Zum Inhalt springen

Anthropic Release Notes

641 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 2.1.170: Claude Fable 5 eingeführt

Claude Fable 5, ein für den allgemeinen Gebrauch abgesichertes Modell der Mythos-Klasse, ist mit Update auf 2.1.170 verfügbar, und das Speichern von Transcripts aus dem VS-Code-Terminal wurde repariert.

  • Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Fable’s capabilities exceed those of any model we’ve ever made generally available. Update to version 2.1.170 for access. https://www.anthropic.com/news/claude-fable-5-mythos-5
  • Fixed sessions not saving transcripts (and not appearing in --resume) when launched from the VS Code integrated terminal or any shell that inherited Claude Code environment variables.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Claude Fable 5 und Claude Mythos 5 veröffentlicht

Mit claude-fable-5 für alle Kunden und claude-mythos-5 für Teilnehmer von Project Glasswing gibt es zwei neue Modelle mit 1M-Token-Kontext, 128k maximaler Ausgabe und stets aktivem Adaptive Thinking, die den Tokenizer von Claude Opus 4.7 nutzen und damit für denselben Text etwa 30 % mehr Tokens erzeugen als frühere Modelle.

  • We've launched Claude Fable 5 (claude-fable-5), our most capable model open to all customers, alongside Claude Mythos 5 (claude-mythos-5) for Project Glasswing participants. Both models support a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking. See Introducing Claude Fable 5 and Claude Mythos 5 for capabilities, API changes, and availability.
  • Claude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7. Compared to models before Claude Opus 4.7, the same text produces roughly 30% more tokens. The exact increase depends on the content and workload shape. Use the token counting API with model: "claude-fable-5" to measure your prompts under the new tokenizer. …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Version 2.1.169: --safe-mode, /cd und Bundled-Skills-Option

Neu sind --safe-mode, der Befehl /cd und die Option disableBundledSkills, außerdem wurden unter anderem die Verlaufsnavigation, die Durchsetzung von MCP-Richtlinien, Remote Control und Windows-Probleme korrigiert.

  • Added --safe-mode flag (and CLAUDE_CODE_SAFE_MODE) to start Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting
  • Added /cd command to move a session to a new working directory without breaking the prompt cache mid-session
  • Added a disableBundledSkills setting and CLAUDE_CODE_DISABLE_BUNDLED_SKILLS environment variable to hide bundled skills, workflows, and built-in slash commands from the model
  • Fixed Up/Down arrows jumping to command history past the wrapped rows of a long input line — they now move through each visual row first, and history recall enters at the near edge
  • Fixed enterprise managed MCP policies (allowedMcpServers/deniedMcpServers) not being enforced on reconnect, IDE-typed configs, --mcp-config servers during the first session after install, or before remote settings loaded; also fixed slow cold starts for orgs without remote settings
  • Fixed a ~30-50ms UI stall at the start of each turn for macOS users logged in with claude.ai credentials
  • Fixed claude -p being slow or appearing to hang on Windows while waiting for the slash-command/skill scan (regression in 2.1.161)
  • Fixed Remote Control getting stuck on "reconnecting" after resuming a session when an OAuth token refresh happened at the same time
  • Fixed Git Credential Manager's "Connect to GitHub" popup appearing on Windows at startup when background git commands ran without cached credentials …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.166: Fallback-Modelle und strengere Cross-Session-Sicherheit

Neu ist die Einstellung fallbackModel mit bis zu drei Ersatzmodellen, außerdem Glob-Muster in Deny-Regeln, abgesicherte Nachrichten zwischen Sessions per SendMessage, ein konsistenteres Abschalten von Thinking sowie mehrere Fehlerbehebungen.

  • Added fallbackModel setting to configure up to three fallback models tried in order when the primary model is overloaded or unavailable; --fallback-model now also applies to interactive sessions
  • Added glob pattern support in deny rule tool-name position ("*" denies all tools); allow rules reject non-MCP globs, and unknown tool names in deny rules warn at startup
  • Hardened cross-session messaging: messages relayed via SendMessage from other Claude sessions no longer carry user authority — receivers refuse relayed permission requests, and auto mode blocks them
  • MAX_THINKING_TOKENS=0, --thinking disabled, and the per-model thinking toggle now disable thinking on models that think by default via the Claude API (3P providers unchanged)
  • Claude Code now retries a turn once on the fallback model when the API rejects an unexpected non-retryable error; auth, rate-limit, request-size, and transport errors still surface immediately
  • claude update now announces the target version before downloading instead of going silent
  • claude agents: typing a URL into the list now filters to the session whose first prompt contained it
  • Fixed a recurring "image could not be processed" error and extra token usage when an unprocessable image was sent in a session
  • Fixed remote sessions becoming permanently stuck when a brief backend disruption occurred during worker registration at startup …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Claude Opus 4.1 wird eingestellt

Das Modell Claude Opus 4.1 (claude-opus-4-1-20250805) ist als veraltet angekündigt und wird am 5. August 2026 in der Claude API abgeschaltet, empfohlen wird die Migration zu Claude Opus 4.8.

  • We announced the deprecation of the Claude Opus 4.1 model (claude-opus-4-1-20250805), with retirement on the Claude API scheduled for August 5, 2026. We recommend migrating to Claude Opus 4.8. Read more in Model deprecations.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.163: Versionsvorgaben, /plugin list und Hook-Erweiterungen

Neu sind die Managed Settings requiredMinimumVersion und requiredMaximumVersion, der Befehl /plugin list, ein Kopier-Shortcut in /btw und additionalContext für Stop-Hooks, dazu mehrere Fehlerbehebungen bei claude -p, Bash und Windows.

  • Added requiredMinimumVersion and requiredMaximumVersion managed settings — Claude Code refuses to start if its version is outside the allowed range and directs the user to an approved version
  • Added /plugin list command to list installed plugins, with --enabled/--disabled filters
  • Added a "c to copy" shortcut to /btw that copies the raw markdown answer to the clipboard, preserving formatting when pasted elsewhere
  • Hooks: Stop and SubagentStop hooks can now return hookSpecificOutput.additionalContext to give Claude feedback and keep the turn going without being labeled a hook error
  • Skills: added \$ escape syntax to include a literal $ before a digit in command bodies
  • stdio MCP servers now receive the same CLAUDE_CODE_SESSION_ID as hooks/Bash on --resume
  • Fixed claude -p hanging forever after its final result when a backgrounded command never exits — background shells are now stopped ~5s after the result once stdin closes
  • Fixed claude -p failing with "ANTHROPIC_API_KEY required" on Bedrock/Vertex/Foundry when CI=true and no Anthropic API key is set
  • Fixed bash commands failing under bazel and EDR-protected Go workflows: $TMPDIR was overridden to /tmp/claude-{uid} for all commands instead of only sandboxed ones (regression in 2.1.154)
  • Fixed Bash commands failing on Windows with "EEXIST: file already exists" on the session-env directory when it has the read-only attribute or is inside OneDrive …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.162: Neuerungen bei agents, /effort und Berechtigungsregeln

Version 2.1.162 ergänzt waitingFor in claude agents --json, bestätigt Einstellungen bei /effort, zeigt Remote Control als Footer-Pill, benennt Windsurf in Devin Desktop um und behebt Fehler bei Start, WebFetch- und Windows-Berechtigungsregeln sowie Interrupts.

  • claude agents --json now includes waitingFor showing what a waiting session is blocked on (e.g. permission prompt)
  • --tools: explicitly listing Grep/Glob now provides the dedicated search tools on native builds with embedded search (previously these names were silently ignored)
  • /effort now confirms when your chosen level will persist as the default for new sessions
  • Clicking a slash command in the autocomplete menu now fills it into your prompt instead of running it immediately; press Enter to run
  • Remote Control now shows as a persistent footer pill (with a link to the session) instead of a startup message
  • Renamed Windsurf to Devin Desktop in the /ide menu, /terminal-setup, and /scroll-speed, following the editor's rebrand
  • Fixed a silent startup hang when the config directory is read-only or unwritable — Claude Code now starts with in-memory config and surfaces startup errors instead of showing a blank screen
  • Fixed WebFetch permission rules not being applied to built-in preapproved domains; explicit WebFetch(domain:...) deny/ask/allow rules now take precedence over the preapproved-host auto-allow
  • Fixed Windows permission rules never matching when spelled with backslashes (~\, \\server\share) or case-variant paths, and Read deny rules not hiding files from Glob/Grep results
  • Fixed an interrupt (Esc) sent at the very start of a turn being silently dropped in stream-json/SDK sessions, leaving the turn running with no "Interrupted" feedback …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.161: OTEL-Labels, /mcp-Ansicht und Fixes

Version 2.1.161 übernimmt OTEL_RESOURCE_ATTRIBUTES als Labels in Metriken, blendet in /mcp ungenutzte claude.ai-Connectors ein, lässt parallele Tool-Calls bei fehlgeschlagenem Bash-Befehl weiterlaufen und behebt mehrere Fehler.

  • OTEL_RESOURCE_ATTRIBUTES values are now included as labels on metric datapoints, so you can slice usage metrics by custom dimensions like team or repo
  • claude agents rows now show done/total before the detail when work is fanned out; peek shows the longest-running item
  • /mcp now collapses claude.ai connectors you've never signed in to behind a "Show unused connectors" row
  • Parallel tool calls: a failed Bash command no longer cancels other calls in the same batch — each tool returns its own result independently
  • Fullscreen mode: clipboard now uses wl-copy/xclip/xsel on Linux when available, copies to both the clipboard and PRIMARY selection for middle-click paste, and the "hold {key} for native selection" hint now shows the correct key per terminal
  • Fixed the /effort dialog, workflow animations, and prompt keyword shimmer not honoring the "Reduce motion" setting
  • Fixed forceLoginOrgUUID/forceLoginMethod managed-settings policies blocking third-party provider sessions (Bedrock, Vertex, Foundry, Mantle) alongside the org pin (regression in 2.1.146)
  • Fixed background subagent output corrupting claude -p stdout when using --output-format text or json
  • Fixed /usage-credits starting a re-login for Team and Enterprise admins instead of pointing to the organization's usage settings page
  • Fixed /autofix-pr reporting "cannot run on the default branch" when the session is inside a git worktree or another repository …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.160: Mehr Rückfragen bei sensiblen Dateien, Fixes

Claude Code fragt nun vor dem Schreiben in Shell-Startdateien und ~/.config/git/ sowie im acceptEdits-Modus vor Build-Tool-Konfigurationsdateien nach, grep erfüllt die Read-vor-Edit-Prüfung, und mehrere Fehler bei Hintergrundsessions und WSL wurden behoben.

  • Added a prompt before writing to shell startup files (.zshenv, .zlogin, .bash_login) and ~/.config/git/, which could otherwise lead to unintended command execution
  • acceptEdits mode now prompts before writing build-tool config files that grant code execution (.npmrc, .yarnrc*, bunfig.toml, .bazelrc, .pre-commit-config.yaml, .devcontainer/, etc.)
  • Edit no longer requires a separate Read after viewing a file with grep: single-file grep/egrep/fgrep commands now satisfy the read-before-edit check
  • Fixed copy-on-select not writing to the Windows clipboard on WSL — now uses PowerShell interop instead of OSC 52, which terminals like MobaXterm don't support
  • Fixed restoring a completed session from claude agents dropping chat history and re-running the original prompt
  • Fixed background sessions re-attached after overnight retire losing their conversation and re-running the original prompt
  • Fixed claude --bg occasionally failing with "socket missing" when the background daemon was cold-starting on a loaded machine
  • Fixed an issue on Windows where the directory a background session was started in could not be deleted after claude rm until the background daemon exited
  • Fixed background agents that resumed work being shown under Completed in the agents list
  • Fixed claude agents freezing for several seconds when returning to the session list due to the auto-updater re-checking on every exit …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Advisor-Tool mit max_tokens; keine Abrechnung bei leeren Refusals

Das Advisor-Tool unterstützt jetzt den Parameter max_tokens, um die Ausgabe des Advisor-Modells pro Aufruf zu begrenzen, und in der Claude API werden Anfragen mit stop_reason: "refusal" ohne generierte Ausgabe nicht mehr berechnet.

  • The advisor tool now supports a max_tokens parameter to cap the advisor model's output per call, reducing latency and output token cost for workloads that don't need full-length advisor responses. Set tools[].max_tokens on the advisor tool definition; see Capping advisor output.
  • On the Claude API, you are no longer billed for a request when it returns stop_reason: "refusal" without Claude having generated any output. See Streaming refusals for detecting and handling refusals.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude von Anthropic

Admin-Berechtigungen für benutzerdefinierte Rollen

Enterprise-Pläne können jetzt Admin-Berechtigungen über benutzerdefinierte Rollen verwalten, z. B. für Abrechnung oder Datenschutz.

Enterprise plans can manage admin permissions with custom roles

We extended the existing custom roles framework by adding admin permissions. Admin permissions give members access to specific administrative areas, like billing or privacy, without the need to make them Owners. For more information, see Manage custom roles on Enterprise plans.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code Version 2.1.159

Version 2.1.159 enthält nur interne Infrastrukturverbesserungen ohne für Nutzer sichtbare Änderungen.

  • Internal infrastructure improvements (no user-facing changes)

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.158: Auto mode auf Bedrock, Vertex und Foundry

Auto mode ist auf Bedrock, Vertex und Foundry für Opus 4.7 und Opus 4.8 verfügbar und wird mit CLAUDE_CODE_ENABLE_AUTO_MODE=1 aktiviert.

  • Auto mode is now available on Bedrock, Vertex, and Foundry for Opus 4.7 and Opus 4.8. Opt in by setting CLAUDE_CODE_ENABLE_AUTO_MODE=1

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.157: Plugins in .claude/skills und neue Plugin-Befehle

Plugins in .claude/skills werden automatisch geladen, claude plugin init <name> erstellt ein Plugin-Grundgerüst, /plugin bekommt Autovervollständigung, und es gibt weitere Verbesserungen bei claude agents, Worktrees und Telemetrie sowie mehrere Fehlerbehebungen.

  • Plugins in .claude/skills directories are now automatically loaded, no marketplace required
  • Added claude plugin init <name> to scaffold a new plugin in .claude/skills
  • Added autocomplete for /plugin arguments: subcommands, installed plugin names, and plugins from known marketplaces
  • claude agents: the agent field in settings.json is now honored for dispatched sessions, with --agent <name> to override it
  • EnterWorktree can now switch between Claude-managed worktrees mid-session
  • tool_decision telemetry events now include tool_parameters (bash commands, MCP/skill names) when OTEL_LOG_TOOL_DETAILS=1
  • Worktrees managed by Claude are now left unlocked when the agent finishes, so git worktree remove/prune can clean them up
  • Fixed unprocessable images (zero-byte, corrupt) attached via paste, MCP, or dialog crashing the request instead of becoming a text placeholder
  • Fixed sandbox network permission prompts appearing in auto and bypass-permissions mode when using the desktop app, IDE extensions, or SDK
  • Fixed claude agents completed sessions not retiring when an idle subagent was still parked or had leaked a backgrounded shell
  • Fixed claude agents pressing Esc not cancelling a slow "opening…", leaving the list unresponsive
  • Fixed background agent worktrees under .claude/worktrees/ being orphaned after the 30-day job retention sweep
  • Fixed background sessions re-attached after a sleep/wake not telling the model the correct date …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.156: Fix für Thinking-Blöcke bei Opus 4.8

Behoben wurde ein Problem bei Opus 4.8, bei dem veränderte Thinking-Blöcke zu API-Fehlern führten.

  • Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Managed-Agents-Funktionen jetzt auf Claude Platform on AWS

Webhooks, Multiagent Orchestration und Self-hosted Sandboxes von Claude Managed Agents sind jetzt auf Claude Platform on AWS verfügbar, inklusive neuer IAM-Aktionen und der Managed Policy AnthropicSelfHostedEnvironmentAccess.

Originalquelle(öffnet in neuem Tab)Problem melden

Ähnlich wie Anthropic, mit neuen Einträgen