STET

task_detail

validation/gpt-5-1-codex-mini/flux-pr-1908/task_detail.v1.json

14117 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": "2026-02-28__18-27-22__gpt-5-1-codex-mini",
    "task_id": "flux-pr-1908",
    "trial_name": "flux-pr-1908.1-of-1.2026-02-28__18-27-22__gpt-5-1-codex-mini"
  },
  "decision": {
    "status": "fail",
    "primary_signal": "equivalence",
    "matrix_status": "fail_high_conf",
    "reason_codes": [
      "primary_equivalence",
      "tests_unknown",
      "needs_generated_tests",
      "weak_signal_risk",
      "tests_all_commands_ignored",
      "tests_unknown_all_commands_ignored_gold_failure_mode_unset",
      "equivalence_non_equivalent",
      "review_fail"
    ],
    "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
    }
  },
  "tests": {
    "outcome": "unknown",
    "unknown_cause": "all_commands_ignored_gold_failure_mode_unset",
    "strength": "missing",
    "command_results": [
      {
        "command": "env PATH=/root/.cargo/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin cargo test --all-features",
        "gold_outcome": "fail",
        "gold_tb_trial_name": "flux-pr-1908.1-of-1.validate-gold-1772316847181065000",
        "gold_failure_mode": "unset",
        "agent_retried": false
      }
    ],
    "partial_score": {
      "level": "command",
      "provenance": "fallback_command_level",
      "reason": "no_gold_pass_commands"
    },
    "tb": {
      "trial_name": "flux-pr-1908.1-of-1.2026-02-28__18-27-22__gpt-5-1-codex-mini",
      "is_resolved": false,
      "failure_mode": "unset",
      "duration_sec": 41.778503875,
      "time_budget_sec": 1200
    },
    "cache": {
      "cache_hit": false,
      "cache_miss_reason": "missing_pinned_dependencies",
      "environment_group_id": "eg_2d84f25b38a313fb6c13d2663529d655"
    }
  },
  "quality": {
    "equivalence": {
      "status": "used",
      "outcome": "non_equivalent",
      "confidence": 0.95,
      "issue_type": "behavioral",
      "notes": "The patch adds AST/parser/test support for `NOT VALID` and `VALIDATE CONSTRAINT`, but it does not add `VALIDATE` to `src/keywords.rs` (while using `Keyword::VALIDATE` in the parser). That is a core missing change and would break/omit proper parsing support. It also restricts the new syntax to PostgreSQL dialect only, unlike the gold behavior."
    },
    "code_review": {
      "status": "used",
      "signal": "fail",
      "confidence": 0.94,
      "issue_type": "unclear",
      "source_field": "code_review",
      "dimension_scores": {
        "correctness": {
          "score_0_4": 1,
          "confidence_0_1": 0.98,
          "rationale": "The patch references `Keyword::VALIDATE` in parser logic but does not add the corresponding keyword variant, which is likely a compile-time failure and blocks the intended feature."
        },
        "edge_case_handling": {
          "score_0_4": 2,
          "confidence_0_1": 0.8,
          "rationale": "Postgres-specific parsing for `NOT VALID` and `VALIDATE CONSTRAINT` is implemented and tests were added, but the missing keyword wiring prevents validating edge behaviors end-to-end."
        },
        "introduced_bug_risk": {
          "score_0_4": 1,
          "confidence_0_1": 0.94,
          "rationale": "A new parser branch depends on a keyword symbol that appears unintroduced in this patch, creating high risk of immediate build/test failure rather than a runtime-only issue."
        },
        "maintainability_idioms": {
          "score_0_4": 3,
          "confidence_0_1": 0.86,
          "rationale": "The AST refactor to a struct-like `AddConstraint` and targeted tests are clean and idiomatic, but incomplete integration (keyword plumbing gap) hurts maintainability until fixed."
        }
      },
      "findings": [
        {
          "id": "f1",
          "dimension": "correctness",
          "severity": "major",
          "title": "Parser uses `Keyword::VALIDATE` without adding keyword definition",
          "detail": "The new `ALTER TABLE ... VALIDATE CONSTRAINT` parser branch references `Keyword::VALIDATE`, but this patch does not include the corresponding keyword addition. In this codebase, missing keyword enum entries cause compilation failure.",
          "confidence_0_1": 0.98,
          "citations": [
            {
              "path": "src/parser/mod.rs",
              "side": "new",
              "start_line": 8785,
              "end_line": 8790,
              "anchor_kind": "diff",
              "head_sha": "936c2f1"
            }
          ]
        }
      ],
      "overall": {
        "confidence_overall": 0.94,
        "summary": "The patch is close to the intended feature but likely does not build as-is due to missing keyword plumbing for `VALIDATE`; therefore it likely does not satisfy the task end-to-end."
      },
      "notes": "The patch is close to the intended feature but likely does not build as-is due to missing keyword plumbing for `VALIDATE`; therefore it likely does not satisfy the task end-to-end."
    },
    "behavioral_robustness": {
      "status": "used",
      "probe_status": "used",
      "coverage_delta_status": "unavailable",
      "coverage_delta_reason": "coverage_adapter_unavailable",
      "mutation_lite_status": "unavailable",
