Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Fable 5 463d4f6eb2 feat(werkbank): job/result contract in compliance-core (WB-01)
CI / Check (pull_request) Successful in 5m44s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been skipped
CI / Deploy Dashboard (pull_request) Has been skipped
CI / Deploy Docs (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
The shared, dependency-free vocabulary the control plane and the Werkbank
execution runner agree on: Job (declarative — TOML on disk, JSON on the wire),
JobType (plc-provision/qemu-boot/dast/pentest), Executor (shell/docker/k8s),
JobStatus lifecycle, InputRef (blob/url — the artifact resolves on the runner,
never through the control plane), JobRuntime, JobCollect, and JobResult (reusing
Finding/DastFinding/SbomEntry so the runner produces exactly what the control
plane persists).

Lives in a mongodb/axum-feature-free module so the runner can depend on
compliance-core without the server stack (verified: cargo check -p
compliance-core --no-default-features). Tests round-trip through JSON and parse
the exact plc-provision + qemu-boot TOML from the Werkbank design doc.

First story of the Werkbank epic (sharang/werkbank#1); implements
sharang/werkbank#2.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-17 10:24:49 +02:00
46 changed files with 90 additions and 5424 deletions
-5
View File
@@ -47,11 +47,6 @@ PLC_RUNTIME_MAX_LIFETIME_SECS=180
PLC_RUNTIME_OPENPLC_USER=openplc
PLC_RUNTIME_OPENPLC_PASSWORD=openplc
# Werkbank runner API (/api/v1/werkbank/jobs/*, /api/v1/werkbank/artifacts/*).
# When set, mounts the runner-facing queue + artifact endpoints behind this
# bearer token; runners present the same token. Unset = endpoints not mounted.
WERKBANK_RUNNER_TOKEN=
# Dashboard
DASHBOARD_PORT=8080
AGENT_API_URL=http://localhost:3001
+2 -4
View File
@@ -107,8 +107,6 @@ jobs:
run: cargo clippy -p compliance-dashboard --features web --no-default-features -- -D warnings
- name: Clippy (mcp)
run: cargo clippy -p compliance-mcp -- -D warnings
- name: Clippy (werkbank-exec)
run: cargo clippy -p werkbank-exec -- -D warnings
# Security audit
- name: Security Audit
@@ -117,8 +115,8 @@ jobs:
RUSTC_WRAPPER: ""
# Tests (reuses compilation artifacts from clippy)
- name: Tests (core + agent + werkbank-exec)
run: cargo test -p compliance-core -p compliance-agent -p werkbank-exec --lib
- name: Tests (core + agent)
run: cargo test -p compliance-core -p compliance-agent --lib
- name: Tests (dashboard server)
run: cargo test -p compliance-dashboard --features server --no-default-features
- name: Tests (dashboard web)
Generated
-27
View File
@@ -699,7 +699,6 @@ dependencies = [
"urlencoding",
"uuid",
"walkdir",
"werkbank-exec",
"zip",
]
@@ -5089,12 +5088,6 @@ dependencies = [
"digest",
]
[[package]]
name = "sha1_smol"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bbfa15b3dddfee50a0fff136974b3e1bde555604ba463834a7eb7deb6417705d"
[[package]]
name = "sha2"
version = "0.10.9"
@@ -6478,7 +6471,6 @@ dependencies = [
"getrandom 0.4.1",
"js-sys",
"serde_core",
"sha1_smol",
"wasm-bindgen",
]
@@ -6722,25 +6714,6 @@ dependencies = [
"rustls-pki-types",
]
[[package]]
name = "werkbank-exec"
version = "0.1.0"
dependencies = [
"compliance-core",
"compliance-dast",
"futures-util",
"hex",
"regex",
"reqwest",
"secrecy",
"sha2",
"thiserror 2.0.18",
"tokio",
"tracing",
"uuid",
"walkdir",
]
[[package]]
name = "which"
version = "6.0.3"
+1 -2
View File
@@ -7,7 +7,6 @@ members = [
"compliance-dast",
"compliance-mcp",
"compliance-smoke",
"werkbank-exec",
]
resolver = "2"
@@ -28,7 +27,7 @@ reqwest = { version = "0.12", features = ["json", "rustls-tls", "multipart", "co
thiserror = "2"
sha2 = "0.10"
hex = "0.4"
uuid = { version = "1", features = ["v4", "v5", "serde"] }
uuid = { version = "1", features = ["v4", "serde"] }
secrecy = { version = "0.10", features = ["serde"] }
regex = "1"
zip = { version = "2", features = ["aes-crypto", "deflate"] }
-3
View File
@@ -10,9 +10,6 @@ workspace = true
compliance-core = { workspace = true, features = ["mongodb", "telemetry", "axum"] }
