efc27932dd
Closes the 12 MAJ raised by the release/0.5.0 audit pipeline (cf.
docs/audit/reports/release-0.5.0/summary.md → summary-reaudit.md).
Volet 1 — Reasoning architecture (audits 01/02/06/07 strengthening)
* Domain ports: LLMProvider, ReasoningRunner, ReasoningParseError
* Domain DTOs: LLMProviderType, ReasoningResult, ReasoningIteration
* infra/llm/ollama_provider.py — OllamaProvider with health_check
* infra/docling_agent_reasoning.py — runner adapter, encapsulates the
private _rag_loop call (tracked at docling-project/docling-agent#26),
commits OLLAMA_HOST once at boot (eliminates the per-request env race),
translates upstream IndexError into ReasoningParseError
* api/reasoning.py — zero coupling to docling-agent / mellea / docling-core,
consumes app.state.reasoning_runner via the port
* main.py — DI wires OllamaProvider + DoclingAgentReasoningRunner at boot
when REASONING_ENABLED=true and deps are importable
* Rename RAG_* env vars → REASONING_*, endpoint /rag → /reasoning,
type RAGResult → ReasoningResult, frontend feature flag wiring,
i18n strings, tests, docs (BREAKING — pre-1.0 surface, no external
consumers in production)
* 17 new tests: adapter unit tests with sys.modules stubs, OllamaProvider
httpx tests, R3 concurrent-host isolation, R6 multi-iteration trace
serialization, R13 Protocol conformance via isinstance
* E2E Karate scenario: nav-reasoning hidden when REASONING_ENABLED=false
* README — Live Reasoning section (env vars, archi, link to issue #26)
Bloc B — Security (audit 08, dev-only context)
* docker-compose.yml — DEV DEFAULTS header, OpenSearch DISABLE_SECURITY_PLUGIN
flagged as dev-only with link to OpenSearch security docs
* main.py — boot warning if NEO4J_URI is set with the default 'changeme'
password, so prod operators can't silently inherit it
Bloc C — DRY frontend (audit 05)
* shared/storage/keys.ts — STORAGE_KEYS centralised (theme, locale)
* features/settings/store.ts — dead apiUrl ref + orphan i18n keys removed
* api/schemas.py — DOCUMENT_STATUS_UPLOADED constant
Bloc D — Quality (audits 02/06/07/09/10/12)
* domain/ports.py — DocumentConverter.supports_page_batching property
(LSP fix, replaces isinstance(ServeConverter) check)
* domain/ports.py — VectorStore.ping() (encapsulation, replaces
_vector_store._client.info() reach-around)
* api/analyses.py + api/ingestion.py — path params {job_id} → {analysis_id}
aligned with the user-facing terminology (URLs unchanged)
* api/documents.py — Path.read_bytes() + generate_preview() wrapped in
asyncio.to_thread, unblocks the FastAPI event loop on /preview
* infra/docling_tree.py — PEP 604 union for isinstance (Ruff UP038)
* src/__tests__/integration/ — cross-feature integration test relocated
out of features/history/ so feature folders stay self-contained
* Tightened terminal `assert X is not None` checks (isinstance(.., datetime),
exact value comparisons)
Validation
* 446 backend pytest, 202 frontend vitest — all green
* ruff + ruff format + ESLint + Prettier + vue-tsc clean
* Re-audit verdict: 0 CRIT / 0 MAJ, score ~94/100, GO
Closes #200
211 lines
7.7 KiB
Python
211 lines
7.7 KiB
Python
"""Tests for persistence repositories using a temporary SQLite database."""
|
|
|
|
from datetime import datetime
|
|
|
|
import pytest
|
|
|
|
from domain.models import AnalysisJob, AnalysisStatus, Document
|
|
from persistence.analysis_repo import SqliteAnalysisRepository
|
|
from persistence.database import init_db
|
|
from persistence.document_repo import SqliteDocumentRepository
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
async def setup_db(monkeypatch, tmp_path):
|
|
"""Use a temp file SQLite database for all repo tests."""
