Claude docs changes for June 6th, 2026 [diff]

Executive Summary

  • New fallbackModel setting in v2.1.166 lets you configure up to three fallback models tried in order when the primary model is overloaded or unavailable
  • New requiredMinimumVersion/requiredMaximumVersion managed settings allow organizations to block Claude Code from starting if the running version is outside an approved range — stronger than the existing minimumVersion floor
  • Stop and SubagentStop hooks now support additionalContext for non-error feedback that continues the conversation without triggering a hook error notification
  • Claude Opus 4.1 is now marked as deprecated across API documentation; Claude Opus 4 is marked as retired on Amazon Bedrock
  • A new api_refusal telemetry event lets operators track API refusal frequency separately from errors

New Claude Code versions

2.1.166

New features

  • 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 agents: typing a URL into the list now filters to the session whose first prompt contained it

Existing feature improvements

  • 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

Major bug fixes

  • 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
  • Fixed flickering in JetBrains IDE terminals (IntelliJ, PyCharm, WebStorm, etc.) on 2026.1+ by enabling synchronized output
  • Fixed Shift+non-ASCII characters (e.g. Shift+ä → Ä) being dropped in terminals using the Kitty keyboard protocol (WezTerm, Ghostty, kitty)
  • Fixed PowerShell command validation occasionally hanging far past its time budget on Windows when a killed process's children held its output pipes
  • Fixed orphaned claude --bg-pty-host processes spinning at 100% CPU after the daemon dies while connected on macOS
  • Fixed managed settings with an invalid entry silently disabling enforcement of their remaining valid policies
  • Fixed managed-settings allowedMcpServers/deniedMcpServers predicates not matching when they use ${VAR} references
  • Fixed background agent sessions that entered a git worktree crash-looping with "No conversation found" when reopened from claude agents
  • Fixed duplicated thinking text in the Ctrl+O transcript view while streaming

2.1.167

Major bug fixes

  • Bug fixes and reliability improvements

Claude Code changes

Changed documents

Admin setup [Source]

  • New requiredMinimumVersion/requiredMaximumVersion managed settings added to the capabilities table — blocks Claude Code from starting when outside the approved version range, which is stronger than minimumVersion (which only prevents downgrades). [line 66] [Source]

Amazon Bedrock [Source]

  • Clarified that model aliases resolve to Claude Code's built-in default for Bedrock (which can lag the newest release), not simply "the latest version". [line 188] [Source]

Claude Platform on AWS [Source]

  • Added a new enterprise/sales call-to-action section at the top of the page. [lines 4-6] [Source]
  • Clarified that the opus alias resolves to Opus 4.7 by default on Claude Platform on AWS.

Commands [Source]

  • /plugin now documented with subcommand support (list, install, enable, disable). [line 234] [Source]
  • /reload-plugins now supports --force flag; without it, the command warns and holds when the reload would invalidate the prompt cache. [line 242] [Source]

Discover plugins [Source]

  • New /plugin list command documented for listing installed plugins without opening the menu; supports --enabled and --disabled filters. [lines 268-273] [Source]

Environment variables [Source]

  • CLAUDE_CODE_FORK_SUBAGENT now accepts 0 to explicitly disable fork subagents, overriding any server-side staged rollout. [line 286] [Source]
  • New CLAUDE_CODE_SYNC_SKILLS_INSTALL_TIMEOUT_MS env var added — bounds the mid-session skills resync triggered when the host requests a skill reload. [line 303] [Source]
  • CLAUDE_CODE_TMPDIR clarified: the short fallback $TMPDIR for long paths only applies to sandboxed Bash; unsandboxed Bash inherits your shell's $TMPDIR unchanged. [line 309] [Source]

Headless mode [Source]

  • New "Background tasks at exit" section: background Bash tasks started during a claude -p run are terminated ~5 seconds after Claude returns its final result and stdin closes. [lines 48-51] [Source]

Hooks guide [Source]

  • Expanded if field documentation with a detailed matching table showing exactly when hooks fire for $(), backtick substitutions, and compound commands. [lines 20-30] [Source]
  • Clarified that the if filter fails open (hook runs) when the Bash command cannot be parsed, and that the permission system should be used for hard allow/deny rather than hooks.

Hooks reference [Source]

  • Expanded Bash if matching table with behavior for leading VAR=value assignments, $(), and backtick patterns. [lines 52-60] [Source]
  • Stop and SubagentStop hooks now support hookSpecificOutput.additionalContext as a non-error way to give Claude feedback that keeps the conversation going without showing a hook error notification. [lines 103-120] [Source]
  • prompt hook field now supports backslash-escaping $ to include literal dollar signs in prompts. [line 69] [Source]

Interactive mode [Source]

  • New c key in the /btw overlay copies the answer to clipboard as raw Markdown (avoids hard-wrapped terminal rendering from mouse selection). [line 133] [Source]

Microsoft Foundry [Source]

  • Clarified that model aliases resolve to Claude Code's built-in default for Foundry and that Foundry has no startup model check — requests fail if the default model is unavailable. [line 155] [Source]

Monitoring usage [Source]

  • New claude_code.api_refusal telemetry event for tracking stop_reason: "refusal" responses, which arrive on a successful stream rather than as HTTP errors. [lines 183-195] [Source]
  • MCP server connection events now include is_plugin, plugin_id_hash, and plugin.name attributes, letting operators identify plugin-provided MCP servers in logs without exposing third-party plugin names. [lines 201-203] [Source]

Plugins reference [Source]

  • Documented that /plugin list is available within interactive sessions, with --enabled/--disabled filters and ls as a shorthand. [line 232] [Source]

Prompt caching [Source]

  • Documented that as of v2.1.163, /reload-plugins warns and holds instead of applying a reload that would trigger a full cache re-read; pass --force to proceed anyway. [line 246] [Source]

Settings [Source]

  • New requiredMinimumVersion and requiredMaximumVersion managed settings documented — Claude Code exits at startup if the running version is outside the approved range. [lines 280-281] [Source]
  • Git commit attribution format updated: the 🤖 Generated with Claude Code line has been removed; only the Co-Authored-By trailer remains. [lines 289-293] [Source]

Setup [Source]

  • Documented the distinction between minimumVersion (constrains updates only) and the new requiredMinimumVersion/requiredMaximumVersion (blocks startup entirely). [line 307] [Source]

Skills [Source]

  • Documented backslash escaping for $ in skill content — \$1.00 renders as $1.00 without triggering argument substitution. [line 319] [Source]

Sub-agents [Source]

  • CLAUDE_CODE_FORK_SUBAGENT=0 now explicitly disables fork mode everywhere, including any server-side staged rollout. [line 341] [Source]
  • Fork mode may now be enabled by default in interactive sessions as part of a staged rollout. [line 341] [Source]

Subagents in the SDK [Source]

  • New initialPrompt parameter added to AgentDefinition — auto-submitted as the first user turn when the agent runs as the main thread agent. [line 41] [Source]
  • Resuming subagents section rewritten: the agentId is now found in the Agent tool result text block; built-in Explore and Plan agents are one-shot and omit the trailer. [lines 70-83] [Source]
  • Resume example replaced: now shows Python (custom endpoint-finder agent) instead of TypeScript. [lines 85-176] [Source]

API changes

Changed documents

Adaptive thinking [Source]

  • No significant content changes (email link obfuscation updated).

Batch processing [Source]

  • Claude Opus 4.1 marked as deprecated in the pricing table. [line 91] [Source]

Claude in Microsoft Foundry [Source]

  • Added a lifecycle terms note linking to the model deprecations page. [line 248] [Source]
  • Claude Opus 4.1 marked as Deprecated with retirement date of August 5, 2026. [line 258] [Source]

Claude on Amazon Bedrock (legacy) [Source]

  • Lifecycle dates note updated: specific Bedrock retirement dates removed; now directs users to Amazon Bedrock's model lifecycle page for current dates. [line 78] [Source]
  • Claude Opus 4.1 marked as Deprecated; Claude Opus 4 changed to Retired (was Deprecated with May 31, 2026 date) with all regional availability removed. [lines 85-93] [Source]

Claude on Vertex AI [Source]

  • Vertex AI documentation links updated to new URL (docs.cloud.google.com). [lines 12, 54, 274]
  • Lifecycle dates note updated: specific Vertex AI retirement dates removed; now directs users to Google Cloud's documentation for current dates. [line 57] [Source]
  • Claude Opus 4.1 marked as Deprecated. [line 73] [Source]

Code execution tool [Source]

  • Claude Opus 4.1 marked as deprecated in the model availability table. [line 28] [Source]

Computer use tool [Source]

  • Claude Opus 4.1 marked as deprecated in the beta header compatibility table. [line 10] [Source]

Context editing [Source]

  • Claude Opus 4.1 marked as deprecated in the thinking block preservation table. [line 42] [Source]

Extended thinking [Source]

  • Anthropic sales contact link changed from obfuscated email to mailto:sales@anthropic.com. [line 101] [Source]
  • Claude Opus 4.1 marked as deprecated in multiple sections covering interleaved thinking and thinking block preservation. [lines 391, 601]

Handle streaming refusals [Source]

Handling stop reasons [Source]

  • Claude Opus 4.1 marked as deprecated in refusal stop reason guidance. [line 297] [Source]

Multilingual support [Source]

  • Column header corrected from "Claude Opus 4.11" to "Claude Opus 4.1 (deprecated)1" in the benchmark table. [line 15] [Source]

Prompt caching [Source]

  • Claude Opus 4.1 marked as deprecated in pricing and minimum cacheable prompt length tables. [lines 77, 252]

Search results [Source]

  • Claude Opus 4.1 marked as deprecated in the model availability list. [line 17] [Source]

Tool use overview [Source]

  • Claude Opus 4.1 marked as deprecated in the tool use token overhead table. [line 86] [Source]