Compare commits

..

1 Commits

Author SHA1 Message Date
agent-company 47cddcbeaf feat(security): add JWT startup guard, configurable CORS, and externalize DB credentials
- Add check_jwt_secret() that refuses default JWT secret when APP_ENV != development
- Make CORS origins configurable via CORS_ORIGINS env var (comma-separated)
- Replace hardcoded postgres credentials in docker-compose.yml with env var references
- Add APP_ENV and cors_origins to config.py
- Update .env.example with all required variables and documentation
- Add tests for JWT startup guard and CORS configuration

Closes leeworks-agents/SPARC#4
Closes leeworks-agents/SPARC#5
Closes leeworks-agents/SPARC#6

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 04:06:31 +00:00
7 changed files with 356 additions and 204 deletions
+30 -9
View File
@@ -1,21 +1,42 @@
# SPARC Configuration
# ---- Application Environment ----
# Set to "production" or "staging" in deployed environments.
# The API will refuse to start with the default JWT secret unless APP_ENV=development.
APP_ENV=development
# ---- API Keys ----
# SerpAPI key for patent search
API_KEY=your_serpapi_key_here
# OpenRouter API key for LLM analysis
OPENROUTER_API_KEY=your_openrouter_key_here
# Database configuration
# All messages are stored in the database for persistence and caching
DATABASE_URL=postgresql://postgres:postgres@localhost:5432/sparc
# ---- Database ----
# Cache configuration
# When USE_CACHE=true: check database for cached responses before making API calls
# When USE_CACHE=false: always make fresh API calls (still stores results in database)
# Default: true
USE_CACHE=true
# PostgreSQL credentials (used by docker-compose)
POSTGRES_USER=postgres
POSTGRES_PASSWORD=change-me-to-a-secure-password
POSTGRES_DB=sparc
# JWT Secret for authentication
# Full database URL (must match the credentials above)
DATABASE_URL=postgresql://postgres:change-me-to-a-secure-password@localhost:5432/sparc
# ---- Authentication ----
# JWT Secret for signing tokens
# IMPORTANT: Change this to a secure random string in production
JWT_SECRET=your-secure-jwt-secret-change-in-production
# ---- CORS ----
# Comma-separated list of allowed origins for CORS
# Defaults to http://localhost:3000,http://localhost:5173 when unset
# CORS_ORIGINS=https://sparc.example.com,https://app.example.com
# ---- Cache ----
# When USE_CACHE=true: check database for cached responses before making API calls
# When USE_CACHE=false: always make fresh API calls (still stores results in database)
USE_CACHE=true
+5 -7
View File
@@ -16,13 +16,12 @@ from SPARC.analyzer import CompanyAnalyzer
from SPARC.auth import (
TokenResponse,
UserResponse,
close_db_client,
check_jwt_secret,
create_tokens,
decode_token,
get_current_admin,
get_current_user,
get_db_client,
init_db_client,
)
from SPARC.types import BatchAnalysisResult, CompanyAnalysisResult
@@ -150,14 +149,13 @@ _analyzer: CompanyAnalyzer | None = None
@asynccontextmanager
async def lifespan(app: FastAPI):
"""Initialize resources on startup, clean up on shutdown."""
"""Initialize resources on startup."""
global _analyzer
init_db_client()
check_jwt_secret()
_analyzer = CompanyAnalyzer()
yield
# Cleanup
# Cleanup if needed
_analyzer = None
close_db_client()
app = FastAPI(
@@ -171,7 +169,7 @@ app = FastAPI(
# Add CORS middleware for React frontend
app.add_middleware(
CORSMiddleware,
allow_origins=["http://localhost:3000", "http://localhost:5173"],
allow_origins=config.cors_origins,
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
+19 -30
View File
@@ -13,11 +13,25 @@ from SPARC import config
from SPARC.database import DatabaseClient
# JWT Configuration
JWT_SECRET = os.getenv("JWT_SECRET", "sparc-secret-key-change-in-production")
_DEFAULT_JWT_SECRET = "sparc-secret-key-change-in-production"
JWT_SECRET = os.getenv("JWT_SECRET", _DEFAULT_JWT_SECRET)
JWT_ALGORITHM = "HS256"
ACCESS_TOKEN_EXPIRE_MINUTES = 30
REFRESH_TOKEN_EXPIRE_DAYS = 7
def check_jwt_secret() -> None:
"""Refuse to start with the default JWT secret in non-development environments.
