#help

1 messages · Page 1 of 1 (latest)

stuck lion
#

gents
┌────────────┬────────────────┬──────────┬──────────┬─────────────────────────────────────────────────────────────────┐
│ Agent │ Bootstrap file │ Sessions │ Active │ Store │
├────────────┼────────────────┼──────────┼──────────┼─────────────────────────────────────────────────────────────────┤
│ main │ ABSENT │ 2 │ 18m ago │ ~.openclaw\agents\main\sessions\sessions.json

vague nestBOT
#

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> ✅ Mark Solution

stuck lion
#

─────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Version │ 2026.2.24 │
│ OS │ windows 10.0.22631 (x64) │
│ Node │ 24.14.0 │
│ Config │ ~.openclaw\openclaw.json │
│ Dashboard │ http://127.0.0.1:18789/ │
│ Tailscale │ off │
│ Channel │ stable (default) │
│ Update │ pnpm · npm update 2026.2.25 │
│ Gateway │ local · ws://127.0.0.1:18789 (local loopback) · unreachable (connect failed: connect │
│ │ ECONNREFUSED 127.0.0.1:18789) │
│ Security │ Run: openclaw security audit --deep │
│ Gateway self │ unknown │
│ Gateway service │ Scheduled Task installed · registered · stopped │
│ Node service │ Scheduled Task not installed │
│ Agents │ 1 total · 0 bootstrapping · 0 active · 2 sessions

sharp edgeBOT
#

That output looks totally normal: it’s just saying your main agent has 2 session records stored, last active 18 minutes ago, and the session store file lives at:

~\.openclaw\agents\main\sessions\sessions.json

Also “Bootstrap file: ABSENT” is good/normal (it only shows up if you have a BOOTSTRAP.md in the agent workspace, which can sometimes cause “stuck bootstrapping” loops).

What problem are you trying to solve with this? (e.g. sessions not resuming, weird history, agent stuck, etc.)

If you paste these, I can tell you the next exact step:

  1. openclaw --version
  2. The command you ran that printed this table (gents?)
  3. Any error/log lines you’re seeing right before/after the issue

If your goal is specifically “wipe/reset sessions”, the safe move is:

  • stop the gateway
  • rename sessions.json → sessions.json.bak
  • start the gateway again (it should recreate a fresh sessions store)
#

Your session store looks fine — the real problem is lower down in that status block:

  • Gateway: unreachable (ECONNREFUSED 127.0.0.1:18789)
  • Gateway service: … stopped

So nothing is listening on 127.0.0.1:18789 right now → the dashboard + agent runtime can’t connect.

Try this command ladder (from the troubleshooting runbook), in order:

openclaw gateway start
openclaw gateway status
openclaw status

Healthy looks like: Runtime: running and RPC probe: ok in openclaw gateway status.
Docs: https://docs.openclaw.ai/gateway/troubleshooting

#

If gateway start immediately fails or the service flips back to stopped, paste:

openclaw gateway status --deep
openclaw logs --follow
openclaw doctor

Two common fixes if it’s an install/service metadata mismatch:

openclaw gateway install --force
openclaw gateway restart

(Also worth checking openclaw config get gateway.mode is local — the docs call out Gateway start blocked: set gateway.mode="local" as a common signature.)