Skip to content

Commit 03b5892

Browse files
committed
chore: Update CHANGELOG.md and feed.xml
1 parent 94506ff commit 03b5892

2 files changed

Lines changed: 112 additions & 9 deletions

File tree

‎CHANGELOG.md‎

Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,59 @@
11
# Changelog
22

3+
## 2.1.301
4+
5+
- Added `CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS` so unattended retry mode (`CLAUDE_CODE_RETRY_WATCHDOG`) ends a request at a usage limit that resets too far away instead of waiting
6+
- Added OpenTelemetry tracing guidance to the `claude-api` skill, including setting up trace destinations with the `ant` CLI
7+
- Added the `%` motion to vim mode: jump to the matching bracket, alone or with d/c/y
8+
- Added `rows` to a mod's `Input`: a text field of several lines in the terminal, where Enter submits and Shift+Enter or a backslash before Enter starts a new line
9+
- Added `classifier_verdict` and `permission_mode` to OpenTelemetry `tool_decision` events, so auto mode classifier decisions can be told apart from permission rules
10+
- Added `classifier_category` to OpenTelemetry `tool_decision` events, naming the built-in rule a classifier block matched, when `OTEL_LOG_TOOL_DETAILS=1`
11+
- Fixed quitting removing a worktree made by a `WorktreeCreate` hook without asking when it may hold unpushed commits
12+
- Fixed the `fable` (and `best`) model alias erroring on the Anthropic API when the newest Fable model is not available to your organization: Claude Code now retries once on the previous Fable model
13+
- Fixed a misleading "Please run /login" error when a full disk keeps the login from being refreshed; the error now names the disk and says to delete files
14+
- Fixed Grep and Glob reporting no matches when the search program failed unexpectedly before returning any results; they now return an error saying the search failed
15+
- Fixed workflow agents sometimes skipping their step, and the run still reporting success, after reading the harness note that their task text carries no user authority
16+
- Fixed artifact updates being refused where a PreToolUse hook covers Edit or Write; Claude now edits the file and then republishes instead of changing it in the publish call
17+
- Fixed skills and commands with very many or very long argument names stalling for seconds when invoked; only the first 64 names, each up to 64 characters, are now filled in
18+
- Fixed skills, commands and hooks using very large amounts of memory when their arguments fill many placeholders
19+
- Fixed stray characters such as `>0q` covering the folder trust prompt, and `>4m` before the shell prompt at exit, in terminals built on VTE older than 0.53 such as MATE Terminal on RHEL 8
20+
- Fixed stray `GOK` text appearing in the prompt at startup in some versions of iTerm2
21+
- Fixed switching to a model whose name contains `application-inference-profile` running your `awsAuthRefresh` command and delaying model-switch hooks when the provider is not Bedrock
22+
- Fixed sign-in refresh timeouts and unexpected sign-outs after a short command such as `claude auth status` or `claude plugin list` exited in the middle of a token refresh
23+
- Fixed a tool call cut off by a message sent mid-turn during its permission check being reported to the model as rejected by the user
24+
- Fixed a case where switching to a model with a smaller context window could spend usage credits on a summary by the previous model without asking first
25+
- Fixed conversations being compacted over and over, on a model you didn't pick, behind an LLM gateway whose responses name a different model than the one requested
26+
- Fixed vim mode sometimes staying in INSERT after Escape on a slow or busy machine
27+
- Fixed Esc discarding a typed AskUserQuestion answer in vim mode: the free-text field now supports vim NORMAL mode, and Esc cancels only from NORMAL
28+
- Fixed the Read tool reading binary files such as .xlsm, .parquet, .epub and .heic as text
29+
- Fixed a Markdown table with only a header row drawing nothing when too wide for the terminal, including in plans on the plan approval card
30+
- Fixed the /claude-api skill saying CMEK external-key endpoints aren't available on Claude Platform on AWS
31+
- Fixed skills no longer being listed to the model after using `/rewind`
32+
- Fixed the compaction row in a resumed session offering ctrl+o for history that is not loaded; it now says where the earlier messages are saved, and also shows in fullscreen
33+
- Fixed the "new task? /clear to save tokens" hint coming back right after you interrupt a response
34+
- Fixed the permission prompt for a plugin or skill hook's `ask` decision not showing which plugin or skill the hook comes from
35+
- Fixed `/diff` not noticing a conflicted cherry-pick or revert in reftable repositories when one of its git checks timed out or failed
36+
- Fixed workflow scripts asking for permission or being refused when read, edited or re-run after a Bash `cd` in the same session
37+
- Fixed dim text on the dark ANSI theme and 16-color terminals: faint inside filled boxes, not faint under selection and search highlights, and list descriptions dimmed like other secondary text
38+
- Fixed a mod's `$.model.fork` returning `nothing-to-fork` when called before the first response of a new Claude Code process had finished, as in `claude -p` runs and cloud sessions
39+
- Fullscreen mode: Fixed `/compact` and auto-compact briefly freezing the UI while the visible transcript is rebuilt
40+
- Self-hosted runner: Fixed sessions started from Slack being unable to find or attach a repository when managed settings restrict MCP servers; use `deniedMcpServers` to keep those tools off
41+
- Self-hosted runner: Fixed sessions being reported as having a deleted source branch, and not retried, when an unrelated setup or session failure quoted git's missing-ref wording
42+
- Self-hosted runner: Fixed the log promising a retry of a failed or declined session release for a session that is ending; repeated failures now show a count
43+
- Windows: Fixed stopped background PowerShell commands missing the closing `[killed]` line in their output file
44+
- Improved switching to a model with a smaller context window: a conversation too long for the new model is now summarized by the previous model first
45+
- Improved rendering performance while a long-running subagent works: its progress trail now updates incrementally instead of being reprocessed in full on every render
46+
- Improved artifacts: pages Claude writes now paint the band above a sticky header, so scrolled text no longer shows there in the mobile apps
47+
- Improved mods: in VS Code and the desktop and mobile apps, a tree drawn above the question dialog can now hold Markdown and up to 48 rows; the terminal keeps 12 plain rows
48+
- Changed a mod hook's `.catch` handler to run only when the hook throws or times out; events raised beneath the hook's own calls now skip that hook without asking its `.catch`
49+
- Changed a mod's `$.env.set` to resolve with `{}` once the variable is set or unset, or with `{ deny }` saying why when the write is not made
50+
- [VSCode] Added LaTeX math rendering in Claude's responses, including `$$` and multi-line `\[ … \]` blocks and inline `$…$` and `\(…\)` math
51+
- [VSCode] Added a "Get more usage" link to the usage-limit banner for Pro and Max plans in the VS Code and JetBrains panels
52+
- [VSCode] Fixed a conversation that crashes or freezes the panel being reopened on every reload
53+
- [VSCode] Fixed the chat panel slowing down during long thinking: it no longer re-parses the whole thinking text on every update
54+
- [VSCode] Fixed diagnostics showing "[object Object]" instead of the rule code (e.g. MD013) for some language servers
55+
- [VSCode] Fixed the native dictation audio module being loaded, to check microphone permission, where dictation is not offered (non-claude.ai sign-ins, remote windows)
56+
357
## 2.1.300
458

