Claude Code changelog changedchangelog
Nearest release: v2.1.284, published an hour before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 28 Sep 2026 18:16 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 28 Sep 2026 18:37 UTC.
Upstream edited
Recorded here
Lines+103added
Lines−0removed
From line
6
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits46to this page, all time
The whole hunk
from line 6, old and new numbered
/
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<Update label="2.1.284" description="September 28, 2026">
10 * 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
11 * 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
12 * 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`
13 * Added `effortSlider:decreaseEffort`, `increaseEffort` and `toggleUltracode` keybinding actions, so the `/effort` slider's arrow and Tab keys can be rebound in `keybindings.json`
14 * 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
15 * Added `/mcp reconnect all` in the interactive terminal to retry every MCP server that failed to connect or needs authentication at once
16 * 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`
17 * 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
18 * 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
19 * 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
20 * Fixed an overloaded or server error arriving right after a thinking block ending the turn with an error instead of being retried
21 * 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
22 * 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
23 * 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
24 * 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
25 * 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
26 * 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
27 * 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
28 * Fixed `ANTHROPIC_FOUNDRY_RESOURCE` being interpolated into the Foundry endpoint host unvalidated; a value that is not a plain resource name is now refused
29 * Fixed Claude Desktop behind a Claude apps gateway offering no 1M context option: the gateway now marks each 1M-capable model for Desktop automatically
30 * Fixed ↓ in shell mode selecting a hidden background-tasks pill, which stopped Backspace and Ctrl+U from editing the prompt
31 * 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
32 * 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"
33 * Fixed fullscreen rendering erasing the terminal output above the session when `[` in transcript mode writes the conversation to scrollback (macOS and Linux)
34 * Fixed fullscreen scroll position jumping to the previous message or to the bottom when a reply finished streaming while scrolled up
35 * 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
36 * 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
37 * Fixed `/keybindings` writing Backspace and Delete bindings for a footer action that does nothing into the generated `keybindings.json`
38 * Fixed a rebound agent panel close key (`footer:close`) typing "x" instead of itself on the row of the agent you're viewing
39 * 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)
40 * 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
41 * Fixed a key pressed the instant the terminal regained focus answering the Remote Control enable prompt before its short safety delay restarted
42 * Fixed the workspace trust dialog appearing a second time after switching renderers or updating when Claude Code was started in the home directory
43 * Fixed rules symlinked into `.claude/rules` from outside the project being skipped without ever showing the external-imports approval prompt; a `.claude` directory symlinked from outside the project now asks for the same approval
44 * Fixed plugins from marketplaces, claude.ai and npm pre-approving their own tools via `allowed-tools` under managed `allowManagedPermissionRulesOnly`; only plugins from an official Anthropic source or a source that managed settings vouch for keep that pre-approval
45 * Fixed a failed first `claude plugin install` leaving the plugin enabled and recorded when a dependency's version range could not be met
46 * Fixed the debug log dropping a failed hook's stderr when the hook also wrote to stdout, and logging nothing for a failed hook with no output; failed hooks now also log their status code
47 * Fixed `{"decision":"block"}` returned by Elicitation and ElicitationResult hooks being ignored; it now declines the MCP elicitation, as exit code 2 does
48 * Fixed sessions launched without the `SendMessage` tool (such as by Claude Desktop) still being told to message other sessions with it
49 * Fixed a photo sent from the Claude app over Remote Control being lost when its queued message was pulled back into the terminal prompt to edit, and the cursor moving one character for a photo with no caption
50 * Fixed typing a message during an automatic usage-limit wait taking the wait out of the "Continue automatically at usage limit" setting's control when that turn hit the limit again
51 * Fixed usage-limit warnings suggesting `/upgrade` to users already on the highest Max plan; the warnings and `/upgrade` itself now point at `/usage-credits` when it is available
52 * Fixed the Explore subagent switching to Opus on the Claude API when the session runs a model ID Claude Code doesn't recognize, such as a custom model behind a proxy; Explore now inherits that model
53 * Fixed `/loop` status updates in self-paced mode often not being shown because Claude wrote them only in its reasoning; Claude now writes each update, and the outcome when the loop stops, as visible text
54 * Fixed `/ultrareview` failing to upload the working tree when started from a git worktree that the Claude desktop app created on macOS or Linux
55 * Fixed sandboxed Bash commands failing to start on Linux when the working directory is write-denied and contains a read-denied directory
56 * Fixed artifact database write results telling Claude that every viewer sees a write to a viewer's private `data/users/` subtree, and added a "view" level to `as_level`
57 * Fixed the Claude apps gateway answering `431 Request Header Fields Too Large` to every request from a sign-in whose identity provider lists many groups; it now accepts request headers up to 256 KiB
58 * 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
59 * Improved the "No such tool available" error for Claude in Chrome tools called without their prefix: it now names the tool to call
60 * 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
61 * Improved Workflow tool sandbox hardening for errors thrown by async script hooks
62 * Improved startup time and memory use by building only the parts of the settings schema that your settings files actually use
63 * 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
64 * 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
65 * 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
66 * 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
67 * 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
68 * Improved `claude remote-control`: in a folder you haven't trusted yet, it now asks for workspace trust on the terminal instead of exiting
69 * 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
70 * 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
71 * 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
72 * 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
73 * 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
74 * Changed the notice shown when a Sonnet model's safeguards flag a message to explain why it happened and to offer editing and retrying
75 * 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
76 * 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`
77 * 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
78 * 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`
79 * 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`
80 * \[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)
81 * \[VSCode] Added plugin load errors and notes to the Manage plugins rows, with a popup to disable, uninstall or copy the error
82 * \[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
83 * \[VSCode] Fixed Reload Claude from the Memory dialog restarting before an edited file was saved
84 * \[VSCode] Fixed a restored tab opening a conversation another Claude process still has open; it now asks first
85 * \[VSCode] Fixed Focus view sections you expanded closing on their own while a sub-agent is working or when the section's first step is trimmed from view
86 * \[VSCode] Fixed typing `/model` and Enter printing usage text into the chat instead of opening the model selector
87 * \[VSCode] Fixed `/feedback` on Vertex, Bedrock and Foundry being refused after you pressed Send; the report is now saved on this computer, as the terminal does
88 * \[VSCode] Fixed sign-in waiting up to a minute for the Python extension after a window reload
89 * \[VSCode] Fixed Claude Code tabs that stopped responding after Restart Extensions: they now reopen on their conversation
90 * \[VSCode] Fixed a message from another agent with no recorded sender showing as raw XML in the chat
91 * \[VSCode] Fixed messages from other agents, sessions or channels disappearing after a reload
92 * \[VSCode] Fixed a user's own `/mcp`, `/config` or `/settings` command being shadowed by the extension's dialog
93 * \[VSCode] Fixed Escape stopping every background agent when no turn was running
94 * \[VSCode] Fixed plugin install links replacing a marketplace you already have that uses the same name
95 * \[VSCode] Fixed "Prompt is too long" errors after compaction when a large text file is attached to a message
96 * \[VSCode] Fixed chat links to files with non-ASCII characters, spaces or brackets in their path not opening
97 * \[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
