feat(api): onboarding endpoints for unified targets (#131)

REST surface the wizard drives onboarding through:
- GET/POST /api/v1/targets (list paginated / create)
- GET/PATCH/DELETE /api/v1/targets/{id} (fetch / update / delete + cascade
  findings/scans by repo_id)
- POST /api/v1/targets/{id}/artifacts (attach an artifact by reference)
- GET /api/v1/targets/{id}/applicable-scans (scan matrix + pentest support)
- POST /api/v1/targets/{id}/detect (kind-based classification — no ingest;
  deep post-ingest detection is a follow-up)

Follows the existing axum handler/route/DTO conventions (ApiResponse,
PaginationParams, tenant_db, collect_cursor_async, TenantCtx). Multipart artifact
upload and the scan-trigger endpoint (needs the unified pipeline, #133) are
follow-ups.

Also fixes the TestServer db-name prefix (was 37 chars, over the pool's 30-char
cap) which had silently broken every API integration test locally.

3 HTTP integration tests (create/list/applicable-scans, detect->PLC,
add-artifact/delete) — pass against local Mongo.

Closes #131.

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

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

@@ -9,6 +9,7 @@ pub mod help_chat;
 pub mod issues;
 pub mod mcp_tokens;
 pub mod notifications;
+pub mod onboarding;
 pub mod pentest_handlers;
 pub use pentest_handlers as pentest;
 pub mod repos;

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

@@ -0,0 +1,350 @@
+//! Onboarding API — CRUD for unified targets, artifact add, classification, and
+//! the scan-applicability matrix. The wizard (and future integrations) drive
+//! onboarding through these endpoints.
+
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use axum::extract::{Extension, Path, Query};
+use axum::http::StatusCode;
+use axum::Json;
+use mongodb::bson::{doc, oid::ObjectId, to_bson};
+use serde::{Deserialize, Serialize};
+
+use compliance_core::models::{
+    Artifact, ArtifactKind, ComplianceProfile, OnboardedTarget, PlcFormat, TargetScanConfig,
+    TargetType,
+};
+use compliance_core::scan_matrix::{applicable_scans, supports_pentest};
+use compliance_core::tenant_ctx::TenantCtx;
+
+use crate::agent::ComplianceAgent;
+use crate::classify::{classify_target, MockFirmwareDetector};
+
+use super::dto::tenant_db;
+use super::{collect_cursor_async, ApiResponse, PaginationParams};
+
+type AgentExt = Extension<Arc<ComplianceAgent>>;
+
+/// A client-supplied artifact spec. The server builds the [`Artifact`] (and its
+/// id) from it, so clients never set internal fields.
+#[derive(Deserialize)]
+pub struct ArtifactInput {
+    pub kind: ArtifactKind,
+    pub source_ref: String,
+    #[serde(default)]
+    pub branch: Option<String>,
+    #[serde(default)]
+    pub plc_format: Option<PlcFormat>,
+}
+
+impl ArtifactInput {
+    fn build(&self) -> Artifact {
+        let s = self.source_ref.clone();
+        match self.kind {
+            ArtifactKind::GitRepo => {
+                Artifact::git_repo(s, self.branch.clone().unwrap_or_else(|| "main".to_string()))
+            }
+            ArtifactKind::LiveUrl => Artifact::live_url(s),
+            ArtifactKind::FirmwareImage => Artifact::firmware_image(s),
+            ArtifactKind::SourceArchive => Artifact::source_archive(s),
+            ArtifactKind::MobilePackage => Artifact::mobile_package(s),
+            ArtifactKind::ContainerImage => Artifact::container_image(s),
+            ArtifactKind::PlcProject => {
+                Artifact::plc_project(s, self.plc_format.unwrap_or(PlcFormat::PlcopenXml))
+            }
+            ArtifactKind::PlaintextDescription => Artifact::plaintext(s),
+        }
+    }
+}
+
+#[derive(Deserialize)]
+pub struct CreateTargetRequest {
+    pub name: String,
+    pub target_type: TargetType,
+    #[serde(default)]
+    pub description: Option<String>,
+    #[serde(default)]
+    pub artifacts: Vec<ArtifactInput>,
+}
+
+#[derive(Deserialize)]
+pub struct UpdateTargetRequest {
+    pub name: Option<String>,
+    pub target_type: Option<TargetType>,
+    pub scan_config: Option<TargetScanConfig>,
+    pub compliance_profile: Option<ComplianceProfile>,
+    pub scan_schedule: Option<String>,
+}
+
+/// One applicable-scan option, serialized for the wizard.
+#[derive(Serialize)]
+pub struct ScanOptionDto {
+    pub scan: String,
+    pub default_on: bool,
+    pub rationale: String,
+    pub required_artifact: Option<String>,
+    pub blocked_reason: Option<String>,
+}
+
+#[derive(Serialize)]
+pub struct ApplicableScansResponse {
+    pub scans: Vec<ScanOptionDto>,
+    pub pentest_supported: bool,
+}
+
+fn parse_oid(id: &str) -> Result<ObjectId, StatusCode> {
+    ObjectId::parse_str(id).map_err(|_| StatusCode::BAD_REQUEST)
+}
+
+/// GET /api/v1/targets — list onboarded targets (paginated).
+#[tracing::instrument(skip_all)]
+pub async fn list_targets(
+    Extension(agent): AgentExt,
+    tenant: TenantCtx,
+    Query(params): Query<PaginationParams>,
+) -> Result<Json<ApiResponse<Vec<OnboardedTarget>>>, StatusCode> {
+    let db = tenant_db(&agent, &tenant).await?;
+    let skip = (params.page.saturating_sub(1)) * params.limit as u64;
+    let total = db
+        .onboarded_targets()
+        .count_documents(doc! {})
+        .await
+        .unwrap_or(0);
+    let targets = match db
+        .onboarded_targets()
+        .find(doc! {})
+        .skip(skip)
+        .limit(params.limit)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch onboarded targets: {e}");
+            Vec::new()
+        }
+    };
+    Ok(Json(ApiResponse {
+        data: targets,
+        total: Some(total),
+        page: Some(params.page),
+    }))
+}
+
+/// POST /api/v1/targets — create an onboarded target.
+#[tracing::instrument(skip_all)]
+pub async fn create_target(
+    Extension(agent): AgentExt,
+    tenant: TenantCtx,
+    Json(req): Json<CreateTargetRequest>,
+) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
+    let mut target = OnboardedTarget::new(req.name, req.target_type);
+    target.description = req.description;
+    target.artifacts = req.artifacts.iter().map(ArtifactInput::build).collect();
+
+    let db = tenant_db(&agent, &tenant).await?;
+    let res = db
+        .onboarded_targets()
+        .insert_one(&target)
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+    target.id = res.inserted_id.as_object_id();
+    Ok(Json(ApiResponse {
+        data: target,
+        total: None,
+        page: None,
+    }))
+}
+
+/// GET /api/v1/targets/{id} — fetch one target.
+#[tracing::instrument(skip_all, fields(target_id = %id))]
+pub async fn get_target(
+    Extension(agent): AgentExt,
+    tenant: TenantCtx,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
+    let oid = parse_oid(&id)?;
+    let db = tenant_db(&agent, &tenant).await?;
+    let target = db
+        .onboarded_targets()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
+        .ok_or(StatusCode::NOT_FOUND)?;
+    Ok(Json(ApiResponse {
+        data: target,
+        total: None,
+        page: None,
+    }))
+}
+
+/// PATCH /api/v1/targets/{id} — update mutable fields.
+#[tracing::instrument(skip_all, fields(target_id = %id))]
+pub async fn update_target(
+    Extension(agent): AgentExt,
