~/tools/codex
/0.72.0

Codex

OpenAI's Rust-based CLI for interacting with the Codex model.

SYSTEM_CHECK...
LATEST_VER:0.74.0-alpha.5
CHANGES:40
[ OPEN_CHANGELOG ]

🔒 Security Updates

>Sandbox and safety updates (#7809, #7889, #7728): Elevated Sandbox 3/4 plus expanded safe command list.
SECURITY
>Elevated Sandbox 4 #7889 @[iceweasel-oai]
SECURITY
>feat: more safe commands #7728 @[jif-oai]
SECURITY
>Elevated Sandbox 3 #7809 @[iceweasel-oai]
SECURITY

✨ New Features

>Config API cleanup (#7924): new config API and cleaner config loading flow.
>Remote compact for API-key users (#7835): enable remote compacting in key-based sessions.
>support 1p #7945 @[aibrahim-oai]
>feat: clean config loading and config api #7924 @[jif-oai]
>Remote compact for API-key users #7835 @[pakrym-oai]
>feat: introduce utilities for locating pwsh.exe and powershell.exe #7893 @[bolinfest]
>feat: use latest disk value for mcp servers status #7907 @[shijie-oai]

🚀 Improvements

>MCP and TUI status visibility (#7828, #7907): restore MCP startup progress messages in the TUI and use latest disk values
>Windows and PowerShell quality-of-life (#7607, #7893, #7942, #7137): locate pwsh/powershell reliably, parse PowerShell with
>Model/prompt UX for gpt-5.2 (#7934, #7910, #7874, #7911): prompt updates and clearer xhigh reasoning warnings/docs.
>Sign two additional exes for Windows #7942 @[iceweasel-oai]
>chore(prompt) Update base prompt #7943 @[dylan-hurd-oai]
>chore(prompt) Remove truncation details #7941 @[dylan-hurd-oai]
>chores: models manager #7937 @[aibrahim-oai]
>chore(gpt-5.2) prompt update #7934 @[dylan-hurd-oai]
>Make skill name and description limit based on characters not byte counts #7915 @[etraut-openai]
>Make migration screen dynamic #7896 @[aibrahim-oai]
>Update Model Info #7853 @[aibrahim-oai]
>Chore: limit find family visability #7891 @[aibrahim-oai]

🐛 Bug Fixes

>fix cargo build switch #7948 @[iceweasel-oai]
>fix: restore MCP startup progress messages in TUI (fixes #7827) #7828 @[ivanmurashko]
>fix: use PowerShell to parse PowerShell #7607 @[bolinfest]
>fix: race on rx subscription #7921 @[jif-oai]
>fix: break tui #7876 @[jif-oai]
>fix(tui): show xhigh reasoning warning for gpt-5.2 #7910 @[voctory]
>Revert "fix(apply-patch): preserve CRLF line endings on Windows" #7903 @[dylan-hurd-oai]
>Fix misleading 'maximize' high effort description on xhigh models #7874 @[voctory]
>Fix toasts on Windows under WSL 2 #7137 @[dank-openai]
>fix: policy/*.codexpolicy -> rules/*.rules #7888 @[bolinfest]
>fix: omit reasoning summary when ReasoningSummary::None #7845 @[apanasenko-oai]
>fix: drop stale filedescriptor output hash for nix #7865 @[tyleranton]
>fix: dont quit on 'q' in onboarding ApiKeyEntry state #7869 @[sayan-oai]

⚠️ Deprecated

>Added deprecation notice for "chat" wire_api #7897 @[etraut-openai]
DEPRECATED

📚 Documentation

>docs: clarify xhigh reasoning effort on gpt-5.2 #7911 @[voctory]
>Update RMCP client config guidance #7895 @[nornagon-openai]

📦 Other Changes

>remove release script #7885 @[aibrahim-oai]