mirror of
https://github.com/PrefectHQ/fastmcp.git
synced 2026-09-01 12:03:19 +02:00
Add configurable max_sampling_rounds parameter to ctx.sample() to allow users to control the maximum number of tool-calling iterations (defaults to 100). This prevents infinite loops if the LLM repeatedly calls tools without converging on a final response. Co-authored-by: Bill Easton <strawgate@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_max_sampling_rounds.py | ||
| test_sampling_tool.py | ||