Raises:
RuntimeError: If JWT_SECRET is the default value and APP_ENV is not 'development'.
"""
if JWT_SECRET == _DEFAULT_JWT_SECRET and config.app_env != "development":
raise RuntimeError(
f"FATAL: JWT_SECRET is set to the default value and APP_ENV={config.app_env!r}. "
"Set a secure JWT_SECRET environment variable before running in non-development environments."
)
security = HTTPBearer()
@@ -132,36 +146,11 @@ def decode_token(token: str) -> Optional[TokenPayload]:
return None
# Shared database client singleton, initialized at startup via init_db_client()
_db_client: DatabaseClient | None = None
def init_db_client() -> None:
"""Initialize the shared database client. Call once at app startup."""
global _db_client
_db_client = DatabaseClient(config.database_url)
_db_client.connect()
def close_db_client() -> None:
"""Close the shared database client. Call at app shutdown."""
global _db_client
if _db_client:
_db_client.close()
_db_client = None
def get_db_client() -> DatabaseClient:
"""Get the shared pooled database client for auth operations.
Returns the module-level singleton DatabaseClient. If not yet initialized
(e.g., during tests), creates a new instance as a fallback.
"""
global _db_client
if _db_client is None:
_db_client = DatabaseClient(config.database_url)
_db_client.connect()
return _db_client
"""Get database client for auth operations."""
client = DatabaseClient(config.database_url)
client.connect()
return client
async def get_current_user(
+13
View File
@@ -33,3 +33,16 @@ patent_thread_workers = int(os.getenv("PATENT_THREAD_WORKERS", "5"))
# Root path for running behind a reverse proxy (e.g., "/api" when served at /api/)
# This ensures OpenAPI docs work correctly when accessed via the proxy
root_path = os.getenv("ROOT_PATH", "")
# Application environment: "development", "staging", or "production"
# Used for safety checks (e.g., refusing default JWT secret in production)
app_env = os.getenv("APP_ENV", "development")
# CORS allowed origins (comma-separated)
# Defaults to localhost dev origins when unset
_cors_origins_raw = os.getenv("CORS_ORIGINS", "")
cors_origins: list[str] = (
[o.strip() for o in _cors_origins_raw.split(",") if o.strip()]
if _cors_origins_raw
else ["http://localhost:3000", "http://localhost:5173"]
)
+165 -152
View File
@@ -201,6 +201,8 @@ class DatabaseClient:
Returns:
Cached message dict if found, None otherwise
"""
self.connect()
prompt_hash = self.hash_prompt(prompt)
query = """
@@ -223,11 +225,10 @@ class DatabaseClient:
query += " ORDER BY timestamp DESC LIMIT 1"
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(query, params)
result = cursor.fetchone()
return dict(result) if result else None
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(query, params)
result = cursor.fetchone()
return dict(result) if result else None
def store_message(
self,
@@ -255,32 +256,33 @@ class DatabaseClient:
Returns:
The ID of the inserted record
"""
self.connect()
prompt_hash = self.hash_prompt(prompt)
with self.get_conn() as conn:
with conn.cursor() as cursor:
cursor.execute(
"""
INSERT INTO llm_messages
(prompt, prompt_hash, response, company_name, analysis_type, model, metadata, token_usage, is_cached)
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
RETURNING id
""",
(
prompt,
prompt_hash,
response,
company_name,
analysis_type,
model,
json.dumps(metadata) if metadata else None,
json.dumps(token_usage) if token_usage else None,
is_cached,
),
)
with self.conn.cursor() as cursor:
cursor.execute(
"""
INSERT INTO llm_messages
(prompt, prompt_hash, response, company_name, analysis_type, model, metadata, token_usage, is_cached)
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
RETURNING id
""",
(
prompt,
prompt_hash,
response,
company_name,
analysis_type,
model,
json.dumps(metadata) if metadata else None,
json.dumps(token_usage) if token_usage else None,
is_cached,
),
)
message_id = cursor.fetchone()[0]
conn.commit()
message_id = cursor.fetchone()[0]
self.conn.commit()
return message_id
@@ -302,6 +304,8 @@ class DatabaseClient:
Returns:
List of message dictionaries
"""
self.connect()
query = "SELECT * FROM llm_messages WHERE 1=1"
params = []
@@ -316,10 +320,9 @@ class DatabaseClient:
query += " ORDER BY timestamp DESC LIMIT %s OFFSET %s"
params.extend([limit, offset])
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(query, params)
return [dict(row) for row in cursor.fetchall()]
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(query, params)
return [dict(row) for row in cursor.fetchall()]
def get_analytics(self, days: int = 30) -> Dict:
"""Get analytics on message usage.
