Who contributed to OpenAI on July 27, 2026?

2 developers shipped this update, including copyberry and Felipe Coury.

What were the notable OpenAI updates?

Preserve terminal turn errors in replayed history, Track model and personality in world state, and Shut down the in-process outbound router explicitly (#35523).

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODEX FIXES THREAD REPLAY ERRORS AND TIGHTENS SHUTDOWN SEQUENCING

By RepoJournal · Filed 06:58 UTC on July 27, 2026 · About OpenAI

2 people shipped this

copyberry @copyberry 4 cited

Felipe Coury @fcoury-oai 1 cited

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

The Codex team landed a critical fix that preserves terminal turn errors during thread replay, ensuring that model-overload warnings and other completion failures no longer disappear from transcripts [1]. Alongside this, world-state tracking now captures model and personality changes as explicit instruction fragments, allowing diffs to properly generate context updates when prior state must be inferred during replay [2]. On the infrastructure side, a shutdown sequence fix ensures the in-process outbound router shuts down explicitly before waiting on message senders, preventing detached processor work from keeping the app-server alive during shutdown [3]. Two developing changes round out the period: a new managed policy feature lets administrators disable in-app updates through `requirements.toml`, exposing the setting through the config API [4], while a TUI routing improvement filters out unrelated requests when surfacing pending user interactions from side conversations [5].

Action items

→ Review and test thread replay with failed turns in your current version openai/codex [plan]
→ Monitor shutdown logs for outbound router cleanup if you run detached processors openai/codex [monitor]

References

[1] Preserve terminal turn errors in replayed history ↗ openai/codex
[2] Track model and personality in world state ↗ openai/codex
[3] Shut down the in-process outbound router explicitly (#35523) openai/codex
[4] Add managed policy for in-app updates ↗ openai/codex
[5] Skip inactive TUI threads without pending user interaction ↗ openai/codex

Quick answers

What shipped in OpenAI on July 27, 2026?: Failed turn completions were being silently restored as successes when replaying conversation history, masking critical errors in the TUI transcript. In total, 5 commits and 5 pull requests landed.
Who contributed to OpenAI on July 27, 2026?: 2 developers shipped this update, including copyberry and Felipe Coury.
What were the notable OpenAI updates?: Preserve terminal turn errors in replayed history, Track model and personality in world state, and Shut down the in-process outbound router explicitly (#35523).

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

OpenAI 5 days ago

CODEX CONSOLIDATES THREAD STARTUP, NODE SDK ADDS REALTIME AND STANDARD SCHEMA SUPPORT

Codex refactored its threading and database layer for consistency while the Node SDK ships four new schema helpers and fixes audio streaming in a single release push.

ai 120 shipped 1-min read

Elsewhere on the wire

AI Agents about 22 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 22 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 22 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 22 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.