- Changed Go version requirement from 1.24+ to 1.26.5+ in multiple tutorial and contributing documents to ensure compatibility with the latest features and security updates.
- Updated search index keywords for improved searchability and relevance.
- Set pnpm version to 10.34.5 in the GitHub Actions workflow for publishing documentation.
- Removed pnpm overrides from package.json and added package manager specification.
- Created a new pnpm-workspace.yaml file to manage package overrides for webpack-dev-server.
- Updated search-index.json to refine keyword entries for improved searchability.
- Added new guides for Anthropic and Google Gemini to the getting started section.
- Updated existing guides for Ollama, OpenAI, and Mistral to correct example links.
- Improved clarity in the architecture documentation regarding streaming responses and memory implementation.
- Enhanced structured output handling and reasoning options across various model integrations.
- Fixed minor formatting issues and updated references to ensure consistency throughout the documentation.
- Removed deprecated RedactedThinkingContent from search index and adjusted related tests to enhance clarity.
- Updated CountTokens test to reflect correct expected token count.
- Refactored marshaling tests to streamline reasoning content handling, removing unnecessary redacted content checks.
- Modified CallOptions struct to use pointers for optional fields, improving memory efficiency and consistency.
- Enhanced test cases for CallOptions to validate new pointer-based logic and default values.
- Updated Anthropic client to utilize new CallOptions methods for better encapsulation and maintainability.
- Introduced reasoning content handling in MessageContent and ToolCall structures, allowing for the preservation of reasoning details during JSON marshaling and unmarshaling.
- Enhanced tests to validate the serialization and deserialization of message content with reasoning, covering various scenarios including text and tool call types.
- Updated marshaling logic to conditionally include reasoning data based on its presence, ensuring accurate representation in JSON format.
- Added new reasoning-related tests to ensure comprehensive coverage of the new functionality.
- Updated reasoning handling in the Anthropic and OpenAI clients to support real-time streaming of reasoning tokens.
- Refactored reasoning structures to improve integration with existing models, ensuring consistent behavior across different LLM implementations.
- Added comprehensive tests for reasoning and caching functionalities, validating the expected behavior in various scenarios.
- Removed deprecated files related to previous caching implementations to streamline the codebase.
This update improves the overall performance and reliability of reasoning capabilities in LLM interactions.
Dmitry Ng