Claude Code
v2.1.231
v2.1.231- What's changed
- Fixed MCP OAuth sign-in failing with a redirect URI mismatch for servers that use a pre-registered OAuth client, such as Slack
952 signals · 959 observation events
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.
v2.1.231### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? `claude.exe` (Cla
## Problem The Claude-in-Chrome extension blocks browser automation on financial sites (Wells Fargo, Charles Schwab, and likely all banking/brokerage domains). The block message is "This site is blocked." ## How it works The extension calls `api.anthropic.com/api/web/domain_info/browser_extension?domain=...` which returns a category. Categories 1 and 2 trigg
## Summary Single-session observations of three repeating Claude Code model behaviors that user-side rules in `~/.claude/CLAUDE.md` did not catch. Reporting because the patterns appear to be model-side and likely generalize beyond one user's setup. Filed at the user's explicit direction via `/goal`. Environment: Claude Code on macOS, model `claude-opus-4-7[1
## Summary Setting `autoMemoryEnabled: false` in `~/.claude/settings.json` correctly disables auto-memory writes and stops Claude from attempting them, but the hardcoded memory preamble (instructional text + \"currently empty\" branch + formatting templates) still loads into the system prompt at session start. This was previously reported in #44829, which wa
## Bug Report ### Description `Shift+Enter` stopped inserting a newline in the chat input and now submits the message instead. This is a regression — it was working prior to approximately June 30, 2026. ### Environment - **Claude Code version**: 2.1.193, 2.1.200 (both affected) - **OS**: macOS Tahoe 26.5.1 - **Terminal (broken)**: Apple Terminal.app 470.2 -
## Environment - Claude desktop app **1.24012.1.0** (MSIX `Claude_pzs8sxrjxfjjc`, `build_type: windows-store`), Electron 42.7.0 / Chrome 148.0.7778.280 / Node 24.18.0 - Windows 11 Home 26200, de-AT locale, 32 GB RAM - GPU: NVIDIA GeForce RTX 2080 — **reproduced on two driver versions** (32.0.15.9595 and 32.0.16.1074), so not driver-specific - Regression: zer
## What happened Starting approximately April 15, 2026, Claude Opus 4.6 in Claude Code has shown a noticeable quality regression compared to the previous month+. The same model that was working well for weeks is now significantly worse. ## Symptoms - **Fails to understand user instructions** that were previously handled well - **Ignores CLAUDE.md project ins
## Environment - Claude Code 2.1.197 (desktop app session with worktree isolation) - macOS (Darwin 24.6.0) ## What happened Starting a new session (new task, worktree isolation enabled) placed the session inside an **existing** worktree directory that a previous session had created for an unrelated task, instead of creating a fresh worktree. A new branch was
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? I have an auto-ap
# The pitch The most interesting thing happening in Claude Code right now is people trying to run it as a brain — not a pair-programming buddy, but the actual orchestrating intelligence behind a long-running system. Pipelines, ML training, build automation, monitoring, content workflows. The operator goes to bed and Claude Code keeps the lights on. That use
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? I've setup agents
## Bug Report ### Summary Claude Code consistently claims UI features "work" based on API/curl tests and code reading, without ever opening the actual application to verify visually. When called out, it saves a "feedback memory" promising to change — then repeats the exact same behavior in the next session. ### Environment - Claude Code CLI on Windows 11 - M
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Claude Code CLI t
## Environment - **OS**: macOS (Darwin 24.6.0) - **Node Version**: v22.10.0 - **npm Version**: 10.9.0 - **Node Manager**: nvm - **Claude Code Version**: 2.0.46 → 2.0.47 (failing to update) - **Installation Path**: `~/.nvm/versions/node/v22.10.0/lib/node_modules/@anthropic-ai/claude-code` ## Description Claude Code's auto-update mechanism repeatedly fails wit
## Summary Per the docs, Opus 4.7 always uses adaptive reasoning, and `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` / `MAX_THINKING_TOKENS` no longer apply. Please provide a way to opt out of adaptive reasoning on 4.7, the same way 4.6 allows. ## Motivation Adaptive reasoning under-thinks on questions where the *premise* is the trap, not the surface complexity. Th
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? The Claude deskto
## Describe the bug Since ~v2.1.154 (coincident with the Opus 4.7 → 4.8 switch), the prompt cache is repeatedly invalidated mid-session in two distinct ways, causing the entire conversation to be re-cached from scratch over and over. Across four of my sessions, **74% of all `cache_creation` tokens were waste** — re-caching content that had been cached second
## Environment - Claude Code CLI **2.1.172** on macOS (Darwin 25.5.0) - Local interactive session, accessed externally via **Remote Control** from the mobile app ## Expected Per the Remote Control docs: "Commands that produce text output, including `/compact`, `/clear`, `/context`, `/usage`, `/exit`, ... **work from mobile and web**." (supported since v2.1.1
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? In the recent upd
### What happened Claude Code's bundled `ugrep` (the CLI re-execs its own binary as `ugrep`, argv0=`ugrep`) allocates unbounded memory during **regex compilation** when run with `-E` (POSIX extended regex) on a pattern containing **two bounded `.{0,N}` intervals**. It reaches multiple GB of RSS *before scanning any input* and is OOM-killed (or SIGSEGVs under
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? I noticed a rapid
