ENOSPC: no space left on device
The disk or inode table filled up mid-operation.
62 issues · 4 open · 58 resolved (94%) · first seen Sep 15, 2025
First response · local
What to do now
Most likely: The operating system rejected a file or directory operation.
- Read the first path in the error and verify that it exists and belongs to the expected user.
- Check disk space, permissions, symlinks and whether another process holds the target.
- Reproduce with the smallest affected path before changing project-wide permissions.
These are conservative triage steps, not an official Anthropic fix. Use the issue and workaround evidence below before making a destructive configuration change.
Is this getting better or worse?
This class of problem is holding steady. 22 new reports in the last 90 days vs 29 in the 90 before — -24%. The open backlog peaked at 16 in 2026-06 and sits at 4 today.
Derived by counting each matching issue from its creation date until it closed. First-party
computation over the anthropics/claude-code tracker — the trend is not published
anywhere upstream.
Which builds report this
35 of these reports name the Claude Code build they were running, spanning 23 releases. Heaviest reporters:
- Claude Code v2.1.114
- Claude Code v2.1.162
- Claude Code v2.1.161
- Claude Code v2.1.84
- Claude Code v2.0.76
- Claude Code v2.1.246
- Claude Code v2.1.170
- Claude Code v2.1.177
Report volume, not a defect count: an issue can mention a build without that build having caused the failure. Versions come from the version string in the bug-report template, matched against real published tags.
Do these get fixed?
Median time to close is 31 days across 58 closures. Of the 58 closures with a recorded reason, 10% were closed as completed and 52 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
22 of these issues post a workaround someone says worked. The highest-engagement ones:
- Task runner reports ENOSPC on subprocess output despite disk having free space
- …rsation (new UUID) does NOT durably fix it, contrary to the workaround mentioned here. A new session works for the first command or two (builtins like pass), then the next external process ( , , ) hits ENOSPC — and this…
Found in the thread of #63909 · still open - Bash tool aborts with "temp filesystem ... is full (0MB free)" / ENOSPC when disk is NOT full (macOS)
- …on a volume with abundant real free space and no snapshots. Workarounds observed - Redirecting a command's output to a file under and reading that file avoids it 100% of the time. - Restarting the CLI also clears it, sug…
Found in the description of #65915 · resolved - [BUG] Cowork VM disk full on session start - ENOSPC blocks all Bash commands
- …that still work: Read, Write, Edit, Glob, Grep, MCP tools. Workaround Built a full 22-slide PptxGenJS presentation by writing scripts to the mounted Mac folder and executing them via ( ). This works but is significantly…
Found in the description of #37581 · resolved - [BUG] Startup crash in Docker: ENOSPC from settings file watcher
- …Terminal/Shell Terminal.app (macOS) Additional Information Workaround - Deleting the settings file(s) lets claude start successfully. This is a bit heavy-handed but confirms watching config files is non-essential to cor…
Found in the description of #7624 · resolved - [Bug] Spurious ENOSPC errors in task output capture with racing cleanup deletes
- …making the CLI largely unusable until a lucky clean window. Workaround that reliably dodges it: redirect all command output to a file outside the tasks dir (e.g. cmd ~/out.txt 2 &1; true) and read that file, or otherwise…
Found in the description of #65067 · resolved
Excerpts are quoted from the linked issue so you can judge relevance before opening it. Threads that only ask for a workaround, or report that there is none, are excluded. These are community suggestions, not official guidance from Anthropic — read the full thread before applying one.
Matching issues 1–62
Ranked by community engagement (reactions weighted over comments).
- Task runner reports ENOSPC on subprocess output despite disk having free space
- [BUG] Cowork VM root partition 86% full on fresh image — only 940 MB free for user work
- Bash tool aborts with "temp filesystem ... is full (0MB free)" / ENOSPC when disk is NOT full (macOS)
- darwin-x64: false "temp filesystem is full (0MB free) / ENOSPC" — statfs().bsize=0 makes the empty-output explainer always report disk-full
- [BUG] Infinite logging loop in debug files causes 200GB+ disk usage
- [BUG] Cowork VM disk full on session start - ENOSPC blocks all Bash commands
- ENOSPC: no space left on device
- [BUG]Critical blocker (Max plan) — Claude Code shell bootstrap fails with ENOSPC
- [BUG] Startup crash in Docker: ENOSPC from settings file watcher
- Bash tool falsely reports 'temp filesystem … is full (0MB free)' on any empty-stdout + non-zero-exit command
- [BUG] False ENOSPC error reported for subprocesses with no stdout and non-zero exit code
- [Bug] Spurious ENOSPC errors in task output capture with racing cleanup deletes
- [BUG] Cowork Plugin cache never cleaned up per session, causing sessiondata.img to fill up and all new conversations to fail
- Temp-filesystem preflight false-positives ENOSPC on filesystems with >17.6 TB free (statfs 32-bit truncation)
- [BUG] ## ESCALATION: Claude Code (Opus 4.8) Bash tool emits false "temp filesystem full / 0MB free" ENOSPC despite ~148 GB free, causing wasted token spend
- [BUG] ENOSPC: no space left on device - Cowork workspace stuck at 75% on Windows 10
- Bash tool silently returns empty output when `/tmp/claude-$UID/` exceeds tmpfs quota
- [BUG] Cowork VM root disk (9.6GB) too small for real projects — mounted folder competes with OS for space
- [BUG] Bash tool cannot start: ENOSPC when creating /sessions/.../tmp/claude-XXXX (bootstrap deadlock)
- [Bug] Bash tool output capture fails with false "disk full" (ENOSPC) error on macOS
- [Bug] v2.1.156+ regression: native Read/Bash return fabricated-but-plausible content, triggering agent confabulation cascades
- [BUG] SANDBOX ERROR CODE ENOSPC: no space left on device,
- Background task output file grows unbounded (224GB single file)
- [BUG] Sidebar session history lost when disk reaches ENOSPC — no recovery path
- [BUG] Claude reports negative free space on large disks, due to integer overflow
- [FEATURE] Expose permission picker decisions (rule + option kind) to hooks
- [BUG] Bash tool fails silently when /tmp is full
- [Bug] Keyboard shortcuts broken: CMD+Backspace, CMD+Left/Right, and CMD+V for images
- [BUG] Include: "Cowork VM shows 'no space left on device', persists across new sessions, logout/login, and multiple browser attempts."
- [BUG] File Descriptor Leak in FSWatcher for pending-claude-sessions.json Causes EINVAL Crash
- [BUG] macOS native build: shell-snapshot grep/find/rg shadowing kills bash mid-command (silent truncation); false 'temp filesystem is full (0MB free)' ENOSPC banner from broken statfs (bsize=0)
- [Bug] Bash tool stdout capture fails with spurious ENOSPC on macOS despite ample disk space
- Bash tool silently returns empty output when /tmp/claude-$UID/ exceeds an auto-applied tmpfs quota (systemd ≥256 + kernel ≥6.6)
- Cowork silent fail on Windows 11 Home
- [Feature Request] Use git fixup workflow for amending non-HEAD commits
- [BUG] Claude Code long running 30+ agents for 18h crashes bash
- [BUG] Bash tool silently returns empty output when /tmp is full (ENOSPC)
- [BUG] Cowork ENOSPC / EXDEV on Windows MSIX install — VM bundle fails to download
- [BUG] Cowork VM disk permanently full (ENOSPC) — persists across restarts, new tasks, and re-login
- [BUG] Cowork VM ENOSPC persists across new sessions — Bash tool completely unusable
- [BUG] ENOSPC error_during_execution should provide actionable guidance and not cascade silently
- [Bug] ENOSPC: No space left on device error during file write operation
- [BUG] Claude Code crashes with unhandled ENOSPC error when disk space is low
- [BUG] ENOSPC: no space left on device error during workflow, despite available disk space
- [Bug] Disk Space Exhaustion: File Write Failure (ENOSPC)
- [Bug] Bash tool ENOSPC error on stdout/stderr capture despite available disk space (macOS)
- [BUG] Cowork (Windows): caches fill sessiondata.vhdx; env-based caches can't be self-fixed & orphaned session dirs never cleaned
- [Bug] /goal command fails with "Prompt is too long" error above 200k tokens when 1M context window disabled
- [BUG] Cowork VM session disk fills within hours for scheduled task users — no cleanup, no resize path
- [BUG] --resume fails with error_during_execution when session was auto-archived during idle period
- [Bug] Anthropic API Error: Request Rate Limited - Server Throttling
- [Bug] Anthropic API Error: Server rate limiting during request
- [Bug] Anthropic API Error: Server Rate Limiting During Normal Usage
- [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 - Temporary Request Throttling
- Bug: workspace bash fails with ENOSPC on `/etc/passwd` during session-user provisioning
- [BUG] vm_bundles/claudevm.bundle consumes ~10 GB on macOS, destroying available disk space
- [BUG] On a genuinely full disk, the Bash ENOSPC notice names the session tmpdir instead of the filesystem, and no command can then run to diagnose it
- Windows desktop app: internal scheduler silently drops scheduled-task slots for hours while app is healthy (+ MSIX updater closes app without relaunch; logger dead after ENOSPC)
- [BUG] Fullscreen TUI: failed Bash tool calls drop the entire ⎿ result row (stdout+stderr present in JSONL and tool_result; success path OK)
- Cowork/Workspace EXDEV rename fails within the SAME directory (not just cross-Temp/Roaming) — MSIX install, v1.19367.0.0