|
|
db_path = str(tmp_path / "test.db")
|
|
monkeypatch.setattr("persistence.database.DB_PATH", db_path)
|
|
await init_db()
|
|
yield
|
|
|
|
|
|
@pytest.fixture
|
|
def document_repo():
|
|
return SqliteDocumentRepository()
|
|
|
|
|
|
@pytest.fixture
|
|
def analysis_repo():
|
|
return SqliteAnalysisRepository()
|
|
|
|
|
|
class TestDocumentRepo:
|
|
async def test_insert_and_find_by_id(self, document_repo):
|
|
doc = Document(
|
|
id="doc-1",
|
|
filename="test.pdf",
|
|
content_type="application/pdf",
|
|
file_size=1024,
|
|
storage_path="/tmp/test.pdf",
|
|
)
|
|
await document_repo.insert(doc)
|
|
|
|
found = await document_repo.find_by_id("doc-1")
|
|
assert found is not None
|
|
assert found.id == "doc-1"
|
|
assert found.filename == "test.pdf"
|
|
assert found.file_size == 1024
|
|
|
|
async def test_find_by_id_not_found(self, document_repo):
|
|
found = await document_repo.find_by_id("nonexistent")
|
|
assert found is None
|
|
|
|
async def test_find_all(self, document_repo):
|
|
for i in range(3):
|
|
doc = Document(id=f"doc-{i}", filename=f"file{i}.pdf", storage_path=f"/tmp/{i}")
|
|
await document_repo.insert(doc)
|
|
|
|
all_docs = await document_repo.find_all()
|
|
assert len(all_docs) == 3
|
|
|
|
async def test_update_page_count(self, document_repo):
|
|
doc = Document(id="doc-1", filename="test.pdf", storage_path="/tmp/test.pdf")
|
|
await document_repo.insert(doc)
|
|
|
|
await document_repo.update_page_count("doc-1", 10)
|
|
|
|
updated = await document_repo.find_by_id("doc-1")
|
|
assert updated.page_count == 10
|
|
|
|
async def test_delete(self, document_repo):
|
|
doc = Document(id="doc-1", filename="test.pdf", storage_path="/tmp/test.pdf")
|
|
await document_repo.insert(doc)
|
|
|
|
deleted = await document_repo.delete("doc-1")
|
|
assert deleted is True
|
|
|
|
found = await document_repo.find_by_id("doc-1")
|
|
assert found is None
|
|
|
|
async def test_delete_nonexistent(self, document_repo):
|
|
deleted = await document_repo.delete("nonexistent")
|
|
assert deleted is False
|
|
|
|
|
|
class TestAnalysisRepo:
|
|
async def _insert_doc(self, document_repo):
|
|
doc = Document(id="doc-1", filename="test.pdf", storage_path="/tmp/test.pdf")
|
|
await document_repo.insert(doc)
|
|
return doc
|
|
|
|
async def test_insert_and_find_by_id(self, document_repo, analysis_repo):
|
|
await self._insert_doc(document_repo)
|
|
job = AnalysisJob(id="job-1", document_id="doc-1")
|
|
await analysis_repo.insert(job)
|
|
|
|
found = await analysis_repo.find_by_id("job-1")
|
|
assert found is not None
|
|
assert found.id == "job-1"
|
|
assert found.document_id == "doc-1"
|
|
assert found.status == AnalysisStatus.PENDING
|
|
assert found.document_filename == "test.pdf"
|
|
|
|
async def test_find_by_id_not_found(self, analysis_repo):
|
|
found = await analysis_repo.find_by_id("nonexistent")
|
|
assert found is None
|
|
|
|
async def test_find_all(self, document_repo, analysis_repo):
|
|
await self._insert_doc(document_repo)
|
|
for i in range(3):
|
|
job = AnalysisJob(id=f"job-{i}", document_id="doc-1")
|
|
await analysis_repo.insert(job)
|
|
|
|
all_jobs = await analysis_repo.find_all()
|
|
assert len(all_jobs) == 3
|
|
|
|
async def test_update_status(self, document_repo, analysis_repo):
|
|
await self._insert_doc(document_repo)
|
|
job = AnalysisJob(id="job-1", document_id="doc-1")
|
|
await analysis_repo.insert(job)
|
|
|
|
job.mark_running()
|
|
await analysis_repo.update_status(job)
|
|
|
|
