Compare commits

..

2 Commits

Author SHA1 Message Date
GitHub Actions
2aa6ef3d35 chore: Update CHANGELOG.md and feed.xml 2026-06-23 21:03:40 +00:00
GitHub Actions
12281998d8 chore: Update CHANGELOG.md and feed.xml 2026-06-22 20:37:27 +00:00
2 changed files with 127 additions and 62 deletions

View File

@@ -1,5 +1,65 @@
# Changelog
## 2.1.187
- Added `sandbox.credentials` setting to block sandboxed commands from reading credential files and secret environment variables
- Added org-configured model restrictions to the model picker, `--model`, `/model`, and `ANTHROPIC_MODEL`, with a "restricted by your organization's settings" message when a restricted model is selected
- Added mouse click support to select menus (permission prompts, `/model`, `/config`, etc.) in fullscreen mode
- Fixed `--resume` failing with "No conversation found" when the original `-p` run produced no model turns
- Fixed `--json-schema` and workflow `agent({schema})` structured output: the model can no longer re-call `StructuredOutput` indefinitely after a successful call, and follow-up turns now reliably return structured output
- Fixed remote MCP tool calls that hang with no response for 5 minutes — they now abort with an error instead of blocking indefinitely (override with `CLAUDE_CODE_MCP_TOOL_IDLE_TIMEOUT`)
- Fixed Claude Code Remote sessions taking ~2.7s longer to start after the agent proxy CA system-trust install was added
- Fixed pasted Korean/CJK text turning into mojibake in terminals that deliver paste as per-byte extended-key events
- Fixed `/update` over Remote Control hanging when a startup trust dialog would have shown
- Fixed background jobs in the agents view getting stuck in "working" indefinitely when the agent ended a turn without producing structured output
- Fixed channel connections dropping after navigating to the agents view and back, and after `/bg`, `/tui`, or `/update`
- Fixed agent stop notifications not correctly attributing who stopped the agent, and improved wording ("finished"/"stopped" instead of "came to rest")
- Fixed subagent depth tracking: resumed subagents now restore their original spawn depth, and forked subagents now count toward the depth cap
- Fixed leaked agent worktree registrations: locked `.git/worktrees/` entries from killed agents are now cleaned up automatically
- Fixed Cmd+click not opening URLs in fullscreen mode in Ghostty on macOS
- Fixed `claude --help` not listing the `--bg`/`--background` flag
- Fixed Esc, Ctrl-C, and Ctrl-D not working while `/share` is uploading
- Improved `/install-github-app`: GitHub Actions workflow setup is now optional — you can install just the GitHub App and skip the workflow/secret steps
- Improved `/btw` with ←/→ arrow navigation to step through earlier answers
- Improved `/plugin` to surface plugins you haven't used recently so you can clean them up
- [VSCode] Fixed extension becoming unresponsive when resuming a large session
## 2.1.186
- Added `claude mcp login <name>` and `claude mcp logout <name>` to authenticate MCP servers from the CLI without opening the interactive `/mcp` menu, with `--no-browser` stdin redirect support for completing over SSH
- Added status filtering (press `f`) to the `/workflows` agent detail view
- Added a "Skills" section to the `/plugin` Installed tab
- Added `teammateMode: "iterm2"` setting with a warning when auto mode cannot find the `it2` CLI
- Added "Claude Platform on AWS - refresh credentials" option to `/login` when `awsAuthRefresh` is configured
- `!` bash commands now trigger Claude to respond to the output automatically; set `"respondToBashCommands": false` in settings.json to keep the previous context-only behavior
- Fixed streaming requests failing with "Content block not found" or JSON parse errors after the machine wakes from sleep
