RepoJournal
OpenAI

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Keep up with OpenAI in about 3 minutes a day: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

One email a day. Unsubscribe in one click.

Pick a date

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

The Wire · Showcase

CODEX CLEANS UP LOGGING, DROPS LEGACY CONFIG SURFACE

By RepoJournal · Filed · About OpenAI

jif-oai iceweasel-oai bolinfest adams-oai
4 people shipped this
jif-oai @jif-oai 2 cited iceweasel-oai @iceweasel-oai 1 cited bolinfest @bolinfest 1 cited adams-oai @adams-oai 1 cited

Windows sandbox logs now roll daily instead of growing unbounded, while the CLI finally stops pretending you can cross-compile sandboxes.

Codex shipped five infrastructure fixes overnight, three of them closing long-standing operational gaps. The Windows sandbox logger [1] now rotates daily with bounded file retention, solving the problem of diagnostic logs ballooning across feedback reports. The TUI stopped dumping logs to disk by default [2], making that file an explicit troubleshooting opt-in instead of a side effect that grows forever. On the config side, the app-server protocol [3] dropped the legacy profile table surface entirely after the CLI already ditched it, cleaning up conversion code that nobody uses. The sandbox command [4] infers your host OS now, collapsing the redundant `codex sandbox linux/macos/windows` ceremony into a single `codex sandbox` that just works. A new enterprise gate was wired into the validation chain [5], though one test is still surfacing a stack overflow in the in-process handler that needs investigation.

One email a day. Unsubscribe in one click.

Action items

References

  1. [1] [codex] Use rolling files for Windows sandbox logs ↗ openai/codex
  2. [2] tui: make `codex-tui.log` opt-in ↗ openai/codex
  3. [3] app-server: drop legacy profile config surface ↗ openai/codex
  4. [4] cli: infer host sandbox backend ↗ openai/codex
  5. [5] Add new enterprise requirement gate ↗ openai/codex

Quick answers

What shipped in OpenAI on May 23, 2026?
Windows sandbox logs now roll daily instead of growing unbounded, while the CLI finally stops pretending you can cross-compile sandboxes. In total, 35 commits, 35 pull requests, and 3 releases landed.
Who contributed to OpenAI on May 23, 2026?
4 developers shipped this update, including iceweasel-oai, jif-oai, bolinfest, and adams-oai.
What were the notable OpenAI updates?
[codex] Use rolling files for Windows sandbox logs, tui: make `codex-tui.log` opt-in, and app-server: drop legacy profile config surface.

More from OpenAI

OpenAI OpenAI

CODEX HARDENS MCP RUNTIME STABILITY ACROSS FIVE CRITICAL FIXES

OpenAI shipped a coordinated hardening of the Model Context Protocol layer across Codex, patching race conditions in thread startup, resource access, and authority management that could leave stale configurations in production.

copyberry Justin Beckwith
ai 66 shipped 1-min read
OpenAI OpenAI

SDK RELEASES LOCK IN PROMPT CACHING AND SPEND CONTROLS

Both Node and Python clients shipped v6.49.0 and v2.48.0 overnight with admin spend limit APIs and relaxed prompt cache validation.

copyberry stainless-app[bot] stainless-app
ai 103 shipped 1-min read
OpenAI OpenAI

CODEX CONSOLIDATES THREAD STARTUP, NODE SDK ADDS REALTIME AND STANDARD SCHEMA SUPPORT

Codex refactored its threading and database layer for consistency while the Node SDK ships four new schema helpers and fixes audio streaming in a single release push.

copyberry HAYDEN-OAI Alex Chang stainless-app[bot] +1
ai 120 shipped 1-min read
OpenAI OpenAI

CODEX FIXES WINDOWS EXECUTION BUGS WHILE TIGHTENING SECURITY REVIEW GATES

Codex shipped critical fixes for Windows process management and terminal navigation that were silently breaking execution sessions on Windows machines.

rhan-oai mandal-OAI copyberry
ai 104 shipped 1-min read

Daily updates, in your inbox

Follow OpenAI

Keep up with OpenAI in about 3 minutes a day: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

or

One email a day. Unsubscribe in one click. Read a past issue →

Elsewhere on the wire

AI Agents AI Agents

CLAUDE OPUS 5 LANDS ACROSS THE STACK

The newest Anthropic model is now live in langchain, Cline, and llama-index, with native support for extended reasoning and 1M context windows.

github-actions[bot] hntrl dependabot ak684 +6
ai-agents 28 shipped 1-min read
Local LLMs Local LLMs

OLLAMA LANDS LAGUNA SUPPORT AND CRUSHES MEMORY LEAKS WHILE SGLANG HITS V0.5.16 WITH CONFIDENCE-DRIVEN SPECULATIVE DECODING

Ollama shipped three critical performance and reliability fixes for Metal residency and concurrent access patterns, while SGL-Lang released 0.5.16 with a new speculative algorithm hitting 383.7 tok/s on DeepSeek-V4.

dhiltgen ParthSareen Xuan-Son Nguyen Johannes Gäßler +11
llms 210 shipped 2-min read
CachyOS @CachyOS

HYPRLAND V0.56 FIXES LAND, PACKAGE ECOSYSTEM ROLLS FORWARD

Hyprland configuration updated for v0.56 compatibility across multiple desks, while the AUR-derived ecosystem locked in four automated package bumps.

cantosun99 Jinra Aarrayy Valeri +7
infra 85 shipped 1-min read
Elixir & Phoenix Elixir & Phoenix

LIVEVIEW ASYNC CLEANUP FIX SHIPS ALONGSIDE RANGE OPTIMIZATIONS

Phoenix LiveView closes a critical async task test failure while Elixir cuts unnecessary abs calls from Range operations.

Barna Kovacs Alexander Gubarev SteffenDE José Valim +1
elixir 19 shipped 1-min read
Want every project, not just this one?