122 lines
4.0 KiB
Python
122 lines
4.0 KiB
Python
"""Base interface adapter for multi-modal interaction."""
|
|
|
|
from abc import ABC, abstractmethod
|
|
from enum import Enum
|
|
from typing import Any, AsyncIterator
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from fusionagi._time import utc_now_iso
|
|
|
|
|
|
class ModalityType(str, Enum):
|
|
"""Types of sensory modalities supported."""
|
|
|
|
TEXT = "text"
|
|
VOICE = "voice"
|
|
VISUAL = "visual"
|
|
HAPTIC = "haptic"
|
|
GESTURE = "gesture"
|
|
BIOMETRIC = "biometric"
|
|
|
|
|
|
class InterfaceMessage(BaseModel):
|
|
"""Message exchanged through an interface."""
|
|
|
|
id: str = Field(description="Unique message identifier")
|
|
modality: ModalityType = Field(description="Sensory modality of this message")
|
|
content: Any = Field(description="Message content (modality-specific)")
|
|
metadata: dict[str, Any] = Field(default_factory=dict, description="Additional metadata")
|
|
timestamp: str = Field(
|
|
default_factory=utc_now_iso,
|
|
description="Message timestamp"
|
|
)
|
|
user_id: str | None = Field(default=None, description="User identifier if applicable")
|
|
session_id: str | None = Field(default=None, description="Session identifier")
|
|
|
|
|
|
class InterfaceCapabilities(BaseModel):
|
|
"""Capabilities of an interface adapter."""
|
|
|
|
supported_modalities: list[ModalityType] = Field(description="Supported sensory modalities")
|
|
supports_streaming: bool = Field(default=False, description="Supports streaming responses")
|
|
supports_interruption: bool = Field(default=False, description="Supports mid-response interruption")
|
|
supports_multimodal: bool = Field(default=False, description="Supports multiple modalities simultaneously")
|
|
latency_ms: float | None = Field(default=None, description="Expected latency in milliseconds")
|
|
max_concurrent_sessions: int | None = Field(default=None, description="Max concurrent sessions")
|
|
|
|
|
|
class InterfaceAdapter(ABC):
|
|
"""
|
|
Abstract base for interface adapters.
|
|
|
|
Interface adapters translate between human sensory modalities and FusionAGI's
|
|
internal message format. Each adapter handles one or more modalities (voice,
|
|
visual, haptic, etc.).
|
|
"""
|
|
|
|
def __init__(self, name: str) -> None:
|
|
self.name = name
|
|
|
|
@abstractmethod
|
|
def capabilities(self) -> InterfaceCapabilities:
|
|
"""Return the capabilities of this interface."""
|
|
...
|
|
|
|
@abstractmethod
|
|
async def send(self, message: InterfaceMessage) -> None:
|
|
"""
|
|
Send a message through this interface to the user.
|
|
|
|
Args:
|
|
message: Message to send (modality-specific content).
|
|
"""
|
|
...
|
|
|
|
@abstractmethod
|
|
async def receive(self, timeout_seconds: float | None = None) -> InterfaceMessage | None:
|
|
"""
|
|
Receive a message from the user through this interface.
|
|
|
|
Args:
|
|
timeout_seconds: Optional timeout for receiving.
|
|
|
|
Returns:
|
|
Received message or None if timeout.
|
|
"""
|
|
...
|
|
|
|
async def stream_send(self, messages: AsyncIterator[InterfaceMessage]) -> None:
|
|
"""
|
|
Stream messages to the user (for streaming responses).
|
|
|
|
Default implementation sends each message individually. Override for
|
|
true streaming support.
|
|
|
|
Args:
|
|
messages: Async iterator of messages to stream.
|
|
"""
|
|
async for msg in messages:
|
|
await self.send(msg)
|
|
|
|
async def initialize(self) -> None:
|
|
"""Initialize the interface (connect, authenticate, etc.)."""
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
"""Shutdown the interface gracefully."""
|
|
pass
|
|
|
|
def validate_message(self, message: InterfaceMessage) -> bool:
|
|
"""
|
|
Validate that a message is compatible with this interface.
|
|
|
|
Args:
|
|
message: Message to validate.
|
|
|
|
Returns:
|
|
True if valid, False otherwise.
|
|
"""
|
|
caps = self.capabilities()
|
|
return message.modality in caps.supported_modalities
|