task_detail
validation/gpt-5-1-codex-mini/flux-pr-1297/task_detail.v1.json
16607 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": "2026-02-28__13-38-10__gpt-5-1-codex-mini",
"task_id": "flux-pr-1297",
"trial_name": "flux-pr-1297.1-of-1.2026-02-28__13-38-10__gpt-5-1-codex-mini"
},
"decision": {
"status": "pass",
"primary_signal": "tests",
"matrix_status": "pass_with_warn",
"reason_codes": [
"primary_tests",
"tests_passed",
"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-1297.1-of-1.validate-gold-1772298860208513000",
"gold_failure_mode": "unset",
"agent_outcome": "pass",
"agent_tb_trial_name": "flux-pr-1297.1-of-1.validate-override-1772298932432908000",
"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-1297.1-of-1.2026-02-28__13-38-10__gpt-5-1-codex-mini",
"is_resolved": true,
"failure_mode": "unset",
"duration_sec": 133.69969075,
"time_budget_sec": 1200
},
"cache": {
"cache_hit": false,
"cache_miss_reason": "missing_pinned_dependencies",
"environment_group_id": "eg_46b6a6c82a4890b6e6e87c39575fd02c"
}
},
"quality": {
"equivalence": {
"status": "used",
"outcome": "non_equivalent",
"confidence": 0.94,
"issue_type": "behavioral",
"notes": "The agent patch only taints entities based on any `_entities` error path index, without validating that the failed field is an optional/nullable external `@requires` dependency. It does not add the planning/fetch-reason metadata needed to distinguish `@requires` nullable dependencies, so behavior is over-broad (can drop entities for unrelated errors) and misses the core intent of targeted validation."
},
"code_review": {
"status": "used",
"signal": "fail",
"confidence": 0.86,
"issue_type": "unclear",
"source_field": "code_review",
"dimension_scores": {
"correctness": {
"score_0_4": 1,
"confidence_0_1": 0.88,
"rationale": "The patch detects tainted entities from any `_entities` error path index, but it does not verify that the failing field is a nullable external field actually used by `@requires`, so behavior can diverge from the requested semantics and exclude valid entities."
},
"edge_case_handling": {
"score_0_4": 1,
"confidence_0_1": 0.84,
"rationale": "Edge filtering is broad and not tied to dependency metadata; any `_entities` error path with index is treated as missing requires dependency, regardless of field or nullability context."
},
"introduced_bug_risk": {
"score_0_4": 1,
"confidence_0_1": 0.83,
"rationale": "Nulling entities based solely on `_entities` path index can over-filter in mixed error scenarios, and `markAll` nulls the merged value for entity fetches whenever any taint is found."
},
"maintainability_idioms": {
"score_0_4": 2,
"confidence_0_1": 0.72,
"rationale": "The change introduces a local execution option and ad-hoc error parsing in loader, but does not show corresponding planner/metadata wiring, making long-term behavior coupling unclear."
}
},
"findings": [
{
"id": "f1",
"dimension": "correctness",
"severity": "major",
"title": "Taint detection is not scoped to nullable `@requires` dependencies",
"detail": "Detection marks entities tainted from any `_entities` error path index and does not validate that the failed field corresponds to a nullable external field used by `@requires`. This can exclude entities for unrelated subgraph errors.",
"confidence_0_1": 0.92,
"citations": [
{
"path": "app/v2/pkg/engine/resolve/loader.go",
"side": "new",
"start_line": 735,
"end_line": 786,
"anchor_kind": "diff",
"head_sha": "2d9a2364bc9ce642ff5909f080f159fc4340e1b3"
}
]
},
{
"id": "f2",
"dimension": "introduced_bug_risk",
"severity": "major",
"title": "Entity fetch result can be nulled too aggressively",
"detail": "For single entity fetches, `markAll` causes the merged value to become null when taint is detected, but taint itself is derived from broad path matching. This risks dropping valid entity data in partial-error responses.",
"confidence_0_1": 0.85,
"citations": [
{
"path": "app/v2/pkg/engine/resolve/loader.go",
"side": "new",
"start_line": 625,
"end_line": 631,
"anchor_kind": "diff",
"head_sha": "2d9a2364bc9ce642ff5909f080f159fc4340e1b3"
},
{
"path": "app/v2/pkg/engine/resolve/loader.go",
"side": "new",
"start_line": 791,
"end_line": 794,
"anchor_kind": "diff",
"head_sha": "2d9a2364bc9ce642ff5909f080f159fc4340e1b3"
}
]
},
{
"id": "f3",
"dimension": "maintainability_idioms",
"severity": "major",
"title": "Feature gating is introduced only as execution option without visible planner-level dependency metadata integration",
"detail": "The new option is wired through execution context, but the patch excerpt does not show corresponding planner/fetch-reason metadata changes needed to precisely identify required external nullable dependencies, making behavior brittle and hard to reason about.",
"confidence_0_1": 0.74,
"citations": [
{
"path": "app/execution/engine/execution_engine.go",
"side": "new",
"start_line": 113,
"end_line": 117,
"anchor_kind": "diff",
"head_sha": "2d9a2364bc9ce642ff5909f080f159fc4340e1b3"
},
{
"path": "app/v2/pkg/engine/resolve/context.go",
"side": "new",
"start_line": 41,
"end_line": 42,
"anchor_kind": "diff",
"head_sha": "2d9a2364bc9ce642ff5909f080f159fc4340e1b3"
}
]
}
],
"overall": {
"confidence_overall": 0.86,
"summary": "The patch appears to pass tests but likely does not fully satisfy the intended change: it implements broad `_entities` error-index tainting rather than validating nullable external `@requires` dependencies, creating meaningful correctness and over-filtering risk."
