Supervisor agent payload

[hanna-paasivirta]

Short Description

Suggested payloads for the Global Agent service. Note that without these changes, it would work with the existing formats used in job_chat and workflow_chat.

Input Payload

{
  "content": "string (REQUIRED)",        // User message

  "context": {                           // All contextual information
    "workflow_yaml": "string (optional)", // Current workflow YAML
    "job_code": {                        // Job code context (optional)
      "expression": "string",
      "page_name": "string",
      "adaptor": "string"
    },
    "errors": "string (optional)"        // Error context
  },

  "history": [                           // Chat history (optional)
    {
      "role": "user|assistant",
      "content": "string",
      "attachments": []
    }
  ],

  "stream": false,
  "read_only": false,
  "api_key": "string (optional)"
}

Output Payload

{
  "response": "string",                  // Main text response

  "attachments": [                       // Output attachments
    {
      "type": "workflow_yaml|job_code|document|link",
      "content": "string"
    }
  ],

  "history": [                           // Updated conversation history
    {
      "role": "user|assistant",
      "content": "string",
      "attachments": []
    }
  ],

  "usage": {                             // Token usage (4 fields)
    "input_tokens": 0,
    "output_tokens": 0,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0
  },

  "meta": {                              // Execution metadata
    "agents": ["router", "planner", "workflow_agent"],  // Execution chain
    "router_confidence": 5,              // Optional details
    "planner_iterations": 2
  }
}

A more detailed breakdown of the changes, including motivations (if not provided in the issue).

AI Usage

Please disclose how you've used AI in this work (it's cool, we just want to know!):

• Code generation (copilot but not intellisense)
• Learning or fact checking
• Strategy / design
• Optimisation / refactoring
• Translation / spellchecking / doc gen
• Other
• I have not used AI

You can read more details in our Responsible AI Policy