Bug type
Behavior bug (incorrect output/state without crash)
Beta release blocker
No
Summary
Discord channel input shows typing for ~30s before model starts.
Steps to reproduce
- Start OpenClaw with moonshot without "openai-compatible" endpoint config.
- Talk to OepnClaw on Discord.
Expected behavior
Show typing indicator in few seconds.
Actual behavior
Show typing indicator after 10~30s
OpenClaw version
2026.5.19 (also reproduced on 2026.5.18)
Operating system
Ubuntu 24.04 / linux 6.8.0-117-generic x64
Install method
npm global
Model
moonshot/kimi-k2.6 native Moonshot provider
Provider / routing chain
openclaw -> moonshot
Additional provider/model setup details
No response
Logs, screenshots, and evidence
actual log
{"0":"{\"subsystem\":\"agent/embedded\"}","1":"[trace:embedded-run] startup stages: runId=10fe5fe6-d988-4cca-ae7b-27b393dbd594 sessionId=7761c6fb-1c9e-4d9e-bf01-eb26e55cc079 phase=attempt-dispatch totalMs=33703 stages=workspace:0ms@0ms,runtime-plugins:17ms@17ms,hooks:0ms@17ms,model-resolution:33681ms@33698ms,auth:1ms@33699ms,context-engine:1ms@33700ms,attempt-workspace:2ms@33702ms,attempt-prompt:0ms@33702ms,attempt-runtime-plan:1ms@33703ms,attempt-dispatch:0ms@33703ms","_meta":{"runtime":"node","runtimeVersion":"24.15.0","hostname":"unknown","name":"{\"subsystem\":\"agent/embedded\"}","parentNames":["openclaw"],"date":"2026-05-21T03:01:30.073Z","logLevelId":4,"logLevelName":"WARN","path":{"fullFilePath":"file:///home/openclaw/.npm-global/lib/node_modules/openclaw/dist/subsystem-C-H8Q21Y.js:178:14","fileName":"subsystem-C-H8Q21Y.js","fileNameWithLine":"subsystem-C-H8Q21Y.js:178","fileColumn":"14","fileLine":"178","filePath":".npm-global/lib/node_modules/openclaw/dist/subsystem-C-H8Q21Y.js","filePathWithLine":".npm-global/lib/node_modules/openclaw/dist/subsystem-C-H8Q21Y.js:178","method":"logToFile"}},"time":"2026-05-21T12:01:30.073+09:00","hostname":"microserver","message":"[trace:embedded-run] startup stages: runId=10fe5fe6-d988-4cca-ae7b-27b393dbd594 sessionId=7761c6fb-1c9e-4d9e-bf01-eb26e55cc079 phase=attempt-dispatch totalMs=33703 stages=workspace:0ms@0ms,runtime-plugins:17ms@17ms,hooks:0ms@17ms,model-resolution:33681ms@33698ms,auth:1ms@33699ms,context-engine:1ms@33700ms,attempt-workspace:2ms@33702ms,attempt-prompt:0ms@33702ms,attempt-runtime-plan:1ms@33703ms,attempt-dispatch:0ms@33703ms"}
---
openclaw@microserver:~$ openclaw models status
🦞 OpenClaw 2026.5.19 (a185ca2) — One CLI to rule them all, and one more restart because you changed the port.
Config : ~/.openclaw/openclaw.json
Agent dir : ~/.openclaw/agents/main/agent
Default : moonshot/kimi-k2.6
Fallbacks (4) : google/gemini-3.1-pro-preview, google/gemini-flash-latest, google/gemini-flash-lite-latest, openai/gpt-5.3-codex
Image model : -
Image fallbacks (0): -
Aliases (3) : gemini -> google/gemini-3.1-pro-preview, Kimi -> moonshot/kimi-k2.6, GPT -> openai/gpt-5.3-codex
Configured models (5): google/gemini-3.1-pro-preview, google/gemini-flash-latest, google/gemini-flash-lite-latest, moonshot/kimi-k2.6, openai/gpt-5.3-codex
Auth overview
Auth store : ~/.openclaw/agents/main/agent/auth-profiles.json
Shell env : on
Providers w/ OAuth/tokens (0): -
- elevenlabs effective=env:[REDACTED] | env=[REDACTED] | source=env: ELEVENLABS_API_KEY
- google effective=env:[REDACTED] | env=[REDACTED] | source=env: GEMINI_API_KEY
- moonshot effective=profiles:~/.openclaw/agents/main/agent/auth-profiles.json | profiles=1 (oauth=0, token=0, api_key=1) | moonshot:default=[REDACTED] | env=[REDACTED] | source=env: MOONSHOT_API_KEY
- openai effective=env:[REDACTED] | env=[REDACTED] | source=env: OPENAI_API_KEY
- openai-codex effective=synthetic:codex-app-server | synthetic=plugin-owned | source=codex-app-server
Runtime auth
- openai via codex uses openai-codex effective=synthetic:codex-app-server | status=usable
OAuth/token status
- none
openclaw@microserver:~$ openclaw status --all
🦞 OpenClaw 2026.5.19 (a185ca2) — I'm not saying your workflow is chaotic... I'm just bringing a linter and a helmet.
│
12:19:00 [plugins] [memory-lancedb-pro] memory_recall queries the plugin store (LanceDB), not MEMORY.md.
- Plugin memory (LanceDB) = primary recall source for semantic search
- MEMORY.md / memory/YYYY-MM-DD.md = startup context / journal only
- Use memory_store or auto-capture for recallable memories.
OpenClaw status --all
Overview
┌────────────────────┬────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ Item │ Value │
├────────────────────┼────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Version │ 2026.5.19 │
│ OS │ linux 6.8.0-117-generic (x64) │
│ Node │ 24.15.0 │
│ Config │ ~/.openclaw/openclaw.json │
│ Dashboard │ http://127.0.0.1:18789/ │
│ Tailscale exposure │ serve · unknown · microserver.taildc77f.ts.net · https://microserver.taildc77f.ts.net │
│ Channel │ stable (default) │
│ Update │ pnpm · up to date · npm latest 2026.5.19 │
│ Gateway │ local · ws://127.0.0.1:18789 (local loopback) · reachable 205ms · auth token · microserver (192.168.11.4) app 2026.5.19 linux │
│ │ 6.8.0-117-generic │
│ Security │ Run: openclaw security audit --deep │
│ Gateway self │ unknown │
│ Gateway service │ systemd user installed · enabled · running (pid 42034, state active) │
│ Node service │ systemd user not installed │
│ Agents │ 3 total · 0 bootstrapping · 0 active · 6 sessions │
│ Secrets │ none │
└────────────────────┴────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
Channels
┌──────────┬─────────┬────────┬───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ Channel │ Enabled │ State │ Detail │
├──────────┼─────────┼────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Discord │ ON │ OK │ token config (sha256:488d4a30 · len 72) · accounts 1/1 │
└──────────┴─────────┴────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
Discord accounts
┌──────────┬──────────┬───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ Account │ Status │ Notes │
├──────────┼──────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ default │ OK │ token:config · credential available in gateway runtime │
└──────────┴──────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
Agents
┌─────────────────┬────────────────┬──────────┬──────────┬────────────────────────────────────────────────────────────────────────────────────────────┐
│ Agent │ Bootstrap file │ Sessions │ Active │ Store │
├─────────────────┼────────────────┼──────────┼──────────┼────────────────────────────────────────────────────────────────────────────────────────────┤
│ main │ ABSENT │ 5 │ 17m ago │ ~/.openclaw/agents/main/sessions/sessions.json │
│ auto-researcher │ ABSENT │ 0 │ unknown │ ~/.openclaw/agents/auto-researcher/sessions/sessions.json │
│ public │ ABSENT │ 1 │ 10d ago │ ~/.openclaw/agents/public/sessions/sessions.json │
└─────────────────┴────────────────┴──────────┴──────────┴────────────────────────────────────────────────────────────────────────────────────────────┘
Diagnosis (read-only)
Gateway connection details:
Gateway target: ws://127.0.0.1:18789
Source: local loopback
Config: /home/openclaw/.openclaw/openclaw.json
Bind: loopback
✓ Config: /home/openclaw/.openclaw/openclaw.json
✓ Secret diagnostics (0)
✓ Restart sentinel: none
✓ Port 18789
Detected OpenClaw Gateway listener on the configured port.
