RepoJournal
OpenAI

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

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

The Wire · Showcase

CODEX SHIPS JSON SCHEMA COMPOSITION SUPPORT AND UNLOCKS WEB SEARCH IN CODE MODE

By RepoJournal · Filed · About OpenAI

Codex now handles the schema shapes that real connectors depend on, while code mode gains direct access to standalone search results.

The oneOf and allOf support landing in Codex [1] closes a gap between what connector golden schemas actually use and what Codex could previously parse. This hits production after the Responses API supports top-level composition, so expect zero disruption and full schema fidelity on the other side. Parallel to that, code mode can now consume plaintext output from standalone web search [2], meaning search results flow directly into nested JavaScript calls instead of getting lost in conversation history. That's a meaningful expansion of what code execution can reach. On the agent side, v2 residency now supports LRU paging [3], letting the stack treat agent identity as separate from whether a thread is currently loaded in ThreadManager. This is the foundation for shifting concurrency counting from "existing agents" to "active execution." Image editing got sharper too: the model now selects exact images for edits instead of Codex inferring them from history [4], which means fewer wrong crops and cleaner intent matching. Finally, sandbox network containment is now properly enforced [5] whenever a configured proxy spins up, ensuring policy-driven network restrictions actually stick across macOS and Linux.

Action items

References

  1. [1] feat: support oneOf and allOf in tool input schemas ↗ openai/codex
  2. [2] [codex] Enable standalone web search in code mode ↗ openai/codex
  3. [3] feat: add v2 agent residency lru ↗ openai/codex
  4. [4] Route image edits through referenced file paths ↗ openai/codex
  5. [5] Enforce configured network proxy in codex sandbox ↗ openai/codex

FAQ

What changed in OpenAI on June 9, 2026?
Codex now handles the schema shapes that real connectors depend on, while code mode gains direct access to standalone search results.
What should OpenAI teams do about it?
Review and test v2 agent residency paging in your session load patterns • Test code mode web search integration before deploying to production • Validate sandbox proxy enforcement on your deployment targets
Which OpenAI repositories shipped on June 9, 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.