devlyn-cli 2.10.0 → 3.0.0

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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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

@@ -0,0 +1,28 @@
+{
+  "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

@@ -0,0 +1,15 @@
+# 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 |

package/benchmark/auto-resolve/scripts/run-fixture.sh

@@ -744,8 +744,18 @@ verify = {"commands": [], "forbidden_pattern_hits": [], "deps_added": 0,
 
 for vc in expected.get("verification_commands", []):
     try:
+        timeout_sec = vc.get("timeout_sec", 60)
+        if (
+            isinstance(timeout_sec, bool)
+            or not isinstance(timeout_sec, int)
+            or not 1 <= timeout_sec <= 600
+        ):
+            raise ValueError(
+                "timeout_sec must be an integer from 1 to 600 (bool is not allowed)"
+            )
         proc = subprocess.run(vc["cmd"], cwd=work, shell=True, env=verify_env,
-                              capture_output=True, text=True, timeout=60)
+                              capture_output=True, text=True,
+                              timeout=timeout_sec)
         out = (proc.stdout or "") + (proc.stderr or "")
         ok_exit = proc.returncode == vc.get("exit_code", 0)
         ok_contains = all(s in out for s in vc.get("stdout_contains", []))

package/benchmark/auto-resolve/scripts/test-benchmark-arg-parsing.sh

@@ -5,7 +5,7 @@ set -euo pipefail
 ROOT="$(cd "$(dirname "$0")/../../.." && pwd)"
 TMP="$(mktemp -d)"
 BENCH_ROOT="$ROOT/benchmark/auto-resolve"
-trap 'rm -rf "$TMP"; rm -rf "$BENCH_ROOT/results/arg-parse-command-test" "$BENCH_ROOT/results/arg-parse-discovery-test" "$BENCH_ROOT/results/arg-parse-shadow-suite-dry-run" "$BENCH_ROOT/results/arg-parse-shadow-cli-suite-dry-run" "$BENCH_ROOT/results/arg-parse-variant-path" "$BENCH_ROOT/results/arg-parse-headroom-cli-replay" "$BENCH_ROOT/results/arg-parse-pair-cli-replay" "$BENCH_ROOT/results/arg-parse-shadow-judge" "$BENCH_ROOT/results/arg-parse-opus-bad-mapping" "$BENCH_ROOT/results/arg-parse-opus-malformed-mapping" "$BENCH_ROOT/results/arg-parse-opus-malformed-score" "$BENCH_ROOT/results/arg-parse-opus-invalid-generated-score" "$BENCH_ROOT/results/arg-parse-opus-invalid-generated-dq" "$BENCH_ROOT/results/arg-parse-opus-summary-mapping" "$BENCH_ROOT/results/arg-parse-opus-summary-null-margin"; rm -rf /tmp/bench-arg-parse-variant-path-* /tmp/bench-arg-parse-headroom-cli-replay-*' EXIT
+trap 'rm -rf "$TMP"; rm -rf "$BENCH_ROOT/results/arg-parse-command-test" "$BENCH_ROOT/results/arg-parse-discovery-test" "$BENCH_ROOT/results/arg-parse-shadow-suite-dry-run" "$BENCH_ROOT/results/arg-parse-shadow-cli-suite-dry-run" "$BENCH_ROOT/results/arg-parse-variant-path" "$BENCH_ROOT/results/arg-parse-timeout-budget" "$BENCH_ROOT/results/arg-parse-headroom-cli-replay" "$BENCH_ROOT/results/arg-parse-pair-cli-replay" "$BENCH_ROOT/results/arg-parse-shadow-judge" "$BENCH_ROOT/results/arg-parse-opus-bad-mapping" "$BENCH_ROOT/results/arg-parse-opus-malformed-mapping" "$BENCH_ROOT/results/arg-parse-opus-malformed-score" "$BENCH_ROOT/results/arg-parse-opus-invalid-generated-score" "$BENCH_ROOT/results/arg-parse-opus-invalid-generated-dq" "$BENCH_ROOT/results/arg-parse-opus-summary-mapping" "$BENCH_ROOT/results/arg-parse-opus-summary-null-margin" "$BENCH_ROOT/shadow-fixtures/arg-parse-timeout-budget"; rm -rf /tmp/bench-arg-parse-variant-path-* /tmp/bench-arg-parse-timeout-budget-* /tmp/bench-arg-parse-headroom-cli-replay-*' EXIT
 
