mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 21:00:42 -07:00
James PineandClaude Opus 4.7
0cef2c9fe1
Mounts FastMCP at /mcp (Streamable HTTP) so Claude Code, Cursor, Windsurf, and the VS Code MCP extensions can call voicebox.speak, voicebox.transcribe, voicebox.list_captures, and voicebox.list_profiles against the running Voicebox server. Backend - new backend/mcp_server package (tools, middleware, profile resolve, pub/sub events); named mcp_server to avoid shadowing the installed mcp PyPI package FastMCP imports internally - app.py migrated from @app.on_event to lifespan= so FastMCP's session manager cohabits with Voicebox's startup/shutdown - new MCPClientBinding table + /mcp/bindings CRUD; ClientIdMiddleware reads X-Voicebox-Client-Id into a ContextVar and stamps last_seen_at - profile resolution precedence: explicit -> per-client binding -> capture_settings.default_playback_voice_id - POST /speak REST wrapper for non-MCP callers (shell, ACP, A2A) - GET /events/speak SSE broadcasts speak-start / speak-end so the pill surfaces agent-initiated speech - backend/mcp_shim proxy (plain httpx) for stdio-only MCP clients - PyInstaller spec updates + new --shim build target (~18 MB) Frontend - Settings -> MCP page with HTTP / stdio / claude-mcp-add copy snippets, default voice picker, per-client bindings table, connection status - useMCPBindings, useSpeakEvents hooks - CapturePill gains 'speaking' state; DictateWindow subscribes to SSE and emits dictate:show so the Rust side surfaces the pill window Native - tauri.conf.json externalBin now includes voicebox-mcp - show_dictate_window helper + dictate:show listener in main.rs - (also in this commit: InputMonitoringGate UX, hotkey_monitor tweaks, landing footer/navbar updates, new overview docs for captures / dictation / mcp-server / voice-personalities) Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
80 lines
2.6 KiB
Python
80 lines
2.6 KiB
Python
"""Construct the FastMCP server and mount it on the FastAPI app.
|
|
|
|
The MCP endpoint lives at ``/mcp`` (Streamable HTTP transport). Modern MCP
|
|
clients (Claude Code, Cursor, Windsurf, VS Code MCP extensions) connect
|
|
directly via URL; older stdio-only clients use the ``voicebox-mcp`` shim
|
|
binary bundled with the desktop app.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from contextlib import AsyncExitStack, asynccontextmanager
|
|
from typing import Callable
|
|
|
|
from fastapi import FastAPI
|
|
from fastmcp import FastMCP
|
|
|
|
from .context import ClientIdMiddleware
|
|
from .tools import register_tools
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def build_mcp_server() -> FastMCP:
|
|
"""Create the FastMCP instance with Voicebox tools registered."""
|
|
mcp = FastMCP(
|
|
name="voicebox",
|
|
instructions=(
|
|
"Voicebox is a local voice I/O layer. Use `voicebox.speak` to "
|
|
"play text in a voice profile, `voicebox.transcribe` for "
|
|
"audio→text, and the `list_*` tools to discover profiles and "
|
|
"captures."
|
|
),
|
|
)
|
|
register_tools(mcp)
|
|
return mcp
|
|
|
|
|
|
def mount_into(
|
|
app: FastAPI,
|
|
*,
|
|
extra_startup: Callable[[], None] | None = None,
|
|
) -> None:
|
|
"""Attach the MCP app to ``app`` at ``/mcp`` and install the client-id middleware.
|
|
|
|
``extra_startup`` — if provided, runs during the FastAPI lifespan. This
|
|
is the hook that lets ``app.py`` keep its existing startup/shutdown
|
|
bodies while also driving FastMCP's session manager.
|
|
"""
|
|
mcp = build_mcp_server()
|
|
mcp_app = mcp.http_app(path="/", transport="http")
|
|
|
|
# ClientIdMiddleware must run before FastMCP so the ContextVar is set
|
|
# by the time tool handlers execute. Starlette composes middlewares
|
|
# outermost-first, so adding here on the parent app is correct.
|
|
app.add_middleware(ClientIdMiddleware)
|
|
app.mount("/mcp", mcp_app)
|
|
app.state.mcp_lifespan = mcp_app.router.lifespan_context
|
|
logger.info("MCP: mounted at /mcp (FastMCP %s)", getattr(mcp, "version", ""))
|
|
|
|
|
|
def compose_lifespan(*lifespans):
|
|
"""Combine multiple async context managers into a single FastAPI lifespan.
|
|
|
|
Used by ``create_app`` to run the existing Voicebox startup/shutdown
|
|
together with FastMCP's session manager (which MUST run in the
|
|
ASGI lifespan for Streamable HTTP to work).
|
|
"""
|
|
|
|
@asynccontextmanager
|
|
async def _combined(app):
|
|
async with AsyncExitStack() as stack:
|
|
for cm_factory in lifespans:
|
|
cm = cm_factory(app) if callable(cm_factory) else cm_factory
|
|
await stack.enter_async_context(cm)
|
|
yield
|
|
|
|
return _combined
|