We break down the latest ChatGPT for iOS release and how it improves remote coding on the go, from choosing branches and carrying over local changes to keeping long setup tasks alive in the background. The episode also covers composer @ mentions, draft preservation, and the caveats around syncing dirty worktrees back to your host machine.

Show Notes

• ChatGPT & Codex changelog: https://learn.chatgpt.com/docs/changelog

This episode breaks down why Codex sessions were losing Guardian approval context during long runs, how context compaction caused security amnesia, and what changed in the latest release to keep approvals persistent.

It also covers subagent isolation, rollback boundaries, and a reliability fix for headless codex exec resume workflows in compressed rollouts.

Show Notes

• Releases · openai/codex - GitHub: https://github.com/openai/codex/releases

This episode breaks down how Codex 0.153.3 brings native GPT 6 Astra support to Amazon Bedrock, eliminating proxy hacks and fixing a Bedrock payload crash. It also covers headless API model overrides, TUI cleanup options, and a new early warning for Plus and Team usage limits.

We break down the latest Codex CLI release, including direct remote plugin marketplace management, enterprise source enforcement, and app server reconciliation for consistent tooling across projects. The episode also covers Guardian latency improvements, TUI cleanup options, and earlier usage warnings for Plus and Team accounts.

We break down Codex CLI 0.153.4’s quiet but major shift to GPT 6 Astra as the bundled default, plus the new request user input async tool that keeps terminal agents moving while they wait on you. The episode also covers Astra’s speed gains, safety behavior, Bedrock availability, and handy TUI fixes like Vim undo/redo and recap controls.

We break down the latest Codex CLI 0.153.0 updates, including account-scoped MCP approvals that prevent cross-account tool leakage, plus more reliable relative path launches on macOS. The episode also covers compressed rollouts, improved resume behavior, earlier usage warnings for Plus and Team users, and a small TUI config migration.

Show Notes

• Releases · openai/codex - GitHub: https://github.com/openai/codex/releases

We break down Codex 0.153.0’s experimental context mode, including the new new_context tool, smarter token budgeting, and which plans can actually enable it. The episode also covers quality-of-life upgrades like plugin marketplace commands, Vim mode fixes, auto recap controls, and stronger TUI reconnection handling.

This episode covers OpenAI Codex 0.152.1 fixes for Guardian authorization persistence during context compaction, plus faster Node REPL execution through model-level policy support. It also digs into terminal security hardening, cloud task origin isolation, and quality-of-life updates like actionable rate limit banners and Vim-style draft search.

We break down Codex CLI 0.152.0, where turn planning is now off by default to cut prompt overhead and token usage, with guidance on when to re-enable it for bigger refactors. The episode also covers MCP output limits, session-safe truncation, expanded server naming, Vim-mode polish, and longer shell command timeouts.

We break down Codex 0.151.0’s biggest workflow fixes, from per-repository plugin catalogs that isolate bad configs to configurable MCP startup grace periods and smarter model fallback handling.

Plus, we cover improved tool planning across mid-session model switches, new diagnostics, and permission profile fixes that keep development environments stable and predictable.