fix(audit): bump crossbeam-epoch to 0.9.20 (RUSTSEC-2026-0204)

Invalid pointer dereference in the `fmt::Pointer` impl for `Atomic`/`Shared`
when the underlying pointer is invalid. Lockfile-only bump; no code changes.

Refs #118.

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

.cargo/audit.toml

@@ -7,4 +7,17 @@ ignore = [
     # not a realistic attack surface here. Revisit when mongodb bumps hickory.
     "RUSTSEC-2026-0118", # NSEC3 loop, no fix available upstream
     "RUSTSEC-2026-0119", # O(n²) name compression, fixed in hickory-proto >=0.26.1
+
+    # rmcp 0.16.0 — DNS rebinding in Streamable HTTP server transport (missing
+    # Host header validation). Patched in rmcp >= 1.4.0, which is a major API
+    # version jump from our pin; rmcp shipped 0.x → 1.x → 2.x in three months
+    # and the migration touches every tool handler + the auth middleware we
+    # just landed in #92. Threat model in our deployment: the MCP server is
+    # exposed at a public hostname (comp-mcp-dev.meghsakha.com) behind orca's
+    # TLS-terminating ingress with per-tenant bearer auth — the attack model
+    # (browser DNS-rebinding into localhost MCP server) doesn't directly apply.
+    # Defense-in-depth Host-header check is still a worthwhile follow-up.
+    # FOLLOW-UP: bump rmcp to 2.x in a dedicated PR (M7.3 follow-up, sized
+    # multi-hour due to API surface change).
+    "RUSTSEC-2026-0189",
 ]

Cargo.lock

@@ -1118,9 +1118,9 @@ dependencies = [
 
 [[package]]
 name = "crossbeam-epoch"
-version = "0.9.18"
+version = "0.9.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
+checksum = "2d6914041f254d6e9176c01941b21115dcfb7089e55135a35411081bd106ef3f"
 dependencies = [
  "crossbeam-utils",
 ]
@@ -4282,9 +4282,9 @@ dependencies = [
 
 [[package]]
 name = "quinn-proto"
-version = "0.11.14"
+version = "0.11.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "434b42fec591c96ef50e21e886936e66d3cc3f737104fdb9b737c40ffb94c098"
+checksum = "4fcb935c5bec503c2f0e306bdd3e58bb9029dcb14fa8d9ac76e3a5256ac0763e"
 dependencies = [
  "bytes",
  "getrandom 0.3.4",

compliance-agent/src/api/handlers/admin.rs

@@ -0,0 +1,115 @@
+//! Cross-tenant admin endpoints (`/api/v1/admin/*`).
+//!
+//! Operator-only. Auth is a **static bearer token** (`ADMIN_API_TOKEN`
+//! env on the agent) — explicitly NOT a Keycloak JWT, because the
+//! whole point of these endpoints is to operate ACROSS tenants. A
+//! customer JWT (which always carries a single tenant_id) has no
+//! business mounting them.
+//!
+//! Routes are only registered when `ADMIN_API_TOKEN` is set. With no
+//! token, the endpoints don't exist at all (404), which is a stronger
+//! guarantee than "401 if you guess the path".
+//!
+//! Operations:
+//! - `GET    /api/v1/admin/tenants`              — list tenant DBs
+//! - `DELETE /api/v1/admin/tenants/{tenant_id}`  — GDPR delete
+//!
+//! Tenant ids in URLs are passed as-is to `DatabasePool::drop_tenant`,
+//! which sanitises them the same way it does for creation. Listing
+//! returns the raw DB names from `list_tenant_db_names` — operators
+//! can reverse-derive the tenant_id from the prefix.
+
+use axum::extract::{Extension, Path, Request};
+use axum::http::{header, StatusCode};
+use axum::middleware::Next;
+use axum::response::{IntoResponse, Response};
+use axum::Json;
+use secrecy::ExposeSecret;
+use serde::Serialize;
+
+use super::dto::AgentExt;
+
+#[derive(Serialize)]
+pub struct ListTenantDbsResponse {
+    pub tenant_db_names: Vec<String>,
+}
+
+#[tracing::instrument(skip_all)]
+pub async fn list_tenant_dbs(
+    Extension(agent): AgentExt,
+) -> Result<Json<ListTenantDbsResponse>, StatusCode> {
+    let names = agent.db_pool.list_tenant_db_names().await.map_err(|e| {
+        tracing::error!("admin: list_tenant_db_names failed: {e}");
+        StatusCode::INTERNAL_SERVER_ERROR
+    })?;
+    Ok(Json(ListTenantDbsResponse {
+        tenant_db_names: names,
+    }))
+}
+
+#[tracing::instrument(skip_all, fields(tenant_id = %tenant_id))]
+pub async fn drop_tenant_db(
+    Extension(agent): AgentExt,
+    Path(tenant_id): Path<String>,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    agent.db_pool.drop_tenant(&tenant_id).await.map_err(|e| {
+        tracing::error!("admin: drop_tenant failed: {e}");
+        StatusCode::INTERNAL_SERVER_ERROR
+    })?;
+    Ok(Json(serde_json::json!({ "status": "dropped" })))
+}
+
+/// Constant-time-ish comparison of the configured admin token against
+/// the incoming bearer. Uses `subtle`-style byte equality so timing
+/// attacks can't probe the token character by character.
+fn tokens_eq(a: &str, b: &str) -> bool {
+    if a.len() != b.len() {
+        return false;
+    }
+    let mut diff = 0u8;
+    for (x, y) in a.bytes().zip(b.bytes()) {
+        diff |= x ^ y;
+    }
+    diff == 0
+}
+
+/// Middleware enforcing the static `ADMIN_API_TOKEN`. Mounted only on
+/// the admin sub-router, so this never runs on customer routes.
+pub async fn require_admin_token(
+    Extension(agent): AgentExt,
+    request: Request,
+    next: Next,
+) -> Response {
+    let Some(expected) = agent.config.admin_api_token.as_ref() else {
+        // Belt-and-braces — if the routes were somehow mounted without
+        // a token configured, refuse rather than no-op-pass.
+        return (StatusCode::NOT_FOUND, "admin disabled").into_response();
+    };
+    let presented = request
+        .headers()
+        .get(header::AUTHORIZATION)
+        .and_then(|v| v.to_str().ok())
+        .and_then(|s| s.strip_prefix("Bearer "))
+        .map(|s| s.trim());
+    let Some(presented) = presented.filter(|s| !s.is_empty()) else {
+        return (StatusCode::UNAUTHORIZED, "Missing bearer token").into_response();
+    };
+    if !tokens_eq(presented, expected.expose_secret()) {
+        return (StatusCode::UNAUTHORIZED, "Invalid admin token").into_response();
+    }
+    next.run(request).await
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn tokens_eq_basic() {
+        assert!(tokens_eq("abc", "abc"));
+        assert!(!tokens_eq("abc", "abd"));
+        assert!(!tokens_eq("abc", "abcd"));
+        assert!(!tokens_eq("", "x"));
+        assert!(tokens_eq("", ""));
+    }
+}

compliance-agent/src/api/handlers/mod.rs

@@ -1,3 +1,4 @@
+pub mod admin;
 pub mod chat;
 pub mod dast;
 pub mod dto;

compliance-agent/src/api/routes.rs

@@ -2,7 +2,6 @@ use axum::routing::{delete, get, patch, post};
 use axum::Router;
 
 use crate::api::handlers;
-use crate::webhooks;
 
 pub fn build_router() -> Router {
     Router::new()
@@ -184,17 +183,10 @@ pub fn build_router() -> Router {
             "/api/v1/pentest/stats",
             get(handlers::pentest::pentest_stats),
         )
-        // Webhook endpoints (proxied through dashboard)
+    // Webhook routes live on the separate webhook server (port 3002,
-        .route(
+    // see crate::webhooks::server). The M7.2-C tenant-in-URL form is
-            "/webhook/github/{repo_id}",
+    // `/webhook/{tenant_id}/{platform}/{repo_id}` and the handlers
-            post(webhooks::github::handle_github_webhook),
+    // expect a (tenant_id, repo_id) path tuple. Anything mounting
-        )
+    // them here on the API server would mismatch the handler
-        .route(
+    // signature, so the routes are not exported.
-            "/webhook/gitlab/{repo_id}",
-            post(webhooks::gitlab::handle_gitlab_webhook),
-        )
-        .route(
-            "/webhook/gitea/{repo_id}",
-            post(webhooks::gitea::handle_gitea_webhook),
-        )
 }

compliance-agent/src/api/server.rs

@@ -4,7 +4,8 @@ use axum::extract::Request;
 use axum::http::HeaderValue;
 use axum::middleware::Next;
 use axum::response::Response;
-use axum::{middleware, Extension};
+use axum::routing::{delete, get};
+use axum::{middleware, Extension, Router};
 use tokio::sync::RwLock;
 use tower_http::cors::CorsLayer;
 use tower_http::set_header::SetResponseHeaderLayer;
@@ -14,6 +15,7 @@ use compliance_core::auth::{require_jwt_auth, require_tenant_status, JwksState};
 use compliance_core::{TenantContext, TenantStatus};
 
 use crate::agent::ComplianceAgent;
+use crate::api::handlers;
 use crate::api::routes;
 use crate::error::AgentError;
 