 expect_fail_contains() {
   local name="$1"
@@ -849,6 +849,88 @@ if grep -Fq -- '--engine auto' \
   exit 1
 fi
 mkdir -p "$BENCH_ROOT/shadow-fixtures"
+rm -rf "$BENCH_ROOT/shadow-fixtures/arg-parse-timeout-budget" \
+  "$BENCH_ROOT/results/arg-parse-timeout-budget"
+cp -R "$BENCH_ROOT/fixtures/F1-cli-trivial-flag" \
+  "$BENCH_ROOT/shadow-fixtures/arg-parse-timeout-budget"
+python3 - "$BENCH_ROOT/shadow-fixtures/arg-parse-timeout-budget/expected.json" <<'PY'
+import json
+import pathlib
+import sys
+
+path = pathlib.Path(sys.argv[1])
+expected = json.loads(path.read_text())
+expected["verification_commands"] = [
+    {"cmd": "true"},
+    {"cmd": "true", "timeout_sec": 1},
+    {"cmd": "true", "timeout_sec": 600},
+    {"cmd": "true", "timeout_sec": True},
+    {"cmd": "true", "timeout_sec": 601},
+    {
+        "cmd": "python3 -c \"import time; time.sleep(2)\"",
+        "timeout_sec": 1,
+    },
+    {
+        "cmd": "python3 -c \"import time; time.sleep(1)\"",
+        "timeout_sec": 5,
+    },
+]
+path.write_text(json.dumps(expected, indent=2) + "\n")
+PY
+bash "$ROOT/benchmark/auto-resolve/scripts/run-fixture.sh" \
+  --fixture arg-parse-timeout-budget \
+  --arm bare \
+  --run-id arg-parse-timeout-budget \
+  --dry-run > "$TMP/timeout-budget-dry-run.out" 2>&1
+python3 - "$BENCH_ROOT/results/arg-parse-timeout-budget/arg-parse-timeout-budget/bare/verify.json" <<'PY'
+import json
+import pathlib
+import sys
+
+commands = json.loads(pathlib.Path(sys.argv[1]).read_text())["commands"]
+assert commands[0]["pass"] is True, commands
+assert commands[1]["pass"] is True, commands
+assert commands[2]["pass"] is True, commands
+expected_error = (
+    "error:ValueError:timeout_sec must be an integer from 1 to 600 "
+    "(bool is not allowed)"
+)
+assert commands[3]["pass"] is False and commands[3]["reason"] == expected_error, commands
+assert commands[4]["pass"] is False and commands[4]["reason"] == expected_error, commands
+assert commands[5]["reason"] == "timeout", commands
+assert commands[6]["pass"] is True, commands
+PY
+
+TIMEOUT_LINT_ROOT="$TMP/timeout-lint-fixtures"
+mkdir -p "$TIMEOUT_LINT_ROOT"
+cp -R "$BENCH_ROOT/fixtures/F1-cli-trivial-flag" \
+  "$TIMEOUT_LINT_ROOT/F1-cli-trivial-flag"
+python3 - "$TIMEOUT_LINT_ROOT/F1-cli-trivial-flag/expected.json" <<'PY'
+import json
+import pathlib
+import sys
+
+path = pathlib.Path(sys.argv[1])
+expected = json.loads(path.read_text())
+expected["verification_commands"][0]["timeout_sec"] = 600
+path.write_text(json.dumps(expected, indent=2) + "\n")
+PY
+DEVLYN_FIXTURES_DIR="$TIMEOUT_LINT_ROOT" DEVLYN_LINT_FIXTURES_NO_JSONSCHEMA=1 \
+  bash "$ROOT/scripts/lint-fixtures.sh" > "$TMP/timeout-lint-pass.out" 2>&1
+python3 - "$TIMEOUT_LINT_ROOT/F1-cli-trivial-flag/expected.json" <<'PY'
+import json
+import pathlib
+import sys
+
+path = pathlib.Path(sys.argv[1])
+expected = json.loads(path.read_text())
+expected["verification_commands"][0]["timeout_sec"] = True
+path.write_text(json.dumps(expected, indent=2) + "\n")
+PY
+expect_fail_contains timeout-lint-bool \
+  "timeout_sec must be an integer from 1 to 600" \
+  env DEVLYN_FIXTURES_DIR="$TIMEOUT_LINT_ROOT" DEVLYN_LINT_FIXTURES_NO_JSONSCHEMA=1 \
+    bash "$ROOT/scripts/lint-fixtures.sh"
 rm -rf "$BENCH_ROOT/shadow-fixtures/arg-parse-nan-metadata" \
   "$BENCH_ROOT/shadow-fixtures/arg-parse-nan-expected" \
   "$BENCH_ROOT/results/arg-parse-nan-metadata" \