Add secure admin AI provider configuration
CI / compose (push) Successful in 12m11s

This commit is contained in:
Marco0300
2026-09-03 21:15:42 +02:00
parent d07dc77ca1
commit 7a010fe865
6 changed files with 254 additions and 7 deletions
+20
View File
@@ -10,6 +10,7 @@ from __future__ import annotations
import json
import os
import re
import sqlite3
from urllib.parse import urlparse
from urllib.request import Request, urlopen
@@ -43,7 +44,26 @@ def _safe_endpoint(value: str, allowed: set[str]) -> str:
return value.rstrip("/")
_DB_PATH = ""
_DB_ORG = "demo-tenant"
def configure_db(path: str, organization_id: str = "demo-tenant") -> None:
global _DB_PATH, _DB_ORG
_DB_PATH, _DB_ORG = path, organization_id
def _config():
if _DB_PATH:
try:
db = sqlite3.connect(_DB_PATH); db.row_factory = sqlite3.Row
row = db.execute("SELECT * FROM ai_remote_provider_configs WHERE organization_id=?", (_DB_ORG,)).fetchone(); db.close()
if row:
from .provider_config import decrypt
credentials = json.loads(decrypt(row["credentials_ciphertext"])) if row["credentials_ciphertext"] else {}
return {"provider": row["provider"], "model": row["model"], "nous_url": row["nous_base_url"], "nous_allowed": {urlparse(row["nous_base_url"]).hostname}, "nous_key": credentials.get("nous_api_key", ""), "firecrawl_url": row["firecrawl_base_url"], "firecrawl_allowed": {urlparse(row["firecrawl_base_url"]).hostname}, "firecrawl_key": credentials.get("firecrawl_api_key", "")}
except Exception:
return {"provider": "", "model": "", "endpoint": "", "allowed": set(), "api_key": ""}
provider = os.environ.get("AI_RESEARCH_PROVIDER", "").strip().lower()
# Nous uses its conventional key directly; no gateway or key translation is needed.
nous_key = os.environ.get("NOUS_API_KEY", "").strip()
+40 -2
View File
@@ -15,9 +15,10 @@ if __package__ in (None, ""):
from app.scoring import DEFAULT_RULES, signals_for_business, evaluate_score, SCORE_VERSION
from app.ai_assistance import generate as generate_ai, input_fingerprint, provider_status, MAX_INPUT_ITEMS, MAX_OUTPUT_CHARS
from app.discovery import discover as scoped_discover
from app.ai_research import provider_status as ai_research_provider_status, validate_criteria as validate_ai_research_criteria, AIResearchConfigError
from app.ai_research import provider_status as ai_research_provider_status, configure_db as configure_ai_research_db, validate_criteria as validate_ai_research_criteria, AIResearchConfigError
from app.search_provider import provider_status as search_provider_status
from app.config import load_config
from app.provider_config import validate_payload as validate_remote_provider, encrypt as encrypt_provider_secret, decrypt as decrypt_provider_secret, safe_status as remote_provider_status, test_connectivity as test_remote_connectivity
else:
from .domain import deduplication_key, deduplicate_businesses, is_suppressed, normalize_business, score_business, normalize_domain, normalize_phone, match_businesses
from .sources import adapter_for, contains_secret
@@ -27,9 +28,10 @@ else:
from .scoring import DEFAULT_RULES, signals_for_business, evaluate_score, SCORE_VERSION
from .ai_assistance import generate as generate_ai, input_fingerprint, provider_status, MAX_INPUT_ITEMS, MAX_OUTPUT_CHARS
from .discovery import discover as scoped_discover
from .ai_research import provider_status as ai_research_provider_status, validate_criteria as validate_ai_research_criteria, AIResearchConfigError
from .ai_research import provider_status as ai_research_provider_status, configure_db as configure_ai_research_db, validate_criteria as validate_ai_research_criteria, AIResearchConfigError
from .search_provider import provider_status as search_provider_status