@@ -50,7 +52,28 @@ pub async fn inject_dev_tenant(mut request: Request, next: Next) -> Response {
 }
 
 pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), AgentError> {
+    // Admin sub-router. Routes are only mounted when ADMIN_API_TOKEN is
+    // configured — without it, the paths don't exist at all (404 rather
+    // than 401), so an operator who hasn't opted in can't fingerprint
+    // the surface area.
+    let admin_router: Router = if agent.config.admin_api_token.is_some() {
+        tracing::info!("Admin API enabled — /api/v1/admin/* mounted behind ADMIN_API_TOKEN bearer");
+        Router::new()
+            .route(
+                "/api/v1/admin/tenants",
+                get(handlers::admin::list_tenant_dbs),
+            )
+            .route(
+                "/api/v1/admin/tenants/{tenant_id}",
+                delete(handlers::admin::drop_tenant_db),
+            )
+            .layer(middleware::from_fn(handlers::admin::require_admin_token))
+    } else {
+        Router::new()
+    };
+
     let mut app = routes::build_router()
+        .merge(admin_router)
         .layer(Extension(Arc::new(agent.clone())))
         .layer(CorsLayer::permissive())
         .layer(TraceLayer::new_for_http())

compliance-agent/src/config.rs

@@ -59,5 +59,7 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
             .unwrap_or(true),
         pentest_imap_username: env_var_opt("PENTEST_IMAP_USERNAME"),
         pentest_imap_password: env_secret_opt("PENTEST_IMAP_PASSWORD"),
+        admin_api_token: env_secret_opt("ADMIN_API_TOKEN"),
+        tenant_registry_url: env_var_opt("TENANT_REGISTRY_URL"),
     })
 }

compliance-agent/src/database.rs

@@ -428,6 +428,36 @@ impl Database {
             )
             .await?;
 
+        // onboarded_targets: multikey on artifact source ref (webhook + dedupe
+        // lookup). Non-unique — "one git URL per tenant" is enforced in the
+        // create handler, since a unique multikey index on an array field has
+        // null-collision caveats.
+        self.onboarded_targets()
+            .create_index(
+                IndexModel::builder()
+                    .keys(doc! { "artifacts.source_ref": 1 })
+                    .build(),
+            )
+            .await?;
+
+        // onboarded_targets: multikey on artifact kind
+        self.onboarded_targets()
+            .create_index(
+                IndexModel::builder()
+                    .keys(doc! { "artifacts.kind": 1 })
+                    .build(),
+            )
+            .await?;
+
+        // onboarded_targets: target_type filter
+        self.onboarded_targets()
+            .create_index(
+                IndexModel::builder()
+                    .keys(doc! { "target_type": 1 })
+                    .build(),
+            )
+            .await?;
+
         tracing::info!("Database indexes ensured");
         Ok(())
     }
@@ -484,6 +514,13 @@ impl Database {
         self.inner.collection("dast_targets")
     }
 
+    /// The unified onboarding targets that replace `repositories` and
+    /// `dast_targets`. Ids are preserved from the legacy collections during
+    /// migration so downstream `repo_id` / `target_id` references keep resolving.
+    pub fn onboarded_targets(&self) -> Collection<OnboardedTarget> {
+        self.inner.collection("onboarded_targets")
+    }
+
     pub fn dast_scan_runs(&self) -> Collection<DastScanRun> {
         self.inner.collection("dast_scan_runs")
     }

compliance-agent/src/pentest/cleanup.rs

@@ -339,6 +339,8 @@ mod tests {
             pentest_imap_tls: true,
             pentest_imap_username: None,
             pentest_imap_password: None,
+            admin_api_token: None,
+            tenant_registry_url: None,
         }
     }
 

compliance-agent/src/pipeline/patterns.rs

@@ -215,7 +215,7 @@ fn scan_with_patterns(
                         repo_id.to_string(),
                         fingerprint,
                         scanner_name.to_string(),
-                        scan_type.clone(),
+                        scan_type,
                         pattern.title.clone(),
                         pattern.description.clone(),
                         pattern.severity.clone(),

compliance-agent/src/scheduler.rs

@@ -7,11 +7,18 @@ use crate::agent::ComplianceAgent;
 use crate::database::Database;
 use crate::error::AgentError;
 
-/// Default tenant the scheduler runs against when `SCHEDULER_TENANT_IDS`
+/// Default tenant the scheduler runs against when neither the tenant
-/// isn't set. Matches the dev-injector default so a bare `cargo run` has
+/// registry nor `SCHEDULER_TENANT_IDS` are configured. Matches the
-/// the scheduler scanning whatever lives in `<prefix>_dev`.
+/// dev-injector default so a bare `cargo run` has the scheduler
+/// scanning whatever lives in `<prefix>_dev`.
 const DEFAULT_SCHEDULER_TENANT_ID: &str = "dev";
 
+/// Request timeout when fetching the live tenant list from the
+/// registry. Kept short — if the registry is slow we'd rather fall
+/// back to env-configured ids and finish the tick than block the
+/// scheduler loop.
+const REGISTRY_FETCH_TIMEOUT_SECS: u64 = 5;
+
 pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError> {
     let sched = JobScheduler::new()
         .await
@@ -24,7 +31,12 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
         let agent = scan_agent.clone();
         Box::pin(async move {
             tracing::info!("Scheduled scan triggered");
-            for tenant_id in scheduler_tenants() {
+            let tenants = scheduler_tenants(&agent).await;
+            tracing::debug!(
+                tenant_count = tenants.len(),
+                "Scheduled scan: tenants resolved"
+            );
+            for tenant_id in tenants {
                 scan_all_repos(&agent, &tenant_id).await;
             }
         })
@@ -42,7 +54,12 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
         let agent = cve_agent.clone();
         Box::pin(async move {
             tracing::info!("CVE monitor triggered");
-            for tenant_id in scheduler_tenants() {
+            let tenants = scheduler_tenants(&agent).await;
+            tracing::debug!(
+                tenant_count = tenants.len(),
+                "CVE monitor: tenants resolved"
+            );
+            for tenant_id in tenants {
                 monitor_cves(&agent, &tenant_id).await;
             }
         })
@@ -58,9 +75,14 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
         .await
         .map_err(|e| AgentError::Scheduler(format!("Failed to start scheduler: {e}")))?;
 
-    let tenants = scheduler_tenants();
+    let tenants = scheduler_tenants(agent).await;
+    let source = if agent.config.tenant_registry_url.is_some() {
+        "tenant-registry (env fallback)"
+    } else {
+        "env (SCHEDULER_TENANT_IDS)"
+    };
     tracing::info!(
-        "Scheduler started: scans='{}', CVE monitor='{}', tenants={tenants:?}",
+        "Scheduler started: scans='{}', CVE monitor='{}', tenant source={source}, tenants={tenants:?}",
         agent.config.scan_schedule,
         agent.config.cve_monitor_schedule,
     );
@@ -71,10 +93,40 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
     }
 }
 
-/// Tenants the scheduler iterates each tick. From `SCHEDULER_TENANT_IDS`
+/// Tenants the scheduler iterates each tick.
-/// (comma-separated), or `DEFAULT_SCHEDULER_TENANT_ID` if unset. M7.2-D
+///
-/// will replace this with a pull from the tenant-registry.
+/// Resolution order:
-fn scheduler_tenants() -> Vec<String> {
+/// 1. **Tenant registry** at `agent.config.tenant_registry_url`
+///    (`GET /v1/tenants`). Fresh on every tick — picks up newly
+///    provisioned tenants without an agent restart.
+/// 2. **`SCHEDULER_TENANT_IDS`** env (comma-separated) — fallback when
+///    the registry is unreachable, the response is malformed, or no
+///    registry URL is configured.
+/// 3. **`DEFAULT_SCHEDULER_TENANT_ID`** (`"dev"`) — last-ditch fallback
+///    so the scheduler keeps doing something useful in dev.
+///
+/// We never panic out of this function — the scheduler must keep
+/// firing even if the registry is offline.
+async fn scheduler_tenants(agent: &ComplianceAgent) -> Vec<String> {
+    if let Some(url) = agent.config.tenant_registry_url.as_deref() {
+        match fetch_tenants_from_registry(&agent.http, url).await {
+            Ok(v) if !v.is_empty() => return v,
+            Ok(_) => {
+                tracing::warn!("tenant-registry returned empty list; falling back to env");
+            }
+            Err(e) => {
+                tracing::warn!(
+                    url = %url,
+                    error = %e,
+                    "tenant-registry fetch failed; falling back to env"
+                );
+            }
+        }
+    }
+    tenants_from_env()
+}
+
+fn tenants_from_env() -> Vec<String> {
     std::env::var("SCHEDULER_TENANT_IDS")
         .ok()
         .map(|s| {
@@ -88,6 +140,134 @@ fn scheduler_tenants() -> Vec<String> {
         .unwrap_or_else(|| vec![DEFAULT_SCHEDULER_TENANT_ID.to_string()])
 }
 
+/// Shape we accept from the registry. Liberal in what we accept:
+/// the registry can return any field shape as long as either `id` or
+/// `tenant_id` is present. Other fields are ignored.
+#[derive(serde::Deserialize)]
+struct RegistryTenant {
+    #[serde(alias = "tenant_id")]
+    id: String,
+    /// Filter out non-running tenants if status is present. Missing
+    /// status defaults to "active" so older registry deployments keep
+    /// working.
+    #[serde(default = "default_status")]
+    status: String,
+}
+
+fn default_status() -> String {
+    "active".to_string()
+}
+
+#[derive(serde::Deserialize)]
+struct RegistryListResponse {
+    data: Vec<RegistryTenant>,
+}
+
+async fn fetch_tenants_from_registry(
+    http: &reqwest::Client,
+    base_url: &str,
+) -> Result<Vec<String>, String> {
+    let url = format!("{}/v1/tenants", base_url.trim_end_matches('/'));
+    let resp = http
+        .get(&url)
+        .timeout(std::time::Duration::from_secs(REGISTRY_FETCH_TIMEOUT_SECS))
+        .send()
+        .await
+        .map_err(|e| format!("request failed: {e}"))?;
+    if !resp.status().is_success() {
+        return Err(format!("registry returned {}", resp.status()));
+    }
+    let body: RegistryListResponse = resp
+        .json()
+        .await
+        .map_err(|e| format!("invalid JSON: {e}"))?;
+    Ok(filter_active(body.data))
+}
+
+/// Frozen/Archived tenants don't need scheduled scans; the M7.1
+/// status gate would 402/410 anyway. Skip them so we don't waste
+/// cycles. Active / trial / demo / anything-else-unknown all run.
+fn filter_active(rows: Vec<RegistryTenant>) -> Vec<String> {
+    rows.into_iter()
+        .filter(|t| !matches!(t.status.as_str(), "frozen" | "archived"))
+        .map(|t| t.id)
+        .collect()
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn tenant(id: &str, status: &str) -> RegistryTenant {
+        RegistryTenant {
+            id: id.to_string(),
+            status: status.to_string(),
+        }
+    }
+
+    #[test]
+    fn filter_active_keeps_running_skips_frozen_archived() {
+        let rows = vec![
+            tenant("a", "active"),
+            tenant("b", "trial"),
+            tenant("c", "demo"),
+            tenant("d", "frozen"),
+            tenant("e", "archived"),
+            tenant("f", "weird-but-not-known-dead"),
+        ];
+        let out = filter_active(rows);
+        assert_eq!(out, vec!["a", "b", "c", "f"]);
+    }
+
+    #[test]
+    fn deserialize_registry_response_accepts_id_or_tenant_id() {
+        let body = r#"{"data":[
+            {"id":"a","status":"active"},
+            {"tenant_id":"b","status":"trial"},
+            {"id":"c"}
+        ]}"#;
+        let parsed: RegistryListResponse = serde_json::from_str(body).unwrap();
+        assert_eq!(parsed.data.len(), 3);
+        assert_eq!(parsed.data[0].id, "a");
+        assert_eq!(parsed.data[1].id, "b");
+        assert_eq!(parsed.data[2].id, "c");
+        // Default status for the third entry should be "active"
+        assert_eq!(parsed.data[2].status, "active");
+    }
+
+    /// Combined into a single test: cargo runs tests in parallel and
+    /// env vars are process-global, so two separate tests touching
+    /// `SCHEDULER_TENANT_IDS` race each other. Doing both checks in
+    /// one test keeps them in a deterministic order.
+    #[test]
+    fn tenants_from_env_resolution() {
+        std::env::remove_var("SCHEDULER_TENANT_IDS");
+        assert_eq!(
+            tenants_from_env(),
+            vec![DEFAULT_SCHEDULER_TENANT_ID.to_string()],
+            "unset → default"
+        );
+
+        std::env::set_var("SCHEDULER_TENANT_IDS", "acme, globex ,,hello");
+        let out = tenants_from_env();
+        std::env::remove_var("SCHEDULER_TENANT_IDS");
+        assert_eq!(
+            out,
+            vec!["acme", "globex", "hello"],
+            "splits + trims + drops empty"
+        );
+
+        std::env::set_var("SCHEDULER_TENANT_IDS", "");
+        let out = tenants_from_env();
+        std::env::remove_var("SCHEDULER_TENANT_IDS");
+        assert_eq!(
+            out,
+            vec![DEFAULT_SCHEDULER_TENANT_ID.to_string()],
+            "empty → default"
+        );
+    }
+}
+
 /// Resolve the per-tenant database. Logs and returns `None` on failure
 /// so the loop in the caller can continue with other tenants.
 async fn tenant_db(agent: &ComplianceAgent, tenant_id: &str) -> Option<Database> {

compliance-agent/tests/common/mod.rs

@@ -66,6 +66,8 @@ impl TestServer {
             pentest_imap_tls: false,
             pentest_imap_username: None,
             pentest_imap_password: None,
+            admin_api_token: None,
+            tenant_registry_url: None,
         };
 
         let agent = ComplianceAgent::new(config, db_pool);

compliance-core/src/auth.rs

@@ -63,16 +63,24 @@ struct Claims {
 
 const PUBLIC_ENDPOINTS: &[&str] = &["/api/v1/health"];
 
+/// Path prefixes that bypass JWT validation. The admin sub-router
+/// (`/api/v1/admin/*`) has its own static-bearer middleware and must
+/// not be routed through the customer-JWT path — a Keycloak token
+/// always carries a single tenant_id and would semantically conflict
+/// with cross-tenant admin operations.
+const PUBLIC_PREFIXES: &[&str] = &["/api/v1/admin/"];
+
 /// Middleware that validates Bearer JWT tokens against Keycloak's JWKS
 /// and attaches a `TenantContext` extension on success.
 ///
-/// Skips validation for the health endpoint.
+/// Skips validation for the health endpoint and any path under one of
-/// If `JwksState` is not present (Keycloak not configured), requests
+/// the [`PUBLIC_PREFIXES`]. If `JwksState` is not present (Keycloak
-/// pass through and downstream code must handle the missing context.
+/// not configured), requests pass through and downstream code must
+/// handle the missing context.
 pub async fn require_jwt_auth(mut request: Request, next: Next) -> Response {
     let path = request.uri().path();
 
-    if PUBLIC_ENDPOINTS.contains(&path) {
+    if PUBLIC_ENDPOINTS.contains(&path) || PUBLIC_PREFIXES.iter().any(|p| path.starts_with(p)) {
         return next.run(request).await;
     }
 

compliance-core/src/config.rs

@@ -37,6 +37,15 @@ pub struct AgentConfig {
     pub pentest_imap_tls: bool,
     pub pentest_imap_username: Option<String>,
     pub pentest_imap_password: Option<SecretString>,
+    /// Static bearer for the cross-tenant admin endpoints under
+    /// `/api/v1/admin/*`. When `None`, those endpoints are not
+    /// mounted at all (defense-in-depth: ops endpoints never reach
+    /// any auth path if no operator has explicitly opted in).
+    pub admin_api_token: Option<SecretString>,
+    /// Live tenant-registry URL the scheduler consults for the list
+    /// of tenants to iterate. When `None` or unreachable, scheduler
+    /// falls back to `SCHEDULER_TENANT_IDS` env (M7.2-C).
+    pub tenant_registry_url: Option<String>,
 }
 
 #[derive(Clone, Debug, Serialize, Deserialize)]

compliance-core/src/lib.rs

@@ -2,6 +2,7 @@ pub mod config;
 pub mod db;
 pub mod error;
 pub mod models;
+pub mod scan_matrix;
 #[cfg(feature = "telemetry")]
 pub mod telemetry;
 pub mod tenant;

compliance-core/src/models/mod.rs

@@ -9,6 +9,7 @@ pub mod issue;
 pub mod mcp;
 pub mod mcp_token;
 pub mod notification;
+pub mod onboarding;
 pub mod pentest;
 pub mod repository;
 pub mod sbom;
@@ -31,6 +32,11 @@ pub use issue::{IssueStatus, TrackerIssue, TrackerType};
 pub use mcp::{McpServerConfig, McpServerStatus, McpTransport};
 pub use mcp_token::{McpToken, McpTokenView};
 pub use notification::{CveNotification, NotificationSeverity, NotificationStatus};
+pub use onboarding::{
+    Artifact, ArtifactAuth, ArtifactKind, Classification, DetectedFact, GitArtifactConfig,
+    IssueTrackerConfig, OnboardedTarget, PlcArtifactConfig, PlcFormat, TargetScanConfig,
+    TargetType, TargetTypeCandidate, WebArtifactConfig,
+};
 pub use pentest::{
     AttackChainNode, AttackNodeStatus, AuthMode, CodeContextHint, Environment, IdentityProvider,
     PentestAuthConfig, PentestConfig, PentestEvent, PentestMessage, PentestSession, PentestStats,

