"""Unit tests for /search's core logic (app.search.run_search) -- no real DB, no real Ollama. Same mocking style as packages/kb-retrieval/tests/test_retrieval.py, extended with an `envelope` table fixture for the join app/db.py adds on top of kb_retrieval.""" from __future__ import annotations import pathlib import sys sys.path.insert(0, str(pathlib.Path(__file__).resolve().parents[1])) from fastapi.testclient import TestClient # noqa: E402 from app.main import app # noqa: E402 from app.search import run_search # noqa: E402 class _FakeConn: """summaries: [(envelope_id, dist), ...] -- cascade stage-1 pre-filter. chunks_by_envelope: envelope_id -> [(chunk_index, text, dist), ...]. envelopes: envelope_id -> {"source": ..., "entities": [...]}. summary_texts: envelope_id -> {"summary": ..., "tags": [...]} -- the document_summary row fetched for the result header (app/db.py fetch_summaries).""" def __init__( self, summaries=None, chunks_by_envelope=None, envelopes=None, summary_texts=None, mail_chunks_by_source=None, ): self._summaries = list(summaries or []) self._chunks_by_envelope = chunks_by_envelope or {} self._envelopes = envelopes or {} self._summary_texts = summary_texts or {} self._mail_chunks_by_source = mail_chunks_by_source or {} async def fetch(self, query, *params): if "FROM document_summary" in query and "= ANY" in query: (envelope_ids, _model) = params return [ {"envelope_id": eid, "summary": s["summary"], "tags": s["tags"]} for eid, s in self._summary_texts.items() if eid in envelope_ids ] if "FROM document_summary" in query: _, _model, limit = params return [{"envelope_id": eid, "dist": dist} for eid, dist in self._summaries[:limit]] if "JOIN envelope" in query: # hybrid's direct summaryless-source chunk scan _, sources, limit = params rows = [ {"envelope_id": eid, "chunk_index": idx, "text": text, "dist": dist} for source in sources for eid, idx, text, dist in self._mail_chunks_by_source.get(source, []) ] rows.sort(key=lambda r: r["dist"]) return rows[:limit] if "FROM document_chunk" in query and "= ANY" in query: _, envelope_ids, limit = params rows = [ {"envelope_id": eid, "chunk_index": idx, "text": text, "dist": dist} for eid in envelope_ids for idx, text, dist in self._chunks_by_envelope.get(eid, []) ] rows.sort(key=lambda r: r["dist"]) return rows[:limit] if "FROM document_chunk" in query: # flat path _, limit = params rows = [ {"envelope_id": eid, "chunk_index": idx, "text": text, "dist": dist} for eid, chunk_list in self._chunks_by_envelope.items() for idx, text, dist in chunk_list ] rows.sort(key=lambda r: r["dist"]) return rows[:limit] if "FROM envelope" in query: (envelope_ids,) = params return [ {"id": eid, "source": self._envelopes[eid]["source"], "entities": self._envelopes[eid]["entities"]} for eid in envelope_ids if eid in self._envelopes ] raise AssertionError(f"unexpected query: {query}") class _FakeSession: """run_search no longer talks HTTP itself -- embedding goes through the router (below), so the session is just passed through untouched.""" class _FakeRouter: """Stands in for app.embed_router.EmbedRouter: returns a fixed embedding and the name of the backend that 'served' it, mirroring EmbedRouter.embed's contract.""" def __init__(self, backend="solaria", primary_name="solaria"): self._backend = backend self.primary = type("B", (), {"name": primary_name})() self.embed_calls: list[str] = [] async def embed(self, session, text): self.embed_calls.append(text) return [0.01] * 1024, self._backend class TestRunSearchHappyPath: async def test_cascade_hit_joins_envelope_and_shapes_paperless_link(self): conn = _FakeConn( summaries=[("paperless:119", 0.1)], chunks_by_envelope={"paperless:119": [(2, "hit text", 0.34)]}, envelopes={"paperless:119": {"source": "paperless", "entities": []}}, ) session = _FakeSession() result = await run_search( conn, session, _FakeRouter(), "polisa