fix(mcp): move discovery out of model_tools import side effect (#16856) (#16899)

model_tools.py ran discover_mcp_tools() as a module-level side effect.
discover_mcp_tools() uses a blocking 120s wait internally (via
_run_on_mcp_loop -> future.result(timeout=120)).

The gateway lazy-imports run_agent -> model_tools on the first user
message, which happens inside the asyncio event loop thread.  A slow or
unreachable MCP server therefore froze Discord shard heartbeats and
Telegram polling for up to 120s on the first message after gateway
start.

Fix: remove the module-level call.  Every entry point now runs
discovery explicitly at its own startup, using the context-appropriate
blocking/non-blocking pattern:

- gateway/run.py:       loop.run_in_executor(None, discover_mcp_tools)
                        before platforms start accepting traffic
- hermes_cli/main.py:   inline (no event loop at CLI startup)
- tui_gateway/entry.py: inline (sync stdin loop, no event loop)
- acp_adapter/entry.py: inline before asyncio.run()

Closes #16856.

acp_adapter/entry.py

@@ -112,6 +112,17 @@ def main() -> 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).
+    try:
+        from tools.mcp_tool import discover_mcp_tools
+        discover_mcp_tools()
+    except Exception:
+        logger.debug("MCP tool discovery failed at ACP startup", exc_info=True)
+
     agent = HermesACPAgent()
     try:
         asyncio.run(acp.run_agent(agent, use_unstable_protocol=True))