surshar / claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Built by Anthropic · github.com/anthropics
Large file, diff not shown.
| @@ -6,8 +6,78 @@ | ||
| 6 | 6 | <author><name>Anthropic</name></author> |
| 7 | 7 | <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/> |
| 8 | 8 | <link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/> |
| 9 | - <updated>2026-09-15T00:42:19Z</updated> | |
| 9 | + <updated>2026-09-15T20:22:55Z</updated> | |
| 10 | 10 | <entry> |
| 11 | + <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.273</id> | |
| 12 | + <title>Claude Code v2.1.273</title> | |
| 13 | + <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.273"/> | |
| 14 | + <updated>2026-09-15T20:22:55Z</updated> | |
| 15 | + <content type="html"><p>• Added x-claude-code-request-class, x-claude-code-agent-type, x-claude-code-prev-tool-durations, x-claude-code-compaction and x-claude-code-context-compacted request headers for LLM gateways; opt in with CLAUDE_CODE_GATEWAY_HINT_HEADERS=1</p> | |
| 16 | +<p>• Added a notification when an MCP server disconnects mid-session and automatic reconnection gives up, pointing at /mcp</p> | |
| 17 | +<p>• Added forking a session started with claude --remote-control or /remote-control from the Claude app; the fork runs as a background session on your computer</p> | |
| 18 | +<p>• Fixed Bash commands the permission checker cannot fully analyze skipping the prompt under permissions.blockReadsOutsideWorkingDirectories, and a subshell hiding a dangerous rm in bypass mode</p> | |
| 19 | +<p>• Fixed skills synced from claude.ai staying available after your organization turns Skills off; they now move to the recoverable trash</p> | |
| 20 | +<p>• Fixed allowManagedMcpServersOnly, deniedMcpServers and disableClaudeAiConnectors set via MDM or managed-settings.json being ignored when server-managed settings are also present</p> | |
| 21 | +<p>• Fixed 401/403 errors on Bedrock, Vertex and Foundry, and Claude apps gateway 403s, telling you to run /login; the message now names the credential to refresh or points to your gateway administrator</p> | |
| 22 | +<p>• Fixed /login, /upgrade, and /extra-usage discarding earlier thinking from the conversation, which forced a full prompt-cache rewrite on the next request</p> | |
| 23 | +<p>• Fixed auto mode stopping for approval when the Artifact tool uploads a file you attached to the chat in a cloud or Remote Control session</p> | |
| 24 | +<p>• Fixed a long-running session recreating a stub .git/info/exclude after the repository's .git directory was removed or moved away</p> | |
| 25 | +<p>• Fixed the main prompt dropping a ! typed at the start while already in shell mode, so negated commands like ! grep … can be typed</p> | |
| 26 | +<p>• Fixed Read on macOS refusing a dragged-in screenshot, or any file the system reports under a second path, with "symlink resolution changed after permission was checked"</p> | |
| 27 | +<p>• Fixed permissions.blockReadsOutsideWorkingDirectories: a memory directory chosen by a repository's settings is no longer loaded into the prompt, recalled, indexed, or used by memory extraction</p> | |
| 28 | +<p>• Fixed sub-agents and background agents being reported as failed, with their result never delivered, when the final streamed reply omitted token usage or carried no model id</p> | |
| 29 | +<p>• Fixed the context meter and auto-compact counting advisor-tool turns at roughly twice their real context size, which made auto-compact fire at about half the real window</p> | |
| 30 | +<p>• Fixed /tui refusing to restart because of an agent-team teammate that had already finished its work and was no longer shown in the agents panel</p> | |
| 31 | +<p>• Fixed saved scheduled tasks running in the wrong session after .claude/scheduled_tasks.json was copied into another folder, such as a new worktree</p> | |
| 32 | +<p>• Fixed SDK and --output-format stream-json output dropping a subagent's remaining messages and final report after it is moved to the background mid-run (e.g. by CLAUDE_AUTO_BACKGROUND_TASKS)</p> | |
| 33 | +<p>• Fixed /install-github-app reporting a SAML single sign-on block as "admin permissions required"</p> | |
| 34 | +<p>• Fixed Remote Control clients attached to a Claude Desktop, VS Code or JetBrains session being refused when they ask for the session's context window usage</p> | |
| 35 | +<p>• Fixed the spinner showing a doubled ellipsis ("……") on compaction status lines such as "Running PreCompact hooks…"</p> | |
| 36 | +<p>• Fixed a false-positive spinner tip suggesting the frontend-design plugin after reading or publishing Artifacts</p> | |
| 37 | +<p>• Reverted a 2.1.268 change that checked Read and Edit deny rules on Bash lines the permission checker can't analyze (eval, env -C); commands like time -p make build prompt again instead of being denied</p> | |
| 38 | +<p>• Improved responsiveness in long sessions: hook progress and sub-agent activity no longer re-process the whole conversation on every update</p> | |
| 39 | +<p>• Improved the Artifact tool's error when a publish includes a file type artifacts don't serve: Claude is told which types are served and what to do instead, and the terminal shows one plain line</p> | |
| 40 | +<p>• Improved the Artifact tool's page read to state the capabilities and database rules the artifact service holds for the page, for anyone who can publish to it</p> | |
| 41 | +<p>• Improved artifact database writes: an update can now remove a single field instead of rewriting the whole document</p> | |
| 42 | +<p>• Improved artifact publishing: a publish whose connection drops after reaching claude.ai is now re-sent safely instead of failing or creating a duplicate version</p> | |
| 43 | +<p>• Improved the cloud-session GitHub error for an IP allow list, a suspended app installation or SAML single sign-on to show the cause instead of a generic install hint</p> | |
| 44 | +<p>• Improved /autofix-pr: when gh pr view fails it now shows gh's own error (sign-in, SAML, rate limit) instead of a generic exit-code line</p> | |
| 45 | +<p>• Improved /autofix-pr to say why GitHub webhook delivery couldn't be set up for the PR (for example, no linked GitHub account) instead of a generic warning</p> | |
| 46 | +<p>• Improved /web-setup errors: a refused GitHub token now lists the likely reasons and the fix, and a connection failure names a configured proxy or TLS certificate problem</p> | |
| 47 | +<p>• Improved the in-session SSL certificate and proxy connection errors to name the error code and what to fix, such as NODE_EXTRA_CA_CERTS for an untrusted corporate CA</p> | |
| 48 | +<p>• Improved the error when a cloud session can't be created because your Claude login expired or was revoked: it now tells you to run /login</p> | |
| 49 | +<p>• Improved the error shown when an MCP server's sign-in expires mid-session to say how to re-authenticate (/mcp)</p> | |
| 50 | +<p>• Changed auto mode on Bedrock, Vertex and Foundry to use the local classifier by default for now; set CLAUDE_CODE_AUTO_MODE_SERVER=1 to use the platform's server-side classifier</p> | |
| 51 | +<p>• Changed OTEL_LOG_TOOL_DETAILS=1 to also include real agent, skill, plugin and MCP server names on cost and token metrics</p> | |
| 52 | +<p>• Changed sign-in with a Claude account to also request access to your claude.ai plugins</p> | |
| 53 | +<p>• Changed /bug and /feedback reports to include only model-behavior params (model, system prompt, tools) from the last API request, omitting request metadata and CLAUDE_CODE_EXTRA_BODY fields</p> | |
| 54 | +<p>• [VSCode] Fixed "Report a problem" still appearing, and /bug / /feedback opening a report form, for organizations that have product feedback disabled</p> | |
| 55 | +<p>• [VSCode] Fixed a red "Claude Code process exited with code 4294967295" banner appearing after completed turns on Windows</p> | |
| 56 | +<p>• Windows: Improved the network-path permission check for UNC paths when a mapped network drive was added with --add-dir</p> | |
| 57 | +<p>• [Claude Code on the web] Fixed routines losing access to an organization connector, and still calling the old one, after an admin removed and re-added that connector</p> | |
| 58 | +<p>• [Claude Code on the web] Fixed creating a self-hosted environment from organization settings occasionally failing with a server error and leaving a half-created environment behind</p> | |
| 59 | +<p>• [Claude Code on the web] Changed the admin "Share cloud sessions" setting to live under Data and privacy instead of the Claude Code page, where Data and privacy admins can also manage it</p> | |
| 60 | +<p>• [Claude Code on the web] Added a "Discard unsaved changes?" confirmation before the New routine page or the Edit routine dialog throws away a routine name, prompt or edit you typed</p> | |
| 61 | +<p>• [Claude Code on the web] Removed the full-page desktop-app download screen that new users without a cloud environment saw on Mac and Windows; they now go straight to setup</p> | |
| 62 | +<p>• [Claude Code on the web] Improved the routine detail page: menu and rename in the breadcrumb, the on/off switch and Run now at the top, and run history beside the routine's settings</p> | |
| 63 | +<p>• [Claude Tag] Fixed Claude going silent minutes after reinstalling the app when an Enterprise Grid was disconnected but one of its workspaces stayed connected</p> | |
| 64 | +<p>• [Claude Tag] Fixed scheduled tasks set up in an organization-shared private Slack channel silently never posting; they now keep running in the thread they were created in</p> | |
| 65 | +<p>• [Claude Tag] Fixed replying in an older Slack thread while Claude is mid-task sometimes restarting it from scratch and losing work it had not pushed yet</p> | |
| 66 | +<p>• [Claude Tag] Fixed Claude occasionally dropping a message with an incorrect "couldn't find a Claude Code environment" notice right after your account token refreshed</p> | |
| 67 | +<p>• [Claude Tag] Fixed AWS connections refusing region-less endpoints such as Budgets, Savings Plans, WAF Classic and Import/Export; Global Accelerator requests now sign correctly</p> | |
| 68 | +<p>• [Claude Tag] Improved AWS connection failures: when a request can't be signed, such as a hostname with no region, Claude is told why and how to fix it instead of a bare error</p> | |
| 69 | +<p>• [Claude Tag] Fixed OAuth client-credentials and JWT-bearer connections failing with providers that return a lowercase token type; requests now send the standard Bearer scheme</p> | |
| 70 | +<p>• [Claude Tag] Fixed adding a channel manager being refused on Enterprise Grid shared channels, on channels where Claude hasn't been used yet, and on legacy private channels</p> | |
| 71 | +<p>• [Claude Tag] Changed Claude to start watching related public channels on its own, such as an incident channel a conversation depends on, instead of only when asked</p> | |
| 72 | +<p>• [Claude Tag] Fixed the admin Memory page not listing Slack channels Claude set up on its own even when they had saved memory; admins can now open, edit and delete that memory</p> | |
| 73 | +<p>• [Code Review] Fixed merging the base branch into a PR whose earlier review listed "Additional findings" triggering a full re-review; these pushes now get the lighter follow-up review</p> | |
| 74 | +<p>• [Code Review] Fixed a whole REVIEW.md being ignored because of an @-mention, a code span wrapped across lines, or a backticked HTML tag; only lines linking to changed files are withheld</p> | |
| 75 | +<p>• [Code Review] Improved suggested fixes to say what the fix must keep working when other code depends on the behavior being changed</p> | |
| 76 | +<p>• [Code Review] Improved review comments that point to a second affected location to state that location's issue in a full sentence instead of a cut-off stub</p> | |
| 77 | +<p>• [Code Review] Fixed /ultrareview --post so a retry after a GitHub error posts the findings comment exactly once instead of never or twice; the comment now names the reviewed commit</p> | |
| 78 | +<p>• [Code Review] Fixed empty or content-identical pushes being re-reviewed on GitHub repositories whose owner or name contains a capital letter; these pushes are now skipped</p></content> | |
| 79 | + </entry> | |
| 80 | + <entry> | |
| 11 | 81 | <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.272</id> |
| 12 | 82 | <title>Claude Code v2.1.272</title> |
| 13 | 83 | <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.272"/> |
| @@ -952,71 +1022,4 @@ | ||
| 952 | 1022 | <p>• Changed Claude apps gateway sign-in requests to identify Claude Code (a surface=claude_code device-authorization parameter and a claude-code/&lt;version&gt; User-Agent)</p> |
| 953 | 1023 | <p>• Changed organization sign-in enforcement to exit at start when the administrator's managed settings cannot be read, even if host-supplied or per-user Windows registry settings exist</p></content> |
| 954 | 1024 | </entry> |
| 955 | - <entry> | |
| 956 | - <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.246</id> | |
| 957 | - <title>Claude Code v2.1.246</title> | |
| 958 | - <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.246"/> | |
| 959 | - <updated>2026-08-25T22:31:43Z</updated> | |
| 960 | - <content type="html"><p>• Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. Bash(git * main)), since they also match options inserted before the subcommand</p> | |
| 961 | -<p>• Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules</p> | |
| 962 | -<p>• Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM</p> | |
| 963 | -<p>• Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress</p> | |
| 964 | -<p>• Fixed a severe transcript slowdown when a diff contained a very long single line (e.g. a base64 string); such lines now render truncated with a marker</p> | |
| 965 | -<p>• Fixed erratic fullscreen scrolling when positioned at an earlier message, including jump-to-bottom getting stuck mid-transcript</p> | |
| 966 | -<p>• Fixed background sessions failing to open after 45 seconds when Claude Code's starting directory had been deleted, the machine had slept, or the host is slow to start processes</p> | |
| 967 | -<p>• Fixed background sessions failing to open with "Couldn't start the background service … EACCES" when another Claude Code process was re-installing the npm package at that moment</p> | |
| 968 | -<p>• Fixed markdown rendering being disabled for a whole message when its first 500 characters contained no markdown, and for +/N) lists and setext headings</p> | |
| 969 | -<p>• Fixed MCP tool calls interrupted by an incoming message in headless/remote sessions being reported to the model as "completed with no output" instead of an explicit interrupted error</p> | |
| 970 | -<p>• Fixed MCP tool arguments being sent as JSON strings when the parameter's schema is empty ({}), instead of their real type</p> | |
| 971 | -<p>• Fixed a command interrupted mid-run showing as "Ran 1 shell command" with no sign it was cut</p> | |
| 972 | -<p>• Fixed pressing ← or running /background during a dynamic workflow restarting its finished subagents; it now asks first and says how many subagents would restart</p> | |
| 973 | -<p>• Fixed opening a just-started session in claude agents while its worker was still booting (common on Windows) stopping it with "was stopped while the respawn was in flight"</p> | |
| 974 | -<p>• Fixed claude agents listing a backgrounded named session twice; backgrounding the same conversation again now numbers the new row (e.g. my-session (2))</p> | |
| 975 | -<p>• Fixed the background retention sweep removing git worktrees under .claude/worktrees/ that you created yourself when an old background-session record pointed at them</p> | |
| 976 | -<p>• Fixed auto mode tool calls being denied as "temporarily unavailable" on very large sessions by scaling the safety-check deadline with prompt size</p> | |
| 977 | -<p>• Fixed the plugin cache creating duplicate SHA-named directories for the same plugin</p> | |
| 978 | -<p>• Fixed plugin skills whose frontmatter name already includes the &lt;plugin&gt;: prefix showing it doubled in the slash menu (e.g. /plugin:plugin:skill)</p> | |
| 979 | -<p>• Fixed claude plugin update failing for an installed plugin given its bare name (only the fully-qualified name worked)</p> | |
| 980 | -<p>• Fixed plugin installation failing when plugin.json was saved with a UTF-8 byte-order mark (BOM)</p> | |
| 981 | -<p>• Fixed /reload-plugins reporting 0 skills for plugins that define skills under skills/*/SKILL.md</p> | |
| 982 | -<p>• Fixed hook error messages showing a literal ${CLAUDE_PLUGIN_ROOT} instead of the resolved plugin path</p> | |
| 983 | -<p>• Fixed /rename replacing the theme's prompt border color (including a custom theme's promptBorder) with the default cyan; the border now keeps your theme's color unless you pick one with /color</p> | |
| 984 | -<p>• Fixed custom theme diff colors (diffAdded/diffRemoved and their dimmed variants) being ignored in diffs and the /theme preview</p> | |
| 985 | -<p>• Fixed a keybindings.json binding with an unknown action name silently deadening that key; it is now skipped so the default binding keeps working, and a warning is logged under --debug</p> | |
| 986 | -<p>• Fixed /stats activity heatmap showing each day's activity one cell off (Sunday's count under Monday) in timezones east of UTC</p> | |
| 987 | -<p>• Fixed /fork from an already-forked or backgrounded session starting the new session with an empty conversation</p> | |
| 988 | -<p>• Fixed prompts beginning with /-- (e.g. Lean doc comments) being rejected as an unknown slash command instead of being sent to Claude</p> | |
| 989 | -<p>• Fixed the @ file picker staying open after the typed text stopped matching a real path</p> | |
| 990 | -<p>• Fixed the status line's cost and duration resetting to zero after navigating to the agents view and back</p> | |
| 991 | -<p>• Fixed fullscreen mode moving keyboard focus onto the control under the pointer when you clicked the terminal window only to bring it back into focus</p> | |
| 992 | -<p>• Fixed path completion failing when the completion token or working directory contained a null byte</p> | |
| 993 | -<p>• Windows/macOS: Fixed headless sessions not cleaning up stale entries in ~/.claude/sessions left by sessions that exited uncleanly</p> | |
| 994 | -<p>• Fixed the UI stopping with a render error on the first tool call when a third-party Anthropic-compatible endpoint (ANTHROPIC_BASE_URL) streams a tool_use block without an id</p> | |
| 995 | -<p>• Fixed the Write tool reporting "Out of memory" or freezing for a long time after overwriting a very large existing file, even though the file had been written</p> | |
| 996 | -<p>• Fixed claude plugin install &lt;name&gt; exiting silently (or hanging in a terminal) instead of reporting an error when ~/.claude/plugins/known_marketplaces.json is empty or corrupted</p> | |
| 997 | -<p>• Fixed resumed sessions failing every turn with a 400 when the saved history contains tool blocks the Anthropic API does not accept (typically written by a third-party API proxy)</p> | |
| 998 | -<p>• Fixed curl -fsSL https://claude.ai/install.sh | bash failing with "Raw mode is not supported" for some Team/Enterprise users with server-managed settings</p> | |
| 999 | -<p>• Fixed sessions that ended in plan mode resuming outside plan mode in the VS Code extension, and in claude -p --continue/--resume with a permission prompt tool, when no permission mode was set</p> | |
| 1000 | -<p>• Fixed the Notification hook not firing while the sandbox "Network request outside of sandbox" permission prompt is waiting</p> | |
| 1001 | -<p>• Fixed Bash permission checks to always require approval for malformed commands with a dangling &amp;&amp; or || operator</p> | |
| 1002 | -<p>• Fixed --strict-mcp-config sessions prompting to approve .mcp.json servers they would never load, which left background sessions waiting at startup</p> | |
| 1003 | -<p>• Fixed telemetry and metrics requests to Anthropic carrying the API key configured for a third-party gateway (ANTHROPIC_BASE_URL); a credential is now only sent to its own host</p> | |
| 1004 | -<p>• Fixed a visible API error on the first prompt after idle when apiKeyHelper returns short-lived JWTs: an expired cached token is now refreshed before sending, and 401/403 auth errors retry quietly</p> | |
| 1005 | -<p>• Fixed memory growing with session length in the fullscreen and Ctrl+O transcript views: each rendered message row no longer retains a full copy of the transcript-wide tool lookups</p> | |
| 1006 | -<p>• Fixed /ultrareview runs and cloud sessions launched at the same time from one repository (e.g. from several worktrees) sometimes starting with another launch's uncommitted changes</p> | |
| 1007 | -<p>• Fixed the task progress count (e.g. 3/5) shown for background cloud sessions such as /autofix-pr occasionally missing a task</p> | |
| 1008 | -<p>• Fixed Remote Control sessions keeping their placeholder name in claude.ai and the Claude app until the second prompt; the auto-generated title now appears after the first prompt</p> | |
| 1009 | -<p>• Fixed MCP tools marked requiresUserInteraction still offering "Yes, and don't ask again" in their permission prompt; the option wrote an allow rule the tool then ignored</p> | |
| 1010 | -<p>• Fixed the self-hosted runner ending its live sessions or exiting when a work-poll response is malformed (e.g. an intercepting proxy's HTML page); it now retries the poll</p> | |
| 1011 | -<p>• Improved /cd: the new directory's project settings, hooks, .mcp.json servers (behind the usual approval prompt), skills, and agents now take effect right after the move instead of on --resume</p> | |
| 1012 | -<p>• Improved Bash tool latency on bash shells by replaying snapshot functions without a base64 subshell per function</p> | |
| 1013 | -<p>• Improved subagent results: a subagent that stops at its maxTurns limit now returns its output marked as partial, with a hint to continue it via SendMessage, instead of appearing finished</p> | |
| 1014 | -<p>• Improved non-interactive sessions (-p, SDK, cloud sessions) to automatically continue a response cut off mid-stream by a server error, connection loss, or stall instead of ending with an error</p> | |
| 1015 | -<p>• Improved attribution of usage telemetry to your organization for workload identity federation sessions, events sent while apiKeyHelper runs at startup, and after a login token expired while idle</p> | |
| 1016 | -<p>• Changed /code-review so Claude can also start it on its own on Bedrock, Vertex AI, and Foundry, through the Claude apps gateway, and when telemetry or non-essential traffic is disabled</p> | |
| 1017 | -<p>• /goal: Changed idle sessions to start at most three check-ins on long-running background work per goal; your next message allows three more</p> | |
| 1018 | -<p>• Changed claude install and claude update to defer a pending managed-settings consent prompt to the next interactive session instead of prompting mid-command</p> | |
| 1019 | -<p>• Changed OpenTelemetry plugin events for plugins synced from claude.ai: plugin_id_hash now reflects the plugin's real marketplace, and enabled_via is admin-install for admin-installed plugins</p> | |
| 1020 | -<p>• Fixed the command sandbox's filesystem configuration not respecting --setting-sources</p></content> | |
| 1021 | - </entry> | |
| 1022 | 1025 | </feed> |