Interactive Mode Commands

Complete reference for all / commands available in AsobaCode interactive mode.

Getting Started

Launch Ona Terminal interactive mode:

ona-terminal

You’ll see the interactive prompt:

🤖 |

All commands start with / and can be typed directly at this prompt.

🛠️ System Commands

`/help`

Show the help menu and available commands.

/help

`/commands`

List all available slash commands with detailed information.

/commands

`/status`

Check system status and model availability.

/status

Example Output:

📆 AsobaCode Status
📍 Config: configs
⏱️  Timeout: 60s
🖥️  Servers: 3 discovered
🐍 Python: 3.10+

`/models`

Manage and view available AI models.

# List all available models
/models list

# Add a custom model
/models add mymodel --endpoint http://localhost:8000

# Test model connectivity
/models test mymodel

# Remove a model
/models remove mymodel

`/configure`

Open interactive configuration management interface.

/configure

`/servers`

List MCP servers and their status.

# List all servers
/servers

# Show server health status
/servers --health

`/exit`

Exit the interactive mode.

/exit

📁 File Operations

`/read`

Read and analyze file contents with AI assistance.

# Read a file
/read config.py

# Read with line limit
/read --lines 50 large_file.txt

Supported File Types:

Text files (.py, .js, .md, .txt, etc.)
PDF documents (.pdf)
Word documents (.docx, .doc)
PowerPoint presentations (.pptx)
Excel spreadsheets (.xlsx, .xls)

`/list`

List directory contents.

# List current directory
/list

# List specific directory
/list src/

# Show all files including hidden
/list --all

# Show detailed information
/list --details

`/find`

Search for files and content.

# Find files by pattern
/find *.py

# Search content within files
/find --type content "def main"

# Search for directories
/find --type dir config

`/edit`

AI-assisted file editing (coming soon).

/edit config.py
/edit src/main.py "add error handling"

🐙 GitHub Integration

`/github auth`

Manage GitHub authentication.

# Login to GitHub
/github auth login

# Check authentication status
/github auth status

# Logout from GitHub
/github auth logout

`/github repo`

Repository management commands.

# Get repository information
/github repo info owner/repo

`/github issues`

Issue management commands.

# List issues
/github issues list owner/repo

# Filter by state
/github issues list owner/repo --state=closed

`/github pr`

Pull request commands.

# List pull requests
/github pr list owner/repo

# Filter by state
/github pr list owner/repo --state=all

`/github webhook`

Webhook management.

# List webhooks
/github webhook list owner/repo

`/github rate-limit`

Check GitHub API rate limits.

/github rate-limit

📝 Planning & Configuration

`/ona`

Manage .ona planning files.

# Set up .ona environment
/ona setup

# List planning files
/ona list

# Create new planning file
/ona create --content "Planning content" --type plan

`/prompts`

Manage system prompts.

# List available prompts
/prompts list

# Select a system prompt
/prompts select medium

# Show current prompt
/prompts show

📤 Upload Commands

`/upload-inverter upload`

Upload data files for processing and model training.

title: “Commands” layout: default nav_order: 2 redirect_from:

/endpoints.html

Interactive Mode Commands

Complete reference for all / commands available in AsobaCode interactive mode.

Getting Started

Launch Ona Terminal interactive mode:

ona-terminal

You’ll see the interactive prompt:

🤖 |

All commands start with / and can be typed directly at this prompt.

🛠️ System Commands

`/help`

Show the help menu and available commands.

/help

`/commands`

List all available slash commands with detailed information.

/commands

`/status`

Check system status and model availability.

/status

Example Output:

📆 AsobaCode Status
📍 Config: configs
⏱️  Timeout: 60s
🖥️  Servers: 3 discovered
🐍 Python: 3.10+

`/models`

Manage and view available AI models.

# List all available models
/models list

# Add a custom model
/models add mymodel --endpoint http://localhost:8000

# Test model connectivity
/models test mymodel

# Remove a model
/models remove mymodel

`/configure`

Open interactive configuration management interface.

/configure

`/servers`

List MCP servers and their status.

# List all servers
/servers

# Show server health status
/servers --health

`/exit`

Exit the interactive mode.

/exit

📁 File Operations

`/read`

Read and analyze file contents with AI assistance.

# Read a file
/read config.py

# Read with line limit
/read --lines 50 large_file.txt

Supported File Types:

Text files (.py, .js, .md, .txt, etc.)
PDF documents (.pdf)
Word documents (.docx, .doc)
PowerPoint presentations (.pptx)
Excel spreadsheets (.xlsx, .xls)

`/list`

List directory contents.

