mirror of
https://github.com/anthropics/claude-code.git
synced 2026-07-17 00:23:30 +00:00
Compare commits
5 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
c39cb0f14b | ||
|
|
b7784f2c63 | ||
|
|
c9181ca6eb | ||
|
|
988b3e5643 | ||
|
|
1fb278b85d |
130
CHANGELOG.md
130
CHANGELOG.md
@@ -1,5 +1,133 @@
|
||||
# Changelog
|
||||
|
||||
## 2.1.211
|
||||
|
||||
- Added `--forward-subagent-text` flag and `CLAUDE_CODE_FORWARD_SUBAGENT_TEXT` environment variable to include subagent text and thinking in stream-json output
|
||||
- Fixed permission previews relayed to chat channels not neutralizing bidirectional-override, zero-width, and look-alike quote characters, so tool inputs cannot visually alter the approval message
|
||||
- Fixed auto mode overriding a PreToolUse hook's `ask` decision for unsandboxed Bash — a hook `ask` now floors the decision at a prompt
|
||||
- Fixed parallel Claude Code sessions all logging out simultaneously after wake-from-sleep when many sessions share one credential store
|
||||
- Fixed plugin MCP servers not reconnecting after an idle web session woke, leaving MCP calls failing until the next message
|
||||
- Fixed Claude Code on Vertex and Bedrock attempting the default Opus model at startup and printing a spurious fallback notice when a model is explicitly configured
|
||||
- Fixed subagents spawned with an explicit model override reverting to the parent's model when resumed or sent a follow-up message
|
||||
- Fixed nested `.claude/rules/*.md` files loading even when setting sources exclude project settings
|
||||
- Fixed file upload validation: filenames ending in a DOS device suffix (`.prn`) or trailing dot are now accepted, and files with multiple hard links are refused
|
||||
- Fixed file uploads to Claude in Chrome from remote and CLI sessions
|
||||
- Fixed edits that leave the input as "?" being silently swallowed and toggling the shortcuts panel
|
||||
- Fixed a startup hang when the Claude in Chrome extension is enabled but Chrome is not running
|
||||
- Fixed a 300ms delay revealing async content (Settings tabs, Stats, diff views, and other loading states)
|
||||
- Fixed reopening a just-stopped background session from the agents view starting a blank conversation under the same session id
|
||||
- Fixed `/loop` hiding the session from `/resume` after a single use
|
||||
- Fixed screen reader users losing the audible terminal bell after `/terminal-setup` or onboarding terminal setup
|
||||
- Fixed background jobs on LLM gateway auth (`ANTHROPIC_AUTH_TOKEN` + `ANTHROPIC_BASE_URL`) coming back "Not logged in" after the daemon respawns them
|
||||
- Fixed `claude agents` jobs becoming permanently undeletable when git no longer recognizes their worktree — the row now shows why the delete was refused instead of silently reappearing
|
||||
- Fixed `/clear` not resetting the session cost counter — the statusline's cost now starts at $0 after `/clear`
|
||||
- Fixed Claude in Chrome setup pages failing to open in the browser on Windows
|
||||
- Fixed headless print-mode sessions on Windows crashing or silently exiting when stdin is unreadable
|
||||
- Fixed background session titles in the agents view showing the naming model's refusal text when the prompt contains a link
|
||||
- Fixed background agents killed by the user auto-respawning, and revived agents re-running stale prompts from old sessions
|
||||
- Fixed routines with no schedule reporting a next run time in the year 1
|
||||
- Hardened synced skill/plugin directory naming on Windows and kept CCR web fetch/search proxies working after `/clear`
|
||||
- Improved terminal layout and rendering performance
|
||||
- Improved background agent result reporting — Claude now reports the status of still-running agents and waits for the real completion instead of fabricating results
|
||||
- Improved the memory index over-limit warning to measure only loaded content, excluding frontmatter and HTML comments
|
||||
- Updated integer environment variables (timeouts, token budgets, retry counts) to accept scientific notation and digit-separator spellings like `1e6` and `64_000`
|
||||
- Updated documentation links to the current docs sites
|
||||
- Changed "always allow" permission rules to save at the repository root, so approvals granted in a git worktree persist across sessions and worktrees
|
||||
- Changed `/usage-credits` to ask for confirmation before sending a request to organization admins
|
||||
- Changed Vim mode `s` and `S` (substitute char/line) to work in NORMAL mode, matching vim behavior
|
||||
- [VSCode] Updated the Remote Control banner to describe what it does
|
||||
- Claude in Chrome: hardened file-upload path validation
|
||||
- Claude in Chrome: `save_to_disk` on screenshot actions now writes the image to disk and returns the path; previously it did nothing
|
||||
- Fixed a prompt-caching regression on Bedrock, Vertex, Mantle, and Foundry that billed the trailing system context block as fresh input tokens on every request.
