feat(controls): enrich semantic retrieval query with finding intent + C5 live test (#222)

2026-07-22 07:14:49 +00:00
parent 60601d8215
commit a25d41c3e5
3 changed files with 164 additions and 8 deletions
@@ -22,18 +22,20 @@ impl<J: ControlJudge> SemanticControlChecker<J> {
        Self { judge }
    }

-    /// Map a code region to the controls it violates. `region_embedding` is the
-    /// region's embedding (the caller computes it via the LLM); the top-`k`
-    /// nearest controls in `index` are judged and grounded.
+    /// Map a code region to the controls it violates. `query_embedding` is the
+    /// caller-supplied retrieval embedding — typically the finding's intent
+    /// (title/description) plus the region, so retrieval keys on what the finding
+    /// is *about*, not just the ambient code. The top-`k` nearest controls in
+    /// `index` are then judged against the raw `region` and grounded.
    pub async fn check(
        &self,
        index: &ControlIndex,
        region: &CandidateRegion,
-        region_embedding: &[f64],
+        query_embedding: &[f64],
        k: usize,
        repo_id: &str,
    ) -> Vec<Finding> {
-        let candidates = index.nearest(region_embedding, k);
+        let candidates = index.nearest(query_embedding, k);
        let mut findings = Vec::new();
        for spec in &candidates {
            let verdict = self.judge.judge(spec, region).await;