> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/skydiscover-ai/skydiscover/llms.txt
> Use this file to discover all available pages before exploring further.

# Monitor Configuration

> Configure the live monitoring dashboard for real-time search progress visualization

## Overview

SkyDiscover includes a built-in live monitoring dashboard that provides real-time visualization of the evolutionary search process. The dashboard displays fitness progression, solution quality, and AI-generated summaries.

## Basic Configuration

```yaml theme={null}
monitor:
  enabled: false
  port: 8765
  host: "127.0.0.1"
  max_solution_length: 10000
```

## Enabling the Monitor

### In Configuration File

```yaml configs/human_in_the_loop.yaml theme={null}
monitor:
  enabled: true
  port: 8765
  host: "127.0.0.1"
```

### From CLI

```bash theme={null}
skydiscover-run program.py evaluator.py \
  -c configs/adaevolve.yaml \
  --monitor
```

### Access the Dashboard

Once enabled, open your browser to:

```
http://127.0.0.1:8765
```

## MonitorConfig Parameters

Defined in `skydiscover/config.py:500-515`

<ParamField path="enabled" type="bool" default="false">
  Enable or disable the live monitoring dashboard
</ParamField>

<ParamField path="port" type="int" default="8765">
  Port number for the web server
</ParamField>

<ParamField path="host" type="str" default="127.0.0.1">
  Host address to bind the server to. Use `0.0.0.0` to allow external access
</ParamField>

<ParamField path="max_solution_length" type="int" default="10000">
  Maximum character length to display for solutions in the dashboard
</ParamField>

## AI Summary Configuration

The monitor can generate AI-powered summaries of search progress using an LLM.

<ParamField path="summary_model" type="str" default="gpt-5-mini">
  Model to use for generating progress summaries
</ParamField>

<ParamField path="summary_api_key" type="str" default="None">
  API key for summary model. Falls back to `OPENAI_API_KEY` if not specified
</ParamField>

<ParamField path="summary_api_base" type="str" default="https://api.openai.com/v1">
  API base URL for summary model
</ParamField>

<ParamField path="summary_top_k" type="int" default="3">
  Number of top programs to include in the summary
</ParamField>

<ParamField path="summary_interval" type="int" default="0">
  Auto-generate summary every N programs. Set to `0` for manual triggering only
</ParamField>

## Complete Example

```yaml configs/monitor_full.yaml theme={null}
monitor:
  # Server settings
  enabled: true
  port: 8765
  host: "0.0.0.0"  # Allow external access
  max_solution_length: 15000
  
  # AI summary settings
  summary_model: "gpt-4o-mini"
  summary_api_key: ${OPENAI_API_KEY}
  summary_api_base: "https://api.openai.com/v1"
  summary_top_k: 5
  summary_interval: 10  # Generate summary every 10 programs
```

## Dashboard Features

The live monitor provides:

<AccordionGroup>
  <Accordion title="Real-Time Fitness Plot" icon="chart-line">
    * Fitness progression over iterations
    * Best, median, and worst fitness curves
    * Island-specific plots (for multi-island algorithms)
    * Interactive zooming and panning
  </Accordion>

  <Accordion title="Solution Browser" icon="code">
    * View all generated solutions
    * Syntax-highlighted code display
    * Fitness metrics for each solution
    * Filtering and sorting capabilities
  </Accordion>

  <Accordion title="AI-Generated Summaries" icon="sparkles">
    * High-level progress overview
    * Key insights from top solutions
    * Strategy recommendations
    * Automatic or manual generation
  </Accordion>

  <Accordion title="Search Statistics" icon="chart-bar">
    * Total iterations completed
    * Best fitness achieved
    * Improvement rate
    * Time per iteration
    * Model usage breakdown
  </Accordion>
</AccordionGroup>

## Human-in-the-Loop Integration

Combine the monitor with human feedback for interactive search:

```yaml configs/human_in_the_loop.yaml theme={null}
# Enable both monitor and human feedback
monitor:
  enabled: true
  port: 8765

human_feedback_enabled: true
human_feedback_file: "feedback.txt"
human_feedback_mode: "append"
```

### Providing Feedback

1. View solutions in the dashboard
2. Write feedback to the feedback file:
   ```txt feedback.txt theme={null}
   The current solutions are too complex. Focus on simpler approaches.
   Try using dynamic programming instead of recursion.
   ```
3. Feedback is incorporated into the next generation

## Network Configuration

### Local Access Only (Default)

```yaml theme={null}
monitor:
  enabled: true
  host: "127.0.0.1"
  port: 8765
```

Access at: `http://127.0.0.1:8765`

### Remote Access

```yaml theme={null}
monitor:
  enabled: true
  host: "0.0.0.0"  # Listen on all interfaces
  port: 8765
```

Access at: `http://<server-ip>:8765`

<Warning>
  Binding to `0.0.0.0` allows external access. Ensure proper firewall rules are in place.
</Warning>

### Custom Port

```yaml theme={null}
monitor:
  enabled: true
  port: 9000
```

Useful if port 8765 is already in use.

## Performance Considerations

<Tip>
  The monitor adds minimal overhead to the search process:

  * WebSocket updates are asynchronous
  * Solution data is sent in batches
  * AI summaries only run when triggered
</Tip>

### Optimizing for Long Runs

```yaml theme={null}
monitor:
  enabled: true
  max_solution_length: 5000    # Reduce to save memory
  summary_interval: 50         # Less frequent summaries
  summary_top_k: 3             # Fewer programs in summary
```

## AI Summary Models

Choose different models based on your needs:

### Fast & Cheap

```yaml theme={null}
monitor:
  summary_model: "gpt-4o-mini"
  summary_interval: 5  # More frequent updates
```

### Detailed Analysis

```yaml theme={null}
monitor:
  summary_model: "gpt-5"
  summary_interval: 20  # Less frequent, deeper analysis
  summary_top_k: 10
```

### Local Model

```yaml theme={null}
monitor:
  summary_model: "ollama/llama3"
  summary_api_base: "http://localhost:11434/v1"
  summary_api_key: null
```

## Troubleshooting

<AccordionGroup>
  <Accordion title="Port Already in Use" icon="exclamation-triangle">
    **Error:** `Address already in use`

    **Solution:** Change the port number

    ```yaml theme={null}
    monitor:
      port: 9000  # Use different port
    ```
  </Accordion>

  <Accordion title="Cannot Connect from Browser" icon="network-wired">
    **Issue:** Dashboard not loading

    **Checklist:**

    1. Verify monitor is enabled: `enabled: true`
    2. Check the console for server startup message
    3. Ensure firewall allows connections to the port
    4. Try `host: "0.0.0.0"` instead of `127.0.0.1`
  </Accordion>

  <Accordion title="AI Summary Not Generating" icon="robot">
    **Issue:** Summaries not appearing

    **Solutions:**

    1. Check API key is set: `summary_api_key` or `OPENAI_API_KEY`
    2. Verify model name is correct
    3. Check API base URL
    4. Set `summary_interval > 0` for automatic generation
    5. Use manual trigger button in dashboard
  </Accordion>

  <Accordion title="High Memory Usage" icon="memory">
    **Issue:** Dashboard consuming too much memory

    **Solutions:**

    1. Reduce `max_solution_length` to 3000-5000
    2. Increase `summary_interval` to generate summaries less often
    3. Clear old solutions from the dashboard periodically
  </Accordion>
</AccordionGroup>

## Example Configurations

### Minimal Monitoring

```yaml theme={null}
monitor:
  enabled: true
  # All other defaults
```

### Production Monitoring

```yaml theme={null}
monitor:
  enabled: true
  port: 8765
  host: "0.0.0.0"
  max_solution_length: 8000
  summary_model: "gpt-4o-mini"
  summary_interval: 15
  summary_top_k: 5
```

### Research Setup

```yaml theme={null}
monitor:
  enabled: true
  port: 8765
  host: "127.0.0.1"
  max_solution_length: 20000
  summary_model: "gpt-5"
  summary_interval: 0  # Manual only
  summary_top_k: 10
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Configuration Overview" icon="gear" href="/config/overview">
    Learn about other configuration options
  </Card>

  <Card title="Human Feedback" icon="user" href="/guides/monitoring">
    Guide the search with human expertise
  </Card>
</CardGroup>