Skip to content
POST/api/v1/traces/analyze

Analyze a trace for issues

Runs TraceAssistant analysis. Body requires EITHER `traceId` OR `spans[]` (max 10,000). With `traceId`, `projectId` is ALSO required — 400 MISSING_PROJECT_ID without it — because the trace store is a process-wide singleton and the lookup must be pinned to your tenant; a traceId that resolves to no spans returns 400 NO_SPANS. With `spans[]` supplied directly, `projectId` is optional. `callLLM: false` selects rule-based quick mode; otherwise the full analysis calls the server-side LLM and degrades to the rule-based signal when no provider is configured. Requires `evals:read` and, when a projectId is given, membership on it.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Request body required

Example

{
  "traceId": "string",
  "spans": [
    {
      "spanId": "",
      "operationName": "string",
      "durationMs": 0,
      "status": "ok",
      "attributes": {},
      "events": [
        {
          "name": "string",
          "attributes": {}
        }
      ]
    }
  ],
  "callLLM": false,
  "projectId": "00000000-0000-0000-0000-000000000000"
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "traceId": {
          "type": "string",
          "maxLength": 200
        },
        "spans": {
          "maxItems": 10000,
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "spanId": {
                "default": "",
                "type": "string",
                "maxLength": 200
              },
              "operationName": {
                "type": "string",
                "minLength": 1,
                "maxLength": 1000
              },
              "durationMs": {
                "type": "number",
                "minimum": 0
              },
              "status": {
                "default": "ok",
                "type": "string",
                "maxLength": 100
              },
              "attributes": {
                "default": {},
                "type": "object",
                "additionalProperties": {
                  "anyOf": [
                    {
                      "type": "string"
                    },
                    {
                      "type": "number"
                    },
                    {
                      "type": "boolean"
                    }
                  ]
                }
              },
              "events": {
                "maxItems": 1000,
                "type": "array",
                "items": {
                  "type": "object",
                  "properties": {
                    "name": {
                      "type": "string",
                      "maxLength": 1000
                    },
                    "attributes": {
                      "default": {},
                      "type": "object",
                      "additionalProperties": {}
                    }
                  },
                  "required": [
                    "name",
                    "attributes"
                  ],
                  "additionalProperties": false
                }
              }
            },
            "required": [
              "spanId",
              "operationName",
              "durationMs",
              "status",
              "attributes"
            ],
            "additionalProperties": {}
          }
        },
        "callLLM": {
          "type": "boolean",
          "description": "Set false for rule-based quick mode."
        },
        "projectId": {
          "type": "string",
          "format": "uuid",
          "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
        }
      },
      "additionalProperties": false
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Analysis findings.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
429(no description)
500Internal Server Error — an unhandled error was converted to the standard error envelope (INTERNAL_ERROR).

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/traces/analyze \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "traceId": "string", "spans": [ { "spanId": "", "operationName": "string", "durationMs": 0, "status": "ok", "attributes": {}, "events": [ { "name": "string", "attributes": {} } ] } ], "callLLM": false, "projectId": "00000000-0000-0000-0000-000000000000" }'

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — eval,
// getEvalRun, securityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/traces/analyze", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "traceId": "string",
    "spans": [
      {
        "spanId": "",
        "operationName": "string",
        "durationMs": 0,
        "status": "ok",
        "attributes": {},
        "events": [
          {
            "name": "string",
            "attributes": {}
          }
        ]
      }
    ],
    "callLLM": false,
    "projectId": "00000000-0000-0000-0000-000000000000"
  }),
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}
headers["Content-Type"] = "application/json"

response = requests.request(
    "POST",
    "https://evalguard.ai/api/v1/traces/analyze",
    headers=headers,
    json={
    "traceId": "string",
    "spans": [
        {
            "spanId": "",
            "operationName": "string",
            "durationMs": 0,
            "status": "ok",
            "attributes": {},
            "events": [
                {
                    "name": "string",
                    "attributes": {}
                }
            ]
        }
    ],
    "callLLM": False,
    "projectId": "00000000-0000-0000-0000-000000000000"
},
)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"traceId":"string","spans":[{"spanId":"","operationName":"string","durationMs":0,"status":"ok","attributes":{},"events":[{"name":"string","attributes":{}}]}],"callLLM":false,"projectId":"00000000-0000-0000-0000-000000000000"}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/traces/analyze", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403429500

Other Traces endpoints