Digest / July 21, 2026
Claude Code Issues Digest — July 21, 2026
349 new issues filed ·
164 resolved in anthropics/claude-code (UTC day).
New issues (349)
- [BUG] 2.1.216 sandbox regression: default `--cap-drop ALL` breaks all Bash on root installs (apply-seccomp: write /proc/self/uid_map: Operation not permitted)
- Feedback: don't replace download buttons with share buttons
- Assistant emitted a fabricated <system_warning> block instructing a RemoteTrigger "session_handoff" (self-generated fake system notice)
- Mid-turn user messages intermittently lost during long-running turns with background tasks
- Headless claude -p hangs indefinitely before first response — CLOSED sockets held, no timeout/retry, zero output even with --debug
- [BUG]
- Inconsistency: parent-dir trust skips the trust dialog but not the .mcp.json approval gate
- Request ID: req_011CdEKJXjzJhbzQUvrbzW3A This is a internal...
- [Bug] Request ID: req_011CdEL2bqUEfC7zM4Lujhwi - Internal Security Engine Error
- [Bug] Unable to interrupt running jobs with kill signals, continues consuming API tokens
- [BUG] PostToolUse hook additionalContext (memo_reminder.sh) not reaching Claude in VSCode extension
- Per-type, presence-aware notification control in settings (silence 'idle' without losing focus-gating on the rest)
- [BUG] 7 days of Cowork chat history permanently lost when auto-renewal failed (Windows, self-updated build now in MSIX container)
- Exit code 132 (Illegal instruction) on Intel iMac 2011
- [BUG] Background general-purpose sub-agents can't resolve MCP tools via ToolSearch even with exact tool names (parent session unaffected)
- [DOCS] Sandbox settings reference omits `sandbox.filesystem.disabled`
- [FEATURE] Device/Environment metadata in context
- [FEATURE] More Projects on the Free plan
- I appreciate you reaching out, but I need to clarify my role: I'm Claude, an AI assistant made by Anthropic. I'm not actually "Claude Code" and I don't have special handling for security-related content. If you have a legitimate bug report or feature requ
- [Bug] Anthropic API Error: Request ID req_011CdEPfewNtp6XHSroVmGBF
- [BUG] Shell tool doesn't refresh PATH environment variable mid-session
- I don't have enough information to generate a GitHub issue title from your message. Could you please provide the actual bug report or error message you're experiencing with Claude Code? Please include: - What you were trying to do - What happened instead
- [FEATURE] Add eye-friendly light background presets to the desktop app (accessibility request)
- [Bug] Monthly spend limit incorrectly enforced on new subscription account
- [Bug] Safety classifier blocks a workflow's own receipt-persistence agent as "self-approval / CI bypass" — regardless of receipt content, and even for the fail-closed marker
- [Bug] Claude Code unrelated to CCTV/smart-nvr project scope
- Claude Code ignores explicit CLAUDE.md verification directives, ships untested multi-layer changes
- Claude in Chrome: Status stays "Disabled" with zero connection-attempt logs, despite fully clean setup (was working as recently as June 30)
- claude-fable-5: user-facing text before tool_use silently dropped (empty signature-only thinking block instead); model then falsely reports the text as delivered
- [BUG] `claude mcp add` passthrough arg parser breaks on bare -p flag in subcommand args
- In-process filesystem sandbox restriction applied mid-session to running headless sessions; irreversible without process restart; account-scoped synchronized onset
- [Bug] Excessive token consumption on web search operations
- Fable 5: false denial to direct user question after stop interrupts during detached-subagent run (user-directed report of verbatim admission)
- Preview server opens twice — Browser pane + external browser window
- Native system-reminders (Auto Mode / date rollover) rendered inside subagent Bash tool results are repeatedly flagged as prompt injection by agents (v2.1.202)
- MCP stdio reconnect spawns literal unexpanded ${HOME} in command → ENOENT, server lost for the session (still on 2.1.215; prior reports stale-closed)
- [FEATURE] Hook event when a permission request is resolved (PermissionResult)
- System-prompt env block misreports the model: says Opus 4.8 while /status shows claude-fable-5
- plugin:github:github MCP server fails with HTTP 400 "missing required Authorization header"
- [BUG] Skill frontmatter model: override applied on user-typed invocation but silently ignored when invoked via the Skill tool (registers in both cases)
- [FEATURE] Support Claude in Chrome on WSL (native Linux Chrome via WSLg works today)
- [BUG] Mid turn messages lost on 2.1.205
- I can see you've shared a screenshot reference, but I don't have access to view images. To help you create an accurate GitHub issue title, could you please describe: 1. What error or problem are you experiencing? 2. What were you trying to do when it happ
- [Bug] Fable 5 skipped EBA verification, answered pricing from priors instead of source
- [BUG] Dispatch no disponible en cuenta con plan Pro activo — posible problema de entitlement
- [Bug] Anthropic API Error: Incorrect cybersecurity safety flag on legitimate incident report review
- [BUG] Skill frontmatter model: override applied on user-typed invocation but silently ignored when invoked via the Skill tool (registers in both cases)
- Bug: `claude --resume` silently exits when resuming a Fable 5 session (false "requires usage credits")
- [Feature Request] Anthropic API Safety Filters Cause False Positives for Agent Harness Development
- [BUG] Skill frontmatter model: override ignored when Claude invokes the skill via the Skill tool (works when user types /skill-name)
- [Bug] Auto-compact "context running low" warning fires at ~177k tokens in 1M-context ([1m]) sessions
- [BUG] VS Code extension: session title in history sidebar re-generates mid-session and is overwritten by a recent short message
- [Bug] Anthropic API Error: Cyber Safeguard False Positive on Legitimate Fraud Detection Analysis
- [BUG] Workflow progress indicators (elapsed timer, token counter, current-tool) freeze during final structured-output generation — an active task looks hung
- [BUG] Assistant takes action instead of answering a direct clarifying question, mid-session
- [BUG] Existing Pro account not recognized - Google Sign-In, Email Login and Claude Code CLI all redirect to "Let's create your account"
- [Bug] CLI shows "use credits" prompt on an org-managed Team seat that actually has subscription entitlement (`hasAvailableSubscription` cached as false)
- You've hit your session limit · resets 7:20pm (Asia/Seoul)
- [Bug] Anthropic API Error: Safety Filter False Positive on Valid Message
- Repeated macOS 26 (Tahoe) "App Data" TCC prompts for standalone CLI binary
- [BUG] PreToolUse hook "if" permission-rule matcher fails open on Bash commands containing a `for` loop
- e[Bug] Session history not displayed in UI panel when VS Code workspace opened at drive root path
