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 2026-07-13
stories 6
RSS Archive Reviews

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

CODEX ROLLS BACK GUARDIAN PROMPTING REGRESSION

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

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.

$ 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 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.
♥

$ 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.