What were the notable OpenAI updates?

ensure thread.history_mode is immutable (#30261), [codex] add process-owned code-mode session client (#30112), and feat(app-server): add optional turn_id to thread/fork (#30277).

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODEX LOCKS DOWN THREAD HISTORY, ADDS FORK PRECISION

By RepoJournal · Filed 06:02 UTC on June 27, 2026 · About OpenAI

Codex shipped three structural upgrades overnight that tighten session management, prevent thread degradation across binary versions, and give you surgical control over fork boundaries.

The biggest move is immutability enforcement on thread.history_mode [1]. An older binary could append metadata that omits this field; when a newer binary replays it, serde defaults to legacy and SQLite downgrades a paginated thread. That's now locked after the canonical first SessionMeta write. Separately, the process-owned code-mode session client landed [2], a complete rewrite of session lifecycle that makes dropped calls cancellation-safe with explicit ownership handoff and validates cell/delegate state transitions end-to-end. On the API side, thread/fork now accepts an optional turnId parameter [3], letting you fork up to and including a specific turn while dropping everything after it, replacing the deprecating thread/rollback endpoint with something more granular. Finally, Codex can now consult user-level code-review skills in addition to repo-level ones [4], giving you a cleaner way to inject custom review criteria without forking configuration.

Action items

→ Review your thread/fork calls and test turnId parameter if you're currently using thread/rollback openai/codex [plan]
→ Verify session handling in production after the process-owned session client upgrade deploys openai/codex [monitor]
→ Check for any custom security check wording that may conflict with updated checks openai/codex [plan]

References

[1] ensure thread.history_mode is immutable (#30261) openai/codex
[2] [codex] add process-owned code-mode session client (#30112) openai/codex
[3] feat(app-server): add optional turn_id to thread/fork (#30277) openai/codex
[4] Let Codex consult user-level code-review-* skills. (#30143) openai/codex

Quick answers

What shipped in OpenAI on June 27, 2026?: Codex shipped three structural upgrades overnight that tighten session management, prevent thread degradation across binary versions, and give you surgical control over fork boundaries. In total, 28 commits, 28 pull requests, and 2 releases landed.
What were the notable OpenAI updates?: ensure thread.history_mode is immutable (#30261), [codex] add process-owned code-mode session client (#30112), and feat(app-server): add optional turn_id to thread/fork (#30277).

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.