feat(agent): C4 — semantic_stamp_findings + provider load_master_controls

Wires the semantic mapping into a callable scan pass:
- OscalControlsProvider: token-based fetch refactor + load_master_controls()
  (pulls ?framework=master-controls)
- semantic_stamp_findings(): build the ControlIndex from the master-controls
  catalog, then per finding embed its code region, retrieve the top-K nearest
  master controls, grounded-judge confirm, and stamp the confirmed ids onto
  control_refs (alongside the CRA CWE-LUT refs).

Opt-in — the orchestrator doesn't auto-run it, and it rebuilds the corpus index
per call (production should cache it). Live-verifiable once breakpilot #129 deploys.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

compliance-agent/src/controls/mod.rs

@@ -17,6 +17,6 @@ pub use checker::GroundedControlChecker;
 pub use index::ControlIndex;
 pub use judge::{ControlJudge, LlmControlJudge, PROMPT_VERSION};
 pub use oscal_provider::OscalControlsProvider;
-pub use scan_triage::triage_repo_findings;
+pub use scan_triage::{semantic_stamp_findings, triage_repo_findings};
 pub use semantic::SemanticControlChecker;
 pub use triage::{ControlTriage, TriageOutcome};

compliance-agent/src/controls/oscal_provider.rs

@@ -43,20 +43,20 @@ impl OscalControlsProvider {
         }
     }
 
-    fn catalog_url(&self, framework: ComplianceFramework) -> String {
+    fn catalog_url(&self, framework: &str) -> String {
         format!(
             "{}/api/compliance/v1/oscal/catalog?framework={framework}",
             self.base_url.trim_end_matches('/')
         )
     }
 
-    fn snapshot_path(&self, framework: ComplianceFramework) -> PathBuf {
+    fn snapshot_path(&self, framework: &str) -> PathBuf {
         self.snapshot_dir
             .join(format!("oscal-catalog-{framework}.json"))
     }
 
-    /// Fetch the raw catalog bytes for a framework over HTTP.
+    /// Fetch the raw catalog bytes for a framework token over HTTP.
-    async fn fetch_raw(&self, framework: ComplianceFramework) -> Result<Vec<u8>, CoreError> {
+    async fn fetch_raw(&self, framework: &str) -> Result<Vec<u8>, CoreError> {
         let mut req = self.http.get(self.catalog_url(framework));
         if let Some(token) = &self.token {
             req = req.bearer_auth(token.expose_secret());
@@ -78,11 +78,7 @@ impl OscalControlsProvider {
     }
 
     /// Write a catalog snapshot atomically (temp file + rename).
-    async fn write_snapshot(
+    async fn write_snapshot(&self, framework: &str, raw: &[u8]) -> Result<(), CoreError> {
-        &self,
-        framework: ComplianceFramework,
-        raw: &[u8],
-    ) -> Result<(), CoreError> {
         tokio::fs::create_dir_all(&self.snapshot_dir).await?;
         let path = self.snapshot_path(framework);
         let tmp = path.with_extension("json.tmp");
@@ -92,10 +88,7 @@ impl OscalControlsProvider {
     }
 
     /// Read a previously written snapshot, if one exists.
-    async fn read_snapshot(
+    async fn read_snapshot(&self, framework: &str) -> Result<Option<OscalDocument>, CoreError> {
-        &self,
-        framework: ComplianceFramework,
-    ) -> Result<Option<OscalDocument>, CoreError> {
         match tokio::fs::read(self.snapshot_path(framework)).await {
             Ok(raw) => Ok(Some(serde_json::from_slice(&raw)?)),
             Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(None),
@@ -103,21 +96,21 @@ impl OscalControlsProvider {
         }
     }
 
-    /// Load the catalog for a framework: fetch fresh + snapshot the exact bytes;
+    /// Load the catalog for a framework token: fetch fresh + snapshot the exact
-    /// on network failure, fall back to the last snapshot so scans still run.
+    /// bytes; on network failure, fall back to the last snapshot so scans run.
-    pub async fn load(&self, framework: ComplianceFramework) -> Result<OscalDocument, CoreError> {
+    async fn load_token(&self, framework: &str) -> Result<OscalDocument, CoreError> {
         match self.fetch_raw(framework).await {
             Ok(raw) => {
                 let doc: OscalDocument = serde_json::from_slice(&raw)?;
                 if let Err(e) = self.write_snapshot(framework, &raw).await {
-                    tracing::warn!(%framework, error = %e, "failed to write OSCAL snapshot");
+                    tracing::warn!(framework, error = %e, "failed to write OSCAL snapshot");
                 }
                 Ok(doc)
             }
             Err(fetch_err) => match self.read_snapshot(framework).await? {
                 Some(doc) => {
                     tracing::warn!(
-                        %framework, error = %fetch_err,
+                        framework, error = %fetch_err,
                         "OSCAL catalog fetch failed; falling back to snapshot"
                     );
                     Ok(doc)
@@ -126,6 +119,17 @@ impl OscalControlsProvider {
             },
         }
     }
+
+    /// Load the OSCAL catalog for a compliance framework.
+    pub async fn load(&self, framework: ComplianceFramework) -> Result<OscalDocument, CoreError> {
+        self.load_token(&framework.to_string()).await
+    }
+
+    /// Load the code-checkable master-controls catalog
+    /// (`?framework=master-controls`).
+    pub async fn load_master_controls(&self) -> Result<OscalDocument, CoreError> {
+        self.load_token("master-controls").await
+    }
 }
 
