One read of Claude Code CLIclaude-code-20260817T210701Z
1 pages moved out of 187 read.
Pages moved
1
significant first
Pages read
187
in this capture
Captured
21:07 UTC
Corpus hash
3c2fee098d1c
sitemap-lastmod
What this read moved
1-1 of 1changelog Changed · +54 / -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="2.1.234" description="August 17, 2026">
10 * Added the optional `CLAUDE_CODE_PROJECT_DIR_NAME` environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory
11 * Added the `selection:clear` keybinding action, so a key can be bound to clear an in-app text selection; also works in the agents view
12 * Added a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states
13 * Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off in `/config` ("Continue automatically at usage limit")
14 * Claude is now told to use your account email only to identify you, and not to send it to unrelated services unless you ask
15 * Security: remote file reads, session restore, CLAUDE.md includes, workflow scripts and file uploads now reject Windows NT-namespace (`\??\`) paths, hardening the remaining pre-approval file accesses against the NTLM credential-leak vector
16 * Fixed auto mode in very long sessions repeatedly re-checking and denying sandboxed commands' network access after the conversation had been compacted
17 * Fixed session-scoped permission answers (including denies) being dropped when answering background subagent tool permission prompts
18 * Fixed a crash when an API response on the non-streaming fallback path (typically via third-party gateways) contained a thinking block missing its thinking field or a text block missing its text field
19 * Fixed markdown rendering becoming extremely slow for some messages containing unusual Unicode sequences
20 * Fixed `SendMessage` rejecting a recipient copied from `ListAgents` when the session name is at the 200-character cap or emoji-heavy
21 * Fixed repository detection mis-reading the host of git remotes with unusual userinfo, producing links and repo-specific behavior for the wrong host
22 * Fixed MCP diagnostics printing resolved secrets: scope-conflict warnings now show the configured `${VAR}` form, and connection-failure details show only the server origin
23 * Fixed `strictKnownMarketplaces` allowlists accepting SCP-style git marketplace sources whose host differs from the one git would actually connect to
24 * Fixed modal text such as the `/login` OAuth URL losing characters when copied in fullscreen
25 * Fixed a `---` horizontal rule in rendered markdown running into the line after it
26 * Fixed consecutive shell commands splitting into multiple "Ran 1 shell command" rows when todo/task updates were interleaved between them
27 * Fixed dialogs like `/permissions` opened while a `!` shell command was running being dismissed when the command finished
28 * Fixed a queued `!` shell command being sent to the model as plain text after pressing up-arrow to edit the queued input
29 * Fixed queued messages reappearing in the prompt history while still queued, Esc while selecting a queued message no longer interrupts the turn, and `!` mode no longer sticks after a mid-turn submit
30 * Fixed accepting the "Try the new fullscreen renderer?" prompt restarting the session without its permission mode (e.g. `--dangerously-skip-permissions`), tool allow/deny rules, model or effort flags
31 * Fixed `/tui` dropping launch `--allowed-tools`/`--disallowed-tools` rules when it restarts; it now declines to switch, with the reason, when the session has restrictions a restart can't carry over
32 * Fixed trust prompts omitting the repository-wide scope warning when the directory was first seen before the repository existed there
33 * Fixed a case where an IDE diff tab closing during a permission re-prompt could answer the new prompt with the previous input
34 * Fixed: files sent to the user during Remote Control sessions hosted by Claude Code Desktop or VS Code now upload, so they open on phone and web instead of showing an empty card
35 * Fixed: after `/login` while `CLAUDE_CODE_OAUTH_TOKEN` is set, the stale-token reminder no longer leaks into Claude's automatically resumed turn — it now appears only to you
36 * Fixed: permission previews now relay only to channel servers admitted by the inbound trust gate, and a server's explicit permission-capability opt-out is honored
37 * Fixed: credential masking on relayed permission previews can no longer hide commands, paths, or destinations from the approver; oversized private-key blocks now redact under full-strength redaction
38 * Fixed: provider API tokens that mask on permission previews now mask even when directly followed by shell delimiters
39 * Fixed Claude Desktop inter-session messages being silently dropped by the recipient session when cross-session messaging read as disabled, which left the sender's query "thinking" for many minutes
40 * Remote Control: signing this computer in to a different claude.ai account or organization now stops the running session within seconds and says why, instead of a misleading HTTP 404 hours later
41 * Remote Control sessions started from Claude Code Desktop or VS Code now keep phones and claude.ai/code updated on the session's permission mode (and claude.ai/code on the model) as they change
42 * Remote Control: effort picks made on a phone or on claude.ai/code now apply to terminal- and Desktop/VS Code-hosted sessions, and the session publishes its effort level to connected clients
43 * `SendMessage` and `ListAgents` now say when your account's session list was too long to check completely, instead of treating unseen sessions as absent
44 * Expired Anthropic profile credential now points you at `/login` when a claude.ai login would take precedence
45 * Improved the transcript: your own prompts now render markdown (highlighted code blocks, inline code, lists) the same way replies do
46 * Improved the "API returned an empty or malformed response" error to say what came back (content type, body kind, size, request ID) and why the original streaming request failed
47 * Improved auto-generated session titles to read as short, specific names (e.g. "Login button bug") rather than sentences restating your request (e.g. "Fix the login button on mobile")
48 * Reduced the context cost of loading the built-in `claude-api` skill from \~200k+ tokens to \~25k by loading reference docs on demand
49 * `/permissions` can now be opened while Claude is working — rule changes apply to the rest of the current turn
50 * `/add-dir <path>` can now be used while Claude is working; `/add-dir`, `/autocompact`, `/theme`, `/help`, `/config` and `/advisor` dialogs open mid-turn in the fullscreen TUI
51 * `/goal` now clears itself with a notice when a turn dies on an unrecoverable error (e.g. revoked auth, an exhausted credit balance, or a context overflow) instead of staying armed
52 * `/goal`: when background tasks keep a goal waiting for 30+ minutes, Claude now checks in on them instead of waiting indefinitely (set `CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0` to opt out)
53 * `claude setup-token` now rejects unexpected extra arguments instead of silently ignoring them
54 * Changed Esc in fullscreen mode to no longer clear a mouse text selection: it interrupts or dismisses as usual and the selection stays highlighted
55 * Removed the redundant "Allowed by auto mode classifier" line that auto mode showed under every Agent tool call
56 * Removed the "Default teammate model" setting from `/config`; agent-team teammates now use the leader's model unless the spawn names one
57 * Dimmed the elapsed-time counter on the running tool header so it no longer competes with the bold counts
58 * Background task notifications delivered between turns are now sent to the model inside `<system-reminder>` tags, matching mid-turn delivery
59 * Mantle: skip the admin-pin availability probe at startup when a main-loop model is already picked
60 * Windows: startup no longer stalls on repeated rename retries when `~/.claude.json` is read-only
61</Update>
62
963<Update label="2.1.233" description="August 14, 2026">
1064 * Added GitLab merge request URL support to the `--worktree` flag and the `claude agents` view (where MRs display as `!N`)
1165 * Added an opt-in `forward_user_identity` apps gateway setting on Anthropic upstreams that sends the signed-in user's identity as headers, so a proxy behind the gateway can attribute spend per user
from line 2184
21302184
21312185<Update label="2.1.126" description="May 1, 2026">
21322186 * The `/model` picker now lists models from your gateway's `/v1/models` endpoint when `ANTHROPIC_BASE_URL` points at an Anthropic-compatible gateway
2133 * * Added `claude project purge [path]` to delete all Claude Code state for a project (transcripts, tasks, file history, config entry) — supports `--dry-run`, `-y/--yes`, `-i/--interactive`, and `--all`
2134 * `--dangerously-skip-permissions` now bypasses prompts for writes to `.claude/`, `.git/`, `.vscode/`, shell config files, and other previously-protected paths (catastrophic removal commands still prompt as a safety net)
2135 * `claude auth login` now accepts the OAuth code pasted into the terminal when the browser callback can't reach localhost (WSL2, SSH, containers)
2136 * `claude_code.skill_activated` OpenTelemetry event now fires for user-typed slash commands and carries a new `invocation_trigger` attribute (`"user-slash"`, `"claude-proactive"`, or `"nested-skill"`)
2137 * Auto mode: the spinner now turns red when a permission check stalls, instead of looking like the tool is running
2138 * Host-managed deployments (`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`) no longer auto-disable analytics on Bedrock/Vertex/Foundry
2139 * Windows: PowerShell 7 installed via the Microsoft Store, MSI without PATH, or `.NET global tool` is now detected
2140 * Windows: when the PowerShell tool is enabled, Claude now treats PowerShell as the primary shell instead of defaulting to Bash
2141 * Read tool: removed the per-file malware-assessment reminder that could cause spurious refusals and "this is not malware" commentary on legacy models
2142 * **Security:** Fixed `allowManagedDomainsOnly` / `allowManagedReadPathsOnly` being ignored when a higher-priority managed-settings source lacked a `sandbox` block
2143 * Fixed pasting an image larger than 2000px breaking the session — images are now downscaled on paste, and oversized images in history are automatically removed and the request retried
2144 * Fixed showing the login screen for "OAuth not allowed for organization" errors — now shows guidance to contact your admin
2145 * Fixed OAuth login failing with timeout on slow or proxied connections, in IPv6-only devcontainers, and when the browser callback can't reach localhost
2146 * Fixed a rare race where a concurrent credential write could clear a valid OAuth refresh token
2147 * Fixed API retry countdown sticking at "0s" instead of counting down between attempts
2148 * Fixed "Stream idle timeout" error after waking Mac from sleep mid-request
2149 * Fixed background and remote sessions falsely aborting with "Stream idle timeout" during long model thinking pauses
2150 * Fixed a hang where the assistant could finish thinking but show no output after a run of empty turns
2151 * Fixed overly fast trackpad scrolling in Cursor and VS Code 1.92–1.104 integrated terminals
2152 * Fixed claude.ai MCP connectors being suppressed by manual servers stuck in needs-auth state
2153 * Fixed Japanese/Korean/Chinese text rendering as garbled characters on Windows in no-flicker mode
2154 * Fixed `Ctrl+L` clearing the prompt input — it now only forces a screen redraw, matching readline behavior
2155 * Fixed deferred tools (WebSearch, WebFetch, etc.) not being available to skills with `context: fork` and other subagents on their first turn
2156 * Fixed plan-mode tools being unavailable in interactive sessions launched with `--channels`
2157 * Fixed `/plugin` Uninstall reporting "Enabled" instead of "Uninstalled"
2158 * Bounded total size of file-modified reminders when a linter touches many files at once
2159 * Fixed `/remote-control` retries appearing stuck on "connecting…" — each retry now shows its result
2160 * Fixed Remote Control failure notification not showing the error reason for initial connection failures
2161 * Windows: clipboard writes no longer expose copied content in process command-line arguments visible to EDR/SIEM telemetry; also fixes >22KB selections not reaching the clipboard
2162 * PowerShell tool: bare `--` (e.g. `git diff -- file`) is no longer mis-flagged as the `--%` stop-parsing token
2163 * Fixed Agent SDK hang when the model emits a malformed tool name in a parallel tool call batch
2164</Update>
2165
2166<Update label="2.1.123" description="April 29, 2026">
2167 * Fixed OAuth authentication failing with a 401 retry loop when `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` is set
2168</Update>
2169
2170<Update label="2.1.122" description="April 28, 2026">
2171 * Added `ANTHROPIC_BEDROCK_SERVICE_TIER` environment variable to select a Bedrock service tier (`default`, `flex`, or `priority`), sent as the `X-Amzn-Bedrock-Service-Tier` header
2172 * Pasting a PR URL into the `/resume` search box now finds the session that created that PR (GitHub, GitHub Enterprise, GitLab, and Bitbucket)
2173 * `/mcp` now shows claude.ai connectors hidden by a manually-added server with the same URL, with a hint to remove the duplicate
2174 * Clarified the `/mcp` message shown when an MCP server is still unauthorized after the browser sign-in flow
2175 * OpenTelemetry: numeric attributes on `api_request`/`api_error` log events are now emitted as numbers, not strings
2176 * OpenTelemetry: added `claude_code.at_mention` log event for `@`-mention resolution
2177 * Fixed `/branch` producing forks that fail with "tool\_use ids were found without tool\_result blocks" when the source session contained entries from rewound timelines
2178 * Fixed `/model` not showing the Effort option for Bedrock application inference profile ARNs, and those ARNs not receiving `output_config.effort`
2179 * Fixed Vertex AI / Bedrock returning `invalid_request_error: output_config: Extra inputs are not permitted` on session-title generation and other structured-output queries
2180 * Fixed Vertex AI `count_tokens` endpoint returning 400 errors for users behind proxy gateways
2181 * Fixed `spinnerTipsOverride.excludeDefault` not suppressing the time-based spinner tips
2182 * Fixed ToolSearch missing MCP tools that connected after session start in nonblocking mode
2183 * Fixed `!exit` / `!quit` in bash mode terminating the CLI instead of running as a shell command
2184 * Fixed images sent to newer models being resized to 2576px per side instead of the correct 2000px maximum
2185 * Fixed remote control session idle status redrawing twice per second, which could flood `tmux -CC` control pipes and pause the terminal
2186 * Fixed assistant messages appearing blank in some sessions due to a stale view preference
2187 * Fixed a malformed hooks entry in `settings.json` no longer invalidating the entire file
2188 * Voice mode: keybindings bound to Caps Lock now show an error since terminals don't deliver Caps Lock as a key event
2189</Update>
2190
2191<Update label="2.1.121" description="April 28, 2026">
2192 * Added `alwaysLoad` option to MCP server config — when `true`, all tools from that server skip tool-search deferral and are always available
2193 * Added `claude plugin prune` to remove orphaned auto-installed plugin dependencies; `plugin uninstall --prune` cascades
2194 * Added a type-to-filter search box to `/skills` so you can find a skill in long lists without scrolling
2195 * PostToolUse hooks can now replace tool output for all tools via `hookSpecificOutput.updatedToolOutput` (previously MCP-only)
2196 * Fullscreen mode: typing into the prompt no longer jumps scroll back to the bottom after you've scrolled up to read earlier output
2197 * Dialogs that overflow the terminal are now scrollable with arrow keys, PgUp/PgDn, home/end, and mouse wheel in both fullscreen and non-fullscreen modes
2198 * Clicking any line of a long URL that wraps across rows in fullscreen mode now opens the full URL
2199 * SDK and `claude -p`: `CLAUDE_CODE_FORK_SUBAGENT=1` now works in non-interactive sessions
2200 * `--dangerously-skip-permissions` no longer prompts for writes to `.claude/skills/`, `.claude/agents/`, and `.claude/commands/`
2201 * `/terminal-setup` now enables iTerm2's "Applications in terminal may access clipboard" setting so `/copy` works, including from tmux
2202 * MCP servers that hit a transient error during startup now auto-retry up to 3 times instead of staying disconnected
2203 * The terminal tab session title is now generated in your configured `language` setting
2204 * Claude.a
2187 * * Added `claude project pur