perf(mcp): non-blocking startup via background MCP discovery + TUI fast path

Fire-and-forget MCP server connections on a daemon thread so the
gateway / CLI / ACP process becomes interactive immediately instead
of blocking on slow remote MCP servers (HTTP timeouts, sluggish
stdio boot).  Previously `hermes --tui` waited 2-5 s after the splash
screen before rendering the UI while `discover_mcp_tools()` ran
synchronously on the critical path.

Changes:
- tools/mcp_tool.py: add `discover_mcp_tools_background()` — thin
  wrapper that spawns `discover_mcp_tools()` on a named daemon thread
- tui_gateway/entry.py: call `discover_mcp_tools_background()` before
  sending gateway.ready (replaces inline call that blocked the JSON-RPC
  pipe for the TUI Ink app)
- hermes_cli/main.py:
  - skip `\_prepare_agent_startup()` for TUI path — plugins, MCP, and
    shell hooks are only needed by the CLI agent loop; the TUI's
    gateway subprocess discovers them independently (~370 ms saved)
  - fast-path in `\_make_tui_argv()`: when `dist/entry.js` exists and
    is fresh, skip npm install / rebuild checks entirely (~350 ms saved)
- cli.py (`\_prepare_deferred_agent_startup`): same background pattern
  for deferred startup (Termux interactive CLI)
- acp_adapter/entry.py: same pattern so ACP server launches asyncio
  immediately while MCP connects in parallel

Result:
- TUI Python wrapper: ~730 ms → ~80 ms (9× faster)
- gateway.ready: ~2700 ms → ~400 ms (7× faster)
- Total TUI cold start: ~3400 ms → ~480 ms

Related: #29726, #29184, #19326 (closed stale)

Closes #29726

acp_adapter/entry.py

@@ -247,16 +247,22 @@ def main(argv: list[str] | None = None) -> None:
     import acp
     from .server import HermesACPAgent
 
-    # MCP tool discovery from config.yaml — run before asyncio.run() so
-    # it's safe to use blocking waits.  (ACP also registers per-session
-    # MCP servers dynamically via asyncio.to_thread inside the event
-    # loop; that path is unaffected.)  Moved from model_tools.py module
-    # scope to avoid freezing the gateway's loop on lazy import (#16856).
+    # MCP tool discovery from config.yaml — fire-and-forget in a
+    # background daemon thread so the ACP server becomes responsive
+    # immediately while MCP servers connect.  Previously this blocked
+    # asyncio.run() for 2-5 s.  (ACP also registers per-session MCP
+    # servers dynamically via asyncio.to_thread inside the event loop;
+    # that path is unaffected.)  Moved from model_tools.py module scope
+    # to avoid freezing the gateway's loop on lazy import (#16856).
     # Metadata-only hosts can opt out of unrelated global MCP startup.
     if os.environ.get("HERMES_ACP_SKIP_CONFIGURED_MCP", "").strip() != "1":
         try:
-            from tools.mcp_tool import discover_mcp_tools
-            discover_mcp_tools()
+            from hermes_cli.mcp_startup import start_background_mcp_discovery
+
+            start_background_mcp_discovery(
+                logger=logger,
+                thread_name="acp-mcp-discovery",
+            )
         except Exception:
             logger.debug("MCP tool discovery failed at ACP startup", exc_info=True)