mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-20 00:11:50 +00:00
Match candidates are restricted to the request's own tool names via route_filter, so routes learned from other principals' listings cannot displace the caller's tools from top_k. Lazy indexing now uses the async aadd flow exclusively; an embedding failure, including a context-window overflow on an oversized description, raises for the requesting call only and never writes the shared context_window_error, so one request cannot poison the filter for every user on the worker. The router is also sized to the configured top_k, which the semantic-router index layer otherwise silently caps at its default of 5. |
||
|---|---|---|
| .. | ||
| mcp_server | ||