feat: add provider selection and persistence

[tode-rl]

Add ability to switch between OpenAI and Anthropic models during a session with the /model slash command. Model choice is persisted in config.json and restored in future sessions.

Changes:

• config.py: Add SessionState.preferred_provider field, refactor create_model() with force_provider parameter, add helper functions (_create_openai_model, _create_anthropic_model, _show_api_key_error), add load_agent_config() and save_agent_config() for persistence
• commands.py: Add /model command handler that returns dict signal for agent recreation, change return type to str | bool | dict
• main.py: Update simple_cli() and main() to return dict | None for special actions, add model switching loop in cli_main() that recreates agent on provider change, load config at startup and save on model switch
• README.md: Document /model command, add Model Switching section, update Agent Storage to mention config.json, update module documentation

Model switching recreates the agent and clears conversation history while preserving memories and custom instructions.

[tode-rl]

I thought /provider made a bit more sense, /model can come later with local configs