@@ -330,52 +333,53 @@ class DatabaseClient:
Returns:
Dictionary with analytics data
"""
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
# Total messages
cursor.execute(
"""
SELECT COUNT(*) as total_messages
FROM llm_messages
WHERE timestamp >= NOW() - INTERVAL '%s days'
""",
(days,),
)
total = cursor.fetchone()["total_messages"]
self.connect()
# Messages by company
cursor.execute(
"""
SELECT company_name, COUNT(*) as count
FROM llm_messages
WHERE timestamp >= NOW() - INTERVAL '%s days'
GROUP BY company_name
ORDER BY count DESC
LIMIT 10
""",
(days,),
)
by_company = cursor.fetchall()
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
# Total messages
cursor.execute(
"""
SELECT COUNT(*) as total_messages
FROM llm_messages
WHERE timestamp >= NOW() - INTERVAL '%s days'
""",
(days,),
)
total = cursor.fetchone()["total_messages"]
# Messages by type
cursor.execute(
"""
SELECT analysis_type, COUNT(*) as count
FROM llm_messages
WHERE timestamp >= NOW() - INTERVAL '%s days'
GROUP BY analysis_type
ORDER BY count DESC
""",
(days,),
)
by_type = cursor.fetchall()
# Messages by company
cursor.execute(
"""
SELECT company_name, COUNT(*) as count
FROM llm_messages
WHERE timestamp >= NOW() - INTERVAL '%s days'
GROUP BY company_name
ORDER BY count DESC
LIMIT 10
""",
(days,),
)
by_company = cursor.fetchall()
return {
"total_messages": total,
"by_company": [dict(row) for row in by_company],
"by_type": [dict(row) for row in by_type],
"period_days": days,
}
# Messages by type
cursor.execute(
"""
SELECT analysis_type, COUNT(*) as count
FROM llm_messages
WHERE timestamp >= NOW() - INTERVAL '%s days'
GROUP BY analysis_type
ORDER BY count DESC
""",
(days,),
)
by_type = cursor.fetchall()
return {
"total_messages": total,
"by_company": [dict(row) for row in by_company],
"by_type": [dict(row) for row in by_type],
"period_days": days,
}
# Patent Cache Methods
@@ -501,23 +505,25 @@ class DatabaseClient:
Returns:
Created user dict or None if email exists
"""
self.connect()
password_hash = self.hash_password(password)
try:
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"""
INSERT INTO users (email, password_hash, role)
VALUES (%s, %s, %s)
RETURNING id, email, role, created_at
""",
(email, password_hash, role),
)
user = cursor.fetchone()
conn.commit()
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"""
INSERT INTO users (email, password_hash, role)
VALUES (%s, %s, %s)
RETURNING id, email, role, created_at
""",
(email, password_hash, role),
)
user = cursor.fetchone()
self.conn.commit()
return dict(user) if user else None
except psycopg2.errors.UniqueViolation:
self.conn.rollback()
return None
def authenticate_user(self, email: str, password: str) -> Optional[Dict]:
@@ -530,22 +536,23 @@ class DatabaseClient:
Returns:
User dict if authenticated, None otherwise
"""
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"SELECT * FROM users WHERE email = %s",
(email,),
)
user = cursor.fetchone()
self.connect()
if user and self.verify_password(password, user["password_hash"]):
return {
"id": user["id"],
"email": user["email"],
"role": user["role"],
"created_at": user["created_at"],
}
return None
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"SELECT * FROM users WHERE email = %s",
(email,),
)
user = cursor.fetchone()
if user and self.verify_password(password, user["password_hash"]):
return {
"id": user["id"],
"email": user["email"],
"role": user["role"],
"created_at": user["created_at"],
}
return None
def get_user_by_id(self, user_id: int) -> Optional[Dict]:
"""Get a user by ID.