compliance-core/src/models/onboarding.rs

@@ -0,0 +1,587 @@
+//! The unified onboarding model.
+//!
+//! An [`OnboardedTarget`] is the single source of truth for anything the scanner
+//! can analyze. It records *what kind of software* the target is ([`TargetType`]),
+//! the concrete [`Artifact`]s that were provided for it (a git repo, a firmware
+//! image, a live URL, a PLC project, ...), the classifier's verdict, and the scan
+//! configuration. It replaces the older git-only `TrackedRepository` and the
+//! standalone `DastTarget`, both of which fold into this type as artifacts.
+
+use std::collections::HashMap;
+
+use chrono::{DateTime, Utc};
+use serde::{Deserialize, Serialize};
+
+use super::dast::{DastAuthConfig, DastTargetType};
+use super::issue::TrackerType;
+use super::pentest::{Environment, PentestConfig, PentestStrategy};
+use super::scan::ScanType;
+
+/// The family of software a target belongs to.
+///
+/// Targets look endlessly varied but fall into a small enumerable set classified
+/// by where the analyzable signal lives. This drives the scan-applicability
+/// matrix and the onboarding wizard's type selection.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case")]
+pub enum TargetType {
+    /// Browser-facing web application (front end + server).
+    WebApp,
+    /// Headless backend service / API (REST, GraphQL, gRPC).
+    BackendService,
+    /// Desktop application (Windows/macOS/Linux GUI or CLI binary).
+    DesktopApp,
+    /// Android application (APK / AAB).
+    AndroidApp,
+    /// iOS application (IPA).
+    IosApp,
+    /// Bare-metal embedded firmware (no operating system).
+    FirmwareBareMetal,
+    /// Embedded firmware running on an RTOS (Zephyr, FreeRTOS, ...).
+    FirmwareRtos,
+    /// Embedded Linux built with Yocto / OpenEmbedded (BSP + image).
+    EmbeddedLinuxYocto,
+    /// Programmable logic controller software (IEC 61131-3, PLCopen / SPS).
+    PlcSps,
+}
+
+impl std::fmt::Display for TargetType {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Self::WebApp => write!(f, "web_app"),
+            Self::BackendService => write!(f, "backend_service"),
+            Self::DesktopApp => write!(f, "desktop_app"),
+            Self::AndroidApp => write!(f, "android_app"),
+            Self::IosApp => write!(f, "ios_app"),
+            Self::FirmwareBareMetal => write!(f, "firmware_bare_metal"),
+            Self::FirmwareRtos => write!(f, "firmware_rtos"),
+            Self::EmbeddedLinuxYocto => write!(f, "embedded_linux_yocto"),
+            Self::PlcSps => write!(f, "plc_sps"),
+        }
+    }
+}
+
+/// The kind of artifact provided for a target.
+///
+/// Which scans are possible is a function of the target type *and* which of
+/// these are present (SAST needs code, DAST needs a running URL, and so on).
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case")]
+pub enum ArtifactKind {
+    /// A git repository (cloned for static analysis).
+    GitRepo,
+    /// A source archive (zip / tarball) with no live git remote.
+    SourceArchive,
+    /// A firmware image or binary blob.
+    FirmwareImage,
+    /// A mobile package: Android APK/AAB or iOS IPA.
+    MobilePackage,
+    /// An OCI/Docker container image reference.
+    ContainerImage,
+    /// A reachable running instance (base URL / endpoint) for dynamic testing.
+    LiveUrl,
+    /// A PLC project: PLCopen XML or Structured Text source.
+    PlcProject,
+    /// Free-form plaintext describing the target (feeds classification only).
+    PlaintextDescription,
+}
+
+impl std::fmt::Display for ArtifactKind {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Self::GitRepo => write!(f, "git_repo"),
+            Self::SourceArchive => write!(f, "source_archive"),
+            Self::FirmwareImage => write!(f, "firmware_image"),
+            Self::MobilePackage => write!(f, "mobile_package"),
+            Self::ContainerImage => write!(f, "container_image"),
+            Self::LiveUrl => write!(f, "live_url"),
+            Self::PlcProject => write!(f, "plc_project"),
+            Self::PlaintextDescription => write!(f, "plaintext_description"),
+        }
+    }
+}
+
+/// Credentials attached to an artifact.
+///
+/// This folds both `TrackedRepository`'s git auth (`auth_token` / `auth_username`
+/// / SSH key) and `DastAuthConfig`'s HTTP auth (form / bearer / cookie) into one
+/// shape so a single artifact carries whatever it needs to be fetched or probed.
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
+pub struct ArtifactAuth {
+    /// Auth method: `none` | `token` | `basic` | `bearer` | `cookie` | `form` | `ssh`.
+    #[serde(default)]
+    pub method: String,
+    /// Username (git user, basic-auth user, or `x-access-token` for PATs).
+    pub username: Option<String>,
+    /// The secret credential: PAT, password, or bearer token. Encrypted at rest.
+    pub secret: Option<String>,
+    /// Path to an SSH private key for git-over-SSH.
+    pub ssh_key_path: Option<String>,
+    /// Login URL for form-based authentication.
+    pub login_url: Option<String>,
+    /// Extra headers to send when authenticating / probing.
+    pub headers: Option<HashMap<String, String>>,
+}
+
+impl From<DastAuthConfig> for ArtifactAuth {
+    fn from(c: DastAuthConfig) -> Self {
+        Self {
+            method: c.method,
+            username: c.username,
+            // Prefer a bearer token; otherwise fall back to the password.
+            secret: c.token.or(c.password),
+            ssh_key_path: None,
+            login_url: c.login_url,
+            headers: c.headers,
+        }
+    }
+}
+
+/// Git-specific configuration for a [`ArtifactKind::GitRepo`] artifact.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct GitArtifactConfig {
+    /// Branch to scan.
+    pub default_branch: String,
+    /// Commit SHA of the last completed scan (change-detection watermark).
+    pub last_scanned_commit: Option<String>,
+    /// Local clone path once the repo has been fetched.
+    pub local_path: Option<String>,
+}
+
+impl GitArtifactConfig {
+    /// Config for a fresh git artifact on the given branch.
+    pub fn on_branch(branch: impl Into<String>) -> Self {
+        Self {
+            default_branch: branch.into(),
+            last_scanned_commit: None,
+            local_path: None,
+        }
+    }
+}
+
+impl Default for GitArtifactConfig {
+    fn default() -> Self {
+        Self::on_branch("main")
+    }
+}
+
+/// Dynamic-analysis configuration for a [`ArtifactKind::LiveUrl`] artifact.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct WebArtifactConfig {
+    /// Whether the endpoint is a web app, REST API, or GraphQL API.
+    pub target_kind: DastTargetType,
+    /// URL paths to exclude from crawling / scanning.
+    #[serde(default)]
+    pub excluded_paths: Vec<String>,
+    /// Maximum crawl depth.
+    pub max_crawl_depth: u32,
+    /// Rate limit in requests per second.
+    pub rate_limit: u32,
+    /// Whether destructive methods (DELETE / PUT) are permitted.
+    #[serde(default)]
+    pub allow_destructive: bool,
+}
+
+impl Default for WebArtifactConfig {
+    fn default() -> Self {
+        Self {
+            target_kind: DastTargetType::WebApp,
+            excluded_paths: Vec::new(),
+            max_crawl_depth: 3,
+            rate_limit: 10,
+            allow_destructive: false,
+        }
+    }
+}
+
+/// The source format of a PLC project artifact.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case")]
+pub enum PlcFormat {
+    /// PLCopen XML project export.
+    PlcopenXml,
+    /// IEC 61131-3 Structured Text source.
+    StructuredText,
+}
+
+/// PLC-specific configuration for a [`ArtifactKind::PlcProject`] artifact.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct PlcArtifactConfig {
+    /// The project source format.
+    pub format: PlcFormat,
+}
+
+/// A single fact discovered about a target by ingest or classification
+/// (e.g. `language=rust`, `build_system=cmake`, `mcu=stm32f429`).
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct DetectedFact {
+    /// The fact name.
+    pub key: String,
+    /// The fact value.
+    pub value: String,
+    /// What produced the fact (e.g. `tramiton`, `language-fingerprint`).
+    pub source: String,
+}
+
+impl DetectedFact {
+    /// Build a fact from its parts.
+    pub fn new(
+        key: impl Into<String>,
+        value: impl Into<String>,
+        source: impl Into<String>,
+    ) -> Self {
+        Self {
+            key: key.into(),
+            value: value.into(),
+            source: source.into(),
+        }
+    }
+}
+
+/// One concrete thing provided for a target: code, a binary, a URL, etc.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct Artifact {
+    /// Stable per-artifact id (UUID v4) — scan steps reference this.
+    pub id: String,
+    /// What kind of artifact this is.
+    pub kind: ArtifactKind,
+    /// The source reference: git URL, blob id, live URL, or image ref.
+    pub source_ref: String,
+    /// Optional human-friendly label.
+    pub display_name: Option<String>,
+    /// Content-addressed storage path once ingested (blobs only).
+    pub stored_path: Option<String>,
+    /// SHA-256 of the ingested content (git artifacts store the head SHA).
+    pub content_hash: Option<String>,
+    /// Size of the stored blob in bytes.
+    pub size_bytes: Option<u64>,
+    /// Credentials for fetching or probing this artifact.
+    pub auth: Option<ArtifactAuth>,
+    /// Git configuration (present for [`ArtifactKind::GitRepo`]).
+    pub git: Option<GitArtifactConfig>,
+    /// Dynamic-analysis configuration (present for [`ArtifactKind::LiveUrl`]).
+    pub web: Option<WebArtifactConfig>,
+    /// PLC configuration (present for [`ArtifactKind::PlcProject`]).
+    pub plc: Option<PlcArtifactConfig>,
+    /// Facts discovered about this artifact by ingest / classification.
+    #[serde(default)]
+    pub detected: Vec<DetectedFact>,
+    /// When this artifact was last ingested.
+    #[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
+    pub ingested_at: Option<DateTime<Utc>>,
+}
+
+impl Artifact {
+    /// A bare artifact of the given kind and source reference.
+    fn bare(kind: ArtifactKind, source_ref: impl Into<String>) -> Self {
+        Self {
+            id: uuid::Uuid::new_v4().to_string(),
+            kind,
+            source_ref: source_ref.into(),
+            display_name: None,
+            stored_path: None,
+            content_hash: None,
+            size_bytes: None,
+            auth: None,
+            git: None,
+            web: None,
+            plc: None,
+            detected: Vec::new(),
+            ingested_at: None,
+        }
+    }
+
+    /// A git-repository artifact tracking the given branch.
