Show Runs for a Simulation Result

List Simulation Runs For Results

curl --request GET \
  --url https://api.eqho.ai/v1/simulation/results/{result_id}/runs \
  --header 'X-API-KEY: <api-key>'

[
  {
    "_id": "<string>",
    "account_id": "<string>",
    "agent_id": "<string>",
    "simulation_results_id": "<string>",
    "scenario_id": "<string>",
    "max_steps": 123,
    "max_errors": 123,
    "trial": 1,
    "simulated_lead_llm_args": {
      "ai_model": "<string>",
      "frequency_penalty": 123,
      "max_tokens": 123,
      "presence_penalty": 123,
      "temperature": 123,
      "reasoning": "none",
      "text_verbosity": "low"
    },
    "scenario_set_id": "<string>",
    "status": "pending",
    "created_at": "2023-11-07T05:31:56Z",
    "started_at": "2023-11-07T05:31:56Z",
    "completed_at": "2023-11-07T05:31:56Z",
    "duration_in_seconds": 123,
    "termination_reason": "user_stop",
    "agent_cost": 123,
    "user_cost": 123,
    "reward_info": {
      "reward": 123,
      "action_checks": [
        {
          "action": {
            "tool_call_id": "<string>",
            "name": "<string>",
            "arguments": {},
            "requestor": "assistant",
            "info": "<string>",
            "compare_args": [
              "<string>"
            ]
          },
          "action_match": true,
          "action_reward": 123
        }
      ],
      "nl_assertions": [
        {
          "nl_assertion": "<string>",
          "met": true,
          "justification": "<string>"
        }
      ],
      "reward_breakdown": {},
      "info": {}
    },
    "messages": [
      {
        "content": "<string>",
        "role": "system",
        "turn_idx": 123,
        "timestamp": "2023-11-07T05:31:56Z"
      }
    ],
    "error": "<string>"
  }
]

GET

simulation

results

{result_id}

runs

List Simulation Runs For Results

curl --request GET \
  --url https://api.eqho.ai/v1/simulation/results/{result_id}/runs \
  --header 'X-API-KEY: <api-key>'

[
  {
    "_id": "<string>",
    "account_id": "<string>",
    "agent_id": "<string>",
    "simulation_results_id": "<string>",
    "scenario_id": "<string>",
    "max_steps": 123,
    "max_errors": 123,
    "trial": 1,
    "simulated_lead_llm_args": {
      "ai_model": "<string>",
      "frequency_penalty": 123,
      "max_tokens": 123,
      "presence_penalty": 123,
      "temperature": 123,
      "reasoning": "none",
      "text_verbosity": "low"
    },
    "scenario_set_id": "<string>",
    "status": "pending",
    "created_at": "2023-11-07T05:31:56Z",
    "started_at": "2023-11-07T05:31:56Z",
    "completed_at": "2023-11-07T05:31:56Z",
    "duration_in_seconds": 123,
    "termination_reason": "user_stop",
    "agent_cost": 123,
    "user_cost": 123,
    "reward_info": {
      "reward": 123,
      "action_checks": [
        {
          "action": {
            "tool_call_id": "<string>",
            "name": "<string>",
            "arguments": {},
            "requestor": "assistant",
            "info": "<string>",
            "compare_args": [
              "<string>"
            ]
          },
          "action_match": true,
          "action_reward": 123
        }
      ],
      "nl_assertions": [
        {
          "nl_assertion": "<string>",
          "met": true,
          "justification": "<string>"
        }
      ],
      "reward_breakdown": {},
      "info": {}
    },
    "messages": [
      {
        "content": "<string>",
        "role": "system",
        "turn_idx": 123,
        "timestamp": "2023-11-07T05:31:56Z"
      }
    ],
    "error": "<string>"
  }
]

Authorizations

X-API-KEY

string

header

required

Path Parameters

result_id

string

required

Required string length: 24

Response

Successful Response

_id

string

required

account_id

string

required

Account ID that owns this simulation run

agent_id

string

required

ID of the Agent being simulated

simulation_results_id

string

required

ID of the parent simulation results

scenario_id

string

required

ID of the Simulation Scenario being run

max_steps

integer

required

The maximum number of steps.

max_errors

integer

required

The maximum number of errors.

trial

integer

default:1

Trial number for this scenario (1 to num_trials).

simulated_lead_llm_args

AiSettingsModel · object

LLM configuration for the simulated user.

