Add MCP server support and image input to Realtime API #180
Conversation
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
- Extend Content type to support both text and image inputs
- Add image case with base64 data URL format
- Support data:image/{format};base64,{bytes} format
- Add flexible Item initializer for multi-content messages
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add RealtimeTool enum supporting both function and MCP tools - Rename Tool to FunctionTool to avoid naming conflicts - Support Tool.MCPTool from shared Tool enum - Enable MCP server integration in Realtime sessions 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add mcpListToolsInProgress, mcpListToolsCompleted, mcpListToolsFailed message cases - Implement comprehensive MCP error logging with full JSON payload inspection - Extract error details from nested and top-level fields (message, code, reason) - Add debug logging for MCP tool discovery lifecycle This enables proper MCP (Model Context Protocol) server integration diagnostics and helps identify authentication and configuration issues. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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
This PR adds comprehensive MCP (Model Context Protocol) server support and image input capabilities to the SwiftOpenAI Realtime API implementation.
Changes Included
1. Image Input Support (ea86a16)
Contentfrom struct to enum supporting both text and image inputsdata:image/{format};base64,{bytes})Iteminitializer accepting multiple content types2. MCP Server Configuration (12a8dc2)
RealtimeToolenum supporting both function tools and MCP toolsToolstruct toFunctionToolto avoid naming conflictsTool.MCPToolfrom shared Tool enum3. MCP Message Types and Error Logging (da4200f)
OpenAIRealtimeMessage:mcpListToolsInProgressmcpListToolsCompleted([String: Any])mcpListToolsFailed(String?)OpenAIRealtimeSessionFiles Modified
Sources/OpenAI/Public/Parameters/Realtime/OpenAIRealtimeConversationItemCreate.swiftSources/OpenAI/Public/Parameters/Realtime/OpenAIRealtimeSessionConfiguration.swiftSources/OpenAI/Private/Realtime/OpenAIRealtimeSession.swiftSources/OpenAI/Public/ResponseModels/Realtime/OpenAIRealtimeMessage.swiftTesting
These changes have been tested with:
Breaking Changes
Toolstruct renamed toFunctionToolinOpenAIRealtimeSessionConfiguration