Claude Code changelog changedchangelog
Nearest release: v2.1.283, published 3 hours 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 25 Sep 2026 22:00 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 25 Sep 2026 22:07 UTC.
Upstream edited
Recorded here
Lines+97added
Lines−0removed
From line
6
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits44to 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="2.1.283" description="September 25, 2026">
10 * 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`
11 * Added `availableModelsMatch` managed setting: with `"exact"`, an `availableModels` entry allows only the model version it names, so new releases stay blocked until listed
12 * Added `deniedModels` managed setting to block specific models, even when `availableModels` allows them
13 * Added MCP tool, WebFetch and WebSearch outputs to the `tool.output` OpenTelemetry span event when `OTEL_LOG_TOOL_CONTENT=1`
14 * Added `/doctor prompt-audit` (also `/checkup prompt-audit`) to audit your CLAUDE.md files, skills, agents and commands for prompting patterns written for older models
15 * Added click-to-expand for truncated messages from your other sessions in fullscreen mode
16 * Added `path` to `--plugin-dir` load-failure entries in the stream-json `system/init` `plugin_errors`, naming the directory that did not load
17 * Added an opt-in `load_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 tested
18 * Added a `mantle` upstream provider to the Claude apps gateway for Amazon Bedrock's Mantle endpoint
19 * Fixed SDK sessions losing a deferred tool call or finished tool result when a turn ended early, a held approval prompt after a worker restart, and a non-streaming fallback's `result.usage`
20 * Fixed MCP progress notifications being discarded once a long-running tool call moved to the background; the background task now shows the latest progress
21 * Fixed stdio MCP servers being left running when the session ended while they were still starting
22 * Fixed a brief HTTP 404 from a stateless remote MCP server (for example a proxy mid-redeploy) leaving that server unusable for the rest of the session while still shown as connected
23 * Fixed MCP sign-in for a server with no valid URL failing with an opaque SDK error; `/mcp` no longer offers Authenticate for such servers
24 * Fixed the weekly Fable limit not appearing in `/usage` and the VS Code usage meters when telemetry is disabled
25 * Fixed `/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
26 * Fixed `/model` picker showing a hardcoded Haiku version and price when `ANTHROPIC_DEFAULT_HAIKU_MODEL` pins a different model
27 * Fixed dynamic workflows started during a model fallback running every agent on the fallback model instead of retrying the configured model
28 * Fixed `DISABLE_PROMPT_CACHING_HAIKU` having no effect when Haiku is the session's main model
29 * Fixed `claude plugin validate` saying Claude Code accepts a plugin or marketplace name it cannot install; such names in `marketplace.json` now fail validation
30 * Fixed `claude plugin validate` passing plugins whose `outputStyles`, `themes`, `monitors`, or `lspServers` paths are missing or point outside the plugin directory
31 * Fixed `claude plugin details` showing 0 MCP servers for plugins that declare their servers in `plugin.json`
32 * Fixed `claude plugin marketplace remove` not saying which installed plugins it uninstalled with the marketplace; it now lists them
33 * Fixed `claude 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 scope
34 * Fixed plugins that declare no version being silently restored at their source's newest commit, not the installed one, when their cached files were missing
35 * Fixed user-installed plugins and marketplaces failing to load with "cache-miss" after the home or config directory was moved, for example in bind-mounted devcontainers
36 * Fixed `installed_plugins.json` showing no plugins when it holds a record under an invalid plugin id; such a file loads again
37 * Fixed `installed_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
38 * Fixed permission dialogs in screen-reader mode reading quoted commands and paths as if they were the dialog's own text
39 * Fixed `/context` not counting MCP server instructions: they now appear as their own row and count toward the total
40 * Fixed markdown links in the Warp terminal rendering as plain text instead of clickable hyperlinks
41 * Fixed `claude mcp add`, `add-json`, and `remove` reporting success when the user or local config file could not be written, for example inside a sandbox
42 * Fixed the first words of a reply in a cloud session sometimes appearing late instead of streaming as Claude writes them
43 * Fixed Claude's built-in keybindings guide saying chords time out after 1 second instead of 3, and calling `cmd` an alias of `meta`, which could produce `cmd+` shortcuts most terminals never send