from .config import load_config
from .provider_config import validate_payload as validate_remote_provider, encrypt as encrypt_provider_secret, decrypt as decrypt_provider_secret, safe_status as remote_provider_status, test_connectivity as test_remote_connectivity
ORGANIZATION_ID = "demo-tenant"
SCHEMA = Path(__file__).resolve().parents[1] / "schema.sql"
SESSION_DAYS = 7
@@ -476,7 +478,39 @@ class ApiHandler(BaseHTTPRequestHandler):
reasons.append("network_send_disabled"); self.audit(db, user, "outreach_draft.send_blocked", f"{did}:network_send_disabled"); db.commit()
return self.send_json(409, {"status": "blocked", "blocked_reasons": reasons, "network_send": False, "id": did})
def remote_ai_provider_config(self, db, user, payload=None, connectivity=False):
org = user["organization_id"]
row = db.execute("SELECT * FROM ai_remote_provider_configs WHERE organization_id=?", (org,)).fetchone()
if connectivity:
if user["role"] not in {"owner", "admin"}:
return self.send_json(403, {"error": "forbidden"})
return self.send_json(200, test_remote_connectivity(row))
if payload is not None:
if user["role"] not in {"owner", "admin"}:
return self.send_json(403, {"error": "forbidden"})
try:
config = validate_remote_provider(payload)
credentials = dict(config["credentials"])
if row:
try: old = json.loads(decrypt_provider_secret(row["credentials_ciphertext"])) if row["credentials_ciphertext"] else {}
except Exception: old = {}
for name in ("nous_api_key", "firecrawl_api_key"):
if name not in credentials and name in old: credentials[name] = old[name]
if config["enabled"] and any(name not in credentials for name in ("nous_api_key", "firecrawl_api_key")):
return self.send_json(400, {"error": "provider_credentials_required"})
ciphertext = encrypt_provider_secret(json.dumps(credentials, sort_keys=True)) if credentials else ""
fingerprint = hashlib.sha256(json.dumps(credentials, sort_keys=True).encode()).hexdigest() if credentials else ""
except (ValueError, TypeError, RuntimeError) as exc:
return self.send_json(400, {"error": str(exc)})
db.execute("INSERT INTO ai_remote_provider_configs(organization_id,provider,model,enabled,nous_base_url,firecrawl_base_url,credentials_ciphertext,credentials_fingerprint) VALUES(?,?,?,?,?,?,?,?) ON CONFLICT(organization_id) DO UPDATE SET provider=excluded.provider,model=excluded.model,enabled=excluded.enabled,nous_base_url=excluded.nous_base_url,firecrawl_base_url=excluded.firecrawl_base_url,credentials_ciphertext=excluded.credentials_ciphertext,credentials_fingerprint=excluded.credentials_fingerprint,updated_at=CURRENT_TIMESTAMP", (org, config["provider"], config["model"], int(config["enabled"]), config["nous_base_url"], config["firecrawl_base_url"], ciphertext, fingerprint))
self.audit(db, user, "ai.remote_provider.updated", config["provider"]); db.commit()
row = db.execute("SELECT * FROM ai_remote_provider_configs WHERE organization_id=?", (org,)).fetchone()
return self.send_json(200, dict(remote_provider_status(row), organization_id=org))
def ai_provider_config(self, db, user, payload=None):
remote = db.execute("SELECT * FROM ai_remote_provider_configs WHERE organization_id=?", (user["organization_id"],)).fetchone()
if remote or (payload and str(payload.get("provider", "")).lower() in {"nous_portal", "nous_portal_web_research"}):
return self.remote_ai_provider_config(db, user, payload)
org = user["organization_id"]
row = db.execute("SELECT * FROM ai_provider_configs WHERE organization_id=?", (org,)).fetchone()
if payload is not None:
@@ -613,6 +647,7 @@ class ApiHandler(BaseHTTPRequestHandler):
if path=="/api/v1/suppressions": return self.list_suppressions(db,org,parse_qs(parsed.query))
if path=="/api/v1/ai-runs": return self.list_ai_runs(db,user,parse_qs(parsed.query))