@@ -556,14 +563,15 @@ class DatabaseClient:
Returns:
User dict or None
"""
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"SELECT id, email, role, created_at FROM users WHERE id = %s",
(user_id,),
)
user = cursor.fetchone()
return dict(user) if user else None
self.connect()
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"SELECT id, email, role, created_at FROM users WHERE id = %s",
(user_id,),
)
user = cursor.fetchone()
return dict(user) if user else None
def get_user_by_email(self, email: str) -> Optional[Dict]:
"""Get a user by email.
@@ -574,14 +582,15 @@ class DatabaseClient:
Returns:
User dict or None
"""
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"SELECT id, email, role, created_at FROM users WHERE email = %s",
(email,),
)
user = cursor.fetchone()
return dict(user) if user else None
self.connect()
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"SELECT id, email, role, created_at FROM users WHERE email = %s",
(email,),
)
user = cursor.fetchone()
return dict(user) if user else None
def get_all_users(self, limit: int = 100, offset: int = 0) -> List[Dict]:
"""Get all users (admin only).
@@ -593,18 +602,19 @@ class DatabaseClient:
Returns:
List of user dicts
"""
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"""
SELECT id, email, role, created_at
FROM users
ORDER BY created_at DESC
LIMIT %s OFFSET %s
""",
(limit, offset),
)
return [dict(row) for row in cursor.fetchall()]
self.connect()
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"""
SELECT id, email, role, created_at
FROM users
ORDER BY created_at DESC
LIMIT %s OFFSET %s
""",
(limit, offset),
)
return [dict(row) for row in cursor.fetchall()]
def update_user_role(self, user_id: int, role: str) -> Optional[Dict]:
"""Update a user's role (admin only).
@@ -616,19 +626,20 @@ class DatabaseClient:
Returns:
Updated user dict or None
"""
with self.get_conn() as conn:
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"""
UPDATE users
SET role = %s, updated_at = CURRENT_TIMESTAMP
WHERE id = %s
RETURNING id, email, role, created_at
""",
(role, user_id),
)
user = cursor.fetchone()
conn.commit()
self.connect()
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
cursor.execute(
"""
UPDATE users
SET role = %s, updated_at = CURRENT_TIMESTAMP
WHERE id = %s
RETURNING id, email, role, created_at
""",
(role, user_id),
)
user = cursor.fetchone()
self.conn.commit()
return dict(user) if user else None
def delete_user(self, user_id: int) -> bool:
@@ -640,11 +651,12 @@ class DatabaseClient:
Returns:
True if deleted
"""
with self.get_conn() as conn:
with conn.cursor() as cursor:
cursor.execute("DELETE FROM users WHERE id = %s", (user_id,))
deleted = cursor.rowcount > 0
conn.commit()
self.connect()
with self.conn.cursor() as cursor:
cursor.execute("DELETE FROM users WHERE id = %s", (user_id,))
deleted = cursor.rowcount > 0
self.conn.commit()
return deleted
def get_user_count(self) -> int:
@@ -653,7 +665,8 @@ class DatabaseClient:
Returns:
Number of users
"""
with self.get_conn() as conn:
with conn.cursor() as cursor:
cursor.execute("SELECT COUNT(*) FROM users")
return cursor.fetchone()[0]
self.connect()
with self.conn.cursor() as cursor:
cursor.execute("SELECT COUNT(*) FROM users")
return cursor.fetchone()[0]
+8 -6
View File
@@ -3,15 +3,15 @@ services:
image: postgres:16-alpine
container_name: sparc-postgres
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: sparc
POSTGRES_USER: ${POSTGRES_USER}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
POSTGRES_DB: ${POSTGRES_DB}
ports:
- "5432:5432"
volumes:
- postgres_data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U postgres"]
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER}"]
interval: 5s
timeout: 5s
retries: 5
@@ -22,7 +22,7 @@ services:
container_name: sparc-init-db
command: python scripts/init_database.py
environment:
DATABASE_URL: postgresql://postgres:postgres@postgres:5432/sparc
DATABASE_URL: postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}
depends_on:
postgres:
condition: service_healthy
@@ -35,9 +35,11 @@ services:
environment:
API_KEY: ${API_KEY}
OPENROUTER_API_KEY: ${OPENROUTER_API_KEY}
DATABASE_URL: postgresql://postgres:postgres@postgres:5432/sparc
DATABASE_URL: postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}
USE_CACHE: "true"
JWT_SECRET: ${JWT_SECRET:-sparc-secret-key-change-in-production}
CORS_ORIGINS: ${CORS_ORIGINS:-}
APP_ENV: ${APP_ENV:-development}
ROOT_PATH: /api
ports:
- "8000:8000"
+116
View File
@@ -0,0 +1,116 @@
"""Tests for security hardening: JWT secret startup check, CORS config, credential handling."""
