mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-25 14:53:34 +00:00
Adds speech-to-text support so WASM channels can emit audio attachments that get automatically transcribed before reaching the agent. Telegram voice notes are the first integration — downloaded via Bot API and transcribed via OpenAI Whisper. - Extend WIT with attachment-kind, attachment records on emitted-message - Add Attachment/AttachmentKind types to channel.rs and IncomingMessage - Add TranscriptionProvider trait, AudioFormat enum, TranscriptionMiddleware - Implement OpenAI Whisper provider (multipart POST, 25MB limit) - Add TranscriptionConfig + TranscriptionSettings with env var overrides - Parse Telegram voice messages, download via getFile, emit as attachments - Apply transcription in both process/dispatch emitted message paths - Graceful degradation: download failures show "[Voice note: download failed]" - Validate attachment sizes (10MB max), drop oversized without losing message Co-Authored-By: Claude Opus 4.6 <[email protected]>
241 lines
6.9 KiB
Rust
241 lines
6.9 KiB
Rust
//! Channel trait and message types.
|
|
|
|
use std::pin::Pin;
|
|
|
|
use async_trait::async_trait;
|
|
use chrono::{DateTime, Utc};
|
|
use futures::Stream;
|
|
use uuid::Uuid;
|
|
|
|
use crate::error::ChannelError;
|
|
|
|
/// Kind of attachment carried on an incoming message.
|
|
#[derive(Debug, Clone, PartialEq, Eq)]
|
|
pub enum AttachmentKind {
|
|
/// Audio content (voice notes, audio files).
|
|
Audio,
|
|
/// Image content (photos, screenshots).
|
|
Image,
|
|
/// Document content (PDFs, files).
|
|
Document,
|
|
}
|
|
|
|
/// Binary attachment on a message (e.g., voice note, photo).
|
|
#[derive(Debug, Clone)]
|
|
pub struct Attachment {
|
|
/// What kind of content this is.
|
|
pub kind: AttachmentKind,
|
|
/// MIME type (e.g., "audio/ogg", "image/jpeg").
|
|
pub mime_type: String,
|
|
/// Raw bytes of the attachment.
|
|
pub data: Vec<u8>,
|
|
/// Optional filename.
|
|
pub filename: Option<String>,
|
|
/// Duration in seconds (for audio/video).
|
|
pub duration_secs: Option<u32>,
|
|
}
|
|
|
|
/// A message received from an external channel.
|
|
#[derive(Debug, Clone)]
|
|
pub struct IncomingMessage {
|
|
/// Unique message ID.
|
|
pub id: Uuid,
|
|
/// Channel this message came from.
|
|
pub channel: String,
|
|
/// User identifier within the channel.
|
|
pub user_id: String,
|
|
/// Optional display name.
|
|
pub user_name: Option<String>,
|
|
/// Message content.
|
|
pub content: String,
|
|
/// Thread/conversation ID for threaded conversations.
|
|
pub thread_id: Option<String>,
|
|
/// When the message was received.
|
|
pub received_at: DateTime<Utc>,
|
|
/// Channel-specific metadata.
|
|
pub metadata: serde_json::Value,
|
|
/// Binary attachments (voice notes, images, etc.).
|
|
pub attachments: Vec<Attachment>,
|
|
}
|
|
|
|
impl IncomingMessage {
|
|
/// Create a new incoming message.
|
|
pub fn new(
|
|
channel: impl Into<String>,
|
|
user_id: impl Into<String>,
|
|
content: impl Into<String>,
|
|
) -> Self {
|
|
Self {
|
|
id: Uuid::new_v4(),
|
|
channel: channel.into(),
|
|
user_id: user_id.into(),
|
|
user_name: None,
|
|
content: content.into(),
|
|
thread_id: None,
|
|
received_at: Utc::now(),
|
|
metadata: serde_json::Value::Null,
|
|
attachments: Vec::new(),
|
|
}
|
|
}
|
|
|
|
/// Set the thread ID.
|
|
pub fn with_thread(mut self, thread_id: impl Into<String>) -> Self {
|
|
self.thread_id = Some(thread_id.into());
|
|
self
|
|
}
|
|
|
|
/// Set metadata.
|
|
pub fn with_metadata(mut self, metadata: serde_json::Value) -> Self {
|
|
self.metadata = metadata;
|
|
self
|
|
}
|
|
|
|
/// Set user name.
|
|
pub fn with_user_name(mut self, name: impl Into<String>) -> Self {
|
|
self.user_name = Some(name.into());
|
|
self
|
|
}
|
|
|
|
/// Set attachments.
|
|
pub fn with_attachments(mut self, attachments: Vec<Attachment>) -> Self {
|
|
self.attachments = attachments;
|
|
self
|
|
}
|
|
}
|
|
|
|
/// Stream of incoming messages.