+    tenant: TenantCtx,
+    Path(id): Path<String>,
+    Json(req): Json<UpdateTargetRequest>,
+) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
+    let oid = parse_oid(&id)?;
+    let db = tenant_db(&agent, &tenant).await?;
+
+    let mut set = doc! { "updated_at": mongodb::bson::DateTime::now() };
+    if let Some(name) = req.name {
+        set.insert("name", name);
+    }
+    if let Some(tt) = req.target_type {
+        set.insert(
+            "target_type",
+            to_bson(&tt).map_err(|_| StatusCode::BAD_REQUEST)?,
+        );
+    }
+    if let Some(sc) = req.scan_config {
+        set.insert(
+            "scan_config",
+            to_bson(&sc).map_err(|_| StatusCode::BAD_REQUEST)?,
+        );
+    }
+    if let Some(cp) = req.compliance_profile {
+        set.insert(
+            "compliance_profile",
+            to_bson(&cp).map_err(|_| StatusCode::BAD_REQUEST)?,
+        );
+    }
+    if let Some(ss) = req.scan_schedule {
+        set.insert("scan_schedule", ss);
+    }
+
+    db.onboarded_targets()
+        .update_one(doc! { "_id": oid }, doc! { "$set": set })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+
+    get_target(Extension(agent), tenant, Path(id)).await
+}
+
+/// DELETE /api/v1/targets/{id} — remove the target and its findings/scans.
+#[tracing::instrument(skip_all, fields(target_id = %id))]
+pub async fn delete_target(
+    Extension(agent): AgentExt,
+    tenant: TenantCtx,
+    Path(id): Path<String>,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    let oid = parse_oid(&id)?;
+    let db = tenant_db(&agent, &tenant).await?;
+    db.onboarded_targets()
+        .delete_one(doc! { "_id": oid })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+    // Cascade the collections keyed by repo_id == target id (best-effort).
+    let by_repo = doc! { "repo_id": &id };
+    let _ = db.findings().delete_many(by_repo.clone()).await;
+    let _ = db.scan_runs().delete_many(by_repo.clone()).await;
+    let _ = db.sbom_entries().delete_many(by_repo.clone()).await;
+    let _ = db.cve_alerts().delete_many(by_repo).await;
+    Ok(Json(serde_json::json!({ "status": "deleted" })))
+}
+
+/// POST /api/v1/targets/{id}/artifacts — attach an artifact (by reference).
+#[tracing::instrument(skip_all, fields(target_id = %id))]
+pub async fn add_artifact(
+    Extension(agent): AgentExt,
+    tenant: TenantCtx,
+    Path(id): Path<String>,
+    Json(input): Json<ArtifactInput>,
+) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
+    let oid = parse_oid(&id)?;
+    let db = tenant_db(&agent, &tenant).await?;
+    let artifact = to_bson(&input.build()).map_err(|_| StatusCode::BAD_REQUEST)?;
+    db.onboarded_targets()
+        .update_one(
+            doc! { "_id": oid },
+            doc! { "$push": { "artifacts": artifact }, "$set": { "updated_at": mongodb::bson::DateTime::now() } },
+        )
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+    get_target(Extension(agent), tenant, Path(id)).await
+}
+
+/// GET /api/v1/targets/{id}/applicable-scans — the scan-applicability matrix.
+#[tracing::instrument(skip_all, fields(target_id = %id))]
+pub async fn applicable_scans_for_target(
+    Extension(agent): AgentExt,
+    tenant: TenantCtx,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<ApplicableScansResponse>>, StatusCode> {
+    let oid = parse_oid(&id)?;
+    let db = tenant_db(&agent, &tenant).await?;
+    let target = db
+        .onboarded_targets()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
+        .ok_or(StatusCode::NOT_FOUND)?;
+
+    let scans = applicable_scans(&target)
+        .into_iter()
+        .map(|o| ScanOptionDto {
+            scan: o.scan.to_string(),
+            default_on: o.default_on,
+            rationale: o.rationale,
+            required_artifact: o.required_artifact.map(|k| k.to_string()),
+            blocked_reason: o.blocked_reason,
+        })
+        .collect();
+
+    Ok(Json(ApiResponse {
+        data: ApplicableScansResponse {
+            scans,
+            pentest_supported: supports_pentest(target.target_type),
+        },
+        total: None,
+        page: None,
+    }))
+}
+
+/// POST /api/v1/targets/{id}/detect — classify the target from its artifacts.
+///
+/// This is the lightweight pass: it classifies from artifact kinds without
+/// ingesting (cloning) sources, so it returns immediately. Deep detection (after
+/// ingest, with tramiton firmware analysis) is a follow-up background step.
+#[tracing::instrument(skip_all, fields(target_id = %id))]
+pub async fn detect_target(
+    Extension(agent): AgentExt,
+    tenant: TenantCtx,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
+    let oid = parse_oid(&id)?;
+    let db = tenant_db(&agent, &tenant).await?;
+    let mut target = db
+        .onboarded_targets()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
+        .ok_or(StatusCode::NOT_FOUND)?;
+
+    // No ingested working paths here → kind-based classification only; the mock
+    // firmware detector is never invoked (no firmware working path present).
+    let empty = HashMap::new();
+    let detector = MockFirmwareDetector { detection: None };
+    let classification = classify_target(&target, &empty, &detector)
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+
+    let classification_bson =
+        to_bson(&classification).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+    db.onboarded_targets()
+        .update_one(
+            doc! { "_id": oid },
+            doc! { "$set": { "classification": classification_bson, "updated_at": mongodb::bson::DateTime::now() } },
+        )
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+    target.classification = Some(classification);
+
+    Ok(Json(ApiResponse {
+        data: target,
+        total: None,
+        page: None,
+    }))
+}

