One read of Claude Code CLIclaude-code-20261008T020701Z
17 pages moved out of 221 read.
Pages moved
17
significant first
Pages read
221
in this capture
Captured
02:07 UTC
Corpus hash
edfa59895cd4
corpus-hash
What this read moved
1-17 of 17agent-view Changed · +4 / -3 lines
from line 208
208208
209209Type a reply in the peek panel and press `Enter` to send it to that session. Prefix a reply with `!` to send a Bash command instead. What happens to the reply depends on the session and on what you send:
210210
211* A session that's working: the reply joins the session's [message queue](/docs/en/interactive-mode#queue-messages-while-claude-works) instead of interrupting the response, and takes effect [when queued input does](/docs/en/interactive-mode#when-claude-code-sends-what-you-queued). A [command](/docs/en/commands) waits for the turn to end, even one that runs as soon as you type it at a session's own prompt
211* A session that's working: `/model`, `/effort`, `/rename`, and `/usage` run right away. Other replies join the session's [message queue](/docs/en/interactive-mode#queue-messages-while-claude-works) instead of interrupting the response, and take effect [when queued input does](/docs/en/interactive-mode#when-claude-code-sends-what-you-queued). Other [commands](/docs/en/commands) wait for the turn to end, even ones that run as soon as you type them at a session's own prompt
212212* A reply that is exactly `/stop`: stops the session at once instead of being delivered to it, whether the session is working or waiting on you
213213* A [shell job](#run-a-shell-command): the reply, `/stop` included, goes to the command's terminal as typed input
214214
from line 216
216216
217217* A question with predefined choices: the panel lists the choices by number. With the reply input empty, press a choice's number to fill it in, then `Enter` to send it, or type your own answer instead
218218* A question without predefined choices: type your answer. When the empty input shows a suggested reply, press `Tab` to fill it in and edit it before sending
219* A permission prompt or another dialog, such as a [sandbox](/docs/en/sandboxing) prompt or an MCP server's [request for input](/docs/en/mcp#respond-to-mcp-elicitation-requests): replying doesn't answer it. Your reply waits in the queue. To answer the dialog, attach with `→`
219* A permission prompt or another dialog, such as a [sandbox](/docs/en/sandboxing) prompt or an MCP server's [request for input](/docs/en/mcp#respond-to-mcp-elicitation-requests): replying doesn't answer it. Your message waits in the queue. To answer the dialog, attach with `→`
220220
221221When a [`PermissionRequest`](/docs/en/hooks#permissionrequest) or [`PreToolUse`](/docs/en/hooks#pretooluse) hook returns output Claude Code can't validate for the call the session is asking about, the row shows the hook event and `hook output invalid:` with the validation error before the pending request's text. For a hook that fails another way, the row says the hook failed. The session still waits on the same request.
222222
from line 802
802802
803803Each session is its own Claude Code process under the supervisor, and what happens to that process depends on the session's state:
804804
805* **Working, paused on a permission prompt or other dialog, or attached**: the process keeps running. A running subagent, workflow, or monitor counts as working.
805* **Working, paused on a permission prompt or other dialog, or attached**: the process keeps running. A running subagent, workflow, or monitor counts as working, and so does a pending [session-scoped scheduled task](/docs/en/scheduled-tasks), such as a `/loop` wakeup.
806806* **Finished or waiting for your next message, and unattached for about an hour**: the supervisor stops the process to free resources. A session that ended its turn by asking you a question counts as waiting for your next message. The conversation stays on disk, and the next time you attach or reply, the session resumes where it left off. Pin a session with `Ctrl+T` to keep its process running.
807807* **Exited unexpectedly while the supervisor is running**: the supervisor restarts the process. Ending a session you backgrounded yourself with `←` or `/background`, for example with `kill`, marks it stopped instead of restarting it. For sessions that ended with a shutdown, see [Sessions show as failed or stopped after shutdown](#sessions-show-as-failed-after-shutdown).
808808* **After an auto-update**: the supervisor restarts itself onto the new version and moves idle sessions over in the background. Sessions that are working, waiting on you, or attached aren't interrupted.
from line 979
979979| Version | Change |
980980| - | - |
981981| v2.1.290 | [`claude attach` and `claude logs`](#manage-sessions-from-the-shell) can take part of a running session's name in place of the ID. |
982| v2.1.290 | `/model`, `/effort`, `/rename`, and `/usage` sent as a [peek reply](#peek-and-reply) to a working session run right away. |
982983| v2.1.288 | `Ctrl+F` finds sessions by name, and `Alt+↑` / `Alt+↓` jump between group headers. Both, and `Ctrl+R`, can be [rebound](/docs/en/keybindings#agents-actions). |
983984| v2.1.287 | The [`n:<text>` filter](#filter-sessions) finds sessions by name or first prompt. While any filter is active, groups you collapsed expand to show their matches and the first match is selected, so `Enter` opens it. |
984985| v2.1.287 | A command sent as a [peek reply](#peek-and-reply) runs when the session's current turn ends, including the commands that run as soon as you type them at a session's own prompt. A reply that is exactly `/stop` stops the session at once. |
keybindings Changed · +45 / -0 lines
### Above-prompt actions ### Pane actions
from line 60
6060| `EffortSlider` | Effort slider opened by `/effort` |
6161| `Select` | Generic select/list components |
6262| `Plugin` | Plugin dialog (browse, discover, manage) |
63| `AbovePrompt` | The [band above the prompt](#above-prompt-actions), or a button in it, has keyboard focus |
64| `AbovePromptInput` | An input field in the band above the prompt or in a mod's pane has keyboard focus |
65| `AbovePromptSelect` | A select in the band above the prompt or in a mod's pane has keyboard focus |
6366| `Pane` | A pane drawn by a [mod](/docs/en/plugins/mods/interface#know-which-keys-your-mod-can-receive) has keyboard focus |
6467| `PaneField` | An input field or select in a mod's pane has keyboard focus |
6568| `Agents` | [Agent view](/docs/en/agent-view) (`claude agents`) |
from line 392
389392| `plugin:toggle` | Space | Toggle plugin selection |
390393| `plugin:install` | I | Install selected plugins |
391394| `plugin:favorite` | F | Favorite the selected plugin so it sorts near the top of the Installed tab |
395
396### Above-prompt actions
397
398Actions for the band above the prompt, the shared strip where [mods](/docs/en/plugins/mods/interface#pick-where-to-draw) draw buttons, input fields, and selects. `abovePrompt:toggle` and `abovePrompt:focus` apply in the `Chat` context. The other actions apply in the [context](#contexts) of whatever has keyboard focus in the band or a pane.
399
400| Action | Default | Description |
401| :- | :- | :- |
402| `abovePrompt:toggle` | Ctrl+X Ctrl+A | Collapse the band to a one-row hint, or expand it again |
403| `abovePrompt:focus` | Ctrl+X Tab | Move keyboard focus into the band, then to each open [pane](#pane-actions), and from the last pane back to the prompt |
404| `abovePrompt:next` | Tab | Focus the next control |
405| `abovePrompt:previous` | Shift+Tab | Focus the previous control |
406| `abovePrompt:press` | Enter | Press the focused button, submit the focused input field, or pick the highlighted option in a select |
407| `abovePrompt:leave` | Escape | Return keyboard focus to the prompt |
408| `abovePrompt:highlightNext` | Down | Highlight the next option in a focused select |
409| `abovePrompt:highlightPrevious` | Up | Highlight the previous option in a focused select |
410
411Two contexts bind more keys to these actions by default:
412
413* **`AbovePrompt`**: Right and Left also run `abovePrompt:next` and `abovePrompt:previous`, and Space also runs `abovePrompt:press`
414* **`AbovePromptInput`**: Down and Up also run `abovePrompt:next` and `abovePrompt:previous`
415
416The `AbovePrompt` context also binds Up, Down, PageUp, PageDown, Home, and End to the [pane scroll actions](#pane-actions) `pane:scrollUp` through `pane:bottom`, so to change one of those keys for the band, bind the scroll action in an `AbovePrompt` block.
