Latest run + stale flag

GET

/v1/agents/{agent_id}/health-checks/latest

const url = 'https://app.everruns.com/api/v1/agents/example/health-checks/latest';
const options = {method: 'GET'};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

curl --request GET \
  --url https://app.everruns.com/api/v1/agents/example/health-checks/latest

Parameters

Path Parameters

agent_id

required

string

Agent ID

Responses

200

Latest health check run with stale-config flag

application/json

The most recent health-check run for an agent, paired with whether the agent’s current resolved config differs from the config that run was executed against. Returned by the latest-run endpoint so the agent editor can show prior results on mount without triggering a new run, and surface a “config changed since last run” hint. See specs/agent-checks.md and EVE-588.

object

config_changed

required

True when run exists but was executed against a different resolved config than the agent currently has (UI shows a re-run hint).

boolean

run

One of:

null
object

null

The latest run, or None if the agent has never been health-checked.

object

agent_id

string | null

completed_at

string | null format: date-time

config_hash

required

string

created_at

required

string format: date-time

error_message

string | null

required

Public ID (healthcheck_…).

string

model_id

string | null

results

Per-case results (present once the run has produced any).

Array<object> | null

Outcome of a single case after the agent ran and was scored.

object

deterministic_reason

required

Deterministic-check explanation (completion, non-empty, turn bound).

string

error

Set when the case errored or timed out instead of completing.

string | null

input_tokens

Input tokens for this case: the agent session turns plus the judge call.

integer format: int32

judge_reason

required

LLM judge explanation.

string

latency_ms

required

integer format: int64

name

required

string

output_tokens

Output tokens for this case: the agent session turns plus the judge call.

integer format: int32

passed

required

True only when both the deterministic checks and the LLM judge pass.

boolean

rubric

required

string

score

required

LLM judge score, 0.0–1.0.

number format: double

session_id

Public ID of the real session created for this case (browsable in UI).

string | null

turns

required

integer format: int32

user_message

required

string

status

required

string

Allowed values: pending running completed failed

summary

One of:

null
object

null

Example

{
  "run": {
    "status": "pending"
  }
}

404

Agent not found

application/json

Standard error response.

Wire shape is RFC 9457 Problem Details: every error response includes title and status, and may include detail, code, allowed_actions, retry_after_seconds, instance, and type. The content type is rewritten to application/problem+json by [problem_json_content_type].

object

allowed_actions

Recovery actions the caller can take next.

Array<object>

Agent-actionable link describing a follow-up the caller can take. Used in two contexts:

Error recovery — ErrorResponse.allowed_actions carries rels like retry, retry-later, unarchive, get-existing so the agent knows the right next call after a 4xx/429.
Entity hypermedia — WithUrls<T>.allowed_actions carries state-aware rels like cancel, events, self, update on the entity itself so the agent can follow links instead of reconstructing routes from prose.

The shape is intentionally identical across both contexts; the closed rel vocabulary documented in specs/api-conventions.md distinguishes them.

object

hint

Short, agent-readable hint (e.g. “Shorten ‘name’ to <= 200 chars.”, “Cancel the active turn for this session.”).

string | null

href

Absolute (preferred) or relative URL the caller may invoke directly. Always present on entity hypermedia actions (WithUrls<T>.allowed_actions); optional on error-recovery actions (ErrorResponse.allowed_actions) where the matching operation_id is enough and the URI is implicit from the failed call.

string | null

method

HTTP method to use against href. Required for entity hypermedia actions; usually omitted on error-recovery actions where the same operation is retried with its original method.

string | null

operation_id

OpenAPI operationId the caller should invoke. Lets an MCP client resolve the call without parsing href.

string | null

rel

required

Link relation describing the action. Closed vocabulary documented in specs/api-conventions.md — examples: self, cancel, pause, resume, events, retry, retry-later, unarchive, get-existing, delete, update.

string

schema_ref

OpenAPI $ref to the request-body schema, when the action takes one (e.g. #/components/schemas/UpdateSessionRequest). Lets a tool-calling agent fetch the input shape without scanning the whole spec.

string | null

code

Stable, machine-readable error code (snake_case).

string | null

detail

Human-readable explanation specific to this occurrence.

string | null

instance

Request URI for this occurrence.

string | null

retry_after_seconds

Seconds the caller should wait before retrying (429 / transient 503).

integer | null format: int32

status

required

HTTP status code; mirrors the response status line.

integer format: int32

title

required

Short, human-readable summary of the problem (e.g. “Not Found”).

string

type

RFC 9457 problem type URI. Optional; identifies the problem class.

string | null

Example

{
  "allowed_actions": [
    {
      "method": "POST"
    }
  ],
  "code": "session_not_found",
  "detail": "Session session_01933b5a000070008000000000000001 not found in org org_01933b5a000070008000000000000001.",
  "instance": "/v1/sessions/session_01933b5a000070008000000000000001",
  "retry_after_seconds": 30,
  "status": 404,
  "title": "Session not found",
  "type": "https://docs.everruns.com/errors/session_not_found"
}