mirror of
https://github.com/anthropics/claude-code.git
synced 2026-08-18 05:23:35 +00:00
Compare commits
9 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
354757e5b2 | ||
|
|
ae58f7a0a2 | ||
|
|
0fa8c19d50 | ||
|
|
1f6015b5d5 | ||
|
|
be90077c6a | ||
|
|
9923819368 | ||
|
|
681a8be245 | ||
|
|
54cc51a08a | ||
|
|
d945a61bc6 |
@@ -68,7 +68,6 @@ for domain in \
|
||||
"registry.npmjs.org" \
|
||||
"api.anthropic.com" \
|
||||
"sentry.io" \
|
||||
"statsig.anthropic.com" \
|
||||
"statsig.com" \
|
||||
"marketplace.visualstudio.com" \
|
||||
"vscode.blob.core.windows.net" \
|
||||
|
||||
197
CHANGELOG.md
197
CHANGELOG.md
@@ -1,5 +1,202 @@
|
||||
# Changelog
|
||||
|
||||
## 2.1.234
|
||||
|
||||
- Added the optional `CLAUDE_CODE_PROJECT_DIR_NAME` environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory
|
||||
- Added the `selection:clear` keybinding action, so a key can be bound to clear an in-app text selection; also works in the agents view
|
||||
- Added a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states
|
||||
- Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off in `/config` ("Continue automatically at usage limit")
|
||||
- Claude is now told to use your account email only to identify you, and not to send it to unrelated services unless you ask
|
||||
- Security: remote file reads, session restore, CLAUDE.md includes, workflow scripts and file uploads now reject Windows NT-namespace (`\??\`) paths, hardening the remaining pre-approval file accesses against the NTLM credential-leak vector
|
||||
- Fixed auto mode in very long sessions repeatedly re-checking and denying sandboxed commands' network access after the conversation had been compacted
|
||||
- Fixed session-scoped permission answers (including denies) being dropped when answering background subagent tool permission prompts
|
||||
- Fixed a crash when an API response on the non-streaming fallback path (typically via third-party gateways) contained a thinking block missing its thinking field or a text block missing its text field
|
||||
- Fixed markdown rendering becoming extremely slow for some messages containing unusual Unicode sequences
|
||||
- Fixed `SendMessage` rejecting a recipient copied from `ListAgents` when the session name is at the 200-character cap or emoji-heavy
|
||||
- Fixed repository detection mis-reading the host of git remotes with unusual userinfo, producing links and repo-specific behavior for the wrong host
|
||||
- Fixed MCP diagnostics printing resolved secrets: scope-conflict warnings now show the configured `${VAR}` form, and connection-failure details show only the server origin
|
||||
- Fixed `strictKnownMarketplaces` allowlists accepting SCP-style git marketplace sources whose host differs from the one git would actually connect to
|
||||
- Fixed modal text such as the `/login` OAuth URL losing characters when copied in fullscreen
|
||||
- Fixed a `---` horizontal rule in rendered markdown running into the line after it
|
||||
- Fixed consecutive shell commands splitting into multiple "Ran 1 shell command" rows when todo/task updates were interleaved between them
|
||||
- Fixed dialogs like `/permissions` opened while a `!` shell command was running being dismissed when the command finished
|
||||
- Fixed a queued `!` shell command being sent to the model as plain text after pressing up-arrow to edit the queued input
|
||||
- Fixed queued messages reappearing in the prompt history while still queued, Esc while selecting a queued message no longer interrupts the turn, and `!` mode no longer sticks after a mid-turn submit
|
||||
- Fixed accepting the "Try the new fullscreen renderer?" prompt restarting the session without its permission mode (e.g. `--dangerously-skip-permissions`), tool allow/deny rules, model or effort flags
|
||||
- Fixed `/tui` dropping launch `--allowed-tools`/`--disallowed-tools` rules when it restarts; it now declines to switch, with the reason, when the session has restrictions a restart can't carry over
|
||||
- Fixed trust prompts omitting the repository-wide scope warning when the directory was first seen before the repository existed there
|
||||
- Fixed a case where an IDE diff tab closing during a permission re-prompt could answer the new prompt with the previous input
|
||||
- Fixed: files sent to the user during Remote Control sessions hosted by Claude Code Desktop or VS Code now upload, so they open on phone and web instead of showing an empty card
|
||||
- Fixed: after `/login` while `CLAUDE_CODE_OAUTH_TOKEN` is set, the stale-token reminder no longer leaks into Claude's automatically resumed turn — it now appears only to you
|
||||
- Fixed: permission previews now relay only to channel servers admitted by the inbound trust gate, and a server's explicit permission-capability opt-out is honored
|
||||
- Fixed: credential masking on relayed permission previews can no longer hide commands, paths, or destinations from the approver; oversized private-key blocks now redact under full-strength redaction
|
||||
- Fixed: provider API tokens that mask on permission previews now mask even when directly followed by shell delimiters
|
||||
- Fixed Claude Desktop inter-session messages being silently dropped by the recipient session when cross-session messaging read as disabled, which left the sender's query "thinking" for many minutes
|
||||
- Remote Control: signing this computer in to a different claude.ai account or organization now stops the running session within seconds and says why, instead of a misleading HTTP 404 hours later
|
||||
- Remote Control sessions started from Claude Code Desktop or VS Code now keep phones and claude.ai/code updated on the session's permission mode (and claude.ai/code on the model) as they change
|
||||
- Remote Control: effort picks made on a phone or on claude.ai/code now apply to terminal- and Desktop/VS Code-hosted sessions, and the session publishes its effort level to connected clients
|
||||
- `SendMessage` and `ListAgents` now say when your account's session list was too long to check completely, instead of treating unseen sessions as absent
|
||||
- Expired Anthropic profile credential now points you at `/login` when a claude.ai login would take precedence
|
||||
- Improved the transcript: your own prompts now render markdown (highlighted code blocks, inline code, lists) the same way replies do
|
||||
- Improved the "API returned an empty or malformed response" error to say what came back (content type, body kind, size, request ID) and why the original streaming request failed
|
||||
- Improved auto-generated session titles to read as short, specific names (e.g. "Login button bug") rather than sentences restating your request (e.g. "Fix the login button on mobile")
|
||||
- Reduced the context cost of loading the built-in `claude-api` skill from ~200k+ tokens to ~25k by loading reference docs on demand
|
||||
- `/permissions` can now be opened while Claude is working — rule changes apply to the rest of the current turn
|
||||
- `/add-dir <path>` can now be used while Claude is working; `/add-dir`, `/autocompact`, `/theme`, `/help`, `/config` and `/advisor` dialogs open mid-turn in the fullscreen TUI
|
||||
- `/goal` now clears itself with a notice when a turn dies on an unrecoverable error (e.g. revoked auth, an exhausted credit balance, or a context overflow) instead of staying armed
|
||||
- `/goal`: when background tasks keep a goal waiting for 30+ minutes, Claude now checks in on them instead of waiting indefinitely (set `CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0` to opt out)
|
||||
- `claude setup-token` now rejects unexpected extra arguments instead of silently ignoring them
|
||||
- Changed Esc in fullscreen mode to no longer clear a mouse text selection: it interrupts or dismisses as usual and the selection stays highlighted
|
||||
- Removed the redundant "Allowed by auto mode classifier" line that auto mode showed under every Agent tool call
|
||||
- Removed the "Default teammate model" setting from `/config`; agent-team teammates now use the leader's model unless the spawn names one
|
||||
- Dimmed the elapsed-time counter on the running tool header so it no longer competes with the bold counts
|
||||
- Background task notifications delivered between turns are now sent to the model inside `<system-reminder>` tags, matching mid-turn delivery
|
||||
- Mantle: skip the admin-pin availability probe at startup when a main-loop model is already picked
|
||||
- Windows: startup no longer stalls on repeated rename retries when `~/.claude.json` is read-only
|
||||
|
||||
## 2.1.233
|
||||
|
||||
- Added GitLab merge request URL support to the `--worktree` flag and the `claude agents` view (where MRs display as `!N`)
|
||||
- Added an opt-in `forward_user_identity` apps gateway setting on Anthropic upstreams that sends the signed-in user's identity as headers, so a proxy behind the gateway can attribute spend per user
|
||||
- Added opt-in memory cgroup support for Bash tool commands on Linux (`CLAUDE_CODE_TOOL_MEMORY_LIMIT`) so a runaway build can't stall the session
|
||||
- Added `CLAUDE_CODE_WEBFETCH_CACHE_TTL_MS` environment variable to configure the WebFetch session URL cache TTL (default unchanged: 15 minutes)
|
||||
- Fixed cloud sessions occasionally being marked as lost when the environment shut down while Claude was waiting on a permission prompt
|
||||
- Fixed MCP v2 connections endlessly reopening the subscriptions/listen stream against servers that terminate long-held streams on a fixed timeout (e.g. serverless hosts)
|
||||
- Fixed Notification hooks not firing for permission prompts when running under Claude Desktop or VS Code
|
||||
- Fixed idle sessions on Linux sometimes keeping one CPU core at 100% when sandboxing is enabled
|
||||
- Fixed bundled skill aliases like `/checkup` and `/review` reporting "Unknown command" in `-p` mode or with plugins/MCP loaded when a user or project skill shadows the bundled skill
|
||||
- Fixed skill/command argument substitution to prevent argument values from being re-expanded as template markers
|
||||
- Fixed Windows paths spelled with the NT `\??\` device prefix bypassing UNC path validation, closing an NTLM credential-leak vector
|
||||
- Improved `claude self-hosted-runner` session start time: the session branch is now created without rewriting the working tree, and two server round trips no longer block the agent's launch
|
||||
- Improved apps gateway error forwarding: 400/413 errors from Vertex, Foundry, and Claude Platform on AWS upstreams now carry the upstream's own message; fixes a bug with auto-compact on apps gateway
|
||||
- Improved `claude plugin validate` to check a bare `.claude/skills` directory, reporting SKILL.md files whose frontmatter fails to parse
|
||||
- Improved screen reader mode: the `/effort` selector renders as a numbered list with a typed-number prompt, and hint and dialog text is no longer clipped
|
||||
- Improved print mode diagnostics: a `[claude-code:unrecognized_model]` line is written to stderr when a request goes out for a model ID Claude Code doesn't recognize; map it with `modelOverrides` to silence
|
||||
- Changed the GitHub app setup tip to no longer appear in repositories whose origin remote is on gitlab.com or bitbucket.org; the enterprise marketplace tip now covers non-GitHub internal git hosts
|
||||
- Todo/task-tracking tools (TaskCreate/Get/Update/List, TodoWrite) are no longer available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and newer models; set `CLAUDE_CODE_ENABLE_TODO_TOOLS=1` to bring them back
|
||||
- Windows: fixed auto mode repeatedly stopping for manual approval on ordinary `cd <dir> && <command> > file` Bash commands (a 2.1.232 regression)
|
||||
- Reverted the 2.1.232 Bash permission changes for Cygwin-style symlinks on Windows and for input redirections (`< file`); a narrower version will return in a later release
|
||||
|
||||
## 2.1.232
|
||||
|
||||
- Subagent forking is now on by default: a `subagent_type: "fork"` subagent inherits the full conversation and prompt cache, and non-teammate agent spawns in interactive sessions now run in the background by default
|
||||
- Type `@` in the prompt to mention another Claude session by name; Claude then uses `SendMessage` to reach that session directly
|
||||
- `SendMessage` now delivers to a bare name that exactly matches one live session, instead of asking to confirm with a ref first
|
||||
- Interactive sessions on one machine now keep unique names: starting or renaming a session to a name another live session already uses gives it a `name-word-word` variant and tells you
|
||||
- Added `/config` rows for "Dialog expiry" and "Messages from your other sessions" (cross-session inbound accept/hold/refuse)
|
||||
- Added secret redaction for GitLab token families (`glrt-`, `gloas-`, `glptt-`, `glagent-`, `glimt-`, `glsoat-`, `glcbt-`, `glft-`, `glffct-`) and full redaction of routable `glpat-`/`gldt-` tokens; the `glab` CLI config store gets the same sandbox and credential-path protection as `gh`
|
||||
- Added GitLab support to plugin marketplaces: bare `gitlab.com` repo URLs (including nested subgroups) now clone like `github.com` URLs, and clone auth-failure hints name your actual git host
|
||||
- Settings: `additionalMarketplaces` and `allowedMarketplaces` are now accepted as friendlier aliases for `extraKnownMarketplaces` and `strictKnownMarketplaces`
|
||||
- Enterprise policy: a url-typed `blockedMarketplaces` entry for a bare repo URL keeps blocking that URL when the CLI classifies it as a git clone
|
||||
- Gateway: the `desktop:` overlay now accepts every released Desktop setting (was 11 hand-listed keys), validated at boot against Desktop's own schema; unknown or invalid keys fail boot
|
||||
- Gateway: empty `managed.policies[].match.groups`/`admin.admin_groups` entries and malformed `email_domain` values (empty, or containing `@`, whitespace, or commas) now fail at boot instead of silently matching no one or granting admin access
|
||||
- Fable 5 is offered as an advisor in `/advisor` again for organizations with Fable access, with usage-credits consent set up through `/model fable`
|
||||
- Fixed a PowerShell permission bypass where variable-writing parameters could silently overwrite `$PSDefaultParameterValues` and redirect later commands' file access
|
||||
- Fixed a Windows permission bypass where Git Bash followed Cygwin-style symlinks that path validation saw as regular files; writes through them now require permission approval
|
||||
- Fixed nested git repositories inheriting trust from a parent directory; each repository now requires its own trust confirmation
|
||||
- Fixed MCP connections hanging for the full 30-second connect timeout when a server fails to answer or sends a malformed reply to the protocol-version probe
|
||||
- Fixed Remote Control sessions hosted by a bridge inside a cloud session inheriting that session's transcript or credentials
|
||||
- Fixed Remote Control sessions started from Claude Desktop or an IDE appearing as a new claude.ai session each time the local session was resumed; they now reattach to the existing one
|
||||
- Fixed Remote Control sessions appearing unreachable to newly attached clients while idle
|
||||
- Fixed Remote Control bridge sessions not restoring conversation history when the session worker restarts
|
||||
- Remote Control: resuming a conversation whose session was deleted from claude.ai or the app now starts a replacement instead of failing with a message about your login (regressed in v2.1.227)
|
||||
- Fixed Cloud gateway `/login` exiting silently or leaving an unresponsive terminal after "Press Enter to continue" when managed settings failed to load; the reason is now shown
|
||||
- Fixed voice mode on native builds getting stuck on "listening…" when the voice service rejected the connection; the rejection is now shown immediately
|
||||
- Fixed mTLS client certificate rotation requiring a restart; Claude Code now reloads the rotated cert and key automatically on connection errors
|
||||
- Fixed malformed AWS or Vertex region values being used to build request URLs; they now fall back to the default region
|
||||
- Fixed stream idle timeout errors failing the request instead of recovering on Bedrock, Vertex, and gateway deployments
|
||||
- Fixed content-sized overlays containing truncated text rendering one column too wide, and start-truncated text collapsing to an ellipsis
|
||||
- Fixed a stray garbled character where a long shell-command or agent-description preview was cut off mid-emoji
|
||||
- Fixed a startup race that could silently unregister a plugin marketplace due to concurrent writes to `known_marketplaces.json`
|
||||
- Fixed `/update` and `/tui` refusing to restart while work that survives the relaunch was running
|
||||
- Fixed usage-limit guidance suggesting unavailable slash commands in SDK and remote sessions
|
||||
- Fixed the consent message for interactive `--advisor fable` launches, which told you to run `/model fable` in an interactive session that had just exited
|
||||
- Improved fullscreen streaming: long sessions stay responsive because the whole conversation is no longer re-normalized on every update
|
||||
- Improved the managed settings approval dialog: shows endpoint URLs, uses clearer wording for telemetry-only changes, skips routine OpenTelemetry options, and requires approval for server-managed sandbox binary overrides (`sandbox.bwrapPath`, `sandbox.socatPath`, `sandbox.ripgrep`)
|
||||
- `/feedback` and `/bug` now open immediately when invoked while Claude is responding, instead of waiting for the turn to finish
|
||||
- `/plugin install plugin@marketplace` now refreshes the marketplace first, so newly published plugins install without a manual marketplace update
|
||||
- `/code-review` at high, xhigh, and max effort now runs in a background agent like the other levels
|
||||
- Pasted and clipboard images are read without blocking the event loop
|
||||
- Remote Control now keeps reconnecting for about 30 minutes after a network blip and no longer drops after a few blips spread across an hour
|
||||
- Remote Control: resuming a conversation no longer silently takes Remote Control away from another Claude Code on the same machine that still has it; run `/remote-control` there to move it
|
||||
- Updated agent panel: completed subagents hide immediately with a `/tasks` footer hint, and the "↓ N more" overflow indicator moved left for visibility
|
||||
- Remote Control: the terminal now says whether a session was taken over by another device, ended from another app, or deleted, and stops suggesting a reconnect that would undo it
|
||||
- Bash input redirections (`< file`) are now permission-checked like their argument spellings on all platforms
|
||||
- Shortened the message shown when resuming a completed background agent
|
||||
- Cowork sessions no longer inline external @-imports from user-scope memory files
|
||||
- Hardened the auto-generated cross-session messaging socket directory on shared `/tmp`: a pre-planted symlink or another user's directory is now refused instead of used
|
||||
- Hardened the Linux filesystem sandbox against a protected-path bypass
|
||||
- Changed `sandbox.ripgrep` to be honored only from user, managed, and `--settings` settings; project settings can no longer override the sandbox's ripgrep binary
|
||||
- Removed the startup tip suggesting you create custom subagents, and the matching nudge in the `/powerup` tour
|
||||
|
||||
## 2.1.231
|
||||
|
||||
- Fixed MCP OAuth sign-in failing with a redirect URI mismatch for servers that use a pre-registered OAuth client, such as Slack
|
||||
|
||||
## 2.1.229
|
||||
|
||||
- Documented `claude remote-control --continue` for resuming the most recent Remote Control session
|
||||
- Added server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-environment behavior
|
||||
- Added SSE keepalive pings to gateway streaming responses during long thinking pauses, preventing idle-timeout disconnects on Vertex and Bedrock upstreams
|
||||
- Added plugin marketplace `command` sources: a local command (e.g. an IDE) prints the plugin directory, which is re-resolved each session and applied without a restart; `mode: "link"` uses it in place
|
||||
- `ListAgents` now marks disconnected Remote Control sessions as `offline` and labels your cloud sessions as `cloud`
|
||||
- Fixed long responses partly disappearing while streaming and being printed twice in the terminal
|
||||
- Fixed a crash to the error screen (including on `--resume` of the affected session) when a tool call had a non-string `glob`, `file_path`, or `command` value
|
||||
- Fixed a RangeError crash when a progress bar or markdown table rendered in a very narrow terminal window (could also crash `claude --continue`/`--resume` at startup)
|
||||
- Fixed a crash on Windows when a tool call or message referenced a file by an extended-length (`\\?\`) or UNC path
|
||||
- Fixed auto mode failing on every tool call for users who disable the attribution header via `CLAUDE_CODE_ATTRIBUTION_HEADER` (direct Anthropic API connections)
|
||||
- Fixed `/model` rejecting Sonnet/Opus 1M for claude.ai subscribers using a custom `ANTHROPIC_BASE_URL` gateway
|
||||
- Fixed MCP OAuth with strict authorization servers by using `127.0.0.1` instead of `localhost` in the redirect URI
|
||||
- Fixed Remote Control clients showing a stuck working spinner after a slash command typed in the laptop terminal
|
||||
- Fixed the Claude Code Review workflow generated by `/install-github-app` completing without posting its review on the pull request
|
||||
- Fixed multi-second UI stalls after editing a file with thousands of IDE diagnostics while the IDE extension is connected
|
||||
- Fixed one-shot `claude plugin` commands leaving a stray liveness file that could prevent cleanup of outdated plugin versions
|
||||
- Fixed dynamic workflows inside CPU-limited containers using the host machine's core count instead of the container's CPU limit
|
||||
- Fixed a file-watcher handle leak after atomic file replacements, and an uncaught error on Windows when the scheduled-tasks watcher failed on a network or virtual filesystem
|
||||
- Fixed SDK and `--input-format stream-json` sessions getting a 400 API error when a whitespace-only message was submitted
|
||||
- Fixed conversations whose messages alone exceed the API's 32 MB request limit retrying compaction when no images or documents can be stripped; they now fail once with a clear message
|
||||
- Fixed OpenTelemetry export from Claude Desktop sessions being rejected by the Desktop-managed gateway when that gateway is also the telemetry endpoint
|
||||
- Fixed self-hosted runner and other remote sessions exiting at startup when `managed-mcp.json` is deployed and the server delivers MCP servers; those servers are now skipped with a warning
|
||||
- Fixed self-hosted runner repository preparation hanging on a Git Credential Manager prompt; git now fails fast when credentials are missing
|
||||
- Improved workflow fan-outs to stagger same-prefix sibling agents so subsequent agents read the cached prompt prefix instead of re-paying it (`CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS=0` disables)
|
||||
- Improved "prompt is too long" errors to explain why automatic compaction could not recover instead of only suggesting `/compact`
|
||||
- Improved sandbox: IPv6 literals in network domain lists are now bracketed (`[::1]:443`), and ambiguous spellings are enforced fail-closed and flagged by `/doctor`
|
||||
- Updated `/login` to repeat the `CLAUDE_CODE_OAUTH_TOKEN` override warning after a successful login
|
||||
- Changed `/commit-push-pr` so git/gh commands with dangerous flags (`--force`, `--amend`, `--no-verify`, etc.) are no longer auto-approved
|
||||
- Changed self-hosted runner Windows startup to require an explicit `--base-dir`; there is no default checkout directory on Windows
|
||||
- [VSCode] "Report a problem" and `/bug` now open the built-in feedback dialog instead of a retired survey link
|
||||
- [VSCode] Made the `/btw` side-question panel resizable by dragging its boundary, in both side-docked and stacked layouts
|
||||
- [VSCode] Added session groups in the sidebar — right-click to create, rename, or delete; Cmd/Ctrl- or Shift-click to move several sessions at once
|
||||
|
||||
## 2.1.228
|
||||
|
||||
- Fixed interactive sessions that could stop redrawing entirely, while the process kept running, after a rare internal layout error
|
||||
- Fixed `git` / Git Bash not being found on Windows when Claude Code is launched from a parent folder of the git installation
|
||||
- Fixed `/tui` reverting the session to an earlier model when `/model` had been changed since the last response
|
||||
- Fixed cross-session messaging sometimes starting without an inbox in the first session after install or upgrade
|
||||
- Fixed Remote Control `/resume` while connected leaking the resumed conversation's title or history into the connected session
|
||||
- Fixed `claude self-hosted-runner` sessions failing on every fresh runner when the `checkout` hook fails for a repository the session doesn't push to; that repository is now skipped with a warning
|
||||
- Fixed self-hosted runners ending sessions in the gap between a background task finishing and the follow-up turn starting
|
||||
- Fixed session cleanup deleting contents inside a project's memory folder
|
||||
- Fixed background plugin-cache cleanup deleting a plugin's cache when its only version is a symlinked development checkout
|
||||
- Fixed a settings-merge issue where a marketplace entry redefined in a higher-precedence settings tier could inherit another tier's custom headers; marketplace entries now merge as whole entries
|
||||
- Fixed the deferred-tools reminder occasionally being sent to the model twice after a skill invocation
|
||||
- Hardened skills synced from claude.ai: they no longer shadow local commands or MCP prompts, their descriptions are sanitized and labeled, and on your machine their bodies don't run `!` commands or expand `@` files
|
||||
- Improved cross-session messages: the sender and body now display inline instead of a collapsed line, and messages to Remote Control sessions on other machines show your Remote Control session name as the sender
|
||||
- Improved Vertex AI credential handling: expired or missing Google Cloud credentials now fail within seconds instead of retrying for minutes
|
||||
- Improved compaction progress: the retry countdown and stall hint now appear during compaction instead of only a progress bar
|
||||
- Updated terminal title busy-spinner glyphs to reduce tab-bar jitter on some terminals
|
||||
- Changed the Write tool so newer models can overwrite an existing file they haven't read this session, matching the Edit tool's rules; older models still require the read first
|
||||
- Removed the outdated note about auto mode sessions costing slightly more from the first-use notice for Pro, Max, and Team plans
|
||||
|
||||
## 2.1.227
|
||||
|
||||
- Fixed feature flags being evaluated without the user's subscription tier when a session started with an expired login token, which could wrongly prompt Max plan users to enable usage credits for Fable
|
||||
- Fixed every Bash command failing under `claude-code-action` with `allowed_non_write_users` on GitHub-hosted runners
|
||||
- Fixed `/tui` bringing back a conversation that had been rewound to before its first message
|
||||
- Improved slash-command menu: blue now marks only the selected row, matched characters are bolded instead of recolored, and emoji or accented names keep their glyphs
|
||||
- Improved performance: fewer event-loop stalls on file-not-found suggestions and at-mention size checks
|
||||
|
||||
## 2.1.226
|
||||
|
||||
- Bug fixes and reliability improvements
|
||||
|
||||
478
feed.xml
478
feed.xml
@@ -6,7 +6,225 @@
|
||||
<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>2026-08-08T02:47:59Z</updated>
|
||||
<updated>2026-08-17T20:20:52Z</updated>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.234</id>
|
||||
<title>Claude Code v2.1.234</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.234"/>
|
||||
<updated>2026-08-17T20:20:52Z</updated>
|
||||
<content type="html"><p>• Added the optional CLAUDE_CODE_PROJECT_DIR_NAME environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory</p>
|
||||
<p>• Added the selection:clear keybinding action, so a key can be bound to clear an in-app text selection; also works in the agents view</p>
|
||||
<p>• Added a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states</p>
|
||||
<p>• Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off in /config ("Continue automatically at usage limit")</p>
|
||||
<p>• Claude is now told to use your account email only to identify you, and not to send it to unrelated services unless you ask</p>
|
||||
<p>• Security: remote file reads, session restore, CLAUDE.md includes, workflow scripts and file uploads now reject Windows NT-namespace (\??\) paths, hardening the remaining pre-approval file accesses against the NTLM credential-leak vector</p>
|
||||
<p>• Fixed auto mode in very long sessions repeatedly re-checking and denying sandboxed commands' network access after the conversation had been compacted</p>
|
||||
<p>• Fixed session-scoped permission answers (including denies) being dropped when answering background subagent tool permission prompts</p>
|
||||
<p>• Fixed a crash when an API response on the non-streaming fallback path (typically via third-party gateways) contained a thinking block missing its thinking field or a text block missing its text field</p>
|
||||
<p>• Fixed markdown rendering becoming extremely slow for some messages containing unusual Unicode sequences</p>
|
||||
<p>• Fixed SendMessage rejecting a recipient copied from ListAgents when the session name is at the 200-character cap or emoji-heavy</p>
|
||||
<p>• Fixed repository detection mis-reading the host of git remotes with unusual userinfo, producing links and repo-specific behavior for the wrong host</p>
|
||||
<p>• Fixed MCP diagnostics printing resolved secrets: scope-conflict warnings now show the configured ${VAR} form, and connection-failure details show only the server origin</p>
|
||||
<p>• Fixed strictKnownMarketplaces allowlists accepting SCP-style git marketplace sources whose host differs from the one git would actually connect to</p>
|
||||
<p>• Fixed modal text such as the /login OAuth URL losing characters when copied in fullscreen</p>
|
||||
<p>• Fixed a --- horizontal rule in rendered markdown running into the line after it</p>
|
||||
<p>• Fixed consecutive shell commands splitting into multiple "Ran 1 shell command" rows when todo/task updates were interleaved between them</p>
|
||||
<p>• Fixed dialogs like /permissions opened while a ! shell command was running being dismissed when the command finished</p>
|
||||
<p>• Fixed a queued ! shell command being sent to the model as plain text after pressing up-arrow to edit the queued input</p>
|
||||
<p>• Fixed queued messages reappearing in the prompt history while still queued, Esc while selecting a queued message no longer interrupts the turn, and ! mode no longer sticks after a mid-turn submit</p>
|
||||
<p>• Fixed accepting the "Try the new fullscreen renderer?" prompt restarting the session without its permission mode (e.g. --dangerously-skip-permissions), tool allow/deny rules, model or effort flags</p>
|
||||
<p>• Fixed /tui dropping launch --allowed-tools/--disallowed-tools rules when it restarts; it now declines to switch, with the reason, when the session has restrictions a restart can't carry over</p>
|
||||
<p>• Fixed trust prompts omitting the repository-wide scope warning when the directory was first seen before the repository existed there</p>
|
||||
<p>• Fixed a case where an IDE diff tab closing during a permission re-prompt could answer the new prompt with the previous input</p>
|
||||
<p>• Fixed: files sent to the user during Remote Control sessions hosted by Claude Code Desktop or VS Code now upload, so they open on phone and web instead of showing an empty card</p>
|
||||
<p>• Fixed: after /login while CLAUDE_CODE_OAUTH_TOKEN is set, the stale-token reminder no longer leaks into Claude's automatically resumed turn — it now appears only to you</p>
|
||||
<p>• Fixed: permission previews now relay only to channel servers admitted by the inbound trust gate, and a server's explicit permission-capability opt-out is honored</p>
|
||||
<p>• Fixed: credential masking on relayed permission previews can no longer hide commands, paths, or destinations from the approver; oversized private-key blocks now redact under full-strength redaction</p>
|
||||
<p>• Fixed: provider API tokens that mask on permission previews now mask even when directly followed by shell delimiters</p>
|
||||
<p>• Fixed Claude Desktop inter-session messages being silently dropped by the recipient session when cross-session messaging read as disabled, which left the sender's query "thinking" for many minutes</p>
|
||||
<p>• Remote Control: signing this computer in to a different claude.ai account or organization now stops the running session within seconds and says why, instead of a misleading HTTP 404 hours later</p>
|
||||
<p>• Remote Control sessions started from Claude Code Desktop or VS Code now keep phones and claude.ai/code updated on the session's permission mode (and claude.ai/code on the model) as they change</p>
|
||||
<p>• Remote Control: effort picks made on a phone or on claude.ai/code now apply to terminal- and Desktop/VS Code-hosted sessions, and the session publishes its effort level to connected clients</p>
|
||||
<p>• SendMessage and ListAgents now say when your account's session list was too long to check completely, instead of treating unseen sessions as absent</p>
|
||||
<p>• Expired Anthropic profile credential now points you at /login when a claude.ai login would take precedence</p>
|
||||
<p>• Improved the transcript: your own prompts now render markdown (highlighted code blocks, inline code, lists) the same way replies do</p>
|
||||
<p>• Improved the "API returned an empty or malformed response" error to say what came back (content type, body kind, size, request ID) and why the original streaming request failed</p>
|
||||
<p>• Improved auto-generated session titles to read as short, specific names (e.g. "Login button bug") rather than sentences restating your request (e.g. "Fix the login button on mobile")</p>
|
||||
<p>• Reduced the context cost of loading the built-in claude-api skill from ~200k+ tokens to ~25k by loading reference docs on demand</p>
|
||||
<p>• /permissions can now be opened while Claude is working — rule changes apply to the rest of the current turn</p>
|
||||
<p>• /add-dir &lt;path&gt; can now be used while Claude is working; /add-dir, /autocompact, /theme, /help, /config and /advisor dialogs open mid-turn in the fullscreen TUI</p>
|
||||
<p>• /goal now clears itself with a notice when a turn dies on an unrecoverable error (e.g. revoked auth, an exhausted credit balance, or a context overflow) instead of staying armed</p>
|
||||
<p>• /goal: when background tasks keep a goal waiting for 30+ minutes, Claude now checks in on them instead of waiting indefinitely (set CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0 to opt out)</p>
|
||||
<p>• claude setup-token now rejects unexpected extra arguments instead of silently ignoring them</p>
|
||||
<p>• Changed Esc in fullscreen mode to no longer clear a mouse text selection: it interrupts or dismisses as usual and the selection stays highlighted</p>
|
||||
<p>• Removed the redundant "Allowed by auto mode classifier" line that auto mode showed under every Agent tool call</p>
|
||||
<p>• Removed the "Default teammate model" setting from /config; agent-team teammates now use the leader's model unless the spawn names one</p>
|
||||
<p>• Dimmed the elapsed-time counter on the running tool header so it no longer competes with the bold counts</p>
|
||||
<p>• Background task notifications delivered between turns are now sent to the model inside &lt;system-reminder&gt; tags, matching mid-turn delivery</p>
|
||||
<p>• Mantle: skip the admin-pin availability probe at startup when a main-loop model is already picked</p>
|
||||
<p>• Windows: startup no longer stalls on repeated rename retries when ~/.claude.json is read-only</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.233</id>
|
||||
<title>Claude Code v2.1.233</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.233"/>
|
||||
<updated>2026-08-14T22:20:50Z</updated>
|
||||
<content type="html"><p>• Added GitLab merge request URL support to the --worktree flag and the claude agents view (where MRs display as !N)</p>
|
||||
<p>• Added an opt-in forward_user_identity apps gateway setting on Anthropic upstreams that sends the signed-in user's identity as headers, so a proxy behind the gateway can attribute spend per user</p>
|
||||
<p>• Added opt-in memory cgroup support for Bash tool commands on Linux (CLAUDE_CODE_TOOL_MEMORY_LIMIT) so a runaway build can't stall the session</p>
|
||||
<p>• Added CLAUDE_CODE_WEBFETCH_CACHE_TTL_MS environment variable to configure the WebFetch session URL cache TTL (default unchanged: 15 minutes)</p>
|
||||
<p>• Fixed cloud sessions occasionally being marked as lost when the environment shut down while Claude was waiting on a permission prompt</p>
|
||||
<p>• Fixed MCP v2 connections endlessly reopening the subscriptions/listen stream against servers that terminate long-held streams on a fixed timeout (e.g. serverless hosts)</p>
|
||||
<p>• Fixed Notification hooks not firing for permission prompts when running under Claude Desktop or VS Code</p>
|
||||
<p>• Fixed idle sessions on Linux sometimes keeping one CPU core at 100% when sandboxing is enabled</p>
|
||||
<p>• Fixed bundled skill aliases like /checkup and /review reporting "Unknown command" in -p mode or with plugins/MCP loaded when a user or project skill shadows the bundled skill</p>
|
||||
<p>• Fixed skill/command argument substitution to prevent argument values from being re-expanded as template markers</p>
|
||||
<p>• Fixed Windows paths spelled with the NT \??\ device prefix bypassing UNC path validation, closing an NTLM credential-leak vector</p>
|
||||
<p>• Improved claude self-hosted-runner session start time: the session branch is now created without rewriting the working tree, and two server round trips no longer block the agent's launch</p>
|
||||
<p>• Improved apps gateway error forwarding: 400/413 errors from Vertex, Foundry, and Claude Platform on AWS upstreams now carry the upstream's own message; fixes a bug with auto-compact on apps gateway</p>
|
||||
<p>• Improved claude plugin validate to check a bare .claude/skills directory, reporting SKILL.md files whose frontmatter fails to parse</p>
|
||||
<p>• Improved screen reader mode: the /effort selector renders as a numbered list with a typed-number prompt, and hint and dialog text is no longer clipped</p>
|
||||
<p>• Improved print mode diagnostics: a [claude-code:unrecognized_model] line is written to stderr when a request goes out for a model ID Claude Code doesn't recognize; map it with modelOverrides to silence</p>
|
||||
<p>• Changed the GitHub app setup tip to no longer appear in repositories whose origin remote is on gitlab.com or bitbucket.org; the enterprise marketplace tip now covers non-GitHub internal git hosts</p>
|
||||
<p>• Todo/task-tracking tools (TaskCreate/Get/Update/List, TodoWrite) are no longer available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and newer models; set CLAUDE_CODE_ENABLE_TODO_TOOLS=1 to bring them back</p>
|
||||
<p>• Windows: fixed auto mode repeatedly stopping for manual approval on ordinary cd &lt;dir&gt; &amp;&amp; &lt;command&gt; &gt; file Bash commands (a 2.1.232 regression)</p>
|
||||
<p>• Reverted the 2.1.232 Bash permission changes for Cygwin-style symlinks on Windows and for input redirections (&lt; file); a narrower version will return in a later release</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.232</id>
|
||||
<title>Claude Code v2.1.232</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.232"/>
|
||||
<updated>2026-08-13T23:29:53Z</updated>
|
||||
<content type="html"><p>• Subagent forking is now on by default: a subagent_type: "fork" subagent inherits the full conversation and prompt cache, and non-teammate agent spawns in interactive sessions now run in the background by default</p>
|
||||
<p>• Type @ in the prompt to mention another Claude session by name; Claude then uses SendMessage to reach that session directly</p>
|
||||
<p>• SendMessage now delivers to a bare name that exactly matches one live session, instead of asking to confirm with a ref first</p>
|
||||
<p>• Interactive sessions on one machine now keep unique names: starting or renaming a session to a name another live session already uses gives it a name-word-word variant and tells you</p>
|
||||
<p>• Added /config rows for "Dialog expiry" and "Messages from your other sessions" (cross-session inbound accept/hold/refuse)</p>
|
||||
<p>• Added secret redaction for GitLab token families (glrt-, gloas-, glptt-, glagent-, glimt-, glsoat-, glcbt-, glft-, glffct-) and full redaction of routable glpat-/gldt- tokens; the glab CLI config store gets the same sandbox and credential-path protection as gh</p>
|
||||
<p>• Added GitLab support to plugin marketplaces: bare gitlab.com repo URLs (including nested subgroups) now clone like github.com URLs, and clone auth-failure hints name your actual git host</p>
|
||||
<p>• Settings: additionalMarketplaces and allowedMarketplaces are now accepted as friendlier aliases for extraKnownMarketplaces and strictKnownMarketplaces</p>
|
||||
<p>• Enterprise policy: a url-typed blockedMarketplaces entry for a bare repo URL keeps blocking that URL when the CLI classifies it as a git clone</p>
|
||||
<p>• Gateway: the desktop: overlay now accepts every released Desktop setting (was 11 hand-listed keys), validated at boot against Desktop's own schema; unknown or invalid keys fail boot</p>
|
||||
<p>• Gateway: empty managed.policies[].match.groups/admin.admin_groups entries and malformed email_domain values (empty, or containing @, whitespace, or commas) now fail at boot instead of silently matching no one or granting admin access</p>
|
||||
<p>• Fable 5 is offered as an advisor in /advisor again for organizations with Fable access, with usage-credits consent set up through /model fable</p>
|
||||
<p>• Fixed a PowerShell permission bypass where variable-writing parameters could silently overwrite $PSDefaultParameterValues and redirect later commands' file access</p>
|
||||
<p>• Fixed a Windows permission bypass where Git Bash followed Cygwin-style symlinks that path validation saw as regular files; writes through them now require permission approval</p>
|
||||
<p>• Fixed nested git repositories inheriting trust from a parent directory; each repository now requires its own trust confirmation</p>
|
||||
<p>• Fixed MCP connections hanging for the full 30-second connect timeout when a server fails to answer or sends a malformed reply to the protocol-version probe</p>
|
||||
<p>• Fixed Remote Control sessions hosted by a bridge inside a cloud session inheriting that session's transcript or credentials</p>
|
||||
<p>• Fixed Remote Control sessions started from Claude Desktop or an IDE appearing as a new claude.ai session each time the local session was resumed; they now reattach to the existing one</p>
|
||||
<p>• Fixed Remote Control sessions appearing unreachable to newly attached clients while idle</p>
|
||||
<p>• Fixed Remote Control bridge sessions not restoring conversation history when the session worker restarts</p>
|
||||
<p>• Remote Control: resuming a conversation whose session was deleted from claude.ai or the app now starts a replacement instead of failing with a message about your login (regressed in v2.1.227)</p>
|
||||
<p>• Fixed Cloud gateway /login exiting silently or leaving an unresponsive terminal after "Press Enter to continue" when managed settings failed to load; the reason is now shown</p>
|
||||
<p>• Fixed voice mode on native builds getting stuck on "listening…" when the voice service rejected the connection; the rejection is now shown immediately</p>
|
||||
<p>• Fixed mTLS client certificate rotation requiring a restart; Claude Code now reloads the rotated cert and key automatically on connection errors</p>
|
||||
<p>• Fixed malformed AWS or Vertex region values being used to build request URLs; they now fall back to the default region</p>
|
||||
<p>• Fixed stream idle timeout errors failing the request instead of recovering on Bedrock, Vertex, and gateway deployments</p>
|
||||
<p>• Fixed content-sized overlays containing truncated text rendering one column too wide, and start-truncated text collapsing to an ellipsis</p>
|
||||
<p>• Fixed a stray garbled character where a long shell-command or agent-description preview was cut off mid-emoji</p>
|
||||
<p>• Fixed a startup race that could silently unregister a plugin marketplace due to concurrent writes to known_marketplaces.json</p>
|
||||
<p>• Fixed /update and /tui refusing to restart while work that survives the relaunch was running</p>
|
||||
<p>• Fixed usage-limit guidance suggesting unavailable slash commands in SDK and remote sessions</p>
|
||||
<p>• Fixed the consent message for interactive --advisor fable launches, which told you to run /model fable in an interactive session that had just exited</p>
|
||||
<p>• Improved fullscreen streaming: long sessions stay responsive because the whole conversation is no longer re-normalized on every update</p>
|
||||
<p>• Improved the managed settings approval dialog: shows endpoint URLs, uses clearer wording for telemetry-only changes, skips routine OpenTelemetry options, and requires approval for server-managed sandbox binary overrides (sandbox.bwrapPath, sandbox.socatPath, sandbox.ripgrep)</p>
|
||||
<p>• /feedback and /bug now open immediately when invoked while Claude is responding, instead of waiting for the turn to finish</p>
|
||||
<p>• /plugin install plugin@marketplace now refreshes the marketplace first, so newly published plugins install without a manual marketplace update</p>
|
||||
<p>• /code-review at high, xhigh, and max effort now runs in a background agent like the other levels</p>
|
||||
<p>• Pasted and clipboard images are read without blocking the event loop</p>
|
||||
<p>• Remote Control now keeps reconnecting for about 30 minutes after a network blip and no longer drops after a few blips spread across an hour</p>
|
||||
<p>• Remote Control: resuming a conversation no longer silently takes Remote Control away from another Claude Code on the same machine that still has it; run /remote-control there to move it</p>
|
||||
<p>• Updated agent panel: completed subagents hide immediately with a /tasks footer hint, and the "↓ N more" overflow indicator moved left for visibility</p>
|
||||
<p>• Remote Control: the terminal now says whether a session was taken over by another device, ended from another app, or deleted, and stops suggesting a reconnect that would undo it</p>
|
||||
<p>• Bash input redirections (&lt; file) are now permission-checked like their argument spellings on all platforms</p>
|
||||
<p>• Shortened the message shown when resuming a completed background agent</p>
|
||||
<p>• Cowork sessions no longer inline external @-imports from user-scope memory files</p>
|
||||
<p>• Hardened the auto-generated cross-session messaging socket directory on shared /tmp: a pre-planted symlink or another user's directory is now refused instead of used</p>
|
||||
<p>• Hardened the Linux filesystem sandbox against a protected-path bypass</p>
|
||||
<p>• Changed sandbox.ripgrep to be honored only from user, managed, and --settings settings; project settings can no longer override the sandbox's ripgrep binary</p>
|
||||
<p>• Removed the startup tip suggesting you create custom subagents, and the matching nudge in the /powerup tour</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.231</id>
|
||||
<title>Claude Code v2.1.231</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.231"/>
|
||||
<updated>2026-08-13T08:38:44Z</updated>
|
||||
<content type="html"><p>• Fixed MCP OAuth sign-in failing with a redirect URI mismatch for servers that use a pre-registered OAuth client, such as Slack</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.229</id>
|
||||
<title>Claude Code v2.1.229</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.229"/>
|
||||
<updated>2026-08-12T20:56:14Z</updated>
|
||||
<content type="html"><p>• Documented claude remote-control --continue for resuming the most recent Remote Control session</p>
|
||||
<p>• Added server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-environment behavior</p>
|
||||
<p>• Added SSE keepalive pings to gateway streaming responses during long thinking pauses, preventing idle-timeout disconnects on Vertex and Bedrock upstreams</p>
|
||||
<p>• Added plugin marketplace command sources: a local command (e.g. an IDE) prints the plugin directory, which is re-resolved each session and applied without a restart; mode: "link" uses it in place</p>
|
||||
<p>• ListAgents now marks disconnected Remote Control sessions as offline and labels your cloud sessions as cloud</p>
|
||||
<p>• Fixed long responses partly disappearing while streaming and being printed twice in the terminal</p>
|
||||
<p>• Fixed a crash to the error screen (including on --resume of the affected session) when a tool call had a non-string glob, file_path, or command value</p>
|
||||
<p>• Fixed a RangeError crash when a progress bar or markdown table rendered in a very narrow terminal window (could also crash claude --continue/--resume at startup)</p>
|
||||
<p>• Fixed a crash on Windows when a tool call or message referenced a file by an extended-length (\\?\) or UNC path</p>
|
||||
<p>• Fixed auto mode failing on every tool call for users who disable the attribution header via CLAUDE_CODE_ATTRIBUTION_HEADER (direct Anthropic API connections)</p>
|
||||
<p>• Fixed /model rejecting Sonnet/Opus 1M for claude.ai subscribers using a custom ANTHROPIC_BASE_URL gateway</p>
|
||||
<p>• Fixed MCP OAuth with strict authorization servers by using 127.0.0.1 instead of localhost in the redirect URI</p>
|
||||
<p>• Fixed Remote Control clients showing a stuck working spinner after a slash command typed in the laptop terminal</p>
|
||||
<p>• Fixed the Claude Code Review workflow generated by /install-github-app completing without posting its review on the pull request</p>
|
||||
<p>• Fixed multi-second UI stalls after editing a file with thousands of IDE diagnostics while the IDE extension is connected</p>
|
||||
<p>• Fixed one-shot claude plugin commands leaving a stray liveness file that could prevent cleanup of outdated plugin versions</p>
|
||||
<p>• Fixed dynamic workflows inside CPU-limited containers using the host machine's core count instead of the container's CPU limit</p>
|
||||
<p>• Fixed a file-watcher handle leak after atomic file replacements, and an uncaught error on Windows when the scheduled-tasks watcher failed on a network or virtual filesystem</p>
|
||||
<p>• Fixed SDK and --input-format stream-json sessions getting a 400 API error when a whitespace-only message was submitted</p>
|
||||
<p>• Fixed conversations whose messages alone exceed the API's 32 MB request limit retrying compaction when no images or documents can be stripped; they now fail once with a clear message</p>
|
||||
<p>• Fixed OpenTelemetry export from Claude Desktop sessions being rejected by the Desktop-managed gateway when that gateway is also the telemetry endpoint</p>
|
||||
<p>• Fixed self-hosted runner and other remote sessions exiting at startup when managed-mcp.json is deployed and the server delivers MCP servers; those servers are now skipped with a warning</p>
|
||||
<p>• Fixed self-hosted runner repository preparation hanging on a Git Credential Manager prompt; git now fails fast when credentials are missing</p>
|
||||
<p>• Improved workflow fan-outs to stagger same-prefix sibling agents so subsequent agents read the cached prompt prefix instead of re-paying it (CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS=0 disables)</p>
|
||||
<p>• Improved "prompt is too long" errors to explain why automatic compaction could not recover instead of only suggesting /compact</p>
|
||||
<p>• Improved sandbox: IPv6 literals in network domain lists are now bracketed ([::1]:443), and ambiguous spellings are enforced fail-closed and flagged by /doctor</p>
|
||||
<p>• Updated /login to repeat the CLAUDE_CODE_OAUTH_TOKEN override warning after a successful login</p>
|
||||
<p>• Changed /commit-push-pr so git/gh commands with dangerous flags (--force, --amend, --no-verify, etc.) are no longer auto-approved</p>
|
||||
<p>• Changed self-hosted runner Windows startup to require an explicit --base-dir; there is no default checkout directory on Windows</p>
|
||||
<p>• [VSCode] "Report a problem" and /bug now open the built-in feedback dialog instead of a retired survey link</p>
|
||||
<p>• [VSCode] Made the /btw side-question panel resizable by dragging its boundary, in both side-docked and stacked layouts</p>
|
||||
<p>• [VSCode] Added session groups in the sidebar — right-click to create, rename, or delete; Cmd/Ctrl- or Shift-click to move several sessions at once</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.228</id>
|
||||
<title>Claude Code v2.1.228</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.228"/>
|
||||
<updated>2026-08-11T19:50:50Z</updated>
|
||||
<content type="html"><p>• Fixed interactive sessions that could stop redrawing entirely, while the process kept running, after a rare internal layout error</p>
|
||||
<p>• Fixed git / Git Bash not being found on Windows when Claude Code is launched from a parent folder of the git installation</p>
|
||||
<p>• Fixed /tui reverting the session to an earlier model when /model had been changed since the last response</p>
|
||||
<p>• Fixed cross-session messaging sometimes starting without an inbox in the first session after install or upgrade</p>
|
||||
<p>• Fixed Remote Control /resume while connected leaking the resumed conversation's title or history into the connected session</p>
|
||||
<p>• Fixed claude self-hosted-runner sessions failing on every fresh runner when the checkout hook fails for a repository the session doesn't push to; that repository is now skipped with a warning</p>
|
||||
<p>• Fixed self-hosted runners ending sessions in the gap between a background task finishing and the follow-up turn starting</p>
|
||||
<p>• Fixed session cleanup deleting contents inside a project's memory folder</p>
|
||||
<p>• Fixed background plugin-cache cleanup deleting a plugin's cache when its only version is a symlinked development checkout</p>
|
||||
<p>• Fixed a settings-merge issue where a marketplace entry redefined in a higher-precedence settings tier could inherit another tier's custom headers; marketplace entries now merge as whole entries</p>
|
||||
<p>• Fixed the deferred-tools reminder occasionally being sent to the model twice after a skill invocation</p>
|
||||
<p>• Hardened skills synced from claude.ai: they no longer shadow local commands or MCP prompts, their descriptions are sanitized and labeled, and on your machine their bodies don't run ! commands or expand @ files</p>
|
||||
<p>• Improved cross-session messages: the sender and body now display inline instead of a collapsed line, and messages to Remote Control sessions on other machines show your Remote Control session name as the sender</p>
|
||||
<p>• Improved Vertex AI credential handling: expired or missing Google Cloud credentials now fail within seconds instead of retrying for minutes</p>
|
||||
<p>• Improved compaction progress: the retry countdown and stall hint now appear during compaction instead of only a progress bar</p>
|
||||
<p>• Updated terminal title busy-spinner glyphs to reduce tab-bar jitter on some terminals</p>
|
||||
<p>• Changed the Write tool so newer models can overwrite an existing file they haven't read this session, matching the Edit tool's rules; older models still require the read first</p>
|
||||
<p>• Removed the outdated note about auto mode sessions costing slightly more from the first-use notice for Pro, Max, and Team plans</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.227</id>
|
||||
<title>Claude Code v2.1.227</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.227"/>
|
||||
<updated>2026-08-10T22:56:45Z</updated>
|
||||
<content type="html"><p>• Fixed feature flags being evaluated without the user's subscription tier when a session started with an expired login token, which could wrongly prompt Max plan users to enable usage credits for Fable</p>
|
||||
<p>• Fixed every Bash command failing under claude-code-action with allowed_non_write_users on GitHub-hosted runners</p>
|
||||
<p>• Fixed /tui bringing back a conversation that had been rewound to before its first message</p>
|
||||
<p>• Improved slash-command menu: blue now marks only the selected row, matched characters are bolded instead of recolored, and emoji or accented names keep their glyphs</p>
|
||||
<p>• Improved performance: fewer event-loop stalls on file-not-found suggestions and at-mention size checks</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.226</id>
|
||||
<title>Claude Code v2.1.226</title>
|
||||
@@ -379,262 +597,4 @@
|
||||
<p>• Changed keep-alive connection pooling to disable after a stale-connection error, so retries open a fresh socket</p>
|
||||
<p>• Changed SessionStart hooks to report source "fork" when a session begins as a fork instead of "resume"</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.212</id>
|
||||
<title>Claude Code v2.1.212</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.212"/>
|
||||
<updated>2026-07-17T00:26:21Z</updated>
|
||||
<content type="html"><p>• /fork now copies your conversation into a new background session (its own row in claude agents) while you keep working; the in-session subagent it used to launch is now /subtask</p>
|
||||
<p>• Added claude auto-mode reset to restore the default auto-mode configuration, with a confirmation prompt (pass --yes to skip)</p>
|
||||
<p>• Added a session-wide limit on WebSearch tool calls (default 200, tunable via CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION) to stop runaway search loops</p>
|
||||
<p>• Added a per-session cap on subagent spawns (default 200, override with CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION) to stop runaway delegation loops; /clear resets the budget</p>
|
||||
<p>• MCP tool calls running longer than 2 minutes now move to the background automatically so the session stays usable; configure the threshold or disable with CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS</p>
|
||||
<p>• Typing /resume in the agent view now opens a picker of past sessions — including sessions deleted from the list — and resumes your pick as a background session</p>
|
||||
<p>• Fixed plan mode auto-running file-modifying Bash commands (e.g. touch, rm) without a permission prompt or SDK canUseTool callback</p>
|
||||
<p>• Fixed worktree creation following a repository-committed symlink at .claude/worktrees, which could create files outside the repository</p>
|
||||
<p>• Fixed a continue:false hook's halt being dropped when the tool fails or completes mid-stream, and hook infrastructure errors being misreported as user rejections</p>
|
||||
<p>• Fixed SIGTERM during a running Bash tool orphaning the command's process tree in print/SDK mode; the CLI now aborts the turn, kills the tree, and exits 143</p>
|
||||
<p>• Fixed /background and claude --bg failing with "EUNKNOWN: unknown error, uv_spawn" on Windows when Group Policy blocks PowerShell 5.1; the daemon now prefers PowerShell 7</p>
|
||||
<p>• Fixed shell mode (!) not executing commands containing file paths while the path autocomplete popup was open</p>
|
||||
<p>• Fixed auto-mode denial notifications rendering broken characters when a long denial reason was truncated mid-emoji</p>
|
||||
<p>• Fixed Ctrl+J not inserting a newline in the agent view dispatch input on terminals with extended key reporting, and surfaced the newline shortcut in the ? help overlay</p>
|
||||
<p>• Fixed /ultrareview rejecting PR references like #123, PR 123, and pasted PR URLs; error hints now name the command you actually typed</p>
|
||||
<p>• Fixed /ultrareview &lt;branch&gt; not fetching the branch from origin when it exists remotely; it now suggests the closest branch name on typos</p>
|
||||
<p>• Fixed /ultrareview skipping the billing confirmation in a new conversation after /clear</p>
|
||||
<p>• Fixed /ultrareview's "not a git repository" error on Claude Desktop now suggesting the project's repository folder instead of terminal commands</p>
|
||||
<p>• Fixed hosted (host-managed) sessions failing at startup when repository settings configured mTLS certs, extra CA bundles, or OAuth scopes; these transport settings are now ignored with a warning</p>
|
||||
<p>• Fixed a spurious "File has not been read yet" error when editing a file that had been read with offset/limit before resuming a session</p>
|
||||
<p>• Fixed ExitWorktree failing with "no active EnterWorktree session" after resuming a session with --continue/--resume in print/SDK mode</p>
|
||||
<p>• Fixed the workflow agent grid staying empty for Remote Control clients that join a session mid-run</p>
|
||||
<p>• Fixed streaming-mode control requests being marked complete before their handler finished, which could lose the request on session restart</p>
|
||||
<p>• Fixed background sessions created with /fork losing their live-parent protection after a state write failure</p>
|
||||
<p>• Fixed reopening a stopped background session from the agent view failing silently — it now resumes the session, or shows why it can't and lets you force a restart</p>
|
||||
<p>• Fixed agent teams: a stopping teammate could send the leader duplicate idle notifications when team initialization re-ran within a session</p>
|
||||
<p>• Fixed the plan-approval dialog footer splitting "ctrl+g to edit in &lt;editor&gt;" apart when the file path is long</p>
|
||||
<p>• Fixed the welcome banner keeping its old panel widths after a combined width+height terminal resize in fullscreen mode</p>
|
||||
<p>• Fixed diff previews losing their line numbers and +/- markers in narrow layouts</p>
|
||||
<p>• Fixed @-mentions attaching nothing after a partial file read, plugin uninstall targeting the wrong marketplace, and false "Command timed out" on exit code 143</p>
|
||||
<p>• Fixed OpenTelemetry HTTP exports being rejected with 411/400 by Azure Monitor and other endpoints that don't accept chunked transfer encoding</p>
|
||||
<p>• Fixed OTLP event log records missing trace_id/span_id when TRACEPARENT is set in SDK/headless mode</p>
|
||||
<p>• Fixed conversations with many images incorrectly failing with "Request too large" errors, and improved the error message to explain the actual cause</p>
|
||||
<p>• Fixed web search and web fetch returning "API Error" text as search results or page content when the API was overloaded</p>
|
||||
<p>• Improved web search and web fetch reliability by retrying 529 errors and rate-limited requests with bounded backoff</p>
|
||||
<p>• Improved prompt caching: the mid-conversation system block now works behind LLM gateways and custom base URLs (Bedrock, Vertex, 1P)</p>
|
||||
<p>• Improved background agent attach: cold-attaching now instantly shows the formatted transcript while the session boots, instead of a blank wait</p>
|
||||
<p>• Reduced token usage in inter-agent messaging: SendMessage bodies are no longer duplicated into replayed history and tool results</p>
|
||||
<p>• Changed /fork to name the copy after your prompt when the session has no title, so the row is recognizable in the agent view</p>
|
||||
<p>• Changed bare /btw to reopen the side-question panel on your most recent exchange so you can browse earlier answers</p>
|
||||
<p>• Changed the ← footer hint to pulse N done for a moment when a background agent finishes while nothing needs your input</p>
|
||||
<p>• Deprecated the Task tool's mode parameter (now ignored); subagents inherit the parent session's permission mode by default</p>
|
||||
<p>• Changed Enterprise forceLoginMethod to be enforced for VS Code extension, SDK, setup-token, and install-github-app logins, not just the terminal</p>
|
||||
<p>• Changed session transcripts to record the reasoning effort level on each assistant message</p>
|
||||
<p>• Changed headless/SDK sessions to apply a set_model control request mid-turn; the next model round-trip uses the new model instead of waiting for the next turn</p>
|
||||
<p>• Changed agent view / claude agents --json: sessions waiting on a sandbox, MCP-input, or managed-settings prompt now show as "Needs input" instead of "Working"</p>
|
||||
<p>• Updated the auth status panel title from "Cloud authentication" to "Authentication"</p>
|
||||
<p>• Corrected an earlier release note (2.1.200): tmux through the 3.6 series lacks synchronized output; newer tmux with support is detected automatically</p></content>
|
||||
</entry>
|
||||
<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>• Changed the Fable 5 usage-credits consent prompt to start with the decline option focused</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>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.207"/>
|
||||
<updated>2026-07-11T00:52:04Z</updated>
|
||||
<content type="html"><p>• Auto mode is now available without CLAUDE_CODE_ENABLE_AUTO_MODE opt-in on Bedrock, Vertex AI, and Foundry; disable via disableAutoMode in settings</p>
|
||||
<p>• Fixed the terminal freezing and keystrokes lagging while streaming responses containing very long lists, tables, paragraphs, or code blocks</p>
|
||||
<p>• Fixed remote managed settings from a non-interactive run (claude -p, the SDK) being permanently recorded as consented without ever showing the security consent dialog</p>
|
||||
<p>• Fixed spurious prompt-injection warnings triggered by benign system-generated conversation updates</p>
|
||||
<p>• Fixed the auto-updater overwriting a custom launcher script or symlink at ~/.local/bin/claude on every release; /doctor now reports an externally managed launcher</p>
|
||||
<p>• Fixed compound commands with cd prompting for permission when the only output redirect was to /dev/null</p>
|
||||
<p>• Fixed the transcript jumping above the start of the answer when a response finishes streaming</p>
|
||||
<p>• Fixed extensions.worktreeConfig being left in the repo's .git/config (breaking go-git tools like tea) after the last worktree.sparsePaths worktree was removed</p>
|
||||
<p>• Fixed malformed bracket patterns in rules globs, skill paths, .ignore, and .worktreeinclude breaking file reads, file suggestions, and worktree creation</p>
|
||||
<p>• Fixed a crash loop in agent teams where a malformed teammate mailbox message caused repeated errors every second until the mailbox file was manually deleted</p>
|
||||
<p>• Fixed background sessions auto-named by accepting a plan not showing that name on their agent-view row</p>
|
||||
<p>• Fixed background sessions that entered a git worktree resuming blank after a cold reopen from the agent list</p>
|
||||
<p>• Fixed Remote Control task status updates being lost when the connection recovered from a network interruption or credential refresh</p>
|
||||
<p>• Fixed Remote Control sessions hosted by the desktop app not showing background agent and workflow progress on mobile and web</p>
|
||||
<p>• Fixed Deep research runs labeling every Fetch-phase agent "unknown" — chips now show the source hostname</p>
|
||||
<p>• Fixed Bedrock repeatedly requesting fresh AWS SSO credentials from IAM Identity Center on every API request</p>
|
||||
<p>• Improved agent view: pasting the same text again now expands the collapsed [Pasted text #N] placeholder instead of adding a second one</p>
|
||||
<p>• Improved agent view: blocked session peeks now lead with the question and show a worded staleness clock (waiting 3m) instead of the same timestamp twice</p>
|
||||
<p>• Changed Bedrock, Vertex, and Claude Platform on AWS to default to Claude Opus 4.8</p>
|
||||
<p>• Changed auto mode to no longer read autoMode from .claude/settings.local.json (repo-resident); use ~/.claude/settings.json instead</p>
|
||||
<p>• Fixed an indefinite hang on Windows when AWS credential resolution stalls (e.g. a stuck credential_process): the 60-second stall guard now fires instead of waiting forever.</p>
|
||||
<p>• Plugin hooks/monitors/MCP headersHelper: ${user_config.*} in shell-form commands is now rejected (shell-injection fix). Hooks: use exec form (args array) or $CLAUDE_PLUGIN_OPTION_&lt;KEY&gt;; monitors and headersHelper: read the value inside the script (config file or the server's env block).</p>
|
||||
<p>• Plugin option values (pluginConfigs) are no longer read from project-level .claude/settings.json; only user, --settings, and managed settings are honored</p>
|
||||
<p>• Fixed /usage-credits amount inputs silently stripping malformed values (e.g. a pasted timestamp) to digits; malformed amounts are now rejected with an error, and amounts over $1,000 require a typed confirmation</p></content>
|
||||
</entry>
|
||||
<entry>
|
||||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.206</id>
|
||||
<title>Claude Code v2.1.206</title>
|
||||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.206"/>
|
||||
<updated>2026-07-09T23:34:23Z</updated>
|
||||
<content type="html"><p>• Added directory path suggestions to /cd, matching /add-dir behavior</p>
|
||||
<p>• Added a /doctor check that proposes trimming checked-in CLAUDE.md files by cutting content Claude could derive from the codebase</p>
|
||||
<p>• /commit-push-pr now auto-allows git push to the repo's configured push remote (remote.pushDefault, or the sole remote when only one is configured) in addition to origin</p>
|
||||
<p>• Gateway: /login now supports Anthropic-operated public gateway endpoints</p>
|
||||
<p>• EnterWorktree now asks for confirmation before entering a git worktree outside the project's .claude/worktrees/ directory</p>
|
||||
<p>• Background agents now upgrade to a new version in the background right after a Claude Code update, instead of paying a slow stale-session upgrade when you attach</p>
|
||||
<p>• Fixed an expired login failing every model with a misleading "There's an issue with the selected model" error instead of prompting to run /login</p>
|
||||
<p>• Fixed claude --resume and --continue not responding to keyboard input on startup</p>
|
||||
<p>• Fixed MCP servers configured via --mcp-config or .mcp.json ignoring a per-server request_timeout_ms, which caused long-running MCP tool calls to time out at the 60s default in fresh sessions</p>
|
||||
<p>• Fixed CLAUDE_CODE_EXTRA_BODY being silently ignored by claude agents / --bg background workers; the shell-exported override now follows the dispatching session</p>
|
||||
<p>• Fixed OAuth MCP servers requiring manual re-authentication after a single failed token refresh</p>
|
||||
<p>• Fixed --permission-prompt-tool pointing at an MCP server crashing with "MCP tool not found" on cold start before the server finishes connecting</p>
|
||||
<p>• Fixed /model picker rows printing a price for a different model than the row named, and stopped quoting first-party list prices on providers that don't bill them</p>
|
||||
<p>• Fixed server-provided model rows being misplaced in the /model picker when an entitlement or allowlist restriction drops the row they were positioned against</p>
|
||||
<p>• Fixed desktop sessions getting stuck showing "running" after a slash command was sent mid-turn</p>
|
||||
<p>• Fixed keyboard input being ignored in the agents view when a setup prompt appeared before a bare claude --resume on Windows</p>
|
||||
<p>• Fixed claude rm leaving the removed job in the daemon roster, causing the row to reappear in claude agents</p>
|
||||
<p>• Fixed /remote-control showing "Unknown command" when logged out — it now explains how to sign in</p>
|
||||
<p>• Fixed left arrow not stepping back out of a phase or agent in the workflow detail view</p>
|
||||
<p>• Fixed /status listing the same broken-install warning twice</p>
|
||||
<p>• Fixed false "disused plugin" tips and skewed disuse telemetry for LSP plugins</p>
|
||||
<p>• Fixed /doctor's update check to compare Homebrew installs against their cask's channel instead of the settings channel</p>
|
||||
<p>• Fixed the fullscreen jump-to-bottom pill suggesting Ctrl+End on macOS, not showing rebound chords, and wrapping over the transcript</p>
|
||||
<p>• Bedrock: fixed a multi-minute startup hang when using an awsCredentialExport helper on networks with restricted egress</p>
|
||||
<p>• Improved /code-review findings quality on claude-opus-4-8 across all effort levels</p>
|
||||
<p>• Improved agents view: status column now uses full terminal width instead of truncating at 64 characters</p>
|
||||
<p>• Changed agents view: Ctrl+X now permanently removes a completed session, and sessions no longer render twice; deleted background jobs stay deleted</p></content>
|
||||
</entry>
|
||||
</feed>
|
||||
|
||||
Reference in New Issue
Block a user