Unnamed resource.

Agent guardrail decision engine. Call once before every agent action; returns a single decision — proceed, slow down (with a reason and wait time), or stop — based on cost budget, chain depth, step cap and retry budget, and request volume pressure. Policy thresholds are configured separately via /policy; this endpoint only reports the decision for a single action.

Eligibility: unprobeable
Failures: 0
Last quote: —
Last probe: —

Payment requirements / accepts[] 1 options

State	Network	Scheme	Atomic amount	Asset	payTo / untrusted
active	eip155:8453	exact	1000	0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913	0x1A9a7C72208ABf3552750eB1C4a4F2cA9e8733E5

All advertised payment options are stored. Base (`eip155:8453`) is the operational network for ranking and canaries; non-Base options remain visible for transparency.

Probe evidence 0 recent

No probe attempts recorded yet. Coverage runs prioritize never-probed endpoints.

Machine contract

Schemas.

InputJSON

{
  "body": {
    "agent_id": "agent_42",
    "chain_id": "chain_abc123",
    "is_retry": false,
    "step_cost": 0.02,
    "tenant_id": "acme_corp"
  },
  "bodyType": "json",
  "method": "POST",
  "type": "http"
}

OutputJSON

{
  "example": {
    "checks": {
      "chain_depth": {
        "current": 3,
        "limit": 10
      },
      "cost": {
        "limit": 50,
        "spent": 12.4
      },
      "paused": false,
      "steps_retries": {
        "retries": 0,
        "retry_limit": 3,
        "step_limit": 25,
        "steps": 7
      },
      "volume": {
        "blocking": false,
        "pct_used": 42
      }
    },
    "decision": "proceed",
    "reason": null,
    "wait_seconds": null
  },
  "type": "json"
}