ReasoningConfig documentation to clarify dependency on effort and max_tokens settings. This update specifies that enabling either of these parameters requires reasoning in OpenRouter to be set to Enabled.

This commit is contained in:
teknium 2026-01-12 17:45:19 +00:00
parent 21504537fc
commit 6aba5244b8

View file

@ -53,6 +53,8 @@ class ReasoningConfig:
# (e.g., Anthropic's latest models support up to 128k extended thinking)
# Auto-enable if effort or max_tokens are specified
# Because if either of these are enabled, reasoning in
# OpenRouter must also be set to Enabled
if self.effort is not None or self.max_tokens is not None:
self.enabled = True