Zum Inhalt springen

Anthropic Release Notes

698 Einträge aus 5 Quellen. Zuletzt aktualisiert:

Folge Anthropic, um die Release Notes in deinen Feed zu holen.

Feed abonnieren:RSS: Feed für Anthropic Release NotesAPI: Einträge von Anthropic Release Notes als JSON

Anthropic-Produkte (3)

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.195: Hook-Matcher, Sprachdiktat und Agents-Fixes

Neu ist CLAUDE_CODE_DISABLE_MOUSE_CLICKS, Hook-Matcher mit Bindestrichen greifen nun exakt, und es gibt Korrekturen bei Sprachdiktat, Plugins und Hintergrundjobs sowie Verbesserungen im Sprachmodus unter Linux und in claude agents.

  • Added CLAUDE_CODE_DISABLE_MOUSE_CLICKS to disable mouse click/drag/hover in fullscreen mode while keeping wheel scroll
  • Fixed hook matchers with hyphenated identifiers (e.g. code-reviewer, mcp__brave-search) accidentally substring-matching — they now exact-match. Use mcp__brave-search__.* to match all tools from a hyphenated MCP server.
  • Fixed voice dictation on macOS capturing silence in long-running sessions after the default input device changes
  • Fixed voice dictation auto-submit never firing for languages written without spaces (Japanese, Chinese, Thai)
  • Fixed external plugins enabled only by project .claude/settings.json not requiring explicit install consent on every loader path
  • Fixed /plugin Enable/Disable not working when a plugin's plugin.json name differs from its marketplace entry name
  • Fixed background jobs disappearing from claude agents or losing data when written by a newer Claude Code version
  • Fixed reopening a crashed background task showing a blank screen for up to 5 seconds instead of its restart
  • Fixed background agent daemons running unreachable when the control socket fails to start, blocking restarts
  • Improved voice mode on Linux: now distinguishes "no microphone" from "SoX not installed" when SoX is present but no audio capture device exists
  • Improved claude agents completed list to fill available vertical space; on short terminals the header compacts so live sessions stay visible …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Höhere Rate Limits und drei konsolidierte Usage Tiers

Die Rate Limits der Claude API wurden erhöht, Sonnet und Haiku entsprechen nun auf jeder Stufe Opus, und die Usage Tiers wurden zu Start, Build und Scale zusammengefasst, ohne dass Nutzer etwas tun müssen und ohne dass Limits sinken.

  • We've raised rate limits across the Claude API. Claude Sonnet and Claude Haiku rate limits now match Claude Opus at every usage tier, and usage tiers have been consolidated into three: Start, Build, and Scale. Most organizations move to a higher tier, no organization receives lower limits than before, and no action is required. You can view your tier and current limits in the Claude Console.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.193: Auto-Mode-Klassifizierung, OTEL-Antwortlog, Autovervollständigung

Neu sind die Einstellung autoMode.classifyAllShell, Ablehnungsgründe des Auto-Modes im Transcript, das OpenTelemetry-Ereignis claude_code.assistant_response, Dateipfad-Autovervollständigung im Bash-Modus, ein Startup-Hinweis zu MCP-Authentifizierung sowie automatisches Beenden inaktiver Hintergrund-Shells bei Speicherdruck, dazu mehrere Fehlerbehebungen bei Hintergrundagenten.

  • Added autoMode.classifyAllShell setting to route all Bash/PowerShell commands through the auto-mode classifier instead of only arbitrary-code-execution patterns
  • Added auto-mode denial reasons to the transcript, the denial toast, and /permissions recent denials
  • Added claude_code.assistant_response OpenTelemetry log event containing the model's response text. Redacted unless OTEL_LOG_ASSISTANT_RESPONSES=1; when that var is unset it follows OTEL_LOG_USER_PROMPTS, so deployments that already log prompt content will start receiving response content on upgrade — set OTEL_LOG_ASSISTANT_RESPONSES=0 to keep prompts-only.
  • Added live file path autocomplete to bash mode (!)
  • Added a startup notice when MCP servers need authentication, pointing at /mcp
  • Added automatic memory-pressure reaping for idle background shell commands (disable with CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP=1)
  • Fixed /model and other client-data-gated UI showing stale/empty state immediately after /login
  • Fixed backgrounding (←←) spuriously cancelling with "N background tasks would be abandoned" when all running tasks carry over to the new session
  • Fixed pinned background agents being re-prompted to "Continue from where you left off" after every auto-update
  • Fixed backgrounding the main turn spawning a phantom "general-purpose (resumed)" subagent that re-ran the main conversation
  • Fixed agent panel hiding sibling agents when viewing a subagent …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Fast mode für Claude Opus 4.7 veraltet, Entfernung am 24. Juli 2026

Fast mode für Claude Opus 4.7 ist veraltet und wird am 24. Juli 2026 entfernt, danach führen Anfragen an claude-opus-4-7 mit speed: "fast" zu einem Fehler, weshalb eine Migration zu Fast mode für Claude Opus 4.8 empfohlen wird.

  • We've deprecated fast mode for Claude Opus 4.7, with removal on July 24, 2026. After removal, requests to claude-opus-4-7 with speed: "fast" will return an error. Migrate to fast mode for Claude Opus 4.8. Read more in Fast mode.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude von Anthropic

Trusted Devices für Remote Control aktivierbar

Admins von Team- und Enterprise-Plänen können nun verlangen, dass Mitglieder ihr Gerät verifizieren, bevor sie lokale Claude-Code-Sitzungen aus der Ferne ansehen oder steuern.

Enable Trusted Devices for Remote Control

Admins for Team and Enterprise plans can now require members to verify their device before viewing or steering local Claude Code sessions remotely. For more information, see Trusted Devices.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude von Anthropic

June 25, 2026

Enable Trusted Devices for Remote Control

Admins for Team and Enterprise plans can now require members to verify their device before viewing or steering local Claude Code sessions remotely. For more information, see Trusted Devices.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.191: /rewind vor /clear und viele Fehlerbehebungen

/rewind kann nun eine Unterhaltung von vor einem /clear wiederherstellen, und es wurden zahlreiche Fehler behoben, darunter Scroll-Sprünge, Hook-Matcher mit Kommas, /permissions, claude agents und verwaltete Einstellungen.

  • Added /rewind support for resuming a conversation from before /clear was run
  • Fixed scroll position jumping to the bottom while reading earlier output during a streaming response
  • Fixed background agents resurrecting after being stopped — stopping an agent from the tasks panel is now permanent
  • Fixed /voice showing a generic "not available" message when disabled by an organization's policy — it now explains the restriction
  • Fixed /login URL opening truncated in Windows Terminal when it wraps across lines
  • Fixed Cmd+click on links in fullscreen mode for Ghostty over ssh/tmux
  • Fixed claude agents sending builtin slash commands like /usage to background sessions as prompt text instead of showing a hint
  • Fixed claude agents job rows showing full filesystem paths for pasted images instead of the [Image #N] placeholder
  • Fixed hooks with comma-separated matchers (e.g. "Bash,PowerShell") silently never firing
  • Fixed /permissions Recently-denied tab: approving a denial now persists on close instead of being silently discarded
  • Fixed the agent panel jumping by one row when scrolling the roster past the overflow cap
  • Fixed the welcome splash art overflowing the default 80×24 macOS Terminal window
  • Fixed managed settings: forceRemoteSettingsRefresh now takes effect when set via MDM or file policy, and the fetch sends Cache-Control: no-cache to prevent proxies from serving stale responses …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.187: sandbox.credentials, Modellbeschränkungen, Mausklicks in Menüs

Neu sind die Einstellung sandbox.credentials zum Schutz von Zugangsdaten, von der Organisation konfigurierbare Modellbeschränkungen und Mausklick-Unterstützung in Auswahlmenüs im Fullscreen-Modus, dazu Korrekturen bei --resume, --json-schema, MCP-Timeouts und weiteren Problemen.

  • Added sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables
  • Added org-configured model restrictions to the model picker, --model, /model, and ANTHROPIC_MODEL, with a "restricted by your organization's settings" message when a restricted model is selected
  • Added mouse click support to select menus (permission prompts, /model, /config, etc.) in fullscreen mode
  • Fixed --resume failing with "No conversation found" when the original -p run produced no model turns
  • Fixed --json-schema and workflow agent({schema}) structured output: the model can no longer re-call StructuredOutput indefinitely after a successful call, and follow-up turns now reliably return structured output
  • Fixed remote MCP tool calls that hang with no response for 5 minutes — they now abort with an error instead of blocking indefinitely (override with CLAUDE_CODE_MCP_TOOL_IDLE_TIMEOUT)
  • Fixed Claude Code Remote sessions taking ~2.7s longer to start after the agent proxy CA system-trust install was added
  • Fixed pasted Korean/CJK text turning into mojibake in terminals that deliver paste as per-byte extended-key events
  • Fixed /update over Remote Control hanging when a startup trust dialog would have shown
  • Fixed background jobs in the agents view getting stuck in "working" indefinitely when the agent ended a turn without producing structured output …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude von Anthropic

Aufgaben in Slack mit Claude Tag an Claude delegieren

Team- und Enterprise-Pläne können Claude jetzt direkt in Slack-Unterhaltungen markieren und ihm Aufgaben übertragen, während sie sich anderen Dingen widmen.

Delegate work to Claude in Slack with Claude Tag

Team and Enterprise plans can now tag Claude directly in Slack conversations and delegate tasks to it while they focus on other work. For more information, see our blog post: Introducing Claude Tag.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.186: MCP-Login per CLI und Bash-Antworten

Neu sind claude mcp login/logout, Statusfilter in /workflows, ein Skills-Bereich in /plugin, die Einstellung teammateMode: "iterm2" und automatische Claude-Antworten auf !-Bash-Befehle (abschaltbar über respondToBashCommands), außerdem wurden mehrere Fehler behoben.

  • Added claude mcp login <name> and claude mcp logout <name> to authenticate MCP servers from the CLI without opening the interactive /mcp menu, with --no-browser stdin redirect support for completing over SSH
  • Added status filtering (press f) to the /workflows agent detail view
  • Added a "Skills" section to the /plugin Installed tab
  • Added teammateMode: "iterm2" setting with a warning when auto mode cannot find the it2 CLI
  • Added "Claude Platform on AWS - refresh credentials" option to /login when awsAuthRefresh is configured
  • ! bash commands now trigger Claude to respond to the output automatically; set "respondToBashCommands": false in settings.json to keep the previous context-only behavior
  • Fixed streaming requests failing with "Content block not found" or JSON parse errors after the machine wakes from sleep
  • Fixed subagent transcript scroll position bleeding into the main transcript on exit
  • Fixed background task previews flashing raw tool names before the agent's plan loaded
  • Fixed Chrome tab-group isolation not applying when the in-product permissions gate is off for concurrent CLI sessions
  • Fixed background session recaps being duplicated; the agent's own end-of-turn summary now shows as the recap line
  • Fixed opening a background session from claude agents leaving the previous screen painted behind it
  • Fixed Agent(type) deny rules and Agent(x,y) allowed-types restrictions not being enforced for named subagent spawns …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

MCP tunnels: Management-API auf /v1/tunnels verschoben

Die Management-API der MCP tunnels (Research Preview) wechselte von /v1/organizations/tunnels auf der Admin API zu /v1/tunnels auf der Claude API mit dem Header anthropic-beta: mcp-tunnels-2026-06-22 und dem WIF-Scope workspace:manage_tunnels, wobei die alte Schnittstelle während eines Migrationszeitraums verfügbar bleibt.

  • MCP tunnels (research preview): the management API moved from /v1/organizations/tunnels on the Admin API to /v1/tunnels on the Claude API. The new surface uses the anthropic-beta: mcp-tunnels-2026-06-22 header and the workspace:manage_tunnels WIF scope. The previous surface remains available during a migration window. See the Tunnels API reference.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.185: Neuer Hinweis bei Stream-Stillstand

Der Hinweis bei stockendem Stream lautet nun „Waiting for API response · will retry in …“ und erscheint erst nach 20 statt 10 Sekunden Stille.

  • The stream-stall hint now reads "Waiting for API response · will retry in …" instead of "No response from API · Retrying in …", and triggers after 20s of silence instead of 10s

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.183: Sicherer Auto-Modus und neue Config-Optionen

Der Auto-Modus blockiert nun destruktive Git- und Infrastrukturbefehle ohne ausdrücklichen Auftrag, es gibt Warnungen bei veralteten Modellen, die Einstellung attribution.sessionUrl und /config --help, /config speichert beim Schließen mit Esc, und mehrere Fehler wurden behoben.

  • Improved auto mode safety: destructive git commands (git reset --hard, git checkout -- ., git clean -fd, git stash drop) are now blocked when you didn't ask to discard local work, git commit --amend is blocked when the commit wasn't made by the agent this session, and terraform destroy/pulumi destroy/cdk destroy are blocked unless you asked for the specific stack
  • Added a warning when the requested model is deprecated or automatically updated to a newer model, shown on stderr in print mode (-p) and now also covering models set in agent frontmatter
  • Added attribution.sessionUrl setting to omit the claude.ai session link from commits and PRs in web and Remote Control sessions
  • Added /config --help to list all available shorthand keys for /config key=value
  • Changed /config toggle behavior: Enter and Space both change the selected setting, and Esc now saves and closes instead of reverting
  • Removed the startup "setup issues" line under the logo — run /doctor to see configuration issues or use --debug
  • Fixed thinking.disabled.display: Extra inputs are not permitted 400 errors on subagent spawns and session-title generation for affected configurations
  • Fixed WebSearch returning empty results in subagents
  • Fixed the terminal cursor being stranded above the prompt after navigating history in vim mode with the native cursor enabled …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

SDKs unterstützen code_execution_20260120 mit REPL-Zustandserhalt

Die SDKs für Python, TypeScript, Go, Java, Ruby, PHP und C# unterstützen nun code_execution_20260120, die Version des Code-Execution-Tools mit REPL-State-Persistenz und Mindestversion für programmatic tool calling, die ohne Beta-Header über den Tool-type aktiviert wird.

  • The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now include support for code_execution_20260120, the code execution tool version that adds REPL state persistence and is the minimum version for programmatic tool calling. To adopt it, set the tool's type to code_execution_20260120; no beta header is required. It's available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.5 and newer, and Claude Sonnet 4.5 and newer; see the code execution tool's Compatibility section.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.181: /config key=value, Bun 1.4 und Streaming-Verbesserungen

Neu sind die Syntax /config key=value, sandbox.allowAppleEvents und CLAUDE_CLIENT_PRESENCE_FILE, die Bun-Runtime wurde auf 1.4 aktualisiert, Streaming, Auto-Retry, Subagent-Panel und MCP-OAuth-Seite wurden verbessert, und es gibt Fehlerbehebungen etwa beim Prompt Caching und bei Write/Edit.

  • Added /config key=value syntax to set any setting from the prompt (e.g. /config thinking=false) — works in interactive, -p, and Remote Control
  • Added sandbox.allowAppleEvents opt-in setting that lets sandboxed commands send Apple Events on macOS
  • Added CLAUDE_CLIENT_PRESENCE_FILE environment variable: point it at a marker file to suppress mobile push notifications while you're at the machine
  • Upgraded the bundled Bun runtime to 1.4
  • Improved streaming of long paragraphs: text now appears line-by-line instead of waiting for the first line break
  • Improved auto-retry: API connection drops mid-thinking now automatically retry instead of showing "Connection closed while thinking"
  • Improved the subagent panel: idle subagents auto-hide after 30s, the list caps at 5 rows with scroll hints, and keyboard hints now show in the footer
  • Improved the MCP OAuth browser page to match Claude Code's visual style and auto-close on success
  • Changed fullscreen mode URL opening to require Cmd+click (macOS) / Ctrl+click, matching native terminal behavior
  • Changed the Improved N memories line to no longer list individual files outside verbose mode
  • Fixed prompt caching not reading on custom ANTHROPIC_BASE_URL and on Foundry due to a per-request attestation token changing every turn
  • Fixed Write/Edit producing 0-byte or truncated files on network drives and cloud-synced folders …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.179: Fixes für Verbindungsabbrüche, Scrollen und Sandbox

Behoben wurden unter anderem Verbindungsabbrüche mitten im Stream, Mausrad-Scrollen in WSL2, ein Sandbox-Problem unter Linux und mehrere Fokus- und Anzeigefehler, zudem wurde das Laden von Plugins in Remote-Sessions beschleunigt.

  • Fixed mid-stream connection drops: partial responses are now preserved instead of showing a raw error, and the spinner no longer gets stuck at "running tool"
  • Fixed mouse-wheel scrolling in WSL2 under Windows Terminal and VS Code (regression in 2.1.172)
  • Fixed a sandbox denyRead/allowRead glob over a large directory tree making the Bash tool description enormous and the session unusable on Linux
  • Fixed the feedback survey capturing a single-digit reply as a session rating immediately after a turn completes
  • Fixed the welcome screen stacking multiple promotional banners — at most one promo now shows per session
  • Fixed Ctrl+O not showing the subagent's transcript when viewing a subagent
  • Fixed clicking the prompt input not returning focus from the subagent/footer panel
  • Fixed remote session background tasks appearing stuck as "still running" between turns
  • Improved plugin loading performance in remote sessions

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.178: Agent Teams vereinfacht, Tool-Parameter-Regeln

TeamCreate und TeamDelete entfallen, da jede Session bei aktiviertem Agent-Teams-Flag ein implizites Team hat, außerdem gibt es die Regelsyntax Tool(param:value), Skills in verschachtelten .claude/skills-Verzeichnissen, einen verbesserten Auto-Modus und ein überarbeitetes /doctor.

  • Agent teams: removed the TeamCreate and TeamDelete tools. With CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 set, every session now has one implicit team — spawn teammates directly with the Agent tool's name parameter, no setup step needed. The team_name parameter on the Agent tool is still accepted but ignored.
  • Added Tool(param:value) syntax for permission rules to match a tool's input parameters (with * wildcard), e.g. Agent(model:opus) to block Opus subagents
  • Skills in nested .claude/skills directories now load when working on files there; on a name clash, the nested skill appears as <dir>:<name> so both stay available
  • Nested .claude/ directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing .claude/workflows/
  • Improved auto mode: subagent spawns are now evaluated by the classifier before launch, closing a gap where a subagent could request a blocked action without review
  • Improved /doctor with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names
  • Improved the skill listing truncation warning to show how many skill descriptions are affected
  • Changed the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like "run a workflow" or "workflow:", not on any mention of the word …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Claude Sonnet 4 und Claude Opus 4 abgeschaltet

Die Modelle Claude Sonnet 4 (claude-sonnet-4-20250514) und Claude Opus 4 (claude-opus-4-20250514) wurden eingestellt, Anfragen an sie liefern in der Claude API einen Fehler, und empfohlen wird der Wechsel zu Claude Sonnet 4.6 bzw. Claude Opus 4.8.

  • We've retired the Claude Sonnet 4 model (claude-sonnet-4-20250514) and the Claude Opus 4 model (claude-opus-4-20250514). All requests to these models on the Claude API will now return an error. We recommend upgrading to Claude Sonnet 4.6 and Claude Opus 4.8 respectively. Researchers can request ongoing access through the External Researcher Access Program.

Originalquelle(öffnet in neuem Tab)Problem melden

Ähnlich wie Anthropic, mit neuen Einträgen