b2379e3275
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>
77 lines
2.9 KiB
Python
77 lines
2.9 KiB
Python
"""Unit tests for per-source /search result shaping."""
|
|
from __future__ import annotations
|
|
|
|
import pathlib
|
|
import sys
|
|
|
|
sys.path.insert(0, str(pathlib.Path(__file__).resolve().parents[1]))
|
|
|
|
from app.links import build_result # noqa: E402
|
|
|
|
|
|
def _chunk(envelope_id="paperless:119", dist=0.34, chunk_index=2, text="hit text"):
|
|
return {"envelope_id": envelope_id, "dist": dist, "chunk_index": chunk_index, "text": text}
|
|
|
|
|
|
class TestBuildResultPaperless:
|
|
def test_shape_and_link(self):
|
|
envelope = {"source": "paperless", "entities": []}
|
|
result = build_result(_chunk(envelope_id="paperless:119"), envelope)
|
|
assert result["source"] == "paperless"
|
|
assert result["link"] == "https://paper.kapala.org/documents/119/details"
|
|
assert "subject" not in result
|
|
assert "mail_ui_url" not in result
|
|
|
|
|
|
class TestBuildResultGmail:
|
|
def test_shape_and_headers(self):
|
|
envelope = {
|
|
"source": "gmail",
|
|
"entities": [
|
|
{
|
|
"type": "headers",
|
|
"from": {"name": "Promocja Lunchroom", "address": "promocja@lunchroom.pl"},
|
|
"subject": "-20% w wybranych restauracjach",
|
|
"date_raw": "Wed, 9 May 2018 10:03:32 +0200",
|
|
}
|
|
],
|
|
}
|
|
result = build_result(_chunk(envelope_id="<msgid@example.com>"), envelope)
|
|
assert result["source"] == "gmail"
|
|
assert result["subject"] == "-20% w wybranych restauracjach"
|
|
assert result["from"] == "Promocja Lunchroom <promocja@lunchroom.pl>"
|
|
assert result["date"] == "Wed, 9 May 2018 10:03:32 +0200"
|
|
assert result["link"] is None
|
|
assert result["mail_ui_url"] is None
|
|
|
|
def test_from_without_name_falls_back_to_address(self):
|
|
envelope = {
|
|
"source": "gmail",
|
|
"entities": [
|
|
{"type": "headers", "from": {"name": None, "address": "a@b.com"}, "subject": "s", "date_raw": "d"}
|
|
],
|
|
}
|
|
result = build_result(_chunk(), envelope)
|
|
assert result["from"] == "a@b.com"
|
|
|
|
def test_missing_headers_entity_yields_none_fields(self):
|
|
envelope = {"source": "gmail", "entities": []}
|
|
result = build_result(_chunk(), envelope)
|
|
assert result["subject"] is None
|
|
assert result["from"] is None
|
|
assert result["date"] is None
|
|
|
|
|
|
class TestBuildResultEdgeCases:
|
|
def test_unknown_source_gets_null_link_no_extra_fields(self):
|
|
result = build_result(_chunk(), {"source": "mystery", "entities": []})
|
|
assert result["source"] == "mystery"
|
|
assert result["link"] is None
|
|
assert "subject" not in result
|
|
|
|
def test_missing_envelope_does_not_crash(self):
|
|
# e.g. a chunk whose envelope vanished between embedding and query time.
|
|
result = build_result(_chunk(), None)
|
|
assert result["source"] == "unknown"
|
|
assert result["link"] is None
|