Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.mirobody.ai/llms.txt

Use this file to discover all available pages before exploring further.

This endpoint requires LLM credentials for the async AI processing (classification / summary / symptom extraction). Pass X-LLM-Provider and X-LLM-Api-Key. See BYOK.

​
Endpoint

POST /api/v1/holywell/journal/create
Authorization:   Bearer <access_token>
X-LLM-Provider:  dashscope | volcengine | openai | gemini
X-LLM-Api-Key:   <your LLM key>
Content-Type:    application/json

{
  "id":         "<optional session_id, for idempotency>",
  "text_input": "Feeling energetic today",
  "files":      [ /* ChatFileObject array, see /api/chat */ ],
  "ts":         1779431900000
}
text_input and files — at least one must be present.

​
Response

{
  "code": 0, "msg": "ok",
  "data": {
    "input":        { "content":"Feeling energetic today", "file_list":[], "ts":1779431900000, "msg_ids":[] },
    "ts":           1779431900000,
    "session_id":   "today_504_2026_05_22_1779431370215",
    "read_status":  0,
    "write_status": 1,
    "ai_status":    0,
    "journal_id":   109,
    "summary":      null,
    "symptom":      null,
    "version":      1
  }
}
The server writes the journal row immediately; AI processing runs asynchronously. Poll /journal/list until ai_status == 1. Recommended polling interval: 2–5 seconds, up to 60s total.