RepoJournal
OpenAI OpenAI
150 wires and counting

$ follow OpenAI

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

or

fair warning: these emails are deeply technical. diffs, version numbers, CVEs, benchmark deltas. if that's not your idea of a good read, this isn't your newsletter.

Folds into your digest — weekly by default, monthly if you prefer. Unsubscribe in one click.

$ status

wire 2026-07-12
stories 8
RSS Archive Reviews

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

CODEX FIXES SKILL NAME TRUNCATION AND TIGHTENS SANDBOX ENFORCEMENT

By RepoJournal · Filed · About OpenAI · Composed from the cited sources · methodology

copyberry Felipe Coury
2 people shipped this
copyberry @copyberry 4 cited Felipe Coury @fcoury-oai

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

The skill toggle view was silently truncating display names to 21 characters regardless of available popup width [1], which could hide the distinguishing suffix in similarly named skills. That's fixed now. The renderer now passes full skill names and fits them intelligently to available space, keeping narrow layouts properly bounded. In parallel, memory consolidation was inadvertently replacing parent sandbox enforcement with managed permissions [2], potentially loosening permission profiles set by operators or legacy systems. The fix preserves the parent turn's effective permission profile including thread-level overrides. Two smaller changes landed: tab characters in TUI diffs now expand to four spaces for proper rendering alignment [3], and the guardian now correctly emits thread-idle lifecycle callbacks after interrupting active turns [4], ensuring extensions hook in at the right moment.

$ ls openai/reviews/ # the step-back reads

the week in review Codex hands model defaults to the server the month in review Agents API lands in both OpenAI SDKs
Full archive → Weekly reviews →

Quick answers

What shipped in OpenAI on July 12, 2026?
Codex shipped two critical UX and security fixes overnight that improve skill discoverability and preserve permission isolation in memory consolidation. In total, 4 commits and 4 pull requests landed.
Who contributed to OpenAI on July 12, 2026?
2 developers shipped this update, including copyberry and Felipe Coury.
What were the notable OpenAI updates?
Use available width for skill names in the toggle view, Preserve parent sandbox enforcement for memory consolidation, and Expand tabs when rendering TUI diffs.
♥

$ log OpenAI --recent

Safety identifiers reach images, plugin approvals bind to contents 93 shipped Credential masking lands in Codex, Live gains Decisions across both SDKs 100 shipped Codex stabilizes environment tools, python adds residency options 135 shipped openai-python restores streaming connection reuse, browser and computer toolsets land in both SDKs 123 shipped

$ log --all # elsewhere on the wire

Alignment & Post-training verl rejects conflicting vLLM engine_kwargs, open-instruct adds MILES OPD behind a Megatron learner Interpretability nnsight 0.8.0 cuts import time from 7.6s to 1.6s

$ ls showcases/

Safety Evals AI Red Teaming Agent Security Interpretability Alignment & Post-training

$ init your-desk

RepoJournal can write one of these for any repo you care about. Sign in with GitHub, pick your repos and sources, and your desk gets a wire like this one every morning.