FabledGrimoire/src/fabledassistant/config.py

import os


def _read_secret(env_var: str, secret_file_var: str, default: str) -> str:
    """Read a config value from env var, or from a Docker secrets file."""
    value = os.environ.get(env_var)
    if value:
        return value
    secret_file = os.environ.get(secret_file_var)
    if secret_file:
        try:
            with open(secret_file) as f:
                return f.read().strip()
        except FileNotFoundError:
            pass
    return default


class Config:
    DATABASE_URL: str = _read_secret(
        "DATABASE_URL",
        "DATABASE_URL_FILE",
        "postgresql+asyncpg://fabled:fabled@localhost:5432/fabledassistant",
    )
    OLLAMA_URL: str = os.environ.get("OLLAMA_URL", "http://localhost:11434")
    OLLAMA_MODEL: str = os.environ.get("OLLAMA_MODEL", "qwen3:latest")
    # Lightweight model for background tasks (title generation, tag suggestions,
    # project summaries). Using a separate model keeps the
    # main model's KV cache intact between user messages, enabling prefix cache hits.
    OLLAMA_BACKGROUND_MODEL: str = os.environ.get("OLLAMA_BACKGROUND_MODEL", "gemma3:4b")
    # Ollama keep_alive — how long a model stays resident in VRAM after its last
    # request. Main model gets a longer window since it's used interactively;
    # the background model is called sporadically and doesn't need to camp VRAM.
    # Format matches Ollama's duration strings: "30m", "10m", "1h", "0s", "-1" (forever).
    OLLAMA_KEEP_ALIVE_MAIN: str = os.environ.get("OLLAMA_KEEP_ALIVE_MAIN", "30m")
    OLLAMA_KEEP_ALIVE_BACKGROUND: str = os.environ.get("OLLAMA_KEEP_ALIVE_BACKGROUND", "10m")
    # KV cache context window for generation. Keep this as small as practical —
    # a larger context forces more KV cache into CPU RAM, drastically slowing prefill.
    # 16384 covers ~30+ message conversations with our system prompt comfortably.
    OLLAMA_NUM_CTX: int = int(os.environ.get("OLLAMA_NUM_CTX", "16384"))
    SECRET_KEY: str = _read_secret("SECRET_KEY", "SECRET_KEY_FILE", "dev-secret-change-me")
    SECURE_COOKIES: bool = os.environ.get("SECURE_COOKIES", "").lower() in ("1", "true", "yes")
    LOG_LEVEL: str = os.environ.get("LOG_LEVEL", "INFO")
    LOG_RETENTION_DAYS: int = int(os.environ.get("LOG_RETENTION_DAYS", "90"))

    # Embedding model for semantic note search (served by Ollama)
    EMBEDDING_MODEL: str = os.environ.get("EMBEDDING_MODEL", "nomic-embed-text")

    # SMTP defaults (overridden by DB settings when configured via admin UI)
    SMTP_HOST: str = os.environ.get("SMTP_HOST", "")
    SMTP_PORT: int = int(os.environ.get("SMTP_PORT", "587"))
    SMTP_USERNAME: str = os.environ.get("SMTP_USERNAME", "")
    SMTP_PASSWORD: str = _read_secret("SMTP_PASSWORD", "SMTP_PASSWORD_FILE", "")
    SMTP_FROM_ADDRESS: str = os.environ.get("SMTP_FROM_ADDRESS", "")
    SMTP_FROM_NAME: str = os.environ.get("SMTP_FROM_NAME", "Fabled Scribe")
    SMTP_USE_TLS: bool = os.environ.get("SMTP_USE_TLS", "true").lower() in ("1", "true", "yes")
    BASE_URL: str = os.environ.get("BASE_URL", "http://localhost:5000").rstrip("/")
    TRUST_PROXY_HEADERS: bool = os.environ.get("TRUST_PROXY_HEADERS", "").lower() in ("1", "true", "yes")