# List current directory
/list

# List specific directory
/list src/

# Show all files including hidden
/list --all

# Show detailed information
/list --details

`/find`

Search for files and content.

# Find files by pattern
/find *.py

# Search content within files
/find --type content "def main"

# Search for directories
/find --type dir config

`/edit`

AI-assisted file editing (coming soon).

/edit config.py
/edit src/main.py "add error handling"

🐙 GitHub Integration

`/github auth`

Manage GitHub authentication.

# Login to GitHub
/github auth login

# Check authentication status
/github auth status

# Logout from GitHub
/github auth logout

`/github repo`

Repository management commands.

# Get repository information
/github repo info owner/repo

`/github issues`

Issue management commands.

# List issues
/github issues list owner/repo

# Filter by state
/github issues list owner/repo --state=closed

`/github pr`

Pull request commands.

# List pull requests
/github pr list owner/repo

# Filter by state
/github pr list owner/repo --state=all

`/github webhook`

Webhook management.

# List webhooks
/github webhook list owner/repo

`/github rate-limit`

Check GitHub API rate limits.

/github rate-limit

📝 Planning & Configuration

`/ona`

Manage .ona planning files.

# Set up .ona environment
/ona setup

# List planning files
/ona list

# Create new planning file
/ona create --content "Planning content" --type plan

`/prompts`

Manage system prompts.

# List available prompts
/prompts list

# Select a system prompt
/prompts select medium

# Show current prompt
/prompts show

📤 Upload Commands

`/upload-inverter upload`

Upload data files for processing and model training.

/upload-inverter upload CUSTOMER_ID LOCATION MANUFACTURER SERIAL_NUMBER FILE_PATH REGION CLIENT_ID

Example:

/upload-inverter upload SOLAR001 "Cape Town" "SolarEdge" SE12345 /data/inverter.csv af-south-1 client123

Parameters:

CUSTOMER_ID - Unique customer identifier
LOCATION - Installation location (quoted if contains spaces)
MANUFACTURER - Equipment manufacturer name
SERIAL_NUMBER - Equipment serial number
FILE_PATH - Path to CSV data file
REGION - AWS region (e.g., af-south-1)
CLIENT_ID - Client identifier

`/upload-inverter status`

Check upload and training status.

# Check specific upload
/upload-inverter status UPLOAD_ID

# List all recent uploads
/upload-inverter status

Example:

/upload-inverter status SOLAR001_SE12345_1754151842

Status Display:

⚙️ Upload Status: PROCESSING
📋 Upload ID: SOLAR001_SE12345_1754151842
👤 Customer: SOLAR001
📍 Current Stage: trainForecaster
⏱️  Duration: 0:15:23

Pipeline Progress:
✅ Upload         → Completed (0:00:45)
✅ Ingestion      → Completed (0:02:15)
✅ Interpolation  → Completed (0:08:30)
🔄 Training       → In Progress (0:15:23)

📈 Forecast Commands

`/forecast-inverter start`

Generate new forecasts for trained models.

/forecast-inverter start CUSTOMER_ID LOCATION MANUFACTURER SERIAL_NUMBER REGION FORECAST_TYPE DAYS FREQUENCY

Example:

/forecast-inverter start SOLAR001 "Cape Town" "SolarEdge" SE12345 af-south-1 P50 7 daily

Parameters:

CUSTOMER_ID - Customer identifier (must match trained model)
LOCATION - Installation location
MANUFACTURER - Equipment manufacturer
SERIAL_NUMBER - Equipment serial number
REGION - AWS region
FORECAST_TYPE - P50 or P90 forecast type
DAYS - Number of days to forecast
FREQUENCY - daily or hourly

`/forecast-inverter get`

Download generated forecast results.

/forecast-inverter get CUSTOMER_ID LOCATION MANUFACTURER SERIAL_NUMBER REGION OUTPUT_PATH FORECAST_TYPE

Example:

/forecast-inverter get SOLAR001 "Cape Town" "SolarEdge" SE12345 af-south-1 /tmp/forecasts P50

`/forecast-inverter status`

Check forecast generation status.

# Check specific forecast
/forecast-inverter status FORECAST_ID

# List all recent forecasts
/forecast-inverter status

🔄 Workflow Example

Complete workflow from data upload to forecast generation:

1. Upload Training Data

🤖 | /upload-inverter upload SOLAR001 "Cape Town" "SolarEdge" SE12345 /data/solar_data.csv af-south-1 client123

2. Monitor Training Progress

🤖 | /upload-inverter status SOLAR001_SE12345_1754151842

Wait for training to complete (status shows “✅ Training → Completed”).

