spacehub

surshar / claude-code

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Built by Anthropic · github.com/anthropics

chore: Update CHANGELOG.md and feed.xmlBrowse files
GitHub Actions authored on May 27, 2026 parent d08288e · commit b7339920b69f
2 changed files+40 -39compared with d08288e
MCHANGELOG.md
Mfeed.xml
Large file, diff not shown.
Mfeed.xml+40 -39
@@ -6,8 +6,47 @@
66 <author><name>Anthropic</name></author>
77 <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/>
88 <link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/>
9- <updated>2026-05-23T04:03:45Z</updated>
9+ <updated>2026-05-27T01:30:52Z</updated>
1010 <entry>
11+ <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.152</id>
12+ <title>Claude Code v2.1.152</title>
13+ <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.152"/>
14+ <updated>2026-05-27T01:30:52Z</updated>
15+ <content type="html">&lt;p&gt;• /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&lt;/p&gt;
16+&lt;p&gt;• Skills and slash commands can now set disallowed-tools in frontmatter to remove tools from the model while the skill is active&lt;/p&gt;
17+&lt;p&gt;• Added /reload-skills command to re-scan skill directories without restarting the session&lt;/p&gt;
18+&lt;p&gt;• SessionStart hooks can now return reloadSkills: true to re-scan skill directories, making skills installed by the hook available in the same session&lt;/p&gt;
19+&lt;p&gt;• SessionStart hooks can now set the session title via hookSpecificOutput.sessionTitle on startup and resume&lt;/p&gt;
20+&lt;p&gt;• Added a MessageDisplay hook event that lets hooks transform or hide assistant message text as it is displayed&lt;/p&gt;
21+&lt;p&gt;• Added pluginSuggestionMarketplaces managed setting: admins can allowlist org marketplaces whose plugins may be suggested via context-aware tips&lt;/p&gt;
22+&lt;p&gt;• claude plugin marketplace remove now accepts --scope user|project|local for symmetry with marketplace add, install, and uninstall&lt;/p&gt;
23+&lt;p&gt;• 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&lt;/p&gt;
24+&lt;p&gt;• Auto mode no longer requires opt-in consent&lt;/p&gt;
25+&lt;p&gt;• Vim mode: / in NORMAL mode now opens reverse history search (like Ctrl+R), matching bash/zsh vi-mode&lt;/p&gt;
26+&lt;p&gt;• The /usage breakdown now includes large session files; files are scanned with a streaming read so memory usage stays flat&lt;/p&gt;
27+&lt;p&gt;• 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)&lt;/p&gt;
28+&lt;p&gt;• 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&lt;/p&gt;
29+&lt;p&gt;• Simplified the Workflow tool's inline progress display — live agent counts now show only in the persistent workflow status row below the prompt&lt;/p&gt;
30+&lt;p&gt;• 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&lt;/p&gt;
31+&lt;p&gt;• Added the session entrypoint as an OpenTelemetry metric attribute (app.entrypoint, opt-in via OTEL_METRICS_INCLUDE_ENTRYPOINT=true)&lt;/p&gt;
32+&lt;p&gt;• Fixed terminal styling degrading in very long sessions by recycling the renderer's style pool&lt;/p&gt;
33+&lt;p&gt;• Fixed the sandbox-enabled warning not appearing in condensed startup mode — it now shows in every layout&lt;/p&gt;
34+&lt;p&gt;• 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&lt;/p&gt;
35+&lt;p&gt;• Fixed focus mode showing a spurious "N messages hidden" count on turns with no hidden activity&lt;/p&gt;
36+&lt;p&gt;• Fixed clicking a link inside an expanded tool result collapsing the section instead of opening the link&lt;/p&gt;
37+&lt;p&gt;• 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&lt;/p&gt;
38+&lt;p&gt;• Fixed plugin MCP servers with the same command but different environment variables being incorrectly deduplicated&lt;/p&gt;
39+&lt;p&gt;• Fixed /doctor reporting "marketplace not found" or "plugin not found" for stale enabledPlugins entries referencing removed marketplaces or dropped plugins&lt;/p&gt;
40+&lt;p&gt;• Fixed plugins that track a git branch silently no longer receiving updates after the plugin registry was rebuilt&lt;/p&gt;
41+&lt;p&gt;• Fixed remote MCP servers failing to connect in Claude Code Remote sessions when the egress proxy is enabled&lt;/p&gt;
42+&lt;p&gt;• 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&lt;/p&gt;
43+&lt;p&gt;• Fixed the Agent tool description referencing an agent list that is never delivered when running with --bare or with attachments disabled&lt;/p&gt;
44+&lt;p&gt;• Fixed a background worker crash in claude agents when accepting a stale permission prompt after a subagent was cancelled&lt;/p&gt;
45+&lt;p&gt;• 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&lt;/p&gt;
46+&lt;p&gt;• Fixed the PushNotification tool incorrectly reporting "Mobile push not sent (Remote Control inactive)" in SDK-hosted sessions when Remote Control is enabled&lt;/p&gt;
47+&lt;p&gt;• 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&lt;/p&gt;</content>
48+ </entry>
49+ <entry>
