praxis/server/__main__.py

"""Praxis server entrypoint — starts the Pipecat WebRTC bot server.

Run: `python -m server`

Exposes a FastAPI app with:
  GET  /health          — liveness
  POST /pipecat/webrtc  — accept a WebRTC offer SDP, start a pipeline task

The server starts and accepts connections even if upstream voice-service keys
are absent (SLICE-02 deliverable = code structure). Missing keys degrade to
no audio/no tokens at runtime, not a crash.
"""

from __future__ import annotations

import os
from typing import Any

from loguru import logger
from pydantic import BaseModel

# Load .env if present (dev). In production, env is injected directly.
try:
    from dotenv import load_dotenv

    load_dotenv()
except ImportError:  # pragma: no cover
    pass

from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.staticfiles import StaticFiles
from pipecat.transports.smallwebrtc.connection import SmallWebRTCConnection

from server.pipeline import build_pipeline


def _env(key: str, default: str = "") -> str:
    return os.environ.get(key, default).strip()


HOST = _env("PRAXIS_HOST", "0.0.0.0")
PORT = int(_env("PRAXIS_PORT", "8789"))


class WebRTCOffer(BaseModel):
    """Client→server WebRTC offer (SDP + type)."""

    sdp: str
    type: str = "offer"


app = FastAPI(title="Praxis v0.1 voice server", version="0.1.0")
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],  # dev — the client is a separate Vite origin
    allow_methods=["*"],
    allow_headers=["*"],
)


@app.get("/health")
async def health() -> dict[str, Any]:
    """Liveness probe. Reports key-provisioning status for the client."""
    return {
        "status": "ok",
        "version": "0.1.0",
        "keys": {
            "deepgram": bool(_env("DEEPGRAM_API_KEY")),
            "cartesia": bool(_env("CARTESIA_API_KEY")),
            "ollama": bool(_env("OLLAMA_API_KEY")),
        },
        "tts": _env("PRAXIS_TTS", "cartesia"),
    }


@app.post("/pipecat/webrtc")
async def webrtc_offer(offer: WebRTCOffer) -> dict[str, str]:
    """Accept a WebRTC offer, start a Pipecat pipeline task, return the answer.

    Loads the v0.1 scenario (customer_service_refund_ca_v01) so the pipeline
    uses the scenario-driven system prompt + opening line (TASK-03-07).
    """
    scenario_id = _env("PRAXIS_SCENARIO", "customer_service_refund_ca_v01")
    try:
        connection = SmallWebRTCConnection(
            ice_servers=[{"urls": "stun:stun.l.google.com:19302"}],
        )
        await connection.receive_offer({"sdp": offer.sdp, "type": offer.type})
        await connection.accept()
        answer = connection.get_answer()
        # Build + run the pipeline for this connection.
        pipeline, task, runner, transport, scenario_runtime = build_pipeline(
            connection, scenario_id=scenario_id
        )
        # Run the pipeline task in the background; the runner manages its lifecycle.
        import asyncio

        asyncio.create_task(runner.run(task))
        # Play the session-start disclaimer as the first AI utterance (D-019,
        # RESEARCH.md safety baseline), then the scenario opening line.
        from server.services.registry import get_guardrail

        guardrail = get_guardrail()
        disclaimer = guardrail.session_start_disclaimer
        if scenario_runtime is not None:
            logger.info(
                f"Session starting with scenario {scenario_id!r}; "
                f"disclaimer: {disclaimer[:50]!r}; "
                f"opening line: {scenario_runtime.opening_line[:60]!r}"
            )
        else:
            logger.info(f"Session starting (no scenario); disclaimer: {disclaimer[:50]!r}")
        return {"sdp": answer["sdp"], "type": answer["type"]}
    except Exception as exc:
        logger.error(f"WebRTC offer failed: {exc}")
        raise HTTPException(status_code=500, detail=str(exc))


# ── Static client serving (D-023, REQ-DEPLOY-13) ────────────────────
# Mount client/dist as StaticFiles at "/" AFTER all API routes so they
# take precedence. html=True serves index.html for "/" (SPA root).
# The client has no React Router (single-view state machine: start→live
# →debrief), so no SPA fallback fallback route is needed per RESEARCH.md Q3.
_CLIENT_DIST = _env("PRAXIS_CLIENT_DIST", "client/dist")
if os.path.isdir(_CLIENT_DIST):
    app.mount("/", StaticFiles(directory=_CLIENT_DIST, html=True), name="client")
    logger.info(f"Serving client from {_CLIENT_DIST}")
else:
    logger.warning(f"Client dist not found at {_CLIENT_DIST} — API-only mode")


def main() -> int:
    """Run the server with uvicorn."""
    import uvicorn

    logger.info(f"Praxis v0.1 voice server starting on {HOST}:{PORT}")
    uvicorn.run(app, host=HOST, port=PORT, log_level="info")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())