Skip to content

0.143.0-cometix

Pre-release
Pre-release

Choose a tag to compare

New Features

  • Remote plugins are now enabled by default, with richer catalog rows, npm marketplace sources, and visible remote/local versions. (openai#30297, openai#26705, openai#29375, openai#30981)
  • Codex can route authentication and Responses API traffic through macOS and Windows system proxies, including PAC and WPAD configurations. (openai#26708, openai#26709, openai#31335)
  • Added codex remote-control pair for generating manual pairing codes from a running daemon. (openai#29913)
  • Added Amazon Bedrock GPT-5.6 Sol, Terra, and Luna models, with first-class support for max reasoning effort. (openai#30285, openai#30467)
  • MCP tools now use tool search by default, and ChatGPT-hosted MCP servers can explicitly use session authentication. (openai#29486, openai#29733)
  • App-server clients can inspect environments, list descendant threads, and fork history through a specific turn. (openai#30291, openai#29591, openai#30277)

Bug Fixes

  • Fixed Windows ConPTY input handling for line endings and backspace, plus sandbox credential retry edge cases. (openai#29734, openai#29624, openai#29637)
  • Fixed stale TUI safety prompts and cancelled reviews that could leave MCP startup appearing busy. (openai#30490, openai#31189)
  • Improved recovery when exec servers are temporarily offline and prevented remote-control token refresh retry storms. (openai#30098, openai#30201)
  • Preserved trailing realtime transcript text and terminal rollout events during shutdown. (openai#29918, openai#30144)
  • Improved incremental WebSocket request success by ignoring response metadata during comparisons. (openai#30770)
  • Reduced installer failures from GitHub API rate limits by reusing release metadata. (openai#31056)

Documentation

  • Documented UUID7 thread and turn IDs, plus recommended remote-executor integration-test workflows. (openai#27714, openai#29790)

Chores

Changelog

Full Changelog: openai/codex@rust-v0.142.0...rust-v0.143.0