Hoppa till innehåll
VibekollenBETAVibekollen

Källa

Claude Code

88 referat i flödet. Sammanfattningarna är skrivna av Vibekollen — innehållet tillhör Claude Code.

ReleaseClaude Code

v2.1.310

What's changed Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now blocked there too Fixed requests failing behind some gateways and compatible servers that reject the effort-2025-11-24 beta value or mid-conversation system messages; Claude Code now retries without them Fixed background cleanup deleting some recent files, such as pasted images, when cleanupPeriodDays is set to a very large value Fixed compaction after a "Prompt is too long" error keeping too much of a conversation with dense text, such as base64 or SVG, so the next request could fail again Fixed file read permission prompts not showing where a symbolic link leads Fixed a question's auto-continue timeout firing the moment the external editor closed after a long edit Windows: Fixed PreToolUse and PermissionRequest hooks letting a tool call through when Git Bash is missing and the hook's command is only quoted strings, such as a quoted path Improved auto mode's prompt before the first read outside the working directories: it now says when blocking those reads makes shell commands ask for permission Improved m…

24 okt. github.com

ReleaseClaude Code

v2.1.309

What's changed Fixed sandboxed Bash commands on macOS and Linux running the shell's startup files outside the sandbox before each command Fixed macOS sandbox denyWrite glob patterns not applying at a path's real location when the pattern's folder is reached through a symlink Fixed sandboxed commands and auto-accepted edits being able to modify the MCP config file passed with --mcp-config Fixed a disabled MCP server being reconnected by a later permission prompt in print and SDK sessions Fixed the Bash permission check trusting a variable set by a command whose redirect can fail to open Fixed Bash permission checks not prompting for some compound commands that change directory before running git when the cd is wrapped or prefixed, as they do for a plain cd Fixed an Edit(path) deny rule not blocking a Bash redirect to that path in some commands that also held a subshell Fixed worktree-isolated sessions accepting some locale-prefixed commands the isolation guard should refuse Fixed worktree-isolated sessions on zsh accepting some arithmetic commands that the isolation guard should refuse Fixed worktrees and branch checkouts that Claude Code creates so they ignore git replace refs, as…

23 okt. github.com

ReleaseClaude Code

v2.1.307

What's changed Added /claude-api api-version to move Claude API code to API version 2026-10-21 Added the claude_code.safety_event OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or sent back Fixed requests failing with a model-not-found error when CLAUDE_CODE_DISABLE_1M_CONTEXT is set and the model is an alias with the [1m] suffix, such as opus[1m] Fixed the prompt-caching-scope beta header being sent behind custom ANTHROPIC_BASE_URL gateways and on Foundry, where it has no effect Fixed MCP servers showing "needs authentication" in claude -p on macOS while the login keychain was locked; they now say why, and the next run after an unlock connects without a new sign-in Fixed MCP servers being reported as timed out, and staying failed in headless runs, when a macOS or Linux computer went to sleep while they were connecting Fixed HTTP MCP tool calls being sent twice when the connection closed mid-call; only read-only or idempotent tools are now retried Fixed a turn sometimes starting without an SDK MCP server's latest tools when a background task was running Fixed some "Autocompact is thrashing" errors in turn…

22 okt. github.com

ReleaseClaude Code

v2.1.305

What's changed Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) notices a usage limit that was lifted before its reset Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search, and behind gateways with ToolSearch disallowed or left out of --tools (a 2.1.304 regression): Claude Code now retries without it Fixed /effort and /autocompact settings not applying when the model name differed from a modelOverrides value by letter case or a [1m] tag Fixed new worktrees in a bare repository sometimes starting from local HEAD instead of the default branch, and unchanged subagent worktrees sometimes not being cleaned up Fixed Bash commands on a full disk failing with a raw ENOSPC file path: the error now says the disk is full and that nothing ran Fixed an MCP server passed by a cloud session or by the SDK's setMcpServers being replaced later in the session by a same-named server from your own…

20 okt. github.com

ReleaseClaude Code

v2.1.304

What's changed Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin Added decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked Added e.isReadOnly to a mod's tool.check event, set when the tool call is read-only Added /auto-mode-setup: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled sessions Added /claude-api managed-agents-secure, which compares a Managed Agents agent's settings with Anthropic's published security guide, without changing anything Added the names of the tools called earlier to the compaction summary in the transcript view (Ctrl+O) Added a warning on Pro and Max plans when resuming an inactive conversation would use a noticeable share of your 5-hour usage limit: resume anyway, or start a new conversation and Claude can look up the previous one if you refer to it Fixed the organization policy not refreshing until the hourly check after…

19 okt. github.com

ReleaseClaude Code

v2.1.302

What's changed Added CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode Added an Idle compaction row to /config for turning idle compaction off or back on; the notices shown after an idle compaction now say how to turn it off Added a notice to /design-sync and /design-login that standalone Claude Design (claude.ai/design) closes by December 14, 2026 Fixed a "Prompt is too long" error when stopping a turn while the conversation was being compacted Fixed requests failing with "diagnostics: Extra inputs are not permitted" after switching to Vertex or Bedrock mid-session Fixed the Read tool loading an image file of any size, or a pipe or device named like an image, entirely into memory; image sources over 128 MB are now refused Fixed /autocompact and /effort saving to the wrong model when a gateway names Opus 4 or 4.1 with a prefix, such as anthropic/claude-opus-4-1 Fixed a prompt cache miss when a tool added mid-session was loaded again through ToolSearch or after compaction Fixed claude plugin and other subcommands sometimes exiting before a queued settings or config write finished, which c…

16 okt. github.com

ReleaseClaude Code

v2.1.301

What's changed Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waiting Added OpenTelemetry tracing guidance to the claude-api skill, including setting up trace destinations with the ant CLI Added the % motion to vim mode: jump to the matching bracket, alone or with d/c/y Added rows to a mod's Input: a text field of several lines in the terminal, where Enter submits and Shift+Enter or a backslash before Enter starts a new line Added classifier_verdict and permission_mode to OpenTelemetry tool_decision events, so auto mode classifier decisions can be told apart from permission rules Added classifier_category to OpenTelemetry tool_decision events, naming the built-in rule a classifier block matched, when OTEL_LOG_TOOL_DETAILS=1 Fixed quitting removing a worktree made by a WorktreeCreate hook without asking when it may hold unpushed commits Fixed the fable (and best) model alias erroring on the Anthropic API when the newest Fable model is not available to your organization: Claude Code now retries once on the previous Fable model Fixed a misleading "Please…

15 okt. github.com

ReleaseClaude Code

v2.1.300

What's changed Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt Added cache_creation_5m_tokens and cache_creation_1h_tokens to the OpenTelemetry api_request event, splitting cache writes by lifetime Added $.ui.view({ agentId }) for mods: shows an agent's transcript in the main view when you ask, and $.ui.view({}) goes back Added a dir prop on a mod's Text for right-to-left text: on Windows and in VS Code's terminal its rows read in that direction and sit flush right Added /advisor on Claude Platform on AWS; no advisor runs until you pick one with /advisor, advisorModel or --advisor, and CLAUDE_CODE_DISABLE_ADVISOR_TOOL=1 turns it off Added OpenTelemetry GenAI semantic-convention attributes to trace spans, such as gen_ai.provider.name, gen_ai.conversation.id, gen_ai.tool.name and error.type Added support for rewriting a workflow agent's prompt and model in the agent.spawn mod hook, which could only refuse workflow agents before Added the prompt.change mod hook, raised when the prompt box's text changes without a typed edit: a recalled history entry, a clear, an undo, or a plugin's fill Fixed cloud sessi…

14 okt. github.com

ReleaseClaude Code

v2.1.299

What's changed Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54 minutes is compacted before its one-hour prompt cache expires, so your next message doesn't reprocess it all Added CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS to change idle compaction's 200K-token minimum; "idleCompaction": false in settings.json turns it off.

14 okt. github.com

ReleaseClaude Code

v2.1.296

What's changed Added a code key to the Claude apps gateway's managed.policies[]: the same settings as cli, also applied in Claude Desktop's Code tab; beside desktop, it turns on Claude Desktop's gateway mode Added autoCompactWindow to subagent frontmatter and --agents definitions, so a subagent can auto-compact earlier than the main conversation's window Added CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL to run every workflow agent on one model while other subagents keep theirs Added CLAUDE_CODE_OVERLOADED_RETRY_MAX_DELAY_MS environment variable to set a longer maximum delay for the backoff when retrying an overloaded (529) request Added a note in /plugin on a plugin whose hooks are left out because another enabled plugin has the same name Added an allow_large option to the Read tool so Claude can read a text file past the usual size limits in one call when it needs the whole file and the context has room Fixed managed-settings PreToolUse hooks that deny a tool call with "continue": false, and managed prompt hooks that block one, refusing the call but not ending the turn Fixed PostToolUse hooks in managed settings not applying updatedMCPToolOutput in some sessions Fixed headless sessions st…

9 okt. github.com

ReleaseClaude Code

v2.1.295

What's changed Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through Added Program Status Protocol (OSC 7501) support: terminals that implement it can show whether Claude Code is working, waiting on you, or done Added quoted text to the /copy picker, so a drafted message copies without its > markers Added a warning to claude plugin install, enable, disable and marketplace add when the settings file they write to does not load Added a line on stderr, when it is a terminal, that says what a claude -p run is waiting for when it stays open after its last turn Added support for timeouts.upstream_ttfb_ms on the Claude apps gateway's Bedrock, Vertex, Foundry and other cloud upstreams: a value you set now limits how long a stream may take to start there, after which it fails over or gets a 502 Added a "Backgrounding cancelled" message when you stop the turn while ← is waiting for the current tool to finish Added an optional models list to every Claude apps gateway upstream: only the listed models are sent there, on failover too, and one * in an entry is a wildcard Added suppo…

8 okt. github.com

ReleaseClaude Code

v2.1.293

What's changed Added Claude Haiku 5.5 (claude-haiku-5-5), now the default Haiku model on the Anthropic API — 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K) Added agentType to the subagentStatusLine payload, so scripts can tell custom subagent types apart Added isDeferred to $.tool.register for mods: false lists the tool's schema in the prompt from the start instead of behind tool search Fixed Claude sometimes treating its own last actions before a context compaction as done after it, and retracting or redoing finished work Fixed a memory leak where an HTTP MCP connection kept every request it had sent until it closed Fixed a message sent while Claude was working being lost when ← moved the session to the background; if a queued message can't move, ← now stays put and says so Fixed /model effort ←/→ wrapping past the highest or lowest level, which could accidentally save Low as a model's default effort Fixed /tui disconnecting Claude in Chrome in a session started with --chrome, and ignoring --no-chrome Fixed Claude being told to continue or message subagents with SendMessage in sessions, including resumed ones, where a host, a permission rule or a --tools list…

7 okt. github.com

ReleaseClaude Code

v2.1.292

What's changed Added --marketplace <source> to claude plugin install: adds the marketplace if needed, under the same policy checks as claude plugin marketplace add, then installs the plugin from it Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for Added CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS environment variable to set a longer base delay for the backoff when retrying an overloaded (529) request Added prompt.autocomplete, an event a mod hooks to add its own rows to the prompt box's autocomplete list Added prompt caching to $.model.complete for mods: prompt and system take blocks of text, and cache: true on a block caches the request up to it Added workflow agents to the agent.spawn mod hook, with their run and index, so a mod can refuse them Fixed subagent definitions with permissionMode: auto entering auto mode when auto mode is unavailable (disabled by settings, circuit breaker, or a model that doesn't support it) Fixed sandboxed commands being able to read the staged file copies of /ultrareview uploads under ~/.claude/seed-admin Fixed a managed sandbox read-deny path (and user ones beside it) that appears or re-points mid…

6 okt. github.com

ReleaseClaude Code

v2.1.290

What's changed Added serverToolUses to the result of a mod's turn.step hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end Added agentId to the tool.check event of plugin hooks, so a hook can tell a subagent's permission check from the main session's Added ceiling to the question and verdict a mod's tool.check hook reads, naming the approval an organization requires for a tool Added ThemeKey and Color types to the plugin hooks typings, so an editor lists the theme colors a mod's drawing can name Added to claude plugin validate: each hook a mod registers at a gating site is listed with whether it has a .catch (gatingHooks under --json) Added a Deny button to the Claude apps gateway's sign-in approval page: it ends the pending sign-in, so the waiting terminal stops within seconds Added claude attach <name> and claude logs <name>: part of a session name works in place of the id Added /claude-api managed-agents-onboard <url> to set up the Managed Agents pattern a page describes as ant apply files Added /claude-api managed-agents-onboard <quickstart-name> to build a Console quickstart template, such as deep-researcher, with the ant CLI Add…

6 okt. github.com

ReleaseClaude Code

v2.1.289

What's changed Fixed a deny or ask rule on a nested part of a compound shell command not holding over a user-installed mod's approval on managed machines Fixed the terminal freezing on short code blocks with many unclosed <script> tags or deeply nested ${ substitutions Fixed Read deny rules not applying to files @-mentioned, changed, or selected in the IDE through a symlink [VSCode] Reverted a 2.1.288 change to claude auth status that may have made sign-outs more frequent Improved how quickly large files open in a plugin code pane by laying the highlighted view out once at its final width Fixed plugin list, plugin eval and plugin update showing a stale copy of a plugin installed from a local folder marketplace, and hot reload for a symlinked --plugin-dir Fixed installed mods not loading in the first session after an upgrade Fixed a plugin's rows above the prompt showing a stale row while the Background tasks dialog was open in fullscreen Fixed plugin panes drawing nothing when a link used a localhost address, an @ in its path, an uppercase host or a file: path Fixed a user-installed plugin being able to rewrite the descriptions of an organization-managed MCP server's sign-in tools…

4 okt. github.com

ReleaseClaude Code

v2.1.288

What's changed Added $.ui.selection() for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row Added a built-in gh api to cloud sessions whose image has no GitHub CLI, and fixed the built-in sending control characters from file names, jq filters or GitHub errors to the terminal Added recovery for a prompt cleared with Ctrl+C: pressing Up on the empty prompt brings the draft back, including pasted text and images Added a re-authenticate prompt when an MCP server asks for more OAuth scope during a tool call Added --max-findings <n>|all to /code-review to report more or fewer findings than the usual limit; the choice is reused until you pass --max-findings default Added Ctrl+F to find a session by name and Alt+↑/↓ to jump between groups in the agents view; both, and rename, can be rebound in keybindings.json Added a screen reader mode announcement of the new permission mode when you approve a plan, including with Shift+Tab Fixed mid-response API timeouts failing the turn: non-interactive sessions and subagents now continue from the partial response, and thinking-only responses are retried Fixed long conversations…

2 okt. github.com

ReleaseClaude Code

v2.1.287

What's changed Added Claude Mods: plugins may now modify deeper behavior Added You should know, an opt-in plugin where a side agent watches your back and flags things you or Claude might miss. Turn it on with /plugin enable cc-plugin-you-should-know@builtin (for first-party sessions with telemetry on) Added an n:<text> filter to the agents view that matches session names and tasks; a filter now shows matches in collapsed sections and Enter opens the first match Added prompt_text to the OpenTelemetry user_prompt event, a copy of prompt for backends that nest dotted keys; drop or mask it wherever you drop or mask prompt (#70763) Added URL prompts from MCP servers on the 2025-11-25 protocol, for example to sign in.

1 okt. github.com

ReleaseClaude Code

v2.1.286

What's changed Added a count such as "2 of 5" to the permission prompt when several permission requests stack up Added mouse support for the "N more" rows of lists in fullscreen mode: click one to jump to that end of the list, with hover and pressed states Fixed several Claude Code processes and IDE extensions each opening a login browser when gcpAuthRefresh or awsAuthRefresh credentials expire Fixed claude --resume and --continue sometimes losing every turn after a batch of parallel tool calls when the earlier session crashed or was killed Fixed API 400 errors after a tool or hook returned an object, number or boolean instead of text, including in resumed sessions Fixed cloud sessions with very large histories never waking up because the container was stopped while the transcript was still loading Fixed the Claude apps gateway's spend meter pricing 1-hour prompt cache writes at the cheaper 5-minute rate, and counting only the first model call's input tokens on streamed turns that run a server-side tool such as web search Fixed macOS sessions still showing "Not logged in" or "Login expired" after /login succeeds in another Claude Code window when a leftover ~/.claude/.credentials.j…

30 sep. github.com

ReleaseClaude Code

v2.1.285

What's changed Added CLAUDE_CODE_DISABLE_WEB_FETCH environment variable to turn off the WebFetch tool Added claude --desktop to open the Claude desktop app on the current directory, or on a session with --continue / --resume <id> Added claude plugin configure <plugin> to show a plugin's options and which are unset, or save new values read from stdin with --values-stdin Added <server>.<key>=<value> to claude plugin install --config, so a bundled .mcpb MCP server's own settings can be set at install time and it starts without visiting /plugin → Configure Added allowedProviders managed setting to limit which API providers a machine may use (Anthropic API, a custom endpoint, Bedrock, Mantle, Vertex AI, Foundry, Claude Platform on AWS, or a Cloud gateway) Added CLAUDE_CODE_NONSTREAMING_TIMEOUT_RETRIES environment variable to cap re-sends of a non-streaming fallback request that timed out Fixed claude -p with CLAUDE_CODE_FORK_SUBAGENT=1: a subagent's own Agent call now runs in the foreground, so the subagent gets the child's result Fixed plugin and marketplace installs and updates over SSH ignoring the ssh program set in GIT_SSH or in your git config's core.sshCommand Fixed Claude Code r…

29 sep. github.com

ReleaseClaude Code

v2.1.284

What's changed Added Claude Sonnet 5.5 (claude-sonnet-5-5), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you can allow that one read and still be asked about later ones Added dollar amounts to the Claude apps gateway spend limit in /usage and the status line (for example "$271.40 / $500.00 spent this month") when the gateway runs this version or later; the status line's rate_limits.spend_limit also gains used_usd, limit_usd and period Added effortSlider:decreaseEffort, increaseEffort and toggleUltracode keybinding actions, so the /effort slider's arrow and Tab keys can be rebound in keybindings.json Added /rate-limit-options to /help and the command menu for claude.ai subscribers, so the usage-limit notices that mention it point to a command you can find Added /mcp reconnect all in the interactive terminal to retry every MCP server that failed to connect or needs authentication at once Added Claude apps gateway startup warnings when a managed policy's availableModels is empty, or leaves out the model Cla…

28 sep. github.com

ReleaseClaude Code

v2.1.283

What's changed Added x-claude-code-prompt-id to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with CLAUDE_CODE_GATEWAY_HINT_HEADERS=1 Added availableModelsMatch managed setting: with "exact", an availableModels entry allows only the model version it names, so new releases stay blocked until listed Added deniedModels managed setting to block specific models, even when availableModels allows them Added MCP tool, WebFetch and WebSearch outputs to the tool.output OpenTelemetry span event when OTEL_LOG_TOOL_CONTENT=1 Added /doctor prompt-audit (also /checkup prompt-audit) to audit your CLAUDE.md files, skills, agents and commands for prompting patterns written for older models Added click-to-expand for truncated messages from your other sessions in fullscreen mode Added path to --plugin-dir load-failure entries in the stream-json system/init plugin_errors, naming the directory that did not load Added an opt-in load_test_mode block to the Claude apps gateway config: requests are built and signed but not sent upstream, and clients get a canned reply, so a deployment can be load tested Added a mantle upstream provider to the Claude apps…

25 sep. github.com

ReleaseClaude Code

v2.1.282

What's changed Added a maxProseWidth setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width Added a startup notice, and /status and claude doctor entries, listing telemetry variables in a project's settings files that were ignored or that turned telemetry off Added the allowClaudeInChromeWithManagedMcp managed setting to let claude --chrome run alongside an exclusive managed-mcp.json; the error shown when Chrome is blocked now names it Added store.readiness_grace_seconds to the Claude apps gateway so /readyz can stay ready through a short Postgres outage such as a database failover Added a scrollbar to the /feedback drafts list in fullscreen mode; it appears while the mouse is over the list Fixed every request failing with a 400 error in conversations whose history holds web search results the API cannot decrypt (for example, from a turn answered through a third-party gateway) Fixed more cases of continued or resumed sessions (--continue, --resume) re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning Fixed earlier extended thinking being dropped when /model, /rename, /artifa…

24 sep. github.com

ReleaseClaude Code

v2.1.281

What's changed Added Claude apps gateway support for newer Claude Desktop keys in desktop policy blocks, including blockReadsOutsideWorkingDirectories and disableBypassPermissionsMode Added assume_role on Claude apps gateway Bedrock upstreams: the gateway calls Bedrock as an IAM role it assumes through STS, in another AWS account if needed, optionally one session per developer Added guardrail: {id, version} on Claude apps gateway Bedrock upstreams to apply an Amazon Bedrock guardrail to every request sent through them (set it on all Bedrock upstreams or none) Added telemetry.resource_attributes to the Claude apps gateway config, to put fixed labels on the telemetry of Claude Desktop and /login sessions Added "attribution": false in settings.json to hide all commit and PR attribution; older CLI versions skip a settings file that holds it, so keep the object form in files shared across versions Added MCP URL-mode elicitation on 2026-07-28 protocol connections, so servers can ask Claude Code to open a browser-based flow; no waiting dialog is left on screen when the server has no way to confirm completion Added MCP server checks to claude plugin validate: it reports .mcp.json entries t…

23 sep. github.com

ReleaseClaude Code

v2.1.280

What's changed Added Claude Opus 5.5 (claude-opus-5-5), now the default Opus model — 1M context, $4/$20 per Mtok with $0.20/Mtok cache reads Added mouse support to more lists in fullscreen mode: the wheel scrolls the /skills list, and a skill's state options in /plugin can be clicked Added CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH to change the 2,048-character cap on MCP tool descriptions and server instructions for every MCP server in the session Added hook output sizes and the number of oversized outputs saved to a file to the hook_execution_complete OpenTelemetry event Fixed writes through a symlinked path being judged by their in-tree spelling: the prompt names where the write lands, and acceptEdits, allow rules and auto mode no longer approve one landing outside Fixed auto mode retrying an action over and over when a safety check declined to review it; the action is now denied once, noting that retrying won't help Fixed auto mode denying actions over and over without pause when a safety check gave no answer; retries now back off, and the turn stops with a message after ten in a row Fixed Write calls failing validation when a model sends path, file_text, file_content or a stray de…

22 sep. github.com

ReleaseClaude Code

v2.1.278

What's changed Changed auto mode for Claude API and Enterprise users, and on Bedrock, Vertex, Foundry and gateways, to default to the server-side classifier, which does not charge for classifier overhead (CLAUDE_CODE_AUTO_MODE_SERVER=0 opts out on Bedrock, Vertex, Foundry and gateways); warns on billed fallback. See https://code.claude.com/docs/en/auto-mode-classifier-billing Added an Auto mode server row to /status showing whether this session's auto mode classifier runs on the server

19 sep. github.com

ReleaseClaude Code

v2.1.277

What's changed Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change it under "Project instructions" in /config (not yet on Bedrock, Vertex or Foundry) Added CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1 for Claude apps gateways whose only egress is a forward proxy: every outbound request hands the proxy the hostname instead of resolving it locally Added an optional headers: map on Claude apps gateway upstreams, to send static headers to a proxy you run in front of a provider Added a line saying a background task's update is waiting when it finishes while a panel such as /tasks is open Fixed claude -p and Agent SDK sessions that could hang with no result after an internal error; they now report the error and exit with code 1 Fixed conversations failing every request with "text content blocks must be non-empty" when an earlier assistant turn held an empty text block beside other content, including after --resume Fixed being unexpectedly logged out when an older Claude Code build (for example an IDE extension's bundled CLI) runs on the same machine as the current one Fixed interactive start-up hanging or showing an error for ANTHROPIC_API_KE…

18 sep. github.com

ReleaseClaude Code

v2.1.275

What's changed Added the signed-in account to Claude apps gateway sign-in: when the gateway names it, you confirm it before the credential is saved, and /status shows it Added a send-now key (ctrl+enter, or ctrl+x ctrl+s) that interrupts the current turn and sends all queued messages at once; sent and queued messages show in gray until the model receives them Added a startup warning when a configured otelHeadersHelper fails, so sessions that silently export no telemetry are noticed Added syncing of the skills and plugins enabled on your claude.ai account to terminal sessions signed in with it; opt out with syncClaudeAiSkills: false or syncClaudeAiPlugins: false Added /plugin install <plugin> --marketplace <source>, which offers to add the marketplace before installing the plugin Fixed a restored memory file's age note changing between requests after a compaction or resume, which caused prompt cache misses Fixed --forward-subagent-text stream-json and SDK output dropping the messages of subagents spawned by a context: fork skill, and of forked skills invoked by a subagent or another forked skill Fixed @-mention file suggestions being buried below MCP resources when using a custom fi…

18 sep. github.com

ReleaseClaude Code

v2.1.274

What's changed Added a visible warning when memory usage is critical, with steps to free memory or restart safely Added CLAUDE_CODE_MCP_STARTUP_WAIT_MS to bound how long the first non-interactive turn waits for connecting MCP servers (0 = don't wait) Added effort attribute to the claude_code.llm_request OpenTelemetry trace span, matching the api_request event Added claude_code.managed_settings_resolved OTel event: managed-settings sources and policy helper state; redacted settings and digests with OTEL_LOG_MANAGED_SETTINGS=1 Added store.connect_timeout_seconds to the Claude apps gateway config to lengthen the Postgres connect timeout (default 5 seconds), and improved the boot error when the database is unreachable to point to store.postgres_url and the configured timeout Added enduser.sub, the IdP subject, to the telemetry Claude Desktop and Cowork send through a Claude apps gateway Added a Claude apps gateway warning when a replica has more requests open than the 256 it sends upstream at once, and a startup log line showing that limit Added click-to-expand for collapsed teammate and agent messages in fullscreen mode Fixed sessions getting stuck endlessly retrying "unexpected tool_…

17 sep. github.com

ReleaseClaude Code

v2.1.273

What's changed 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 Added a notification when an MCP server disconnects mid-session and automatic reconnection gives up, pointing at /mcp 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 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 Fixed skills synced from claude.ai staying available after your organization turns Skills off; they now move to the recoverable trash Fixed allowManagedMcpServersOnly, deniedMcpServers and disableClaudeAiConnectors set via MDM or managed-settings.json being ignored when server-managed settings are also present 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…

15 sep. github.com

ReleaseClaude Code

v2.1.271

What's changed Added fast mode in Claude Code Remote sessions (cloud and self-hosted runners): the host's fast-mode setting or /fast typed in the session applies where your organization allows it Added mouse support to the /config panel in fullscreen mode: the wheel scrolls the settings list, a click on a setting's value changes it, and the row under the pointer is highlighted Added claude self-hosted-runner --drain-marker-file <path>: when that file exists at a SIGTERM drain, the runner reports its exit to the server as a host drain (telemetry only) Added per-command allowed_domains to Bash, PowerShell and Monitor in auto mode with sandboxing: the hosts a command needs are reviewed with it and opened for it alone; other hosts are refused Added omitClaudeMd to agent frontmatter and --agents JSON, letting custom and plugin subagents run without user, project and local CLAUDE.md files; managed policy files still load Added --accept-command <sha256> to claude plugin install and claude plugin update to accept exactly the command a previous --json run displayed, instead of -y Added support for a multiplier above 1, up to 10, in the modelPricing managed setting and the Claude apps gatewa…

15 sep. github.com

ReleaseClaude Code

v2.1.269

Claude Code v2.1.269 introducerar ett värderingsverktyg för plugins, nya alternativ för output-stil, och en mängd felrättningar. Nya funktioner inkluderar möjligheten att visa vilka filer ett bash-kommando ändrade, bättre konfigurationsalternativ för hur Claude kan arbeta parallellt, och stöd för att konvertera CMYK JPEG-bilder. De flesta uppdateringarna är buggfixar som rör sessioner som återupptas, terminalkommunikation, behörighetsregler, och hanteringen av prompter på icke-latinska språk.

11 sep. github.com

ReleaseClaude Code

v2.1.268

Claude Code version 2.1.268 är en uppdatering med många felbuggar och förbättringar. Den lägger till nya funktioner för administratörer — bland annat möjligheten att sätta priser via gateway-inställningar och nya varningar för säkerhet. Uppdateringen fixar också problem där Claude ibland svarade "your message came through empty", där sessioner använde för mycket processorkraft, och där vissa behörighetsregler inte fungerade korrekt. Dessutom åtgärdas fel med WebFetch som kunde hänga oändligt, och problem med MCP-verktygen (standarden som kopplar AI-modeller till externa tjänster) som visade lösenord i felmeddelanden.

10 sep. github.com

ReleaseClaude Code

v2.1.267

Claude Code version 2.1.267 är en uppdatering med många felkorrigeringar och mindre förbättringar. Det finns en ny maxEffortLevel-inställning som begränsar ansträngningsnivån på alla AI-providrar, och ett till ett dussintal buggar är fixade — framför allt problem med sessioner som återupptas, verktyg som kopplas till AI-modellen (MCP-servrar), och olikaUI-problem på mobil och desktop. Uppdateringen fokuserar på stabilitet snarare än nya funktioner.

9 sep. github.com

ReleaseClaude Code

v2.1.266

Claude Code version 2.1.266 fixar ett problem från föregående version som gjorde att vissa konfigurationer slutade fungera. Om du använder Claude Code med en proxy eller gateway och hade satt en miljövariabel kallad CLAUDE_CODE_USE_GATEWAY, krävde versionen 2.1.265 plötsligt att du loggade in via Cloud-gatewayen — även om du redan hade ett API-nyckel eller annan autentisering konfigurerad. Det nya uppdateringen löser detta så att din befintliga konfiguration fungerar igen utan ändringar.

9 sep. github.com

ReleaseClaude Code

v2.1.265

Claude Code version 2.1.265 är en underhållsuppdatering som fixar ett 30-tal problem. Det mest användbara för vibekodare är att verktyget nu begränsar resultat från verktyg till 1 GB på disk och visar när en fil har trunkeras, samt förbättrat stöd för plugins genom att läsa in mappar med plugins som kan laddas om medan programmet körs. Uppdateringen fixar också flera stabilitets- och säkerhetsproblem, som att sessions kan starta om ordentligt efter avbrott och att MCP-servrar (protokoll för att koppla AI-modeller till externa verktyg) kan ansluta via fallback-lägen.

8 sep. github.com

ReleaseClaude Code

v2.1.261

Claude Code v2.1.261 är en uppdatering med många bugfixar och små förbättringar. Nya funktioner inkluderar bättre kontroll över hur mycket output Claude får direkt (upp till 128K tecken innan det sparas i fil), ett /skill-doctor-kommando för att se vilka verktyg som inte används, och bättre felmeddelanden när organisationspolicyer inte kan laddas. De flesta ändringar fixar problem med inmatning, fjärrsessioner, plugin-hantering och autentisering mot olika molntjänster som AWS och Google Cloud.

4 sep. github.com

ReleaseClaude Code

v2.1.260

Claude Code v2.1.260 är en uppdatering med många buggfixar och mindre nya funktioner. Den lägger till en diff-panel som visar ändringar när Claude redigerar kod, lägger till /reload-plugins-kommando för sessioner utan användargränssnitt, och fixar problem med filrättigheter, modellväxling, prompt-caching och Git-integration. Uppdateringen adresserar också problem med inloggning, plugin-hantering och gränssnittsproblem som textåtergivning och sessionshantering.

4 sep. github.com

ReleaseClaude Code

v2.1.259

Claude Code v2.1.259 är en uppdatering som framför allt fixar buggar och lägger till nya funktioner för organisationer och utvecklare. Bland nyheterna finns möjligheten för organisationer att dela MCP-servrar (verktyg som kopplar AI-modellen till andra program) med alla användare, samt ett sätt att köra Claude Code på servrar utan att ställa frågor — allt svar blir automatiskt nej. Uppdateringen fixar också många problem: när man kör flera sessioner samtidigt förlorades tidigare inte längre inställningar, GitLab-funktioner fungerar bättre, och många mindre fel med behörigheter och visning är rättade.

3 sep. github.com

ReleaseClaude Code

v2.1.257

Claude Code version 2.1.257 introducerar Claude Fable 5.1 som ny standardmodell med 1 miljons tokens kontextfönster, lägre priser ($10/$50 per miljon tokens med cachetillägg), och nya tidsinställningar för 12- eller 24-timmarformat. Uppdateringen lägger till säkerhetskontroller för automatiskt läge som förhindrar obehörig åtkomst till molnuppgifter och dataladdning, samt många buggfixar för sessionshantering, bakgrundsprocesser och behörighetskontroller.

1 sep. github.com

ReleaseClaude Code

v2.1.251

Claude Code version 2.1.251 är en uppdatering som fokuserar på säkerhet, stabilitet och nya funktioner. Den lägger till möjligheter att övervaka modellbyten med hook-event, live-streaming av underagenter till Remote Control-klienter, och spendgränser för utvecklare. Uppdateringen fixar många buggar, bland annat säkerhetsproblem där filverktyg kunde läsa eller skriva utanför godkända områden, problem med sessioner som fastnade på fel, och laggar när många parallella underagenter kördes.

28 aug. github.com

ReleaseClaude Code

v2.1.248

Claude Code version 2.1.248 är en uppdatering med nya säkerhetsfunktioner, buggrättningar och förbättringar av sessionshantering. Den lägger till ett `--restricted`-läge som tar bort inbyggda verktyg för att köra kommandon och kod, samt nya diagnostikverktyg för att felsöka inställningar. Uppdateringen fixar flera problem där långa sessioner förlorade cacheminne efter tokenuppdateringar, där sessioner försvann eller startades om felaktigt, och där verktygsdefinitioner blev inkonsistenta.

28 aug. github.com

ReleaseClaude Code

v2.1.247

Claude Code v2.1.247 lägger till ett verktyg för att skicka felrapporter direkt från appen, en ny funktion för att analysera och optimera kostnader när du använder Claude API, och ett antal buggfixar. Bland annat förbättras stabiliteten när Claude kör kod i bakgrunden, tangentbordsgenvägar fungerar nu på fler språkkonfigurationer, och sessioner slutar att fastna på felmeddelanden. Uppdateringen innehåller också förbättringar för organisationer som vill anpassa tips och meddelandeloggning.

27 aug. github.com

ReleaseClaude Code

v2.1.243

Claude Code v2.1.243 lägger till flera nya funktioner för att övervaka och kontrollera AI-körningar bättre. Du kan nu se en detaljerad uppdelning av loop-körningar för att upptäcka problem, välja vilka AI-modeller som ska visas, och bestämma hur länge den kan spara tidigare samtal för att gå snabbare nästa gång. Organisationer kan nu definiera sina egna priser för olika modeller, och användare kan logga in utan API-nycklar. Uppdateringen fixar också många buggar, bland annat problem med automatiska lägen som inte fungerade ordentligt, sessioner som frös, och inloggningsproblem.

25 aug. github.com

ReleaseClaude Code

v2.1.239

Claude Code version 2.1.239 är en uppdatering med många buggrättningar och förbättringar. Den lägger till funktioner som fullscreen-läge för fler plattformar, bättre kostnadskalkyl med premiumavgifter för vissa workspaces, och ett verktyg för att uppdatera Python-kod från äldre versioner. Uppdateringen fixar också många problem — bland annat att sessioner hängde sig bakom proxyservrar, att motsäg-tangenten inte fungerade rätt, och att gamla webbsidor stannade kvar i minnet längre än de skulle.

21 aug. github.com

ReleaseClaude Code

v2.1.236

Claude Code version 2.1.236 innehåller främst buggfixar och mindre förbättringar. Nya funktioner inkluderar möjligheten att sätta en standardmodell via ANTHROPIC_DEFAULT_MODEL, en notifieringsfunktion mellan sessioner (notify_when_idle), och förbättrad säkerhet för sandbox-läget på macOS. Flera fel har fixats som rörde renderingen av gränssnittet, hanterings av sessioner, och auto-lägets beteende. Förbättringar gjordes även för prestanda vid uppstart och för tillgänglighet med skärmläsarstöd i VSCode.

19 aug. github.com

ReleaseClaude Code

v2.1.235

Claude Code version 2.1.235 är en uppdatering med flera buggrätningar och förbättringar. Den lägger till stavningskontroll som markerar fel medan du skriver, fixar problem med att textmarkeringar hamnade på fel plats i långa instruktioner, och löser ett fel där Shift+Tab i behörighetsdialogen gjorde något oväntat. Uppdateringen förbättrar också minnesanvändning när molnsessioner körs i bakgrunden och fixar flera mindre fel i gränssnittet.

