docs: Claude Code v2.1.218 - Managed Agents effort control + dreaming beta + /code-review backgrounded

content/CHANGELOG.md

@@ -1,5 +1,45 @@
 # Changelog
 
+## 2.1.218
+
+- Changed `/code-review` to run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target
+- Added screen-reader announcements of deleted text for word and line deletions (`Option+Delete`, `Ctrl+W`, `Cmd+Backspace`, `Ctrl+U`, `Ctrl+K`) in `--ax-screen-reader` mode
+- Fixed Windows paths with `\u`-prefixed segments (like `C:\Users\unicorn`) being corrupted into CJK characters in tool inputs, which made those files inaccessible
+- Fixed the left arrow key discarding the conversation with no undo: presses right after editing now ask to confirm, and Esc in the agent view returns to the conversation it backgrounded
+- Added HTTP status and error text to `claude mcp list` and `/mcp` when a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace
+- Fixed multi-line paste collapsing into one line with `j` in place of newlines in terminals that encode pasted newlines as Ctrl+J
+- Fixed `/context` reporting stale pre-compact token usage after compacting from the message picker
+- Fixed `/ultrareview` failing on descriptive arguments like "review my auth changes" — they now run a review of your current branch with the text applied as a note to the findings
+- Fixed `/code-review ultra` silently running a local review in non-interactive sessions — it now launches the cloud review
+- Fixed gateway spend metering to price Bedrock application-inference-profile ARNs and other config-mapped upstream model IDs at the configured model's rates
+- Fixed mojibake when a long IDE selection was truncated mid-emoji, and a case where a tool executor error could be silently dropped
+- Fixed an engine teardown race that could start and abandon a phantom turn, and made input pushed after close consistently rejected
+- Fixed spurious "[Request interrupted by user]" messages after interrupted tool calls, and an unpaired `tool_use` block left in the transcript when a tool aborted mid-response
+- Fixed VoiceOver reading "new line" instead of echoing the typed space at the end of the input in `--ax-screen-reader` mode
+- Fixed plugin and settings panels not moving the terminal cursor to the focused row, so screen readers and magnifiers can follow arrow-key navigation
+- Fixed crashes (maximum call stack exceeded) when a deeply nested watched directory tree was deleted or moved, and when rendering deeply nested UI trees
+- Fixed pull request events occasionally being lost when a session exited immediately after creating or linking a PR
+- Fixed the Bedrock setup wizard failing profile verification for assume-role profiles in partitioned AWS regions and on proxy-only networks
+- Fixed rare negative or incorrect turn duration measurements after a system clock adjustment by timing turns with a monotonic clock
+- Fixed the "N MCP servers need authentication" startup notice over-counting claude.ai connectors that aren't connected in claude.ai
+- Fixed prompt history entries being dropped or duplicated when history writes raced or failed
+- Fixed a retry loop that re-sent identical doomed requests after a context-overflow error with a large thinking budget; `Ctrl+B` backgrounding now applies the same background-shell caps as other paths
+- Fixed agent frontmatter hooks running from untrusted folders: hooks now require the agent file's own folder to have accepted workspace trust
+- Fixed fork-session lineage being lost after compaction in headless and SDK sessions
+- Fixed a resumed session failing every turn, or crashing on resume, when its history held a malformed delta attachment
+- Improved `/ultrareview` error feedback so Claude can correct an invalid argument instead of retrying it unchanged
+- Improved auto mode: the dangerous-rm, background-`&`, and suspicious-Windows-path checks no longer open permission dialogs; the auto-mode classifier adjudicates them instead
+- Improved sandbox command restrictions for IDE interactions
+- Improved trust dialogs to name the repository root the grant covers
+- Changed `/deep-research` to start only when invoked manually; Claude no longer launches it on its own
+- Changed plan mode with auto to no longer prompt for Bash commands the static analyzer can't prove read-only; the auto-mode classifier judges them instead
+- Added an announcement when fast mode changes as a result of switching models via `/config model=<x>` or Remote Control
+- Changed server-managed settings so benign feature and cost toggles no longer trigger the settings-approval prompt
+- Changed agent markdown files to reject agent names containing `:`, which is reserved for plugin namespacing
+- Changed skills with `context: fork` to run in the background by default; opt out per skill with `background: false`
+- Added `yes`/`no`/`on`/`off`/`1`/`0` (case-insensitive) as accepted values for skill and plugin frontmatter booleans, alongside `true`/`false`
+- Fixed remote sessions continuing to send heartbeats after their worker was replaced, which left long-lived desktop and IDE processes retrying a rejected request every few seconds forever
+
 ## 2.1.217
 
