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]

Claude Code 2.1.218: additional updates

CLI surface:
Added:
• models: claude-coworker-terminal

Removed:
• env vars: CLAUDE_CODE_ENABLE_XAA

File: https://t.co/MpqMH8SJHH

Metadata:
• Time since 2.1.217 release: 23h 5m 23s
• Bundle file size: +777.3 kB (+2.1%)

• Prompt files: -3 (-15.0%)
• Prompt tokens: +6,098 (+18.9%)

Prompt token mix by kind:
• system: 56.7%→62.0%
• tools: 43.3%→38.0%

Files:
• metadata: https://t.co/ZaFBUOAjLR
• prompt stats: https://t.co/ZtVHJr47VQ

Other prompt/string highlights:
1) Clarifies that the edit tool performs exact string replacements in files.

Links:
1) https://t.co/9tbXrbmqD1

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

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.218 has been released.

37 CLI changes

Highlights:
• /code-review runs as background subagent so reviews don't fill conversation and stacked /commands target it
• Screen-reader mode announces deleted words/lines for common deletions, providing audible edit feedback
• Fixed Windows paths with \u-prefixed segments corrupted into CJK chars in tool inputs, restoring access

Full details available in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.218 changelog:

New features:
• Added screen-reader announcements of deleted text for word and line deletions (Option+Delete, Ctrl+W, Cmd+Backspace, Ctrl+U, Ctrl+K) in --ax-screen-reader mode
• Added HTTP status and error text to claude mcp list and /mcp when a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace
• Added an announcement when fast mode changes as a result of switching models via /config model=<x> or Remote Control
• Added yes/no/on/off/1/0 (case-insensitive) as accepted values for skill and plugin frontmatter booleans, alongside true/false

Fixes:
• Fixed Windows paths with \u-prefixed segments (like C:\Users\unicorn) being corrupted into CJK characters in tool inputs, which made those files inaccessible
• Fixed the left arrow key discarding the conversation with no undo: presses right after editing now ask to confirm, and Esc in the agent view returns to the conversation it backgrounded
• Fixed multi-line paste collapsing into one line with j in place of newlines in terminals that encode pasted newlines as Ctrl+J
• Fixed /context reporting stale pre-compact token usage after compacting from the message picker
• Fixed /ultrareview failing on descriptive arguments like "review my auth changes" — they now run a review of your current branch with the text applied as a note to the findings
• Fixed /code-review ultra silently running a local review in non-interactive sessions — it now launches the cloud review
• Fixed gateway spend metering to price Bedrock application-inference-profile ARNs and other config-mapped upstream model IDs at the configured model's rates
• Fixed mojibake when a long IDE selection was truncated mid-emoji, and a case where a tool executor error could be silently dropped
• Fixed an engine teardown race that could start and abandon a phantom turn, and made input pushed after close consistently rejected
• Fixed spurious "[Request interrupted by user]" messages after interrupted tool calls, and an unpaired tool_use block left in the transcript when a tool aborted mid-response
• Fixed VoiceOver reading "new line" instead of echoing the typed space at the end of the input in --ax-screen-reader mode
• Fixed plugin and settings panels not moving the terminal cursor to the focused row, so screen readers and magnifiers can follow arrow-key navigation
• Fixed crashes (maximum call stack exceeded) when a deeply nested watched directory tree was deleted or moved, and when rendering deeply nested UI trees
• Fixed pull request events occasionally being lost when a session exited immediately after creating or linking a PR
• Fixed the Bedrock setup wizard failing profile verification for assume-role profiles in partitioned AWS regions and on proxy-only networks
• Fixed rare negative or incorrect turn duration measurements after a system clock adjustment by timing turns with a monotonic clock
• Fixed the "N MCP servers need authentication" startup notice over-counting https://t.co/ldz5BaC3j0 connectors that aren't connected in https://t.co/ldz5BaC3j0
• Fixed prompt history entries being dropped or duplicated when history writes raced or failed
• Fixed a retry loop that re-sent identical doomed requests after a context-overflow error with a large thinking budget; Ctrl+B backgrounding now applies the same background-shell caps as other paths
• Fixed agent frontmatter hooks running from untrusted folders: hooks now require the agent file's own folder to have accepted workspace trust
• Fixed fork-session lineage being lost after compaction in headless and SDK sessions
• Fixed a resumed session failing every turn, or crashing on resume, when its history held a malformed delta attachment
• Fixed remote sessions continuing to send heartbeats after their worker was replaced, which left long-lived desktop and IDE processes retrying a rejected request every few seconds forever

Improvements:
• Improved /ultrareview error feedback so Claude can correct an invalid argument instead of retrying it unchanged
• Improved auto mode: the dangerous-rm, background-&, and suspicious-Windows-path checks no longer open permission dialogs; the auto-mode classifier adjudicates them instead
• Improved sandbox command restrictions for IDE interactions
• Improved trust dialogs to name the repository root the grant covers

Other changes:
• Changed /code-review to run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target
• Changed /deep-research to start only when invoked manually; Claude no longer launches it on its own
• Changed plan mode with auto to no longer prompt for Bash commands the static analyzer can't prove read-only; the auto-mode classifier judges them instead
• Changed server-managed settings so benign feature and cost toggles no longer trigger the settings-approval prompt
• Changed agent markdown files to reject agent names containing :, which is reserved for plugin namespacing
• Changed skills with context: fork to run in the background by default; opt out per skill with background: false

Source: https://t.co/UecwsnSlQm

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.218 is about to be released
#cccnext

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.217 additional updates

CLI surface:
Removed:
• env vars: TEST_ENABLE_SESSION_PERSISTENCE

File: https://t.co/5CCMNbWsFJ

Metadata:
• Time since 2.1.216 release: 1d 0h 3m 10s
• Bundle file size: +222.6 kB (+0.6%)

• Prompt files: +3 (+17.6%)
• Prompt tokens: +7,002 (+27.7%)

Prompt token mix by kind:
• system: 52.3%→56.7%
• tools: 47.7%→43.3%

Files:
• metadata: https://t.co/nGc1xxVl0r
• prompt stats: https://t.co/yKbnFH90TT

Other prompt/string highlights:
1) Clarified grep tool docs to note it’s a ripgrep-based search tool, recommend using Grep for search tasks, and refine the output_mode, head_limit, and offset parameter descriptions.

Links:
1) https://t.co/bwkKiNr7AE

More details: https://t.co/jcVRr1bmKl

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.217 has been released.

20 CLI changes

Highlights:
• Prompts instruct use of the ripgrep-backed Grep tool for search tasks, yielding faster, more accurate results
• Added warnings when transcript writes fail (e.g. disk full) or session saving is disabled to avoid silent loss
• Limit concurrent subagents to 20 (default), configurable via env var, to prevent unbounded agent fan-out

Complete details in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.217 changelog:

New features:
• Added emoji shortcode autocomplete in the prompt input: type :heart: to insert ❤️, or :hea for suggestions — disable with the emojiCompletionEnabled setting
• Added warnings when transcript writes are failing (e.g. disk full) or when session saving is off due to an inherited environment variable, instead of losing transcripts silently
• Added a cap on concurrently-running subagents (default 20, override with CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS) so one message can't fan out unbounded background agents

Fixes:
• Fixed a memory leak where truncated MCP tool outputs kept the full untruncated result in memory for the rest of the session
• Fixed Windows auto-update failures that could leave claude.exe missing; failed updates now restore the preserved executable automatically
• Fixed background session isolation not canonicalizing symlinked working directories, which could let sessions escape their workspace folder
• Fixed auto-compact never triggering for Claude Opus 4.8 on Bedrock and /compact failing once over the limit
• Fixed corporate mTLS, TLS-verify, OAuth scope, and proxy settings being ignored in Claude Desktop sessions
• Fixed screen reader mode's startup announcement being cut off by the first prompt render, and the thinking status row re-rendering every few seconds to update elapsed time and token counts
• Fixed managed settings that set OTEL_EXPORTER_OTLP_ENDPOINT not governing all signals — lower-scope signal-specific overrides no longer redirect telemetry away from the managed endpoint
• Fixed --resume/--continue and /resume failing with a TypeError when a transcript has a malformed attachment entry
• Fixed Remote Control sessions not showing a pending permission prompt or dialog to viewers that connected after it appeared
• Fixed background shells sometimes becoming impossible to stop after a session is sent to the background (/background or ←) or when the session exits on a heavily loaded machine, most visible on Windows
• Fixed a CLAUDE.md or SKILL.md paths frontmatter value with many brace groups OOM-killing or stalling the CLI at startup — brace expansion is now budget-bounded
• Fixed the transcript preview sitting flush against the input area when attaching to a starting background session; it now leaves the same one-line gap as the live layout, so the transcript no longer shifts when the session takes over
• Fixed --max-budget-usd not stopping background subagents: once the cap is reached, new spawns are denied and running background agents are halted

Improvement:
• Improved footer PR badge links to be clickable hyperlinks even when terminal support can't be detected (e.g. over ssh/tmux); set FORCE_HYPERLINK=0 to opt out

Other changes:
• Changed the login-expiry warning to appear 3 days before expiry instead of 5
• Capped the frontend-design plugin suggestion tip at 3 lifetime impressions instead of repeating indefinitely
• Changed subagents to no longer spawn nested subagents by default; set CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH to allow deeper nesting

Source: https://t.co/0e4JwaCMBJ

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.217 is about to be released
#cccnext

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.216 additional updates

CLI surface:
Added:
• models: claude-code-guide

Removed:
• models: claude-code-guideG

File: https://t.co/4mJQF7xfzz

Metadata:
• Time since 2.1.215 release: 1d 18h 31m 5s
• Bundle file size: +332.7 kB (+0.9%)

• Prompt files: +2 (+13.3%)
• Prompt tokens: +3,099 (+14.0%)

Prompt token mix by kind:
• system: 38.4%→52.3%
• tools: 61.6%→47.7%

Files:
• metadata: https://t.co/xLOqD6UyqR
• prompt stats: https://t.co/Ay27aaDtXs

Other prompt/string highlights:
1) Documents that the write tool writes files to the local filesystem.

Links:
1) https://t.co/kRPNcEPj5B

More details: https://t.co/wp2bPNT7k4

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.216 is now available.

40 CLI changes, 1 system prompt change

Highlights:
• Added sandbox.filesystem.disabled setting to skip filesystem isolation while keeping network egress control
• Fixed quadratic message normalization in long sessions, preventing multi-second stalls on resume
• Resumed background agent sessions restore agent prompt and tool restrictions to preserve configured behavior

Complete details in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.216 system prompt updates

Notable changes:
1) Claude no longer sees a stray Bun HMR error about adding https://t.co/fsmgq9eZed.accept. Removing this unrelated log line reduces prompt noise and lowers the chance Claude treats it as a required action or shifts the conversation toward frontend hot-reload fixes.

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

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.216 is about to be released
#cccnext

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.215 additional modifications

CLI surface:
Added:
• models: claude-code-guideG

Removed:
• models: claude-code-guide

File: https://t.co/fjLNvQfT7o

Metadata:
• Time since 2.1.214 release: 1d 0h 36m 14s
• Bundle file size: -48.8 kB (-0.1%)

• Prompt files: +2 (+15.4%)
• Prompt tokens: +6,001 (+37.2%)

Prompt token mix by kind:
• tools: 74.0%→61.6%
• system: 26.0%→38.4%

Files:
• metadata: https://t.co/zB08BxBXs2
• prompt stats: https://t.co/XazPkjU15D

Other prompt/string highlights:
1) Assistant will now always use the grep search tool for search tasks.
2) Clarifies that the write tool writes files to the local filesystem.

Links:
1) https://t.co/Ozd9dlPrgH
2) https://t.co/G90PSKIrtz

More details: https://t.co/gTJsS1HRJV

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.215 has been released.

1 CLI change

Highlights:
• Documentation designates ripgrep as the primary search tool for faster, more consistent codebase searches
• Skills /verify and /code-review no longer auto-run; they need explicit invocation to avoid unsolicited checks

Full details in the thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.215 changelog:

Other change:
• Claude no longer runs the /verify and /code-review skills on its own; invoke them with /verify or /code-review when you want them

Source: https://t.co/H1A7WaZFZn

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.215 is about to be released
#cccnext

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.214: additional changes

CLI surface:
Removed:
• models: claude-code-github-actionj

File: https://t.co/uPzGz6fnuQ

Metadata:
• Time since 2.1.213 release: 2h 25m 30s
• Bundle file size: +6.9 kB (+0.0%)

• Prompt files: -18 (-58.1%)
• Prompt tokens: -92,279 (-85.1%)

Prompt token mix by kind:
• tools: 14.3%→74.0%
• system: 33.1%→26.0%
• system-reminder: 52.6%→0.0%

Files:
• metadata: https://t.co/F11XU98LQ2
• prompt stats: https://t.co/NGJKdUipqo

Other prompt/string highlights:
1) Edit tool now documented to perform exact string replacements in files, with guidance to use replace_all for renaming.

Links:
1) https://t.co/4gHbnyuwHJ

More details: https://t.co/skNUXuIKA3

[Claude Code Changelog @ClaudeCodeLog]

Claude Code 2.1.214 has been released.

47 CLI changes

Highlights:
• Added EndConversation tool to end sessions with abusive users or jailbreak attempts and halt interaction
• Added permission prompts for Docker/Podman daemon-redirect flags to prevent accidental remote daemon access
• Edit tool makes literal string replacements in files so edits affect only exact specified text, not patterns

Complete details available in thread ↓

[Claude Code Changelog @ClaudeCodeLog]

Claude Code CLI 2.1.214 changelog:

New features:
• Added the EndConversation tool: Claude can end sessions with highly abusive users or jailbreak attempts, as on https://t.co/ldz5BaC3j0 since 2025 — see https://t.co/kySFQpxpsf
• Added a periodic progress heartbeat for long-running tool calls that previously went silent
• Added an ISO modified timestamp to memory file frontmatter
• Added message.uuid, client_request_id, and tool_source attributes to OpenTelemetry log events for message-level correlation and tool provenance
• Added CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH to configure the 60 KB truncation limit on OpenTelemetry content attributes
• Added reasoning effort to the subagentStatusLine payload, so custom agent rows can render model and effort
• Added permission prompts for docker commands (including the Podman docker shim) carrying daemon-redirect flags (--url, --connection, --identity, and Podman's remote mode) that previously ran without one

Fixes:
• Fixed single-segment dir/ allow rules like Edit(src/) auto-approving writes to nested dir/ directories anywhere in the tree instead of only <cwd>/dir
• Fixed a permission-check bypass affecting commands run in Windows PowerShell 5.1 sessions
• Fixed Bash permission checks to fail closed on file-descriptor redirect forms that bash parses differently than the permission analyzer
• Fixed Bash permission checks misjudging very long commands — commands over 10,000 characters now always prompt instead of running automatically
• Fixed Bash permission checks treating zsh variable subscripts and modifiers in [[ ]] comparisons as inert text — these commands now prompt for approval
• Fixed Bash permission checks to no longer auto-approve certain help and man commands that could run unsafe options, command substitutions, or backslash paths
• Fixed permission prompts on remote sessions that could proceed before the local confirmation dialog
• Fixed a crash when a GrowthBook feature evaluates to null, and a bug where a malformed flag payload could wipe the cached feature flags
• Fixed Bash tool killing the Claude session when a pkill -f pattern accidentally matched the CLI's own process (Linux)
• Fixed unbounded memory growth when --settings points at a device file or multi-GB file; oversized (>2 MiB) settings files now fail at startup with a clear error
• Fixed streaming turns failing with "Socket is closed" behind corporate proxies on Windows
• Fixed stream-json output truncation at exit for slow-reading SDK/pipeline consumers; the exit drain now scales with queued bytes instead of a flat 2s cap
• Fixed scheduled tasks refusing their own configured prompt as untrusted input — the fired prompt is now delivered as the session's assigned task
• Fixed PowerShell tool commands hanging until timeout when a child process waited on standard input (Windows)
• Fixed Python scripts under the PowerShell tool crashing with UnicodeDecodeError when reading non-UTF-8 data from standard input (Windows)
• Fixed Python scripts run via the PowerShell tool crashing with UnicodeEncodeError on non-ASCII output, and PowerShell 7 error messages containing raw ANSI escape sequences (Windows)
• Fixed the PowerShell tool reporting where.exe, fc.exe, and diff.exe as errors when they return a valid negative answer (Windows)
• Fixed > and >> under the PowerShell tool on Windows PowerShell 5.1 writing UTF-16LE files that other tools couldn't read as UTF-8
• Fixed a displaced background daemon deleting its successor's control socket on shutdown, which made the next client kill the healthy replacement daemon
• Fixed background sessions parked with ← or /background and left idle keeping the background daemon and a worker process alive indefinitely
• Fixed completed background sessions being impossible to remove via claude rm or the agent view once the background service had gone idle
• Fixed background sessions dispatched from a non-git folder being impossible to delete from the agents view
• Fixed reopening a stopped background session failing to restore its saved conversation when an unreadable folder exists in the session store
• Fixed the Remote Control "session ready" push notification firing for sessions where Remote Control was not explicitly enabled
• Fixed /install-github-app and the /mcp settings menu being blocked in agent-view sessions — they're now refused only in background sessions with no terminal attached
• Fixed plugins enabled via the --settings CLI flag not loading (regression since v2.1.181)
• Fixed feature flags going stale in long-running sessions after the OAuth token rotates
• Fixed /ultrareview refusing to run in repos with no merge base — it now offers to review all tracked files
• Fixed claude update and claude doctor hanging silently, and the /status System diagnostics section going blank, when a shell-config path is a directory
• Fixed memory frontmatter values being silently truncated at an inline # when memory files are saved
• Fixed session cost and token telemetry double-counting on streams that emit multiple cumulative message_delta frames
• Fixed a spurious "check your network" warning that appeared while the advisor was thinking
• Fixed hooks with exit code 2 not blocking as documented when the hook's stdout JSON fails schema validation
• Fixed OTel log events emitted outside the turn's async context missing the interaction span's trace context
• Fixed MCP transient errors during prompts/resources refresh clearing the server's slash commands and resources

Improvement:
• Improved the claude rc workspace-trust error in the home directory to say trust there is never saved and to suggest running from a project directory

Security/safety changes:
• Changed single-segment dir/ hook if: conditions to match only <cwd>/dir; write /dir/ for any-depth matching. deny/ask permission rules keep their any-depth match.
• Changed file commands using -m/--magic-file or -f/--files-from to require permission instead of being auto-allowed as read-only

Other changes:
• Changed keep-alive connection pooling to disable after a stale-connection error, so retries open a fresh socket
• Changed SessionStart hooks to report source "fork" when a session begins as a fork instead of "resume"

Source: https://t.co/r0AVEskMkU