fix: resolve workflow gaps exposed by frontier evals

Clarify plan-review ordering and fallback modes, preserve deploy readiness gates, honor configured merge methods, correct benchmark and canary contracts, and restore vendored installs on setup failure. Cover recovery with real-shell regressions.

Co-Authored-By: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Garry Tan
2026-09-09 04:20:08 +00:00
co-authored by OpenAI Codex
parent a9f9ec5f08
commit 1f678a5b81
28 changed files with 317 additions and 130 deletions
+1 -1
View File
@@ -839,7 +839,7 @@ ${litmusItems}
- ALWAYS preserve visited vs unvisited link distinction (visited links must have a different color)
- NEVER float headings between paragraphs (heading must be visually closer to the section it introduces than to the preceding section)
**AI Slop blacklist** (the 10 patterns that scream "AI-generated"):
**AI Slop blacklist** (the ${AI_SLOP_BLACKLIST.length} patterns that scream "AI-generated"):
${slopItems}
Source: [OpenAI "Designing Delightful Frontends with GPT-5.4"](https://developers.openai.com/blog/designing-delightful-frontends-with-gpt-5-4) (Mar 2026) + gstack design methodology.`;