Import bounded content-free production request shapes for monitoring and replay

curl --request POST \
  --url http://127.0.0.1:18000/api/v1/deployments/{name}/traffic-observations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "observations": [
    {
      "latency_ms": 43200000,
      "operation": "<string>",
      "source_request_id": "<string>",
      "started_at": "2023-11-07T05:31:56Z",
      "status_code": 349,
      "streaming": true,
      "error_type": "<string>",
      "generation_ms": 43200000,
      "input_tokens": 5000000,
      "output_tokens": 5000000,
      "parent_session_id_hash": "<string>",
      "provider": "<string>",
      "queue_ms": 43200000,
      "request_model": "<string>",
      "response_model": "<string>",
      "retry_count": 50,
      "runtime": "<string>",
      "semantic_convention_schema": "<string>",
      "session_id_hash": "<string>",
      "shared_prefix_hash": "<string>",
      "tool_pause_ms": 43200000,
      "ttft_ms": 43200000
    }
  ],
  "schema_version": "infercrane.traffic-observations/v1"
}
'

import requests

url = "http://127.0.0.1:18000/api/v1/deployments/{name}/traffic-observations"

payload = {
    "observations": [
        {
            "latency_ms": 43200000,
            "operation": "<string>",
            "source_request_id": "<string>",
            "started_at": "2023-11-07T05:31:56Z",
            "status_code": 349,
            "streaming": True,
            "error_type": "<string>",
            "generation_ms": 43200000,
            "input_tokens": 5000000,
            "output_tokens": 5000000,
            "parent_session_id_hash": "<string>",
            "provider": "<string>",
            "queue_ms": 43200000,
            "request_model": "<string>",
            "response_model": "<string>",
            "retry_count": 50,
            "runtime": "<string>",
            "semantic_convention_schema": "<string>",
            "session_id_hash": "<string>",
            "shared_prefix_hash": "<string>",
            "tool_pause_ms": 43200000,
            "ttft_ms": 43200000
        }
    ],
    "schema_version": "infercrane.traffic-observations/v1"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    observations: [
      {
        latency_ms: 43200000,
        operation: '<string>',
        source_request_id: '<string>',
        started_at: '2023-11-07T05:31:56Z',
        status_code: 349,
        streaming: true,
        error_type: '<string>',
        generation_ms: 43200000,
        input_tokens: 5000000,
        output_tokens: 5000000,
        parent_session_id_hash: '<string>',
        provider: '<string>',
        queue_ms: 43200000,
        request_model: '<string>',
        response_model: '<string>',
        retry_count: 50,
        runtime: '<string>',
        semantic_convention_schema: '<string>',
        session_id_hash: '<string>',
        shared_prefix_hash: '<string>',
        tool_pause_ms: 43200000,
        ttft_ms: 43200000
      }
    ],
    schema_version: 'infercrane.traffic-observations/v1'
  })
};

fetch('http://127.0.0.1:18000/api/v1/deployments/{name}/traffic-observations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "http://127.0.0.1:18000/api/v1/deployments/{name}/traffic-observations"

	payload := strings.NewReader("{\n  \"observations\": [\n    {\n      \"latency_ms\": 43200000,\n      \"operation\": \"<string>\",\n      \"source_request_id\": \"<string>\",\n      \"started_at\": \"2023-11-07T05:31:56Z\",\n      \"status_code\": 349,\n      \"streaming\": true,\n      \"error_type\": \"<string>\",\n      \"generation_ms\": 43200000,\n      \"input_tokens\": 5000000,\n      \"output_tokens\": 5000000,\n      \"parent_session_id_hash\": \"<string>\",\n      \"provider\": \"<string>\",\n      \"queue_ms\": 43200000,\n      \"request_model\": \"<string>\",\n      \"response_model\": \"<string>\",\n      \"retry_count\": 50,\n      \"runtime\": \"<string>\",\n      \"semantic_convention_schema\": \"<string>\",\n      \"session_id_hash\": \"<string>\",\n      \"shared_prefix_hash\": \"<string>\",\n      \"tool_pause_ms\": 43200000,\n      \"ttft_ms\": 43200000\n    }\n  ],\n  \"schema_version\": \"infercrane.traffic-observations/v1\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "category": "<string>",
    "remediation": "<string>",
    "request_id": "<string>",
    "retryable": true
  }
}