Compile bounded user intent into an editable reviewed configuration

curl --request POST \
  --url http://127.0.0.1:18000/api/v1/planning/intents \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "intent": "<string>",
  "gpu": "<string>",
  "model": "<string>",
  "provider": "<string>",
  "region": "<string>"
}
'

import requests

url = "http://127.0.0.1:18000/api/v1/planning/intents"

payload = {
    "intent": "<string>",
    "gpu": "<string>",
    "model": "<string>",
    "provider": "<string>",
    "region": "<string>"
}
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({
    intent: '<string>',
    gpu: '<string>',
    model: '<string>',
    provider: '<string>',
    region: '<string>'
  })
};

fetch('http://127.0.0.1:18000/api/v1/planning/intents', 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/planning/intents"

	payload := strings.NewReader("{\n  \"intent\": \"<string>\",\n  \"gpu\": \"<string>\",\n  \"model\": \"<string>\",\n  \"provider\": \"<string>\",\n  \"region\": \"<string>\"\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))

}

{
  "capacity_reserved": false,
  "performance_claims": false,
  "plan": {
    "architecture": {
      "edges": [
        {
          "from": "<string>",
          "label": "<string>",
          "to": "<string>"
        }
      ],
      "nodes": [
        {
          "id": "<string>",
          "kind": "<string>",
          "label": "<string>",
          "state": "<string>"
        }
      ]
    },
    "choices": [
      {
        "editable": true,
        "field": "<string>",
        "label": "<string>",
        "required": true,
        "options": [
          {
            "label": "<string>",
            "value": "<string>",
            "reason": "<string>",
            "state": "<string>"
          }
        ],
        "value": "<string>"
      }
    ],
    "evidence": {
      "capacity": "<string>",
      "configuration": "<string>",
      "performance": "<string>",
      "price": {
        "deployment_comparable": true,
        "reason": "<string>",
        "state": "current",
        "cost_scope": "<string>",
        "currency": "<string>",
        "hourly_usd_per_replica": 1,
        "observed_at": "2023-11-07T05:31:56Z",
        "price_authority": "<string>",
        "source": "<string>",
        "valid_until": "2023-11-07T05:31:56Z"
      }
    },
    "interpretation": {
      "action": "deploy",
      "objective": "interactive",
      "compute_mode": "elastic"
    },
    "missing_choices": [
      {
        "field": "<string>",
        "prompt": "<string>",
        "reason": "<string>",
        "remediation": "<string>",
        "options": [
          {
            "label": "<string>",
            "value": "<string>",
            "reason": "<string>",
            "state": "<string>"
          }
        ]
      }
    ],
    "mutation": "none",
    "schema_version": "infercrane.intent-plan/v1",
    "status": "ready",
    "warnings": [
      "<string>"
    ],
    "configuration": {
      "compute_mode": "elastic",
      "gpu": "<string>",
      "gpu_count": 512,
      "max_replicas": 1,
      "min_replicas": 1,
      "model": "<string>",
      "model_revision": "<string>",
      "profile": "<string>",
      "routing": "<string>",
      "runtime": "<string>",
      "runtime_args": [
        "<string>"
      ],
      "provider": "<string>",
      "provider_adapter": "<string>",
      "region": "<string>",
      "runtime_version": "<string>"
    },
    "model": {
      "display_name": "<string>",
      "evidence_class": "<string>",
      "evidence_summary": "<string>",
      "gated": true,
      "name": "<string>",
      "repository": "<string>",
      "revision": "<string>",
      "runtime": "<string>",
      "tasks": [
        "<string>"
      ]
    }
  },
  "provider_mutation": false,
  "selection_boundary": "<string>",
  "deployment_draft": {
    "cloud": "<string>",
    "gpu": "<string>",
    "model": "<string>",
    "name": "<string>",
    "compute_mode": "elastic",
    "endpoint_name": "<string>",
    "gpu_count": 1,
    "max_replicas": 1,
    "min_replicas": 1,
    "model_revision": "<string>",
    "port": 32768,
    "provider_adapter": "<string>",
    "region": "<string>",
    "runtime": "vllm",
    "runtime_args": [
      "<string>"
    ],
    "runtime_version": "<string>",
    "serving": {
      "autoscaling": {
        "max": 5000,
        "min": 5000,
        "owner": "disabled"
      },
      "backend": "dynamo",
      "cache": {
        "backend": "none",
        "configuration_ref": "<string>",
        "disk_gib": 1,
        "host_gib": 1,
        "memory_gib": 1,
        "metrics": true,
        "storage_claim": "<string>"
      },
      "decode": {
        "replicas": 5000,
        "tensor_parallelism": 512
      },
      "mode": "aggregated",
      "prefill": {
        "replicas": 5000,
        "tensor_parallelism": 512
      },
      "profile": "baseline",
      "routing": "direct",
      "schema_version": "infercrane.serving/v1",
      "worker": {
        "replicas": 5000,
        "tensor_parallelism": 512
      }
    },
    "workload": {
      "cancellation": "http-disconnect",
      "command": [
        "<string>"
      ],
      "drain": "connection",
      "image": "<string>",
      "metrics_path": "/metrics",
      "models_path": "/v1/models",
      "port": 32768,
      "protocol": "openai",
      "readiness_path": "/health",
      "shutdown_grace_seconds": 1800
    }
  }
}

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