10000 Support audio content type in tools/call and prompts/get by dugenkui03 · Pull Request #250 · mark3labs/mcp-go · GitHub
[go: up one dir, main page]
Skip to content

Support audio content type in tools/call and prompts/get #250

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 2 commits into from
May 8, 2025
Merged

Support audio content type in tools/call and prompts/get #250

merged 2 commits into from
May 8, 2025

Conversation

dugenkui03
Copy link
Collaborator
@dugenkui03 dugenkui03 commented May 6, 2025 •
edited
Loading

details in #243

Summary by CodeRabbit

  • New Features
    • Added support for audio content in prompts and tool call results, allowing audio data to be included alongside text and images.
  • Bug Fixes
    • Enhanced test coverage to verify correct handling of audio content in responses.
  • Documentation
    • Updated comments to reflect audio content as a valid type in relevant structures.

@coderabbitai coderabbitai
Copy link
Contributor
coderabbitai bot commented May 6, 2025 •
edited
Loading

"""

Walkthrough

This change introduces support for handling audio content in the MCP client and related data structures. It adds a new AudioContent type, updates comments and parsing logic to recognize audio content, and extends test cases and helper functions to include and validate audio data alongside existing text and image content.

Changes

Files/Paths Change Summary
mcp/types.go Added AudioContent struct and its interface method; updated SamplingMessage.Content comment to include audio.
mcp/utils.go Added AsAudioContent, NewAudioContent, and NewToolResultAudio functions; extended ParseContent to support audio content.
client/inprocess_test.go Enhanced test setup and assertions to include audio content in tool and prompt responses.
mcp/prompts.go, mcp/tools.go Updated comments on Content fields in PromptMessage and CallToolResult to document support for AudioContent.

Possibly related PRs

  • change to strong content type #26: Refactored the Content field to use a strong typed interface and updated parsing logic, which this PR builds upon to add audio content support.

Suggested reviewers

  • ezynda3
    """
📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between b7f2605 and ea87396.

📒 Files selected for processing (5)
  • client/inprocess_test.go (4 hunks)
  • mcp/prompts.go (1 hunks)
  • mcp/tools.go (1 hunks)
  • mcp/types.go (2 hunks)
  • mcp/utils.go (4 hunks)
✅ Files skipped from review due to trivial changes (1)
  • mcp/prompts.go
🚧 Files skipped from review as they are similar to previous changes (4)
  • mcp/tools.go
  • client/inprocess_test.go
  • mcp/utils.go
  • mcp/types.go
✨ Finishing Touches
  • 📝 Generate Docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

coderabbitai[bot]
coderabbitai bot reviewed May 6, 2025
View reviewed changes
Copy link
Contributor
@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 2

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between f47e2bc and b7f2605.

📒 Files selected for processing (5)
  • client/inprocess_test.go (4 hunks)
  • mcp/prompts.go (1 hunks)
  • mcp/tools.go (1 hunks)
  • mcp/types.go (2 hunks)
  • mcp/utils.go (4 hunks)
🧰 Additional context used
🧬 Code Graph Analysis (3)
mcp/prompts.go (1)
mcp/types.go (1)
  • Content (684-686)
mcp/tools.go (1)
mcp/types.go (1)
  • Content (684-686)
client/inprocess_test.go (2)
mcp/types.go (4)
  • AudioContent (714-721)
  • AudioContent (723-723)
  • Content (684-686)
  • Params (118-118)
mcp/prompts.go (2)
  • Role (68-68)
  • RoleUser (71-71)
🔇 Additional comments (11)
mcp/prompts.go (1)

81-81: Documentation update looks good.

The comment has been updated to include AudioContent as a valid content type alongside the existing types in the PromptMessage struct. This aligns well with the implementation of the new audio content type in the MCP protocol.

mcp/tools.go (1)

36-36: Documentation update looks good.

The comment has been properly updated to include AudioContent as a valid content type alongside the existing types in the CallToolResult struct. This change is consistent with the audio content support being added to the MCP protocol.

client/inprocess_test.go (5)

39-43: Audio content implementation in test tool looks good.

Adding AudioContent to the test tool's response appropriately tests the newly added audio content type support. The structure includes all required fields for audio content.

85-92: Adding audio content to test prompt messages is appropriate.

Good implementation of audio content in the prompt message with the user role. This properly tests the bidirectional support for audio content in the protocol.

208-209: Test assertion updated correctly.

The assertion has been properly updated to expect 2 content items (text and audio) in the tool call response.

375-377: Adding required arguments to the GetPrompt request is appropriate.

Adding argument data to match the prompt's expected arguments is necessary for the test to work properly with the implementation.

384-385: Test assertion updated correctly.

The assertion has been properly updated to expect 2 messages in the prompt response (one from assistant with text content and one from user with audio content).

mcp/types.go (2)

659-659: Documentation update for SamplingMessage looks good.

The comment has been updated to include AudioContent as a valid content type for the SamplingMessage struct, which is consistent with the changes in the rest of the codebase.

712-724: AudioContent implementation looks good.

The AudioContent struct is well-implemented with appropriate fields:

  • Type field to identify it as "audio"
  • Data field for base64-encoded audio content
  • MIMEType field for the audio format specification
  • isContent() method implementation to satisfy the Content interface

This implementation follows the same pattern as the existing TextContent and ImageContent types, maintaining consistency in the codebase.

mcp/utils.go (2)

216-223: Looks good!

The implementation of NewAudioContent correctly follows the established pattern for content creation functions in this file.

456-463: Looks good!

The implementation of audio content parsing in the ParseContent function correctly follows the pattern used for other content types.

@dugenkui03 dugenkui03 force-pushed the support_audio_content_type branch from b7f2605 to ea87396 Compare May 6, 2025 10:30
@dugenkui03 dugenkui03 mentioned this pull request May 6, 2025
Closed
@ezynda3 ezynda3 merged commit cb632f2 into mark3labs:main May 8, 2025
2 checks passed
tendant pushed a commit to tendant/mcp-go that referenced this pull request May 8, 2025
@dugenkui03 @tendant
support audio content type (mark3labs#250)
55897af
@ghchinoy ghchinoy mentioned this pull request May 10, 2025
Closed
adlternative pushed a commit to adlternative/mcp-go that referenced this pull request May 20, 2025
@dugenkui03 @adlternative
support audio content type (mark3labs#250)
99d2ae7
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@coderabbitai coderabbitai[bot] coderabbitai[bot] left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@dugenkui03 @ezynda3
0