Digest / July 17, 2026
Claude Code Issues Digest — July 17, 2026
386 new issues filed ·
178 resolved in anthropics/claude-code (UTC day).
New issues (386)
- [Bug] Remote control startup fails with intermittent 401s from code-session endpoints
- [Bug] Claude Code fails to review iOS app code
- [FEATURE] Machine-readable provenance for installed plugins (version + source ref/SHA) so installs can be verified and pinned reproducibly
- [Bug] Sub-agents ignore default TUI setting and force fullscreen terminal mode
- Intermittent: subagents hang on their first tool call (0 tool uses, no error, parent waits forever)
- `disabledMcpServers` in `~/.claude.json` project entry has no effect on user-scope MCP servers (still connect, tools + instructions loaded)
- Browser tool "read tools" per-action approval doesn't respect launchPreviewAllowedOrigins / "Allowed sites" list
- Auto-generated permission entries in `.claude/settings.local.json` contain malformed globs (dead entries)
- [BUG] Desktop Windows: sidebar pins never persist across app relaunch — pin-to-server sync fails, sidebar re-hydrates a stale pin set (repro on 1.21459.3.0 and 1.22209.0.0)
- [Bug] Auto-compact window not updated after mid-session model switch
- [BUG] Claude Tag: editing a custom connection (Rotate secret / edit allowed hosts) silently stops Agent Proxy attaching the credential; delete+recreate with identical config works
- Thinking volume ~2x between 2.1.206 and 2.1.211 at identical model/effort/prompts (measured across 4 benchmark runs)
- settings.json read-modify-write race: /model save in one session clobbers another session's /effort save
- [FEATURE]
- [BUG] --remote-control intermittently fails: createCodeSession 401s on attempts 1–2 every launch, only 3 retries, so occasional total failure
- [FEATURE] Add localization (l10n) support for extension UI strings (e.g. permission dialogs)
- Fable 5 at max/xhigh effort: polished but ungrounded outputs; effort deepens reasoning inside the chosen frame instead of expanding ground-truth gathering
- [BUG] Code tab popup not responding in Claude Desktop
- [FEATURE] Add localization (l10n) support for extension UI strings (e.g. permission dialogs)
- [BUG]
- Feature request: session-only switch (`s` key) in /effort and /advisor pickers, matching /model
- [BUG] GitHub proxy 403s release-asset downloads in cloud sessions, breaking builds
- [Bug] Conversation blocked when discussing cybersecurity topics
- [Bug] Overly restrictive safety guardrails preventing legitimate code operations
- Remote Control: disconnect crashes (session_url undefined) → session accumulates → new connections fail (Session creation failed / Remote credentials fetch failed), one session stuck even after re-auth
- CronDelete reports success but the deleted job reappears in CronList after a session restart
- [BUG] /desktop fails with "Failed to open Claude Desktop" on Windows while the same deep link works manually
- [BUG] Desktop app: /remote-control disconnect throws "Cannot read properties of undefined (reading 'session_url')" and leaves the toggle ON
- [Bug] Interrupting Ultraplan thinking turn stops/crashes cloud container and ends session
- Background agents drop queued SendMessages and skip completion notifications
- Claude Code fabricated a factual claim from incomplete tool output, ignored contradicting evidence, and ran unauthorized state-changing commands
- [BUG] Large session hangs then errors on new turn; last message lost and never persisted
- Path-scoped rules injected twice when a plugin is installed and its source repo is the working directory
- Read tool displays secret file contents in plaintext with no redaction, even when user only asked for a path
- Desktop app (Windows): Transcript view "Thinking" never renders thinking — blocks exist in .jsonl; showThinkingSummaries:true has no effect
- Auto-mode permission classifier blocks every path to handle a user-provided token — 5 denials, one task, zero safety gained
- [BUG] Claude Code v2.1.212 asks approval for ALL bash commands in plan mode
- code-review: findings are adversarially verified, but the fix plan never is — a fix-plan design pass measurably breaks fix→regress cascades
- Agent invents new deliverables instead of following the user's defined workflow step, then repairs its invention through repeated corrections
- [Feature Request] Let a Claude Design conversation be shared/transferred to a different Claude account than the one it was created under
- Max plan models (Opus 4.8, Fable) not available in Claude Code CLI
- [WorktreePool] reaps a worktree while its leasing session is actively running (3s after the session's last command)
- False-positive safety flag on routine product/coding conversation (Fable 5 -> forced Opus 4.8 switch)
- [BUG]
- [BUG] Claude Code crashed
- [FEATURE] Support multiple OTEL endpoints simultaneously for telemetry export
- ExitWorktree refuses to remove clean squash-merged worktrees, forcing a model turn to dismiss from Agent View
- Retry prompt "no visible output" injected when a turn ends with a tool call, even when the tool produces output
- [BUG] Windows desktop app: show_widget ⋯ menu → 'Download file' silently does nothing (Copy to clipboard works)
- Remote session (mobile app): image-only paste uploads the attachment but never submits the prompt
- [BUG] 3P managed-marketplace auto-install rejects plugins with source "./" (path escape) — manual Directory install of the same entry succeeds; CLI equivalent was fixed in 2.1.142 (#57570)
- Idle "task tools haven't been used recently" nudge omits the deferred-tool ToolSearch step, so acting on it fails with InputValidationError
- Fullscreen: Cmd+C and Ctrl+Shift+C clear the selection instead of copying it
- [FEATURE] Real-time plan usage/quota indicator in Cowork (5-hour & weekly limits)
- Scheduled routine (CCR) fails with generic "An error occurred while executing Claude Code" even for trivial MCP-free tasks
- Remote Control silently self-disables after 3 transient failures and never recovers (per-session init latch + persisted OAuth dead-token backoff)
- [Bug] Session timeout mid-task causes incomplete execution and excessive token consumption
- [BUG] Remote Control presence pulses get intermittent 401 on healthy connected bridges (no retry) — session shows offline/missing in mobile session list
- Auto-mode classifier denial triggers unrequested model fallback (claude-fable-5 → Opus) and accumulates empty orphaned sessions
- [BUG] Cowork: update retroactively invalidated custom Cowork files root; "Change location" then copied 12.87GB incl. credentials and git repo to world-readable /Library/Application Support/Claude
- [BUG] Plan side panel shows a stale snapshot from the first proposal, never updates
- Bundled native addon (image_processor .node) unsigned -- hard-blocked under Windows Smart App Control enforcement, no user workaround
- Auto-mode safety classifier routes through ANTHROPIC_BASE_URL (undocumented) — gateway users' classifier is served by their gateway
- [BUG] Cowork Linux: SDK verification fails permanently ("SDK version X not verified") even after full VM bundle + SDK reset — checksum mismatch suspected
- Artifact public sharing blocked ("uses connectors" / "This version can't be shared publicly") even with no capabilities declared
- [Bug] Claude Code ignores system rules and provides unsolicited explanations
- [BUG] [Desktop][Linux] App fails to connect after update via KDE Discover — "Couldn't connect to Claude / network redirected to www.anthropic.com"
- Mid-turn user messages get buried between tool blocks and often end up unanswered
- `headersHelper` on `type:"http"` hooks silently ignored since ≤2.1.209 — no changelog, no deprecation, no unknown-field warning
- /remote-control fails silently on FIRST in-session invocation, succeeds on retry (v2.1.212, Linux)
- Desktop app: Remote Control fails with 'Session creation failed — see debug log' on sessions that previously had remote control enabled; new sessions work
- Google Drive MCP connector: /mcp reports successful re-auth but tool calls still fail with 'token expired'
- [BUG] Cloud Routines: container starts detached-HEAD over stale baked-in branch refs — `git checkout main` time-travels days back; no way to pin the checkout ref
- "script injection times out on a static page" error
- [FEATURE] allow unattended (Routines) republish to refresh the shared/public version of an artifact
- Show live session/weekly usage % and reset countdown in CLI (e.g. /usage)
- Claude desktop auto-update reset Cowork VM workspace directory, wiping existing files
- Cowork & Claude Code deliver MCP App tool results with Messages-API image shape; widget stuck on "Waiting for results…"
- Claude Code repeatedly rediscovers solved problems (reopened – still relevant, closed only for inactivity)
- [Bug] AskUserQuestion tool response not displayed before follow-up confirmation prompt
- You've hit your session limit · resets 6:50am (America/New_York)
- [Bug] Content filtering incorrectly flags educational biology terms
- settings.json rewritten with only {env, statusLine} model — drops hooks key (440 captured occurrences)
- PostToolUse hook exit-2 stderr not surfaced to Claude in conversation or in --debug-file logs
- [Bug Report] User feedback regarding safeguards implementation
- [BUG] Windows Alt+V image paste fails once after idle, immediate second press succeeds (v2.1.212)
- Rewind/edit kills ALL background tasks; should only kill tasks spawned after the rewind point
- VS Code extension: tool OUT panels truncate narrative text instead of wrapping (re-filing #40901 / #41736 — the stale bot asked me to!)
