mirror of
https://github.com/openai/codex.git
synced 2026-10-18 17:18:52 +00:00
Eric Traut
57567b8d9e
## Why
Fullscreen composer hints used a small, fixed rotation, while catalog shortcut tips hard-coded default bindings. Tips should reflect the user's configured shortcuts and expose the shared catalog with working links.
## What changed
- Select complete, single-row catalog tips that fit the composer gap, keeping selection stable across redraws and varying it across sessions and turns.
- Prefer eligible startup announcements until a user turn begins, without restoring them after history is cleared. Cache parsed announcements while reevaluating eligibility.
- Resolve `{key:context.action}` placeholders using current primary shortcuts and chords; skip tips with invalid or unbound actions.
- Expand the tip catalog and share Markdown rendering between composer and session tips, preserving hyperlinks and supporting Ctrl/Super-click in the composer gap.
- Keep usage notices and interaction controls ahead of tips, and respect `show_tooltips` and idle, empty input.
## Testing
Add tests and snapshots for remapped shortcuts, unbound actions, stable tip selection, announcement dismissal, narrow layouts, styled links, and removal of stale link targets.
GitOrigin-RevId: 64751293d9f91e4444b112361540a73234f1d51d
47 lines
3.4 KiB
Plaintext
47 lines
3.4 KiB
Plaintext
# Tips support Markdown: **emphasis**, `code`, and [label](https://example.com) links.
|
||
# Tips may use {key:context.action} to insert the configured primary key or chord.
|
||
# A tip is skipped if any referenced action is unbound or unavailable.
|
||
Start a fresh idea with **/new**; the previous session stays in history.
|
||
Use **/feedback** to send logs to the maintainers when something looks off.
|
||
Switch models or reasoning effort quickly with **/model**.
|
||
Use **/permissions** to control when Codex asks for confirmation.
|
||
Run **/review** to get a code review of your current changes.
|
||
Use **/skills** to list available skills or ask Codex to use one.
|
||
Use **/status** to see the current model, approvals, and token usage.
|
||
Use **/statusline** to configure which items appear in the status line.
|
||
Use **/fork** to branch the current chat into a new thread.
|
||
Use **/side** to start a side conversation in a temporary fork without polluting the main thread.
|
||
Use **/init** to create an `AGENTS.md` with project-specific guidance.
|
||
Use **/mcp** to list configured MCP tools.
|
||
Use **/rename** to rename your threads for easier thread resuming.
|
||
Use the OpenAI docs MCP for API questions; enable it with `codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp`.
|
||
Visit the [Codex community forum](https://community.openai.com/c/codex/37).
|
||
You can run any shell command from Codex using `!` (e.g. `!ls`)
|
||
Type `/` to open the command popup; `Tab` autocompletes slash commands.
|
||
When the composer is empty, press `Esc` to step back and edit your last message; `Enter` confirms.
|
||
Press {key:composer.queue} to queue a message when a task is running; otherwise it sends immediately (except `!`).
|
||
Use **/keymap** to configure keyboard shortcuts.
|
||
Paste an image with `Ctrl+V` to attach it to your next message.
|
||
You can resume a previous conversation by running `codex resume`
|
||
Use **/copy** or press {key:global.copy} to copy the latest agent response as Markdown.
|
||
Use **/vim** to toggle Vim editing in the composer.
|
||
Moving from Claude Code? Use **/import** to bring over your setup, project, and recent chats.
|
||
Use **/hooks** to view and manage lifecycle hooks.
|
||
Use **/archive** to archive the current session.
|
||
When worktree support is available, use **/worktree** to start or continue a conversation in a separate Git worktree.
|
||
Coming back to a conversation? Use **/recap** to summarize it.
|
||
When voice is available, use **/voice** to start or stop a voice conversation, or **/voice settings** to choose a voice.
|
||
When goals are enabled, use **/goal** to set or inspect the objective for a long-running task.
|
||
Use **/agents** to open the agent command center.
|
||
Use **/subagents** to switch between this session’s subagents.
|
||
Use **/export** to save your conversation as Markdown.
|
||
When signed in with ChatGPT, use **/usage** to check your account usage and access available usage limit resets.
|
||
Use **/title** to choose what appears in your terminal’s title.
|
||
Use **/theme** to choose a syntax highlighting theme.
|
||
When plugins are enabled, use **/plugins** to browse plugins.
|
||
Press {key:global.open_transcript} to open the full transcript.
|
||
Press {key:global.find_transcript} to search this conversation.
|
||
Press {key:global.open_external_editor} to edit your current draft in an external editor.
|
||
Press {key:composer.history_search_previous} to search previously entered prompts.
|
||
For models with adjustable reasoning, press {key:chat.increase_reasoning_effort} to increase reasoning effort or {key:chat.decrease_reasoning_effort} to decrease it.
|