compliance-graph = { path = "../compliance-graph" }
compliance-dast = { path = "../compliance-dast" }
# Shared dynamic-execution logic (soft-PLC provisioning + ICS probing), also
# used by the Werkbank runner.
werkbank-exec = { path = "../werkbank-exec" }
# Native firmware build/target detection for bare-metal & RTOS artifacts.
# Same-company IP, used directly (not via CLI) so the whole tramiton suite is
# available to the onboarding classifier. NOTE: CI must be able to fetch this
-2
View File
@@ -10,12 +10,10 @@ pub mod issues;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod oscal;
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::*;
@@ -1,89 +0,0 @@
//! OSCAL assessment endpoint.
//!
//! Assesses a target's findings against the breakpilot-compliance control
//! catalog and returns a standard OSCAL assessment-results document. Ties
//! together the ingest provider ([`OscalControlsProvider`]) and the assessment
//! emitter (`compliance_core::models::oscal_assessment`).
use axum::extract::Extension;
use axum::http::StatusCode;
use axum::response::{IntoResponse, Response};
use axum::Json;
use mongodb::bson::doc;
use serde::Deserialize;
use compliance_core::models::onboarding::ComplianceFramework;
use compliance_core::models::oscal_assessment::{assess, ControlLinker};
use compliance_core::models::Finding;
use compliance_core::tenant_ctx::TenantCtx;
use super::dto::{collect_cursor_async, tenant_db, AgentExt};
use crate::controls::OscalControlsProvider;
#[derive(Debug, Deserialize)]
pub struct AssessRequest {
/// The target / repo id whose findings are assessed.
pub target_id: String,
/// Frameworks to assess against; defaults to `[Cra]` when empty.
#[serde(default)]
pub frameworks: Vec<ComplianceFramework>,
}
/// `POST /api/v1/oscal/assess` — pull the catalog(s), load the target's findings,
/// and emit an OSCAL assessment-results document linking findings to controls.
pub async fn assess_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<AssessRequest>,
) -> Response {
let cfg = &agent.config.breakpilot;
let Some(base_url) = cfg.base_url.clone() else {
return (
StatusCode::SERVICE_UNAVAILABLE,
"breakpilot base URL not configured (set BREAKPILOT_BASE_URL)",
)
.into_response();
};
let frameworks = if req.frameworks.is_empty() {
vec![ComplianceFramework::Cra]
} else {
req.frameworks.clone()
};
let db = match tenant_db(&agent, &tenant).await {
Ok(db) => db,
Err(code) => return code.into_response(),
};
let findings: Vec<Finding> = match db.findings().find(doc! { "repo_id": &req.target_id }).await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!(error = %e, "failed to load findings for OSCAL assessment");
return StatusCode::INTERNAL_SERVER_ERROR.into_response();
}
};
let provider = OscalControlsProvider::new(
agent.http.clone(),
base_url,
cfg.token.clone(),
&cfg.snapshot_dir,
);
let mut controls = Vec::new();
for framework in &frameworks {
match provider.load(*framework).await {
Ok(document) => controls.extend(document.to_controls()),
Err(e) => tracing::warn!(?framework, error = %e, "OSCAL catalog load failed"),
}
}
let assessment = assess(
&controls,
&findings,
&ControlLinker::cra_seed(),
chrono::Utc::now(),
);
Json(assessment).into_response()
}
@@ -1,289 +0,0 @@
//! 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, Path, Request};
use axum::http::{header, StatusCode};
use axum::middleware::Next;
use axum::response::{IntoResponse, Response};
use axum::Json;
use mongodb::bson::{doc, oid::ObjectId};
use secrecy::ExposeSecret;
use serde::{Deserialize, Serialize};
use std::time::Duration;
use compliance_core::models::werkbank::{
CompleteRequest, CompleteResponse, HeartbeatRequest, InputRef, Job, JobResult, LeaseRequest,
};
use compliance_core::models::ArtifactKind;
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 }))
}
/// `GET /api/v1/werkbank/artifacts/{hash}` — serve a content-addressed blob (the
/// program a runner needs to load). The hash is validated against traversal by
/// [`crate::ingest::blob::read_blob`]; a runner fetches this for a job's `blob`
/// input.