- Adjudication step for auto-memory — batched promote/keep/discard review
- Mid-turn channel-message injection: no way to declare an operator channel as trusted ("This is NOT from your user")
- [BUG] /goal does not start immediately in /remote-control
- [Feature Request] /inject command to steer an in-progress run without stopping it
- [BUG] Claude Code reports that I've hit my usage limit immediately after my session limit was reset.
- [DOCS] Document `/subtask` and the new `/fork` background-session behavior
- [DOCS] Auto mode configuration guide missing `claude auto-mode reset`
- [DOCS] Environment-variable reference missing the WebSearch per-session cap
- [DOCS] Environment-variable reference missing the per-session subagent spawn cap
- [DOCS] MCP auto-background threshold and disable setting are missing from the docs
- [DOCS] Agent view docs omit the `/resume` picker for sessions removed from the list
- [DOCS] Ultrareview docs list only a bare PR number, not accepted PR reference formats
- [DOCS] Prompt-caching docs do not explain mid-conversation system-block caching through gateways
- [DOCS] Enterprise authentication docs omit the login surfaces enforced by `forceLoginMethod`
- [DOCS] Fullscreen docs use an outdated tmux 3.4 synchronized-output threshold
- [BUG] Plugin-bundled MCP servers (.mcp.json) never appear in claude mcp list, regardless of install scope
- /compact executes repeatedly with no user input — phantom dequeue events in queue-operation log (Remote Control + concurrent sessions)
- [BUG] Session auto-naming stopped after Claude Desktop update — sessions stay "Untitled session" (Desktop 1.22209.0, macOS)
- [Bug] False positive detection in linting or validation
- [FEATURE] Read a routine run's transcript/output from the terminal (CLI or API), without opening the session URL in a browser
- Resume-from-summary guard doesn't fire when the session prefix was invalidated by a CLI version change
- Sandbox stubs break `git add .` and are indistinguishable from real repo state to the agent
- Prompt intermittently sent doubled (exact 2x conversation prefix, cache_read=2.00x prev) since v2.1.209 — hidden request burns quota, pins context meter at 100%
- MCP OAuth stuck at "unauthenticated" — no browser launch, state mismatch, cross-platform
- MCP OAuth state mismatch on Windows — root cause likely matches closed #17733 (state/redirect_uri omitted from authorize request)
- [BUG] Plugin/Skill "Update" button stays disabled even when a newer version exists upstream
- [MODEL]
- [Bug] Session missing cybersecurity module initialization
- Expose an autoplay-policy control for the in-app Browser pane
- [BUG] Remote Control registration: orphans on OAuth access-token rotation (~8h), dead session names never re-register, CLAUDE_CODE_OAUTH_TOKEN in env silently blocks registration
- [FEATURE] Show Remote Control status in the agent view / session lists
- Scheduled tasks (routines) reset run mode from "auto" to "manual" on every restart
- [BUG] you stupid agent used my real email as user agent string without asking anything
- [Bug] Assistant text blocks between tool calls not rendered in terminal output
- [Bug] Model unexpectedly switches to Opus 4.8 during basic code modification tasks
- [BUG] Parent resumes as if subagent completed while subagent is waiting in Monitor for a background process
- [BUG] The Claude Code CLI updated more than 15 times within two hours and kept downloading updates nonstop.
