How I kept provider and pane control in Codex without losing flow
Resuming a chat after changing your default provider or replaying a conversation could silently break continuity, losing your saved model and reasoning summaries. Codex now pins resumed chats to their saved provider and restores reasoning summaries on replay.
What it is
A Codex TUI update that adds a model provider browser, a side conversation workspace pane, and several fixes for resuming chats, steering running turns, and replaying transcripts.
Applied case
A developer running long Codex sessions in the TUI found that resumed chats ignored their original provider after changing the default for new chats. With this update, open and resumed chats use their saved model provider, and replayed conversations render interrupted replies as a single Markdown message with reasoning summaries restored.
- Resumed chats keep their saved provider even after you change the default for new chats
When to use it
Use when you juggle multiple providers, long-running chats, or side conversations in the TUI.
Skip when a single provider and short chats already work fine.
What it does not solve
The workspace pane and image generation features are behind feature flags you must enable manually, and GIF animation requires an audio or image-capable model. Terminal notifications via osc777 need a terminal that supports it.
Read more
Recommended for you
- WorkflowCodex CLI
How I keep Codex side chats and old tasks findable without losing work
Terminal Codex sessions scatter context across chats and tasks, making it hard to resume past work or hold several investigations at once.
- WorkflowCodex CLI
When to use incremental tool updates instead of legacy streaming?
Codex tool updates on Google Cloud Vertex AI previously arrived in batches rather than as they happen; incremental sending is now the default, with a flag to opt out.
- WorkflowVercel
When to use AI Gateway instead of direct image model APIs?
A separate MiniMax account, key, and bill just to generate product images slows you down until one gateway API key covers it.
- WorkflowVercel
How I filter agent tools without burning output tokens
Routing and policy checks with generative models spend tokens on text you never use.
Enjoyed this article?
Subscribe for new articles. No spam. Unsubscribe anytime.