417
418### Pane actions
419
420Actions for a pane drawn by a [mod](/docs/en/plugins/mods/interface#know-which-keys-your-mod-can-receive). The scroll, resize, and close actions apply in the `Pane` [context](#contexts). `pane:close` also applies in the `PaneField` context, so it works while one of the pane's fields has focus. `pane:next` and `pane:previous` apply in the `Global` context while more than one pane is open.
421
422| Action | Default | Description |
423| :- | :- | :- |
424| `pane:scrollUp` | Up | Scroll the pane up when it has more rows than it can show |
425| `pane:scrollDown` | Down | Scroll the pane down when it has more rows than it can show |
426| `pane:pageUp` | PageUp | Scroll the pane up a page |
427| `pane:pageDown` | PageDown | Scroll the pane down a page |
428| `pane:top` | Home | Jump to the top of the pane |
429| `pane:bottom` | End | Jump to the bottom of the pane |
430| `pane:grow` | Ctrl+X Left, Ctrl+X Up | Give the pane more room: width when it sits beside the transcript, height when it sits above the prompt |
431| `pane:shrink` | Ctrl+X Right, Ctrl+X Down | Give the pane less room: width when it sits beside the transcript, height when it sits above the prompt |
432| `pane:close` | Ctrl+X X | Close the pane |
433| `pane:next` | (unbound) | Show the next open pane |
434| `pane:previous` | (unbound) | Show the previous open pane |
435
436The `Pane` context also binds Tab, Shift+Tab, Enter, and Escape to the same [above-prompt actions](#above-prompt-actions) as the band, and a pane's input fields and selects use the `AbovePromptInput` and `AbovePromptSelect` contexts. [Keyboard focus and hotkeys](/docs/en/plugins/mods/interface#know-which-keys-your-mod-can-receive) lists what each key does in a pane.
392437
393438### Settings actions
394439
plugins/mods/api Changed · +5 / -0 lines
from line 188
188188
189189Every one of these calls is itself an event, named for its namespace and method without the `$.`, such as `fs.read` for `$.fs.read`. A mod [earlier in the chain](/docs/en/plugins/mods/events#the-order-mods-run-in) can observe, rewrite, or refuse your call, which is how an organization restricts what mods reach.
190190
191A mod can refuse your `$.process.spawn` call after the command has produced output or exited, and nothing the command did is undone. The call then rejects with a message that ends with one of these strings and the refusing mod's reason:
192
193* **`$.process.spawn started, and a plugin withheld its result:`**: the refusing mod hadn't read the command's output to the end. Claude Code stops the command if it's still running.
194* **`$.process.spawn ran, and a plugin withheld its result:`**: the refusing mod had read the command's output to the end, so the command had exited
195
191196## Next steps
192197
193198* [React to events](/docs/en/plugins/mods/events): hook tool calls, prompts, and turns
plugins/mods/gallery Changed · +8 / -0 lines
from line 373
373373
374374Two more elements have no sample here. `Image` draws a PNG or raw pixels in the terminal. `Client` is a region that a second file of yours draws, for animation and pointer input. The [elements reference](/docs/en/plugins/mods/reference#elements) lists their props.
375375
376Unless Claude Code detects that the terminal draws kitty graphics protocol images with Unicode placeholders, the user sees an `Image`'s `alt` text, dimmed, in place of the picture. Write `alt` text that stands on its own. Detection runs at startup: it succeeds in kitty 0.28 or later and in Ghostty, once the terminal answers Claude Code's graphics query, and fails in these cases:
377
378* **Other terminals**: any terminal that isn't one of those two, or that doesn't answer the query.
379* **tmux and screen**: a session running inside tmux or screen, in any terminal, kitty and Ghostty included.
380* **Background sessions**: every [background session](/docs/en/agent-view), whatever terminal it's attached from.
381
382If your mod's users see the dimmed text in a terminal that does draw those placeholder images, they can set [`CLAUDE_CODE_FORCE_TERMINAL_IMAGES`](/docs/en/env-vars) to `1`, which skips detection. Inside tmux or screen that doesn't help: the `alt` text goes away, and Claude Code sends the picture without wrapping it for tmux or screen passthrough.