- [BUG] Bun v1.4.0 segfault at 0xFFFFFFFFFFFFFFFF ~30 min into remote-bridged session - 'exited with code 3' (Windows 11 26200, CC 2.1.209)
- Backup retention (keep-last-5) evicts the last good .claude.json after concurrent-write corruption, making config loss permanent
- [BUG] Repos no longer visible in claude.ai/code repo picker after update (worked until Jul 16, 2026)
- Backup retention (keep-last-5) evicts the last good .claude.json after concurrent-write corruption, making config loss permanent
- [BUG] CronCreate: fs.mkdirSync(path) does not have the { recursive: true } option, and does not catch EEXIST
- [BUG] [VS Code Extension]: Chat file links open a spurious external browser tab in web/code-server (missing stopPropagation)
- [BUG] Remote Control auto-registration mints an empty <hostname>-* session every ~5 minutes, flooding Recents (onset 2026-07-16, server-side default; workaround: remoteControlAtStartup=false)
- [BUG] Backgrounded/reconnected sessions do not use the configured proxy and fail to connect (ConnectionRefused)
- [BUG] Remote Control: session creation fails with "The request was invalid" when the environment's git remote is not GitHub (e.g. AWS CodeCommit)
- Routines fire API: newly generated routine tokens rejected (401) / expire within minutes; tokens issued before ~2026-07-16 unaffected
- [BUG] VS Code extension 2.1.211: renderer crash (SIGBUS, code 135) opening projects with large session-transcript dirs
- [Bug] Fable recommending unavailable Fable Advisor tool
- [Bug] Missing /survey-analysis skill reference in start-research-4
- [BUG] Mobile app has no Bypass Permissions mode; with the fail-closed auto-mode classifier outage, remote users are completely locked out (no prompt fallback, settings.json edits also gated)
- [Bug] Remote Control: 401 Authentication failed at /bridge endpoint after session creation
- Stale worker entries in ~/.claude/daemon/roster.json survive process death, show as "Login required" ghosts
- SessionStart hooks fire for phantom sessions that never materialize (no transcript is ever created), racing the real session within a few hundred ms
- I need more information to create a proper GitHub issue title. Your message doesn't describe a specific technical problem with Claude Code. Please provide: - What specific error or unexpected behavior occurred? - What command were you running? - What was
- Fable 5 dual-use safeguard routes legitimate defensive security work off the model (false positive)
- [BUG] Assistant text completes (end_turn, 20k output tokens) but is never rendered; ESC reveals silent verbatim recitation of the system prompt
- Show remaining session/weekly usage on the Code tab dashboard alongside totals
- Subagents are capped at 8000 output tokens while the main loop is not — high effort exhausts the budget on thinking alone, killing the agent before it emits anything
- Local sessions list empty for workspaces on a mapped network drive (native realpath != session-write path on Windows)
- [BUG] "Clean my computer" skill deletes staged files on unrelated command
- SubagentStart/SubagentStop counts stay mismatched: SubagentStop not emitted for subagents that terminate during an API-error burst
- Cannot change a session's working folder from the UI
- [BUG] claude.ai chat unusable for entire account: server-side ~4.8M-token blob injected into prompt assembly (all models, all surfaces, 1+ week) — follow-up to #62175
- [BUG] Session history / resume list is silently empty on Windows when the workspace is on a `subst` drive
- [BUG] Cowork VM bundle path ignores --user-data-dir on Windows (MSIX)
- [Bug] Requests flagged by content policy despite harmless content
- [BUG] Remote Control fails at bridge init: /v1/code/sessions intermittently 401s a valid OAuth token (~50-70% of requests, split backend fleet)
- [BUG] Remote Control intermittently fails with 'Remote credentials fetch failed' / 'Session creation failed': transient 401s from code-session service exhaust the 3-attempt retry budget
- [Feature Request] Add `--advisor` flag to Claude Code CLI
- 'manual mode on' indicator is invisible to the model: no context injection, main-loop behavior unchanged
- [BUG] Web interface: tool calls (file writes) intermittently return "user rejected" without the user acting, and the session then stalls silently
- [Bug] Model switches to Opus when analyzing project code instead of staying on selected model
- Session scratchpad directory is derived from TEMP — live session state gets destroyed by routine temp-directory cleanup
- Feature request: expose subscription usage percentages headlessly (stream-json rate_limit_event or `claude usage --json`)
- x
- [BUG] Claude Desktop code agent drops MCP per-tool `_meta` — `anthropic/maxResultSizeChars` ignored (CLI honors it)
- ta
- [bug/feature] Protect against dangerous irresponsible humans? - You've hit your session limit · resets 12:50pm (Europe/London)
- [BUG] OSC 8 file-path hyperlinks use a scheme-less URI → macOS "The application can't be opened. -50"
- Remote Control: crash on /compact ('Cannot read properties of undefined (reading session_url)') — session vanishes from mobile until new desktop activity
- [Bug] Linear MCP fails to initialize from agents view
- Remote Control (Windows desktop): disconnect crash permanently sticks the toggle; all sessions now fail with "Remote credentials fetch failed"
- [BUG] Session permanently bricked: 400 "Tool reference 'LSP' not found in available tools" after a deferred tool leaves the pool mid-session
- Worktree isolation silently lost when repo has core.worktree in shared config + extensions.worktreeConfig
- [BUG] Workflow/background-spawned agents block indefinitely on unanswered permission prompts — no auto-deny, timeout, or idle watchdog (55-min silent stall)
- [Bug] Claude 3.5 Sonnet inconsistently follows complex instructions
- Deferred tools (Monitor) unavailable in interactive sessions launched from inside a Claude session — env-var stripping does not help, only full environment replacement does
- [BUG] Unquoted ${CLAUDE_PLUGIN_ROOT} in plugin hooks.json breaks all hooks on macOS (space in path); hookify's PreToolUse hook blocks every tool call
- Env ANTHROPIC_API_KEY silently routed all sessions (incl. scheduled runs) to API billing despite active Max subscription — request louder consent + persistent indicator
- Remote Control: createCodeSession returns 401 (silently) from Docker/container environments since ~2026-07-17 — attestation enforcement?
- SSH remote environment: binary upload always fails with ENOENT on Synology DSM (internal-sftp virtual root ≠ shell-resolved $HOME)
- [Bug] Inconsistent Performance: Tool execution time degradation between sessions
- Feature request: share/attach conversation context across project folders (VS Code extension)
- [Feature Request] Allow disabling automatic default model persistence across sessions
- [FEATURE] Subcommand autocomplete for custom slash commands
- [Bug] Circular dependency in workflow: requesting manual steps before commit+push available
- [FEATURE] Workspace boundary enforcement for local file writes — auto mode allows out-of-workspace Bash writes silently; recommended alternative (sandbox) unavailable on native Windows
- [BUG] PyCharm plugin always reports Cannot launch Claude code even though it has
- caller does not have permission” after revoke/reconnect and fresh OAuth flows
- [Bug] Misleading tool capability claims and unverified verification assertions
- MCP stdio server fails to (re)connect with error -32000 after update to 2.1.212, though the subprocess handshakes correctly when invoked directly
- [Bug] Safeguard false positive preventing Tcpreplay PR verification
- Cloud multi-repo sessions never load repo .claude/settings.json (hooks silently don't fire), and CLAUDE_PROJECT_DIR is empty
- Add keyboard-only copy mode (no mouse required to start a selection)
- [BUG] /usage no longer renders the per-model weekly bar (Weekly · Fable) — weekly_scoped limit present in payload but dropped (scope.model.id is null)
- [Bug] Unable to debug game crashes using self-compiled DLL with Claude Code
- [BUG] [Cowork] Windows: Excel "open in app" fails silently when generated path exceeds MAX_PATH (preview still works)
- Workflow tool: persist each agent() call's label/phase in the agent's on-disk metadata at spawn time
