forked from 0xWheatyz/SPARC
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 7c6eed8d72 |
+30
-37
@@ -81,57 +81,50 @@ Items that have been implemented and merged into main.
|
||||
- ~~OpenAPI client generation.~~ TypeScript API client auto-generated from
|
||||
FastAPI spec with CI freshness check.
|
||||
|
||||
### Resilience
|
||||
|
||||
- ~~`_jobs` dict is in-memory only.~~ Database-backed job persistence
|
||||
implemented using `db.list_jobs()` and `mark_stale_jobs_failed()`. The
|
||||
in-memory `_jobs` dict has been removed.
|
||||
|
||||
### Test coverage (P1/P2)
|
||||
|
||||
- ~~Export endpoint tests.~~ Tests added for CSV and PDF export endpoints.
|
||||
- ~~Tracked company admin endpoint tests.~~ Tests added for `/admin/tracked`
|
||||
CRUD endpoints and scheduler integration.
|
||||
- ~~Webhook integration tests.~~ Tests added for retry logic, Slack/Discord
|
||||
payload format, and multi-URL dispatch.
|
||||
- ~~S3/MinIO storage backend tests.~~ Unit tests added for the S3 backend
|
||||
(read, write, exists, delete, error handling).
|
||||
- ~~`analyze_single_patent` auto-download path tests.~~ Tests added for the
|
||||
auto-download fallback (cache lookup, PDF download, FileNotFoundError).
|
||||
|
||||
### Code quality
|
||||
|
||||
- ~~Scheduler creates its own DatabaseClient.~~ Refactored to use the
|
||||
application-level pooled `get_db_client()`.
|
||||
|
||||
---
|
||||
|
||||
## P1 -- High Priority
|
||||
|
||||
These items address correctness, reliability, and coverage gaps that should be
|
||||
resolved before broader production use.
|
||||
|
||||
### Resilience
|
||||
|
||||
- **`_jobs` dict is in-memory only.** Job state is lost on API restart.
|
||||
Persist job status in PostgreSQL or Redis so async batch results survive
|
||||
restarts.
|
||||
|
||||
### Test coverage gaps
|
||||
|
||||
- **Export endpoint tests.** The CSV and PDF export endpoints (`/export/`)
|
||||
lack test coverage. Add tests covering auth, success, 404, and edge cases.
|
||||
*(Issue #1655)*
|
||||
- **Tracked company admin endpoint tests.** The `/admin/tracked` CRUD
|
||||
endpoints and scheduler integration lack test coverage. *(Issue #1656)*
|
||||
No outstanding P1 items. All previously listed items have been completed and
|
||||
moved to the Completed section above.
|
||||
|
||||
---
|
||||
|
||||
## P2 -- Medium Priority
|
||||
|
||||
Improvements to reliability, test coverage, and code quality.
|
||||
|
||||
### Test coverage
|
||||
|
||||
- **Webhook integration tests.** The retry logic, Slack/Discord payload
|
||||
format, and multi-URL dispatch in `webhooks.py` need test coverage.
|
||||
*(Issue #1657)*
|
||||
- **S3/MinIO storage backend tests.** `storage.py` has local filesystem tests
|
||||
but no unit tests for the S3 backend (read, write, exists, delete,
|
||||
error handling). *(Issue #1660)*
|
||||
- **`analyze_single_patent` auto-download path tests.** The auto-download
|
||||
fallback (cache lookup, PDF download, FileNotFoundError) in
|
||||
`analyzer.py` lacks test coverage. *(Issue #1661)*
|
||||
|
||||
### Code quality
|
||||
|
||||
- **Scheduler creates its own DatabaseClient.** `scheduler.py` bypasses the
|
||||
application-level pooled client, creating a new connection on every tick.
|
||||
Refactor to use `get_db_client()`. *(Issue #1658)*
|
||||
Improvements to the API surface.
|
||||
|
||||
### API improvements
|
||||
|
||||
- **API pagination.** The `/analyze/batch` and `/jobs` endpoints could benefit
|
||||
from cursor-based pagination for large result sets.
|
||||
- **API pagination.** The `/analyze/batch` endpoint needs cursor-based
|
||||
pagination for large result sets. The `/jobs` endpoint already has cursor
|
||||
pagination. *(Issue #1669)*
|
||||
- **Request validation improvements.** Add stricter input validation for
|
||||
company names (disallow special characters, enforce length limits).
