Claude docs changes for October 10th, 2026 [diff]

Executive Summary

  • Claude Code 2.1.296 adds a code key to Claude apps gateway policies (also applied in Claude Desktop's Code tab), autoCompactWindow for subagents, and new environment variables for workflow subagent models and overloaded-retry delays
  • Hooks now have an onFailure: "block" option so a crashing, missing, or timed-out policy hook blocks the action instead of letting it through, and the hooks reference documents exit codes and stdout combinations in detail
  • The Managed Agents API reference gains a new multiagent_20261001 configuration (separately enabled advisor, subagents, and workflows) and full workflow run event types
  • The Agent SDK exposes a structured usage_report (SDKUsageReport) for /usage, and mods can call models directly with $.model.complete / $.model.fork, including prompt caching
  • New guidance on the output-token cost of drop_block in preserved thinking (up to +67% at max effort), and a Compliance API addition for downloading Claude Docs documents

New Claude Code versions

2.1.296

New features

  • Added a code key to the Claude apps gateway's managed.policies[]: same settings as cli, also applied in Claude Desktop's Code tab
  • Added autoCompactWindow to subagent frontmatter and --agents definitions
  • Added CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL to run every workflow agent on one model
  • Added CLAUDE_CODE_OVERLOADED_RETRY_MAX_DELAY_MS to set a longer maximum backoff for overloaded (529) retries
  • Added an allow_large option to the Read tool for reading a whole large text file in one call
  • Added a /plugin note when a plugin's hooks are left out because another enabled plugin has the same name
  • [Cloud sessions] Added a status filter to the Sessions and Runners lists on a self-hosted environment's Activity tab
  • [Claude Tag] Added creating, editing and deleting workspace and channel memory files on the Activity page's Memory tab

Existing feature improvements

  • Fullscreen mode underlines the link under the mouse pointer
  • Faster transcript toggle (ctrl+o) in code-heavy conversations via cached syntax highlighting
  • --debug now names unrecognized frontmatter fields in custom agent files and logs command hook command, plugin, outcome and duration
  • Auto mode shows a dim "Not run" row instead of a red error when its check had no usable answer
  • Clearer errors for refused cloud sessions and in Code Review admin settings
  • Sonnet 5.5 cache reads now priced at $0.10 per million tokens (was $0.20) in /cost, status line, --max-budget-usd and SDK cost figures
  • Default limit on MCP tool descriptions and server instructions raised from 2,048 to 4,096 characters
  • ← now stops a turn or ! command started while the session moves to the background
  • [VSCode] Claude in Chrome now asks before browser actions in every session, including @browser

Major bug fixes

  • Fixed managed-settings PreToolUse hooks denying with "continue": false and managed prompt hooks not ending the turn, and PostToolUse hooks not applying updatedMCPToolOutput
  • Fixed Bash permission checks auto-approving some commands that use BASH_ARGV0
  • Fixed Edit and NotebookEdit corrupting non-UTF-8 files (Windows-1252, Shift-JIS, GBK); such edits are now refused
  • Fixed a saved Claude apps gateway sign-in being ignored when forceLoginMethod is gateway with no forceLoginGatewayUrl (regression in 2.1.295)
  • Fixed headless sessions starting MCP servers that were switched off for the folder
  • Fixed Esc/interrupt during UserPromptSubmit hooks ending headless sessions or letting the unchecked prompt through
  • Fixed /code-review ending on a raw JSON array in cloud sessions, the Agent SDK and IDE integrations
  • Fixed $.agent.register succeeding from a stale mod hook after reload or removal
  • Fixed secret redaction missing some values in shared transcripts and debug logs
  • Windows: Fixed long PowerShell commands always prompting, stdio MCP servers being force-killed at shutdown, and plugin install failing for GitHub sources without an SSH key

Claude Code changes

Changed documents

agent-sdk/typescript [Source]

  • Added usage_report on SDKAssistantMessage and a new SDKUsageReport type: a structured copy of the /usage report (session cost totals, rate-limit meters, extra usage), experimental, requires Agent SDK v0.3.273+. [line 1435] [lines 2060-2130] [Source]
  • Documented size limits for pasted_content (1,000 entries) and inline_pastes (first 100 non-blank). [lines 1470-1474] [Source]
  • Interrupted-turn wording changed from "re-run" to "continues" for CLAUDE_CODE_RESUME_INTERRUPTED_TURN and resume_reason. [line 1691] [Source]
  • Added reason: "worker_restart" to SDKTaskNotificationMessage. [line 5188] [Source]
  • Workflow scriptPath is rejected when the session's tools don't include Read. [line 3240] [Source]

chrome [Source]

  • VS Code sessions show browser-action permission prompts as chat cards, with an option to allow the site. [line 106] [Source]
  • Uploads: Claude refuses credential-named files (.env, .pem, .key, .ssh), v2.1.293+. [line 171] [Source]
  • New troubleshooting: project settings can't turn on Chrome via CLAUDE_CODE_ENABLE_CFC, extension signed in to a different organization, and /chrome "Reconnect extension". [lines 260-290] [Source]

claude-apps-gateway-config [Source]

  • New code policy key (recommended) versus legacy cli; requires v2.1.296+ gateway and can't be mixed with cli/settings in one file. [lines 891-920] [Source]
  • New section on applying code settings in Claude Desktop's Code tab (requirements: desktop key, Desktop 2.9939.2+, client-side managed settings, HTTPS on a private network). [lines 1047-1070] [Source]
  • Telemetry: user identity attributes stamped from the gateway JWT, and handling user.groups changes during an open session. [line 1180] [lines 1286-1303] [Source]

env-vars [Source]

  • Added CLAUDE_CODE_ENABLE_CFC to start a CLI session with Chrome integration on or off. [line 280] [Source]

errors [Source]

  • Installation errors section moved to troubleshoot-install; index links updated. [line 184] [Source]
  • New entries: "Claude Code couldn't restart", invalid marketplace name, settings file that "does not load", "Plugin directory does not exist", and a /loop wakeup missed after restart. [line 3610] [Source]
  • Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS retry variable. [line 430] [Source]

hooks [Source]

  • New onFailure field ("continue" or "block") for command and HTTP hooks, v2.1.295+, with a new section "Block the action when a hook fails". [line 443] [lines 850-899] [Source]
  • Rewrote exit code output: success, blocking, and non-blocking outcomes, with a table by stdout type and exit code plus per-event exceptions. [lines 754-776] [Source]
  • Exit 2 blocks even when JSON is printed; "allow" cannot override it. [lines 796-803] [Source]
  • A timed-out command, http, or mcp_tool hook doesn't block the tool call. [line 847] [Source]
  • HTTP hooks: a non-2xx status is a non-blocking error; block via a 2xx response body. [line 953] [Source]
  • PermissionRequest hook exiting 2 without a decision leaves the flow unchanged; TaskCreated can block via exit 2 or JSON. [line 2010] [line 2518] [Source]

hooks-guide [Source]

  • New "Check what a hook did" section describing how success and errors appear in the transcript. [lines 1027-1038] [Source]
  • HTTP hook response status handling and onFailure: "block". [line 916] [Source]

interactive-mode [Source]

  • Vim mode: documented f/F/t/T character jumps and df/dt deletes. [line 185] [Source]

mcp [Source]

  • Documented claude mcp login <name> to run a server's OAuth flow from the shell. [line 786] [Source]

monitoring-usage [Source]

  • Mention-resolution events capped at 100 per prompt for agent and mcp_resource. [line 1087] [Source]

plugins/mods/api [Source]

