feat(auth, rfc): Add support for Bearer (api_key) Authentication (#1626)

This PR adds support (or is a proposal for) for supporting API KEY
authentication on the Llama Stack server end. `llama-stack-client`
already supports accepting an api_key parameter and passes it down
through every request as an `Authentication: ` header.

Currently, Llama Stack does not propose APIs for handling authentication
or authorization for resources of any kind. Given that, and the fact
that any deployment will typically have _some_ authentication system
present, we simply adopt a delegation mechanism: delegate to an HTTPS
endpoint performing key management / authentication.

It is configured via: 
```yaml
server: 
   auth:
     endpoint: <...>
```

in the run.yaml configuration.


## How It Works

When authentication is enabled:

1. Every API request must include an `Authorization: Bearer <token>`
header
2. The server will send a _POST_ validation request to the configured
endpoint with the following payload:
   ```json
   {
     "api_key": "<token>",
     "request": {
       "path": "/api/path",
       "headers": { "header1": "value1", ... },
       "params": { "param1": "value1", ... }
     }
   }
   ```
3. If the authentication endpoint returns a 200 status code, the request
is allowed to proceed
4. If the authentication endpoint returns any other status code, a 401
Unauthorized response is returned

## Test Plan

Unit tests

llama_stack/distribution/server/auth.py

@@ -0,0 +1,69 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import json
+from urllib.parse import parse_qs
+
+import httpx
+
+from llama_stack.log import get_logger
+
+logger = get_logger(name=__name__, category="auth")
+
+
+class AuthenticationMiddleware:
+    def __init__(self, app, auth_endpoint):
+        self.app = app
+        self.auth_endpoint = auth_endpoint
+
+    async def __call__(self, scope, receive, send):
+        if scope["type"] == "http":
+            headers = dict(scope.get("headers", []))
+            auth_header = headers.get(b"authorization", b"").decode()
+
+            if not auth_header or not auth_header.startswith("Bearer "):
+                return await self._send_auth_error(send, "Missing or invalid Authorization header")
+
+            api_key = auth_header.split("Bearer ", 1)[1]
+
+            path = scope.get("path", "")
+            request_headers = {k.decode(): v.decode() for k, v in headers.items()}
+
+            query_string = scope.get("query_string", b"").decode()
+            params = parse_qs(query_string)
+
+            auth_data = {
+                "api_key": api_key,
+                "request": {
+                    "path": path,
+                    "headers": request_headers,
+                    "params": params,
+                },
+            }
+
+            # Validate with authentication endpoint
+            try:
+                async with httpx.AsyncClient() as client:
+                    response = await client.post(self.auth_endpoint, json=auth_data)
+                    if response.status_code != 200:
+                        logger.warning(f"Authentication failed: {response.status_code}")
+                        return await self._send_auth_error(send, "Authentication failed")
+            except Exception:
+                logger.exception("Error during authentication")
+                return await self._send_auth_error(send, "Authentication service error")
+
+        return await self.app(scope, receive, send)
+
+    async def _send_auth_error(self, send, message):
+        await send(
+            {
+                "type": "http.response.start",
+                "status": 401,
+                "headers": [[b"content-type", b"application/json"]],
+            }
+        )
+        error_msg = json.dumps({"error": {"message": message}}).encode()
+        await send({"type": "http.response.body", "body": error_msg})

llama_stack/distribution/server/server.py

@@ -52,6 +52,7 @@ from llama_stack.providers.utils.telemetry.tracing import (
     start_trace,
 )
 
+from .auth import AuthenticationMiddleware
 from .endpoints import get_all_api_endpoints
 
 REPO_ROOT = Path(__file__).parent.parent.parent.parent
@@ -351,6 +352,11 @@ def main():
     if not os.environ.get("LLAMA_STACK_DISABLE_VERSION_CHECK"):
         app.add_middleware(ClientVersionMiddleware)
 
+    # Add authentication middleware if configured
+    if config.server.auth and config.server.auth.endpoint:
+        logger.info(f"Enabling authentication with endpoint: {config.server.auth.endpoint}")
+        app.add_middleware(AuthenticationMiddleware, auth_endpoint=config.server.auth.endpoint)
+
     try:
         impls = asyncio.run(construct_stack(config))
     except InvalidProviderError as e: