Claude Code Changelog

UNOFFICIAL – but tolerated – bot posting Claude Code CLI, feature flag & prompt changes. Full CC history in github repo.

[Claude Code Changelog @ClaudeCodeLog]

Friends, @marc_krenn here.

I haven't updated @ClaudeCodeLog in a while, and I'd love to hear what you'd like to see improved.

Anything I could change to make the account more useful, relevant, fun or interesting to you?

Really appreciate any feedback & have a nice weekend! :)

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.308 further changes

Metadata:
• Time since 2.1.307 release: 7h 48m 35s
• Bundle file size: +10.1 kB (+0.0%)

• Prompt files: +3 (+9.7%)
• Prompt tokens: +10,950 (+17.7%)

Prompt token mix by kind:
• system: 57.5%→57.9%
• tools: 42.5%→42.1%

Files:
• metadata: https://t.co/BuBnCELFWH
• prompt stats: https://t.co/4sE4p0SmDk

More details: https://t.co/L0ouqoVzPU

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.308 has been released.

1 CLI change

Highlights:
• CLI bug fixes and reliability improvements that reduce failures and produce smoother, more stable behavior

Further details in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.308 changelog:

Other change:
• Bug fixes and reliability improvements

Source: https://t.co/WmGMzldgrE

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.308 is about to be released
#cccnext

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.307 additional updates

CLI surface:
Added:
• env vars: CLAUDE_CODE_SPAWNED_BY_SERVER, CLAUDE_SSH_DAEMON_CHILD, CLAUDE_SSH_RUN_DIR, SELF_HOSTED_RUNNER_AGENT_PROXY_URL, SELF_HOSTED_RUNNER_CHECKOUT_HOOK_TIMEOUT_MS, SELF_HOSTED_RUNNER_DIFF_FINDS_NESTED_REPOSITORY
• models: claude-lsremote-T

Removed:
• env vars: AGENT_PROXY_AUTH_TOKEN, AGENT_PROXY_URL
• models: claude-haiku-3-5, claude-lsremote-E

File: https://t.co/V1cxxUzdP3

Metadata:
• Time since 2.1.306 release: 18h 41m 11s
• Bundle file size: +483.1 kB (+0.7%)

• Prompt files: +1 (+3.3%)
• Prompt tokens: +4,281 (+7.5%)

Prompt token mix by kind:
• system: 51.0%→57.5%
• tools: 49.0%→42.5%

Files:
• metadata: https://t.co/4qxlCHJGZu
• prompt stats: https://t.co/kq2DNdcuPZ

More details: https://t.co/cls3zhhXXu

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.307 has been released.

43 CLI changes, 1 system prompt change

Highlights:
• Added /claude-api api-version to switch Claude API code to 2026-10-21, enabling updated API behavior
• Stop double HTTP MCP sends on disconnect; only idempotent/read-only tools retried to avoid duplicates
• The /clear command now makes cleared conversations persist across restarts, preventing them from reappearing

Full details are in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.307 system prompt updates

Notable changes:
1) Claude’s tool-hook guidance is cleaned up: the Harness bullet now ends after “treat hook output as user feedback” instead of the malformed “feedback.Response”. This reduces ambiguity/noise in how Claude interprets hook output during tool use.

Links:
1) https://t.co/DgHu9ZTFXZ

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.307 is about to be released
#cccnext

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.306 additional modifications

CLI surface:
Added:
• models: claude-lsremote-E

Removed:
• models: claude-lsremote-F

File: https://t.co/hT7y4nLUyd

Metadata:
• Time since 2.1.305 release: 6h 54m 24s
• Bundle file size: +0.0 kB (+0.0%)

• Prompt files: +3 (+11.1%)
• Prompt tokens: +9,115 (+18.9%)

Prompt token mix by kind:
• system: 48.6%→51.0%
• tools: 51.4%→49.0%

Files:
• metadata: https://t.co/i4aLmRO0B7
• prompt stats: https://t.co/7N7uYUpwzd

More details: https://t.co/HpCHatIFDX

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.306 is now available.

2 CLI changes

Highlights:
• Fixed claude -p reporting 'Not logged in' in cloud sessions without env vars, restoring login status
• Fixed API errors being replaced by 'prompt is too long' in MCP-heavy sessions, showing original API errors

More details in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.306 changelog:

Fixes:
• Fixed claude -p inside cloud sessions reporting "Not logged in" when started without the session's environment variables
• Fixed an API error being replaced by "prompt is too long", and an unneeded compaction, in sessions with many MCP tools

Source: https://t.co/bumj1zuKEZ

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.306 is about to be released
#cccnext

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.305: additional changes

CLI surface:
Added:
• models: claude-lsremote-F

Removed:
• env vars: API_TIMEOUT_MS

File: https://t.co/zaT1SU0Qgh

Metadata:
• Time since 2.1.304 release: 23h 52m 39s
• Bundle file size: +655.2 kB (+1.0%)

• Prompt files: +3 (+12.5%)
• Prompt tokens: +8,852 (+22.4%)

Prompt token mix by kind:
• tools: 54.3%→51.4%
• system: 45.7%→48.6%

Files:
• metadata: https://t.co/5vvcrkiooQ
• prompt stats: https://t.co/vi1HZYQ7LD

Other prompt/string highlights:
1) Adds a tool that executes a given Bash command and returns its output.
2) Adds a tool to start a new agent that handles complex multi-step tasks.

Links:
1) https://t.co/8zBd4c6LQo
2) https://t.co/kZu8q2s3bP

More details: https://t.co/LC7DNj6woI

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.305 has been released.

38 CLI changes

Highlights:
• Executes a provided Bash command and returns its output so callers can directly capture shell results
• System starts a new agent for complex tasks, delegating long workflows to dedicated subagents so they continue
• Sandbox allows nested user namespaces on Linux, enabling Chromium and rootless podman to run there

Complete details in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.305 changelog:

New features:
• Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections
• Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) notices a usage limit that was lifted before its reset

Fixes:
• Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search, and behind gateways with ToolSearch disallowed or left out of --tools (a 2.1.304 regression): Claude Code now retries without it
• Fixed /effort and /autocompact settings not applying when the model name differed from a modelOverrides value by letter case or a [1m] tag
• Fixed new worktrees in a bare repository sometimes starting from local HEAD instead of the default branch, and unchanged subagent worktrees sometimes not being cleaned up
• Fixed Bash commands on a full disk failing with a raw ENOSPC file path: the error now says the disk is full and that nothing ran
• Fixed an MCP server passed by a cloud session or by the SDK's setMcpServers being replaced later in the session by a same-named server from your own settings
• Fixed Claude naming the wrong model for a subagent's work after the subagent switched to a fallback model
• Fixed cloud sessions and teammates not telling Claude when a compaction had to leave the oldest messages out of its summary to fit
• Fixed more cases of scheduled Cowork cloud sessions waiting five minutes for each subagent whose WebFetch needed a URL approval that nobody was there to give
• Fixed Workflow resume re-running already-completed pipeline() and parallel() agents instead of serving them from the run's journal
• Fixed Remote Control leaving empty "(session)" entries in /resume after switching conversations with /resume
• Fixed /usage rows being cut off in narrow terminals
• Fixed startup warnings printing as raw text above the logo: they now go to the debug log, and permission rules that restrict nothing show as warning rows under the banner
• Fixed screen reader mode: search boxes now say "Search:" instead of a symbol VoiceOver read as "telephone recorder", and highlighted prompt text, such as Ctrl+R search matches and "ultrathink", no longer has spaces inside words
• Self-hosted runner: Fixed a start script that shares only its stdout with the runner or orchestrator failing with Resource temporarily unavailable when TERM is set (a 2.1.300 regression)

Improvements:
• Improved /usage: each warning is now a one-line fix that names its source, and f applies the fixes; the same fixes appear in VS Code and /doctor
• Improved MCP consent dialogs so an Enter meant for the prompt is less likely to be taken as Accept
• Improved a mod's Image to draw its picture in iTerm2 3.5 and later with fullscreen rendering, where it showed only its alt text

Security/safety change:
• Changed plugins that Claude Desktop mounts by path to no longer keep their allowed-tools when your organization's managed settings set allowManagedPermissionRulesOnly