! Tailscale exposure: serve · daemon unknown · microserver.taildc77f.ts.net
https: https://microserver.taildc77f.ts.net
✓ Skills: 24 eligible · 0 missing · /home/openclaw/.openclaw/workspace
✓ Plugin compatibility (none)
Gateway restart attempts (tail): /home/openclaw/.openclaw/logs/gateway-restart.log
[2026-05-20T16:06:48Z] openclaw restart attempt source=update target=openclaw-gateway.service
[2026-05-20T16:06:48Z] openclaw restart done source=update
[2026-05-21T02:12:41Z] openclaw restart attempt source=update target=openclaw-gateway.service
[2026-05-21T02:12:45Z] openclaw restart done source=update
✓ Channel issues (none)
Pasteable debug report. Auth tokens redacted.
Troubleshooting: https://docs.openclaw.ai/troubleshooting
◇
openclaw@microserver:~$ openclaw config get agents.defaults.model
🦞 OpenClaw 2026.5.19 (a185ca2) — I'm not magic—I'm just extremely persistent with retries and coping strategies.
{
"primary": "moonshot/kimi-k2.6",
"fallbacks": [
"google/gemini-3.1-pro-preview",
"google/gemini-flash-latest",
"google/gemini-flash-lite-latest",
"openai/gpt-5.3-codex"
]
}
openclaw@microserver:~$ openclaw config get models.providers.moonshot
🦞 OpenClaw 2026.5.19 (a185ca2) — Greetings, Professor Falken
Config path not found: models.providers.moonshot. Run openclaw config validate to inspect config shape.Impact and severity
No response
Additional information
No response
Bug type
Behavior bug (incorrect output/state without crash)
Beta release blocker
No
Summary
Discord channel input shows typing for ~30s before model starts.
Steps to reproduce
Expected behavior
Show typing indicator in few seconds.
Actual behavior
Show typing indicator after 10~30s
OpenClaw version
2026.5.19 (also reproduced on 2026.5.18)
Operating system
Ubuntu 24.04 / linux 6.8.0-117-generic x64
Install method
npm global
Model
moonshot/kimi-k2.6 native Moonshot provider
Provider / routing chain
openclaw -> moonshot
Additional provider/model setup details
No response
Logs, screenshots, and evidence
actual log {"0":"{\"subsystem\":\"agent/embedded\"}","1":"[trace:embedded-run] startup stages: runId=10fe5fe6-d988-4cca-ae7b-27b393dbd594 sessionId=7761c6fb-1c9e-4d9e-bf01-eb26e55cc079 phase=attempt-dispatch totalMs=33703 stages=workspace:0ms@0ms,runtime-plugins:17ms@17ms,hooks:0ms@17ms,model-resolution:33681ms@33698ms,auth:1ms@33699ms,context-engine:1ms@33700ms,attempt-workspace:2ms@33702ms,attempt-prompt:0ms@33702ms,attempt-runtime-plan:1ms@33703ms,attempt-dispatch:0ms@33703ms","_meta":{"runtime":"node","runtimeVersion":"24.15.0","hostname":"unknown","name":"{\"subsystem\":\"agent/embedded\"}","parentNames":["openclaw"],"date":"2026-05-21T03:01:30.073Z","logLevelId":4,"logLevelName":"WARN","path":{"fullFilePath":"file:///home/openclaw/.npm-global/lib/node_modules/openclaw/dist/subsystem-C-H8Q21Y.js:178:14","fileName":"subsystem-C-H8Q21Y.js","fileNameWithLine":"subsystem-C-H8Q21Y.js:178","fileColumn":"14","fileLine":"178","filePath":".npm-global/lib/node_modules/openclaw/dist/subsystem-C-H8Q21Y.js","filePathWithLine":".npm-global/lib/node_modules/openclaw/dist/subsystem-C-H8Q21Y.js:178","method":"logToFile"}},"time":"2026-05-21T12:01:30.073+09:00","hostname":"microserver","message":"[trace:embedded-run] startup stages: runId=10fe5fe6-d988-4cca-ae7b-27b393dbd594 sessionId=7761c6fb-1c9e-4d9e-bf01-eb26e55cc079 