Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: Openclaw is stupid again: 200000 tool calls, no feedback, interruptions [3 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#48947•Fetched 2026-04-08 00:50:40
View on GitHub
Comments
3
Participants
2
Timeline
6
Reactions
0
Author
pacioxpaciox
Participants
pacioxpacioxRyceRyce
Timeline (top)
commented ×3labeled ×2subscribed ×1

Jesus.... you can't do a release with breaking anything eh? After #35077 #35077

we're at it again......

<img width="1029" height="651" alt="Image" src="https://github.com/user-attachments/assets/e007d5b7-17fd-435f-b490-56d645be90c2" />

I explicitly asked also in soul.md and agents.md for a feedback after this but it continues to shoot a billion of tool calls without even telling me what the heck is doing. Then at random times, it just sto doing stuff randomly and it acts like it finished.

Like, tell me the heck you did.

It doesn't complete tasks 50% of the times, it shoots ton of tool calls without giving feedback and more than anything the goddamn UI doesn't update again and again. I have to switch between menu and chat to get a refreshed update with recent tool calls and all.

I'm starting to lose hope and switch to something else like hermes agent or picoclaw or whatever else. This is starting to be annoying.

Thanks god I'm on free SOTA models. I would have already thrown in the trash hunderd of bucks for child play.

EDIT:

NOW ASKING TO PRECISELY EDIT THE GITHUB PROJECT I DOWNLOADED THIS STUPID THING EDITED IS OWN OPENCLAW JSON CONFIG AND INCURRED IN COST AND USAGE. JESUS...... ALSO BROKE HIS OWN CONFIG....... NICE, WHAT A JEWEL THIS PROJECT IS.....

Root Cause

Jesus.... you can't do a release with breaking anything eh? After #35077 #35077

we're at it again......

<img width="1029" height="651" alt="Image" src="https://github.com/user-attachments/assets/e007d5b7-17fd-435f-b490-56d645be90c2" />

I explicitly asked also in soul.md and agents.md for a feedback after this but it continues to shoot a billion of tool calls without even telling me what the heck is doing. Then at random times, it just sto doing stuff randomly and it acts like it finished.

Like, tell me the heck you did.

It doesn't complete tasks 50% of the times, it shoots ton of tool calls without giving feedback and more than anything the goddamn UI doesn't update again and again. I have to switch between menu and chat to get a refreshed update with recent tool calls and all.

I'm starting to lose hope and switch to something else like hermes agent or picoclaw or whatever else. This is starting to be annoying.

Thanks god I'm on free SOTA models. I would have already thrown in the trash hunderd of bucks for child play.

EDIT:

NOW ASKING TO PRECISELY EDIT THE GITHUB PROJECT I DOWNLOADED THIS STUPID THING EDITED IS OWN OPENCLAW JSON CONFIG AND INCURRED IN COST AND USAGE. JESUS...... ALSO BROKE HIS OWN CONFIG....... NICE, WHAT A JEWEL THIS PROJECT IS.....

RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Summary

Jesus.... you can't do a release with breaking anything eh? After #35077 #35077

we're at it again......

<img width="1029" height="651" alt="Image" src="https://github.com/user-attachments/assets/e007d5b7-17fd-435f-b490-56d645be90c2" />

I explicitly asked also in soul.md and agents.md for a feedback after this but it continues to shoot a billion of tool calls without even telling me what the heck is doing. Then at random times, it just sto doing stuff randomly and it acts like it finished.

Like, tell me the heck you did.

It doesn't complete tasks 50% of the times, it shoots ton of tool calls without giving feedback and more than anything the goddamn UI doesn't update again and again. I have to switch between menu and chat to get a refreshed update with recent tool calls and all.

I'm starting to lose hope and switch to something else like hermes agent or picoclaw or whatever else. This is starting to be annoying.

Thanks god I'm on free SOTA models. I would have already thrown in the trash hunderd of bucks for child play.

EDIT:

NOW ASKING TO PRECISELY EDIT THE GITHUB PROJECT I DOWNLOADED THIS STUPID THING EDITED IS OWN OPENCLAW JSON CONFIG AND INCURRED IN COST AND USAGE. JESUS...... ALSO BROKE HIS OWN CONFIG....... NICE, WHAT A JEWEL THIS PROJECT IS.....

Steps to reproduce

Just run openclaw? using step 3.5 fun: free one of the top models on openrouter

Expected behavior

You know, work? like You tell me what you're doing, launch tools and give a feedback, not just shoot 50 tool calls without not even letting me know what the heck is happening (or having me open all the 50 tool calls with the little arrow to expand and read commands)

Actual behavior

For your fun, an even more zoomed out image of what is happening

<img width="525" height="743" alt="Image" src="https://github.com/user-attachments/assets/fffb673f-a611-4809-aecb-bd576572d331" />

lmao

OpenClaw version

2026.3.13

Operating system

ubuntu 25

Install method

npm

Model

step3.5-fun:free

Provider / routing chain

web ui

Config file / key location

default

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

extent analysis

Fix Plan

To address the issues with OpenClaw, we will focus on improving feedback mechanisms, reducing unnecessary tool calls, and ensuring the UI updates correctly.

Step 1: Modify the OpenClaw Configuration

Edit the OpenClaw JSON configuration file to include feedback settings. Add the following lines to enable detailed logging and feedback:

{
  "feedback": {
    "enabled": true,
    "level": "detailed"
  }
}

Step 2: Implement Tool Call Limiting

To prevent excessive tool calls, we can introduce a rate limiter. Modify the tool call function to include a delay between calls:

const rateLimit = require('express-rate-limit');

const limiter = rateLimit({
  windowMs: 1 * 60 * 1000, // 1 minute
  max: 10 // limit each IP to 10 requests per window
});

// Apply the rate limiter to the tool call endpoint
app.use('/tool-call', limiter);

Step 3: Enhance UI Updates

To ensure the UI updates correctly, we can use WebSockets to push updates from the server to the client. Install the ws library and establish a WebSocket connection:

const WebSocket = require('ws');
const wss = new WebSocket.Server({ port: 8080 });

// Send updates to the client
wss.on('connection', (ws) => {
  // Handle messages from the client
  ws.on('message', (message) => {
    console.log(`Received message => ${message}`);
  });

  // Send updates to the client
  ws.send('Update: Tool call completed');
});

On the client-side, establish a WebSocket connection and update the UI accordingly:

const socket = new WebSocket('ws://localhost:8080');

// Handle messages from the server
socket.onmessage = (event) => {
  console.log(`Received update => ${event.data}`);
  // Update the UI
  document.getElementById('update').innerHTML = event.data;
};

Verification

To verify the fixes, run OpenClaw and monitor the feedback, tool calls, and UI updates. Check the logs for detailed feedback and ensure the UI updates correctly after each tool call.

Extra Tips

  • Regularly review and update the OpenClaw configuration to ensure optimal performance.
  • Consider implementing additional logging and monitoring tools to track issues and improve the overall user experience.
  • For further assistance, refer to the OpenClaw documentation and community resources.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

You know, work? like You tell me what you're doing, launch tools and give a feedback, not just shoot 50 tool calls without not even letting me know what the heck is happening (or having me open all the 50 tool calls with the little arrow to expand and read commands)

#api#ssr#installation#tensor shape#autograd error#runtime error#dependency conflict#environment setup#docker error#permission error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING