Compare commits

...

4 Commits

Author SHA1 Message Date
GitHub Actions
64ceb97caa chore: Update CHANGELOG.md and feed.xml 2026-06-15 21:35:48 +00:00
GitHub Actions
ca9f6045fc chore: Update CHANGELOG.md and feed.xml 2026-06-12 21:53:22 +00:00
GitHub Actions
ee81682a72 chore: Update CHANGELOG.md and feed.xml 2026-06-12 04:23:45 +00:00
GitHub Actions
5754a8bd4f chore: Update CHANGELOG.md and feed.xml 2026-06-12 01:16:30 +00:00
2 changed files with 153 additions and 139 deletions

View File

@@ -1,5 +1,75 @@
# Changelog
## 2.1.178
- Added `Tool(param:value)` syntax for permission rules to match a tool's input parameters (with `*` wildcard), e.g. `Agent(model:opus)` to block Opus subagents
- Skills in nested `.claude/skills` directories now load when working on files there; on a name clash, the nested skill appears as `<dir>:<name>` so both stay available
- Nested `.claude/` directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing `.claude/workflows/`
- Improved auto mode: subagent spawns are now evaluated by the classifier before launch, closing a gap where a subagent could request a blocked action without review
- Improved `/doctor` with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names
- Improved the skill listing truncation warning to show how many skill descriptions are affected
- Changed the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like "run a workflow" or "workflow:", not on any mention of the word
- Improved Remote Control error messages: connection failures now show a persistent red "/rc failed" indicator in the footer, and the "not yet enabled" error now explains whether it's a gate, a check failure, stale entitlement, or org policy
- `/bug` now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title
- Fixed a crash (out-of-memory) when the CLI inherits a stale websocket/OAuth file-descriptor environment variable from a parent process
- Fixed Claude in Chrome silently failing to connect when the OAuth token belongs to a different account than the Claude Code login
- Fixed nested `.claude/skills` skills with directory-qualified names being blocked by permission prompts in non-interactive runs
- Fixed several subagent issues: viewing a subagent's transcript now shows tool results and live progress, messages sent while it finishes its turn are no longer dropped, and backgrounding a running subagent (ctrl+b) no longer restarts it from scratch
- Fixed `claude agents` workers failing with `401 Invalid bearer token` when the daemon was started from a shell with a custom API gateway via `ANTHROPIC_BASE_URL` and `ANTHROPIC_AUTH_TOKEN`
- Fixed compaction not honoring `--fallback-model`: compaction now falls back to the configured fallback model chain on overload or model-availability errors
- Fixed model requests continuing to fail with auth errors after credentials were refreshed outside the session, due to a stale cached request configuration
- Fixed background sessions created with `/bg` or `←←` after a turn finished showing "Working" forever in the agents list
- Fixed `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1` preventing fresh marketplace installs from cloning
- Fixed MCP server-level specs (`mcp__server`, `mcp__server__*`, `mcp__*`) in subagent `disallowedTools` being silently ignored
- Fixed vim mode undo: `u` now steps through NORMAL/VISUAL-mode commands one at a time instead of merging commands in quick succession into a single undo step
- Fixed statusline links with custom URI schemes (e.g. `vscode://`) not opening when clicked in `claude agents`
- [VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task
## 2.1.176
- Session titles are now generated in the language of your conversation (set the `language` setting to pin a specific language)
- Added `footerLinksRegexes` setting for regex-matched link badges in the footer row, configurable via user or managed settings
- Improved Bedrock credential caching: credentials from `awsCredentialExport` are now cached until their `Expiration` instead of a fixed 1 hour
- Fixed `availableModels` enforcement: alias model picks can no longer be redirected to a blocked model via `ANTHROPIC_DEFAULT_*_MODEL` environment variables, and `/fast` now refuses to toggle when it would switch to a model outside the allowlist
- Fixed auto mode failing on Fable 5 for organizations without Opus 4.8 enabled — the classifier now falls back to the best available Opus model
- Fixed hook `if` conditions for Read/Edit/Write tool paths: documented patterns like `Edit(src/**)`, `Read(~/.ssh/**)`, and `Read(.env)` now match correctly
- Fixed Linux sandbox failing to start when `.claude/settings.json` is a symlink with an absolute target
- Fixed `/copy` and mouse-selection copy not reaching the system clipboard inside tmux over SSH, and tmux paste buffer not loading on versions older than 3.2
- Fixed Remote Control connecting from web/mobile silently switching the session's model
- Fixed Remote Control disconnect notifications showing a bare numeric code instead of a human-readable reason, and connection failures adding a duplicate line to the conversation transcript
- Fixed Remote Control sessions not disconnecting when you sign in to a different account
- Fixed `/cd` and worktree moves leaving the session reporting the previous directory's git branch
- Fixed `claude agents`: pressing back in one window no longer detaches other windows attached to the same session
- Fixed backgrounded sessions showing "Working" forever when `/bg` mid-turn had nothing left to continue
- Fixed background agent search by PR URL: PRs opened during scheduled wakeups or while a job was blocked now appear in `claude agents` search
- Fixed the agents view input showing no text cursor on Windows
- Fixed `claude --bg -cn <name>` not seeding the session name
- Fixed background sessions to neutralize Windows network paths in persisted state before respawn
- Fixed background-session respawn rejecting malformed resume IDs from corrupted state files
- Fixed the Windows background-service daemon not starting when `~/.claude/daemon` has the ReadOnly attribute set
- Fixed cloud sessions failing with "Could not resolve authentication method" when idle for too long before being claimed
- Background sessions now show clearer guidance when a window left open across an auto-update can't submit a reply, and `claude daemon status` explains version-skew behavior
## 2.1.175
- Added `enforceAvailableModels` managed setting — when enabled, the `availableModels` allowlist also constrains the Default model (a Default that would resolve to a disallowed model now falls back to the first allowed model), and user or project settings can no longer widen a managed `availableModels` list
## 2.1.174
- Added `wheelScrollAccelerationEnabled` setting to disable mouse-wheel scroll acceleration in fullscreen mode
- Fixed the `/model` picker hiding the model family that Default resolves to — Opus now appears as its own row on Max/Team Premium/Enterprise plans, Sonnet on Pro/Team plans, and Opus on pay-as-you-go API accounts
- Fixed `/model` picker showing a hardcoded Sonnet version label when `ANTHROPIC_DEFAULT_SONNET_MODEL` pins a different Sonnet
- Fixed the "Fable 5 is now consuming usage credits" banner incorrectly showing for enterprise accounts with usage-based billing
- Fixed Bedrock GovCloud regions (`us-gov-*`) deriving the wrong inference profile prefix (`global` instead of `us-gov`), causing 400 errors on derived model IDs
- Fixed background sessions inheriting another session's `ANTHROPIC_*` provider env (gateway URL, custom headers, `/model` aliases) from the shell that started the background daemon
- Fixed a 1-2 second pause when exiting Claude Code shortly after a shell command was interrupted or killed on macOS and Linux
- Fixed git commit co-author attribution showing an incorrect model name for some models
- Fixed the `/advisor` dialog pre-selecting a saved advisor model that is blocked by the `availableModels` allowlist
- Fixed skill hot-reload re-sending the entire skill listing when a single skill changed; only changed skills are now re-announced
- Fixed Workflow tool `agent()` subagents missing per-agent attribution headers
- [VSCode] Added usage attribution to the Account & usage dialog (`/usage`) showing cache misses, long context, subagents, and per-skill/agent/plugin/MCP breakdowns over the last 24h or 7d
- Fixed pre-warmed background workers failing with "Could not resolve authentication method" when claimed after sitting idle
## 2.1.173
- Fixed Fable 5 model names with a `[1m]` suffix not being normalized — Fable 5 includes 1M context by default, so the suffix is now stripped automatically

222
feed.xml
View File

@@ -6,7 +6,89 @@
<author><name>Anthropic</name></author>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/>
<link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/>
<updated>2026-06-11T05:41:48Z</updated>
<updated>2026-06-15T21:35:48Z</updated>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.178</id>
<title>Claude Code v2.1.178</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.178"/>
<updated>2026-06-15T21:35:48Z</updated>
