gartoid/Prompt-optimizer
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: v0.2.0 sprint — ground truth eval, crossover/mutation, checkpointing, similarity guards, dataset loader, CLI commands, extended test coverage

Browse Source 
Aggregates all v0.2.0 sprint work (GARAA-30 through GARAA-40) and fixes
2 integration tests that broke when the codebase went async (DSPyLLMAdapter
and full pipeline tests now properly await coroutines).

277 tests pass (260 unit + 17 integration).

Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
FullStackDev
2026-03-29 19:13:50 +00:00
parent b9745566c8
commit a5bf2ad59c
43 changed files with 5007 additions and 358 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
tests/integration/test_full_pipeline.py
View File

@@ -1,7 +1,9 @@
"""End-to-end pipeline test with mocked LLM calls."""
from __future__ import annotations
from unittest.mock import MagicMock
from unittest.mock import AsyncMock, MagicMock
import pytest
from prometheus.application.bootstrap import SyntheticBootstrap
from prometheus.application.dto import OptimizationConfig
@@ -23,9 +25,10 @@ def _make_eval(scores: list[float]) -> EvalResult:
class TestFullPipeline:
def test_pipeline_produces_result(self) -> None:
@pytest.mark.asyncio
async def test_pipeline_produces_result(self) -> None:
"""Full pipeline with mocked ports produces an OptimizationResult."""
mock_llm = MagicMock(spec=LLMPort)
mock_llm = AsyncMock(spec=LLMPort)
mock_llm.execute.return_value = "mock response"
mock_judge = MagicMock(spec=JudgePort)
@@ -38,11 +41,11 @@ class TestFullPipeline:
eval_sequence.append(_make_eval([0.6, 0.6, 0.6, 0.6, 0.6])) # new eval (accepted)
mock_judge.judge_batch.return_value = [(0.5, "ok")] * 5
mock_proposer = MagicMock(spec=ProposerPort)
mock_proposer = AsyncMock(spec=ProposerPort)
mock_proposer.propose.return_value = Prompt(text="Improved prompt")
evaluator = PromptEvaluator(mock_llm, mock_judge)
evaluator.evaluate = MagicMock(side_effect=eval_sequence)
evaluator.evaluate = AsyncMock(side_effect=eval_sequence)
mock_gen = MagicMock()
mock_gen.generate_inputs.return_value = [
@@ -65,7 +68,7 @@ class TestFullPipeline:
seed=42,
)
result = use_case.execute(config)
result = await use_case.execute(config)
assert result.initial_prompt == "Answer questions."
assert result.optimized_prompt == "Improved prompt"