Fable 5.1 debuts as the default Fable model (1M context) in a huge release: 67 fixes for hangs, MCP, and memory leaks, plus new /doctor checks and tighter auto-mode permissions.
claude-fable-5-1), now the default Fable model — 1M context, $10/$50 per Mtok with $0.25/Mtok cache readstimeFormat) and timeZone settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestampsCLAUDE_CODE_SUBAGENT_MODEL_FORCE to apply CLAUDE_CODE_SUBAGENT_MODEL (or the main model) to every subagent, ignoring per-spawn and agent-definition model overridess in /effort to change effort for the current session only, matching /model/doctor warning for stale sandbox mask files left by a killed sessionpermissions.blockReadsOutsideWorkingDirectories)description on discovered /model picker entries (CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY); entries without one still read "From gateway"/status, declining the managed-settings dialog prints why Claude Code exited, and helper timeouts are reported as timeouts/code-review --comment to post findings on GitLab merge requests via glab mr note instead of reporting the target as unsupportedclaude self-hosted-runner --configure-git to also enable git push negotiation, so the first push of a new branch from a stale clone uploads only the new commits instead of the whole treeCLAUDE_STREAM_IDLE_TIMEOUT_MS are not mistaken for a hung session/fork to keep the original conversation's prompt cache in the new background session: its worktree briefing now arrives as a message instead of a system-prompt change:satisfied:, :telephone:, :collision:, …).claude/ folder created after startup not being picked up until restart← always starting in the original session's permission mode, overriding the target directory's defaultMode and the agent's permissionModekeybindings.json rebinds of Ctrl+G being ignored in claude agents; its Ctrl+S / Ctrl+T are now rebindable via the new Agents contextstate.json detail repeating its own dispatch prompt after a scheduled wake-upclaude agents keeping a background session you re-prompted buried in Completed after it finished again; Completed now orders by the latest finishclaude --bg from a directory that was just deleted reporting "backgrounded" and leaving a crashed session row; it now prints the reason and exits 1Authorization header overriding the configured credential on Bedrock, Mantle, Vertex, and WIF, and the Vertex setup wizard picking up a leftover Anthropic profile from ~/.config/anthropicAuthorization or profile headers to Foundry, Vertex, and Bedrock, and Foundry Entra ID upstreams not starting when ANTHROPIC_FOUNDRY_API_KEY is set/schedule routines whose prompt was saved without a message role and then ran with nothing to doclaude agents not saying that a background session is waiting for you to approve a message from another session, or who sent itpolicyHelper timeoutMs and refreshIntervalMs values above the timer maximum (2147483647) causing failures or re-runs every millisecond; they are now clampedexample.com.): a deniedDomains entry didn't block the host inside the sandbox, and "don't ask again" for such a host kept promptingn at claude remote-control) counting as consent, so the next request connected without asking/mcp reconnect and enable still connecting a settings-file MCP server that a managed MCP allow/deny list or strictPluginOnlyCustomization loaded after startup should blockclaude mcp remove leaving a remote server's stored OAuth credentials behind when strictPluginOnlyCustomization locks MCP to plugin-only serversclaude remote-control) sessions started from the Claude app ignoring the selected model and running on the machine's default instead--disallowedTools and session deny rules being dropped after the first settings reload when allowManagedPermissionRulesOnly is enabled--resume listing a backgrounded conversation twice and --continue reopening its stalled pre-background copy; --continue now also opens finished background sessions! shell command output to expand itclaude agents --json briefly switching the terminal to raw mode and undoing another program's terminal settings on exit← doing nothing in the /btw panel inside a claude agents session: it now returns to the agents list (even mid-answer), and the panel comes back when you reopen the session/recap, prompt suggestions) and re-sending the full conversation uncached each timeclaude -p exiting about 5 seconds after its final result while a Monitor the model armed was still running; it now waits for the watch to fire or time outpermissions.ask rule being skipped in auto mode when the matching command ran inside a compound command or subshell, letting it run without the confirmation prompt/add-dir rejecting a directory inside the current working directory; it now loads that directory's skills, commands, and agents like --add-dir does at startup/feedbackclaude mcp add/remove hanging or exhausting memory when the project's .mcp.json is a FIFO or a device-file symlink; it now fails fast with an actionable messageclaude -p --input-format stream-json; it now fails fast with a clear error← or Ctrl+B) while a subagent or other tool was running occasionally making the background session treat that tool as rejected instead of re-running itRead()/Edit() deny rules not applying to < file redirects and reader commands like tac and egrep; a deny rule on any argument or redirect target now refuses the command$VAR reads, "$(…)" and heredocs that never touch git as "too complex to verify that it stays inside the worktree"/model and /effort showing a prompt-cache warning after rewinding a conversation back to emptytimeout or setsid) surviving a task stop or Claude Code exit.git directory after cd into a subdirectory/login instead of reporting a network errorcc-daemon-* folders in the system temp directory after an interrupted background daemon start; the cleanupPeriodDays retention sweep now removes them[[ ]] conditionals that zsh parses differently from bash; these commands now prompt for approval/status not showing the Organization for that sign-in--effort to lift a new model's default-effort hold for that session only rather than permanently; an effort picked on claude.ai for a Remote Control session now applies during the holdpolicyHelper in MDM or managed-settings.json shadowed at launch by cached server-managed settings to run (or exit) as soon as the fetch reports them removed, not at the next launchmanagedSourcesBehavior: "merge" to take sandbox.credentials.awsPairs and sandbox.ripgrep whole from the highest managed source that sets them instead of combining the sources' valuesCLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1) to run even when CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC is set, since it only queries your gatewayclaude --resume <session-id> --bg to continue that session under its own ID when nothing is running it, instead of silently starting a copy; a copy is now announced/btw history browsing from ←/→ to Shift+←/Shift+→ (or [/]), stepping through your recent side questions and back to the live answerdefaultMode: "bypassPermissions" in .claude/settings.json or .claude/settings.local.json to be ignored, like "auto"; set it in user or managed settings, or pass --permission-modefable and best in Claude apps gateway sessions to keep resolving to Fable 5 for now, since gateways not yet configured for Fable 5.1 reject it; pick Fable 5.1 in /model to use it--add-dir, /add-dir, and additionalDirectories to refuse network paths (UNC shares, /net/<host> automounts) with a message before touching them; on Windows use a mapped drive letter