},
"notes": "The patch appears to pass tests but likely does not fully satisfy the intended change: it implements broad `_entities` error-index tainting rather than validating nullable external `@requires` dependencies, creating meaningful correctness and over-filtering risk."
},
"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": 0.11589991203175924,
"flag": false,
"severe_flag": false
},
"cost": {
"status": "tokens_only",
"token_status": "present",
"cache_token_status": "present",
"total_input_tokens": 13392580,
"total_output_tokens": 47979,
"total_tokens": 13440559,
"uncached_input_tokens": 1389892,
"cache_read_input_tokens": 12002688,
"cached_input_tokens": 12002688,
"total_cost_usd": 4.1731152,
"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": true,
"tb_failure_mode": "unset",
"tb_total_input_tokens": 13392580,
"tb_total_output_tokens": 47979,
"tb_total_tokens": 13440559,
"tb_uncached_input_tokens": 1389892,
"tb_cache_creation_input_tokens": null,
"tb_cache_read_input_tokens": 12002688,
"tb_cached_input_tokens": 12002688,
"token_status": "present",
"cache_token_status": "present",
"token_source": "openai_cached_tokens_usage",
"task_cost": 4.1731152,
"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": 0.11589991203175924,
"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__13-38-10__gpt-5-1-codex-mini",
"passRate": 0.9655172413793104,
"ciLow": 0.896551724137931,
"ciHigh": 1,
"effectiveN": 29,
"tier": 1,
"validation_counts": {
"fail_guardrail": 0,
"fail_high_conf": 0,
"fail_infra": 1,
"fail_likely_equiv": 0,
"fail_with_diag": 0,
"missing": 0,
"pass": 2,
"pass_with_warn": 26
}
},
"run_metadata": {
"agent_name": "codex",
"model_name": "gpt-5.1-codex-mini",
"start_time": "2026-02-28T15:13:02.887835+00:00",
"end_time": "2026-02-28T16:42:40.244280+00:00",
"commit_hash": "99ae882e59281de74856a3e7eeb1b7c986b466af",
"accuracy": 0.6896551724137931,
"reasoning_effort": "medium"
}
},
"evidence": {
"task_detail": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1297/task_detail.v1.json",
"exists": true
},
"trajectory": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1297/trajectory.v1.json",
"exists": true,
"non_empty": true,
"size_bytes": 15393
},
"validation": {
"path": "validation/gpt-5-1-codex-mini/flux-pr-1297/validation.json",
"exists": true,
"non_empty": true,
"size_bytes": 131687
},
"results": {
"path": "runs/2026-02-28__13-38-10__gpt-5-1-codex-mini/results.json",
"exists": true,
"non_empty": true,
"size_bytes": 57447
},
"run_metadata": {
"path": "runs/2026-02-28__13-38-10__gpt-5-1-codex-mini/run_metadata.json",
"exists": true,
"non_empty": true,
"size_bytes": 1645
},
"agent_patch": {
"path": "runs/2026-02-28__13-38-10__gpt-5-1-codex-mini/flux-pr-1297/flux-pr-1297.1-of-1.2026-02-28__13-38-10__gpt-5-1-codex-mini/agent-logs/agent.patch",
"exists": true,
"non_empty": true,
"size_bytes": 6473
},
"summary": {
"path": "reports/summary.json",
"exists": true,
"non_empty": true,
"size_bytes": 269968
},
"manifest": {
"path": "manifest.json",
"exists": true,
"non_empty": true,
"size_bytes": 677
},
"validation_inputs": {
"required_for_rescue_ok": true,
"gold_patch": {
"exists": true,
"non_empty": true,
"size_bytes": 33111,
"sha256": "dca574ebbbbc28305087866b6d1516bd622c9155da542736fe135ea864dda233",
"required_for_rescue": true
},
"repo_tarball": {
"exists": true,
"non_empty": true,
"size_bytes": 4042243,
"sha256": "c1e6e0fec74700b00abd45c660d3fd7b6b8ea69027c6a5091cbb059ff394ec33",
"required_for_rescue": true
},
"agent_patch": {
"path": "runs/2026-02-28__13-38-10__gpt-5-1-codex-mini/flux-pr-1297/flux-pr-1297.1-of-1.2026-02-28__13-38-10__gpt-5-1-codex-mini/agent-logs/agent.patch",
"exists": true,
"non_empty": true,
"size_bytes": 6473,
"sha256": "d3506e6c4bd33c74ea9823ab92be459988afc7bb5fbc66e7bcf25704e115a25f",
"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
}
]
}
}