110 lines
3.8 KiB
Python
110 lines
3.8 KiB
Python
"""Shared pytest fixtures for backend tests.
|
|
|
|
All external LLM/ASR calls must be mocked. Use tmp_path for ChromaDB instances.
|
|
"""
|
|
import pytest
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_llm_client(monkeypatch):
|
|
"""Mock LLM client to avoid hitting live APIs."""
|
|
class _Mock:
|
|
async def complete(self, prompt: str, temperature: float = 0.7) -> str: # type: ignore
|
|
return "{\"choices\": [{\"message\": {\"content\": \"mock response\"}}]}"
|
|
|
|
return _Mock()
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_asr_client(monkeypatch):
|
|
"""Mock ASR client to avoid hitting live APIs."""
|
|
class _Mock:
|
|
async def transcribe(self, audio_bytes): # type: ignore
|
|
return ""
|
|
|
|
return _Mock()
|
|
|
|
|
|
@pytest.fixture
|
|
def chroma_test_dir(tmp_path):
|
|
"""Provide a temporary directory for isolated ChromaDB instances."""
|
|
return tmp_path / "chroma_test"
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_prompt_service():
|
|
"""Mock PromptService for tests that don't need real DB.
|
|
|
|
Returns seed templates matching the built-in defaults so tests
|
|
that verify prompt content pass without a real prompts.db.
|
|
"""
|
|
_SEEDS = {
|
|
"decompose": (
|
|
"Given this question: '{question}'\n\n"
|
|
"Break it down into 2-5 simplified sub-questions that would help "
|
|
"search for relevant information. Each sub-question should be short "
|
|
"and focused on one aspect. Return as a JSON array of strings."
|
|
),
|
|
"filter": (
|
|
"Given question '{question}' and these document chunks, rate each 0-10 for relevance. "
|
|
"Return JSON array of scores.\n{chunks}\n"
|
|
),
|
|
"generate": (
|
|
"Question: {question}\n\n"
|
|
"Answer the question using ONLY these document chunks. "
|
|
"Do not use any external knowledge. "
|
|
"Format your answer as bullet points. "
|
|
"Cite your sources inline using the exact bracket labels provided, "
|
|
"e.g. [filename, page N]. Place the citation at the end of each relevant point.\n\n"
|
|
"Document chunks:\n{context}\n\n"
|
|
"Answer:"
|
|
),
|
|
"generate_per_subq": (
|
|
"Answer each sub-question using ONLY its document chunks.\n"
|
|
"Format as markdown sections with ## Sub-question N: headers.\n"
|
|
"{context_sections}\n\n"
|
|
"Answer:"
|
|
),
|
|
"filter_intro": "Evaluate each chunk for relevance to its associated sub-question only.",
|
|
"filter_section": (
|
|
'\nSub-question {subq_idx}: "{subq_question}"\n{chunks}'
|
|
),
|
|
"filter_outro": (
|
|
"\nFor each chunk, rate its relevance 0-10 considering ONLY its associated sub-question.\n"
|
|
'Return a JSON object mapping sub-question indices to arrays of scores.\n'
|
|
'Example: {"0": [8.5, 3.2, 9.0], "1": [7.0, 9.1]}'
|
|
),
|
|
}
|
|
|
|
class _MockPromptService:
|
|
def get_active_profile_name(self) -> str:
|
|
return "A"
|
|
|
|
def get_prompt_template(self, step: str) -> str:
|
|
return _SEEDS.get(step, "Template for {question}")
|
|
|
|
def list_profiles(self) -> list[dict]:
|
|
return [
|
|
{"name": "A", "is_active": True},
|
|
{"name": "B", "is_active": False},
|
|
{"name": "C", "is_active": False},
|
|
]
|
|
|
|
def activate_profile(self, name: str) -> None:
|
|
pass
|
|
|
|
def get_profile_prompts(self, name: str) -> dict:
|
|
return {k: v for k, v in _SEEDS.items()}
|
|
|
|
def update_prompt(self, name: str, step: str, template: str) -> None:
|
|
pass
|
|
|
|
def update_all_prompts(self, name: str, prompts: dict[str, str]) -> None:
|
|
pass
|
|
|
|
def reset_to_defaults(self, name: str, step: str | None = None) -> None:
|
|
pass
|
|
|
|
return _MockPromptService()
|