Support multimodal tool

[guanxuc]

AgentScope-Java Version

1.0.4-SNAPSHOT

Description

• Closes: [Feature] Text to Multi-Modal Tool Support #90
• Support dashscope multimodal tool
• Support openai multimodal tool

Checklist

Please check the following items before code is ready to be reviewed.

• Code has been formatted with mvn spotless:apply
• All tests are passing (mvn test)
• Javadoc comments are complete and follow project conventions
• Related documentation has been updated (e.g. links, examples, etc.)
• Code is ready for review

[codecov]

Codecov Report

❌ Patch coverage is 87.42964% with 67 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
...ope/core/tool/multimodal/OpenAIMultiModalTool.java	88.35%	17 Missing and 17 partials ⚠️
.../core/tool/multimodal/DashScopeMultiModalTool.java	87.61%	17 Missing and 10 partials ⚠️
.../java/io/agentscope/core/formatter/MediaUtils.java	73.91%	3 Missing and 3 partials ⚠️

📢 Thoughts on this report? Let us know!

[Copilot]

Pull request overview

This PR adds comprehensive multimodal tool support for both OpenAI and DashScope platforms, enabling text-to-image, image-to-text, text-to-audio, and audio-to-text conversions.

Key Changes:

• Implements OpenAI multimodal tools (DALL-E, GPT-4 Vision, Whisper, TTS)
• Implements DashScope multimodal tools (Wanx, Qwen-VL, Paraformer, Sambert)
• Extends MediaUtils with new utility methods for handling file/URL conversions and image processing
• Adds comprehensive unit and E2E tests for both implementations

Reviewed changes

Copilot reviewed 10 out of 12 changed files in this pull request and generated 10 comments.

Show a summary per file

File	Description
pom.xml	Adds mockito-junit-jupiter dependency for enhanced testing capabilities
agentscope-dependencies-bom/pom.xml	Defines mockito-junit-jupiter version in dependency management
OpenAIMultiModalTool.java	Implements OpenAI multimodal conversions with comprehensive error handling
DashScopeMultiModalTool.java	Implements DashScope multimodal conversions with streaming audio support
MediaUtils.java	Adds URL/file handling utilities, RGBA image conversion, and protocol URL methods
OpenAIMultiModalToolTest.java	Provides comprehensive unit tests with mocking for OpenAI tools
DashScopeMultiModalToolTest.java	Provides comprehensive unit tests with mocking for DashScope tools
OpenAIMultiModalToolE2ETest.java	Provides E2E tests for OpenAI API integration
DashScopeMultiModalToolE2ETest.java	Provides E2E tests for DashScope API integration
MediaUtilsTest.java	Adds tests for new MediaUtils methods

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 12 out of 14 changed files in this pull request and generated 8 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.