Other changes:
• Self-hosted runner: Fixed repository access failing since 2.1.296 when a git credential helper or askpass program reads its settings through GIT_CONFIG
• Self-hosted runner: Fixed the orchestrator reporting a spawn-runner hook as timed out when a runner it started in the background kept its output open
• Remote Control: Improved the spawn-mode messages: pressing w now says the new mode is saved for the folder, and a later claude remote-control start that uses the saved mode says where it came from
• Changed allowedMcpServers to stop filtering managed-mcp.json stdio servers that use ＄{VAR} only in env: one your allowlist left out now loads on upgrade; use deniedMcpServers to keep it off
• Changed the /artifacts delete confirmation to take 1 or Enter to keep, 2 to delete, and Esc to cancel; y and n no longer answer it
• Changed a mod's docked pane to stay within 45% of the terminal's width, including a width kept from a wider terminal
• [VSCode] Added a "Running start-up hooks" spinner status, with a screen reader announcement, while SessionStart or Setup hooks run
• [VSCode] Fixed the spinner cutting off "Compacting..." when your spinnerVerbs setting replaces the built-in verbs with short ones
• [VSCode] Changed the message shown when a session does not start in time and no hook is running: it now leads with the output logs and lists causes instead of pointing to sign-in and network first
• [Cloud sessions] Fixed the Cloud environments admin page wrongly refusing to save an existing environment with an "installs packages" error
• [Cloud sessions] Improved deleting a self-hosted environment so the dialog and error messages say what blocks the delete and what it will affect
• [Claude Tag] Added public Slack channels Claude hasn't joined to the Claude Tag admin Add place search, so admins can set one up from there
• [Claude Tag] Fixed Claude Tag access bundles so a repository that moved to another GitHub account can be added again
• [Claude Tag] Fixed a routine set up in a Slack DM thread no longer posting after another routine in that thread restarted the conversation; both now keep posting there
• [Claude Tag] Fixed routines set up in a Slack thread reporting success without posting after the conversation ended; those runs are now skipped and the creator is told
• [Claude Tag] Improved Claude Tag admin pages in large organizations so plugin, skill and bundle edits work while the channel list is still loading
• [Code Review] Fixed Code Review sometimes not reviewing the newest commit when several pushes landed on a pull request during a review
• [Code Review] Changed Code Review re-reviews so they no longer open with LGTM while earlier blocking findings are still open

Source: https://t.co/wga1EJygBw

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.305 is about to be released
#cccnext

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.304 additional updates

CLI surface:
Added:
• env vars: CLAUDE_INTERNAL_FC_OVERRIDES
• models: claude-haiku-3-5, claude-test:explorer

Removed:
• env vars: CLAUDE_CODE_AUTO_COMPACT_WINDOW, NODE_ENVC
• models: claude-code-cli, claude-haiku-3-5B, claude-lsremote-K

File: https://t.co/999i2X5xny

Metadata:
• Time since 2.1.303 release: 21h 50m 51s
• Bundle file size: +853.1 kB (+1.4%)

• Prompt files: +5 (+26.3%)
• Prompt tokens: +12,506 (+46.3%)

Prompt token mix by kind:
• tools: 51.7%→54.3%
• system: 48.3%→45.7%

Files:
• metadata: https://t.co/u9fHplk6v0
• prompt stats: https://t.co/0uhSfLSjsZ

More details: https://t.co/K5YG4K0z8g

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.304 has been released.

76 CLI changes

Highlights:
• tool.check decider:\"person\" makes a mod require human approval; unapproved asks are refused with mod reason
• Added /auto-mode-setup: guided scan of project and history so Auto Mode learns environment for smarter actions
• Added /claude-api managed-agents-secure: read-only check flags Managed Agents deviations vs Anthropic guide

Full details available in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.304 changelog:

New features:
• Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin
• Added decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked
• Added e.isReadOnly to a mod's tool.check event, set when the tool call is read-only
• Added /auto-mode-setup: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled sessions
• Added /claude-api managed-agents-secure, which compares a Managed Agents agent's settings with Anthropic's published security guide, without changing anything
• Added the names of the tools called earlier to the compaction summary in the transcript view (Ctrl+O)
• Added a warning on Pro and Max plans when resuming an inactive conversation would use a noticeable share of your 5-hour usage limit: resume anyway, or start a new conversation and Claude can look up the previous one if you refer to it

Fixes:
• Fixed the organization policy not refreshing until the hourly check after approving an ANTHROPIC_API_KEY at startup or switching "Use custom API key" in /config
• Fixed sandboxed commands failing to start on Linux when a sandbox.filesystem.denyRead glob contains brackets that are not a character class, such as a [user-id] route folder
• Fixed rm -r of a mounted drive or a folder at its top level (/Volumes, /media, WSL's /mnt/c) not getting the safety prompt that rm -rf /Applications gets
• Fixed CLAUDE_CODE_TRANSCRIPT_LOCAL_GC dropping messages from the saved transcript when the disk filled up while the file was being trimmed
• Fixed a plugin keeping a headless run going past --max-turns, Stop, or ended input by spawning subagents or re-running a finished one
• Fixed a failed mod reload removing the tools and commands of the version that stays loaded, and its messages being wrong or silent about whether the previous version is still loaded
• Fixed a click on a mod's button being lost when buttons with the same label and no key were redrawn unchanged
• Fixed mod sharing in the built-in plugin-authoring skill stopping at the secret scan on machines with managed settings and on Team and Enterprise plans
• Fixed scheduled Cowork cloud sessions waiting five minutes again for each subagent whose WebFetch needed a URL approval that nobody was there to give
• Fixed Write results and rejected edits showing a file outside the working directory as ../../…; they now show ~/… or the full path
• Fixed a https://t.co/ldz5BaC3j0 Directory plugin's skills not running as commands when picked from the "/" menu in Cowork cloud sessions
• Fixed Remote Control permanently withholding a desktop conversation's history when a different account was signed in to the terminal
• Fixed Remote Control failing to start from Claude Desktop when DISABLE_TELEMETRY or DO_NOT_TRACK is set on a paid plan
• Fixed model switches, messages and interrupts waiting behind a context usage check in SDK and desktop sessions
• Fixed context_management: Extra inputs are not permitted errors behind LLM gateways; Claude Code now resends the request without that field
• Fixed OpenTelemetry settings delivered through server-managed settings being ignored for the whole session after signing in during first-run setup or the first start after /logout
• Fixed unsandboxed Bash commands in Claude Desktop Code tab sessions on macOS and Linux not seeing environment variables exported in shell startup files such as ~/.zshrc
• Fixed the Consumer Terms notice being skipped for a day or longer after a server error
• Fixed /privacy-settings offering choices that may not apply to you after a network or server error
• Fixed a "Context limit reached" or "Prompt is too long" error after stopping a turn while Claude Code was compacting a conversation the API had rejected as too long
• Fixed subagents sometimes forgetting their most recent work when they were messaged or resumed right after finishing
• Fixed claude --help text for --tools, --resume, --debug, --json-schema, --disable-slash-commands, --system-prompt-snapshot and claude update to match actual behavior
• Fixed claude --worktree removing the worktree and its branch without asking at exit when HEAD was detached or on another branch, which could lose commits
• Fixed resumed and cloud sessions sending Claude the whole skill list again each time plugins reloaded at startup
• Fixed an interrupt not ending a Read that waits on an idle pipe or device named like an image
• Fixed /effort status, /effort ultracode and the prompt's effort indicator showing a guessed effort level when CLAUDE_CODE_EFFORT_LEVEL is auto or unset and no level is sent
• Fixed a PreToolUse hook's deny reason being replaced by a timeout error when an Agent SDK callback hook on the same tool call timed out
• Fixed Bash and PowerShell deleting a large command's output file when it could not be copied to the session's tool-results folder, unless the disk is full
• Fixed notes typed into a multiple-choice question with previews being cut off with "…" in terminals under about 100 columns, hiding what was typed (anthropics/claude-code#82768)
• Fixed self-paced /loop wakeups scheduled at the 1-hour maximum firing just after the 1-hour prompt cache expired, so those wakeups no longer re-read the conversation uncached
• Fixed agent teams: approving a shutdown request from the main session no longer exits the whole CLI
• Fixed a skill's once hook also removing another skill's identical hook after it ran
• Fixed transcript mode's { and } landing the prompt on an inconsistent row, or off screen, instead of the transcript's first row
• Fixed CLAUDE_CODE_AUTO_COMPACT_WINDOW=200k silently setting a 100K window: the variable now accepts k and M suffixes like --autocompact, and warns when a value is out of range or ignored
• Fixed Ctrl+C in the agents view clearing a text selection without copying it when pressed before the mouse button was released

