Claude Code v2.1.287 发布：新增 Claude Mods 与 You should know 插件

What's changed

• Added Claude Mods: plugins may now modify deeper behavior
• Added You should know, a built-in mod where a side agent watches your back and flags things you or Claude might miss. Turn it on with /plugin enable cc-plugin-you-should-know@builtin (for first-party sessions with telemetry on)
• Added an n:<text> filter to the agents view that matches session names and tasks; a filter now shows matches in collapsed sections and Enter opens the first match
• Added prompt_text to the OpenTelemetry user_prompt event, a copy of prompt for backends that nest dotted keys; drop or mask it wherever you drop or mask prompt (#70763)
• Added URL prompts from MCP servers on the 2025-11-25 protocol, for example to sign in. If a server no longer connects after this update, add "bareElicitationCapability": true to its MCP config entry
• Windows: Added a startup warning when denying the Bash tool also turns off the PowerShell tool, so Claude has no shell tool
• Self-hosted runner: Added a built-in gh api (REST only) for sessions that use Anthropic-managed git on macOS and Linux machines where the GitHub CLI is not installed
• Fixed fast mode staying off in remote sessions owned by an agent with no user account, even when the organization allows it
• Fixed Remote Control not receiving messages for minutes at a time when a reconnect request got no response; it now gives up after 30 seconds and retries
• Fixed hooks configured with asyncRewake waking Claude over and over with "found issues" notifications when the hook's script file is missing; the broken hook is now reported once
• Fixed tool heartbeats not reaching SDK hosts while the model's response stream was stalled with no data arriving
• Fixed Bedrock and Vertex startup model checks ignoring an enforced availableModels list, which could collapse /model to one Opus row
• Fixed the Claude in Chrome browser picker showing a JSON parse error when Chrome could not be reached
• Fixed picking Fable in /model on a claude.ai login saving the current version's id, so your saved default now follows the newest Fable like Opus and Sonnet do
• Fixed switching between Opus 5.5 and Sonnet 5.5 (/model, opusplan) rewriting earlier MCP tool announcements, which could drop earlier extended thinking
• Fixed Amazon Bedrock Guardrails blocks that arrive mid-response ending the turn with an API error instead of the guardrail's message when the reply began with thinking
• Fixed a dangerous rm (such as one on / or the home directory) losing its always-ask safeguard when the same command also redirected output to a ~ or wildcard path
• Fixed claude -p and SDK sessions repeating a model fallback on every later message after the model was switched while a reply was running
• Fixed a folder's CLAUDE.md being attached a second time after resuming a session or after a compaction
• Fixed background sessions that could not be reopened from claude agents after the agent exited and removed the worktree the session was started in
• Fixed /advisor pairing checks: Sonnet 5.5 can now advise Opus 4.7 and 4.8, and advisors the API would refuse are flagged up front instead of being silently dropped
• Fixed Bash permission prompts showing internal parser names such as "Contains simple_expansion" instead of a plain explanation
• Fixed a cause of fullscreen sessions on slow or busy machines exiting with "Claude Code exited after an unrecoverable interface error" while a scroll key was held in a long conversation
• Fixed organization per-tool permission ceilings being silently dropped for an MCP tool named __proto__
• Fixed Claude being told to page large MCP results saved as JSON with Read's offset and limit, which cannot split one long line
• Fixed the commit attribution reminder being delivered inside a tool result after a compaction
• Fixed screen reader mode leaving the cursor away from the typed text in search boxes (such as /resume and /permissions) and sign-in code fields
• Fixed screen reader mode refusing Enter with nothing typed on /rewind's summarize options, whose added context is optional
• Fixed screen reader mode showing a "Tab to amend" hint on approval prompts, where Tab does nothing
• Fixed screen reader mode listing arrow keys that do nothing in /permissions and /mcp, and saying "Select with numbers" in empty menus or while a search box has the keys
• Fixed screen reader mode leaving out the changed lines in file edit approval prompts and other diffs
• Fixed screen reader mode sending the claude --teleport progress screen, and an MCP form field while it is being checked, to the screen reader again on every spinner frame
• Fixed CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS not removing the structured-output format from session-title and prompt-hook requests, which Bedrock-backed gateways reject
• Fixed screen reader mode leaving out the top lines of a second approval prompt, a changed /config row or the rejected-plan line when the previous screen was taller than the terminal window
• Fixed --include-partial-messages sending a cut-short reply's message_stop late or never, so apps could show the reply as still in progress
• Fixed claude agents sometimes not showing the permission prompt a background session is waiting on
• Fixed /ultrareview giving advice about .git/info/attributes when the upload stops on a committed .gitattributes it cannot read, such as one saved as UTF-16
• Fixed claude remote-control failing to register behind an HTTP proxy with a misleading "Check your organization permissions" error (#97352)
• Fixed sandboxed Bash commands on Linux inheriting an open handle on the Claude Code executable
• Fixed the running-tool dot and three spinners still moving with the "Reduce motion" setting on, and /rewind's confirm screen updating its "ago" time while you type a note
• Fixed times in claude agents changing every second in screen reader mode; they now change at most every 10 seconds
• Fixed a revoked claude.ai login showing a generic API Error: 401 instead of "OAuth token revoked"; in -p mode the error now starts with "Failed to authenticate"
• Fixed /ultrareview upload refusals advising you to copy a variable named by a repository's settings file into your own user settings
• Fixed --output-format stream-json and the SDK not streaming the turns of a context: fork skill run by typing /<skill> as the prompt, as they do for the Skill tool's fork
• Fixed /feedback and /bug: the pre-filled GitHub issue no longer includes your recent error messages, and the confirmation screen now lists them as part of the report
• Fixed claude plugin marketplace add --sparse and git-subdir plugin installs failing with "transport 'http' not allowed" when the repository is served over plain http
• Fixed cloud sessions sometimes losing the earlier conversation when the session restarted while it was being compacted
• Fixed a plugin reload that overlapped the startup --plugin-url download corrupting the session's cached copy of the plugin archive
• Fixed /desktop quoting partial output when opening Claude Desktop timed out or printed too much output; the error now names the cause
• Fixed an MCP connector tool call occasionally running twice, or the connector's calls failing until restart, when its server changed which MCP protocol version it supports
• Fixed SessionStart hooks from synced plugins not running in new cloud sessions
• Fixed the transcript's "N hooks ran" summary and the verbose debug log's matched-hooks count including Claude Code's internal callbacks, so one configured hook no longer shows as two
• Fixed files Claude sends from cloud and Remote Control sessions failing when the upload finished just after the 30-second timeout; it now waits 35 seconds
• Fixed repositories added mid-session in cloud and SDK sessions not loading their skills and plugins, and loading CLAUDE.md late, after Claude changed directory
• Fixed PNG, JPEG and WebP images over 8,000 pixels on a side failing to send from a remote session; Claude now sends a scaled-down copy
• Fixed messages sent from the Claude apps with 17 to 20 attached files delivering only the first 16
• Fixed headless sessions reporting an MCP server as needing authentication after one refused call, even though later calls succeed
• macOS: Fixed Remote Control sessions started with claude remote-control stopping mid-turn when the Mac went to idle sleep
• Windows: Fixed interactive claude hanging or crashing with "Raw mode is not supported" when its input is piped or redirected; it now says why and exits (use -p for piped input)
• Bedrock, Vertex, Mantle: Fixed model availability checks under CLAUDE_CODE_SKIP_*_AUTH sending a different Authorization header than real requests when ANTHROPIC_CUSTOM_HEADERS repeats it
• Improved /config: settings that cycle show ‹ › and step both ways with ←/→, narrow terminals stack each value under its label, and PgUp/PgDn page the list
• Improved plugin marketplace errors to say in plain words why a marketplace was ignored or refused, and what to do
• Improved plugin listings to note when a plugin's dependencies were not installed, and updating a plugin now retries an install that did not finish
• Improved the Claude apps gateway's error when Amazon Bedrock rejects a model ID: developers now see which model is unavailable, and the gateway log names the ID that was sent
• Improved SDK sessions so a message sent with priority "now" no longer cancels a running web fetch or web search; it keeps loading in the background
• Improved /memory: the left and right arrow keys now flip its on/off settings, such as Auto-memory
• Improved /skill names typed mid-message: Claude is now told they are skills, including disable-model-invocation ones
• Improved the contrast of the prompt input border in light themes and of the ❯ before your earlier messages
• Improved delivery of files Claude sends from cloud sessions and Remote Control: an upload that fails on a timeout, a network error or a 502, 503 or 504 is now retried once
• Improved what Claude says when a file cannot be sent for a reason that may be temporary: it now mentions that you can ask for the file again in a few minutes
• Improved the prompt for a held message from another session to show the message between dashed lines, matching other permission prompts
• Improved MCP and other tool permission prompts to show the tool call between dashed lines, matching file edit prompts
• Improved MCP startup in headless mode: a remote server whose first connect fails transiently is now retried without waiting for the slowest server to finish connecting
• Improved files Claude sends from a remote session: large files now stream from disk instead of being read into memory, and a file over the size limit is refused with the server's limit named
• Improved the explanation Claude gives when the server refuses a file it sends from a Remote Control or cloud session, such as an oversized image
• Improved handling of large MCP tool results: less memory, smaller session files, and no extra upload to count tokens for results far over the limit
• Windows: Improved Bash tool speed by removing a subshell that ran before every command
• Changed a shell write through a repo-committed symlink onto a sensitive file or out of the working tree to name where it lands and wait for a person, on lines with a ~ target too
• Changed Opus 4.7+ and Fable to use a 1M context window by default on Bedrock, Vertex, Foundry and the Claude apps gateway, with no [1m] suffix (CLAUDE_CODE_DISABLE_1M_CONTEXT=1 keeps 200K)
• Changed replies from claude agents to arrive as queued messages; slash commands other than /stop sent while a turn is running now run when it ends
• Changed whole-tool Bash allow rules and allowing hooks to prompt for, not run, shell writes to files Claude Code's file tools refuse outright (the Anthropic profile store, the host credentials file)
• Changed right-click paste on Windows and Linux, and middle-click paste on Linux, to happen when the button is released; moving the pointer away before releasing cancels it
• Changed MCP server alwaysLoad: false to defer all of that server's tools behind tool search
• Changed screen reader mode to write new or changed lines without first pausing with the cursor at the start of the line; set CLAUDE_AX_PREPARK_MS=50 to restore the pause
• Changed automatic model switches after a flagged message to keep your current effort level instead of the new model's default
• Changed waiting permission prompts to show oldest first, so a new prompt no longer covers the one you're reading (prompts with a countdown still open on top)
• [VSCode] Added "Run in background" to a running command or sub-agent, to move it to the background and keep working
• [VSCode] Added the output of background shells and Monitors to their cards in the agent map
• [VSCode] Fixed settings dialogs blaming a timeout when Claude Code's reply was too large to confirm a save
• [VSCode] Fixed reopening a cloud session that the side bar already brought to this machine opening it again in a new tab; the side bar is shown instead
• [VSCode] Fixed the side bar's Web tab not listing cloud sessions started after the window loaded; a failed load now says "Remote server is not connected" instead of "No web sessions yet"
• [VSCode] Fixed a tab restored after a reload starting a second Claude process on a conversation the side bar already has open; it now shows the "still open somewhere else" notice
• [VSCode] Fixed tool-row file links, session-list links and two hints showing in plain text
• [VSCode] Fixed a background agent's still-running command showing as failed once the main turn ended
• [VSCode] Fixed a user's own /usage or /context command opening the extension's dialog instead of running when picked from the command menu
• [VSCode] Fixed file links in the plan preview tab doing nothing when clicked; they now open the file like links in chat replies
• [VSCode] Fixed opening a tool's input or output in an editor tab failing with "Timeout waiting after 1000ms" on remote hosts such as WSL when the tab is slow to appear
• [VSCode] Improved the Manage plugins dialog: a failed marketplace add, remove or refresh now says what went wrong
• [VSCode] Changed the Claude in Chrome "Enabled by default" switch to also connect the editor's own sessions, which still ask before browser actions
• [Cloud sessions] Fixed occasional failures to fetch from or push to GitHub when GitHub briefly refused a newly issued access token
• [Claude Tag] Fixed Claude posting a failure warning, such as a spend limit notice, in a Slack thread when a background event like GitHub activity woke it and nobody was waiting on a reply
• [Claude Tag] Fixed Claude Tag's spend limits page in admin settings leaving out recently created and private channels in organizations with many channels
• [Claude Tag] Improved Claude's task list in long Slack threads: background work no longer reposts it as a new message on its own, so people following the thread aren't notified
• [Code Review] Fixed finding comments and their "Why this was flagged" text stopping mid-sentence; they now end on a complete sentence
• [Code Review] Fixed Code Review skipping a pull request after a new push when its review had failed twice on the previous commit; it now reviews the latest commit
• [Code Review] Improved the failed-review card on a pull request whose conversation is locked: it now says the lock blocked the review and that nothing was posted or charged