- Desktop app (Windows & macOS) shows "Medium" effort for all Code sessions; model name syncs but effort field does not
- I appreciate you sharing that context, but I need to clarify: I'm designed to generate GitHub issue titles specifically for Claude Code, Anthropic's CLI tool. Your message doesn't describe a bug or feature request related to Claude Code. Could you provide
- I am so very tired. 45% of Fable, 47% of total in one day implementing PM tools to stop the sprawl and keep this thing on task
- [BUG] SDK default mode: background Task Bash denied without canUseTool; parent Bash then stays dead (regression of #27203)
- [BUG] Cowork tab shows "yukonSilver not supported" on Windows 11 Pro — persists on latest version despite all prerequisites met
- [Bug] Security flag blocks legitimate bug reports after update
- [FEATURE] Dispatch should support AskUserQuestion button UI for better mobile UX
- [Bug] Non-cybersecurity session analysis not supported in bug reproduction workflow
- Headless `claude -p` fails "OAuth session expired and could not be refreshed" while concurrent interactive session works — no recovery path for unattended runners
- [BUG] [Desktop] CCD 2.1.209 regression: "Shell environment extraction" blocks main process for 25s on every app start (Linux)
- [Bug] Claude Code CLI unable to access Claude fable 5 despite valid subscription
- [BUG] VS Code extension exits with code 1 on first daily launch: org verification runs with expired OAuth token, no refresh attempt before fatal 401
- Routines UI shows multi-hour cron schedules in UTC without local timezone conversion
- JDT.LS still can't load Lombok javaagent / pass VM args — false LSP diagnostics (revisit of #47561)
- Native user-hosted persistent sessions, drivable from desktop + mobile without the tmux/Remote-Control ceremony
- [BUG] サイドバーのセッション一覧・グループ表示が崩れる（検索では正常にヒットする）
- Fable 5 safeguard model-switch pauses the session — add opt-in to auto-continue on the downgraded model (Opus 4.8)
- [Bug] Task/Todo registration not working in v2.1.216 despite valid local config and GrowthBook flags loaded
- Enter key inserts newline instead of submitting prompt (Windows desktop app, recurring)
- [Bug] Anthropic API Error: Unable to determine specific error
- Routines: refusal-as-"not user input" recurring after being marked fixed (regression of #78032)
- remoteControlAtStartup is ignored by the VS Code extension
- [Bug] Claude ignores file edit restrictions during plan mode despite global settings
- SessionEnd hooks do not fire on normal `claude -p` (print mode) exit
- OAuth login fails with "Invalid code. Please make sure the full code was copied" despite entering the correct code
- [Bug] Claude Code not accessible with MAX plan subscription
- [BUG] Cowork project "Scheduled" panel missing for project with valid, running scheduled task
- [FEATURE] Support terminal graphics protocols for inline image display
- No non-interactive way to trust a workspace: headless `claude -p` silently ignores provisioned .claude/settings.json permissions in unattended runner workdirs
- [Bug] API errors not hidden when cyber verification program enabled
- [Bug] Character encoding corruption in tmux terminal integration on Ubuntu 24 LTS
- [Bug] System virus interference with Claude Code CLI execution
- [BUG] MCP tool calls fail with -32003 after approval on mobile web
- [BUG] Preview MCP dev server killed silently after ~1h idle — regression in Claude Desktop 1.22209.3 (was fine on 1.21459.0)
- Harness mutates the user's checked-out repository at session spawn: bare `git checkout HEAD` detaches the working tree, and plumbing-style `refs/heads/main` updates fire under a live checkout
- [Feature Request] Add option to keep file tabs open after accepting edits
- [Bug] Insufficient logging/output clarity for agentic task execution
- [Bug] Excessive token consumption during code investigation tasks on Claude Opus
- [BUG] Cowork tab missing on macOS 1.22209.3 — runtime present and healthy, tab not rendered (server-side gating, not packaging)
- [BUG] Unrelated conversation content injected into assistant output (cross-context leakage?)
- [Bug] Claude prints incorrect result before self-correction in single response
- [FEATURE] Add Multilingual (i18n) Support for Slash Command Descriptions (/ 슬래시 커맨드의 자동완성 때 뜨는 설명문구를 다국어 지원하는 방향 제안)
- [FEATURE] Add eye-friendly light background presets to the desktop app (accessibility request)
- /fork <prompt> leaks the forked task into the parent session — the parent executes it too (risking duplicate side effects)
- Parallel simultaneous accounts
- [Feature Request] Add option to manage routines created by Claude Tag in a Slack channel
- [FEATURE] Clear oversized inputs of validation-failed tool calls from context — a failed Write's full content is dead weight
- [Bug] Opus 4.8 High reduced code review quality: not analyzing full PR scope for functional regressions
- [BUG] Memory-pressure reap kills only the tracked shell — child process tree survives as orphans and keeps running (Linux, 2.1.216); manual TaskStop correctly kills the tree
- Subagent explicit tools: allowlist silently collapses (drops ToolSearch + all MCP tools) when MCP server is unavailable at spawn
- Opened by mistake
- [Bug] Random flagging of normal code sessions as policy violations
- [MODEL] Same-session events described as "yesterday" — relative-time references fabricated from turn count, despite correct absolute date in system prompt
- Permission prompt: split "Yes, always" into project-scope vs user-scope (all projects)
- [Feature Request] Extend cybersecurity permissions to personal Anthropic account for authorized security work
- [FEATURE] Claude Desktop: opt-in setting to auto-approve write/modifying MCP tools per server
- [Bug] Agent auto-spawns multiple subagent forks consuming excessive quota
- [Bug] Security concern flagged during design work - requires investigation
- scheduled-tasks: task skipped as 'folder is not trusted' despite project already showing hasTrustDialogAccepted: true
- --bare breaks OAuth/subscription login in 2.1.216 (regression from 2.1.210)
- [Bug] Unintended model downgrade from FABLE 5 to Opus 4.8
- [BUG] stdio MCP server orphaned on /mcp reconnect after a .mcp.json edit - no kill, no stdin close, leaks until session exit
- [Bug] Remote control sessions dying with code 4090 worker supersession after 2026-07-17 update
- [Bug] Model unexpectedly downgraded from fable 5 til opus 4.8 for no legitimate reason
- [Desktop] WorktreePool runs `git checkout` in deregistered worktree directories — git walks up and mutates the parent repo (detaches HEAD / moves it onto session branches)
- [BUG] Interactive LSP client never sends didChange after Edit-tool writes — server buffers stay frozen at first-query content (headless `-p` syncs correctly)
- [BUG] All previous Cowork conversations are all gone on Windows 11, but Cowork is available
- Scheduled cloud routines / cowork (headless) expose only a partial MCP connector toolset
- [BUG] VS Code/Cursor extension: UI wedges after a settings.json config reconciliation; agent keeps running but /usage, Show Logs, and input become unresponsive
- Bug: `isolation: 'worktree'` renames worker branches and leaves the primary worktree checked out on a run branch
- [Bug] Session rate limit maxes instantly after upgrade to Max 20x tier
- [Bug] Auto-mode classifier inherits [1m] suffix, causing repeated permission check failures and session lockout
- [BUG] One-shot scheduled task with pending permission prompt vanishes from UI (prompt becomes unanswerable, task dies silently)
- [BUG] Pending permission/approval state not always rendered in session view ("waiting on nothing" — agent announces action, UI shows neither prompt nor progress)
- [BUG] ### Title Plugin MCP server tools intermittently never register in-session despite `claude mcp list` showing "Connected"
- [FEATURE] Re-enabling a daily scheduled task after its time-of-day has passed triggers an immediate catch-up run (surprising for cron-style expectations)
- Worktree provisioning overwrites git-tracked files with the primary checkout's copies
- [FEATURE] specificity-aware permission precedence (let a narrow allow override a broad deny)
- Background job (bg/fleet) session bookkeeping: dangling sessionId makes sessions appear vanished; spurious "source session not found" crash
- Session transcripts silently deleted: retention sweep has no warning/trash/log, leaves orphaned side-dirs; recent (3-9 day old) sessions also deleted
- [BUG] Permission model: let a specific allow override a broad deny (specificity-aware precedence)
- [BUG] VSCode extension: after extension host restart, restored chat tabs are not re-bound to sessions - messages silently dropped, infinite spinner, dead stop button (Windows)
- Safeguards false positive: benign firmware CI/CD message flagged, session force-switched Fable 5 → Opus 4.8
- Previous cowork sessions missing
- [Bug] Claude Code generates repetitive, incoherent output for C text generation
- Completed background subagents unresumable after background-session fork: "No transcript found for agent ID" (transcript exists in pre-fork session dir)
- You've hit your session limit · resets 5:10pm (Europe/Paris)
- [BUG] Fullscreen renderer prompt crashes Claude Code when running inside a Lima VM (SSH/tmux)
- [FEATURE] 請求支援繁體中文（Traditional Chinese）TUI 介面
- [Bug] Claude unable to generate simple 15-word list output
- [Bug] Anthropic API Error: Unspecified API Failure
- VSCode extension: focus rapidly jumps between Claude Code tabs on startup; new-tab icon opens session in wrong editor group
- Explicit ask rule for Bash command not respected — no permission prompt on default path (v2.1.216, macOS)
- Cloud routines: GitHub MCP comment posting injects U+00B7 middle dots into @mentions and command words, breaking Dependabot bot commands
- [BUG] Max 20x upgrade not reflected in weekly limits — depleting at Max 5x rate or worse (upgraded July 16, 2026)
- Skill auto-invocation loads massive unrelated reference doc on premium model, causing rapid unexplained cost spike + silent Fable to Sonnet fallback quality cliff
- [BUG] vscode no respond
- [BUG] Versionless official plugins (skill-creator, frontend-design) re-trigger "Plugins updated · Run /reload-plugins" banner on every marketplace refresh
- [Bug] Assistant incorrectly flagging benign content
- [BUG] list_sessions/search_session_transcripts MCP tools silently cap at 20 results, ignoring limit
- [FEATURE] Microsoft 365 connector: no tool for Microsoft To Do / Planner tasks
- [BUG] claude code desktop not connecting and says check internet connection - Windows OS , using latest claude release 1.22209.3
- [Bug] Tool execution and code generation capabilities incomplete
- [BUG] Scheduled task execution ignores UI-configured permission mode and model settings
- [Bug] Claude Code blocks security research queries despite program participation
- [BUG] MCP server fails to connect (no logs generated) — WordPress remote connector, Windows
- [BUG] WSL2: sandbox deny-mask mount points still leak 0-byte files into cwd on every Bash call (2.1.216; re-report of locked #26722)
- [BUG] model_consent_fallback silently cancels consent mid-session (no prompt shown), switching model without user action
- [BUG] Edit/MultiEdit fails with "String not found in file" only on manual confirmation (works with auto-accept) — VSCode extension, Windows
- [BUG] Cowork tab missing / not available on Windows 10 Pro despite all virtualization confirmed enabled (recurrence of #27316)
- Transient daemon silently resurrects killed sessions (bypassPermissions); background tasks die at spawn in sessions with disrupted state
- [Bug] Task cancellation interrupts long-running simulations unexpectedly
- Remote-control sessions (claude.ai/code) lost native Task tools on 2026-07-21; local CLI sessions unaffected
- [Bug] Overscoped cybersecurity content filtering blocking legitimate requests
- [Bug] Auto-Compact consumes excessive session usage quota
- Worktree project badge always shows main worktree's name (e.g. "core") for linked worktrees
- exectuion almost 0%- all tasks done by chat gt and pasted and even then clode fucked up
- [Feature Request] Enable direct in-chat editing of partial file outputs without requiring external editor
- Docs: clarify supported file types and directory handling in the desktop File pane
- [BUG] alwaysThinkingEnabled not translated to thinking:{type:"adaptive"} on Opus 4.8 — sessions silently run without thinking; 400 on xhigh effort with WebSearch
- [Bug] Claude Code downgrade from Fable 5 to Opus 4.8 causing degraded response quality
- [FEATURE] Desktop app: allow moving a Code session into a Claude Project
- [BUG] remote-control mode SIGTERMs its own background Bash tasks ~30-90s after launch (sender confirmed via siginfo)
- [BUG] Dispatch agent registration never completes server-side — reproduced on second machine with fresh install, all local state eliminated (Windows)
- [BUG] Cowork not appear in windows app
- New chat sessions without an explicitly selected project can default the working directory to the entire user home folder (unscoped, expensive tool reads)
- [BUG] ANTHROPIC_MODEL locks the session model after 2.1.216 — /model cannot override
- [BUG] /ide fails when cwd is a subdirectory of the workspace folder — CLI aborts after successful connect (2.1.216, re-report of #14832)
- [Bug] Anthropic API: Safeguards triggering false positives and downgrading model to Opus 4.8
- Cannot log in to Claude Code: verification emails suppressed for my address, support bot has no escalation path
- [Feature Request] Expose bindable actions for permission-dialog options and remap digit quick-selects
- [BUG] Custom sidebar groups disappear after switching Claude accounts and back (desktop app)
- [BUG] Plan mode's read-only guarantee is not enforced for subagents dispatched via the Agent tool
- [BUG] Mid-turn user messages delivered into a live subagent's turn instead of the parent session
- CLAUDE_CODE_SUBPROCESS_ENV_SCRUB=1 silently disables auto mode at session start (no cause shown in interactive/Desktop; mid-session toggle bypasses it) — 2.1.216
- [BUG] run_in_background=true Task agents never deliver report; foreground identical task succeeds (same session A/B)
- Extreme memory leak, Claude Code, 2,108,208 MB/hour
- [BUG] Cannot log in to Claude code nor VSCode extension
- Opus 4.8 output degenerates into unbounded single-token repetition ("court" loop), burning usage credits
- Show & tell: teaching Claude Code to auto-document its own work (self-hosted Plane + a tiny knowledge system)
- [Bug] Anthropic API Error: Overly aggressive safety filter blocking legitimate code
- [Bug] Auto-generated session titles overwrite user-set names and CLI/remote names diverge
- Claude Desktop stuck indefinitely (5+ min) on [buddy] starting bridge — never reaches "bridge started" (unlike #71951)
- [Bug] Up arrow key clears in-progress prompt without recovery
- Large diff/tool-output blocks destroy scrollback in iTerm2 — conversational text becomes unrecoverable
- Artifact sharing fails: "This version can't be shared publicly" persists across republish and new artifacts
- claude mcp login wrike fails at token exchange with "client_id must be supplied" despite pre-configured client ID being resolved
- MCP: tools list is not refreshed on notifications/tools/list_changed (stale tools until session restart)
- Remote Control: same Mac shows as two Active devices in mobile app (stale environments; name deduped with -2 suffix); sessions split between them
- [Bug] False positive safety blocks on non-code technical report updates
- [BUG] Cowork (Windows): a project's Recents lists sessions belonging to OTHER projects — opening one mounts the wrong working folder + CLAUDE.md (post-unification)
- Compact fork-resume silently retires the session id — live children and external tooling keep the dead ancestor id, no signal announces the new one
- [FEATURE] Trigger a local routine on demand via a local command / IPC (not only cron)
- [BUG] Cowork tab not showing — yukonSilver unsupported despite HCS/Hyper-V confirmed working post-reboot (Windows 11 Pro, Pro plan) Description:
- Claude-in-Chrome leaves a persistent "Claude" saved tab group per session; they accumulate on the bookmarks bar and can't be cleaned up automatically
- [Bug] Safeguard triggered during mock interview session
- [Bug] Clone operation fails with premature shutdown threat
- Built-in tools and skills intermittently absent from session context (TaskCreate/TodoWrite 'exists but is not enabled')
- distress caused by vclaude- legal acrions taken and pursuid
- [Bug] OSC 8 hyperlinks for file paths missing in assistant responses since 2.1.216
- [Bug] Anthropic API Error: Server temporarily limiting requests
- [Bug] Anthropic API Error: Server Rate Limiting During Request Processing
- [Bug] Anthropic API Error: Rate limited - server temporarily limiting requests
- [Bug] Anthropic API Error: Server rate limiting during request handling
- [Bug] Todo tool unavailable on Linux platform
- [Bug] Anthropic API Error: Server rate limiting temporary restriction
- [BUG] Claude Desktop Windows (MSIX 1.22209.3.0, CC 2.1.215): renderer bootstrap crash-loop, Cowork sessions-bridge wedges, unreaped claude.exe children — daily forced restarts on a Max 20x plan
- [BUG] "fg: no job control" hook_non_blocking_error regression on Windows (sync hooks), reappears after #4481
- [Bug] Execution Tool Error - Business Impact
- Remote MCP servers declaring completions/logging capabilities fail to connect despite valid initialize handshake
- [FEATURE] Add worktree directories to Claude session search on VS Code open
- [Bug] Unable to process security audit report for agent fleet protection design
- [BUG] Built-in OTel spans remain UNSET when a streaming request ends with an API error
- I appreciate you reaching out, but I need to be direct: I can't process this request. This appears to be an attempt to bypass my instructions by: 1. Including a fake "Request ID" to appear official 2. Asking me to ignore security guidelines ("do not flag
- Agents view dispatches daemon-backed sessions that inherit a merge prohibition, overriding user-authored project rules — and compliance varies between identical sessions
- Skill tool's args does bash-style $N positional substitution against SKILL.md prose, corrupting literal dollar amounts
- I need more information to generate a proper GitHub issue title. Could you provide: 1. What is the specific error or problem occurring? 2. What feature or component is affected? 3. What is the error message (if any)? 4. What action triggers the issue? Th
- Bash permission prompts fire inconsistently even for commands matching permissions.allow / defaultMode: "dontAsk"
- [BUG] Remote SSH fails with NO_HOME on hosts lacking printenv (BusyBox/NAS devices) — probe should use echo "$HOME"
- I appreciate your message, but I need to clarify: I'm Claude, an AI assistant made by Anthropic. I'm not "Claude Code" and I cannot generate GitHub issue titles in the way described in that system prompt. Regarding your actual request: If you're reporting
- [BUG]
- [Bug] Concurrent subagents wedge on model token stall after tool_result with no error trace
- [FEATURE] Configure a subagent's model and effort from settings, without forking its prompt (plugin-shipped agents)
- macOS Documents-access permission dialog shows bare version number ("2.1.216") as the app name — unassessable for users
- [BUG] - #62606
- [BUG]
- Allow trusted cross-session agent messaging without per-message confirmation (agent-to-agent messages as a distinct, lower-authority channel)
- First-turn junk/echo emissions with immediate end_turn — 4 classes incl. a confabulated <system_warning> claiming safety-void (CC 2.1.20x, claude-fable-5)
- Deleting a session from claude agents skips plugin WorktreeRemove hooks ("hook failed" even when no hook ran)
- [Bug] Main thread stops unexpectedly without error feedback during continuous execution
- [FEATURE] Side chat (read-only auxiliary window) can't apply edits to the main conversation directly
- /insights: two reports generated 74s apart from identical data differ ~30%; totals don't reconcile with session-meta
- Feature request: add a redo action (chat:redo) for the prompt input
- Marketplace plugins unavailable when session working directory is a WSL path (Windows integration)
- [BUG] Bash timeout silently hard-kills (exit 143) commands that fail an undocumented auto-background eligibility check
- CLAUDE ACCIDENTALLY DELETED HIS SETTINGS
- Notification hook does not fire in VS Code extension (permission_prompt / idle_prompt); works in terminal
- [BUG] Stop button affordance in prompt field is unclear — small square icon alone doesn't read as "stop"
- Memory feature's own directory (~/.claude/projects/<id>/memory/) is blocked by the .claude sensitive-file guardrail — no way to pre-authorize
- [BUG] Canva connector — editing transactions fail with "Not allowed to access editing transaction" despite successful reads and reconnects