|
|
pub type MessageStream = Pin<Box<dyn Stream<Item = IncomingMessage> + Send>>;
|
|
|
|
/// Response to send back to a channel.
|
|
#[derive(Debug, Clone)]
|
|
pub struct OutgoingResponse {
|
|
/// The content to send.
|
|
pub content: String,
|
|
/// Optional thread ID to reply in.
|
|
pub thread_id: Option<String>,
|
|
/// Channel-specific metadata for the response.
|
|
pub metadata: serde_json::Value,
|
|
}
|
|
|
|
impl OutgoingResponse {
|
|
/// Create a simple text response.
|
|
pub fn text(content: impl Into<String>) -> Self {
|
|
Self {
|
|
content: content.into(),
|
|
thread_id: None,
|
|
metadata: serde_json::Value::Null,
|
|
}
|
|
}
|
|
|
|
/// Set the thread ID for the response.
|
|
pub fn in_thread(mut self, thread_id: impl Into<String>) -> Self {
|
|
self.thread_id = Some(thread_id.into());
|
|
self
|
|
}
|
|
}
|
|
|
|
/// Status update types for showing agent activity.
|
|
#[derive(Debug, Clone)]
|
|
pub enum StatusUpdate {
|
|
/// Agent is thinking/processing.
|
|
Thinking(String),
|
|
/// Tool execution started.
|
|
ToolStarted { name: String },
|
|
/// Tool execution completed.
|
|
ToolCompleted { name: String, success: bool },
|
|
/// Brief preview of tool execution output.
|
|
ToolResult { name: String, preview: String },
|
|
/// Streaming text chunk.
|
|
StreamChunk(String),
|
|
/// General status message.
|
|
Status(String),
|
|
/// A sandbox job has started (shown as a clickable card in the UI).
|
|
JobStarted {
|
|
job_id: String,
|
|
title: String,
|
|
browse_url: String,
|
|
},
|
|
/// Tool requires user approval before execution.
|
|
ApprovalNeeded {
|
|
request_id: String,
|
|
tool_name: String,
|
|
description: String,
|
|
parameters: serde_json::Value,
|
|
},
|
|
/// Extension needs user authentication (token or OAuth).
|
|
AuthRequired {
|
|
extension_name: String,
|
|
instructions: Option<String>,
|
|
auth_url: Option<String>,
|
|
setup_url: Option<String>,
|
|
},
|
|
/// Extension authentication completed.
|
|
AuthCompleted {
|
|
extension_name: String,
|
|
success: bool,
|
|
message: String,
|
|
},
|
|
}
|
|
|
|
/// Trait for message channels.
|
|
///
|
|
/// Channels receive messages from external sources and convert them to
|
|
/// a unified format. They also handle sending responses back.
|
|
#[async_trait]
|
|
pub trait Channel: Send + Sync {
|
|
/// Get the channel name (e.g., "cli", "slack", "telegram", "http").
|
|
fn name(&self) -> &str;
|
|
|
|
/// Start listening for messages.
|
|
///
|
|
/// Returns a stream of incoming messages. The channel should handle
|
|
/// reconnection and error recovery internally.
|
|
async fn start(&self) -> Result<MessageStream, ChannelError>;
|
|
|
|
/// Send a response back to the user.
|
|
///
|
|
/// The response is sent in the context of the original message
|
|
/// (same channel, same thread if applicable).
|
|
async fn respond(
|
|
&self,
|
|
msg: &IncomingMessage,
|
|
response: OutgoingResponse,
|
|
) -> Result<(), ChannelError>;
|
|
|
|
/// Send a status update (thinking, tool execution, etc.).
|
|
///
|
|
/// The metadata contains channel-specific routing info (e.g., Telegram chat_id)
|
|
/// needed to deliver the status to the correct destination.
|
|
///
|
|
/// Default implementation does nothing (for channels that don't support status).
|
|
async fn send_status(
|
|
&self,
|
|
_status: StatusUpdate,
|
|
_metadata: &serde_json::Value,
|
|
) -> Result<(), ChannelError> {
|
|
Ok(())
|
|
}
|
|
|
|
/// Send a proactive message without a prior incoming message.
|
|
///
|
|
/// Used for alerts, heartbeat notifications, and other agent-initiated communication.
|
|
/// The user_id helps target a specific user within the channel.
|
|
///
|
|
/// Default implementation does nothing (for channels that don't support broadcast).
|
|
async fn broadcast(
|
|
&self,
|
|
_user_id: &str,
|
|
_response: OutgoingResponse,
|
|
) -> Result<(), ChannelError> {
|
|
Ok(())
|
|
}
|
|
|
|
/// Check if the channel is healthy.
|
|
async fn health_check(&self) -> Result<(), ChannelError>;
|
|
|
|
/// Gracefully shut down the channel.
|
|
async fn shutdown(&self) -> Result<(), ChannelError> {
|
|
Ok(())
|
|
}
|
|
}
|