Test 109

Jan 1, 2028 / 2 facts

YAML

Request

Create a rollup-service runbook entry titled "Tenant-size validation metric" with the current metric-label contract.

Required memory

Fact 102

For the rollup-service validation metric, the raw tenant hash is available only in debug logs.

Source evidence (1)

000974Jan 8, 2024 / 11:28 UTC-05:00

The revised rollup-service validation metric finished production review and landed. The raw tenant hash is still only in debug logs, and `tenant_size_class` is limited to `small`, `medium`, `large`, and `unknown`, with the enum source owned by the rollup-service maintainers. Cyrus verified the bounded-cardinality shape, and Nadia checked the rendered dashboard and confirmed it presents the metric as validation evidence rather than live rollback criteria. I am just recording the completed result; nothing else needs doing here.

Message 000974 in history

Fact 103

For the rollup-service validation metric, `tenant_size_class` is limited to `small`, `medium`, `large`, and `unknown`; the rollup-service maintainers own the enum source.

Source evidence (1)

000974Jan 8, 2024 / 11:28 UTC-05:00

Message 000974 in history

Expected tool calls

create_runbook_entry

Grading

1. field_equals / create_runbook_entry

{
  "type": "field_equals",
  "tool": "create_runbook_entry",
  "action_id": "alex_109_create_runbook_entry",
  "path": "result.ok",
  "value": true,
  "check_id": "alex_109_00"
}

2. field_equals / create_runbook_entry

{
  "type": "field_equals",
  "path": "result.runbook.service",
  "value": "rollup-service",
  "tool": "create_runbook_entry",
  "action_id": "alex_109_create_runbook_entry",
  "check_id": "alex_109_01"
}

3. field_equals / create_runbook_entry

{
  "type": "field_equals",
  "path": "result.runbook.title",
  "value": "Tenant-size validation metric",
  "tool": "create_runbook_entry",
  "action_id": "alex_109_create_runbook_entry",
  "check_id": "alex_109_02"
}

4. field_llm_judge / create_runbook_entry

{
  "type": "field_llm_judge",
  "path": "result.runbook.body",
  "criterion": "The entry says the raw tenant hash is available only in debug logs, not as a metric label; tenant_size_class is limited to exactly small, medium, large, and unknown; and rollup-service maintainers own that enum source.",
  "tool": "create_runbook_entry",
  "action_id": "alex_109_create_runbook_entry",
  "check_id": "alex_109_03"
}

Complete grading specification

{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2028-01-01",
    "assertions": [
      {
        "type": "field_equals",
        "tool": "create_runbook_entry",
        "action_id": "alex_109_create_runbook_entry",
        "path": "result.ok",
        "value": true,
        "check_id": "alex_109_00"
      },
      {
        "type": "field_equals",
        "path": "result.runbook.service",
        "value": "rollup-service",
        "tool": "create_runbook_entry",
        "action_id": "alex_109_create_runbook_entry",
        "check_id": "alex_109_01"
      },
      {
        "type": "field_equals",
        "path": "result.runbook.title",
        "value": "Tenant-size validation metric",
        "tool": "create_runbook_entry",
        "action_id": "alex_109_create_runbook_entry",
        "check_id": "alex_109_02"
      },
      {
        "type": "field_llm_judge",
        "path": "result.runbook.body",
        "criterion": "The entry says the raw tenant hash is available only in debug logs, not as a metric label; tenant_size_class is limited to exactly small, medium, large, and unknown; and rollup-service maintainers own that enum source.",
        "tool": "create_runbook_entry",
        "action_id": "alex_109_create_runbook_entry",
        "check_id": "alex_109_03"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/alex/109.yaml

SHA-256: 1b3062b29e1d9985b6182c5f9a54487b8105a959fe2c2c2f96a0d80182d2f9f6