|
||||
|
||||
## 2.1.210
|
||||
|
||||
- Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck
|
||||
- Added a startup warning for `Write(path)`, `NotebookEdit(path)`, and `Glob(path)` permission rules — use `Edit(path)` or `Read(path)` instead
|
||||
- Fixed `isolation: 'worktree'` subagents being able to run git-mutating commands against the main repo checkout instead of their own isolated worktree
|
||||
- Fixed the `ultracode` keyword opt-in firing on non-human-originated input such as webhook payloads and relayed PR comments
|
||||
- Fixed a rendered text fragment leaking into crash telemetry when a UI component returned content outside a styled text element
|
||||
- Fixed paste markers leaking into external editors opened from Claude Code, which could appear as stray È/É characters around pasted text
|
||||
- Fixed `claude attach` sometimes failing with "job not found" or "agent is still starting" errors during session transitions — attach now waits for the daemon to settle, and terminal resizes during a slow attach are applied once it completes
|
||||
- Fixed a session crash when a tool's result renderer returned a numeric bigint value or plain text instead of a UI element
|
||||
- Fixed a hook callback timeout being misreported to the model as a user rejection, which made unattended sessions stop and wait
|
||||
- Fixed Claude assuming a `cd` took effect after its command was moved to the background; the tool result now states the working directory is unchanged
|
||||
- Fixed plugin-provided MCP servers being torn down when MCP servers are re-synced mid-session
|
||||
- Fixed plan approvals without edits being labeled "(edited by user)" and overwriting the plan file with a stale snapshot
|
||||
- Fixed `/doctor` skipping its auto-mode-default proposal on Bedrock, Vertex, and Foundry, where auto mode no longer needs an opt-in
|
||||
- Fixed Grep content mode claiming "No matches found" when paginating past the end of results
|
||||
- Fixed unmatched `$1`/`$2` positional placeholders in skills and commands being silently stripped; they are now preserved verbatim
|
||||
- Fixed plugin cache writes leaving temp files behind on failure and failing on locked-file renames on Windows and network filesystems
|
||||
- Fixed background workers crash-looping when a client resets its connection to the background service
|
||||
- Fixed `claude agents --effort ultracode` not reaching dispatched sessions; the value was silently dropped
|
||||
- Fixed pressing ← to open the agents view dropping the task tracker when returning to the session
|
||||
- Fixed the agents dashboard retaining pasted images from abandoned reply drafts after their session was deleted
|
||||
- Fixed killed background sessions leaving a permanent `git worktree lock` behind; the periodic sweep now releases locks whose owning process is gone
|
||||
- Fixed SDK MCP servers registered via an `initialize` control request waiting until the next turn to start connecting
|
||||
- Fixed returning to the agents view from a session leaving overlapping ghost frames with `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1`
|
||||
- Fixed late-appearing `.claude/*` symlinks not being reconciled into the sandbox deny-write list
|
||||
- Hardened the Agent tool against indirect prompt injection via content a subagent read
|
||||
- Improved the Bash/PowerShell tool message when a command hits its timeout and is auto-backgrounded, so the model can distinguish a hang from an explicit background request
|
||||
- Improved auto mode: the permission classifier now defaults to Sonnet 5 for external sessions, validated on the session's first request and pinned for the session
|
||||
- Improved the bundled dataviz skill's chart color validation with perceptual OKLab color difference and recalibrated color-blindness thresholds
|
||||
- Memory writes that leave a MEMORY.md index over its read limit now produce an explicit error instead of silent truncation
|
||||
- Screen reader mode now announces permission mode changes aloud when cycling modes with Shift+Tab
|
||||
- The agents footer hint now shows how many background agents are waiting on your input, with a brief color emphasis when the count changes
|
||||
- Agent view: the session you pressed ← from stays visibly marked even after mouse hover or arrow keys move the selection
|
||||
- Fable temporarily shows as unavailable in the advisor picker while a server-side issue causing Fable advisor failures is fixed
|
||||
|
||||
## 2.1.209
|
||||
|
||||
- Fixed /model and other dialogs being blocked in `claude agents` background sessions (reverts an overly broad guard)
|
||||
|
||||
## 2.1.208
|
||||
|
||||
- Added screen reader mode: opt-in plain-text rendering for screen reader users. Run `claude --ax-screen-reader`, set CLAUDE_AX_SCREEN_READER=1, or add "axScreenReader": true to settings.
|
||||
- Added `vimInsertModeRemaps` setting: map two-key insert-mode sequences like `jj` to Escape in vim mode
|
||||
- Added `CLAUDE_CODE_PROCESS_WRAPPER`: agent view and the background service now honor a corporate launcher by running every Claude Code self-spawn through a required wrapper executable
|
||||
- Added mouse-click support for multi-select menus and "Other" input rows in fullscreen mode
|
||||
- Fixed fast mode staying off after switching back to a model that supports it — it now restores automatically when enabled in settings
|
||||
- Fixed replies typed to a background agent being lost when delivery fails — the text is now saved and delivered when the session restarts
|
||||
- Fixed background-session attach failing permanently ("Couldn't start the background daemon") after an update replaced the binary a running `claude agents` process was launched from
|
||||
- Fixed the context window (and auto-compact indicator) briefly resetting to 200k after the CLI auto-updates, causing a false "100% context used" when resuming long-context sessions
|
||||
- Fixed supervised and background sessions crashing when a server closed an HTTP/2 connection with a GOAWAY while requests were in flight
|
||||
- Fixed truncated stream-json/JSON output and missing result message when piping large responses from `claude -p`
|
||||
- Fixed `CLAUDE_CODE_MAX_OUTPUT_TOKENS` and similar env vars silently using the mantissa of scientific-notation values (`1e6` became `1`)
|
||||
- Fixed very large markdown tables stalling rendering or using excessive memory; tables over 200 rows show the first 200 with a "… N more rows" notice
|
||||
- Fixed the Edit tool failing on files modified after reading when the target text still matches uniquely
|
||||
- Fixed Read reporting empty files as "shorter than offset", Grep silently returning "No files found" for invalid regex patterns, Grep count mode under-reporting totals when paginated, and Glob crashing with an unclear error when the pattern, path, or working directory contained a null byte
|
||||
- Fixed `apiKeyHelper` script failures being hidden behind a generic 401 after ~10 silent retries; the script's own error is now shown within 3 attempts
|
||||
- Fixed Bedrock streaming requests failing with a misleading "Truncated event message received" when a gateway transforms the response — the error now names the content-type and points at the proxy
|
||||
- Fixed `/upgrade` showing a login flow instead of the upgrade URL when the browser fails to open
|
||||
- Fixed stream-json input killing the session on blank CRLF or whitespace-only lines from Windows-style SDK hosts
|
||||
- Fixed headless stream-json sessions hanging permanently when a `control_request` carried a non-string `set_model` payload; the CLI now answers with an error response
|
||||
- Fixed repeated "No completion record was found" notices on session resume — orphaned background tasks now collapse into a single summary
|
||||
- Fixed Remote Control clients attaching to a terminal-hosted session not seeing background agents and workflow progress until a task started or stopped
|
||||
- Fixed the Agent tool launching with no tools when a subagent's `tools` list resolves to nothing — it now returns a clear error naming the unrecognized entries
|
||||
- Fixed `/usage` showing stale cached bars over fresher data, and `/mcp` not reclassifying placeholder servers after config edits
|
||||
- Fixed "Change directory" in SDK hosts (e.g. Claude Desktop) failing with "A turn is in progress" on idle sessions that have a running background task
|
||||
- Fixed the workflow save dialog showing `~/.claude/workflows/` instead of the `CLAUDE_CONFIG_DIR` location for user-scope saves
|
||||
- Fixed `/release-notes` adding the viewed notes to the model's context — "Show all" previously injected the entire changelog into every subsequent request
|
||||
- Fixed a memory leak in the agent view where pasted images were retained for the screen's lifetime after sending peek replies
|
||||
- Fixed SDK sessions losing agents defined via the initialize request when a plugin refresh ran before the client attached
|
||||
- Fixed several memory leaks in long sessions: MCP stdio server stderr accumulating up to 64 MB per server, LSP documents staying open indefinitely (now LRU with 50-doc cap), async hook output retained after backgrounding, and unbounded growth in headless/SDK sessions from large tool-result payloads
|
||||
- Fixed a memory blowup when reading files with extremely long single lines using offset/limit — the read now returns a clean error instead of loading the whole line
|
||||
- Fixed multi-second per-turn slowdowns in sessions with many permission deny/ask rules — rule matchers are now compiled once and cached
|
||||
- Improved input responsiveness while agent task lists update — task updates no longer re-render the entire UI
|
||||
- Reduced per-tool-call CPU overhead in print/SDK sessions with many MCP tools by caching tool-pool assembly (up to 7x faster tool rounds at high tool counts)
|
||||
- Reduced memory usage by bounding the file edit read cache to 16 MB instead of pinning up to 1,000 full files
|
||||
- Reduced session transcript size (up to 79x in edit-heavy sessions) and bounded checkpoint disk usage by pruning superseded file-history backups
|
||||
- Reduced memory usage when resuming sessions with background agents or forks spawned from large conversations
|
||||
- Completed background agents now stay listed in `/tasks` until cleanup instead of vanishing the moment they finish
|
||||
- Attaching to a stopped background agent now shows its transcript immediately while the session warms up, instead of a blank "Session is starting" screen
|
||||
- Background sessions: an older daemon no longer silently restarts workers spawned by a newer version onto the older binary
|
||||
