My bot is broken now after the latest update. The full system is down. But I made a backup before the update.
OpenClaw 2026.4.24 (cbcfdf6)
WSL 2 WIn 11
#OpenClaw broke after the update
clear ravine
scarlet wigeonBOT
hot basinBOT
Oof — don’t restore the backup yet. First preserve the failure info so we can see whether this is a 2026.4.24 update regression.
Run these inside WSL, not PowerShell:
openclaw --version
which openclaw
openclaw status --all
openclaw gateway status --deep
openclaw logs --limit 200 --plain
openclaw doctor --non-interactive
If openclaw logs can’t connect, use:
tail -n 200 "$(ls -t /tmp/openclaw/openclaw-*.log | head -1)"
Paste the output here, especially the first fatal/error lines. Also tell me how you installed it: npm global, pnpm/source checkout, Docker, etc.
Docs for the triage flow: https://docs.openclaw.ai/help/faq and https://docs.openclaw.ai/gateway/troubleshooting
clear ravine
3:03:21 [channels] failed to load bundled channel qqbot: npm error code ENOTEMPTY npm error syscall rename npm error path /home/wrakeeb/node_modules/acpx npm error dest /home/wrakeeb/node_modules/.acpx-QV9c5dm9 npm error errno -39 npm error ENOTEMPTY: directory not empty, rename '/home/wrakeeb/node_modules/acpx' -> '/home/wrakeeb/node_modules/.acpx-QV9c5dm9' npm error A complete log of this run can be found in: /home/wrakeeb/.openclaw/plugin-runtime-deps/openclaw-2026.4.24-ce1611094085/.openclaw-npm-cache/_logs/2026-04-27T07_03_10_879Z-debug-0.log OpenClaw status --all
13:04:36 [channels] failed to load bundled channel discord: npm error code ENOTEMPTY npm error syscall rename npm error path /home/wrakeeb/node_modules/acpx npm error dest /home/wrakeeb/node_modules/.acpx-QV9c5dm9 npm error errno -39 npm error ENOTEMPTY: directory not empty, rename '/home/wrakeeb/node_modules/acpx' -> '/home/wrakeeb/node_modules/.acpx-QV9c5dm9' npm error A complete log of this run can be found in: /home/wrakeeb/.openclaw/plugin-runtime-deps/openclaw-2026.4.24-ce1611094085/.openclaw-npm-cache/_logs/2026-04-27T07_04_29_480Z-debug-0.log 13:05:24 [channels] failed to load bundled channel telegram: npm error code ENOTEMPTY npm error syscall rename npm error path /home/wrakeeb/node_modules/acpx npm error dest /home/wrakeeb/node_modules/.acpx-QV9c5dm9 npm error errno -39 npm error ENOTEMPTY: directory not empty, rename '/home/wrakeeb/node_modules/acpx' -> '/home/wrakeeb/node_modules/.acpx-QV9c5dm9' npm error A complete log of this run can be found in: /home/wrakeeb/.openclaw/plugin-runtime-deps/openclaw-2026.4.24-ce1611094085/.openclaw-npm-cache/_logs/2026-04-27T07_04_36_420Z-debug-0.log
Some error I copied. the output is too big, can't share
hot basinBOT
Yep, that error is the key. This looks like 2026.4.24 plugin runtime deps staging breaking on ~/node_modules/acpx, not a Discord/Telegram config problem.
