task_detail
validation/gpt-5-3-codex/flux-pr-1308/task_detail.v1.json
17599 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-1308",
"trial_name": "flux-pr-1308.1-of-1.2026-02-28__13-38-10__gpt-5-3-codex"
},
"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-1308.1-of-1.validate-gold-1772290855737709000",
"gold_failure_mode": "unset",
"agent_outcome": "pass",
"agent_tb_trial_name": "flux-pr-1308.1-of-1.validate-override-1772290913361619000",
"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-1308.1-of-1.2026-02-28__13-38-10__gpt-5-3-codex",
"is_resolved": true,
"failure_mode": "unset",
"duration_sec": 117.294286833,
"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": 0.84,
"issue_type": "behavioral",
"notes": "The patch appears to add schema/introspection surface changes and some operation-level/error-location updates, but it does not clearly implement the full required behavior, especially OneOf enforcement in runtime variable validation (`variablesvalidation`) and directive exposure in all expected introspection outputs. It also introduces `isOneOf`-centric introspection changes that differ from the stated intent of exposing the `@oneOf` directive itself."
},
"code_review": {
"status": "used",
"signal": "fail",
"confidence": 0.9,
"issue_type": "unclear",
"source_field": "code_review",
"dimension_scores": {
"correctness": {
"score_0_4": 1,
"confidence_0_1": 0.92,
"rationale": "The patch diverges materially from the requested OneOf directive behavior: it adds schema tokens and introspection fields, but the shown validation core change in Values is only a constant declaration and does not implement OneOf runtime/operation checks expected by the task."
},
"edge_case_handling": {
"score_0_4": 0,
"confidence_0_1": 0.86,
"rationale": "The visible implementation does not show the required OneOf edge-case enforcement (exactly one field, non-null value, nullable-variable handling at operation/variables runtime), indicating substantial missing edge-case logic."
},
"introduced_bug_risk": {
"score_0_4": 1,
"confidence_0_1": 0.88,
"rationale": "The patch alters introspection shape by adding `isOneOf` to `__Type` selection/fixtures, which is a compatibility-risky API surface change and not aligned with the requested directive exposure path."
},
"maintainability_idioms": {
"score_0_4": 2,
"confidence_0_1": 0.79,
"rationale": "There is some test coverage added, but the implementation direction mixes schema directive support with introspection-structure changes (`isOneOf`) and message variants, which increases long-term maintenance and spec-alignment burden."
}
},
"findings": [
{
"id": "f1",
"dimension": "correctness",
"severity": "major",
"title": "OneOf validation logic appears missing in Values rule",
"detail": "The shown change in `operation_rule_values.go` only introduces a directive-name constant and does not include OneOf enforcement (exactly one field, non-null, nullable-variable checks) required by the task.",
"confidence_0_1": 0.93,
"citations": [
{
"path": "v2/pkg/astvalidation/operation_rule_values.go",
"side": "new",
"start_line": 11,
"end_line": 13,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
}
]
},
{
"id": "f2",
"dimension": "correctness",
"severity": "major",
"title": "Introspection change targets `isOneOf` field rather than directive exposure",
"detail": "The patch modifies `__Type` selections/fixtures to include `isOneOf`; requested behavior is to expose/support `@oneOf` as a built-in directive in schema/introspection, so this is likely misaligned with intended API output.",
"confidence_0_1": 0.9,
"citations": [
{
"path": "v2/pkg/engine/datasource/introspection_datasource/config_factory.go",
"side": "new",
"start_line": 71,
"end_line": 74,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
},
{
"path": "v2/pkg/engine/datasource/introspection_datasource/fixtures/type_introspection.golden",
"side": "new",
"start_line": 55,
"end_line": 60,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
}
]
},
{
"id": "f3",
"dimension": "edge_case_handling",
