gateway/app.py

"""
FastAPI gateway — Custom GPT Action surface (Path A).

Receives messages from the GPT Action, routes to the right adapter,
calls the HF Inference Endpoint, and returns both raw ui_spec and a
markdown fallback so the GPT can render something useful inline.
"""
import os
import sys
from pathlib import Path

import httpx
from dotenv import load_dotenv
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel

load_dotenv()

# Allow shared lib to be imported when running from repo root or this dir
sys.path.insert(0, str(Path(__file__).parent.parent))
from lib.router import route
from lib.markdown_renderer import render

HF_ENDPOINT_URL = os.getenv("HF_ENDPOINT_URL", "")
HF_TOKEN        = os.getenv("HF_TOKEN", "")

app = FastAPI(
    title="Adaptive Model Gateway",
    version="1.0.0",
    description="Routes chat turns to the right LoRA adapter and returns adaptive UI specs.",
)
app.add_middleware(
    CORSMiddleware,
    allow_origins=["https://chat.openai.com", "https://chatgpt.com"],
    allow_methods=["POST", "GET"],
    allow_headers=["*"],
)


# ── request / response models ─────────────────────────────────────────────────

class Message(BaseModel):
    role: str
    content: str


class GenerateRequest(BaseModel):
    messages: list[Message]
    mode: str | None = None     # explicit override; omit for heuristic routing


class GenerateResponse(BaseModel):
    text: str
    ui_spec: dict | None = None
    ui_markdown: str | None = None  # markdown fallback for Custom GPT rendering
    adapter: str


# ── endpoints ─────────────────────────────────────────────────────────────────

@app.post("/generate", response_model=GenerateResponse)
async def generate(req: GenerateRequest) -> GenerateResponse:
    if not HF_ENDPOINT_URL:
        raise HTTPException(500, "HF_ENDPOINT_URL not set — check .env")

    messages  = [m.model_dump() for m in req.messages]
    adapter   = route(messages, req.mode)

    headers = {"Content-Type": "application/json"}
    if HF_TOKEN:
        headers["Authorization"] = f"Bearer {HF_TOKEN}"

    async with httpx.AsyncClient(timeout=60.0) as client:
        resp = await client.post(
            HF_ENDPOINT_URL,
            json={"inputs": {"messages": messages, "mode": adapter}},
            headers=headers,
        )

    if resp.status_code != 200:
        raise HTTPException(resp.status_code, f"HF endpoint error: {resp.text[:400]}")

    data    = resp.json()
    ui_spec = data.get("ui_spec")

    return GenerateResponse(
        text=data.get("text", ""),
        ui_spec=ui_spec,
        ui_markdown=render(ui_spec),
        adapter=data.get("adapter", adapter),
    )


@app.get("/health")
async def health() -> dict:
    return {"status": "ok", "endpoint_configured": bool(HF_ENDPOINT_URL)}


# ── dev entry-point ───────────────────────────────────────────────────────────

if __name__ == "__main__":
    import uvicorn
    uvicorn.run("gateway.app:app", host="0.0.0.0", port=8000, reload=True)