From 2982f951552e94f38cd972764ae94c1d90c41da3 Mon Sep 17 00:00:00 2001 From: GitHub Actions Date: Wed, 22 Jul 2026 21:24:49 +0000 Subject: [PATCH] chore: Update CHANGELOG.md and feed.xml --- CHANGELOG.md | 40 ++++++++++++++++++++++++++++++++++++++++ feed.xml | 52 ++++++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 84 insertions(+), 8 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index d0eab90e4..7b4d63ae5 100644 --- a/CHANGELOG.md +++ b/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=` 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 diff --git a/feed.xml b/feed.xml index a8b3cf6a0..0f5a702b6 100644 --- a/feed.xml +++ b/feed.xml @@ -6,7 +6,50 @@ Anthropic - 2026-07-21T21:35:04Z + 2026-07-22T21:24:49Z + + https://github.com/anthropics/claude-code/releases/tag/v2.1.218 + Claude Code v2.1.218 + + 2026-07-22T21:24:49Z + <p>• 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</p> +<p>• 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</p> +<p>• Fixed Windows paths with \u-prefixed segments (like C:\Users\unicorn) being corrupted into CJK characters in tool inputs, which made those files inaccessible</p> +<p>• 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</p> +<p>• 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</p> +<p>• Fixed multi-line paste collapsing into one line with j in place of newlines in terminals that encode pasted newlines as Ctrl+J</p> +<p>• Fixed /context reporting stale pre-compact token usage after compacting from the message picker</p> +<p>• 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</p> +<p>• Fixed /code-review ultra silently running a local review in non-interactive sessions — it now launches the cloud review</p> +<p>• Fixed gateway spend metering to price Bedrock application-inference-profile ARNs and other config-mapped upstream model IDs at the configured model's rates</p> +<p>• Fixed mojibake when a long IDE selection was truncated mid-emoji, and a case where a tool executor error could be silently dropped</p> +<p>• Fixed an engine teardown race that could start and abandon a phantom turn, and made input pushed after close consistently rejected</p> +<p>• 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</p> +<p>• Fixed VoiceOver reading "new line" instead of echoing the typed space at the end of the input in --ax-screen-reader mode</p> +<p>• Fixed plugin and settings panels not moving the terminal cursor to the focused row, so screen readers and magnifiers can follow arrow-key navigation</p> +<p>• Fixed crashes (maximum call stack exceeded) when a deeply nested watched directory tree was deleted or moved, and when rendering deeply nested UI trees</p> +<p>• Fixed pull request events occasionally being lost when a session exited immediately after creating or linking a PR</p> +<p>• Fixed the Bedrock setup wizard failing profile verification for assume-role profiles in partitioned AWS regions and on proxy-only networks</p> +<p>• Fixed rare negative or incorrect turn duration measurements after a system clock adjustment by timing turns with a monotonic clock</p> +<p>• Fixed the "N MCP servers need authentication" startup notice over-counting claude.ai connectors that aren't connected in claude.ai</p> +<p>• Fixed prompt history entries being dropped or duplicated when history writes raced or failed</p> +<p>• 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</p> +<p>• Fixed agent frontmatter hooks running from untrusted folders: hooks now require the agent file's own folder to have accepted workspace trust</p> +<p>• Fixed fork-session lineage being lost after compaction in headless and SDK sessions</p> +<p>• Fixed a resumed session failing every turn, or crashing on resume, when its history held a malformed delta attachment</p> +<p>• Improved /ultrareview error feedback so Claude can correct an invalid argument instead of retrying it unchanged</p> +<p>• Improved auto mode: the dangerous-rm, background-&amp;, and suspicious-Windows-path checks no longer open permission dialogs; the auto-mode classifier adjudicates them instead</p> +<p>• Improved sandbox command restrictions for IDE interactions</p> +<p>• Improved trust dialogs to name the repository root the grant covers</p> +<p>• Changed /deep-research to start only when invoked manually; Claude no longer launches it on its own</p> +<p>• 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</p> +<p>• Added an announcement when fast mode changes as a result of switching models via /config model=&lt;x&gt; or Remote Control</p> +<p>• Changed server-managed settings so benign feature and cost toggles no longer trigger the settings-approval prompt</p> +<p>• Changed agent markdown files to reject agent names containing :, which is reserved for plugin namespacing</p> +<p>• Changed skills with context: fork to run in the background by default; opt out per skill with background: false</p> +<p>• Added yes/no/on/off/1/0 (case-insensitive) as accepted values for skill and plugin frontmatter booleans, alongside true/false</p> +<p>• 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</p> + https://github.com/anthropics/claude-code/releases/tag/v2.1.217 Claude Code v2.1.217 @@ -599,11 +642,4 @@ <p>• Subagents now treat messages from the agent that launched them as normal task direction; an agent's message is still never treated as the user's approval</p> <p>• Removed the /agents wizard; ask Claude to create or manage subagents, or edit .claude/agents/ directly</p> - - https://github.com/anthropics/claude-code/releases/tag/v2.1.197 - Claude Code v2.1.197 - - 2026-06-30T17:56:29Z - <p>• Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access. https://www.anthropic.com/news/claude-sonnet-5</p> -