1150 <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.150</id>
1251 <title>Claude Code v2.1.150</title>
1352 <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.150"/>
@@ -598,42 +637,4 @@
598637 &lt;p&gt;• Fixed sub-agent summaries firing repeatedly while a sub-agent's transcript is static, capping worst-case token cost on idle sub-agents&lt;/p&gt;
599638 &lt;p&gt;• Headless --output-format stream-json: init.plugin_errors now includes --plugin-dir load failures in addition to dependency demotions&lt;/p&gt;</content>
600639 </entry>
601- <entry>
602- <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.126</id>
603- <title>Claude Code v2.1.126</title>
604- <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.126"/>
605- <updated>2026-05-18T01:52:01Z</updated>
606- <content type="html">&lt;p&gt;• The /model picker now lists models from your gateway's /v1/models endpoint when ANTHROPIC_BASE_URL points at an Anthropic-compatible gateway&lt;/p&gt;
607-&lt;p&gt;• - 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&lt;/p&gt;
608-&lt;p&gt;• --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)&lt;/p&gt;
609-&lt;p&gt;• claude auth login now accepts the OAuth code pasted into the terminal when the browser callback can't reach localhost (WSL2, SSH, containers)&lt;/p&gt;
610-&lt;p&gt;• 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")&lt;/p&gt;
611-&lt;p&gt;• Auto mode: the spinner now turns red when a permission check stalls, instead of looking like the tool is running&lt;/p&gt;
612-&lt;p&gt;• Host-managed deployments (CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST) no longer auto-disable analytics on Bedrock/Vertex/Foundry&lt;/p&gt;
613-&lt;p&gt;• Windows: PowerShell 7 installed via the Microsoft Store, MSI without PATH, or .NET global tool is now detected&lt;/p&gt;
614-&lt;p&gt;• Windows: when the PowerShell tool is enabled, Claude now treats PowerShell as the primary shell instead of defaulting to Bash&lt;/p&gt;
615-&lt;p&gt;• Read tool: removed the per-file malware-assessment reminder that could cause spurious refusals and "this is not malware" commentary on legacy models&lt;/p&gt;
616-&lt;p&gt;• Security: Fixed allowManagedDomainsOnly / allowManagedReadPathsOnly being ignored when a higher-priority managed-settings source lacked a sandbox block&lt;/p&gt;
617-&lt;p&gt;• 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&lt;/p&gt;
618-&lt;p&gt;• Fixed showing the login screen for "OAuth not allowed for organization" errors — now shows guidance to contact your admin&lt;/p&gt;
619-&lt;p&gt;• Fixed OAuth login failing with timeout on slow or proxied connections, in IPv6-only devcontainers, and when the browser callback can't reach localhost&lt;/p&gt;
620-&lt;p&gt;• Fixed a rare race where a concurrent credential write could clear a valid OAuth refresh token&lt;/p&gt;
621-&lt;p&gt;• Fixed API retry countdown sticking at "0s" instead of counting down between attempts&lt;/p&gt;
622-&lt;p&gt;• Fixed "Stream idle timeout" error after waking Mac from sleep mid-request&lt;/p&gt;
623-&lt;p&gt;• Fixed background and remote sessions falsely aborting with "Stream idle timeout" during long model thinking pauses&lt;/p&gt;
624-&lt;p&gt;• Fixed a hang where the assistant could finish thinking but show no output after a run of empty turns&lt;/p&gt;
625-&lt;p&gt;• Fixed overly fast trackpad scrolling in Cursor and VS Code 1.92–1.104 integrated terminals&lt;/p&gt;
626-&lt;p&gt;• Fixed claude.ai MCP connectors being suppressed by manual servers stuck in needs-auth state&lt;/p&gt;
627-&lt;p&gt;• Fixed Japanese/Korean/Chinese text rendering as garbled characters on Windows in no-flicker mode&lt;/p&gt;
628-&lt;p&gt;• Fixed Ctrl+L clearing the prompt input — it now only forces a screen redraw, matching readline behavior&lt;/p&gt;
629-&lt;p&gt;• Fixed deferred tools (WebSearch, WebFetch, etc.) not being available to skills with context: fork and other subagents on their first turn&lt;/p&gt;
630-&lt;p&gt;• Fixed plan-mode tools being unavailable in interactive sessions launched with --channels&lt;/p&gt;
631-&lt;p&gt;• Fixed /plugin Uninstall reporting "Enabled" instead of "Uninstalled"&lt;/p&gt;
632-&lt;p&gt;• Bounded total size of file-modified reminders when a linter touches many files at once&lt;/p&gt;
633-&lt;p&gt;• Fixed /remote-control retries appearing stuck on "connecting…" — each retry now shows its result&lt;/p&gt;
634-&lt;p&gt;• Fixed Remote Control failure notification not showing the error reason for initial connection failures&lt;/p&gt;
635-&lt;p&gt;• Windows: clipboard writes no longer expose copied content in process command-line arguments visible to EDR/SIEM telemetry; also fixes &amp;gt;22KB selections not reaching the clipboard&lt;/p&gt;
636-&lt;p&gt;• PowerShell tool: bare -- (e.g. git diff -- file) is no longer mis-flagged as the --% stop-parsing token&lt;/p&gt;
637-&lt;p&gt;• Fixed Agent SDK hang when the model emits a malformed tool name in a parallel tool call batch&lt;/p&gt;</content>
638- </entry>
639640 </feed>