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.

.cursor/mcp.json

@@ -1,12 +0,0 @@
-{
-    "mcpServers": {
-        "task-master-ai": {
-            "command": "/home/geir/Home-lab/result/bin/task-master-ai",
-            "args": [],
-            "env": {
-                "OPENAI_API_KEY": "fake-key-for-local-ollama",
-                "OPENAI_BASE_URL": "http://grey-area:11434/v1"
-            }
-        }
-    }
-}