<content type="html">&lt;p&gt;• Added Tool(param:value) syntax for permission rules to match a tool's input parameters (with * wildcard), e.g. Agent(model:opus) to block Opus subagents&lt;/p&gt;
&lt;p&gt;• Skills in nested .claude/skills directories now load when working on files there; on a name clash, the nested skill appears as &amp;lt;dir&amp;gt;:&amp;lt;name&amp;gt; so both stay available&lt;/p&gt;
&lt;p&gt;• Nested .claude/ directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing .claude/workflows/&lt;/p&gt;
&lt;p&gt;• Improved auto mode: subagent spawns are now evaluated by the classifier before launch, closing a gap where a subagent could request a blocked action without review&lt;/p&gt;
&lt;p&gt;• Improved /doctor with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names&lt;/p&gt;
&lt;p&gt;• Improved the skill listing truncation warning to show how many skill descriptions are affected&lt;/p&gt;
&lt;p&gt;• Changed the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like "run a workflow" or "workflow:", not on any mention of the word&lt;/p&gt;
&lt;p&gt;• Improved Remote Control error messages: connection failures now show a persistent red "/rc failed" indicator in the footer, and the "not yet enabled" error now explains whether it's a gate, a check failure, stale entitlement, or org policy&lt;/p&gt;
&lt;p&gt;• /bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title&lt;/p&gt;
&lt;p&gt;• Fixed a crash (out-of-memory) when the CLI inherits a stale websocket/OAuth file-descriptor environment variable from a parent process&lt;/p&gt;
&lt;p&gt;• Fixed Claude in Chrome silently failing to connect when the OAuth token belongs to a different account than the Claude Code login&lt;/p&gt;
&lt;p&gt;• Fixed nested .claude/skills skills with directory-qualified names being blocked by permission prompts in non-interactive runs&lt;/p&gt;
&lt;p&gt;• Fixed several subagent issues: viewing a subagent's transcript now shows tool results and live progress, messages sent while it finishes its turn are no longer dropped, and backgrounding a running subagent (ctrl+b) no longer restarts it from scratch&lt;/p&gt;
&lt;p&gt;• Fixed claude agents workers failing with 401 Invalid bearer token when the daemon was started from a shell with a custom API gateway via ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN&lt;/p&gt;
&lt;p&gt;• Fixed compaction not honoring --fallback-model: compaction now falls back to the configured fallback model chain on overload or model-availability errors&lt;/p&gt;
&lt;p&gt;• Fixed model requests continuing to fail with auth errors after credentials were refreshed outside the session, due to a stale cached request configuration&lt;/p&gt;
&lt;p&gt;• Fixed background sessions created with /bg or ←← after a turn finished showing "Working" forever in the agents list&lt;/p&gt;
&lt;p&gt;• Fixed CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloning&lt;/p&gt;
&lt;p&gt;• Fixed MCP server-level specs (mcp__server, mcp__server__*, mcp__*) in subagent disallowedTools being silently ignored&lt;/p&gt;
&lt;p&gt;• Fixed vim mode undo: u now steps through NORMAL/VISUAL-mode commands one at a time instead of merging commands in quick succession into a single undo step&lt;/p&gt;
&lt;p&gt;• Fixed statusline links with custom URI schemes (e.g. vscode://) not opening when clicked in claude agents&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.176</id>
<title>Claude Code v2.1.176</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.176"/>
<updated>2026-06-12T21:53:21Z</updated>
<content type="html">&lt;p&gt;• Session titles are now generated in the language of your conversation (set the language setting to pin a specific language)&lt;/p&gt;
&lt;p&gt;• Added footerLinksRegexes setting for regex-matched link badges in the footer row, configurable via user or managed settings&lt;/p&gt;
&lt;p&gt;• Improved Bedrock credential caching: credentials from awsCredentialExport are now cached until their Expiration instead of a fixed 1 hour&lt;/p&gt;
&lt;p&gt;• Fixed availableModels enforcement: alias model picks can no longer be redirected to a blocked model via ANTHROPIC_DEFAULT_*_MODEL environment variables, and /fast now refuses to toggle when it would switch to a model outside the allowlist&lt;/p&gt;
&lt;p&gt;• Fixed auto mode failing on Fable 5 for organizations without Opus 4.8 enabled — the classifier now falls back to the best available Opus model&lt;/p&gt;
&lt;p&gt;• Fixed hook if conditions for Read/Edit/Write tool paths: documented patterns like Edit(src/), Read(~/.ssh/), and Read(.env) now match correctly&lt;/p&gt;
