SilverSight/.atlas/benchmark.sh
allaun 7fcfde3ca7 feat(polyglot): add GEPA infrastructure for Python shim optimization
- Add .atlas/ with benchmark.sh, score.py, gate.sh for GEPA campaigns
- Add atlas.json project config (auto.capture=suggest, reflection_lm=openai/auto)
- Fix test_search.py receipt path from /mnt/agents/ to /tmp/

Metric targets:
  dna_qubo_sort.py: avg |Rank corr| (higher=better, baseline=0.8547)
  dna_qubo_nn.py:   NN Tm correlation (higher=better, baseline=0.4649)
  dna_lut.py:       avg |Rank corr| (higher=better, baseline=0.5808)
  test_search.py:   pass count (ceiling=43, for stability verification)
2026-07-07 01:08:49 -05:00

20 lines
502 B
Bash
Executable file

#!/usr/bin/env bash
set -uo pipefail
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
OUT="$(mktemp)"
TARGET="${ATLAS_OPTIMIZE_TARGET:-$1}"
export ATLAS_EVAL_SEED="${ATLAS_EVAL_SEED:-0}"
START=$(date +%s.%N)
( python3 "$TARGET" ) >"$OUT" 2>&1
RC=$?
END=$(date +%s.%N)
if [ "$RC" -ne 0 ]; then
echo "[benchmark] run command exited $RC — candidate failed" >&2
tail -n 40 "$OUT" >&2
exit "$RC"
fi
python3 "$HERE/score.py" --stdout "$OUT" --elapsed "$(awk "BEGIN { print $END - $START }")"