Anthropic

Claude -p and Agent SDK sessions with no permission mode now start in default mode on third-party providers with telemetry off or on a fresh install, and fork subagents are on by default across the CLI, Agent SDK, desktop app, and VS Code. The Read tool no longer loads image files of any size into memory and refuses image sources over 128 MB, and idle compaction can be toggled off from a new row in /config.

Vim mode gains the % motion to jump to the matching bracket, mods get a multi-line rows input field, and CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS now bounds unattended retry at far-off usage limits. Fixed quitting removing a WorktreeCreate hook's worktree without asking, and sign-in refresh timeouts that caused unexpected sign-outs after short commands like claude auth status exited mid-refresh.

The Compliance API now returns the text each org member saved as Instructions for Claude and Global instructions, in beta for Claude Enterprise via GET /v1/compliance/organizations/{org_uuid}/user_preferences with the read:compliance_user_data scope. Fast mode is out of research preview for Claude Opus 5.5, with the fast-mode-2026-02-01 beta header no longer required, a default rate limit added for Start, Build, and Scale tiers, and availability on Claude in Microsoft Foundry for Azure deployments.

Adds mod authoring capabilities including virtualText prompt decorations, agentId transcript views, the prompt.change hook, and prompt/model rewriting in the agent.spawn hook, plus OpenTelemetry GenAI semantic-convention attributes on trace spans. The release also fixes more than 35 issues across subagent tracking, worktree handling in reftable repositories, resume/compaction message loss, and cloud session policy handling.

What's changed

Anthropic published an update on its preparations for the 2026 US midterms, following earlier election integrity preparations shared this year.

• OpenTelemetry export launched in beta: trace Messages API requests and Claude Managed Agents sessions in your observability backend. SDK emits spans in Python, TypeScript, C#, Go, Java, PHP, and Ruby.
• Claude Managed Agents scheduled deployments are now available on Claude…

Anthropic engineering describes redesigning source control at Anthropic.

Managed-settings PreToolUse and prompt hooks that block a tool call now refuse it and end the turn, and Edit and NotebookEdit no longer replace every non-ASCII character in files that are not valid UTF-8 — such edits are refused instead. Adds a code key to the Claude apps gateway's managed.policies[], autoCompactWindow for subagents, CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL, an allow_large option for the Read tool, plus a long list of fixes across MCP servers, plugins, self-hosted runners, cloud sessions, and Windows.

Claude Managed Agents can now use dynamic workflows in beta via the managed-agents-2026-04-01 header, where the agent writes a workflow program that runs many agents in phases and combines results while the server runs it in the background. Enable with multiagent: {"type": "multiagent_20261001", "workflows": {"type": "enabled"}} and follow runs via workflow_run.* events on the session event stream.

Command and HTTP hooks support onFailure: "block" so a hook that fails to start, times out, or exits unexpectedly blocks the action instead of allowing it, and Claude apps gateway upstreams now accept an optional models list that limits which models are sent there, including on failover. Also fixed context-1m beta rejection breaking all requests on [1m] models, remote MCP reconnects looping against servers that drop connections, and claude -p text output dropping earlier responses when background work started another turn.

Fixed an issue where prompt and agent hooks written as instructions, such as "Block commands that...", allowed what they should block. Improved how prompt hooks on Stop and SubagentStop written as instructions are judged, so Claude is less likely to stop early.

Anthropic introduces its Cyber Mission.

Anthropic updated its Usage Policy.