Repository navigation
Conversation
…or "none" #687 wrote that only LiteLLM below 1.110 sends no thinking field for reasoning_effort "none". 1.110 fixed that for claude-haiku-5-5, claude-sonnet-5 and claude-opus-5 (BerriAI/litellm#47924) but not for claude-sonnet-5-5 (#44298), so a reader trusting the comment could drop the ladder and leave Sonnet 5.5 thinking unseen. get_optional_params with reasoning_effort "none": 1.109 sends no thinking field for any of the four; 1.110 sends thinking disabled for three and none for sonnet-5-5.
Codex Review Summary: ✅ CompletedThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The comment on the Claude "none" ladder now says LiteLLM 1.110 still sends claude-sonnet-5-5 no thinking field for "none". #687 said only versions below 1.110 do, which could lead someone to drop the ladder and leave Sonnet 5.5 thinking unseen.
Changes
pageindex/utils.py: the_CLAUDE_LADDERcomment names both cases: below 1.110 on any Claude ([Bug]: reasoning_effort="none" omits thinking instead of disabling it on default-on Claude models BerriAI/litellm#47924), and on claude-sonnet-5-5 in 1.110 too (#44298). Comment only.Verification
get_optional_params(..., reasoning_effort="none"): on 1.109 no thinking field for claude-haiku-5-5, claude-sonnet-5, claude-opus-5 or claude-sonnet-5-5; on 1.110 thinking disabled for the first three and none for claude-sonnet-5-5.