if path=="/api/v1/ai/provider-config": return self.ai_provider_config(db,user)
if path=="/api/v1/admin/ai-provider-config": return self.remote_ai_provider_config(db,user)
if path=="/api/v1/outreach/drafts": return self.list_outreach_drafts(db,user,parse_qs(parsed.query))
if path=="/api/v1/outreach/provider-config": return self.provider_config(db,user)
if path in ("/api/v1/reports/pipeline","/api/v1/reports/outcomes","/api/v1/reports/activity"): return self.report(db,org,path.rsplit('/',1)[1],parse_qs(parsed.query))
@@ -1029,6 +1064,8 @@ class ApiHandler(BaseHTTPRequestHandler):
if path=="/api/v1/saved-filters": return self.save_filter(payload,db,user)
if path=="/api/v1/outreach/provider-config": return self.provider_config(db,user,payload)
if path=="/api/v1/ai/provider-config": return self.ai_provider_config(db,user,payload)
if path=="/api/v1/admin/ai-provider-config": return self.remote_ai_provider_config(db,user,payload)
if path=="/api/v1/admin/ai-provider-config/test": return self.remote_ai_provider_config(db,user,connectivity=True)
if path=="/api/v1/businesses/bulk-review": return self.bulk_review(payload,db,user)
bits_ai=path.split("/")
if len(bits_ai)==7 and bits_ai[:4]==["","api","v1","businesses"] and bits_ai[5]=="ai" and bits_ai[6]=="suggest": return self.suggest_ai(int(bits_ai[4]) if bits_ai[4].isdigit() else -1,payload,db,user)
@@ -1440,6 +1477,7 @@ def _job_worker(server):
def create_server(host="127.0.0.1",port=8000,db_path="prospects.db"):
load_config()
configure_ai_research_db(db_path)
server=ThreadingHTTPServer((host,port),ApiHandler);server.db_path=db_path;connect(db_path).close();server.job_stop=threading.Event();server.job_wakeup=threading.Event();server.job_thread=threading.Thread(target=_job_worker,args=(server,),daemon=True);server.job_thread.start()
original_close=server.server_close
def close():
+129
View File
@@ -0,0 +1,129 @@
"""Encrypted, tenant-scoped AI provider configuration storage.
The key is generated under the private data volume and is never stored in SQLite.
The small authenticated stream construction here uses HMAC-SHA256 for the
keystream and integrity tag; ciphertext is prefixed with ``pc1`` and never
returned by the API.
"""
from __future__ import annotations
import base64
import hashlib
import hmac
import json
import os
import secrets
from pathlib import Path
from urllib.parse import urlparse
from urllib.request import Request, urlopen
MAX_SECRET = 4096
MAX_MODEL = 160
ALLOWED_PROVIDERS = {"nous_portal", "nous_portal_web_research"}
DEFAULT_NOUS_URL = "https://inference-api.nousresearch.com/v1"
DEFAULT_FIRECRAWL_URL = "https://api.firecrawl.dev/v1"
def key_path() -> Path:
return Path(os.environ.get("PROVIDER_CONFIG_KEY_FILE", "/data/provider-config.key")).expanduser()
def _key() -> bytes:
path = key_path()
path.parent.mkdir(parents=True, exist_ok=True)
if path.exists():
key = path.read_bytes()
if len(key) != 32:
raise RuntimeError("invalid_provider_config_key")
return key
key = secrets.token_bytes(32)
flags = os.O_CREAT | os.O_EXCL | os.O_WRONLY
fd = os.open(path, flags, 0o600)
try:
os.write(fd, key)
finally:
os.close(fd)
os.chmod(path, 0o600)
return key
def _stream(key: bytes, nonce: bytes, size: int) -> bytes:
return b"".join(hmac.new(key, nonce + i.to_bytes(8, "big"), hashlib.sha256).digest() for i in range((size + 31) // 32))[:size]
def encrypt(value: str) -> str:
raw = value.encode("utf-8")
nonce = secrets.token_bytes(16)
cipher = bytes(a ^ b for a, b in zip(raw, _stream(_key(), nonce, len(raw))))
tag = hmac.new(_key(), nonce + cipher, hashlib.sha256).digest()
return "pc1:" + base64.urlsafe_b64encode(nonce + tag + cipher).decode("ascii")
def decrypt(value: str) -> str:
if not isinstance(value, str) or not value.startswith("pc1:"):
raise ValueError("invalid_ciphertext")
raw = base64.urlsafe_b64decode(value[4:].encode("ascii"))
nonce, tag, cipher = raw[:16], raw[16:48], raw[48:]
key = _key()
if not hmac.compare_digest(tag, hmac.new(key, nonce + cipher, hashlib.sha256).digest()):
raise ValueError("invalid_ciphertext")
return bytes(a ^ b for a, b in zip(cipher, _stream(key, nonce, len(cipher)))).decode("utf-8")
def validate_payload(payload: dict) -> dict:
if not isinstance(payload, dict):
raise ValueError("invalid_config")
provider = str(payload.get("provider", "nous_portal")).strip().lower()
if provider not in ALLOWED_PROVIDERS:
raise ValueError("invalid_provider")
model = str(payload.get("model", "Hermes-4-405B")).strip()
if not model or len(model) > MAX_MODEL:
raise ValueError("invalid_model")
enabled = payload.get("enabled", True)
if not isinstance(enabled, bool):
raise ValueError("invalid_enabled")
urls = {"nous_base_url": DEFAULT_NOUS_URL, "firecrawl_base_url": DEFAULT_FIRECRAWL_URL}
for field, default in urls.items():
value = str(payload.get(field, default)).strip().rstrip("/")
parsed = urlparse(value)
if parsed.scheme != "https" or not parsed.hostname or parsed.username or parsed.password or parsed.fragment or parsed.query:
raise ValueError("unsafe_provider_url")
urls[field] = value
credentials = payload.get("credentials", {})
if not isinstance(credentials, dict):
raise ValueError("invalid_credentials")
result = {"provider": provider, "model": model, "enabled": enabled, **urls, "credentials": {}}
for name in ("nous_api_key", "firecrawl_api_key"):
if name in credentials:
value = credentials[name]
if not isinstance(value, str) or not value or len(value) > MAX_SECRET:
raise ValueError("invalid_secret")
result["credentials"][name] = value
return result
def safe_status(row, *, env_bootstrap=False) -> dict:
if not row:
return {"provider": "", "status": "not_configured", "configured": False, "enabled": False, "network_enabled": False, "outbound_calls": False, "source": "env_bootstrap" if env_bootstrap else "none"}
return {"provider": row["provider"], "model": row["model"], "enabled": bool(row["enabled"]), "configured": bool(row["credentials_ciphertext"]), "status": "ready" if row["enabled"] and row["credentials_ciphertext"] else "disabled", "network_enabled": bool(row["enabled"] and row["credentials_ciphertext"]), "outbound_calls": bool(row["enabled"] and row["credentials_ciphertext"]), "source": "database", "nous_host": urlparse(row["nous_base_url"]).hostname, "firecrawl_host": urlparse(row["firecrawl_base_url"]).hostname, "updated_at": row["updated_at"]}
def test_connectivity(row) -> dict:
"""Make only bounded GET requests to fixed configured HTTPS hosts."""
if not row or not row["enabled"] or not row["credentials_ciphertext"]:
return {"status": "not_configured", "network_calls": 0, "outbound_calls": False}
credentials = json.loads(decrypt(row["credentials_ciphertext"]))
checks = []
for label, url, key_name in (("nous", row["nous_base_url"] + "/models", "nous_api_key"), ("firecrawl", row["firecrawl_base_url"], "firecrawl_api_key")):
key = credentials.get(key_name)
if not isinstance(key, str) or not key:
checks.append({"provider": label, "ok": False})
continue
request = Request(url, headers={"Accept": "application/json", "Authorization": "Bearer " + key}, method="GET")
try:
with urlopen(request, timeout=3) as response:
response.read(8193)
checks.append({"provider": label, "ok": 200 <= response.status < 500})
except Exception:
checks.append({"provider": label, "ok": False})
return {"status": "ready" if all(x["ok"] for x in checks) else "unavailable", "network_calls": len(checks), "outbound_calls": False, "checks": checks}