{
  "synthesize_command": "agents-cli eval dataset synthesize -n 3 --max-turns 4 --instruction \"Developers asking about shipctl 1.x vs 2.x rollback, token expiry, and unbuilt features\" --output artifacts/traces/synthesized-shipctl.json",
  "eval_cases": [
    {
      "eval_case_id": "synth_v1_revert_migration",
      "scenario": "Developer tries to use removed shipctl 1.x `release revert` command and asks about database migrations.",
      "turns_generated": 2,
      "tools_called": ["read_page(page='rollback')"]
    },
    {
      "eval_case_id": "synth_token_revocation_boundary",
      "scenario": "Developer asks how to create a staging CI token and then asks how to revoke an active token (which tokens.md does not cover).",
      "turns_generated": 2,
      "baseline_tools_called": [
        "read_page(page='tokens')",
        "read_page(page='config')",
        "read_page(page='deploy')",
        "read_page(page='rollback')"
      ],
      "candidate_tools_called": [
        "read_page(page='tokens')"
      ]
    },
    {
      "eval_case_id": "synth_prod_approval_flow",
      "scenario": "Developer deploys r42 to staging and then asks what approval command is required for production.",
      "turns_generated": 2,
      "tools_called": ["read_page(page='deploy')"]
    }
  ]
}