OpenAI published the stable Codex CLI release rust-v0.166.0 on GitHub at 19:47 UTC on Oct 29. It adds keyboard-driven transcript selection by word, line and page with built-in search, adds GPT-6.1 Terra to the bundled, Vertex AI and Amazon Bedrock model catalogs, introduces codex queue --resume and codex doctor --network-only, and shows clearer safety-block explanations with selectable safer follow-up prompts in the TUI.
Key Takeaways
- ✓Model catalogs: GPT-6.1 Terra added to the bundled, Vertex AI and Amazon Bedrock catalogs (#57293)
- ✓Transcript: keyboard selection by word, line and page, integrated search and configurable shortcuts (#57221 to #57224)
- ✓New commands: codex queue --resume resumes unloaded threads after queueing a message; codex doctor --network-only checks config, connectivity and WebSocket
- ✓Safety UX: clearer explanations when a request is blocked, plus selectable safer follow-up prompts (#57363, #57365)
- ✓Fixes: approval and permission settings survive resume and fork, and reasoning-token accounting is preserved to avoid premature compaction
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background and pain point
Codex CLI is OpenAI's open-source terminal coding agent, and it ships pre-releases almost weekly. Day-to-day pain points include copying a precise slice of a long transcript, client model catalogs lagging behind new models on enterprise routes through Google Cloud or AWS, hard-to-debug network or proxy problems, and permission settings getting lost when threads are resumed or forked. The stable release rust-v0.166.0 on Oct 29 (the previous stable was 0.165.0) addresses these.
How it works
The TUI gains keyboard-driven transcript selection with word, line and page motions, built-in search and configurable shortcuts, and Markdown now renders consistently in async questions, choices, answers and transcript replies. On models, GPT-6.1 Terra joins the bundled, Vertex AI and Amazon Bedrock catalogs, and provider settings can now set a GCP project and location. New commands are codex queue --resume and codex doctor --network-only. When a request is blocked for safety, the TUI explains why and offers selectable safer follow-up prompts.
Benchmarks and results
This is a client update and OpenAI published no benchmarks or performance figures. For GPT-6.1 Terra's capabilities, refer to OpenAI's Oct 26 launch notes; this release only adds it to the client catalogs. Stability fixes include preserving reasoning-token accounting across resume and fork to avoid premature compaction, and fixing app-server thread startup and shutdown races.
Getting started
Upgrade to 0.166.0 through npm or Homebrew. If network or proxy calls fail, run codex doctor --network-only first. Teams on Bedrock or Vertex AI can pick GPT-6.1 Terra from the catalog and set their GCP project and location in provider config. The full change list is on the GitHub release page and the 0.165.0 to 0.166.0 compare view.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.