task_detail
validation/gpt-5-3-codex/flux-pr-1293/task_detail.v1.json
16214 bytes
{
"version": "v1",
"materialization": {
"mode": "canonical"
},
"identity": {
"variant_id": "gpt-5.3-codex",
"requested_model": "gpt-5.3-codex",
"model_key": "gpt-5-3-codex",
"run_id": "2026-02-28__13-38-10__gpt-5-3-codex",
"task_id": "flux-pr-1293",
"trial_name": "flux-pr-1293.1-of-1.2026-02-28__13-38-10__gpt-5-3-codex"
},
"decision": {
"status": "fail",
"primary_signal": "tests",
"matrix_status": "fail_high_conf",
"reason_codes": [
"primary_tests",
"tests_failed",
"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": "fail",
"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-1293.1-of-1.validate-gold-1772290689599159000",
"gold_failure_mode": "unset",
"agent_outcome": "fail",
"agent_tb_trial_name": "flux-pr-1293.1-of-1.validate-override-1772290806502963000",
"agent_failure_mode": "unset",
"agent_retried": false
}
],
"partial_score": {
"score": 0,
"denominator": 1,
"level": "command",
"provenance": "fallback_command_level",
"reason": "test_case_detail_unavailable"
},
"tb": {
"trial_name": "flux-pr-1293.1-of-1.2026-02-28__13-38-10__gpt-5-3-codex",
"is_resolved": false,
"failure_mode": "unset",
"duration_sec": 166.726058041,
"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": 0.74,
"issue_type": "behavioral",
"notes": "The patch only partially implements the intended refactor. It adds `BuildFetchReasons` and moves some metadata into `FetchInfo`, but it does not complete the centralization: `resolve.Fetch` API appears to retain old reason/dependency access patterns, loader propagation is handled via concrete-type switching instead of uniformly via `FetchInfo`, and the full planner-side separation/filtering path (including datasource-driven propagated subset handling) is not clearly implemented end-to-end. This misses core intent beyond stylistic differences."
},
"code_review": {
"status": "used",
"signal": "fail",
"confidence": 0.8,
"issue_type": "unclear",
"source_field": "code_review",
"dimension_scores": {
"correctness": {
"score_0_4": 1,
"confidence_0_1": 0.82,
"rationale": "The patch only partially applies the metadata refactor and introduces behavior that can silently skip propagation for unhandled fetch variants by hard-coding concrete type checks in the loader instead of using a unified fetch-info API."
},
"edge_case_handling": {
"score_0_4": 1,
"confidence_0_1": 0.74,
"rationale": "Edge cases around planner flags are not robustly handled: FetchInfo can be created as an empty struct when include-info is disabled, and propagation depends on explicit concrete types."
},
"introduced_bug_risk": {
"score_0_4": 1,
"confidence_0_1": 0.78,
"rationale": "Risk is high because propagation logic is duplicated via a type switch and the planner now conditionally constructs partial FetchInfo, which increases chances of inconsistent runtime behavior."
},
"maintainability_idioms": {
"score_0_4": 2,
"confidence_0_1": 0.76,
"rationale": "The change moves some metadata into FetchInfo, but keeps compatibility-style methods and introduces concrete-type branching, which works against the intended centralization and clean abstraction."
}
},
"findings": [
{
"id": "f1",
"dimension": "correctness",
"severity": "major",
"title": "Fetch-reason propagation is hard-coded to specific concrete fetch types",
"detail": "The loader now uses a type switch over a few fetch structs to read `Info.PropagatedFetchReasons`. Any fetch kind not listed will silently skip propagation, which is brittle and diverges from the intended unified metadata access.",
"confidence_0_1": 0.88,
"citations": [
{
"path": "v2/pkg/engine/resolve/loader.go",
"side": "new",
"start_line": 1601,
"end_line": 1623,
"anchor_kind": "diff",
"head_sha": "4c2d0aa25474f60c759d568ef647823ef245d035"
}
]
},
{
"id": "f2",
"dimension": "edge_case_handling",
"severity": "major",
"title": "Planner can emit partially populated FetchInfo",
"detail": "When field dependencies are enabled but include-info is disabled, `configureFetch` allocates `FetchInfo{}` and fills only dependency/reason fields. This creates a non-nil but incomplete metadata object, which can cause inconsistent downstream assumptions.",
"confidence_0_1": 0.79,
"citations": [
{
"path": "v2/pkg/engine/plan/visitor.go",
"side": "new",
"start_line": 1338,
"end_line": 1347,
"anchor_kind": "diff",
"head_sha": "4c2d0aa25474f60c759d568ef647823ef245d035"
}
]
},
{
"id": "f3",
"dimension": "maintainability_idioms",
"severity": "major",
"title": "Refactor remains mixed between old and new metadata access patterns",
"detail": "SingleFetch methods still expose legacy-style coordinate/reason access, while loader bypasses polymorphism via type switching. This mixed model undermines the intended centralization around a single `FetchInfo` contract.",
"confidence_0_1": 0.73,
"citations": [
{
"path": "v2/pkg/engine/resolve/fetch.go",
"side": "new",
"start_line": 102,
"end_line": 114,
"anchor_kind": "diff",
"head_sha": "4c2d0aa25474f60c759d568ef647823ef245d035"
},
{
"path": "v2/pkg/engine/resolve/loader.go",
"side": "new",
"start_line": 1601,
"end_line": 1623,
"anchor_kind": "diff",
"head_sha": "4c2d0aa25474f60c759d568ef647823ef245d035"
}
]
}
],
"overall": {
"confidence_overall": 0.8,
"summary": "The patch appears incomplete versus the intended refactor: it introduces parts of FetchInfo centralization but keeps brittle, concrete-type-based propagation and partial metadata construction paths, so it likely does not fully satisfy the task."
