Who contributed to OpenAI on August 3, 2026?

3 developers shipped this update, including copyberry, Daniel Wolf, and Charlie Marsh.

What were the notable OpenAI updates?

Expose onboarding hints in login completion notifications, Preserve SQLite thread metadata during goal mutations, and Capture rollout budget units from response usage.

OpenAI

Codex, the SDKs, and the engine behind ChatGPT

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODEX HARDENS LOGIN FLOW WITH ONBOARDING HINTS AND METADATA PROTECTION

By RepoJournal · Filed 06:58 UTC on August 3, 2026 · About OpenAI

3 people shipped this

copyberry @copyberry 3 cited

Daniel Wolf @wolf-openai

Charlie Marsh @charliemarsh-oai

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

Codex now accepts allowlisted onboarding entry points in OAuth state parameters while rejecting malformed suffixes, exposing onboarding hints through the v2 login completion notification [1]. This tightens the login flow without breaking existing callback handling. In parallel, a SQLite metadata preservation fix prevents goal mutations from reconciling rollouts unnecessarily and overwriting thread previews and session data [2]. The change skips reconciliation when the indexed rollout matches what's already stored, letting goal mutations repair corrupted thread metadata only when needed. Finally, the platform began capturing rollout budget units from Responses API usage, routing the provider-only value through TokenUsage while keeping it out of client-facing schemas and TypeScript representations [3]. All three changes land as 3 commits across 3 PRs with no breaking shifts to public contracts.

Action items

→ Verify onboarding entrypoint handling in your OAuth integrations for life_sciences suffix support openai/codex [plan]
→ Test thread goal mutations in staging to confirm metadata preservation on next deploy openai/codex [plan]
→ Monitor rollout budget unit capture in token usage telemetry openai/codex [monitor]

References

[1] Expose onboarding hints in login completion notifications ↗ openai/codex
[2] Preserve SQLite thread metadata during goal mutations ↗ openai/codex
[3] Capture rollout budget units from response usage ↗ openai/codex

Quick answers

What shipped in OpenAI on August 3, 2026?: Three critical fixes shipped across auth, data persistence, and usage tracking to prevent thread metadata loss and secure OAuth callback handling. In total, 3 commits and 3 pull requests landed.
Who contributed to OpenAI on August 3, 2026?: 3 developers shipped this update, including copyberry, Daniel Wolf, and Charlie Marsh.
What were the notable OpenAI updates?: Expose onboarding hints in login completion notifications, Preserve SQLite thread metadata during goal mutations, and Capture rollout budget units from response usage.

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 2

CODEX SHIPS AGENT PLUGIN OVERHAUL AND TUI PERFORMANCE FIXES

Codex now handles portable Agent Plugins with schema-declared manifests and cuts terminal redraw overhead by caching screen dimensions instead of querying on every frame.

ai 12 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.