STET

task_detail

validation/gpt-5-1-codex-mini/flux-pr-1169/task_detail.v1.json

15760 bytes

Back to adjudication
{
  "version": "v1",
  "materialization": {
    "mode": "canonical"
  },
  "identity": {
    "variant_id": "gpt-5-1-codex-mini",
    "requested_model": "gpt-5-1-codex-mini",
    "model_key": "gpt-5-1-codex-mini",
    "run_id": "2026-02-21__03-36-16__gpt-5-1-codex-mini",
    "task_id": "flux-pr-1169",
    "trial_name": "flux-pr-1169.1-of-1.2026-03-05__17-48-26__gpt-5-1-codex-mini"
  },
  "decision": {
    "status": "fail",
    "primary_signal": "equivalence",
    "matrix_status": "fail_guardrail",
    "reason_codes": [
      "guardrail_preflight_failed",
      "primary_equivalence",
      "tests_unknown",
      "equivalence_non_equivalent",
      "needs_generated_tests",
      "weak_signal_risk",
      "tests_all_commands_ignored",
      "tests_unknown_no_gold_pass_commands"
    ],
    "flags": [
      "equiv_warn",
      "review_warn"
    ],
    "lane_report": {
      "lane": "lane_unknown",
      "source": "lane_unknown",
      "reasons": [
        "lane_unknown"
      ]
    },
    "publish": {
      "include_in_leaderboard": true,
      "weak_signal_risk": true
    },
    "rescue": {
      "candidate": false,
      "eligible": false,
      "decision": "not_candidate",
      "required_artifacts_ok": true
    },
    "notes": [
      "gold baseline failed for \"go test -C v2 ./... -count=1 -timeout=300s\": apply test.patch to gold baseline repo: extract repo tarball: invalid tar symlink target: ../README.md",
      "repo context unavailable: extract repo tarball: invalid tar symlink target: ../README.md"
    ]
  },
  "tests": {
    "outcome": "unknown",
    "unknown_cause": "no_gold_pass_commands",
    "strength": "missing",
    "command_results": [
      {
        "command": "go test -C v2 ./... -count=1 -timeout=300s",
        "gold_outcome": "unknown",
        "agent_retried": false
      }
    ],
    "partial_score": {
      "level": "command",
      "provenance": "fallback_command_level",
      "reason": "no_gold_pass_commands"
    },
    "tb": {
      "trial_name": "flux-pr-1169.1-of-1.2026-03-05__17-48-26__gpt-5-1-codex-mini",
      "is_resolved": true,
      "failure_mode": "unset",
      "duration_sec": 217.680305458,
      "time_budget_sec": 1800
    },
    "cache": {}
  },
  "quality": {
    "equivalence": {
      "status": "used",
      "outcome": "non_equivalent",
      "evaluator_model": "gpt-5.3-codex",
      "confidence": 0.82,
      "issue_type": "behavioral"
    },
    "code_review": {
      "status": "used",
      "signal": "fail",
      "evaluator_model": "gpt-5.3-codex",
      "confidence": 0.87,
      "issue_type": "unclear",
      "source_field": "code_review",
      "dimension_scores": {
        "correctness": {
          "score_0_4": 1,
          "confidence_0_1": 0.89,
          "rationale": "The patch improves some messages, but it misses key intended behavior: enum leaf selections are still not rejected, missing-subfield errors still use the enclosing type instead of the field return type, and validation-failed status/code application remains tied to the old compatibility flag path."
        },
        "edge_case_handling": {
          "score_0_4": 1,
          "confidence_0_1": 0.9,
          "rationale": "Important edge cases in GraphQL field-selection validation are still mishandled, notably enum fields with sub-selections and spec-accurate typing in missing-selection errors."
        },
        "introduced_bug_risk": {
          "score_0_4": 1,
          "confidence_0_1": 0.82,
          "rationale": "Error-constructor signatures were changed and behavior was shifted inconsistently (rule-level logic plus validator post-processing), increasing regression risk across call sites and compatibility paths."
