Upload app.py

app.py

@@ -1,14 +1,16 @@
-"""LibBee - Main Application Entry Point
-Phase 3: production hardening, persistence, metrics, and safer staff routing
-
-Fixes applied (v3.1):
-1. _request_log replaced with cachetools.TTLCache — no more unbounded IP dict
-2. MetricsService background flush task started in lifespan
-3. Circular import risk reduced — rag_service / metrics_service exposed via
-   module-level accessors get_rag_service() / get_metrics_service() so routers
-   can import the accessor instead of doing a deferred 'from app import ...'
-4. Startup errors no longer silently swallow RAG init exceptions
 """
+app.py — LibBee v3.5
+FastAPI entry point: CORS, middleware, lifespan, router mounting.
+
+Changes over v3.1:
+- Maintenance mode middleware now reads from JsonRuntimeStore (admin-editable)
+  instead of settings.maintenance_mode (env var, static at startup).
+- CORS origins updated: added ku-library.github.io.
+- Section headers added throughout.
+"""
+
+# ── Imports ────────────────────────────────────────────────────────────────────
+
 import asyncio
 import logging
 import time
@@ -32,23 +34,30 @@ from src.services.rag_service import RAGService
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-rag_service = RAGService()
-cache_service = CacheService()
+
+# ── Service Instances ──────────────────────────────────────────────────────────
+
+rag_service     = RAGService()
+cache_service   = CacheService()
 metrics_service = MetricsService(get_settings().metrics_path)
 
-# ── Rate-limit request log ─────────────────────────────────────────────────────
-# TTLCache(maxsize, ttl) auto-evicts entries older than ttl seconds.
-# Falls back to a plain dict with manual sweep if cachetools not installed.
+
+# ── Rate-limit Request Log ─────────────────────────────────────────────────────
+# TTLCache auto-evicts entries older than ttl seconds.
+# Falls back to a plain deque-based dict if cachetools is not installed.
+
 if _ttl_cache_available:
-    _request_log = TTLCache(maxsize=10_000, ttl=120)
+    _request_log      = TTLCache(maxsize=10_000, ttl=120)
     _request_log_lock = asyncio.Lock()
 else:
     from collections import defaultdict, deque
-    _request_log = defaultdict(deque)  # type: ignore[assignment]
+    _request_log      = defaultdict(deque)   # type: ignore[assignment]
     _request_log_lock = asyncio.Lock()
 
 
-# ── Public accessors (used by routers to avoid circular imports) ───────────────
+# ── Public Accessors ───────────────────────────────────────────────────────────
+# Routers import these instead of importing module-level globals directly,
+# which avoids circular-import issues at import time.
 
 def get_rag_service() -> RAGService:
     return rag_service
@@ -58,7 +67,7 @@ def get_metrics_service() -> MetricsService:
     return metrics_service
 
 
-# ── Background flush task ──────────────────────────────────────────────────────
+# ── Background Tasks ───────────────────────────────────────────────────────────
 
 async def _metrics_flush_loop(interval: int = 30) -> None:
     """Flush in-memory metric counters to disk every `interval` seconds."""
@@ -70,6 +79,8 @@ async def _metrics_flush_loop(interval: int = 30) -> None:
             logger.warning("Metrics flush error: %s", exc)
 
 
+# ── Lifespan ───────────────────────────────────────────────────────────────────
+
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     from src.services.staff_service import build_staff_index
@@ -83,7 +94,7 @@ async def lifespan(app: FastAPI):
     except Exception as exc:
         logger.error("Staff index build failed: %s", exc)
 
-    # Initialize RAG
+    # Initialise RAG service
     if settings.openai_api_key:
         try:
             await rag_service.initialize(openai_api_key=settings.openai_api_key)
@@ -108,17 +119,23 @@ async def lifespan(app: FastAPI):
     logger.info("LibBee shutting down")
 
 
+# ── FastAPI App ──────────────────────────────────────────────────────��─────────
+
 app = FastAPI(
     title="LibBee - KU Library AI",
     description="Khalifa University Library AI Assistant",
-    version="3.1.0",
+    version="3.5.0",
     lifespan=lifespan,
 )
 
