feat(werkbank): runner queue endpoints + result persistence (WB-05) (#207)

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

@@ -14,6 +14,7 @@ pub mod pentest_handlers;
 pub use pentest_handlers as pentest;
 pub mod sbom;
 pub mod scans;
+pub mod werkbank_jobs;
 
 // Re-export all handler functions so routes.rs can use `handlers::function_name`
 pub use dto::*;

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

@@ -0,0 +1,193 @@
+//! Werkbank runner endpoints (`/api/v1/werkbank/jobs/*`).
+//!
+//! The pull API a Werkbank runner talks to: lease a job, heartbeat while it runs,
+//! and post the result back. Machine auth is a **static bearer token**
+//! (`WERKBANK_RUNNER_TOKEN`) — not a Keycloak JWT, because a runner acts across
+//! tenants (each request names its `tenant`). Routes are only mounted when the
+//! token is configured; with none set they don't exist (404).
+//!
+//! On completion the runner's findings are persisted against the job's target,
+//! so a job run by a remote runner lands the same findings an in-process run
+//! would (WB-05, the control-plane cut-over).
+
+use axum::extract::{Extension, Request};
+use axum::http::{header, StatusCode};
+use axum::middleware::Next;
+use axum::response::{IntoResponse, Response};
+use axum::Json;
+use mongodb::bson::doc;
+use secrecy::ExposeSecret;
+use std::time::Duration;
+
+use compliance_core::models::werkbank::{
+    CompleteRequest, CompleteResponse, HeartbeatRequest, JobResult, LeaseRequest,
+};
+
+use super::dto::AgentExt;
+use crate::database::Database;
+use crate::werkbank::JobQueue;
+
+/// Gate the runner endpoints behind the static runner bearer token.
+pub async fn require_runner_token(
+    Extension(agent): AgentExt,
+    request: Request,
+    next: Next,
+) -> Response {
+    let Some(expected) = agent.config.werkbank_runner_token.as_ref() else {
+        return (StatusCode::NOT_FOUND, "werkbank runner API 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(str::trim)
+        .filter(|s| !s.is_empty());
+    let Some(presented) = presented else {
+        return (StatusCode::UNAUTHORIZED, "Missing bearer token").into_response();
+    };
+    if !constant_time_eq(presented, expected.expose_secret()) {
+        return (StatusCode::UNAUTHORIZED, "Invalid runner token").into_response();
+    }
+    next.run(request).await
+}
+
+/// `POST /api/v1/werkbank/jobs/lease` — lease the oldest runnable job, or `204`.
+#[tracing::instrument(skip_all, fields(tenant = %req.tenant, runner = %req.runner_id))]
+pub async fn lease(
+    Extension(agent): AgentExt,
+    Json(req): Json<LeaseRequest>,
+) -> Result<Response, StatusCode> {
+    let queue = JobQueue::new(&tenant_db(&agent, &req.tenant).await?);
+    let leased = queue
+        .lease(
+            &req.runner_id,
+            req.executor,
+            &req.labels,
+            Duration::from_secs(req.lease_ttl_secs),
+            chrono::Utc::now(),
+        )
+        .await
+        .map_err(internal)?;
+    Ok(match leased {
+        Some(job) => Json(job).into_response(),
+        None => StatusCode::NO_CONTENT.into_response(),
+    })
+}
+
+/// `POST /api/v1/werkbank/jobs/heartbeat` — extend the lease; `409` if it's lost.
+#[tracing::instrument(skip_all, fields(tenant = %req.tenant, job = %req.job_id))]
+pub async fn heartbeat(
+    Extension(agent): AgentExt,
+    Json(req): Json<HeartbeatRequest>,
+) -> Result<Response, StatusCode> {
+    let queue = JobQueue::new(&tenant_db(&agent, &req.tenant).await?);
+    let ack = queue
+        .heartbeat(
+            &req.job_id,
+            &req.lease_token,
+            Duration::from_secs(req.lease_ttl_secs),
+            chrono::Utc::now(),
+        )
+        .await
+        .map_err(internal)?;
+    Ok(match ack {
+        Some(ack) => Json(ack).into_response(),
+        // Lease lost — the runner should abandon the job.
+        None => StatusCode::CONFLICT.into_response(),
+    })
+}
+
+/// `POST /api/v1/werkbank/jobs/complete` — record the result and persist findings.
+#[tracing::instrument(skip_all, fields(tenant = %req.tenant, job = %req.job_id))]
+pub async fn complete(
+    Extension(agent): AgentExt,
+    Json(req): Json<CompleteRequest>,
+) -> Result<Json<CompleteResponse>, StatusCode> {
+    let db = tenant_db(&agent, &req.tenant).await?;
+    let queue = JobQueue::new(&db);
+    let now = chrono::Utc::now();
+    let recorded = queue
+        .complete(&req.job_id, &req.lease_token, &req.result, now)
+        .await
+        .map_err(internal)?;
+
+    // Only persist findings for the run that actually recorded the result, so a
+    // duplicate/late completion can't double-insert.
+    if recorded {
+        if let Some(record) = queue.get(&req.job_id).await.map_err(internal)? {
+            persist_findings(&db, &record.job.target_id, &req.result).await;
+        }
+    }
+    Ok(Json(CompleteResponse { recorded }))
+}
+
+/// Persist a job result's findings against its target: general findings
+/// (dedup'd by fingerprint) and DAST findings. Best-effort — a persistence hiccup
+/// is logged, not surfaced to the runner (its result is already recorded).
+async fn persist_findings(db: &Database, target_id: &str, result: &JobResult) {
+    for finding in &result.findings {
+        let exists = db
+            .findings()
+            .find_one(doc! { "fingerprint": &finding.fingerprint })
+            .await
+            .ok()
+            .flatten()
+            .is_some();
+        if !exists {
+            if let Err(e) = db.findings().insert_one(finding).await {
+                tracing::warn!(target_id, error = %e, "werkbank: persist finding failed");
+            }
+        }
+    }
+    for finding in &result.dast_findings {
+        if let Err(e) = db.dast_findings().insert_one(finding).await {
+            tracing::warn!(target_id, error = %e, "werkbank: persist DAST finding failed");
+        }
+    }
+    tracing::info!(
+        target_id,
+        findings = result.findings.len(),
+        dast = result.dast_findings.len(),
+        "werkbank: persisted runner results"
+    );
+}
+
+/// Resolve the tenant-scoped database for a request.
+async fn tenant_db(
+    agent: &crate::agent::ComplianceAgent,
+    tenant: &str,
+) -> Result<Database, StatusCode> {
+    agent.db_pool.for_tenant_id(tenant).await.map_err(internal)
+}
+
+/// Map any internal error to a 500.
+fn internal<E: std::fmt::Display>(e: E) -> StatusCode {
+    tracing::error!("werkbank endpoint error: {e}");
+    StatusCode::INTERNAL_SERVER_ERROR
+}
+
+/// Length-checked, constant-time-ish token comparison.
+fn constant_time_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
+}
+
+#[cfg(test)]
+mod tests {
+    use super::constant_time_eq;
+
+    #[test]
+    fn token_compare() {
+        assert!(constant_time_eq("secret", "secret"));
+        assert!(!constant_time_eq("secret", "secrex"));
+        assert!(!constant_time_eq("secret", "secretx"));
+        assert!(!constant_time_eq("", "x"));
+    }
+}