import os
from unittest.mock import patch
import pytest
class TestJWTSecretStartupCheck:
"""Test the startup guard that refuses default JWT secret in non-dev environments."""
def test_default_secret_in_production_raises(self):
"""Starting with default secret and APP_ENV=production must raise RuntimeError."""
with patch.dict(os.environ, {"APP_ENV": "production"}):
# Reload config to pick up the new APP_ENV
import importlib
import SPARC.config
importlib.reload(SPARC.config)
from SPARC.auth import _DEFAULT_JWT_SECRET, check_jwt_secret
# Patch JWT_SECRET to the default
with patch("SPARC.auth.JWT_SECRET", _DEFAULT_JWT_SECRET):
with pytest.raises(RuntimeError, match="FATAL.*JWT_SECRET"):
check_jwt_secret()
# Restore config
with patch.dict(os.environ, {"APP_ENV": "development"}):
importlib.reload(SPARC.config)
def test_default_secret_in_development_succeeds(self):
"""Starting with default secret and APP_ENV=development must not raise."""
with patch.dict(os.environ, {"APP_ENV": "development"}):
import importlib
import SPARC.config
importlib.reload(SPARC.config)
from SPARC.auth import _DEFAULT_JWT_SECRET, check_jwt_secret
with patch("SPARC.auth.JWT_SECRET", _DEFAULT_JWT_SECRET):
# Should not raise
check_jwt_secret()
# Restore
importlib.reload(SPARC.config)
def test_custom_secret_in_production_succeeds(self):
"""Starting with a custom secret in production must not raise."""
with patch.dict(os.environ, {"APP_ENV": "production"}):
import importlib
import SPARC.config
importlib.reload(SPARC.config)
from SPARC.auth import check_jwt_secret
with patch("SPARC.auth.JWT_SECRET", "my-secure-random-secret-abc123"):
# Should not raise
check_jwt_secret()
with patch.dict(os.environ, {"APP_ENV": "development"}):
importlib.reload(SPARC.config)
def test_default_secret_unset_env_succeeds(self):
"""When APP_ENV is unset (defaults to development), default secret is allowed."""
with patch.dict(os.environ, {}, clear=False):
# Remove APP_ENV if present
env = os.environ.copy()
env.pop("APP_ENV", None)
with patch.dict(os.environ, env, clear=True):
import importlib
import SPARC.config
importlib.reload(SPARC.config)
from SPARC.auth import _DEFAULT_JWT_SECRET, check_jwt_secret
with patch("SPARC.auth.JWT_SECRET", _DEFAULT_JWT_SECRET):
# Should not raise (defaults to development)
check_jwt_secret()
with patch.dict(os.environ, {"APP_ENV": "development"}):
importlib.reload(SPARC.config)
class TestCORSConfig:
"""Test that CORS origins are configurable via environment variable."""
def test_default_cors_origins(self):
"""When CORS_ORIGINS is unset, defaults to localhost origins."""
with patch.dict(os.environ, {"CORS_ORIGINS": ""}):
import importlib
import SPARC.config
importlib.reload(SPARC.config)
assert SPARC.config.cors_origins == [
"http://localhost:3000",
"http://localhost:5173",
]
def test_custom_cors_origins(self):
"""Setting CORS_ORIGINS configures allowed origins."""
with patch.dict(os.environ, {"CORS_ORIGINS": "https://sparc.example.com,https://app.example.com"}):
import importlib
import SPARC.config
importlib.reload(SPARC.config)
assert SPARC.config.cors_origins == [
"https://sparc.example.com",
"https://app.example.com",
]
# Restore
with patch.dict(os.environ, {"CORS_ORIGINS": ""}):
importlib.reload(SPARC.config)
def test_single_cors_origin(self):
"""A single origin without comma works correctly."""
with patch.dict(os.environ, {"CORS_ORIGINS": "https://sparc.example.com"}):
import importlib
import SPARC.config
importlib.reload(SPARC.config)
assert SPARC.config.cors_origins == ["https://sparc.example.com"]
with patch.dict(os.environ, {"CORS_ORIGINS": ""}):
importlib.reload(SPARC.config)