Skip to content

Add latest model constants (#229)#234

Merged
lzsweb merged 6 commits into
mainfrom
dev/issues-2
Jun 18, 2026
Merged

Add latest model constants (#229)#234
lzsweb merged 6 commits into
mainfrom
dev/issues-2

Conversation

@lzsweb

@lzsweb lzsweb commented Jun 17, 2026

Copy link
Copy Markdown
Collaborator

Summary

Test plan

  • mvn compile passes

🤖 Generated with Claude Code

Co-Authored-By: Claude Opus 4.7 noreply@anthropic.com

zhansheng.lzs and others added 3 commits June 17, 2026 10:26
The workflow streaming API now returns parent_node_id to indicate
parent-child relationships between workflow nodes.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Generation: add qwen3.x (3.7-max/plus, 3.6-plus/flash, 3.5-plus/flash),
qwen3-coder (plus/flash/next), qwq-plus, qvq-max/plus, qwen-flash, qwen-long.

MultiModalConversation: add qwen-vl-max/ocr, qwen3-vl-plus/flash,
qwen-omni-turbo, qwen3/qwen3.5-omni-flash/plus.

VideoSynthesis: add wan2.6 (t2v/i2v/r2v), wan2.7 (t2v/i2v/r2v/videoedit),
happyhorse i2v/r2v/video-edit.

ImageGeneration: add wan2.7 (t2v/i2v/image/image-pro/videoedit/r2v),
qwen-image/edit/2.0/2.0-pro/plus/max/edit-plus.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request bumps the SDK version to 2.22.23 and adds several new model constants across different generation tasks, including text generation (Qwen, Qwen3, QWQ, QVQ), image generation (WanX2.7, Qwen Image), multimodal conversation (Qwen VL, Omni), and video synthesis (Wan2.6, Wan2.7, HappyHorse). It also adds a parentNodeId field to WorkflowMessage. The review feedback highlights two main issues: first, video synthesis models were incorrectly added to the ImageGeneration class and should be removed; second, the newly added Wan models in VideoSynthesis should be renamed to use the WANX_ prefix instead of WAN to maintain naming consistency with existing constants.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

Comment thread src/main/java/com/alibaba/dashscope/aigc/imagegeneration/ImageGeneration.java Outdated
Comment thread src/main/java/com/alibaba/dashscope/aigc/videosynthesis/VideoSynthesis.java Outdated
zhansheng.lzs and others added 2 commits June 17, 2026 11:35
- Remove video models (t2v/i2v/videoedit/r2v) from ImageGeneration
- Remove WAN2_6_* from VideoSynthesis (WAN_2_7_* supersedes)
- Remove WanX2_6_IMAGE from ImageGeneration (WanX2_7_IMAGE supersedes)
- Use WAN_ prefix for new video synthesis constants instead of WAN2_

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Generation: remove qwen3.5, qwen3.6, qwq, qvq (qwen3.7 covers these).
VideoSynthesis: remove wanx2.1 t2v/i2v (wan2.7 supersedes), keep kf2v.
ImageGeneration: rename WanX2_7 to WAN_2_7 for naming consistency.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Adds WANX_2_1_T2V_PLUS, WANX_2_1_T2V_TURBO, WANX_2_1_I2V_PLUS, and WANX_2_1_I2V_TURBO constants to VideoSynthesis.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
@lzsweb lzsweb merged commit 5eed3ed into main Jun 18, 2026
3 checks passed
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.

dashscope-sdk-java 作为官方 SDK,内置的模型 ID 常量已经过时很久了

1 participant