mirror of
https://github.com/priyanshujain/sanderling.git
synced 2026-10-02 19:17:10 +00:00
Merge branch 'replay-ui-vacuity-counts' into pr-73-followups
This commit is contained in:
commit
bbedd462dd
8 files changed
+396
-14
No files matched your search
@@ -121,20 +121,14 @@ jobs:
|
||||
SEED: ${{ inputs.seed }}
|
||||
MAX_STEPS: ${{ inputs.max-steps }}
|
||||
|
||||
# Exit 0 above means no property returned false. It does not mean any
|
||||
# property was ever evaluated against real content: they all decline to
|
||||
# judge when the elements they read are absent, so a run that never
|
||||
# rendered the step page is green and worthless. This step is what tells
|
||||
# the two apart, and it fails the job when nothing was judged.
|
||||
- name: Summarise
|
||||
if: always()
|
||||
run: |
|
||||
{
|
||||
echo "### replay-ui dogfood"
|
||||
echo
|
||||
echo "- seed \`$SEED\`, budget $MAX_STEPS steps"
|
||||
for dir in runs/dogfood/*/; do
|
||||
[ -f "$dir/trace.jsonl" ] || continue
|
||||
steps=$(wc -l < "$dir/trace.jsonl" | tr -d ' ')
|
||||
violations=$(grep -c '"violations":\[' "$dir/trace.jsonl" || true)
|
||||
echo "- $steps steps recorded, $violations step(s) with violations"
|
||||
done
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
run: .github/scripts/replay-ui-summary.sh runs/dogfood
|
||||
env:
|
||||
SEED: ${{ inputs.seed }}
|
||||
MAX_STEPS: ${{ inputs.max-steps }}
|
||||
|
||||
Reference in new issue
Block a user