{
  "$schema": "../schemas/evaluation-report.schema.json",
  "schema_version": "1.1.0",
  "report_id": "bounded_workflow_shadow_report",
  "version": "0.1.0",
  "owner": "evaluation-preparer",
  "generated_at": "2026-08-07T16:00:00Z",
  "claim": "The bounded workflow meets its declared shadow threshold for the named target segment.",
  "objective": "regression",
  "population": {
    "eligible_population": {
      "definition": "All work items entering the named low-risk workflow segment",
      "denominator_event": "eligible work item enters the target queue",
      "exclusions": [
        "items outside the approved segment"
      ],
      "source": "versioned workflow event stream"
    },
    "segments": [
      "one low-risk workflow segment"
    ],
    "eligible_cases": 1,
    "evaluated_cases": 0,
    "excluded_cases": 1,
    "case_coverage": [
      {
        "slice": "one low-risk workflow segment",
        "eligible_cases": 1,
        "evaluated_cases": 0,
        "rationale": "The canonical template declares the intended slice but contains no executed cases."
      }
    ]
  },
  "system": {
    "agent_system_uri": "agent-system.json",
    "system_version": "0.1.0",
    "system_digest": "sha256:87a9eb0ac9daf09c06058cf5f71b66ab5603ba0831918d1f197bb21b42170659",
    "component_manifest": [
      {
        "role": "model_route",
        "component_id": "workflow_model_route",
        "version": "0.1.0",
        "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
      },
      {
        "role": "prompt_bundle",
        "component_id": "workflow_prompt_bundle",
        "version": "0.1.0",
        "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
      },
      {
        "role": "tool_bundle",
        "component_id": "workflow_tool_bundle",
        "version": "0.1.0",
        "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
      },
      {
        "role": "context_policy",
        "component_id": "workflow_context_policy",
        "version": "0.1.0",
        "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
      },
      {
        "role": "guardrail_bundle",
        "component_id": "workflow_guardrail_policy",
        "version": "0.1.0",
        "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
      }
    ],
    "environment": {
      "runtime": {
        "component_id": "template-reference-runtime",
        "uri": "reference-runtime.mjs",
        "version": "0.1.0",
        "schema_version": null,
        "digest": "sha256:c7fa90936171f0fc6036bfa98976d1c26480c813f6693f1b964b15f57162d22d"
      },
      "harness": {
        "component_id": "workflow_harness",
        "version": "0.1.0",
        "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
      },
      "sandbox": {
        "component_id": "not-executed-template-environment",
        "version": "0.1.0",
        "image_digest": null,
        "isolation": "not_executed",
        "cpu_limit": null,
        "memory_limit_mb": null,
        "filesystem": "not_applicable",
        "max_wall_time_ms": null,
        "network_enforced": false,
        "wall_time_enforced": false,
        "digest": "sha256:eda9ff46d7fe3244cd44a84d7e0f827345239352c6b908d3c6b787a8b82e3da4"
      },
      "world": {
        "component_id": "template-evaluation-world",
        "uri": "evaluation-world.mjs",
        "version": null,
        "schema_version": null,
        "digest": "sha256:00237d1efcb077be4103f9bd1cff94c857dcc68387301c25ee48234b748b9f16"
      },
      "policy": {
        "component_id": "template-deny-policy",
        "uri": "authorization-policy.mjs",
        "version": null,
        "schema_version": null,
        "digest": "sha256:94d1613d8de02f02be155fcdd6bfa145808ea4dfd314fb6b4271ea92819f274e"
      },
      "dependencies": [
        {
          "component_id": "node-dependency-lock",
          "uri": "../package-lock.json",
          "version": "2.1.0",
          "schema_version": null,
          "digest": "sha256:330d714dbb7e2a43c670b00acb3a6fd478c801b58b6698c3a03011cf4d4c2e57"
        },
        {
          "component_id": "operational-ontology",
          "uri": "operational-ontology.json",
          "version": "0.1.0",
          "schema_version": "1.1.0",
          "digest": "sha256:dd5a1f5ec5bb48609e2e2847abaea6d8c99b66f5bf5bd184b7884ecb1bd63928"
        },
        {
          "component_id": "workflow-behavior-bundle",
          "uri": "behavior-bundle.json",
          "version": "0.1.0",
          "schema_version": "1.0.0",
          "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
        },
        {
          "component_id": "bounded-tool-contract",
          "uri": "tool-contract.json",
          "version": "0.1.0",
          "schema_version": "1.1.0",
          "digest": "sha256:6f589f84fdd8aa1fd3b68e7f3cbf11f79c8b5ec3a29961aec2f68ffcba88b17c"
        },
        {
          "component_id": "stage-proposal-capability",
          "uri": "capability-manifest.json",
          "version": "0.1.0",
          "schema_version": "1.1.0",
          "digest": "sha256:4fe9e3f8ddb9a904f0e85889699369179dd66e0123600ef16167e5d415fded74"
        }
      ],
      "environment_digest": "sha256:d41a75e2454cf63e09a8c382c38ebf08bce3a4d609ba20a8f4dcb0d0554da6d5",
      "network_mode": "not_executed"
    }
  },
  "suite": {