- [BUG] Cowork on Debian 12: helper resolves system C virtiofsd instead of bundled Rust virtiofsd, causing setgroups/FUSE failures
- [Bug] Anthropic API Error: Unexpected model downgrade from Fable 5.0 to Opus 4.8 during session
- [BUG] PowerShell guard blocks Remove-Item for any direct child of a drive root, including nonexistent paths
- [BUG] Login OTP
- [Bug] Claude Code ignores custom Azure DevOps build tracking skill
- Opus 4.8: two consecutive 64K-token runaway thinking generations with zero visible output (empty thinking blocks)
- [BUG] Workflow tool hard-rejects run_in_background with a bare 'unexpected parameter' error instead of stating the tool is background-only
- I appreciate your feedback, but this appears to be a complaint about Claude's capabilities rather than a specific bug report for Claude Code (the CLI tool). If you have a specific technical issue with Claude Code to report, please provide: - What command
- [FEATURE] Warn before reviving a stale session - large cache-expired context re-billed on manual follow-ups AND automatic hook wake-ups
- [Bug] Requests being blocked by Anthropic API safety filters during normal development use
- Planning-instance failure pattern: abandons committed lane mid-arc, then cites unverified self-built checkers as evidence (claude.ai, Fable 5)
- [BUG]
- disable-model-invocation: true breaks explicit /skill-name invocation
- [Bug] Excessive resource consumption - tasks using 20x normal resources
- Background Bash tasks get lost/duplicated, turning a simple deploy into 10+ hours of retries
- Scope overstep on a GUI-launch task: model mutates persistent window/launch state it was never asked to touch, and repeats it across corrections (claude-code, Opus 4.8)
- [BUG] v2.1.210 regression: PreToolUse prompt-hook deny stops the entire turn (hook_stopped_continuation) instead of returning a tool error
- Model reports a failed detached action as 'done' and force-kills process state without authorization — in the same turn it was corrected for both (claude-code, Opus 4.8)
- [BUG] Claude Code (Bun runtime) fails with getaddrinfo ETIMEOUT when /etc/resolv.conf has trailing inline comments on nameserver lines
- Model executes a destructive persistent state change (deletes OS-level saved settings) inferred from a goal-level instruction — no confirmation, no backup, Nth same-session recurrence
- [BUG] Session-zugewiesener Worktree-Ordner unter `.claude/worktrees/<name>` ist kein registrierter Git-Worktree mehr (leere Ordnerhülle, Edits würden in den Hauptordner/falschen Branch durchschlagen)
- Claude in Chrome: Page.captureScreenshot times out (30s) on any tab whose visibilityState is "hidden" (renderer backgrounded while the desktop/chat window is focused); same mechanism as #53475
- [BUG] headersHelper on http transport still falls into "Incompatible auth server: does not support dynamic client registration" on 2.1.211 (regression from #53267 persists)
- [BUG] Lots of 529 Overloaded · Retrying in 19s · attempt 8/10 with claude code using GitHub speck kit - /speckit.constitution
- Agent's remediation regresses project state: deletes load-bearing user state on a goal instruction, causing a new outage its 'fix' was meant to prevent
- Feature request: org-level default sharing for published artifacts
- Auto-updater (ShipIt) doesn't relaunch the desktop app after installing an update — breaks anything relying on the app staying open
- [Feature Request] Disable mouse interactions and implement keyboard-based text selection in TUI
- [Bug] Cyber Safeguards false positive blocks legitimate CVE disclosure workflow
- [BUG] VS Code extension native panel resolves a different `claude` binary than the shell, causing global config (~/.claude/CLAUDE.md) to not load
- [/design-review] --guide mode shows too many examples
- [BUG] Regression (v2.1.212): VS Code extension hangs at "Connecting…" for a healthy stdio MCP server on Windows 11 — cmd /c fixes it
- [Bug] Claude Code ignores CLAUDE.md prohibitions and pushes to protected branch without approval
- [BUG] Remote Control fails with "Session creation failed" from VS Code sidebar only (regression, extension v2.1.212)
- claude remote-control: session-host RSS leaks ~1GB/day while idle, eventually wedging the relay
- [BUG] Cowork: scheduler "protected host location" registration persists server-side
- Browser tool: click coordinates drift because outerWidth/outerHeight diverge from the CDP-overridden viewport
- [Bug] Model switching to Opus for web scraping tasks without user request
- Transcript writer intermittently drops assistant text blocks ("mute windows"); thinking/tool_use of the same messages persist
- Playwright MCP server leaves orphaned browser processes after /mcp reconnect — no cleanup, accumulates over days
- VS Code extension crash-loops after VS Code update (chatParticipant manifest error → renderer process dies repeatedly)
- [FEATURE] Allow adding a comment when selecting a valid option in single-select prompts
- [Bug] Anthropic API Error: Request blocked as security policy violation (false positive on cancer research code)
- Feature request: UI localization (l10n) support for Claude Code VS Code extension
- [BUG] Screen scrollback does not work on iTerm2
- Status line: include permission_mode in the stdin payload (mode changes already trigger a refresh, but the field is missing)
- Desktop app (Windows): headless scheduled-task runs hang mid-tool-call (~100% rate) — tool_result never delivered; interactive sessions and CLI claude -p unaffected
- [BUG] Spurious tool-use rejections and background tasks silently marked "stopped" during long sessions
- [BUG] Git proxy returns 403 Forbidden
- [Bug] GitHub secret scanning not being cleaned/removed from codebase
- Approved tool-use prompts (Write/Edit/Bash) are sometimes silently rejected — no error, indistinguishable from a genuine decline; combined/multi-argument commands fail more than split single-argument ones
- [BUG] Desktop app: forked sessions never enable Remote Control, so they never appear on mobile/web
- [BUG] Desktop app: resuming a previously-bridged session doesn't re-mint a Remote Control bridge; work after the first run never reaches mobile/web
- iOS app Code tab stuck at "Setting up a cloud container" on every new instruction — session actually running (display-only stall)
- [BUG] MCP auto-backgrounding at 120s: silently enabled via server flag, undocumented, orphans the result
- settings.json `env` block overrides `env(1)` prefix for CLAUDE_CODE_SUBPROCESS_ENV_SCRUB, breaking the documented per-invocation opt-out and forcing --permission-mode to default
- [Bug] Model emits wrong CJK characters (1-byte UTF-8 neighbors) in Traditional Chinese output
- [BUG] Auto-memory instructions direct an immediate MEMORY.md pointer edit, but the read-before-write gate deterministically rejects it
- [Bug] /remote-control silently no-ops on Pro plan (no output, no error) — cached flag shows remoteEnabled: false
- Remote control: web panel resets a session's effort to account-last-used (Medium), overriding the project effortLevel pin
- Remote control: bare /effort renders nothing in the web UI (selector self-cancels), so a session's current effort is unreadable
- [Bug] Unintended model switching away from Claude Fable
- Auto mode hard-blocks Bash/Write/Edit when safety-classifier model (claude-opus-4-8[1m]) is unavailable — flapping outage, no fallback or retry
- [Bug] Identical API responses despite different models and multiple retry attempts
- Auto mode blocked intermittently for ~20h: safety classifier (claude-opus-4-8[1m]) unavailable, rejecting Bash/PowerShell/Workflow calls
- [Billing Bug] Repeated unauthorized Pro→Max upgrades, second refund denied despite documentation
- VS Code extension hard-deletes conversation transcript on update/restart (no soft-delete, bypasses Recycle Bin)
- [Bug] Tool execution not functioning as agentic agent - reverting to chatbot behavior
- Remote Control: Session creation fails with 401 "Authentication failed" — stale/incorrect cached subscription tier (Windows, v2.1.212)
- [Bug] Anthropic API Error: Safety flagging blocks legitimate cybersecurity assistance requests
- [BUG] Claude Desktop's built-in terminal can never get Apple Events (Automation) permission
- Claude Design agent can't use a connected filesystem MCP — defaults to per-file download cards and loops expensive rework
- [BUG] Remote control error: Remote credentials fetch failed - see debug log
- 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] '- c' flag silently starts new session when no prior session resolves instead of erroring
- Claude Fable 5: AskUserQuestion free-text answer treated as option approval
- [BUG] Windows desktop: file preview & download broken — preview window base-URI blocked by app's own CSP (base-uri 'none')
- [Feature Request] Allow user override for medical content restrictions on capable models
- Desktop app Remote Control repeatedly fails: 'Remote credentials fetch failed' / 'Session creation failed', then silent no-op after reboot; claude.ai session expiry breaks credential refresh
- [FEATURE]
- [Bug] Edit/Write operations store full file content per edit, causing transcript bloat and resume hang on large files
- [BUG] No option to hide/disable the extended thinking display on desktop app (shows inconsistently: visible while streaming, hidden after restart)
- Remote Control: session creation fails — claude.ai serves Cloudflare challenge (cf-mitigated: challenge) to datacenter server IPs
- [FEATURE] VS Code extension: session-list status indicators + notifications when a background session finishes or needs attention
- [BUG] Windows Desktop integrated terminal hardcodes powershell.exe → "Shell exited" (CreateProcess error 1260) when PowerShell 5.1 is blocked by policy
- /remote-control fails with 'remote credentials fetch failed' inside a long-lived session; standalone claude remote-control works
- [BUG] remoteControlAtStartup races OAuth token refresh at cold start → transient 401 'Remote credentials fetch failed' (--rc flag is clean)
- [Bug] Model deployed to production without explicit confirmation during development
- [Bug] Auto-linkified file paths don't validate resolution before clickification
- Remote-control session list in claude.ai/code app shows far fewer entries than sessions actually registered
- [FEATURE] In Claude Code, store recent prompt history and allow for rerunning a recent prompt
- v2.1.205 brew cask ships x86_64-only binary; broken on Apple Silicon under Rosetta
- [BUG] LSP plugins installed before the lspServers manifest-format change load as silent empty shells; `plugin update` reports the broken artifact as up-to-date
- [BUG] Can't close the artifact link in the terminal
- [BUG] Remote Control: POST /bridge returns 401 with fresh full-scope token while createCodeSession and archive succeed (v2.1.212)
- [Bug] Remote control connection failures
- [BUG] sandbox.network.allowedDomains does not block egress — non-allowlisted hosts return 200 with real content (macOS)
- Routines sidebar shows only the fixed task name — no way to surface live per-run status
- [Bug] Incorrectly Prompts for API Credits Despite Active Subscription Usage Limit
- [Bug] Anthropic API Error: Usage credits are required for this model
- [BUG] Composio MCP server stuck on "needs authentication" despite successful browser OAuth
- Fable 5 → API-only: please reconsider a subscription path (👍 + comment here if it affects you)
- [Bug] Anthropic API Error: Usage credits required mid-session
- [Bug] Anthropic API Error: Usage Credits Required for Model Access
- [Bug] Credit usage calculation shows inaccurate percentage on Max plan
- [BUG]b"Usage limit reached" triggered after weekly usage jumped from ~35% to blocked in ~12 minutes
- [Bug] Fable 5 model missing from model picker after API incident
- [Bug] Documentation: Clarify Claude Code policy on impersonation and content restrictions
- [Bug] Anthropic API Error: Usage credits required despite extended plan validity
- the issue guys is this you are a professional company you...
- [BUG] Fable 5 [1m] prompts 'usage credits required' during active 1M promo window (Jul 17, promo extended to Jul 19)
- [BUG] Fable 5 requires API credits before metering on Jul 19
- Allow Slack bots to trigger Claude Tag
- Add dir="auto" to assistant-message div for RTL language support
- I appreciate you reaching out, but I need clarification to help you properly. Your message doesn't contain a specific bug report or technical issue that I can convert into a GitHub issue title. To create an appropriate issue title for Claude Code, please
- [Bug] Anthropic API Error: Fable 5 model unavailable in CLI mode while accessible in web interface
- [Bug] Anthropic API: Model unavailability without notice breaks production workflows
- API key scoping: differentiate application (API-only / Claude Code / Both)
- [BUG] Claude Desktop crashes/restarts when Google Drive virtual drive unmounts during file-index scan
- [Bug] Anthropic API Error: Safety filtering incorrectly blocks Rust transpiler code analysis
- Per-routine Runs panel shows only timestamp + generic "Completed" status, no per-run title
- [Bug] Claude Fable 5 returns usage credit error while Claude 4.8 Opus works normally in both claude.ai and claude code
- [Bug] Misleading error message about usage credits when billing cycle not yet active
- Feature request: in-app font/text size setting for accessibility (low vision)
- [Bug] Git detection fails in desktop app despite Git being installed and in PATH
- [MODEL] Claude refused accept that you could solve an equation using the transitive property of math, where a formula with 2 known values and one unknown could be used to calculate the unknown value
- [BUG] Forked sessions aren't grouped in the session picker
- [Bug] Unable to access Claude models - authentication or API error
- [BUG] Cowork incompatible with Universal Audio Apollo (UAD kernel drivers) on Windows 11 Pro — Hyper-V conflicts with pro audio hardware
- [FEATURE] Surface the teleport command ("Open in CLI") directly in the Slack session message
- 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? For example: - What error message did you encounter? - What were you trying to do when the issue occurr
- [FEATURE] VS Code extension: option to disable Up/Down arrow keys switching between past sessions in chat input
- [Feature Request] Reduce over-flagging of benign academic content in safety filters
- [BUG] Plugin and marketplace source refs not surfaced in UI — users cannot see which channel or plugin version they are tracking
- [BUG] Subagent card stays 'running' after completion notification is delivered; only manual stop freezes it, then persists as a ghost card visible from another session
- Built-in workflows (code-review) pin no model: every agent inherits the session model, and local .claude/workflows can't shadow built-in names
- 🐛 [CRITICAL] Workspace VM Service Crash + Memory Leak: 18+ Processes, 2.5GB RAM, Complete Freeze
- Reviewing image evidence is painful: delivered files lack open/copy-path affordances and can't be referenced back
- [BUG] All running sessions segfault simultaneously on macOS wake from deep sleep (Bun 1.4.0 GC socket finalizer, SIGSEGV at 0x4)
- [Feature Request] Add settings.json toggle to suppress footer hint row
- [BUG]
- Feature request: let a successful delivery-tool call (e.g. a messaging MCP reply) satisfy the turn's visible-output requirement
- /model picker: Enter persists the choice globally — should default to session scope like /effort
- I appreciate you explaining the context, but I need to clarify my purpose: I'm designed to help generate GitHub issue titles for Claude Code (Anthropic's CLI tool) based on bug reports. If you're reporting a bug in Claude Code itself, please provide: 1. W
- [Bug] Incorrect token usage comparison between Sonnet 4.6 and Sonnet 5 in model advisor
- Input-area git chip: distinguish "Commit changes" (dirty tree) vs "Push changes" (ahead of upstream)
- Model behavior: Sonnet 5 recommended a security control with no enforcement value, despite explicit safety-critical project context (session evidence + transcript line included)
- [BUG] Reinstalling Claude Desktop on Windows wipes Code tab session history (no warning, no recovery)
- [BUG] task_reminder nudge fired mid-tool-loop rewrites cached history (near-total rebuild per firing in autonomous sessions); 29% of sessions double-write the opening context — 3-week measured audit
- I don't see a bug report in your message to analyze. Please provide the bug report details so I can generate an appropriate GitHub issue title.
- You've hit your session limit · resets 9:20pm (America/New_York)
- [Bug] Cyber safeguard pipeline fails end-to-end in one day: 5 FP refusals on own-code defensive review, the appeal draft itself flagged, CVP denial-by-template, and 5 auto-replies (0 humans) at usersafety@
- [FEATURE] Change the session's default working directory mid-session
- [Bug] pdf-viewer plugin: local PDFs always rejected — MCP roots never populated + Windows file:// path mangling (C:\C:\...)
- Auto-reconnect after wake exhausts after 3 attempts (~6s), no further retry
- Remote-control bridge auto-registration silently stops after app update (session stays connected regardless)
- Orphaned duplicate session runner processes after Desktop App restart
- Mobile client shows infinite loading spinner instead of an error when the session runner has died
- [FEATURE] Option to hide the worktree card(s) shown in a session
- [BUG] Cloud Cowork sessions provisioned without remote-devices MCP despite authenticated device bridge — signCreateSessionBind not_registered, silent unbound fallback
- Allow skills to be hot-reloaded without restarting the session
- MCP JSON Schema: additionalProperties `{}` normalized to `false`, breaking z.record() fields
- Background tasks mass-killed by memory-pressure reaper on Linux hosts with low MemFree but high MemAvailable (PSI ~0)
- 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
- 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
- [BUG] Cowork: folders attached in Project → Context are not mounted in new chat 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
- [FEATURE] Mobile app Code tab: no Pinned sessions section, desktop/web session pins never surface on mobile
- [BUG] Claude Desktop (Windows): orphaned processes after close block relaunch
- [withdrawn] filed in error — deletion requested
- [BUG] Desktop app microphone dictation ignores "language" setting — Ukrainian speech transcribed as gibberish
- /model saves ANSI formatting fragment into settings.json model value (e.g. "claude-fable-5[1m]")
- [BUG] Code sessions started via Dispatch don't appear in mobile Dispatch list
- [BUG] Native installer does not add ~/.local/bin to PATH on Pop!_OS, despite reporting success
- stream-json: result event `.result` drops all but the first text chunk when one assistant message streams as multiple events
- Scratchpad temp dir hardcoded to /private/tmp, ignores $TMPDIR, no config override
- [BUG] Fable 5 → Opus 4.8 mid-session safeguard auto-switch makes the post-switch model re-spawn duplicate agents (double token burn)
- Desktop app: Make suggested prompts interactive (press Enter to execute)
- [Bug] TUI doesn't restore terminal state on SIGTSTP; suspend + paste wedges terminal
- "Ultracode" in the /effort menu is easily mistaken for an effort level above Max
- Desktop app sidebar should show all local sessions from ~/.claude/projects/, not just sessions started in the app
- [BUG] Stray SGR mouse-report escape codes leak into input during fullscreen TUI mode
- [BUG] スケジュールタスクの実行履歴パネルで結果をクリックすると表示が消える
- Remote Control: stale environment registrations cannot be removed from claude.ai/code picker
- [FEATURE] Add interpolation for ANTHROPIC_CUSTOM_HEADERS
- @import in an ancestor CLAUDE.md does not expand (subdirectory launch)
- [BUG] VS Code extension: Alt+K / Ctrl+Esc don't focus the input when the Claude panel is in an auxiliary window; at-mention is broadcast to all visible panels
- Model silently normalizes user-supplied URL, then contradicts user based on substituted domain
- [BUG] Embedded ugrep OOMs on bounded-repeat regex while Bash grep is silently shadowed (Linux, 2.1.205-2.1.212)
Resolved issues (178)
- [Bug] Claude Code fails to review iOS app code
- [FEATURE] Add localization (l10n) support for extension UI strings (e.g. permission dialogs)
- Remote Control: disconnect crashes (session_url undefined) → session accumulates → new connections fail (Session creation failed / Remote credentials fetch failed), one session stuck even after re-auth
- [Feature Request] Configurable verbs for turn duration display
- [BUG] Unable to connect to API (ConnectionRefused) after uninstalling MCP tools — network and Node.js confirmed healthy
- Backup retention (keep-last-5) evicts the last good .claude.json after concurrent-write corruption, making config loss permanent
- [Bug] Model downgrade to Opus without user action
- [Bug] Safeguards flag legitimate UI development code with Fable 5
- [FEATURE] Implement automatic cleanup of old Claude versions during updates
- [BUG] Missing HCS services: HNS, vmcompute, vfpext - Cowork does not work on Windows 11 Pro
- Auto-mode classifier: incorrect denial reasoning on git commit, then unrelated transient error on identical retry
- [BUG] Remote Control: Messages get permanently stuck in queue (not just delayed)
- [Bug] Overly aggressive safeguard flags during legitimate software development tasks
- [Feature Request] Document respectGitignore and fileSuggestion settings with UI feedback for filtered files
- Desktop app /mcp gallery lacks reauthenticate state and per-session server visibility (vs terminal)
- [BUG] Desktop task panel: subagent resumed via SendMessage has no Running card — original card stays Completed while the execution runs
- [BUG] Reconnecting an existing remote MCP connector in Desktop does nothing after a successful OAuth round trip — only remove-and-re-add works
- [BUG] Organization missing in switcher on platform.claude.com
- [BUG] Model fabricates content-policy text in tool result and user message (false-positive hallucination, Claude Sonnet 5)
- This doesn't appear to be a bug report for Claude Code. If you have an actual technical issue with the Claude Code CLI tool, please provide: 1. What you were trying to do 2. What error or unexpected behavior occurred 3. Steps to reproduce the problem 4. A
- [BUG] claude.ai connector ingestion silently drops any tool with inputSchema >16,384 bytes; refresh path applies no limit
- [BUG] : claude.ai voice mode: custom MCP connector tools fail with "tool is not registered" (text mode works in the same chat)
- [DOCS]
- [BUG] MCP tool-result images are not visible to the model on the same turn as the tool call (Claude Desktop, Windows)
- [BUG] Conta Pro válida (até 06/2027) aparecendo como Free após falha em upgrade para Max; Fin não escala para suporte humano
- Feature idea: Donate unused weekly usage credits to nonprofits
- [BUG] str_replace silently drops the adjacent line when inserting a record near a line boundary (confirmed twice, data-integrity risk)
- [BUG] Claude Science Unable to Access GPU on WSL2
- feat: API-level health check dashboard with endpoint timeline visualization
- [BILLING] Claude for Startups credits stranded on suspended Console org — migration to active org unresolved for weeks
- [Bug] Excessive token consumption exceeding expected usage patterns
- [Bug] Fable 5 flag causes repeated errors on every invocation
- [Bug] API Request Flagged When Inspecting Error Logs in GNSS Application
- [Bug] Session audit with Fable causes permission-related behavioral issues
- [Bug] Incorrect model routing for UI tasks
- My query got flagged by Fable guardrails. It should not have been flagged.
