{
  "schema": "agent-rerun-receipt.v1",
  "record": {
    "id": "TEST-blueprint-planning-20261016T035735Z-blueprint-explicit-dependencies-raw-glm",
    "taskId": "blueprint-explicit-dependencies",
    "taskTitle": "Structured PRD: inventory reservation dependency chain (synthetic PRD input)",
    "agent": "Raw model planning baseline",
    "requestedModel": "byok/zai/glm-5.3-flash",
    "resolvedModel": null,
    "wallSeconds": 13.895,
    "inputTokens": null,
    "outputTokens": null,
    "totalTokens": null,
    "costUsd": null,
    "energyWh": null,
    "assertionsPassed": 13,
    "assertionsTotal": 13,
    "observedNativeModel": null,
    "modelIdentityStatus": null,
    "modelIdentityEvidence": null,
    "providerResponseModel": null,
    "reasoningEffort": null,
    "family": "blueprint",
    "status": "PASS",
    "tier": "cloud/BYOK",
    "diagnosticOnly": false,
    "comparisonEligible": false,
    "cohort": "original-model",
    "resultNote": null,
    "limitations": [
      "Synthetic PRD input; planning-only: no generated-file, build, or code-execution proof.",
      "One trial per task and arm; exact rubric is deliberately narrow; no statistical or production claim.",
      "Raw model baseline, not a competing coding agent. Requested model held constant only within this baseline; Blueprint has no inference model.",
      "Cost is published-rate estimate at $0.15 input/$0.50 output per MTok; provider cash receipt not captured.",
      "Semantic rubric v2 excludes exact task count from acceptance. Count is diagnostic only; exclusion mentions are evaluated for explicit delivery versus reaffirmed non-delivery. Ambiguous wording remains UNVERIFIED.",
      "Semantic-v2 rerun uses originalunchanged synthetic PRDs. Originalv1 attempts remain published separately. No generated-code execution claim."
    ],
    "evidenceFile": "TEST-blueprint-planning-20261016T035735Z-blueprint-explicit-dependencies-raw-glm.json"
  },
  "sourceRecord": {
    "id": "TEST-blueprint-planning-20261016T035735Z-blueprint-explicit-dependencies-raw-glm",
    "family": "planning",
    "taskId": "blueprint-explicit-dependencies",
    "taskTitle": "Structured PRD: inventory reservation dependency chain (synthetic PRD input)",
    "agent": "Raw model planning baseline",
    "requestedModel": "byok/zai/glm-5.3-flash",
    "resolvedModel": null,
    "status": "PASS",
    "wallSeconds": 13.895,
    "inputTokens": null,
    "outputTokens": null,
    "totalTokens": null,
    "costUsd": null,
    "energyWh": null,
    "assertionsPassed": 13,
    "assertionsTotal": 13,
    "evidencePaths": [
      "artifacts/agent_comparison_rerun_20261016/blueprint/TEST-blueprint-planning-20261016T035735Z/blueprint-explicit-dependencies-raw-glm-checks.json",
      "artifacts/agent_comparison_rerun_20261016/blueprint/TEST-blueprint-planning-20261016T035735Z/blueprint-explicit-dependencies-raw-glm-request.json",
      "artifacts/agent_comparison_rerun_20261016/blueprint/TEST-blueprint-planning-20261016T035735Z/blueprint-explicit-dependencies-raw-glm-response.json"
    ],
    "limitations": [
      "Synthetic PRD input; planning-only: no generated-file, build, or code-execution proof.",
      "One trial per task and arm; exact rubric is deliberately narrow; no statistical or production claim.",
      "Raw model baseline, not a competing coding agent. Requested model held constant only within this baseline; Blueprint has no inference model.",
      "Cost is published-rate estimate at $0.15 input/$0.50 output per MTok; provider cash receipt not captured.",
      "Semantic rubric v2 excludes exact task count from acceptance. Count is diagnostic only; exclusion mentions are evaluated for explicit delivery versus reaffirmed non-delivery. Ambiguous wording remains UNVERIFIED.",
      "Semantic-v2 rerun uses originalunchanged synthetic PRDs. Originalv1 attempts remain published separately. No generated-code execution claim."
    ],
    "cleanup": null,
    "serviceBuildSha": null,
    "rubric": "planning_semantics.v2",
    "observedTaskCount": 6,
    "exactTaskCountDiagnostic": false,
    "comparisonEligible": false,
    "proofLevel": "LIVE_PLANNING_ONLY"
  },
  "sourceFile": "artifacts/agent_comparison_rerun_20261016/blueprint/reviewed-summary.json",
  "sourceFileSha256": "31c06cd32a53180bb9526100e08ad645b4728cedac87e47aa70788749d485f57",
  "files": [
    {
      "path": "artifacts/agent_comparison_rerun_20261016/blueprint/TEST-blueprint-planning-20261016T035735Z/blueprint-explicit-dependencies-raw-glm-checks.json",
      "sha256": "71344a447d70a99dcef775dc55ad8c10f64d89c82d69c1bd35ea9b94fafaa849",
      "bytes": 833,
      "content": "[\n  {\n    \"name\": \"covers:stock+schema\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"covers:atomic+reservation\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"covers:reservation+api\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"covers:integration+test\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"does_not_deliver:cryptocurrency\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"does_not_deliver:subscription\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"unique_nonempty_ids\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"no_dangling_dependencies\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"acyclic\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"dependency:1->2\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"dependency:2->3\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"dependency:2->4\",\n    \"passed\": true\n  },\n  {\n    \"name\": \"dependency:3->4\",\n    \"passed\": true\n  }\n]",
      "contentRedacted": false,
      "publishedContentSha256": "71344a447d70a99dcef775dc55ad8c10f64d89c82d69c1bd35ea9b94fafaa849"
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/blueprint/TEST-blueprint-planning-20261016T035735Z/blueprint-explicit-dependencies-raw-glm-request.json",
      "sha256": "da8a96337633e4a2ec9e3b24b7ecaf02378ab30e7205e815527f602d0d2e1986",
      "bytes": 1152
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/blueprint/TEST-blueprint-planning-20261016T035735Z/blueprint-explicit-dependencies-raw-glm-response.json",
      "sha256": "cd931c412ea93e6dd7ada0bc3e4073b5ea17ddc25b8e8d97795c989f31fd9cd9",
      "bytes": 27197
    }
  ],
  "disclosure": "Synthetic inputs and observed execution. Original-byte hashes retained; selected source and oracle outputs reproduced. Private provider transcripts remain local."
}