gstack/evals/parity/transcripts/deterministic/design-review.json

{
  "schema_version": 1,
  "kind": "deterministic-semantic-transcript",
  "suite": "Design review",
  "execution_id": "design-review",
  "fixture": {
    "id": "implemented-interface-audit",
    "prompt": "Inspect the running dashboard, repair visual inconsistencies, and prove the improvements with before-and-after evidence.",
    "signals": {
      "surface": "web",
      "implementation_exists": true,
      "mutation_authorized": true,
      "evidence": "before-after"
    },
    "rationale": "Live evidence, taste, iteration, and before/after proof."
  },
  "baseline_invocation": {
    "base_sha": "bb57306d98c97011b0919c6132705a15b1579781",
    "modules": [
      "design-review"
    ],
    "input": "Inspect the running dashboard, repair visual inconsistencies, and prove the improvements with before-and-after evidence."
  },
  "candidate_invocation": {
    "dispatcher": "design",
    "mode": "Implement",
    "depth": "deep",
    "mutation": "fix-safe",
    "active_modules": [
      "design-review"
    ],
    "skipped_modules": [
      "design-consultation",
      "design-shotgun",
      "design-html",
      "plan-design-review",
      "ios-design-review"
    ],
    "web_context": "local-browser",
    "input": "Inspect the running dashboard, repair visual inconsistencies, and prove the improvements with before-and-after evidence."
  },
  "source_comparisons": [
    {
      "source": "design-review",
      "baseline": {
        "base_sha": "bb57306d98c97011b0919c6132705a15b1579781",
        "source_path": "design-review/SKILL.md.tmpl",
        "rendered_sha256": "ff6d5d4858ed45db1e9581080739c0b4c5029bca44ecabe0c385637ece68e0cb",
        "semantic_signature": {
          "normalized_sha256": "ff6d5d4858ed45db1e9581080739c0b4c5029bca44ecabe0c385637ece68e0cb",
          "headings_sha256": "97a3a2d7f1cbb79a0350d5566733da579c5fe42c4686a96cf043edd7be609fc8",
          "questions_sha256": "4b8b600fcded979889a6f78e0b6542da825ec6c93dfa6c79129a099e808187a6",
          "obligations_sha256": "92150da73b1620171e0e2584f248d4fcb524294526b6dcddb46fa2fb3555cb02",
          "heading_count": 87,
          "question_count": 28,
          "obligation_count": 113
        }
      },
      "mechanical_port": {
        "rendered_sha256": "8711f4910f9cb9d022d024c432093bccbcf8d4e74250a3a25f915eb086de6c5a",
        "differs_from_baseline": true,
        "allowed_difference": "Package-local skill, section, support-artifact, and stable runtime path relocation only."
      },
      "candidate": {
        "target_path": "skills/design/references/legacy/design-review.md",
        "rendered_legacy_body_sha256": "8711f4910f9cb9d022d024c432093bccbcf8d4e74250a3a25f915eb086de6c5a",
        "semantic_signature": {
          "normalized_sha256": "8711f4910f9cb9d022d024c432093bccbcf8d4e74250a3a25f915eb086de6c5a",
          "headings_sha256": "97a3a2d7f1cbb79a0350d5566733da579c5fe42c4686a96cf043edd7be609fc8",
          "questions_sha256": "5db89e726e874b1f4b28c24490923a7c6b9042f5abbc173ea698e1b1e459d017",
          "obligations_sha256": "4c463b201237a4eb9cfbfe2fd520096a256b4188b383922b0e98bccc4e53f131",
          "heading_count": 87,
          "question_count": 27,
          "obligation_count": 114
        }
      },
      "deterministic_comparison": {
        "normalized_body_equal": false,
        "installable_port_equal": true,
        "contract_equal": true,
        "classification": "EQUIVALENT"
      },
      "differences": [
        {
          "classification": "INTENTIONAL_IMPROVEMENT",
          "issue_or_pr": "https://github.com/garrytan/gstack/pull/679",
          "reproduced_defect": "Match the user language",
          "regression_fixture": "evals/parity/regressions/pr-679.json",
          "explanation": "### User-language rule\n\nWrite questions, progress updates, reports, and artifacts in the language used by the user. Source material, code identifiers, commands, and quotations may remain in their original language when translating them would reduce accuracy."
        },
        {
          "classification": "INTENTIONAL_IMPROVEMENT",
          "issue_or_pr": "https://github.com/garrytan/gstack/pull/1920",
          "reproduced_defect": "Infer the design system before auditing deviations",
          "regression_fixture": "evals/parity/regressions/pr-1920.json",
          "explanation": "### Design-system-first audit\n\nInfer the product's existing design thesis, typography, color, spacing, component language, and motion before scoring inconsistencies. Audit the implementation against that inferred system and the product domain, not against a generic house style. Include domain-appropriate trust, registration, empty-state, and user-facing copy checks before declaring the surface complete."
        },
        {
          "classification": "INTENTIONAL_IMPROVEMENT",
          "issue_or_pr": "https://github.com/garrytan/gstack/pull/2030",
          "reproduced_defect": "Record only signal-bearing learnings",
          "regression_fixture": "evals/parity/regressions/pr-2030.json",
          "explanation": "### Signal-gated learning\n\nPersist a learning only when the interaction contains a useful, reusable signal such as an explicit preference, correction, accepted recommendation, or rejected direction. Track helpful and harmful outcomes separately. Do not manufacture a learning merely because a workflow completed."
        },
        {
          "classification": "INTENTIONAL_IMPROVEMENT",
          "issue_or_pr": "https://github.com/garrytan/gstack/pull/2189",
          "reproduced_defect": "Accept coherent design-thesis framing",
          "regression_fixture": "evals/parity/regressions/pr-2189.json",
          "explanation": "### Design-thesis equivalence\n\nAccept a coherent design thesis expressed through product principles, visual rationale, interaction philosophy, or equivalent framing. Evaluate substance and consistency; do not require a literal “design thesis” heading or one exact vocabulary to award credit."
        }
      ]
    }
  ],
  "semantic_dimensions": {
    "questions": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "question_order": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "follow_up_pressure": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "smart_skips": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "pushback_strength": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "scope_recommendation": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "active_reasoning_modules": {
      "classification": "EQUIVALENT",
      "evidence": "Structured route selected design-review from product/evidence signals."
    },
    "findings": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "evidence": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "artifacts": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "approval_gates": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "mutation_behavior": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "completion_status": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "recommended_next_action": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    },
    "voice": {
      "classification": "EQUIVALENT",
      "evidence": "The candidate exactly matches the deterministic installable port of the pinned 1.x workflow; only enumerated package-local path mechanics differ from the immutable oracle."
    }
  },
  "verdict": "PASS"
}