- Agent view: Ctrl+X now deletes renamed-branch worktrees, never destroys unpushed commits, keeps the session row when a worktree is kept, and reused worktree names reset to the current base
|
||||
- Catastrophic removals (e.g. `rm -rf ~`) in commands containing `$(…)`/backticks/`<(…)` now prompt in `--dangerously-skip-permissions` and auto mode, matching the plain form
|
||||
- `/install-github-app` and the `/mcp` settings menu no longer open in background sessions
|
||||
- MCP servers configured with an empty URL now show as "not configured" in `/mcp` instead of a config error
|
||||
- `/usage` now shows your last-known usage bars with an "as of" note when the usage endpoint is rate-limited, instead of an error screen
|
||||
- Fixed Bedrock auth failing with "Session token not found or invalid" for AWS SSO profiles whose sso_region differs from the Bedrock region (2.1.207 regression)
|
||||
|
||||
## 2.1.207
|
||||
|
||||
- Auto mode is now available without `CLAUDE_CODE_ENABLE_AUTO_MODE` opt-in on Bedrock, Vertex AI, and Foundry; disable via `disableAutoMode` in settings
|
||||
@@ -3431,7 +3559,7 @@
|
||||
|
||||
## 2.1.15
|
||||
|
||||
- Added deprecation notification for npm installations - run `claude install` or see https://docs.anthropic.com/en/docs/claude-code/getting-started for more options
|
||||
- Added deprecation notification for npm installations - run `claude install` or see https://code.claude.com/docs/en/setup for more options
|
||||
- Improved UI rendering performance with React Compiler
|
||||
- Fixed the "Context left until auto-compact" warning not disappearing after running `/compact`
|
||||
- Fixed MCP stdio server timeout not killing child process, which could cause UI freezes
|
||||
|
||||
238
feed.xml
238
feed.xml
@@ -6,7 +6,147 @@
|
||||
<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>2026-07-11T00:52:04Z</updated>
|
||||
<updated>2026-07-15T23:02:29Z</updated>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.211</id>
|
||||
<title>Claude Code v2.1.211</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.211"/>
|
||||
<updated>2026-07-15T23:02:29Z</updated>
|
||||
<content type="html"><p>• Added --forward-subagent-text flag and CLAUDE_CODE_FORWARD_SUBAGENT_TEXT environment variable to include subagent text and thinking in stream-json output</p>
|
||||
<p>• Fixed permission previews relayed to chat channels not neutralizing bidirectional-override, zero-width, and look-alike quote characters, so tool inputs cannot visually alter the approval message</p>
|
||||
<p>• Fixed auto mode overriding a PreToolUse hook's ask decision for unsandboxed Bash — a hook ask now floors the decision at a prompt</p>
|
||||
<p>• Fixed parallel Claude Code sessions all logging out simultaneously after wake-from-sleep when many sessions share one credential store</p>
|
||||
<p>• Fixed plugin MCP servers not reconnecting after an idle web session woke, leaving MCP calls failing until the next message</p>
|
||||
<p>• Fixed Claude Code on Vertex and Bedrock attempting the default Opus model at startup and printing a spurious fallback notice when a model is explicitly configured</p>
|
||||
<p>• Fixed subagents spawned with an explicit model override reverting to the parent's model when resumed or sent a follow-up message</p>
|
||||
<p>• Fixed nested .claude/rules/*.md files loading even when setting sources exclude project settings</p>
|
||||
<p>• Fixed file upload validation: filenames ending in a DOS device suffix (.prn) or trailing dot are now accepted, and files with multiple hard links are refused</p>
|
||||
<p>• Fixed file uploads to Claude in Chrome from remote and CLI sessions</p>
|
||||
<p>• Fixed edits that leave the input as "?" being silently swallowed and toggling the shortcuts panel</p>
|
||||
<p>• Fixed a startup hang when the Claude in Chrome extension is enabled but Chrome is not running</p>
|
||||
<p>• Fixed a 300ms delay revealing async content (Settings tabs, Stats, diff views, and other loading states)</p>
|
||||
<p>• Fixed reopening a just-stopped background session from the agents view starting a blank conversation under the same session id</p>
|
||||
<p>• Fixed /loop hiding the session from /resume after a single use</p>
|
||||
<p>• Fixed screen reader users losing the audible terminal bell after /terminal-setup or onboarding terminal setup</p>
|
||||
<p>• Fixed background jobs on LLM gateway auth (ANTHROPIC_AUTH_TOKEN + ANTHROPIC_BASE_URL) coming back "Not logged in" after the daemon respawns them</p>
|
||||
<p>• Fixed claude agents jobs becoming permanently undeletable when git no longer recognizes their worktree — the row now shows why the delete was refused instead of silently reappearing</p>
|
||||
<p>• Fixed /clear not resetting the session cost counter — the statusline's cost now starts at $0 after /clear</p>
|
||||
<p>• Fixed Claude in Chrome setup pages failing to open in the browser on Windows</p>
|
||||
<p>• Fixed headless print-mode sessions on Windows crashing or silently exiting when stdin is unreadable</p>
|
||||
<p>• Fixed background session titles in the agents view showing the naming model's refusal text when the prompt contains a link</p>
|
||||
<p>• Fixed background agents killed by the user auto-respawning, and revived agents re-running stale prompts from old sessions</p>
|
||||
<p>• Fixed routines with no schedule reporting a next run time in the year 1</p>
|
||||
<p>• Hardened synced skill/plugin directory naming on Windows and kept CCR web fetch/search proxies working after /clear</p>
|
||||
<p>• Improved terminal layout and rendering performance</p>
|
||||
<p>• Improved background agent result reporting — Claude now reports the status of still-running agents and waits for the real completion instead of fabricating results</p>
|
||||
<p>• Improved the memory index over-limit warning to measure only loaded content, excluding frontmatter and HTML comments</p>
|
||||