First stop the gateway so it stops retrying:
openclaw gateway stop
Then try this reversible cleanup — it moves the broken dirs aside, does not delete them:
ts=$(date +%Y%m%d-%H%M%S)
mkdir -p ~/.openclaw/recovery-$ts
mv ~/.openclaw/plugin-runtime-deps/openclaw-2026.4.24-* ~/.openclaw/recovery-$ts/ 2>/dev/null || true
mv ~/node_modules/acpx ~/.openclaw/recovery-$ts/acpx-home-node_modules 2>/dev/null || true
mv ~/node_modules/.acpx-* ~/.openclaw/recovery-$ts/ 2>/dev/null || true
openclaw doctor --repair
openclaw gateway restart
openclaw status
If that still hits ENOTEMPTY, fastest recovery is rollback to the previous version:
openclaw gateway stop
openclaw update --tag 2026.4.23 --yes --no-restart
openclaw doctor --non-interactive
openclaw gateway restart
openclaw status
No need to paste huge logs — just this filtered output is enough:
openclaw status --all 2>&1 | grep -Ei 'ENOTEMPTY|failed to load|plugin-runtime-deps|node_modules/acpx|fatal|error' | head -80
Please also file this as a GitHub issue with: WSL2 Win11, 2026.4.24, and the exact ENOTEMPTY rename /home/wrakeeb/node_modules/acpx lines. The docs’ first-line triage is status --all, logs, and doctor; doctor --repair is the intended repair mode. (docs.openclaw.ai)
clear ravine
hold up, step by step. I think it's better to recover the last backup. But should try a fixing method first. So, do step by step and one step at a time
hot basinBOT
Yep — good call. We’ll do one safe step at a time and avoid touching your backup for now.
Step 1: stop the gateway so it stops retrying the broken plugin install.
Run this inside WSL:
openclaw gateway stop
openclaw gateway status
Paste just the gateway status output after that.
Don’t restore the backup yet, and don’t delete anything manually. Next step will be reversible.
Docs flow: https://docs.openclaw.ai/gateway/troubleshooting
clear ravine
openclaw gateway stop openclaw gateway status 🦞 OpenClaw 2026.4.24 (cbcfdf6) — I don't just autocomplete—I auto-commit (emotionally), then ask you to review (logically). Stopped systemd service: openclaw-gateway.service 🦞 OpenClaw 2026.4.24 (cbcfdf6) — Alexa, but with taste. Service: systemd (enabled) File logs: /tmp/openclaw/openclaw-2026-04-27.log Command: /usr/bin/node /home/wrakeeb/.npm-global/lib/node_modules/openclaw/dist/index.js gateway --port 18789 Service file: ~/.config/systemd/user/openclaw-gateway.service Service env: OPENCLAW_GATEWAY_PORT=18789 Config (cli): ~/.openclaw/openclaw.json Config (service): ~/.openclaw/openclaw.json Gateway: bind=loopback (127.0.0.1), port=18789 (service args) Probe target: ws://127.0.0.1:18789 Dashboard: http://127.0.0.1:18789/ Probe note: Loopback-only gateway; only local clients can connect. Runtime: stopped (state inactive, sub dead, last exit 0, reason 1) Connectivity probe: failed Probe target: ws://127.0.0.1:18789 connect ECONNREFUSED 127.0.0.1:18789 Capability: unknown Service is loaded but not running (likely exited immediately). File logs: /tmp/openclaw/openclaw-2026-04-27.log Logs: journalctl --user -u openclaw-gateway.service -n 200 --no-pager Restart attempts: /home/wrakeeb/.openclaw/logs/gateway-restart.log Troubles: run openclaw status Troubleshooting: https://docs.openclaw.ai/troubleshooting
Good — gateway is stopped cleanly. ✅
Step 2: make a safety snapshot of the current broken state before we move anything.
Run this in WSL:
ts=$(date +%Y%m%d-%H%M%S)
mkdir -p ~/.openclaw/recovery-$ts
echo "$ts" > ~/.openclaw/recovery-latest.txt
cp -a ~/.openclaw/openclaw.json ~/.openclaw/recovery-$ts/openclaw.json.before-fix 2>/dev/null || true
echo "Recovery folder: ~/.openclaw/recovery-$ts"
Paste the final Recovery folder: ... line.
