STET

task_detail

validation/gpt-5-1-codex-mini/flux-pr-1260/task_detail.v1.json

16454 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-1260",
    "trial_name": "flux-pr-1260.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini"
  },
  "decision": {
    "status": "pass",
    "primary_signal": "tests",
    "matrix_status": "pass_with_warn",
    "reason_codes": [
      "primary_tests",
      "tests_passed",
      "decision_conflict",
      "equivalence_non_equivalent",
      "review_fail"
    ],
    "flags": [
      "equiv_warn",
      "review_warn"
    ],
    "publish": {
      "include_in_leaderboard": true,
      "weak_signal_risk": false
    },
    "rescue": {
      "candidate": false,
      "eligible": false,
      "decision": "not_candidate",
      "required_artifacts_ok": true
    }
  },
  "tests": {
    "outcome": "pass",
    "strength": "strong",
    "commands": [
      "go test -C v2 ./... -count=1 -timeout=300s"
    ],
    "command_results": [
      {
        "command": "go test -C v2 ./... -count=1 -timeout=300s",
        "gold_outcome": "pass",
        "gold_tb_trial_name": "flux-pr-1260.1-of-1.validate-gold-1771693292905556000",
        "gold_failure_mode": "unset",
        "agent_outcome": "pass",
        "agent_tb_trial_name": "flux-pr-1260.1-of-1.validate-override-1771693344735598000",
        "agent_failure_mode": "unset",
        "agent_retried": false
      }
    ],
    "partial_score": {
      "score": 1,
      "numerator": 1,
      "denominator": 1,
      "level": "command",
      "provenance": "fallback_command_level",
      "reason": "test_case_detail_unavailable"
    },
    "tb": {
      "trial_name": "flux-pr-1260.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini",
      "is_resolved": false,
      "failure_mode": "unset",
      "duration_sec": 372.638310583,
      "time_budget_sec": 600
    },
    "cache": {
      "cache_hit": false,
      "cache_miss_reason": "missing_pinned_dependencies",
      "environment_group_id": "eg_46b6a6c82a4890b6e6e87c39575fd02c"
    }
  },
  "quality": {
    "equivalence": {
      "status": "used",
      "outcome": "non_equivalent",
      "evaluator_model": "codex-5.3",
      "confidence": 0.86,
      "issue_type": "behavioral",
      "notes": "The agent adds `QueryPlan`/metadata to `GraphQLSubscriptionTrigger` and threads some of it into postprocessing, but it misses a core part of the intended behavior: subscription query-plan rendering. The gold change updates fetch-tree plan printing to include subscription trigger (`Primary`) and handle query formatting safely; the agent patch does not modify `resolve/fetchtree.go`, so subscription plans can still be incomplete in output. It also still depends on parsing trigger input via `jsonparser` (with fallback), whereas the intended fix removes that dependency for introspection-first subscription plans."
    },
    "code_review": {
      "status": "used",
      "signal": "fail",
      "evaluator_model": "codex-5.3",
      "confidence": 0.86,
      "issue_type": "unclear",
      "source_field": "code_review",
      "dimension_scores": {
        "correctness": {
          "score_0_4": 1,
          "confidence_0_1": 0.89,
          "rationale": "Patch adds trigger metadata fields and wires `QueryPlan`, but it misses the subscription query-plan printer updates and still relies on parsed trigger input fallback logic, so it likely does not fully implement the intended subscription plan introspection behavior."
        },
        "edge_case_handling": {
          "score_0_4": 1,
          "confidence_0_1": 0.78,
          "rationale": "It keeps mixed fallback paths (`jsonparser` result vs `Trigger.QueryPlan`) instead of consistently using planned metadata, so subscription trigger query text can diverge by execution mode and input shape."
        },
        "introduced_bug_risk": {
          "score_0_4": 1,
          "confidence_0_1": 0.83,
          "rationale": "It introduces extra trigger fields (`ResponsePath`, `SourceID`, `SourceName`, `FetchID`) that are not part of the minimal design and duplicates source-of-truth between plan/postprocess stages, increasing inconsistency risk."
        },
        "maintainability_idioms": {
          "score_0_4": 2,
          "confidence_0_1": 0.8,
          "rationale": "The patch works around missing data by adding multiple ad-hoc fields and conditional fallbacks in postprocessing rather than following a single clear path from planner metadata to printed query plan."
        }
      },
      "findings": [
        {
          "id": "f1",
          "dimension": "correctness",
          "severity": "major",
          "title": "Subscription query-plan printer changes are missing",
          "detail": "The intended behavior includes explicit subscription trigger rendering in query plans (primary trigger + rest of plan). This patch does not update `resolve/fetchtree.go`, so subscription plan output is likely still incomplete for introspection.",
          "confidence_0_1": 0.9,
          "citations": [
            {
              "path": "v2/pkg/engine/resolve/fetchtree.go",
              "side": "context",
              "start_line": 306,
              "end_line": 351,
              "anchor_kind": "file",
              "head_sha": "392f524dfb280fceb82762ce28ed4d2b189e11d9"
            }
          ]
        },
        {
          "id": "f2",
          "dimension": "correctness",
          "severity": "major",
          "title": "Trigger query source remains partially derived from runtime input parsing",
          "detail": "Postprocess still starts from parsed `res.Trigger.Input` (`query := v`) and only conditionally overrides from `Trigger.QueryPlan`, which can produce mismatched/empty trigger query data in skip-loader-like introspection paths where runtime input parsing is not authoritative.",