383
376384## See where a mod can draw
377385
378386The samples all draw in a pane. A mod can also draw in other places, and call Claude Code to show something for it:
common-workflows Changed · +1 / -1 lines
from line 363
363363 Explain the logic in @src/utils/auth.js
364364 ```
365365
366 This includes the full content of the file in the conversation.
366 This includes the content of the file in the conversation when it fits the [Read tool](/docs/en/tools-reference#read-tool-behavior)'s token limit, 25,000 tokens by default. A text file larger than 256KB isn't included.
367367 </Step>
368368
369369 <Step title="Reference a directory">
corporate-launcher Changed · +1 / -0 lines
from line 114
114114* **Reach `exec` within about three seconds each time the launcher runs.** A cold background dispatch runs the launcher twice in series before the first byte of output, so do slow work such as a single sign-on exchange lazily or from a cache.
115115* **Tolerate being invoked from inside itself.** Claude Code applies the launcher to every nested self-spawn, so a launcher that acquires an exclusive resource must detect that it already holds it.
116116* **Don't write to the terminal before Claude Code starts.** Anything printed before the `exec` is reported as the crash cause if the session dies before initializing.
117* **Don't depend on how arguments are spelled.** A flag's value can arrive as its own argument, `--flag value`, or joined to the flag, `--flag=value`. Which form a flag uses can change between versions.
117118
118119### Format of the launcher value
119120
desktop Changed · +0 / -1 lines
from line 865
865865assets-proxy.anthropic.com
866866claude.ai
867867a.claude.ai
868a-cdn.claude.ai
869868assets.claude.ai
870869downloads.claude.ai
871870*.livepreview.claude.ai
feature-availability Changed · +1 / -2 lines
from line 80
8080 <td>✗</td>
8181 <td>✓</td>
8282 <td>See note <sup><a href="#fn1">1</a></sup></td>
83 <td>✓ ([deployments hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options))</td>
83 <td>✓</td>
8484 </tr>
8585
8686 <tr>
from line 267
267267 **Partial support:**
268268
269269 * [Desktop](/docs/en/desktop): only via [Claude Desktop on 3P](https://claude.com/docs/third-party/claude-desktop/overview)
270 * [Web search](/docs/en/tools-reference#websearch-tool-behavior): [deployments hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options) only
271270 * [Auto mode](/docs/en/auto-mode-config): Sonnet 5 or later, Opus 4.7 or later, Haiku 5.5, and Fable models only
272271 * [Cross-session messaging](/docs/en/cross-session-messaging): between your sessions on this machine only <sup><a href="#fn5">5</a></sup>
273272 * [Zero Data Retention](/docs/en/zero-data-retention): subject to your Azure agreement
github-actions Changed · +2 / -0 lines
from line 124
124124| Permission | Access |
125125| - | - |
126126| Actions | Read and write |
127| Administration | Read |
127128| Checks | Read and write |
128129| Contents | Read and write |
129130| Discussions | Read and write |
130131| Issues | Read and write |
131132| Members | Read |
133| Merge queues | Read |
132134| Metadata | Read |
133135| Pull requests | Read and write |
134136| Repository hooks | Read and write |
llm-gateway-protocol Changed · +1 / -1 lines
from line 172
172172
173173| Header | What to return and why |
174174| :- | :- |
175| `content-type` | Return `text/event-stream` on streamed Anthropic Messages-format responses, and `application/vnd.amazon.eventstream`, unmodified, on Amazon Bedrock-format responses, where [a different type fails the request](/docs/en/amazon-bedrock#streaming-errors-behind-a-gateway-or-proxy). [Streaming](#streaming) lists which connections run stall detection on these streams |
175| `content-type` | Return `text/event-stream` on streamed Anthropic Messages-format responses, and `application/vnd.amazon.eventstream`, unmodified, on Amazon Bedrock-format responses, where [a different type fails the request](/docs/en/amazon-bedrock#streaming-errors-behind-a-gateway-or-proxy) |
176176| `retry-after` | Return integer seconds rather than an HTTP date. Claude Code waits at least that long before the next [automatic retry](/docs/en/errors#automatic-retries), and outside [`CLAUDE_CODE_RETRY_WATCHDOG`](/docs/en/env-vars) sessions a value above 60 stops the retries and shows the error at once |
177177| `x-should-retry` | Pass the upstream's value through unchanged. Claude Code reads this header as one input when deciding whether to retry a failed request: `true` marks the response retryable and `false` marks it not retryable. For retry counts, backoff, and which failures Claude Code retries, see [automatic retries](/docs/en/errors#automatic-retries) |
178178| `anthropic-ratelimit-unified-*` | Forward the upstream's values unchanged on every response. Claude Code reads them on successful responses to show usage against plan limits to developers signed in with claude.ai, and on a `429` to tell a plan limit or spend cap from a temporary throttle; see [usage limits](/docs/en/errors#usage-limits) |
mcp Changed · +0 / -4 lines
from line 1306
13061306
13071307The annotation applies independently of `MAX_MCP_OUTPUT_TOKENS` for text content, so users don't need to raise the environment variable for tools that declare it. Tools that return image data are still subject to the token limit.