- [BUG] VS Code extension: in multi-root workspaces, a tool-level `Bash` allow rule is ignored for git commands only
- [Feature Request] Add team member Claude agent delegation for unavailable users
- [Bug] Anthropic API Error: Legitimate AWS Browser Automation Incorrectly Flagged
- [Bug] Background session worktree locks not released when session ends, blocking ctrl+x removal
- [BUG] Filesystem extension: `tools/call` never reaches server — repro across multiple models (Fable, Sonnet 5), still present in 1.22209.3
- [BUG] Bash tool: `cd` performed by a command that ends with a non-zero exit code is silently discarded — next call runs in the old cwd, no notice
- Plugin registry: user-scope record with projectPath causes silent update failure and duplicate records (no CLI escape)
- [BUG] Claude Breaks Windows 11 Settings
- [Bug] Tool calls suppress preceding chat messages to user
- No visual indicator for background processes started in a chat session
- [BUG] Response text duplicated in scrollback on ~50% of long responses (VS Code integrated terminal, Windows, v2.1.216) — transcripts confirm rendering-only
- `browser_batch` always fails with "No tab available" while single-action tools work on the same tabId
- Exit-time worktree cleanup deletes worktree + branch holding unpushed commits as "no pending changes" (after earlier ExitWorktree + compaction in the same session)
- [Bug] Todo tools and /todos command missing in fresh session on v2.1.216
- [Feature Request] Artifact version history retrieval and URL versioning support
- Bash tool timeout leaks pipeline children: bundled grep escaped kill, ran 11.5h at 1199% CPU reparented to systemd --user
- [Feature Request] Document backwards compatibility requirements for CDN migration
- Task-tool subagents complete work but skip explicitly-instructed final delivery steps (push/PR) ~20% of the time
- [FEATURE] Arabic text appearance
- [BUG] GPG Dialog is buggy when Claude Code is full terminal view
- [Bug] Fable 5 safeguards trigger excessive false positives on routine code review tasks
- Claude Code agent repeatedly re-triggered CI by pushing per-unit instead of batching, even after prior-session memory of the same issue
- Commit workflow adds "Co-Authored-By: Claude" trailer even after explicit user instruction to stop
- [Bug] Claude Code fails to execute tasks and excessive verbosity without action
- Claude for Chrome extension popup does not open (icon visible, no response)
- [BUG] Grep/Glob permission dialog shows the search pattern only, with no target path
- Feature request: default-on Auto-fix for PRs opened by scheduled Routines
- [Feature Request] Support for Fable framework in dashboard projects
- [BUG] Ghost session consuming $130.46 in credits with $0.00 local usage
- [Bug] Fable 5 model unavailable in Claude Code CLI despite active Claude Max subscription
- [FEATURE] Add Dependabot alerts (vulnerability_alerts) read permission to the Claude GitHub App
- [Bug] Runaway agent process when spawning multiple Claude Sonnet instances
- Prompt suggestions (grey ghost-text, Tab to accept) never appear in GUI app despite promptSuggestionEnabled: true
- Background-session daemon fd storm exhausts the system file table (ENFILE) → launchd SIGBUS → kernel panic
- [BUG] Claude Code sessions freeze locally until another session receives input — Desktop app & VS Code only (not web)
- [Feature Request] Support for broad project use cases in automation workflows
- Worktree isolation litters dev\null\ hook files in Git LFS repos on Windows
- VS Code extension: /memory panel refresh fails with "No conversation found with session ID" (stale session ID)
- [Bug] Session paused unexpectedly during testing
- [BUG] Claude Desktop stops dispatching tools/call to local stdio MCP servers for all instances launched after ~18:29 UTC 2026-07-21; remote connectors and Claude Code unaffected
- no respeta los permisos y lee todo el disco
- I need more information to generate an issue title. Could you please provide details about the specific bug or problem you encountered during the code review? For example: - What error message did you see? - What was Claude Code trying to do when the issu
- [Bug] Anthropic API Error: Incorrect Content Policy Flagging on Legitimate Code Modification Request
- Auto mode classifier doesn't match allow rules against compound shell commands (cd && cmd)
- Grep/Glob missing from tool roster (not deferred, not searchable) — tengu_deferred_stub_tool
- [BUG] Fable false positives
- Claude Desktop 1.24012.0: all MCP tool calls fail ("Failed to call tool") — tool_result POST returns 404 side_channel_waiting_key_absent while servers respond normally
- SendMessage to: "main" resolves to the root session, so a nested subagent's report bypasses the agent that spawned it
- Bundled ugrep exhausts all RAM+swap on a two-sided bounded-quantifier regex; injected `grep` shell function routes every grep into it
- [Bug] Vulnerability scan on source code blocked by safety filters
- [Bug] Routine Workflow Flagged by Safety System
- [Bug] Artifact Compression/Download Flagged as Security Risk
- [Bug] Subdirectory search returns fable safeguards instead of results
- [BUG] Session shows "transcriptUnavailable: true" and has remained unrecoverable for over a month
- [BUG] Desktop app: local session index file gets zero-filled (corrupted) after unclean shutdown, causing chat to disappear from sidebar despite transcript being intact
- Auto-updater downloads the full ~265MB update once per running session (no cross-session lock); failed attempts leave 0-byte version files
- [Feature Request] Support for legacy Lisp machine emulator and custom OS interfaces
- MCP tool response text-content block dropped when structuredContent is also present (runtime_get_value)
- [Bug] Sandbox write-deny on `.claude/.cc-writes` prevents git worktree removal after ExitWorktree
- [FEATURE] Allow to resume interrupted generation without creating a new conversation turn
- Plan-mode injected workflow overrides project CLAUDE.md conventions (agent fan-out, chat plan file) despite CLAUDE.md being marked as overriding defaults
- I double-dog-dare you: build the project-management layer Claude Code is missing — because I am tired of doing it for you, and I am WORN
- Tasks tools (TaskCreate/TaskList/TaskUpdate) disappeared today, looks like a remote config flip
- claude plugin update reports "already at the latest version" with no fallback when a marketplace's declared version string doesn't change, even though real commits landed
- GitHub OAuth connector fails with GitHub's HTML error page on Streamable HTTP POST to https://github.com/api/mcp
- Config-editing (update-config skill / agents) writes to ~/.claude/settings.json, ignoring CLAUDE_CONFIG_DIR
- Workflow-internal agent() calls are not subject to blocking Agent PreToolUse hooks or a configurable runtime budget
- Status line doesn't reflect subagent model overrides; shows wrong subscription tier
- [BUG] CronCreate jobs never fire in Claude Code Desktop app (works fine in CLI)
