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
Large file, diff not shown.
| @@ -6,8 +6,15 @@ | ||
| 6 | 6 | <author><name>Anthropic</name></author> |
| 7 | 7 | <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/> |
| 8 | 8 | <link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/> |
| 9 | - <updated>2026-07-24T17:14:14Z</updated> | |
| 9 | + <updated>2026-07-25T01:35:47Z</updated> | |
| 10 | 10 | <entry> |
| 11 | + <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.220</id> | |
| 12 | + <title>Claude Code v2.1.220</title> | |
| 13 | + <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.220"/> | |
| 14 | + <updated>2026-07-25T01:35:47Z</updated> | |
| 15 | + <content type="html"><p>• Bug fixes and reliability improvements</p></content> | |
| 16 | + </entry> | |
| 17 | + <entry> | |
| 11 | 18 | <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.219</id> |
| 12 | 19 | <title>Claude Code v2.1.219</title> |
| 13 | 20 | <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.219"/> |
| @@ -20,10 +27,7 @@ | ||
| 20 | 27 | <p>• Added nested subagent forwarding in stream-json: subagents spawned at depth-2+ now appear when --forward-subagent-text is set, keyed by their spawning Agent tool_use id</p> |
| 21 | 28 | <p>• Fixed claude -p text output dropping the answer already produced when a turn dies on a mid-stream API error</p> |
| 22 | 29 | <p>• 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</p> |
| 23 | -<p>• Fixed a permission you approved while a self-hosted runner was restarting being dropped when the session resumed, so the approved action now runs</p> | |
| 24 | 30 | <p>• Fixed the Fable model row showing "Requires usage credits" for plans that include it, when a stale cache had baked the label in</p> |
| 25 | -<p>• Fixed a SIGTERM arriving while a self-hosted runner was starting up leaving a stale active row until the lease expired; it now deregisters cleanly</p> | |
| 26 | -<p>• Added structured failure categories to self-hosted runner spawn and session failures, so hook errors, runner crashes and config errors can be told apart</p> | |
| 27 | 31 | <p>• Fixed the /model picker showing the merged Opus row as plain "Opus" instead of "Opus (1M context)"</p> |
| 28 | 32 | <p>• Fixed copy-on-select inside GNU screen printing base64 into the terminal instead of copying the selection</p> |
| 29 | 33 | <p>• Fixed Remote Control clients keeping a stale fast-mode status after a model switch, reconnect, or failed org check</p> |
| @@ -605,34 +609,4 @@ | ||
| 605 | 609 | <p>• Improved screen-reader output: decorative glyphs are now hidden, transcript symbols read as short labels, and nested tables read as Header: value. lines</p> |
| 606 | 610 | <p>• Improved the install script to explain when installation is killed by the system running out of memory</p></content> |
| 607 | 611 | </entry> |
| 608 | - <entry> | |
| 609 | - <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.199</id> | |
| 610 | - <title>Claude Code v2.1.199</title> | |
| 611 | - <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.199"/> | |
| 612 | - <updated>2026-07-02T23:35:12Z</updated> | |
| 613 | - <content type="html"><p>• Stacked slash-skill invocations like /skill-a /skill-b do XYZ now load all leading skills (up to 5), not just the first</p> | |
| 614 | -<p>• Fixed SSL certificate errors (TLS-inspecting proxies, missing NODE_EXTRA_CA_CERTS, expired certs) burning retries before showing actionable guidance — they now fail immediately with the fix hint</p> | |
| 615 | -<p>• Fixed streaming responses being discarded when the API emits a mid-stream overloaded/server error after partial output — the partial is now kept with an incomplete-response notice</p> | |
| 616 | -<p>• Fixed subagents cut off by a rate limit or server error silently failing instead of returning their partial work to the parent</p> | |
| 617 | -<p>• Fixed subagents reporting API errors (e.g. usage limit reached) as successful results — the error is now reported to the parent agent</p> | |
| 618 | -<p>• Fixed the background-agent daemon on Linux killing itself and every running agent every ~50 seconds after an unclean shutdown left a corrupted worker record</p> | |
| 619 | -<p>• Fixed background agents failing to cold-start over SSH on macOS with "Could not switch to audit session" (regression in 2.1.196)</p> | |
| 620 | -<p>• Fixed claude stop being silently undone when it raced a background-agent respawn — the respawn now honors the stop</p> | |
| 621 | -<p>• Fixed background job progress indicators stalling for minutes while the job ran long commands</p> | |
| 622 | -<p>• Fixed background sessions on memory-starved machines showing a generic error — they now indicate low memory and suggest freeing resources</p> | |
| 623 | -<p>• Fixed remote sessions briefly flapping between Working and Idle in the agent view when a background agent completes</p> | |
| 624 | -<p>• Fixed idle subagents vanishing from the agent panel while other subagents were still working; surplus idle agents now collapse into an expandable summary row</p> | |
| 625 | -<p>• Fixed typing /model or /fast while viewing a subagent silently opening the lead's model picker — a notice now explains the command applies to the lead</p> | |
| 626 | -<p>• Fixed SessionStart, Setup, and SubagentStart hooks silently hiding stderr when exiting with code 2 — the error is now shown in the transcript</p> | |
| 627 | -<p>• Fixed claude --dangerously-skip-permissions daemon &lt;subcommand&gt; being treated as a chat prompt instead of running the subcommand</p> | |
| 628 | -<p>• Fixed SendMessage silently misrouting when a re-spawned agent reuses a previous agent's name — the tool now detects the mismatch and asks the caller to retarget</p> | |
| 629 | -<p>• Fixed opening or resuming a session with no new messages needlessly growing the transcript file</p> | |
| 630 | -<p>• Fixed backgrounding a session with ← or /background dropping its /color from the agent view row</p> | |
| 631 | -<p>• Fixed resetting a corrupted config file from the startup recovery dialog destroying it unrecoverably — it now backs up the file first</p> | |
| 632 | -<p>• Fixed Claude in Chrome repeatedly opening the reconnect page when sessions run from different builds or config directories</p> | |
| 633 | -<p>• Fixed plan mode not prompting for state-changing browser tool calls; read-only browser_batch calls are now correctly auto-allowed</p> | |
| 634 | -<p>• Transient server rate-limit errors (429s unrelated to your usage limit) are now retried automatically with backoff for subscribers instead of failing the turn</p> | |
| 635 | -<p>• CLAUDE_CODE_RETRY_WATCHDOG now raises the default retry count for non-capacity transient errors to 300 and lifts the cap of 15 on CLAUDE_CODE_MAX_RETRIES</p> | |
| 636 | -<p>• claude agents session rows now show pull-request links as bare #N without the redundant "PR" label</p></content> | |
| 637 | - </entry> | |
| 638 | 612 | </feed> |