One read of Claude Code CLIclaude-code-20260828T183701Z
1 pages moved out of 191 read.
Pages moved
1
significant first
Pages read
191
in this capture
Captured
18:37 UTC
Corpus hash
7055e9f8a1c0
corpus-hash
What this read moved
1-1 of 1changelog Changed · +74 / -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<Update label="2.1.251" description="August 28, 2026">
10 * Added `PreModelSwitch` and `PostModelSwitch` hook events (block, confirm, or annotate a model switch); `SessionStart` resume hooks now receive session staleness and the estimated re-cache cost
11 * Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only)
12 * Added a Spend limit bar to `/usage` and a `rate_limits.spend_limit` status line field for developers behind a Claude apps gateway with spend limits
13 * Added a per-session prompt-cache line to `/cost` (hit ratio, misses, tokens re-cached, warm/cold) and a matching `prompt_cache` object for status line scripts
14 * Added `attach`, `logs`, `stop`, `respawn`, and `rm` to `claude --help`; the `--resume` message for a running background session now names the exact `claude attach <id>` command
15 * Fixed file tools (Read, Write, Edit) following a symlink swapped inside the working directory after the permission check, which could read or write outside the approved location
16 * Fixed plugin commands declared in a marketplace entry being able to point outside the plugin directory; such paths are now rejected with a path-traversal error
17 * Fixed project settings being able to enable detailed beta tracing or raw API body logging, and a lower-scope beta tracing endpoint bypassing an OTLP collector pinned by managed settings or a host app
18 * Fixed the Workflow tool reading (and quoting in errors) a `scriptPath` outside what the session may read before the permission check ran
19 * Fixed Grep and Glob not applying `Read(...)` deny rules to files reached through a symlinked search path
20 * Fixed conversations getting stuck on "text content blocks must be non-empty" errors after a turn where the model produced only thinking
21 * Fixed the first launch on a fresh install starting in default mode instead of auto mode for accounts whose startup default is auto mode
22 * Fixed Opus 5 requests failing with "effort … is not supported when thinking is disabled" when effort was xhigh/max and thinking was turned off; effort is now sent as `high` in that case
23 * Fixed replying to a message Claude Desktop delivered from another session: `SendMessage` to that session id now delivers through Claude Desktop instead of failing with "not reachable"
24 * Fixed TUI lag with many parallel subagents: per-second progress ticks now replace their predecessor instead of piling up in the transcript
25 * Fixed agent teams: a teammate's final answer not reaching the team lead — it now arrives in the idle notification instead of a content-free "available" notice
26 * Fixed background subagents being unable to reply to a message from an unnamed sibling or parent agent (`from` was the agent type, which is not an address)
27 * Fixed managed-settings `disableAutoMode` arriving mid-session not moving an already-running auto-mode session back to default mode
28 * Fixed a "switch to Opus 1M for 5x more context" tip that appeared even when the current Opus model already has a 1M context window
29 * Fixed Claude apps gateway sessions treating a stored Anthropic profile (e.g. a Console sign-in) as active: listing it in `/status` and retrying gateway 401s with it, though requests never use it
30 * Fixed cloud sessions telling Claude the model had changed when the host was only setting the session's initial model
31 * Fixed Remote Control reporting a failure when an organization's policy disables it; it now shows a single quiet notice instead
32 * Fixed `/mcp reconnect` on Remote Control showing a generic withheld-detail error instead of the real remedy when a server was disabled in another session
33 * Fixed `--input-format stream-json`: client-injected assistant tool calls sent without a message id were merged into the first one and their results lost, including when resuming older sessions
34 * Fixed session transcripts being silently overwritten when a directory change relocated a session onto an existing same-ID transcript
35 * Fixed background sessions and their subagents being unable to edit files inside a git worktree they created with `git worktree add`
36 * Fixed background sessions occasionally starting without any plugin skills (and staying that way) when another Claude Code process was refreshing the plugin marketplace at the same moment
37 * Fixed selecting text in an opened background session inside tmux over SSH: it now copies to the tmux buffer like a foreground session instead of falling back to OSC 52
38 * Fixed SDK and cloud sessions hanging indefinitely when an SDK MCP server's handshake acknowledgment was lost; the wait now times out after 70 seconds and marks only that server failed
39 * Fixed self-hosted runner leaving a stuck session's Bash tool processes running after the session was force-stopped
40 * Fixed `/usage-credits` for Team and Enterprise members whose admin set the org's usage-credit limit to \$0: it now offers to ask the admin instead of saying a cap was reached
41 * Fixed `--worktree --tmux` with a merge-request number on a gitlab.com origin trying a doomed GitHub-style fetch first instead of fetching the GitLab ref directly
42 * Fixed Ctrl+G failing with "Emacs quit unexpectedly" in background sessions for editors that open `/dev/tty`, such as `emacs -nw` and `micro`
43 * Fixed an `additionalDirectories` entry containing a null byte crashing startup, or breaking `/add-dir` and later settings updates when it came from an SDK host, IDE, or hook; it is now skipped
44 * Fixed the MCP server menu's copy shortcut: it now says how the sign-in URL was copied instead of always claiming success
45 * Fixed italic text (such as the session recap line) rendering as highlighted blocks in GNU screen and in tmux sessions using a `screen` terminal type
46 * Fixed `claude mcp add --header` and `claude mcp add-json` help text naming the wrong transports
47 * 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
48 * 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
