Admins can now block models with deniedModels and pin exact versions via availableModelsMatch; auto mode becomes default on third-party providers, plus /doctor prompt-audit.
x-claude-code-prompt-id to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with CLAUDE_CODE_GATEWAY_HINT_HEADERS=1availableModelsMatch managed setting: with "exact", an availableModels entry allows only the model version it names, so new releases stay blocked until listeddeniedModels managed setting to block specific models, even when availableModels allows themtool.output OpenTelemetry span event when OTEL_LOG_TOOL_CONTENT=1/doctor prompt-audit (also /checkup prompt-audit) to audit your CLAUDE.md files, skills, agents and commands for prompting patterns written for older modelspath to --plugin-dir load-failure entries in the stream-json system/init plugin_errors, naming the directory that did not loadload_test_mode block to the Claude apps gateway config: requests are built and signed but not sent upstream, and clients get a canned reply, so a deployment can be load testedmantle upstream provider to the Claude apps gateway for Amazon Bedrock's Mantle endpoint/mcp tool list: it shows more tools at once, scrolls with the page keys and mouse, and marks tools your organization blocked with a warning icon/tasks: rows show a status icon, the name and whole facts, the title and key hints stay on screen with many tasks, and the list gains paging keys, the mouse wheel and clicks/help, /hooks, /copy, /chrome, /memory, /ide, /release-notes, /rewind, /diff, /remote-env, /plugin and other pickers with page keys, mouse wheel and clicks/skills and /artifacts, to draw their pointer dim while the search box has the keys, so only one pointer is highlightedprompt-audit on Claude Code configuration: stale paths, stale commands and contradicting instruction files now lead the report, and thinking keywords that Claude Code documents are keptinstalled_plugins.json that cannot be read at all: its contents are kept in a file beside it before it is rebuilt, and claude plugin list names that fileclaude -p and Claude Code Remote no longer load the interactive UI, and the auto-mode classifier's rules and the Artifact tool load on first use instead of at launchresult.usage/mcp no longer offers Authenticate for such servers/usage and the VS Code usage meters when telemetry is disabled/model accepting Sonnet 4.6 or Sonnet 5 with [1m] when the id carried a date or -v1:0 suffix, in the cases where the plain id was refused/model picker showing a hardcoded Haiku version and price when ANTHROPIC_DEFAULT_HAIKU_MODEL pins a different modelDISABLE_PROMPT_CACHING_HAIKU having no effect when Haiku is the session's main modelclaude plugin validate saying Claude Code accepts a plugin or marketplace name it cannot install; such names in marketplace.json now fail validationclaude plugin validate passing plugins whose outputStyles, themes, monitors, or lspServers paths are missing or point outside the plugin directoryclaude plugin details showing 0 MCP servers for plugins that declare their servers in plugin.jsonclaude plugin marketplace remove not saying which installed plugins it uninstalled with the marketplace; it now lists themclaude plugin uninstall removing the other of two installed plugins whose ids differ only in case, with its options and secrets, when the one named had no enabledPlugins entry at that scopeinstalled_plugins.json showing no plugins when it holds a record under an invalid plugin id; such a file loads againinstalled_plugins.json being rewritten, losing records, when it holds a record this version cannot read; claude plugin commands now name the record and say how to recover/context not counting MCP server instructions: they now appear as their own row and count toward the totalclaude mcp add, add-json, and remove reporting success when the user or local config file could not be written, for example inside a sandboxcmd an alias of meta, which could produce cmd+ shortcuts most terminals never sendkeybindings.json silently accepting a misspelled modifier such as ctl+k; it now warns in the debug log and suggests the fixfooter:openSelected was rebound or unbound in keybindings.jsonGIT_CONFIG_COUNT environment pairsgit asking credential helpers to store the sandbox proxy's login, which printed "failed to store"sandbox settings being ignored entirely when one nested value was invalid; the invalid value now fails closed and the rest of the block still appliesDISABLE_TELEMETRY or DO_NOT_TRACK/remote-control menu cutting its QR-code hint mid-word in narrow terminals. dropping a Shift+Enter newline, leaving the cursor inside an accented letter, and repeating an older change after 3J or Visual-mode J on the last lineV then p now lands on the first non-blankJ joining lines with different spacing than Vim (such as a space before ) or after a tab), and 3J or Visual-mode J on the last line not moving the cursor as Vim doescmd /c rd, rmdir, del or erase delete drive roots, the home folder and other folders that Remove-Item refusespermissions.defaultMode still overrides it/ultrareview launch dialog to say that reviewing a local branch may upload uncommitted changes to tracked files/model picker's Opus row and the Default model's name to drop "(1M context)" where Opus already has a 1M context window; the window is unchanged--system-prompt and --append-system-prompt to accept their text and -file forms together; the file's text comes firstSkill(anthropic-skills:<name>) deny rules to also block that skill when Claude Desktop delivers it as a plugin, and Skill(skill:<name>) denies to match the skill's alias and display name/rewind and /diff lists to move on the same keybinding actions as every other list (select:*); messageSelector:*/diff:* rebinds still work/workflows run list to size itself like other lists: half the terminal inline, and it keeps its title on screen when the prompt shows belowclaude plugin eval to require git 2.31 or later when git is installed; a run on an older git is refused with a message naming the versionclaude-ai name: skills, commands, workflows and MCP servers' skills and prompts so named load again, and Skill(claude-ai:*) rules are ordinary prefix rulespre-push hook, ignore a writable system core.hooksPath, and not sign commits without --configure-gitGIT_SSL_CAINFO and GIT_SSL_NO_VERIFY under Anthropic-managed git: the runner's own git always verifies Anthropic's git route, and warning lines say what applies where