Who contributed to OpenAI on May 8, 2026?

3 developers shipped this update, including bbrown-oai, owenlin0, and charliemarsh-oai.

What were the notable OpenAI updates?

v6.37.0, v2.36.0, and [codex] Apply a Dependabot cooldown of 7 days (#21599).

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

SDK TWINS SHIP REALTIME 2 AS CODEX HARDENS DEPENDENCY GATES

By RepoJournal · Filed 06:03 UTC on May 8, 2026 · About OpenAI

3 people shipped this

bbrown-oai @bbrown-oai 1 cited

owenlin0 @owenlin0 1 cited

charliemarsh-oai @charliemarsh-oai 1 cited

Both the Node and Python SDKs released major versions this morning with realtime translate support and manual API updates, while Codex tightened its dependency intake with a 7-day bake period and normalized tool identity across MCP connections.

The openai-node [1] and openai-python [2] ecosystems are now in lockstep on the realtime 2 spec, with web_search_call.results output options and admin organization usage response updates flowing through both. This matters because teams using parallel SDKs won't hit integration drift. On the Codex side, three structural changes landed overnight that reshape how the platform absorbs external code: a 7-day Dependabot cooldown [3] that lets dependencies stabilize before adoption and gives security tooling time to detect malware, removal of synthetic string-keyed MCP tool maps [4] to keep tool identity single-sourced in ToolInfo objects, and configurable trace metadata [5] that flows through OtelSettings without touching span callsites. Thread pagination APIs [6] landed to handle large thread queries across app-server and ThreadStore, and cargo doctest disabling [7] cut test execution time 4x for crates without doctests.

Action items

→ Update openai-node to v6.37.0 and openai-python to v2.36.0 if you're using realtime features openai/openai-node [plan]
→ Merge the Dependabot cooldown PR if managing Codex dependencies openai/codex [plan]
→ Review MCP tool map refactoring if you have custom ToolInfo consumers openai/codex [monitor]

References

[1] v6.37.0 ↗ openai/openai-node
[2] v2.36.0 ↗ openai/openai-python
[3] [codex] Apply a Dependabot cooldown of 7 days (#21599) openai/codex
[4] [codex] Remove string-keyed MCP tool maps (#21454) openai/codex
[5] codex-otel: add configurable trace metadata ↗ openai/codex
[6] feat(app-server, threadstore): Thread pagination APIs and ThreadStore contract ↗ openai/codex
[7] Disable empty Cargo test targets ↗ openai/codex

Quick answers

What shipped in OpenAI on May 8, 2026?: Both the Node and Python SDKs released major versions this morning with realtime translate support and manual API updates, while Codex tightened its dependency intake with a 7-day bake period and normalized tool identity across MCP connections. In total, 59 commits, 40 pull requests, and 7 releases landed.
Who contributed to OpenAI on May 8, 2026?: 3 developers shipped this update, including bbrown-oai, owenlin0, and charliemarsh-oai.
What were the notable OpenAI updates?: v6.37.0, v2.36.0, and [codex] Apply a Dependabot cooldown of 7 days (#21599).

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 1 day 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 2 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

OpenAI 3 days ago

CODEX FIXES WINDOWS EXECUTION BUGS WHILE TIGHTENING SECURITY REVIEW GATES

Codex shipped critical fixes for Windows process management and terminal navigation that were silently breaking execution sessions on Windows machines.

ai 104 shipped 1-min read

Elsewhere on the wire

AI Agents about 9 hours ago

CLAUDE OPUS 5 LANDS ACROSS THE STACK

The newest Anthropic model is now live in langchain, Cline, and llama-index, with native support for extended reasoning and 1M context windows.

ai-agents 28 shipped 1-min read

Local LLMs about 9 hours ago

OLLAMA LANDS LAGUNA SUPPORT AND CRUSHES MEMORY LEAKS WHILE SGLANG HITS V0.5.16 WITH CONFIDENCE-DRIVEN SPECULATIVE DECODING

Ollama shipped three critical performance and reliability fixes for Metal residency and concurrent access patterns, while SGL-Lang released 0.5.16 with a new speculative algorithm hitting 383.7 tok/s on DeepSeek-V4.