Conversation
Contributor
Author
|
Superseded by updated PR from current main |
This was referenced Aug 15, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
vision_analyzeandbrowser_visionboth return truncated responses when analyzing complex images. The auxiliary vision model is called with a hardcodedmax_tokens: 2000cap, so descriptions of complex screenshots get cut off mid-sentence at exactly 2000 tokens.Root cause — two files, same pattern
tools/vision_tools.py"max_tokens": 2000tools/browser_tool.py"max_tokens": 2000Both correctly read
timeoutandtemperaturefromauxiliary.visionconfig, but skipmax_tokensentirely — so there is no way to raise it without editing source.Fix
In both files, add config reading for
max_tokensright after thetemperatureblock (which already readstimeoutandtempfrom config), and use the configured value with a fallback to 2000:Then replace
"max_tokens": 2000→"max_tokens": vision_max_tokens.Users can now configure it in
config.yaml:Related issues/PRs
auxiliary.vision.max_tokensfrom configagent/auxiliary_client.pybut NOTvision_tools.pyorbrowser_tool.py(they build their own kwargs dicts manually)Verification
All 139 vision-related tests pass: