mirror of
https://github.com/obra/superpowers.git
synced 2026-05-09 18:49:04 +08:00
3c046f579e
rsync of obra/drill@013fcb8b7d into superpowers/evals/, excluding .git/, .venv/, results/, .env/, __pycache__/, *.egg-info/, .private-journal/. The drill repo is unaffected by this commit; archival is a separate manual step after this PR merges. Source SHA recorded at evals/.drill-source-sha for divergence detection.
28 lines
750 B
Bash
Executable File
28 lines
750 B
Bash
Executable File
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
command -v jq >/dev/null || { echo "jq required"; exit 127; }
|
|
|
|
TOOL="$1"
|
|
OP="$2"
|
|
EXPECTED="$3"
|
|
FILE="tool_calls.jsonl"
|
|
|
|
COUNT=$(jq -s "[.[] | select(.tool == \"$TOOL\")] | length" "$FILE" 2>/dev/null || echo 0)
|
|
|
|
case "$OP" in
|
|
eq) TEST=$(( COUNT == EXPECTED )) ;;
|
|
gt) TEST=$(( COUNT > EXPECTED )) ;;
|
|
gte) TEST=$(( COUNT >= EXPECTED )) ;;
|
|
lt) TEST=$(( COUNT < EXPECTED )) ;;
|
|
lte) TEST=$(( COUNT <= EXPECTED )) ;;
|
|
*) echo "Unknown operator: $OP (expected: eq, gt, gte, lt, lte)"; exit 2 ;;
|
|
esac
|
|
|
|
if [ "$TEST" -eq 1 ]; then
|
|
echo "PASS: $TOOL called $COUNT time(s) ($OP $EXPECTED)"
|
|
exit 0
|
|
else
|
|
echo "FAIL: $TOOL called $COUNT time(s) (expected $OP $EXPECTED)"
|
|
exit 1
|
|
fi
|