Max tokens fixes #1092
Merged
Max tokens fixes #1092
Conversation
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
Since it's optional Signed-off-by: Djordje Lukic <djordje.lukic@docker.com>
Signed-off-by: Djordje Lukic <djordje.lukic@docker.com>
dgageot
approved these changes
Dec 15, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
If no
max_tokenswere set we would set it to 8k in the anthropic case. This is way less than the 64k that its models can do.We will now look at the models.dev data to get the limit and use it if it's defined, if not we set 32k as a more sensible default.
If a limit is set in the yaml we take that one of course.
Fixes #1090