id: '199'
narrative_anchor_date: '2028-01-01'
test: Create a focused document titled `2026 Helio Start paid-pilot high-support case review`. Review
  all seven mature cases from the 2026 paid pilot that exceeded 90 support minutes, clearly distinguish
  external owner-permission or network-allowlist coordination from ordinary integration troubleshooting,
  state which causes were ruled out across all seven cases, and explain what the findings mean for admission
  correctness and operational follow-up. Keep it claims-safe and concise.
load_bearing_facts:
- 220
- 221
- 222
expected_tool_calls:
- create_doc
grade:
  type: tool_trace
  config:
    check_version: 2
    today: '2028-01-01'
    semantic_judge_version: 2
    assertions:
    - type: field_equals
      tool: create_doc
      action_id: create_case_review
      path: result.ok
      value: true
      check_id: riley_199_00
    - check_id: riley_199_01
      type: field_equals
      tool: create_doc
      action_id: create_case_review
      path: args.title
      value: 2026 Helio Start paid-pilot high-support case review
    - type: field_llm_judge
      tool: create_doc
      action_id: create_case_review
      path: args
      criterion: 'The document clearly says that all seven paid-pilot workspaces exceeding 90 support
        minutes were reviewed, with five requiring a supported owner-level permission or network-allowlist
        action after admission and two requiring ordinary integration troubleshooting. Missing or contradictory
        counts or categories must fail.


        The document states that the review found none of the seven cases involved billing, an unsupported
        admission, stale state, or conflicting state. Any assertion that one of these causes occurred
        must fail.


        The document explains that in every one of the five authority-action cases, external-authority
        status was current and verified yes at admission; therefore the external-authority meaning and
        admission decisions remained correct. It identifies setup sequencing—not eligibility—as the gap
        and directs follow-up toward setup sequencing or coordination while preserving the decision not
        to change eligibility. Missing or contradictory meaning must fail.


        The document treats the high-support case findings as descriptive and does not claim or imply
        that they prove causal acquisition performance, improved activation, reduced support demand or
        support-effort improvement, or scalability. Any such causal or improvement claim must fail.'
      check_id: riley_199_02
mock_state: {}