 /// Order controls whose title/text mention the query context first (stable), then
@@ -181,11 +185,11 @@ mod tests {
     fn builds_catalog_url_and_snapshot_path() {
         let p = provider(std::path::Path::new("/snap"));
         assert_eq!(
-            p.catalog_url(ComplianceFramework::Cra),
+            p.catalog_url("cra"),
             "http://unused/api/compliance/v1/oscal/catalog?framework=cra"
         );
         assert_eq!(
-            p.snapshot_path(ComplianceFramework::Cra),
+            p.snapshot_path("cra"),
             std::path::Path::new("/snap/oscal-catalog-cra.json")
         );
     }
@@ -213,19 +217,11 @@ mod tests {
     async fn snapshot_round_trip_and_offline_fallback() {
         let dir = std::env::temp_dir().join(format!("oscal-test-{}", uuid::Uuid::new_v4()));
         let p = provider(&dir);
-        assert!(p
+        assert!(p.read_snapshot("cra").await.unwrap().is_none());
-            .read_snapshot(ComplianceFramework::Cra)
+        p.write_snapshot("cra", MINI_CATALOG.as_bytes())
-            .await
-            .unwrap()
-            .is_none());
-        p.write_snapshot(ComplianceFramework::Cra, MINI_CATALOG.as_bytes())
             .await
             .unwrap();
-        let doc = p
+        let doc = p.read_snapshot("cra").await.unwrap().unwrap();
-            .read_snapshot(ComplianceFramework::Cra)
-            .await
-            .unwrap()
-            .unwrap();
         assert_eq!(doc.to_controls().len(), 1);
         assert_eq!(doc.framework(), Some(ComplianceFramework::Cra));
         let _ = std::fs::remove_dir_all(&dir);

compliance-agent/src/controls/scan_triage.rs

@@ -16,9 +16,15 @@ use compliance_core::models::onboarding::ComplianceFramework;
 use compliance_core::AgentConfig;
 use control_map::ControlMap;
 
-use super::{ControlTriage, LlmControlJudge, OscalControlsProvider, TriageOutcome};
+use super::{
+    ControlIndex, ControlTriage, LlmControlJudge, OscalControlsProvider, SemanticControlChecker,
+    TriageOutcome,
+};
 use crate::llm::LlmClient;
 
+/// Nearest master controls judged per code region in the semantic pass.
+const SEMANTIC_TOP_K: usize = 5;
+
 /// Lines of context to read on each side of a finding's line.
 const REGION_WINDOW: usize = 6;
 
@@ -116,6 +122,103 @@ fn fetch_region(repo_path: &Path, file: &str, line: u32) -> Option<CandidateRegi
     })
 }
 
+/// Master-controls **semantic** pass: for each finding's code region, retrieve the
+/// top-K nearest master controls by embedding, have the grounded judge confirm,
+/// and stamp the confirmed control ids onto the finding — the scale path for the
+/// ~13.6k master-control corpus (which has no CWE to LUT on). Returns the number
+/// of findings that gained a master-control ref.
+///
+/// Opt-in: the orchestrator does not run this yet. It builds the control embedding
+/// index per call (embeds the whole corpus) — production should cache/persist that
+/// index rather than rebuild it each scan.
+pub async fn semantic_stamp_findings(
+    config: &AgentConfig,
+    llm: Arc<LlmClient>,
+    repo_path: &Path,
+    findings: &mut [Finding],
+) -> usize {
+    let Some(base_url) = config.breakpilot.base_url.clone() else {
+        return 0;
+    };
+    let provider = OscalControlsProvider::new(
+        reqwest::Client::new(),
+        base_url,
+        config.breakpilot.token.clone(),
+        &config.breakpilot.snapshot_dir,
+    );
+    let doc = match provider.load_master_controls().await {
+        Ok(d) => d,
+        Err(e) => {
+            tracing::warn!(error = %e, "master-controls catalog unavailable; skipping semantic pass");
+            return 0;
+        }
+    };
+    let specs: Vec<ControlCheckSpec> = doc
+        .to_controls()
+        .into_iter()
+        .map(|c| ControlCheckSpec {
+            control_id: c.id,
+            title: c.title,
+            requirement: c.text,
+            default_cwe: None,
+            severity: Severity::Medium,
+        })
+        .collect();
+    let index = match ControlIndex::build(&llm, specs).await {
+        Ok(i) if !i.is_empty() => i,
+        Ok(_) => return 0,
+        Err(e) => {
+            tracing::warn!(error = %e, "failed to embed master-controls corpus");
+            return 0;
+        }
+    };
+    let checker = SemanticControlChecker::new(LlmControlJudge::new(llm.clone()));
+
+    let mut tagged = 0;
+    for finding in findings.iter_mut() {
+        if finding.status == FindingStatus::FalsePositive {
+            continue;
+        }
+        let (Some(file), Some(line)) = (finding.file_path.clone(), finding.line_number) else {
+            continue;
+        };
+        let Some(region) = fetch_region(repo_path, &file, line) else {
+            continue;
+        };
+        let region_emb = match llm.embed(vec![region.content.clone()]).await {
+            Ok(mut embs) => match embs.pop() {
+                Some(v) => v,
+                None => continue,
+            },
+            Err(e) => {
+                tracing::warn!(error = %e, "region embed failed; skipping finding");
+                continue;
+            }
+        };
+        let confirmed = checker
+            .check(
+                &index,
+                &region,
+                &region_emb,
+                SEMANTIC_TOP_K,
+                &finding.repo_id,
+            )
+            .await;
+        let before = finding.control_refs.len();
+        for f in confirmed {
+            for cref in f.control_refs {
+                if !finding.control_refs.contains(&cref) {
+                    finding.control_refs.push(cref);
+                }
+            }
+        }
+        if finding.control_refs.len() > before {
+            tagged += 1;
+        }
+    }
+    tagged
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;