feat(controls): promote grounded controls to covered + enable LLM passes by default (#224)
This commit was merged in pull request #224.
This commit is contained in:
@@ -112,9 +112,9 @@ async fn build_specs(provider: &OscalControlsProvider) -> HashMap<String, Contro
|
||||
/// the grounded judge decide whether the control holds there. Returns net-new
|
||||
/// findings, each already tagged with its control and grounded to a real snippet.
|
||||
///
|
||||
/// Gated: the orchestrator runs this only when `breakpilot.grounded_control_checks`
|
||||
/// is set. Absence detection is the least deterministic path (the judge decides
|
||||
/// presence/absence, not a syntactic pattern), so it stays off until tuned live.
|
||||
/// The orchestrator runs this when `breakpilot.grounded_control_checks` is set
|
||||
/// (on by default). Validated live; it covers the 8 absence-based CRA controls
|
||||
/// (the judge decides presence/absence, grounded to a real snippet).
|
||||
pub async fn grounded_surface_findings(
|
||||
config: &AgentConfig,
|
||||
llm: Arc<LlmClient>,
|
||||
@@ -173,11 +173,10 @@ fn fetch_region(repo_path: &Path, file: &str, line: u32) -> Option<CandidateRegi
|
||||
/// ~13.6k master-control corpus (which has no CWE to LUT on). Returns the number
|
||||
/// of findings that gained a master-control ref.
|
||||
///
|
||||
/// Gated: the orchestrator runs this only when `breakpilot.semantic_mapping` is
|
||||
/// set (default off, flipped on once the master-controls catalog is live). The
|
||||
/// control embedding index is built once and cached to `snapshot_dir` keyed by
|
||||
/// corpus hash ([`ControlIndex::load_or_build`]), so only the first scan after a
|
||||
/// catalog change pays the embedding cost.
|
||||
/// The orchestrator runs this when `breakpilot.semantic_mapping` is set (on by
|
||||
/// default). The control embedding index is built once and cached to
|
||||
/// `snapshot_dir` keyed by corpus hash ([`ControlIndex::load_or_build`]), so only
|
||||
/// the first scan after a catalog change pays the embedding cost.
|
||||
pub async fn semantic_stamp_findings(
|
||||
config: &AgentConfig,
|
||||
llm: Arc<LlmClient>,
|
||||
|
||||
@@ -232,9 +232,9 @@ impl PipelineOrchestrator {
|
||||
|
||||
// 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.
|
||||
// nearest master controls, grounded-judge, and stamp confirmed refs. On by
|
||||
// default (validated live); the corpus embedding is cached so only the
|
||||
// first scan after a catalog change pays it.
|
||||
if self.config.breakpilot.semantic_mapping {
|
||||
self.update_phase(scan_run_id, "semantic_control_mapping")
|
||||
.await;
|
||||
@@ -256,8 +256,8 @@ impl PipelineOrchestrator {
|
||||
// rate limiting, no security logging, no update-signature check) have no
|
||||
// syntactic pattern to match, so we retrieve the code surface each governs
|
||||
// and let the grounded judge decide whether it holds, producing net-new
|
||||
// findings already tagged + grounded. Gated (default off): absence
|
||||
// detection is the least deterministic path, kept off until tuned live.
|
||||
// findings already tagged + grounded. On by default (validated live); it
|
||||
// covers the 8 absence-based CRA controls.
|
||||
if self.config.breakpilot.grounded_control_checks {
|
||||
self.update_phase(scan_run_id, "grounded_control_checks")
|
||||
.await;
|
||||
|
||||
Reference in New Issue
Block a user