Who contributed to OpenAI on June 13, 2026?

2 developers shipped this update, including celia-oai and jbeckwith-oai.

What were the notable OpenAI updates?

feat: use encrypted local secrets for CLI auth, feat: use encrypted local secrets for MCP OAuth, and feat(app-server): enforce managed remote control disable (#27961).

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODEX SHIPS AUTH OVERHAUL AS OPENAI-NODE GOES PNPM

By RepoJournal · Filed 06:02 UTC on June 13, 2026 · About OpenAI

2 people shipped this

celia-oai @celia-oai 2 cited

jbeckwith-oai @jbeckwith-oai 1 cited

Codex locked in encrypted credentials for CLI and MCP OAuth while tightening remote control security, and the Node SDK completed its package manager migration in one swing.

The Codex team landed three major auth improvements across the stack. First, they wired encrypted local secrets into the CLI auth pipeline [1] to solve a Windows Credential Manager limitation that was breaking large ChatGPT payloads, then extended that same encrypted backend to MCP OAuth storage [2] with support for legacy keyring migration. In parallel, they added a dedicated kill switch for remote control in managed deployments [3], letting admins disable the feature without touching persisted user preferences. These three PRs represent the completion of a planned encryption stack that keeps only keys in OS keystores and payloads in Codex's encrypted vault. On the packaging front, Codex cut Windows x64 build time by parallelizing archive operations [4], dropping a 116-second serial job to concurrent execution. Meanwhile, openai-node completed its migration from Yarn to pnpm 11.5.1 [5], updating CI, release workflows, and contributor docs in one lift while upgrading Node types to 24.x and pinning TypeSpec runtime to avoid registry warnings.

Action items

→ Review and merge encrypted auth PRs in Codex if on Windows or MCP OAuth path openai/codex [plan]
→ Test Codex builds with parallelized Windows packaging in staging openai/codex [monitor]
→ Update local dev setup if you contribute to openai-node; pnpm is now canonical openai/openai-node [plan]

References

[1] feat: use encrypted local secrets for CLI auth ↗ openai/codex
[2] feat: use encrypted local secrets for MCP OAuth ↗ openai/codex
[3] feat(app-server): enforce managed remote control disable (#27961) openai/codex
[4] [codex] parallelize Windows package archives (#27854) openai/codex
[5] chore: Convert repository to pnpm ↗ openai/openai-node

Quick answers

What shipped in OpenAI on June 13, 2026?: Codex locked in encrypted credentials for CLI and MCP OAuth while tightening remote control security, and the Node SDK completed its package manager migration in one swing. In total, 51 commits, 51 pull requests, and 3 releases landed.
Who contributed to OpenAI on June 13, 2026?: 2 developers shipped this update, including celia-oai and jbeckwith-oai.
What were the notable OpenAI updates?: feat: use encrypted local secrets for CLI auth, feat: use encrypted local secrets for MCP OAuth, and feat(app-server): enforce managed remote control disable (#27961).

CODEX FIXES THREAD REPLAY ERRORS AND TIGHTENS SHUTDOWN SEQUENCING

Failed turn completions were being silently restored as successes when replaying conversation history, masking critical errors in the TUI transcript.

ai 10 shipped 1-min read

OpenAI 2 days ago

CODEX SHIPS RESPONSIVE UI FIXES AND FRESHENS MENTION SEARCH STATE

Codex tightened its interface handling across four critical flows: responsive keymap menus now adapt to narrow terminals, mention popups purge stale search results, completion events now track item lifecycles, and exec-server network policy decisions move client-side.

ai 15 shipped 1-min read

OpenAI 3 days ago

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.

ai 66 shipped 1-min read

OpenAI 4 days ago

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.

ai 103 shipped 1-min read

Elsewhere on the wire

AI Agents about 21 hours ago

CLINE SHIPS FIVE CRITICAL AGENT FIXES AFTER END-TO-END TESTING BLITZ

Saoudrizwan just landed a cascade of fixes that prevent the agent loop from running wild, stop file reads from resolving to the wrong directory, and plug the compaction pipeline.

ai-agents 16 shipped 2-min read

Local LLMs about 21 hours ago

LLAMA.CPP SHIPS MINIMAX-M3 SPARSE ATTENTION, VLLM UNLOCKS HETEROGENEOUS PREFILL-DECODE

The inference stack gets a new model architecture and a fundamental shift in how prefill and decode can run on different hardware configurations.

+10

llms 125 shipped 1-min read

@CachyOS about 21 hours ago

GLIBC 2.43 REBUILD SHIPS, INSTALLER JUMPS TO C++26

CachyOS pushed glibc 2.43 through the pipeline while the CLI installer upgraded its C++ standard to C++26, signaling a major refresh across core infrastructure.

infra 97 shipped 1-min read

Elixir & Phoenix about 21 hours ago

ECTO FIXES SUBQUERY PLANNING IN JOINS, ELIXIR PATCHES IEX PARSING

Ecto's query planner now handles subqueries correctly in interpolated join filters, while Elixir fixes a syntax error that broke 'not in' as a continuation operator in IEx.