opencode/picoclaw
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(eval): improve compare script error handling

Browse source
This commit is contained in:
ZanzyTHEbar 2026-02-18 13:22:15 +00:00
parent 01a9068494
commit 3ea30372aa
1 changed files with 12 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
eval/scripts/compare.sh
View file

@ -19,26 +19,29 @@ echo ""
cd "$PROJECT_ROOT"
# 1. Build current branch
echo "[1/4] Building current branch..."
make build 2>&1 | tail -1
cp build/picoclaw "$EVAL_DIR/bin/eval-runner"
# 1. Build current branch eval-runner (instrumented wrapper)
echo "[1/4] Building eval-runner from current branch..."
make eval-build 2>&1 | tail -1
cp "$EVAL_DIR/bin/eval-runner" "$EVAL_DIR/bin/eval-runner-branch"
# 2. Build main branch
# 2. Build main branch eval-runner
CURRENT_BRANCH=$(git branch --show-current)
STASH_RESULT=$(git stash 2>&1)
echo "[2/4] Building main branch..."
echo "[2/4] Building eval-runner from main branch..."
git checkout main 2>/dev/null
make build 2>&1 | tail -1
cp build/picoclaw "$EVAL_DIR/bin/eval-runner-main"
make eval-build 2>&1 | tail -1
cp "$EVAL_DIR/bin/eval-runner" "$EVAL_DIR/bin/eval-runner-main"
# Restore
# Restore working branch
git checkout "$CURRENT_BRANCH" 2>/dev/null
if [[ "$STASH_RESULT" != "No local changes to save" ]]; then
git stash pop 2>/dev/null || true
fi
# Put branch binary back as the default eval-runner
cp "$EVAL_DIR/bin/eval-runner-branch" "$EVAL_DIR/bin/eval-runner"
# 3. Update promptfoo config to enable comparison
cd "$EVAL_DIR"