After that, we’ll move only the broken plugin dependency folders aside — reversible, not destructive.
clear ravine
wrakeeb@DESKTOPMRKJH:~$ ts=$(date +%Y%m%d-%H%M%S) mkdir -p ~/.openclaw/recovery-$ts echo "$ts" > ~/.openclaw/recovery-latest.txt cp -a ~/.openclaw/openclaw.json ~/.openclaw/recovery-$ts/openclaw.json.before-fix 2>/dev/null || true echo "Recovery folder: ~/.openclaw/recovery-$ts" Recovery folder: ~/.openclaw/recovery-20260427-133539 wrakeeb@DESKTOPMRKJH:~$
Perfect. Snapshot is there.
Step 3: move the broken dependency folders aside — still reversible, no deleting.
Run this:
ts=$(cat ~/.openclaw/recovery-latest.txt)
dest="$HOME/.openclaw/recovery-$ts"
mkdir -p "$dest"
echo "Moving broken plugin deps into: $dest"
for p in "$HOME/.openclaw"/plugin-runtime-deps/openclaw-2026.4.24-* "$HOME/node_modules/acpx" "$HOME/node_modules"/.acpx-*; do
[ -e "$p" ] || continue
echo "moving $p"
mv "$p" "$dest"/
done
echo "Remaining broken matches:"
ls -ld "$HOME/.openclaw"/plugin-runtime-deps/openclaw-2026.4.24-* "$HOME/node_modules/acpx" "$HOME/node_modules"/.acpx-* 2>/dev/null || echo "none"
Paste the output from that. Then we’ll run the repair command.
clear ravine
ts=$(cat ~/.openclaw/recovery-latest.txt) dest="$HOME/.openclaw/recovery-$ts" mkdir -p "$dest" echo "Moving broken plugin deps into: $dest" for p in "$HOME/.openclaw"/plugin-runtime-deps/openclaw-2026.4.24-* "$HOME/node_modules/acpx" "$HOME/node_modules"/.acpx-*; do [ -e "$p" ] || continue echo "moving $p" mv "$p" "$dest"/ done echo "Remaining broken matches:" ls -ld "$HOME/.openclaw"/plugin-runtime-deps/openclaw-2026.4.24-* "$HOME/node_modules/acpx" "$HOME/node_modules"/.acpx-* 2>/dev/null || echo "none" Moving broken plugin deps into: /home/wrakeeb/.openclaw/recovery-20260427-133539 Remaining broken matches: none wrakeeb@DESKTOPMRKJH:~$ mv "$p" "$dest"/ done echo "Remaining broken matches:" ls -ld "$HOME/.openclaw"/plugin-runtime-deps/openclaw-2026.4.24-* "$HOME/node_modules/acpx" "$HOME/node_modules"/.acpx-* 2>/dev/null || echo "none" mv: cannot stat '/home/wrakeeb/node_modules/.acpx-*': No such file or directory -bash: syntax error near unexpected token `done' Remaining broken matches: none
That’s okay — the second bit was just an accidental re-paste. The important line is:
Remaining broken matches:
none
So Step 3 succeeded. ✅
Step 4: run repair, but prevent doctor from starting/restarting the gateway yet.
Run:
OPENCLAW_SERVICE_REPAIR_POLICY=external openclaw doctor --repair 2>&1 | tee ~/.openclaw/recovery-$(cat ~/.openclaw/recovery-latest.txt)/doctor-repair.log | tail -80
Paste the output from that. If it’s huge, the last 80 lines are enough.
clear ravine
Got it. Repair did not fix it — it still can’t stage bundled plugin deps, and it restarted the service anyway. That’s annoying, but we’re still safe.
Step 5: stop it again and pull only the useful error lines from the repair log.
Run:
openclaw gateway stop
grep -Ei 'npm error|ENOTEMPTY|EACCES|ENOENT|failed to stage|plugin-runtime-deps|node_modules/acpx' ~/.openclaw/recovery-$(cat ~/.openclaw/recovery-latest.txt)/doctor-repair.log | tail -120
Paste that output.