- Fixed subagent transcript scroll position bleeding into the main transcript on exit
- Fixed background task previews flashing raw tool names before the agent's plan loaded
- Fixed Chrome tab-group isolation not applying when the in-product permissions gate is off for concurrent CLI sessions
- Fixed background session recaps being duplicated; the agent's own end-of-turn summary now shows as the recap line
- Fixed opening a background session from `claude agents` leaving the previous screen painted behind it
- Fixed `Agent(type)` deny rules and `Agent(x,y)` allowed-types restrictions not being enforced for named subagent spawns
- Fixed Esc and Ctrl+C not responding while background agents are still running after the main turn ends
- Fixed misaligned option numbers in permission prompts when the option text overflows
- Fixed pressing `x` on a finished subagent in the agent panel not dismissing it
- Fixed a misleading "MCP server disconnected" notice for intentionally retired tools when resuming older sessions
- Fixed `/plugin` Installed showing a "more above" indicator when already scrolled to the top
- Fixed `~~strikethrough~~` showing literal tildes in assistant messages instead of rendering as strikethrough
- Fixed `--tools` allowing feature-gated tools to slip through before flags loaded on a cold first launch
- Fixed background job status in `claude agents` showing a stale "needs input" message after replying
- Fixed a dark-theme flash when opening a background session from `claude agents` on a light terminal
- Fixed mouse-selected text staying highlighted after deleting it in `claude agents`
- Fixed session cost not showing for usage-based Enterprise and Team subscribers
- Fixed agent teams: teammates spawned via tmux/pane backends now inherit the leader's `--effort` level
- Fixed Workflow `agent({schema})` subagents looping forever on repeated schema validation failures instead of aborting after 5 attempts
- Improved `claude mcp get` and `claude mcp remove` to suggest the closest configured server name on a typo and truncate long server lists
- Improved memory: the agent is now reminded to compact its `MEMORY.md` index when nearing the size limit
- Improved skill frontmatter: `display-name`, `default-enabled`, `fallback`, and `metadata.*` keys now accept kebab-case, snake_case, and camelCase
- Improved malformed `SKILL.md` YAML frontmatter handling: loads the skill body with empty metadata instead of failing silently
- Changed `CLAUDE_CODE_MAX_RETRIES` to cap at 15; for unattended sessions, use `CLAUDE_CODE_RETRY_WATCHDOG` instead
- Changed background subagents to surface permission prompts in the main session instead of auto-denying; the dialog shows which agent is asking, and Esc denies just that tool
- Changed `/review <pr>` to use the same review engine as `/code-review medium`
## 2.1.185
- The stream-stall hint now reads "Waiting for API response · will retry in …" instead of "No response from API · Retrying in …", and triggers after 20s of silence instead of 10s

129
feed.xml
View File

@@ -6,7 +6,73 @@
<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>2026-06-20T20:59:12Z</updated>
<updated>2026-06-23T21:03:40Z</updated>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.187</id>
<title>Claude Code v2.1.187</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.187"/>
<updated>2026-06-23T21:03:40Z</updated>
<content type="html">&lt;p&gt;• Added sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables&lt;/p&gt;
&lt;p&gt;• Added org-configured model restrictions to the model picker, --model, /model, and ANTHROPIC_MODEL, with a "restricted by your organization's settings" message when a restricted model is selected&lt;/p&gt;
&lt;p&gt;• Added mouse click support to select menus (permission prompts, /model, /config, etc.) in fullscreen mode&lt;/p&gt;