18 aug. github.com

ReleaseClaude Code

v2.1.234

Claude Code v2.1.234 är en uppdatering med nya funktioner och många buggfixar. Det finns nu en miljövariabel för att namnge sessionskataloger, möjlighet att binda en tangent för att rensa textval, GitLab merge request-märken, och sessioner fortsätter automatiskt när din API-gräns återställs. Säkerhetsmässigt blockerar uppdateringen nu farliga Windows-sökvägar för att skydda mot attacker, och många fel har fixats — från långsam markdown-rendering till problem med behörighetskontroller och sessionshantering.

17 aug. github.com

ReleaseClaude Code

v2.1.233

Claude Code v2.1.233 lägger till stöd för GitLab merge requests, nya konfigurationsalternativ för användarkonton och minnesbegränsningar på Linux, samt åtgärdar ett tjugotal buggar. Bland fixarna märks problem med sessioner som markeras som förlorade, MCP-anslutningar som öppnas om utan slut, notifieringar som inte visas, och en säkerhetslucka på Windows där vissa filsökvägar kunde kringgå validering. Versionen tar också bort taskspårningsverktyg från nyare modeller såsom Opus 4.8 och Sonnet 5.

15 aug. github.com

ReleaseClaude Code

v2.1.232

Claude Code v2.1.232 introducerar flera nya funktioner för att göra det lättare att arbeta med flera AI-sessioner samtidigt — du kan nu säga @ för att nämna en annan session, och subsessioner kör som standard i bakgrunden. Uppdateringen lägger till stöd för GitLab i plugin-marknadsplatser och förbättrar säkerheten genom att dölja känsliga tokens och säkra rättigheter för Git-lagringsplatser. Det finns också många buggfixar, bland annat för Remote Control-sessioner som nu återkopplas korrekt när du återuppta arbete, och för PowerShell- och Windows-säkerhetsproblem.

14 aug. github.com

ReleaseClaude Code

v2.1.229

Claude Code version 2.1.229 är en uppdatering som fixar många fel och förbättrar stabiliteten. Den lägger till stöd för att återuppta Remote Control-sessioner, förbättrar plugin-systemet så det uppdateras utan omstart, och fixar problem med krascher när terminalen är smal, när fil-sökvägar är långa på Windows, och när AI-modellen behöver bearbeta mycket lång text. Uppdateringen gör också GitHub-integreringen mer tillförlitlig och lägger till session-grupper i VSCode-tillägget.

12 aug. github.com

ReleaseClaude Code

v2.1.228

Claude Code v2.1.228 är en uppdatering som fixar ett tjugotal buggar och förbättringar. Bland annat åtgärds problem där interaktiva sessioner slutade att uppdatera skärmen, där Git inte hittades på Windows, och där inställningar för modelval inte sparades korrekt mellan sessioner. Säkerhetsmässigt förstärks skills som synkroniseras från claude.ai så de inte kan köra alla kommandon. Också förbättras hur Google Cloud-legitimation hanteras och hur meddelanden visas mellan sessioner.

11 aug. github.com

ReleaseClaude Code

v2.1.227

Claude Code version 2.1.227 är en uppdatering med flera buggrättningar och förbättringar. Den fixar ett problem där användare med Max-plan felaktigt fick uppmaningar om att aktivera krediträkning, löser ett problem med Bash-kommandon som inte fungerade på GitHub-hostad infrastruktur, och åtgärdar en bugg där konversationer kunde återhämtas felaktigt. Dessutom förbättras slash-kommandomenyn med bättre visuell formatering, och prestandan ökas genom att minska systemstörningar.

11 aug. github.com

ReleaseClaude Code

v2.1.225

Claude Code v2.1.225 är en uppdatering som lägger till stöd för utgiftsgränser i användarvarningar och lägger till säkerhetskontroller för opålitliga mappar. Uppdateringen fixar flera buggar relaterade till autentisering, sessioner och Remote Control-funktionen — bland annat problem med sessions som fastnade utan att avslutas, bruten konversationshistorik och fel med OAuth-servrar på macOS. Den förbättrar också Remote Control så att bilder från Claude-appen visas direkt istället för att läsas från disk, och gör det möjligt att starta konversationer med Remote Control-sessioner på andra datorer via namn.

8 aug. github.com

ReleaseClaude Code

v2.1.224

Claude Code version 2.1.224 innehåller nya funktioner för att köra sessioner på egna servrar (self-hosted environments), installera plugins från zip-filer, och låta Claude Code-sessioner skicka meddelanden till varandra. Uppdateringen fixar också ett flertal buggar — bland annat problem med långa projektvägar som blandades ihop, säkerhetshål i sandlådan, och felaktig rapportering av misslyckade meddelandeöverföringar. Dessutom tas det bort en gräns på 200 underagenter per session, så långvariga arbeten kan fortsätta utan att nya agenter vägras.

7 aug. github.com

ReleaseClaude Code

v2.1.216

Claude Code version 2.1.216 innehåller många buggfixar och förbättringar. Det här är en stor uppdatering med fokus på stabilitet: långsamma sessioner blir snabbare, Claude slutar att fråga om samma sak efter att man varit inaktiv ett tag, sessioner återställs rätt när man återupptar dem, och inloggningsfel hanteras bättre. Det finns också nya inställningar för att kontrollera filåtkomst och flera andra förbättringar av gränssnitt och kommandohantering.

21 juli github.com