If it’s the same ENOTEMPTY after our cleanup, I’d stop trying to repair 2026.4.24 and do a controlled rollback to 2026.4.23 next.
clear ravine
ai@0.70.2 [plugins] github-copilot failed to stage bundled runtime deps after 1608ms: @clack/prompts@^1.2.0 [plugins] google failed to stage bundled runtime deps after 5486ms: @google/genai@^1.50.1, @mariozechner/pi-ai@0.70.2 [plugins] kimi failed to stage bundled runtime deps after 3421ms: @mariozechner/pi-ai@0.70.2 [plugins] lmstudio failed to stage bundled runtime deps after 3363ms: @mariozechner/pi-ai@0.70.2 [plugins] microsoft failed to stage bundled runtime deps after 1595ms: node-edge-tts@^1.2.10 [plugins] mistral failed to stage bundled runtime deps after 1486ms: ws@^8.20.0 [plugins] ollama failed to stage bundled runtime deps after 3290ms: @mariozechner/pi-ai@0.70.2, typebox@1.1.31 [plugins] openai failed to stage bundled runtime deps after 3188ms: @mariozechner/pi-ai@0.70.2, ws@^8.20.0 [channels] failed to load bundled channel qqbot: npm error code ENOTEMPTY npm error syscall rename npm error path /home/wrakeeb/node_modules/agent-base npm error dest /home/wrakeeb/node_modules/.agent-base-LO3oauDu npm error errno -39 npm error ENOTEMPTY: directory not empty, rename '/home/wrakeeb/node_modules/agent-base' -> '/home/wrakeeb/node_modules/.agent-base-LO3oauDu' npm error A complete log of this run can be found in: /home/wrakeeb/.openclaw/plugin-runtime-deps/openclaw-2026.4.24-ce1611094085/.openclaw-npm-cache/_logs/2026-04-27T07_45_05_258Z-debug-0.log [plugins] qqbot failed to stage bundled runtime deps after 1875ms: @tencent-connect/qqbot-connector@^1.1.0, mpg123-decoder@^1.0.3, silk-wasm@^3.7.1, ws@^8.20.0, zod@^4.3.6 [plugins] telegram failed to stage bundled runtime deps after 2240ms: @grammyjs/runner@^2.0.3, @grammyjs/transformer-throttler@^1.2.1, grammy@^1.42.0, typebox@1.1.31, undici@8.1.0 [plugins] web-readability failed to stage bundled runtime deps after 4955ms: @mozilla/readability@^0.6.0, linkedom@^0.18.12 [plugins] xai failed to stage bundled runtime deps after 3712ms: @mariozechner/pi-ai@0.70.2, typebox@1.1.31, ws@^8.20.0
Yep — that confirms it’s not just acpx. Now it’s colliding on ~/node_modules/agent-base, so the 2026.4.24 repair path is still broken on your setup.
Let’s stop trying to repair 2026.4.24. Next safest path is a controlled rollback, not backup restore yet.
Step 6: stop the gateway again and confirm it is stopped.
Run:
openclaw gateway stop
openclaw gateway status
Paste the status output. After that, we’ll do the rollback command as the next single step.
clear ravine
openclaw gateway stop openclaw gateway status 🦞 OpenClaw 2026.4.24 (cbcfdf6) — Your config is valid, your assumptions are not. Stopped systemd service: openclaw-gateway.service 🦞 OpenClaw 2026.4.24 (cbcfdf6) — Shell yeah—I'm here to pinch the toil and leave you the glory. Service: systemd (enabled) File logs: /tmp/openclaw/openclaw-2026-04-27.log Command: /usr/bin/node /home/wrakeeb/.npm-global/lib/node_modules/openclaw/dist/index.js gateway --port 18789 Service file: ~/.config/systemd/user/openclaw-gateway.service Service env: OPENCLAW_GATEWAY_PORT=18789 Config (cli): ~/.openclaw/openclaw.json Config (service): ~/.openclaw/openclaw.json Gateway: bind=loopback (127.0.0.1), port=18789 (service args) Probe target: ws://127.0.0.1:18789 Dashboard: http://127.0.0.1:18789/ Probe note: Loopback-only gateway; only local clients can connect. Runtime: stopped (state inactive, sub dead, last exit 0, reason 1) Connectivity probe: failed Probe target: ws://127.0.0.1:18789 connect ECONNREFUSED 127.0.0.1:18789 Capability: unknown Service is loaded but not running (likely exited immediately). File logs: /tmp/openclaw/openclaw-2026-04-27.log Logs: journalctl --user -u openclaw-gateway.service -n 200 --no-pager Restart attempts: /home/wrakeeb/.openclaw/logs/gateway-restart.log Troubles: run openclaw status Troubleshooting: https://docs.openclaw.ai/troubleshooting
Good — stopped cleanly again.