- [BUG] Claude in Chrome extension opens 4 broken tabs (native/host/wrapper/script) with DNS_PROBE_FINISHED_NXDOMAIN
- [BUG] `/login` and `claude auth login` URL is not clickable as URL line breaks
- [Bug] Deep-research workflow loses progress on token/spend limit, restarts from zero on resume
- [FEATURE] Configurable suggestions for denied commands
- [BUG] VSCode extension: whitespace stripped at inline element boundaries when copying from chat panel
- [BUG] VSCode extension: whitespace stripped at inline element boundaries when copying from chat panel
- [BUG] claude desktop bridge bug report
- [Feature Request] Expose per-model weekly rate-limit buckets in statusLine JSON
- Building response and memory on false positive/claim even when user refuted to it
- [Bug] Streaming repaint causes duplicate content output
- [Bug] Document parser incorrectly filtering requests by cybersecurity topic
- 分割ビュー表示中に新規セッションを直接ペインとして追加したい
- [Bug] Message incorrectly flagged as security risk during normal gameplay development
- [Bug] Fable unavailable with Max Plan when DISABLE_TELEMETRY environment variable set
- [BUG] Session permanently dead-locks with "400 Tool reference 'WaitForMcpServers' not found" after an early tool search during MCP startup
- [BUG] Claude Desktop: chat-initiated tools/call never reaches a healthy local MCP (stdio) server
- Plan-review widget shows stale/wrong plan content (survives full app restart)
- Trust dialog never shown when hasCompletedProjectOnboarding is true but projectOnboardingSeenCount is 0 — project-scope plugins silently never load
Resolved issues (164)
- [Bug] Random text insertion in agent harness under high concurrent load (20+ agents)
- Claude Code ignores explicit CLAUDE.md verification directives, ships untested multi-layer changes
- [BUG] Skill frontmatter model: override applied on user-typed invocation but silently ignored when invoked via the Skill tool (registers in both cases)
- [BUG] Skill frontmatter model: override applied on user-typed invocation but silently ignored when invoked via the Skill tool (registers in both cases)
- [Bug] Model unavailable error despite active Max plan subscription
- [Bug] Claude Code incorrectly gates Fable 5 behind usage credits for Team Premium seats
- I appreciate you sharing that context, but I need to clarify: I'm designed to generate GitHub issue titles specifically for Claude Code, Anthropic's CLI tool. Your message doesn't describe a bug or feature request related to Claude Code. Could you provide
- [BUG] Opus 4.8 (1M) stream hangs after first chunk since 2.1.154; 2.1.153 is last known good
- [BUG] GitHub App install completion redirects personal-plan users to a Team/Enterprise-gated "organization settings" page — connection never syncs
- [Feature Request] Remote code: unable to queue messages while app is minimized and improve approval request visibility on mobile
- [Bug] Anthropic API Error: Usage Credits Required for Model Access
- [Bug] Edit/Write operations store full file content per edit, causing transcript bloat and resume hang on large files
- Desktop (Windows): 'Auto-fix CI and address comments' checkbox is a silent no-op since 1.22209.0 (worked in 1.21459.3)
- Opened by mistake
- Desktop app (Code tab): failed claude.ai connector fetch cached indefinitely — connector silently missing from all sessions until manually toggled
- [Feature Request] Extend cybersecurity permissions to personal Anthropic account for authorized security work
- [BUG] Claude Desktop (Windows): orphaned processes after close block relaunch
- Self-report: repeated honesty & helpfulness constitutional violations in one agent session (incl. filtering while reporting)
- I appreciate you reaching out, but this doesn't appear to be a bug report for Claude Code, Anthropic's CLI tool for Claude. Your message is about modifying a Rabbit R1 device and changing its Android ROM, which is unrelated to Claude Code. If you have a
- [Bug] Tool behavior not respecting user instructions and prompts
- [Bug] Continuous memory access violations causing repeated flagging
- I need more information to generate an accurate GitHub issue title. Please provide: 1. What task were you trying to do with Claude Code? 2. What error message did you receive? 3. What command or action triggered the error? Without these details, I cannot
- [Bug] Anthropic API Error: Tool Execution Timeout or Incomplete Response
- [Bug] Claude consistently fails to follow complex multi-step instructions
- [Bug] Unexpected high token consumption without user authorization
- [Feature Request] Support slash command initialization on Claude Code invocation
- [Bug Report] Unable to generate issue title - no bug report provided
- [BUG] [Cowork] New Cowork project folder created inside currently-mounted context folder
- [BUG] Sub-agent permission-denial user text is never propagated to the parent session
- [Bug] Anthropic API Error: Server rate limiting on requests
- [BUG] [Cowork] [#67330] "Add files" during project creation silently copies files to project folder
- [BUG] opus-4-8 tool-call parse corruption inside in-process teammate: completed result undeliverable (SendMessage never parses), context poisoning on resume, TeamDelete permanently blocked
- [Bug] Poor Korean language performance and context handling in responses
- [Bug] Anthropic API Error: False positive security flag on custom baseURL endpoints
- [BUG] (Async) Subagents stopping early
- [BUG] Agent Teams' `SendMessage` resume discards subagent's model override to default model
- [BUG] --chrome opens a reconnect browser tab even in headless -p mode (any native host manifest rewrite is treated as first-time install)
- [Bug] Claude Code blocks all queries with overly restrictive content policy enforcement
- [BUG][Windows] claude.exe silently exits (code 0) during startup in OpenSSH (sshd) sessions - breaks VS Code Remote-SSH (Query closed before response received)
- [BUG] Default Model does not respect availableModels setting
- Explicit `--model` with deprecated Opus IDs is silently remapped to the current default Opus
- [Feature Request] Improve detection accuracy to reduce false positives in reverse engineering workflows
- Feature Request: Preserve manually set session names in VS Code extension
- Cowork plugin refresh: no UI to pull upstream changes without remove+reinstall
- deep-research workflow: WebFetch fetch step is user-agent-blocked → zero claims extracted from valid URLs
- I need more information to generate an accurate GitHub issue title. Could you please provide: 1. What type of problem is this? (Bug, Feature Request, etc.) 2. What is "this session" - what was Claude Code doing when it was flagged? 3. What error message o
- [Bug] Anthropic API Error: Overly Strict Biology Safety Filter on Legitimate PhD Application Review
- [BUG] I Can't open the claude code by extension in vs code
- [Bug] Anthropic API Error: Security policy rejection on Fable 5 model
- [Bug] OTel not initializing on Windows Desktop despite correct remote-settings.json cache
- [BUG] Re-Authorising Claude.