### Preflight Checklist - [x] I have searched [existing requests](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20label%3Aenhancement) and this feature hasn't been requested yet - [x] This is a single feature request (not multiple features) ### Problem Statement ## Context We are building a sibling VS Code / Cursor / Windsurf extension (`aims
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Claude Desktop (C
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Claude can read a
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? # Claude Code 2.1
## Summary On the Windows Claude Desktop app, `mcp__ccd_session_mgmt__send_message` stopped delivering messages to **paused** (idle-timed-out) sessions after the desktop app switched its bundled Claude Code binary to 2.1.227. The tool returns `Message sent`, the target session is resumed, and the message renders in the target session's UI — but the model nev
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Cloud connectors
# Post-mortem 2026-04-28: 12 multi-agent coordination bugs surfaced across a single autonomous-overnight cycle > Filed as a new issue rather than as a comment on FR #53610 because this catalog is generic to any multi-agent-coordination project — not specific to that FR's "9 architectural gaps that defeat unattended overnight operation" framing. FR #53610 has
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Environment: Clau
### Preflight Checklist - [x] I have searched existing issues and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? When `~/.claude/settings.json` is a symbolic link to a file outside `~/.claude/`, 2.1.139 does not load the env
## What's Wrong? Over three consecutive days (2026-06-09 to 2026-06-11, JST), content that **does not exist in the saved transcript on disk** repeatedly appeared in the model's context across 4 different sessions on the same machine, steering the model toward data exfiltration. The model refused every time, and our local audit found no actual egress — but th
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? When attempting t
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Connecting to a r
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? After updating to
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? ## Summary Since
**Environment:** Claude Code 2.1.210 / 2.1.211, macOS (darwin 25), interactive sessions. **Setup:** a `type: "prompt"` PreToolUse hook on Bash (LLM security judge using the documented `{ok, reason}` contract from https://code.claude.com/docs/en/hooks). **Before (≤2.1.209):** judge `ok:false` denials fed back to the model as `is_error` tool_results; the model
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? [BUG] Receiving s
# Bug report — desktop app (Windows): cross-session messages are silently dropped: held for an approval the UI never offers, then expire after ~5 minutes ## Preflight - Searched existing issues. Closest are #86212 (recipient never runs a turn, normal-mode, recoverable by typing) and #85888 (held-for-approval with no approval surface, macOS agents dashboard).
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? I am trying to us
## Summary When working in a Claude Code-managed git **worktree**, file edits can silently be written to the **parent repository checkout** instead of the active worktree. The worktree stays clean, so the diff panel shows "No changes" and the preview doesn't reflect edits — while the work actually lands in a different checkout of the same repo. ## Environmen
**Type:** Cybersecurity safety-filter false positive · **Work domain (heuristic):** `general` ### Why this is a false positive This request was part of an authorized, in-scope effort to gather publicly available tooling and research and to prepare a local USB/ADB diagnostic path against the operator's own hardware. The flagged content is dual-use device-rese
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? When using Claude
**Bug Description** False positive: Fable 5 dual-use safeguard downgraded me to Opus 4.8 during an authorized security review of my OWN codebase. Context: I'm the owner/founder of a B2B SaaS (FastAPI backend). I asked Fable 5 to run a deep security review of my own repo — tenant-isolation/IDOR, auth-token forgery, SQL injection, webhook signature verificatio
## Description During a long `subagent-driven-development` session (implementing a multi-task plan via the Agent tool), the auto-mode permission classifier repeatedly denied `Agent` tool calls, citing prompt-injection / "classifier bypass" concerns. Every denial pointed at the same source: a `<context_window_protection>` instruction block that names MCP tool
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? On Windows 11 (bu
For almost a week now, I have been completely unable to use my Claude Max 20 subscription. A few minutes after each quota reset, my entire quota is already exhausted **without me even using Claude**. ## What I've already tried - Revoked every Claude Code token. - Deleted all Claude sessions. - Verified that I have **no API keys** associated with my account.
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? ## Summary A Clau
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? On Windows (MSIX/
### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Since ~06:30 ET o
# Claude Code published a user's personal information to a public GitHub issue, unprompted and unchecked ## Summary While drafting a comment for a public issue on this repository, Claude Code included the user's Windows account name — quoted from working material it had generated earlier in the session — and posted it with `gh` without any review of the cont