perf(tui): stop slow/dead MCP servers from freezing TUI startup

The 'summoning hermes…' phase blocked on gateway.ready, which ran MCP
tool discovery inline. Any configured-but-unreachable MCP server burned
its full connect-retry backoff (1+2+4s ≈ 7s) before the composer
appeared — startup went from instant to ~7.5s of dead air for anyone
with a down stdio/http server in mcp_servers.

Move discovery into a background daemon thread so gateway.ready fires
immediately; tools register into the shared registry as servers connect,
and the agent isn't built until the first prompt. Measured spawn→ready:
~7500ms → ~115ms (dead twozero_td server in config).

Also drop rich.console + prompt_toolkit off banner.py's import path
(lazy-imported inside cprint/build_welcome_banner). tui_gateway.server
imports banner only to reach the lightweight prefetch_update_check
helper; the eager rich/pt imports added ~45ms before gateway.ready for
no benefit. tui_gateway.server import: ~115ms → ~69ms.

hermes_cli/banner.py

@@ -12,14 +12,16 @@ import threading
 import time
 from pathlib import Path
 from hermes_constants import get_hermes_home
-from typing import Dict, List, Optional
+from typing import TYPE_CHECKING, Dict, List, Optional
 
-from rich.console import Console
-from rich.panel import Panel
-from rich.table import Table
-
-from prompt_toolkit import print_formatted_text as _pt_print
-from prompt_toolkit.formatted_text import ANSI as _PT_ANSI
+# rich and prompt_toolkit are imported lazily (inside the functions that use
+# them) rather than at module level.  Importing this module is on the TUI
+# gateway's critical startup path purely to reach the lightweight update-check
+# helpers (``prefetch_update_check``); pulling rich.console + prompt_toolkit
+# eagerly added ~50ms of wasted imports before ``gateway.ready`` could fire.
+# Keep the type-only reference available to checkers without the runtime cost.
+if TYPE_CHECKING:
+    from rich.console import Console
 
 logger = logging.getLogger(__name__)
 
@@ -36,6 +38,8 @@ _RST = "\033[0m"
 
 def cprint(text: str):
     """Print ANSI-colored text through prompt_toolkit's renderer."""
+    from prompt_toolkit import print_formatted_text as _pt_print
+    from prompt_toolkit.formatted_text import ANSI as _PT_ANSI
     _pt_print(_PT_ANSI(text))
 
 
@@ -471,7 +475,7 @@ def _display_toolset_name(toolset_name: str) -> str:
     )
 
 
-def build_welcome_banner(console: Console, model: str, cwd: str,
+def build_welcome_banner(console: "Console", model: str, cwd: str,
                          tools: List[dict] = None,
                          enabled_toolsets: List[str] = None,
                          session_id: str = None,
@@ -490,6 +494,8 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
         context_length: Model's context window size in tokens.
     """
     from model_tools import check_tool_availability, TOOLSET_REQUIREMENTS
+    from rich.panel import Panel
+    from rich.table import Table
     if get_toolset_for_tool is None:
         from model_tools import get_toolset_for_tool