fix: resolve Taskmaster AI MCP integration with local Ollama models

- Fix provider configuration from 'openai' to 'ollama' in .taskmaster/config.json
- Remove conflicting MCP configurations (.cursor/mcp.json, packages/.cursor/mcp.json)
- Standardize on single .vscode/mcp.json configuration for VS Code
- Update environment variables for proper Ollama integration
- Add .env.taskmaster for easy environment setup
- Verify AI functionality: task creation, expansion, and research working
- All models (qwen2.5-coder:7b, deepseek-r1:7b, llama3.1:8b) operational
- Cost: /run/current-system/sw/bin/zsh (using local Ollama server at grey-area:11434)

Resolves configuration conflicts and enables full AI-powered task management
with local models instead of external API dependencies.

.env.taskmaster

@@ -0,0 +1,14 @@
+# Taskmaster AI Environment Variables
+# Source this file to set up Ollama integration for taskmaster
+export OPENAI_API_BASE="http://grey-area:11434/v1"
+export OPENAI_API_KEY="ollama"
+export OPENAI_BASE_URL="http://grey-area:11434/v1"
+export OLLAMA_BASE_URL="http://grey-area:11434/api"
+export MODEL="qwen2.5-coder:7b"
+export RESEARCH_MODEL="deepseek-r1:7b"
+export FALLBACK_MODEL="llama3.1:8b"
+export MAX_TOKENS="8192"
+export TEMPERATURE="0.3"
+
+echo "✅ Taskmaster AI environment variables loaded"
+echo "🤖 Using Ollama models at grey-area:11434"