Claude Sonnet 5.5 is now the default Sonnet on the Anthropic API with 1M context; sessions also start in auto mode by default, and Ultracode becomes its own /effort toggle.
claude-sonnet-5-5), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads/usage and the status line (for example "$271.40 / $500.00 spent this month") when the gateway runs this version or later; the status line's rate_limits.spend_limit also gains used_usd, limit_usd and periodeffortSlider:decreaseEffort, increaseEffort and toggleUltracode keybinding actions, so the /effort slider's arrow and Tab keys can be rebound in keybindings.json/rate-limit-options to /help and the command menu for claude.ai subscribers, so the usage-limit notices that mention it point to a command you can find/mcp reconnect all in the interactive terminal to retry every MCP server that failed to connect or needs authentication at onceavailableModels is empty, or leaves out the model Claude Code starts on without setting model or enforceAvailableModelsauth: { google: {} } for Claude apps gateway telemetry.forward_to destinations, so telemetry can be exported straight to Google Cloud's OTLP endpoint using the gateway's Google Cloud credentialsprivate_key_jwt) between the Claude apps gateway and its identity provider, for identity providers that issue certificate credentials instead of client secrets/claude-api: hillclimb no longer spends rounds on prompt rewordings too small for the eval to measure, and an extra page you ask for beside report.html is built as one local file that loads nothing from the network/tasks, /copy and /hooks: the details after each name now line up in one column when they fit, and otherwise sit at the right edgeclaude plugin marketplace add to say when it replaces a marketplace already added under the same name from a different source, and how to undo itforceLoginMethod or forceLoginOrgUUID) and an API key, token or apiKeyHelper is configured: it now names the credential in use, where it is set, and how to remove itMEMORY.md and recalled memory notes before they reach Claudeclaude remote-control: in a folder you haven't trusted yet, it now asks for workspace trust on the terminal instead of exitingsource, and failing on every later turn after a malformed document block; a malformed image is now replaced with an explanatory note/usage, /extra-usage and IDE usage views now back off instead of re-askingclaude mcp add reporting success when managed settings restrict MCP servers to plugins; it now refuses and says what to do, instead of saving a server that never loads/plugin configure screen: boolean options are now a true/false choice instead of free text, number options refuse invalid input, and ←/→ change an options field instead of switching tabsANTHROPIC_FOUNDRY_RESOURCE being interpolated into the Foundry endpoint host unvalidated; a value that is not a plain resource name is now refusedbin/ directories that don't exist are no longer added to PATH, and inherited entries aren't added twicesparsePaths plugin marketplaces cloning empty and replacing a working local copy on older git (before 2.39), which failed every refresh with "marketplace.json file is no longer present"[ in transcript mode writes the conversation to scrollback (macOS and Linux)/config and /plugin breaking the title and tab labels mid-word in a narrow terminal; a tab that doesn't fit now moves to the next line whole/model picker showing "+1 model" below the list after scrolling to the last model; the count now covers only the models below the visible rows/keybindings writing Backspace and Delete bindings for a footer action that does nothing into the generated keybindings.jsonfooter:close) typing "x" instead of itself on the row of the agent you're viewing. not repeating text typed very fast (for example over ssh or in tmux) or pasted without bracketed paste, and leaving the prompt in INSERT mode after repeating a change with nothing typed (such as cw then Esc)dd on the last line or yy at the end of the prompt, where r or x would break or delete the image.claude/rules from outside the project being skipped without ever showing the external-imports approval prompt; a .claude directory symlinked from outside the project now asks for the same approvalallowed-tools under managed allowManagedPermissionRulesOnly; only plugins from an official Anthropic source or a source that managed settings vouch for keep that pre-approvalclaude plugin install leaving the plugin enabled and recorded when a dependency's version range could not be met{"decision":"block"} returned by Elicitation and ElicitationResult hooks being ignored; it now declines the MCP elicitation, as exit code 2 doesSendMessage tool (such as by Claude Desktop) still being told to message other sessions with it/upgrade to users already on the highest Max plan; the warnings and /upgrade itself now point at /usage-credits when it is available/loop status updates in self-paced mode often not being shown because Claude wrote them only in its reasoning; Claude now writes each update, and the outcome when the loop stops, as visible text/ultrareview failing to upload the working tree when started from a git worktree that the Claude desktop app created on macOS or Linuxdata/users/ subtree, and added a "view" level to as_level431 Request Header Fields Too Large to every request from a sign-in whose identity provider lists many groups; it now accepts request headers up to 256 KiB/model and Enter printing usage text into the chat instead of opening the model selector/feedback on Vertex, Bedrock and Foundry being refused after you pressed Send; the report is now saved on this computer, as the terminal does/mcp, /config or /settings command being shadowed by the extension's dialogpermissions.defaultMode still overrides it/effort (Tab, or /effort ultracode [on|off]): it no longer forces xhigh effort and stays on at any effort levelANTHROPIC_DEFAULT_OPUS_MODEL or modelOverrides: on the Anthropic API, the API now picks the model to switch to for each kind of flag, not the pinned model--allowedTools or an mcp_tool hook, even when CLAUDE_CODE_MCP_STARTUP_WAIT_MS is 0/recap to decline with a short notice when it arrives relayed from a chat thread (your own included) or from a routine or webhook; typed in the terminal, the Claude apps, Remote Control, -p or an SDK host, it runs as before/artifacts to show its filter tabs beside the title with one-word labels (All, Mine, Shared), using the same tab bar as /config and /plugin\\host\share path or a /net automount) unless it is on a mapped network drive added with --add-dirCLAUDE_CONFIG_DIR in the claudeCode.environmentVariables setting to apply only when it is an absolute path, and passed it to terminals that continue the chat