task_detail
validation/gpt-5-1-codex-mini/flux-pr-1184/task_detail.v1.json
16044 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-1184",
"trial_name": "flux-pr-1184.1-of-1.2026-02-21__03-36-16__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"
],
"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": "go test -C v2 ./... -count=1 -timeout=300s",
"gold_outcome": "fail",
"gold_tb_trial_name": "flux-pr-1184.1-of-1.validate-gold-1771692519523184000",
"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-1184.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini",
"is_resolved": true,
"failure_mode": "unset",
"duration_sec": 495.520354625,
"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": 0.92,
"issue_type": "behavioral",
"notes": "The patch only partially addresses the intent. It adds some union-fragment flattening and fixes `entitiesImplementingInterface` plus parent-type checks in `objectFragmentNeedCleanup`, but it does not update rewrite-decision logic to account for union inline fragments (e.g., `unionFieldSelectionNeedsRewrite` / interface-side union cleanup paths). As a result, queries with nested union fragments can still skip required rewriting and produce incorrect plans. It also lacks the fuller recursive cleanup/flatten behavior from the intended change (notably union cleanup checks and robust nested object/union handling)."
},
"code_review": {
"status": "used",
"signal": "fail",
"evaluator_model": "codex-5.3",
"confidence": 0.81,
"issue_type": "unclear",
"source_field": "code_review",
"dimension_scores": {
"correctness": {
"score_0_4": 2,
"confidence_0_1": 0.85,
"rationale": "Patch fixes the interface-entity filtering return bug and adds some union-fragment flattening, but the union handling is incomplete versus the intended behavior and can drop valid selections when union member metadata is absent."
},
"edge_case_handling": {
"score_0_4": 1,
"confidence_0_1": 0.84,
"rationale": "Nested union handling is added, but object selections inside unions are copied verbatim rather than recursively normalized, which is weak for nested abstract-in-abstract fragment edge cases."
},
"introduced_bug_risk": {
"score_0_4": 2,
"confidence_0_1": 0.79,
"rationale": "New union flatten logic introduces branchy behavior tied to `unionMemberEntityNames/unionMemberTypeNames` and early returns, increasing risk of silently missing fragments in planner output."
},
"maintainability_idioms": {
"score_0_4": 2,
"confidence_0_1": 0.73,
"rationale": "Changes are localized and readable, but they add special-case fallback logic and partial handling paths rather than the more systematic cleanup/flattening approach expected for long-term planner maintenance."
}
},
"findings": [
{
"id": "f1",
"dimension": "correctness",
"severity": "major",
"title": "Union flattening can discard valid fragments when union member lists are empty",
"detail": "The new `flattenFragmentOnUnion` returns immediately if both `unionMemberEntityNames` and `unionMemberTypeNames` are empty. That can drop a valid inline union fragment selection instead of rewriting it using parent-allowed types.",
"confidence_0_1": 0.87,
"citations": [
{
"path": "v2/pkg/engine/plan/abstract_selection_rewriter.go",
"side": "new",
"start_line": 456,
"end_line": 463,
"anchor_kind": "diff",
"head_sha": "ae9f57aca01c7c1e3b8175c487c46b8bb96fb0a9"
}
]
},
{
"id": "f2",
"dimension": "edge_case_handling",
"severity": "major",
"title": "Object fragments inside union fragments are copied instead of recursively flattened",
"detail": "Inside `flattenFragmentOnUnion`, object inline fragments are appended via `CopySelection` rather than being normalized recursively. Nested abstract fragments under those object branches may remain unrewritten in federated plans.",
"confidence_0_1": 0.82,
"citations": [
{
"path": "v2/pkg/engine/plan/abstract_selection_rewriter.go",
"side": "new",
"start_line": 482,
"end_line": 489,
"anchor_kind": "diff",
"head_sha": "ae9f57aca01c7c1e3b8175c487c46b8bb96fb0a9"
}
]
},
{
"id": "f3",
"dimension": "correctness",
"severity": "minor",
"title": "Object cleanup fix is partial for nested abstract fragments",
"detail": "The helper now validates parent-type membership, but the cleanup change is narrow and does not add corresponding union-fragment cleanup pathways, so nested union-in-object scenarios are still under-protected.",
"confidence_0_1": 0.71,
"citations": [
{
"path": "v2/pkg/engine/plan/abstract_selection_rewriter_helpers.go",
"side": "new",
"start_line": 168,
"end_line": 176,
"anchor_kind": "diff",
"head_sha": "ae9f57aca01c7c1e3b8175c487c46b8bb96fb0a9"
}
]
}
],
"overall": {
"confidence_overall": 0.81,
"summary": "Patch addresses two requested pieces (entity filtering bug and parent-type check for object fragments) and adds union flattening, but it likely does not fully satisfy the intended nested abstract-fragment behavior and carries notable edge-case risk."
},
"notes": "Patch addresses two requested pieces (entity filtering bug and parent-type check for object fragments) and adds union flattening, but it likely does not fully satisfy the intended nested abstract-fragment behavior and carries notable edge-case risk."
},
"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": 0.15927334080964062,
"flag": false,
"severe_flag": false
},
"cost": {
"status": "tokens_only",
"token_status": "present",
"cache_token_status": "present",
"total_input_tokens": 3401794,
"total_output_tokens": 68463,
"total_tokens": 3470257,
"uncached_input_tokens": 370626,
"cache_read_input_tokens": 3031168,
"cached_input_tokens": 3031168,
"total_cost_usd": 1.4213922,
"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": 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": 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": 3401794,
"tb_total_output_tokens": 68463,
"tb_total_tokens": 3470257,
"tb_uncached_input_tokens": 370626,
"tb_cache_creation_input_tokens": null,
"tb_cache_read_input_tokens": 3031168,
"tb_cached_input_tokens": 3031168,
"token_status": "present",
"cache_token_status": "present",
"token_source": "openai_cached_tokens_usage",
"task_cost": 1.4213922,
"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": 0.15927334080964062,
"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-1184/task_detail.v1.json",
"exists": true
},
"trajectory": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1184/trajectory.v1.json",
"exists": true,
"non_empty": true,
"size_bytes": 15378
},
"validation": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1184/validation.json",
"exists": true,
"non_empty": true,
"size_bytes": 173552
},
"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-1184/flux-pr-1184.1-of-1.2026-02-21__03-36-16__gpt-5-1-codex-mini/agent-logs/agent.patch",
"exists": true,
"non_empty": true,
"size_bytes": 5127
},
"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": 23450,
"sha256": "de907438d0c4ce9fc38e20cb9194ebbf86f18973dbbbb4a95457a9f4a80e022e",
"required_for_rescue": true
},
"repo_tarball": {
"exists": true,
"non_empty": true,
"size_bytes": 4281607,
"sha256": "122b56b076b160f5c1ff920fbf5b851dae1433b3718824dc611b0858cb4a222e",
"required_for_rescue": true
},
"agent_patch": {
"exists": true,
"non_empty": true,
"size_bytes": 5127,
"sha256": "566ab760de2860314fdf0cb71fa14f987dde9322993db6befe8156c039900a03",
"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
}
]
}
}