98 * \[Cloud sessions] Fixed a routine's Edit and Duplicate controls saying the routine was still loading while you were offline; they now tell you you're offline
99 * \[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
100 * \[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
101 * \[Claude Tag] Fixed the earlier Claude in Slack app's progress card and link previews omitting the repository and Create PR button when a GitHub Enterprise host name contains an underscore
102 * \[Claude Tag] Fixed Claude staying silent in a channel whose environment declines to start it; it now posts one notice asking you to contact an admin, and retries when @-mentioned
103 * \[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
104 * \[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
105 * \[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
106 * \[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
107 * \[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
108 * \[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
109 * \[Code Review] Fixed Code Review giving up without posting a finished review when an unsubmitted review under its GitHub App was open on the pull request; it now retries the post first
110</Update>
111
9112<Update label="2.1.283" description="September 25, 2026">
10113 * Added `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=1`
11114 * Added `availableModelsMatch` managed setting: with `"exact"`, an `availableModels` entry allows only the model version it names, so new releases stay blocked until listed
from line 1730
16271730 * Fixed `claude ultrareview` and `/ultrareview` waiting the full 30 minutes when the cloud session fails to start; they now stop early and report the reason
16281731 * Fixed Bash permission checks auto-approving commands that assign an arithmetic expression to an integer shell variable (e.g. `OPTIND=1/0`, `RANDOM=2+2`); these now prompt for approval
16291732 * Fixed backgrounded sessions (`←`, `/background`, `--bg`) losing a Vertex/Bedrock gateway (`ANTHROPIC_*_BASE_URL` + `CLAUDE_CODE_SKIP_*_AUTH`) exported in the shell, so every request failed
1630 * Fixed `claude --bg --model fable` on Max plans stopping to ask for usage credits while the interactive session on the same account still had Fable allowance
1631 * Fixed the one-time "make auto mode your default" offer appearing in unattended sessions (e.g. agent-team teammate panes), where a stray keypress could accept it unread
1632 * Fixed the managed-settings approval prompt re-appearing after signing in again to the same Claude apps gateway when the settings are unchanged
1633 * Fixed disabled `/bug` and `/share` reporting that `/feedback` was disabled; tips, `/help`, and refusal messages no longer suggest `/feedback` when an org policy or env var turns it off
1634 * Fixed cloud session creation advising GitHub setup after a transient GitHub connection failure — the message now says to retry instead
1635 * Improved CPU usage during turns in interactive sessions by cutting redundant UI re-renders
1636 * Improved install size: the native binary is about 5 MB smaller
1637 * Improved cloud sessions: when the session's network proxy drops a connection during a Bash command, the tool result now names the host and reason instead of only "connection reset"
1638 * Improved `/schedule` to explain that MCP servers configured in Claude Code can't be attached to cloud routines, instead of a bare "No MCP connectors" message
1639 * Improved framing of messages from your own subagents: Claude is told the sender is a worker inside this session, not an unrelated Claude session
1640 * Improved the prompt placeholder to read "Message @name…" while viewing a background subagent or fork transcript opened from the subagent panel or `/tasks`
1641 * Improved sanitization of MCP server names in error messages, menus, and command results
1642 * Improved Amazon Bedrock session start under `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` (e.g. Claude Desktop): a session given a Bedrock model ID or ARN no longer waits for inference-profile discovery
1643 * Improved the managed settings approval dialog to list only the settings that changed since you last approved them
1644 * Improved retry when the model's tool call is malformed: the broken output is now dropped from the retry context, including on Bedrock, Vertex, and Foundry
1645 * Changed `/radio` to be available on Bedrock, Vertex AI, Foundry, and Claude Platform on AWS, and when telemetry is disabled
1646 * Changed Claude in Chrome so browser actions always go through Claude Code's permission checks, including in sessions with telemetry disabled, which previously used the Chrome extension's own prompts
1647 * Changed `CLAUDE_CODE_SUBAGENT_MODEL` to set the default subagent model rather than override everything: an agent definition's `model:` and an explicit per-spawn model now take precedence over it
1648 * Changed the default commit trailer to `Co-Authored-By: Claude Code` when the active model isn't a recognized Claude model (e.g. third-party models behind a custom `ANTHROPIC_BASE_URL`)
1649 * Changed the default model for seat-based Enterprise subscriptions to Opus 5, matching other premium plans
1650 * Changed `/effort` to save your default effort level per model, so each model keeps its own setting when you switch
1651 * Changed analytics to no longer turn off before sign-in solely because managed settings force gateway login (or cannot be read); they stay off once signed in to the gateway or via `DISABLE_TELEMETRY`
1652 * Changed the footer PR badge on Bedrock, Vertex, and Foundry, and when telemetry is off, to call the GitHub API directly (via `gh auth token`, `GH_TOKEN`, or `GITHUB_TOKEN`) instead of `gh pr view`
1653 * Changed how Bash command output files are created and read back when commands run in the sandbox, so a sandboxed command cannot redirect or replace them
1654 * Changed plugin/LSP install suggestions and the auto-mode default offer to wait until you've sent or cleared what you're typing, so the Enter that sends your prompt can't answer them
1655 * Changed server-managed settings that terminate sandbox TLS, route sandbox traffic through your own proxy, inject credentials, or weaken sandbox isolation to require approval before they apply
1656 * Changed `ANTHROPIC_CUSTOM_HEADERS` from managed or project settings to require approval when it sets a credential, org/tenant, routing, or API-behavior header (e.g. `Authorization`, `Host`)
1657 * Changed project-level `.claude/settings.json` `env` to no longer set `CLAUDE_CONFIG_DIR`, `CLAUDE_CODE_TMPDIR`, or `TMPDIR`/`TMP`/`TEMP`; set them in your shell, user, or managed settings instead
1658 * Removed syntax highlighting for six rarely used languages (1c, gml, isbl, mathematica, maxima, sqf); the binary is 2.5 MB smaller
1659 * \[VSCode] Fixed the sign-in screen's "Bedrock, Foundry, or Vertex" button opening the docs at the top of the page instead of the third-party provider setup section
1660 * \[VSCode] Changed the Remote Control banner to a footer pill (shown while Remote Control is on or has failed) that opens the session on claude.ai/code; turn it on or off with `/remote-control`
1661</Update>
1662
1663<Update label="2.1.250" description="August 28, 2026">
1664 * Bug fixes and reliability improvements
1665</Update>
1666
1667<Update label="2.1.248" description="August 27, 2026">
1668 * Added `--restricted` (or `CLAUDE_CODE_RESTRICTED=1`): removes the built-in tools that run commands or code and `WebFetch` (unless named in `--tools`), keeps file tools inside the working directory, refuses `bypassPermissions`, and ignores user, project and local settings files
1669 * Added `experimental.cacheTtl` (`"5m"` or `"1h"`) to agent frontmatter: a per-agent prompt cache TTL used when no subagent TTL setting is configured
1670 * Added `claude self-hosted-runner --client-label <label>` (or `SELF_HOSTED_RUNNER_CLIENT_LABEL`) to override the label the runner registers with (default: hostname)
1671 * Added server-managed settings diagnostics: a startup warning when the settings fail to load, and a `/doctor` and `/status` line explaining a load failure or why they weren't fetched (Bedrock/Vertex/third-party provider, custom `ANTHROPIC_BASE_URL`)
1672 * Added a warning in `/web-setup` when the GitHub CLI token lacks the `workflow` scope, since pushes to very large repositories can be rejected without it
1673 * Added `/usage-credits` for Enterprise organizations billed through AWS Marketplace, self-serve Enterprise, and Enterprise trials, so members can request a higher usage limit from their admin
1674 * Added cross-session messaging (`SendMessage` / `ListAgents`) between sessions on the same machine on Bedrock, Vertex, and Foundry, and when telemetry is disabled
1675 * Fixed a prompt-cache miss (and lost extended-thinking context) roughly once an hour in long sessions, caused by tool definitions being re-rendered after an OAuth token refresh
1676 * Fixed the `ScheduleWakeup` tool definition changing between a session and its `--resume` when the account had entered usage overage, causing a full prompt-cache miss on the resumed session's first turn
1677 * Fixed Claude Desktop and Cowork sessions disappearing after 30 days: the transcript cleanup now keeps desktop-written sessions while they are in the app (unless org policy manages retention); the new `desktopSessionCleanupPeriodDays` setting caps the exemption
1678 * Fixed being sent to the login screen when another Claude Code process held the token refresh lock while the session token had expired; the request now fails with a retryable error instead
1679 * Windows: Fixed the `claude agents` list not responding to the keyboard after detaching from a session, or when launched in a terminal tab left in win32-input-mode
1680 * Fixed the recommended Console sign-in in `/login` failing with an OAuth error before showing a sign-in URL on machines where it can't be used (for example when `ANTHROPIC_API_KEY` or an API key helper is set); it now falls back to the API-key sign-in
1681 * Fixed model names in `/model` and fast-mode switch notices to render as code, so suffixes like `[1m]` display literally instead of as a link
1682 * Fixed `claude agents` skipping the workspace trust prompt when the `CI` environment variable is set
1683 * Fixed `claude agents` crashing on launch when the PR-status cache held a malformed entry
1684 * Fixed agent view resurrecting a weeks-old background session after the machine was off: such a session now shows as stopped at its real end, and opening it asks before resuming its saved conversation
1685 * Fixed agent view sometimes opening an older conversation, and dropping the typed prompt, when starting a new session
1686 * Fixed `claude agents`: opening a stopped session that you already resumed in another terminal no longer starts a second process on that conversation; the row now says it is open in a terminal
1687 * Fixed `claude agents` and `claude rm` refusing to delete a session ("has commits that are not pushed anywhere") when its worktree branch was already merged into your checked-out default branch (e.g. local `main`) but not yet pushed
1688 * Fixed background sessions waiting silently when a `PermissionRequest` or `PreToolUse` hook prints an invalid answer: the `claude agents` row now names the hook and the schema error
1689 * Fixed hooks silently treating a stdout `{…}` object that isn't valid JSON as plain text; it's now reported as a hook error with the parse message
1690 * Fixed `/mcp` listing a project `.mcp.json` entry that declares the claude.ai connector type under the trusted "claude.ai" heading; it now appears under its real scope
1691 * Fixed MCP servers whose `headersHelper` supplies the `Authorization` header falling into OAuth discovery on a 401 instead of re-running the helper and retrying the call as documented
1692 * Fixed `/login` to a Claude apps gateway hanging when the managed-settings security approval dialog was required
1693 * Fixed gateway model discovery (`CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY`) never running when `apiKeyHelper` is the only credential
1694 * Fixed `claude logs` leaving mouse tracking, bracketed paste and the alternate screen switched on in the terminal it was run from
1695 * Fixed the trust dialog's list of repo permission rules showing a garbled character when a long rule was cut off in the middle of an emoji
1696 * Fixed the permission mode indicator staying hidden behind the "Press Ctrl-C again to exit" hint when you press shift+tab right after ctrl+c
1697 * Fixed `/ultrareview` and locally seeded cloud sessions uploading uncommitted edits to `prod.env`-style and `*.tfvars` files, or to editor swap, temp, and backup copies of credential files (e.g. `key.pem.tmp`, `id_rsa.swo`); they now stay on your machine
1698 * Fixed Remote Control sessions occasionally never showing a permission prompt or the latest messages on the connected device after the CLI silently reconnected
1699 * Fixed cloud sessions occasionally failing at startup when the container's session credentials were not yet readable
1700 * Fixed `claude remote-control` rejecting its own flags (e.g. `--spawn`, `--name`) when a global flag or a wrapper-injected option precedes the subcommand
1701 * Fixed startup warnings (e.g. "N MCP servers need authentication") rendering one column right of the rest of the transcript
1702 * Fixed a backgrounded worktree session losing its checkout: the background session now holds the worktree's lock while it runs, so cleanup and `git worktree remove` leave it alone
1703 * Fixed @-mentions of other sessions not matching names typed with non-Latin characters (for example Korean entered through an IME)
1704 * Fixed an invalid `crossSessionInbound` value being silently ignored: it now warns and holds cross-session messages (user settings) or refuses them (managed settings) until fixed
1705 * Fixed rate-limit, usage, and fast-mode messages telling you to run `/usage-credits` when that command isn't available for your organization (e.g. hidden with `DISABLE_EXTRA_USAGE_COMMAND`)
1706 * \[VSCode] Fixed a chat tab getting stuck on "No conversation found" when its session was never saved; it now starts a new conversation instead
1707 * Improved the Workflow tool's prompt footprint: its description is now about 1k tokens instead of 5.7k, with the script-writing reference moved into a bundled `workflow-authoring` skill
1708 * Improved the prompt-footer PR badge to check GitHub less often while the pull request is unchanged; a push or a `gh pr` command still refreshes it right away
1709 * Improved managed settings: client-side timeout, MCP startup-mode, and stream-watchdog env vars no longer trigger the settings-approval prompt