    "uri": "evaluation-case.json",
    "version": null,
    "schema_version": "1.1.0",
    "digest": "sha256:7ded144811432dbdec79b034820ebdfd0d1ccfb5b858f243eddca5f5d5b012ed",
    "fixture_uri": "evaluation-case.json",
    "fixture_revision": null,
    "fixture_schema_version": "1.1.0",
    "fixture_digest": "sha256:7ded144811432dbdec79b034820ebdfd0d1ccfb5b858f243eddca5f5d5b012ed",
    "holdout_isolated": true,
    "agent_can_modify": false
  },
  "evaluator": {
    "grader": {
      "component_id": "template-evaluation-grader",
      "uri": "evaluation-runner.mjs",
      "version": null,
      "schema_version": null,
      "digest": "sha256:14ad18b9119824d137d3cf00f7162c6c00a84fe14b415d1e03d356219bec906e"
    },
    "runner": {
      "component_id": "template-evaluation-runner",
      "uri": "evaluation-runner.mjs",
      "version": null,
      "schema_version": null,
      "digest": "sha256:14ad18b9119824d137d3cf00f7162c6c00a84fe14b415d1e03d356219bec906e"
    },
    "output": {
      "component_id": "empty-trial-output",
      "uri": null,
      "version": null,
      "schema_version": null,
      "digest": "sha256:442ecf70a462ec0b9ff3652f2095397149ab6a9656254128c568a132ff1a2ad7"
    },
    "minimum_confidence": 0.95
  },
  "resource_budgets": {
    "max_turns": 12,
    "max_tool_calls": 24,
    "max_total_tokens": 50000,
    "max_wall_time_ms": 90000,
    "max_cost_usd": 0.5,
    "max_parallel_workers": 1
  },
  "resource_usage": {
    "turns": 0,
    "tool_calls": 0,
    "total_tokens": 0,
    "wall_time_ms": 0,
    "cost_usd": 0,
    "peak_parallel_workers": 0
  },
  "trials": {
    "count": 0,
    "independent": true,
    "state_reset_between_trials": true,
    "aggregation": "single_pass",
    "k": null,
    "quantile": null
  },
  "results": [
    {
      "metric": "accepted_outcome_rate",
      "slice": "one low-risk workflow segment",
      "value": 0,
      "unit": "ratio",
      "threshold": {
        "operator": "gte",
        "value": 0.95
      },
      "pass": false,
      "uncertainty": null
    }
  ],
  "contamination_controls": {
    "answer_key_access": false,
    "cross_trial_state": false,
    "external_network": "not_executed",
    "known_exposures": [],
    "reference_solution_reviewed": false
  },
  "deployment_qualification": {
    "status": "not_evaluated",
    "rationale": "The template declares the qualification contract but contains no executed policy-selection or held-out qualification evidence.",
    "workflow_success_metric": "accepted_outcome_rate",
    "oversight_policy": {
      "policy_id": "bounded_workflow_review_policy",
      "version": "0.1.0",
      "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0",
      "class": "terminal_accept_or_escalate",
      "routing_signal": "versioned workflow-specific routing score",
      "selected_on": "development",
      "frozen_before_qualification": false,
      "trajectory_invariant": true
    },
    "evidence_partitions": {
      "development": {
        "dataset_id": "bounded_workflow_development_cases",
        "version": "0.1.0",
        "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
      },
      "qualification": {
        "dataset_id": "bounded_workflow_qualification_cases",
        "version": "0.1.0",
        "digest": "sha256:4437d91ff17fe266a6754d495a9fdf430b7cbea72a0484cbb60d4f05a2c1aaf0"
      },
      "disjoint": true
    },
    "sampling": {
      "unit": "eligible workflow case",
      "dependence": "Declare clustering, repeated actors, temporal dependence, and any correction before qualification.",
      "qualification_method": "one-sided lower confidence bound"
    },
    "execution_mode": "not_executed",
    "operating_point": {
      "target_reliability": 0.95,
      "observed_reliability": null,
      "reliability_lower_bound": null,
      "confidence": null,
      "confidence_method": null,
      "autonomous_coverage": null,
      "human_review_burden": null,
      "routing_signal_quality": null,
      "expected_cost_per_case": null,
      "currency": null
    },
    "review_path": {
      "effectiveness_basis": "unmeasured",
      "effectiveness": null,
      "reviewer_population": "named qualified reviewers for the target workflow",
      "capacity_source": "measured review-capacity exercise",
      "latency_target_ms": null
    },
    "risk_constraints": [
      "No prohibited effect may be accepted autonomously."
    ],
    "scope_assumptions": [
      "Qualification applies only to the declared workflow population, policy, environment, and reviewer path."
    ],
    "requalification_triggers": [
      "Requalify after a material behavior, context, routing-policy, reviewer-effectiveness, cost, population, or environment change."
    ]
  },
  "limitations": [
    "This canonical template contains no collected release evidence and therefore records an inconclusive decision."
  ],
  "decision": {
    "status": "inconclusive",
    "rationale": "No representative trials have been recorded for this template.",
    "decided_by": "evaluation-authority",
    "authority_role": "independent-release-evaluator",
    "decided_at": "2026-08-07T16:00:00Z",
    "independent_from_candidate": true
  },
  "control_ids": [
    "EVA-001",
    "EVA-002",
    "EVA-003",
    "EVA-005",
    "EVA-006"
  ]
}