3 ファイル変更+42-7
この更新の概要
利用状況のモニタリングにおける決定ソースの詳細な定義と、各項目の具体的な意味が追加されました。ターミナルの外観カスタマイズ設定に、使用量メーターやメッセージラベル、虹色グラデーションを含む多数の新しいトークンが導入されています。古いCPUや仮想環境で発生するインストールの問題について、AVX命令セットの有無を確認する具体的なコマンドと解説が拡充されました。
@@ -198,7 +198,7 @@ When `OTEL_LOG_TOOL_CONTENT=1`, this span also records a `tool.output` span even
| - | - | - |
| `duration_ms` | Time spent waiting for the permission decision | |
| `decision` | `accept` or `reject` | |
| `source` | Decision source, matching the `tool_decision` event | |
| `source` | Decision source, matching the [Tool decision event](#tool-decision-event) | |
**`claude_code.tool.execution`**
@@ -451,7 +451,7 @@ Incremented when user accepts or rejects Edit, Write, or NotebookEdit tool usage
- All [standard attributes](#standard-attributes)
- `tool_name`: Tool name (`"Edit"`, `"Write"`, `"NotebookEdit"`)
- `decision`: User decision (`"accept"`, `"reject"`)
- `source`: Decision source - `"config"`, `"hook"`, `"user_permanent"`, `"user_temporary"`, `"user_abort"`, or `"user_reject"`
- `source`: Where the decision came from. One of `"config"`, `"hook"`, `"user_permanent"`, `"user_temporary"`, `"user_abort"`, or `"user_reject"`. See the [Tool decision event](#tool-decision-event) for what each value means.
- `language`: Programming language of the edited file, such as `"TypeScript"`, `"Python"`, `"JavaScript"`, or `"Markdown"`. Returns `"unknown"` for unrecognized file extensions.
#### Active time counter
@@ -515,7 +515,7 @@ Logged when a tool completes execution.
- `error_type`: Error category string when the tool failed, such as `"Error:ENOENT"` or `"ShellError"`
- `error` (when `OTEL_LOG_TOOL_DETAILS=1`): Full error message when the tool failed
- `decision_type`: Either `"accept"` or `"reject"`
- `decision_source`: Decision source - `"config"`, `"hook"`, `"user_permanent"`, `"user_temporary"`, `"user_abort"`, or `"user_reject"`
- `decision_source`: Where the decision came from. One of `"config"`, `"hook"`, `"user_permanent"`, `"user_temporary"`, `"user_abort"`, or `"user_reject"`. See the [Tool decision event](#tool-decision-event) for what each value means.
- `tool_input_size_bytes`: Size of the JSON-serialized tool input in bytes
- `tool_result_size_bytes`: Size of the tool result in bytes
- `mcp_server_scope`: MCP server scope identifier (for MCP tools)
@@ -626,7 +626,13 @@ Logged when a tool permission decision is made (accept/reject).
- `tool_name`: Name of the tool (for example, "Read", "Edit", "Write", "NotebookEdit")
- `tool_use_id`: Unique identifier for this tool invocation. Matches the `tool_use_id` passed to hooks, allowing correlation between OTel events and hook-captured data.
- `decision`: Either `"accept"` or `"reject"`
- `source`: Decision source - `"config"`, `"hook"`, `"user_permanent"`, `"user_temporary"`, `"user_abort"`, or `"user_reject"`
- `source`: Where the decision came from:
- `"config"`: Decided automatically without prompting, based on project settings, enterprise managed policy, `--allowedTools` or `--disallowedTools` flags, the active permission mode, or because the tool is inherently safe.
- `"hook"`: A `PreToolUse` or `PermissionRequest` hook returned the decision.
- `"user_permanent"`: Emitted when the user chose "Always allow" when prompted, saving a rule to their personal settings. Also emitted for later calls that match that saved rule. Treated as an accept.
- `"user_temporary"`: Emitted when the user chose "Yes" or "Yes, for this session" when prompted, without saving a rule. Also emitted for later calls in the same session that match that session-scoped allow. Treated as an accept.
- `"user_abort"`: Emitted when the user dismissed the permission prompt without answering. Treated as a reject.
- `"user_reject"`: Emitted when the user chose "No" when prompted, or a call matched a deny rule in their personal settings. Treated as a reject.
#### Permission mode changed event
@@ -134,7 +134,7 @@ The following example defines a theme that keeps the dark preset but recolors th
Claude Code watches `~/.claude/themes/` and reloads when a file changes, so edits made in your editor apply to a running session without a restart.
Below is the full list of customizations you can set in `overrides`. The interactive editor in `/theme` shows the same tokens with a live preview, including a small number of internal tokens not covered here.
The reference below covers the tokens you can set in `overrides`. The interactive editor in `/theme` shows the same tokens with a live preview, plus a few single-purpose accents such as onboarding screen colors that are omitted here.
The following example combines tokens from several of the groups below: the brand accent, the plan mode border, the diff backgrounds, and the fullscreen message background.