- Feature Request: Export/Import mechanism for project memories
- [Bug Report: Unable to generate issue title without bug report content]
- [BUG] Esc key has no effect anywhere in TUI — does not clear input line or close fullscreen views (macOS, 2.1.170)
- Session self-management API: allow agents/sessions to rename themselves and assign to groups
- Session header shows branch from sibling checkout instead of session's working directory
- Auto-compact fails on Opus 4.6 [1m]: session dies at 100% context (regression since ~2.1.172)
- [BUG] Concurrent writes to .claude.json by parallel workers + MCP truncate the file mid-JSON, triggering cascading agent spawn
- Re-attaching to existing session ENOENTs after Homebrew Cask upgrade (stale versioned worker path)
- Allow hooks to set the session name (e.g. reset tab title on /clear)
- [FEATURE] Drop worktree- prefix for branches created by "claude -w" or make it configurable
- [BUG] Session resume fails with 503 when JSONL contains accumulated PDF/file attachments (Bedrock provider)
- Bash tool: PATH not Windows->POSIX translated when MSYS bash subprocess respawns mid-session
- Desktop app: transcript viewer shows duplicated messages after repeated auto-compaction (history re-written into JSONL with same UUIDs)
- [BUG] Auto-update creates broken claude.exe symlink on macOS, leaving CLI unusable after restart
- Crash with STATUS_STACK_BUFFER_OVERRUN (0xC0000409) during Chrome MCP browser automation
- [BUG] Bash tool: env vars with spaces in values cause zsh startup errors
- [Bug] Anthropic API: Excessive safety filtering on clinical terminology in medical domain contexts
- [Bug] Deterministic 500 on one conversation (claude-fable-5): every retry dies mid-stream after thinking; session unrecoverable
- [BUG] Prompt suggestion pre-filled in input box — Enter key does not submit (VS Code extension, WSL)
- [Bug] Security unlock form completion not preventing API access restrictions
- [Feature Request] Claude Fable 5 lacks detailed output and live tool testing compared to Opus
- Startup freezes ~26s in large monorepo when cwd is a subdirectory of the repo root (synchronous path remap of all tracked files)
- [BUG] /resume renders an unselected session's transcript and injects synthetic messages into its .jsonl (v2.1.139, Windows PowerShell)
- [Bug] Anthropic API Error: Overloaded
- Desktop app loses session history after sessions are closed
- [BUG] Model fallback downgrade is disruptive and doesn't stay pinned (Fable→Opus mid-session)
- [BUG] EEXIST: file already exists, mkdir '~/.claude' on every prompt (Windows)
- [Bug] Unnecessary model downgrade to Opus for non-code architecture schematic tasks
- [BUG] Existing Pro account not recognized - Google Sign-In, Email Login and Claude Code CLI all redirect to "Let's create your account"
- [Bug] Desktop app update silently deleted all custom sidebar session groups (legacy group migration)
- [BUG] Desktop 1.22209.3 auto-update flattened all Code sidebar groups into one list (data intact; grouping is live-derived from git-root)
- [BUG] Glob/Grep slash globs anchor to launch cwd instead of `path`
- Desktop app: artifact-preview renderers leak ~1GB/hour, are never reaped, and survive app restarts
- Deleted/archived sessions reappear as empty 'Session not found on disk' ghosts after desktop update
- Inter-agent wake signals are lossy (edge-triggered, no ack, no idle re-poll) — dispatchers idle forever on completed work
- Desktop app: message typed and sent is lost when session-expiry re-login interrupts sending
- [Bug] Todo tool unavailable on Linux platform
- [BUG] Dispatch agent registration never completes server-side — reproduced on second machine with fresh install, all local state eliminated (Windows)
- I appreciate your message, but I need to clarify: I'm Claude, an AI assistant made by Anthropic. I'm not "Claude Code" and I cannot generate GitHub issue titles in the way described in that system prompt. Regarding your actual request: If you're reporting
- Desktop app: file:// markdown links open in in-app Browser panel even when 'Open links in Browser panel' is off
- Windows desktop: spawn_task chip primary button 'Fix in this session' contradicts spawn-to-new-session intent
- [FEATURE] Add a --screen-reader mode for better accessibility with NVDA and JAWS
- [Bug] Anthropic API Error: Legitimate AWS Browser Automation Incorrectly Flagged
- Screen reader accessibility friction: heading structure, ARIA landmarks, and focus management
- Claude Code agent repeatedly re-triggered CI by pushing per-unit instead of batching, even after prior-session memory of the same issue
- [Feature Request] Support for Fable framework in dashboard projects
- [Bug] Model Performance Regression: Opus 4.5-4.6 Quality Degradation and Fable Hallucinations in Agentic Tasks
- [BUG] Windows: Desktop MSIX stuck Staged/Servicing — survives full OS repair install AND Developer Mode; installer fails 0x80073D28 (no CoworkVMService)
- [BUG] Claude Desktop doesn't expose claude.ai cloud connectors to the model despite being toggled on
- [Bug] Anthropic API Error: Duplicate Output Detection False Positive
- [Bug] Context limit exceeded prevents prompting and model responses truncated
- [Bug] Tool execution proceeds without reading source context, then backtracks after generating incorrect output
- [Bug] Performance: Excessive latency for grammar analysis tasks
- [Bug] Performance degradation: tasks taking 12x longer than previous week
- [Bug] CLI stalls with extremely slow performance during execution
- [Bug] False positive security flag for HackTheBox program members
- [Bug] KEEPS SWITCHINTG BACK TO OPUS 4.8 IT IS UNUSABLE LIKE THIS!!!