&lt;p&gt;• Fixed Linux sandbox failing to start when .claude/settings.json is a symlink with an absolute target&lt;/p&gt;
&lt;p&gt;• Fixed /copy and mouse-selection copy not reaching the system clipboard inside tmux over SSH, and tmux paste buffer not loading on versions older than 3.2&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control connecting from web/mobile silently switching the session's model&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control disconnect notifications showing a bare numeric code instead of a human-readable reason, and connection failures adding a duplicate line to the conversation transcript&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control sessions not disconnecting when you sign in to a different account&lt;/p&gt;
&lt;p&gt;• Fixed /cd and worktree moves leaving the session reporting the previous directory's git branch&lt;/p&gt;
&lt;p&gt;• Fixed claude agents: pressing back in one window no longer detaches other windows attached to the same session&lt;/p&gt;
&lt;p&gt;• Fixed backgrounded sessions showing "Working" forever when /bg mid-turn had nothing left to continue&lt;/p&gt;
&lt;p&gt;• Fixed background agent search by PR URL: PRs opened during scheduled wakeups or while a job was blocked now appear in claude agents search&lt;/p&gt;
&lt;p&gt;• Fixed the agents view input showing no text cursor on Windows&lt;/p&gt;
&lt;p&gt;• Fixed claude --bg -cn &amp;lt;name&amp;gt; not seeding the session name&lt;/p&gt;
&lt;p&gt;• Fixed background sessions to neutralize Windows network paths in persisted state before respawn&lt;/p&gt;
&lt;p&gt;• Fixed background-session respawn rejecting malformed resume IDs from corrupted state files&lt;/p&gt;
&lt;p&gt;• Fixed the Windows background-service daemon not starting when ~/.claude/daemon has the ReadOnly attribute set&lt;/p&gt;
&lt;p&gt;• Fixed cloud sessions failing with "Could not resolve authentication method" when idle for too long before being claimed&lt;/p&gt;
&lt;p&gt;• Background sessions now show clearer guidance when a window left open across an auto-update can't submit a reply, and claude daemon status explains version-skew behavior&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.175</id>
<title>Claude Code v2.1.175</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.175"/>
<updated>2026-06-12T04:23:45Z</updated>
<content type="html">&lt;p&gt;• Added enforceAvailableModels managed setting — when enabled, the availableModels allowlist also constrains the Default model (a Default that would resolve to a disallowed model now falls back to the first allowed model), and user or project settings can no longer widen a managed availableModels list&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.174</id>
<title>Claude Code v2.1.174</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.174"/>
<updated>2026-06-12T01:16:30Z</updated>
<content type="html">&lt;p&gt;• Added wheelScrollAccelerationEnabled setting to disable mouse-wheel scroll acceleration in fullscreen mode&lt;/p&gt;
&lt;p&gt;• Fixed the /model picker hiding the model family that Default resolves to — Opus now appears as its own row on Max/Team Premium/Enterprise plans, Sonnet on Pro/Team plans, and Opus on pay-as-you-go API accounts&lt;/p&gt;
&lt;p&gt;• Fixed /model picker showing a hardcoded Sonnet version label when ANTHROPIC_DEFAULT_SONNET_MODEL pins a different Sonnet&lt;/p&gt;
&lt;p&gt;• Fixed the "Fable 5 is now consuming usage credits" banner incorrectly showing for enterprise accounts with usage-based billing&lt;/p&gt;
&lt;p&gt;• Fixed Bedrock GovCloud regions (us-gov-*) deriving the wrong inference profile prefix (global instead of us-gov), causing 400 errors on derived model IDs&lt;/p&gt;
&lt;p&gt;• Fixed background sessions inheriting another session's ANTHROPIC_* provider env (gateway URL, custom headers, /model aliases) from the shell that started the background daemon&lt;/p&gt;
&lt;p&gt;• Fixed a 1-2 second pause when exiting Claude Code shortly after a shell command was interrupted or killed on macOS and Linux&lt;/p&gt;
&lt;p&gt;• Fixed git commit co-author attribution showing an incorrect model name for some models&lt;/p&gt;
&lt;p&gt;• Fixed the /advisor dialog pre-selecting a saved advisor model that is blocked by the availableModels allowlist&lt;/p&gt;
&lt;p&gt;• Fixed skill hot-reload re-sending the entire skill listing when a single skill changed; only changed skills are now re-announced&lt;/p&gt;
&lt;p&gt;• Fixed Workflow tool agent() subagents missing per-agent attribution headers&lt;/p&gt;
