Fix infinite retry loop in StreamableHTTP _handle_reconnection

When a reconnection succeeds at the HTTP level but the SSE stream ends
without delivering a complete response, _handle_reconnection recursed
with attempt=0, resetting the counter and making MAX_RECONNECTION_ATTEMPTS
ineffective. This caused the client to retry forever if the server
repeatedly accepted connections but dropped streams.

Pass attempt + 1 instead of 0 so total reconnection attempts are properly
tracked across recursions.

Fixes #2393

Author: Christian-Sidak

src/mcp/client/streamable_http.py

@@ -421,9 +421,9 @@ async def _handle_reconnection(
                         await event_source.response.aclose()
                         return
 
-                # Stream ended again without response - reconnect again (reset attempt counter)
+                # Stream ended again without response - reconnect again
                 logger.info("SSE stream disconnected, reconnecting...")
-                await self._handle_reconnection(ctx, reconnect_last_event_id, reconnect_retry_ms, 0)
+                await self._handle_reconnection(ctx, reconnect_last_event_id, reconnect_retry_ms, attempt + 1)
         except Exception as e:  # pragma: no cover
             logger.debug(f"Reconnection failed: {e}")
             # Try to reconnect again if we still have an event ID