  • New docs for mods calling models: $.model.complete versus $.model.fork, request contents comparison, sending one prompt, and prompt caching with cache: true blocks (v2.1.292+). [lines 68-166] [Source]

plugins/troubleshooting [Source]

  • New sections: invalid marketplace name, "does not load, so Claude Code ignores the whole file", and "Plugin directory does not exist". [line 230] [line 786] [line 898] [Source]

remote-control [Source]

  • New section "Authorize a connector again from your shell" using claude mcp login "<connector>" --no-browser and /mcp reconnect. [lines 347-375] [Source]

scheduled-tasks [Source]

  • Explained recurring-task jitter: a fixed per-task delay up to 30 minutes (table by frequency), and one-shot tasks at :00/:30 running up to 90 seconds early. [lines 164-182] [Source]

self-hosted-environments-configuration [Source]

  • New wrapper environment variables: CCR_SESSION_ACCOUNT_EMAIL, CLAUDE_RUNNER_CLIENT_PLATFORM, CLAUDE_CODE_REMOTE_SLACK_THREAD_URL/_TS, with guidance on defaults and quoting. [line 26] [Source]
  • Warning that backgrounding the child with a bare & severs stdin and breaks the session after ~30 minutes; fd 3 and stderr handling. [lines 55-69] [Source]
  • Checkout hook: CLAUDE_RUNNER_REPO_REF, .git verification, getting git credentials, and failure behavior by repository type. [lines 109-140] [Source]
  • Session-end hook statuses completed and interrupted detailed. [lines 163-174] [Source]

troubleshoot-install [Source]

  • Absorbed the installation error sections (install killed by OOM, connection dropped while downloading) moved from the errors page.

API changes

Changed documents

api/beta/agents [Source]

  • New multiagent_20261001 configuration with independently enabled advisor, subagents (predefined_agents), and workflows members, merged level by level on update. The same change appears in the Go, Python, TypeScript, Ruby, Java, C#, CLI and PHP SDK references. [lines 29-140] [Source]
  • The existing coordinator topology is now documented as BetaManagedAgentsMultiagentCoordinatorParams.

api/beta/sessions [Source]

  • Large regeneration of the Managed Agents sessions, events, threads and thread events references (all SDK languages and CLI), adding workflow run events (created, phase started/ended, status running/idle/ended, errors and results), inline agent and session thread types, and session refusal and retries-exhausted stop details.

build-with-claude/preserved-thinking [Source]

  • New section "Output-token cost of drop_block": output tokens rose 2.5%-20.1% when dropping once per session and 4.6%-67.1% when dropping on every turn (low to max effort). Recommends running your own evals and fixing the prefix edit. [lines 99-131] [Source]

manage-claude/compliance-content-data [Source]

  • Claude Docs documents are listed via List code artifacts with artifact_type claude_docs, and downloaded as a ZIP using multi_file_format=zip. [line 209] [Source]

manage-claude/user-management [Source]

  • Custom roles: read the name from display_name; the name field is deprecated and equal to it. Store the role id for lasting references. [line 435] [Source]

managed-agents/budgets [Source]

  • A user.interrupt can pause open workflow runs, and a run paused by an interrupt does not resume when the budget changes; send a user.message asking the agent to continue its runs. The same clarification is in events-and-streaming, multiagent-orchestration and workflow-runs. [lines 188-196] [Source]

managed-agents/session-threads [Source]

  • C# examples updated; from_agent_name is now described as absent rather than null for workflow prompts. [line 405] [Source]

managed-agents/workflow-runs [Source]

  • A paused run's lifetime keeps passing, so it can end with timeout_error while paused. [line 758] [Source]

models/fable-5-1/migration-guide [Source]

  • Checklist now says responses can start with thinking blocks (select content by type), and notes thinking tokens bill as output tokens. [lines 1582-1588] [Source]

release-notes/overview [Source]

  • New entry: the Compliance API can download Claude Docs documents as Word files, in beta. [line 22] [Source]