Claude Code v2.1.205
Released Jul 8, 2026 (1 month ago).
235 issues reference this build
150 still open
85 resolved (36%)
"References this build" means the issue body mentions running 2.1.205 (from the
bug-report template). It reflects report volume, not a proven defect count — an issue may mention a
version without being caused by it. First-party data from the anthropics/claude-code tracker.
Top issues reported on v2.1.205
Ranked by community engagement (reactions and comments).
- [BUG] 400 "output_config.effort 'xhigh' is not supported when thinking is disabled" on Opus 4.8 despite alwaysThinkingEnabled: true (VS Code, 2.1.205–2.1.207)
- Assistant text between tool calls is not rendered, not shown in ctrl-o, and not saved to the session file
- [BUG] Native installer (2.1.243) segfaults in newlocale/free during startup on glibc 2.44 (CachyOS)
- [Bug] Advisor "unavailable" = `advisorModel: fable` + any `tool_use` in the transcript; executor-irrelevant, `opus` advisor immune (supersedes #73923's ToolSearch cause)
- /model shows Fable 5 as credits-only (€0.00) on Max plan, while /usage shows Fable covered by plan (5% of weekly limit)
- Fullscreen TUI renderer opens hyperlinks twice on click
- [BUG] Fable is unusable! Constatnly switching to Opus!
- [BUG] Ctrl+click on a link in Claude Code's output opens 2 duplicate browser tabs (xfce4-terminal)
- [BUG] Cowork: desktop device bridge authenticates but device tools are never provisioned into newly created sessions (works in pre-existing sessions)
- [BUG] v2.1.206 silently broke unattended scheduled tasks: runs no longer inherit permissions.defaultMode, fall back to Manual, and per-task mode has no programmatic or bulk control
- [BUG] [VS Code Sidebar] Fable 5 doesn't show text responses in chat
- Claude Desktop MSIX crash on Intel integrated GPU during browser pane use — reproducible, no workaround available
- [BUG] Desktop (Cowork/Code): showThinkingSummaries is ignored — thinking arrives empty (display: omitted) on Fable 5 / Opus 4.7+, "Thought process" panel permanently empty
- All sessions appear as background agents; subagents stall 100% of the time
- [BUG] Copy /login url does not work most the time.
- [Windows] /resume / session history always empty for projects on mapped network drives — extension and CLI compute different project slugs
- skillOverrides silently ignored for plugin-provided skills — runtime hard-codes source==="plugin" to "on" while the /skills UI implies overrides work
- [BUG] /mcp shows unconnected integrations (Gmail, Google Calendar, Google Drive) as connected
- [BUG] Unable to connect to API (ECONNRESET)
- Cmd+click on file links in iTerm2 fails with "The application can't be opened. -50" — OSC 8 URI lacks file:// scheme
- MCP HTTP client fails to resolve JSON Schema $ref (#/$defs/ScreenInstance) from Google Stitch MCP server
- Advisor tool: Fable 5 (claude-fable-5) consistently returns error_code "unavailable"; Opus 4.8 succeeds under identical config
- --thinking-display is not propagated to the Bedrock request (thinking blocks stay empty on Sonnet 5)
- [BUG] Embedded ugrep OOMs on bounded-repeat regex while Bash grep is silently shadowed (Linux, 2.1.205-2.1.212)
- [BUG] 3P LLM gateway: natively-1M models (Sonnet 5) are budgeted at 200K because the embedded/standalone CLI never resolves provider "gateway" — verified root cause + working env workaround
- [Bug] LLM output contains inappropriate phrase "The money shot"
- [Feature Request] Improve Claude Code's adherence to user-specified technical constraints and requirements
- [BUG] Task management tools silently unavailable on Opus 4.8 / Sonnet 5 / Fable 5 (tengu_vellum_ash model gate)
- VS Code: make session Delete recoverable (confirm + restore + reconcile from disk)
- [BUG] Skill activation emits a second `isMeta` message that orphans the Skill `tool_use` → 400 invalid_request (surfaced as "tool use concurrency")
Changelog
What's changed
- Added an auto mode rule that blocks tampering with session transcript files
- Fixed
--json-schemasilently producing unstructured output when the schema was invalid, and schemas using theformatkeyword being rejected - Fixed a message sent while Claude was working being silently lost when the turn ended at the
--max-turnslimit - Fixed Windows worktree removal deleting files outside the worktree when an NTFS junction or directory symlink existed inside it
- Fixed background agents staying shown as "failed" or "completed" in the agent list after being resumed with
SendMessage - Fixed background jobs flipping from "needs input" back to "working" in the agent list when the agent's turn contained no readable text
- Fixed
claude attacherroring when a background agent was mid-upgrade restart instead of waiting for it to come back - Fixed session-to-PR linking missing a PR created in a Bash call whose output exceeded the 30K inline limit
- Fixed
claude mcp add-from-claude-desktopgetting stuck when a server name contains unsupported characters; invalid names are now reported and remaining servers still import - Fixed a plugin LSP server that fails to initialize preventing a valid LSP server from another plugin handling the same file extension
- Fixed a Windows crash when the directory Claude was launched from is deleted, locked, or unmounted while a command is running
- Fixed a crash when a file watcher was closed while a directory scan was still in flight
- Fixed project verify skills being rewritten on every session instead of only when a documented command changed
- Fixed the agent view rendering one line too high and clipping its header when the job list slightly overflowed the screen
- Fixed background tasks in the web and mobile Remote Control panels showing stale "Running" status by forwarding full task state on every membership change
- Improved auto mode to ask before running
rm -rfon a variable it can't resolve from context - Auto-update binary downloads now stream to disk instead of buffering in memory, cutting the updater's peak memory usage by roughly 400 MB
- Background task notifications now explicitly state that no human input has occurred, preventing fabricated in-transcript approvals from being acted on
- Improved agent view: sessions that edit, merge, comment on, or push to an existing PR now link it in
claude agents - Improved agent view: rows now show a colored state word and a classifier-written headline instead of raw tool call text, and the peek opens with full status including the exact ask for blocked sessions
/doctoris now a full setup checkup that can diagnose and fix issues;/checkupis its alias- Reserved the "Claude Browser" MCP server name (alongside "Claude Preview") ahead of the Claude Desktop pane rename; user-configured MCP servers can no longer register under either name
- Fixed Cowork VM-mode local-agent sessions failing to start with "Not logged in · Please run /login" on CLI 2.1.203+