Release 0.124.0-cometix · Haleclipse/codex

New Features

The TUI now has quick reasoning controls: Alt+, lowers reasoning, Alt+. raises it, and accepted model upgrades now reset reasoning to the new model’s default instead of carrying over stale settings. (openai#18866, openai#19085)
App-server sessions can now manage multiple environments and choose an environment and working directory per turn, which makes multi-workspace and remote setups easier to target precisely. (openai#18401, openai#18416)
Added first-class Amazon Bedrock support for OpenAI-compatible providers, including AWS SigV4 signing and AWS credential-based auth. (openai#17820)
Remote plugin marketplaces can now be listed and read directly, with more reliable detail lookups and larger result pages. (openai#18452, openai#19079)
Hooks are now stable, can be configured inline in config.toml and managed requirements.toml, and can observe MCP tools as well as apply_patch and long-running Bash sessions. (openai#18893, openai#18385, openai#18391, openai#18888, openai#19012)
Eligible ChatGPT plans now default to the Fast service tier unless you explicitly opt out. (openai#19053)

Preserved Cloudflare cookies across approved ChatGPT hosts, reducing auth breakage in HTTP-backed ChatGPT flows. (openai#17783)
Fixed remote app-server reliability issues so websocket events keep draining under load and shutdown no longer fails when the remote worker exits during cleanup. (openai#18932, openai#18936)
Fixed permission-mode drift so /permissions changes survive side conversations and updated Full Access state is correctly reflected in MCP approval handling. (openai#18924, openai#19033)
Fixed wait_agent so it returns promptly when mailbox work is already queued instead of waiting for a fresh notification or timing out. (openai#18968)
Fixed local stdio MCP launches for relative commands without an explicit cwd, bringing fallback path resolution in line with CLI behavior. (openai#19031)
Startup now fails less often on managed config edge cases: unknown feature requirements warn instead of aborting, and cloud-requirements errors are clearer about what failed. (openai#19038, openai#19078)

openai#18870 Load app-server config through ConfigManager @pakrym-oai
openai#18866 feat(tui): shortcuts to change reasoning level temporarily @fcoury-oai
openai#18430 app-server: implement device key v2 methods @euroelessar
openai#18757 fix: fully revert agent identity runtime wiring @efrazer-oai
openai#17783 Preserve Cloudfare HTTP cookies in codex @shijie-oai
openai#18876 [rollout_trace] Add rollout trace crate @cassirer-openai
openai#18401 Support multiple managed environments @starr-openai
openai#18797 Allow guardian bare allow output @maja-openai
openai#18886 Normalize /statusline & /title items @canvrno-oai
openai#18768 [codex] Tighten external migration prompt tests @alexsong-oai