#[tracing::instrument(skip_all, fields(hash = %hash))]
pub async fn serve_artifact(
Extension(agent): AgentExt,
Path(hash): Path<String>,
) -> Result<Response, StatusCode> {
let base = std::path::Path::new(&agent.config.artifact_store_base_path);
match crate::ingest::blob::read_blob(base, &hash) {
Ok(bytes) => {
Ok(([(header::CONTENT_TYPE, "application/octet-stream")], bytes).into_response())
}
Err(_) => Err(StatusCode::NOT_FOUND),
}
}
/// Enqueue a `plc-provision` job for a target: extract its control-logic program,
/// stash it as a content-addressed blob (which the runner fetches via
/// [`serve_artifact`]), and queue the job. This is the control-plane "enqueue"
/// half of the loop — a runner then leases it, provisions, and posts results.
#[derive(Debug, Deserialize)]
pub struct EnqueueRequest {
/// The tenant whose queue to enqueue into.
pub tenant: String,
/// The onboarded target to test.
pub target_id: String,
}
/// The enqueued job's id.
#[derive(Debug, Serialize)]
pub struct EnqueueResponse {
/// The new job id.
pub job_id: String,
/// Whether this call inserted it (false = already queued).
pub enqueued: bool,
}
#[tracing::instrument(skip_all, fields(tenant = %req.tenant, target = %req.target_id))]
pub async fn enqueue(
Extension(agent): AgentExt,
Json(req): Json<EnqueueRequest>,
) -> Result<Json<EnqueueResponse>, StatusCode> {
let db = tenant_db(&agent, &req.tenant).await?;
let oid = ObjectId::parse_str(&req.target_id).map_err(|_| StatusCode::BAD_REQUEST)?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(internal)?
.ok_or(StatusCode::NOT_FOUND)?;
// Extract the control-logic program from the target's PLC-source artifacts
// (same selection as the in-process PLC scan).
let ctx = crate::ingest::IngestContext::from_config(&agent.config, &req.target_id);
let ingest_set = crate::ingest::ingest_all(&target, &ctx).map_err(internal)?;
let program = target
.artifacts
.iter()
.filter(|a| {
matches!(
a.kind,
ArtifactKind::PlcProject | ArtifactKind::GitRepo | ArtifactKind::SourceArchive
)
})
.find_map(|a| {
let path = ingest_set
.get(&a.id)
.and_then(|ia| ia.working_path.clone())?;
werkbank_exec::plc::extract_program(&path)
})
.ok_or(StatusCode::UNPROCESSABLE_ENTITY)?;
// Stash the program source so the runner can fetch it by hash.
let base = std::path::Path::new(&agent.config.artifact_store_base_path);
let hash =
crate::ingest::blob::store_bytes(base, program.source.as_bytes()).map_err(internal)?;
let job_id = format!("job_{}", uuid::Uuid::new_v4().simple());
let job = Job::plc_provision(
&job_id,
&req.tenant,
&req.target_id,
InputRef::blob(hash),
agent.config.plc_runtime.max_lifetime_secs,
);
let enqueued = JobQueue::new(&db)
.enqueue(job, chrono::Utc::now())
.await
.map_err(internal)?;
Ok(Json(EnqueueResponse { job_id, enqueued }))
}
/// 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"));
}
}
-1
View File
@@ -6,7 +6,6 @@ use crate::api::handlers;
pub fn build_router() -> Router {
Router::new()
.route("/api/v1/health", get(handlers::health))
.route("/api/v1/oscal/assess", post(handlers::oscal::assess_target))
.route("/api/v1/stats/overview", get(handlers::stats_overview))
.route(
"/api/v1/settings/ssh-public-key",
+1 -36
View File
@@ -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, post};
use axum::routing::{delete, get};
use axum::{middleware, Extension, Router};
use tokio::sync::RwLock;
use tower_http::cors::CorsLayer;
@@ -72,43 +72,8 @@ 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),
)
.route(
"/api/v1/werkbank/jobs/enqueue",
post(handlers::werkbank_jobs::enqueue),
)
.route(
"/api/v1/werkbank/artifacts/{hash}",
get(handlers::werkbank_jobs::serve_artifact),
)
.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))
+1 -14
View File
@@ -1,4 +1,4 @@
use compliance_core::config::{BreakpilotConfig, PlcRuntimeConfig};
use compliance_core::config::PlcRuntimeConfig;
use compliance_core::AgentConfig;
use secrecy::SecretString;
@@ -65,8 +65,6 @@ 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"),
breakpilot: load_breakpilot_config(),
})
}
@@ -91,14 +89,3 @@ fn load_plc_runtime_config() -> PlcRuntimeConfig {
.unwrap_or(d.openplc_password),
}
}
/// Assemble the breakpilot OSCAL-catalog source from env, defaulting the snapshot
/// directory. A missing `BREAKPILOT_BASE_URL` leaves the controls provider off.
fn load_breakpilot_config() -> BreakpilotConfig {
let d = BreakpilotConfig::default();
BreakpilotConfig {
base_url: env_var_opt("BREAKPILOT_BASE_URL"),
token: env_secret_opt("BREAKPILOT_TOKEN"),
snapshot_dir: env_var_opt("BREAKPILOT_SNAPSHOT_DIR").unwrap_or(d.snapshot_dir),
}
}
-10
View File
@@ -1,10 +0,0 @@
//! Controls corpus providers.
