task_detail
validation/gpt-5-1-codex-mini/flux-pr-1308/task_detail.v1.json
15403 bytes
{
"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-1308",
"trial_name": "flux-pr-1308.1-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": false,
"exclusion_reasons": [
"zero_token_agent_timeout"
],
"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-1308.1-of-1.2026-03-05__17-48-26__gpt-5-1-codex-mini",
"is_resolved": false,
"failure_mode": "agent_timeout",
"duration_sec": 189.929110125,
"time_budget_sec": 1800
},
"cache": {}
},
"quality": {
"equivalence": {
"status": "used",
"outcome": "non_equivalent",
"evaluator_model": "gpt-5.3-codex",
"confidence": 0.78,
"issue_type": "behavioral"
},
"code_review": {
"status": "used",
"signal": "fail",
"evaluator_model": "gpt-5.3-codex",
"confidence": 0.86,
"issue_type": "unclear",
"source_field": "code_review",
"dimension_scores": {
"correctness": {
"score_0_4": 1,
"confidence_0_1": 0.89,
"rationale": "The patch contains a concrete logic error in definition validation (`v.definition` is set from `operation`), and it introduces non-target introspection schema changes (`isOneOf`) instead of matching the intended directive/error-behavior implementation."
},
"edge_case_handling": {
"score_0_4": 1,
"confidence_0_1": 0.77,
"rationale": "Added operation tests cover only basic literal oneOf object cases and do not demonstrate key variable-path/undefined-variable behavior expected by the task."
},
"introduced_bug_risk": {
"score_0_4": 1,
"confidence_0_1": 0.85,
"rationale": "The incorrect document binding in the new validation visitor is high-risk, and adding a new introspection field across model/schema fixtures increases compatibility and regression risk."
},
"maintainability_idioms": {
"score_0_4": 2,
"confidence_0_1": 0.74,
"rationale": "The patch broadens surface area with a new `isOneOf` introspection property and many fixture updates that do not align with the intended minimal directive-based change, increasing maintenance burden."
}
},
"findings": [
{
"id": "f1",
"dimension": "correctness",
"severity": "major",
"title": "Definition validator reads from wrong AST document",
"detail": "In `EnterDocument`, the visitor stores `operation` into `v.definition` instead of `definition`, so subsequent oneOf checks run against the wrong document context and can mis-validate.",
"confidence_0_1": 0.97,
"citations": [
{
"path": "app/v2/pkg/astvalidation/rule_one_of_input_objects.go",
"side": "new",
"start_line": 26,
"end_line": 29,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
}
]
},
{
"id": "f2",
"dimension": "correctness",
"severity": "major",
"title": "Patch introduces non-target `isOneOf` introspection field",
"detail": "The change adds `isOneOf` to `__Type` model/schema and fixture outputs, which is a broader API change than the target directive/validation updates and likely causes incompatibilities with expected outputs.",
"confidence_0_1": 0.9,
"citations": [
{
"path": "app/v2/pkg/introspection/introspection.go",
"side": "new",
"start_line": 61,
"end_line": 66,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
},
{
"path": "app/v2/pkg/astprinter/astprinter_test.go",
"side": "new",
"start_line": 1023,
"end_line": 1027,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
}
]
},
{
"id": "f3",
"dimension": "edge_case_handling",
"severity": "major",
"title": "Validation coverage misses variable-focused oneOf behavior",
"detail": "New tests only assert literal object cases; they do not cover oneOf with variables/nullability/undefined-variable-position behavior that the task explicitly calls out.",
"confidence_0_1": 0.78,
"citations": [
{
"path": "app/v2/pkg/astvalidation/operation_validation_test.go",
"side": "new",
"start_line": 3105,
"end_line": 3147,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
}
]
}
],
"overall": {
"overall_score_0_100": 30.000000000000004,
"signal": "fail",
"confidence_overall": 0.86,
"summary": "The patch likely does not satisfy the intended change: it contains a concrete validator bug and diverges materially by adding `isOneOf` introspection surface rather than cleanly implementing the targeted directive exposure and runtime/operation validation behavior."
},
"notes": "review JSON parse recovered after one retry"
},
"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": "high",
"score": 0.7604586822681538,
"flag": true,
"severe_flag": false
},
"cost": {
"status": "tokens_only",
"token_status": "present",
"cache_token_status": "missing",
"total_input_tokens": 0,
"total_output_tokens": 0,
"total_tokens": 0,
"uncached_input_tokens": 0,
"total_cost_usd": 0,
"pricing_model_key": "gpt-5.1-codex-mini",
"pricing_mode": "legacy_input_output"
}
},
"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": false,
"tb_failure_mode": "agent_timeout",
"tb_total_input_tokens": 0,
"tb_total_output_tokens": 0,
"tb_total_tokens": 0,
"tb_uncached_input_tokens": 0,
"tb_cache_creation_input_tokens": null,
"tb_cache_read_input_tokens": null,
"tb_cached_input_tokens": null,
"token_status": "present",
"cache_token_status": "missing",
"token_source": null,
"task_cost": 0,
"cost_status": "present",
"cost_pricing_mode": "legacy_input_output",
"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": false,
"publish_exclusion_reasons": [
"zero_token_agent_timeout"
],
"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": "high",
"footprint_risk_score": 0.7604586822681538,
"footprint_risk_flag": true,
"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-1308/task_detail.v1.json",
"exists": true
},
"trajectory": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1308/trajectory.v1.json",
"exists": true,
"non_empty": true,
"size_bytes": 15378
},
"validation": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1308/validation.json",
"exists": true,
"non_empty": true,
"size_bytes": 199811
},
"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-1308/flux-pr-1308.1-of-1.2026-03-05__17-48-26__gpt-5-1-codex-mini/agent-logs/agent.patch",
"exists": true,
"non_empty": true,
"size_bytes": 122804
},
"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": 24668,
"sha256": "84c6d0a576ca7a0db5e3262170eb3c8fe4bb83901a1e00a39caf52b059caa8a7",
"required_for_rescue": true
},
"repo_tarball": {
"exists": true,
"non_empty": true,
"size_bytes": 2055392,
"sha256": "9abac454baa18318efac0d0c2d411c481be5d4e9ebca3ad04ef3e07b63086960",
"required_for_rescue": true
},
"agent_patch": {
"exists": true,
"non_empty": true,
"size_bytes": 122804,
"sha256": "8ea42a3972fc75ed50cc0c279575141acceeac5e4f3bdca8fd2205adcb855516",
"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
}
]
}
}