Troubleshooting - Circuit Breaker Labs CLI

This page covers common issues you may encounter and how to resolve them.

Common Errors

Missing API Key

Error Message

error: the following required arguments were not provided:
  --cbl-api-key <CBL_API_KEY>

Solution

Set the CBL_API_KEY environment variable:

export CBL_API_KEY="cbl_your_api_key_here"

Or provide it as a command-line argument:

cbl --cbl-api-key "cbl_your_key" single-turn ...

Get your API key by contacting team@circuitbreakerlabs.ai

OpenAI API Key Missing

Error Message

error: the following required arguments were not provided:
  --api-key <API_KEY>

Solution

When using the OpenAI provider, set the OPENAI_API_KEY environment variable:

export OPENAI_API_KEY="sk-your_openai_key"

Or provide it explicitly:

cbl single-turn openai --api-key "sk-your_key" --model gpt-4o ...

WebSocket Connection Failed

Error Message

WebSocket error: failed to connect to wss://api.circuitbreakerlabs.ai/v1

Possible Causes and Solutions

1. Network connectivity issuesCheck your internet connection and verify you can reach the API:

ping api.circuitbreakerlabs.ai

2. Firewall or proxy blocking WebSocket connectionsEnsure your firewall allows outbound WebSocket connections on port 443. If behind a corporate proxy, you may need to configure proxy settings.3. Invalid API keyVerify your API key is correct and active:

echo $CBL_API_KEY

4. Custom base URL misconfiguredIf using a custom CBL_API_BASE_URL, verify the URL format:

# Correct format (wss:// for WebSocket Secure)
export CBL_API_BASE_URL="wss://api.circuitbreakerlabs.ai/v1"

# NOT https:// or http://

Provider API Errors

OpenAI Errors

Error: Rate limit exceeded

Provider error: API error: Rate limit exceeded

Solution: Wait and retry, or reduce the number of variations/test cases:

# Reduce load
cbl single-turn --variations 2 --maximum-iteration-layers 1 ...

Error: Invalid model

Provider error: API error: The model 'gpt-5' does not exist

Solution: Use a valid OpenAI model name:

cbl single-turn openai --model gpt-4o ...
# Valid models: gpt-4o, gpt-4-turbo, gpt-3.5-turbo, etc.

Error: Insufficient quota

Provider error: API error: You exceeded your current quota

Solution: Check your OpenAI billing settings and add credits to your account.

Ollama Errors

Error: Connection refused

Provider error: Network error: Connection refused

Solution: Ensure Ollama is running:

# Start Ollama
ollama serve

# Verify it's running
curl http://localhost:11434/api/tags

Error: Model not found

Provider error: API error: model 'llama3' not found

Solution: Pull the model first:

# Pull the model
ollama pull llama2

# List available models
ollama list

# Then run evaluation
cbl single-turn ollama --model llama2 ...

Script Errors (Custom Provider)

Error Message

Provider error: Script execution error: Function not found: transform_request

Solution

Your Rhai script must define the required functions. See the examples/providers/ directory for templates.Minimal script structure:

// Transform CBL request to your API format
fn transform_request(messages) {
    #{
        messages: messages,
        // your API-specific fields
    }
}

// Extract response from your API format
fn extract_response(response) {
    response.content  // adjust for your API
}

File Write Errors

Error Message

Result save error: Permission denied (os error 13)

Solution

1. Check directory permissions

ls -la results/

2. Use a different output directory

cbl --output-file ~/evaluations/results.json single-turn ...

3. Ensure the parent directory exists

mkdir -p results
cbl --output-file results/eval.json single-turn ...

JSON Parsing Errors

Error Message

JSON serialization error: expected value at line 1 column 1

Solution

This usually indicates the API returned unexpected output. Enable debug logging:

cbl --log-mode --log-level debug single-turn ...

Check the logs for the actual API response and verify:

The provider is returning valid responses
Your custom script (if using custom provider) is formatting output correctly
The API endpoint is responding with the expected format

Debugging Techniques

Enable Log Mode

Disable the TUI and see detailed logs:

cbl --log-mode --log-level debug single-turn ...

This shows:

WebSocket connection details
API requests and responses
Evaluation progress
Error stack traces

Increase Log Level

Get more detailed information:

# Show all debug information
cbl --log-level debug single-turn ...

# Show extremely verbose trace logs
cbl --log-level trace single-turn ...

trace level logging can be very verbose. Use it only when debugging specific issues.

Test Provider Connection

Verify your provider is working before running full evaluations: OpenAI:

curl https://api.openai.com/v1/models \
  -H "Authorization: Bearer $OPENAI_API_KEY"

Ollama:

curl http://localhost:11434/api/tags

Use Minimal Test Cases

Start with a small evaluation to isolate issues:

cbl single-turn \
  --threshold 0.5 \
  --variations 1 \
  --maximum-iteration-layers 1 \
  openai --model gpt-4o

Check Network Connectivity

Verify you can reach the Circuit Breaker Labs API:

# Check DNS resolution
nslookup api.circuitbreakerlabs.ai

# Check HTTPS connectivity
curl -I https://api.circuitbreakerlabs.ai

Configuration Issues

Environment Variables Not Working

Issue

Environment variables aren’t being recognized.

