hold-slayer/models/call.py

"""
Call models — Active call state, requests, and responses.
"""

from datetime import datetime
from enum import Enum
from typing import Optional

from pydantic import BaseModel, Field


class CallStatus(str, Enum):
    """Call lifecycle states."""

    INITIATING = "initiating"
    RINGING = "ringing"
    CONNECTED = "connected"
    NAVIGATING_IVR = "navigating_ivr"
    ON_HOLD = "on_hold"
    HUMAN_DETECTED = "human_detected"
    TRANSFERRING = "transferring"
    BRIDGED = "bridged"  # User is connected to the remote party
    COMPLETED = "completed"
    FAILED = "failed"
    CANCELLED = "cancelled"


class CallMode(str, Enum):
    """How the call should be handled."""

    DIRECT = "direct"  # Call and connect immediately
    HOLD_SLAYER = "hold_slayer"  # Navigate IVR, wait on hold, transfer when human
    AI_ASSISTED = "ai_assisted"  # Connect with transcription, recording, noise cancel
    RECEPTIONIST = "receptionist"  # AI screens inbound caller, then routes or takes a message


class AudioClassification(str, Enum):
    """What kind of audio is currently playing."""

    SILENCE = "silence"
    MUSIC = "music"  # Hold music
    IVR_PROMPT = "ivr_prompt"  # Automated voice (TTS/recording)
    LIVE_HUMAN = "live_human"  # Real person talking
    RINGING = "ringing"  # Ring-back tone
    DTMF = "dtmf"  # Touch tones
    UNKNOWN = "unknown"


class ClassificationResult(BaseModel):
    """A single audio classification at a point in time."""

    timestamp: float  # Unix timestamp
    audio_type: AudioClassification
    confidence: float  # 0.0 - 1.0
    details: Optional[dict] = None  # Extra analysis data


class TranscriptEntry(BaseModel):
    """One transcribed utterance, offset from call start for seek."""

    t_offset_ms: int
    speaker: str = "unknown"  # caller / agent / receptionist / unknown
    text: str


class ActiveCall(BaseModel):
    """In-memory state for an active call."""

    id: str
    direction: str = "outbound"
    remote_number: str
    status: CallStatus = CallStatus.INITIATING
    mode: CallMode = CallMode.DIRECT
    intent: Optional[str] = None
    call_flow_id: Optional[str] = None
    device: Optional[str] = None
    started_at: datetime = Field(default_factory=datetime.now)
    connected_at: Optional[datetime] = None
    hold_started_at: Optional[datetime] = None
    current_classification: AudioClassification = AudioClassification.UNKNOWN
    classification_history: list[ClassificationResult] = Field(default_factory=list)
    transcript_chunks: list[TranscriptEntry] = Field(default_factory=list)
    current_step_id: Optional[str] = None  # Current position in call flow
    services: list[str] = Field(default_factory=list)  # Active services on this call

    @property
    def duration(self) -> int:
        """Total call duration in seconds."""
        if self.connected_at:
            return int((datetime.now() - self.connected_at).total_seconds())
        return 0

    @property
    def hold_time(self) -> int:
        """Time spent on hold in seconds."""
        if self.hold_started_at and self.status == CallStatus.ON_HOLD:
            return int((datetime.now() - self.hold_started_at).total_seconds())
        return 0

    @property
    def transcript(self) -> str:
        """Full transcript so far."""
        return "\n".join(e.text for e in self.transcript_chunks)

    def summary(self) -> dict:
        """Compact summary for list views."""
        return {
            "call_id": self.id,
            "remote_number": self.remote_number,
            "status": self.status.value,
            "mode": self.mode.value,
            "duration": self.duration,
            "hold_time": self.hold_time,
            "audio_type": self.current_classification.value,
            "intent": self.intent,
        }


# ============================================================
# API Request/Response Models
# ============================================================


class CallRequest(BaseModel):
    """Request to place an outbound call."""

    number: str  # E.164 format
    mode: CallMode = CallMode.DIRECT
    intent: Optional[str] = None  # What you need (for hold_slayer IVR navigation)
    device: Optional[str] = None  # Target device to ring / transfer to
    call_flow_id: Optional[str] = None  # Use a stored IVR tree
    services: list[str] = Field(
        default_factory=lambda: ["recording", "transcription"]
    )


class HoldSlayerRequest(BaseModel):
    """Request to launch the Hold Slayer."""

    number: str  # E.164 format
    intent: str  # "dispute a charge on my December statement"
    call_flow_id: Optional[str] = None  # Optional: use stored IVR tree
    transfer_to: Optional[str] = None  # Device to ring when human detected
    notify: list[str] = Field(default_factory=lambda: ["push"])  # Notification channels


class CallResponse(BaseModel):
    """Response after initiating a call."""

    call_id: str
    status: str
    number: str
    mode: str
    message: Optional[str] = None

    @classmethod
    def from_call(cls, call: "ActiveCall", message: Optional[str] = None) -> "CallResponse":
        return cls(
            call_id=call.id,
            status=call.status.value,
            number=call.remote_number,
            mode=call.mode.value,
            message=message,
        )


class CallStatusResponse(BaseModel):
    """Full status of an active or completed call."""

    call_id: str
    status: str
    direction: str
    remote_number: str
    mode: str
    duration: int
    hold_time: int
    audio_type: str
    intent: Optional[str] = None
    transcript_excerpt: Optional[str] = None  # Last N chars
    classification_history: list[ClassificationResult] = Field(default_factory=list)
    current_step: Optional[str] = None
    services: list[str] = Field(default_factory=list)

    @classmethod
    def from_call(cls, call: "ActiveCall") -> "CallStatusResponse":
        """The one ActiveCall → status-response mapping."""
        return cls(
            call_id=call.id,
            status=call.status.value,
            direction=call.direction,
            remote_number=call.remote_number,
            mode=call.mode.value,
            duration=call.duration,
            hold_time=call.hold_time,
            audio_type=call.current_classification.value,
            intent=call.intent,
            transcript_excerpt=call.transcript[-500:] if call.transcript else None,
            classification_history=call.classification_history[-20:],
            current_step=call.current_step_id,
            services=call.services,
        )


class TransferRequest(BaseModel):
    """Request to transfer a call to a device."""

    device: str  # Device ID or type