},
"notes": "The patch appears incomplete versus the intended refactor: it introduces parts of FetchInfo centralization but keeps brittle, concrete-type-based propagation and partial metadata construction paths, so it likely does not fully satisfy the task."
},
"behavioral_robustness": {
"status": "used",
"probe_status": "used",
"gold_pass_candidate_fail_count": 1,
"agreement_rate": 0,
"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": 0.30310009516125536,
"flag": false,
"severe_flag": false
},
"cost": {
"status": "tokens_only",
"token_status": "present",
"cache_token_status": "present",
"total_input_tokens": 4303725,
"total_output_tokens": 18867,
"total_tokens": 4322592,
"uncached_input_tokens": 101485,
"cache_read_input_tokens": 4202240,
"cached_input_tokens": 4202240,
"total_cost_usd": 8.957655,
"token_source": "openai_cached_tokens_usage",
"pricing_model_key": "gpt-5.3-codex",
"pricing_mode": "cache_aware"
}
},
"summary": {
"task": {
"matrix_status": "fail_high_conf",
"tests_outcome": "fail",
"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": 0,
"probe_gold_pass_candidate_pass_count": null,
"probe_gold_pass_candidate_fail_count": 1,
"probe_review_required_count": null,
"flags": [
"equiv_warn",
"review_warn"
],
"tb_is_resolved": false,
"tb_failure_mode": "unset",
"tb_total_input_tokens": 4303725,
"tb_total_output_tokens": 18867,
"tb_total_tokens": 4322592,
"tb_uncached_input_tokens": 101485,
"tb_cache_creation_input_tokens": null,
"tb_cache_read_input_tokens": 4202240,
"tb_cached_input_tokens": 4202240,
"token_status": "present",
"cache_token_status": "present",
"token_source": "openai_cached_tokens_usage",
"task_cost": 8.957655,
"cost_status": "present",
"cost_pricing_mode": "cache_aware",
"pricing_model_key": "gpt-5.3-codex",
"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": 0,
"rescue_aware_outcome": 0,
"partial_score": 0,
"partial_score_numerator": 0,
"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": 0.30310009516125536,
"footprint_risk_flag": false,
"footprint_risk_severe_flag": false
},
"run": {
"model": "gpt-5.3-codex",
"requested_model": "gpt-5.3-codex",
"run_id": "2026-02-28__13-38-10__gpt-5-3-codex",
"passRate": 0.9310344827586207,
"ciLow": 0.8275862068965517,
"ciHigh": 1,
"effectiveN": 29,
"tier": 1,
"validation_counts": {
"fail_guardrail": 0,
"fail_high_conf": 1,
"fail_infra": 0,
"fail_likely_equiv": 1,
"fail_with_diag": 0,
"missing": 0,
"pass": 6,
"pass_with_warn": 21
}
},
"run_metadata": {
"agent_name": "codex",
"model_name": "gpt-5.3-codex",
"start_time": "2026-02-28T13:38:12.733292+00:00",
"end_time": "2026-02-28T14:43:03.470912+00:00",
"commit_hash": "99ae882e59281de74856a3e7eeb1b7c986b466af",
"accuracy": 0.896551724137931,
"reasoning_effort": "medium"
}
},
"evidence": {
"task_detail": {
"path": "validation/gpt-5-3-codex/flux-pr-1293/task_detail.v1.json",
"exists": true
},
"trajectory": {
"path": "validation/gpt-5-3-codex/flux-pr-1293/trajectory.v1.json",
"exists": true,
"non_empty": true,
"size_bytes": 15254
},
"validation": {
"path": "validation/gpt-5-3-codex/flux-pr-1293/validation.json",
"exists": true,
"non_empty": true,
"size_bytes": 146120
},
"results": {
"path": "runs/2026-02-28__13-38-10__gpt-5-3-codex/results.json",
"exists": true,
"non_empty": true,
"size_bytes": 62248
},
"run_metadata": {
"path": "runs/2026-02-28__13-38-10__gpt-5-3-codex/run_metadata.json",
"exists": true,
"non_empty": true,
"size_bytes": 1634
},
"agent_patch": {
"path": "runs/2026-02-28__13-38-10__gpt-5-3-codex/flux-pr-1293/flux-pr-1293.1-of-1.2026-02-28__13-38-10__gpt-5-3-codex/agent-logs/agent.patch",
"exists": true,
"non_empty": true,
"size_bytes": 32332
},
"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": 26980,
"sha256": "f16e327c81b387c2e64df3bfbece7ffeb3f0f49415b647caf9a813ed52a36099",
"required_for_rescue": true
},
"repo_tarball": {
"exists": true,
"non_empty": true,
"size_bytes": 4040634,
"sha256": "7bf69fc2f752dd605115fbbd3e22d0743a4eb14144b49b03008eb3fba1fa4699",
"required_for_rescue": true
},
"agent_patch": {
"path": "runs/2026-02-28__13-38-10__gpt-5-3-codex/flux-pr-1293/flux-pr-1293.1-of-1.2026-02-28__13-38-10__gpt-5-3-codex/agent-logs/agent.patch",
"exists": true,
"non_empty": true,
"size_bytes": 32332,
"sha256": "61ff37869205e9f2f5f212aefb5aa73c90b3b7c681a05c431edfc91b7f539f42",
"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
}
]
}
}