    # OIDC / OAuth2 SSO (e.g. Authentik)
    OIDC_ISSUER: str = os.environ.get("OIDC_ISSUER", "")
    OIDC_CLIENT_ID: str = os.environ.get("OIDC_CLIENT_ID", "")
    OIDC_CLIENT_SECRET: str = _read_secret("OIDC_CLIENT_SECRET", "OIDC_CLIENT_SECRET_FILE", "")
    OIDC_SCOPES: str = os.environ.get("OIDC_SCOPES", "openid profile email")
    LOCAL_AUTH_ENABLED: bool = os.environ.get("LOCAL_AUTH_ENABLED", "true").lower() not in ("0", "false", "no")

    # SearXNG web search (external instance)
    SEARXNG_URL: str = os.environ.get("SEARXNG_URL", "")

    # Image cache — images fetched from the web are stored here and served locally
    IMAGE_CACHE_DIR: str = os.environ.get("IMAGE_CACHE_DIR", "/data/images")
    # Maximum size of a single image to cache (default 5 MB)
    IMAGE_MAX_BYTES: int = int(os.environ.get("IMAGE_MAX_BYTES", str(5 * 1024 * 1024)))

    # VAPID keys for browser push notifications
    VAPID_PRIVATE_KEY: str = os.environ.get("VAPID_PRIVATE_KEY", "")
    VAPID_PUBLIC_KEY: str = os.environ.get("VAPID_PUBLIC_KEY", "")
    VAPID_CLAIMS_SUB: str = os.environ.get("VAPID_CLAIMS_SUB", "mailto:admin@fabledassistant.local")

    # Voice (Speech-to-Speech) feature
    VOICE_ENABLED: bool = os.environ.get("VOICE_ENABLED", "").lower() in ("1", "true", "yes")
    STT_BACKEND: str = os.environ.get("STT_BACKEND", "faster-whisper")
    STT_MODEL: str = os.environ.get("STT_MODEL", "base.en")
    TTS_BACKEND: str = os.environ.get("TTS_BACKEND", "kokoro")

    @classmethod
    def oidc_enabled(cls) -> bool:
        return bool(cls.OIDC_ISSUER and cls.OIDC_CLIENT_ID and cls.OIDC_CLIENT_SECRET)

    @classmethod
    def searxng_enabled(cls) -> bool:
        return bool(cls.SEARXNG_URL)

    @classmethod
    def validate(cls) -> None:
        """Validate critical config values at startup. Raises ValueError on misconfiguration."""
        errors: list[str] = []
        if cls.OLLAMA_NUM_CTX < 512:
            errors.append(f"OLLAMA_NUM_CTX={cls.OLLAMA_NUM_CTX} is too small (minimum 512)")
        if cls.LOG_RETENTION_DAYS < 1:
            errors.append(f"LOG_RETENTION_DAYS={cls.LOG_RETENTION_DAYS} must be >= 1")
        if cls.IMAGE_MAX_BYTES < 1024:
            errors.append(f"IMAGE_MAX_BYTES={cls.IMAGE_MAX_BYTES} must be >= 1024")
        if not (1 <= cls.SMTP_PORT <= 65535):
            errors.append(f"SMTP_PORT={cls.SMTP_PORT} must be between 1 and 65535")
        if cls.oidc_enabled() and not cls.BASE_URL.startswith(("http://", "https://")):
            errors.append(f"BASE_URL='{cls.BASE_URL}' must start with http:// or https:// when OIDC is enabled")
        if cls.SECRET_KEY == "dev-secret-change-me" and cls.SECURE_COOKIES:
            errors.append(
                "SECRET_KEY is set to the insecure default but SECURE_COOKIES=true indicates "
                "a production deployment. Set SECRET_KEY or SECRET_KEY_FILE before starting."
            )
        _valid_stt_models = {"tiny.en", "base.en", "small.en", "medium.en"}
        if cls.VOICE_ENABLED and cls.STT_MODEL not in _valid_stt_models:
            errors.append(
                f"STT_MODEL='{cls.STT_MODEL}' is not supported. "
                f"Valid values: {', '.join(sorted(_valid_stt_models))}"
            )
        if errors:
            raise ValueError("Configuration errors:\n" + "\n".join(f"  - {e}" for e in errors))