        },
        "maintainability_idioms": {
          "score_0_4": 2,
          "confidence_0_1": 0.77,
          "rationale": "The patch leaves mixed paradigms (old compatibility flag semantics plus new message changes) instead of the intended single centralized mechanism, making future behavior harder to reason about."
        }
      },
      "findings": [
        {
          "id": "f1",
          "dimension": "correctness",
          "severity": "major",
          "title": "Enum leaf fields with sub-selections are still accepted",
          "detail": "Validation only rejects sub-selections for scalar fields (`NodeKindScalarTypeDefinition`) and does not reject enum fields with selections, which should also be treated as leaf types.",
          "confidence_0_1": 0.94,
          "citations": [
            {
              "path": "v2/pkg/astvalidation/operation_rule_validate_field_selections.go",
              "side": "new",
              "start_line": 58,
              "end_line": 60,
              "anchor_kind": "diff",
              "head_sha": "57b5188"
            }
          ]
        },
        {
          "id": "f2",
          "dimension": "correctness",
          "severity": "major",
          "title": "Missing-subfield error uses wrong type context",
          "detail": "The call passes `typeName` (enclosing type) into `ErrMissingFieldSelectionOnNonScalar`, but the spec-style message expects the field's return type (e.g., `User`, `User!`, `[User]`). This can produce incorrect error text.",
          "confidence_0_1": 0.92,
          "citations": [
            {
              "path": "v2/pkg/astvalidation/operation_rule_validate_field_selections.go",
              "side": "new",
              "start_line": 61,
              "end_line": 62,
              "anchor_kind": "diff",
              "head_sha": "57b5188"
            },
            {
              "path": "v2/pkg/operationreport/externalerror.go",
              "side": "new",
              "start_line": 166,
              "end_line": 169,
              "anchor_kind": "diff",
              "head_sha": "57b5188"
            }
          ]
        },
        {
          "id": "f3",
          "dimension": "maintainability_idioms",
          "severity": "major",
          "title": "Centralized validation-failed mechanism not implemented as intended",
          "detail": "Status/extension codes are applied in `Validate` only when `ReplaceUndefinedOpFieldError` is set, rather than via a centralized walker-level external-error hook with the new dedicated compatibility flag. This keeps old flag semantics and misses the intended architecture change.",
          "confidence_0_1": 0.88,
          "citations": [
            {
              "path": "v2/pkg/astvalidation/operation_validation.go",
              "side": "new",
              "start_line": 90,
              "end_line": 96,
              "anchor_kind": "diff",
              "head_sha": "57b5188"
            },
            {
              "path": "v2/pkg/astvalidation/operation_validation.go",
              "side": "new",
              "start_line": 72,
              "end_line": 74,
              "anchor_kind": "diff",
              "head_sha": "57b5188"
            }
          ]
        }
      ],
      "overall": {
        "overall_score_0_100": 30.000000000000004,
        "signal": "fail",
        "confidence_overall": 0.87,
        "summary": "The agent patch partially updates message text and locations, but it likely does not satisfy the intended PR: key spec-compliant field-selection behaviors and the new centralized Apollo validation-failed mechanism are not correctly implemented."