 - Added emoji shortcode autocomplete in the prompt input: type `:heart:` to insert ❤️, or `:hea` for suggestions — disable with the `emojiCompletionEnabled` setting

content/claude-code-manifest.json

@@ -1,12 +1,12 @@
 {
   "name": "@anthropic-ai/claude-code",
-  "version": "2.1.217",
+  "version": "2.1.218",
   "author": {
     "name": "Anthropic",
     "email": "support@anthropic.com"
   },
   "license": "SEE LICENSE IN README.md",
-  "_id": "@anthropic-ai/claude-code@2.1.217",
+  "_id": "@anthropic-ai/claude-code@2.1.218",
   "maintainers": [
     {
       "name": "zak-anthropic",
@@ -69,20 +69,20 @@
     "claude": "bin/claude.exe"
   },
   "dist": {
-    "shasum": "54b77f547936a6a2d39599521366dc5f0e5ccbec",
-    "tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.217.tgz",
+    "shasum": "018479d04265ca1b03b87060ca459d14419fac1f",
+    "tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.218.tgz",
     "fileCount": 7,
-    "integrity": "sha512-EIcc3GmI7x+qPlKCjpcLIjCh7YOaCFbOqKfL4BmwZS6QmtduVNT5E98oyr8n2cxsgeWVbnQ0mSVljTw5C/kFtA==",
+    "integrity": "sha512-BHV951ruIa6QXaZFDF1wRhwxAOkAiafB2AOWG6wGRUJ4apaJ9mlzp1BFLAhGfG0SknwAyqBenqeT6nit6at4uQ==",
     "signatures": [
       {
-        "sig": "MEQCIDZyT1ZQyS+UmDvjkU2P2K1zB++6d8XLjSSz26d3H6zcAiAQz+zQTB/zTzuNBYxzuW9QsfnPD04pORZXst0kMy/wFw==",
+        "sig": "MEQCIBXHx44miNa0xlUeRM5+8GnFXTvtg9FIQdXkjqUPY5HzAiAyVpAtVg4pDl8DogLyIQgAJtMP5l1lFIdU/8eBvswJMg==",
         "keyid": "SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"
       }
     ],
-    "unpackedSize": 165315
+    "unpackedSize": 165478
   },
   "type": "module",
-  "_from": "file:staged-npm/anthropic-ai-claude-code-2.1.217.tgz",
+  "_from": "file:staged-npm/anthropic-ai-claude-code-2.1.218.tgz",
   "engines": {
     "node": ">=22.0.0"
   },
@@ -94,8 +94,8 @@
     "name": "wolffiex",
     "email": "wolffiex@anthropic.com"
   },
-  "_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/staged-npm/anthropic-ai-claude-code-2.1.217.tgz",
-  "_integrity": "sha512-EIcc3GmI7x+qPlKCjpcLIjCh7YOaCFbOqKfL4BmwZS6QmtduVNT5E98oyr8n2cxsgeWVbnQ0mSVljTw5C/kFtA==",
+  "_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/staged-npm/anthropic-ai-claude-code-2.1.218.tgz",
+  "_integrity": "sha512-BHV951ruIa6QXaZFDF1wRhwxAOkAiafB2AOWG6wGRUJ4apaJ9mlzp1BFLAhGfG0SknwAyqBenqeT6nit6at4uQ==",
   "_npmVersion": "11.16.0",
   "description": "Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.",
   "directories": {},
@@ -104,17 +104,17 @@
   "_hasShrinkwrap": false,
   "readmeFilename": "README.md",
   "optionalDependencies": {
-    "@anthropic-ai/claude-code-linux-x64": "2.1.217",
-    "@anthropic-ai/claude-code-win32-x64": "2.1.217",
-    "@anthropic-ai/claude-code-darwin-x64": "2.1.217",
-    "@anthropic-ai/claude-code-linux-arm64": "2.1.217",
-    "@anthropic-ai/claude-code-win32-arm64": "2.1.217",
-    "@anthropic-ai/claude-code-darwin-arm64": "2.1.217",
-    "@anthropic-ai/claude-code-linux-x64-musl": "2.1.217",
-    "@anthropic-ai/claude-code-linux-arm64-musl": "2.1.217"
+    "@anthropic-ai/claude-code-linux-x64": "2.1.218",
+    "@anthropic-ai/claude-code-win32-x64": "2.1.218",
+    "@anthropic-ai/claude-code-darwin-x64": "2.1.218",
+    "@anthropic-ai/claude-code-linux-arm64": "2.1.218",
+    "@anthropic-ai/claude-code-win32-arm64": "2.1.218",
+    "@anthropic-ai/claude-code-darwin-arm64": "2.1.218",
+    "@anthropic-ai/claude-code-linux-x64-musl": "2.1.218",
+    "@anthropic-ai/claude-code-linux-arm64-musl": "2.1.218"
   },
   "_npmOperationalInternal": {
-    "tmp": "tmp/claude-code_2.1.217_1784663738795_0.022419413634853447",
+    "tmp": "tmp/claude-code_2.1.218_1784750131986_0.5945423694454417",
     "host": "s3://npm-registry-packages-npm-production"
   }
 }

content/en/about-claude/models/choosing-a-model.md

@@ -58,7 +58,7 @@ This approach is best for:
   The [effort parameter](/docs/en/build-with-claude/effort) defaults to `high` on Claude Opus 4.8 across all surfaces, including Claude Code and the Messages API. Use `xhigh` for coding, high-autonomy work, and the most intelligence-demanding tasks.
 </Note>
 
-**Claude Fable 5** (`claude-fable-5`) is Anthropic's most capable widely released model, delivering next-generation intelligence for long-running agents. **Claude Mythos 5** (`claude-mythos-5`) is available through [Project Glasswing](https://anthropic.com/glasswing). Both models support a 1M token context window by default, up to 128k output tokens, and always-on [adaptive thinking](/docs/en/build-with-claude/adaptive-thinking). See [Introducing Claude Fable 5 and Claude Mythos 5](/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5) for launch details.
+**Claude Fable 5** (`claude-fable-5`) is Anthropic's most capable widely released model, delivering next-generation intelligence for long-running agents. **Claude Mythos 5** (`claude-mythos-5`) is available through [Project Glasswing](https://anthropic.com/glasswing). Both models support a 1M token context window by default, up to 128k output tokens, and always-on [adaptive thinking](/docs/en/build-with-claude/thinking-steering-and-cost). See [Introducing Claude Fable 5 and Claude Mythos 5](/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5) for launch details.
 
 Claude Fable 5 and Claude Mythos 5 are priced at $10 per million input tokens and $50 per million output tokens.
 

content/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5.md

@@ -69,7 +69,7 @@ Claude Fable 5 responds to the same prompting techniques as other Claude models,
 
 ### Adaptive thinking is always on
 
-[Adaptive thinking](/docs/en/build-with-claude/adaptive-thinking) is the only thinking mode on Claude Fable 5 and Claude Mythos 5. It applies whenever the `thinking` parameter is unset. `thinking: {"type": "disabled"}` is not supported. Use the [effort parameter](/docs/en/build-with-claude/effort) to control thinking depth.
+[Adaptive thinking](/docs/en/build-with-claude/thinking-steering-and-cost) is the only thinking mode on Claude Fable 5 and Claude Mythos 5. It applies whenever the `thinking` parameter is unset. `thinking: {"type": "disabled"}` is not supported. Use the [effort parameter](/docs/en/build-with-claude/effort) to control thinking depth.
 
 ### Raw thinking content is never returned
 
@@ -78,7 +78,7 @@ The raw chain of thought is never returned on Claude Fable 5 and Claude Mythos 5
 * `"summarized"` returns thinking blocks with a readable summary of the reasoning.
 * `"omitted"` (the default) returns thinking blocks with an empty `thinking` field.
 
-Pass thinking blocks back unchanged in multi-turn conversations on the same model. See [thinking output on Claude Fable 5 and Claude Mythos 5](/docs/en/build-with-claude/adaptive-thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5) for cross-model handling.
+Pass thinking blocks back unchanged in multi-turn conversations on the same model. See [thinking output on Claude Fable 5 and Claude Mythos 5](/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5) for cross-model handling.
 
 ## Supported features
 
@@ -111,7 +111,7 @@ Step-by-step instructions live in the migration guide:
     Specs and comparison for all current Claude models.
   </Card>
 
-  <Card title="Adaptive thinking" icon="brain" href="/docs/en/build-with-claude/adaptive-thinking">
+  <Card title="Adaptive thinking" icon="brain" href="/docs/en/build-with-claude/thinking-steering-and-cost">
     The only thinking mode on Claude Fable 5 and Claude Mythos 5.
   </Card>