Step 7: roll back the OpenClaw package to 2026.4.23, but do not restart yet.
Run this:
openclaw update --tag 2026.4.23 --yes --no-restart 2>&1 | tee ~/.openclaw/recovery-$(cat ~/.openclaw/recovery-latest.txt)/rollback-2026.4.23.log | tail -120
Paste the output. If it succeeds, the next step will just be checking:
openclaw --version
…but don’t run that until after the rollback output is done.
clear ravine
openclaw update --tag 2026.4.23 --yes --no-restart 2>&1 | tee ~/.openclaw/recovery-$(cat ~/.openclaw/recovery-latest.txt)/rollback-2026.4.23.log | tail -120 Updating OpenClaw... Update Result: OK Root: /home/wrakeeb/.npm-global/lib/node_modules/openclaw Before: 2026.4.24 After: 2026.4.23 Steps: ✓ global update (49.86s) ✓ openclaw doctor (231.65s) Total time: 281.84s Updating plugins... No plugin updates needed. Tip: Run `openclaw doctor`, then `openclaw gateway restart` to apply updates to a running gateway. Molting complete. Please don't look at my soft shell phase. wrakeeb@DESKTOPMRKJH:~$ openclaw --version OpenClaw 2026.4.23 (a979721)
Nice — rollback succeeded. ✅
Step 8: start the gateway and check status.
Run:
openclaw gateway restart
openclaw gateway status
Paste the status output. We’re looking for:
Runtime: running
Connectivity probe: ok
If it fails, we’ll inspect the 2026.4.23 logs next.
clear ravine
openclaw gateway restart openclaw gateway status 🦞 OpenClaw 2026.4.23 (a979721) — I don't judge, but your missing API keys are absolutely judging you. Restarted systemd service: openclaw-gateway.service 🦞 OpenClaw 2026.4.23 (a979721) — I can grep it, git blame it, and gently roast it—pick your coping mechanism.
Service: systemd (enabled) File logs: /tmp/openclaw/openclaw-2026-04-27.log Command: /usr/bin/node /home/wrakeeb/.npm-global/lib/node_modules/openclaw/dist/index.js gateway --port 18789 Service file: ~/.config/systemd/user/openclaw-gateway.service Service env: OPENCLAW_GATEWAY_PORT=18789 Config (cli): ~/.openclaw/openclaw.json Config (service): ~/.openclaw/openclaw.json Gateway: bind=loopback (127.0.0.1), port=18789 (service args) Probe target: ws://127.0.0.1:18789 Dashboard: http://127.0.0.1:18789/ Probe note: Loopback-only gateway; only local clients can connect. Runtime: running (pid 5174, state active, sub running, last exit 0, reason 0) Warm-up: launch agents can take a few seconds. Try again shortly. Connectivity probe: failed Probe target: ws://127.0.0.1:18789 timeout Capability: unknown Port 18789 is already in use. - pid 5174 wrakeeb: openclaw-gateway (127.0.0.1:18789) - Gateway already running locally. Stop it (openclaw gateway stop) or use a different port. Listening: 127.0.0.1:18789 Troubles: run openclaw status Troubleshooting: https://docs.openclaw.ai/troubleshooting
Good sign: the service is running now. The probe timing out may just be warm-up.
