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 Aug 13, 2026 parent be90077 · commit 1f6015b5d578
2 changed files+56 -40compared with be90077
MCHANGELOG.md
Mfeed.xml
MCHANGELOG.md
Large file, diff not shown.
Mfeed.xml+56 -40
@@ -6,8 +6,63 @@
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>2026-08-13T08:38:44Z</updated>
9+ <updated>2026-08-13T23:29:53Z</updated>
1010 <entry>
11+ <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.232</id>
12+ <title>Claude Code v2.1.232</title>
13+ <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.232"/>
14+ <updated>2026-08-13T23:29:53Z</updated>
15+ <content type="html">&lt;p&gt;• Subagent forking is now on by default: a subagent_type: "fork" subagent inherits the full conversation and prompt cache, and non-teammate agent spawns in interactive sessions now run in the background by default&lt;/p&gt;
16+&lt;p&gt;• Type @ in the prompt to mention another Claude session by name; Claude then uses SendMessage to reach that session directly&lt;/p&gt;
17+&lt;p&gt;• SendMessage now delivers to a bare name that exactly matches one live session, instead of asking to confirm with a ref first&lt;/p&gt;
18+&lt;p&gt;• Interactive sessions on one machine now keep unique names: starting or renaming a session to a name another live session already uses gives it a name-word-word variant and tells you&lt;/p&gt;
19+&lt;p&gt;• Added /config rows for "Dialog expiry" and "Messages from your other sessions" (cross-session inbound accept/hold/refuse)&lt;/p&gt;
20+&lt;p&gt;• Added secret redaction for GitLab token families (glrt-, gloas-, glptt-, glagent-, glimt-, glsoat-, glcbt-, glft-, glffct-) and full redaction of routable glpat-/gldt- tokens; the glab CLI config store gets the same sandbox and credential-path protection as gh&lt;/p&gt;
21+&lt;p&gt;• Added GitLab support to plugin marketplaces: bare gitlab.com repo URLs (including nested subgroups) now clone like github.com URLs, and clone auth-failure hints name your actual git host&lt;/p&gt;
22+&lt;p&gt;• Settings: additionalMarketplaces and allowedMarketplaces are now accepted as friendlier aliases for extraKnownMarketplaces and strictKnownMarketplaces&lt;/p&gt;
23+&lt;p&gt;• Enterprise policy: a url-typed blockedMarketplaces entry for a bare repo URL keeps blocking that URL when the CLI classifies it as a git clone&lt;/p&gt;
24+&lt;p&gt;• Gateway: the desktop: overlay now accepts every released Desktop setting (was 11 hand-listed keys), validated at boot against Desktop's own schema; unknown or invalid keys fail boot&lt;/p&gt;
25+&lt;p&gt;• Gateway: empty managed.policies[].match.groups/admin.admin_groups entries and malformed email_domain values (empty, or containing @, whitespace, or commas) now fail at boot instead of silently matching no one or granting admin access&lt;/p&gt;
26+&lt;p&gt;• Fable 5 is offered as an advisor in /advisor again for organizations with Fable access, with usage-credits consent set up through /model fable&lt;/p&gt;
27+&lt;p&gt;• Fixed a PowerShell permission bypass where variable-writing parameters could silently overwrite $PSDefaultParameterValues and redirect later commands' file access&lt;/p&gt;
28+&lt;p&gt;• Fixed a Windows permission bypass where Git Bash followed Cygwin-style symlinks that path validation saw as regular files; writes through them now require permission approval&lt;/p&gt;
29+&lt;p&gt;• Fixed nested git repositories inheriting trust from a parent directory; each repository now requires its own trust confirmation&lt;/p&gt;
30+&lt;p&gt;• Fixed MCP connections hanging for the full 30-second connect timeout when a server fails to answer or sends a malformed reply to the protocol-version probe&lt;/p&gt;
31+&lt;p&gt;• Fixed Remote Control sessions hosted by a bridge inside a cloud session inheriting that session's transcript or credentials&lt;/p&gt;
32+&lt;p&gt;• Fixed Remote Control sessions started from Claude Desktop or an IDE appearing as a new claude.ai session each time the local session was resumed; they now reattach to the existing one&lt;/p&gt;
33+&lt;p&gt;• Fixed Remote Control sessions appearing unreachable to newly attached clients while idle&lt;/p&gt;
34+&lt;p&gt;• Fixed Remote Control bridge sessions not restoring conversation history when the session worker restarts&lt;/p&gt;
35+&lt;p&gt;• Remote Control: resuming a conversation whose session was deleted from claude.ai or the app now starts a replacement instead of failing with a message about your login (regressed in v2.1.227)&lt;/p&gt;
36+&lt;p&gt;• Fixed Cloud gateway /login exiting silently or leaving an unresponsive terminal after "Press Enter to continue" when managed settings failed to load; the reason is now shown&lt;/p&gt;
37+&lt;p&gt;• Fixed voice mode on native builds getting stuck on "listening…" when the voice service rejected the connection; the rejection is now shown immediately&lt;/p&gt;
38+&lt;p&gt;• Fixed mTLS client certificate rotation requiring a restart; Claude Code now reloads the rotated cert and key automatically on connection errors&lt;/p&gt;
39+&lt;p&gt;• Fixed malformed AWS or Vertex region values being used to build request URLs; they now fall back to the default region&lt;/p&gt;
40+&lt;p&gt;• Fixed stream idle timeout errors failing the request instead of recovering on Bedrock, Vertex, and gateway deployments&lt;/p&gt;
41+&lt;p&gt;• Fixed content-sized overlays containing truncated text rendering one column too wide, and start-truncated text collapsing to an ellipsis&lt;/p&gt;
42+&lt;p&gt;• Fixed a stray garbled character where a long shell-command or agent-description preview was cut off mid-emoji&lt;/p&gt;
43+&lt;p&gt;• Fixed a startup race that could silently unregister a plugin marketplace due to concurrent writes to known_marketplaces.json&lt;/p&gt;
44+&lt;p&gt;• Fixed /update and /tui refusing to restart while work that survives the relaunch was running&lt;/p&gt;
45+&lt;p&gt;• Fixed usage-limit guidance suggesting unavailable slash commands in SDK and remote sessions&lt;/p&gt;
46+&lt;p&gt;• Fixed the consent message for interactive --advisor fable launches, which told you to run /model fable in an interactive session that had just exited&lt;/p&gt;
47+&lt;p&gt;• Improved fullscreen streaming: long sessions stay responsive because the whole conversation is no longer re-normalized on every update&lt;/p&gt;
48+&lt;p&gt;• Improved the managed settings approval dialog: shows endpoint URLs, uses clearer wording for telemetry-only changes, skips routine OpenTelemetry options, and requires approval for server-managed sandbox binary overrides (sandbox.bwrapPath, sandbox.socatPath, sandbox.ripgrep)&lt;/p&gt;
49+&lt;p&gt;• /feedback and /bug now open immediately when invoked while Claude is responding, instead of waiting for the turn to finish&lt;/p&gt;
50+&lt;p&gt;• /plugin install plugin@marketplace now refreshes the marketplace first, so newly published plugins install without a manual marketplace update&lt;/p&gt;
51+&lt;p&gt;• /code-review at high, xhigh, and max effort now runs in a background agent like the other levels&lt;/p&gt;
52+&lt;p&gt;• Pasted and clipboard images are read without blocking the event loop&lt;/p&gt;
53+&lt;p&gt;• Remote Control now keeps reconnecting for about 30 minutes after a network blip and no longer drops after a few blips spread across an hour&lt;/p&gt;
54+&lt;p&gt;• Remote Control: resuming a conversation no longer silently takes Remote Control away from another Claude Code on the same machine that still has it; run /remote-control there to move it&lt;/p&gt;
55+&lt;p&gt;• Updated agent panel: completed subagents hide immediately with a /tasks footer hint, and the "↓ N more" overflow indicator moved left for visibility&lt;/p&gt;
56+&lt;p&gt;• Remote Control: the terminal now says whether a session was taken over by another device, ended from another app, or deleted, and stops suggesting a reconnect that would undo it&lt;/p&gt;
57+&lt;p&gt;• Bash input redirections (&amp;lt; file) are now permission-checked like their argument spellings on all platforms&lt;/p&gt;
58+&lt;p&gt;• Shortened the message shown when resuming a completed background agent&lt;/p&gt;
59+&lt;p&gt;• Cowork sessions no longer inline external @-imports from user-scope memory files&lt;/p&gt;
60+&lt;p&gt;• Hardened the auto-generated cross-session messaging socket directory on shared /tmp: a pre-planted symlink or another user's directory is now refused instead of used&lt;/p&gt;
61+&lt;p&gt;• Hardened the Linux filesystem sandbox against a protected-path bypass&lt;/p&gt;
62+&lt;p&gt;• Changed sandbox.ripgrep to be honored only from user, managed, and --settings settings; project settings can no longer override the sandbox's ripgrep binary&lt;/p&gt;
63+&lt;p&gt;• Removed the startup tip suggesting you create custom subagents, and the matching nudge in the /powerup tour&lt;/p&gt;</content>
64+ </entry>
65+ <entry>
1166 <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.231</id>
1267 <title>Claude Code v2.1.231</title>
1368 <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.231"/>
@@ -556,43 +611,4 @@
556611 &lt;p&gt;• Claude in Chrome: save_to_disk on screenshot actions now writes the image to disk and returns the path; previously it did nothing&lt;/p&gt;
557612 &lt;p&gt;• Fixed a prompt-caching regression on Bedrock, Vertex, Mantle, and Foundry that billed the trailing system context block as fresh input tokens on every request.&lt;/p&gt;</content>
558613 </entry>
559- <entry>
560- <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.210</id>
561- <title>Claude Code v2.1.210</title>
562- <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.210"/>
563- <updated>2026-07-14T23:45:19Z</updated>
564- <content type="html">&lt;p&gt;• Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck&lt;/p&gt;
565-&lt;p&gt;• Added a startup warning for Write(path), NotebookEdit(path), and Glob(path) permission rules — use Edit(path) or Read(path) instead&lt;/p&gt;
566-&lt;p&gt;• Fixed isolation: 'worktree' subagents being able to run git-mutating commands against the main repo checkout instead of their own isolated worktree&lt;/p&gt;
567-&lt;p&gt;• Fixed the ultracode keyword opt-in firing on non-human-originated input such as webhook payloads and relayed PR comments&lt;/p&gt;
568-&lt;p&gt;• Fixed a rendered text fragment leaking into crash telemetry when a UI component returned content outside a styled text element&lt;/p&gt;
569-&lt;p&gt;• Fixed paste markers leaking into external editors opened from Claude Code, which could appear as stray È/É characters around pasted text&lt;/p&gt;
570-&lt;p&gt;• Fixed claude attach sometimes failing with "job not found" or "agent is still starting" errors during session transitions — attach now waits for the daemon to settle, and terminal resizes during a slow attach are applied once it completes&lt;/p&gt;
571-&lt;p&gt;• Fixed a session crash when a tool's result renderer returned a numeric bigint value or plain text instead of a UI element&lt;/p&gt;
572-&lt;p&gt;• Fixed a hook callback timeout being misreported to the model as a user rejection, which made unattended sessions stop and wait&lt;/p&gt;
573-&lt;p&gt;• Fixed Claude assuming a cd took effect after its command was moved to the background; the tool result now states the working directory is unchanged&lt;/p&gt;
574-&lt;p&gt;• Fixed plugin-provided MCP servers being torn down when MCP servers are re-synced mid-session&lt;/p&gt;
575-&lt;p&gt;• Fixed plan approvals without edits being labeled "(edited by user)" and overwriting the plan file with a stale snapshot&lt;/p&gt;
576-&lt;p&gt;• Fixed /doctor skipping its auto-mode-default proposal on Bedrock, Vertex, and Foundry, where auto mode no longer needs an opt-in&lt;/p&gt;
577-&lt;p&gt;• Fixed Grep content mode claiming "No matches found" when paginating past the end of results&lt;/p&gt;
578-&lt;p&gt;• Fixed unmatched $1/$2 positional placeholders in skills and commands being silently stripped; they are now preserved verbatim&lt;/p&gt;
579-&lt;p&gt;• Fixed plugin cache writes leaving temp files behind on failure and failing on locked-file renames on Windows and network filesystems&lt;/p&gt;
580-&lt;p&gt;• Fixed background workers crash-looping when a client resets its connection to the background service&lt;/p&gt;
581-&lt;p&gt;• Fixed claude agents --effort ultracode not reaching dispatched sessions; the value was silently dropped&lt;/p&gt;
582-&lt;p&gt;• Fixed pressing ← to open the agents view dropping the task tracker when returning to the session&lt;/p&gt;
583-&lt;p&gt;• Fixed the agents dashboard retaining pasted images from abandoned reply drafts after their session was deleted&lt;/p&gt;
584-&lt;p&gt;• Fixed killed background sessions leaving a permanent git worktree lock behind; the periodic sweep now releases locks whose owning process is gone&lt;/p&gt;
585-&lt;p&gt;• Fixed SDK MCP servers registered via an initialize control request waiting until the next turn to start connecting&lt;/p&gt;
586-&lt;p&gt;• Fixed returning to the agents view from a session leaving overlapping ghost frames with CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1&lt;/p&gt;
587-&lt;p&gt;• Fixed late-appearing .claude/* symlinks not being reconciled into the sandbox deny-write list&lt;/p&gt;
588-&lt;p&gt;• Hardened the Agent tool against indirect prompt injection via content a subagent read&lt;/p&gt;
589-&lt;p&gt;• Improved the Bash/PowerShell tool message when a command hits its timeout and is auto-backgrounded, so the model can distinguish a hang from an explicit background request&lt;/p&gt;
590-&lt;p&gt;• Improved auto mode: the permission classifier now defaults to Sonnet 5 for external sessions, validated on the session's first request and pinned for the session&lt;/p&gt;
591-&lt;p&gt;• Improved the bundled dataviz skill's chart color validation with perceptual OKLab color difference and recalibrated color-blindness thresholds&lt;/p&gt;
592-&lt;p&gt;• Memory writes that leave a MEMORY.md index over its read limit now produce an explicit error instead of silent truncation&lt;/p&gt;
593-&lt;p&gt;• Screen reader mode now announces permission mode changes aloud when cycling modes with Shift+Tab&lt;/p&gt;
594-&lt;p&gt;• The agents footer hint now shows how many background agents are waiting on your input, with a brief color emphasis when the count changes&lt;/p&gt;
595-&lt;p&gt;• Agent view: the session you pressed ← from stays visibly marked even after mouse hover or arrow keys move the selection&lt;/p&gt;
596-&lt;p&gt;• Fable temporarily shows as unavailable in the advisor picker while a server-side issue causing Fable advisor failures is fixed&lt;/p&gt;</content>
597- </entry>
598614 </feed>