homelab-codex-ws/services/kb-query/tests/test_search.py
oskar b2379e3275 feat(kb): add kb-query service skeleton (search API, no ingress yet)
Module 5 phase 4 step 1 (docs/kb/modules/05-faza4-plan.md, §4): first
user-facing HTTP entry point to the KB. FastAPI wrapping
kb_retrieval.cascade_query/flat_query — GET /search (query_text -> embed via
Ollama@SOLARIA -> cascade/flat -> envelope join -> JSON with per-source
links) and GET /healthz. Search API only, no answer synthesis (phase 5) and
no server-side dist filtering — the 0.45/0.55 colour thresholds are a
frontend concern (plan §7, a later step).

Hard startup invariant (plan §2 decision 2): refuses to start unless the
configured EMBED_MODEL is present in both document_chunk.model and
document_summary.embedding_model. Note the latter: document_summary.model is
the LLM that *wrote* the summary (claude-haiku-4-5/gemma3:12b), not the
embedder — checked live against kb-postgres@PIHA before writing this, see
app/startup.py's docstring. Verified end-to-end with a live docker run: the
invariant crash-loops on a mismatched EMBED_MODEL and passes through to a
real /search hit against the live corpus with a correct model.

Repo-only: no deploy, no npm/OIDC/DNS wiring (plan §8, later step), no local
embed fallback (plan §5, later step) — Ollama@SOLARIA is called directly and
a failure surfaces as 503, not a crash.

Also: scripts/deploy/deploy.sh's gate now builds each service via
`docker compose build` instead of a raw `docker build <svc_dir>`, so a
service whose docker-compose.yml declares a repo-root build context (needed
here to COPY packages/kb-retrieval/, the packages/ Dockerfile convention
already documented in CLAUDE.md) resolves the same way in the gate as it
does at real deploy time (deploy-node.sh's `docker compose ... up --build`).
No behavior change for existing single-context services — verified against
llm-gateway's compose file.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-22 16:06:18 +02:00

164 lines
6.4 KiB
Python

"""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 app.search import run_search # noqa: E402
class _FakeConn:
"""summaries: [(envelope_id, dist), ...]. chunks_by_envelope: envelope_id -> [(chunk_index,
text, dist), ...]. envelopes: envelope_id -> {"source": ..., "entities": [...]}."""
def __init__(self, summaries=None, chunks_by_envelope=None, envelopes=None):
self._summaries = list(summaries or [])
self._chunks_by_envelope = chunks_by_envelope or {}
self._envelopes = envelopes or {}
async def fetch(self, query, *params):
if "FROM document_summary" in query:
_, _model, limit = params
return [{"envelope_id": eid, "dist": dist} for eid, dist in self._summaries[: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 _FakeEmbedResponse:
def __init__(self, payload):
self._payload = payload
async def __aenter__(self):
return self
async def __aexit__(self, *exc):
return False
def raise_for_status(self):
pass
async def json(self):
return self._payload
class _FakeSession:
def __init__(self):
self.post_calls: list[dict] = []
def post(self, url, json):
self.post_calls.append({"url": url, "json": json})
return _FakeEmbedResponse({"embedding": [0.01] * 1024})
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, "http://fake-ollama", "polisa PZU", "cascade", "bge-m3", "claude-haiku-4-5"
)
assert result["query"] == "polisa PZU"
assert result["mode"] == "cascade"
assert result["sol_status"] == "up"
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, "http://fake-ollama", "q", "flat", "bge-m3", "claude-haiku-4-5"
)
assert result["mode"] == "flat"
assert len(result["results"]) == 1
async def test_gmail_hit_carries_header_metadata_not_a_link(self):
conn = _FakeConn(
summaries=[("<msgid@example.com>", 0.1)],
chunks_by_envelope={"<msgid@example.com>": [(0, "body text", 0.4)]},
envelopes={
"<msgid@example.com>": {
"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, "http://fake-ollama", "q", "cascade", "bge-m3", "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 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, "http://fake-ollama", "unrelated query", "cascade", "bge-m3", "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, "http://fake-ollama", "nothing matches", "cascade", "bge-m3", "claude-haiku-4-5"
)
assert result["results"] == []