phase=attempt-dispatch totalMs=33703 stages=workspace:0ms@0ms,runtime-plugins:17ms@17ms,hooks:0ms@17ms,model-resolution:33681ms@33698ms,auth:1ms@33699ms,context-engine:1ms@33700ms,attempt-workspace:2ms@33702ms,attempt-prompt:0ms@33702ms,attempt-runtime-plan:1ms@33703ms,attempt-dispatch:0ms@33703ms"} --- openclaw@microserver:~$ openclaw models status 🦞 OpenClaw 2026.5.19 (a185ca2) — One CLI to rule them all, and one more restart because you changed the port. Config : ~/.openclaw/openclaw.json Agent dir : ~/.openclaw/agents/main/agent Default : moonshot/kimi-k2.6 Fallbacks (4) : google/gemini-3.1-pro-preview, google/gemini-flash-latest, google/gemini-flash-lite-latest, openai/gpt-5.3-codex Image model : - Image fallbacks (0): - Aliases (3) : gemini -> google/gemini-3.1-pro-preview, Kimi -> moonshot/kimi-k2.6, GPT -> openai/gpt-5.3-codex Configured models (5): google/gemini-3.1-pro-preview, google/gemini-flash-latest, google/gemini-flash-lite-latest, moonshot/kimi-k2.6, openai/gpt-5.3-codex Auth overview Auth store : ~/.openclaw/agents/main/agent/auth-profiles.json Shell env : on Providers w/ OAuth/tokens (0): - - elevenlabs effective=env:[REDACTED] | env=[REDACTED] | source=env: ELEVENLABS_API_KEY - google effective=env:[REDACTED] | env=[REDACTED] | source=env: GEMINI_API_KEY - moonshot effective=profiles:~/.openclaw/agents/main/agent/auth-profiles.json | profiles=1 (oauth=0, token=0, api_key=1) | moonshot:default=[REDACTED] | env=[REDACTED] | source=env: MOONSHOT_API_KEY - openai effective=env:[REDACTED] | env=[REDACTED] | source=env: OPENAI_API_KEY - openai-codex effective=synthetic:codex-app-server | synthetic=plugin-owned | source=codex-app-server Runtime auth - openai via codex uses openai-codex effective=synthetic:codex-app-server | status=usable OAuth/token status - none openclaw@microserver:~$ openclaw status --all 🦞 OpenClaw 2026.5.19 (a185ca2) — I'm not saying your workflow is chaotic... I'm just bringing a linter and a helmet. │ 12:19:00 [plugins] [memory-lancedb-pro] memory_recall queries the plugin store (LanceDB), not MEMORY.md. - Plugin memory (LanceDB) = primary recall source for semantic search - MEMORY.md / memory/YYYY-MM-DD.md = startup context / journal only - Use memory_store or auto-capture for recallable memories. OpenClaw status --all Overview ┌────────────────────┬────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐ │ Item │ Value │ ├────────────────────┼────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤ │ Version │ 2026.5.19 │ │ OS │ linux 6.8.0-117-generic (x64) │ │ Node │ 24.15.0 │ │ Config │ ~/.openclaw/openclaw.json │ │ Dashboard │ http://127.0.0.1:18789/ │ │ Tailscale exposure │ serve · unknown · microserver.taildc77f.ts.net · https://microserver.taildc77f.ts.net │ │ Channel │ stable (default) │ │ Update │ pnpm · up to date · npm latest 2026.5.19 │ │ Gateway │ local · ws://127.0.0.1:18789 (local loopback) · reachable 205ms · auth token · microserver (192.168.11.4) app 2026.5.19 linux │ │ │ 6.8.0-117-generic │ │ Security │ Run: openclaw security audit --deep │ │ Gateway self │ unknown │ │ Gateway service │ systemd user installed · enabled · running (pid 42034, state active) │ │ Node service │ systemd user not installed │ │ Agents │ 3 total · 0 bootstrapping · 0 active · 6 sessions │ │ Secrets │ none │ └────────────────────┴────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘ Channels ┌──────────┬─────────┬────────┬───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐ │ Channel │ Enabled │ State │ Detail │ ├──────────┼─────────┼────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤ │ Discord │ ON │ OK │ token config (sha256:488d4a30 · len 72) · accounts 1/1 │ └──────────┴─────────┴────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘ Discord accounts ┌──────────┬──────────┬───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐ │ Account │ Status │ Notes │ ├──────────┼──────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤ │ default │ OK │ token:config · credential available in gateway runtime │ └──────────┴──────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘ Agents ┌─────────────────┬────────────────┬──────────┬──────────┬────────────────────────────────────────────────────────────────────────────────────────────┐ │ Agent │ Bootstrap file │ Sessions │ Active │ Store │ ├─────────────────┼────────────────┼──────────┼──────────┼────────────────────────────────────────────────────────────────────────────────────────────┤ │ main │ ABSENT │ 5 │ 17m ago │ ~/.openclaw/agents/main/sessions/sessions.json │ │ auto-researcher │ ABSENT │ 0 │ unknown │ ~/.openclaw/agents/auto-researcher/sessions/sessions.json │ │ public │ ABSENT │ 1 │ 10d ago │ ~/.openclaw/agents/public/sessions/sessions.json │ └─────────────────┴────────────────┴──────────┴──────────┴────────────────────────────────────────────────────────────────────────────────────────────┘ Diagnosis (read-only) Gateway connection details: Gateway target: ws://127.0.0.1:18789 Source: local loopback Config: /home/openclaw/.openclaw/openclaw.json Bind: loopback ✓ Config: /home/openclaw/.openclaw/openclaw.json ✓ Secret diagnostics (0) ✓ Restart sentinel: none ✓ Port 18789 Detected OpenClaw Gateway listener on the configured port. ! Tailscale exposure: serve · daemon unknown · microserver.taildc77f.ts.net https: https://microserver.taildc77f.ts.net ✓ Skills: 24 eligible · 0 missing · /home/openclaw/.openclaw/workspace ✓ Plugin compatibility (none) Gateway restart attempts (tail): /home/openclaw/.openclaw/logs/gateway-restart.log [2026-05-20T16:06:48Z] openclaw restart attempt source=update target=openclaw-gateway.service [2026-05-20T16:06:48Z] openclaw restart done source=update [2026-05-21T02:12:41Z] openclaw restart attempt source=update target=openclaw-gateway.service [2026-05-21T02:12:45Z] openclaw restart done source=update ✓ Channel issues (none) Pasteable debug report. Auth tokens redacted. Troubleshooting: https://docs.openclaw.ai/troubleshooting ◇ openclaw@microserver:~$ openclaw config get agents.defaults.model 🦞 OpenClaw 2026.5.19 (a185ca2) — I'm not magic—I'm just extremely persistent with retries and coping strategies. { "primary": "moonshot/kimi-k2.6", "fallbacks": [ "google/gemini-3.1-pro-preview", "google/gemini-flash-latest", "google/gemini-flash-lite-latest", "openai/gpt-5.3-codex" ] } openclaw@microserver:~$ openclaw config get models.providers.moonshot 🦞 OpenClaw 2026.5.19 (a185ca2) — Greetings, Professor Falken Config path not found: models.providers.moonshot. Run openclaw config validate to inspect config shape.Impact and severity
No response
Additional information
No response