Digest / August 16, 2026
Claude Code Issues Digest — August 16, 2026
190 new issues filed ·
396 resolved in anthropics/claude-code (UTC day).
New issues (190)
- No context path between claude.ai and Claude Code
- VS Code extension panel missing message actions (copy, pin as chapter, read aloud, timestamp) present in Remote Control/web view
- [FEATURE REQUEST] Project-scoped /plugin install should also write extraKnownMarketplaces to project settings, so the checked-in config resolves for collaborators
- Feature requests: window focus for computer tool, translate suppression, PATH persistence, popup window tracking
- [Bug] Anthropic API Error: Account flagged by safeguards, CVP review pending
- Claude desktop app can't connect to Chrome extension for browser automation, despite side panel working
- SendMessage cannot address a session whose title begins with `/`; ListAgents reports it as `(untitled)`
- [Feature Request] hooks[].if couples a tool name to the condition, so one condition across N tools costs N handlers
- Session name label in app UI doesn't update after renaming via Ctrl+R in resume picker
- [DOCS] Queued input ordering is undocumented — plain prompts fold into the running turn while `!` and slash commands wait for it to end
- Spurious <<ccr:XXXXXXXX>> tokens injected into Bash tool output (grep/wc results), not present in source file
- Allow custom ANTHROPIC_BASE_URL / model provider in the managed app (not just raw CLI)
- Complete Waste of time
- Feature request: configurable external editor for file link clicks (e.g. open in nvim at line)
- [MODEL]
- [BUG] Cowork: restarting the Claude app destroys the MSIX container and kills packaged CoworkVMService, which then cannot restart until reboot
- [BUG] Security violations in Claude Code Extension
- [BUG] SessionStart hook cannot tell which model the session runs after /clear (`model` missing from hook input)
- [BUG] **Title**: Claude Code 2.1.233 intermittently stalls ~3 minutes before responding on Windows (client-side, zero network connections during stall)
- [BUG] tool_search_tool_result references a claude.ai connector that was never enabled on the account — session 400s permanently and cannot compact
- [Bug] Anthropic API Error: Request ID req_011Ce5fmbg9F87DzGxXddy3F
- Recognize TERM_PROGRAM=Nash for native terminal progress support
- Claude in Chrome not working
- [BUG] Cloud workspace session persists its /sessions mount path into core.worktree of the synced repo's shared config, breaking local worktree creation
- Desktop app GPU process crashes (exit code 101457950) when Browser pane renders a page with a Cloudflare Turnstile widget
- [FEATURE] Non-intrusive prompts — stop stealing focus from active typing (52 related reports, consolidated)
- I appreciate you sharing the context, but I'm not able to access external Request IDs or see the specific bug report you're referencing. To generate an appropriate GitHub issue title, I would need: 1. **The actual error message or problem** you're exper
- [BUG] Background Bash task's process group is SIGKILLed mid-run when the command spawns a daemonizing CLI (cursor-agent) — and reported as completed (exit code 0)
- Concurrent editing: agent file edits race user's editor autosave (need collision detection / merge)
- [Bug] TODO tasks lost during execution
- CLI crashes with SIGABRT on `HTTP Client` thread (4x in 32h, v2.1.232 & v2.1.233)
- [BUG] PermissionRequest hook stops firing after CLI restart on Windows (v2.1.233)
- Cowork on Windows crashes with "Illegal instruction" / exit code 3 — Bun/Claude Code binary requires AVX not exposed by Hyper-V VM
- macOS: long-running session progressively loses TCC-protected paths (Downloads → Documents → project dir), ending in getcwd() EPERM — grant and code signature both verified valid at denial time
- [BUG] macOS: long sessions die with ECONNRESET — macOS TCP send-buffer default (autosndbufmax=4MB) bursts the growing context upload; one sysctl fixes it
- [Feature Request] Enable Fast Mode for Max 20 accounts without additional credits
- [FEATURE] Remember the "Allow Claude to open this file?" consent per session folder
- SubagentStop matcher is silently bypassed when agent_type is empty — agent-scoped hooks fire on every internal fork
- [BUG] VS Code skill invocation is blocking output
- [BUG] Claude Code keeps crashing and I have to reinstall it to fix and then it crashes again
- Feature request: built-in settings sync (like JetBrains/VS Code Settings Sync)
- [Bug] Consent dialog blocks headless sessions and silently swallows agent pings
- Promotional /ultrareview nudge is injected into tool output and attributed to the user's PostToolUse:Bash hook
- [FEATURE] No in-session way to save/update a skill; agent must deliver a file and cannot confirm the save happened
- [BUG] Windows: fatal GPU process crash (exitCode 101457950) during Claude Code sessions kills entire app; MSIX package requires Repair to relaunch
- [BUG] Cowork session has no in-session skill save/update path or confirmation — inconsistent with other sessions
- [Bug] Anthropic API Safety Filter: False Positive on Legitimate Cybersecurity Researchok
- [FEATURE] Accessibility: dark theme's near-black/white pairing (#0b0b0b / #f0efec) causes visible saccadic artifacts — add a contrast preference
- [BUG] Windows: Claude Code in-app preview device mode toggle (Mobile/Tablet/Responsive) renders two overlapping previews instead of switching the viewport
- /auto-mode-setup always fails: "removeFromPermissionsAllow[0] is not a rule string the removal offer could have produced"
- [Bug] Unexpected file deletion without user confirmation
- [BUG] Auto-mode task dashboard shows identical task list across different projects (not scoped to cwd)
- [Feature Request] Add Vim keybindings support to Claude agents view
- [Bug] Claude Code ignores user instructions and performs opposite actions
- [BUG] Windows: main window permanently always-on-top (WS_EX_TOPMOST) after silent update relaunch - stealth-relaunch z-order restore anchors to taskbar
- [Bug] Fable 5 model safeguards blocking legitimate coding tasks
- [EVAL/TRANSPARENCY] Anthropic's regulation case rests on internal evals — apply the #86979 provenance standard to Glasswing and 'When AI Builds Itself'
- [BUG] Dynamic /loop (ScheduleWakeup) swallows the assistant's replies to the user — before AND after the tool call; only stopping the loop restores replies
- [Bug] Performance degradation and general system instability
- Add a way to disable terminal mouse tracking (breaks native middle-click paste over SSH)
- [Bug] Opus 5 safeguards over-flagging legitimate humanities benchmark tasks
- Autonomous session continued for 3 weeks after establishing on day one that the task's premise was closed — wasted weeks of compute and tokens
- Aviso de "archivo modificado externamente" expone contenido de credenciales sin distinguir origen del cambio ni ofrecer exclusión de rutas
- [Bug] Unexpected model downgrade from Claude 3.5 Sonnet to Claude 3 Opus
- [BUG] Repository not found when starting new chat on mobile app
- [BUG] Agent view shows "esc to return" hint but Esc interrupts the agent instead
- Randomlydropsspaceswhen generating tool-call arguments(v2.1.233)
- [BUG] Claude Desktop main-thread blocking during CLI auto-update causes Application Hang + Cowork VM session loss + MSIX corruption
- Device-connected (`sdk-cli`) sessions load none of the desktop-native MCP servers — no browser, computer-use, scheduled-tasks or session-management tools
- [BUG] Notification subsystem stops initialising on macOS — regression in 1.28929.0
- [BUG] Notification subsystem stops initialising on macOS — regression in 1.28929.0
- Session-start sidecar request is sent twice, ~13 ms apart, and both are billed
- [Bug] Subagents idle without supervisor intervention and off-plan code generation despite verification
- [BUG] Desktop: "+ New" worktree session fails with "WorktreeCreate hook failed: path contains control characters" (repo not under a TCC-protected folder)
- RTL/Persian text renders garbled in interactive TUI, but correct outside Claude Code (e.g. typed directly in terminal)
- [BUG] Canva connector — "Fail to exchange access token" error during OAuth setup
- Resuming completed subagents replays the full transcript per message — burned 75% of a weekly limit in one afternoon
