Add Aliyun GUI-OWL coordinate fix and GUI-Plus model support#112
Merged
tsubasakong merged 2 commits intomainfrom Mar 16, 2026
Merged
Add Aliyun GUI-OWL coordinate fix and GUI-Plus model support#112tsubasakong merged 2 commits intomainfrom
tsubasakong merged 2 commits intomainfrom
Conversation
- Fix GUI-OWL (pre-gui_owl_7b) coordinate rescaling from 1000x1000 normalized space to actual device pixel dimensions - Add GUI-Plus model client with smart_resize coordinate conversion - Add aliyun_gui_plus backend type and model provider preset - Wire GUI-Plus execution loop into runtime attempt - Handle SWIPE as alias for SCROLL in GUI-Plus responses - Include official Aliyun system prompt adapted for mobile Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Add supporting changes required for Aliyun model integration: - Human-auth relay: signed screenshot URL support for GUI-OWL - Setup wizard: Aliyun UI Agent provider onboarding flow - CLI: backend recognition for aliyun models - Dashboard control-store: Aliyun backend handling - Frontend docs: configuration and troubleshooting for Aliyun models - Tests for all the above Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
pre-gui_owl_7b) coordinate rescaling from 1000x1000 normalized space to device pixelsgui-plus) model client withsmart_resizecoordinate conversionSWIPEaction as alias forSCROLLwith direction/amountWhy
The Aliyun GUI-OWL model outputs coordinates in a 1000x1000 normalized space, causing taps to land off-screen on devices with different resolutions (e.g. 720x1600). The newer GUI-Plus model offers a standard DashScope API with improved capabilities but had no integration.
Changes
src/agent/aliyun-ui-agent-client.ts— GUI-OWL client with 1000x1000 coordinate rescalingsrc/agent/aliyun-gui-plus-client.ts— GUI-Plus client withsmart_resizecoordinate conversion and official Aliyun system promptsrc/types.ts— addedaliyun_gui_plusbackend typesrc/config/model-provider-presets.ts— GUI-Plus provider presetsrc/agent/runtime/attempt.ts— GUI-Plus execution loop (inline base64 screenshots, no ngrok needed)src/human-auth/local-stack.ts— signed screenshot URL support for GUI-OWLsrc/onboarding/setup-wizard.ts— Aliyun provider onboarding flowTesting
Manual testing: verified GUI-OWL swipes and GUI-Plus SCROLL actions execute on 720x1600 physical device.
Checklist
Closes #111