Compare commits

...

2 Commits

Author SHA1 Message Date
GitHub Actions
53a5f3ee07 chore: Update CHANGELOG.md 2026-03-07 00:11:59 +00:00
GitHub Actions
da80366c48 chore: Update CHANGELOG.md 2026-03-06 01:19:18 +00:00

View File

@@ -1,5 +1,68 @@
# Changelog
## 2.1.71
- Added `/loop` command to run a prompt or slash command on a recurring interval (e.g. `/loop 5m check the deploy`)
- Added cron scheduling tools for recurring prompts within a session
- Added `voice:pushToTalk` keybinding to make the voice activation key rebindable in `keybindings.json` (default: space) — modifier+letter combos like `meta+k` have zero typing interference
- Added `fmt`, `comm`, `cmp`, `numfmt`, `expr`, `test`, `printf`, `getconf`, `seq`, `tsort`, and `pr` to the bash auto-approval allowlist
- Fixed stdin freeze in long-running sessions where keystrokes stop being processed but the process stays alive
- Fixed a 58 second startup freeze for users with voice mode enabled, caused by CoreAudio initialization blocking the main thread after system wake
- Fixed startup UI freeze when many claude.ai proxy connectors refresh an expired OAuth token simultaneously
- Fixed forked conversations (`/fork`) sharing the same plan file, which caused plan edits in one fork to overwrite the other
- Fixed the Read tool putting oversized images into context when image processing failed, breaking subsequent turns in long image-heavy sessions
- Fixed false-positive permission prompts for compound bash commands containing heredoc commit messages
- Fixed plugin installations being lost when running multiple Claude Code instances
- Fixed claude.ai connectors failing to reconnect after OAuth token refresh
- Fixed claude.ai MCP connector startup notifications appearing for every org-configured connector instead of only previously connected ones
- Fixed background agent completion notifications missing the output file path, which made it difficult for parent agents to recover agent results after context compaction
- Fixed duplicate output in Bash tool error messages when commands exit with non-zero status
- Fixed Chrome extension auto-detection getting permanently stuck on "not installed" after running on a machine without local Chrome
- Fixed `/plugin marketplace update` failing with merge conflicts when the marketplace is pinned to a branch/tag ref
- Fixed `/plugin marketplace add owner/repo@ref` incorrectly parsing `@` — previously only `#` worked as a ref separator, causing undiagnosable errors with `strictKnownMarketplaces`
- Fixed duplicate entries in `/permissions` Workspace tab when the same directory is added with and without a trailing slash
- Fixed `--print` hanging forever when team agents are configured — the exit loop no longer waits on long-lived `in_process_teammate` tasks
- Fixed " Tool loaded." appearing in the REPL after every `ToolSearch` call
- Fixed prompting for `cd <cwd> && git ...` on Windows when the model uses a mingw-style path
- Improved startup time by deferring native image processor loading to first use
- Improved bridge session reconnection to complete within seconds after laptop wake from sleep, instead of waiting up to 10 minutes
- Improved `/plugin uninstall` to disable project-scoped plugins in `.claude/settings.local.json` instead of modifying `.claude/settings.json`, so changes don't affect teammates
- Improved plugin-provided MCP server deduplication — servers that duplicate a manually-configured server (same command/URL) are now skipped, preventing duplicate connections and tool sets. Suppressions are shown in the `/plugin` menu.
- Updated `/debug` to toggle debug logging on mid-session, since debug logs are no longer written by default
- Removed startup notification noise for unauthenticated org-registered claude.ai connectors
## 2.1.70
- Fixed API 400 errors when using `ANTHROPIC_BASE_URL` with a third-party gateway — tool search now correctly detects proxy endpoints and disables `tool_reference` blocks
- Fixed `API Error: 400 This model does not support the effort parameter` when using custom Bedrock inference profiles or other model identifiers not matching standard Claude naming patterns
- Fixed empty model responses immediately after `ToolSearch` — the server renders tool schemas with system-prompt-style tags at the prompt tail, which could confuse models into stopping early
- Fixed prompt-cache bust when an MCP server with `instructions` connects after the first turn
- Fixed Enter inserting a newline instead of submitting when typing over a slow SSH connection
- Fixed clipboard corrupting non-ASCII text (CJK, emoji) on Windows/WSL by using PowerShell `Set-Clipboard`
- Fixed extra VS Code windows opening at startup on Windows when running from the VS Code integrated terminal
- Fixed voice mode failing on Windows native binary with "native audio module could not be loaded"
- Fixed push-to-talk not activating on session start when `voiceEnabled: true` was set in settings
- Fixed markdown links containing `#NNN` references incorrectly pointing to the current repository instead of the linked URL
- Fixed repeated "Model updated to Opus 4.6" notification when a project's `.claude/settings.json` has a legacy Opus model string pinned
- Fixed plugins showing as inaccurately installed in `/plugin`
- Fixed plugins showing "not found in marketplace" errors on fresh startup by auto-refreshing after marketplace installation
- Fixed `/security-review` command failing with `unknown option merge-base` on older git versions
- Fixed `/color` command having no way to reset back to the default color — `/color default`, `/color gray`, `/color reset`, and `/color none` now restore the default
- Fixed a performance regression in the `AskUserQuestion` preview dialog that re-ran markdown rendering on every keystroke in the notes input
- Fixed feature flags read during early startup never refreshing their disk cache, causing stale values to persist across sessions
- Fixed `permissions.defaultMode` settings values other than `acceptEdits` or `plan` being applied in Claude Code Remote environments — they are now ignored
- Fixed skill listing being re-injected on every `--resume` (~600 tokens saved per resume)
- Fixed teleport marker not rendering in VS Code teleported sessions
- Improved error message when microphone captures silence to distinguish from "no speech detected"
- Improved compaction to preserve images in the summarizer request, allowing prompt cache reuse for faster and cheaper compaction
- Improved `/rename` to work while Claude is processing, instead of being silently queued
- Reduced prompt input re-renders during turns by ~74%
- Reduced startup memory by ~426KB for users without custom CA certificates
- Reduced Remote Control `/poll` rate to once per 10 minutes while connected (was 12s), cutting server load ~300×. Reconnection is unaffected — transport loss immediately wakes fast polling.
- [VSCode] Added spark icon in VS Code activity bar that lists all Claude Code sessions, with sessions opening as full editors
- [VSCode] Added full markdown document view for plans in VS Code, with support for adding comments to provide feedback
- [VSCode] Added native MCP server management dialog — use `/mcp` in the chat panel to enable/disable servers, reconnect, and manage OAuth authentication without switching to the terminal
## 2.1.69
- Added the `/claude-api` skill for building applications with the Claude API and Anthropic SDK