<p>• Updated integer environment variables (timeouts, token budgets, retry counts) to accept scientific notation and digit-separator spellings like 1e6 and 64_000</p>
|
||||
<p>• Updated documentation links to the current docs sites</p>
|
||||
<p>• Changed "always allow" permission rules to save at the repository root, so approvals granted in a git worktree persist across sessions and worktrees</p>
|
||||
<p>• Changed /usage-credits to ask for confirmation before sending a request to organization admins</p>
|
||||
<p>• Changed Vim mode s and S (substitute char/line) to work in NORMAL mode, matching vim behavior</p>
|
||||
<p>• [VSCode] Updated the Remote Control banner to describe what it does</p>
|
||||
<p>• Claude in Chrome: hardened file-upload path validation</p>
|
||||
<p>• Claude in Chrome: save_to_disk on screenshot actions now writes the image to disk and returns the path; previously it did nothing</p>
|
||||
<p>• Fixed a prompt-caching regression on Bedrock, Vertex, Mantle, and Foundry that billed the trailing system context block as fresh input tokens on every request.</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.210</id>
|
||||
<title>Claude Code v2.1.210</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.210"/>
|
||||
<updated>2026-07-14T23:45:19Z</updated>
|
||||
<content type="html"><p>• Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck</p>
|
||||
<p>• Added a startup warning for Write(path), NotebookEdit(path), and Glob(path) permission rules — use Edit(path) or Read(path) instead</p>
|
||||
<p>• Fixed isolation: 'worktree' subagents being able to run git-mutating commands against the main repo checkout instead of their own isolated worktree</p>
|
||||
<p>• Fixed the ultracode keyword opt-in firing on non-human-originated input such as webhook payloads and relayed PR comments</p>
|
||||
<p>• Fixed a rendered text fragment leaking into crash telemetry when a UI component returned content outside a styled text element</p>
|
||||
<p>• Fixed paste markers leaking into external editors opened from Claude Code, which could appear as stray È/É characters around pasted text</p>
|
||||
<p>• Fixed claude attach sometimes failing with "job not found" or "agent is still starting" errors during session transitions — attach now waits for the daemon to settle, and terminal resizes during a slow attach are applied once it completes</p>
|
||||
<p>• Fixed a session crash when a tool's result renderer returned a numeric bigint value or plain text instead of a UI element</p>
|
||||
<p>• Fixed a hook callback timeout being misreported to the model as a user rejection, which made unattended sessions stop and wait</p>
|
||||
<p>• Fixed Claude assuming a cd took effect after its command was moved to the background; the tool result now states the working directory is unchanged</p>
|
||||
<p>• Fixed plugin-provided MCP servers being torn down when MCP servers are re-synced mid-session</p>
|
||||
<p>• Fixed plan approvals without edits being labeled "(edited by user)" and overwriting the plan file with a stale snapshot</p>
|
||||
<p>• Fixed /doctor skipping its auto-mode-default proposal on Bedrock, Vertex, and Foundry, where auto mode no longer needs an opt-in</p>
|
||||
<p>• Fixed Grep content mode claiming "No matches found" when paginating past the end of results</p>
|
||||
<p>• Fixed unmatched $1/$2 positional placeholders in skills and commands being silently stripped; they are now preserved verbatim</p>
|
||||
<p>• Fixed plugin cache writes leaving temp files behind on failure and failing on locked-file renames on Windows and network filesystems</p>
|
||||
<p>• Fixed background workers crash-looping when a client resets its connection to the background service</p>
|
||||
<p>• Fixed claude agents --effort ultracode not reaching dispatched sessions; the value was silently dropped</p>
|
||||
<p>• Fixed pressing ← to open the agents view dropping the task tracker when returning to the session</p>
|
||||
<p>• Fixed the agents dashboard retaining pasted images from abandoned reply drafts after their session was deleted</p>
|
||||
<p>• Fixed killed background sessions leaving a permanent git worktree lock behind; the periodic sweep now releases locks whose owning process is gone</p>
|
||||
<p>• Fixed SDK MCP servers registered via an initialize control request waiting until the next turn to start connecting</p>
|
||||
<p>• Fixed returning to the agents view from a session leaving overlapping ghost frames with CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1</p>
|
||||
<p>• Fixed late-appearing .claude/* symlinks not being reconciled into the sandbox deny-write list</p>
|
||||
<p>• Hardened the Agent tool against indirect prompt injection via content a subagent read</p>
|
||||
<p>• Improved the Bash/PowerShell tool message when a command hits its timeout and is auto-backgrounded, so the model can distinguish a hang from an explicit background request</p>
|
||||
<p>• Improved auto mode: the permission classifier now defaults to Sonnet 5 for external sessions, validated on the session's first request and pinned for the session</p>
|
||||
<p>• Improved the bundled dataviz skill's chart color validation with perceptual OKLab color difference and recalibrated color-blindness thresholds</p>
|
||||
<p>• Memory writes that leave a MEMORY.md index over its read limit now produce an explicit error instead of silent truncation</p>
|
||||
<p>• Screen reader mode now announces permission mode changes aloud when cycling modes with Shift+Tab</p>
|
||||
<p>• The agents footer hint now shows how many background agents are waiting on your input, with a brief color emphasis when the count changes</p>
|
||||
<p>• Agent view: the session you pressed ← from stays visibly marked even after mouse hover or arrow keys move the selection</p>
|
||||
<p>• Fable temporarily shows as unavailable in the advisor picker while a server-side issue causing Fable advisor failures is fixed</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.209</id>
