feat(01-05): final cutover — delete data/, prune config.py, async-only tests

- Delete backend/data/ tracked files (D-04): flat-file metadata, settings.json,
  topics.json, and uploaded files removed from git; backend/data/ added to
  .gitignore (empty dir remains on macOS due to ACL — no tracked files remain)
- Prune backend/config.py: remove DATA_DIR, UPLOADS_DIR, METADATA_DIR,
  TOPICS_FILE, ensure_data_dirs(); rebase SETTINGS_FILE as derived path from
  settings.data_dir (Phase 1 flat-file settings kept per plan decision)
- Prune backend/tests/conftest.py: remove isolated_data_dir autouse fixture
  and sync TestClient client fixture; add SQLite type compatibility shim
  (visit_INET/JSONB) so in-memory db_session can create tables with
  PostgreSQL-specific column types; add live_services_available fixture
- Rewrite backend/tests/test_documents.py: delete all legacy sync tests,
  remove all @pytest.mark.xfail markers; async-only document tests now
  use async_client + storage service directly for topic wiring
- Rewrite backend/tests/test_health.py: delete legacy sync test_health(client);
  remove @pytest.mark.xfail from test_health_checks_postgres_and_minio
- Port backend/tests/test_topics.py to async_client (sync client removed)
- Port backend/tests/test_settings.py to async_client with monkeypatch for
  SETTINGS_FILE isolation (settings remain flat-file in Phase 1)
This commit is contained in:
curo1305
2026-05-22 09:53:39 +02:00
parent c1931fd566
commit 970c8e4e44
17 changed files with 327 additions and 13135 deletions
+3 -26
View File
@@ -1,5 +1,3 @@
import json
import os
from pathlib import Path
from pydantic_settings import BaseSettings, SettingsConfigDict
@@ -14,7 +12,7 @@ class Settings(BaseSettings):
extra="ignore",
)
# Data directory (legacy flat-file path — kept until Plan 05 removes it)
# Data directory — used only for the flat-file settings.json path (Phase 1)
data_dir: str = "/app/data"
# PostgreSQL
@@ -36,18 +34,8 @@ class Settings(BaseSettings):
settings = Settings()
# ──────────────────────────────────────────────────────────────────────────────
# Legacy flat-file constants — kept for backward compatibility through Wave 4.
# These are consumed by services/storage.py, services/classifier.py, and
# api/settings.py until Plan 05 rewrites those modules.
# DO NOT DELETE until Plan 05 completes the storage service cutover.
# ──────────────────────────────────────────────────────────────────────────────
DATA_DIR = Path(os.environ.get("DATA_DIR", "/app/data"))
UPLOADS_DIR = DATA_DIR / "uploads"
METADATA_DIR = DATA_DIR / "metadata"
TOPICS_FILE = DATA_DIR / "topics.json"
SETTINGS_FILE = DATA_DIR / "settings.json"
# SETTINGS_FILE: still flat-file in Phase 1; migrates to users.ai_provider in Phase 2
SETTINGS_FILE = Path(settings.data_dir) / "settings.json"
DEFAULT_SYSTEM_PROMPT = """You are a document classification assistant. When given a document's text content and a list of existing topics, you must:
1. Assign the document to one or more relevant topics from the list.
@@ -79,14 +67,3 @@ DEFAULT_SETTINGS = {
}
}
}
def ensure_data_dirs():
UPLOADS_DIR.mkdir(parents=True, exist_ok=True)
METADATA_DIR.mkdir(parents=True, exist_ok=True)
if not TOPICS_FILE.exists():
TOPICS_FILE.write_text(json.dumps({"topics": []}, indent=2))
if not SETTINGS_FILE.exists():
SETTINGS_FILE.write_text(json.dumps(DEFAULT_SETTINGS, indent=2))