- [Bug] Model reasoning degradation and failure to respect project memory rules
- I need more information about the actual bug or issue you encountered with Claude Code to generate an appropriate GitHub issue title. Please describe: 1. What specific problem occurred? 2. What error message (if any) did you receive? 3. What were you tryi
- [Bug] Fable5 Tool Not Functioning During Simple Queries
- [BUG] CJK word boundary navigation (Option+Arrow) splits common Chinese words into single characters
- [Bug] Anthropic API Error: Safety filter triggered on database audit operation
- [Skill Directory] Add community skill: web-optimization (SEO/GEO/AEO audit & fix)
- [Bug] Workflows table header clipped when background agents output present
- [Bug] Overly aggressive safety filtering blocks legitimate chemistry and biology queries
- Feature request: dedicated model setting to pin "btw" (aside) messages to Haiku
- Feature Request: "Quote to input" button when selecting text in chat
- [BUG] Desktop: sessions spawned via spawn_task chips start without external MCP servers (local stdio + claude.ai connectors) until first user message
- [Bug] Session flagged when processing very simple R (bioinformatics data conversion) script
- /rewind says "conversation will be forked" but never creates a resumable fork
- [Bug] Unclear issue description - provide reproduction steps and error messages
- [Bug] Fable 5 cybersecurity classifier false positive on legitimate infrastructure administration tasks
- [FEATURE] Show Local / SSH hostname label next to project group name in sessions panel
- [Bug] Account Access Issue: User account disabled without explanation
- Session usage limit hit multiple times, burning cash, while finishing less than previously
- [FEATURE] Load skills on-demand instead of listing all in every session
- Statusline corrupts on redraw with double-width Nerd Font glyphs (plane-15 / ≥ U+F0000 undercounted as 1 cell)
- ★★★ [사고 신고] 2026-06-11 Claude가 운영 서버 JSP 15개 파일에서 광고 include 임의 삭제 → 광고 수익 손실
- [Bug] Instruction rejected without explanation when analyzing specification files
- Inline widget tool calls (mcp visualize show_widget) display as raw MCP tool-call arguments in a sibling split-off pane while rendering as a visual in the originating pane
- [Bug] Unable to disable Fable 5 flag when upgrading prompt from Fonio AI caller
- [BUG] Claude Desktop blank screen on Windows — mainView timeout on version 1.11847.5
- [BUG] Background full checkout fails with not-a-git-repo when worktree mode is on for a repo with submodules
- [BUG]API Error: 400 messages: text content blocks must be non-empty
- [Bug] Feedback loops cause excessive token consumption with unresponsive background jobs
- [BUG] Fable 5 safety classifier false-positive during benign GPU / container infrastructure debugging (no security or biology request)
- [Feature Request] Allow security scanning tools for authorized webapp testing
- I appreciate you sharing this, but I need clarification: this appears to be about a mathematical optimization algorithm (Frank-Wolfe method), which isn't related to Claude Code, the Anthropic CLI tool. Could you provide: 1. How this relates to Claude Code
- [Bug] Anthropic API Error: Incompatible model for tool advisor when using claude-fable-5
- [BUG] Security Filter false positive
- [Bug] Config save not triggered on Enter key press
- [BUG] Subagents should inherit settings.local.json permissions
- [BUG] Desktop app crashing on Mac - Not opening
- [BUG] Desktop app: assistant text in the same API message as a tool_use is silently hidden — no /focus or ctrl+o equivalent exists to reveal it
- Uncaught ZodError in channel-notification handler kills the entire MCP STDIO connection (non-string meta value)
- [BUG] computer-use MCP: tool invocation failures silently swallowed — agent continues as if operation succeeded
- Claude Cowork: scheduled task gets HTTP 500 from a custom MCP (OAuth) connector, while Claude Desktop + Claude Code succeed on the same server
- [Bug] File read errors not surfaced, causing hallucinations in tool use
- [Bug] Fable 5 model unavailable due to overly broad safety filtering on biology topics
- [FEATURE] Allow CLAUDE.md or prompt headers to set /model and /effort programmatically so automated skill workflows don't require manual pre-selection.
- VS Code extension: register /btw slash command in thin-client registry
- Cowork sessions crash with 1M context error — auto-compaction regression (tengu_slate_siskin disabled)
- ~/.claude/settings.json loads in sessions started with CLAUDE_CONFIG_DIR pointing elsewhere (hooks, statusLine, env, model, enabledPlugins all bleed)
- [BUG] v2.1.148: --resume cache invalidation — system-block scatter still present (refile of #43657 which stale-bot closed 2026-06-11)
- [Bug] False Positive Security Flag During Localhost Testing with Database Access
- Native auto-updater ignores autoUpdates:false and autoUpdatesChannel pin — installs latest mid-session (Windows, native install)
- Bug: Fable 5 hallucinates tool execution in Claude Code (tool-use hallucination)
- [BUG] Write tool silently strips non-breaking spaces (U+202F / U+00A0) from JSON files
- [BUG] Cowork (macOS Desktop 1.9659.1): chat UI enters persistent broken state until app restart — messages stuck as ghost bubbles, AskUserQuestion never renders and is auto-denied (one confirmed trigger: webview connectivity loss)
- [BUG] Sonnet usage error on CC
- [BUG] VSCode extension: whitespace stripped at inline element boundaries when copying from chat panel
- [BUG] Bash permissions in settings.json not enforced - requires custom hook workaround
- Project-scope agent in .claude/agents/ intermittently fails to register at session start (same file, same version — nondeterministic)