+    pub fn git_repo(url: impl Into<String>, branch: impl Into<String>) -> Self {
+        let mut a = Self::bare(ArtifactKind::GitRepo, url);
+        a.git = Some(GitArtifactConfig::on_branch(branch));
+        a
+    }
+
+    /// A live-URL artifact with default crawl settings.
+    pub fn live_url(url: impl Into<String>) -> Self {
+        let mut a = Self::bare(ArtifactKind::LiveUrl, url);
+        a.web = Some(WebArtifactConfig::default());
+        a
+    }
+
+    /// A firmware-image artifact referenced by name (blob ingested later).
+    pub fn firmware_image(source_ref: impl Into<String>) -> Self {
+        Self::bare(ArtifactKind::FirmwareImage, source_ref)
+    }
+
+    /// A source-archive artifact referenced by name (blob ingested later).
+    pub fn source_archive(source_ref: impl Into<String>) -> Self {
+        Self::bare(ArtifactKind::SourceArchive, source_ref)
+    }
+
+    /// A mobile-package artifact (APK/AAB/IPA) referenced by name.
+    pub fn mobile_package(source_ref: impl Into<String>) -> Self {
+        Self::bare(ArtifactKind::MobilePackage, source_ref)
+    }
+
+    /// A container-image artifact referenced by OCI ref.
+    pub fn container_image(source_ref: impl Into<String>) -> Self {
+        Self::bare(ArtifactKind::ContainerImage, source_ref)
+    }
+
+    /// A PLC-project artifact in the given format.
+    pub fn plc_project(source_ref: impl Into<String>, format: PlcFormat) -> Self {
+        let mut a = Self::bare(ArtifactKind::PlcProject, source_ref);
+        a.plc = Some(PlcArtifactConfig { format });
+        a
+    }
+
+    /// A plaintext-description artifact (classification input only).
+    pub fn plaintext(text: impl Into<String>) -> Self {
+        Self::bare(ArtifactKind::PlaintextDescription, text)
+    }
+}
+
+/// One ranked candidate produced by the classifier.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct TargetTypeCandidate {
+    /// The candidate target type.
+    pub target_type: TargetType,
+    /// Confidence in `[0.0, 1.0]`.
+    pub confidence: f32,
+    /// Why this candidate was proposed.
+    pub rationale: String,
+}
+
+/// The classifier's verdict for a target: a suggested type plus ranked
+/// alternatives and the facts the decision rested on.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct Classification {
+    /// The top-ranked target type.
+    pub suggested: TargetType,
+    /// All candidates, sorted by descending confidence.
+    #[serde(default)]
+    pub candidates: Vec<TargetTypeCandidate>,
+    /// Facts gathered during classification.
+    #[serde(default)]
+    pub facts: Vec<DetectedFact>,
+    /// Which classifiers contributed (e.g. `["tramiton", "language-fingerprint"]`).
+    #[serde(default)]
+    pub detected_by: Vec<String>,
+    /// When classification ran.
+    #[serde(with = "super::serde_helpers::bson_datetime")]
+    pub detected_at: DateTime<Utc>,
+    /// Whether a human confirmed the suggestion.
+    #[serde(default)]
+    pub confirmed: bool,
+}
+
+/// Issue-tracker linkage, migrated from `TrackedRepository`'s `tracker_*` fields.
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
+pub struct IssueTrackerConfig {
+    /// The tracker platform.
+    pub tracker_type: Option<TrackerType>,
+    /// Tracker owner / organization.
+    pub owner: Option<String>,
+    /// Tracker repository / project.
+    pub repo: Option<String>,
+    /// Per-target tracker access token.
+    pub token: Option<String>,
+}
+
+/// How a target should be scanned.
+///
+/// `enabled_scans` / `disabled_scans` override the scan-applicability matrix
+/// defaults; the pentest and tracker blocks reuse the existing wizard config.
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
+pub struct TargetScanConfig {
+    /// Scans explicitly turned on (empty means "use matrix defaults").
+    #[serde(default)]
+    pub enabled_scans: Vec<ScanType>,
+    /// Scans explicitly turned off.
+    #[serde(default)]
+    pub disabled_scans: Vec<ScanType>,
+    /// Target environment (gates destructive / active testing).
+    #[serde(default)]
+    pub environment: Environment,
+    /// Whether destructive tests are permitted for this target.
+    #[serde(default)]
+    pub allow_destructive: bool,
+    /// Pentest strategy selector.
+    pub strategy: Option<PentestStrategy>,
+    /// Full pentest wizard configuration.
+    pub pentest: Option<PentestConfig>,
+    /// Issue-tracker linkage.
+    pub issue_tracker: Option<IssueTrackerConfig>,
+}
+
+/// A target onboarded for scanning: the unified replacement for the legacy
+/// `TrackedRepository` (SAST) and `DastTarget` (DAST) records.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct OnboardedTarget {
+    /// Mongo id. Preserved from the legacy record during migration so every
+    /// downstream collection keyed by `repo_id` / `target_id` keeps resolving.
+    #[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
+    pub id: Option<bson::oid::ObjectId>,
+    /// Human-friendly name.
+    #[serde(default)]
+    pub name: String,
+    /// The software family this target belongs to.
+    pub target_type: TargetType,
+    /// Optional free-form description (also a classification input).
+    pub description: Option<String>,
+    /// The artifacts provided for this target.
+    #[serde(default)]
+    pub artifacts: Vec<Artifact>,
+    /// The classifier's verdict, once run.
+    pub classification: Option<Classification>,
+    /// How this target should be scanned.
+    #[serde(default)]
+    pub scan_config: TargetScanConfig,
+    /// Cron schedule for recurring scans, if any.
+    pub scan_schedule: Option<String>,
+    /// Whether inbound webhooks are enabled for this target.
+    #[serde(default)]
+    pub webhook_enabled: bool,
+    /// HMAC secret for verifying inbound webhooks.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub webhook_secret: Option<String>,
+    /// Cached count of findings across this target's scans.
+    #[serde(default)]
+    pub findings_count: u32,
+    /// Creation timestamp.
+    #[serde(
+        default = "chrono::Utc::now",
+        with = "super::serde_helpers::bson_datetime"
+    )]
+    pub created_at: DateTime<Utc>,
+    /// Last-update timestamp.
+    #[serde(
+        default = "chrono::Utc::now",
+        with = "super::serde_helpers::bson_datetime"
+    )]
+    pub updated_at: DateTime<Utc>,
+}
+
+impl OnboardedTarget {
+    /// A new target of the given type with a freshly generated webhook secret.
+    pub fn new(name: String, target_type: TargetType) -> Self {
+        let now = Utc::now();
+        let webhook_secret = uuid::Uuid::new_v4().to_string().replace('-', "");
+        Self {
+            id: None,
+            name,
+            target_type,
+            description: None,
+            artifacts: Vec::new(),
+            classification: None,
+            scan_config: TargetScanConfig::default(),
+            scan_schedule: None,
+            webhook_enabled: false,
+            webhook_secret: Some(webhook_secret),
+            findings_count: 0,
+            created_at: now,
+            updated_at: now,
+        }
+    }
+
+    /// The first artifact of the given kind, if present.
+    pub fn first_of(&self, kind: ArtifactKind) -> Option<&Artifact> {
+        self.artifacts.iter().find(|a| a.kind == kind)
+    }
+
+    /// Whether the target has at least one artifact of the given kind.
+    pub fn has(&self, kind: ArtifactKind) -> bool {
+        self.artifacts.iter().any(|a| a.kind == kind)
+    }
+
+    /// The primary code artifact (git repo or source archive), if any.
+    pub fn code_artifact(&self) -> Option<&Artifact> {
+        self.artifacts
+            .iter()
+            .find(|a| matches!(a.kind, ArtifactKind::GitRepo | ArtifactKind::SourceArchive))
+    }
+
+    /// The live-URL artifact, if any.
+    pub fn live_url(&self) -> Option<&Artifact> {
+        self.first_of(ArtifactKind::LiveUrl)
+    }
+}
+
+#[cfg(test)]
+#[allow(clippy::expect_used, clippy::unwrap_used)]
+mod tests {
+    use super::*;
+
+    fn sample_target() -> OnboardedTarget {
+        let mut t = OnboardedTarget::new("acme-web".to_string(), TargetType::WebApp);
+        t.artifacts.push(Artifact::git_repo(
+            "https://git.example.com/acme.git",
+            "main",
+        ));
+        t.artifacts
+            .push(Artifact::live_url("https://acme.example.com"));
+        t
+    }
+
+    #[test]
+    fn onboarded_target_bson_round_trip() {
+        let t = sample_target();
+        let b = bson::to_bson(&t).expect("serialize");
+        let back: OnboardedTarget = bson::from_bson(b.clone()).expect("deserialize");
+        let b2 = bson::to_bson(&back).expect("re-serialize");
+        assert_eq!(b, b2);
+    }
+
+    #[test]
+    fn enum_display_is_snake_case() {
+        assert_eq!(
+            TargetType::FirmwareBareMetal.to_string(),
+            "firmware_bare_metal"
+        );
+        assert_eq!(TargetType::PlcSps.to_string(), "plc_sps");
+        assert_eq!(ArtifactKind::PlcProject.to_string(), "plc_project");
+        assert_eq!(ArtifactKind::MobilePackage.to_string(), "mobile_package");
+    }
+
+    #[test]
+    fn helpers_locate_artifacts() {
+        let t = sample_target();
+        assert!(t.has(ArtifactKind::GitRepo));
+        assert!(t.live_url().is_some());
+        assert!(t.code_artifact().is_some());
+        assert!(!t.has(ArtifactKind::FirmwareImage));
+        assert_eq!(
+            t.first_of(ArtifactKind::GitRepo).map(|a| a.kind),
+            Some(ArtifactKind::GitRepo)
+        );
+    }
+
+    #[test]
+    fn new_target_generates_webhook_secret() {
+        let t = OnboardedTarget::new("t".to_string(), TargetType::BackendService);
+        let secret = t.webhook_secret.expect("secret present");
+        assert_eq!(secret.len(), 32);
+        assert!(!secret.contains('-'));
+    }
+
+    #[test]
+    fn dast_auth_folds_into_artifact_auth() {
+        let dast = DastAuthConfig {
+            method: "bearer".to_string(),
+            login_url: Some("https://x/login".to_string()),
+            username: Some("user".to_string()),
+            password: Some("pw".to_string()),
+            token: Some("tok".to_string()),
+            headers: None,
+        };
+        let auth = ArtifactAuth::from(dast);
+        assert_eq!(auth.method, "bearer");
+        // Bearer token wins over password.
+        assert_eq!(auth.secret.as_deref(), Some("tok"));
+        assert_eq!(auth.login_url.as_deref(), Some("https://x/login"));
+    }
+
+    #[test]
+    fn each_artifact_gets_a_unique_id() {
+        let a = Artifact::firmware_image("fw.bin");
+        let b = Artifact::firmware_image("fw.bin");
+        assert_ne!(a.id, b.id);
+    }
+}

compliance-core/src/models/scan.rs

@@ -3,7 +3,7 @@ use serde::{Deserialize, Serialize};
 
 use super::repository::ScanTrigger;
 
-#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
+#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
 #[serde(rename_all = "lowercase")]
 pub enum ScanType {
     Sast,
@@ -16,6 +16,14 @@ pub enum ScanType {
     SecretDetection,
     Lint,
     CodeReview,
+    /// Static analysis of a firmware image (unpack + component CVE).
+    FirmwareStatic,
+    /// Control-logic security analysis of PLC / SPS programs.
+    PlcControlLogic,
+    /// Static analysis of a mobile package (APK / AAB / IPA).
+    MobileStatic,
+    /// Static analysis of a container image.
+    ContainerScan,
 }
 
 impl std::fmt::Display for ScanType {
@@ -31,6 +39,10 @@ impl std::fmt::Display for ScanType {
             Self::SecretDetection => write!(f, "secret_detection"),
             Self::Lint => write!(f, "lint"),
             Self::CodeReview => write!(f, "code_review"),
+            Self::FirmwareStatic => write!(f, "firmware_static"),
+            Self::PlcControlLogic => write!(f, "plc_control_logic"),
+            Self::MobileStatic => write!(f, "mobile_static"),
+            Self::ContainerScan => write!(f, "container_scan"),
         }
     }
 }
@@ -47,6 +59,8 @@ pub enum ScanRunStatus {
 #[serde(rename_all = "snake_case")]
 pub enum ScanPhase {
     ChangeDetection,
+    ArtifactIngest,
+    Classification,
     Sast,
     SbomGeneration,
     CveScanning,
@@ -55,6 +69,10 @@ pub enum ScanPhase {
     LintScanning,
     CodeReview,
     GraphBuilding,
+    FirmwareStatic,
+    PlcAnalysis,
+    MobileStatic,
+    ContainerScan,
     LlmTriage,
     IssueCreation,
     DastScanning,

compliance-core/src/scan_matrix.rs

@@ -0,0 +1,379 @@
+//! The scan-applicability matrix.
+//!
+//! Which scans are possible for a target is a function of its [`TargetType`] and
+//! which [`ArtifactKind`]s are actually present: SAST needs code, DAST needs a
+//! running URL, firmware-static analysis needs a firmware image, and so on. This
+//! module encodes that as a table — one rule set per target type — and resolves
+//! it against a concrete [`OnboardedTarget`] into a list of [`ScanOption`]s the
+//! onboarding wizard and the scan pipeline both consume.
+
+use crate::models::{ArtifactKind, OnboardedTarget, ScanType, TargetType};
+
+/// What an artifact a scan needs in order to run.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ArtifactRequirement {
+    /// Source code — a git repo or a source archive.
+    Code,
+    /// A reachable running instance (live URL / endpoint).
+    RunningUrl,
+    /// A firmware image / binary blob.
+    Firmware,
+    /// A PLC project (PLCopen XML or Structured Text).
+    Plc,
+    /// A mobile package (APK / AAB / IPA).
+    Mobile,
+    /// A container image.
+    Container,
+    /// No specific artifact required.
+    Any,
+}
+
+/// A static rule: this scan applies to a target type, needs this artifact, and
+/// defaults on/off. The rationale explains the entry to the user.
+#[derive(Debug, Clone, Copy)]
+pub struct ScanRule {
+    /// The scan this rule governs.
+    pub scan: ScanType,
+    /// Whether the scan is on by default (only when its artifact is present).
+    pub default_on: bool,
+    /// Human-readable explanation of what the scan does here.
+    pub rationale: &'static str,
+    /// The artifact the scan consumes.
+    pub requires: ArtifactRequirement,
+}
+
+impl ScanRule {
+    const fn new(
+        scan: ScanType,
+        default_on: bool,
+        rationale: &'static str,
+        requires: ArtifactRequirement,
+    ) -> Self {
+        Self {
+            scan,
+            default_on,
+            rationale,
+            requires,
+        }
+    }
+}
+
+/// A resolved scan choice for a specific target: a rule intersected with the
+/// artifacts actually present. `blocked_reason` is `Some` when the required
+/// artifact is missing.
+#[derive(Debug, Clone)]
+pub struct ScanOption {
+    /// The scan.
+    pub scan: ScanType,
+    /// Whether to pre-select the scan (false when blocked).
+    pub default_on: bool,
+    /// Why the scan is offered.
+    pub rationale: String,
+    /// The artifact kind the scan needs, if any specific one.
+    pub required_artifact: Option<ArtifactKind>,
+    /// Set when the required artifact is absent, explaining the block.
+    pub blocked_reason: Option<String>,
+}
+
+/// The SAST umbrella: every static-analysis sub-scan that runs over source code.
+fn sast_umbrella() -> Vec<ScanRule> {
+    use ArtifactRequirement::Code;
+    vec![
+        ScanRule::new(
+            ScanType::Sast,
+            true,
+            "Static analysis (Semgrep) over source",
+            Code,
+        ),
+        ScanRule::new(
+            ScanType::Sbom,
+            true,
+            "Software bill of materials from source",
+            Code,
+        ),
+        ScanRule::new(
+            ScanType::Cve,
+            true,
+            "Match dependencies against known CVEs",
+            Code,
+        ),
+        ScanRule::new(
+            ScanType::SecretDetection,
+            true,
+            "Scan source for committed secrets",
+            Code,
+        ),
+        ScanRule::new(ScanType::Lint, true, "Language linters over source", Code),
+        ScanRule::new(
+            ScanType::Gdpr,
+            true,
+            "GDPR data-handling pattern checks",
+            Code,
+        ),
+        ScanRule::new(
+            ScanType::OAuth,
+            true,
+            "OAuth misconfiguration patterns",
+            Code,
+        ),
+        ScanRule::new(
+            ScanType::Graph,
+            true,
+            "Build the code graph for impact analysis",
+            Code,
+        ),
+        ScanRule::new(
+            ScanType::CodeReview,
+            false,
+            "LLM code review over changed source",
+            Code,
+        ),
+    ]
+}
+
+/// The rule set for a target type. Scans that are never applicable to a type are
+/// simply absent (e.g. DAST is not listed for a PLC target).
+pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
+    use ArtifactRequirement::{Firmware, Mobile, Plc, RunningUrl};
+    match target_type {
+        TargetType::WebApp | TargetType::BackendService => {
+            let mut r = sast_umbrella();
+            r.push(ScanRule::new(
+                ScanType::Dast,
+                true,
+                "Dynamic scan of the running endpoint",
+                RunningUrl,
+            ));
+            r
+        }
+        TargetType::DesktopApp => sast_umbrella(),
+        TargetType::AndroidApp | TargetType::IosApp => {
+            let mut r = sast_umbrella();
+            r.push(ScanRule::new(
+                ScanType::MobileStatic,
+                true,
+                "Static analysis of the mobile package (manifest, permissions, libs)",
+                Mobile,
+            ));
+            r
+        }
+        TargetType::FirmwareBareMetal | TargetType::FirmwareRtos => {
+            let mut r = sast_umbrella();
+            r.push(ScanRule::new(
+                ScanType::FirmwareStatic,
+                true,
+                "Unpack and statically analyze the firmware image",
+                Firmware,
+            ));
+            r.push(ScanRule::new(
+                ScanType::Sbom,
+                true,
+                "SBOM from the firmware image (binwalk / tramiton)",
+                Firmware,
+            ));
+            r.push(ScanRule::new(
+                ScanType::Cve,
+                true,
+                "Match firmware components against known CVEs",
+                Firmware,
+            ));
+            r
+        }
+        TargetType::EmbeddedLinuxYocto => {
+            let mut r = sast_umbrella();
+            r.push(ScanRule::new(
+                ScanType::FirmwareStatic,
+                true,
+                "EMBA / binwalk static analysis of the image",
+                Firmware,
+            ));
+            r.push(ScanRule::new(
+                ScanType::Sbom,
+                true,
+                "SBOM from image layers / recipes",
+                Firmware,
+            ));
+            r.push(ScanRule::new(
+                ScanType::Cve,
+                true,
+                "Match image components against known CVEs",
+                Firmware,
+            ));
+            r.push(ScanRule::new(
+                ScanType::Dast,
+                false,
+                "Dynamic scan of exposed network services (if any)",
+                RunningUrl,
+            ));
+            r
+        }
+        TargetType::PlcSps => vec![ScanRule::new(
+            ScanType::PlcControlLogic,
+            true,
+            "Control-logic security rules over the PLC program",
+            Plc,
+        )],
+    }
+}
+
+/// Whether an active penetration test is applicable to this target type.
+///
+/// Pentest runs as its own session (not a [`ScanType`] scan) and needs a
+/// reachable running target, so it is offered only for the network-reachable
+/// families.
+pub fn supports_pentest(target_type: TargetType) -> bool {
+    matches!(
+        target_type,
+        TargetType::WebApp
+            | TargetType::BackendService
+            | TargetType::AndroidApp
+            | TargetType::IosApp
+            | TargetType::EmbeddedLinuxYocto
+    )
+}
+
+/// The representative artifact kind a requirement is satisfied by.
+fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
+    match req {
+        ArtifactRequirement::Code => Some(ArtifactKind::GitRepo),
+        ArtifactRequirement::RunningUrl => Some(ArtifactKind::LiveUrl),
+        ArtifactRequirement::Firmware => Some(ArtifactKind::FirmwareImage),
+        ArtifactRequirement::Plc => Some(ArtifactKind::PlcProject),
+        ArtifactRequirement::Mobile => Some(ArtifactKind::MobilePackage),
+        ArtifactRequirement::Container => Some(ArtifactKind::ContainerImage),
+        ArtifactRequirement::Any => None,
+    }
+}
+
+/// Whether the target carries an artifact that satisfies the requirement.
+fn requirement_satisfied(req: ArtifactRequirement, target: &OnboardedTarget) -> bool {
+    match req {
+        ArtifactRequirement::Code => target.code_artifact().is_some(),
+        ArtifactRequirement::RunningUrl => target.has(ArtifactKind::LiveUrl),
+        ArtifactRequirement::Firmware => target.has(ArtifactKind::FirmwareImage),
+        ArtifactRequirement::Plc => target.has(ArtifactKind::PlcProject),
+        ArtifactRequirement::Mobile => target.has(ArtifactKind::MobilePackage),
+        ArtifactRequirement::Container => target.has(ArtifactKind::ContainerImage),
+        ArtifactRequirement::Any => true,
+    }
+}
+
+/// Resolve the matrix for a concrete target into the scans it can run, marking
+/// any whose required artifact is missing as blocked.
+pub fn applicable_scans(target: &OnboardedTarget) -> Vec<ScanOption> {
+    rules_for(target.target_type)
+        .into_iter()
+        .map(|rule| {
+            let satisfied = requirement_satisfied(rule.requires, target);
+            let required_artifact = representative_kind(rule.requires);
+            let blocked_reason = if satisfied {
+                None
+            } else {
+                Some(match required_artifact {
+                    Some(kind) => format!("no {kind} artifact provided"),
+                    None => "required artifact missing".to_string(),
+                })
+            };
+            ScanOption {
+                scan: rule.scan,
+                default_on: rule.default_on && satisfied,
+                rationale: rule.rationale.to_string(),
+                required_artifact,
+                blocked_reason,
+            }
+        })
+        .collect()
+}
+
+#[cfg(test)]
+#[allow(clippy::expect_used, clippy::unwrap_used)]
+mod tests {
+    use super::*;
+    use crate::models::{Artifact, PlcFormat};
+
+    fn target_with(target_type: TargetType, artifacts: Vec<Artifact>) -> OnboardedTarget {
+        let mut t = OnboardedTarget::new("t".to_string(), target_type);
+        t.artifacts = artifacts;
+        t
+    }
+
+    fn option<'a>(opts: &'a [ScanOption], scan: ScanType) -> Option<&'a ScanOption> {
+        opts.iter().find(|o| o.scan == scan)
+    }
+
+    #[test]
+    fn webapp_with_code_and_url_offers_sast_and_dast() {
+        let t = target_with(
+            TargetType::WebApp,
+            vec![
+                Artifact::git_repo("u", "main"),
+                Artifact::live_url("http://x"),
+            ],
+        );
+        let opts = applicable_scans(&t);
+        let sast = option(&opts, ScanType::Sast).expect("sast offered");
+        assert!(sast.default_on && sast.blocked_reason.is_none());
+        let dast = option(&opts, ScanType::Dast).expect("dast offered");
+        assert!(dast.default_on && dast.blocked_reason.is_none());
+    }
+
+    #[test]
+    fn webapp_without_url_blocks_dast() {
+        let t = target_with(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
+        let opts = applicable_scans(&t);
+        let dast = option(&opts, ScanType::Dast).expect("dast listed");
+        assert!(!dast.default_on);
+        assert!(dast.blocked_reason.is_some());
+        assert_eq!(dast.required_artifact, Some(ArtifactKind::LiveUrl));
+    }
+
+    #[test]
+    fn firmware_offers_firmware_static_and_not_dast() {
+        let t = target_with(
+            TargetType::FirmwareBareMetal,
+            vec![Artifact::firmware_image("fw.bin")],
+        );
+        let opts = applicable_scans(&t);
+        let fw = option(&opts, ScanType::FirmwareStatic).expect("firmware static offered");
+        assert!(fw.default_on && fw.blocked_reason.is_none());
+        assert!(option(&opts, ScanType::Dast).is_none());
+    }
+
+    #[test]
+    fn plc_offers_only_control_logic() {
+        let t = target_with(
+            TargetType::PlcSps,
+            vec![Artifact::plc_project("p.xml", PlcFormat::PlcopenXml)],
+        );
+        let opts = applicable_scans(&t);
+        assert_eq!(opts.len(), 1);
+        assert_eq!(opts[0].scan, ScanType::PlcControlLogic);
+        assert!(opts[0].default_on);
+    }
+
+    #[test]
+    fn pentest_support_matches_reachable_families() {
+        assert!(supports_pentest(TargetType::WebApp));
+        assert!(supports_pentest(TargetType::BackendService));
+        assert!(!supports_pentest(TargetType::PlcSps));
+        assert!(!supports_pentest(TargetType::FirmwareBareMetal));
+        assert!(!supports_pentest(TargetType::DesktopApp));
+    }
+
+    #[test]
+    fn every_target_type_has_at_least_one_rule() {
+        for tt in [
+            TargetType::WebApp,
+            TargetType::BackendService,
+            TargetType::DesktopApp,
+            TargetType::AndroidApp,
+            TargetType::IosApp,
+            TargetType::FirmwareBareMetal,
+            TargetType::FirmwareRtos,
+            TargetType::EmbeddedLinuxYocto,
+            TargetType::PlcSps,
+        ] {
+            assert!(!rules_for(tt).is_empty(), "{tt} has no rules");
+        }
+    }
+}