49 * 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
50 * 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
51 * 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
52 * Fixed the managed-settings approval prompt re-appearing after signing in again to the same Claude apps gateway when the settings are unchanged
53 * 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
54 * Fixed cloud session creation advising GitHub setup after a transient GitHub connection failure — the message now says to retry instead
55 * Improved CPU usage during turns in interactive sessions by cutting redundant UI re-renders
56 * Improved install size: the native binary is about 5 MB smaller
57 * 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"
58 * 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
59 * Improved framing of messages from your own subagents: Claude is told the sender is a worker inside this session, not an unrelated Claude session
60 * Improved the prompt placeholder to read "Message @name…" while viewing a background subagent or fork transcript opened from the subagent panel or `/tasks`
61 * Improved sanitization of MCP server names in error messages, menus, and command results
62 * 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
63 * Improved the managed settings approval dialog to list only the settings that changed since you last approved them
64 * 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
65 * Changed `/radio` to be available on Bedrock, Vertex AI, Foundry, and Claude Platform on AWS, and when telemetry is disabled
66 * 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
67 * 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
68 * 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`)
69 * Changed the default model for seat-based Enterprise subscriptions to Opus 5, matching other premium plans
70 * Changed `/effort` to save your default effort level per model, so each model keeps its own setting when you switch
71 * 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`
72 * 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`
73 * 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
74 * 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
75 * 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
76 * 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`)
77 * 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
78 * Removed syntax highlighting for six rarely used languages (1c, gml, isbl, mathematica, maxima, sqf); the binary is 2.5 MB smaller
79 * \[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
80 * \[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`
81</Update>
82
983<Update label="2.1.250" description="August 28, 2026">
1084 * Bug fixes and reliability improvements
1185</Update>
from line 2058
19842058 * Fixed a regression where a custom API gateway could receive the user's Anthropic OAuth credential instead of the gateway's own token
19852059 * Fixed subagent (Agent tool) frontmatter MCP servers ignoring `--strict-mcp-config`, `--bare`, remote mode, enterprise managed MCP config, and managed-settings MCP server allow/deny policies
19862060 * `--strict-mcp-config` no longer strips inline `mcpServers` from explicitly-passed agent definitions (`--agents` / SDK `agents`), and blocked subagent MCP servers now surface a visible warning
1987 * Fixed the Windows PowerShell installer reporting "Installation complete!" when installation actually failed
1988 * Fixed `claude update` installing the latest version instead of the configured release channel's version for npm installations
1989 * Fixed excessive memory usage (multiple GB) when resuming a session by transcript file path on machines with many stored sessions
1990 * Fixed `claude agents` and `claude --bg` running on a stale daemon started before binary-takeover support, even after upgrading
1991 * Fixed a hang where the CLI could fail to exit when stdin was closed without EOF in stream-json mode, leaving a stale session marker behind
1992 * Fixed malformed `file://` links in Claude's responses not being clickable in the terminal
1993 * Fixed `claude --help` rendering unwrapped output on terminals narrower than 92 columns
1994 * Fixed MCP tool progress notifications not rendering in the collapsed tool view
1995 * Fixed `Agent` tool with `subagent_type: 'claude'` running in an undocumented temporary worktree, which could silently discard outputs written to gitignored paths
1996 * `/bg` while Claude is responding now continues the response in the background session instead of dropping it
1997 * Fixed `/btw` keyboard shortcuts becoming unresponsive in background sessions while a task is running
1998 * Fixed background sessions writing temp files to `$CLAUDE_JOB_DIR` triggering a "sensitive file" permission prompt
1999 * Fixed recovering a background agent whose working directory was deleted showing a truncated stack trace instead of a clear error message
2000 * Fixed `EnterWorktree` not being available immediately in background sessions (previously required `ToolSearch` first)
2001 * Fixed `cmd+k` in iTerm2/Terminal.app not repainting attached background sessions
2002 * Fixed the IME candidate window appearing at the bottom of the screen instead of next to the input caret in attached background sessions on Windows
2003 * Fixed background-color bleed when attaching to a background agent from 256-color-only terminals after the agent had rendered file diffs
2004 * Fixed `/copy` and copy-on-select silently failing to update the system clipboard when attached to a background session inside tmux
2005 * Fixed opening `claude agents` with Remote Control enabled leaving zombie session entries on the Code tab after exiting
2006 * Fixed `/rename` in background sessions not updating the session banner immediately
2007 * Fixed Windows update rollback: if a Windows update fails, Claude Code now restores the original executable by copy and tells you how to recover
2008 * \[VSCode] Fixed Claude Code processes not shutting down cleanly when VS Code closed on Windows, causing false "unclean exit" reports and orphaned MCP servers
2009 * `/model` now saves your selection as the default for new sessions (matching the IDE). Press `s` in the picker to switch models for the current session only.
2010 * If you customized the `modelPicker:setAsDefault` keybinding, rename it to `modelPicker:thisSessionOnly` in keybindings.json (the `d` action was replaced by `s`)
2011</Update>
2012
2013<Update label="2.1.152" description="May 27, 2026">
2014 * `/code-review --fix` now applies review findings to your working tree after the review, surfacing reuse, simplification, and efficiency suggestions; `/simplify` now invokes `/code-review --fix`
2015 * Skills and slash commands can now set `disallowed-tools` in frontmatter to remove tools from the model while the skill is active
2016 * Added `/reload-skills` command to re-scan skill directories without restarting the session
2017 * `SessionStart` hooks can now return `reloadSkills: true` to re-scan skill directories, making skills installed by the hook available in the same session
2018 * `SessionStart` hooks can now set the session title via `hookSpecificOutput.sessionTitle` on startup and resume
2019 * Added a `MessageDisplay` hook event that lets hooks transform or hide assistant message text as it is displayed
2020 * Added `pluginSuggestionMarketplaces` managed setting: admins can allowlist org marketplaces whose plugins may be suggested via context-aware tips
2021 * `claude plugin marketplace remove` now accepts `--scope user|project|local` for symmetry with `marketplace add`, `install`, and `uninstall`
2022 * Claude Code now switches to your configured `--fallback-model` for the rest of the session when the primary model is not found, instead of failing every request
2023 * Auto mode no longer requires opt-in consent
2024 * Vim mode: `/` in NORMAL mode now opens reverse history search (like Ctrl+R), matching bash/zsh vi-mode
2025 * The `/usage` breakdown now includes large session files; files are scanned with a streaming read so memory usage stays flat
2026 * Thinking summaries in the collapsed group now stay readable for at least 3 seconds, render as markdown, and cap at 10 lines (`Ctrl+O` shows the full thinking)
2027 * In fullscreen mode, the "Thinking for Ns" indicator now counts up live while the model is thinking, and keeps its value if you interrupt mid-thought
2028 * Simplified the Workflow tool's inline progress display — live agent counts now show only in the persistent workflow status row below the prompt
2029 * The post-response timer now shows "Waiting for N background agents/workflows to finish" when backgrounded agents or workflows are still running, and reports the cumulative time once their results are processed
2030 * Added the session entrypoint as an OpenTelemetry metric attribute (`app.entrypoint`, opt-in via `OTEL_METRICS_INCLUDE_ENTRYPOINT=true`)
2031 * Fixed terminal styling degrading in very long sessions by recycling the renderer's style pool
2032 * Fixed the sandbox-enabled warning not appearing in condensed startup mode — it now shows in every layout
2033 * Fixed the loading spinner showing "still thinking"/"almost done thinking" while a tool is running, and reset the thinking status to "thinking" after each tool
2034 * Fixed focus mode showing a spurious "N messages hidden" count on turns with no hidden activity
2035 * Fixed clicking a link inside an expanded tool result collapsing the section instead of opening the link
2036 * Fixed markdown table cell borders inheriting the color of inline code, wrapped continuation lines losing their style, and empty header cells showing a label in the narrow-terminal stacked layout
2037 * Fixed plugin MCP servers with the same command but different environment variables being incorrectly deduplicated
2038 * Fixed `/doctor` reporting "marketplace not found" or "plugin not found" for stale `enabledPlugins` entries referencing removed marketplaces or dropped plugins
2039 * Fixed plugins that track a git branch silently no longer receiving updates after the plugin registry was rebuilt
2040 * Fixed remote MCP servers failing to connect in Claude Code Remote sessions when the egress proxy is enabled
2041 * Fixed the effort-change confirmation dialog appearing when the conversation has no messages or when switching between effort levels that resolve to the same underlying value
2042 * Fixed the Agent tool description referencing an agent list that is never delivered when running with `--bare` or with attachments disabled
2043 * Fixed a background worker crash in `claude agents` when accepting a stale permission prompt after a subagent was cancelled