PZU", "cascade", "claude-haiku-4-5" ) assert result["query"] == "polisa PZU" assert result["mode"] == "cascade" assert result["sol_status"] == "up" assert result["embed_backend"] == "solaria" assert len(result["results"]) == 1 hit = result["results"][0] assert hit["envelope_id"] == "paperless:119" assert hit["source"] == "paperless" assert hit["dist"] == 0.34 assert hit["chunk_index"] == 2 assert hit["text"] == "hit text" assert hit["link"] == "https://paper.kapala.org/documents/119/details" async def test_flat_mode_skips_cascade_stage1(self): conn = _FakeConn( chunks_by_envelope={"paperless:1": [(0, "a", 0.2)]}, envelopes={"paperless:1": {"source": "paperless", "entities": []}}, ) session = _FakeSession() result = await run_search( conn, session, _FakeRouter(), "q", "flat", "claude-haiku-4-5" ) assert result["mode"] == "flat" assert len(result["results"]) == 1 async def test_summary_attached_when_document_summary_row_exists(self): conn = _FakeConn( summaries=[("paperless:119", 0.1)], chunks_by_envelope={"paperless:119": [(2, "hit text", 0.34)]}, envelopes={"paperless:119": {"source": "paperless", "entities": []}}, summary_texts={"paperless:119": {"summary": "Polisa OC 2024", "tags": ["ubezpieczenia"]}}, ) session = _FakeSession() result = await run_search( conn, session, _FakeRouter(), "polisa PZU", "cascade", "claude-haiku-4-5" ) hit = result["results"][0] assert hit["summary"] == "Polisa OC 2024" assert hit["summary_tags"] == ["ubezpieczenia"] async def test_summary_defaults_to_none_when_no_document_summary_row(self): conn = _FakeConn( summaries=[("paperless:119", 0.1)], chunks_by_envelope={"paperless:119": [(2, "hit text", 0.34)]}, envelopes={"paperless:119": {"source": "paperless", "entities": []}}, ) session = _FakeSession() result = await run_search( conn, session, _FakeRouter(), "polisa PZU", "cascade", "claude-haiku-4-5" ) hit = result["results"][0] assert hit["summary"] is None assert hit["summary_tags"] == [] async def test_hybrid_mode_merges_cascade_and_mail_branches(self): conn = _FakeConn( summaries=[("paperless:1", 0.3)], chunks_by_envelope={"paperless:1": [(0, "doc text", 0.3)]}, envelopes={ "paperless:1": {"source": "paperless", "entities": []}, "": { "source": "gmail", "entities": [{"type": "headers", "from": None, "subject": "s", "date_raw": "d"}], }, }, mail_chunks_by_source={"gmail": [("", 0, "mail text", 0.2)]}, ) session = _FakeSession() result = await run_search( conn, session, _FakeRouter(), "q", "hybrid", "claude-haiku-4-5" ) assert result["mode"] == "hybrid" envelope_ids = [r["envelope_id"] for r in result["results"]] assert envelope_ids == ["", "paperless:1"] async def test_gmail_hit_carries_header_metadata_not_a_link(self): conn = _FakeConn( summaries=[("", 0.1)], chunks_by_envelope={"": [(0, "body text", 0.4)]}, envelopes={ "": { "source": "gmail", "entities": [ {"type": "headers", "from": {"name": "A", "address": "a@b.com"}, "subject": "s", "date_raw": "d"} ], } }, ) session = _FakeSession() result = await run_search( conn, session, _FakeRouter(), "q", "cascade", "claude-haiku-4-5" ) hit = result["results"][0] assert hit["source"] == "gmail" assert hit["subject"] == "s" assert hit["link"] is None assert hit["mail_ui_url"] is None class TestRunSearchEmbedBackendMarking: async def test_fallback_embed_marks_backend_piha_and_sol_status_down(self): # Task spec: the response must say WHICH backend embedded the query (quality # debugging), and sol_status must reflect the router's world view -- the frontend # renders "down" as "offline (fallback embed)". conn = _FakeConn( summaries=[("paperless:119", 0.1)], chunks_by_envelope={"paperless:119": [(2, "hit text", 0.34)]}, envelopes={"paperless:119": {"source": "paperless", "entities": []}}, ) result = await run_search( conn, _FakeSession(), _FakeRouter(backend="piha"), "q", "cascade", "claude-haiku-4-5" ) assert result["embed_backend"] == "piha" assert