feat(controls): promote grounded controls to covered + enable LLM passes by default (#224)

compliance-agent/src/controls/scan_triage.rs

@@ -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>,

compliance-agent/src/pipeline/orchestrator.rs

@@ -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;

compliance-agent/tests/c5_example2.rs

@@ -0,0 +1,125 @@
+//! C5 example 2 — exploratory (not a committed regression test). Four topically
+//! distinct findings, to see whether tuned semantic retrieval maps each to the
+//! right master-control family. Run:
+//!   export ... (LITELLM_* + BREAKPILOT_BASE_URL)
+//!   cargo test -p compliance-agent --test c5_example2 -- --ignored --nocapture
+
+mod common;
+
+use std::sync::Arc;
+
+use compliance_agent::llm::LlmClient;
+use compliance_core::config::BreakpilotConfig;
+use compliance_core::models::finding::{Finding, Severity};
+use compliance_core::models::scan::ScanType;
+use secrecy::SecretString;
+
+fn env(k: &str) -> String {
+    std::env::var(k).unwrap_or_else(|_| panic!("env {k} must be set"))
+}
+
+fn mk(file: &str, line: u32, title: &str, desc: &str) -> Finding {
+    let mut f = Finding::new(
+        "repo-c5b".into(),
+        format!("{file}:{line}"),
+        "semgrep".into(),
+        ScanType::Sast,
+        title.into(),
+        desc.into(),
+        Severity::High,
+    );
+    f.file_path = Some(file.into());
+    f.line_number = Some(line);
+    f
+}
+
+fn write(repo: &std::path::Path, rel: &str, body: &str) {
+    let p = repo.join(rel);
+    if let Some(parent) = p.parent() {
+        std::fs::create_dir_all(parent).unwrap();
+    }
+    std::fs::write(p, body).unwrap();
+}
+
+#[tokio::test]
+#[ignore = "live: api-dev + LiteLLM"]
+async fn c5b_varied_findings() {
+    let llm = Arc::new(LlmClient::new(
+        env("LITELLM_URL"),
+        SecretString::from(env("LITELLM_API_KEY")),
+        env("LITELLM_MODEL"),
+        env("LITELLM_EMBED_MODEL"),
+    ));
+    let mut config = common::dev_config("mongodb://unused".into(), "c5b".into());
+    config.breakpilot = BreakpilotConfig {
+        base_url: Some(env("BREAKPILOT_BASE_URL")),
+        token: None,
+        snapshot_dir: std::env::temp_dir()
+            .join("c5-oscal-snap")
+            .to_string_lossy()
+            .into_owned(),
+        semantic_mapping: true,
+        grounded_control_checks: false,
+    };
+
+    let repo = std::env::temp_dir().join("c5b-fixture-repo");
+    let _ = std::fs::remove_dir_all(&repo);
+    write(
+        &repo,
+        "app/db.py",
+        "import sqlite3\n\ndef get_user(username):\n    q = \"SELECT * FROM users WHERE name = '\" + username + \"'\"\n    return conn.execute(q)\n",
+    );
+    write(
+        &repo,
+        "app/config.py",
+        "# service config\nAPI_KEY = \"sk_live_51H8xYz3kQ9v2bNmR7wT4uSpQ\"\nDB_HOST = \"db.internal\"\n",
+    );
+    write(
+        &repo,
+        "app/net.py",
+        "import requests\n\ndef fetch(url):\n    return requests.get(url, verify=False, timeout=5)\n",
+    );
+    write(
+        &repo,
+        "app/ser.py",
+        "import pickle\n\ndef load_state(blob):\n    return pickle.loads(blob)\n",
+    );
+
+    let mut findings = vec![
+        mk(
+            "app/db.py",
+            4,
+            "SQL injection via string-concatenated query",
+            "User input is concatenated directly into a SQL statement, allowing SQL injection.",
+        ),
+        mk(
+            "app/config.py",
+            2,
+            "Hardcoded API credential in source",
+            "A live API key is hardcoded in source code instead of a secret store.",
+        ),
+        mk(
+            "app/net.py",
+            4,
+            "TLS certificate verification disabled",
+            "requests is called with verify=False, disabling TLS certificate validation.",
+        ),
+        mk(
+            "app/ser.py",
+            3,
+            "Insecure deserialization with pickle.loads",
+            "Untrusted data is deserialized with pickle.loads, allowing remote code execution.",
+        ),
+    ];
+
+    let tagged =
+        compliance_agent::controls::semantic_stamp_findings(&config, llm, &repo, &mut findings)
+            .await;
+    println!("\n=== C5 example 2: varied findings ===");
+    for f in &findings {
+        println!("  {:52} -> {:?}", f.title, f.control_refs);
+    }
+    println!("tagged: {tagged}/4");
+    let _ = std::fs::remove_dir_all(&repo);
+    assert!(tagged >= 1);
+}