"severity": "major",
"title": "No visible runtime variables-level OneOf enforcement",
"detail": "The task requires validation at runtime variables level as well; the provided diff excerpt does not show corresponding `variablesvalidation` OneOf checks, leaving key edge cases uncovered.",
"confidence_0_1": 0.82,
"citations": [
{
"path": "v2/pkg/astvalidation/operation_rule_values.go",
"side": "new",
"start_line": 11,
"end_line": 13,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
},
{
"path": "v2/pkg/astvalidation/operation_rule_oneof_test.go",
"side": "new",
"start_line": 14,
"end_line": 54,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
}
]
},
{
"id": "f4",
"dimension": "introduced_bug_risk",
"severity": "major",
"title": "Base schema OneOf directive lacks descriptive block expected by fixtures/introspection",
"detail": "The directive is added without the descriptive doc string, which can desynchronize generated schema/introspection descriptions from expected outputs and reduce compatibility with existing golden expectations.",
"confidence_0_1": 0.76,
"citations": [
{
"path": "v2/pkg/asttransform/baseschema.go",
"side": "new",
"start_line": 168,
"end_line": 172,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
},
{
"path": "v2/pkg/asttransform/fixtures/complete.golden",
"side": "new",
"start_line": 57,
"end_line": 61,
"anchor_kind": "diff",
"head_sha": "49b8a69cab1c77b398a71c157a5d051ebd3e2ee8"
}
]
}
],
"overall": {
"confidence_overall": 0.9,
"summary": "The patch appears only partially aligned and likely does not satisfy the intended OneOf feature set end-to-end; core validation behavior and introspection direction differ from the requested change."
},
"notes": "The patch appears only partially aligned and likely does not satisfy the intended OneOf feature set end-to-end; core validation behavior and introspection direction differ from the requested change."
},
"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": "medium",
"score": 0.6463775438172967,
"flag": false,
"severe_flag": false
},
"cost": {
"status": "tokens_only",
"token_status": "present",
"cache_token_status": "present",
"total_input_tokens": 5994908,
"total_output_tokens": 18102,
"total_tokens": 6013010,
"uncached_input_tokens": 123292,
"cache_read_input_tokens": 5871616,
"cached_input_tokens": 5871616,
"total_cost_usd": 11.742924,
"token_source": "openai_cached_tokens_usage",
"pricing_model_key": "gpt-5.3-codex",
"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": 5994908,
"tb_total_output_tokens": 18102,
"tb_total_tokens": 6013010,
"tb_uncached_input_tokens": 123292,
"tb_cache_creation_input_tokens": null,
"tb_cache_read_input_tokens": 5871616,
"tb_cached_input_tokens": 5871616,
"token_status": "present",
"cache_token_status": "present",
"token_source": "openai_cached_tokens_usage",
"task_cost": 11.742924,
"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": 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": "medium",
"footprint_risk_score": 0.6463775438172967,
"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-1308/task_detail.v1.json",
"exists": true
},
"trajectory": {
"path": "validation/gpt-5-3-codex/flux-pr-1308/trajectory.v1.json",
"exists": true,
"non_empty": true,
"size_bytes": 15275
},
"validation": {
"path": "validation/gpt-5-3-codex/flux-pr-1308/validation.json",
"exists": true,
"non_empty": true,
"size_bytes": 231599
},
"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-1308/flux-pr-1308.1-of-1.2026-02-28__13-38-10__gpt-5-3-codex/agent-logs/agent.patch",
"exists": true,
"non_empty": true,
"size_bytes": 79246
},
"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": 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": {
"path": "runs/2026-02-28__13-38-10__gpt-5-3-codex/flux-pr-1308/flux-pr-1308.1-of-1.2026-02-28__13-38-10__gpt-5-3-codex/agent-logs/agent.patch",
"exists": true,
"non_empty": true,
"size_bytes": 79246,
"sha256": "531e6840ddd16538f677939626c248194730ec6e4ba6627e91bca787772ea10d",
"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
}
]
}
}