task_detail
validation/gpt-5-1-codex-mini/flux-pr-1076/task_detail.v1.json
9771 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-1076",
"trial_name": "flux-pr-1076.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini"
},
"decision": {
"status": "fail",
"primary_signal": "tests",
"matrix_status": "fail_no_patch",
"reason_codes": [
"fail_no_patch"
],
"lane_report": {
"lane": "lane_unknown",
"source": "lane_unknown",
"reasons": [
"lane_unknown"
]
},
"publish": {
"include_in_leaderboard": false,
"exclusion_reasons": [
"agent_patch_empty"
],
"weak_signal_risk": false
},
"rescue": {
"candidate": false,
"eligible": false,
"decision": "not_candidate",
"required_artifacts_ok": false
},
"notes": [
"agent patch is empty (0 bytes); skipping all validation"
]
},
"tests": {
"outcome": "unknown",
"strength": "unknown",
"tb": {
"trial_name": "flux-pr-1076.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini",
"is_resolved": true,
"failure_mode": "unset",
"duration_sec": 0.008611334,
"time_budget_sec": 300
},
"cache": {}
},
"quality": {
"equivalence": {
"status": "skipped"
},
"code_review": {
"status": "skipped",
"source_field": "code_review"
},
"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": "agent patch is empty; behavioral robustness skipped"
},
"footprint_risk": {
"status": "unavailable",
"reason": "agent_patch_missing",
"version": "v1",
"score": 0,
"flag": false,
"severe_flag": false
},
"cost": {
"total_cost_usd": 1.2491442,
"pricing_model_key": "gpt-5.1-codex-mini",
"pricing_mode": "cache_aware"
}
},
"summary": {
"task": {
"matrix_status": "fail_no_patch",
"tests_outcome": "unknown",
"tests_unknown_cause": "unspecified",
"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": "skipped",
"equivalence_outcome": null,
"code_review_status": "skipped",
"code_review_signal": null,
"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": [],
"tb_is_resolved": true,
"tb_failure_mode": "unset",
"tb_total_input_tokens": 2764702,
"tb_total_output_tokens": 22484,
"tb_total_tokens": 2787186,
"tb_uncached_input_tokens": 518174,
"tb_cache_creation_input_tokens": null,
"tb_cache_read_input_tokens": 2246528,
"tb_cached_input_tokens": 2246528,
"token_status": "present",
"cache_token_status": "present",
"token_source": "openai_cached_tokens_usage",
"task_cost": 1.2491442,
"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": false,
"publish_exclusion_reasons": [
"agent_patch_empty"
],
"publish_weak_signal_risk": false,
"tests_only_outcome": 0,
"rescue_aware_outcome": 0,
"partial_score": null,
"partial_score_numerator": 0,
"partial_score_denominator": 0,
"partial_score_level": null,
"partial_score_provenance": null,
"partial_score_reason": null,
"partial_score_unknown_count": 0,
"footprint_risk_status": "unavailable",
"footprint_risk_reason": "agent_patch_missing",
"footprint_risk_level": null,
"footprint_risk_score": 0,
"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-1076/task_detail.v1.json",
"exists": true
},
"trajectory": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1076/trajectory.v1.json",
"exists": true,
"non_empty": true,
"size_bytes": 15017
},
"validation": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1076/validation.json",
"exists": true,
"non_empty": true,
"size_bytes": 5059
},
"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-1076/flux-pr-1076.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini/agent-logs/agent.patch",
"exists": true,
"non_empty": false,
"size_bytes": 0
},
"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": false,
"missing_for_rescue": [
"agent.patch"
],
"gold_patch": {
"path": ".tmp/graphql-go-tools-dataset/flux-pr-1076/gold.patch",
"exists": true,
"non_empty": true,
"size_bytes": 28154,
"sha256": "630de79193967ed7e442edb80ba1ba1e3ac8b27f43da1f24237307df46ec39fa",
"required_for_rescue": true
},
"repo_tarball": {
"path": ".tmp/graphql-go-tools-dataset/flux-pr-1076/repo.tar.gz",
"exists": true,
"non_empty": true,
"size_bytes": 4171519,
"sha256": "12b8370532022eedd8bc584c8636a5388510622c9af50f3585870d32a23c7966",
"required_for_rescue": true
},
"agent_patch": {
"path": ".tmp/h2h-graphql-flu77-mini-backfill-20260303/runs/2026-02-21__03-36-16__gpt-5-1-codex-mini/flux-pr-1076/flux-pr-1076.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini/agent-logs/agent.patch",
"exists": true,
"non_empty": false,
"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
}
]
}
}