Skip to content

feat: add vision toggle for agents#11504

Closed
JumpLink wants to merge 5 commits intodanny-avila:mainfrom
faktenforum:feat/agent-vision-toggle
Closed

feat: add vision toggle for agents#11504
JumpLink wants to merge 5 commits intodanny-avila:mainfrom
faktenforum:feat/agent-vision-toggle

Conversation

@JumpLink
Copy link
Copy Markdown

Adds a vision boolean toggle to agent configuration, allowing users to control vision capability per agent. This works together with the agents package PR to filter image artifacts when vision is disabled.

Related to: #11418 (partially addresses)
Related PRs:

Changes

  • Add vision to AgentCapabilities enum and default capabilities
  • Add vision?: boolean field to Agent type and validation schema
  • Add vision toggle UI component for agents with hover card and info description
  • Include vision in agent create/update payload
  • Pass vision from agent to AgentInputs in run API
  • Remove modelSpecs parameter from createRun() API (agents use direct vision toggle)

Benefits

  • Agent-level control: users can enable/disable vision per agent via UI toggle
  • Consistent pattern: follows same approach as end_after_tools and hide_sequential_outputs
  • Enables artifact filtering in agents package (requires agents PR)
  • Clear UI: "Image Vision" heading with "Enable Image Vision" checkbox and info tooltip

Dependencies

Testing

  • Verify vision toggle appears in agent capabilities section with "Image Vision" heading
  • Verify "Enable Image Vision" checkbox and info tooltip are displayed
  • Verify vision setting is saved/loaded correctly
  • Verify vision is passed to agents package correctly

Add `vision` boolean field to modelSpecs configuration to explicitly
declare model vision support. This enables proper filtering of image
artifacts for non-vision models and UI gating for image upload options.

- Add vision field to TModelSpec type/schema
- Extend validateVisionModel() to check modelSpecs first
- Pass modelSpecs from API to agents package
- Update UI components to use vision capability check
- Removed direct calls to validateVisionModel in AttachFileMenu and DragDropModal components.
- Introduced useVisionModel hook to encapsulate vision model validation logic.
- Updated imports to reflect the new hook usage, improving code modularity and readability.
- Remove modelSpecs parameter from createRun() function
- Remove modelSpecs conversion logic (handled by agent-level vision toggle)
- Remove modelSpecs from createRun() call in client.js
- This keeps PR 11501 focused on modelSpecs vision for UI gating only
- Add vision to AgentCapabilities enum and default capabilities
- Add vision?: boolean field to Agent type and validation schema
- Add vision toggle UI component for agents with hover card and info description
- Include vision in agent create/update payload
- Pass vision from agent to AgentInputs in run API

Depends on PR danny-avila#11501 (modelSpecs vision) for validateVisionModel function
@JumpLink JumpLink force-pushed the feat/agent-vision-toggle branch from 1a0d2ff to 3ec5bea Compare January 24, 2026 18:02
@JumpLink JumpLink closed this Jan 25, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant