One read of Claude Code CLIclaude-code-20261026T220701Z
1 pages moved out of 228 read.
Pages moved
1
significant first
Pages read
228
in this capture
Captured
22:07 UTC
Corpus hash
8321333f6048
corpus-hash
What this read moved
1-1 of 1changelog Changed · +108 / -0 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 6
66
77Run `claude --version` to check your installed version.
88
9**2.1.311**
10
11October 26, 2026
12
13**Added**
14
15* Added `--hold-idle-file` and `--max-hold-min` to `self-hosted-runner`, to keep an idle session while your host reports processes it left running
16* Added a tip for the Explanatory output style, shown when you ask Claude for explanations
17* \[VSCode] Added syntax coloring to code blocks in Claude's replies, in light, dark and high contrast dark themes
18* \[VSCode] Added a "Running UserPromptSubmit hooks" spinner status and screen reader announcement for slow UserPromptSubmit hooks
19* \[Claude Tag] Added a Skills view to Claude Tag analytics showing how often Claude runs each attached skill in Slack channels and which go unused, with Usage links in admin settings
20
21**Changed**
22
23* Changed `ultrathink` in the interactive terminal to run its turn at xhigh effort on Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.1 through Anthropic's API; typed while Claude is working, it raises the rest of that turn
24* Changed the `ultrathink` rainbow to appear only where the keyword can raise effort, and not when the word is quoted or part of a file path
25* Changed Ctrl+D in agent view to match the prompt: on an empty input, pressing it twice exits
26* Changed `--output-format json` and `stream-json` output to write DEL, C1 control and Unicode format characters inside strings as `\uXXXX` escapes; parsed values are unchanged
27* Changed model names and IDs to drop the `[1m]` suffix and its label on models where the suffix has no effect; the suffix is still accepted
28* Changed startup warnings about permission rules in settings files to show once per user until the rule changes
29* Changed `/code-review` to tell Claude to put the effort level first and use max only when asked
30* Changed `DISABLE_COMPACT` in settings files and in a mod's `$.env.set` so they can only turn compaction off, not back on
31* Changed Claude Code on Bedrock, Mantle, Vertex, and Foundry to load model settings from a signed file on downloads.claude.ai; set CLAUDE\_CODE\_MODEL\_CATALOG=off to turn this off
32* Changed sessions that set `CLAUDE_CODE_SYNC_SKILLS` with feature-flag fetching off to reuse a claude.ai skills list up to 10 minutes old that another session on the machine fetched
33* Changed clicks on scrollbar arrows and bars in fullscreen lists to act when the mouse button is released, so moving off the scrollbar before letting go cancels the click
34* Changed `claude purge` to say it deletes data only on this computer, not anything stored by Anthropic
35* \[VSCode] Changed the extension to start Claude Code sessions with `DISABLE_TELEMETRY` set while VS Code's telemetry setting is off, so they send no usage metrics or error reports and fetch no feature flags
36* \[VSCode] Changed the session list side bar to load Web sessions when the Web tab is first opened, not at startup
37* \[Claude Tag] Changed Claude Tag admin settings to show a lock instead of # for private Slack channels that your own Slack account can see
38
39**16 improvements**
40
41* Improved startup time for Pro and Max accounts by skipping two network requests on launches within an hour of the last check
42* Improved `/teleport` and `claude --teleport` to warn when a compacted cloud session loads from its last compaction, so the messages it summarized aren't in the local copy
43* Improved the messages shown when a background session's process exits: they no longer promise a restart that isn't coming, and they say how to resume the session
44* Improved artifacts with several views: Claude now routes each view on the link's `#name` and no longer says the address bar stays the same as you switch views
45* Improved shell commands that reach their timeout: the result now shows the output so far and says the command is still running in the background
46* Improved compaction: when the model's reply has no summary in it, Claude Code now usually asks for the summary once more before it replaces the conversation
47* Improved the Artifact tool's choice between a page and a document: explainers and visual or interactive work become artifact pages; documents are for writing people keep editing or pass around
48* Improved startup time for launches whose only arguments are options and their values, such as `claude --model opus`
49* Improved the "Connection dropped" API error: it now says where to look first (the proxy or gateway in use, else VPN or firewall; Anthropic API only, Bedrock, Vertex and Foundry are unchanged)
50* Improved screen reader mode: deleting a rule in /permissions says "Deleted allow rule …" right away
51* Improved the message shown when a pasted sign-in code is refused: it now says the code may have expired or been used, and to sign in again
52* Improved Slack connector sends: Claude now checks a channel's topic for posting rules before messaging a channel you didn't name
53* Improved screen reader mode: Claude's questions are listed as "Questions: Color (answered), Pages", without arrows or symbols
54* \[Claude Tag] Improved Claude Tag routines that run in a new session: a run with nothing to report can now end without posting a throwaway message to the channel
55* \[Code Review] Improved Code Review's check run to say no further automatic review will start when the model still can't analyze a change on the automatic retry
56* \[Code Review] Improved Code Review reliability: a review whose session fails to start because of a transient server fault is now retried once automatically, and its check run says so
57
58**56 bug fixes**
59
60* Fixed long freezes at startup and after reading or editing files when a CLAUDE.md file holds a very long list item
61* Fixed interrupting Claude not taking effect until a timeout while an MCP server had not answered a resource read or a skill was still downloading
62* Fixed standard-context sessions stopping with "Usage credits required for 1M context" when a request ran over 200K tokens; Claude Code now compacts the conversation and continues
63* Fixed Write and Edit stalling for up to 5 seconds after they ran, and reporting 0 lines changed, when changing thousands of lines in a file
64* Fixed subagents being unable to use MCP tools from servers that finish connecting after the subagent starts
65* Fixed Claude seeing stale MEMORY.md and CLAUDE.md content right after automatic compaction when those files were edited earlier in the session
66* Fixed `claude -p` and SDK sessions saving transcript messages out of order or keeping messages that were taken back
67* Fixed `SubagentStop` hooks running about twice a minute for each running subagent instead of once when it finishes
68* Fixed the @ file picker ignoring `.ignore`/`.rgignore` negation rules that re-include git-ignored files
69* Fixed a subagent's isolated worktree being removed while a background subagent it started was still working in it
70* Fixed background agents in auto mode that wait on their own shells starting a new main conversation turn on every wake
71* Fixed the Bash tool description claiming the working directory always persists between calls
72* Fixed the environment block naming a shell commands don't run in, such as fish when the Bash tool uses zsh
73* Fixed `claude mcp add`, `claude mcp remove` and `/mcp` naming the current folder instead of the project entry in `~/.claude.json` that holds a local-scope server when run below a repository root
74* Fixed `claude mcp list` and `claude mcp get` showing the error code twice on failed-connection lines (for example `ENOENT: ENOENT: …`)
75* Fixed Remote Control sessions staying on "Connecting" for about two minutes when a network proxy blocks a startup request
76* Fixed messages that Claude sends to a cloud or Remote Control session appearing as your own message in the Claude mobile apps
77* Fixed Claude not being told the cause when a file attached to a message sent over Remote Control or to a cloud session could not be saved because the disk was full, or that a message's attachments past the first 20 were left out
78* Fixed WebFetch and WebSearch hanging on a stalled response in Cowork cloud sessions; an unfinished request now fails after 300 seconds
79* Fixed a background session that crashed between turns not being restarted while it was attached, pinned, or had a scheduled task or wake-up set
80* Fixed the "background service did not respond" error suggesting the disabled `claude daemon restart`; it now suggests `claude daemon stop --any` and says it ends background sessions
81* Fixed `claude respawn <id>` starting the background service before reporting that no background session matches the id
82* Fixed `/effort` not warning about a prompt cache miss in plan mode when the plan model differs from the session model
83* Fixed `/ide` saying the VS Code extension was installed before the install finished or when it failed
84* Fixed the Write tool's file preview skipping rows and miscounting hidden lines when a line is wider than the terminal
85* Fixed ↑ in an agent's chat tab recalling a message that was still waiting to be delivered, so resending it sent a second copy
86* Fixed Cowork cloud sessions losing their connectors and most tools after a restart when a plugin or your settings named an `agent`; Cowork cloud sessions now ignore that setting
87* Fixed agent teams sessions showing an empty task list when coming back with `--resume`, `--continue`, `/resume` or `--session-id`, including after `/clear` or a crash, and `/branch` writing to the original session's list
88* Fixed pasting text that mentions an image file, such as `! open /tmp/shot.png` or `/review look at /tmp/shot.png`, attaching the image and dropping its path from the prompt
89* Fixed the feedback draft card showing its 1/2/0 and Esc shortcuts while the prompt has text, when those keys act on the prompt instead of the card
90* Fixed a lone backslash in quotes or brackets, like `"\"` or `(\)`, disappearing from Claude's responses
91* Fixed agent teammates compacting their history when `DISABLE_COMPACT` is set
92* Fixed the rewind menu offering "Summarize from here" and "Summarize up to here" when `DISABLE_COMPACT` is set
93* Fixed a finished `/code-review`, or another skill that runs in a sub-agent, running a second time when a cloud or background session restarts
94* Fixed long hidden thinking being cut off as idle on Google Vertex AI, Microsoft Foundry and Claude Platform on AWS, where the endpoint sends thinking progress updates
95* Fixed `/ide` saying it had installed the JetBrains plugin when nothing was installed
96* Fixed Claude Pro and Max subscribers being told to ask their admin when their subscription can't be used; the message now points to billing settings
97* Fixed the diff pane opening by itself after an edit in wide fullscreen terminals when it had nothing to show
98* Fixed `/mcp` showing a remote server as failed after "Clear authentication" when the server works without sign-in
99* Fixed `/mcp` showing "authenticated" for a remote server that Claude Code sends no credentials to
100* Fixed a `--plugin-dir` folder of plugins loading as one plugin when an empty `.mcp.json` was at its top
101* Fixed `/usage` never showing large prompt-cache misses under "What's contributing to your limits usage?"
102* Fixed status line links staying plain text in background sessions after you open them from a terminal that supports links
103* Fixed the /rewind confirmation saying the conversation "will be forked" when the later messages are removed from the conversation
104* Fixed the /rewind warning that wrongly said manual and Bash edits are never affected by a code restore
105* Fixed plan approval in screen reader mode sending feedback you had dismissed with Escape
106* Fixed Claude Code retrying requests the API marked not to retry, which could hold a turn for minutes or, in unattended retry mode (`CLAUDE_CODE_RETRY_WATCHDOG`), indefinitely
107* Linux: Fixed sandboxed Bash commands failing with `bwrap: Can't create file` when a `--plugin-dir` folder was also an added directory and `permissions.blockReadsOutsideWorkingDirectories` was on
108* Self-hosted runner: Fixed a session failing to start when a rate limit (HTTP 429, or a git wrapper that exits 75) blocks an added read-only repository; it now starts without that repository
109* \[VSCode] Fixed custom skills and custom slash commands sent from the VS Code or JetBrains panel leaving out the open file or selected lines that ordinary messages include (anthropics/claude-code#102799)
110* \[VSCode] Fixed the extension host freezing while the login shell ran its start-up files to read PATH on macOS and Linux
111* \[VSCode] Fixed clicking an image in a tool result, or closing its preview, also opening the result's text in an editor tab
112* \[VSCode] Fixed voice dictation continuing to record after a message was sent with the Send button; sending now stops dictation first, as pressing Enter already did
113* \[Cloud sessions] Fixed routines in Anthropic-hosted environments staying locked after their owner left the organization and rejoined; the owner can now turn them back on
114* \[Cloud sessions] Fixed a failed routine API token delete or regenerate showing nothing if the edit dialog had already closed; it now shows an error toast
115* \[Cloud sessions] Fixed cloud environment dialogs, including the admin dialog, accepting duplicate names; they now refuse a name another listed environment already has
116
9117**2.1.310**
10118
11119October 23, 2026
from line 2100
19922100* \[VSCode] Fixed tabs stuck on a conversation that can't be resumed: the error now says so and offers to start a new conversation
19932101* \[VSCode] Fixed every file Read, Write and Edit stalling for ten minutes and then being skipped when the editor stops responding to the extension's automatic save before the tool runs
19942102* \[VSCode] Fixed the agent map labeling a sub-agent with the session's model instead of the model it actually ran on (e.g. under `CLAUDE_CODE_SUBAGENT_MODEL_FORCE` or an agent's own `model`)
1995* \[VSCode] Fixed uninstalling a plugin from the Manage plugins dialog, which removed the wrong installation or failed for a plugin installed for the project
1996* \[VSCode] Fixed sign-in staying on the authorization-code step after going back and choosing the same sign-in method again
1997* \[VSCode] Fixed the chat panel stalling when a long session trims its oldest rows
1998* \[VSCode] Fixed the conversation disappearing from a session when many agents run
1999* \[VSCode] Fixed the editor tab keeping an old name after a session was renamed with /rename, by a SessionStart hook, or on claude.ai
2000* \[VSCode] Fixed the agent map's transcript view leaving out messages sent to a running agent
2001* \[Cloud sessions] Fixed Run now on a routine showing internal error text when the run is refused before it starts; it now shows the same explanation as the routine's failure notification
2002* \[Claude Tag] Fixed the Default model setting in admin settings and a channel's Configure page offering models your organization can't use, which made saves or new sessions fail
2003* \[Claude Tag] Fixed the note under Claude's Slack messages saying it answered on a fallback model, and why, disappearing when Claude later edited that message
2004* \[Code Review] Fixed the organization menu in Code Review's "Add a repository" dialog showing only a few of your GitHub organizations; it now loads more as you scroll
2005
2006**2.1.284**
2007
2008September 28, 2026
2009
2010**Added**
2011
2012* Added Claude Sonnet 5.5 (`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
2013* Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you can allow that one read and still be asked about later ones
2014* Added dollar amounts to the Claude apps gateway spend limit in `/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 `period`
2015* Added `effortSlider:decreaseEffort`, `increaseEffort` and `toggleUltracode` keybinding actions, so the `/effort` slider's arrow and Tab keys can be rebound in `keybindings.json`
2016* Added `/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
2017* Added `/mcp reconnect all` in the interactive terminal to retry every MCP server that failed to connect or needs authentication at once
2018* Added Claude apps gateway startup warnings when a managed policy's `availableModels` is empty, or leaves out the model Claude Code starts on without setting `model` or `enforceAvailableModels`
2019* Added `auth: { 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 credentials
2020* Added certificate client authentication (`private_key_jwt`) between the Claude apps gateway and its identity provider, for identity providers that issue certificate credentials instead of client secrets
2021* \[VSCode] Added an optional time above each prompt and response, with a date line where the day changes (Claude Code: Show Message Timestamps setting, off by default)
2022* \[VSCode] Added plugin load errors and notes to the Manage plugins rows, with a popup to disable, uninstall or copy the error
2023* \[VSCode] Added an Ultracode on/off switch under the Effort slider, replacing the slider's Ultracode stop; the model pill shows "· Ultracode" at any effort level
2024* \[Claude Tag] Added model family choices such as "Opus (latest)" for a thread, a channel default or your DM, so the choice follows the newest model in that family
2025* \[Claude Tag] Added the spend that counts toward your organization-wide limit to the analytics spend projection chart, with how much of the limit is used
2026
2027**Changed**
2028
2029* Changed interactive terminal and VS Code sessions to start in auto mode when no permission mode is configured, on every plan and provider; `permissions.defaultMode` still overrides it
2030* Changed Ultracode into its own toggle in `/effort` (Tab, or `/effort ultracode [on|off]`): it no longer forces xhigh effort and stays on at any effort level
2031* Changed retries after a dropped connection mid-response to share one budget with the rest of the request's retries, so a failing request gives up sooner
2032* Changed the notice shown when a Sonnet model's safeguards flag a message to explain why it happened and to offer editing and retrying
2033* Changed safety-related model switches in sessions that pin an Opus model with `ANTHROPIC_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
2034* Changed the non-interactive first turn to still wait up to 2s for connecting MCP servers named by `--allowedTools` or an `mcp_tool` hook, even when `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` is `0`
2035* Changed `/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
2036* Changed `/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`
2037* Changed artifact publishing to refuse a file on a network share (a `\\host\share` path or a `/net` automount) unless it is on a mapped network drive added with `--add-dir`
2038* \[VSCode] Changed `CLAUDE_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
2039* \[Claude Tag] Changed Claude to post its private sign-in notice at every @mention from someone who hasn't connected their Claude account, instead of going quiet after the first
2040
2041**18 improvements**
2042
2043* Improved the usage-limit wait: the limit's state and the countdown with the usage-credits option now show as one block under the prompt, and limit messages no longer repeat the countdown
2044* Improved the "No such tool available" error for Claude in Chrome tools called without their prefix: it now names the tool to call
2045* Improved Monitor event rows to show what each event printed instead of repeating the description, and stopped repeating an unchanged "Waiting for N … to finish" line after every event
2046* Improved Workflow tool sandbox hardening for errors thrown by async script hooks
2047* Improved startup time and memory use by building only the parts of the settings schema that your settings files actually use
2048* Improved `/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
2049* Improved lists such as `/tasks`, `/copy` and `/hooks`: the details after each name now line up in one column when they fit, and otherwise sit at the right edge
2050* Improved `claude plugin marketplace add` to say when it replaces a marketplace already added under the same name from a different source, and how to undo it
2051* Improved the startup refusal when managed settings require a sign-in (`forceLoginMethod` 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 it
2052* Improved auto-memory loading: invisible characters and tags that imitate Claude Code's own markup are neutralized in `MEMORY.md` and recalled memory notes before they reach Claude
2053* Improved `claude remote-control`: in a folder you haven't trusted yet, it now asks for workspace trust on the terminal instead of exiting
2054* Improved artifact pages: Claude writes its design plan into the page instead of the reply, and uses the name you already gave something as the page title
2055* Improved the Artifact tool so that when Claude is given a claude.ai chat or project link, an artifact from a chat, or an artifact id on its own, it asks for the right link or the content instead of stopping
2056* \[Claude Tag] Improved "Notify members now" in admin settings: one press reaches every workspace your organization claimed in an Enterprise Grid, and more members in large workspaces
2057* \[Claude Tag] Improved Claude's wait notice on self-hosted environments with on-demand runners: it now says whether a runner is starting, a start will be retried, or no runner will start
2058* \[Claude Tag] Improved the error shown when adding a channel manager fails because the channel's Slack workspace can't be confirmed as connected to your organization
2059* \[Claude Tag] Improved a channel's access lists in admin settings to show the connectors, repositories and plugins an auto-join pattern attaches, and where each comes from
2060* \[Claude Tag] Improved adding repositories as a channel manager: when your GitHub sign-in can't confirm you're a repository admin, the page asks you to sign in with GitHub
2061
2062**57 bug fixes**
2063
2064* Fixed a damaged response stream showing raw errors such as "JSON Parse error" or "undefined is not an object", or writing the word "undefined" into an answer, instead of being retried or reported as an interrupted response
2065* Fixed an overloaded or server error arriving right after a thinking block ending the turn with an error instead of being retried
2066* Fixed "Prompt is too long" errors that persisted after compacting: when the compacted request is still too long, Claude Code now compacts once more, keeping less of the recent conversation
2067* Fixed a session whose model is unavailable, with no fallback model left, showing a bare "is currently unavailable" message (or "Something went wrong" in cloud sessions) instead of the model-unavailable notice and its Learn more link
2068* Fixed Agent SDK sessions crashing when a user message contains an image with a malformed `source`, and failing on every later turn after a malformed document block; a malformed image is now replaced with an explanatory note
2069* Fixed MCP tool calls in a resumed session failing with "No such tool available" while their server was still connecting; the call now waits up to 10 seconds for the server
2070* Fixed repeated calls to the plan-usage endpoint after it rate-limits or rejects your login: `/usage`, `/extra-usage` and IDE usage views now back off instead of re-asking
2071* Fixed `claude 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
2072* Fixed the `/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 tabs
2073* Fixed `ANTHROPIC_FOUNDRY_RESOURCE` being interpolated into the Foundry endpoint host unvalidated; a value that is not a plain resource name is now refused
2074* Fixed Claude Desktop behind a Claude apps gateway offering no 1M context option: the gateway now marks each 1M-capable model for Desktop automatically
2075* Fixed ↓ in shell mode selecting a hidden background-tasks pill, which stopped Backspace and Ctrl+U from editing the prompt
2076* Fixed Bash tool failing on Windows with many plugins enabled: plugin `bin/` directories that don't exist are no longer added to PATH, and inherited entries aren't added twice
2077* Fixed `sparsePaths` 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"
2078* Fixed fullscreen rendering erasing the terminal output above the session when `[` in transcript mode writes the conversation to scrollback (macOS and Linux)
2079* Fixed fullscreen scroll position jumping to the previous message or to the bottom when a reply finished streaming while scrolled up
2080* Fixed tab bars in dialogs such as `/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
2081* Fixed the `/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
2082* Fixed `/keybindings` writing Backspace and Delete bindings for a footer action that does nothing into the generated `keybindings.json`
2083* Fixed a rebound agent panel close key (`footer:close`) typing "x" instead of itself on the row of the agent you're viewing
2084* Fixed vim mode `.` 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)
2085* Fixed vim mode leaving the cursor on an image placeholder's opening bracket after `dd` on the last line or `yy` at the end of the prompt, where `r` or `x` would break or delete the image
2086* Fixed a key pressed the instant the terminal regained focus answering the Remote Control enable prompt before its short safety delay restarted
2087* Fixed the workspace trust dialog appearing a second time after switching renderers or updating when Claude Code was started in the home directory
2088* Fixed rules symlinked in
2103* \[VSCode] Fixed uninstalling a plugin from the