RepoJournal
OpenAI

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

  1. Wed 20 may
  2. Thu 21 may
  3. Sat 23 may
  4. Mon 25 may
  5. Tue 26 may
  6. Wed 27 may
  7. Thu 28 may
  8. Fri 29 may
  9. Sat 30 may
  10. Sun 31 may
  11. Mon 1 jun
  12. Mon 8 jun
  13. Tue 9 jun
  14. Wed 10 jun
  15. Thu 11 jun
  16. Fri 12 jun
  17. Sat 13 jun
  18. Sun 14 jun
  19. Mon 15 jun
  20. Tue 16 jun
  21. Wed 17 jun
  22. Thu 18 jun
  23. Fri 19 jun
  24. Sat 27 jun
  25. Sun 28 jun
  26. Mon 29 jun
  27. Tue 30 jun
  28. Wed 1 jul
  29. Thu 2 jul
  30. Today 3 jul

The Wire · Showcase

CODEX CUTS REQUEST CLONING OVERHEAD WHILE HARDENING SANDBOX AND SPEECH CONTROLS

By RepoJournal · Filed · About OpenAI

A critical performance fix removes O(n) clones from every model request, while three parallel hardening efforts shore up Windows sandbox isolation, resource caching, and policy evaluation.

The biggest win lands in sampling: Codex now avoids cloning the full prepared input on every request [1], eliminating expensive copies that grow with conversation size. Instead, the input moves into the sampling loop and returns with results, preserving backward compatibility for the legacy after-agent hook. On the security front, Windows sandbox session management gets refactored [2] to extract reusable launch logic before a follow-up PR ships the fs-helper fix, making the eventual security review cleaner. Realtime speech gains explicit app-side control [3] so backends stop over-chatting by automatically speaking every preamble and progress update. Resource caching now lives at the thread level [4], eliminating repeated remote MCP fetches for the same orchestrator skill within a single thread and preventing prompt injection from observing stale catalog state. Finally, Apps policy evaluation consolidates into connectors [5], moving the evaluator out of codex-core to resolve one immutable policy snapshot per exposure build instead of rebuilding on every sampling request.

Action items

References

  1. [1] avoid cloning sampling request input (#28306) openai/codex
  2. [2] Extract shared Windows sandbox session runner (#28357) openai/codex
  3. [3] Add realtime speech append control (#27917) openai/codex
  4. [4] skills: cache orchestrator resources per thread (#28336) openai/codex
  5. [5] [codex] Reuse Apps policy evaluation across MCP tool exposure ↗ openai/codex

FAQ

What changed in OpenAI on June 16, 2026?
A critical performance fix removes O(n) clones from every model request, while three parallel hardening efforts shore up Windows sandbox isolation, resource caching, and policy evaluation.
What should OpenAI teams do about it?
Review and merge cloning fix [ref:4] before next deployment cycle • Stage Windows sandbox refactor [ref:1] for security fix integration • Monitor thread-level caching [ref:2] for MCP latency improvements in production
Which OpenAI repositories shipped on June 16, 2026?
openai/codex

Related across the cluster

For your repos

The showcase is a teaser.
Your wire is the product.

Same engine. Different stack. Below: what changes when the wire is yours.

Showcase wire

  • •14 famous open source orgs
  • •One wire per day
  • •Public, generic
  • •Read on the web, when you remember

Your wire

  • →Up to 1,500 of your repos - orgs, deps, vendors
  • →Morning and evening briefs
  • →Action items routed to your team
  • →Slack delivery, email, breaking-news CVE alerts

Want a hands-on demo first? Ask a current user for an invite link.