          "confidence_0_1": 0.85,
          "citations": [
            {
              "path": "v2/pkg/engine/postprocess/postprocess.go",
              "side": "new",
              "start_line": 216,
              "end_line": 246,
              "anchor_kind": "diff",
              "head_sha": "392f524dfb280fceb82762ce28ed4d2b189e11d9"
            }
          ]
        },
        {
          "id": "f3",
          "dimension": "maintainability_idioms",
          "severity": "minor",
          "title": "Adds redundant trigger metadata fields beyond required change",
          "detail": "Introducing `ResponsePath`, `SourceID`, `SourceName`, and `FetchID` in `GraphQLSubscriptionTrigger` duplicates data already available via planning/fetch info and increases drift risk without clear necessity for the requested fix.",
          "confidence_0_1": 0.78,
          "citations": [
            {
              "path": "v2/pkg/engine/resolve/response.go",
              "side": "new",
              "start_line": 24,
              "end_line": 33,
              "anchor_kind": "diff",
              "head_sha": "392f524dfb280fceb82762ce28ed4d2b189e11d9"
            },
            {
              "path": "v2/pkg/engine/plan/visitor.go",
              "side": "new",
              "start_line": 1283,
              "end_line": 1288,
              "anchor_kind": "diff",
              "head_sha": "392f524dfb280fceb82762ce28ed4d2b189e11d9"
            }
          ]
        }
      ],
      "overall": {
        "confidence_overall": 0.86,
        "summary": "Patch appears partially aligned but likely does not satisfy the intended change end-to-end; key subscription query-plan introspection behavior and output formatting updates are missing or inconsistently implemented."
      },
      "notes": "Patch appears partially aligned but likely does not satisfy the intended change end-to-end; key subscription query-plan introspection behavior and output formatting updates are missing or inconsistently implemented."
    },
    "behavioral_robustness": {
      "status": "used",
      "probe_status": "used",
      "gold_pass_candidate_pass_count": 1,
      "agreement_rate": 1,
      "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": 0.16326361063811723,
      "flag": false,
      "severe_flag": false
    },
    "cost": {
      "status": "tokens_only",
      "token_status": "present",
      "cache_token_status": "present",
      "total_input_tokens": 5927854,
      "total_output_tokens": 43930,
      "total_tokens": 5971784,
      "uncached_input_tokens": 882734,
      "cache_read_input_tokens": 5045120,
      "cached_input_tokens": 5045120,
      "total_cost_usd": 2.344449,
      "token_source": "openai_cached_tokens_usage",
      "pricing_model_key": "gpt-5.1-codex-mini",
      "pricing_mode": "cache_aware"
    }
  },
  "summary": {
    "task": {
      "matrix_status": "pass_with_warn",
      "tests_outcome": "pass",
      "tests_unknown_cause": null,
      "lane_report_lane": null,
      "lane_report_source": null,
      "lane_report_reasons": null,
      "cache_hit": false,
      "cache_miss_reason": "missing_pinned_dependencies",
      "setup_ms_saved": null,
      "pinned_bytes": null,
      "environment_group_id": "eg_46b6a6c82a4890b6e6e87c39575fd02c",
      "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": 1,
      "probe_gold_pass_candidate_pass_count": 1,
      "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": 5927854,
      "tb_total_output_tokens": 43930,
      "tb_total_tokens": 5971784,
      "tb_uncached_input_tokens": 882734,
      "tb_cache_creation_input_tokens": null,
      "tb_cache_read_input_tokens": 5045120,
      "tb_cached_input_tokens": 5045120,
      "token_status": "present",
      "cache_token_status": "present",
      "token_source": "openai_cached_tokens_usage",
      "task_cost": 2.344449,
      "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": false,
      "tests_only_outcome": 1,
      "rescue_aware_outcome": 1,
      "partial_score": 1,
      "partial_score_numerator": 1,
      "partial_score_denominator": 1,
      "partial_score_level": "command",
      "partial_score_provenance": "fallback_command_level",
      "partial_score_reason": "test_case_detail_unavailable",
      "partial_score_unknown_count": 0,
      "footprint_risk_status": "used",
      "footprint_risk_reason": "none",
      "footprint_risk_level": "low",
      "footprint_risk_score": 0.16326361063811723,
      "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-1260/task_detail.v1.json",
      "exists": true
    },
    "trajectory": {
      "path": "validation/gpt-5-1-codex-mini/flux-pr-1260/trajectory.v1.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 15393
    },
    "validation": {
      "path": "validation/gpt-5-1-codex-mini/flux-pr-1260/validation.json",
      "exists": true,
      "non_empty": true,
      "size_bytes": 111485
    },
    "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-1260/flux-pr-1260.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini/agent-logs/agent.patch",
      "exists": true,
      "non_empty": true,
      "size_bytes": 3610
    },
    "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": 5108,
        "sha256": "46727ff557296376f47e4d08cd75a3da1917e639244ae4ef49252e1b97580e9f",
        "required_for_rescue": true
      },
      "repo_tarball": {
        "exists": true,
        "non_empty": true,
        "size_bytes": 4368476,
        "sha256": "ce34295bf7c4aabe8f2c0474873884cdccdec4dfe1c28a714a444c5f29b60d3f",
        "required_for_rescue": true
      },
      "agent_patch": {
        "exists": true,
        "non_empty": true,
        "size_bytes": 3610,
        "sha256": "cd1eaa836da686f33ab93d38c11ec9cf8838ed1215cbb64c260ad4dbb2ce254d",
        "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
      }
    ]
  }
}