devlyn-cli 3.2.1 → 3.3.0

package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/F21-cli-scheduler-priority/l2_risk_probes/result.json

@@ -1,32 +0,0 @@
-{
-  "fixture": "F21-cli-scheduler-priority",
-  "arm": "l2_risk_probes",
-  "run_id": "20260511-f21-current-riskprobes-v1",
-  "disqualifier": false,
-  "oracle_disqualifier": false,
-  "oracle_findings_count": 0,
-  "verify_score": 1.0,
-  "commands_passed": 3,
-  "commands_total": 3,
-  "diff_bytes": 14846,
-  "files_changed": 2,
-  "elapsed_seconds": 1112,
-  "timed_out": false,
-  "environment_contamination": false,
-  "environment_contamination_reason": null,
-  "invoke_exit": 0,
-  "invoke_failure": false,
-  "invoke_failure_reason": null,
-  "terminal_verdict": "PASS",
-  "verify_verdict": "PASS",
-  "pair_trigger": {
-    "eligible": true,
-    "reasons": [
-      "complexity.high",
-      "risk_profile.high_risk",
-      "risk_probes_enabled"
-    ],
-    "skipped_reason": null
-  },
-  "pair_mode": true
-}

package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/full-pipeline-pair-gate.json

@@ -1,44 +0,0 @@
-{
-  "run_id": "20260511-f21-current-riskprobes-v1",
-  "rule": "headroom candidates only; bare headroom >= 5; solo_claude headroom >= 5; l2_risk_probes must be evidence-clean, pair_mode true, pair_trigger eligible with a canonical reason, and beat solo_claude by the configured margin",
-  "verdict": "PASS",
-  "fixtures_total": 1,
-  "fixtures_passed": 1,
-  "min_fixtures": 1,
-  "fixture_count_ok": true,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "min_pair_margin": 5,
-  "pair_arm": "l2_risk_probes",
-  "max_pair_solo_wall_ratio": 3.0,
-  "require_hypothesis_trigger": false,
-  "max_observed_pair_solo_wall_ratio": 1.4728476821192054,
-  "avg_pair_margin": 33.0,
-  "avg_pair_solo_wall_ratio": 1.4728476821192054,
-  "rows": [
-    {
-      "fixture": "F21-cli-scheduler-priority",
-      "status": "PASS",
-      "bare_score": 33,
-      "bare_headroom": 27,
-      "solo_score": 66,
-      "solo_headroom": 14,
-      "pair_score": 99,
-      "pair_margin": 33,
-      "pair_mode": true,
-      "pair_trigger_eligible": true,
-      "pair_trigger_reasons": [
-        "complexity.high",
-        "risk.high",
-        "risk_probes.enabled",
-        "spec.solo_headroom_hypothesis"
-      ],
-      "pair_trigger_has_canonical_reason": true,
-      "pair_trigger_has_hypothesis_reason": true,
-      "pair_solo_wall_ratio": 1.4728476821192054,
-      "reason": ""
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/full-pipeline-pair-gate.md

@@ -1,16 +0,0 @@
-# Full-Pipeline Pair Gate - 20260511-f21-current-riskprobes-v1
-
-Verdict: **PASS**
-
-Fixtures passed: 1/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60; bare headroom >= 5; solo_claude <= 80; solo_claude headroom >= 5; l2_risk_probes evidence-clean; pair_mode true; pair_trigger eligible with canonical reason; l2_risk_probes - solo_claude >= 5.
-Average pair margin: +33.0
-Allowed pair/solo wall ratio: 3.00x
-Maximum observed pair/solo wall ratio: 1.47x
-Average pair/solo wall ratio: 1.47x
-Hypothesis trigger required: false
-
-| Fixture | Bare | Bare headroom | Solo_claude | Solo_claude headroom | Pair | Margin | Pair mode | Hypothesis trigger | Triggers | Wall ratio | Status | Reason |
-|---|---:|---:|---:|---:|---:|---:|---|---|---|---:|---|---|
-| F21-cli-scheduler-priority | 33 | 27 | 66 | 14 | 99 | +33 | true | true | complexity.high,risk.high,risk_probes.enabled,spec.solo_headroom_hypothesis | 1.47x | PASS |  |

package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/headroom-gate.json

@@ -1,18 +0,0 @@
-{
-  "run_id": "20260511-f21-current-riskprobes-v1",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 and solo_claude <= 80, with both arms clean",
-  "verdict": "PASS",
-  "fixtures_total": 1,
-  "fixtures_passed": 1,
-  "min_fixtures": 1,
-  "fixture_count_ok": true,
-  "rows": [
-    {
-      "fixture": "F21-cli-scheduler-priority",
-      "status": "PASS",
-      "bare_score": 33,
-      "solo_score": 66,
-      "reason": ""
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/headroom-gate.md

