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 2026-06-29
stories 11
RSS Archive Reviews

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

CODEX SHIPS REMOTE PLUGINS BY DEFAULT, RESTORES AGENT DELEGATION GUARDRAILS

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

xl-openai ani-oai dylan-hurd-oai
3 people shipped this
xl-openai @xl-openai 1 cited ani-oai @ani-oai 1 cited dylan-hurd-oai @dylan-hurd-oai 1 cited

Remote plugins graduate from experimental to stable, but the team is tightening agent spawning rules after a simplification removed critical delegation guidance.

Codex is shipping remote plugins enabled by default [1], moving the feature out of experimental and into production for all configurations that don't explicitly disable it. The backend authentication gate remains in place, so this is a controlled rollout, not a free-for-all. At the same time, the team restored v1 delegation guidance [2] that was accidentally stripped out earlier, re-establishing the rule that requests for depth, research, or investigation don't automatically authorize spawning subagents. This matters because the simplification that removed that guidance left the authorization check intact but lost the reasoning behind it, which engineers clearly found too permissive in practice. On the model side, Codex is now consuming model metadata to control skills usage instructions [3], removing hardcoded legacy matching and enabling the pattern for gpt-5.5. A revert [4] backed out an overly aggressive auto-review prompt change, and the team cut a routine patch [5] with no user-facing impact.

$ 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 June 29, 2026?
Remote plugins graduate from experimental to stable, but the team is tightening agent spawning rules after a simplification removed critical delegation guidance. In total, 5 commits, 5 pull requests, and 1 releases landed.
Who contributed to OpenAI on June 29, 2026?
3 developers shipped this update, including xl-openai, ani-oai, and dylan-hurd-oai.
What were the notable OpenAI updates?
[codex] Enable remote plugins by default, [codex] Restore v1 delegation guidance (#30511), and [codex] Use model metadata for skills usage instructions.
♥

$ 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.