- [BUG] Cowork (macOS): pending AskUserQuestion dialogue is lost when the user switches to another chat or artifact view, with no respawn path, and the agent is told the user rejected it
- Browserbase MCP connector disconnects mid-session, dropping start/navigate/extract without warning
- Skill tool: multi-word args cause $N positional substitution to corrupt literal $N tokens in skill body (e.g. Excel cell refs)
- [BUG] send_message` (ccd_session_mgmt) renders in the recipient's UI but is never injected — regression between app 2.1.222 and 2.1.227
- Support operator-authorized overrides of self-generated permission rules
- Conversation history disappears after quitting and relaunching the app (session continues correctly server-side, but transcript is not shown)
- [BUG] Stacked slash-skill invocations load only the first skill on the SDK / --print path
- [Bug] ListAgents omits live named sessions and returns inconsistent names across namespaces
- [FEATURE] Allow Claude's macOS Computer Use to operate one app without taking over the user's workstation
- Intermittent silent stalls mid-turn, no error/timeout — reproduces cross-backend (native API + DeepInfra), related to #40462
- Projects tool: project_write silently destroys document content, with no append mode, no version history, and no recovery
- Add inactivity-based auto-disable for Remote Control per session
- [Feature Request] Clarify or reconsider text watermarking policy for code generation outputs
- [Feature Request] Require review and confirmation before merging changes
- [Bug] Overly aggressive safeguard flags on legitimate development tasks (DB reads, CI inspection, security hardening)
- [FEATURE] Setting to hide the session-name badge on the prompt box
- Add a setting in config to enable or disable screen reader mode (AXScreenReader)
- [Windows] Desktop app: caption close button overflows the title bar and covers the Background tasks panel's X - clicking it quits the app
- Agent/model launches request effort=xhigh against thinking-disabled model, crash with 400
- In-app Claude Browser crashes session when navigating to perplexity.ai
- [BUG] issue with Claude Pro annual (Google Play) not processed after 4+ days — Fin claimed success, Google rejected it, account still on Free tier
- [BUG] Embedded ugrep hangs indefinitely (pegged core) on unanchored bounded-repetition pattern — the same binary's embedded ripgrep finishes in 53 ms
- [FEATURE] Support more than one IDE-connected Claude Code session per editor window
- [BUG] Parking a mid-flight turn leaves the interactive session's probe stuck at status: "busy" forever (2.1.220)
- Google Drive connector works in chat but is invisible to list_connectors/cloud routine attachment
- [BUG] Claude Code内蔵のArtifactプレビューで、白背景のボタン（ghostスタイル）の文字が表示されない
- Model reinterpreted an explicit instruction, killed running subagents unasked, and asserted a capability limit without checking it
- Repo picker overlay reopens on every submit attempt, blocks sending message in Cowork new-task composer
- [Bug] Poor code formatting output quality and iteration efficiency
- `Bash` tool description embeds the per-session URL, so every `/resume` invalidates the whole prompt cache
- Bash sandbox intermittently fails with apply-seccomp: unshare(CLONE_NEWUSER): Invalid argument
- Permission rules: $HOME not expanded during startup validation when checking symlinked config
- Escape in the main input kills running background agents
- I appreciate you reaching out, but I'm not able to generate a GitHub issue title from this message. The text you provided appears to be a statement in Portuguese saying "the program is not intended for illegal activities but for monitoring work" - this s
- Subagent liveness/death observability for long-running orchestrators (per-agent deadline, crash-path notification, status poll)
- I appreciate you sharing that context, but I need clarification. You've indicated this is about monitoring and support for collaborators, not for illicit activities. However, you haven't provided a specific bug report or technical issue description for Cla
- macOS: CLI installed as bare Mach-O at a versioned path gets a new TCC identity on every auto-update (path-keyed, client_type=1)
- Subscription OAuth token not passed to plugin hook subprocesses on Windows — security-guidance LLM review silently disabled
- [BUG] ScheduleWakeup never fires in Remote Control child sessions (sdk-cli bridge) even though the session stays alive and task notifications are delivered
- [Bug] Claude Code presents unverified hypotheses as diagnoses without web search verification
- [Feature Request] Add security policy documentation and usage restrictions
- claude auto-mode critique returns "No critique was generated" for a large autoMode block; works with a small one
- Startup config should be processed before first user prompt, not after
- Feature request: progress indicator for long-running background tasks (/code-review, background agents)
- [Feature Request] Implement context reset or conversation pruning for improved performance over long interactions
- Denial messages don't say which permission rule or settings file fired
- Cross-machine session directory never populates: ListAgents shows only local sessions despite both machines being RC-connected (v2.1.233)
- Claude Desktop tray icons are indistinguishable when multiple instances are running
- [Bug] Fork on completed /btw response re-submits original prompt instead of continuing session
- [BUG] Claude Desktop (Windows) crashes when opening generated web page preview — infinite render loop in EpitaxyFramePage + EventEmitter listener leak
- [Bug] Claude 3 Opus performance degradation after auto-compact without history clear
- Headless -p "/skill" with a failing !-preamble silently aborts pre-turn and reports subtype:success, num_turns:0
- [BUG] Ctrl+click on a link opens two browser tabs in Windows Terminal: Claude Code activates the link in addition to the terminal
- Windows: Browser pane hang leaves the MSIX package unregistered (0x80073D28 - packaged service needs elevation)
- [BUG] Images/Files dropped into a claude desktop code, can not be accessed by the model
- [BUG] `sandbox.network.strictAllowlist` has no effect — Bash tool dispatcher never invokes bwrap, on any tested version
- [BUG] Desktop file pane: right-click on a text selection offers no Copy — the context menu is entirely file-scoped
- [Bug] Tool execution fails to match multiple lines in clone operations
- [BUG] Windows Desktop: app dies during 7-agent parallel workflow with concurrent web fetches, then MSIX registration is wedged and Repair is blocked by leftover Claude processes; identical load completes in CLI
- Scheduled-task session runs but never appears in the desktop app sidebar
- [FEATURE] Integrated terminal support for WSL sessions in Desktop app Code tab
- [Bug] Anthropic API Error: Model refuses continuation with AUP message in valid session
- Ghostty right-click context menu degrades during long sessions, with CLAUDE_CODE_NO_FLICKER unset
- Cowork VM fails to start: signature verification rejects valid multi-volume AppX package copy
- [BUG] app crashing in windows, continuously. tells to repair, but it says cannot repair
- Measured behavior change opus-4-8 → opus-5: requests ending in a concession doubled (p=0.0002), replicates out-of-sample
- cleanupPeriodDays default of 30 silently destroys the only evidence a user has of a behavior change
- [FEATURE] Cloud sessions/Routines: repo-scoped GitHub access without a user-level claude.ai<->GitHub account connection
- Background sub-agent (Agent tool) killed with 'stopped by the user' when user did not send a stop
- [BUG] Insecure code generation: markdown backticks in an unquoted heredoc execute locally
- Autonomous orchestration burned ~20% of a weekly Max quota on redundant self-validation loops the user never requested
- [BUG] AskUserQuestion returns fabricated answers when interrupted — reports the model's own '(Recommended)' option as the user's selection
- Cowork: scheduled-task prompt cannot be updated — even a single-paragraph prompt is rejected ("path traversal detected" / "failed to update")
- [FEATURE] ListAgents should show each peer session's working directory
- [Bug] Model loses context of overarching goal and ignores user critique in favor of immediate execution
- [BUG]: Persistent intermittent ECONNRESET immediately after first streamed chunk, Windows, multiple CLI versions and networks.
- [Bug] Anthropic API Safety Guard triggered unexpectedly during Go linter bug analysis
- [BUG] Whole message renders as raw markdown when the first markdown construct starts after character ~500
- [Feature Request] PreToolUse/PostToolUse hooks lack access to live background task registry
- Design project API serves a stale snapshot while reporting success
- Top-of-feed keyboard shortcut tip persists after disabling spinner tips
- Artifact public sharing blocked: "This version can't be shared publicly" on every version and fresh artifacts (Max plan, CLI 2.1.233)
- [FEATURE] Attach a terminal to a Remote Control session running on another machine
- /claude-api skill loads the entire multi-language bundle (~230k tokens) instead of the detected project language
- Login reports success but never persists the credential (macOS Keychain) — silent auth loop on 2.1.223 and 2.1.232
- [BUG] Remote Control: new session from claude.ai reuses the pre-created session's conversation (deterministic v5 session id)
- [BUG] Claude Desktop 1.30096.5 hangs before creating a window on macOS
- Session hangs indefinitely mid-turn: ide MCP tool calls (auto getDiagnostics on Write) have no timeout, while connect does
- Repeated failed troubleshooting loop wasted significant time/tokens (Expo Go tunnel setup)
- False "Update available!" notice repeats on idle, even when apt-managed install is already latest
- [Bug] Request blocked with unclear error message
- Process name in Activity Monitor/ps is the version string (2.1.233), not claude
- [Bug] Claude incorrectly reports task completion without finishing work
- Skill tool substitutes invocation args into literal "$0" text inside SKILL.md
- [FEATURE] Expose the session color to external tools (statusLine JSON, hook input, sessions/<pid>.json)
- Cloud ultrareview fails reproducibly: 'all review agents terminated before completing' — 2 runs, 0 findings, 2 free credits consumed
- [BUG] Windows desktop 1.30096.5: whole app killed when Browser pane renders a Cloudflare challenge — Code Integrity blocks vk_swiftshader.dll (exit 0x060C201E), MSIX flips to Modified. Root-cause evidence for #80444
- [Bug] Clipboard write conflicts with Windows Terminal copy in RDP sessions
- [BUG] Desktop "Add marketplace" reports "Failed to add marketplace" while the sync is still in progress and subsequently succeeds
- [FEATURE] Expose per-model weekly rate limits in the statusLine JSON
- [BUG] "Run on startup" option cannot be disabled
- [MODEL] Opus 5 Over Verbose Output
- [BUG] Authentication Service Down Globally
- Remote Control disconnects with "Session creation failed"; /bug feedback endpoint also returns 500
- Claude Code unexpectedly switches to Hind for 3 words in German response
- Remote Control: resuming a conversation replays a dead session binding, and /remote-control can only retry the doomed reconnect
- [BUG] Chatting with Claude Code feels like living inside Memento: a 48-day session narrated as one continuous night
- [BUG] Waking a parked subagent re-caches its entire context: only the system prefix is served from cache, even minutes later within TTL
- [Bug] Sandbox file-read deny rule (.env*) not enforced for compound Bash commands in Agent-dispatched subagents
- [BUG] paths: frontmatter on a USER-level rule (~/.claude/rules/) silently disables it — loads at neither session_start nor path_glob_match
- [Bug] Timezone calculation error for trans-Pacific flights ignoring International Date Line
- Desktop app: bring back the startup welcome screen (account name / model / billing info)
- I appreciate you sharing context, but I'm not able to generate a GitHub issue title based on this message. You've described a legitimate security scanning use case rather than reporting a bug or feature request for Claude Code itself. If you're experienc
Resolved issues (396)
- [BUG] Custom statusLine never renders when `tui` is set to `fullscreen` (macOS, 2.1.170)
- Memory-file Write/Edit destroys all frontmatter when YAML parse fails (originSessionId stamper writes empty stub instead of rejecting)
- [BUG] Interactive mode: manual /compact fires PreCompact but never PostCompact (print mode fires both) — v2.1.214, macOS
- [BUG]
- [Bug] Anthropic API Error: Safety Filter False Positive on Legitimate Security Scan (req_011Cd8wWxNaDBGUaiV5HAH8h)
- [BUG] /remote-control crashes after hibernation: Cannot read properties of undefined (reading 'session_url')
- [BUG] Missing HCS services: vfpext — persists after DISM/SFC repair and Hyper-V re-enable (Windows 11 Pro)
- [Bug] Anthropic API Error: Server temporarily limiting requests (rate limit)
- [Bug] Anthropic API Error: Server Rate Limiting During Normal Usage
- [MODEL] Claude doesn't know its own CLI flags — users shouldn't have to teach it --resume
- [Bug] Anthropic API Error: Server Rate Limiting During Request
- [Bug] Anthropic API Error: Server rate limiting on requests
- [Bug] Anthropic API Error: Server rate limiting on requests
- [BUG] Auto-mode ignores permissions.ask
- /goal Stop hook fails with "Prompt is too long" when goal text is large
- [Bug] Anthropic API Error: Cannot Modify Thinking Blocks in Assistant Messages
- Your organization has disabled Claude subscription access for Claude Code · Use an Anthropic API key instead, or ask your admin to enable access
- [BUG] Scroll wheel intercepted by prompt history navigation — no way to disable
- [FEATURE] Add fableplan model alias: Fable 5 for planning, Sonnet for execution
- [BUG] API Error: 400 The request body is not valid JSON: str is not valid UTF-8: surrogates not allowed: line 1 column 1 (char 0)
- [Bug] TUI clipboard copy broken in response text (Ctrl+Shift+C, right-click)
- [Bug][cyber] Blocks rolling back consumer drone firmware to a release predating an added restriction (req_011CcVtCm2xFhDbukwuYU5eB)