compliance-agent/tests/grounded_surface_live.rs

@@ -0,0 +1,92 @@
+//! Live validation of the grounded surface path (Stage 5d) for absence-based CRA
+//! controls. Ignored (hits api-dev CRA catalog + LiteLLM). Run:
+//!   export ... (LITELLM_* + BREAKPILOT_BASE_URL)
+//!   cargo test -p compliance-agent --test grounded_surface_live -- --ignored --nocapture
+//!
+//! Builds a fixture whose code surfaces trigger several absence-based controls
+//! (no rate limiting, no security logging, unverified update) and checks that the
+//! grounded checker produces control-tagged findings.
+
+mod common;
+
+use std::sync::Arc;
+
+use compliance_agent::llm::LlmClient;
+use compliance_core::config::BreakpilotConfig;
+use secrecy::SecretString;
+
+fn env(k: &str) -> String {
+    std::env::var(k).unwrap_or_else(|_| panic!("env {k} must be set"))
+}
+
+fn write(repo: &std::path::Path, rel: &str, body: &str) {
+    let p = repo.join(rel);
+    if let Some(parent) = p.parent() {
+        std::fs::create_dir_all(parent).unwrap();
+    }
+    std::fs::write(p, body).unwrap();
+}
+
+#[tokio::test]
+#[ignore = "live: api-dev CRA catalog + LiteLLM"]
+async fn grounded_surface_flags_absence_controls() {
+    let llm = Arc::new(LlmClient::new(
+        env("LITELLM_URL"),
+        SecretString::from(env("LITELLM_API_KEY")),
+        env("LITELLM_MODEL"),
+        env("LITELLM_EMBED_MODEL"),
+    ));
+    let mut config = common::dev_config("mongodb://unused".into(), "grounded".into());
+    config.breakpilot = BreakpilotConfig {
+        base_url: Some(env("BREAKPILOT_BASE_URL")),
+        token: None,
+        snapshot_dir: std::env::temp_dir()
+            .join("grounded-snap")
+            .to_string_lossy()
+            .into_owned(),
+        semantic_mapping: false,
+        grounded_control_checks: true,
+    };
+
+    let repo = std::env::temp_dir().join("grounded-fixture-repo");
+    let _ = std::fs::remove_dir_all(&repo);
+    // cra-ai-11: login endpoint with no rate limiting / lockout
+    write(
+        &repo,
+        "app/auth.py",
+        "@app.route('/login', methods=['POST'])\ndef login():\n    u = request.form['username']\n    p = request.form['password']\n    if authenticate(u, p):\n        return redirect('/')\n    return 'bad credentials', 401\n",
+    );
+    // cra-ai-24: privileged admin action with no security/audit logging
+    write(
+        &repo,
+        "app/admin.py",
+        "@app.route('/admin/delete_user', methods=['POST'])\ndef admin_delete_user():\n    uid = request.form['uid']\n    db.users.delete_one({'_id': uid})\n    return 'ok', 200\n",
+    );
+    // cra-ai-28/29/30: firmware update applied without signature / checksum verification
+    write(
+        &repo,
+        "app/updater.py",
+        "def apply_firmware_update(url):\n    blob = download(url)\n    install_firmware(blob)\n    reboot_device()\n",
+    );
+
+    let findings =
+        compliance_agent::controls::grounded_surface_findings(&config, llm, &repo, "repo-grounded")
+            .await;
+
+    println!("\n=== Grounded surface findings ({}) ===", findings.len());
+    for f in &findings {
+        println!(
+            "  {:24} {}:{:?}  {}",
+            f.control_refs.join(","),
+            f.file_path.as_deref().unwrap_or(""),
+            f.line_number,
+            f.title
+        );
+    }
+    let _ = std::fs::remove_dir_all(&repo);
+
+    assert!(
+        !findings.is_empty(),
+        "expected the grounded pass to flag at least one absence-based control"
+    );
+}