OpenAI Codex shipped rust-v0.159.0 on 2026-09-29 (npm @openai/[email protected]): opt-in instant_interrupt steers mid-response or long code-mode calls; compact welcome/headers; warnings viewer dismisses reviewed items on close (k to keep); scroll transcript while reviewing a plan; richer native Mermaid; app-server can paginate thread history from an item anchor. ~89 commits / 300 files vs v0.158.0. Windows suppresses stray consoles for MCP/code-mode; .aws protected under writable roots; macOS sandbox TLS/proxy fixes.

Key Takeaways

  • ✓Release rust-v0.159.0 on 2026-09-29; ~89 commits / 300 files vs v0.158.0
  • ✓Opt-in instant_interrupt steers mid-response / long code-mode (#48135/#48141)
  • ✓Warnings dismiss on close (k to keep); scroll while reviewing plans; richer Mermaid
  • ✓App-server paginates thread history from an item anchor (#48151)
  • ✓Install: npm i -g @openai/[email protected]; removed tui.prompt_suggestions and bundled plugin-creator skill
🧭

Finished reading? Explore benchmark rankings & pricing

Real-world SWE-bench scores & $20/mo vs API cost break-even calculator

🔬

In-Depth Technical Analysis

Background Long Codex turns often need mid-flight steering—waiting for a full response or killing the process wastes context. 0.158.0 hardened MCP OAuth and exec-server tokens; 0.159.0 targets interruptibility and review UX. ### What shipped v0.159.0 adds opt-in instant_interrupt (#48135/#48141), compact welcome/headers, dismiss-on-close warnings (k to keep), scroll-while-planning, richer Mermaid, and item-anchored thread/items/list pagination (#48151). Windows suppresses stray consoles; .aws protected under writable roots; macOS sandbox TLS/proxy fixes. ### Benchmarks No public SWE-bench numbers in the notes. Signal: ~89 commits / 300 files vs v0.158.0. Validate interrupt success and MCP spawn behavior on your stack. ### Get started npm i -g @openai/[email protected] or grab assets from the release. Note removal of tui.prompt_suggestions and the bundled plugin-creator skill.