@@ -163,6 +163,7 @@ Control the primary brand accent and the foreground text shades used throughout
| `inverseText` | Text drawn on top of a colored background, such as status badges |
| `inactive` | Secondary text such as hints, timestamps, and disabled items |
| `subtle` | Faint borders and de-emphasized secondary text |
| `suggestion` | Autocomplete suggestions and selection highlight in pickers |
| `permission` | Dialog borders, including permission prompts and pickers |
| `remember` | Memory and `CLAUDE.md` indicators |
@@ -210,14 +211,38 @@ Apply only in [fullscreen rendering mode](/en/fullscreen), where messages have a
| Token | Controls |
| :- | :- |
| `userMessageBackground` | Background behind your messages in the transcript |
| `userMessageBackgroundHover` | Background behind a message while hovered or expanded |
| `messageActionsBackground` | Background behind the selected message when the action bar is open |
| `bashMessageBackgroundColor` | Background behind `!` shell command entries in the transcript |
| `memoryBackgroundColor` | Background behind `#` memory entries in the transcript |
| `selectionBg` | Background of text selected with the mouse |
#### Usage meter and speaker labels
Adjust the bar shown in the `/usage` view and the labels that distinguish your messages from Claude's.
| Token | Controls |
| :- | :- |
| `rate_limit_fill` | Filled portion of the usage meter |
| `rate_limit_empty` | Unfilled portion of the usage meter |
| `briefLabelYou` | Color of the `You` label on your messages |
| `briefLabelClaude` | Color of the `Claude` label on assistant messages |
#### Shimmer variants and subagent colors
Several tokens have a paired `Shimmer` variant, such as `claudeShimmer` and `warningShimmer`, that supplies the lighter color used in the spinner's animated gradient. Override the shimmer alongside its base token if the animation looks mismatched.
Several tokens have a paired shimmer variant that supplies the lighter color used in the spinner's animated gradient. Override the shimmer alongside its base token if the animation looks mismatched.
- `claude` and `claudeShimmer`
- `warning` and `warningShimmer`
- `permission` and `permissionShimmer`
- `promptBorder` and `promptBorderShimmer`
- `inactive` and `inactiveShimmer`
- `fastMode` and `fastModeShimmer`
Each [subagent](/en/sub-agents) and parallel task is shown in one of eight named colors so you can tell them apart in the transcript. The token names follow the pattern `<color>_FOR_SUBAGENTS_ONLY`, where `<color>` is `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, or `cyan`. Override these to change what each named color looks like. For example, a subagent with `color: blue` in its definition is drawn using the `blue_FOR_SUBAGENTS_ONLY` value.
The [`ultrathink`](/en/model-config#use-ultrathink-for-one-off-deep-reasoning) and [`ultraplan`](/en/ultraplan) keywords in the prompt input are rendered with a seven-color rainbow gradient. The token names follow the pattern `rainbow_<color>` and `rainbow_<color>_shimmer`, where `<color>` is `red`, `orange`, `yellow`, `green`, `blue`, `indigo`, or `violet`.
## Switch to fullscreen rendering
If the display flickers or the scroll position jumps while Claude is working, switch to [fullscreen rendering mode](/en/fullscreen). It draws to a separate screen the terminal reserves for full-screen apps instead of appending to your normal scrollback, which keeps memory usage flat and adds mouse support for scrolling and selection. In this mode you scroll with the mouse or PageUp inside Claude Code rather than with your terminal's native scrollback; see the [fullscreen page](/en/fullscreen#search-and-review-the-conversation) for how to search and copy.
@@ -568,7 +568,11 @@ If running `claude` or the installer prints `Illegal instruction`, the native bi
**Architecture mismatch.** The installer downloaded the wrong binary, for example x86 on an ARM server. Check with `uname -m` on macOS or Linux, or `$env:PROCESSOR_ARCHITECTURE` in PowerShell. If the result doesn't match the binary you received, [file a GitHub issue](https://github.com/anthropics/claude-code/issues) with the output.
**Missing instruction set on older CPUs.** If your architecture is correct but you still see `Illegal instruction`, your CPU likely lacks AVX or another instruction the binary requires. This affects roughly pre-2013 Intel and AMD processors. There is currently no native-binary workaround; track [issue #50384](https://github.com/anthropics/claude-code/issues/50384) for status, and include your CPU model from `cat /proc/cpuinfo | grep "model name" | head -1` on Linux or `sysctl -n machdep.cpu.brand_string` on macOS when reporting.
**Missing AVX instruction set.** If your architecture is correct but you still see `Illegal instruction`, your CPU likely lacks AVX or another instruction the binary requires. This affects roughly pre-2013 Intel and AMD processors, and virtual machines where the hypervisor does not pass AVX through to the guest.
On a VPS or VM, run `grep -m1 -ow avx /proc/cpuinfo`; an empty result means AVX is not available to the guest.
There is no native-binary workaround; track [issue #50384](https://github.com/anthropics/claude-code/issues/50384) for status, and include your CPU model from `grep -m1 "model name" /proc/cpuinfo` on Linux or `sysctl -n machdep.cpu.brand_string` on macOS when reporting.
Alternative install methods download the same native binary and won't resolve either cause.