feat: Add OPENHANDS_FORCE_VISION env var to override vision capability detection #10255
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Outdated suggestions cannot be applied.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.
End-user friendly description of the problem this fixes or functionality this introduces.
LiteLLM sometimes misreports vision capability for models that actually support it. This change allows users to manually enable vision support by setting the OPENHANDS_FORCE_VISION environment variable.
Summarize what the PR does, explaining any non-trivial design decisions.
This PR adds an environment variable check to _supports_vision that, if set to 1, true, yes, or on (case-insensitive), will override LiteLLM’s detection and force vision capability to be reported as supported. The implementation only applies the override if explicitly enabled.
Link of any specific issues this addresses:
#9750