FusionAGI/fusionagi/api/app.py

"""FastAPI application factory for FusionAGI Dvādaśa API.

Includes versioned API negotiation, metrics, and CORS support."""

from __future__ import annotations

import json
import os
import time
from collections import defaultdict
from contextlib import asynccontextmanager
from typing import Any

from fusionagi._logger import logger
from fusionagi.api.dependencies import SessionStore, default_orchestrator, set_app_state
from fusionagi.api.metrics import get_metrics, metrics_enabled

API_VERSION = "1"
SUPPORTED_VERSIONS = ["1"]
DEPRECATED_VERSIONS: list[str] = []


def create_app(
    adapter: Any = None,
    cors_origins: list[str] | None = None,
) -> Any:
    """Create FastAPI app with Dvādaśa routes.

    Args:
        adapter: Optional LLMAdapter for head/Witness LLM calls.
        cors_origins: Optional list of CORS allowed origins.
    """
    try:
        from fastapi import FastAPI, Request, Response
        from starlette.middleware.base import BaseHTTPMiddleware
    except ImportError as e:
        raise ImportError("Install with: pip install fusionagi[api]") from e

    # --- Lifespan (replaces deprecated on_event) ---
    @asynccontextmanager
    async def lifespan(application: FastAPI):  # type: ignore[type-arg]
        """Startup / shutdown lifecycle."""
        adapter_inner = getattr(application.state, "llm_adapter", None)
        orch, bus = default_orchestrator(adapter_inner)
        store = SessionStore()
        set_app_state(orch, bus, store)
        application.state._dvadasa_ready = True
        logger.info("FusionAGI Dvādaśa API started")
        yield
        logger.info("FusionAGI Dvādaśa API shutdown")

    app = FastAPI(
        title="FusionAGI Dvādaśa API",
        description=(
            "12-headed multi-agent orchestration API.\n\n"
            "## Authentication\n"
            "Set `FUSIONAGI_API_KEY` to require Bearer token auth on all `/v1/` routes.\n\n"
            "## Rate Limiting\n"
            "Default: 120 requests/minute per client IP. "
            "Configure via `FUSIONAGI_RATE_LIMIT` (requests) and "
            "`FUSIONAGI_RATE_WINDOW` (seconds) env vars."
        ),
        version="0.1.0",
        lifespan=lifespan,
    )
    app.state.llm_adapter = adapter
    from fusionagi.api.dependencies import set_default_adapter

    set_default_adapter(adapter)

    # --- Auth middleware ---
    api_key = os.environ.get("FUSIONAGI_API_KEY")

    class AuthMiddleware(BaseHTTPMiddleware):
        """Bearer token authentication for /v1/ routes."""

        async def dispatch(self, request: Request, call_next: Any) -> Response:
            if api_key and request.url.path.startswith("/v1/"):
                auth = request.headers.get("authorization", "")
                if not auth.startswith("Bearer ") or auth[7:].strip() != api_key:
                    return Response(
                        content='{"detail":"Invalid or missing API key"}',
                        status_code=401,
                        media_type="application/json",
                    )
            return await call_next(request)  # type: ignore[no-any-return]

    app.add_middleware(AuthMiddleware)

    # --- Rate limiting middleware ---
    rate_limit = int(os.environ.get("FUSIONAGI_RATE_LIMIT", "120"))
    rate_window = float(os.environ.get("FUSIONAGI_RATE_WINDOW", "60"))
    _buckets: dict[str, list[float]] = defaultdict(list)

    class RateLimitMiddleware(BaseHTTPMiddleware):
        """Per-tenant + per-IP sliding window rate limiter (advisory mode).

        Tracks both IP-level and tenant-level request rates. Logs exceedances
        but allows requests through (advisory governance).
        """

        async def dispatch(self, request: Request, call_next: Any) -> Response:
            client_ip = request.client.host if request.client else "unknown"
            tenant_id = request.headers.get("x-tenant-id", "default")
            now = time.monotonic()
            cutoff = now - rate_window

            # Per-IP tracking
            ip_key = f"ip:{client_ip}"
            _buckets[ip_key] = [t for t in _buckets[ip_key] if t > cutoff]
            if len(_buckets[ip_key]) >= rate_limit:
                logger.info(
                    "API rate limit advisory: IP limit exceeded (proceeding)",
                    extra={"client_ip": client_ip, "count": len(_buckets[ip_key]), "limit": rate_limit},
                )