44 * Fixed `keybindings.json` silently accepting a misspelled modifier such as `ctl+k`; it now warns in the debug log and suggests the fix
45 * Fixed footer hints still saying "Enter to view" after `footer:openSelected` was rebound or unbound in `keybindings.json`
46 * Fixed keys typed quickly together (type-ahead, key repeat, bursts over ssh or tmux) sometimes being handled against stale state
47 * Fixed worktree checkouts failing certificate verification (for example on Git LFS downloads) when the CA certificate is passed to git as `GIT_CONFIG_COUNT` environment pairs
48 * Fixed sandboxed `git` asking credential helpers to store the sandbox proxy's login, which printed "failed to store"
49 * Fixed managed `sandbox` settings being ignored entirely when one nested value was invalid; the invalid value now fails closed and the rest of the block still applies
50 * Fixed Claude's edits to its own auto-memory notes being blocked as sensitive-file writes when Claude Code was started in a subdirectory of a git repository
51 * Fixed Remote Control being unavailable on paid plans when telemetry is turned off with `DISABLE_TELEMETRY` or `DO_NOT_TRACK`
52 * Fixed the `/remote-control` menu cutting its QR-code hint mid-word in narrow terminals
53 * Fixed vim mode `.` 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 line
54 * Fixed vim mode cursor placement: recalling a prompt over 10,000 characters in normal mode no longer leaves the cursor past the end, and `V` then `p` now lands on the first non-blank
55 * Fixed vim mode `J` 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 does
56 * Windows: Fixed the PowerShell tool letting `cmd /c rd`, `rmdir`, `del` or `erase` delete drive roots, the home folder and other folders that `Remove-Item` refuses
57 * Improved the `/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
58 * Improved MCP tool results: images returned by MCP tools are now also saved to a file, so Bash, Read and other tools can open them
59 * Improved `/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
60 * Improved lists in `/help`, `/hooks`, `/copy`, `/chrome`, `/memory`, `/ide`, `/release-notes`, `/rewind`, `/diff`, `/remote-env`, `/plugin` and other pickers with page keys, mouse wheel and clicks
61 * Improved lists beside a search box, such as `/skills` and `/artifacts`, to draw their pointer dim while the search box has the keys, so only one pointer is highlighted
62 * Improved the compaction spinner: its timer now starts when compaction begins and it counts the summary's tokens as they stream, replacing the percentage bar
63 * Improved the browser page shown after signing in to an MCP server: centered layout, dark mode, and new artwork
64 * Improved the Skill tool's reply when a skill belongs to a plugin that failed to load, so Claude tells you the plugin could not be loaded instead of calling the skill uninstalled
65 * Improved `prompt-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 kept
66 * Improved recovery from an `installed_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 file
67 * Improved artifact database reads: an ordered query that returns a full page now says it is one page and how to read the rest
68 * Improved first-reply latency: a pattern-compile step that ran at the end of a session's first reply now runs while the reply streams in
69 * Improved first-request latency by reusing the preconnected API connection
70 * Improved startup: `claude -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 launch
71 * Improved startup for claude.ai accounts whose Artifact tool features aren't known yet, as on a first run: the prompt no longer waits up to 1.5 s to check them; the first message waits if needed
72 * Changed interactive sessions on third-party providers or with telemetry off to start in auto mode when no permission mode is configured; `permissions.defaultMode` still overrides it
73 * Changed the `/ultrareview` launch dialog to say that reviewing a local branch may upload uncommitted changes to tracked files
74 * Changed the `/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
75 * Changed prompt suggestions in the terminal to appear less often after 20 in a row go unused; using one brings them back
76 * Changed `--system-prompt` and `--append-system-prompt` to accept their text and `-file` forms together; the file's text comes first
77 * Changed `Skill(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
78 * Changed `/rewind` and `/diff` lists to move on the same keybinding actions as every other list (`select:*`); `messageSelector:*`/`diff:*` rebinds still work
79 * Changed the `/workflows` run list to size itself like other lists: half the terminal inline, and it keeps its title on screen when the prompt shows below
80 * Changed `claude 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 version
81 * Changed artifact watching: a watch that was armed automatically (not one you asked for) now ends after 3.5 hours with no activity; publishing or watching the artifact again re-arms it
82 * Self-hosted runner: Changed lifecycle hooks' git to skip a repository's Git LFS `pre-push` hook, ignore a writable system `core.hooksPath`, and not sign commits without `--configure-git`
83 * Self-hosted runner: Changed `GIT_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
84 * Reverted the 2.1.282 reservation of the `claude-ai` name: skills, commands, workflows and MCP servers' skills and prompts so named load again, and `Skill(claude-ai:*)` rules are ordinary prefix rules
85 * \[VSCode] Fixed the permission mode indicator showing Default while the session kept running in auto or bypass mode after an automatic switch out of it failed; the switch is now retried until it lands
86 * \[VSCode] Fixed a session teleported from the web dropping the messages sent while Claude was working
87 * \[VSCode] Fixed a Web session staying hidden from the session list, and an empty chat opening in its place, when an older version had saved an empty local copy of it
88 * \[VSCode] Fixed a reopened session splitting a turn at a message Claude received mid-turn, such as an automatic continuation
89 * \[VSCode] Fixed a reloaded session showing a rewound-away turn, or only the rows before a compaction
90 * \[VSCode] Fixed the footer's agents pill drawing its icon off-center, with the status dot against the edge, in narrow panels
91 * \[VSCode] Fixed the chat input showing its text slightly below the cursor and selection after pasting lines that end with a line break into a long prompt
92 * \[Cloud sessions] Improved adding a repository to a running cloud session: a private repository your GitHub account can read but not push to now attaches for reading
93 * \[Cloud sessions] Fixed cloud sessions occasionally redoing an already-finished step, such as posting a duplicate comment or push, after recovering from a server-side restart
94 * \[Cloud sessions] Changed new routine schedules to default to a few minutes past the hour, with a note that routines set exactly on the hour can start several minutes late
95 * \[Claude Tag] Added a "Channels Claude can search" admin setting that limits Claude's Slack search to public channels it has been added to, set per organization, workspace or channel
96 * \[Claude Tag] Added a Back to Slack button on the page shown after connecting your Claude account, returning you to the thread you started from
97 * \[Claude Tag] Fixed a channel's configure page listing no connectors or plugins when the channel gets its access bundle through an attach rule; rule-attached bundles are now shown
98 * \[Claude Tag] Fixed access-bundle repository search missing repositories on GitHub App installs that are limited to a large list of selected repositories
99 * \[Claude Tag] Fixed Claude occasionally posting the same reply twice when a new message interrupted it mid-reply
100 * \[Claude Tag] Fixed channel routines that stopped running in older private channels whose Slack channel ID changed, for example after a Slack Connect share
101 * \[Claude Tag] Fixed conversations in a channel set to "Channel only" all ending when a non-guest member joined and Slack was slow to confirm their membership
102 * \[Code Review] Fixed "@claude review" requests going silent when GitHub failed to return the pull request: the request is retried once, and a comment explains if it still fails
103 * \[Code Review] Fixed billing for a review that stopped at its time limit with nothing verified: it now shows as incomplete, isn't charged, and is retried once
104</Update>
105
9106<Update label="2.1.282" description="September 24, 2026">
10107 * Added a `maxProseWidth` setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width
11108 * Added a startup notice, and `/status` and `claude doctor` entries, listing telemetry variables in a project's settings files that were ignored or that turned telemetry off
from line 1738
16411738 * 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
16421739 * Fixed Remote Control sessions started with `/remote-control` not reporting the working-tree diff to connected clients
16431740 * 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
1644 * Fixed first-run setup exiting with "Unable to connect to Anthropic services" when managed settings configure Claude apps gateway sign-in and Anthropic endpoints are unreachable
1645 * Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) sometimes showing the previous permission mode when you switch modes right after sending a message
1646 * Fixed cloud sessions going silent when the session's container restarts between turns while a background agent, shell, or monitor is still running — the resumed session now reports the lost work
1647 * Improved plugin marketplace hardening: names containing control or invisible characters are rejected, and marketplace-supplied text in `/plugin` and `claude plugin` output is escape-safe
1648 * Improved Bedrock, Vertex, and Foundry sessions (and any with telemetry disabled): Claude is now told when a configured MCP server failed to connect, instead of concluding its tools don't exist
1649 * Changed Sonnet 5's default auto-compact window to its full 1M context, so sessions on the 1M window now auto-compact at about 967K tokens instead of about 934K
1650 * Changed cross-session peer messages to collapse by default to a one-line `Message from @<sender>: <first line>` preview; Ctrl+O expands the full body
1651 * Changed terminal hyperlinks in rendered markdown: link targets that point at a network or automounter path, contain a control character, or lead with an invisible character now render as plain text
1652 * Changed the prompt-footer PR badge to skip its GitHub re-check on terminal refocus when the last check is under a minute old
1653 * Changed analytics to stay off from startup, not only after login, when managed settings force gateway login or a custom OAuth deployment is configured
1654 * Changed Claude apps gateway sign-in requests to identify Claude Code (a `surface=claude_code` device-authorization parameter and a `claude-code/<version>` User-Agent)
1655 * Changed organization sign-in enforcement to exit at start when the administrator's managed settings cannot be read, even if host-supplied or per-user Windows registry settings exist
1656</Update>
1657
1658<Update label="2.1.246" description="August 25, 2026">
1659 * Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. `Bash(git * main)`), since they also match options inserted before the subcommand
1660 * Added an Auto mode tab to `/permissions` for viewing and editing auto mode classifier rules
1661 * Added the turn's completion time to the end-of-turn duration line, e.g. `✻ Sautéed for 23s · done 6:05 PM`
1662 * Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress
1663 * Fixed a severe transcript slowdown when a diff contained a very long single line (e.g. a base64 string); such lines now render truncated with a marker
1664 * Fixed erratic fullscreen scrolling when positioned at an earlier message, including jump-to-bottom getting stuck mid-transcript
1665 * Fixed background sessions failing to open after 45 seconds when Claude Code's starting directory had been deleted, the machine had slept, or the host is slow to start processes
1666 * Fixed background sessions failing to open with "Couldn't start the background service … EACCES" when another Claude Code process was re-installing the npm package at that moment
1667 * Fixed markdown rendering being disabled for a whole message when its first 500 characters contained no markdown, and for `+`/`N)` lists and setext headings
1668 * Fixed MCP tool calls interrupted by an incoming message in headless/remote sessions being reported to the model as "completed with no output" instead of an explicit interrupted error
1669 * Fixed MCP tool arguments being sent as JSON strings when the parameter's schema is empty (`{}`), instead of their real type
1670 * Fixed a command interrupted mid-run showing as "Ran 1 shell command" with no sign it was cut
1671 * Fixed pressing ← or running `/background` during a dynamic workflow restarting its finished subagents; it now asks first and says how many subagents would restart
1672 * Fixed opening a just-started session in `claude agents` while its worker was still booting (common on Windows) stopping it with "was stopped while the respawn was in flight"
1673 * Fixed `claude agents` listing a backgrounded named session twice; backgrounding the same conversation again now numbers the new row (e.g. `my-session (2)`)
1674 * Fixed the background retention sweep removing git worktrees under `.claude/worktrees/` that you created yourself when an old background-session record pointed at them
1675 * Fixed auto mode tool calls being denied as "temporarily unavailable" on very large sessions by scaling the safety-check deadline with prompt size
1676 * Fixed the plugin cache creating duplicate SHA-named directories for the same plugin
1677 * Fixed plugin skills whose frontmatter `name` already includes the `<plugin>:` prefix showing it doubled in the slash menu (e.g. `/plugin:plugin:skill`)
1678 * Fixed `claude plugin update` failing for an installed plugin given its bare name (only the fully-qualified name worked)
1679 * Fixed plugin installation failing when `plugin.json` was saved with a UTF-8 byte-order mark (BOM)
1680 * Fixed `/reload-plugins` reporting 0 skills for plugins that define skills under `skills/*/SKILL.md`
1681 * Fixed hook error messages showing a literal `${CLAUDE_PLUGIN_ROOT}` instead of the resolved plugin path
1682 * Fixed `/rename` replacing the theme's prompt border color (including a custom theme's `promptBorder`) with the default cyan; the border now keeps your theme's color unless you pick one with `/color`
1683 * Fixed custom theme diff colors (`diffAdded`/`diffRemoved` and their dimmed variants) being ignored in diffs and the `/theme` preview
1684 * Fixed a `keybindings.json` binding with an unknown action name silently deadening that key; it is now skipped so the default binding keeps working, and a warning is logged under `--debug`
1685 * Fixed `/stats` activity heatmap showing each day's activity one cell off (Sunday's count under Monday) in timezones east of UTC
1686 * Fixed `/fork` from an already-forked or backgrounded session starting the new session with an empty conversation
1687 * Fixed prompts beginning with `/--` (e.g. Lean doc comments) being rejected as an unknown slash command instead of being sent to Claude
1688 * Fixed the `@` file picker staying open after the typed text stopped matching a real path
1689 * Fixed the status line's cost and duration resetting to zero after navigating to the agents view and back
1690 * Fixed fullscreen mode moving keyboard focus onto the control under the pointer when you clicked the terminal window only to bring it back into focus
1691 * Fixed path completion failing when the completion token or working directory contained a null byte
1692 * Windows/macOS: Fixed headless sessions not cleaning up stale entries in `~/.claude/sessions` left by sessions that exited uncleanly
1693 * Fixed the UI stopping with a render error on the first tool call when a third-party Anthropic-compatible endpoint (`ANTHROPIC_BASE_URL`) streams a `tool_use` block without an `id`
1694 * Fixed the Write tool reporting "Out of memory" or freezing for a long time after overwriting a very large existing file, even though the file had been written
1695 * Fixed `claude plugin install <name>` exiting silently (or hanging in a terminal) instead of reporting an error when `~/.claude/plugins/known_marketplaces.json` is empty or corrupted
1696 * Fixed resumed sessions failing every turn with a 400 when the saved history contains tool blocks the Anthropic API does not accept (typically written by a third-party API proxy)
1697 * Fixed `curl -fsSL https://claude.ai/install.sh | bash` failing with "Raw mode is not supported" for some Team/Enterprise users with server-managed settings
1698 * Fixed sessions that ended in plan mode resuming outside plan mode in the VS Code extension, and in `claude -p --continue`/`--resume` with a permission prompt tool, when no permission mode was set
1699 * Fixed the `Notification` hook not firing while the sandbox "Network request outside of sandbox" permission prompt is waiting
1700 * Fixed Bash permission checks to always require approval for malformed commands with a dangling `&&` or `||` operator
1701 * Fixed `--strict-mcp-config` sessions prompting to approve `.mcp.json` servers they would never load, which left background sessions waiting at startup
1702 * Fixed telemetry and metrics requests to Anthropic carrying the API key configured for a third-party gateway (`ANTHROPIC_BASE_URL`); a credential is now only sent to its own host
1703 * Fixed a visible API error on the first prompt after idle when `apiKeyHelper` returns short-lived JWTs: an expired cached token is now refreshed before sending, and 401/403 auth errors retry quietly
1704 * Fixed memory growing with session length in the fullscreen and Ctrl+O transcript views: each rendered message row no longer retains a full copy of the transcript-wide tool lookups
1705 * Fixed `/ultrareview` runs and cloud sessions launched at the same time from one repository (e.g. from several worktrees) sometimes starting with another launch's uncommitted changes
1706 * Fixed the task progress count (e.g. `3/5`) shown for background cloud sessions such as `/autofix-pr` occasionally missing a task
1707 * Fixed Remote Control sessions keeping their placeholder name in claude.ai and the Claude app until the second prompt; the auto-generated title now appears after the first prompt
1708 * Fixed MCP tools marked `requiresUserInteraction` still offering "Yes, and don't ask again" in their permission prompt; the option wrote an allow rule the tool then ignored
1709 * Fixed the self-hosted runner ending its live sessions or exiting when a work-poll response is malformed (e.g. an intercepting proxy's HTML page); it now retries the poll
1710 * Improved `/cd`: the new directory's project settings, hooks, `.mcp.json` servers (behind the usual approval prompt), skills, and agents now take effect right after the move instead of on `--resume`
