How to use @mbanucu/opencode-background

by mbanucu
Download
.cast - original recording .txt - plain text version .gif - animated GIF
GNU/Linux • xterm-256color • bash 50 views

OpenCode Background Processes Plugin (fork from zenobi-us/opencode-background)

The original npm package @zenobius/opencode-background from https://github.com/zenobi-us/opencode-background isn’t being maintained or updated, so I’ve stepped in with a maintained fork/version.

Until (or if) the original gets attention, use the @mbanucu version instead.

Demo: How to use @mbanucu/opencode-background

Here is the code for the echo_server.py:

import http.server
import socketserver
from datetime import datetime
import json

class EchoHandler(http.server.BaseHTTPRequestHandler):
    def do_POST(self):
        content_length = int(self.headers['Content-Length'])
        post_data = self.rfile.read(content_length)
        msg = post_data.decode('utf-8')
        print(msg, flush=True)
        now = datetime.now().astimezone().isoformat(timespec='seconds')
        try:
            server_ip, server_port = self.connection.getsockname()[:2]
            server_info = f'{server_ip}:{server_port}'
        except Exception:
            server_info = 'unknown'
        log_object = {
            'timestamp': now,
            'message': msg,
            'client_ip': self.client_address[0],
            'server': server_info
        }
        log_line = json.dumps(log_object, indent=2)
        with open('echo_server.log', 'a') as f:
            f.write(log_line + '\n')
        self.send_response(200)
        self.send_header('Content-Type', 'application/json')
        self.end_headers()
        self.wfile.write(log_line.encode('utf-8'))

if __name__ == '__main__':
    with socketserver.TCPServer(("", 0), EchoHandler) as httpd:
        port = httpd.server_address[1]
        print(f"Server running on port {port}", flush=True)
        httpd.serve_forever()

Links

OpenCode session transcript

Testing echo_server manually with curl in background

Session ID: ses_47028381cffeUyoaJzJtLY2P6k Created: 1/5/2026, 9:27:21 PM Updated: 1/5/2026, 9:27:36 PM

User

test the echo_server manually by running it in background and sending some data with curl commands

Assistant (Build · grok-code · 2.9s)

Thinking:

The user wants to test the echo_server manually by running it in background and sending some data with curl commands.

Tool: glob

**Input:**
```json
{
  "pattern": "*"
}
```
**Output:**
```
/home/michi/dev/opencode-background/demo/Running background processes/python server/demo.cast
/home/michi/dev/opencode-background/demo/Running background processes/python server/echo_server.py
```

Assistant (Build · grok-code · 1.1s)

Thinking:

There’s an echo_server.py file. Let me read it to understand what it does.

Tool: read

**Input:**
```json
{
  "filePath": "/home/michi/dev/opencode-background/demo/Running background processes/python server/echo_server.py"
}
```
**Output:**
```
<file>
00001| import http.server
00002| import socketserver
00003| from datetime import datetime
00004| import json
00005| 
00006| class EchoHandler(http.server.BaseHTTPRequestHandler):
00007|     def do_POST(self):
00008|         content_length = int(self.headers['Content-Length'])
00009|         post_data = self.rfile.read(content_length)
00010|         msg = post_data.decode('utf-8')
00011|         print(msg, flush=True)
00012|         now = datetime.now().astimezone().isoformat(timespec='seconds')
00013|         try:
00014|             server_ip, server_port = self.connection.getsockname()[:2]
00015|             server_info = f'{server_ip}:{server_port}'
00016|         except Exception:
00017|             server_info = 'unknown'
00018|         log_object = {
00019|             'timestamp': now,
00020|             'message': msg,
00021|             'client_ip': self.client_address[0],
00022|             'server': server_info
00023|         }
00024|         log_line = json.dumps(log_object, indent=2)
00025|         with open('echo_server.log', 'a') as f:
00026|             f.write(log_line + '\n')
00027|         self.send_response(200)
00028|         self.send_header('Content-Type', 'application/json')
00029|         self.end_headers()
00030|         self.wfile.write(log_line.encode('utf-8'))
00031| 
00032| if __name__ == '__main__':
00033|     with socketserver.TCPServer(("", 0), EchoHandler) as httpd:
00034|         port = httpd.server_address[1]
00035|         print(f"Server running on port {port}", flush=True)
00036|         httpd.serve_forever()

(End of file - total 36 lines)
</file>
```

Assistant (Build · grok-code · 2.3s)

Thinking:

The echo_server.py is a Python HTTP server that listens on a random port (port 0 means it chooses an available port). It handles POST requests, echoes back the message with timestamp, client IP, and server info, and logs to a file.

Tool: createBackgroundProcess

**Input:**
```json
{
  "command": "python3 echo_server.py",
  "name": "echo_server"
}
```
**Output:**
```
task-y1i1772
```

Assistant (Build · grok-code · 1.1s)

Thinking:

The server is now running in background with task ID task-y1i1772.

Tool: getBackgroundProcess

**Input:**
```json
{
  "taskId": "task-y1i1772"
}
```
**Output:**
```
{"id":"task-y1i1772","name":"echo_server","status":"running","command":"python3 echo_server.py","startedAt":"2026-01-05T20:27:28.168Z","completedAt":"","error":"","sessionId":"ses_47028381cffeUyoaJzJtLY2P6k","tags":[],"pid":597739,"global":false,"outputStream":["Server running on port 37427"]}
```

Assistant (Build · grok-code · 1.5s)

Thinking:

The server is running on port 37427.

