docs(mcp): fix stale ~0.75s discovery-wait reference in late-refresh docstring

The MCP discovery wait is now bounded by the config-driven mcp_discovery_timeout
(default 1.5s), not the old 0.75s flat value. Updates the _schedule_mcp_late_refresh
docstring that still cited ~0.75s after #49208 made the bound configurable.
This commit is contained in:
teknium1 2026-06-19 11:58:42 -07:00 committed by Teknium
parent b337afdf6e
commit 98ecd0beeb

View file

@ -3526,7 +3526,8 @@ def _schedule_mcp_late_refresh(sid: str, agent) -> None:
The agent snapshots ``agent.tools`` once at build time and never re-reads
the registry (run_agent/agent_init). ``_make_agent`` briefly joins the
background MCP discovery thread (``wait_for_mcp_discovery``, ~0.75s) so
background MCP discovery thread (``wait_for_mcp_discovery``, bounded by the
``mcp_discovery_timeout`` config value, default 1.5s) so
already-spawning servers land in that snapshot but a server that takes
longer than the bound to connect (common for an HTTP MCP server on first
connect) lands *after* the agent is built. Its tools are then absent from