      "mutation_lite_reason": "mutation_runner_unavailable",
      "notes": "derived from command-level outcomes; no accepted generated probes"
    },
    "footprint_risk": {
      "status": "used",
      "reason": "none",
      "version": "v1",
      "level": "low",
      "score": 0.3024402890316348,
      "flag": false,
      "severe_flag": false
    },
    "cost": {
      "status": "tokens_only",
      "token_status": "present",
      "cache_token_status": "present",
      "total_input_tokens": 2302211,
      "total_output_tokens": 26985,
      "total_tokens": 2329196,
      "uncached_input_tokens": 274179,
      "cache_read_input_tokens": 2028032,
      "cached_input_tokens": 2028032,
      "total_cost_usd": 0.8773833,
      "token_source": "openai_cached_tokens_usage",
      "pricing_model_key": "gpt-5.1-codex-mini",
      "pricing_mode": "cache_aware"
    }
  },
  "summary": {
    "task": {
      "matrix_status": "fail_high_conf",
      "tests_outcome": "unknown",
      "tests_unknown_cause": "all_commands_ignored_gold_failure_mode_unset",
      "lane_report_lane": "lane_unknown",
      "lane_report_source": "lane_unknown",
      "lane_report_reasons": [
        "lane_unknown"
      ],
      "cache_hit": false,
      "cache_miss_reason": "missing_pinned_dependencies",
      "setup_ms_saved": null,
      "pinned_bytes": null,
      "environment_group_id": "eg_2d84f25b38a313fb6c13d2663529d655",
      "equivalence_status": "used",
      "equivalence_outcome": "non_equivalent",
      "code_review_status": "used",
      "code_review_signal": "fail",
      "behavioral_robustness_status": "used",
      "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": false,
      "tb_failure_mode": "unset",
      "tb_total_input_tokens": 2302211,
      "tb_total_output_tokens": 26985,
      "tb_total_tokens": 2329196,
      "tb_uncached_input_tokens": 274179,
      "tb_cache_creation_input_tokens": null,
      "tb_cache_read_input_tokens": 2028032,
      "tb_cached_input_tokens": 2028032,
      "token_status": "present",
      "cache_token_status": "present",
      "token_source": "openai_cached_tokens_usage",
      "task_cost": 0.8773833,
      "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": 0.3024402890316348,
      "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": "2026-02-28__18-27-22__gpt-5-1-codex-mini",
      "passRate": 0.9333333333333333,
      "ciLow": 0.8333333333333334,
      "ciHigh": 1,
      "effectiveN": 30,
      "tier": 1,
      "validation_counts": {
        "fail_guardrail": 0,
        "fail_high_conf": 1,
        "fail_infra": 0,
        "fail_likely_equiv": 1,
        "fail_with_diag": 0,
        "missing": 0,
        "pass": 3,
        "pass_with_warn": 25
      }
    },
    "run_metadata": {
      "agent_name": "codex",
      "model_name": "gpt-5.1-codex-mini",
      "start_time": "2026-02-28T20:00:12.722616+00:00",
      "end_time": "2026-02-28T21:48:26.352711+00:00",
      "commit_hash": "32dbe1950f8d0a4ed6db86745bf0a62da2ee0921",
      "accuracy": 0.26666666666666666,
      "reasoning_effort": "medium"
    }
  },
  "evidence": {
    "task_detail": {
      "path": "validation/gpt-5-1-codex-mini/flux-pr-1908/task_detail.v1.json",
      "exists": true
    },
    "trajectory": {
      "path": "validation/gpt-5-1-codex-mini/flux-pr-1908/trajectory.v1.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 15378
    },
    "validation": {
      "path": "validation/gpt-5-1-codex-mini/flux-pr-1908/validation.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 109250
    },
    "results": {
      "path": "runs/2026-02-28__18-27-22__gpt-5-1-codex-mini/results.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 61948
    },
    "run_metadata": {
      "path": "runs/2026-02-28__18-27-22__gpt-5-1-codex-mini/run_metadata.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 1673
    },
    "agent_patch": {
      "path": "runs/2026-02-28__18-27-22__gpt-5-1-codex-mini/flux-pr-1908/flux-pr-1908.1-of-1.2026-02-28__18-27-22__gpt-5-1-codex-mini/agent-logs/agent.patch",
      "exists": true,
      "non_empty": true,
      "size_bytes": 10623
    },
    "summary": {
      "path": "reports/summary.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 280264
    },
    "manifest": {
      "path": "manifest.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 675
    },
    "validation_inputs": {
      "required_for_rescue_ok": true,
      "gold_patch": {
        "exists": true,
        "non_empty": true,
        "size_bytes": 6897,
        "sha256": "d3e8979def09e66013f98a40adcb3f7ed7507bd6a9798c8f40dee7a743ef3fab",
        "required_for_rescue": true
      },
      "repo_tarball": {
        "exists": true,
        "non_empty": true,
        "size_bytes": 760410,
        "sha256": "a3bd41c5b19d58efa1b0581ea1382f7baa83a356297f704128ae21e48f10c8a8",
        "required_for_rescue": true
      },
      "agent_patch": {
        "path": "runs/2026-02-28__18-27-22__gpt-5-1-codex-mini/flux-pr-1908/flux-pr-1908.1-of-1.2026-02-28__18-27-22__gpt-5-1-codex-mini/agent-logs/agent.patch",
        "exists": true,
        "non_empty": true,
        "size_bytes": 10623,
        "sha256": "5acc35086460e924fb87dd6fa33dca94eac2113c9a1ea3d721f853c86166c0d9",
        "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
      }
    ]
  }
}