Feature/integrate llm providers

[Sirajmx]

Summary

• Adds OpenAI and Gemini as supported LLM providers alongside the existing Anthropic default
• Installs the required crewai extras (openai, gemini) in pyproject.toml so dependencies are present when a non-Anthropic model is configured
• Adds OPENAI_API_KEY and GOOGLE_API_KEY as optional fields in Settings with inline provider-switch docs
• Updates model references from gemini-2.0-flash (deprecated June 2026) to gemini-2.5-flash across settings.py, .env.example, and
  docs/guides/configuration.md
• Fixes MANAGER_LLM_MODEL default in .env.example from claude-sonnet to claude-opus-4 to match settings.py

Provider configuration (.env.example)

Only one provider can be active at a time. The file ships with Anthropic uncommented as the default. To switch, comment out the Anthropic block
and uncomment the target block:

--Provider: Anthropic (default — active)
ANTHROPIC_API_KEY=your-anthropic-api-key-here
DEFAULT_LLM_MODEL=anthropic/claude-sonnet-4-5-20250929
MANAGER_LLM_MODEL=anthropic/claude-opus-4-20250514

-- Provider: OpenAI (alternative)
--OPENAI_API_KEY=your-openai-api-key-here
--DEFAULT_LLM_MODEL=openai/gpt-4o
-- MANAGER_LLM_MODEL=openai/gpt-4o

--Provider: Google Gemini (alternative)
--GOOGLE_API_KEY=your-google-api-key-here
--DEFAULT_LLM_MODEL=gemini/gemini-2.5-flash
--MANAGER_LLM_MODEL=gemini/gemini-2.5-flash

Test plan

• Start seller agent with default Anthropic config — agents initialize without error
• Swap to openai/gpt-4o + OPENAI_API_KEY — crew runs using OpenAI
• Swap to gemini/gemini-2.5-flash + GOOGLE_API_KEY — crew runs using Gemini
• Verify pyproject.toml extras install cleanly: pip install -e ".[anthropic,openai,gemini]"

[Sirajmx]

This should go to main branch to reflect all other llm providers