&lt;p&gt;• [VSCode] Added usage attribution to the Account &amp;amp; usage dialog (/usage) showing cache misses, long context, subagents, and per-skill/agent/plugin/MCP breakdowns over the last 24h or 7d&lt;/p&gt;
&lt;p&gt;• Fixed pre-warmed background workers failing with "Could not resolve authentication method" when claimed after sitting idle&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.173</id>
<title>Claude Code v2.1.173</title>
@@ -327,142 +409,4 @@
<updated>2026-05-29T01:42:17Z</updated>
<content type="html">&lt;p&gt;• Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.154</id>
<title>Claude Code v2.1.154</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.154"/>
<updated>2026-05-28T18:00:47Z</updated>
<content type="html">&lt;p&gt;• Opus 4.8 is here! Now defaults to high effort · /effort xhigh for your hardest tasks&lt;/p&gt;
&lt;p&gt;• Introducing dynamic workflows: ask Claude to create a workflow and it orchestrates work across tens to hundreds of agents in the background, so you can take on larger, more complex tasks. Run /workflows to view your runs&lt;/p&gt;
&lt;p&gt;• Fast mode on Opus 4.8 is now available at a fraction of its previous cost: 2x the standard rate for 2.5x the speed&lt;/p&gt;
&lt;p&gt;• The lean system prompt is now the default for all models except Haiku, Sonnet, and Opus 4.7 and earlier&lt;/p&gt;
&lt;p&gt;• Claude now reserves the multiple-choice question prompt for decisions it genuinely cannot make itself, instead of asking when it already has enough context to proceed&lt;/p&gt;
&lt;p&gt;• /simplify now runs a cleanup-only review (reuse, simplification, efficiency, altitude) and applies the fixes, instead of running the full /code-review --fix bug-hunting review&lt;/p&gt;
&lt;p&gt;• Renamed the /effort slider labels from "Speed"/"Intelligence" to "Faster"/"Smarter" for clarity&lt;/p&gt;
&lt;p&gt;• claude agents: type ! &amp;lt;command&amp;gt; to run a shell command as a background session you can attach to and detach from. Also available as claude --bg --exec '&amp;lt;command&amp;gt;'&lt;/p&gt;
&lt;p&gt;• claude agents: /logout now signs you out instead of being sent to a background session&lt;/p&gt;
&lt;p&gt;• ←← to open the agents view now works on Bedrock, Vertex, Foundry, and with telemetry disabled&lt;/p&gt;
&lt;p&gt;• Claude in Chrome: pick which connected browser to use via /chrome → "Select browser…", or in-chat when a browser action runs with multiple connected&lt;/p&gt;
&lt;p&gt;• Plugins can now declare defaultEnabled: false in plugin.json or a marketplace entry; enable them with /plugin or claude plugin enable. Dependencies of enabled plugins are still enabled automatically&lt;/p&gt;
&lt;p&gt;• The /plugin Discover tab now pins plugins whose relevance signals match the current directory with a "suggested for this directory" annotation&lt;/p&gt;
&lt;p&gt;• Streaming tool execution is now always enabled, including when telemetry is disabled or on Bedrock/Vertex/Foundry (previously behind a feature flag)&lt;/p&gt;
&lt;p&gt;• Stdio MCP server subprocesses now receive CLAUDE_CODE_SESSION_ID and CLAUDECODE=1 in their environment&lt;/p&gt;
&lt;p&gt;• claude mcp list/get now show unapproved .mcp.json servers as ⏸ Pending approval instead of auto-approving and connecting when output is piped&lt;/p&gt;
&lt;p&gt;• /remote-control autocomplete now shows "Disconnect Remote Control" when Remote Control is already active&lt;/p&gt;
&lt;p&gt;• Added Claude Opus 4.8 support and 4.7 → 4.8 migration guidance to the /claude-api skill&lt;/p&gt;
&lt;p&gt;• Deprecated CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE (will be removed on 06/01). To use fast mode on Opus 4.6, switch with /model claude-opus-4-6[1m] and then /fast on&lt;/p&gt;
&lt;p&gt;• Improved the auto-mode classifier's detection of data exfiltration, particularly bulk transfers of repository contents&lt;/p&gt;
&lt;p&gt;• Fixed rm -rf $HOME not being blocked as a dangerous path when HOME has a trailing slash&lt;/p&gt;
&lt;p&gt;• Fixed $TMPDIR resolving to different directories in sandboxed vs unsandboxed Bash commands within the same session&lt;/p&gt;
&lt;p&gt;• Fixed unreadable highlighted-row text in claude agents when the Claude Code theme doesn't match the terminal background&lt;/p&gt;
&lt;p&gt;• Fixed background-agent completion notifications triggering premature "out of context" behavior on some 1M-context models&lt;/p&gt;
&lt;p&gt;• Fixed background-session classifier losing the user's goal when a scheduled /command fires&lt;/p&gt;
&lt;p&gt;• Fixed pinned background sessions respawning every minute after a Claude Code update, causing repeated agent-start notifications and process churn at idle&lt;/p&gt;
&lt;p&gt;• Fixed background sessions stuck at "blocked", "running", or "working" not retiring after the idle grace period&lt;/p&gt;
&lt;p&gt;• Fixed subagents in background sessions bypassing the worktree-isolation guard and writing to the shared checkout&lt;/p&gt;
&lt;p&gt;• Fixed orphaned claude --bg-pty-host processes spinning at 100% CPU after the daemon exits on macOS&lt;/p&gt;
&lt;p&gt;• Fixed number key shortcuts not working for options shown below the divider in option dialogs&lt;/p&gt;
&lt;p&gt;• Fixed worktree.baseRef: "head" resolving to the main checkout's HEAD instead of the current worktree's HEAD when spawning subagents or calling EnterWorktree from inside a linked worktree&lt;/p&gt;
&lt;p&gt;• Fixed a stray leading space on wrapped lines when the previous line ended exactly at the terminal width&lt;/p&gt;
&lt;p&gt;• Fixed intermittent terminal rendering corruption in VS Code by capping the number of distinct colors the thinking spinner produces&lt;/p&gt;
&lt;p&gt;• Fixed plan file names including [Image #N] / [Pasted text #N] placeholders when a plan-mode prompt starts with pasted images or text&lt;/p&gt;
&lt;p&gt;• Fixed a phantom expand/click affordance on colored tool output: short ANSI-colored lines that fit on screen no longer show a "ctrl+o to expand" hint&lt;/p&gt;
&lt;p&gt;• Fixed a single invalid allowedMcpServers/deniedMcpServers entry in managed settings discarding all managed-settings policy; the bad entry is now dropped with a claude doctor warning&lt;/p&gt;
&lt;p&gt;• Fixed API 400 errors on models that don't support the effort parameter when CLAUDE_CODE_ALWAYS_ENABLE_EFFORT is set&lt;/p&gt;
&lt;p&gt;• Windows: Fixed update failures caused by claude.exe being in use showing a generic error instead of telling you to close other sessions and retry&lt;/p&gt;
&lt;p&gt;• Removed the stale "&amp;amp; for background" hint from the shortcuts help panel&lt;/p&gt;
&lt;p&gt;• [VSCode] Auto mode no longer requires the bypass-permissions setting to appear in the mode picker, and a dismissable notice on the new-session screen explains auto mode the first time it's active&lt;/p&gt;
&lt;p&gt;• Fixed the task panel below the prompt showing a stray unselectable "main" row when only a workflow is running&lt;/p&gt;
&lt;p&gt;• Fixed /mcp tools list and tool detail rendering when MCP servers have long or multi-line tool names or long descriptions&lt;/p&gt;
&lt;p&gt;• Fixed the /model picker not showing fast mode pricing on the Default option for API (pay-as-you-go) users when fast mode is on&lt;/p&gt;
&lt;p&gt;• Fixed auto mode incorrectly blocking actions with "could not evaluate this action" when the safety classifier ran out of output tokens while reasoning&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.153</id>
<title>Claude Code v2.1.153</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.153"/>
<updated>2026-05-28T00:52:02Z</updated>
<content type="html">&lt;p&gt;• Added skipLfs option to github/git plugin marketplace sources to skip Git LFS downloads during clone and update&lt;/p&gt;
&lt;p&gt;• Claude Code now shows a one-time notice when your npm global install can't auto-update; /doctor lists the fixes&lt;/p&gt;
&lt;p&gt;• Status line commands now receive COLUMNS and LINES environment variables so scripts can size output to the terminal width&lt;/p&gt;
&lt;p&gt;• claude agents: autocomplete in the dispatch input now suggests native slash commands and bundled skills, not just project skills&lt;/p&gt;
&lt;p&gt;• claude agents: PR column now shows PR #N for a single PR or N PRs for multiple&lt;/p&gt;
&lt;p&gt;• claude doctor now shows the result of your last update attempt&lt;/p&gt;
&lt;p&gt;• Combined the separate "needs authentication" startup notifications for MCP servers and connectors into a single message&lt;/p&gt;
&lt;p&gt;• macOS: background agents now appear as "Claude Code" in Privacy &amp;amp; Security and keep their permission grants across upgrades&lt;/p&gt;
&lt;p&gt;• Fixed stateful MCP servers without the optional GET SSE stream reconnect-looping on tools/list (regression in v2.1.147)&lt;/p&gt;
&lt;p&gt;• Fixed a regression where a custom API gateway could receive the user's Anthropic OAuth credential instead of the gateway's own token&lt;/p&gt;
&lt;p&gt;• Fixed subagent (Agent tool) frontmatter MCP servers ignoring --strict-mcp-config, --bare, remote mode, enterprise managed MCP config, and managed-settings MCP server allow/deny policies&lt;/p&gt;
&lt;p&gt;• --strict-mcp-config no longer strips inline mcpServers from explicitly-passed agent definitions (--agents / SDK agents), and blocked subagent MCP servers now surface a visible warning&lt;/p&gt;
&lt;p&gt;• Fixed the Windows PowerShell installer reporting "Installation complete!" when installation actually failed&lt;/p&gt;
&lt;p&gt;• Fixed claude update installing the latest version instead of the configured release channel's version for npm installations&lt;/p&gt;
&lt;p&gt;• Fixed excessive memory usage (multiple GB) when resuming a session by transcript file path on machines with many stored sessions&lt;/p&gt;
&lt;p&gt;• Fixed claude agents and claude --bg running on a stale daemon started before binary-takeover support, even after upgrading&lt;/p&gt;
&lt;p&gt;• Fixed a hang where the CLI could fail to exit when stdin was closed without EOF in stream-json mode, leaving a stale session marker behind&lt;/p&gt;
&lt;p&gt;• Fixed malformed file:// links in Claude's responses not being clickable in the terminal&lt;/p&gt;
&lt;p&gt;• Fixed claude --help rendering unwrapped output on terminals narrower than 92 columns&lt;/p&gt;
&lt;p&gt;• Fixed MCP tool progress notifications not rendering in the collapsed tool view&lt;/p&gt;
&lt;p&gt;• Fixed Agent tool with subagent_type: 'claude' running in an undocumented temporary worktree, which could silently discard outputs written to gitignored paths&lt;/p&gt;
&lt;p&gt;• /bg while Claude is responding now continues the response in the background session instead of dropping it&lt;/p&gt;
&lt;p&gt;• Fixed /btw keyboard shortcuts becoming unresponsive in background sessions while a task is running&lt;/p&gt;
&lt;p&gt;• Fixed background sessions writing temp files to $CLAUDE_JOB_DIR triggering a "sensitive file" permission prompt&lt;/p&gt;
&lt;p&gt;• Fixed recovering a background agent whose working directory was deleted showing a truncated stack trace instead of a clear error message&lt;/p&gt;
&lt;p&gt;• Fixed EnterWorktree not being available immediately in background sessions (previously required ToolSearch first)&lt;/p&gt;
&lt;p&gt;• Fixed cmd+k in iTerm2/Terminal.app not repainting attached background sessions&lt;/p&gt;
&lt;p&gt;• Fixed the IME candidate window appearing at the bottom of the screen instead of next to the input caret in attached background sessions on Windows&lt;/p&gt;
&lt;p&gt;• Fixed background-color bleed when attaching to a background agent from 256-color-only terminals after the agent had rendered file diffs&lt;/p&gt;
&lt;p&gt;• Fixed /copy and copy-on-select silently failing to update the system clipboard when attached to a background session inside tmux&lt;/p&gt;
&lt;p&gt;• Fixed opening claude agents with Remote Control enabled leaving zombie session entries on the Code tab after exiting&lt;/p&gt;
&lt;p&gt;• Fixed /rename in background sessions not updating the session banner immediately&lt;/p&gt;
&lt;p&gt;• Fixed Windows update rollback: if a Windows update fails, Claude Code now restores the original executable by copy and tells you how to recover&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed Claude Code processes not shutting down cleanly when VS Code closed on Windows, causing false "unclean exit" reports and orphaned MCP servers&lt;/p&gt;
&lt;p&gt;• /model now saves your selection as the default for new sessions (matching the IDE). Press s in the picker to switch models for the current session only.&lt;/p&gt;
&lt;p&gt;• If you customized the modelPicker:setAsDefault keybinding, rename it to modelPicker:thisSessionOnly in keybindings.json (the d action was replaced by s)&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.152</id>
<title>Claude Code v2.1.152</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.152"/>
<updated>2026-05-27T01:30:52Z</updated>
<content type="html">&lt;p&gt;• /code-review --fix now applies review findings to your working tree after the review, surfacing reuse, simplification, and efficiency suggestions; /simplify now invokes /code-review --fix&lt;/p&gt;
&lt;p&gt;• Skills and slash commands can now set disallowed-tools in frontmatter to remove tools from the model while the skill is active&lt;/p&gt;
&lt;p&gt;• Added /reload-skills command to re-scan skill directories without restarting the session&lt;/p&gt;
&lt;p&gt;• SessionStart hooks can now return reloadSkills: true to re-scan skill directories, making skills installed by the hook available in the same session&lt;/p&gt;
&lt;p&gt;• SessionStart hooks can now set the session title via hookSpecificOutput.sessionTitle on startup and resume&lt;/p&gt;
