Improved prompt for immediate action
Additional logging of tool names
Updated documentation
Context aware decomposition system prompt
New script to run code quality checks
Docs added to show how a new tool is created
All tools should add numbers to code for models to be able to reference if needed
Enabled line numbering for code for all tools to use
Additional tests to validate line numbering is not added to git diffs
Supports decomposing large components and files, finding codesmells, finding modernizing opportunities as well as code organization opportunities. Fix this mega-classes today!
Line numbers added to embedded code for better references from model -> claude
Further fixes to tests
Pass O3 simulation test when keys are not set, along with a notice
Updated docs on testing, simulation tests / contributing
Support for OpenAI o4-mini and o4-mini-high
* Support for Custom URLs and custom models, including locally hosted models such as ollama
* Support for native + openrouter + local models (i.e. dozens of models) means you can start delegating sub-tasks to particular models or work to local models such as localizations or other boring work etc.
* Several tests added
* precommit to also include untracked (new) files
* Logfile auto rollover
* Improved logging
Changed all Claude Desktop configuration examples to use 'zen' as the mcpServers key
for consistency with project naming (zen-mcp-server, zen-mcp-redis). This aligns the
configuration naming with Docker service names and repository naming conventions.
Users will need to update their claude_desktop_config.json files to use 'zen' instead
of 'gemini' as the server key.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Updated claude mcp add/remove commands from 'gemini' to 'zen' to match the docker-compose.yml
service names and maintain consistency across the project. All container references now
align with zen-mcp-server, zen-mcp-redis naming convention.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
The documentation incorrectly stated that DEFAULT_MODEL defaults to gemini-2.5-pro-preview-06-05,
when in fact config.py defaults to 'auto' mode if the environment variable is not set. Updated
the table to clarify that the server uses 'auto' mode (Claude picks best model) when no
DEFAULT_MODEL env var is provided to the Docker container.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Repository URL consistency: Updated all references to BeehiveInnovations/zen-mcp-server format
- Documentation clarity: Fixed misleading table headers and improved Docker configuration examples
- File conventions: Added missing final newlines to all files
- Configuration consistency: Clarified API key placeholder format in documentation
Addresses all points raised in PR #17 review by Gemini Code Assist.
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
