Improve provider compatibility, browser automation workflow, and configuration handling - #741

Summary

This PR contains several improvements made while testing and extending the project.

Highlights

• Improved LLM provider compatibility
• Better Docker configuration
• Browser automation improvements
• Configuration persistence improvements
• Better setup validation
• UI and workflow refinements

These changes were tested using Docker with Gemini and Ollama providers.

Summary by cubic

Migrates the Web UI to streamlit and adds a guided job-application workflow with persistent profile and application history. Improves LLM provider compatibility, browser automation reliability, and Docker configuration, with new security and deployment guides.

• New Features

  • New streamlit app with pages for Profile, Browser Settings, Job Application, and Application History.
  • Persistent config and data via StreamlitManager and JSON files under data/.
  • Async browser start and external browser path support in CustomBrowser; controller expanded with job tools.
  • Deployment and security docs added (STREAMLIT_DEPLOYMENT.md, SECURITY_GUIDE.md), plus .streamlit/config.toml.
  • Docker updates: expose 8501, start streamlit_app.py via supervisord; runner script run_streamlit.py.

• Migration

  • Install deps: pip install -r requirements.txt (replaces gradio with streamlit, adds python-dotenv, bumps langchain-ibm).
  • Copy env.example to .env and set keys (e.g., OPENAI_API_KEY, LLM_PROVIDER, LLM_MODEL).
  • Start locally: python run_streamlit.py or streamlit run streamlit_app.py --server.port 8501.
  • For Docker, use updated docker-compose.yml (port 8501 exposed).

^{Written for commit a187ed3. Summary will update on new commits.}