feat(agent): cache control embedding index + auto-wire semantic pass (gated) (#217)

2026-07-21 11:29:16 +00:00
parent f516ecf3b5
commit 0ef2cd1b23
6 changed files with 176 additions and 5 deletions
@@ -230,6 +230,28 @@ impl PipelineOrchestrator {
            tracing::info!("[{repo_id}] Control triage tagged {tagged} findings with control refs");
        }

+        // Stage 5c: semantic control mapping — scale path for the master-controls
+        // corpus (no CWE to LUT on): embed each finding's region, retrieve the
+        // nearest master controls, grounded-judge, and stamp confirmed refs. Gated
+        // (default off) as the corpus embedding + per-finding judging is the heavy
+        // path; enabled once verified live against a deployed master-controls catalog.
+        if self.config.breakpilot.semantic_mapping {
+            self.update_phase(scan_run_id, "semantic_control_mapping")
+                .await;
+            let sem = crate::controls::semantic_stamp_findings(
+                &self.config,
+                self.llm.clone(),
+                &repo_path,
+                &mut all_findings,
+            )
+            .await;
+            if sem > 0 {
+                tracing::info!(
+                    "[{repo_id}] Semantic mapping tagged {sem} findings with master-control refs"
+                );
+            }
+        }
+
        // Dedup against existing findings and insert new ones
        let mut new_count = 0u32;
        let mut new_findings: Vec<Finding> = Vec::new();