      }
    },
    "behavioral_robustness": {
      "status": "skipped",
      "probe_status": "skipped",
      "coverage_delta_status": "unavailable",
      "coverage_delta_reason": "coverage_adapter_unavailable",
      "mutation_lite_status": "unavailable",
      "mutation_lite_reason": "mutation_runner_unavailable",
      "notes": "no accepted probe tests"
    },
    "footprint_risk": {
      "status": "used",
      "reason": "none",
      "version": "v1",
      "level": "low",
      "score": 0.1694095619334414,
      "flag": false,
      "severe_flag": false
    },
    "cost": {
      "status": "tokens_only",
      "token_status": "present",
      "cache_token_status": "present",
      "total_input_tokens": 9175810,
      "total_output_tokens": 31914,
      "total_tokens": 9207724,
      "uncached_input_tokens": 817282,
      "cache_read_input_tokens": 8358528,
      "cached_input_tokens": 8358528,
      "total_cost_usd": 2.6711861999999997,
      "token_source": "openai_cached_tokens_usage",
      "pricing_model_key": "gpt-5.1-codex-mini",
      "pricing_mode": "cache_aware"
    }
  },
  "summary": {
    "task": {
      "matrix_status": "fail_guardrail",
      "tests_outcome": "unknown",
      "tests_unknown_cause": "no_gold_pass_commands",
      "lane_report_lane": "lane_unknown",
      "lane_report_source": "lane_unknown",
      "lane_report_reasons": [
        "lane_unknown"
      ],
      "cache_hit": null,
      "cache_miss_reason": null,
      "setup_ms_saved": null,
      "pinned_bytes": null,
      "environment_group_id": null,
      "equivalence_status": "used",
      "equivalence_outcome": "non_equivalent",
      "code_review_status": "used",
      "code_review_signal": "fail",
      "behavioral_robustness_status": "skipped",
      "coverage_delta_status": "unavailable",
      "mutation_lite_status": "unavailable",
      "probe_accepted_candidates": null,
      "probe_accepted_commands": null,
      "probe_agreement_rate": null,
      "probe_gold_pass_candidate_pass_count": null,
      "probe_gold_pass_candidate_fail_count": null,
      "probe_review_required_count": null,
      "flags": [
        "equiv_warn",
        "review_warn"
      ],
      "tb_is_resolved": true,
      "tb_failure_mode": "unset",
      "tb_total_input_tokens": 9175810,
      "tb_total_output_tokens": 31914,
      "tb_total_tokens": 9207724,
      "tb_uncached_input_tokens": 817282,
      "tb_cache_creation_input_tokens": null,
      "tb_cache_read_input_tokens": 8358528,
      "tb_cached_input_tokens": 8358528,
      "token_status": "present",
      "cache_token_status": "present",
      "token_source": "openai_cached_tokens_usage",
      "task_cost": 2.6711861999999997,
      "cost_status": "present",
      "cost_pricing_mode": "cache_aware",
      "pricing_model_key": "gpt-5.1-codex-mini",
      "equiv_rescue_policy": "on",
      "rescue_candidate": false,
      "rescue_eligible": false,
      "rescue_decision": "not_candidate",
      "publish_include_in_leaderboard": true,
      "publish_exclusion_reasons": [],
      "publish_weak_signal_risk": true,
      "tests_only_outcome": 0,
      "rescue_aware_outcome": 0,
      "partial_score": null,
      "partial_score_numerator": 0,
      "partial_score_denominator": 0,
      "partial_score_level": "command",
      "partial_score_provenance": "fallback_command_level",
      "partial_score_reason": "no_gold_pass_commands",
      "partial_score_unknown_count": 0,
      "footprint_risk_status": "used",
      "footprint_risk_reason": "none",
      "footprint_risk_level": "low",
      "footprint_risk_score": 0.1694095619334414,
      "footprint_risk_flag": false,
      "footprint_risk_severe_flag": false
    },
    "run": {
      "model": "gpt-5-1-codex-mini",
      "requested_model": "gpt-5-1-codex-mini",
      "run_id": "2026-02-21__03-36-16__gpt-5-1-codex-mini",
      "passRate": 0.5714285714285714,
      "ciLow": 0.38095238095238093,
      "ciHigh": 0.8095238095238095,
      "effectiveN": 21,
      "tier": 1,
      "validation_counts": {
        "fail_guardrail": 13,
        "fail_high_conf": 1,
        "fail_infra": 2,
