Add Yutori Navigator as a CUA engine (#5513)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Shuchang Zheng <wintonzheng0325@gmail.com>
This commit is contained in:
Lawrence Chen 2026-05-24 21:38:20 -07:00 committed by GitHub
parent 6b9d7b0eda
commit aa51d2eb6c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
30 changed files with 1003 additions and 31 deletions

View file

@ -291,6 +291,7 @@
"openai_cua": "#/components/schemas/TaskRunResponse",
"anthropic_cua": "#/components/schemas/TaskRunResponse",
"ui_tars": "#/components/schemas/TaskRunResponse",
"yutori_navigator": "#/components/schemas/TaskRunResponse",
"workflow_run": "#/components/schemas/WorkflowRunResponse"
}
},
@ -17352,10 +17353,11 @@
"task_v2",
"openai_cua",
"anthropic_cua",
"ui_tars"
"ui_tars",
"yutori_navigator"
],
"title": "Run Type",
"description": "Types of a task run - task_v1, task_v2, openai_cua, anthropic_cua, ui_tars"
"description": "Types of a task run - task_v1, task_v2, openai_cua, anthropic_cua, ui_tars, yutori_navigator"
},
"run_request": {
"anyOf": [

View file

@ -25,6 +25,7 @@ This parameter defines the engine that powers the agent task.
- `openai-cua`: uses OpenAI's CUA model.
- `anthropic-cua`: uses Anthropic's Claude Sonnet 3.7 model with the computer use tool.
- `ui-tars`: uses the UI-TARS model (Seed1.5-VL) via Doubao API for computer vision and GUI automation with multi-turn conversation support (https://seed.bytedance.com/zh/tech/seed1_5_vl).
- `yutori-navigator`: uses Yutori's Navigator computer-use model for visual browsing with tool-calling support (https://docs.yutori.com/reference/navigator).
### [Data Extraction Schema](/api-reference/api-reference/agent/run-task#request.body.data_extraction_schema)