@@ -1,9 +0,0 @@
-# Headroom Gate — 20260511-f21-current-riskprobes-v1
-
-Verdict: **PASS**
-
-Rule: at least 1 fixtures; bare <= 60, solo_claude <= 80, both arms clean.
-
-| Fixture | Bare | Solo | Status | Reason |
-|---|---:|---:|---|---|
-| F21-cli-scheduler-priority | 33 | 66 | PASS |  |

package/benchmark/auto-resolve/results/20260511-f3-http-error-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260511-f3-http-error-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": -37.0,
-  "min_bare_headroom": -37,
-  "avg_solo_headroom": -19.0,
-  "min_solo_headroom": -19,
-  "rows": [
-    {
-      "fixture": "F3-backend-contract-risk",
-      "status": "FAIL",
-      "bare_score": 97,
-      "solo_score": 99,
-      "bare_headroom": -37,
-      "solo_headroom": -19,
-      "reason": "bare score 97 > 60; solo_claude score 99 > 80"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260511-f3-http-error-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260511-f3-http-error-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: -37.0
-Minimum bare headroom: -37
-Average solo headroom: -19.0
-Minimum solo headroom: -19
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F3-backend-contract-risk | 97 | -37 | 99 | -19 | FAIL | bare score 97 > 60; solo_claude score 99 > 80 |

package/benchmark/auto-resolve/results/20260512-f2-medium-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260512-f2-medium-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": -23.0,
-  "min_bare_headroom": -23,
-  "avg_solo_headroom": -15.0,
-  "min_solo_headroom": -15,
-  "rows": [
-    {
-      "fixture": "F2-cli-medium-subcommand",
-      "status": "FAIL",
-      "bare_score": 83,
-      "solo_score": 95,
-      "bare_headroom": -23,
-      "solo_headroom": -15,
-      "reason": "bare score 83 > 60; solo_claude score 95 > 80"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260512-f2-medium-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260512-f2-medium-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: -23.0
-Minimum bare headroom: -23
-Average solo headroom: -15.0
-Minimum solo headroom: -15
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F2-cli-medium-subcommand | 83 | -23 | 95 | -15 | FAIL | bare score 83 > 60; solo_claude score 95 > 80 |

package/benchmark/auto-resolve/results/20260512-f31-seat-rebalance-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260512-f31-seat-rebalance-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": 27.0,
-  "min_bare_headroom": 27,
-  "avg_solo_headroom": -18.0,
-  "min_solo_headroom": -18,
-  "rows": [
-    {
-      "fixture": "F31-cli-seat-rebalance",
-      "status": "FAIL",
-      "bare_score": 33,
-      "solo_score": 98,
-      "bare_headroom": 27,
-      "solo_headroom": -18,
-      "reason": "solo_claude score 98 > 80; bare judge disqualifier; bare result disqualifier; bare verify disqualifier"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260512-f31-seat-rebalance-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260512-f31-seat-rebalance-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: 27.0
-Minimum bare headroom: 27
-Average solo headroom: -18.0
-Minimum solo headroom: -18
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F31-cli-seat-rebalance | 33 | 27 | 98 | -18 | FAIL | solo_claude score 98 > 80; bare judge disqualifier; bare result disqualifier; bare verify disqualifier |

package/benchmark/auto-resolve/results/20260512-f32-subscription-renewal-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260512-f32-subscription-renewal-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": 27.0,
-  "min_bare_headroom": 27,
-  "avg_solo_headroom": -18.0,
-  "min_solo_headroom": -18,
-  "rows": [
-    {
-      "fixture": "F32-cli-subscription-renewal",
-      "status": "FAIL",
-      "bare_score": 33,
-      "solo_score": 98,
-      "bare_headroom": 27,
-      "solo_headroom": -18,
-      "reason": "solo_claude score 98 > 80"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260512-f32-subscription-renewal-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260512-f32-subscription-renewal-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: 27.0
-Minimum bare headroom: 27
-Average solo headroom: -18.0
-Minimum solo headroom: -18
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F32-cli-subscription-renewal | 33 | 27 | 98 | -18 | FAIL | solo_claude score 98 > 80 |

package/benchmark/auto-resolve/results/20260512-f4-web-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260512-f4-web-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": -10.0,
-  "min_bare_headroom": -10,
-  "avg_solo_headroom": -12.0,
-  "min_solo_headroom": -12,
-  "rows": [
-    {
-      "fixture": "F4-web-browser-design",
-      "status": "FAIL",
-      "bare_score": 70,
-      "solo_score": 92,
-      "bare_headroom": -10,
-      "solo_headroom": -12,
-      "reason": "bare score 70 > 60; solo_claude score 92 > 80; bare judge disqualifier; bare result disqualifier; bare verify disqualifier"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260512-f4-web-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260512-f4-web-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: -10.0
-Minimum bare headroom: -10
-Average solo headroom: -12.0
-Minimum solo headroom: -12
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F4-web-browser-design | 70 | -10 | 92 | -12 | FAIL | bare score 70 > 60; solo_claude score 92 > 80; bare judge disqualifier; bare result disqualifier; bare verify disqualifier |