|
||||
<title>Claude Code v2.1.209</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.209"/>
|
||||
<updated>2026-07-14T06:36:21Z</updated>
|
||||
<content type="html"><p>• Fixed /model and other dialogs being blocked in claude agents background sessions (reverts an overly broad guard)</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.208</id>
|
||||
<title>Claude Code v2.1.208</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.208"/>
|
||||
<updated>2026-07-14T01:10:34Z</updated>
|
||||
<content type="html"><p>• Added screen reader mode: opt-in plain-text rendering for screen reader users. Run claude --ax-screen-reader, set CLAUDE_AX_SCREEN_READER=1, or add "axScreenReader": true to settings.</p>
|
||||
<p>• Added vimInsertModeRemaps setting: map two-key insert-mode sequences like jj to Escape in vim mode</p>
|
||||
<p>• Added CLAUDE_CODE_PROCESS_WRAPPER: agent view and the background service now honor a corporate launcher by running every Claude Code self-spawn through a required wrapper executable</p>
|
||||
<p>• Added mouse-click support for multi-select menus and "Other" input rows in fullscreen mode</p>
|
||||
<p>• Fixed fast mode staying off after switching back to a model that supports it — it now restores automatically when enabled in settings</p>
|
||||
<p>• Fixed replies typed to a background agent being lost when delivery fails — the text is now saved and delivered when the session restarts</p>
|
||||
<p>• Fixed background-session attach failing permanently ("Couldn't start the background daemon") after an update replaced the binary a running claude agents process was launched from</p>
|
||||
<p>• Fixed the context window (and auto-compact indicator) briefly resetting to 200k after the CLI auto-updates, causing a false "100% context used" when resuming long-context sessions</p>
|
||||
<p>• Fixed supervised and background sessions crashing when a server closed an HTTP/2 connection with a GOAWAY while requests were in flight</p>
|
||||
<p>• Fixed truncated stream-json/JSON output and missing result message when piping large responses from claude -p</p>
|
||||
<p>• Fixed CLAUDE_CODE_MAX_OUTPUT_TOKENS and similar env vars silently using the mantissa of scientific-notation values (1e6 became 1)</p>
|
||||
<p>• Fixed very large markdown tables stalling rendering or using excessive memory; tables over 200 rows show the first 200 with a "… N more rows" notice</p>
|
||||
<p>• Fixed the Edit tool failing on files modified after reading when the target text still matches uniquely</p>
|
||||
<p>• Fixed Read reporting empty files as "shorter than offset", Grep silently returning "No files found" for invalid regex patterns, Grep count mode under-reporting totals when paginated, and Glob crashing with an unclear error when the pattern, path, or working directory contained a null byte</p>
|
||||
<p>• Fixed apiKeyHelper script failures being hidden behind a generic 401 after ~10 silent retries; the script's own error is now shown within 3 attempts</p>
|
||||
<p>• Fixed Bedrock streaming requests failing with a misleading "Truncated event message received" when a gateway transforms the response — the error now names the content-type and points at the proxy</p>
|
||||
<p>• Fixed /upgrade showing a login flow instead of the upgrade URL when the browser fails to open</p>
|
||||
<p>• Fixed stream-json input killing the session on blank CRLF or whitespace-only lines from Windows-style SDK hosts</p>
|
||||
<p>• Fixed headless stream-json sessions hanging permanently when a control_request carried a non-string set_model payload; the CLI now answers with an error response</p>
|
||||
<p>• Fixed repeated "No completion record was found" notices on session resume — orphaned background tasks now collapse into a single summary</p>
|
||||
<p>• Fixed Remote Control clients attaching to a terminal-hosted session not seeing background agents and workflow progress until a task started or stopped</p>
|
||||
<p>• Fixed the Agent tool launching with no tools when a subagent's tools list resolves to nothing — it now returns a clear error naming the unrecognized entries</p>
|
||||
<p>• Fixed /usage showing stale cached bars over fresher data, and /mcp not reclassifying placeholder servers after config edits</p>
|
||||
<p>• Fixed "Change directory" in SDK hosts (e.g. Claude Desktop) failing with "A turn is in progress" on idle sessions that have a running background task</p>
|
||||
<p>• Fixed the workflow save dialog showing ~/.claude/workflows/ instead of the CLAUDE_CONFIG_DIR location for user-scope saves</p>
|
||||
<p>• Fixed /release-notes adding the viewed notes to the model's context — "Show all" previously injected the entire changelog into every subsequent request</p>
|
||||
<p>• Fixed a memory leak in the agent view where pasted images were retained for the screen's lifetime after sending peek replies</p>
|
||||
<p>• Fixed SDK sessions losing agents defined via the initialize request when a plugin refresh ran before the client attached</p>
|
||||
<p>• Fixed several memory leaks in long sessions: MCP stdio server stderr accumulating up to 64 MB per server, LSP documents staying open indefinitely (now LRU with 50-doc cap), async hook output retained after backgrounding, and unbounded growth in headless/SDK sessions from large tool-result payloads</p>
|
||||
<p>• Fixed a memory blowup when reading files with extremely long single lines using offset/limit — the read now returns a clean error instead of loading the whole line</p>
|
||||
<p>• Fixed multi-second per-turn slowdowns in sessions with many permission deny/ask rules — rule matchers are now compiled once and cached</p>
|
||||
<p>• Improved input responsiveness while agent task lists update — task updates no longer re-render the entire UI</p>
|
||||
