stock-analysis-api / eval_agent.py
vjeai's picture
Deploy: all fixes β€” yfinance candles, ml_signal 2y history, no handoff schemas, sequential report phase
3be03dd
Raw
History Blame Contribute Delete
581 Bytes
"""
eval_agent.py β€” thin entry point for the evaluation suite.
Usage:
python eval_agent.py # all non-LLM tests (fast, ~30s)
python eval_agent.py --full # includes LLM agent run (~3 min)
python eval_agent.py --ticker NVDA # use a different test ticker
python eval_agent.py --suite tools # run only one suite
python eval_agent.py --list # list all test names
Implementation lives in eval/ (runner, suites_core, suites_advanced).
"""
from eval.suites_advanced import main
if __name__ == "__main__":
main()