Zum Inhalt springen

Anthropic Release Notes

632 Einträge aus 4 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 aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Neuer Eintragstyp thinking_mismatch_allowed in input_transformations

Mit dem Beta-Header thinking-binding-controls-2026-08-01 kennt das Antwortfeld input_transformations den neuen Eintragstyp thinking_mismatch_allowed, der Thinking-Blöcke meldet, die die Präfixprüfung nicht bestanden haben, aber unverändert beim Modell ankamen.

  • The Messages API can now compact a conversation on demand on the Claude API, in beta with the compact-2026-09-04 beta header. Send the top-level compaction parameter, and the API returns a signed compaction block that summarizes the messages you sent. On later requests, send that block first, in place of those messages. You choose when to compact, the request can run in the background, and you can keep recent turns word for word after the summary. On models with preserved thinking, the thinking in those kept turns can stay valid.
  • With the thinking-binding-controls-2026-08-01 beta header, the input_transformations response field gains a second entry type, thinking_mismatch_allowed. It names a thinking block that failed the prefix check on a request where the API doesn't enforce that check: on Claude Fable 5.1, for example, a request from an account created before August 31, 2026, with prefix_mismatch_behavior unset. The block still reaches the model unchanged. Log these entries to find history edits in production traffic before you opt into enforcement. See Set the mismatch behavior and read input_transformations.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.270

Version 2.1.270 behebt eine Regression aus 2.1.269, bei der schreibgeschützte git-Befehle in Bash nach längerer Sitzungsdauer unerwartet um Erlaubnis fragten.

  • Fixed read-only git commands in Bash unexpectedly asking for permission after a session had been running for a while (regression in 2.1.269)

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.269

Version 2.1.269 ergänzt claude plugin eval, /output-style, einen Diff geänderter Dateien im Bash-Ergebnis, neue OpenTelemetry- und Gateway-Optionen sowie CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS und behebt Probleme mit der Prompt-Cache-Wiederverwendung.

  • Added claude plugin eval: run a plugin's eval suite against Claude Code and get scored, reproducible results (JSON + HTML report); see claude plugin eval --help
  • Added /output-style [name] to list and switch output styles, including over Remote Control and in cloud and other headless sessions
  • Added a diff of the files a Bash command changed to the Bash tool result when the Bash tool handles file edits (setting bashEditDiffEnabled)
  • Added OTEL_METRICS_INCLUDE_REPOSITORY to tag OpenTelemetry metrics and events with vcs.* repository attributes; commit events get vcs.ref.head.* with OTEL_LOG_TOOL_DETAILS
  • Added CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS to extend the LLM gateway /v1/models discovery timeout (default 3s)
  • Added a spinner tip suggesting /focus for a view with just your prompt, a one-line work summary, and the response
  • Added CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS (1–256) to raise the Workflow tool's per-run concurrent agent limit for inference-bound fan-outs
  • Fixed the prompt cache being partially invalidated on the turn after a response was cut off at the output-token limit and automatically resumed
  • Fixed a case where resuming a session after interrupting Claude mid-thought could change how earlier context was re-sent, hurting prompt-cache reuse …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.268

Das Claude apps gateway übermittelt mit pricing: in gateway.yaml Preise an Clients und warnt bei leerer access_control.allow_cidrs, außerdem gibt es die Managed Setting gatewayInternalNetworks, neue Optionen für claude self-hosted-runner, claude auth status --json und claude plugin ... --json, Tab-Icons für veröffentlichte Artifacts sowie Fixes für HTTP-400-Fehler auf Anthropic-kompatiblen Endpunkten und hängendes WebFetch.

  • Added to the Claude apps gateway: with pricing: set in gateway.yaml, signed-in Claude Code clients receive the same rates through managed settings, so /cost and telemetry match the spend meter
  • Added a startup warning for gateways when access_control.allow_cidrs is empty, and a one-time warning the first time a request arrives from a public address
  • Added the gatewayInternalNetworks managed setting, letting administrators allow /login to a Claude apps gateway on their organization's own public IPv4 block
  • Added claude self-hosted-runner --remove-session-state (default off): delete each session's per-session directories under <base-dir>/_sessions/ when the session ends
  • Added configDirectory to the output of claude auth status --json
  • Added --json to claude plugin install, uninstall, update, enable and disable, and errorDetails/noteDetails to each row of claude plugin list --json
  • Added browser-tab icons for published artifacts, chosen by Claude to match each page
  • Fixed every turn failing with HTTP 400 on third-party Anthropic-compatible endpoints (ANTHROPIC_BASE_URL) since 2.1.265: a regex in the Artifact tool's input schema that those endpoints reject
  • Fixed WebFetch hanging indefinitely on a server that keeps the response open without finishing; a fetch now fails after 300 seconds. Set CLAUDE_CODE_WEBFETCH_DEADLINE_MS to override the deadline (0 turns it off) …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

ant CLI 1.32.0: Verbindung zu Managed-Agents-Sessions per sessions connect

Version 1.32.0 der ant CLI ergänzt ant beta:sessions connect, womit sich das Terminal mit einer Managed-Agents-Session verbinden lässt, um sie live zu verfolgen, Nachrichten zu senden und Tool-Aufrufe freizugeben oder abzulehnen.

  • Claude Managed Agents permission policies now include auto: the server evaluates each agent or MCP tool call and runs it, denies it, or pauses for your approval. agent.tool_use and agent.mcp_tool_use events report how each call was evaluated in an evaluation field alongside evaluated_permission. See Let the server evaluate each call with auto.
  • Version 1.32.0 of the ant CLI adds ant beta:sessions connect, which attaches your terminal to a Claude Managed Agents session. You can follow the session live, send messages, and allow or deny tool calls that are waiting for approval. Pass --web to serve the Claude Console's session viewer locally and open the session there instead. See Connect to a Managed Agents session from your terminal.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude von Anthropic

Smart reports als Beta für Claude Enterprise

Smart reports sind als Beta für Claude Enterprise verfügbar und analysieren, wie ein Team Claude nutzt, welche Arbeit entsteht, was sie kostet, wo es Reibung gibt und welche wiederkehrenden Muster sich als gemeinsame Skills eignen.

Smart reports (beta)

We’ve launched smart reports, which analyze how a team uses Claude and report on the work getting done, what it costs, where sessions run into friction, and which repeated patterns are worth packaging as shared skills. Smart reports are available in beta on Claude Enterprise plans. Learn more in Get started with smart reports.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.267

Neu sind die Einstellung maxEffortLevel zur Begrenzung des Effort-Levels und --system-prompt-snapshot off, dazu kommen Fixes unter anderem für Cowork-Aufgaben, mobile Anzeige, tmux/ssh, Auto-Modus und eine Marketplace-Pfadprüfung.

  • Added maxEffortLevel setting (top-level or per model under modelSettings): caps the effort level on every provider, including Bedrock, Vertex and Foundry; users can still pick a lower level
  • Added --system-prompt-snapshot off to render the system prompt fresh on every request instead of reusing the conversation's recorded prompt (for iterating on prompt text)
  • Fixed Cowork scheduled tasks in the cloud failing at startup for organizations whose managed settings require sandboxing
  • Fixed /context and other local command output rendering blank on mobile clients
  • Fixed shift+enter and option+backspace not working after reconnecting to a tmux or ssh session inside an agent view
  • Fixed the dim last-prompt header not appearing at the top of the conversation when scrolling up in fullscreen mode
  • Fixed Workflow agent() calls with large output schemas being refused in auto mode instead of being checked by the safety classifier
  • Fixed a case where a marketplace entry path containing a backslash could bypass the containment check for fetched marketplaces on macOS and Linux
  • Fixed expired AWS or Google Cloud credentials under a host app such as Claude Desktop retrying ten times with a generic "request failed" before the re-authenticate error appeared
  • Fixed resuming a session after /compact or another slash command ran via -p --resume: a spurious "Continue from where you left off." turn is no longer inserted …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Cache diagnostics: Fingerabdruck nur noch mit diagnostics-Objekt gespeichert