compliance-agent/src/api/server.rs

@@ -4,7 +4,7 @@ use axum::extract::{DefaultBodyLimit, Request};
 use axum::http::HeaderValue;
 use axum::middleware::Next;
 use axum::response::Response;
-use axum::routing::{delete, get};
+use axum::routing::{delete, get, post};
 use axum::{middleware, Extension, Router};
 use tokio::sync::RwLock;
 use tower_http::cors::CorsLayer;
@@ -72,8 +72,35 @@ pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), A
         Router::new()
     };
 
+    // Werkbank runner API. Like admin, only mounted when its bearer token is
+    // configured; runners authenticate with WERKBANK_RUNNER_TOKEN (not a JWT).
+    let werkbank_router: Router = if agent.config.werkbank_runner_token.is_some() {
+        tracing::info!(
+            "Werkbank runner API enabled — /api/v1/werkbank/jobs/* behind WERKBANK_RUNNER_TOKEN"
+        );
+        Router::new()
+            .route(
+                "/api/v1/werkbank/jobs/lease",
+                post(handlers::werkbank_jobs::lease),
+            )
+            .route(
+                "/api/v1/werkbank/jobs/heartbeat",
+                post(handlers::werkbank_jobs::heartbeat),
+            )
+            .route(
+                "/api/v1/werkbank/jobs/complete",
+                post(handlers::werkbank_jobs::complete),
+            )
+            .layer(middleware::from_fn(
+                handlers::werkbank_jobs::require_runner_token,
+            ))
+    } else {
+        Router::new()
+    };
+
     let mut app = routes::build_router()
         .merge(admin_router)
+        .merge(werkbank_router)
         // Allow large artifact uploads (PLC .projectarchive, firmware images,
         // mobile packages) — axum's default request-body limit is only 2 MiB.
         .layer(DefaultBodyLimit::max(512 * 1024 * 1024))

compliance-agent/src/config.rs

@@ -65,6 +65,7 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
         admin_api_token: env_secret_opt("ADMIN_API_TOKEN"),
         tenant_registry_url: env_var_opt("TENANT_REGISTRY_URL"),
         plc_runtime: load_plc_runtime_config(),
+        werkbank_runner_token: env_secret_opt("WERKBANK_RUNNER_TOKEN"),
     })
 }
 

compliance-agent/src/pentest/cleanup.rs

@@ -343,6 +343,7 @@ mod tests {
             admin_api_token: None,
             tenant_registry_url: None,
             plc_runtime: compliance_core::PlcRuntimeConfig::default(),
+            werkbank_runner_token: None,
         }
     }