559
- Added `virtualText` to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt

‎feed.xml‎

Lines changed: 58 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,64 @@
66
<author><name>Anthropic</name></author>
77
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/>
88
<link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/>
9-
<updated>2026-10-14T18:24:07Z</updated>
9+
<updated>2026-10-15T19:21:45Z</updated>
10+
<entry>
11+
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.301</id>
12+
<title>Claude Code v2.1.301</title>
13+
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.301"/>
14+
<updated>2026-10-15T19:21:45Z</updated>
15+
<content type="html">&lt;p&gt;• Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waiting&lt;/p&gt;
16+
&lt;p&gt;• Added OpenTelemetry tracing guidance to the claude-api skill, including setting up trace destinations with the ant CLI&lt;/p&gt;
17+
&lt;p&gt;• Added the % motion to vim mode: jump to the matching bracket, alone or with d/c/y&lt;/p&gt;
18+
&lt;p&gt;• Added rows to a mod's Input: a text field of several lines in the terminal, where Enter submits and Shift+Enter or a backslash before Enter starts a new line&lt;/p&gt;
19+
&lt;p&gt;• Added classifier_verdict and permission_mode to OpenTelemetry tool_decision events, so auto mode classifier decisions can be told apart from permission rules&lt;/p&gt;
20+
&lt;p&gt;• Added classifier_category to OpenTelemetry tool_decision events, naming the built-in rule a classifier block matched, when OTEL_LOG_TOOL_DETAILS=1&lt;/p&gt;
21+
&lt;p&gt;• Fixed quitting removing a worktree made by a WorktreeCreate hook without asking when it may hold unpushed commits&lt;/p&gt;
22+
&lt;p&gt;• Fixed the fable (and best) model alias erroring on the Anthropic API when the newest Fable model is not available to your organization: Claude Code now retries once on the previous Fable model&lt;/p&gt;
23+
&lt;p&gt;• Fixed a misleading "Please run /login" error when a full disk keeps the login from being refreshed; the error now names the disk and says to delete files&lt;/p&gt;
24+
&lt;p&gt;• Fixed Grep and Glob reporting no matches when the search program failed unexpectedly before returning any results; they now return an error saying the search failed&lt;/p&gt;
25+
&lt;p&gt;• Fixed workflow agents sometimes skipping their step, and the run still reporting success, after reading the harness note that their task text carries no user authority&lt;/p&gt;
26+
&lt;p&gt;• Fixed artifact updates being refused where a PreToolUse hook covers Edit or Write; Claude now edits the file and then republishes instead of changing it in the publish call&lt;/p&gt;
27+
&lt;p&gt;• Fixed skills and commands with very many or very long argument names stalling for seconds when invoked; only the first 64 names, each up to 64 characters, are now filled in&lt;/p&gt;
28+
&lt;p&gt;• Fixed skills, commands and hooks using very large amounts of memory when their arguments fill many placeholders&lt;/p&gt;
29+
&lt;p&gt;• Fixed stray characters such as &amp;gt;0q covering the folder trust prompt, and &amp;gt;4m before the shell prompt at exit, in terminals built on VTE older than 0.53 such as MATE Terminal on RHEL 8&lt;/p&gt;
30+
&lt;p&gt;• Fixed stray GOK text appearing in the prompt at startup in some versions of iTerm2&lt;/p&gt;
31+
&lt;p&gt;• Fixed switching to a model whose name contains application-inference-profile running your awsAuthRefresh command and delaying model-switch hooks when the provider is not Bedrock&lt;/p&gt;
32+
&lt;p&gt;• Fixed sign-in refresh timeouts and unexpected sign-outs after a short command such as claude auth status or claude plugin list exited in the middle of a token refresh&lt;/p&gt;
33+
&lt;p&gt;• Fixed a tool call cut off by a message sent mid-turn during its permission check being reported to the model as rejected by the user&lt;/p&gt;
34+
&lt;p&gt;• Fixed a case where switching to a model with a smaller context window could spend usage credits on a summary by the previous model without asking first&lt;/p&gt;
35+
&lt;p&gt;• Fixed conversations being compacted over and over, on a model you didn't pick, behind an LLM gateway whose responses name a different model than the one requested&lt;/p&gt;
36+
&lt;p&gt;• Fixed vim mode sometimes staying in INSERT after Escape on a slow or busy machine&lt;/p&gt;
37+
&lt;p&gt;• Fixed Esc discarding a typed AskUserQuestion answer in vim mode: the free-text field now supports vim NORMAL mode, and Esc cancels only from NORMAL&lt;/p&gt;
38+
&lt;p&gt;• Fixed the Read tool reading binary files such as .xlsm, .parquet, .epub and .heic as text&lt;/p&gt;
39+
&lt;p&gt;• Fixed a Markdown table with only a header row drawing nothing when too wide for the terminal, including in plans on the plan approval card&lt;/p&gt;
40+
&lt;p&gt;• Fixed the /claude-api skill saying CMEK external-key endpoints aren't available on Claude Platform on AWS&lt;/p&gt;
41+
&lt;p&gt;• Fixed skills no longer being listed to the model after using /rewind&lt;/p&gt;
42+
&lt;p&gt;• Fixed the compaction row in a resumed session offering ctrl+o for history that is not loaded; it now says where the earlier messages are saved, and also shows in fullscreen&lt;/p&gt;
43+