&lt;p&gt;• Fixed --resume failing with "No conversation found" when the original -p run produced no model turns&lt;/p&gt;
&lt;p&gt;• Fixed --json-schema and workflow agent({schema}) structured output: the model can no longer re-call StructuredOutput indefinitely after a successful call, and follow-up turns now reliably return structured output&lt;/p&gt;
&lt;p&gt;• Fixed remote MCP tool calls that hang with no response for 5 minutes — they now abort with an error instead of blocking indefinitely (override with CLAUDE_CODE_MCP_TOOL_IDLE_TIMEOUT)&lt;/p&gt;
&lt;p&gt;• Fixed Claude Code Remote sessions taking ~2.7s longer to start after the agent proxy CA system-trust install was added&lt;/p&gt;
&lt;p&gt;• Fixed pasted Korean/CJK text turning into mojibake in terminals that deliver paste as per-byte extended-key events&lt;/p&gt;
&lt;p&gt;• Fixed /update over Remote Control hanging when a startup trust dialog would have shown&lt;/p&gt;
&lt;p&gt;• Fixed background jobs in the agents view getting stuck in "working" indefinitely when the agent ended a turn without producing structured output&lt;/p&gt;
&lt;p&gt;• Fixed channel connections dropping after navigating to the agents view and back, and after /bg, /tui, or /update&lt;/p&gt;
&lt;p&gt;• Fixed agent stop notifications not correctly attributing who stopped the agent, and improved wording ("finished"/"stopped" instead of "came to rest")&lt;/p&gt;
&lt;p&gt;• Fixed subagent depth tracking: resumed subagents now restore their original spawn depth, and forked subagents now count toward the depth cap&lt;/p&gt;
&lt;p&gt;• Fixed leaked agent worktree registrations: locked .git/worktrees/ entries from killed agents are now cleaned up automatically&lt;/p&gt;
&lt;p&gt;• Fixed Cmd+click not opening URLs in fullscreen mode in Ghostty on macOS&lt;/p&gt;
&lt;p&gt;• Fixed claude --help not listing the --bg/--background flag&lt;/p&gt;
&lt;p&gt;• Fixed Esc, Ctrl-C, and Ctrl-D not working while /share is uploading&lt;/p&gt;
&lt;p&gt;• Improved /install-github-app: GitHub Actions workflow setup is now optional — you can install just the GitHub App and skip the workflow/secret steps&lt;/p&gt;
&lt;p&gt;• Improved /btw with ←/→ arrow navigation to step through earlier answers&lt;/p&gt;
&lt;p&gt;• Improved /plugin to surface plugins you haven't used recently so you can clean them up&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed extension becoming unresponsive when resuming a large session&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.186</id>
<title>Claude Code v2.1.186</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.186"/>
<updated>2026-06-22T20:37:26Z</updated>
<content type="html">&lt;p&gt;• Added claude mcp login &amp;lt;name&amp;gt; and claude mcp logout &amp;lt;name&amp;gt; to authenticate MCP servers from the CLI without opening the interactive /mcp menu, with --no-browser stdin redirect support for completing over SSH&lt;/p&gt;
&lt;p&gt;• Added status filtering (press f) to the /workflows agent detail view&lt;/p&gt;
&lt;p&gt;• Added a "Skills" section to the /plugin Installed tab&lt;/p&gt;
&lt;p&gt;• Added teammateMode: "iterm2" setting with a warning when auto mode cannot find the it2 CLI&lt;/p&gt;
&lt;p&gt;• Added "Claude Platform on AWS - refresh credentials" option to /login when awsAuthRefresh is configured&lt;/p&gt;
&lt;p&gt;• ! bash commands now trigger Claude to respond to the output automatically; set "respondToBashCommands": false in settings.json to keep the previous context-only behavior&lt;/p&gt;
&lt;p&gt;• Fixed streaming requests failing with "Content block not found" or JSON parse errors after the machine wakes from sleep&lt;/p&gt;
&lt;p&gt;• Fixed subagent transcript scroll position bleeding into the main transcript on exit&lt;/p&gt;
&lt;p&gt;• Fixed background task previews flashing raw tool names before the agent's plan loaded&lt;/p&gt;