- [Bug] Safeguard blocks triggering excessively on all tasks
- [Bug] Overly Restrictive Safety Constraints Blocking Valid Operations
- [Bug] Agentic reasoning produces inferior outputs compared to alternative models on fact-checking tasks
- [BUG] Touchscreen scrolling injects repeated aN;NaNm fragments into prompt input
- I don't see a bug report in your message - you've only provided a session ID. Please share the actual bug report details so I can generate an appropriate GitHub issue title for you.
- MacOS Claude in Chrome — extension never connects; list_connected_browsers and tabs_context_mcp always return "Browser extension is not connected"
- [BUG] Claude Desktop failed to launch on Windows 11 Pro 25H2 (OS build 26200.8246)
- Plugin Submission: claude-idle-alert
- Write tool fails immediately in local VS Code despite Write(**) in permissions.allow — Edit works fine
- Categorized regression analysis: Opus 4.7
- VSCode mcp.json gallery and settings.json mcpServers silently launch duplicate MCP server processes for the same name
- Session list PR status chip always renders greyed out despite gh + backend reporting correct state
- [BUG] Agent still misspells .claude -> .claire creating stray dir on v2.1.169 (recurrence of #31493 / #31984)
- [BUG] - Windows: PowerShell tool pre-validation intermittently fails with pwsh exited with code 1: the command line is too long / pwsh timed out after 5000ms, blocking shell commands behind approval-prompt loops
- [FEATURE] 桌面版输入框布局切换：支持经典模式（输入框跟随对话流）
- Content filtering incorrectly blocking requests involving the Declaration of Independence
- Babysit agents stop with 'socket connection closed unexpectedly' API error
- skillOverrides: "off" does not block explicit slash command invocation
- Bug: Stored memory directives (MEMORY.md) are ignored during fast state processing, causing false infrastructure alerts
- [BUG] [Claude Code for VS Code] ESC during IME composition cancels the running task in VS Code extension (root cause located)
- [Feature request] Expose --channels flag from Claude Code Desktop app launch (UI / config / URL scheme)
- [BUG] Durable CronCreate jobs are project-cwd-scoped and fire into unrelated sessions sharing that directory; tool defaults to durable without confirming scope
- [BUG] /clear drops ultracode (model reverts to non-ultracode) while the corner effort indicator still shows ultracode
- [BUG] Claude Desktop app: Remote Control never reattaches existing sessions after a WiFi drop — mints a new auth token per reconnect (99 accumulated, unrevocable); CLI works, Desktop app doesn't
- [BUG] PR status badge is shown in every session's composer, not only the session that created the PR
- [BUG] Cowork feature executed PowerShell that removed AMD display driver without user consent
- [Bug] Advisor mode incorrectly routes to Opus when Opus advisor is enabled
- [Bug] Tool invocation parsing failed: Invalid XML structure in Bash tool call
- [BUG] Create button remains grayed out when creating a Briefing Routine with Google Calendar, Gmail, and Slack connectors
- [BUG] Report: Claude Code VS Code Extension crashes with exit code 3221225477 on Windows 11 x64
- [BUG] Subagents return only "Done" with no output when dispatched for search/research tasks (Opus 4.8)
- [FEATURE] Allow configurable OAuth redirect URI (host + path), not just callbackPort, in MCP server definitions
- `.claude/` edits prompt on every edit in acceptEdits mode; `permissions.allow` rules and the per-session option don't suppress it (2.1.169)
- [Bug] TDD writes KNOWN_RED tests masking actual CLI exit code failures
- [BUG] it's a pice of shit!!!
- [BUG] .mcp.json env var substitution: unset variables silently suppress trust prompts for ALL servers
- [FEATURE] Dockable side chat: embed it as a resizable right-hand panel in the desktop app instead of a floating window
- Permission rules should (optionally) evaluate against the original input when a PreToolUse hook returns updatedInput
- [BUG] API Error: Extra usage is required for 1M context · enable extra usage at claude.ai/settings/usage, or use --model to switch to standard context
- [Opus 4.7 + 4.8] Recurring instruction-following + spec-bypass + conditional-correction-framing failures across many sessions
- Allow disabling built-in PR number display on status line
- [Bug] Anthropic API Error: Tool result without corresponding tool use block
- claude.ai web slows down as stale scheduled-routine run cards accumulate (showing 137 'running' tasks)
- Smart auto-compact — skip if session is ending
- [Bug] Tool use false positive triggers repeated blocks on benign prompts
- [Bug] Anthropic API Error: False Positive AUP Violation on Legitimate Academic Manuscript Analysis
- Context limit clear doesnt do anything
- MCP SSE server: tools/call fails with -32602 despite valid connection and correct schemas
- Plugin skill names with non-ASCII (e.g. Japanese) characters are sanitized to hyphens, causing identifier collisions and "Unknown skill" on Skill-tool invocation
- [BUG] Empty chat, single 'hi' message consumes 47.7k tokens
- Allow model selection for Slack-triggered Claude Code sessions
- [FEATURE] Add minimize / collapse control to side-chat panels (long-running sessions stack visual context)
- Add SessionRename (PreSessionRename / PostSessionRename) hook event
- Regression: compound && commands prompt for approval even when all segments are individually allowlisted (v2.1.158–2.1.168, Windows)
- [BUG] Claude Code on the web: `us.sentry.io` blocked under Trusted egress (403 `host_not_allowed`) — `*.sentry.io` missing from the enforced allowlist despite being a documented Trusted default
- [BUG] Managed Agents git push to non-claude/* branch returns HTTP 403 with App-installation token
- [BUG]
- Bash tool (fish): block constructs (`for…end`, `if…end`) fail inline with `parse error near 'end'` though valid in fish
- [BUG] Failed payment still upgrades account to Pro plan via Claude Code /login
- [BUG] In VSCode, claudeProcessWrapper doesn't work with .cmd wrapper
- 'manual mode on' indicator is invisible to the model: no context injection, main-loop behavior unchanged
- [BUG] OSC 8 file-path hyperlinks use a scheme-less URI → macOS "The application can't be opened. -50"
- [BUG] Cowork (macOS): connected folders are no longer writable-mounted into the workspace sandbox since the new mandatory write-consent (~Jul 8, 2026) — device bridge works, but in-place editing is gone
- x
- [/design-review] --guide mode shows too many examples
- [FEATURE] Add localization (l10n) support for extension UI strings (e.g. permission dialogs)
- [FEATURE]
- Desktop preview pane can't render SendUserFile attachments outside the session worktree — misleading "deleted or moved" error
- [BUG] Can't close the artifact link in the terminal
