Harden CI eval: container crash detection, empty STEP guard, extended timeout#218
Merged
Conversation
Three independent fixes identified in scale readiness audit: 1. run_eval_pool.py: distinguish container crash (returncode != 0, no output) from bad JSON (container ran but output is garbage). Previously both showed "Invalid JSON output" — crash now shows "Container exited 137" with stderr tail, making OOM kills and segfaults debuggable by miners. 2. record_submissions.py: skip STEP files smaller than 200 bytes. The file is pre-created as 0 bytes before docker run so the container can write to it; if the container crashes mid-run the file stays empty. Storing an empty BLOB sets has_step=true for a submission with no geometry, breaking the 3D viewer for that entry. 3. score.yml: increase score-round timeout-minutes from 90 → 150. 15 specs × ~180s each + Docker overhead ≈ 50 min per round; 90 min was dangerously close to the limit for slower specs under high load. eval.yml and hidden-eval remain at 90 min (3 specs each — sufficient). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Three fixes from a scale readiness audit against the 100+ miner launch scenario:
Container crash detection (
scripts/run_eval_pool.py): OOM kills, segfaults, and other Docker exits now surface asContainer exited 137with stderr tail instead of the misleadingInvalid JSON output:message. Distinguishes clean bad-output from hard crashes.0-byte STEP guard (
scripts/record_submissions.py): The eval pre-creates.forge_step_{spec_id}.stepas an empty file beforedocker runso the container can write to it. If the container crashes, the file stays 0 bytes. Previously this empty blob was base64-encoded and stored in SQLite, settinghas_step=truefor a submission with no geometry — breaking the 3D viewer. Now skips STEP files under 200 bytes.Score-round timeout 90→150 min (
.github/workflows/score.yml): 15 specs × ~180s each + Docker overhead ≈ 50 min per round. 90 minutes is too close to the wire, especially on loaded GitHub runners.eval.ymlandhidden-eval(3 specs each) remain at 90 min.Test plan
Container exited N | stderr: ...in the PR commenthas_step=truescore.ymlfull-round job hastimeout-minutes: 150in the workflow file🤖 Generated with Claude Code