package/benchmark/auto-resolve/results/20260512-f5-fixloop-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260512-f5-fixloop-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": -39.0,
-  "min_bare_headroom": -39,
-  "avg_solo_headroom": -19.0,
-  "min_solo_headroom": -19,
-  "rows": [
-    {
-      "fixture": "F5-fix-loop-red-green",
-      "status": "FAIL",
-      "bare_score": 99,
-      "solo_score": 99,
-      "bare_headroom": -39,
-      "solo_headroom": -19,
-      "reason": "bare score 99 > 60; solo_claude score 99 > 80"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260512-f5-fixloop-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260512-f5-fixloop-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: -39.0
-Minimum bare headroom: -39
-Average solo headroom: -19.0
-Minimum solo headroom: -19
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F5-fix-loop-red-green | 99 | -39 | 99 | -19 | FAIL | bare score 99 > 60; solo_claude score 99 > 80 |

package/benchmark/auto-resolve/results/20260512-f6-checksum-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260512-f6-checksum-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": -37.0,
-  "min_bare_headroom": -37,
-  "avg_solo_headroom": -16.0,
-  "min_solo_headroom": -16,
-  "rows": [
-    {
-      "fixture": "F6-dep-audit-native-module",
-      "status": "FAIL",
-      "bare_score": 97,
-      "solo_score": 96,
-      "bare_headroom": -37,
-      "solo_headroom": -16,
-      "reason": "bare score 97 > 60; solo_claude score 96 > 80"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260512-f6-checksum-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260512-f6-checksum-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: -37.0
-Minimum bare headroom: -37
-Average solo headroom: -16.0
-Minimum solo headroom: -16
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F6-dep-audit-native-module | 97 | -37 | 96 | -16 | FAIL | bare score 97 > 60; solo_claude score 96 > 80 |

package/benchmark/auto-resolve/results/20260512-f7-scope-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260512-f7-scope-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": -39.0,
-  "min_bare_headroom": -39,
-  "avg_solo_headroom": -20.0,
-  "min_solo_headroom": -20,
-  "rows": [
-    {
-      "fixture": "F7-out-of-scope-trap",
-      "status": "FAIL",
-      "bare_score": 99,
-      "solo_score": 100,
-      "bare_headroom": -39,
-      "solo_headroom": -20,
-      "reason": "bare score 99 > 60; solo_claude score 100 > 80"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260512-f7-scope-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260512-f7-scope-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: -39.0
-Minimum bare headroom: -39
-Average solo headroom: -20.0
-Minimum solo headroom: -20
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F7-out-of-scope-trap | 99 | -39 | 100 | -20 | FAIL | bare score 99 > 60; solo_claude score 100 > 80 |

package/benchmark/auto-resolve/results/20260512-f9-e2e-headroom/headroom-gate.json

@@ -1,28 +0,0 @@
-{
-  "run_id": "20260512-f9-e2e-headroom",
-  "rule": "at least 1 candidate fixtures; each must satisfy bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, with both baseline arms evidence-complete",
-  "verdict": "FAIL",
-  "fixtures_total": 1,
-  "fixtures_passed": 0,
-  "min_fixtures": 1,
-  "bare_max": 60,
-  "solo_max": 80,
-  "min_bare_headroom_required": 5,
-  "min_solo_headroom_required": 5,
-  "fixture_count_ok": true,
-  "avg_bare_headroom": 0.0,
-  "min_bare_headroom": 0,
-  "avg_solo_headroom": -10.0,
-  "min_solo_headroom": -10,
-  "rows": [
-    {
-      "fixture": "F9-e2e-ideate-to-resolve",
-      "status": "FAIL",
-      "bare_score": 60,
-      "solo_score": 90,
-      "bare_headroom": 0,
-      "solo_headroom": -10,
-      "reason": "bare headroom 0 < 5; solo_claude score 90 > 80; bare judge disqualifier"
-    }
-  ]
-}

package/benchmark/auto-resolve/results/20260512-f9-e2e-headroom/headroom-gate.md

@@ -1,15 +0,0 @@
-# Headroom Gate — 20260512-f9-e2e-headroom
-
-Verdict: **FAIL**
-
-Fixtures passed: 0/1 (minimum required: 1)
-
-Rule: at least 1 fixtures; bare <= 60 with headroom >= 5, solo_claude <= 80 with headroom >= 5, both baseline arms evidence-complete.
-Average bare headroom: 0.0
-Minimum bare headroom: 0
-Average solo headroom: -10.0
-Minimum solo headroom: -10
-
-| Fixture | Bare | Bare headroom | Solo | Solo headroom | Status | Reason |
-|---|---:|---:|---:|---:|---|---|
-| F9-e2e-ideate-to-resolve | 60 | 0 | 90 | -10 | FAIL | bare headroom 0 < 5; solo_claude score 90 > 80; bare judge disqualifier |