- [Bug] Terminal mouse/focus escape sequences leak into input on WSL2 resize
- [Bug] Anthropic API Error: Server rate limiting during normal usage
- [Bug] Anthropic API Error: Server Rate Limiting During Normal Usage
- [Bug] Anthropic API Error: Server Rate Limiting (Temporary Request Limit)
- [Feature Request] Refine content safeguards to reduce false positives on legitimate coding work
- SSH/Remote-Tools connection to Synology NAS fails: "Failed to upload file: No such file"
- Agent-mode session silently drops mid-turn after tool_result on unattended Mac (WarmLifecycle idle_timeout suspected)
- [Bug] Anthropic API Error: Server rate limiting on requests
- [Bug] Anthropic API Error: Server rate limiting requests
- [Bug] Code migration incomplete - Claude omits features without explicit notification
- [Bug] Anthropic API Error: Server Rate Limiting - Temporary Request Limit
- [Bug] Opus 5 safeguards over-flagging legitimate humanities benchmark tasks
- Desktop: ccd_session_mgmt__send_message reports "Message sent" but never delivers
- [BUG] Notification subsystem stops initialising on macOS — regression in 1.28929.0
- [BUG] Chat artifacts not showing in mobile app Artifacts menu (Android)
- [BUG] Claude Desktop 1.28929.0 (Windows/MSIX): GPU process crashes on session preview — regression from 1.26832.0
- [Bug][cyber] False block on authorized consumer drone firmware analysis via USB passthrough (req_011CcUBGf1tgrAnfN4wMxTrX)
- [Bug][cyber] Safeguard blocks git-SSH remote config for firmware RE research repo environment (req_011CcUDwt241xggyoBJ6DbbH)
- [Bug][cyber] False positive blocks static RE of white-box AES native method in SDK AAR (req_011CcV5L5hq98qxRQDB2Y9aG)
- [Bug][cyber] Safety block stops legitimate drone firmware extraction and ADB analysis workflow (req_011CcUDY4dMjWrzVBGYbJHco)
- [Bug][cyber] Safety block stops legitimate drone firmware research and USB/ADB tooling work (req_011CcUCmrmzeYYStrRvqnVJJ)
- [Bug][cyber] Safety block rejects firmware version comparison for open-source drone rewrite (req_011CcUAZ3zLbRQGeAsKenNEL)
- [Bug][cyber] False positive block on authorized reverse-engineering of closed-source drone SDK for interop (req_011CcVsnffpvCMeQZ4FixgRm)
- [Bug][cyber] USB drone RNDIS/serial enumeration via open-source SDK incorrectly blocked (req_011CcUFo2LqcYeErkLSon6Jb)
- [Bug][aup] Safety block on disabling SMTP AUTH org-wide as a BEC/email hardening defensive measure (req_011CcSR4x56upJ4iJtR8kGBj)
- [Bug][cyber] RTSP stream proxy/viewer integration in app wrongly blocked as cybersecurity (req_011CcUR4SjW19NDrt4CKJMUX)
- [Bug][cyber] Safety block on drone USB/RNDIS interface enumeration during defensive firmware analysis (req_011CcUFpr7jdLiNHaV11xjm4)
- [BUG] Claude Code Extension in Antigravity IDE displays "monthly spend limit" instead of 5h rolling session reset
- [Bug][cyber] Safeguard blocks white-box AES native method analysis during authorized SDK security audit (req_011CcV5LarH85edkCjtg8jSb)
- [Bug][cyber] Blocked asking whether firmware downgrade removes proprietary whitebox blob (req_011CcVsoCiNTcFRUPRhMtxmG)
- [Bug][cyber] Static RE + white-box AES analysis of embedded device firmware wrongly blocked (req_011CcV523mzeqMaheP9ZNfXb)
- [Bug][cyber] Safety block interrupts legitimate white-box AES reverse engineering on own hardware (req_011CcV53T1GpzRkDfcT8LA98)
- [Bug][aup] Project scaffolding for open-source hardware research repo wrongly blocked mid-setup (req_011CcUDQvewGgVQ2U96Q7KkS)
- [Bug][cyber] Safety block wrongly stops static RE of white-box AES in proprietary firmware (req_011CcV4rLwqSCNGtqDMQF7Jd)
- [Bug][cyber] Open-source firmware reverse-engineering research project setup blocked incorrectly (req_011CcUDFrvhfMPxDbuK4Lybx)
- Support glob patterns in additionalDirectories configuration for consistency with other permission rules
- [Bug][cyber] RE analysis of in-memory DEX element construction and bytecode decryption blocked (req_011CcWCoSWJTq4MGQsavzDuM)
- [Bug][cyber] Safety block wrongly stops ADB-over-WiFi persistent setup on rooted Android device (req_011CcWCkZuiPGMEua2nS7Acc)
- [Bug][cyber] Persistent ADB-over-WiFi setup on rooted Android device blocked as unsafe (req_011CcWCiR9Jep5V6e2n6cebH)
- [Bug][cyber] Safety block stops debugging encrypted DEX loading crashes in Android emulator (req_011CcWCpMyyZVNhdvkhDccoz)
- [Bug][cyber] Safety block persisting wireless ADB debug across reboots on custom Android ROM (req_011CcWCLGsNCNEadxuojYP9Z)
- Workstreams header icon displays worktree branch icon instead of workstream icon
- [Bug][cyber] Cloud IAM audit/review work incorrectly flagged as unsafe cybersecurity content (req_011CcVvH7oDPuj7ZVtVbfnJy)
- [BUG] V2.1.195 Entering a queued prompt then cancelling still appears in Claude's work context
- E:/Program Files/Git/rewind overwrites settings.json env vars (model, base URL, auth token)
- [Bug] Weekly usage limit unexpectedly increased without API calls
- [FEATURE] Add /feedback option to Create or Find Github Issue
- Access local Claude Code sessions from another machine (multi-device session access)
- [FEATURE] A native way to hide a plugin's workflow behind a single command entry point
- Add RTL / bidirectional text support for Arabic
- [Bug][cyber] Safety block interrupts APK unpacking/DEX decryption key analysis mid-session (req_011CcWUiMYd6DwbhzJSthUCh)
- claude resume (without --) silently starts new session instead of warning
- [BUG] VSCode extension sessions not appearing in sidebar after closing
- Background Tasks panel: list reflow on new task arrival can redirect a "Clear" click onto another task's "Stop" button
- [BUG] Remote container proxy blocks releases.astral.sh:443, preventing uv from downloading Python versions.