+
+# ── CORS Middleware ────────────────────────────────────────────────────────────
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=[
         "https://nikeshn.github.io",
+        "https://ku-library.github.io",       # added v3.5
         "http://localhost:8080",
         "http://localhost:3000",
         "http://127.0.0.1:5500",
@@ -130,24 +147,38 @@ app.add_middleware(
 )
 
 
+# ── Operational Guardrails Middleware ──────────────────────────────────────────
+
 @app.middleware("http")
 async def operational_guardrails(request: Request, call_next):
     settings = get_settings()
 
-    # Maintenance mode
-    if settings.maintenance_mode and request.url.path not in {"/", "/config"}:
+    # ── Maintenance mode ───────────────────────────────────────────────────────
+    # FIX v3.5: read from JsonRuntimeStore (admin-editable) rather than
+    # settings.maintenance_mode (env var, static at startup). This means
+    # toggling maintenance via the admin dashboard actually takes effect.
+    _maintenance_on = False
+    try:
+        from src.services.runtime_store import JsonRuntimeStore
+        _store = JsonRuntimeStore(settings.config_path, default={"maintenance_mode": False})
+        _maintenance_on = bool(_store.load().get("maintenance_mode", False))
+    except Exception:
+        # If store is unreadable fall back to env-var setting
+        _maintenance_on = settings.maintenance_mode
+
+    _exempt_paths = {"/", "/config", "/admin", "/admin/login", "/admin/auth"}
+    if _maintenance_on and request.url.path not in _exempt_paths:
         return JSONResponse(
             status_code=503,
             content={"detail": "LibBee is in maintenance mode. Please try again shortly."},
         )
 
-    # Rate limiting
+    # ── Rate limiting ──────────────────────────────────────────────────────────
     client_ip = request.client.host if request.client else "unknown"
     now = time.time()
 
     async with _request_log_lock:
         if _ttl_cache_available:
-            # TTLCache stores a list of timestamps per IP
             timestamps = _request_log.get(client_ip, [])
             timestamps = [t for t in timestamps if now - t < 60]
             if len(timestamps) >= settings.rate_limit_per_minute:
@@ -159,7 +190,6 @@ async def operational_guardrails(request: Request, call_next):
             timestamps.append(now)
             _request_log[client_ip] = timestamps
         else:
-            # Fallback: deque-based sliding window
             from collections import deque
             bucket = _request_log[client_ip]  # type: ignore[index]
             while bucket and now - bucket[0] > 60:
@@ -172,6 +202,7 @@ async def operational_guardrails(request: Request, call_next):
                 )
             bucket.append(now)
 
+    # ── Request execution ──────────────────────────────────────────────────────
     try:
         response = await call_next(request)
         return response
@@ -181,20 +212,24 @@ async def operational_guardrails(request: Request, call_next):
         return JSONResponse(status_code=500, content={"detail": "Unexpected server error."})
 
 
+# ── Router Mounting ────────────────────────────────────────────────────────────
+
 from src.api import admin, agent, feedback, search  # noqa: E402
 
-app.include_router(agent.router, prefix="/agent", tags=["Agent"])
-app.include_router(search.router, prefix="/search", tags=["Search"])
-app.include_router(admin.router, prefix="/admin", tags=["Admin"])
+app.include_router(agent.router,    prefix="/agent",    tags=["Agent"])
+app.include_router(search.router,   prefix="/search",   tags=["Search"])
+app.include_router(admin.router,    prefix="/admin",    tags=["Admin"])
 app.include_router(feedback.router, prefix="/feedback", tags=["Feedback"])
 
 
+# ── Health & Public Endpoints ──────────────────────────────────────────────────
+
 @app.get("/")
 def health_check():
     settings = get_settings()
     return {
         "status": "ok",
-        "version": "3.1.0",
+        "version": "3.5.0",
         "service": "LibBee KU Library AI",
         "rag_ready": rag_service.is_ready(),
         "maintenance_mode": settings.maintenance_mode,
@@ -204,6 +239,7 @@ def health_check():
 
 @app.get("/config")
 def public_config():
+    """Legacy public config endpoint — frontend uses /admin/public-config instead."""
     settings = get_settings()
     return {
         "welcome_message": "Hi! I'm LibBee, the Khalifa University Library AI Assistant.",