[aisdk] Set model config for CUA models #576
Merged
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
loreto
approved these changes
Nov 10, 2025
| SystemMessageMode: "developer", | ||
| RequiredAutoTruncation: false, | ||
| } | ||
| } else if len(modelID) > 0 && strings.HasPrefix(modelID, "computer") { |
Contributor
There was a problem hiding this comment.
Make the prefix "computer-use" to be safer?
ipince
force-pushed
the
rodrigo/aisdk-cua-truncation
branch
from
5ca0c82 to
93de906
Compare
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Outdated suggestions cannot be applied.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.
Summary
CUA models require auto-truncation.
I also set
isReasoningandsystemMessageModeto match what Vercel's AISDK sets for them, but honestly I'm not sure how those fields are used... The inference calls worked just fine whether the roles were "system" or "developer".Also, it seems that CUA is indeed a "reasoning model", because we do get reasoning output from it, even if it's not listed as a reasoning model in OpenAI's docs. But, OpenAI's docs also say that reasoning models do not support temperature, but we do set temperature (after loop-detection) and it does seem to work... so I'm a bit confused here. I might have to change some of the AISDK code that currently enforces that temperature is NOT set for reasoning models.
How was it tested?
Ran
testpilot testwhile pulling these local changes.Community Contribution License
All community contributions in this pull request are licensed to the project maintainers under the terms of the Apache 2 License.
By creating this pull request I represent that I have the right to license the contributions to the project maintainers under the Apache 2 License as stated in the Community Contribution License.