Migration from Docker to Standalone Python Server (#73)

* Migration from docker to standalone server
Migration handling
Fixed tests
Use simpler in-memory storage
Support for concurrent logging to disk
Simplified direct connections to localhost

* Migration from docker / redis to standalone script
Updated tests
Updated run script
Fixed requirements
Use dotenv
Ask if user would like to install MCP in Claude Desktop once
Updated docs

* More cleanup and references to docker removed

* Cleanup

* Comments

* Fixed tests

* Fix GitHub Actions workflow for standalone Python architecture

- Install requirements-dev.txt for pytest and testing dependencies
- Remove Docker setup from simulation tests (now standalone)
- Simplify linting job to use requirements-dev.txt
- Update simulation tests to run directly without Docker

Fixes unit test failures in CI due to missing pytest dependency.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Remove simulation tests from GitHub Actions

- Removed simulation-tests job that makes real API calls
- Keep only unit tests (mocked, no API costs) and linting
- Simulation tests should be run manually with real API keys
- Reduces CI costs and complexity

GitHub Actions now only runs:
- Unit tests (569 tests, all mocked)
- Code quality checks (ruff, black)

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Fixed tests

* Fixed tests

---------

Co-authored-by: Claude <noreply@anthropic.com>

docs/advanced-usage.md

@@ -239,9 +239,9 @@ All tools that work with files support **both individual files and entire direct
 
 **The Zen MCP Server's most revolutionary feature** is its ability to maintain conversation context even after Claude's memory resets. This enables truly persistent AI collaboration across multiple sessions and context boundaries.
 
-### 🔥 **The Breakthrough**
+### **The Breakthrough**
 
-Even when Claude's context resets or compacts, conversations can continue seamlessly because other models (O3, Gemini) have access to the complete conversation history stored in Redis and can "remind" Claude of everything that was discussed.
+Even when Claude's context resets or compacts, conversations can continue seamlessly because other models (O3, Gemini) have access to the complete conversation history stored in memory and can "remind" Claude of everything that was discussed.
 
 ### Key Benefits