Who contributed to OpenAI on July 18, 2026?

4 developers shipped this update, including Felipe Coury, viyatb-oai, copyberry, and jbeckwith-oai.

What were the notable OpenAI updates?

Make parent-owned sub-agent threads read-only in the TUI, Add SessionEnd hooks for thread teardown, and Render inline visualization links in the TUI (#33925).

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODEX LOCKS DOWN MULTI-AGENT THREADS WHILE NODE AND PYTHON SDKS PATCH SECURITY GAPS

By RepoJournal · Filed 06:58 UTC on July 18, 2026 · About OpenAI

4 people shipped this

jbeckwith-oai @jbeckwith-oai 5 cited

copyberry @copyberry 2 cited

Felipe Coury @fcoury-oai 1 cited

viyatb-oai @viyatb-oai 1 cited

Codex made parent-controlled sub-agent threads read-only in the TUI to prevent rejected server operations, while the Node and Python SDKs are closing security holes across GitHub Actions permissions, error handling, and dependency chains.

In brief

Codex now makes parent-owned sub-agent threads read-only in the TUI. multi-agent workflows need guard rails. this one makes sense.
SessionEnd hooks landed for thread teardown in Codex. proper cleanup beats implicit GC when you're spinning up agents.
openai-python now requires patched aiohttp on Python 3.10+. security fixes in your dependencies matter. don't skip this one.
openai-node addressed remaining Dependabot alerts. incremental security beats the panic patch three months later.
Codex renders inline visualization links in the TUI now. small UX win. beats clicking through to a separate window.

The Codex team shipped three high-impact changes that tighten control and visibility in multi-agent workflows. Parent-owned sub-agent threads now properly expose their read-only status through the new `Thread.canAcceptDirectInput` capability [1], preventing users from attempting input that the server would reject anyway. The team also added SessionEnd hooks for graceful thread teardown [2], letting operators run cleanup logic before archive or deletion with bounded execution (one second default timeout). Inline visualization links now render as browser-accessible fallbacks in the TUI [3], while managed network proxies on remote executors [4] handle loopback routing for spawned processes. Over in openai-node, the SDK just closed out 10 open Dependabot alerts by upgrading Next.js to 15.5, patching js-yaml and PostCSS transitives, and migrating Cloudflare from Wrangler 3 to 4 [5]. The team also addressed code scanning findings by restricting GitHub Actions to read-only permissions and removing stack traces from production error responses [6], then refreshed Vercel and Node toolchain fixtures to eliminate 105 of 115 remaining alerts [7]. Meanwhile, openai-python is requiring aiohttp 3.14.1+ and limiting the aiohttp backend to Python 3.10+, cutting off the vulnerable 3.13.x versions entirely [8], while CodeQL scanning now runs on pull requests and pushes to main [9].

Action items

→ Review SessionEnd hook implementation for your thread lifecycle workflows in Codex openai/codex [plan]
→ Upgrade openai-node to pick up the code scanning and Dependabot fixes openai/openai-node [plan]
→ Update openai-python pin to aiohttp 3.14.1+ if you use the aiohttp backend on Python 3.10+ openai/openai-python [plan]
→ Monitor Codex plugin installation interstitial requirements for client implementations openai/codex [monitor]

References

[1] Make parent-owned sub-agent threads read-only in the TUI ↗ openai/codex
[2] Add SessionEnd hooks for thread teardown ↗ openai/codex
[3] Render inline visualization links in the TUI (#33925) openai/codex
[4] Launch managed network proxies on remote executors (#33906) openai/codex
[5] fix: address remaining Dependabot alerts ↗ openai/openai-node
[6] fix: address code scanning findings ↗ openai/openai-node
[7] chore: refresh more ecosystem test dependencies ↗ openai/openai-node
[8] fix(deps): require patched aiohttp on Python 3.10+ ↗ openai/openai-python
[9] Set up CodeQL code scanning ↗ openai/openai-python

Quick answers

What shipped in OpenAI on July 18, 2026?: Codex made parent-controlled sub-agent threads read-only in the TUI to prevent rejected server operations, while the Node and Python SDKs are closing security holes across GitHub Actions permissions, error handling, and dependency chains. In total, 52 commits, 52 pull requests, and 2 releases landed.
Who contributed to OpenAI on July 18, 2026?: 4 developers shipped this update, including Felipe Coury, viyatb-oai, copyberry, and jbeckwith-oai.
What were the notable OpenAI updates?: Make parent-owned sub-agent threads read-only in the TUI, Add SessionEnd hooks for thread teardown, and Render inline visualization links in the TUI (#33925).

CODEX SHIPS PAGINATED HISTORY INHERITANCE FOR SUBAGENTS

Codex now preserves conversation context when spawning child agents, fixing a critical gap in multi-agent workflows where history was getting lost on fork.

ai 67 shipped 1-min read

OpenAI 3 days ago

CODEX TIGHTENS MCP PLUMBING WHILE NODE SDK SHIPS ASYNC STREAMING

Codex is systematizing how agents talk to external tools: concurrent writes now serialize, tool catalogs cache across sessions, and failure details stick around through imports.

ai 100 shipped 1-min read

OpenAI 4 days ago

CODEX FIXES GUARDIAN ALIGNMENT AND THREAD HISTORY DURABILITY

Codex shipped critical fixes for Guardian review configuration and SQLite projection recovery, ensuring conversation history stays consistent even when materializations fail.

ai 118 shipped 2-min read

OpenAI 5 days ago

CODEX ROLLS BACK GUARDIAN PROMPTING REGRESSION

Codex 0.144.2 reverted a broken auto-review policy that degraded Guardian behavior, then shipped a version bump with no additional changes.

ai 6 shipped 1-min read

— or follow the whole beat:

Elsewhere on the wire

@cachyos about 6 hours ago

PACKAGE UPDATES ROLL ACROSS AUR DERIVED AND PROTON CACHYOS

Claude Desktop jumped to 1.22209.0, Zen Browser patched to 1.21.8b, and documentation fixes landed across the stack overnight.

infra 43 shipped 1-min read

Elixir & Phoenix about 6 hours ago

ELIXIR CUTS EXPONENTIAL GROWTH IN BDD INTERSECTIONS, PHOENIX LIVE VIEW SKIPS CLONES ON STABLE LISTS

The compiler just got smarter about preventing exponential blowup in type intersection logic, while Phoenix Live View stops wastefully copying keyed comprehensions that aren't moving.

elixir 16 shipped 1-min read

@dotnet about 6 hours ago

ASPNETCORE TIGHTENS AUTHORIZATION METADATA EVERYWHERE, BLAZOR DEBUGGING EXITS

Authorization policies now work consistently across all routing paths, not just endpoint middleware, while Blazor templates drop their deprecated WebAssembly debugging hook.

dotnet 58 shipped 2-min read

@spring-projects about 6 hours ago

SPRING FRAMEWORK TIGHTENS RESOURCE SECURITY, NEO4J FIXES CONVERSION LOGIC

Spring Framework reinstated critical resource location validation checks that prevent unauthorized static resource resolution in sensitive directories.

java 4 shipped 1-min read