mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-30 01:41:43 +00:00
dd789a4fdf
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.
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| entry.py | ||
| event_publisher.py | ||
| render.py | ||
| server.py | ||
| slash_worker.py | ||
| transport.py | ||
| ws.py | ||