fix: misc fixes (bad link to old docs, composio print statement, context window selection)

[cpacker]

• disabled composio print statement
• fixed link to old readme docs when you to python main.py (from ancient youtube videos)
• made it so that the CLI flow has an easy way to change the context window
  • important note: there's a min context window and a max (the provider's output) for the questionary input field

% letta run
Initializing database...

🧬 Creating new agent...
? Select LLM model: letta-free [type=openai] [ip=https://inference.memgpt.ai]
? Context window (hit enter for default): 6000
? Select embedding model: letta-free [type=hugging-face] [ip=https://embeddings.memgpt.ai]
->  🤖 Using persona profile: 'sam_pov'
->  🧑 Using human profile: 'basic'
->  🛠️  7 tools: send_message, conversation_search, conversation_search_date, archival_memory_insert, archival_memory_search, core_memory_append, core_memory_replace
/Users/loaner/dev/MemGPT-fresh/letta/agent.py:251: UserWarning: Tool rules only work reliably for the latest OpenAI models that support structured outputs.
  warnings.warn("Tool rules only work reliably for the latest OpenAI models that support structured outputs.")
🎉 Created new agent 'BenevolentUmbrella' (id=agent-a655de82-78df-47ba-b7f9-17ca65c90dfa)

Hit enter to begin (will request first Letta message)