feat(axbuild): grade review bench cases with same agent#1625
Merged
Conversation
ZR233
marked this pull request as ready for review
July 16, 2026 01:13
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
问题
现有 Review Bench 的 grader 依赖 case 中面向评分器的
match_if,并且只允许一个 candidate finding 命中一个 expected finding。Reviewer 与 grader 还可以分别指定 agent、model 和 reasoning effort,导致评分配置与实际审查配置不一致,也无法正确评价多条审查意见共同识别同一底层问题的情况。修改
known_findings.json:case 的全部已知问题。candidate_findings.json:reviewer 输出的全部 findings。extra_findings,不影响 recall gate。match_if。实现逻辑
评分器只判断 candidate 是否识别了同一底层缺陷或实质风险,不要求相同措辞、精确行号、完整影响或指定修复方案。每个 expected 的
finding_indices非空即记为 caught;所有匹配数组的 candidate 索引并集用于排除extra_findings。这种设计保持 recall 的含义为“是否发现已知问题”,同时把额外发现单独呈现,避免把尚未验证真伪的额外意见误当成 false positive。
验证
cargo fmt --all --checkcargo xtask agent-review-bench check:5 个 case 全部通过cargo xtask clippy --package axbuildcargo test -p axbuild agent_review_bench:仓库现有测试模块缺少QemuConfigimport,直接编译会被该基线问题阻断;临时补充 import 后本次 25 个定向测试全部通过,临时改动未纳入提交1/1 (100%),extra_findings = 51/1 (100%),extra_findings = 4