Who contributed to OpenAI on June 11, 2026?

3 developers shipped this update, including jbeckwith-oai, xl-openai, and stefanstokic-oai.

What were the notable OpenAI updates?

Add app-server `thread/delete` API (#25018), Forward standalone assistant output to realtime (#27319), and v2.41.1.

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODEX SHIPS THREAD DELETION AND REALTIME SYNC, PYTHON SDK FIXES RELEASE PIPELINE

By RepoJournal · Filed 06:03 UTC on June 11, 2026 · About OpenAI

3 people shipped this

jbeckwith-oai @jbeckwith-oai 1 cited

xl-openai @xl-openai 1 cited

stefanstokic-oai @stefanstokic-oai 1 cited

Codex now permanently deletes threads with full session tree cleanup, while the Python SDK patches a broken release workflow that left v2.41.1 half-shipped.

The Codex team landed two critical infrastructure moves overnight. Thread deletion [1] now ships as a v2 app-server API with cascading cleanup of spawned subagent threads and orphaned metadata, filling a gap where clients could only archive. In parallel, realtime sessions now receive completed assistant messages [2] that were previously dropped when no active frontend-model handoff existed, fixing a disconnect where the two models presented as separate personas. The Python SDK hit a snag yesterday when the release workflow for v2.41.1 [3] failed mid-flight, bumping the version and changelog but leaving no GitHub tag, release, or PyPI package behind [4]. The fix restores `contents: write` permissions to the release job while keeping the trusted publishing split intact [5]. On the Codex CLI side, tool-suggest discovery now skips the local curated marketplace when using remote plugins [6], preventing malformed manifest reads, and external-agent import is now discoverable via slash command [7] instead of blocking startup. Test infrastructure got hardened too: subprocess cleanup now properly orphan-hunts grandchild processes after `codex exec` runs [8].

Action items

→ Pull Codex changes into your next build to get thread deletion and realtime sync fixes openai/codex [plan]
→ If you're on openai-python, pull v2.41.1 and verify your release pipeline didn't leave partial state openai/openai-python [monitor]
→ Review the /import slash command addition if you're integrating external agents openai/codex [plan]

References

[1] Add app-server `thread/delete` API (#25018) openai/codex
[2] Forward standalone assistant output to realtime (#27319) openai/codex
[3] v2.41.1 ↗ openai/openai-python
[4] build: fix release workflow permissions ↗ openai/openai-python
[5] build: fix release workflow permissions (#3389) openai/openai-python
[6] [codex] Skip local curated discovery for remote plugins ↗ openai/codex
[7] [codex] add /import for external agents ↗ openai/codex
[8] Guard core test subprocess cleanup (#27343) openai/codex

Quick answers

What shipped in OpenAI on June 11, 2026?: Codex now permanently deletes threads with full session tree cleanup, while the Python SDK patches a broken release workflow that left v2.41.1 half-shipped. In total, 53 commits, 53 pull requests, and 3 releases landed.
Who contributed to OpenAI on June 11, 2026?: 3 developers shipped this update, including jbeckwith-oai, xl-openai, and stefanstokic-oai.
What were the notable OpenAI updates?: Add app-server `thread/delete` API (#25018), Forward standalone assistant output to realtime (#27319), and v2.41.1.

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.