diff --git a/CHANGELOG.md b/CHANGELOG.md index 31df4f17..90492036 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,31 @@ # Changelog +## 2.1.205 + +- Added an auto mode rule that blocks tampering with session transcript files +- Fixed `--json-schema` silently producing unstructured output when the schema was invalid, and schemas using the `format` keyword being rejected +- Fixed a message sent while Claude was working being silently lost when the turn ended at the `--max-turns` limit +- Fixed Windows worktree removal deleting files outside the worktree when an NTFS junction or directory symlink existed inside it +- Fixed background agents staying shown as "failed" or "completed" in the agent list after being resumed with `SendMessage` +- Fixed background jobs flipping from "needs input" back to "working" in the agent list when the agent's turn contained no readable text +- Fixed `claude attach` erroring when a background agent was mid-upgrade restart instead of waiting for it to come back +- Fixed session-to-PR linking missing a PR created in a Bash call whose output exceeded the 30K inline limit +- Fixed `claude mcp add-from-claude-desktop` getting stuck when a server name contains unsupported characters; invalid names are now reported and remaining servers still import +- Fixed a plugin LSP server that fails to initialize preventing a valid LSP server from another plugin handling the same file extension +- Fixed a Windows crash when the directory Claude was launched from is deleted, locked, or unmounted while a command is running +- Fixed a crash when a file watcher was closed while a directory scan was still in flight +- Fixed project verify skills being rewritten on every session instead of only when a documented command changed +- Fixed the agent view rendering one line too high and clipping its header when the job list slightly overflowed the screen +- Fixed background tasks in the web and mobile Remote Control panels showing stale "Running" status by forwarding full task state on every membership change +- Improved auto mode to ask before running `rm -rf` on a variable it can't resolve from context +- Auto-update binary downloads now stream to disk instead of buffering in memory, cutting the updater's peak memory usage by roughly 400 MB +- Background task notifications now explicitly state that no human input has occurred, preventing fabricated in-transcript approvals from being acted on +- Improved agent view: sessions that edit, merge, comment on, or push to an existing PR now link it in `claude agents` +- Improved agent view: rows now show a colored state word and a classifier-written headline instead of raw tool call text, and the peek opens with full status including the exact ask for blocked sessions +- `/doctor` is now a full setup checkup that can diagnose and fix issues; `/checkup` is its alias +- Reserved the "Claude Browser" MCP server name (alongside "Claude Preview") ahead of the Claude Desktop pane rename; user-configured MCP servers can no longer register under either name +- Fixed Cowork VM-mode local-agent sessions failing to start with "Not logged in · Please run /login" on CLI 2.1.203+ + ## 2.1.204 - Fixed hook events not streaming during SessionStart hooks in headless sessions, which could cause remote workers to be idle-reaped mid-hook diff --git a/feed.xml b/feed.xml index c536523c..dd04d617 100644 --- a/feed.xml +++ b/feed.xml @@ -6,7 +6,36 @@ Anthropic - 2026-07-08T00:27:43Z + 2026-07-08T21:21:58Z + + https://github.com/anthropics/claude-code/releases/tag/v2.1.205 + Claude Code v2.1.205 + + 2026-07-08T21:21:58Z + <p>• Added an auto mode rule that blocks tampering with session transcript files</p> +<p>• Fixed --json-schema silently producing unstructured output when the schema was invalid, and schemas using the format keyword being rejected</p> +<p>• Fixed a message sent while Claude was working being silently lost when the turn ended at the --max-turns limit</p> +<p>• Fixed Windows worktree removal deleting files outside the worktree when an NTFS junction or directory symlink existed inside it</p> +<p>• Fixed background agents staying shown as "failed" or "completed" in the agent list after being resumed with SendMessage</p> +<p>• Fixed background jobs flipping from "needs input" back to "working" in the agent list when the agent's turn contained no readable text</p> +<p>• Fixed claude attach erroring when a background agent was mid-upgrade restart instead of waiting for it to come back</p> +<p>• Fixed session-to-PR linking missing a PR created in a Bash call whose output exceeded the 30K inline limit</p> +<p>• Fixed claude mcp add-from-claude-desktop getting stuck when a server name contains unsupported characters; invalid names are now reported and remaining servers still import</p> +<p>• Fixed a plugin LSP server that fails to initialize preventing a valid LSP server from another