&lt;p&gt;• Added a MessageDisplay hook event that lets hooks transform or hide assistant message text as it is displayed&lt;/p&gt;
&lt;p&gt;• Added pluginSuggestionMarketplaces managed setting: admins can allowlist org marketplaces whose plugins may be suggested via context-aware tips&lt;/p&gt;
&lt;p&gt;• claude plugin marketplace remove now accepts --scope user|project|local for symmetry with marketplace add, install, and uninstall&lt;/p&gt;
&lt;p&gt;• Claude Code now switches to your configured --fallback-model for the rest of the session when the primary model is not found, instead of failing every request&lt;/p&gt;
&lt;p&gt;• Auto mode no longer requires opt-in consent&lt;/p&gt;
&lt;p&gt;• Vim mode: / in NORMAL mode now opens reverse history search (like Ctrl+R), matching bash/zsh vi-mode&lt;/p&gt;
&lt;p&gt;• The /usage breakdown now includes large session files; files are scanned with a streaming read so memory usage stays flat&lt;/p&gt;
&lt;p&gt;• Thinking summaries in the collapsed group now stay readable for at least 3 seconds, render as markdown, and cap at 10 lines (Ctrl+O shows the full thinking)&lt;/p&gt;
&lt;p&gt;• In fullscreen mode, the "Thinking for Ns" indicator now counts up live while the model is thinking, and keeps its value if you interrupt mid-thought&lt;/p&gt;
&lt;p&gt;• Simplified the Workflow tool's inline progress display — live agent counts now show only in the persistent workflow status row below the prompt&lt;/p&gt;
&lt;p&gt;• The post-response timer now shows "Waiting for N background agents/workflows to finish" when backgrounded agents or workflows are still running, and reports the cumulative time once their results are processed&lt;/p&gt;
&lt;p&gt;• Added the session entrypoint as an OpenTelemetry metric attribute (app.entrypoint, opt-in via OTEL_METRICS_INCLUDE_ENTRYPOINT=true)&lt;/p&gt;
&lt;p&gt;• Fixed terminal styling degrading in very long sessions by recycling the renderer's style pool&lt;/p&gt;
&lt;p&gt;• Fixed the sandbox-enabled warning not appearing in condensed startup mode — it now shows in every layout&lt;/p&gt;
&lt;p&gt;• Fixed the loading spinner showing "still thinking"/"almost done thinking" while a tool is running, and reset the thinking status to "thinking" after each tool&lt;/p&gt;
&lt;p&gt;• Fixed focus mode showing a spurious "N messages hidden" count on turns with no hidden activity&lt;/p&gt;
&lt;p&gt;• Fixed clicking a link inside an expanded tool result collapsing the section instead of opening the link&lt;/p&gt;
&lt;p&gt;• Fixed markdown table cell borders inheriting the color of inline code, wrapped continuation lines losing their style, and empty header cells showing a label in the narrow-terminal stacked layout&lt;/p&gt;
&lt;p&gt;• Fixed plugin MCP servers with the same command but different environment variables being incorrectly deduplicated&lt;/p&gt;
&lt;p&gt;• Fixed /doctor reporting "marketplace not found" or "plugin not found" for stale enabledPlugins entries referencing removed marketplaces or dropped plugins&lt;/p&gt;
&lt;p&gt;• Fixed plugins that track a git branch silently no longer receiving updates after the plugin registry was rebuilt&lt;/p&gt;
&lt;p&gt;• Fixed remote MCP servers failing to connect in Claude Code Remote sessions when the egress proxy is enabled&lt;/p&gt;
&lt;p&gt;• Fixed the effort-change confirmation dialog appearing when the conversation has no messages or when switching between effort levels that resolve to the same underlying value&lt;/p&gt;
&lt;p&gt;• Fixed the Agent tool description referencing an agent list that is never delivered when running with --bare or with attachments disabled&lt;/p&gt;
&lt;p&gt;• Fixed a background worker crash in claude agents when accepting a stale permission prompt after a subagent was cancelled&lt;/p&gt;
&lt;p&gt;• Fixed cache_creation_input_tokens reporting as 0 in transcript and result usage when the API reports cache writes only via the nested cache_creation breakdown&lt;/p&gt;
&lt;p&gt;• Fixed the PushNotification tool incorrectly reporting "Mobile push not sent (Remote Control inactive)" in SDK-hosted sessions when Remote Control is enabled&lt;/p&gt;
&lt;p&gt;• Fixed sessions getting stuck after a model or login switch left stale thinking-block signatures in history; now stripped proactively with a retry safety-net&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.150</id>
<title>Claude Code v2.1.150</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.150"/>
<updated>2026-05-23T04:03:45Z</updated>
<content type="html">&lt;p&gt;• Internal infrastructure improvements (no user-facing changes)&lt;/p&gt;</content>
</entry>
</feed>