Analyze this single multi-agent trajectory and architecture to identify features that are suitable to insert into a classification model to replace certain nodes.

TRAJECTORY DATA:
${trajectory_json}

The schema of the trajectory data is given to you:
${trajectory_schema}

Your task is to:
1. The classification suitable component is given to you: ${target_name}
2. For this classification node, extract potential features that could be used to train a replacement model using past steps.
3. Consider features from: user inputs, system prompts, context from previous steps, available options, thoughts of previous steps etc.
4. Do not try to solve classification with embeddings, classification should only be based on data that can be taken from the trajectory using code.

The classification suitable component full step is given to you, but in your analysis, you should only use the data that can be taken from the trajectory before this component:

${target_json}

Return your analysis in this JSON format:
{
  "potential_features": [
    {
      "feature_name": "descriptive name",
      "feature_type": "text/numeric/categorical/computed",
      "description": "what this feature represents",
      "extraction_source": "where in the data this comes from",
      "computation": "how to compute this feature",
      "classification_relevance": "how this helps with the classification task",
      "rationale": "why this would be useful",
      "trajectory_file": "${trajectory_file}"
    }
  ]
}

Focus on features that would actually help a model learn to make the same decisions as the original agents, and are obtained from the trajectory before the classification suitable component.