compliance-agent/src/api/routes.rs

@@ -25,6 +25,29 @@ pub fn build_router() -> Router {
             "/api/v1/repositories/{id}/webhook-config",
             get(handlers::get_webhook_config),
         )
+        // Unified onboarding targets (#131).
+        .route(
+            "/api/v1/targets",
+            get(handlers::onboarding::list_targets).post(handlers::onboarding::create_target),
+        )
+        .route(
+            "/api/v1/targets/{id}",
+            get(handlers::onboarding::get_target)
+                .patch(handlers::onboarding::update_target)
+                .delete(handlers::onboarding::delete_target),
+        )
+        .route(
+            "/api/v1/targets/{id}/artifacts",
+            post(handlers::onboarding::add_artifact),
+        )
+        .route(
+            "/api/v1/targets/{id}/applicable-scans",
+            get(handlers::onboarding::applicable_scans_for_target),
+        )
+        .route(
+            "/api/v1/targets/{id}/detect",
+            post(handlers::onboarding::detect_target),
+        )
         .route("/api/v1/findings", get(handlers::list_findings))
         .route("/api/v1/findings/{id}", get(handlers::get_finding))
         .route(

compliance-agent/tests/common/mod.rs

@@ -25,8 +25,9 @@ impl TestServer {
         let mongodb_uri = std::env::var("TEST_MONGODB_URI")
             .unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
 
-        // Unique database name per test run to avoid collisions
-        let db_name = format!("test_{}", uuid::Uuid::new_v4().simple());
+        // Unique db-name prefix per run. Must fit the pool's 30-char cap
+        // (`<prefix>_<32 hex>` <= 63), so use a 16-hex-char suffix.
+        let db_name = format!("t_{}", &uuid::Uuid::new_v4().simple().to_string()[..16]);
 
         let db_pool = DatabasePool::connect(&mongodb_uri, &db_name)
             .await

compliance-agent/tests/integration/api/mod.rs

@@ -2,5 +2,6 @@ mod cascade_delete;
 mod dast;
 mod findings;
 mod health;
+mod onboarding;
 mod repositories;
 mod stats;

