feat(axbuild): grade review bench cases with same agent

scripts/agent-review-bench/cases/1039-qperf-monolithic-perf-module.toml

@@ -0,0 +1,15 @@
+id = "1039-qperf-monolithic-perf-module"
+pr = 1039
+title = "qperf：单体 perf 模块与巨型输出结构体"
+remote = "https://github.com/rcore-os/tgoskits.git"
+base = "f0a27a0a47b0bf520a5bad2824e399616428b04a"
+head = "4e6d7ecac930eec51c419eb8cea28e396fe82a39"
+source = "https://github.com/rcore-os/tgoskits/pull/1039#discussion_r3585803023"
+fixed_by = "0bfaa3e6a3d90d81ff7a344e434f1274673ad593"
+
+[[expected]]
+id = "qperf-perf-module-mixes-responsibilities"
+path = "scripts/axbuild/src/starry/perf.rs"
+line = 56
+severity = "major"
+description = "该 PR 将 perf.rs 从 406 行扩展到 2013 行，并把 PerfOutputs 从 6 个字段扩展到 28 个；参数、构建、QEMU/QMP 生命周期、监控、指标、analyzer、ELF 解析和报告输出被集中在同一模块和大结构体中。"

scripts/agent-review-bench/cases/1495-axtask-deferred-wake-local-reschedule.toml

@@ -13,4 +13,3 @@ path = "os/arceos/modules/axtask/src/run_queue.rs"
 line = 1125
 severity = "major"
 description = "owner CPU 清空 deferred wake 时总是调用 kick_remote_cpu(target)。select_wake_run_queue 可能再次选择同一个 owner CPU 作为 target，而这种 self-kick 不会产生作用。因此，可运行任务会丢失原始远端唤醒者提供的 reschedule 通知，并可能在 owner 进入 idle 后一直留在队列中，直到后续 tick 才得到调度。"
-match_if = "评审必须指出：deferred-wake drain 在 target 为当前或 owner CPU 时会丢失必要的调度通知，因为 kick_remote_cpu 对 self-target 无效；并要求显式触发本地 reschedule，或用等价机制保留 handoff 状态。"

scripts/agent-review-bench/cases/1505-ipv6-pktinfo-family-validation.toml

@@ -13,4 +13,3 @@ path = "os/StarryOS/kernel/src/syscall/net/opt.rs"
 line = 521
 severity = "major"
 description = "新的 IPV6_RECVPKTINFO/IPV6_PKTINFO 快速路径在调用 ensure_ipv6_socket 前直接返回成功。因此，AF_INET 套接字可以成功使用 IPPROTO_IPV6 选项；这与 Linux 以及现有 IPv6 选项路径不一致，后者会对地址族不匹配返回 ENOPROTOOPT。getsockopt 路径存在同样问题。"
-match_if = "评审必须指出：新接受的 IPv6 pktinfo 选项在 set 和/或 get 路径中绕过 IPv6 套接字地址族校验，导致 AF_INET 套接字被错误接受；并要求在成功返回前调用 ensure_ipv6_socket 或执行等价校验。"

scripts/agent-review-bench/cases/1583-rtl8125-regression-covers-constants-only.toml

@@ -13,4 +13,3 @@ path = "drivers/net/realtek-rtl8125/src/hw.rs"
 line = 550
 severity = "major"
 description = "该回归测试只检查新常量之间的关系，从未调用 hw_phy_config，也未观察 PHY 读写。因此，即使删除生产代码中的 MII_CTRL1000 和 MII_BMCR 配置，测试仍会通过，原来的自协商缺陷也会复现。"
-match_if = "评审必须指出：新增测试只验证常量，而没有覆盖生产 PHY 配置行为，所以移除新增的页选择、通告和重启序列后测试仍不会失败；并要求通过记录型或 mock PHY 边界，或等价方式建立确定性的生产路径回归测试。"

scripts/agent-review-bench/cases/1611-axvisor-qemu-timeout-watchdog.toml

@@ -13,4 +13,3 @@ path = "test-suit/axvisor/normal/qemu/smoke/qemu-x86_64-svm.toml"
 line = 25
 severity = "major"
 description = "SVM 与 VMX 嵌套虚拟化冒烟配置删掉了仅有的有限 timeout。解析后 QemuConfig.timeout 变为 None，测试运行器因而不再安装 watchdog；一旦 QEMU 启动、guest shell 或结束条件卡住，任务会无限等待。慢速 runner 已可通过提高基线值或 timeout scale 放宽，不应通过删除超时规避失败。"
-match_if = "评审必须指出：SVM 和 VMX 配置删除 timeout 会使 watchdog 失效，并导致 QEMU 或 guest shell 卡住时无限等待；同时要求为两者恢复有限超时，允许调整基线值或使用 timeout scale。只泛泛建议增加超时或只讨论测试速度不算命中。"

scripts/agent-review-bench/schemas/grade.schema.json

@@ -9,14 +9,12 @@
       "items": {
         "type": "object",
         "additionalProperties": false,
-        "required": ["expected_id", "finding_index", "reason"],
+        "required": ["expected_id", "finding_indices", "reason"],
         "properties": {
           "expected_id": { "type": "string" },
-          "finding_index": {
-            "anyOf": [
-              { "type": "integer", "minimum": 0 },
-              { "type": "null" }
-            ]
+          "finding_indices": {
+            "type": "array",
+            "items": { "type": "integer", "minimum": 0 }
           },
           "reason": { "type": "string" }
         }

scripts/axbuild/src/agent_review_bench/cases.rs

@@ -32,7 +32,6 @@ pub(super) struct ExpectedFinding {
     pub(super) line: usize,
     pub(super) severity: Severity,
     pub(super) description: String,
-    pub(super) match_if: String,
 }
 
 #[derive(Clone, Copy, Debug, Deserialize, Serialize)]
@@ -226,11 +225,8 @@ fn validate_case_schema(case: &BenchCase) -> anyhow::Result<()> {
         if expected.line == 0 {
             bail!("finding `{}` line must be greater than zero", expected.id);
         }
-        if expected.description.trim().is_empty() || expected.match_if.trim().is_empty() {
-            bail!(
-                "finding `{}` description and match_if must not be empty",
-                expected.id
-            );
+        if expected.description.trim().is_empty() {
+            bail!("finding `{}` description must not be empty", expected.id);
         }
     }
     Ok(())
@@ -410,7 +406,6 @@ mod tests {
                 line: 1,
                 severity: Severity::Major,
                 description: "sample defect".into(),
-                match_if: "reviewer identifies sample defect".into(),
             }],
         }
     }