Bei Cache diagnostics speichert die API den Fingerabdruck einer Anfrage nur noch, wenn sie das diagnostics-Objekt enthält, sodass dieses bei jedem Turn mitgesendet werden sollte.

  • For cache diagnostics, the API now stores a request's fingerprint only when the request includes the diagnostics object. A request that sends only the cache-diagnosis-2026-04-07 beta header is still accepted, but no fingerprint is stored. A later turn that points previous_message_id at it reports previous_message_not_found. Include diagnostics on every turn, with "previous_message_id": null on the first.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.266

Behebt eine Regression aus 2.1.265, bei der CLAUDE_CODE_USE_GATEWAY allein die Cloud-Gateway-Anmeldung erzwang und Anfragen mit "Not signed in to the Cloud gateway" scheiterten; die Variable wird allein wieder ignoriert.

  • Fixed a 2.1.265 regression affecting LLM-gateway and proxy setups: the undocumented CLAUDE_CODE_USE_GATEWAY environment variable, previously ignored unless ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN were both set, began forcing Cloud-gateway sign-in on its own in 2.1.265, so configurations that set it alongside an API key, apiKeyHelper, or custom auth headers failed every request with "Not signed in to the Cloud gateway". The variable on its own is ignored again; no configuration change is needed

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.265

Neu sind user.email und user.groups in der Telemetrie über das Claude apps gateway, --plugin-dir auf einen Plugin-Ordner sowie ein 1-GB-Limit für gespeicherte Tool-Ergebnisse, zudem gibt es mehrere Fixes zu Prompt-Cache, Resume, /model opusplan[1m], Anzeige und Plugin-Pfaden.

  • Added user.email and user.groups to the telemetry Claude Desktop and Cowork send through a Claude apps gateway, matching terminal sessions
  • Added support for pointing --plugin-dir at a folder of plugins: each child folder with a manifest loads, and children added or removed while running are picked up
  • Added a 1 GB cap on tool results saved to disk; the in-conversation preview says when a saved file was truncated
  • Fixed resuming a foreground-spawned subagent changing its tool list and system prompt prefix, which broke prompt-cache reuse for that agent
  • Fixed agent teammates and resumed subagents moving SubagentStart hook context and preloaded skills out of the prompt prefix on later turns, which broke prompt-cache reuse
  • Fixed resume after the previous process died while a tool was running: the last prompt is no longer rewritten, and the interrupted tool call is kept and marked interrupted
  • Fixed /model opusplan[1m] being rejected with "Model not found"
  • Fixed syntax-highlighted code in permission prompts and messages sometimes omitting a character after a Ruby ?, Erlang $, or Perl $ sigil
  • Fixed the fullscreen transcript jumping by one row whenever the slash-command or @-file suggestion list opened or closed
  • Fixed a plugin path containing a backslash bypassing the symlink containment check on macOS and Linux
  • Fixed plugin directories whose names begin with two dots being wrongly refused as outside the plugin root …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.261

Neu sind eine "Organization policy"-Zeile in /status und claude doctor, die Einstellungen bashOutputMaxChars und taskOutputMaxChars, --append-subagent-system-prompt-file und /skill-doctor, außerdem Fixes für Eingabe, /add-dir, Bedrock-Setup und Resume.

  • Added an "Organization policy" line to /status and claude doctor that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint through
  • Added bashOutputMaxChars and taskOutputMaxChars settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters
  • Added --append-subagent-system-prompt-file to read the subagent system prompt from a file, for prompts too large to pass on the command line
  • Added /skill-doctor to show which loaded skills go unused and what they cost in context, so you can prune them
  • Fixed typed or pasted characters occasionally landing out of order or being dropped during fast input or key repeat
  • Fixed /add-dir <subdirectory> printing a false "couldn't be resolved" error when the working directory is on a /net automount
  • Fixed the Bedrock setup wizard hanging when AWS or an AWS credential helper never responds (it now times out with a clear error), and its model checks failing behind a TLS-inspecting proxy
  • Fixed cloud sessions discarding a plugin synced from claude.ai when managed settings force-enable it in enabledPlugins, then falling back to a marketplace clone that could fail
  • Fixed being unable to delete the character immediately before an inline [Image #N] chip in the prompt input
  • Fixed resuming a session losing hook output and other context around parallel tool calls, which changed the resumed request …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.260

Neu sind ein Diff-Panel im Fullscreen-Modus (/diff), Hinweise auf Ursachen von Prompt-Cache-Misses in /cost, /reload-plugins und /advisor in Headless-Sessions sowie Gateway-Erweiterungen und Fixes für Berechtigungsregeln.

  • Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with /diff
  • Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to /cost and the status line's prompt_cache field
  • Added /reload-plugins to headless sessions, so it appears in the Claude Code Desktop and SDK command lists
  • Added a text form of /advisor (/advisor, /advisor <model>, /advisor off) for the desktop app, Remote Control, and other headless (-p/Agent SDK) sessions
  • Added oidc.scope_on_refresh to the Claude apps gateway for IdPs that return an id_token on refresh only when asked for openid again
  • Added Claude apps gateway support for newer Claude Desktop keys in desktop policy blocks, including userPluginMarketplacesEnabled and userPluginUploadsEnabled
  • Fixed Edit/Write/Read permission rules whose path contains parentheses being dropped as invalid or ignored by the Bash sandbox, which left "read-only" folders writable
  • Fixed one file permission rule with an uncompilable pattern (e.g. an unclosed [) making every file edit fail with Invalid regular expression; such a deny rule now guards the literal path it spells
  • Fixed Bash permission checks auto-approving zsh commands that hide a command substitution in a REPORTTIME, REPORTMEMORY or DIRSTACKSIZE assignment; these now prompt for approval …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Per-message-Effort-Änderungen in der Beta jetzt auch auf Google Cloud

Per-message-Effort-Änderungen sind in der Beta nun mit dem Header mid-conversation-output-config-2026-07-01 auch auf Google Cloud für Claude Fable 5.1, Claude Mythos 5.1 und Claude Opus 5 verfügbar.

  • Version 1.30.0 of the ant CLI adds ant apply, which creates and updates agents, environments, skills, memory stores, and deployments from files in your repository. Describe each resource in a file, run ant apply, and approve the plan it prints. Commit the claude-lock.json lockfile it writes so that later runs, on your machine or in CI, update the same resources instead of creating new ones. See Manage resources as code with ant apply.
  • Per-message effort changes, in beta, are also available on Google Cloud for Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5, with the same mid-conversation-output-config-2026-07-01 beta header.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.259

Neu sind die Managed Setting managedMcpServers, --permission-prompts none für Headless-Hosts, Erkennung von glab mr-Befehlen und --json für claude plugin validate, dazu Fixes für ~/.claude.json, Deny-Regeln, Prompt-Cache und Fullscreen-Modus.

  • Added managedMcpServers managed setting: organizations can provide HTTP/SSE MCP servers to every user (same entry shape as .mcp.json); entries that name a command to run are skipped
  • Added --permission-prompts none for unattended headless hosts: anything that would prompt is denied automatically while the active permission mode (including auto mode) keeps deciding
  • Added recognition of glab mr create/merge/close/reopen/note/update so GitLab merge requests show as MR !N in the collapsed tool summary and refresh the footer MR badge
  • Added --json to claude plugin validate for a machine-readable validation report
  • Fixed concurrent sessions silently reverting each other's ~/.claude.json changes — workspace trust no longer resets and MCP/project state is no longer lost when running many sessions at once
  • Fixed a conversation whose thinking was rejected once being rejected again on every later turn
  • Fixed Bash Read() deny rules not covering files given as option values (--ignore-revs-file=.env, -f.env, @file), git diff/git grep file operands, or cd DIR && cat FILE compounds; grep -r/cp -r over a directory holding a denied file now asks
  • Fixed the prompt cache being invalidated when the OAuth token refreshed in sessions with telemetry disabled
  • Fixed fullscreen mode showing a blank conversation after a long turn with hundreds of tool calls …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.258

Behebt den Startfehler unter macOS 12 (Monterey) aus 2.1.255 sowie fehlschlagende Remote- und geplante Sessions nach einer erneut gesendeten Berechtigungsfreigabe.

  • Fixed Claude Code failing to launch on macOS 12 (Monterey), a regression introduced in 2.1.255
  • Fixed remote and scheduled sessions failing with "user messages must have non-empty content" after a re-sent permission approval could not be applied

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.257

Neu sind Claude Fable 5.1 (claude-fable-5-1) als Standard-Fable-Modell, die Einstellungen timeFormat und timeZone, eine Containment-Escape-Regel im Auto-Modus und CLAUDE_CODE_SUBAGENT_MODEL_FORCE, dazu weitere Ergänzungen und Fixes.

  • Added Claude Fable 5.1 (claude-fable-5-1), now the default Fable model — 1M context, $10/$50 per Mtok with $0.25/Mtok cache reads
  • Added "Time format" (timeFormat) and timeZone settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestamps
  • Added a Containment Escape rule to auto mode so cloud metadata-credential fetches, egress evasion, and cross-tenant reach are no longer auto-approved unless your environment marks them expected
  • Added CLAUDE_CODE_SUBAGENT_MODEL_FORCE to apply CLAUDE_CODE_SUBAGENT_MODEL (or the main model) to every subagent, ignoring per-spawn and agent-definition model overrides
  • Added s in /effort to change effort for the current session only, matching /model
  • Added a /doctor warning for stale sandbox mask files left by a killed session
  • Added a one-time prompt in auto mode before the first file read outside the working directories, with the option to block such reads (permissions.blockReadsOutsideWorkingDirectories)
  • Added support for a gateway-supplied description on discovered /model picker entries (CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY); entries without one still read "From gateway"
  • Fixed settings in a .claude/ folder created after startup not being picked up until restart …

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum aus der Quelle.

Erstmals gesehen am .

Claude Developer Platform von Anthropic

Claude Fable 5.1 und Claude Mythos 5.1 verfügbar

Claude Fable 5.1 (claude-fable-5-1) und Claude Mythos 5.1 (claude-mythos-5-1, für Project-Glasswing-Teilnehmer) sind mit 1M Token Kontextfenster, 128k Ausgabetokens und adaptivem Thinking zu 10 / 50 USD pro MTok und reduziertem Cache-Read-Preis von 0,25 USD verfügbar.

Originalquelle(öffnet in neuem Tab)Problem melden

Angaben zum Datum

Datum des passenden GitHub-Releases.

Erstmals gesehen am .

Claude Code von Anthropic

Claude Code 2.1.252

Behebt Fehler bei Bash-Befehlen auf manchen Macs, nicht gespeichertes "always allow", hängende Remote-Control-Sessions und zu große Hintergrund-Task-Benachrichtigungen.

  • Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs
  • Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet
  • Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded
  • Fixed background task notifications with very large failure output (for example git errors on a full disk) making the conversation exceed the API request size limit

Originalquelle(öffnet in neuem Tab)Problem melden

Ähnlich wie Anthropic, mit neuen Einträgen