13081308
1309<Warning>
1310 If you frequently encounter output warnings with specific MCP servers you don't control, consider increasing the `MAX_MCP_OUTPUT_TOKENS` limit. You can also ask the server author to add the `anthropic/maxResultSizeChars` annotation or to paginate their responses. The annotation has no effect on tools that return image content; for those, raising `MAX_MCP_OUTPUT_TOKENS` is the only option.
1311</Warning>
1312
13131309### Images in tool results
13141310
13151311When an MCP tool returns a PNG, JPEG, GIF, or WebP image, Claude sees the image inline in the conversation. The inline copy may be scaled down or compressed to fit the model's image size limits. Claude Code also saves the original bytes to a file in the session's `tool-results` directory under [`~/.claude/projects/`](/docs/en/claude-directory#cleaned-up-automatically) and gives Claude the path. Claude can then crop, convert, or reuse the full-resolution file with tools such as Bash.
overview Changed · +1 / -1 lines
from line 36
3636 curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
3737 ```
3838
39 When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or isn't recognized, the install directory isn't on your PATH yet: see [Fix your PATH](/docs/en/troubleshoot-install#command-not-found-claude-after-installation).
39 The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or isn't recognized, the install directory isn't on your PATH yet: see [Fix your PATH](/docs/en/troubleshoot-install#command-not-found-claude-after-installation).
4040
4141 If you see `The token '&&' is not a valid statement separator`, you're in PowerShell, not CMD. If you see `'irm' is not recognized as an internal or external command`, you're in CMD, not PowerShell.
4242
plugins/mods/reference Changed · +2 / -2 lines
from line 223
223223| [`Text`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `color`, `backgroundColor`, `bold`, `italic`, `underline`, `dimColor`, `inverse`, `wrap` | ✓ | ✓ |
224224| [`Button`](/docs/en/plugins/mods/interface#respond-to-presses-and-typing) | `key`, `label`, `onPress`, `hotkey`, `plain`, `dimColor`, `autoFocus`, `action` | ✓ | ✓ |
225225| `Link` | `href`, `label` | ✓ | ✓ |
226| `Code` | The code | ✓ | ✓ |
226| [`Code`](/docs/en/plugins/mods/gallery#show-code-and-changes) | `source`, `language`, `path`, `startLine`, `format`, `wrap` | ✓ | ✓ |
227227| `Markdown` | `text`, `key`, `dimColor`, `onLinkPress`, `pressableLinks` | ✓ | ✓ |
228228| [`Input`](/docs/en/plugins/mods/interface#take-typed-input-and-draw-a-row-for-each-item) | `key`, `label`, `placeholder`, `value`, `submitLabel`, `onSubmit`, `onInput`, `autoFocus` | ✓ | ✓ |
229229| `Select` | `key`, `label`, `options`, `value`, `onSelect`, `autoFocus` | ✓ | ✓ |
from line 230
230230| `Svg` | An SVG document, up to 131,072 characters | | ✓ |
231231| [`Client`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `module`, `key` | ✓ | ✓ |
232232| [`Raster`](/docs/en/plugins/mods/interface#draw-a-grid-of-colored-cells) | `key`, `columns` up to 512, `rows` up to 256, `cells`. See [Draw a grid of colored cells](/docs/en/plugins/mods/interface#draw-a-grid-of-colored-cells). | ✓ | |
233| `Image` | PNG or RGBA bytes up to 2 MiB, or a file path | ✓ | |
233| `Image` | PNG or RGBA bytes up to 2 MiB, or a file path, `columns` and `rows` up to 255, and `alt` text. | ✓ | |
234234
235235More `Button` rules: `action` names one of Claude Code's own [keybinding actions](/docs/en/keybindings), and the user's binding for it presses the button when that binding is a chord or a modified key. A digit `hotkey` on a button in the band also fires when the user types that digit alone into an empty prompt and pauses. When two buttons in one drawing name the same `hotkey`, the later one gets it. `autoFocus` accepts only `true` on any control, so omit the prop to leave it off.