compliance-core/src/traits/classifier.rs

@@ -0,0 +1,51 @@
+//! The target-classification port.
+//!
+//! A [`TargetClassifier`] inspects a target's artifacts (and optionally their
+//! ingested working directories) and proposes one or more [`ClassifierVerdict`]s
+//! — a target type, a confidence, and the facts the decision rested on. Concrete
+//! classifiers live in the agent (language/build-system fingerprinting, a
+//! firmware detector backed by tramiton, etc.); a registry merges and ranks
+//! their verdicts. This mirrors the [`crate::traits::Scanner`] port so the two
+//! read the same way.
+
+use std::collections::HashMap;
+use std::path::PathBuf;
+
+use crate::error::CoreError;
+use crate::models::{Artifact, DetectedFact, TargetType};
+
+/// Everything a classifier needs to reason about a target.
+pub struct ClassificationInput<'a> {
+    /// The artifacts declared for the target.
+    pub artifacts: &'a [Artifact],
+    /// Ingested working paths, keyed by [`Artifact::id`]. Absent for artifacts
+    /// with no on-disk form (e.g. a live URL).
+    pub working_paths: &'a HashMap<String, PathBuf>,
+    /// Free-form description of the target, if provided.
+    pub description: Option<&'a str>,
+}
+
+/// A single classifier's proposal for a target.
+pub struct ClassifierVerdict {
+    /// The proposed target type.
+    pub target_type: TargetType,
+    /// Confidence in `[0.0, 1.0]`.
+    pub confidence: f32,
+    /// Facts that informed the proposal.
+    pub facts: Vec<DetectedFact>,
+    /// Human-readable explanation.
+    pub rationale: String,
+}
+
+/// A source of target-type classification.
+#[allow(async_fn_in_trait)]
+pub trait TargetClassifier: Send + Sync {
+    /// Stable identifier for this classifier (recorded in `detected_by`).
+    fn name(&self) -> &str;
+
+    /// Propose zero or more ranked verdicts for the given input.
+    async fn classify(
+        &self,
+        input: &ClassificationInput<'_>,
+    ) -> Result<Vec<ClassifierVerdict>, CoreError>;
+}

compliance-core/src/traits/mod.rs

@@ -1,9 +1,11 @@
+pub mod classifier;
 pub mod dast_agent;
 pub mod graph_builder;
 pub mod issue_tracker;
 pub mod pentest_tool;
 pub mod scanner;
 
+pub use classifier::{ClassificationInput, ClassifierVerdict, TargetClassifier};
 pub use dast_agent::{DastAgent, DastContext, DiscoveredEndpoint, EndpointParameter};
 pub use graph_builder::{LanguageParser, ParseOutput};
 pub use issue_tracker::IssueTracker;