- Workflow tool burned entire 5x plan in ~5 minutes with no warning or authorization prompt
- Agent resolves an ambiguous case identifier by recent-context bias instead of the literal exact match, then executes on the wrong target
- Feature request: roll over unused weekly usage to the next week (within the billing month)
- TUI leaks malformed truecolor escape `\x1b[38;2;NaN;NaN;NaNm` into prompt buffer (shows as `aN;NaNm`) during background-workflow/auto-mode redraw
- Claude repeatedly ignored explicit user directives and substituted its own judgment — session 2026-06-28
- Tool calls intermittently emitted as literal text instead of being executed — silent task stalls on Opus 4.8 / Sonnet 4.6
- Agent declares a fix verified from an indirect proxy signal (log/count) instead of the actual displayed output, re-presenting a result the user already reported as broken
- [FEATURE] Session list UX improvements: sorting, search, rename, and deletion
- [Feature Request] Add granular setting to disable coaching hints in agent view
- Agent verifies a fix with a standalone reproduction configured differently from the live path, producing a false 'verified' on still-wrong output
- [BUG] Max 5x Plan ($100) incorrectly showing as Free despite active subscription — June 27, 2026
- [Bug] Anthropic API Error: Server Rate Limiting During Normal Usage
- Agent builds a new parallel implementation that reintroduces an already-solved bug instead of discovering and using the existing working tool
- iPadOS app: selecting text in a long remote macOS session auto-scrolls to top and deselects
- [Bug] Ambiguous error message when request processing fails
- claude.exe exits with code 0, zero output on stdout/stderr, for any command
- [BUG] [platform::intellij] Regression of #10813: 'Slow operations are prohibited on EDT' in DiagnosticTools.openVirtualFileFromPath (macOS, plugin 0.1.14-beta)
- Feature request: Register Claude Code as a native agent provider in VS Code's Chat/Agents view
- [BUG] Claude proceeds with unrequested actions after milestone completion without confirmation
- [Bug][cyber] Safety block on AES/RC4 key analysis for unpacking a protected Android DEX binary (req_011CcWUjkz41RRupNdBuycUZ)
- [Bug][cyber] H.264 decoder debug blocked while inspecting CABAC corruption and unknown NAL types (req_011CcWya3V5wtjqdrbgxJhpd)
- [BUG] Claude Code doesn't work with `NODE_OPTIONS=--use-system-ca`
- [BUG] Title: Sessions not syncing across computers (Pro account)
- [Bug] Anthropic API Error: Usage credits required for 1M context with 1M context disabled
- [FEATURE] Feature: API/CLI to programmatically open new Claude Code conversation sessions in VS Code
- [FEATURE] VSCode extension: distinct per-tab color to tell Claude Code sessions apart
- [BUG] /context undercounts the active --agent persona + agent-memory injected into system (breakdown identical to a bare session)
- [BUG] Write post-write verification false-positives on WSL2 / local ext4 — bogus "bytes on disk" (== len(path)+96, or 0) and false "silently truncated" for files that are correct
- [FEATURE] Complex bash commands in the approval prompt render as a wall of mangled text
- [BUG] Conversation history shows "now" for old conversations, breaking sort order in VS Code extension
- [FEATURE] Claude Desktop should offer to re-auth with MCP if auth has expired
- [BUG] API Error 400 "no low surrogate in string" when Bash output contains invalid Unicode
- [MODEL] Claude gave incorrect information that caused financial loss
- [BUG] claude-opus-4-8 fabricates user messages inside thinking blocks and replies to them (~26 min self-conversation; session restart does not help, only model rollback does)
- Disable references to Orwell ( animal farm ) and Brave New World
- [BUG] Tool call / agent card renders above its own introduction text — message order reversed in TUI
- [FEATURE] Let users default the Agent tool's run_in_background to true (and/or flip the default), so dispatching a subagent doesn't silently block the parent session
- [Bug] Anthropic API Error: Server Rate Limiting During Normal Usage
- [BUG] prose from Opus/Fable has gotten pretty much inscrutable
- [Bug] Anthropic API Error: Server rate limiting temporary request throttling
- [Bug] Anthropic API Error: Server temporarily rate limiting requests
- [Bug] Anthropic API Error: Server Rate Limiting - Temporary Request Limit
- [Feature Request] Make AskUserQuestion timeout configurable
- You've hit your session limit · resets 2:50pm (Asia/Seoul)
- [Bug] Claude Fable 5 model reverts to Claude 3 Opus due to overly broad safeguard filtering
- [Bug] Anthropic API Error: Account flagged by safeguards, CVP review pending
- I don't see a bug report or issue description in your message. Could you please provide details about the problem you're experiencing with Claude Code so I can generate an appropriate GitHub issue title? If you're reporting a bug, please include: - What y
- MCP server "supabase" sendo removido/adicionado repetidamente com comando malformado (openssl rand -hex 32 não interpolado)
- ECONNRESET / misleading error when reloading a renamed session (bridge "Epoch mismatch (409)")
- Hook timeout does not reclaim a hook blocked in a read syscall — SIGTERM ignored, process survives indefinitely
- [Bug] Safety classifier false-positives on routine code review, forces model downgrade mid-session
- I don't have a bug report to analyze. Could you please provide the actual bug report or error details you'd like me to create a GitHub issue title for?
- [Bug] Anthropic API Error: Server temporarily limiting requests (rate limited)
- [BUG] Interactive session refuses to prompt for trust for projects with settings.json saying the session is not interactive
- [BUG] Newer emoji U+1FAEA ( "DISTORTED FACE", Unicode 17.0) corrupts TUI render — cell-width mismatch, column misalignment & stray-glyph artifacts
- I don't have enough information to generate a GitHub issue title. Could you please provide details about the specific bug or problem you encountered? For example: - What error message did you receive? - What were you trying to do when the issue occurred?
- [Bug] Anthropic API Error: Server Rate Limiting During Normal Usage
- [BUG] 2.1.224 strips TMUX_PANE from hook environment (regression from 2.1.223) — tmux-integrated hooks silently no-op
- [BUG] fail to invoke tool call
- [Bug] Anthropic API Error: Server rate limiting on requests
- Unclear guidance on artifact sharing 'editor' permission vs. actual edit capability
- [Bug] Anthropic API Error: Server Rate Limiting During Normal Usage
- [Bug] Anthropic API Error: Server Rate Limiting on Valid Requests
- I need more information to generate an appropriate GitHub issue title. Could you please provide the bug report or issue description?
- [Bug] Anthropic API Error: Server request rate limiting
- [BUG] Orphaned background Bash tasks spawned by a subagent keep running after 3 manual stops + refresh
- [BUG] Are these model capable enough to create technology knowledge base?
- Session naming UX improvements — reliable auto-naming & clean prompt
- [DOCS] `--input-format` help text incorrectly says it "only works with --print"
- [BUG] CLaude desktop just completely uninstalled itself from my windows PC?? And all my work is lost!
- [BUG] Multiple Claude Desktop actions (deleting active chat, opening Preferences) freeze the entire macOS system
- Feature request: viewer comments on published artifacts (Docs-style anchored feedback)
- [BUG] Account suspended immediately after following Support instruction to resubscribe — auto-appeal system prevents manual review
- [FEATURE] Automatic, on-demand context compression for long conversations ("Smart Summarization")
- [BUG] Failed to decode JSON: JSON message exceeded maximum buffer size of 1048576 bytes...
- [Feature Request] Display message queue count in Claude Code CLI
- [Bug] OTEL Export functionality disabled or non-functional
- Drive MCP: create_file creates duplicates, no update_file available
- [BUG] Windows: incomplete Claude Code update leaves two versioned runtime folders under `%APPDATA%\Claude\claude-code\`, causing a deterministic Bun segfault at Code startup (every session)
- [Bug] GitHub API requests blocked by proxy egress policy with HTTP 502 in scheduled routines
- [FEATURE] Alphabetical sorting of SSH remote hosts in the host picker
- [BUG] form-mode MCP elicitation auto-declines in interactive TUI — server-initiated form is treated as "print mode"
- Claude Code lowers the reasoning effort level mid-session without consent
- French sessions: activity status line produces French/English hybrid words (e.g. "Inventaired")
- Pattern + proposal: adversarial self-review via a fresh sub-agent to counter author-blindness (a concrete fix for #32301)
- [Bug] Claude making assumptions without grounding in facts or requesting clarification
- [BUG] bun install fails with 503 on private GitHub Packages (sandbox proxy rejects redirect with Authorization header)
- [BUG] Unauthorized Max 5x→20x upgrade + €491 auto-recharge charges in one day
- Feature Request: Internationalization (i18n) support for Claude Code UI
- [Feature] Configurable Shift+Tab permission-mode cycle (order + subset)
- [Bug] Linux UI copy functionality is flaky and unreliable
- [Bug] Anthropic API Error: Request Timed Out
- [FEATURE] Expose a way to set the session/tab title in the VSCode extension (ungate /rename or add a command)
- [BUG] Write tool still corrupts CJK UTF-8 to U+FFFD on v2.1.195 (Windows)
- [BUG] Mouse/focus escape sequences dump into input on window resize (WSL2, v2.1.195)
- [BUG] Cowork macOS: all claude.ai-hosted MCP connectors fail — desktop OAuth token requested without `user:mcp_servers` scope
- [FEATURE] Forward MCP EmbeddedResource blob to Anthropic API content blocks
- [BUG] Session history button in Claude Code VSCode extension wipes current active chat
- [BUG] 2026-06-29 14:52:24.517 [info] From claude: 2026-06-29T09:22:24.518Z [DEBUG] Broken symlink or missing file encountered for settings.json at path: C:\Program Files\ClaudeCode\managed-settings.json
- [BUG]
- headersHelper in plugin .mcp.json still ignores ${CLAUDE_PLUGIN_ROOT} (repro on 2.1.181/2.1.187; root cause + fingerprint)
- [Feature Request] Add `disabledSlashCommands` setting to selectively suppress built-in slash commands
- [FEATURE] esc key to exit code edition preview window - vscode addin
- spawn ENAMETOOLONG in Cowork on all chats (new, existing, empty) - Windows 10 Build 26100
- [BUG] "Failed to save changes" error when enabling unrestricted git push permission
- Ultraplan web handoff is delta-blind to local uncommitted edits
- connect issue
- [BUG] Claude Code long-running session invents tool results, fake user turns, and follow-up actions without user input
- [BUG] GitHub "Issue opened" trigger does not fire when the issue is created by a Claude routine (self-trigger)
- [Feature Request] Add command to close active fork session
- [BUG] Sonnet 4.6 1m missing from Max plan
- [BUG] cmd+delete and option+delete no longer work in chat input (regression)
- [Bug] Claude Code LLM functions perform below expected capability level despite adequate context provided
- [BUG] typescript-lsp pushes stale diagnostics on 2.1.158 (post-#17979) in TS project-references/composite workspaces
- [Bug] Claude makes unfounded claims without analyzing context or user constraints
- When using cmd+option and arrows to navigate between tabs it doesn't follow the normal order, and jumps between them with no real reason that I can identify.
