hold-slayer/config.py

"""
Hold Slayer Gateway — Configuration

All settings loaded from environment variables / .env file.
"""

from pydantic import Field, SecretStr
from pydantic_settings import BaseSettings, SettingsConfigDict


class SIPTrunkSettings(BaseSettings):
    """SIP trunk provider configuration."""

    model_config = SettingsConfigDict(env_prefix="SIP_TRUNK_", env_file=".env", extra="ignore")

    host: str = "sip.provider.com"
    port: int = 5060
    username: str = ""
    password: SecretStr = SecretStr("")
    transport: str = "udp"  # udp, tcp, tls
    did: str = ""  # Your phone number (E.164)


class GatewaySIPSettings(BaseSettings):
    """Gateway SIP listener for device registration."""

    model_config = SettingsConfigDict(env_prefix="GATEWAY_SIP_", env_file=".env", extra="ignore")

    host: str = "0.0.0.0"
    port: int = 5060
    domain: str = "gateway.local"


class SpeachesSettings(BaseSettings):
    """Speaches STT service configuration."""

    model_config = SettingsConfigDict(env_prefix="SPEACHES_", env_file=".env", extra="ignore")

    url: str = "http://localhost:22070"
    model: str = "whisper-large-v3"


class ClassifierSettings(BaseSettings):
    """Audio classifier thresholds."""

    model_config = SettingsConfigDict(env_prefix="CLASSIFIER_", env_file=".env", extra="ignore")

    music_threshold: float = 0.7
    speech_threshold: float = 0.6
    silence_threshold: float = 0.85
    window_seconds: float = 3.0


class LLMSettings(BaseSettings):
    """LLM service configuration (OpenAI-compatible API)."""

    model_config = SettingsConfigDict(env_prefix="LLM_", env_file=".env", extra="ignore")

    base_url: str = "http://localhost:11434/v1"
    model: str = "llama3"
    api_key: SecretStr = SecretStr("not-needed")
    timeout: float = 30.0
    max_tokens: int = 1024
    temperature: float = 0.3


class HoldSlayerSettings(BaseSettings):
    """Hold Slayer behavior settings."""

    model_config = SettingsConfigDict(env_prefix="HOLD_SLAYER_", env_prefix_allow_empty=True, env_file=".env", extra="ignore")

    default_transfer_device: str = Field(
        default="sip_phone", validation_alias="DEFAULT_TRANSFER_DEVICE"
    )
    max_hold_time: int = Field(default=7200, validation_alias="MAX_HOLD_TIME")
    hold_check_interval: float = Field(default=2.0, validation_alias="HOLD_CHECK_INTERVAL")


class TTSSettings(BaseSettings):
    """Rhema TTS service configuration (OpenAI-compatible /v1/audio/speech)."""

    model_config = SettingsConfigDict(env_prefix="TTS_", env_file=".env", extra="ignore")

    base_url: str = "http://localhost:8000"
    model: str = "speaches-ai/Kokoro-82M-v1.0-ONNX"
    voice: str = "af_heart"
    api_key: SecretStr = SecretStr("")
    timeout: float = 30.0
    sample_rate: int = 16000


class CasdoorSettings(BaseSettings):
    """Casdoor SSO (OIDC) configuration.

    When `enabled` is true the browser authenticates via Casdoor and every
    surface is gated to the owner; the SDK is used only for the OAuth2 code
    exchange in the /auth/callback route (JWTs are validated against the
    endpoint's JWKS). When false, the app runs in dev-owner mode (loopback only).
    """

    model_config = SettingsConfigDict(env_prefix="CASDOOR_", env_file=".env", extra="ignore")

    enabled: bool = False
    endpoint: str = "https://id.ouranos.helu.ca"
    client_id: str = ""
    client_secret: SecretStr = SecretStr("")
    org_name: str = "heluca"
    app_name: str = ""


class ReceptionistSettings(BaseSettings):
    """AI Receptionist behavior settings."""

    model_config = SettingsConfigDict(env_prefix="RECEPTIONIST_", env_file=".env", extra="ignore")

    enabled: bool = True
    greeting_template: str = (
        "Hi, you've reached Robert's line. Who's calling, and what's this about?"
    )
    message_prompt: str = "Please leave your message after the tone."
    listen_timeout_s: float = 15.0
    end_of_utterance_silence_s: float = 1.2
    message_max_seconds: int = 90
    llm_persona: str = (
        "You are a helpful, concise phone receptionist. Decide whether to ring "
        "the owner, take a message, or politely decline."
    )


class Settings(BaseSettings):
    """Root application settings."""

    model_config = SettingsConfigDict(
        env_file=".env",
        env_file_encoding="utf-8",
        extra="ignore",
    )

    # Database — no default credentials; must be set in the environment
    database_url: str = ""

    # Server
    host: str = "0.0.0.0"
    port: int = 8000
    debug: bool = False
    log_level: str = "info"

    # Log rendering: "text" (human-readable, for a terminal) or "json" (one
    # object per line, for Loki). Text is the default so local dev is readable;
    # the container sets LOG_FORMAT=json. See core/logging_config.py.
    log_format: str = "text"

    # Auth — Casdoor SSO for the browser + owner-minted PATs for MCP/CLI,
    # gated to a single owner. `owner_name` is the Casdoor username that owns
    # this gateway (everyone else gets 403). `public_base_url` seeds the OAuth
    # discovery URLs; blank derives them from request headers. Both cross-cut
    # every surface, so they live on the root model (like DATABASE_URL); the
    # Casdoor connection knobs live under the CASDOOR_ prefix.
    owner_name: str = ""
    public_base_url: str = ""

    # Outbound-call safety cap (REST + MCP make_call)
    max_concurrent_calls: int = 4

    # Explicit engine mode — the mock engine must be asked for. An
    # unconfigured trunk without this flag fails startup instead of
    # silently degrading to a gateway that can't place real calls.
    use_mock_sip: bool = False

    # SIP stack: "sippy" (signalling only — the classifier gets no audio) or
    # "pjsua2" (call control + media, the only path where audio reaches the
    # classifier). Opt-in while the PJSUA2 engine is proven against the lab;
    # see docs/architecture.md → "Media plane: why PJSUA2 places the call".
    sip_engine: str = "sippy"

    # Notifications
    notify_sms_number: str = ""

    # Sub-configs
    sip_trunk: SIPTrunkSettings = Field(default_factory=SIPTrunkSettings)
    gateway_sip: GatewaySIPSettings = Field(default_factory=GatewaySIPSettings)
    speaches: SpeachesSettings = Field(default_factory=SpeachesSettings)
    classifier: ClassifierSettings = Field(default_factory=ClassifierSettings)
    llm: LLMSettings = Field(default_factory=LLMSettings)
    hold_slayer: HoldSlayerSettings = Field(default_factory=HoldSlayerSettings)
    tts: TTSSettings = Field(default_factory=TTSSettings)
    receptionist: ReceptionistSettings = Field(default_factory=ReceptionistSettings)
    casdoor: CasdoorSettings = Field(default_factory=CasdoorSettings)


# Singleton
_settings: Settings | None = None


def get_settings() -> Settings:
    """Get cached application settings."""
    global _settings
    if _settings is None:
        _settings = Settings()
    return _settings