1711 * Improved Bash tool latency on bash shells by replaying snapshot functions without a base64 subshell per function
1712 * Improved subagent results: a subagent that stops at its `maxTurns` limit now returns its output marked as partial, with a hint to continue it via `SendMessage`, instead of appearing finished
1713 * Improved non-interactive sessions (`-p`, SDK, cloud sessions) to automatically continue a response cut off mid-stream by a server error, connection loss, or stall instead of ending with an error
1714 * Improved attribution of usage telemetry to your organization for workload identity federation sessions, events sent while `apiKeyHelper` runs at startup, and after a login token expired while idle
1715 * Changed `/code-review` so Claude can also start it on its own on Bedrock, Vertex AI, and Foundry, through the Claude apps gateway, and when telemetry or non-essential traffic is disabled
1716 * `/goal`: Changed idle sessions to start at most three check-ins on long-running background work per goal; your next message allows three more
1717 * Changed `claude install` and `claude update` to defer a pending managed-settings consent prompt to the next interactive session instead of prompting mid-command
1718 * Changed OpenTelemetry plugin events for plugins synced from claude.ai: `plugin_id_hash` now reflects the plugin's real marketplace, and `enabled_via` is `admin-install` for admin-installed plugins
1719 * Fixed the command sandbox's filesystem configuration not respecting `--setting-sources`
1720</Update>
1721
1722<Update label="2.1.245" description="August 25, 2026">
1723 * Fixed a crash on startup on Linux distributions that ship glibc 2.44 (for example Arch Linux, CachyOS and Fedora Rawhide)
1724</Update>
1725
1726<Update label="2.1.243" description="August 25, 2026">
1727 * Added a Loops breakdown to `/usage`: per-loop run count, total tokens, tokens per run, and last run, so runaway or chatty `/loop` tasks are easy to spot
1728 * Added `modelPicker` setting: curate the `/model` picker with an ordered, labeled list of models (any id spelling, including Vertex/Bedrock ids), appended to or replacing the built-in lineup
1729 * Added `promptCacheTtl` and `subagentPromptCacheTtl` settings so API-key and cloud-provider users can keep a 1-hour prompt cache on the main conversation while subagents stay at 5 minutes
1730 * Added `modelPricing` managed setting so an organization's contracted per-model rates and discount multiplier are used for `/cost`, the status line, and telemetry cost figures instead of list price
1731 * Added a keyless sign-in under `/login` → Anthropic Console: "Sign in with your Console account" (recommended) alongside creating an API key, so organizations that don't allow API keys can sign in
1732 * Added a `Skipped sources` line to `/status` that lists managed settings sources (for example `managed-settings.json`) present but not applied because a higher-precedence managed source is active
1733 * Added a `managed` marker in `/mcp` and `/plugins` on claude.ai connectors whose authentication is managed by your organization
1734 * Added a tip pointing claude.ai users who haven't connected GitHub for Claude Code on the web to `/web-setup`
1735 * Added a `/status` line showing whether GitHub is connected for Claude Code on the web (Pro/Max), pointing to `/web-setup` when it isn't
1736 * Added the model (and effort level) each subagent ran on to `/tasks` and the agent detail dialogs
1737 * Fixed remote MCP servers in non-interactive (`-p`) and SDK sessions never recovering after a dropped connection; they now reconnect automatically or report as failed
1738 * Fixed MCP server sign-in started from the desktop app failing with "Invalid redirect URI" on servers that support client ID metadata documents (for example Linear)
1739 * Fixed auto mode staying unavailable at startup when a temporary server-side disable was cached and later flag fetches failed
1740 * Fixed auto mode tool calls being denied as "temporarily unavailable" after about a minute of waiting when the API was briefly overloaded and asked the client to retry
1741 * Fixed the `/model` picker silently ignoring an Ultracode selection; picking Ultracode now applies it to the current session
1742 * Fixed `/resume` only listing the 50 most recent sessions; the picker now loads more as you scroll
1743 * Fixed cloud sessions resuming after a mid-turn restart with a pending hook or background-task notification re-sent as the prompt instead of the normal continuation message
1744 * Fixed cross-session messaging silently turning off inside user namespaces and rootless containers after the 2.1.232 socket-directory hardening
1745 * Fixed text that hangs outside its container (for example th
1741 * Fixed first-run setup exiting with "Unable to conne
No line in this hunk matches that.