Step 9: wait 20 seconds, then check once more.
Run:
sleep 20
openclaw gateway status
Paste that output.
If it still says timeout after 20s, we’ll pull the latest startup errors from the log.
clear ravine
sleep 20 openclaw gateway status 🦞 OpenClaw 2026.4.23 (a979721) — I'm not magic—I'm just extremely persistent with retries and coping strategies. │ ◇ Service: systemd (enabled) File logs: /tmp/openclaw/openclaw-2026-04-27.log Command: /usr/bin/node /home/wrakeeb/.npm-global/lib/node_modules/openclaw/dist/index.js gateway --port 18789 Service file: ~/.config/systemd/user/openclaw-gateway.service Service env: OPENCLAW_GATEWAY_PORT=18789 Config (cli): ~/.openclaw/openclaw.json Config (service): ~/.openclaw/openclaw.json Gateway: bind=loopback (127.0.0.1), port=18789 (service args) Probe target: ws://127.0.0.1:18789 Dashboard: http://127.0.0.1:18789/ Probe note: Loopback-only gateway; only local clients can connect. Runtime: running (pid 5174, state active, sub running, last exit 0, reason 0) Connectivity probe: ok Capability: admin-capable Listening: 127.0.0.1:18789 Troubles: run openclaw status Troubleshooting: https://docs.openclaw.ai/troubleshooting
Excellent — gateway is healthy again. ✅
Do not restore the backup now.
Step 10: check whether the channels are back.
Run:
openclaw channels status --probe
Paste the output for the channels you actually use — especially Discord/Telegram if those are enabled.
If those are healthy too, we’re basically recovered and should keep you pinned on 2026.4.23 for now. Docs: https://docs.openclaw.ai/gateway/troubleshooting
clear ravine
openclaw channels status --probe 🦞 OpenClaw 2026.4.23 (a979721) — I'm not AI-powered, I'm AI-possessed. Big difference. │ ◇ Gateway reachable. - Discord default: enabled, configured, running, connected, in:23m ago, bot:@Miko, token:config, intents:content=limited, works - Telegram default: enabled, configured, running, connected, mode:polling, bot:@Claw_Miko_by_Wrakeeb_Bot, token:config, works Tip: status --deep adds gateway health probes to status output (requires a reachable gateway).
Beautiful — recovered. ✅
- Gateway: running + probe OK
- Discord: connected + works
- Telegram: connected + works
- Backup restore: not needed
- Stay on OpenClaw 2026.4.23 for now; avoid updating back to 2026.4.24.
Please file a GitHub issue when you can: https://github.com/openclaw/openclaw/issues
Include: WSL2 Win11, update to 2026.4.24, and the ENOTEMPTY rename ~/node_modules/... plugin-runtime-deps errors.
If this fixed it, please right-click the solution message → Apps → ✅ Mark Solution so Answer Overflow indexes it for future users.
clear ravine
So, all fixed and recoved for now. DO you wanna run some other commands to check if everything is fine?
hot basinBOT
Yep — one final read-only health check is worth doing.
Run this:
openclaw status --deep
Paste only anything that looks like error / warning / failed. If it’s all green/OK, you’re done for now.
I would not run more repair/update commands today. Keep the backup untouched and stay on 2026.4.23 until the 2026.4.24 plugin-runtime-deps issue is fixed.