        "fail_likely_equiv": 0,
        "fail_no_patch": 1,
        "fail_with_diag": 0,
        "missing": 0,
        "pass": 2,
        "pass_with_warn": 11
      }
    },
    "run_metadata": {
      "agent_name": "codex",
      "model_name": "gpt-5.1-codex-mini",
      "start_time": "2026-02-21T03:36:19.601271+00:00",
      "end_time": "2026-02-21T06:29:08.047412+00:00",
      "commit_hash": "f09baebe0424b002663dfd81a4ba49701bb870e3",
      "accuracy": 0.5,
      "reasoning_effort": "medium"
    }
  },
  "evidence": {
    "task_detail": {
      "path": "validation/gpt-5-1-codex-mini/flux-pr-1169/task_detail.v1.json",
      "exists": true
    },
    "trajectory": {
      "path": "validation/gpt-5-1-codex-mini/flux-pr-1169/trajectory.v1.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 15378
    },
    "validation": {
      "path": "validation/gpt-5-1-codex-mini/flux-pr-1169/validation.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 118311
    },
    "results": {
      "path": "runs/2026-02-21__03-36-16__gpt-5-1-codex-mini/results.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 59870
    },
    "run_metadata": {
      "path": "runs/2026-02-21__03-36-16__gpt-5-1-codex-mini/run_metadata.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 1662
    },
    "agent_patch": {
      "path": "runs/2026-02-21__03-36-16__gpt-5-1-codex-mini/flux-pr-1169/flux-pr-1169.1-of-1.2026-03-05__17-48-26__gpt-5-1-codex-mini/agent-logs/agent.patch",
      "exists": true,
      "non_empty": true,
      "size_bytes": 12557
    },
    "summary": {
      "path": "reports/summary.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 96753
    },
    "manifest": {
      "path": "manifest.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 495
    },
    "validation_inputs": {
      "required_for_rescue_ok": true,
      "gold_patch": {
        "exists": true,
        "non_empty": true,
        "size_bytes": 10940,
        "sha256": "6f12a30ad451adb641b97861c7d346e166b038d30895e2c48a758cac4d3c3437",
        "required_for_rescue": true
      },
      "repo_tarball": {
        "exists": true,
        "non_empty": true,
        "size_bytes": 4280604,
        "sha256": "b0aec80c0eb61f316ed27d0fbe664447261590a37f7d8f92cadf390b4056da87",
        "required_for_rescue": true
      },
      "agent_patch": {
        "exists": true,
        "non_empty": true,
        "size_bytes": 12557,
        "sha256": "94b6a34f6f4d2773e2d0cd15771022841344a2219ce739bfb568f7f343a6a268",
        "required_for_rescue": true
      }
    }
  },
  "provenance": {
    "identity": [
      {
        "source": "manifest",
        "available": true
      },
      {
        "source": "tb_results",
        "available": true
      }
    ],
    "decision": [
      {
        "source": "validation",
        "available": true
      }
    ],
    "tests": [
      {
        "source": "validation",
        "available": true
      },
      {
        "source": "tb_results",
        "available": true
      }
    ],
    "quality": {
      "equivalence": [
        {
          "source": "validation",
          "available": true
        }
      ],
      "code_review": [
        {
          "source": "validation",
          "available": true
        }
      ],
      "behavioral_robustness": [
        {
          "source": "validation",
          "available": true
        }
      ],
      "footprint_risk": [
        {
          "source": "validation",
          "available": true
        }
      ],
      "cost": [
        {
          "source": "validation",
          "available": true
        },
        {
          "source": "summary",
          "available": true
        }
      ]
    },
    "summary": {
      "task": [
        {
          "source": "summary",
          "available": true
        }
      ],
      "run": [
        {
          "source": "summary",
          "available": true
        }
      ],
      "run_metadata": [
        {
          "source": "run_metadata",
          "available": true
        }
      ]
    },
    "evidence": [
      {
        "source": "filesystem",
        "available": true
      }
    ]
  }
}