gautamk1512/TradingAgents ? reverse-engineered prompt

Build me a Python app called TradingAgents that acts like a multi agent stock trading research assistant. I want it to take a ticker symbol and then have different AI roles look at it, like fundamentals, sentiment, news, technicals, research debate, trader, risk, and portfolio manager. It should gather market data and news from available sources, compare bullish and bearish views, and then produce a clear final recommendation with a reasoned report, not just a yes or no.

Make it runnable from the command line and also easy to run with Docker. Use environment variables for API keys and provider settings, and let me switch between different LLM providers if possible. Include a simple simulated trading flow so it can show what would happen without needing real money. Add sensible defaults, clear logging, and a clean README with setup steps and example usage. If you need current docs for any APIs or model providers, look them up online first.