&lt;p&gt;• Fixed Chrome tab-group isolation not applying when the in-product permissions gate is off for concurrent CLI sessions&lt;/p&gt;
&lt;p&gt;• Fixed background session recaps being duplicated; the agent's own end-of-turn summary now shows as the recap line&lt;/p&gt;
&lt;p&gt;• Fixed opening a background session from claude agents leaving the previous screen painted behind it&lt;/p&gt;
&lt;p&gt;• Fixed Agent(type) deny rules and Agent(x,y) allowed-types restrictions not being enforced for named subagent spawns&lt;/p&gt;
&lt;p&gt;• Fixed Esc and Ctrl+C not responding while background agents are still running after the main turn ends&lt;/p&gt;
&lt;p&gt;• Fixed misaligned option numbers in permission prompts when the option text overflows&lt;/p&gt;
&lt;p&gt;• Fixed pressing x on a finished subagent in the agent panel not dismissing it&lt;/p&gt;
&lt;p&gt;• Fixed a misleading "MCP server disconnected" notice for intentionally retired tools when resuming older sessions&lt;/p&gt;
&lt;p&gt;• Fixed /plugin Installed showing a "more above" indicator when already scrolled to the top&lt;/p&gt;
&lt;p&gt;• Fixed ~~strikethrough~~ showing literal tildes in assistant messages instead of rendering as strikethrough&lt;/p&gt;
&lt;p&gt;• Fixed --tools allowing feature-gated tools to slip through before flags loaded on a cold first launch&lt;/p&gt;
&lt;p&gt;• Fixed background job status in claude agents showing a stale "needs input" message after replying&lt;/p&gt;
&lt;p&gt;• Fixed a dark-theme flash when opening a background session from claude agents on a light terminal&lt;/p&gt;
&lt;p&gt;• Fixed mouse-selected text staying highlighted after deleting it in claude agents&lt;/p&gt;
&lt;p&gt;• Fixed session cost not showing for usage-based Enterprise and Team subscribers&lt;/p&gt;
&lt;p&gt;• Fixed agent teams: teammates spawned via tmux/pane backends now inherit the leader's --effort level&lt;/p&gt;
&lt;p&gt;• Fixed Workflow agent({schema}) subagents looping forever on repeated schema validation failures instead of aborting after 5 attempts&lt;/p&gt;
&lt;p&gt;• Improved claude mcp get and claude mcp remove to suggest the closest configured server name on a typo and truncate long server lists&lt;/p&gt;
&lt;p&gt;• Improved memory: the agent is now reminded to compact its MEMORY.md index when nearing the size limit&lt;/p&gt;
&lt;p&gt;• Improved skill frontmatter: display-name, default-enabled, fallback, and metadata.* keys now accept kebab-case, snake_case, and camelCase&lt;/p&gt;
&lt;p&gt;• Improved malformed SKILL.md YAML frontmatter handling: loads the skill body with empty metadata instead of failing silently&lt;/p&gt;
&lt;p&gt;• Changed CLAUDE_CODE_MAX_RETRIES to cap at 15; for unattended sessions, use CLAUDE_CODE_RETRY_WATCHDOG instead&lt;/p&gt;
&lt;p&gt;• Changed background subagents to surface permission prompts in the main session instead of auto-denying; the dialog shows which agent is asking, and Esc denies just that tool&lt;/p&gt;
&lt;p&gt;• Changed /review &amp;lt;pr&amp;gt; to use the same review engine as /code-review medium&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.185</id>
<title>Claude Code v2.1.185</title>
@@ -380,65 +446,4 @@
&lt;p&gt;• Background dispatch spawn failures now report the error class name when no errno is available&lt;/p&gt;
&lt;p&gt;• Removed the "Claude in Chrome enabled" and "marketplace installed" startup messages; model auto-updates and the team-onboarding tip now show as quiet notices under the logo&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.161</id>
<title>Claude Code v2.1.161</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.161"/>
<updated>2026-06-02T21:58:16Z</updated>
<content type="html">&lt;p&gt;• OTEL_RESOURCE_ATTRIBUTES values are now included as labels on metric datapoints, so you can slice usage metrics by custom dimensions like team or repo&lt;/p&gt;
