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 6, 2026 parent 3b27276 · commit 5cf69b18c86d
2 changed files+26 -25compared with 3b27276
MCHANGELOG.md
Mfeed.xml
Large file, diff not shown.
Mfeed.xml+26 -25
@@ -6,8 +6,33 @@
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>2026-08-04T22:39:48Z</updated>
9+ <updated>2026-08-06T00:52:31Z</updated>
1010 <entry>
11+ <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.223</id>
12+ <title>Claude Code v2.1.223</title>
13+ <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.223"/>
14+ <updated>2026-08-06T00:52:31Z</updated>
15+ <content type="html">&lt;p&gt;• Added owner wildcard entries ("owner/*") to the strictKnownMarketplaces and blockedMarketplaces managed settings for allowing or blocking all marketplace repos under a GitHub org&lt;/p&gt;
16+&lt;p&gt;• Added a warning when workflow agents, forked skills, slash commands, or resumed background agents' requested subagent model is restricted and the parent model runs instead&lt;/p&gt;
17+&lt;p&gt;• Added a /teleport hint in cloud sessions showing how to continue locally with claude --teleport &amp;lt;session id&amp;gt;&lt;/p&gt;
18+&lt;p&gt;• Fixed a Bash permission bypass where a crafted command could hide parts of itself from permission checks&lt;/p&gt;
19+&lt;p&gt;• Fixed permission prompts so commands padded with tabs or invisible Unicode can no longer hide part of the command from the approval dialog&lt;/p&gt;
20+&lt;p&gt;• Fixed workflow scripts being able to use dynamic import() to run code outside the workflow sandbox&lt;/p&gt;
21+&lt;p&gt;• Fixed a permission gap where an agent definition's bypassPermissions mode ignored the org bypass-permissions disable policy&lt;/p&gt;
22+&lt;p&gt;• Fixed resuming a session after a mid-session /cd coming back empty&lt;/p&gt;
23+&lt;p&gt;• Fixed gateway model discovery hiding Claude models registered under provider-prefixed IDs such as vertex_ai/claude-* or bedrock/anthropic.claude-*&lt;/p&gt;
24+&lt;p&gt;• Fixed modelOverrides keys that aren't Anthropic model IDs being treated as the session's canonical model ID; unknown keys are now ignored as documented&lt;/p&gt;
25+&lt;p&gt;• Fixed managed settings: server-delivered settings no longer disable the env block of a machine-local managed-settings.json or MDM profile; admin env now merges per key&lt;/p&gt;
26+&lt;p&gt;• Fixed sandboxed commands failing to start on Linux when sandbox.filesystem.denyWrite covers the working directory&lt;/p&gt;
27+&lt;p&gt;• Fixed forked background agents getting stuck "already resuming" for the rest of the session when rebuilding the fork's parent prompt failed during resume&lt;/p&gt;
28+&lt;p&gt;• Fixed a resumed session failing every turn, or leaving the interactive app on an unresponsive error screen, when its history held a malformed diagnostics attachment&lt;/p&gt;
29+&lt;p&gt;• Fixed a rare hang when parsing unusual git push output&lt;/p&gt;
30+&lt;p&gt;• Changed CLAUDE_CODE_DISABLE_1M_CONTEXT to hold every Claude model with a native 1M window to 200K via auto-compaction, not just a fixed list; a startup warning now appears when auto-compaction isn't holding the session to 200K&lt;/p&gt;
31+&lt;p&gt;• Changed auto-compact to keep sessions on unrecognized model IDs within the assumed context window instead of letting them grow past it; set CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT=1 to restore the previous behavior&lt;/p&gt;
32+&lt;p&gt;• Changed /review to be an alias of /code-review, which reviews the current diff or a PR (/code-review &amp;lt;level&amp;gt; &amp;lt;pr#&amp;gt;); use /code-review ultra for a deep cloud review&lt;/p&gt;
33+&lt;p&gt;• Changed /code-review with no effort level to reuse the level you typed last; type a level like /code-review high to change it&lt;/p&gt;</content>
34+ </entry>
35+ <entry>
1136 <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.222</id>
1237 <title>Claude Code v2.1.222</title>
1338 <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.222"/>
@@ -627,28 +652,4 @@
627652 &lt;p&gt;• Removed a redundant navigation hint from the claude agents footer&lt;/p&gt;
628653 &lt;p&gt;• [VSCode] Added a Settings toggle for "Enable Remote Control for all sessions"&lt;/p&gt;</content>
629654 </entry>
630- <entry>
631- <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.202</id>
632- <title>Claude Code v2.1.202</title>
633- <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.202"/>
634- <updated>2026-07-06T22:51:10Z</updated>
635- <content type="html">&lt;p&gt;• Added a "Dynamic workflow size" setting in /config for controlling how large Claude generally makes dynamic workflows (small/medium/large agent counts) — an advisory guideline, not an enforced cap&lt;/p&gt;
636-&lt;p&gt;• Added workflow.run_id and workflow.name OpenTelemetry attributes to telemetry emitted by workflow-spawned agents, so a workflow run's activity can be reconstructed from OTel data&lt;/p&gt;
637-&lt;p&gt;• Fixed a crash in the inline Ctrl+R history search when accepting or cancelling while the search was still scanning the history file&lt;/p&gt;
638-&lt;p&gt;• Fixed /rename on background sessions being reverted when the job restarts, which broke addressing the session by its new name&lt;/p&gt;
639-&lt;p&gt;• Fixed transient mTLS handshake failures when settings were re-applied during an in-place client certificate rotation&lt;/p&gt;
640-&lt;p&gt;• Fixed commands sent from Remote Control (mobile/web) into an interactive session failing with "Unknown command"&lt;/p&gt;
641-&lt;p&gt;• Fixed images and files sent from the Remote Control mobile or web app without a caption being silently dropped&lt;/p&gt;
642-&lt;p&gt;• Fixed the sign-in URL printed by claude auth login and claude mcp login --no-browser not being reliably clickable when it wraps over SSH — it is now emitted as a single hyperlink&lt;/p&gt;
643-&lt;p&gt;• Fixed opening a chat from claude agents sometimes failing with "currently running as a background agent" followed by a worker crash/respawn loop&lt;/p&gt;
644-&lt;p&gt;• Fixed workflow scripts with unicode quote escapes in strings being corrupted before parsing; workflow parse errors now show the offending line instead of always blaming TypeScript&lt;/p&gt;
645-&lt;p&gt;• Fixed voice dictation retrying in an unbounded loop when the microphone or audio recorder fails — repeated capture failures now pause voice input&lt;/p&gt;
646-&lt;p&gt;• Fixed /remote-control sessions showing the wrong permission mode in the mobile and web apps&lt;/p&gt;
647-&lt;p&gt;• Fixed resuming a session by name, or opening the resume picker, taking minutes and using a large amount of memory in repositories with many git worktrees&lt;/p&gt;
648-&lt;p&gt;• Fixed installer and updater downloads failing immediately with "aborted" when a proxy or network drops the connection mid-download — transient connection drops now retry&lt;/p&gt;
649-&lt;p&gt;• Fixed re-invoking an already-loaded skill appending a duplicate copy of its instructions to context&lt;/p&gt;
650-&lt;p&gt;• Improved /workflows agent list layout: wider titles, a dedicated time column, shorter model names, and no per-row tool-call counts&lt;/p&gt;
651-&lt;p&gt;• Improved MCP error messages: clearer error when a server config has url but no type, suggesting "type": "http" instead of the misleading "command: expected string"&lt;/p&gt;
652-&lt;p&gt;• Changed /review &amp;lt;pr&amp;gt; back to a fast single-pass review; use /code-review &amp;lt;level&amp;gt; &amp;lt;pr#&amp;gt; for the multi-agent review at a chosen effort level&lt;/p&gt;</content>
653- </entry>
654655 </feed>