Solution

1. Verify they’re exported

echo $CBL_API_KEY
echo $OPENAI_API_KEY

2. Export in the same shell session

# These must be in the same terminal session
export CBL_API_KEY="cbl_..."
export OPENAI_API_KEY="sk-..."
cbl single-turn ...

3. Add to shell profile for persistence

# Add to ~/.bashrc or ~/.zshrc
echo 'export CBL_API_KEY="cbl_..."' >> ~/.bashrc
source ~/.bashrc

Custom Headers Not Applied

Issue

Headers specified with --add-header aren’t being sent.

Solution

Verify the header format:

# Correct format (in quotes, with colon)
cbl --add-header "X-Custom:value" single-turn ...

# Multiple headers
cbl --add-header "X-Custom:value" --add-header "X-Another:value2" single-turn ...

Enable debug logging to verify headers are being sent:

cbl --log-mode --log-level debug --add-header "X-Test:value" single-turn ...

Wrong Command Order

Issue

error: unexpected argument '--threshold' found

Solution

The command structure is:

cbl [GLOBAL_OPTIONS] <EVALUATION_TYPE> [EVAL_OPTIONS] <PROVIDER> [PROVIDER_OPTIONS]

Example order:

# Correct
cbl --log-mode --output-file results.json \
  single-turn --threshold 0.5 --variations 2 \
  openai --model gpt-4o --temperature 0.7

# Wrong - global options must come first
cbl single-turn --threshold 0.5 --log-mode ...

Performance Issues

Evaluation Running Slowly

Possible Causes and Solutions

1. High number of variationsReduce --variations and --maximum-iteration-layers:

# Faster
cbl single-turn --variations 2 --maximum-iteration-layers 1 ...

# Slower
cbl single-turn --variations 5 --maximum-iteration-layers 3 ...

2. Provider rate limitsOpenAI and other providers have rate limits. The CLI automatically retries, but this adds latency.3. Network latencyIf using Ollama, ensure it’s running locally for best performance:

# Local Ollama (fast)
ollama serve
cbl single-turn ollama --model llama2 ...

4. Large context windowsFor Ollama, reduce --num-ctx if you don’t need large contexts:

cbl single-turn ollama --model llama2 --num-ctx 2048 ...

High Memory Usage

Issue

The CLI or provider is consuming too much memory.

Solution

For Ollama, limit GPU layers and context size:

cbl single-turn ollama \
  --model llama2 \
  --num-gpu 20 \
  --num-ctx 2048 \
  ...

Run fewer evaluations concurrently and process in batches.

Getting Help

Command Help

View available options for any command:

# Main help
cbl help

# Evaluation type help
cbl single-turn help
cbl multi-turn help

# Provider help
cbl single-turn openai help
cbl single-turn ollama help
cbl single-turn custom help

Enable Verbose Output

Combine log mode with debug level for maximum information:

cbl --log-mode --log-level trace single-turn ...

Check Version

cbl --version

Contact Support

If you’re still experiencing issues:

Collect debug logs:

cbl --log-mode --log-level debug single-turn ... > debug.log 2>&1

Check the repository:
Visit github.com/circuitbreakerlabs/cli for:
- Known issues
- Latest releases
- Example configurations
Contact the team:
Email team@circuitbreakerlabs.ai with:
- Your command
- Error message
- Debug logs
- CLI version (cbl --version)

When reporting issues, always include the CLI version and relevant error messages from debug logs.

​Common Errors

​Error Message

​Solution

​Error Message

​Solution

​Error Message

​Possible Causes and Solutions

​OpenAI Errors

​Ollama Errors

​Error Message

​Solution

​Error Message

​Solution

​Error Message

​Solution

​Debugging Techniques

​Enable Log Mode

​Increase Log Level

​Test Provider Connection

​Use Minimal Test Cases

​Check Network Connectivity

​Configuration Issues

​Issue

​Solution

​Issue

​Solution

​Issue

​Solution

​Performance Issues

​Possible Causes and Solutions

​Issue

​Solution

​Getting Help

​Command Help

​Enable Verbose Output

​Check Version

​Contact Support

Common Errors

Error Message

Solution

Error Message

Solution

Error Message

Possible Causes and Solutions

OpenAI Errors

Ollama Errors

Error Message

Solution

Error Message

Solution

Error Message

Solution

Debugging Techniques

Enable Log Mode

Increase Log Level

Test Provider Connection

Use Minimal Test Cases

Check Network Connectivity

Configuration Issues

Issue

Solution

Issue

Solution

Issue

Solution

Performance Issues

Possible Causes and Solutions

Issue

Solution

Getting Help

Command Help

Enable Verbose Output

Check Version

Contact Support