plugin handling the same file extension</p> +<p>• Fixed a Windows crash when the directory Claude was launched from is deleted, locked, or unmounted while a command is running</p> +<p>• Fixed a crash when a file watcher was closed while a directory scan was still in flight</p> +<p>• Fixed project verify skills being rewritten on every session instead of only when a documented command changed</p> +<p>• Fixed the agent view rendering one line too high and clipping its header when the job list slightly overflowed the screen</p> +<p>• Fixed background tasks in the web and mobile Remote Control panels showing stale "Running" status by forwarding full task state on every membership change</p> +<p>• Improved auto mode to ask before running rm -rf on a variable it can't resolve from context</p> +<p>• Auto-update binary downloads now stream to disk instead of buffering in memory, cutting the updater's peak memory usage by roughly 400 MB</p> +<p>• Background task notifications now explicitly state that no human input has occurred, preventing fabricated in-transcript approvals from being acted on</p> +<p>• Improved agent view: sessions that edit, merge, comment on, or push to an existing PR now link it in claude agents</p> +<p>• Improved agent view: rows now show a colored state word and a classifier-written headline instead of raw tool call text, and the peek opens with full status including the exact ask for blocked sessions</p> +<p>• /doctor is now a full setup checkup that can diagnose and fix issues; /checkup is its alias</p> +<p>• Reserved the "Claude Browser" MCP server name (alongside "Claude Preview") ahead of the Claude Desktop pane rename; user-configured MCP servers can no longer register under either name</p> +<p>• Fixed Cowork VM-mode local-agent sessions failing to start with "Not logged in · Please run /login" on CLI 2.1.203+</p> + https://github.com/anthropics/claude-code/releases/tag/v2.1.204 Claude Code v2.1.204 @@ -448,34 +477,4 @@ <p>• Fixed remote session background tasks appearing stuck as "still running" between turns</p> <p>• Improved plugin loading performance in remote sessions</p> - - https://github.com/anthropics/claude-code/releases/tag/v2.1.178 - Claude Code v2.1.178 - - 2026-06-15T21:35:48Z - <p>• Agent teams: removed the TeamCreate and TeamDelete tools. With CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 set, every session now has one implicit team — spawn teammates directly with the Agent tool's name parameter, no setup step needed. The team_name parameter on the Agent tool is still accepted but ignored.</p> -<p>• 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</p> -<p>• Skills in nested .claude/skills directories now load when working on files there; on a name clash, the nested skill appears as &lt;dir&gt;:&lt;name&gt; so both stay available</p> -<p>• 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/</p> -<p>• 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</p> -<p>• Improved /doctor with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names</p> -<p>• Improved the skill listing truncation warning to show how many skill descriptions are affected</p> -<p>• 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</p> -<p>• 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</p> -<p>• /bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title</p> -<p>• Fixed a crash (out-of-memory) when the CLI inherits a stale websocket/OAuth file-descriptor environment variable from a parent process</p> -<p>• Fixed Claude in Chrome silently failing to connect when the OAuth token belongs to a different account than the Claude Code login</p> -<p>• Fixed nested .claude/skills skills with directory-qualified names being blocked by permission prompts in non-interactive runs</p> -<p>• 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</p> -<p>• 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</p> -<p>• Fixed compaction not honoring --fallback-model: compaction now falls back to the configured fallback model chain on overload or model-availability errors</p> -<p>• Fixed model requests continuing to fail with auth errors after credentials were refreshed outside the session, due to a stale cached request configuration</p> -<p>• Fixed background sessions created with /bg or ←← after a turn finished showing "Working" forever in the agents list</p> -<p>• Fixed Linux sandbox failing to start when .claude/skills or .claude/hooks is a symlink</p> -<p>• Fixed CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloning</p> -<p>• Fixed MCP server-level specs (mcp__server, mcp__server__*, mcp__*) in subagent disallowedTools being silently ignored</p> -<p>• 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</p> -<p>• Fixed statusline links with custom URI schemes (e.g. vscode://) not opening when clicked in claude agents</p> -<p>• [VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task</p> -