"""Real-Postgres tests for finding a plan by meaning (milestone 415, step 3). A project's roadmap written as milestones was invisible to recall: `search` covered notes, tasks and rules, so "is there already a plan for this?" had no tool. What a mock cannot show is the join scoping the vectors to a project and to what the caller may read, so these seed real milestones with hand-made vectors and stub only the embedder. """ import uuid from unittest.mock import AsyncMock, patch import pytest import pytest_asyncio from scribe.models import async_session from scribe.models.embedding import EMBEDDING_DIM, MilestoneEmbedding from scribe.models.milestone import Milestone from scribe.models.project import Project from scribe.services.embeddings import CHUNKER_VERSION, semantic_search_milestones from tests.helpers import ensure_user pytestmark = [pytest.mark.integration, pytest.mark.usefixtures("_dispose_engine", "_no_embedding")] NEAR = [1.0] + [0.0] * (EMBEDDING_DIM - 1) FAR = [0.0, 1.0] + [0.0] * (EMBEDDING_DIM - 2) @pytest_asyncio.fixture async def roadmap(): tag = uuid.uuid4().hex[:8] async with async_session() as s: owner = await ensure_user(s, f"ms_search_owner_{tag}") stranger = await ensure_user(s, f"ms_search_stranger_{tag}") mine = Project(user_id=owner.id, title="Librarian") other = Project(user_id=owner.id, title="Elsewhere") s.add_all([mine, other]) await s.flush() m3 = Milestone(user_id=owner.id, project_id=mine.id, title="M3 — Metadata", description="works, editions, providers, provenance", status="active") done = Milestone(user_id=owner.id, project_id=mine.id, title="Covers", description="cover art", status="done") unrelated = Milestone(user_id=owner.id, project_id=mine.id, title="Android client", description="native app", status="active") foreign = Milestone(user_id=owner.id, project_id=other.id, title="Metadata elsewhere", description="same words, other project", status="active") s.add_all([m3, done, unrelated, foreign]) await s.flush() for ms, vec in ((m3, NEAR), (done, NEAR), (unrelated, FAR), (foreign, NEAR)): s.add(MilestoneEmbedding(milestone_id=ms.id, chunk_index=0, embedding=vec, chunk_text=ms.title, chunker_version=CHUNKER_VERSION)) ids = {"owner": owner.id, "stranger": stranger.id, "mine": mine.id, "m3": m3.id, "done": done.id, "unrelated": unrelated.id, "foreign": foreign.id} await s.commit() return ids async def _found(user_id, **kw) -> list[int]: with patch("scribe.services.embeddings.get_embedding", AsyncMock(return_value=NEAR)): hits = await semantic_search_milestones(user_id, "book metadata and providers", threshold=0.5, limit=10, **kw) return [m.id for _s, m in hits] async def test_a_plan_is_found_in_its_project_and_not_in_another(roadmap): found = await _found(roadmap["owner"], project_id=roadmap["mine"]) assert set(found) == {roadmap["m3"], roadmap["done"]} assert roadmap["foreign"] not in found and roadmap["unrelated"] not in found async def test_status_narrows_to_open_plans(roadmap): found = await _found(roadmap["owner"], project_id=roadmap["mine"], status="active") assert found == [roadmap["m3"]] async def test_without_a_project_it_searches_the_callers_own(roadmap): found = await _found(roadmap["owner"]) assert {roadmap["m3"], roadmap["done"], roadmap["foreign"]} <= set(found) async def test_a_project_the_caller_cannot_read_returns_nothing(roadmap): assert await _found(roadmap["stranger"], project_id=roadmap["mine"]) == [] assert await _found(roadmap["stranger"]) == []