messagesarray<object>RequiredKeep the task boundary explicit: name the deliverable, the information that controls it and the conditions that make it acceptable. Include a counterexample when nearby categories are easy to confuse. If the source material has conflicting dates or values, ask Terra to retain the conflict and identify what would resolve it instead of selecting an unsupported answer.
- Default
- Not specified
- Constraints
- minItems:1maxItems:256
messages[].rolestringRequired within objectRole of the message author.
- Default
- Not specified
- Allowed values
"system""developer""user""assistant""tool"
messages[].namestringOptionalOptional name identifying the speaker within its role.
- Default
- Not specified
messages[].contentstring | array | nullOptionalMessage content, either plain text or a list of content parts.
- Default
- Not specified
{
"type": [
"string",
"array",
"null"
],
"items": {
"oneOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"const": "text"
}
}
},
{
"type": "object",
"required": [
"type",
"image_url"
],
"properties": {
"type": {
"const": "image_url"
},
"image_url": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
}
}
}
}
}
]
},
"description": "Message content, either plain text or a list of content parts."
}messages[].tool_callsarray<object>OptionalTool calls the assistant requested in this message.
- Default
- Not specified
messages[].tool_call_idstringOptionalIdentifier of the tool call this message answers. Required on tool messages.
- Default
- Not specified
messages[].reasoning_contentstringOptionalReasoning text from a previous assistant reply, preserved when continuing a tool conversation.
- Default
- Not specified
{
"type": "array",
"x-ui": {
"order": 100,
"widget": "chat-messages",
"primary": true
},
"items": {
"type": "object",
"allOf": [
{
"if": {
"required": [
"reasoning_content"
]
},
"then": {
"properties": {
"role": {
"const": "assistant"
}
}
}
}
],
"required": [
"role"
],
"properties": {
"name": {
"type": "string",
"description": "Optional name identifying the speaker within its role."
},
"role": {
"enum": [
"system",
"developer",
"user",
"assistant",
"tool"
],
"type": "string",
"description": "Role of the message author."
},
"content": {
"type": [
"string",
"array",
"null"
],
"items": {
"oneOf": [
{
"type": "object",
"required": [
"type",
"text"
],
"properties": {
"text": {
"type": "string"
},
"type": {
"const": "text"
}
}
},
{
"type": "object",
"required": [
"type",
"image_url"
],
"properties": {
"type": {
"const": "image_url"
},
"image_url": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
}
}
}
}
}
]
},
"description": "Message content, either plain text or a list of content parts."
},
"tool_calls": {
"type": "array",
"items": {
"type": "object"
},
"description": "Tool calls the assistant requested in this message."
},
"tool_call_id": {
"type": "string",
"description": "Identifier of the tool call this message answers. Required on tool messages."
},
"reasoning_content": {
"type": "string",
"description": "Reasoning text from a previous assistant reply, preserved when continuing a tool conversation."
}
},
"additionalProperties": false
},
"maxItems": 256,
"minItems": 1,
"description": "Conversation history in order, oldest message first."
}