在 POST /v1/responses 上用 text.format 把模型输出强制为 JSON。它遵循 OpenAI Responses text.format 规范，仅在 backbone 模式（mode:"model"）下可用。
text.format 需要 mode:"model"。在默认的 agent 模式下它返回 400 unsupported_parameter（param: "text"）—— 自由文本在下游爆炸比接口报错贵得多。Answers API（/v1/chat/completions）同样以 400 拒绝 response_format。
json_object
把输出约束为语法合法的 JSON 对象（无 schema）：
{
"model": "mirobody-flash",
"mode": "model",
"input": "Reply with a JSON object having keys a and b.",
"text": { "format": { "type": "json_object" } }
}
{ "output_text": "{\"a\":1,\"b\":2}", "status": "completed", ... }
json_schema
把输出约束为你提供的 schema。设 strict: true 要求严格贴合 schema：
curl https://mirobody-api.thetahealth.ai/v1/responses \
-H "Authorization: Bearer $MIROBODY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mirobody-flash",
"mode": "model",
"input": "Give me a manifest for apples with count 3.",
"text": {
"format": {
"type": "json_schema",
"name": "manifest",
"strict": true,
"schema": {
"type": "object",
"properties": {
"item": { "type": "string" },
"count": { "type": "integer" }
},
"required": ["item", "count"],
"additionalProperties": false
}
}
}
}'
from openai import OpenAI
client = OpenAI(api_key="mb_live_...", base_url="https://mirobody-api.thetahealth.ai/v1")
resp = client.responses.create(
model="mirobody-flash",
extra_body={"mode": "model"},
input="Give me a manifest for apples with count 3.",
text={
"format": {
"type": "json_schema",
"name": "manifest",
"strict": True,
"schema": {
"type": "object",
"properties": {"item": {"type": "string"}, "count": {"type": "integer"}},
"required": ["item", "count"],
"additionalProperties": False,
},
}
},
)
print(resp.output_text) # {"item":"apples","count":3}
Provider 降级
text.format 透传给底层模型。当背后的 provider 没有原生 json_schema 支持时，Mirobody 会自动降级重试一次 —— 用 json_object + 把 schema 注入系统提示。该重试对你透明（你仍拿到符合 schema 形状的 JSON），因此无需关心某个档位背后是哪个 provider，都可把结构化输出当作可靠能力使用。