- [BUG] Fable 5 [1m] prompts 'usage credits required' during active 1M promo window (Jul 17, promo extended to Jul 19)
- [BUG] Fable 5 requires API credits before metering on Jul 19
- [Bug] Anthropic API: Model unavailability without notice breaks production workflows
- [FEATURE] Allow sending a fresh (zero-message) session to the background / agent view without first exchanging a message
- Input-area git chip: distinguish "Commit changes" (dirty tree) vs "Push changes" (ahead of upstream)
- Claude Desktop repo/branch chip doesn't update after EnterWorktree switches into a worktree
- Desktop app crashes and not reopen
- In-app browser view hijacks main window and kills active API/MCP connections (Windows, v2.1.20x)
- [Bug] Federated learning security research incorrectly flagged as cybersecurity work
- [Bug] False positive content policy flag on non-restricted content
- [Bug] Tool execution creates unwanted files and directories, causing simple tasks to take hours
- [Bug] Misclassification of non-cybersecurity content as security-related
- [Bug] File editor proceeds with modifications despite user rejection
- [Bug] Fable model stops responding on software/API/product coding tasks
- [Bug] Session Initialization Error: All Commands Failing
- [Bug] Unable to reopen HTML files
- [Bug] Claude Code ignores file read requests and generates hallucinated content instead
- [Bug] Tool fails to read cloned repository
- [Bug] Task blocked on 3D path computation for tennis racket geometry
- [Bug] Performance degradation: Extreme slowness during execution
- [Bug] Excessive token consumption during data processing tasks
- [Bug] Unclear or Invalid Issue Report
- I'm not able to generate a GitHub issue title from this message, as it doesn't appear to be a bug report for Claude Code. The message seems to be a comment or question unrelated to the Claude Code CLI tool. If you have a specific bug or issue with Claude
- Allow skills to be hot-reloaded without restarting the session
- [Bug] Anthropic API Error: Unexpected Safeguard Trigger on Unrelated Content
- Voice input (Linux/PulseAudio): audio streamed to STT is ~6× undersampled vs declared 16 kHz → always "no speech detected"
- [BUG] tools.10.model: 'claude-sonnet-4-6' cannot be used as an advisor when the request model is 'claude-opus-4-7'.
- MCP tools inaccessible in --agent mode even with explicit --mcp-config flag
- [Feature Request] Allow biology content for legitimate medical/research use cases
- [BUG] Claude Desktop blurry on high-DPI ultrawide display due to MSIX packaging blocking DPI override
- [Feature Request] Add support for ancient DNA alignment workflows
- [BUG] Built-in Co-Authored-By: Claude commit trailer asserts AI co-authorship by default (contrary to U.S. Copyright Office guidance)
- EnterWorktree tool creates worktrees inside .claude/ directory, breaking slash command and skill discovery
- [BUG] .worktreeinclude silently skips files with non-ASCII characters in their name
- [Feature Request] Actor-based output highlighting: distinguish "user must act" from "assistant is handling"
- Feature suggestion: Culturally diverse / multilingual loading messages in the processing spinner
- [DOCS] [Troubleshooting] Sessions launched from VS Code integrated terminal or any shell that inherited Claude Code env vars — v2.1.170 transcript/resume fix is not mentioned in the troubleshooting or VS Code pages
- [Workflow tool] resume cache is unreachable for nontrivial workflows because LLM dispatchers can't transcribe args byte-exactly
- [Bug] Incorrect Security Classification of Reversible Hardware Modifications
- [Bug] Norwegian number formatting not following writing conventions
- [Feature Request] Enable Anthropic API security scanning for PHI/healthcare data protection
- [BUG] Account restriction appeal flow redirects to /new after Max upgrade + CVP application
- [Bug] Anthropic API: Overly broad cybersecurity classifier flags defensive vulnerability redaction as offensive content
- [FEATURE] Slack plugin: add slack_pin_message / slack_unpin_message tools
- [BUG] 100% CPU / frozen UI during plan mode streaming — auto-mode + fast-mode hot-loop in reactive state
- [BUG] Subagent dispatch prompt and returned result hidden in main thread — collapsed line cannot be expanded (regression after 2.1.160, still in 2.1.170)
- [FEATURE] Slack plugin: add slack_trigger_workflow tool
- [BUG] Regression (v2.1.160+): subagent spawning fails on Bedrock with "thinking.type must be enabled or adaptive" for Claude 4.x models
- [BUG] Agent window fails to connect in VS Code when using AWS Bedrock (CLAUDE_CODE_USE_BEDROCK=true)
- [Bug] CVP-enrolled repo flagged for security review despite receive-only RF tool compliance
- UserPromptSubmit hook timeout is hardcoded to 30s (HN4=30000) with no override; context silently dropped on timeout
- [BUG] Fable 5 safety classifier auto-switches to Opus mid-session during authorized, in-scope security testing
- [MODEL] Your Fable 5 is officially a waste of fucking water, congratulations!
- Fable 5 safety classifier fires model_refusal_fallback on a bare `hello` — scores the static request preamble, not the user message
- [FEATURE] route specific sub-agents to a different API endpoint/key
- --remote-control: model selection in Claude app does not propagate to remote session
- VSCode: Config probe subprocess always times out (60s) on first tab
- [Bug] Fable 5 security classifier incorrectly flags legitimate CSRF/HMAC-protected code as threat
- [Bug] Anthropic API Error: Content Policy Violation on Security Review Request
- Long-session time/state drift: assistant produces wrap-up artifacts with stale 'today/tomorrow' phrasing after date-rollover system-reminder
- [BUG]
- [Feature Request] Allow Claude Code to integrate with security hardening tools like Fable
- [BUG] Desktop: computer-use side-panel dock fires phantom quit event; "Wait for Claude" silently quits app after task; no setting to disable docking (multi-monitor)
- [Bug] Missing Fable 5 option in /advisor command choices
- Claude for Chrome extension: add global 'always allow all actions' setting to bypass per-site permission dialogs
- [BUG] "Thinking" text bullet is half-white when the text is a shade of yellow
- [Feature Request] Enable penetration testing of user code locally
- [Bug] Unable to respond to clarifying questions in multi-turn security audit conversations
- [BUG] UI shows "update available" for latest-channel versions when installed from stable apt repo
- [BUG] Every single attempt at reviewing my codebase triggers fall back to opus 4.8
- [Bug] Workflow tool accepts arguments without validation, causing silent failures with wasted API calls
- [withdrawn] filed in error — deletion requested
- [BUG] Embedded ugrep OOMs on bounded-repeat regex while Bash grep is silently shadowed (Linux, 2.1.205-2.1.212)