//!
//! Implementations of [`compliance_core::traits::ControlsProvider`] that supply
//! the control corpus the mapping engine assesses findings against. Currently:
//! [`OscalControlsProvider`], which pulls breakpilot-compliance's OSCAL catalog
//! and snapshots it locally.
mod oscal_provider;
pub use oscal_provider::OscalControlsProvider;
@@ -1,233 +0,0 @@
//! Pull + snapshot [`ControlsProvider`] backed by breakpilot-compliance's OSCAL
//! catalog export.
//!
//! Fetches `GET {base}/api/compliance/v1/oscal/catalog?framework=<fw>`, snapshots
//! the exact bytes to disk (so scans are deterministic and keep working offline /
//! on-prem), and maps the catalog into the corpus controls the mapping engine
//! consumes. The producer owns the catalog; we own the assessment — this is the
//! ingest half of the loop.
use std::path::PathBuf;
use secrecy::{ExposeSecret, SecretString};
use compliance_core::error::CoreError;
use compliance_core::models::onboarding::ComplianceFramework;
use compliance_core::models::oscal::OscalDocument;
use compliance_core::traits::{Control, ControlQuery, ControlsProvider};
/// A [`ControlsProvider`] that pulls the OSCAL catalog from breakpilot-compliance
/// and snapshots it locally for deterministic / offline reuse.
pub struct OscalControlsProvider {
http: reqwest::Client,
base_url: String,
token: Option<SecretString>,
snapshot_dir: PathBuf,
}
impl OscalControlsProvider {
/// Create a provider. `base_url` is the breakpilot-compliance root (e.g.
/// `http://backend-compliance:8002`); `snapshot_dir` is where catalog
/// snapshots are written so a later scan can reuse them without the network.
pub fn new(
http: reqwest::Client,
base_url: impl Into<String>,
token: Option<SecretString>,
snapshot_dir: impl Into<PathBuf>,
) -> Self {
Self {
http,
base_url: base_url.into(),
token,
snapshot_dir: snapshot_dir.into(),
}
}
fn catalog_url(&self, framework: ComplianceFramework) -> String {
format!(
"{}/api/compliance/v1/oscal/catalog?framework={framework}",
self.base_url.trim_end_matches('/')
)
}
fn snapshot_path(&self, framework: ComplianceFramework) -> PathBuf {
self.snapshot_dir
.join(format!("oscal-catalog-{framework}.json"))
}
/// Fetch the raw catalog bytes for a framework over HTTP.
async fn fetch_raw(&self, framework: ComplianceFramework) -> Result<Vec<u8>, CoreError> {
let mut req = self.http.get(self.catalog_url(framework));
if let Some(token) = &self.token {
req = req.bearer_auth(token.expose_secret());
}
let resp = req
.send()
.await
.map_err(|e| CoreError::Http(e.to_string()))?;
if !resp.status().is_success() {
return Err(CoreError::Http(format!(
"catalog fetch for {framework} returned HTTP {}",
resp.status()
)));
}
resp.bytes()
.await
.map(|b| b.to_vec())
.map_err(|e| CoreError::Http(e.to_string()))
}
/// Write a catalog snapshot atomically (temp file + rename).
async fn write_snapshot(
&self,
framework: ComplianceFramework,
raw: &[u8],
) -> Result<(), CoreError> {
tokio::fs::create_dir_all(&self.snapshot_dir).await?;
let path = self.snapshot_path(framework);
let tmp = path.with_extension("json.tmp");
tokio::fs::write(&tmp, raw).await?;
tokio::fs::rename(&tmp, &path).await?;
Ok(())
}
/// Read a previously written snapshot, if one exists.
async fn read_snapshot(
&self,
framework: ComplianceFramework,
) -> Result<Option<OscalDocument>, CoreError> {
match tokio::fs::read(self.snapshot_path(framework)).await {
Ok(raw) => Ok(Some(serde_json::from_slice(&raw)?)),
Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(None),
Err(e) => Err(e.into()),
}
}
/// Load the catalog for a framework: fetch fresh + snapshot the exact bytes;
/// on network failure, fall back to the last snapshot so scans still run.
