Who contributed to OpenAI on July 10, 2026?

2 developers shipped this update, including bolinfest and raquel-openai.

What were the notable OpenAI updates?

codex-api: route file uploads through HTTP client factory, fix: forward originator to Codex Apps MCP, and v6.46.0.

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODEX TIGHTENS PROXY ENFORCEMENT, SDK CLIENTS SHIP GPT-5.6-SOL SUPPORT

By RepoJournal · Filed 06:57 UTC on July 10, 2026 · About OpenAI

2 people shipped this

bolinfest @bolinfest 1 cited

raquel-openai @raquel-openai 1 cited

Codex closed a proxy bypass hole in file uploads while both Node and Python clients landed new model capabilities overnight.

The Codex team plugged a critical gap where file upload flows could ignore system proxy settings even after API requests honored them [1]. The fix makes HTTP client policy a required input across the three-step upload process (create record, PUT bytes, finalize), resolving each destination independently so no step can slip through the configured proxy. On the SDK front, both openai-node v6.46.0 and openai-python v2.45.0 shipped with gpt-5.6-sol model updates [3] [4], though the Python release also had to restore beta resource accessors that got inadvertently stripped [4]. In parallel, Codex is fixing its conversation tracking by properly forwarding originator headers to ChatGPT-hosted Apps and plugin-runtime MCP requests [2], resolving production validation gaps where plugin creation logs were showing `CODEX_UNKNOWN_DEFAULT` instead of actual surface origins. Internal cleanup work removed the redundant `NetworkProxyConfig` wrapper that forced runtime callers to repeat `.network` everywhere , and the TUI now strips empty reasoning-summary placeholders that were leaking into transcript history .

Action items

→ Update openai-node to v6.46.0 and openai-python to v2.45.0 for gpt-5.6-sol model support openai/openai-node [plan]
→ Deploy Codex file upload proxy fix [ref:1] to staging immediately if handling sensitive proxy configurations openai/codex [plan]
→ Monitor Codex originator header forwarding [ref:2] in production logs for correct project creation attribution openai/codex [monitor]

References

[1] codex-api: route file uploads through HTTP client factory ↗ openai/codex
[2] fix: forward originator to Codex Apps MCP ↗ openai/codex
[3] v6.46.0 ↗ openai/openai-node
[4] v2.45.0 ↗ openai/openai-python

Quick answers

What shipped in OpenAI on July 10, 2026?: Codex closed a proxy bypass hole in file uploads while both Node and Python clients landed new model capabilities overnight. In total, 34 commits, 34 pull requests, and 6 releases landed.
Who contributed to OpenAI on July 10, 2026?: 2 developers shipped this update, including bolinfest and raquel-openai.
What were the notable OpenAI updates?: codex-api: route file uploads through HTTP client factory, fix: forward originator to Codex Apps MCP, and v6.46.0.

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.