Who contributed to OpenAI on July 30, 2026?

3 developers shipped this update, including seanh-oai, copyberry, and Celia Chen.

What were the notable OpenAI updates?

Remove codex-core's direct reqwest dependency (#36076), Route pet asset downloads through the shared HTTP client (#36008), and Load cloud-managed servers in MCP CLI commands.

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODEX CONSOLIDATES HTTP PLUMBING ACROSS CORE AND CLI

By RepoJournal · Filed 06:58 UTC on July 30, 2026 · About OpenAI

3 people shipped this

copyberry @copyberry 2 cited

Celia Chen @celia-oai 2 cited

seanh-oai @seanh-oai 1 cited

OpenAI shipped four targeted refactors across Codex in the past 24 hours, each tightening dependency ownership and routing logic to reduce technical debt.

The most consequential change removes codex-core's direct reqwest dependency [1], consolidating HTTP handling through the dedicated codex-http-client layer. That same consolidation logic now applies to pet asset downloads, which moved from a standalone blocking client to an async-capable RouteAwareClientPool [2], ensuring CDN redirects respect Codex's configured route handling. On the CLI side, cloud-managed MCP server definitions now load before list, get, login, and logout commands [3], letting enterprise users interact with managed servers while keeping add and remove operations scoped to local configuration. Documentation routing got refined too [4], making official OpenAI docs the default first search target while splitting self-knowledge and setup guidance into focused references. The cleanup also removed obsolete rusty_v8 146.4.0 Bazel targets [5], leaving only the 150.4.0 build targets in place.

Action items

→ Review dependency exceptions for any remaining HTTP client usage in codex-core openai/codex [plan]
→ Test MCP cloud server loading in your enterprise CLI workflows openai/codex [monitor]
→ Validate pet asset downloads work on your configured CDN routes openai/codex [monitor]

References

[1] Remove codex-core's direct reqwest dependency (#36076) openai/codex
[2] Route pet asset downloads through the shared HTTP client (#36008) openai/codex
[3] Load cloud-managed servers in MCP CLI commands ↗ openai/codex
[4] Refine OpenAI docs skill source routing ↗ openai/codex
[5] Remove obsolete rusty_v8 146.4.0 Bazel targets (#35997) openai/codex

Quick answers

What shipped in OpenAI on July 30, 2026?: OpenAI shipped four targeted refactors across Codex in the past 24 hours, each tightening dependency ownership and routing logic to reduce technical debt. In total, 39 commits, 39 pull requests, and 4 releases landed.
Who contributed to OpenAI on July 30, 2026?: 3 developers shipped this update, including seanh-oai, copyberry, and Celia Chen.
What were the notable OpenAI updates?: Remove codex-core's direct reqwest dependency (#36076), Route pet asset downloads through the shared HTTP client (#36008), and Load cloud-managed servers in MCP CLI commands.

CODEX HARDENS SKILL SELECTION AND SESSION LOOKUP, NODE SDK CLOSES LINTER GAPS

Codex decouples explicit skill selection into a dedicated crate while tightening TUI session validation, as the Node SDK completes its oxlint cleanup stack across five rule categories.

ai 118 shipped

OpenAI Aug 5

CODEX HARDENS SECURITY, SDKS MODERNIZE TOOLCHAINS

Codex now prompts users before trusting local directories, closing a prompt injection exposure, while both Node and Python SDKs shift to Oxlint and Oxfmt tooling.

ai 114 shipped

OpenAI Aug 4

GPT-5.5 LANDS ACROSS NODE AND PYTHON SDKS, CODEX HARDENS MCP CONFORMANCE

OpenAI shipped gpt-5.5 model support and tool metadata across both JavaScript and Python SDKs while Codex locked down a full MCP client conformance regression suite to prevent protocol slippage.

ai 115 shipped

OpenAI Aug 3

CODEX HARDENS LOGIN FLOW WITH ONBOARDING HINTS AND METADATA PROTECTION

Three critical fixes shipped across auth, data persistence, and usage tracking to prevent thread metadata loss and secure OAuth callback handling.

ai 6 shipped

Elsewhere on the wire

AI Agents Aug 6

LANGCHAIN HARDENS ANTHROPIC TOOL CALLING AND GIT CREDENTIALS AS OPENHANDS SHIPS 1.10.0

LangChain fixed a critical credential leak in evaluation runs while Anthropic tool schemas get proper fallback handling, as three major agent frameworks push releases across the ecosystem.

ai-agents 54 shipped

Local LLMs Aug 6

OLLAMA FIXES KV CACHE CORRUPTION, LLAMA.CPP HARDENS FILE SEARCH, VLLM KILLS MOE LEGACY CODE

Ollama patched a critical cache corruption bug that corrupts lazy snapshots during multi-request prefills, while llama.cpp hardened Windows junction traversal and vLLM removed 14 hardcoded MoE shards across quantization methods.