pub async fn load(&self, framework: ComplianceFramework) -> Result<OscalDocument, CoreError> {
match self.fetch_raw(framework).await {
Ok(raw) => {
let doc: OscalDocument = serde_json::from_slice(&raw)?;
if let Err(e) = self.write_snapshot(framework, &raw).await {
tracing::warn!(%framework, error = %e, "failed to write OSCAL snapshot");
}
Ok(doc)
}
Err(fetch_err) => match self.read_snapshot(framework).await? {
Some(doc) => {
tracing::warn!(
%framework, error = %fetch_err,
"OSCAL catalog fetch failed; falling back to snapshot"
);
Ok(doc)
}
None => Err(fetch_err),
},
}
}
}
/// Order controls whose title/text mention the query context first (stable), then
/// truncate to the requested limit. Naive relevance — refined when the assessment
/// layer lands.
fn rank_and_truncate(mut controls: Vec<Control>, context: &str, limit: usize) -> Vec<Control> {
if !context.is_empty() {
let needle = context.to_lowercase();
controls.sort_by_key(|c| {
let hit =
c.title.to_lowercase().contains(&needle) || c.text.to_lowercase().contains(&needle);
u8::from(!hit)
});
}
controls.truncate(limit);
controls
}
impl ControlsProvider for OscalControlsProvider {
fn name(&self) -> &str {
"breakpilot-oscal"
}
async fn controls(&self, query: &ControlQuery<'_>) -> Result<Vec<Control>, CoreError> {
let mut out: Vec<Control> = Vec::new();
for &framework in query.frameworks {
match self.load(framework).await {
Ok(doc) => out.extend(doc.to_controls()),
Err(e) => {
tracing::warn!(%framework, error = %e, "skipping framework: catalog unavailable")
}
}
}
Ok(rank_and_truncate(out, query.context, query.limit))
}
}
#[cfg(test)]
#[allow(clippy::unwrap_used)]
mod tests {
use super::*;
const MINI_CATALOG: &str = r#"{"catalog":{"uuid":"u","metadata":{"title":"T",
"version":"1.0.0","oscal-version":"1.1.2","props":[{"name":"framework","value":"cra"}]},
"groups":[{"id":"g","title":"G","controls":[{"id":"cra-ai-1","title":"MFA",
"props":[],"parts":[{"name":"statement","prose":"require mfa"}]}]}]}}"#;
fn provider(dir: &std::path::Path) -> OscalControlsProvider {
OscalControlsProvider::new(reqwest::Client::new(), "http://unused/", None, dir)
}
#[test]
fn builds_catalog_url_and_snapshot_path() {
let p = provider(std::path::Path::new("/snap"));
assert_eq!(
p.catalog_url(ComplianceFramework::Cra),
"http://unused/api/compliance/v1/oscal/catalog?framework=cra"
);
assert_eq!(
p.snapshot_path(ComplianceFramework::Cra),
std::path::Path::new("/snap/oscal-catalog-cra.json")
);
}
#[test]
fn ranks_context_hits_first_then_truncates() {
let mk = |id: &str, title: &str| Control {
id: id.into(),
framework: ComplianceFramework::Cra,
title: title.into(),
text: String::new(),
source: None,
};
let controls = vec![
mk("a", "logging policy"),
mk("b", "multi-factor auth"),
mk("c", "backup"),
];
let ranked = rank_and_truncate(controls, "auth", 2);
assert_eq!(ranked.len(), 2);
assert_eq!(ranked[0].id, "b"); // the "auth" hit floats to the top
}
#[tokio::test]
async fn snapshot_round_trip_and_offline_fallback() {
let dir = std::env::temp_dir().join(format!("oscal-test-{}", uuid::Uuid::new_v4()));
let p = provider(&dir);
assert!(p
.read_snapshot(ComplianceFramework::Cra)
.await
.unwrap()
.is_none());
p.write_snapshot(ComplianceFramework::Cra, MINI_CATALOG.as_bytes())
.await
.unwrap();
let doc = p
.read_snapshot(ComplianceFramework::Cra)
.await
.unwrap()
.unwrap();
assert_eq!(doc.to_controls().len(), 1);
assert_eq!(doc.framework(), Some(ComplianceFramework::Cra));
let _ = std::fs::remove_dir_all(&dir);
}
}
-34
View File
@@ -465,34 +465,6 @@ impl Database {
)
.await?;
// werkbank_jobs: unique job id (idempotent enqueue by job id)
self.werkbank_jobs()
.create_index(
IndexModel::builder()
.keys(doc! { "job.id": 1 })
.options(IndexOptions::builder().unique(true).build())
.build(),
)
.await?;
// werkbank_jobs: lease query — oldest queued job for an executor
self.werkbank_jobs()
.create_index(
IndexModel::builder()
.keys(doc! { "status": 1, "job.executor": 1, "created_at": 1 })
.build(),
)
.await?;
// werkbank_jobs: visibility-timeout sweep of expired leases
self.werkbank_jobs()
.create_index(
IndexModel::builder()
.keys(doc! { "status": 1, "lease_expires_at": 1 })
.build(),
)
.await?;
tracing::info!("Database indexes ensured");
Ok(())
}
@@ -591,12 +563,6 @@ impl Database {
self.inner.collection("pentest_messages")
}
/// The Werkbank job queue (WB-02): declarative dynamic-execution jobs the
/// control plane enqueues and runners lease.
