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.mdBrowse files
GitHub Actions authored on Apr 17, 2026 parent 2b53fac · commit 71366ecf5dd9
1 changed file+41 -0compared with 2b53fac
MCHANGELOG.md
@@ -1,5 +1,46 @@
11 # Changelog
22
3+## 2.1.113
4+
5+- Changed the CLI to spawn a native Claude Code binary (via a per-platform optional dependency) instead of bundled JavaScript
6+- Added `sandbox.network.deniedDomains` setting to block specific domains even when a broader `allowedDomains` wildcard would otherwise permit them
7+- Fullscreen mode: Shift+↑/↓ now scrolls the viewport when extending a selection past the visible edge
8+- `Ctrl+A` and `Ctrl+E` now move to the start/end of the current logical line in multiline input, matching readline behavior
9+- Windows: `Ctrl+Backspace` now deletes the previous word
10+- Long URLs in responses and bash output stay clickable when they wrap across lines (in terminals with OSC 8 hyperlinks)
11+- Improved `/loop`: pressing Esc now cancels pending wakeups, and wakeups display as "Claude resuming /loop wakeup" for clarity
12+- `/extra-usage` now works from Remote Control (mobile/web) clients
13+- Remote Control clients can now query `@`-file autocomplete suggestions
14+- Improved `/ultrareview`: faster launch with parallelized checks, diffstat in the launch dialog, and animated launching state
15+- Subagents that stall mid-stream now fail with a clear error after 10 minutes instead of hanging silently
16+- Bash tool: multi-line commands whose first line is a comment now show the full command in the transcript, closing a UI-spoofing vector
17+- Running `cd <current-directory> && git …` no longer triggers a permission prompt when the `cd` is a no-op
18+- Security: on macOS, `/private/{etc,var,tmp,home}` paths are now treated as dangerous removal targets under `Bash(rm:*)` allow rules
19+- Security: Bash deny rules now match commands wrapped in `env`/`sudo`/`watch`/`ionice`/`setsid` and similar exec wrappers
20+- Security: `Bash(find:*)` allow rules no longer auto-approve `find -exec`/`-delete`
21+- Fixed MCP concurrent-call timeout handling where a message for one tool call could silently disarm another call's watchdog
22+- Fixed Cmd-backspace / `Ctrl+U` to once again delete from the cursor to the start of the line
23+- Fixed markdown tables breaking when a cell contains an inline code span with a pipe character
24+- Fixed session recap auto-firing while composing unsent text in the prompt
25+- Fixed `/copy` "Full response" not aligning markdown table columns for pasting into GitHub, Notion, or Slack
26+- Fixed messages typed while viewing a running subagent being hidden from its transcript and misattributed to the parent AI
27+- Fixed Bash `dangerouslyDisableSandbox` running commands outside the sandbox without a permission prompt
28+- Fixed `/effort auto` confirmation — now says "Effort level set to max" to match the status bar label
29+- Fixed the "copied N chars" toast overcounting emoji and other multi-code-unit characters
30+- Fixed `/insights` crashing with `EBUSY` on Windows
31+- Fixed exit confirmation dialog mislabeling one-shot scheduled tasks as recurring — now shows a countdown
32+- Fixed slash/@ completion menu not sitting flush against the prompt border in fullscreen mode
33+- Fixed `CLAUDE_CODE_EXTRA_BODY` `output_config.effort` causing 400 errors on subagent calls to models that don't support effort and on Vertex AI
34+- Fixed prompt cursor disappearing when `NO_COLOR` is set
35+- Fixed `ToolSearch` ranking so pasted MCP tool names surface the actual tool instead of description-matching siblings
36+- Fixed compacting a resumed long-context session failing with "Extra usage is required for long context requests"
37+- Fixed `plugin install` succeeding when a dependency version conflicts with an already-installed plugin — now reports `range-conflict`
38+- Fixed "Refine with Ultraplan" not showing the remote session URL in the transcript
39+- Fixed SDK image content blocks that fail to process crashing the session — now degrade to a text placeholder
40+- Fixed Remote Control sessions not streaming subagent transcripts
41+- Fixed Remote Control sessions not being archived when Claude Code exits
42+- Fixed `thinking.type.enabled is not supported` 400 error when using Opus 4.7 via a Bedrock Application Inference Profile ARN
43+
344 ## 2.1.112
445
546 - Fixed "claude-opus-4-7 is temporarily unavailable" for auto mode