Claude Code v2.1.268
Released Sep 10, 2026 (3 days ago).
84 issues reference this build
84 still open
0 resolved (0%)
"References this build" means the issue body mentions running 2.1.268 (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 v2.1.268
Ranked by community engagement (reactions and comments).
- [FEATURE] Cache CLAUDE.md and rules across sessions: they are re-written to the prompt cache at every session start
- [BUG] --resume never hits the prompt cache past the static prefix on Fable 5.1 (opus hits): session-start context message is replayed as a plain string instead of the content blocks it was sent with
- [FEATURE] Expose the Artifact tool and artifact-* skills in Remote Control (sdk-cli) sessions
- Agent teams: task self-claim has no role/tool-compatibility filter, so read-only teammates claim tasks they cannot do
- [BUG] VS Code 2.1.268: current-file chip Hide toggle replaced by X - context auto-attach opt-out no longer persists
- [Bug] Anthropic API Error: Overly aggressive content filtering blocking legitimate MD simulation research
- [Bug] all my messages are getting flagged because i ran a security audit on my repo with os4int tools
- Instruction injected into every tool result overrides explicit user instruction and has no opt-out
- [BUG] /btw appends "Never consult the advisor tool." to the user's message, so the model treats it as a user instruction
- Desktop app /mcp OAuth sends a claude:// redirect URI that mcp.cloudflare.com rejects (Redirect URI must use HTTPS or a local loopback address); CLI connection not shared with the desktop session
- [BUG] 2.1.268: statusLine command is never invoked when cwd is a git repo (works in a non-git cwd) — regression from 2.1.267
- Constant 'API Error / Disconnected / Retry x of 10' on 2.1.268 (macOS 26.2) — auto-mode classifier also timing out
- [Bug Report: Unable to process input]
- [Bug] Anthropic API Error: Content flagged by safeguards on Claude 3.5 Opus
- [Bug] Agent hallucinating and ignoring claude.md rules during task execution
- Desktop app: /compact shows no progress indicator (terminal CLI has one)
- [Feature Request] Per-model spend caps and token allowance allocation
- [Bug] Image data not persisting after multiple upload attempts
- Remote Control 2.1.268 (macOS): session spawned by `claude rc` stops all outbound traffic after its first turn; hub marks it offline, app shows "Reconnect from your computer"
- [BUG] WSL2: a read-deny path symlinked into /mnt/c fails bwrap for every Bash command, and is unremovable when it comes from managed settings
- [Bug Report] Model performance issue affecting token usage efficiency
- [Bug] Unexpected model downgrade on simple temperature sensor task
- [BUG] Pop-out/maximised plan window: text doesn't reflow to window width (related to #62543, closed not-planned)
- [BUG] Windows: ECONNRESET on first Claude Code prompt despite working HTTPS
- Chat panel: Send/Stop button has no accessible name (WCAG 4.1.2)
- [Bug] Anthropic API Error: Content flagged by safeguards with Opus 5 model
- Fable 5: CSS-only layout fix escalated to dev server + Playwright screenshots; the requested artifact preview was two pasted PNGs with no design work
- [Bug] Conversation restart requires excessive token reuse after API-forced session termination
- /goal: Stop condition evaluator cannot see the instruction passed via /goal, loops until it declares itself unachievable
- [Bug] Can Anthropic look at your session transcript to help us improve Claude Code? Not taking the y
Changelog
What's changed
- Added to the Claude apps gateway: with
pricing:set ingateway.yaml, signed-in Claude Code clients receive the same rates through managed settings, so/costand telemetry match the spend meter - Added a startup warning for gateways when
access_control.allow_cidrsis empty, and a one-time warning the first time a request arrives from a public address - Added the
gatewayInternalNetworksmanaged setting, letting administrators allow/loginto a Claude apps gateway on their organization's own public IPv4 block - Added
claude self-hosted-runner --remove-session-state(default off): delete each session's per-session directories under<base-dir>/_sessions/when the session ends - Added
configDirectoryto the output ofclaude auth status --json - Added
--jsontoclaude plugin install,uninstall,update,enableanddisable, anderrorDetails/noteDetailsto each row ofclaude plugin list --json - Added browser-tab icons for published artifacts, chosen by Claude to match each page
- Fixed every turn failing with HTTP 400 on third-party Anthropic-compatible endpoints (
ANTHROPIC_BASE_URL) since 2.1.265: a regex in the Artifact tool's input schema that those endpoints reject - Fixed WebFetch hanging indefinitely on a server that keeps the response open without finishing; a fetch now fails after 300 seconds. Set
CLAUDE_CODE_WEBFETCH_DEADLINE_MSto override the deadline (0 turns it off) - Fixed a respawned in-process teammate picking up tools or a system prompt from a same-named agent file in a folder you have not trusted
- Fixed sustained high CPU usage: a busy loop in long-running idle sessions no longer pins a CPU core, and rapid terminal focus reports during a session recap no longer keep the CPU high
- Fixed Claude sometimes replying "your message came through empty" after an MCP tool call
- Fixed deny and ask permission rules on symlinked directories (
/etc,/tmp,/varon macOS;/binon Linux) not applying when a path was given by its real location, and Bash commands ignoring deny rules written on a symlinked path spelling - Fixed a case where a Read or Edit deny rule did not apply when an
env -C,evalor similar command the permission checker cannot analyze was on the same line - Fixed plugin and marketplace errors showing a token or password from a git source URL
- Fixed
/mcpand/pluginserver details,claude mcp list/get, and MCP login errors showing secrets resolved from${VAR}placeholders in MCP configs - Fixed prompt caching and extended thinking breaking mid-session for SDK sessions using
excludeDynamicSections: the first message is no longer re-rendered each request - Fixed entitled users being told a model is restricted after restart or in the Desktop Code tab when a cached model-access denial was stale
- Fixed a running session silently switching to the organization's default model when another Claude Code process refreshed a stale model-access entry
- Fixed long-context 429s on Fable models showing the usage-credits consent prompt instead of the 1M-context message on Pro and Team plans
- Fixed workload identity federation via a profile (as claude-code-action configures it): processes sharing the profile could fail mid-run with
401 … jti reused - Fixed MCP server OAuth sign-in failing with "No available ports for OAuth redirect" when the local callback port range can't be bound
- Fixed the conversation summary produced by
/compactand auto-compact mangling text that contained$sequences - Fixed resuming a conversation that ended with
/compact: its restored-file notes now load in the same order on every resume - Fixed SDK prompt suggestions, side questions and
/renamesending the conversation from before a compaction - Fixed
@file and/command suggestions not appearing after recalling a previous prompt with the up arrow and editing it - Fixed
claude agents: pressing ← again at a natural pace to go back to the agent list no