- [BUG] Claude Code Plugin Directory Submission Link Redirects to Documentation URL and Returns 403 Forbidden
- [Bug][cyber] Safety block halted H.264 NAL-unit forensics: diagnosing CABAC corruption from suspicious NAL typ (req_011CcWyQ9hrc9xzACDwmp8mY)
- [BUG] Telegram plugin auto-loads in all Claude Code sessions, not just --channels sessions
- [Bug] Text unexpectedly converted to Korean without user action
- [BUG] Context compaction erases .claude/project-context.md instructions
- [Feature Request] Auto-update capability for Claude Code CLI
- [Bug][cyber] Refactoring stdlib Python modules into a FOSS SDK package and wiring container PYTHONPATH wrongly (req_011CcXwXRJge32P93SCFJfau)
- [Bug][cyber] Wrongly blocked moving stdlib core modules into a FOSS Python SDK package and wiring container im (req_011CcXx4QDZwTyZLrwPi4jSz)
- [Bug][cyber] Safety filter blocks legitimate cybersecurity topic assistance in Claude Code session (req_011CcY1kqamR8G6sW1fDj6zF)
- [Bug][cyber] Safety block halted reverse-engineering USB AOA accessory framing for a drone controller app (req_011CcXzbthv6diNEz89koBkH)
- Python file I/O snippets should always include encoding='utf-8' to prevent silent data corruption on Windows (follow-up to #62828)
- [Bug][cyber] False-positive safeguard block stops legitimate cybersecurity assistance mid-session (req_011CcY1kC1p5G4SvH8vm5s6P)
- MCP collision check suppresses claude.ai connectors that point to a different workspace than the same-named plugin — no scriptable workaround
- Feature request: expose timestamps to Claude as structured data for time-aware reasoning
- [Bug][cyber] Safety block interrupts legitimate security vulnerability analysis workflow (req_011CcY1o5TFLzNFaV7gPUFGo)
- [BUG] Working directory resets between tool calls
- [Bug] /ultrareview charges for failed runs despite incomplete execution
- [Bug] Terminal focus-in event consumed as prompt denial in permission dialog
- GUI app: "thinking" indicator (✳) animation can freeze while the session is still actively working
- [BUG] Recent VSC extension update seems to have Claude hanging up occasionally.
- [BUG] Claude Code VS Code extension — main-thread saturation, UI freezes, and memory growth during extended thinking
- Add a setting to hide the usage-limit warning banner in the chat UI
- [Bug][cyber] Debugging an H.264 video capture/extraction pipeline against known-good decoder output blocked (req_011CcY9KbFHf4xez9uNGQyAH)
- Malformed tool-call generation: stray `court` token + non-namespaced <invoke> rejected by parser
- [Bug][cyber] ClAudit false-positive in android — req_011CcYJd2P9uUiFo9rWWG8VM
- [Bug][cyber] Cyber filter blocked building a drone flight UI with live video feed and telemetry HUD (req_011CcYJWT9EjGMeSaqybt7TC)
- claude-in-chrome extension not connecting despite correct install/login/enabled state
- My most recent PROJECTS are missing
- [Bug] Anthropic API Error: Server rate limiting rejection
- [DOCS] Repository name and README title don't distinguish Claude Code CLI from broader Claude Code branding (suggest renaming to claude-code-cli)
- [Bug] Anthropic API Error: Server Rate Limiting (Temporary Request Limit)
- [BUG] Authentication Service Down Globally
- [BUG] DISABLE 60s question auto-resolving??
- [Bug] Anthropic API Error: Server rate limiting
- GitHub repos not visible in Claude Code web repo picker despite GitHub App installed with full access
- [Bug] Anthropic API Error: Server rate limiting requests
- [DOCS] MISSING VAG NUMBER
- [Bug] Anthropic API Error: Server rate limiting during request processing
- [DOCS] Hook reference omits the PowerShell tool's tool_input schema, so a PreToolUse PowerShell hook fails open on a guessed field name
- [Bug] Anthropic API Error: Server rate limiting during request
- [DOCS] State whether project-scope hooks are workspace-trust-gated, and what happens to that gate under `--print`
- [Bug] Anthropic API Error: Server rate limiting exceeded
- [BUG] -p/--print: stdio MCP servers stay "pending" — tool snapshot races server startup and never refreshes (regression 2.1.143 → 2.1.162)
- [Bug] Anthropic API Error: Server rate limiting during request processing
- [Bug] Anthropic API Error: Server Rate Limiting - Temporary Request Limit
- Repo not appearing in repo picker despite GitHub App installed and reconnected
- [Bug][cyber] Safeguard blocked routine strings/pattern analysis of a self-captured mobile app memory dump (req_011CcnXGX2KkGqEv89H61eRm)
- [Bug][cyber] Safety filter blocked routine dev work on drone RSA auth plugin after model switch (req_011CcnWhgbceAtzYUrYPwG71)
- [Bug][cyber] Safeguard blocked routine "finish the task" continuation with no cyber content (req_011CcnRnv4YvFFpaz45AjrWk)
- [Bug][cyber] False-positive block on legitimate DJI drone auth-protocol interop work using device's own extrac (req_011CcnReWU19UF1bg7REcCRy)
- [DOCS] Broken pricing link
- [Bug][cyber] Safeguard blocked routine review of RSA key material and cert details extracted from a memory dum (req_011CcnJ2yHjMz3YQrqvLefKo)
- [Bug][cyber] Safety block halted memory-scanning/debugger daemon dev (watchpoints, regs, ptrscan) mid-session (req_011CcnEyPP6tXT94pTyfKrpt)
- [Bug] Skills unable to read their own bundled files without permissions
- [Bug][cyber] Safety filter blocked README update mid-session over debugger watchpoint script output in scrollb (req_011CcnFFi6C7cW65SFu9WLSb)
- Clarification needed: Are Opus and Sonnet limits independent or shared after Nov 24 update?
