Big stability sweep: 51 fixes for session resume, worktrees, hangs and cloud sessions, plus a new /advisor command on AWS and a few breaking hook and remote-control changes.
virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted promptcache_creation_5m_tokens and cache_creation_1h_tokens to the OpenTelemetry api_request event, splitting cache writes by lifetime$.ui.view({ agentId }) for mods: shows an agent's transcript in the main view when you ask, and $.ui.view({}) goes backdir prop on a mod's Text for right-to-left text: on Windows and in VS Code's terminal its rows read in that direction and sit flush right/advisor on Claude Platform on AWS; no advisor runs until you pick one with /advisor, advisorModel or --advisor, and CLAUDE_CODE_DISABLE_ADVISOR_TOOL=1 turns it offgen_ai.provider.name, gen_ai.conversation.id, gen_ai.tool.name and error.typeprompt and model in the agent.spawn mod hook, which could only refuse workflow agents beforeprompt.change mod hook, raised when the prompt box's text changes without a typed edit: a recalled history entry, a clear, an undo, or a plugin's fillclaudeCode.attachSelection setting to stop text selected in the editor from being added to your messagesplugin-authoring skill: Claude scans a mod's files for keys before opening them, and asks before scanning a folder outside the project/autocompact warning about high token usage when you choose a smaller auto-compact windowclaude --help naming a removed tool in its description of --restrictedclaude agents not refreshing any pull request's status when the data for one of them came back incomplete/tasks shortly after finishing, leaving no way back to the conversationENABLE_TOOL_SEARCH=auto) turning off part-way through a conversation, for example while MCP servers reconnect after a resumeforceLoginOrgUUID leaving the refused organization's token stored, or live after /loginArtifact("(unprintable path)") while a call's input arrives; its row now shows "Waiting…" and "Running…" as Bash's does/branch dropping messages, and claude purge skipping subfolder projects, when they contain a Unicode line or paragraph separator (U+2028, U+2029)WorktreeCreate and WorktreeRemove hooks not running when Claude Code starts with --worktree (not yet with --tmux)tool_result events missing git_commit_id after git commit -q in repositories using reftable ref storageprompt.submit hook rewrote or dropped still being recorded as typed in the OpenTelemetry user_prompt event and interaction span, and in session title requestsmodel: aliases like haiku now resolve, a subagent's model no longer overrides it, and an unavailable model falls back to the caller's instead of allowing the action--worktree sessions sometimes starting from the wrong commit when a tag or branch was named like a commit ID, and their starting git status naming a branch other than the new worktree's--worktree failing to reopen a worktree in repositories using git's reftable ref storageclaude remote-control servers giving up on renewing their connection after a brief sign-in error, such as a locked keychain; they now retry, and warn when you need to run claude /login--worktree failing in a worktree of a bare repository when origin's default branch can't be fetched; the fallback base is now the current checkout's HEAD, not the main repository'sprompt.edit hook not being raised for a newline entered with the chat:newline keybinding (Ctrl+J, or a rebound Enter)claude daemon stop --any printing "stopped" while a stuck background service kept running: it now waits, force-kills the service, and says so with exit 1 if it is still thereclaude daemon stop exiting with no output, and leaving sessions listed as running, when telemetry is turned off/c:/… path instead of a mention relative to the working directory/bin/ps directly instead of searching PATH for ps on every checkCLAUDE_CODE_PROVIDER_MANAGED_BY_HOST sessions to ignore CA-bundle, tool-proxy, git TLS and git config variables like SSL_CERT_FILE in settings; under Claude Desktop, only in project settingsforceLoginGatewayUrl names an Anthropic-operated gateway that serves the session's hostname; that gateway must be reachable at startclaude gateway to stop at start, naming the key, on a desktop: policy key that Claude Desktop cannot use from a gateway, where it earlier started with a warningCLAUDE_CODE_GZIP_REQUEST_BODIES=0 to turn it offclaude-api skill to leave Managed Agents sessions in place unless you ask to archive or delete them/sandbox mode options to read "Sandbox commands" instead of "Sandbox BashTool"PermissionRequest hooks in Cowork cloud sessions: a setMode update in a hook's allow is now ignored; the rest of the approval still appliesupdatedInput from PreToolUse and PermissionRequest hooks is now validated like Claude's own input: unknown keys are dropped, and input the tool rejects denies the call--sandbox and --no-sandbox flags from claude remote-control, which had no effect; passing either now exits with an error. Set sandbox.enabled in settings to sandbox sessions/healthz or SIGTERM shutdown) while nobody reads their output; logs keep the latest 256 KiB and count drops (not on Windows)@claude review comments from people with write access whose GitHub organization membership is private; their comments now start a review