pub fn werkbank_jobs(&self) -> Collection<compliance_core::models::werkbank::JobRecord> {
self.inner.collection("werkbank_jobs")
}
#[allow(dead_code)]
pub fn raw_collection(&self, name: &str) -> Collection<mongodb::bson::Document> {
self.inner.collection(name)
-3
View File
@@ -27,9 +27,6 @@ pub enum AgentError {
#[error("Configuration error: {0}")]
Config(String),
#[error("Dynamic-execution error: {0}")]
Exec(#[from] werkbank_exec::ExecError),
#[error("{0}")]
Other(String),
}
-24
View File
@@ -32,30 +32,6 @@ pub fn hash_file(path: &Path) -> Result<(String, u64), AgentError> {
Ok((hex::encode(hasher.finalize()), total))
}
/// Store raw bytes in the content-addressed blob store under `base`, returning
/// the SHA-256 digest. Used to stash a small derived artifact (e.g. the extracted
/// PLC program source) so a Werkbank runner can fetch it by hash. Idempotent.
pub fn store_bytes(base: &Path, bytes: &[u8]) -> Result<String, AgentError> {
let sha = hex::encode(Sha256::digest(bytes));
let dir = base.join("blobs").join(&sha[0..2]);
fs::create_dir_all(&dir)?;
let dest = dir.join(&sha);
if !dest.exists() {
fs::write(&dest, bytes)?;
}
Ok(sha)
}
/// Read a blob's bytes by its SHA-256 digest. Rejects a non-hex/wrong-length hash
/// so a request can't traverse outside the blob store.
pub fn read_blob(base: &Path, sha: &str) -> Result<Vec<u8>, AgentError> {
if sha.len() != 64 || !sha.bytes().all(|b| b.is_ascii_hexdigit()) {
return Err(AgentError::Other(format!("invalid content hash '{sha}'")));
}
let path = base.join("blobs").join(&sha[0..2]).join(sha);
Ok(fs::read(path)?)
}
/// Copy `src` into the content-addressed blob store under `base`, returning the
/// stored path. Idempotent: an already-present blob is not rewritten.
pub fn store_file(base: &Path, src: &Path, sha: &str) -> Result<PathBuf, AgentError> {
+1 -1
View File
@@ -6,7 +6,7 @@
//! is also the reconciliation key against sibling products (a firmware sha256
//! matches tramiton's `Artifact.sha256`).
pub(crate) mod blob;
mod blob;
use std::collections::HashMap;
use std::path::{Path, PathBuf};
-2
View File
@@ -4,7 +4,6 @@ pub mod agent;
pub mod api;
pub mod classify;
pub mod config;
pub mod controls;
pub mod database;
pub mod error;
pub mod ingest;
@@ -17,4 +16,3 @@ pub mod ssh;
#[allow(dead_code)]
pub mod trackers;
pub mod webhooks;
pub mod werkbank;
-2
View File
@@ -343,8 +343,6 @@ mod tests {
admin_api_token: None,
tenant_registry_url: None,
plc_runtime: compliance_core::PlcRuntimeConfig::default(),
werkbank_runner_token: None,
breakpilot: compliance_core::config::BreakpilotConfig::default(),
}
}
@@ -14,7 +14,7 @@ use std::time::Duration;
use compliance_core::models::{Finding, ScanType, Severity};
use crate::fingerprint as dedup;
use crate::pipeline::dedup;
/// Well-known deep-probe ports (each independent of any WebVisu HTTP port).
const MODBUS_PORT: u16 = 502;
+1
View File
@@ -5,6 +5,7 @@ pub mod firmware_sbom;
pub mod git;
pub mod gitleaks;
mod graph_build;
pub mod ics;
mod issue_creation;
pub mod lint;
pub mod orchestrator;
@@ -587,7 +587,7 @@ impl PipelineOrchestrator {
let path = ingest_set
.get(&a.id)
.and_then(|ia| ia.working_path.clone())?;
werkbank_exec::plc::extract_program(&path)
crate::pipeline::plc::runtime::extract_program(&path)
});
let Some(program) = program else {
tracing::info!(
@@ -597,9 +597,10 @@ impl PipelineOrchestrator {
return Ok(0);
};
let http = werkbank_exec::plc::http_client()?;
let provisioner = werkbank_exec::plc::DockerSoftPlc::new(self.config.plc_runtime.clone());
let outcome = werkbank_exec::plc::provision_and_test(
let http = crate::pipeline::plc::runtime::http_client()?;
let provisioner =
crate::pipeline::plc::runtime::DockerSoftPlc::new(self.config.plc_runtime.clone());
let outcome = crate::pipeline::plc::runtime::provision_and_test(
&provisioner,
&http,
&self.config.plc_runtime,
@@ -662,7 +663,7 @@ impl PipelineOrchestrator {
};
// Short per-request budget so an unreachable device doesn't stall the scan.