found = await analysis_repo.find_by_id("job-1")
|
|
assert found.status == AnalysisStatus.RUNNING
|
|
assert isinstance(found.started_at, datetime)
|
|
|
|
async def test_update_status_completed(self, document_repo, analysis_repo):
|
|
await self._insert_doc(document_repo)
|
|
job = AnalysisJob(id="job-1", document_id="doc-1")
|
|
await analysis_repo.insert(job)
|
|
|
|
job.mark_running()
|
|
job.mark_completed(markdown="# Test", html="<h1>Test</h1>", pages_json="[]")
|
|
await analysis_repo.update_status(job)
|
|
|
|
found = await analysis_repo.find_by_id("job-1")
|
|
assert found.status == AnalysisStatus.COMPLETED
|
|
assert found.content_markdown == "# Test"
|
|
assert found.content_html == "<h1>Test</h1>"
|
|
assert found.pages_json == "[]"
|
|
|
|
async def test_delete(self, document_repo, analysis_repo):
|
|
await self._insert_doc(document_repo)
|
|
job = AnalysisJob(id="job-1", document_id="doc-1")
|
|
await analysis_repo.insert(job)
|
|
|
|
deleted = await analysis_repo.delete("job-1")
|
|
assert deleted is True
|
|
|
|
found = await analysis_repo.find_by_id("job-1")
|
|
assert found is None
|
|
|
|
async def test_delete_nonexistent(self, analysis_repo):
|
|
deleted = await analysis_repo.delete("nonexistent")
|
|
assert deleted is False
|
|
|
|
async def test_find_latest_completed_by_document(self, document_repo, analysis_repo):
|
|
"""Reasoning tunnel helper: latest COMPLETED analysis with document_json."""
|
|
await self._insert_doc(document_repo)
|
|
|
|
# Each job must be insert()'d before update_status can touch it.
|
|
# Scenarios: pending (excluded — not COMPLETED), old completed without
|
|
# document_json (excluded — NULL json), recent completed with
|
|
# document_json (the one we want), running (excluded).
|
|
pending = AnalysisJob(id="job-pending", document_id="doc-1")
|
|
await analysis_repo.insert(pending)
|
|
|
|
old_completed = AnalysisJob(id="job-old", document_id="doc-1")
|
|
await analysis_repo.insert(old_completed)
|
|
old_completed.mark_running()
|
|
old_completed.mark_completed(markdown="", html="", pages_json="[]")
|
|
await analysis_repo.update_status(old_completed)
|
|
|
|
latest = AnalysisJob(id="job-latest", document_id="doc-1")
|
|
await analysis_repo.insert(latest)
|
|
latest.mark_running()
|
|
latest.mark_completed(
|
|
markdown="md",
|
|
html="<p/>",
|
|
pages_json="[]",
|
|
document_json='{"body":{"children":[]},"texts":[]}',
|
|
)
|
|
await analysis_repo.update_status(latest)
|
|
|
|
running = AnalysisJob(id="job-running", document_id="doc-1")
|
|
await analysis_repo.insert(running)
|
|
running.mark_running()
|
|
await analysis_repo.update_status(running)
|
|
|
|
found = await analysis_repo.find_latest_completed_by_document("doc-1")
|
|
assert found is not None
|
|
assert found.id == "job-latest"
|
|
assert found.document_json == '{"body":{"children":[]},"texts":[]}'
|
|
|
|
async def test_find_latest_completed_by_document_none(self, document_repo, analysis_repo):
|
|
await self._insert_doc(document_repo)
|
|
found = await analysis_repo.find_latest_completed_by_document("doc-1")
|
|
assert found is None
|
|
|
|
async def test_delete_by_document(self, document_repo, analysis_repo):
|
|
await self._insert_doc(document_repo)
|
|
for i in range(3):
|
|
job = AnalysisJob(id=f"job-{i}", document_id="doc-1")
|
|
await analysis_repo.insert(job)
|
|
|
|
count = await analysis_repo.delete_by_document("doc-1")
|
|
assert count == 3
|
|
|
|
all_jobs = await analysis_repo.find_all()
|
|
assert len(all_jobs) == 0
|