2044 * Fixed `cache_creation_input_tokens` reporting as 0 in transcript and result usage when the API reports cache writes only via the nested `cache_creation` breakdown
2045 * Fixed the PushNotification tool incorrectly reporting "Mobile push not sent (Remote Control inactive)" in SDK-hosted sessions when Remote Control is enabled
2046 * Fixed sessions getting stuck after a model or login switch left stale thinking-block signatures in history; now stripped proactively with a retry safety-net
2047</Update>
2048
2049<Update label="2.1.150" description="May 23, 2026">
2050 * Internal infrastructure improvements (no user-facing changes)
2051</Update>
2052
2053<Update label="2.1.149" description="May 22, 2026">
2054 * `/usage` now shows a per-category breakdown of what's driving your limits usage — skills, subagents, plugins, and per-MCP-server cost
2055 * `/diff` detail view can now be scrolled with the keyboard (arrows, `j`/`k`, `PgUp`/`PgDn`, `Space`, `Home`/`End`)
2056 * Markdown output now renders GFM task list checkboxes (`- [ ] todo` / `- [x] done`) instead of plain bullets
2057 * Enterprise: added the `allowAllClaudeAiMcps` managed setting to load claude.ai cloud MCP connectors alongside `managed-mcp.json`
2058 * Fixed a PowerShell permission bypass: built-in `cd` functions (`cd..`, `cd\`, `cd~`, `X:`) changed the working directory undetected, letting a later command read outside the workspace
2059 * Fixed the sandbox write allowlist in git worktrees covering the entire main repository root instead of only the shared `.git` directory (with `hooks/` and `config` denied)
2060 * Fixed PowerShell prefix/wildcard allow rules (e.g. `PowerShell(dotnet.exe build *)`) not pre-approving native executables and scripts
2061 * Fixed a permission-analysis gap where the parser trusted stale variable-tracking values for `PWD`/`OLDPWD`/`DIRSTACK` across `cd`/`pushd`/`popd`
2062 * Fixed `find` in the Bash tool exhausting the macOS system file/vnode table and crashing the host on large directory trees
2063 * Fixed the managed-settings approval dialog leaving the terminal frozen after accepting at startup
2064 * Fixed `/ultraplan` and remote session creation failing with "Could not capture uncommitted changes" when the working tree has no real changes
2065 * Fixed `otelHeadersHelper` failing silently when the script path contains spaces; helper failures are now reported in `/doctor` and the debug log
2066 * Fixed the thinking spinner staying amber across tool calls and onto fresh thinking bursts
2067 * Fixed collapsed Bash output reporting the wrong hidden-line count for outputs with many short lines
2068 * Fixed slash-command argument-hint clipping trailing typed characters when the hint overflows the input box
2069 * Fixed argument-hint and progressive arg suggestions not appearing after Tab-completing a skill whose frontmatter `name:` differs from its directory basename
2070 * Fixed the status bar showing the user's baseline `/effort` setting instead of the effort level applied by skill/agent `effort:` frontmatter
2071 * Fixed Ctrl+O transcript view freezing at the moment it was opened instead of tailing new messages
2072 * Fixed editing a recalled prompt-history entry losing the edit when navigating further up/down with arrow keys
2073 * Fixed `/config` exit summary reporting phantom changes to auto-compact and theme when toggling unrelated settings
2074 * Fixed `/insights` crashing when cached session-meta files are missing optional fields
2075 * Fixed malformed PowerShell and History tool calls with missing input being misclassified as reads in transcript collapsing
2076 * Fixed renaming a Remote Control session from claude.ai or the Claude mobile app not updating the local session name for `claude --resume`
2077 * Fixed a race where a just-submitted prompt could appear twice in the up-arrow history
2078 * Fixed tapping the "Jump to bottom" pill in fullscreen mode not dismissing it immediately
2079 * Improved `/feedback` reports to include the conversation that happened before context compaction, making issues from earlier in long sessions easier to triage
2080</Update>
2081
2082<Update label="2.1.148" description="May 22, 2026">
2083 * Fixed the Bash tool returning exit code 127 on every command for some users (a regression introduced in 2.1.147)
2084</Update>
2085
2086<Update label="2.1.147" description="May 21, 202
2061 * Fixed