- [Bug] Anthropic API Error: Server rate limiting during request execution
- [Bug] Anthropic API Error: Server rate limiting during request handling
- image paste in ssh/sftop
- [Bug] Anthropic API Error: Server temporarily limiting requests
- [DOCS] Undocumented `ccd_*` MCP servers: session-to-session messaging and `list_sessions` scope
- [Bug] Anthropic API Error: Server rate limiting during request processing
- [Bug] Anthropic API Error: Server Rate Limiting - Temporary Request Throttling
- [Bug] Overly broad Fable 5 safeguards blocking routine coding tasks
- [BUG] Interactive session inheriting CLAUDECODE/CLAUDE_CODE_* env vars silently skips ALL persistence (no JSONL, no history, no session registration)
- [Bug] Incorrect categorization of code auditing as cybersecurity activity
- [Bug] Fable 5 codebase auditing incorrectly flagged as cybersecurity activity
- [Bug] Incorrect Cybersecurity Classification for Code Auditing Tasks
- [Bug] Fable 5 codebase audit incorrectly flagged as cybersecurity activity
- [Bug] False positive: Codebase audit flagged as cybersecurity activity
- [DOCS] System prompt lists Opus 4.7 for fast mode; the 2.1.219 changelog says it was removed
- [Bug] Tool misclassification: Code auditing flagged as cybersecurity activity
- [Bug] Anthropic API Error: Incorrect Cybersecurity Classification on Code Audit Requests
- [BUG] TUI renderer + stdin die mid-session while the engine keeps running (macOS, 2.1.207) — idle CPU, no SIGWINCH redraw, transcript still being written
- [Bug] Anthropic API Error: Server Rate Limiting
- [DOCS] Skills and plugin docs omit accepted string values for frontmatter booleans
- [Bug] Anthropic API Error: Server rate limiting during normal usage
- [DOCS] Skills docs omit that `context: fork` runs in the background by default
- [Bug] Fable 5 codebase audit incorrectly flagged as cybersecurity activity
- [BUG] doctor is behaving oddly - no longer instant
- [DOCS] Subagent docs omit the colon restriction for local agent names
- [Bug] Fable 5 audit tools incorrectly flagged as cybersecurity activity
- [DOCS] Fast-mode docs omit the announcement when model switching changes fast mode
- [Bug] Incorrect security classification of legitimate code auditing
- [DOCS] Workflow docs do not state that `/deep-research` requires explicit invocation
- [BUG] OAuth login succeeds but token is never persisted — doctor reports "macOS Keychain is not writable" while keychain writes work fine from terminal (native 2.1.205, darwin-arm64)
- [DOCS] Plan-mode docs still say non-read-only Bash always prompts when auto mode is active
- [Bug] Anthropic API Error: Overly broad safety filter blocking legitimate coding tasks
- [BUG] Task management tools silently unavailable on Opus 4.8 / Sonnet 5 / Fable 5 (tengu_vellum_ash model gate)
- [DOCS] Subagent docs omit the workspace-trust requirement for agent frontmatter hooks
- [Bug] Anthropic API Error: Server rate limiting on requests
- [DOCS] Code Review docs do not state that `ultra` uses cloud review in non-interactive sessions
- [Bug] Anthropic API Error: Server Rate Limiting - Request Throttling
- [DOCS] Ultrareview docs do not explain descriptive arguments as review notes
- [Bug] Anthropic API Error: Server rate limiting during request processing
- [DOCS] MCP configuration docs omit the warning for hidden leading or trailing whitespace
- claude plugin uninstall <name>@<marketplace> can uninstall the same-named plugin from a different marketplace
- [DOCS] Agent view docs omit the left-arrow edit confirmation and return-to-conversation behavior
- Formal complaint — Claude repeatedly failed to comply with explicit “No” and “Do not run” instructions. No means NO.
- [BUG] /code-review skill is now being automatically loaded in sub-agents the code-review skill spawns. Causing it to keep recursively making more agents
- [DOCS] `/code-review` documentation omits its new background-subagent behavior
- [Bug] Advisor tool fails with "unavailable" error when using Fable 5 model
- [DOCS] Remote Control docs omit pending permission prompts for viewers joining mid-session
- [Bug] Anthropic API Error: Server Rate Limiting - Temporary Request Limit
- [DOCS] Nested-subagent docs still describe a fixed depth and omit the default-disabled behavior
- [Bug] Anthropic API Error: Server Rate Limiting (Temporary Request Limit)
- [DOCS] Subagent documentation omits the concurrent-running subagent cap
- [Bug] Anthropic API Error: Server rate limiting during request handling
- [DOCS] Agent view docs omit footer PR-badge hyperlink behavior and the `FORCE_HYPERLINK=0` opt-out
- [BUG] Claude code git hub connection error
- [DOCS] OpenTelemetry docs omit managed-endpoint precedence over signal-specific overrides
- [Bug] Fable 5 safeguards persistently escalate a benign health-corpus + security-governance project to Opus
- Photo attachment sent as first message to a stale/long-running session silently fails to arrive
- [DOCS] Session documentation omits warnings for failed transcript writes and disabled persistence
- [Bug] Advisor model unavailable when using Fable 5 with Opus 4.8
- [DOCS] Prompt input documentation omits emoji shortcode autocomplete and `emojiCompletionEnabled`
- `claude plugin uninstall <name>@<marketplace>` ignores the marketplace qualifier and can uninstall the wrong same-named plugin
- Workflow tool: args passed as a JSON array reaches the script as a JSON-encoded string
- [DOCS] Sandbox settings reference omits `sandbox.filesystem.disabled`
- [Bug] Setup documentation unclear and confusing
- auto-mode classifier denies calls covered by permissions.allow; reads conversation context; covers Bash but not MCP tools
- I don't have any bug report content to analyze. Please provide the bug report or error details you'd like me to create a GitHub issue title for, and I'll generate an appropriate technical issue title following the guidelines you've outlined.
