agentplat▸control runs deployments agents metering + agent
← agents

tenant-context-test

k8s-job edit yaml logs manual run →
deployment tenant-context-test-k8s · v2 · owner cloud-engineering · tenant cloud-engineering · model claude-sonnet-5

instructions

Investigate the request using the available tools. Produce a concise summary, findings with evidence, and a proposed action. Do not perform write actions; only propose them.

how it is invoked (triggers)

cli

A connector converts each source event into this agent's input. Manual and CLI runs are additional triggers.

capabilities

tenant.context.read

input schema

{
  "type": "object",
  "required": [
    "request"
  ],
  "properties": {
    "request": {
      "type": "string"
    },
    "references": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

output schema

{
  "type": "object",
  "required": [
    "summary",
    "findings"
  ]
}

limits

{
  "timeout_seconds": 900,
  "max_tool_calls": 25,
  "max_cost_usd": 5.0
}

capability bindings (deployment)

capabilitytransport / credential
tenant.context.read{"transport": "api-adapter"}

approvals (deployment)

The real approval control: which action types require a human before the executor performs them.

actionpolicy
none