&lt;p&gt;• claude agents rows now show done/total before the detail when work is fanned out; peek shows the longest-running item&lt;/p&gt;
&lt;p&gt;• /mcp now collapses claude.ai connectors you've never signed in to behind a "Show unused connectors" row&lt;/p&gt;
&lt;p&gt;• Parallel tool calls: a failed Bash command no longer cancels other calls in the same batch — each tool returns its own result independently&lt;/p&gt;
&lt;p&gt;• Fullscreen mode: clipboard now uses wl-copy/xclip/xsel on Linux when available, copies to both the clipboard and PRIMARY selection for middle-click paste, and the "hold {key} for native selection" hint now shows the correct key per terminal&lt;/p&gt;
&lt;p&gt;• Fixed the /effort dialog, workflow animations, and prompt keyword shimmer not honoring the "Reduce motion" setting&lt;/p&gt;
&lt;p&gt;• Fixed forceLoginOrgUUID/forceLoginMethod managed-settings policies blocking third-party provider sessions (Bedrock, Vertex, Foundry, Mantle) alongside the org pin (regression in 2.1.146)&lt;/p&gt;
&lt;p&gt;• Fixed background subagent output corrupting claude -p stdout when using --output-format text or json&lt;/p&gt;
&lt;p&gt;• Fixed /usage-credits starting a re-login for Team and Enterprise admins instead of pointing to the organization's usage settings page&lt;/p&gt;
&lt;p&gt;• Fixed /autofix-pr reporting "cannot run on the default branch" when the session is inside a git worktree or another repository&lt;/p&gt;
&lt;p&gt;• Fixed --resume picker not showing sessions from the current directory when it isn't a git worktree (e.g., jj workspaces)&lt;/p&gt;
&lt;p&gt;• Fixed Windows hooks that invoke bash explicitly (e.g., /usr/bin/bash script.sh) failing with "command not found" or "cannot execute binary file"&lt;/p&gt;
&lt;p&gt;• Fixed OpenTelemetry log events (user_prompt, api_request, tool_result, tool_decision) being silently dropped when emitted before telemetry initialization completed&lt;/p&gt;
&lt;p&gt;• Fixed claude mcp list/get/add printing secrets to the terminal: ${VAR} references are no longer expanded, and credential headers and URL secrets are redacted&lt;/p&gt;
&lt;p&gt;• Fixed Workflow agents spawned with isolation: "worktree" in background sessions being blocked from editing files inside their own worktree&lt;/p&gt;
&lt;p&gt;• Fixed background sessions dispatched from claude agents booting on a stale model from the daemon's environment instead of the model in settings.json&lt;/p&gt;
&lt;p&gt;• Fixed a potential crash when rendering Write tool results after resuming a session&lt;/p&gt;
&lt;p&gt;• Fixed completed subagents getting stuck showing as running when an error occurs while finalizing their result&lt;/p&gt;
&lt;p&gt;• Fixed EADDRINUSE errors from tools that bind Unix sockets under $TMPDIR when CLAUDE_CODE_TMPDIR is set to a deep path&lt;/p&gt;
&lt;p&gt;• Improved terminal rendering performance by stabilizing the layout engine's JIT compilation profile&lt;/p&gt;
&lt;p&gt;• Improved rendering performance for large file writes&lt;/p&gt;
&lt;p&gt;• [VSCode] Added a tip suggesting disabling terminal GPU acceleration (or running /terminal-setup) to fix garbled glyphs&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.160</id>
<title>Claude Code v2.1.160</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.160"/>
<updated>2026-06-02T02:10:17Z</updated>
<content type="html">&lt;p&gt;• Added a prompt before writing to shell startup files (.zshenv, .zlogin, .bash_login) and ~/.config/git/, which could otherwise lead to unintended command execution&lt;/p&gt;
&lt;p&gt;• acceptEdits mode now prompts before writing build-tool config files that grant code execution (.npmrc, .yarnrc*, bunfig.toml, .bazelrc, .pre-commit-config.yaml, .devcontainer/, etc.)&lt;/p&gt;
&lt;p&gt;• Edit no longer requires a separate Read after viewing a file with grep: single-file grep/egrep/fgrep commands now satisfy the read-before-edit check&lt;/p&gt;
&lt;p&gt;• Fixed copy-on-select not writing to the Windows clipboard on WSL — now uses PowerShell interop instead of OSC 52, which terminals like MobaXterm don't support&lt;/p&gt;
&lt;p&gt;• Fixed restoring a completed session from claude agents dropping chat history and re-running the original prompt&lt;/p&gt;
&lt;p&gt;• Fixed background sessions re-attached after overnight retire losing their conversation and re-running the original prompt&lt;/p&gt;
&lt;p&gt;• Fixed claude --bg occasionally failing with "socket missing" when the background daemon was cold-starting on a loaded machine&lt;/p&gt;
&lt;p&gt;• Fixed an issue on Windows where the directory a background session was started in could not be deleted after claude rm until the background daemon exited&lt;/p&gt;
&lt;p&gt;• Fixed background agents that resumed work being shown under Completed in the agents list&lt;/p&gt;
&lt;p&gt;• Fixed claude agents freezing for several seconds when returning to the session list due to the auto-updater re-checking on every exit&lt;/p&gt;
&lt;p&gt;• Fixed Esc, arrow keys, and typing becoming unresponsive on Windows when attached to a background session or in the agent view while the host is under heavy CPU load&lt;/p&gt;
&lt;p&gt;• Fixed background agents emitting terminal sync-output markers to terminals that don't support them (Apple Terminal, tmux), causing render artifacts when entering a running agent&lt;/p&gt;
&lt;p&gt;• Fixed mouse wheel scrolling prompt history instead of the transcript right after opening a session from the agents list&lt;/p&gt;
&lt;p&gt;• Fixed CJK IME composition appearing at the bottom-left of the screen instead of at the input caret in the claude agents view&lt;/p&gt;
&lt;p&gt;• Fixed valid file:///C:/... links being rewritten to a broken path on Windows terminals with hyperlink support&lt;/p&gt;
&lt;p&gt;• Fixed voice mode failing to connect when the project directory or branch name contains non-ASCII or special characters&lt;/p&gt;
&lt;p&gt;• Fixed the auto mode unavailability message on third-party providers (Bedrock/Vertex/Foundry) to point to the CLAUDE_CODE_ENABLE_AUTO_MODE opt-in instead of incorrectly blaming the model&lt;/p&gt;
&lt;p&gt;• Fixed /effort ultracode incorrectly blaming the dynamic workflows setting when the model cannot run xhigh; ultracode is no longer offered on models that do not support it&lt;/p&gt;
&lt;p&gt;• Fixed model-not-found errors suggesting --model when running via the SDK or other hosts where the CLI flag doesn't apply&lt;/p&gt;
&lt;p&gt;• Fixed Claude's past replies disappearing from scrollback when resuming a brief mode session with brief mode turned off&lt;/p&gt;
&lt;p&gt;• Fixed vim mode p pasting on the line below instead of at the cursor when the register was yanked with v$&lt;/p&gt;
&lt;p&gt;• Improved performance of opening recently-inactive background agent sessions in claude agents&lt;/p&gt;
&lt;p&gt;• Improved auto mode classifier latency by reducing reasoning on routine actions, lowering the chance of "could not evaluate this action" blocks&lt;/p&gt;
&lt;p&gt;• Improved background-session teardown (claude rm/stop, idle reap) to send SIGTERM to running shell subprocesses before SIGKILL, so cleanup handlers run&lt;/p&gt;
&lt;p&gt;• Removed CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE; the environment variable is now a no-op&lt;/p&gt;
&lt;p&gt;• Removed the JetBrains plugin install suggestion from startup&lt;/p&gt;
&lt;p&gt;• Renamed the dynamic-workflow trigger keyword from workflow to ultracode. The word "workflow" no longer triggers a run; asking for one in your own words still works. The trigger keyword is highlighted in violet in the prompt input&lt;/p&gt;</content>
</entry>
</feed>