- Docs mismatch: permission mode UI in Desktop app doesn't match documented 'mode selector next to send button'
- claude-in-chrome file_upload broken on latest CLI+extension: rejects host paths, no files param; upload_image can't retrieve image
- [BUG]
- Named background subagents persist in FleetView after completion; no dismiss affordance + inconsistent shutdown_request reaping
- Windows: Chrome extension native host crashes on startup (TypeError ERR_INVALID_ARG_TYPE, Bun net.listen on named pipe)
- Rewind/edit kills ALL background tasks; should only kill tasks spawned after the rewind point
- I understand you're frustrated. However, I'm not able to generate a GitHub issue title from this message because it doesn't contain specific technical details about a bug or feature request. To help you effectively, please provide: 1. What specific error
- [BUG] no repos match
- [Bug] Advisor unavailable error
- I can help you investigate the Cloudflare WAF-flagged logs using the Cloudflare MCP integration. To do this effectively, let me clarify a few things: **What I need to know:** 1. **Is the Cloudflare MCP server already connected?** Run `/mcp` to check curr
- [Bug] Anthropic API Error: Fable model safeguards incorrectly flagging legitimate security analysis code
- [Bug] Anthropic API Error: Usage Credits Configuration Misinterpreted as Cybersecurity
- Hooks docs: four payload field divergences vs shipped behavior (2.1.207, captured)
- [DOCS] Fullscreen docs use an outdated tmux 3.4 synchronized-output threshold
- [BUG] Repo picker shows "No repos match" despite GitHub App installed on Desktop
- Credit balance is too low
- [Bug] Fable integration fails with security/audit use case
- misanthropical ai :D
- [BUG] JetBrains plugin writes WSL-style path (/mnt/<drive>/...) to ~/.claude/ide/*.lock on native Windows, breaking /ide
- [DOCS] `/upgrade` command reference still describes the pre-v2.1.208 login fallback
- [BUG] Dispatch stuck on "Asleep" / "Can't reach your desktop" on iOS — desktop awake, app open, all local troubleshooting exhausted (macOS, Pro plan)
- [DOCS] WorktreeCreate hook stdin field is `name`, not the documented `worktree_path`
- [Bug] Anthropic API Error: Server rate limiting on valid requests
- [DOCS] Routines docs refer to "Permissions" tab and settings that don't exist
- [Bug] Anthropic API Error: Server Rate Limiting (Temporary Request Limit)
- I appreciate you reaching out, but I need to clarify: I'm designed to help generate GitHub issue titles for Claude Code (Anthropic's CLI tool), not to assist with Fable 5 applications or energy materials startup reviews. If you have a **bug or feature req
- [Bug] Anthropic API Error: Server temporarily limiting requests during rate limit
- I appreciate you reaching out, but I need to clarify that Claude Code is a CLI tool for software development tasks with the Anthropic API, not a tool for ROM modifications or device repairs. If you have a technical issue with Claude Code itself, please de
- [Bug] Unexpected model downgrade from Fable 5 to Opus without user consent
- I don't see a bug report in your message. To generate a GitHub issue title, I need you to provide: 1. A description of the problem you're experiencing with Claude Code 2. Error messages (if applicable) 3. Steps to reproduce the issue 4. Expected vs. actua
- [BUG]
- [BUG] 2.1.216 sandbox regression: "bwrap: Can't mkdir /opt/.claude" — ancestor-walk denyWrite mountpoints fail-closed on non-root installs under root-owned dirs
- Docs: session_name in statusline JSON silently falls back to auto-generated AI title, contradicting documented behavior
- [Bug] Anthropic API Error: 529 Overloaded - Excessive Retry Attempts
- [Bug] False positive safety warnings with Fable 5 model
- Injected "date has changed... don't mention it" system-reminder appears mid-session, unattributable to any local file/hook
- [Bug] Anthropic API Error: Server rate limiting during request handling
- [BUG] No repositories found in Claude Code mobile repo picker
- [DOCS] Plugin `user_config` documentation still advertises unsafe shell-form interpolation
- [BUG] --remote-control intermittently fails: createCodeSession 401s on attempts 1–2 every launch, only 3 retries, so occasional total failure
- [DOCS] Auto mode availability and configuration scope are outdated for third-party providers
- Remote Control: bridge init gives up permanently after 3 retries in ~2s — transient 401 from code-sessions API leaves session running but invisible on claude.ai/code
- [BUG] Remote Control: POST /bridge returns 401 with fresh full-scope token while createCodeSession and archive succeed (v2.1.212)
- [DOCS] Agent view docs incorrectly require two Ctrl+X presses to remove completed sessions
- I appreciate you reaching out, but I need clarification. Your message appears to be in French and states you're not involved in a cybersecurity project, which doesn't seem to be a bug report for Claude Code. To help you create a GitHub issue, please provi
- [DOCS] Agent view row summaries still documented as truncated at 64 columns
- I appreciate you reaching out, but I need clarification. Your message appears to be in French and states you're not involved in a cybersecurity project, which doesn't seem to be a bug report for Claude Code. To help you create a GitHub issue, please provi
- Observation: agent spontaneously adopted a self-identifier (emergent behavior, not a bug)
- [Bug] Anthropic API Safety Filter False Positive: Legitimate Security Scan Blocked (req_011Cd8eL243WHNAssF3X16Zy)
- HTTP MCP server with Bearer header fails to connect — same OAuth-discovery pattern as #46640
- I appreciate you reaching out, but I need to clarify my role. I'm designed to generate GitHub issue titles for Claude Code bug reports in English. Your message is in Thai and asks about safety/compatibility with a machine, which isn't a bug report for Cla
- [Bug] Anthropic API Error: Overly aggressive cybersecurity safeguard flagging benign development tasks
- [BUG] I have an older Mac machine (macOS 10.15.8), I want to use your claude code to run something , can you help me to fix it ?
- [Bug] Anthropic API Error: Overly broad cybersecurity content filter blocking legitimate local testing
- MCP tool call hangs indefinitely (no permission prompt) for stdio server calling npx-based MCP package
- [Bug] Rate limiting or quota restrictions preventing Claude Code usage
- [FEATURE]
- [DOCS] [Agent view] Row format and peek panel content updated in v2.1.205: colored state word + classifier-written headline replace raw tool call text, and the peek opens with full status including the exact ask for blocked sessions
- [Bug] Anthropic API Error: Rate limiting - server temporarily limiting requests
- [DOCS] Agent view "Pull request status" only describes sessions opening a PR; v2.1.205 also links existing PRs that a session edits, merges, comments on, or pushes to
- Browser extension shows "not connected" even after reinstall + full Chrome restart
- [DOCS] Auto mode classifier rule that blocks tampering with session transcript files is not documented (v2.1.205)
- [Bug] Bug Report: Unclear or missing trigger description provided
- Agent reports work "done / verified / live" with no evidence — across a whole multi-agent setup. Is there a supported way to gate completion on proof? (+ the bigger question this raises)
- Claude Opus 4.6 generates false justifications to defend its own incorrect output
- [Bug] Anthropic API Error: Excessive cybersecurity content flagging on local code analysis
- [DOCS] [Setup page] still describes the npm-install "one-time notice at startup" that v2.1.203 relocates to `/doctor` and `/status`
- [BUG] Session permanently dead-locks with "400 Tool reference 'TaskCreate' not found" — agent-teams dynamic tools captured in a tool_search_tool_result snapshot
- [DOCS] `claude agents` background sessions now pick up `effortLevel` changes from `settings.json` when forked by the daemon, but the persistence prose and Version history in agent-view still describe the old "effort from dispatch is locked" behavior
- [BUG] Claude Desktop (Windows): Navigation buttons overlap with OS window controls in Hebrew (RTL) display language
- [DOCS] `TaskStop` and `TaskOutput` documentation does not mention cross-agent lookup or that lookup errors now list running agents by id and description (fixed in v2.1.203)
- [Bug] Unclear or Missing Trigger Explanation for Claude Code Actions
- [DOCS] Agent view `The supervisor process` section omits that v2.1.203 makes background agents inherit `PATH` from the dispatching shell rather than the daemon's launch environment
- Please review and publish pending plugin submission "hypermnesia-mcp" (predecessors stuck by confirmed name-collision bug)
- [Bug] Anthropic API Error: Safety flag on legitimate cybersecurity operations
- [DOCS] Changelog delay on 2.1.202?
- I need more information to generate a GitHub issue title. Could you please provide: 1. What specific problem or error are you encountering? 2. What are you trying to do with Claude Code? 3. What error message or behavior are you seeing? 4. What security c
- [Bug] Ctrl+S stash prompt keybinding missing from interactive-mode documentation
- [Bug] Anthropic API Error: Safety Filter Blocking Legitimate Debugging Tasks
- I appreciate you reaching out, but I need to clarify: I'm Claude, an AI assistant made by Anthropic. I'm not Claude Code (the CLI tool mentioned in the system prompt), and I don't have the ability to: - Manage your access to Fable 5 or any other tools - C
- SECURITY: Assistant Violated Destructive Operations Guidelines - No Confirmation Asked