let budget = std::time::Duration::from_secs(5);
let findings = werkbank_exec::ics::probe_target(&endpoint, target_id, budget).await;
let findings = crate::pipeline::ics::probe_target(&endpoint, target_id, budget).await;
tracing::info!(
target_id,
endpoint = %endpoint,
+1
View File
@@ -9,6 +9,7 @@ pub mod lexer;
pub mod parser;
pub mod plcopen;
pub mod rules;
pub mod runtime;
pub mod sbom;
use std::path::Path;
@@ -24,7 +24,7 @@ use compliance_core::models::dast::{DastFinding, DastScanRun, DastTarget, DastTa
use compliance_core::models::Finding;
use compliance_core::PlcRuntimeConfig;
use crate::error::ExecError;
use crate::error::AgentError;
pub use provision::{DockerSoftPlc, ProvisionedRuntime, SoftPlc};
@@ -61,12 +61,12 @@ pub struct PlcProgram {
/// A cookie-aware HTTP client for the OpenPLC web UI. A fresh client per scan
/// isolates the OpenPLC session (its Flask login cookie) from every other scan.
pub fn http_client() -> Result<reqwest::Client, ExecError> {
pub fn http_client() -> Result<reqwest::Client, AgentError> {
reqwest::Client::builder()
.cookie_store(true)
.timeout(Duration::from_secs(30))
.build()
.map_err(ExecError::Http)
.map_err(AgentError::Http)
}
/// Pick the control-logic program to run from an ingested PLC source tree.
@@ -151,7 +151,7 @@ pub async fn provision_and_test<P: SoftPlc>(
cfg: &PlcRuntimeConfig,
program: &PlcProgram,
target_id: &str,
) -> Result<ProvisionOutcome, ExecError> {
) -> Result<ProvisionOutcome, AgentError> {
let handle = provisioner.provision(target_id).await?;
tracing::info!(
target_id,
@@ -193,7 +193,7 @@ async fn run_dynamic_test(
program: &PlcProgram,
target_id: &str,
handle: &ProvisionedRuntime,
) -> Result<ProvisionOutcome, ExecError> {
) -> Result<ProvisionOutcome, AgentError> {
let ready_budget = Duration::from_secs((cfg.max_lifetime_secs / 3).clamp(10, 60));
openplc::wait_ready(http, &handle.webvisu_url, ready_budget).await?;
@@ -212,7 +212,8 @@ async fn run_dynamic_test(
tokio::time::sleep(Duration::from_secs(3)).await;
let probe_budget = Duration::from_secs(5);
let findings = crate::ics::probe_target(&handle.modbus_endpoint, target_id, probe_budget).await;
let findings =
crate::pipeline::ics::probe_target(&handle.modbus_endpoint, target_id, probe_budget).await;
tracing::info!(
target_id,
instance = %handle.name,
@@ -347,10 +348,10 @@ mod tests {
}
impl SoftPlc for FakeSoftPlc {
async fn provision(&self, _target_id: &str) -> Result<ProvisionedRuntime, ExecError> {
async fn provision(&self, _target_id: &str) -> Result<ProvisionedRuntime, AgentError> {
self.provisions.fetch_add(1, Ordering::SeqCst);
if self.fail_provision {
return Err(ExecError::Other("provision failed".into()));
return Err(AgentError::Other("provision failed".into()));
}
// Unreachable address so run_dynamic_test blocks on readiness until the
// deadline fires — exercising the teardown-on-deadline path.