1710 * Improved `/ultrareview <PR#>` to check before launch that the GitHub account connected to your Claude account can access the repository, and to explain how to fix it, instead of failing after the cloud session starts
1711 * Improved cross-session messaging: falls back to a private per-user `/tmp` directory when the default one can't be used, and the notice and `/status` name the directory to fix
1712 * Changed shift+enter in the agent view dispatch input to insert a newline (matching the prompt); ctrl+enter now dispatches and attaches
1713 * Changed `/loop`: self-paced dynamic mode and the no-prompt autonomous default are now always available, including on Bedrock/Vertex/Foundry
1714 * Changed Anthropic telemetry export failures to log at debug level as `[Anthropic telemetry]` instead of `[3P telemetry] OTEL diag error`, so they are not mistaken for your OTel collector failing
1715 * Changed cross-session messaging in Linux user namespaces: root-equivalent trust for unmapped owners is limited to canonical system directories
1716 * Changed `SendMessage` from a subagent to another session: the result now notes that any reply is delivered to the parent session's conversation, not to the subagent
1717</Update>
1718
1719<Update label="2.1.247" description="August 26, 2026">
1720 * Added the `SendFeedback` tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from `/feedback` (turn off with the `feedbackDrafts` setting)
1721 * Added `{id, text, cooldownSessions, priority}` entries, `tipsFile`, and `label` to `spinnerTipsOverride`, so organizations can rotate their own tips alongside the built-in ones
1722 * Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option
1723 * Added `/claude-api cost-optimize` to profile an existing project's Claude API spend and work through cost levers (caching, token hygiene, batch, effort, model choice) one measured change at a time
1724 * Updated the `/claude-api` skill with Admin API coverage (organization members, invites, workspaces, API keys, rate limit reports, workload identity federation, CMEK)
1725 * Fixed fast arrow-key + Enter sequences acting on the row above the one you navigated to in history search, `/config`, `/mcp`, `/skills`, background tasks, and `/model`
1726 * Fixed sub-agents dying on a first-call model 404: they now use the session's fallback model chain, and the error returned to the parent includes the error type, status, request id, and model
1727 * Fixed a hook or background agent that printed megabytes of error output being able to overflow the conversation and wedge the session on "Prompt is too long"
1728 * Fixed Ctrl keyboard shortcuts not firing under non-Latin (e.g. Cyrillic) keyboard layouts in kitty-protocol terminals
1729 * Fixed text like `<35;150;7M` being inserted into the prompt when a mouse report arrived split across reads right after the escape prefix
1730 * Fixed the Bash sandbox's after-command cleanup deleting a dotfile-managed `~/.claude/settings.json` symlink (nix/home-manager, stow) when it is repointed outside the sandbox's writable area
1731 * Fixed `/terminal-setup` overwriting your entire Zed `keymap.json` instead of merging in its keybinding
1732 * Fixed `/rename` silently confirming when the session registry could not be updated; it now says other sessions may still show the old name
1733 * Fixed `/compact` and "Summarize from here" in sessions started with `--agent` summarizing under the default system prompt instead of the conversation's own
1734 * Fixed a background session showing "opening…" forever in `claude agents` after its terminal host process died; the row now fails within seconds with the reason, and Enter restarts it
1735 * Fixed unbounded memory growth when a hook's or background task's output file could not be written; the file now notes where output was lost
1736 * Fixed `/install-github-app` over SSH: the copy shortcut now says how the sign-in URL was copied instead of always claiming success, and the URL appears immediately when no browser can open
1737 * Fixed shell commands carried over from the foreground logging an internal error or showing a misleading `[exited with code -1]` line when they finish in background sessions
1738 * Fixed a version-less marketplace plugin's live cache directory being deleted and recreated on a second-scope install, which could disrupt a running session using it
1739 * Fixed Remote Control sessions started with `/remote-control` not reporting the working-tree diff to connected clients
1740 * Fixed self-hosted runner sessions reporting `running` before Claude Code had started, which could trigger a premature "Claude is waiting for your input" notification from the Claude desktop app
1741 * Fixed first-run setup exiting with "Unable to conne
1733 * Fixed `claude --bg --model fable` on Max plans stopping to ask for usage credits while the interactive session on the same account still had Fable all
No line in this hunk matches that.