Improvements:
• Improved /usage to say when a rate limit on usage data ends instead of "try again in a moment"
• Improved the lines shown when a mod written in the session loads, reloads or fails to load
• Improved artifacts with several views: when you ask for links to them, Claude now writes out each view's link and explains that the address bar stays the same as you switch views
• Improved cloud sessions: a new conversation's first turn no longer waits for the local (stdio) MCP servers of plugins synced from https://t.co/ldz5BaC3j0, unless a server sets alwaysLoad: true
• Improved how a remote session recovers its status when the server refuses a status update that carried other session data
• Improved session file size in auto mode: the safety classifier's context is no longer stored with every request
• Improved the claude -p invalid-settings warning: a file that did not load lists only what stopped it, and long lists are capped per file
• Improved resume of large compacted sessions in SDK and headless mode: the first request after resuming is sent sooner
• Improved responsiveness and throughput when many subagents are running at the same time
• Improved memory use when sending requests in long or resumed conversations
• Windows: Improved git command start-up with a standard Git for Windows install by running its git.exe directly instead of through its cmd launcher

Removals:
• Removed the notes from claude plugin validate that predicted where a mod's hooks would run
• Removed the "(research preview)" label from the /fast dialog title on Opus 5.5

Other changes:
• Self-hosted runner: Improved the error shown when the git host answers "not found" for a session's repository: it now names the repository and whom to ask
• Changed mods' https://t.co/RfZH6hwYvi hooks to receive each settings layer and rewrite the merged settings, so a managed mod can make an organization's setting a ceiling, including the cleanupPeriodDays the retention sweep uses
• Changed the /artifacts delete confirmation to show numbered choices: 1 or Enter keeps the artifact, 2 deletes it, and y, n and Esc still work
• Changed the question that turns on the mods Claude writes in a session to plain text with no link or session id; it stays up when a new turn starts, and Claude tells you what loaded when you turn them on
• Changed tool search to be on by default behind a custom ANTHROPIC_BASE_URL; a 400 or 422 from the gateway is retried without it
• Changed compaction to send Claude the skill list again afterwards; /reload-skills now sends only new or changed skills
• Changed skill hooks: the skills of one source (a repo, your own folder, or a plugin) can register at most 1,024 hooks and 16,384 matcher characters per session
• Changed skills under a policy that allows hooks from plugins only: a skill used in the main conversation whose hooks are kept out no longer gets its allowed-tools
• Updated the /claude-api skill to use the ant CLI on Claude Platform on AWS instead of falling back to the SDK or curl
• [VSCode] Added mod drawing in the chat panel for sessions on Amazon Bedrock, Google Vertex AI and Microsoft Foundry, behind an LLM gateway, or with telemetry turned off
• [VSCode] Fixed one cause of sessions failing to start with "Subprocess initialization did not complete within 60000ms": time a SessionStart command hook spends running no longer counts toward the limit, up to 10 minutes in total
• [VSCode] Fixed a session closed while it was starting keeping its Claude Code process running until the start ended
• [VSCode] Fixed a mod's drawings disappearing from a long-open panel until the next turn on machines that also run an older Claude Code
• [VSCode] Fixed Past conversations hiding sessions when claudeCode.claudeProcessWrapper is set
• [VSCode] Changed background sub-agents to show as one status line under their Agent card instead of streaming every step into the chat; the full transcript stays in /tasks
• [Cloud sessions] Fixed folders in the composer's @ list showing no name in cloud sessions, where picking one added only a space instead of a mention
• [Claude Tag] Fixed Claude going silent in a thread when its channel becomes shared across Enterprise Grid workspaces mid-task; it now posts a one-time note to @-mention it in a new thread
• [Claude Tag] Fixed @Claude !fork typed outside a thread getting no visible reply; Claude now shows you a private note saying to run it from inside a thread
• [Code Review] Added review levels to Code Review: Owners choose Quick, Standard (the default), or Deep for the organization, and can give individual repositories their own level
• [Code Review] Added an option in Code Review admin settings to review every repository in a GitHub organization, including ones added later, without selecting them one by one
• [Code Review] Fixed pull requests opened within a minute or two of an admin turning on Code Review being silently skipped; they are now retried and reviewed

Source: https://t.co/Udbr1JDrVK