Claude Code v2.1.317：修复auto模式失败、MCP断开及多项SDK与CLI问题

What's changed

• Added a warning to /schedule when a new cloud scheduled task gets connectors you did not ask for, with how to remove them
• Added a check that asks before a web or shell tool call sends your account email address to the network
• Added onFailure: "block" for Agent SDK hook callbacks, so a callback that fails blocks the action instead of letting it run
• Added a notice in Claude Desktop's Code tab when your organization's remote managed settings haven't loaded for the session, and another once they do
• Added a notice when auto mode's check has no answer for a subagent's tool call, which used to leave nothing in the main view
• Added anthropic.plan, anthropic.seat_type, anthropic.provider and anthropic.custom_base_url to OTel metrics, events and spans
• Added a cost report to the Claude apps gateway admin API, GET /v1/organizations/analytics/cost, for reading past spend over a date range in total, per developer, per day or per IdP group
• Added a daily record of each developer's IdP groups on Claude apps gateways with admin: set, kept for admin.identity_retention_days, which the cost report groups by
• Added CLAUDE_CODE_DISABLE_NESTED_SESSION_ID: set it to 1 on a self-hosted runner to have claude -p run inside a session use that session's ID and transcript, as in earlier versions
• Fixed project and local MCP servers disconnecting after the first turn in some Claude desktop sessions
• Fixed auto mode failing every turn when an LLM gateway set as the base URL answers 403 or 422 to its server-side safety check (a 403 with an apiKeyHelper is unchanged)
• Fixed claude auth status exiting before a slow token refresh was saved, which could sign you out on the next run
• Fixed a project's effortLevel setting being ignored by sessions that an app starts ahead of time and then opens in the project, such as new sessions in the desktop app's Code tab
• Fixed claude --from-pr reporting "No conversations found" in projects with many sessions when the linked session was older than the first page
• Fixed the second of two simultaneous permission prompts showing no file path or command on claude.ai and the mobile apps
• Fixed Remote Control and SDK hosts offering "don't ask again" on a mod's tool calls
• Fixed session titles being lost in cloud and SDK sessions when a new message or Stop arrived while the title was generating
• Fixed self-paced /loop wakeups sometimes not being scheduled when Claude left a field out of its request
• Fixed auto mode in cloud sessions stopping for approval when the Artifact tool uploaded, wrote to a database or saved a file through the outputs folder
• Fixed skills synced from claude.ai being lost or downloaded again every ten minutes when they can't be written to disk
• Fixed /schedule leaving a cloud scheduled task's next run time and link out of its results after creating or updating it
• Fixed screen readers speaking a running subagent's elapsed time and token count on every change in screen reader mode
• Fixed a region or network block (HTTP 403) being shown as a sign-in failure; the error now explains the block
• Fixed Claude saying a working claude.ai connector needed authorization or had failed in cloud sessions when a synced plugin included the same server
• Fixed claude -p exiting 0 when a full disk or quota lost its transcript or ~/.claude.json writes; it now prints an error and, in text and json output, exits 1. Full NFS exports may be missed
• Fixed edits to settings files made in the first second or so after launch not taking effect until a settings file changed again
• Fixed old transcripts not being cleaned up on machines where some runs skip cleanup, such as runs using --setting-sources
• Fixed deleted agent team inboxes being re-created by a teammate's late message
• Fixed a re-created agent teammate being removed from its team by an earlier shutdown approval
• Fixed stored scheduled tasks being impossible to list or delete after scheduled tasks were turned off
• Fixed Claude deleting your most recently updated /team-onboarding guide when asked to delete one without naming which
• Fixed Claude saying a /team-onboarding guide was deleted when the server refused the delete
• Fixed the Claude apps gateway hiding Amazon Bedrock's "Input is too long." error, which left sessions failing every turn with "upstream rejected the request" instead of compacting
• Fixed self-hosted runner sessions losing recent turns or the whole conversation when restarted while a plan waited for approval
• Fixed "Prompt is too long" after automatic compaction in sessions whose very large CLAUDE.md changed since it was last sent
• Fixed high memory use and slow startup in headless sessions with many plugins that register commands
• Fixed stdio MCP servers receiving an empty AWS_BEARER_TOKEN_BEDROCK when their env config sets it to empty; the variable is now unset, so the server can use the machine's own AWS credentials
• Fixed API requests failing with "unable to get local issuer certificate" behind some TLS-inspecting proxies after a root certificate renewal
• Fixed very long conversations losing their earlier summary when compaction had to shorten its own request
• Fixed a PDF's own metadata being able to make Read and @-mentions under-count its pages
• Fixed DISABLE_PROMPT_CACHING_OPUS and DISABLE_PROMPT_CACHING_SONNET having no effect on [1m], other-region and undated spellings of the default model
• Fixed /artifacts and the Artifact tool's shared list showing no shared artifacts when you have 200 or more of your own
• Fixed Claude treating partial Grep and Glob results as complete when a search hit its time limit
• Fixed OpenTelemetry exports to an https:// endpoint through a proxy never being sent when they started while another export was still in progress
• Fixed a flood of connection attempts to a proxy that blocks (HTTP 403) OpenTelemetry exports to an http:// endpoint
• Fixed OpenTelemetry exports hanging indefinitely behind a proxy that never answers; they now time out after 10 seconds, or OTEL_EXPORTER_OTLP_TIMEOUT up to 30 seconds
• Fixed resumed sessions telling Claude again about a file change it already knew about
• Fixed Claude sometimes not using a built-in tool in a resumed session after an earlier call failed because the tool was switched off
• Fixed /remote-control answering "Unknown command" instead of saying that Remote Control is turned off by the disableRemoteControl setting
• Fixed agent team teammates in tmux or iTerm2 panes starting in auto mode when the lead session was in manual mode
• Fixed a background session sometimes losing a just-made change of permission mode when it was upgraded or retired
• Fixed Ctrl+C stopping all running background agents when pressed to clear typed text at the prompt
• Fixed /feedback showing "Enter to confirm" while a report is being sent
• Fixed child processes of a stopped shell command sometimes being sent SIGTERM twice, which could make some programs skip their cleanup
• Fixed claude -p run inside a cloud or self-hosted runner session sharing that session's ID: it wrote into the session's transcript, and a restart could resume the wrong conversation
• Fixed claude -p run inside a cloud or self-hosted runner session generating a title of its own and sending it to that session
• Improved the error shown on Microsoft Foundry when Azure credentials can't be loaded: it now says to check or refresh them, and reports as cloud_credential_error
• Improved /design-sync to say up front when your design system has moved to Claude, and stop before building instead of failing at upload
• Improved the startup error when a required Claude apps gateway can't be reached: it points to the network instead of a sign-in, and says when the gateway's TLS certificate can't be verified