&lt;p&gt;• Fixed the "new task? /clear to save tokens" hint coming back right after you interrupt a response&lt;/p&gt;
44+
&lt;p&gt;• Fixed the permission prompt for a plugin or skill hook's ask decision not showing which plugin or skill the hook comes from&lt;/p&gt;
45+
&lt;p&gt;• Fixed /diff not noticing a conflicted cherry-pick or revert in reftable repositories when one of its git checks timed out or failed&lt;/p&gt;
46+
&lt;p&gt;• Fixed workflow scripts asking for permission or being refused when read, edited or re-run after a Bash cd in the same session&lt;/p&gt;
47+
&lt;p&gt;• Fixed dim text on the dark ANSI theme and 16-color terminals: faint inside filled boxes, not faint under selection and search highlights, and list descriptions dimmed like other secondary text&lt;/p&gt;
48+
&lt;p&gt;• Fixed a mod's $.model.fork returning nothing-to-fork when called before the first response of a new Claude Code process had finished, as in claude -p runs and cloud sessions&lt;/p&gt;
49+
&lt;p&gt;• Fullscreen mode: Fixed /compact and auto-compact briefly freezing the UI while the visible transcript is rebuilt&lt;/p&gt;
50+
&lt;p&gt;• Self-hosted runner: Fixed sessions started from Slack being unable to find or attach a repository when managed settings restrict MCP servers; use deniedMcpServers to keep those tools off&lt;/p&gt;
51+
&lt;p&gt;• Self-hosted runner: Fixed sessions being reported as having a deleted source branch, and not retried, when an unrelated setup or session failure quoted git's missing-ref wording&lt;/p&gt;
52+
&lt;p&gt;• Self-hosted runner: Fixed the log promising a retry of a failed or declined session release for a session that is ending; repeated failures now show a count&lt;/p&gt;
53+
&lt;p&gt;• Windows: Fixed stopped background PowerShell commands missing the closing [killed] line in their output file&lt;/p&gt;
54+
&lt;p&gt;• Improved switching to a model with a smaller context window: a conversation too long for the new model is now summarized by the previous model first&lt;/p&gt;
55+
&lt;p&gt;• Improved rendering performance while a long-running subagent works: its progress trail now updates incrementally instead of being reprocessed in full on every render&lt;/p&gt;
56+
&lt;p&gt;• Improved artifacts: pages Claude writes now paint the band above a sticky header, so scrolled text no longer shows there in the mobile apps&lt;/p&gt;
57+
&lt;p&gt;• Improved mods: in VS Code and the desktop and mobile apps, a tree drawn above the question dialog can now hold Markdown and up to 48 rows; the terminal keeps 12 plain rows&lt;/p&gt;
58+
&lt;p&gt;• Changed a mod hook's .catch handler to run only when the hook throws or times out; events raised beneath the hook's own calls now skip that hook without asking its .catch&lt;/p&gt;
59+
&lt;p&gt;• Changed a mod's $.env.set to resolve with {} once the variable is set or unset, or with { deny } saying why when the write is not made&lt;/p&gt;
60+
&lt;p&gt;• [VSCode] Added LaTeX math rendering in Claude's responses, including $$ and multi-line \[ … \] blocks and inline $…$ and \(…\) math&lt;/p&gt;
61+
&lt;p&gt;• [VSCode] Added a "Get more usage" link to the usage-limit banner for Pro and Max plans in the VS Code and JetBrains panels&lt;/p&gt;
62+
&lt;p&gt;• [VSCode] Fixed a conversation that crashes or freezes the panel being reopened on every reload&lt;/p&gt;
63+
&lt;p&gt;• [VSCode] Fixed the chat panel slowing down during long thinking: it no longer re-parses the whole thinking text on every update&lt;/p&gt;
64+
&lt;p&gt;• [VSCode] Fixed diagnostics showing "[object Object]" instead of the rule code (e.g. MD013) for some language servers&lt;/p&gt;
65+
&lt;p&gt;• [VSCode] Fixed the native dictation audio module being loaded, to check microphone permission, where dictation is not offered (non-claude.ai sign-ins, remote windows)&lt;/p&gt;</content>
66+
</entry>
1067
<entry>
1168
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.300</id>
1269
<title>Claude Code v2.1.300</title>
@@ -1980,12 +2037,4 @@
19802037
&lt;p&gt;• [Claude Tag] Improved the GitHub banner in Claude Tag admin settings to say why GitHub isn't connected: not signed in, app not linked or not installed, sign-in expired, or SSO not authorized&lt;/p&gt;
19812038
&lt;p&gt;• [Code Review] Improved the Code Review check run to say when REVIEW.md instructions were cut or left out of a review for exceeding a size limit, naming the file and the limit&lt;/p&gt;</content>
19822039
</entry>
1983-
<entry>
1984-
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.278</id>
1985-
<title>Claude Code v2.1.278</title>
1986-
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.278"/>
1987-
<updated>2026-09-19T03:10:24Z</updated>
1988-
<content type="html">&lt;p&gt;• Changed auto mode for Claude API and Enterprise users, and on Bedrock, Vertex, Foundry and gateways, to default to the server-side classifier, which does not charge for classifier overhead (CLAUDE_CODE_AUTO_MODE_SERVER=0 opts out on Bedrock, Vertex, Foundry and gateways); warns on billed fallback. See https://code.claude.com/docs/en/auto-mode-classifier-billing&lt;/p&gt;
1989-
&lt;p&gt;• Added an Auto mode server row to /status showing whether this session's auto mode classifier runs on the server&lt;/p&gt;</content>
1990-
</entry>
19912040
</feed>

0 commit comments

Comments
 (0)