            # Per-tenant tracking (separate quota)
            tenant_key = f"tenant:{tenant_id}"
            tenant_limit = rate_limit * 5  # tenants get 5x the per-IP limit
            _buckets[tenant_key] = [t for t in _buckets[tenant_key] if t > cutoff]
            if len(_buckets[tenant_key]) >= tenant_limit:
                logger.info(
                    "API rate limit advisory: tenant limit exceeded (proceeding)",
                    extra={"tenant_id": tenant_id, "count": len(_buckets[tenant_key]), "limit": tenant_limit},
                )

            _buckets[ip_key].append(now)
            _buckets[tenant_key].append(now)
            return await call_next(request)  # type: ignore[no-any-return]

    app.add_middleware(RateLimitMiddleware)

    # --- Version negotiation middleware ---
    class VersionMiddleware(BaseHTTPMiddleware):
        """API version negotiation via Accept-Version header.

        Adds X-API-Version and deprecation warnings to responses.
        """

        async def dispatch(self, request: Request, call_next: Any) -> Response:
            requested = request.headers.get("accept-version", API_VERSION)
            if requested not in SUPPORTED_VERSIONS:
                return Response(
                    content=json.dumps({
                        "detail": f"Unsupported API version: {requested}",
                        "supported_versions": SUPPORTED_VERSIONS,
                    }),
                    status_code=400,
                    media_type="application/json",
                )
            response = await call_next(request)
            response.headers["X-API-Version"] = requested
            if requested in DEPRECATED_VERSIONS:
                response.headers["Deprecation"] = "true"
                response.headers["Sunset"] = "2026-12-31"
            return response  # type: ignore[no-any-return]

    app.add_middleware(VersionMiddleware)

    # --- Metrics middleware ---
    if metrics_enabled():
        class MetricsMiddleware(BaseHTTPMiddleware):
            async def dispatch(self, request: Request, call_next: Any) -> Response:
                m = get_metrics()
                m.inc("http_requests_total", labels={"method": request.method, "path": request.url.path})
                start = time.monotonic()
                response = await call_next(request)
                duration = time.monotonic() - start
                m.observe("http_request_duration_seconds", duration, labels={"path": request.url.path})
                m.inc("http_responses_total", labels={"status": str(response.status_code)})
                return response  # type: ignore[no-any-return]

        app.add_middleware(MetricsMiddleware)

    # --- Routes ---
    from fusionagi.api.routes import router as api_router

    app.include_router(api_router, prefix="/v1", tags=["dvadasa"])

    # Metrics endpoint
    if metrics_enabled():
        @app.get("/metrics", tags=["monitoring"])
        def metrics_endpoint() -> dict[str, Any]:
            return get_metrics().snapshot()

    # Health check endpoints (no auth required)
    _start_time = time.time()

    @app.get("/health", tags=["monitoring"])
    def health_check() -> dict[str, Any]:
        """Basic health check for load balancer probes."""
        return {"status": "healthy", "uptime_seconds": round(time.time() - _start_time, 1)}

    @app.get("/ready", tags=["monitoring"])
    def readiness_check() -> dict[str, Any]:
        """Readiness probe. Returns 503 if not initialized."""
        ready = getattr(app.state, "_dvadasa_ready", False)
        if not ready:
            from starlette.responses import JSONResponse
            return JSONResponse(  # type: ignore[return-value]
                content={"status": "not_ready"},
                status_code=503,
            )
        return {"status": "ready", "uptime_seconds": round(time.time() - _start_time, 1)}

    # Version info endpoint
    @app.get("/version", tags=["meta"])
    def version_info() -> dict[str, Any]:
        return {
            "current_version": API_VERSION,
            "supported_versions": SUPPORTED_VERSIONS,
            "deprecated_versions": DEPRECATED_VERSIONS,
        }

    if cors_origins is not None:
        try:
            from fastapi.middleware.cors import CORSMiddleware

            app.add_middleware(
                CORSMiddleware,
                allow_origins=cors_origins,
                allow_methods=["*"],
                allow_headers=["*"],
            )
        except ImportError:
            pass

    return app


# Default app instance for uvicorn/gunicorn
app = create_app()