MarketingTool/apps/api/app/provider_config.py

"""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/v2"
DEFAULT_SEARXNG_URL = "http://searxng:8080"


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": str(payload.get("searxng_base_url", DEFAULT_SEARXNG_URL)).strip() or DEFAULT_SEARXNG_URL}
    for field, default in urls.items():
        value = str(payload.get(field, default)).strip().rstrip("/")
        parsed = urlparse(value)
        if (parsed.scheme != "https" and not (field == "firecrawl_base_url" and parsed.scheme == "http" and parsed.hostname == "searxng")) 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}