# Demand from the agent and get a full response when it finishes

Executes a chain of AI-powered reasoning and actions to respond to a given query or task.
    
    The agent leverages its configured tools and knowledge to:
    - Analyze the input query
    - Plan necessary steps
    - Execute relevant tools
    - Synthesize a comprehensive response
    
    ## Image Support
    Include images in your request using the images field:
    - Base64 Format: Set type="base64" with base64-encoded image data
    - File Path: Set type="file_path" with path to existing image
    
    Maximum 5 images per request. Invalid images will trigger a 400 response.
    
    ## Authentication
    Requires API key via x-wabee-access header.
    
    ## Session Management
    Use session-id header to maintain conversation context across requests.

Endpoint: POST /core/v1/chain
Version: v1
Security: APIKeyHeader

## Header parameters:

  - `session-id` (any)
    Session unique identifier, used to keep track of previous interations and enhanced observability. We recommend using a UUID string.

  - `request-id` (any)
    Custom request unique identifier, if not provided a new one will be generated. We recommend using a UUID string.

## Request fields (application/json):

  - `messages` (array, required)
    List of messages to be processed by the agent
    Example: [{"content":"What is the economic outlook?","role":"user"}]

  - `messages.role` (string, required)
    defines the role associated with the message
    Example: "assistant"

  - `messages.content` (string, required)
    message content
    Example: "Hello, I am your virtual assistant"

  - `data_filter_hints` (any)
    Special metadata-like hints to be passed to the agent in order to instruct him on how to filter the data on some tools that support filter
    Example: [{"filter_key":"unitname","filter_type":"equals","filter_value":"Unit 1","tool_name":"bubble_data"}]

  - `auto_memory_retain` (boolean)
    Indicates whether the agent should automatically retain information from the session in memory. When enabled, allows the agent to learn from experiences and feedback.

  - `context_files` (any)
    The path for files which the agent already has access to and should be considered by it when processing the messages
    Example: ["inputs/chat-files/test123/file.pdf"]

  - `images` (any)
    List of images associated with the message

## Response 200 fields (application/json):

  - `body` (object, required)
    The complete agent response

  - `body.input` (string, required)
    The original input message sent to the agent
    Example: "What is the economic outlook?"

  - `body.output` (string, required)
    The final response generated by the agent
    Example: "The economic outlook varies significantly by region..."

  - `body.intermediate_steps` (array, required)
    The sequence of steps taken by the agent to generate the response, including tool usage and reasoning
    Example: [[{"log":"Retrieving news data","tool":"api_tool","tool_input":"curl https://newsapi.org/v2/everything","type":"AgentAction"},"Explanation: Gathering real-time economic data from trusted sources"]]

  - `body.usage` (array, required)
    Resource usage metrics for the request

  - `body.usage.costAttribute` (string, required)
    The name of the resource being measured (e.g. model name)
    Example: "gpt-4-32k"

  - `body.usage.usage` (string, required)
    The quantity of the resource used
    Example: "100"

  - `body.usage.unit` (string, required)
    The unit of measurement (e.g. tokens, requests)
    Example: "tokens"

## Response 400 fields (application/json):

  - `body` (string, required)
    Error message or description

  - `status_code` (integer, required)
    HTTP status code
    Example: 400

  - `details` (any)
    Additional error details if available

## Response 401 fields (application/json):

  - `body` (string, required)
    Error message or description

  - `status_code` (integer, required)
    HTTP status code
    Example: 400

  - `details` (any)
    Additional error details if available

## Response 403 fields (application/json):

  - `body` (string, required)
    Error message or description

  - `status_code` (integer, required)
    HTTP status code
    Example: 400

  - `details` (any)
    Additional error details if available

## Response 413 fields (application/json):

  - `body` (string, required)
    Error message or description

  - `status_code` (integer, required)
    HTTP status code
    Example: 400

  - `details` (any)
    Additional error details if available

## Response 422 fields (application/json):

  - `body` (string, required)
    Error message or description

  - `status_code` (integer, required)
    HTTP status code
    Example: 400

  - `details` (any)
    Additional error details if available

## Response 500 fields (application/json):

  - `body` (string, required)
    Error message or description

  - `status_code` (integer, required)
    HTTP status code
    Example: 400

  - `details` (any)
    Additional error details if available