#!/usr/bin/env bash
# Runs the three evaluations with the ForexBot2 venv (it has requests,
# pandas and the live news code; the model loads identically there).
# Total DeepSeek spend on a first run: ~4 calls (golden) + ~4 (reprobe)
# + one call per 25 fresh headlines (live). Everything is cached, so a
# second run makes no calls unless new headlines arrived.
set -euo pipefail
PY=/home/harwinder/Development/ForexBot2/venv/bin/python
cd "$(dirname "$0")"

echo "### 1/3 golden set (independent human labels)"
"$PY" eval_golden.py "$@"

echo
echo "### 2/3 archive time-split + DeepSeek self-agreement"
"$PY" eval_archive.py --reprobe 100 "$@"

echo
echo "### 3/3 live shadow run (24 h of headlines)"
"$PY" eval_live.py --max-age-hours 24 "$@"