3. Generate Forecast

🤖 | /forecast-inverter start SOLAR001 "Cape Town" "SolarEdge" SE12345 af-south-1 P50 7 daily

4. Download Results

🤖 | /forecast-inverter get SOLAR001 "Cape Town" "SolarEdge" SE12345 af-south-1 /tmp/forecasts P50

💡 Tips & Best Practices

File Requirements

CSV format with timestamp and generation columns
Consistent naming for customer IDs and serial numbers
Valid file paths accessible from current directory

Monitoring

Use status commands regularly to track progress
Training typically takes 10-30 minutes depending on data size
Forecast generation is usually quick (1-2 minutes)

Error Handling

Commands validate parameters before execution
Clear error messages guide you to correct issues
Use status to check for detailed error information

Regional Considerations

Use af-south-1 for South African deployments
Ensure AWS credentials are configured for the specified region
Data processing occurs in the specified region

🔧 Status Indicators

Icon	Stage	Description
⏳	Pending	Waiting to start
🔄	Processing	Currently running
✅	Completed	Successfully finished
❌	Failed	Error occurred
⚠️	Warning	Completed with warnings

Pipeline Stages

Upload Pipeline:

Upload - File transfer to S3
Ingestion - Data validation and formatting
Interpolation - Gap filling and cleaning
Training - ML model training

Forecast Pipeline:

Generation - Creating forecast using trained model
Processing - Output formatting and validation
Storage - Saving results for download

Common Issues

Upload Fails

Check file path exists and is readable
Verify CSV format is correct
Ensure AWS credentials are configured

Training Stuck

Large datasets take longer (15-30 minutes)
Check CloudWatch logs for detailed progress
Contact support if stuck over 1 hour

Forecast Generation Fails

Ensure model training completed successfully
Verify customer ID and equipment details match exactly
Check forecast parameters are valid

Downloads Fail

Confirm forecast generation completed
Check output directory exists and is writable
Verify forecast type matches what was generated

Get Help & Stay Updated

Contact Support

For technical assistance, feature requests, or any other questions, please reach out to our dedicated support team.

Email Support Join Our Discord

Example:

/upload-inverter upload SOLAR001 "Cape Town" "SolarEdge" SE12345 /data/inverter.csv af-south-1 client123

Parameters:

CUSTOMER_ID - Unique customer identifier
LOCATION - Installation location (quoted if contains spaces)
MANUFACTURER - Equipment manufacturer name
SERIAL_NUMBER - Equipment serial number
FILE_PATH - Path to CSV data file
REGION - AWS region (e.g., af-south-1)
CLIENT_ID - Client identifier

`/upload-inverter status`

Check upload and training status.

# Check specific upload
/upload-inverter status UPLOAD_ID

# List all recent uploads
/upload-inverter status

Example:

/upload-inverter status SOLAR001_SE12345_1754151842

Status Display:

⚙️ Upload Status: PROCESSING
📋 Upload ID: SOLAR001_SE12345_1754151842
👤 Customer: SOLAR001
📍 Current Stage: trainForecaster
⏱️  Duration: 0:15:23

Pipeline Progress:
✅ Upload         → Completed (0:00:45)
✅ Ingestion      → Completed (0:02:15)
✅ Interpolation  → Completed (0:08:30)
🔄 Training       → In Progress (0:15:23)

📈 Forecast Commands

`/forecast-inverter start`

Generate new forecasts for trained models.

/forecast-inverter start CUSTOMER_ID LOCATION MANUFACTURER SERIAL_NUMBER REGION FORECAST_TYPE DAYS FREQUENCY

Example:

/forecast-inverter start SOLAR001 "Cape Town" "SolarEdge" SE12345 af-south-1 P50 7 daily

Parameters:

CUSTOMER_ID - Customer identifier (must match trained model)
LOCATION - Installation location
MANUFACTURER - Equipment manufacturer
SERIAL_NUMBER - Equipment serial number
REGION - AWS region
FORECAST_TYPE - P50 or P90 forecast type
DAYS - Number of days to forecast
FREQUENCY - daily or hourly

`/forecast-inverter get`

Download generated forecast results.

/forecast-inverter get CUSTOMER_ID LOCATION MANUFACTURER SERIAL_NUMBER REGION OUTPUT_PATH FORECAST_TYPE

Example:

/forecast-inverter get SOLAR001 "Cape Town" "SolarEdge" SE12345 af-south-1 /tmp/forecasts P50

`/forecast-inverter status`

Check forecast generation status.

# Check specific forecast
/forecast-inverter status FORECAST_ID

# List all recent forecasts
/forecast-inverter status

🔄 Workflow Example

Complete workflow from data upload to forecast generation:

1. Upload Training Data

🤖 | /upload-inverter upload SOLAR001 "Cape Town" "SolarEdge" SE12345 /data/solar_data.csv af-south-1 client123

2. Monitor Training Progress

🤖 | /upload-inverter status SOLAR001_SE12345_1754151842

Wait for training to complete (status shows “✅ Training → Completed”).

3. Generate Forecast

🤖 | /forecast-inverter start SOLAR001 "Cape Town" "SolarEdge" SE12345 af-south-1 P50 7 daily

4. Download Results

🤖 | /forecast-inverter get SOLAR001 "Cape Town" "SolarEdge" SE12345 af-south-1 /tmp/forecasts P50

💡 Tips & Best Practices

File Requirements

CSV format with timestamp and generation columns
Consistent naming for customer IDs and serial numbers
Valid file paths accessible from current directory

Monitoring

Use status commands regularly to track progress
Training typically takes 10-30 minutes depending on data size
Forecast generation is usually quick (1-2 minutes)

Error Handling

Commands validate parameters before execution
Clear error messages guide you to correct issues
Use status to check for detailed error information

Regional Considerations

Use af-south-1 for South African deployments
Ensure AWS credentials are configured for the specified region
Data processing occurs in the specified region

🔧 Status Indicators

Icon	Stage	Description
⏳	Pending	Waiting to start
🔄	Processing	Currently running
✅	Completed	Successfully finished
❌	Failed	Error occurred
⚠️	Warning	Completed with warnings

Pipeline Stages

Upload Pipeline:

Upload - File transfer to S3
Ingestion - Data validation and formatting
Interpolation - Gap filling and cleaning
Training - ML model training

Forecast Pipeline:

Generation - Creating forecast using trained model
Processing - Output formatting and validation
Storage - Saving results for download

Common Issues

Upload Fails

Check file path exists and is readable
Verify CSV format is correct
Ensure AWS credentials are configured

Training Stuck

Large datasets take longer (15-30 minutes)
Check CloudWatch logs for detailed progress
Contact support if stuck over 1 hour

Forecast Generation Fails

Ensure model training completed successfully
Verify customer ID and equipment details match exactly
Check forecast parameters are valid

Downloads Fail

Confirm forecast generation completed
Check output directory exists and is writable
Verify forecast type matches what was generated

Get Help & Stay Updated

Contact Support

For technical assistance, feature requests, or any other questions, please reach out to our dedicated support team.

Email Support Join Our Discord

Interactive Mode Commands

Getting Started

🛠️ System Commands

/help

/commands

/status

/models

/configure

/servers

/exit

📁 File Operations

/read

/list

/find

/edit

🐙 GitHub Integration

/github auth

/github repo

/github issues

/github pr

/github webhook

/github rate-limit

📝 Planning & Configuration

/ona

/prompts

📤 Upload Commands

/upload-inverter upload

/endpoints.html

Interactive Mode Commands

Getting Started

🛠️ System Commands

/help

/commands

/status

/models

/configure

/servers

/exit

📁 File Operations

/read

/list

/find

/edit

🐙 GitHub Integration

/github auth

/github repo

/github issues

/github pr

/github webhook

/github rate-limit

📝 Planning & Configuration

/ona

/prompts

📤 Upload Commands

/upload-inverter upload

/upload-inverter status

📈 Forecast Commands

/forecast-inverter start

/forecast-inverter get

/forecast-inverter status

🔄 Workflow Example

1. Upload Training Data

2. Monitor Training Progress

3. Generate Forecast

4. Download Results

💡 Tips & Best Practices

File Requirements

Monitoring

Error Handling

Regional Considerations

🔧 Status Indicators

Pipeline Stages

Common Issues

Upload Fails

Training Stuck

Forecast Generation Fails

Downloads Fail

Get Help & Stay Updated

Contact Support

Subscribe to Updates

`/help`

`/commands`

`/status`

`/models`

`/configure`

`/servers`

`/exit`

`/read`

`/list`

`/find`

`/edit`

`/github auth`

`/github repo`

`/github issues`

`/github pr`

`/github webhook`

`/github rate-limit`

`/ona`

`/prompts`

`/upload-inverter upload`

`/help`

`/commands`

`/status`

`/models`

`/configure`

`/servers`

`/exit`

`/read`

`/list`

`/find`

`/edit`

`/github auth`

`/github repo`

`/github issues`

`/github pr`

`/github webhook`

`/github rate-limit`

`/ona`

`/prompts`

`/upload-inverter upload`

`/upload-inverter status`

`/forecast-inverter start`

`/forecast-inverter get`

`/forecast-inverter status`

`/upload-inverter status`

`/forecast-inverter start`

`/forecast-inverter get`

`/forecast-inverter status`