observability

Observability diagnostics and trace verification CLI

praisonai obs

Observability diagnostics and management commands.

Usage

# Via praisonai wrapper
praisonai obs [COMMAND] [OPTIONS]

# Standalone (no wrapper needed)
python -m praisonai_tools.observability.cli [COMMAND] [OPTIONS]

Commands

doctor

Run observability health checks.

praisonai obs doctor
praisonai obs doctor --json

Option	Description
--json	Output as JSON

Output:

Check	Description
Enabled	Whether observability is initialized
Active Provider	Currently configured provider
Connection	Provider connectivity status
Available Providers	Providers with installed dependencies
Registered Providers	All known provider plugins

verify

Verify traces are recorded in the observability backend using the provider’s SDK.

praisonai obs verify --provider langsmith --project "My First App"
praisonai obs verify --provider langsmith --project "My First App" --json

Option	Default	Description
--provider	langsmith	Provider to verify
--project	default	Project name to check
--limit	5	Number of recent runs to check
--json		Output as JSON

Required environment variables:

export LANGSMITH_API_KEY=lsv2_xxx
export LANGSMITH_ENDPOINT=https://api.smith.langchain.com  # or eu endpoint

Output:

The verify command checks each run for PraisonAI branding metadata (praisonai.version, praisonai.framework) and shows inputs/outputs status.

Examples

Quick Health Check

python -m praisonai_tools.observability.cli doctor --json

{
  "enabled": true,
  "provider": "langsmith",
  "connection_status": true,
  "connection_message": "LangSmith API key configured"
}

Verify LangSmith Traces

export LANGSMITH_API_KEY=lsv2_xxx
python -m praisonai_tools.observability.cli verify --project "My First App"

Programmatic Usage

from praisonai_tools.observability import obs

obs.init(provider="langsmith")
results = obs.doctor()
print(results)

What Gets Checked

• Provider initialization status
• API key configuration
• Backend connectivity
• Trace branding (praisonai.version, praisonai.framework)
• Input/output data capture
• Agent and workflow span recording

Related

• Observability Overview - All providers
• LangSmith - LangSmith setup
• Langfuse - Langfuse setup