<p>• Reduced per-tool-call CPU overhead in print/SDK sessions with many MCP tools by caching tool-pool assembly (up to 7x faster tool rounds at high tool counts)</p>
|
||||
<p>• Reduced memory usage by bounding the file edit read cache to 16 MB instead of pinning up to 1,000 full files</p>
|
||||
<p>• Reduced session transcript size (up to 79x in edit-heavy sessions) and bounded checkpoint disk usage by pruning superseded file-history backups</p>
|
||||
<p>• Reduced memory usage when resuming sessions with background agents or forks spawned from large conversations</p>
|
||||
<p>• Completed background agents now stay listed in /tasks until cleanup instead of vanishing the moment they finish</p>
|
||||
<p>• Attaching to a stopped background agent now shows its transcript immediately while the session warms up, instead of a blank "Session is starting" screen</p>
|
||||
<p>• Background sessions: an older daemon no longer silently restarts workers spawned by a newer version onto the older binary</p>
|
||||
<p>• Agent view: Ctrl+X now deletes renamed-branch worktrees, never destroys unpushed commits, keeps the session row when a worktree is kept, and reused worktree names reset to the current base</p>
|
||||
<p>• Catastrophic removals (e.g. rm -rf ~) in commands containing $(…)/backticks/&lt;(…) now prompt in --dangerously-skip-permissions and auto mode, matching the plain form</p>
|
||||
<p>• /install-github-app and the /mcp settings menu no longer open in background sessions</p>
|
||||
<p>• MCP servers configured with an empty URL now show as "not configured" in /mcp instead of a config error</p>
|
||||
<p>• /usage now shows your last-known usage bars with an "as of" note when the usage endpoint is rate-limited, instead of an error screen</p>
|
||||
<p>• Fixed Bedrock auth failing with "Session token not found or invalid" for AWS SSO profiles whose sso_region differs from the Bedrock region (2.1.207 regression)</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.207</id>
|
||||
<title>Claude Code v2.1.207</title>
|
||||
@@ -384,100 +524,4 @@
|
||||
<updated>2026-06-24T15:53:48Z</updated>
|
||||
<content type="html"><p>• Bug fixes and reliability improvements</p></content>
|
||||
</entry>
|
||||
<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"><p>• Added sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables</p>
|
||||
<p>• 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</p>
|
||||
<p>• Added mouse click support to select menus (permission prompts, /model, /config, etc.) in fullscreen mode</p>
|
||||
<p>• Fixed --resume failing with "No conversation found" when the original -p run produced no model turns</p>
|
||||
<p>• 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</p>
|
||||
<p>• 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)</p>
|
||||
<p>• Fixed Claude Code Remote sessions taking ~2.7s longer to start after the agent proxy CA system-trust install was added</p>
|
||||
<p>• Fixed pasted Korean/CJK text turning into mojibake in terminals that deliver paste as per-byte extended-key events</p>
|
||||
<p>• Fixed /update over Remote Control hanging when a startup trust dialog would have shown</p>
|
||||
<p>• Fixed background jobs in the agents view getting stuck in "working" indefinitely when the agent ended a turn without producing structured output</p>
|
||||
<p>• Fixed channel connections dropping after navigating to the agents view and back, and after /bg, /tui, or /update</p>
|
||||
<p>• Fixed agent stop notifications not correctly attributing who stopped the agent, and improved wording ("finished"/"stopped" instead of "came to rest")</p>
|
||||
<p>• Fixed subagent depth tracking: resumed subagents now restore their original spawn depth, and forked subagents now count toward the depth cap</p>
|
||||
<p>• Fixed leaked agent worktree registrations: locked .git/worktrees/ entries from killed agents are now cleaned up automatically</p>
|
||||
<p>• Fixed Cmd+click not opening URLs in fullscreen mode in Ghostty on macOS</p>
|
||||
<p>• Fixed claude --help not listing the --bg/--background flag</p>
|
||||
<p>• Fixed Esc, Ctrl-C, and Ctrl-D not working while /share is uploading</p>
|
||||
<p>• Improved /install-github-app: GitHub Actions workflow setup is now optional — you can install just the GitHub App and skip the workflow/secret steps</p>
|
||||
<p>• Improved /btw with ←/→ arrow navigation to step through earlier answers</p>
|
||||
<p>• Improved /plugin to surface plugins you haven't used recently so you can clean them up</p>
|
||||
<p>• [VSCode] Fixed extension becoming unresponsive when resuming a large session</p></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"><p>• Added claude mcp login &lt;name&gt; and claude mcp logout &lt;name&gt; to authenticate MCP servers from the CLI without opening the interactive /mcp menu, with --no-browser stdin redirect support for completing over SSH</p>
|
||||
<p>• Added status filtering (press f) to the /workflows agent detail view</p>
|
||||
<p>• Added a "Skills" section to the /plugin Installed tab</p>
|
||||
<p>• Added teammateMode: "iterm2" setting with a warning when auto mode cannot find the it2 CLI</p>
|
||||
<p>• Added "Claude Platform on AWS - refresh credentials" option to /login when awsAuthRefresh is configured</p>
|
||||
<p>• ! bash commands now trigger Claude to respond to the output automatically; set "respondToBashCommands": false in settings.json to keep the previous context-only behavior</p>
|
||||
<p>• Fixed streaming requests failing with "Content block not found" or JSON parse errors after the machine wakes from sleep</p>
|
||||
<p>• Fixed subagent transcript scroll position bleeding into the main transcript on exit</p>
|
||||
<p>• Fixed background task previews flashing raw tool names before the agent's plan loaded</p>
|
||||
<p>• Fixed Chrome tab-group isolation not applying when the in-product permissions gate is off for concurrent CLI sessions</p>
|
||||