236236
quickstart Changed · +1 / -1 lines
from line 45
4545 curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
4646 ```
4747
48 When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or isn't recognized, the install directory isn't on your PATH yet: see [Fix your PATH](/docs/en/troubleshoot-install#command-not-found-claude-after-installation).
48 The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or isn't recognized, the install directory isn't on your PATH yet: see [Fix your PATH](/docs/en/troubleshoot-install#command-not-found-claude-after-installation).
4949
5050 If you see `The token '&&' is not a valid statement separator`, you're in PowerShell, not CMD. If you see `'irm' is not recognized as an internal or external command`, you're in CMD, not PowerShell.
5151
setup Changed · +1 / -1 lines
from line 53
5353 curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
5454 ```
5555
56 When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or isn't recognized, the install directory isn't on your PATH yet: see [Fix your PATH](/docs/en/troubleshoot-install#command-not-found-claude-after-installation).
56 The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or isn't recognized, the install directory isn't on your PATH yet: see [Fix your PATH](/docs/en/troubleshoot-install#command-not-found-claude-after-installation).
5757
5858 If you see `The token '&&' is not a valid statement separator`, you're in PowerShell, not CMD. If you see `'irm' is not recognized as an internal or external command`, you're in CMD, not PowerShell.
5959
tools-reference Changed · +1 / -1 lines
from line 625
625625The search backend is not configurable. To search with a different provider, add an [MCP server](/docs/en/mcp) that exposes a search tool.
626626
627627<Note>
628 WebSearch is available on the Claude API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws). On Microsoft Foundry it requires a [deployment hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options): deployments hosted on Azure don't support server-side tools, so the WebSearch call fails. On Google Cloud's Agent Platform it works with Claude 4 and later models, including Opus, Sonnet, and Haiku. Amazon Bedrock doesn't expose the server-side web search tool.
628 WebSearch is available on the Claude API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and Microsoft Foundry. On Google Cloud's Agent Platform it works with Claude 4 and later models, including Opus, Sonnet, and Haiku. Amazon Bedrock doesn't expose the server-side web search tool.
629629</Note>
630630
631631### Session search limit
vs-code Changed · +1 / -0 lines
from line 565
565565* **Claude's replies**: the extension announces each reply once, when it's complete, and stays silent while text streams in. Your screen reader reads code blocks as a line-count summary, reads links by their label, and reads tables cell by cell; the full reply stays readable in the transcript.
566566* **Permission requests and questions**: the extension announces a request when its permission prompt appears, naming the tool Claude wants to use. It announces in the same way when Claude asks you a question and when Claude finishes a plan and waits for your review.
567567* **Status changes**: the extension announces when Claude starts working, when Claude is ready for your input, and when Claude Code starts compacting the conversation.
568* **Queued messages**: when you send a message while Claude is working, the extension announces "Message queued." for that message.
568569* **Errors and model prompts**: the extension announces errors in the conversation, and announces when the [usage-credits consent prompt](/docs/en/model-config#fable-and-usage-credits) or the [flagged-request prompt](/docs/en/model-config#ask-before-switching) appears.
569570
570571While Claude works, your screen reader reads a text label in place of the progress spinner's animation.