm_port: MagicMock,
+        mock_judge_port: MagicMock,
+        mock_proposer_port: MagicMock,
+    ) -> None:
+        """When all scores are perfect, no proposition is made."""
+        evaluator = PromptEvaluator(mock_llm_port, mock_judge_port)
+        bootstrap = MagicMock(spec=SyntheticBootstrap)
+        bootstrap.sample_minibatch.return_value = synthetic_pool[:5]
+
+        perfect_eval = EvalResult(
+            scores=[1.0, 1.0, 1.0, 1.0, 1.0],
+            feedbacks=["perfect"] * 5,
+            trajectories=[
+                Trajectory(f"input{i}", f"output{i}", 1.0, "perfect", "prompt")
+                for i in range(5)
+            ],
+        )
+        evaluator.evaluate = MagicMock(return_value=perfect_eval)
+
+        loop = EvolutionLoop(
+            evaluator=evaluator,
+            proposer=mock_proposer_port,
+            bootstrap=bootstrap,
+            max_iterations=3,
+            minibatch_size=5,
+        )
+        with patch.object(loop, "_log"):
+            loop.run(seed_prompt, synthetic_pool, task_description)
+
+        mock_proposer_port.propose.assert_not_called()