compliance-agent/tests/integration/api/onboarding.rs

@@ -0,0 +1,115 @@
+use crate::common::TestServer;
+use serde_json::json;
+
+#[tokio::test]
+async fn create_list_and_applicable_scans() {
+    let server = TestServer::start().await;
+
+    // Initially empty.
+    let resp = server.get("/api/v1/targets").await;
+    assert_eq!(resp.status(), 200);
+    let body: serde_json::Value = resp.json().await.unwrap();
+    assert_eq!(body["data"].as_array().unwrap().len(), 0);
+
+    // Create a web-app target with a git repo + a live URL.
+    let resp = server
+        .post(
+            "/api/v1/targets",
+            &json!({
+                "name": "acme-web",
+                "target_type": "web_app",
+                "artifacts": [
+                    { "kind": "git_repo", "source_ref": "https://git/acme.git", "branch": "main" },
+                    { "kind": "live_url", "source_ref": "https://acme.example.com" }
+                ]
+            }),
+        )
+        .await;
+    assert_eq!(resp.status(), 200);
+    let body: serde_json::Value = resp.json().await.unwrap();
+    let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
+    assert!(!id.is_empty());
+    assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 2);
+
+    // List returns it.
+    let resp = server.get("/api/v1/targets").await;
+    let body: serde_json::Value = resp.json().await.unwrap();
+    assert_eq!(body["data"].as_array().unwrap().len(), 1);
+
+    // Applicable scans: SAST present + DAST offered (live URL present), pentest supported.
+    let resp = server
+        .get(&format!("/api/v1/targets/{id}/applicable-scans"))
+        .await;
+    assert_eq!(resp.status(), 200);
+    let body: serde_json::Value = resp.json().await.unwrap();
+    let scans = body["data"]["scans"].as_array().unwrap();
+    let names: Vec<&str> = scans.iter().filter_map(|s| s["scan"].as_str()).collect();
+    assert!(names.contains(&"sast"));
+    assert!(names.contains(&"dast"));
+    assert_eq!(body["data"]["pentest_supported"], true);
+
+    server.cleanup().await;
+}
+
+#[tokio::test]
+async fn detect_classifies_a_plc_target() {
+    let server = TestServer::start().await;
+
+    // A PLC project artifact is a strong kind-based signal.
+    let resp = server
+        .post(
+            "/api/v1/targets",
+            &json!({
+                "name": "line-controller",
+                "target_type": "backend_service", // deliberately wrong; detect should suggest PLC
+                "artifacts": [
+                    { "kind": "plc_project", "source_ref": "line.xml", "plc_format": "plcopen_xml" }
+                ]
+            }),
+        )
+        .await;
+    let body: serde_json::Value = resp.json().await.unwrap();
+    let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
+
+    let resp = server
+        .post(&format!("/api/v1/targets/{id}/detect"), &json!({}))
+        .await;
+    assert_eq!(resp.status(), 200);
+    let body: serde_json::Value = resp.json().await.unwrap();
+    assert_eq!(body["data"]["classification"]["suggested"], "plc_sps");
+
+    server.cleanup().await;
+}
+
+#[tokio::test]
+async fn add_artifact_and_delete_target() {
+    let server = TestServer::start().await;
+
+    let resp = server
+        .post(
+            "/api/v1/targets",
+            &json!({ "name": "svc", "target_type": "backend_service" }),
+        )
+        .await;
+    let body: serde_json::Value = resp.json().await.unwrap();
+    let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
+
+    // Attach a git repo.
+    let resp = server
+        .post(
+            &format!("/api/v1/targets/{id}/artifacts"),
+            &json!({ "kind": "git_repo", "source_ref": "https://git/svc.git" }),
+        )
+        .await;
+    assert_eq!(resp.status(), 200);
+    let body: serde_json::Value = resp.json().await.unwrap();
+    assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 1);
+
+    // Delete it.
+    let resp = server.delete(&format!("/api/v1/targets/{id}")).await;
+    assert_eq!(resp.status(), 200);
+    let resp = server.get(&format!("/api/v1/targets/{id}")).await;
+    assert_eq!(resp.status(), 404);
+
+    server.cleanup().await;
+}