|
||||
*(Issue #1670)*
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -217,37 +217,10 @@ app = FastAPI(
|
||||
limiter = Limiter(key_func=get_remote_address)
|
||||
app.state.limiter = limiter
|
||||
|
||||
# In-memory rate limit statistics
|
||||
_rate_limit_stats: dict[str, dict] = {}
|
||||
|
||||
|
||||
def _track_rate_limit_request(endpoint: str, ip: str, rejected: bool = False) -> None:
|
||||
"""Record a request against a rate-limited endpoint."""
|
||||
key = endpoint
|
||||
if key not in _rate_limit_stats:
|
||||
_rate_limit_stats[key] = {
|
||||
"endpoint": endpoint,
|
||||
"total_requests": 0,
|
||||
"rejected_requests": 0,
|
||||
"by_ip": {},
|
||||
}
|
||||
_rate_limit_stats[key]["total_requests"] += 1
|
||||
if rejected:
|
||||
_rate_limit_stats[key]["rejected_requests"] += 1
|
||||
ip_stats = _rate_limit_stats[key].setdefault("by_ip", {})
|
||||
if ip not in ip_stats:
|
||||
ip_stats[ip] = {"total": 0, "rejected": 0}
|
||||
ip_stats[ip]["total"] += 1
|
||||
if rejected:
|
||||
ip_stats[ip]["rejected"] += 1
|
||||
|
||||
|
||||
@app.exception_handler(RateLimitExceeded)
|
||||
async def rate_limit_handler(request: Request, exc: RateLimitExceeded):
|
||||
"""Return 429 with Retry-After header when rate limit is exceeded."""
|
||||
endpoint = request.url.path
|
||||
ip = get_remote_address(request)
|
||||
_track_rate_limit_request(endpoint, ip, rejected=True)
|
||||
retry_after = getattr(exc, "retry_after", 60)
|
||||
return JSONResponse(
|
||||
status_code=429,
|
||||
@@ -276,7 +249,6 @@ async def register(request: Request, body: RegisterRequest):
|
||||
|
||||
The first registered user automatically becomes an admin.
|
||||
"""
|
||||
_track_rate_limit_request("/auth/register", get_remote_address(request))
|
||||
db = get_db_client()
|
||||
|
||||
# First user becomes admin
|
||||
@@ -307,7 +279,6 @@ async def register(request: Request, body: RegisterRequest):
|
||||
@limiter.limit("10/minute")
|
||||
async def login(request: Request, body: LoginRequest):
|
||||
"""Authenticate user and return JWT tokens."""
|
||||
_track_rate_limit_request("/auth/login", get_remote_address(request))
|
||||
db = get_db_client()
|
||||
|
||||
user = db.authenticate_user(body.email, body.password)
|
||||
@@ -472,36 +443,6 @@ async def remove_tracked_company(
|
||||
return {"message": f"Stopped tracking {company_name}"}
|
||||
|
||||
|
||||
@app.get("/admin/rate-limits", tags=["Admin"])
|
||||
async def get_rate_limit_stats(
|
||||
_: UserResponse = Depends(get_current_admin),
|
||||
):
|
||||
"""Get rate limit status and usage statistics (admin only).
|
||||
|
||||
Returns current rate limit configuration and request statistics
|
||||
for all rate-limited endpoints.
|
||||
|
||||
Returns:
|
||||
List of rate limit stats per endpoint with total/rejected counts
|
||||
"""
|
||||
rate_limits_config = {
|
||||
"/auth/register": {"limit": "5/minute"},
|
||||
"/auth/login": {"limit": "10/minute"},
|
||||
}
|
||||
|
||||
results = []
|
||||
for endpoint, conf in rate_limits_config.items():
|
||||
stats = _rate_limit_stats.get(endpoint, {})
|
||||
results.append({
|
||||
"endpoint": endpoint,
|
||||
"limit": conf["limit"],
|
||||
"total_requests": stats.get("total_requests", 0),
|
||||
"rejected_requests": stats.get("rejected_requests", 0),
|
||||
})
|
||||
|
||||
return {"rate_limits": results}
|
||||
|
||||
|
||||
@app.get("/admin/alerts", tags=["Admin"])
|
||||
async def list_alerts(
|
||||
limit: int = Query(default=50, ge=1, le=200),
|
||||
|
||||
@@ -1,109 +0,0 @@
|
||||
"""Tests for the /admin/rate-limits endpoint."""
