> ## Documentation Index > Fetch the complete documentation index at: https://docs.llmide.app/llms.txt > Use this file to discover all available pages before exploring further. # Submit diagnosis data > Submits external diagnosis session data (including input/output, timing, and additional fields) to the backend diagnosis table and generates API call logs ## OpenAPI ````yaml api-reference/openapi.json post /v1/prompts openapi: 3.1.0 info: title: Prompt Management API description: >- API for managing and retrieving prompt configurations with deployment and workspace information license: name: MIT version: 1.0.0 servers: - url: https://api.llmide.app description: Production API server security: - bearerAuth: [] paths: /v1/prompts: post: tags: - Diagnosis summary: Submit diagnosis data description: >- Submits external diagnosis session data (including input/output, timing, and additional fields) to the backend diagnosis table and generates API call logs operationId: submitDiagnosisData parameters: - name: deployId in: query description: >- The target deployment ID. Must belong to the current API key's workspace and be in active state required: true schema: type: string example: dep_12345 requestBody: required: true description: Diagnosis session data to be recorded content: application/json: schema: $ref: '#/components/schemas/DiagnosisRequest' responses: '201': description: Diagnosis data recorded successfully headers: X-RateLimit-Limit: description: The rate limit ceiling for the workspace schema: type: integer X-RateLimit-Remaining: description: >- The number of requests remaining in the current rate limit window schema: type: integer X-RateLimit-Used: description: The number of requests used in the current rate limit window schema: type: integer X-RateLimit-Reset: description: The time when the rate limit resets (Unix timestamp) schema: type: integer content: application/json: schema: $ref: '#/components/schemas/DiagnosisResponse' '400': description: >- Bad request - missing required fields, invalid deployId, empty content, or invalid timestamp format content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized - missing, invalid, or expired authorization content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Not found - deploy not found, inactive, or not accessible content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Rate limit exceeded - monthly quota exhausted content: application/json: schema: $ref: '#/components/schemas/RateLimitErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' x-codeSamples: - lang: curl source: >- curl -X POST "https://api.llmide.app/v1/diagnosis?deployId=dep_12345" \ -H "Authorization: Bearer sk_live_xxx" \ -H "Content-Type: application/json" \ -d '{ "sessionId": "sess_789", "status": 0, "content": { "input": "Prompt variables: {...}", "output": "LLM reply content" }, "latency": 2450, "startAt": 1720780800000, "endAt": 1720780802450, "additional_properties": { "trace_id": "trc_abc", "token_usage": { "prompt_tokens": 200, "completion_tokens": 150 } } }' - lang: python source: |- import requests import json headers = { 'Authorization': 'Bearer sk_live_xxx', 'Content-Type': 'application/json' } params = { 'deployId': 'dep_12345' } data = { 'sessionId': 'sess_789', 'status': 0, 'content': { 'input': 'Prompt variables: {...}', 'output': 'LLM reply content' }, 'latency': 2450, 'startAt': 1720780800000, 'endAt': 1720780802450, 'additional_properties': { 'trace_id': 'trc_abc', 'token_usage': {'prompt_tokens': 200, 'completion_tokens': 150} } } response = requests.post( 'https://api.llmide.app/v1/diagnosis', headers=headers, params=params, data=json.dumps(data) ) print(response.json()) - lang: javascript source: >- const response = await fetch('https://api.llmide.app/v1/diagnosis?deployId=dep_12345', { method: 'POST', headers: { 'Authorization': 'Bearer sk_live_xxx', 'Content-Type': 'application/json' }, body: JSON.stringify({ sessionId: 'sess_789', status: 0, content: { input: 'Prompt variables: {...}', output: 'LLM reply content' }, latency: 2450, startAt: 1720780800000, endAt: 1720780802450, additional_properties: { trace_id: 'trc_abc', token_usage: { prompt_tokens: 200, completion_tokens: 150 } } }) }); const data = await response.json(); console.log(data); components: schemas: DiagnosisRequest: type: object required: - sessionId - status - content properties: sessionId: type: string description: External diagnosis session identifier example: sess_789 status: type: integer description: Business-defined status code, stored as integer example: 0 content: $ref: '#/components/schemas/DiagnosisContent' latency: type: number description: Call latency in milliseconds minimum: 0 example: 2450 startAt: type: integer description: Session start time, UNIX millisecond timestamp, must be non-negative minimum: 0 example: 1720780800000 endAt: type: integer description: Session end time, UNIX millisecond timestamp, must be non-negative minimum: 0 example: 1720780802450 additional_properties: type: object description: Arbitrary JSON structure for additional information, stored as-is example: trace_id: trc_abc token_usage: prompt_tokens: 200 completion_tokens: 150 additionalProperties: true DiagnosisResponse: type: object required: - id - status - message properties: id: type: string description: Newly created diagnosis record ID example: diag_abc123 status: type: string description: Fixed value 'success' enum: - success example: success message: type: string description: Success message example: Diagnosis data recorded successfully ErrorResponse: type: object required: - error properties: error: type: string description: Error message examples: - Missing or invalid deployId parameter - Missing or invalid authorization header - No API key provided - Invalid API key - Deploy not found or not accessible - Internal server error RateLimitErrorResponse: type: object required: - error - details properties: error: type: string description: Rate limit error message example: Rate limit exceeded details: type: object properties: limit: type: integer description: Monthly rate limit used: type: integer description: Requests used this month resetTime: type: integer description: Unix timestamp when the limit resets upgradeUrl: type: string nullable: true description: Optional upgrade link DiagnosisContent: type: object description: >- Session input/output content. At least one of input or output must be provided properties: input: type: string description: Session input text example: 'Prompt variables: {...}' output: type: string description: Session output text example: LLM reply content anyOf: - required: - input - required: - output securitySchemes: bearerAuth: type: http scheme: bearer ````