anthropic: warn instead of silently downgrading or dropping thinking effort. - #757
Open
copybara-service[bot] wants to merge 1 commit into
Open
anthropic: warn instead of silently downgrading or dropping thinking effort.#757copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
copybara-service
Bot
force-pushed
the
test_967903055
branch
2 times, most recently
from
August 21, 2026 21:04
c93c6c0 to
87ac63d
Compare
…effort. Previously, a per-call `reasoning_effort` could silently downgrade a model's configured `effort`, and an explicitly configured `effort` was silently dropped when thinking was disabled or on non-adaptive models. The effort configuration is now honest: a value that cannot be honored is reported via a warning instead of being silently dropped or downgraded. Wire behavior is unchanged; only logging is added. PiperOrigin-RevId: 967903055
copybara-service
Bot
force-pushed
the
test_967903055
branch
from
August 21, 2026 21:16
87ac63d to
fa182dd
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
anthropic: warn instead of silently downgrading or dropping thinking effort.
Previously, a per-call
reasoning_effortcould silently downgrade a model's configuredeffort, and an explicitly configuredeffortwas silently dropped when thinking was disabled or on non-adaptive models. The effort configuration is now honest: a value that cannot be honored is reported via a warning instead of being silently dropped or downgraded. Wire behavior is unchanged; only logging is added.