result["sol_status"] == "down" assert len(result["results"]) == 1 class TestRunSearchNoGoodResults: async def test_results_above_no_answer_threshold_are_still_returned_unfiltered(self): # Plan §7: the 0.55 "no answer" colour threshold is a frontend concern -- the API # must not silently drop/hide a poor match, only report its true dist so the caller # (UI or eval harness) can apply that policy itself. conn = _FakeConn( summaries=[("paperless:1", 0.6)], chunks_by_envelope={"paperless:1": [(0, "unrelated text", 0.62)]}, envelopes={"paperless:1": {"source": "paperless", "entities": []}}, ) session = _FakeSession() result = await run_search( conn, session, _FakeRouter(), "unrelated query", "cascade", "claude-haiku-4-5" ) assert len(result["results"]) == 1 assert result["results"][0]["dist"] == 0.62 async def test_no_summaries_yields_empty_results_not_an_error(self): conn = _FakeConn(summaries=[], chunks_by_envelope={}, envelopes={}) session = _FakeSession() result = await run_search( conn, session, _FakeRouter(), "nothing matches", "cascade", "claude-haiku-4-5" ) assert result["results"] == [] class _FakePool: """asyncpg pool stand-in: `async with pool.acquire() as conn` yields the fake conn.""" def __init__(self, conn): self._conn = conn def acquire(self): conn = self._conn class _Acquire: async def __aenter__(self): return conn async def __aexit__(self, *exc_info): return False return _Acquire() def _client_with_fake_state(conn) -> TestClient: # Same trick as tests/test_frontend.py: TestClient is NOT entered as a context manager, # so `lifespan` (live DSN + Ollama) never runs and we inject app.state ourselves. app.state.pool = _FakePool(conn) app.state.http = _FakeSession() app.state.embed_router = _FakeRouter() return TestClient(app) def _mixed_corpus_conn() -> _FakeConn: """One paperless envelope reachable via the summary pre-filter + one gmail envelope reachable ONLY through hybrid's summaryless-source branch -- so the mode a request actually took is visible in the results, not just in the echoed `mode` field.""" return _FakeConn( summaries=[("paperless:1", 0.3)], chunks_by_envelope={"paperless:1": [(0, "doc text", 0.3)]}, envelopes={ "paperless:1": {"source": "paperless", "entities": []}, "": { "source": "gmail", "entities": [{"type": "headers", "from": None, "subject": "s", "date_raw": "d"}], }, }, mail_chunks_by_source={"gmail": [("", 0, "mail text", 0.2)]}, ) class TestSearchEndpointModeDefault: """HTTP-level contract of `mode` (kb/phases/kb-m5-faza-mailowa.md DoD (d), bramka §8 PASS on the full corpus 2026-08-06): no `mode` parameter => hybrid.""" def test_default_without_mode_param_takes_the_hybrid_path(self): client = _client_with_fake_state(_mixed_corpus_conn()) response = client.get("/search", params={"q": "q"}) assert response.status_code == 200 body = response.json() assert body["mode"] == "hybrid" # The mail envelope is unreachable from the cascade/flat paths in this fixture, # so its presence proves the hybrid branch really ran (not just a relabelled cascade). assert [r["envelope_id"] for r in body["results"]] == [ "", "paperless:1", ] def test_explicit_mode_flat_still_takes_the_flat_path(self): client = _client_with_fake_state(_mixed_corpus_conn()) body = client.get("/search", params={"q": "q", "mode": "flat"}).json() assert body["mode"] == "flat" assert [r["envelope_id"] for r in body["results"]] == ["paperless:1"] def test_explicit_mode_cascade_still_takes_the_cascade_path(self): client = _client_with_fake_state(_mixed_corpus_conn()) body = client.get("/search", params={"q": "q", "mode": "cascade"}).json() assert body["mode"] == "cascade" assert [r["envelope_id"] for r in body["results"]] == ["paperless:1"] def test_unknown_mode_is_rejected(self): client = _client_with_fake_state(_mixed_corpus_conn()) assert client.get("/search", params={"q": "q", "mode": "turbo"}).status_code == 422