<p>• Fixed background session recaps being duplicated; the agent's own end-of-turn summary now shows as the recap line</p>
|
||||
<p>• Fixed opening a background session from claude agents leaving the previous screen painted behind it</p>
|
||||
<p>• Fixed Agent(type) deny rules and Agent(x,y) allowed-types restrictions not being enforced for named subagent spawns</p>
|
||||
<p>• Fixed Esc and Ctrl+C not responding while background agents are still running after the main turn ends</p>
|
||||
<p>• Fixed misaligned option numbers in permission prompts when the option text overflows</p>
|
||||
<p>• Fixed pressing x on a finished subagent in the agent panel not dismissing it</p>
|
||||
<p>• Fixed a misleading "MCP server disconnected" notice for intentionally retired tools when resuming older sessions</p>
|
||||
<p>• Fixed /plugin Installed showing a "more above" indicator when already scrolled to the top</p>
|
||||
<p>• Fixed ~~strikethrough~~ showing literal tildes in assistant messages instead of rendering as strikethrough</p>
|
||||
<p>• Fixed --tools allowing feature-gated tools to slip through before flags loaded on a cold first launch</p>
|
||||
<p>• Fixed background job status in claude agents showing a stale "needs input" message after replying</p>
|
||||
<p>• Fixed a dark-theme flash when opening a background session from claude agents on a light terminal</p>
|
||||
<p>• Fixed mouse-selected text staying highlighted after deleting it in claude agents</p>
|
||||
<p>• Fixed session cost not showing for usage-based Enterprise and Team subscribers</p>
|
||||
<p>• Fixed agent teams: teammates spawned via tmux/pane backends now inherit the leader's --effort level</p>
|
||||
<p>• Fixed Workflow agent({schema}) subagents looping forever on repeated schema validation failures instead of aborting after 5 attempts</p>
|
||||
<p>• Improved claude mcp get and claude mcp remove to suggest the closest configured server name on a typo and truncate long server lists</p>
|
||||
<p>• Improved memory: the agent is now reminded to compact its MEMORY.md index when nearing the size limit</p>
|
||||
<p>• Improved skill frontmatter: display-name, default-enabled, fallback, and metadata.* keys now accept kebab-case, snake_case, and camelCase</p>
|
||||
<p>• Improved malformed SKILL.md YAML frontmatter handling: loads the skill body with empty metadata instead of failing silently</p>
|
||||
<p>• Changed CLAUDE_CODE_MAX_RETRIES to cap at 15; for unattended sessions, use CLAUDE_CODE_RETRY_WATCHDOG instead</p>
|
||||
<p>• 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</p>
|
||||
<p>• Changed /review &lt;pr&gt; to use the same review engine as /code-review medium</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.185</id>
|
||||
<title>Claude Code v2.1.185</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.185"/>
|
||||
<updated>2026-06-20T20:59:12Z</updated>
|
||||
<content type="html"><p>• 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</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.183</id>
|
||||
<title>Claude Code v2.1.183</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.183"/>
|
||||
<updated>2026-06-19T01:20:44Z</updated>
|
||||
<content type="html"><p>• Improved auto mode safety: destructive git commands (git reset --hard, git checkout -- ., git clean -fd, git stash drop) are now blocked when you didn't ask to discard local work, git commit --amend is blocked when the commit wasn't made by the agent this session, and terraform destroy/pulumi destroy/cdk destroy are blocked unless you asked for the specific stack</p>
|
||||
<p>• Added a warning when the requested model is deprecated or automatically updated to a newer model, shown on stderr in print mode (-p) and now also covering models set in agent frontmatter</p>
|
||||
<p>• Added attribution.sessionUrl setting to omit the claude.ai session link from commits and PRs in web and Remote Control sessions</p>
|
||||
<p>• Added /config --help to list all available shorthand keys for /config key=value</p>
|
||||
<p>• Changed /config toggle behavior: Enter and Space both change the selected setting, and Esc now saves and closes instead of reverting</p>
|
||||
<p>• Removed the startup "setup issues" line under the logo — run /doctor to see configuration issues or use --debug</p>
|
||||
<p>• Fixed thinking.disabled.display: Extra inputs are not permitted 400 errors on subagent spawns and session-title generation for affected configurations</p>
|
||||
<p>• Fixed WebSearch returning empty results in subagents</p>
|
||||
<p>• Fixed the terminal cursor being stranded above the prompt after navigating history in vim mode with the native cursor enabled</p>
|
||||
<p>• Fixed fullscreen TUI corruption (statusline mid-screen, duplicated spinner rows, merged text) in Windows Terminal under heavy nested-subagent load</p>
|
||||
<p>• Fixed turns silently completing with no visible output when the model returned only a thinking block; Claude now re-prompts once</p>
|
||||
<p>• Fixed user-level skills appearing multiple times in slash-command autocomplete when multiple plugins are enabled</p>
|
||||
<p>• Fixed MCP servers requiring authentication exposing auth-stub tools to the model in headless/SDK mode</p>
|
||||
<p>• Fixed tmux teammate panes failing to launch when the shell has slow rc-file initialization, and keystrokes typed during agent spawn leaking into the new tmux pane instead of the leader prompt</p>
|
||||
<p>• Fixed background tasks started by a teammate being killed when the teammate finishes a turn</p>
|
||||
<p>• Fixed scheduled task and webhook trigger deliveries being treated as keyboard input; they now classify as task notifications and can no longer approve a pending action or set the session title in auto mode</p>
|
||||
<p>• Fixed focus mode showing "Ran N PostToolUse hooks" timing lines under each response</p></content>
|
||||
</entry>
|
||||
</feed>
|
||||
|
||||
Reference in New Issue
Block a user