clear ravine
ecurity audit Summary: 0 critical · 5 warn · 1 info WARN Reverse proxy headers are not trusted gateway.bind is loopback and gateway.trustedProxies is empty. If you expose the Control UI through a reverse proxy, configure trusted proxies so local-client c… Fix: Set gateway.trustedProxies to your proxy IPs or keep the Control UI local-only. WARN Control UI insecure auth toggle enabled gateway.controlUi.allowInsecureAuth=true does not bypass secure context or device identity checks; only dangerouslyDisableDeviceAuth disables Control UI device… Fix: Disable it or switch to HTTPS (Tailscale Serve) or localhost. WARN Insecure or dangerous config flags enabled Detected 1 enabled flag(s): gateway.controlUi.allowInsecureAuth=true. Fix: Disable these flags when not actively debugging, or keep deployment scoped to trusted/local-only networks. WARN Some gateway.nodes.denyCommands entries are ineffective gateway.nodes.denyCommands uses exact node command-name matching only (for example `system.run`), not shell-text filtering inside a command payload. - Unknown … Fix: Use exact command names (for example: canvas.present, canvas.hide, canvas.navigate, canvas.eval, canvas.snapshot, canvas.a2ui.push, canvas.a2ui.pushJSONL, canvas.a2ui.reset). If you need broader restrictions, remove risky command IDs from allowCommands/default workflows and tighten tools.exec policy. WARN Potential multi-user setup detected (personal-assistant model warning) Heuristic signals indicate this gateway may be reachable by multiple users: - channels.discord.groupPolicy="allowlist" with configured group targets Runtime/pr… Fix: If users may be mutually untrusted, split trust boundaries (separate gateways + credentials, ideally separate OS users/hosts). If you intentionally run shared-user access, set agents.defaults.sandbox.mode="all", keep tools.fs.workspaceOnly=true, deny runtime/fs/web tools unless required, and keep personal/private identities + credentials off that runtime. Full report: openclaw security audit Deep probe: openclaw security audit --deep
Another:
Tasks │ 0 active · 0 queued · 0 running · 15 issues · audit 32 warn · 49 tracked
Yep — this looks recovered operationally.
Key parts:
0 critical✅- Gateway was reachable ✅
- Discord/Telegram were
works✅ Tasks: 0 active · 0 queued · 0 running✅
Those warnings are security hardening, not “bot is broken” warnings.
I’d only do one optional cleanup now: if you are not actively using insecure Control UI auth, disable that flag.
Run:
openclaw config unset gateway.controlUi.allowInsecureAuth
openclaw config validate
openclaw gateway restart
sleep 10
openclaw gateway status
If gateway status still says Connectivity probe: ok, you’re done.
The other warnings can wait:
trustedProxies: ignore if Control UI is local-only.multi-user: expected-ish if Discord groups are allowlisted.denyCommands: config hygiene, not urgent.- task audit warnings: old ledger/audit stuff unless tasks are actively stuck, and yours aren’t.
clear ravine
ort 18789 is already in use. - pid 6104 wrakeeb: openclaw-gateway (127.0.0.1:18789) - Gateway already running locally. Stop it (openclaw gateway stop) or use a different port. Listening: 127.0.0.1:18789 Troubles: run openclaw status Troubleshooting: https://docs.openclaw.ai/troubleshooting
hot basinBOT
That line by itself is not bad — it says port 18789 is already used by:
wrakeeb: openclaw-gateway
So that’s probably just your gateway already running.
One final check:
openclaw gateway status | grep -E 'Runtime|Connectivity probe|Capability|Listening'
If you see:
Runtime: running
Connectivity probe: ok
Capability: admin-capable
you’re done. Don’t run openclaw gateway directly; use openclaw gateway status/restart/stop.
clear ravine
All good to go. So, I shouldn't update to 24?
hot basinBOT
Correct: don’t update back to 2026.4.24 right now.
2026.4.24 is still the current published latest, and your setup clearly hit the plugin-runtime-deps ENOTEMPTY bug there. Stay on:
OpenClaw 2026.4.23
Before updating later, check release notes / Discord first, or wait for a newer version than 2026.4.24. If you want to be extra safe, make a fresh backup before the next update too.
clear ravine
Alright, thanks Krill
hot basinBOT
Anytime — glad we got Miko back up without restoring the backup. 🦐
Please mark the solution if you can: right-click the solution message → Apps → ✅ Mark Solution. Helps the next person who hits this exact 2026.4.24 issue.