|
||||
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
from fastapi.testclient import TestClient
|
||||
|
||||
from SPARC import api
|
||||
from SPARC.api import app
|
||||
from SPARC.auth import UserResponse
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def client():
|
||||
"""Create test client."""
|
||||
return TestClient(app)
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def reset_stats():
|
||||
"""Reset rate limit stats between tests."""
|
||||
api._rate_limit_stats.clear()
|
||||
yield
|
||||
api._rate_limit_stats.clear()
|
||||
|
||||
|
||||
def _mock_admin():
|
||||
"""Return a mock admin user."""
|
||||
return UserResponse(id=1, email="admin@test.com", role="admin", created_at="2025-01-01T00:00:00")
|
||||
|
||||
|
||||
def _mock_user():
|
||||
"""Return a mock non-admin user."""
|
||||
return UserResponse(id=2, email="user@test.com", role="user", created_at="2025-01-01T00:00:00")
|
||||
|
||||
|
||||
class TestRateLimitAdminEndpoint:
|
||||
"""Test GET /admin/rate-limits."""
|
||||
|
||||
def test_admin_can_access(self, client):
|
||||
"""Admin users should be able to access the rate-limits endpoint."""
|
||||
app.dependency_overrides[api.get_current_admin] = _mock_admin
|
||||
try:
|
||||
response = client.get("/admin/rate-limits")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert "rate_limits" in data
|
||||
assert isinstance(data["rate_limits"], list)
|
||||
finally:
|
||||
app.dependency_overrides.clear()
|
||||
|
||||
def test_non_admin_rejected(self, client):
|
||||
"""Non-admin users should get 403."""
|
||||
# Without overriding the dependency, it should fail auth
|
||||
response = client.get("/admin/rate-limits")
|
||||
assert response.status_code in (401, 403)
|
||||
|
||||
def test_returns_configured_endpoints(self, client):
|
||||
"""Should list all rate-limited endpoints."""
|
||||
app.dependency_overrides[api.get_current_admin] = _mock_admin
|
||||
try:
|
||||
response = client.get("/admin/rate-limits")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
endpoints = [rl["endpoint"] for rl in data["rate_limits"]]
|
||||
assert "/auth/register" in endpoints
|
||||
assert "/auth/login" in endpoints
|
||||
finally:
|
||||
app.dependency_overrides.clear()
|
||||
|
||||
def test_empty_state_shows_zero_counts(self, client):
|
||||
"""When no requests have been made, counts should be zero."""
|
||||
app.dependency_overrides[api.get_current_admin] = _mock_admin
|
||||
try:
|
||||
response = client.get("/admin/rate-limits")
|
||||
data = response.json()
|
||||
for rl in data["rate_limits"]:
|
||||
assert rl["total_requests"] == 0
|
||||
assert rl["rejected_requests"] == 0
|
||||
finally:
|
||||
app.dependency_overrides.clear()
|
||||
|
||||
def test_tracks_requests(self, client):
|
||||
"""After making requests, the stats should reflect them."""
|
||||
api._track_rate_limit_request("/auth/login", "127.0.0.1")
|
||||
api._track_rate_limit_request("/auth/login", "127.0.0.1")
|
||||
api._track_rate_limit_request("/auth/login", "192.168.1.1", rejected=True)
|
||||
|
||||
app.dependency_overrides[api.get_current_admin] = _mock_admin
|
||||
try:
|
||||
response = client.get("/admin/rate-limits")
|
||||
data = response.json()
|
||||
login_stats = next(rl for rl in data["rate_limits"] if rl["endpoint"] == "/auth/login")
|
||||
assert login_stats["total_requests"] == 3
|
||||
assert login_stats["rejected_requests"] == 1
|
||||
finally:
|
||||
app.dependency_overrides.clear()
|
||||
|
||||
def test_includes_limit_config(self, client):
|
||||
"""Each endpoint entry should include the rate limit config string."""
|
||||
app.dependency_overrides[api.get_current_admin] = _mock_admin
|
||||
try:
|
||||
response = client.get("/admin/rate-limits")
|
||||
data = response.json()
|
||||
for rl in data["rate_limits"]:
|
||||
assert "limit" in rl
|
||||
assert isinstance(rl["limit"], str)
|
||||
finally:
|
||||
app.dependency_overrides.clear()
|
||||
Reference in New Issue
Block a user