Frontend (17 items): - Virtualized message list with batch loading - CSS split with skeleton, drawer, search filter, message action styles - Code splitting via React.lazy + Suspense for Admin/Ethics/Settings pages - Skeleton loading components (Skeleton, SkeletonCard, SkeletonGrid) - Debounced search/filter component (SearchFilter) - Error boundary with fallback UI - Keyboard shortcuts (Ctrl+K search, Ctrl+Enter send, Escape dismiss) - Page transition animations (fade-in) - PWA support (manifest.json + service worker) - WebSocket auto-reconnect with exponential backoff (10 retries) - Chat history persistence to localStorage (500 msg limit) - Message edit/delete on hover - Copy-to-clipboard on code blocks - Mobile drawer (bottom-sheet for consensus panel) - File upload support - User preferences sync to backend Testing (8 items): - Component tests: Toast, Markdown, ChatMessage, Avatar, ErrorBoundary, Skeleton - Hook tests: useChatHistory - E2E smoke tests (5 tests) - Accessibility audit utility Backend (12 items): - Vector memory with cosine similarity search - TTS/STT adapter factory wiring - Geometry kernel with orphan detection - Tenant registry with CRUD operations - Response cache with TTL - Connection pool (async) - Background task queue - Health check endpoints (/health, /ready) - Request tracing middleware (X-Request-ID) - API key rotation mechanism - Environment-based config (settings.py) - API route documentation improvements Infrastructure (4 items): - Grafana dashboard template - Database migration system - Storybook configuration Documentation (3 items): - ADR-001: Advisory Governance Model - ADR-002: Twelve-Head Architecture - ADR-003: Consequence Engine 552 Python tests + 45 frontend tests passing, 0 ruff errors. Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
217 lines
8.1 KiB
Python
217 lines
8.1 KiB
Python
"""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-IP sliding window rate limiter (advisory mode).
|
|
|
|
Logs rate limit exceedances but allows the request through.
|
|
Consistent with the advisory governance philosophy.
|
|
"""
|
|
|
|
async def dispatch(self, request: Request, call_next: Any) -> Response:
|
|
client_ip = request.client.host if request.client else "unknown"
|
|
now = time.monotonic()
|
|
cutoff = now - rate_window
|
|
_buckets[client_ip] = [t for t in _buckets[client_ip] if t > cutoff]
|
|
if len(_buckets[client_ip]) >= rate_limit:
|
|
logger.info(
|
|
"API rate limit advisory: limit exceeded (proceeding)",
|
|
extra={"client_ip": client_ip, "count": len(_buckets[client_ip]), "limit": rate_limit},
|
|
)
|
|
_buckets[client_ip].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()
|