RepoJournal
OpenAI

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

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

The Wire · Showcase

CODEX ROLLS BACK GUARDIAN PROMPTING REGRESSION

By RepoJournal · Filed · About OpenAI

github-actions[bot] copyberry Matthew Zeng
3 people shipped this
github-actions[bot] @github-actions[bot] 2 cited copyberry @copyberry 2 cited Matthew Zeng @mzeng-openai

Codex 0.144.2 reverted a broken auto-review policy that degraded Guardian behavior, then shipped a version bump with no additional changes.

The team caught a prompting regression in Guardian's auto-review policy and request format, rolling it back in 0.144.2 [1] to restore previous behavior and tool reliability. That fix shipped immediately, followed by a clean version-only release at 0.144.3 [2] with no code changes. In parallel, the connector runtime refactor landed [3], moving Codex Apps tool caching into a reusable `codex-connectors` manager with atomic snapshot publishing and hardened disk persistence to prevent older fetches from overwriting newer state. Composer completion target resolution also improved [4], resolving `@` and `$` completions on both sides of the cursor while preferring the nearest editable mention and avoiding false positives on uppercase environment variables. These changes strengthen the caching layer and completion accuracy without touching the core inference path.

Action items

References

  1. [1] 0.144.2 ↗ openai/codex
  2. [2] 0.144.3 ↗ openai/codex
  3. [3] Extract connector runtime snapshot management ↗ openai/codex
  4. [4] Improve composer completion target resolution ↗ openai/codex

Quick answers

What shipped in OpenAI on July 13, 2026?
Codex 0.144.2 reverted a broken auto-review policy that degraded Guardian behavior, then shipped a version bump with no additional changes. In total, 2 commits, 2 pull requests, and 2 releases landed.
Who contributed to OpenAI on July 13, 2026?
3 developers shipped this update, including github-actions[bot], copyberry, and Matthew Zeng.
What were the notable OpenAI updates?
0.144.2, 0.144.3, and Extract connector runtime snapshot management.

More from OpenAI

OpenAI OpenAI

CODEX FIXES SKILL NAME TRUNCATION AND TIGHTENS SANDBOX ENFORCEMENT

Codex shipped two critical UX and security fixes overnight that improve skill discoverability and preserve permission isolation in memory consolidation.

copyberry Felipe Coury
ai 8 shipped 1-min read
OpenAI OpenAI

CODEX HARDENS THREADING AND TIGHTENS CREDENTIAL SYNC

Codex locked down concurrent OAuth refreshes and added permission-hook control over auto-review routing in five infrastructure hardening changes.

copyberry
ai 81 shipped 1-min read
OpenAI OpenAI

CODEX TIGHTENS PROXY ENFORCEMENT, SDK CLIENTS SHIP GPT-5.6-SOL SUPPORT

Codex closed a proxy bypass hole in file uploads while both Node and Python clients landed new model capabilities overnight.

bolinfest raquel-openai
ai 74 shipped 1-min read
OpenAI OpenAI

CODEX SHIPS CROSS-OS TEST MIGRATION WHILE NODE SDK HARDENS AZURE ASSISTANTS DOCS

Codex closed out a major test infrastructure refactor that consolidates Windows and Unix CI builds through unified cache roots, while openai-node added critical Azure Assistants documentation that was blocking enterprise deployments.

anp-oai bolinfest owenlin0 HAYDEN-OAI
ai 99 shipped 1-min read

Daily updates, in your inbox

Follow OpenAI

Codex, the SDKs, and the engine behind ChatGPT We'll email you a link to confirm first.

Free. Confirm via email. Unsubscribe in one click.

— or follow the whole beat:

Elsewhere on the wire

Elixir & Phoenix Elixir & Phoenix

ELIXIR FIXES SPEC AND ARITY BUGS ACROSS CORE MODULES

Elixir core shipped three precision fixes overnight that tighten specs on IEx and EEx utilities, catching the kind of type mismatches that slip past dialyzer.

Alexander Gubarev Steffen Deusch
elixir 7 shipped 1-min read
Mobile platforms Mobile platforms

FLUTTER CLEANS HOUSE ON ANALYSIS RULES WHILE SWIFT FIXES C-INTEROP CRASHES

Flutter is migrating away from deprecated strict analysis modes in favor of lint rules, while Swift patches critical crashes in bit-field accessors and C interoperability.

Sam Rawlins duow310 j-hui nkcsgexi +2
mobile 21 shipped 1-min read
.NET @dotnet

ASPNETCORE VALIDATION GENERATOR FIXED, MSBUILD SYNCS ROSLYN AND NUGET

ASP.NET Core's validation source generator now correctly unwraps array types, closing a gap that could slip validation past your models.

Vladik29w dotnet-maestro dotnet-maestro[bot]
dotnet 6 shipped 1-min read
Spring @spring-projects

SPRING-AI FIXES CRITICAL TOOL CALLING BUG THAT BROKE OPENAI STRICT MODE

The `strict` parameter in OpenAI tool calling was silently failing across all Spring AI implementations because it was serialized in the wrong place in the payload.

prachipanditrao Taewoong Kim dependabot Brian Clozel
java 8 shipped 1-min read