Show child attributes

simulated_lead_llm_args.ai_model

string | null

The ID of the LLM model to use. If None, the Eqho default model will be used.

simulated_lead_llm_args.frequency_penalty

number | null

Number between -2.0 and 2.0. If None, the Eqho default value will be used.

Used to discourage the model from repeating the same words or phrases too frequently within the generated text. A higher frequency_penalty value will result in the model being more conservative in its use of repeated tokens. Available for OpenAI models only.

simulated_lead_llm_args.max_tokens

integer | null

The maximum number of tokens the AI can generate.

simulated_lead_llm_args.presence_penalty

number | null

Number between -2.0 and 2.0. If None, the Eqho default value will be used. Used to encourage the model to include a diverse range of tokens in the generated text. A higher presence_penalty value will result in the model being more likely to generate tokens that have not yet been included in the generated text. Available for OpenAI models only.

simulated_lead_llm_args.temperature

number | null

The sampling temperature, if you use OpenAI model, the temperature should be between 0 and 2 and if you use Anthropic model, the temperature should be between 0 and 1. If None, the Eqho default value will be used. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

simulated_lead_llm_args.reasoning

enum<string> | null

Available options:

none,

low,

medium,

high

simulated_lead_llm_args.text_verbosity

enum<string> | null

Available options:

low,

medium,

high

scenario_set_id

string | null

ID of the Scenario Set the scenario belongs to

status

enum<string>

default:pending

Current status of the simulation run

Available options:

pending,

running,

completed

created_at

string<date-time>

When this run record was created (UTC)

started_at

string<date-time> | null

The start time of the simulation. None if still PENDING.

completed_at

string<date-time> | null

The end time of the simulation. None if not yet COMPLETED.

duration_in_seconds

number | null

The duration of the simulation run.

termination_reason

enum<string> | null

The reason for the termination of the simulation.

Available options:

user_stop,

agent_stop,

max_steps,

too_many_errors,

cancelled

agent_cost

number | null

The cost of the agent.

user_cost

number | null

The cost of the user.

reward_info

RewardInfo · object

The reward received by the agent.

Show child attributes

reward_info.reward

number

required

The reward received by the agent.

reward_info.action_checks

ActionCheck · object[] | null

The action checks.

Show child attributes

reward_info.action_checks.action

GoldenToolCall · object

required

The expected tool call being validated

Show child attributes

reward_info.action_checks.action.tool_call_id

string

required

The unique identifier for the gold tool call within a scenario.

reward_info.action_checks.action.name

string

required

The action/tool name (must match an action slug configured in the agent).

reward_info.action_checks.action.arguments

Arguments · object

required

Expected arguments for the tool call. Used for validation against actual calls.

reward_info.action_checks.action.requestor

enum<string>

default:assistant

Who should make this call (usually 'assistant' for agent actions).

Available options:

user,

assistant

reward_info.action_checks.action.info

string | null

Human-readable explanation of why this tool call is expected. Not used in validation.

reward_info.action_checks.action.compare_args

string[] | null

List of argument keys to validate. If None, validates ALL arguments match exactly. Use this to ignore arguments that may vary (like timestamps or auto-generated IDs).

reward_info.action_checks.action_match

boolean

required

True if agent made a matching tool call

reward_info.action_checks.action_reward

number

required

Reward points for this action (1.0 or 0.0)

reward_info.nl_assertions

NLAssertionCheck · object[] | null

The natural language assertions.

Show child attributes

reward_info.nl_assertions.nl_assertion

string

required

The natural language criteria being evaluated

reward_info.nl_assertions.met

boolean

required

Whether the assertion was satisfied during the conversation

reward_info.nl_assertions.justification

string

required

LLM's explanation for the met/not met determination

reward_info.reward_breakdown

Reward Breakdown · object

The breakdown of the reward.

Show child attributes

reward_info.reward_breakdown.{key}

number

reward_info.info

Info · object

Additional information about the reward.

messages

(SystemMessage · object | AssistantMessage · object | UserMessage · object | ToolMessage · object)[] | null

Complete simulation transcript

A system message.

SystemMessage
AssistantMessage
UserMessage
ToolMessage

Show child attributes

messages.content

string

required

The content of the message.

messages.role

string

default:system

The role of the message sender.

Allowed value: "system"

messages.turn_idx

integer | null

The index of the turn in the conversation.

messages.timestamp

string<date-time> | null

The timestamp of the message.

error

string | null

Error message if the simulation failed.

Get Simulation Results Show Simulation Runs

⌘I

API Reference

Endpoints

Show Runs for a Simulation Result

Authorizations

Path Parameters

Response