Tool: bash

**Input:**
```json
{
  "command": "curl -X POST -d \"Hello, World!\" http://localhost:37427",
  "description": "Send POST request with message to echo server"
}
```
**Output:**
```
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
  0     0   0     0   0     0     0     0  --:--:-- --:--:-- --:--:--     0
100   148   0   135 100    13 25802  2484  --:--:-- --:--:-- --:--:-- 29600
{
  "timestamp": "2026-01-05T21:27:30+01:00",
  "message": "Hello, World!",
  "client_ip": "127.0.0.1",
  "server": "127.0.0.1:37427"
}
```

Assistant (Build · grok-code · 1.1s)

Thinking:

Good! The server responded with the echoed data. Let me send another test with different data.

Tool: bash

**Input:**
```json
{
  "command": "curl -X POST -d '{\"key\": \"value\", \"test\": true}' http://localhost:37427",
  "description": "Send JSON POST request to test echo server"
}
```
**Output:**
```
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
  0     0   0     0   0     0     0     0  --:--:-- --:--:-- --:--:--     0
100   188   0   158 100    30 68427 12992  --:--:-- --:--:-- --:--:-- 94000
{
  "timestamp": "2026-01-05T21:27:31+01:00",
  "message": "{\"key\": \"value\", \"test\": true}",
  "client_ip": "127.0.0.1",
  "server": "127.0.0.1:37427"
}
```

Assistant (Build · grok-code · 0.9s)

Thinking:

Excellent! Let me check the log file to see if it’s being written correctly.

Tool: read

**Input:**
```json
{
  "filePath": "/home/michi/dev/opencode-background/demo/Running background processes/python server/echo_server.log"
}
```
**Output:**
```
<file>
00001| {
00002|   "timestamp": "2026-01-05T21:27:30+01:00",
00003|   "message": "Hello, World!",
00004|   "client_ip": "127.0.0.1",
00005|   "server": "127.0.0.1:37427"
00006| }
00007| {
00008|   "timestamp": "2026-01-05T21:27:31+01:00",
00009|   "message": "{\"key\": \"value\", \"test\": true}",
00010|   "client_ip": "127.0.0.1",
00011|   "server": "127.0.0.1:37427"
00012| }
00013| 

(End of file - total 13 lines)
</file>
```

Assistant (Build · grok-code · 1.1s)

Thinking:

Perfect! The server is working correctly. It echoes back the data with timestamp, client/server info, and logs to the file.

Tool: bash

**Input:**
```json
{
  "command": "curl -X POST -d \"Final test message\" http://localhost:37427",
  "description": "Send final test POST request to echo server"
}
```
**Output:**
```
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
  0     0   0     0   0     0     0     0  --:--:-- --:--:-- --:--:--     0
100   158   0   140 100    18 55183  7094  --:--:-- --:--:-- --:--:-- 79000
{
  "timestamp": "2026-01-05T21:27:34+01:00",
  "message": "Final test message",
  "client_ip": "127.0.0.1",
  "server": "127.0.0.1:37427"
}
```

Assistant (Build · grok-code · 0.8s)

Thinking:

Now let me stop the server.

Tool: killTasks

**Input:**
```json
{
  "taskId": "task-y1i1772"
}
```
**Output:**
```
["task-y1i1772"]
```

Assistant (Build · grok-code · 1.0s)

Thinking:

The server has been stopped. The testing is complete. The echo server is working correctly.

Testing complete! The echo_server.py runs in the background and correctly echoes POST data with timestamps, client/server info, and logs to echo_server.log.

More by mbanucu

How to use @zenobius/opencode-background npm package 0:35

by mbanucu

See all

Share this recording
https://asciinema.org/a/765970
Copied!

Append ?t=30 to start the playback at 30s, ?t=3:20 to start the playback at 3m 20s.

See sharing docs for more link customization options.

Embed as image link

Use snippets below to display a preview image linking to this recording.
Ideal for places where scripts are not allowed, such as project README files.

HTML: 

<a href="https://asciinema.org/a/765970" target="_blank"><img src="https://asciinema.org/a/765970.svg" /></a>
Copied!

Markdown: 

[![asciicast](https://asciinema.org/a/765970.svg)](https://asciinema.org/a/765970)
Copied!

Embed the player

If you're embedding on your own page or on a site which permits script tags, you can use the full player widget:

<script src="https://asciinema.org/a/765970.js" id="asciicast-765970" async="true"></script>
Copied!

Paste the above script tag where you want the player to be displayed on your page.

See embedding docs for more player customization options.

Download this recording

You can download this recording in asciicast v2 format, as a .cast file.

Download

Replay in terminal

You can replay the downloaded recording in your terminal using the asciinema play command: 

asciinema play 765970.cast
Copied!

If you don't have asciinema CLI installed then see installation instructions.

Use with stand-alone player on your website

Download asciinema player from the releases page (you only need .js and .css file), then use it like this: 

<!DOCTYPE html>
<html>
<head>
  <link rel="stylesheet" type="text/css" href="/assets/asciinema-player.css" />
</head>
<body>
  <div id="player"></div>
  <script src="/assets/asciinema-player.min.js"></script>
  <script>
    AsciinemaPlayer.create(
      '/assets/765970.cast',
      document.getElementById('player'),
      { cols: 190, rows: 49 }
    );
  </script>
</body>
</html>

See asciinema player quick-start guide for full usage instructions.

Generate GIF from this recording

While this site doesn't provide GIF conversion at the moment, you can still do it yourself with the help of asciinema GIF generator utility - agg.

Once you have it installed, generate a GIF with the following command:

agg https://asciinema.org/a/765970 demo.gif
Copied!

Or, if you already downloaded the recording file:

agg demo.cast demo.gif
Copied!

Check agg --help for all available options. You can change font family and size, select color theme, adjust speed and more.

See agg manual for full usage instructions.