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/conftest.py

@@ -0,0 +1,93 @@
+"""Shared test fixtures."""
+from __future__ import annotations
+
+from unittest.mock import MagicMock
+
+import pytest
+
+from prometheus.domain.entities import (
+    EvalResult,
+    Prompt,
+    SyntheticExample,
+    Trajectory,
+)
+
+
+@pytest.fixture
+def seed_prompt() -> Prompt:
+    return Prompt(text="You are a helpful assistant. Answer the question.")
+
+
+@pytest.fixture
+def task_description() -> str:
+    return "Answer factual questions accurately and concisely."
+
+
+@pytest.fixture
+def synthetic_pool() -> list[SyntheticExample]:
+    return [
+        SyntheticExample(input_text=f"Test input {i}", id=i) for i in range(20)
+    ]
+
+
+@pytest.fixture
+def mock_eval_result() -> EvalResult:
+    return EvalResult(
+        scores=[0.3, 0.5, 0.4, 0.6, 0.2],
+        feedbacks=[
+            "Incomplete answer",
+            "Missing key detail",
+            "Wrong format",
+            "Partially correct",
+            "Completely off topic",
+        ],
+        trajectories=[
+            Trajectory(
+                input_text=f"Input {i}",
+                output_text=f"Output {i}",
+                score=s,
+                feedback=f,
+                prompt_used="test prompt",
+            )
+            for i, (s, f) in enumerate(
+                zip(
+                    [0.3, 0.5, 0.4, 0.6, 0.2],
+                    [
+                        "Incomplete answer",
+                        "Missing key detail",
+                        "Wrong format",
+                        "Partially correct",
+                        "Completely off topic",
+                    ],
+                )
+            )
+        ],
+    )
+
+
+@pytest.fixture
+def mock_llm_port() -> MagicMock:
+    """Mock LLMPort that returns canned responses."""
+    port = MagicMock()
+    port.execute.return_value = "This is a mock response."
+    return port
+
+
+@pytest.fixture
+def mock_judge_port() -> MagicMock:
+    """Mock JudgePort that returns moderate scores."""
+    port = MagicMock()
+    port.judge_batch.return_value = [
+        (0.5, "Moderate quality, needs improvement."),
+    ] * 5
+    return port
+
+
+@pytest.fixture
+def mock_proposer_port() -> MagicMock:
+    """Mock ProposerPort that returns a slightly modified prompt."""
+    port = MagicMock()
+    port.propose.return_value = Prompt(
+        text="You are a very helpful assistant. Answer the question precisely."
+    )
+    return port