@@ -10,7 +10,7 @@
use std::time::Duration;
use crate::error::ExecError;
use crate::error::AgentError;
use super::PlcProgram;
@@ -27,7 +27,7 @@ pub async fn wait_ready(
http: &reqwest::Client,
base_url: &str,
budget: Duration,
) -> Result<(), ExecError> {
) -> Result<(), AgentError> {
let login = format!("{base_url}/login");
let outcome = tokio::time::timeout(budget, async {
loop {
@@ -40,7 +40,7 @@ pub async fn wait_ready(
}
})
.await;
outcome.map_err(|_| ExecError::Other(format!("OpenPLC at {base_url} did not become ready")))
outcome.map_err(|_| AgentError::Other(format!("OpenPLC at {base_url} did not become ready")))
}
/// Log in, upload the program, compile it, and start the runtime. On success the
@@ -52,7 +52,7 @@ pub async fn load_and_start(
password: &str,
program: &PlcProgram,
compile_budget: Duration,
) -> Result<(), ExecError> {
) -> Result<(), AgentError> {
login(http, base_url, user, password).await?;
let prog_file = upload_program(http, base_url, program).await?;
save_program(http, base_url, &prog_file).await?;
@@ -68,14 +68,14 @@ async fn login(
base_url: &str,
user: &str,
password: &str,
) -> Result<(), ExecError> {
) -> Result<(), AgentError> {
let resp = http
.post(format!("{base_url}/login"))
.form(&[("username", user), ("password", password)])
.send()
.await?;
if resp.status().is_server_error() {
return Err(ExecError::Other(format!(
return Err(AgentError::Other(format!(
"OpenPLC login failed: HTTP {}",
resp.status()
)));
@@ -90,7 +90,7 @@ async fn upload_program(
http: &reqwest::Client,
base_url: &str,
program: &PlcProgram,
) -> Result<String, ExecError> {
) -> Result<String, AgentError> {
let part = reqwest::multipart::Part::text(program.source.clone())
.file_name(program.file_name.clone())
.mime_str("application/octet-stream")?;
@@ -102,7 +102,7 @@ async fn upload_program(
.await?;
let html = resp.text().await?;
parse_prog_file(&html).ok_or_else(|| {
ExecError::Other("OpenPLC upload did not return a prog_file handle".to_string())
AgentError::Other("OpenPLC upload did not return a prog_file handle".to_string())
})
}
@@ -113,7 +113,7 @@ async fn save_program(
http: &reqwest::Client,
base_url: &str,
prog_file: &str,
) -> Result<(), ExecError> {
) -> Result<(), AgentError> {
let epoch = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.map(|d| d.as_secs())
@@ -130,7 +130,7 @@ async fn save_program(
.send()
.await?;
if resp.status().is_server_error() {
return Err(ExecError::Other(format!(
return Err(AgentError::Other(format!(
"OpenPLC save-program failed: HTTP {}",
resp.status()
)));
@@ -146,7 +146,7 @@ async fn compile(
base_url: &str,
prog_file: &str,
budget: Duration,
) -> Result<(), ExecError> {
) -> Result<(), AgentError> {
http.get(format!("{base_url}/compile-program"))
.query(&[("file", prog_file)])
.send()
@@ -168,20 +168,20 @@ async fn compile(
.await;
match outcome {
Ok(true) => Ok(()),
Ok(false) => Err(ExecError::Other(
Ok(false) => Err(AgentError::Other(
"OpenPLC compilation finished with errors".to_string(),
)),
Err(_) => Err(ExecError::Other(
Err(_) => Err(AgentError::Other(
"OpenPLC compilation did not finish in time".to_string(),
)),
}
}
/// `GET /start_plc` — starts the runtime, opening Modbus/TCP on 502.
async fn start(http: &reqwest::Client, base_url: &str) -> Result<(), ExecError> {
async fn start(http: &reqwest::Client, base_url: &str) -> Result<(), AgentError> {
let resp = http.get(format!("{base_url}/start_plc")).send().await?;
if resp.status().is_server_error() {
return Err(ExecError::Other(format!(
return Err(AgentError::Other(format!(
"OpenPLC start_plc failed: HTTP {}",
resp.status()
)));
@@ -15,7 +15,7 @@ use std::time::{SystemTime, UNIX_EPOCH};
use compliance_core::PlcRuntimeConfig;
use crate::error::ExecError;
use crate::error::AgentError;
/// The Modbus/TCP port an OpenPLC instance opens once a program is running.
const MODBUS_PORT: u16 = 502;
@@ -45,7 +45,7 @@ pub trait SoftPlc {
fn provision(
&self,
target_id: &str,
) -> impl std::future::Future<Output = Result<ProvisionedRuntime, ExecError>> + Send;
) -> impl std::future::Future<Output = Result<ProvisionedRuntime, AgentError>> + Send;
/// Tear an instance down. Best-effort and idempotent — never fails the scan.
fn teardown(&self, handle: &ProvisionedRuntime)
@@ -65,7 +65,7 @@ impl DockerSoftPlc {
}
impl SoftPlc for DockerSoftPlc {
async fn provision(&self, target_id: &str) -> Result<ProvisionedRuntime, ExecError> {
async fn provision(&self, target_id: &str) -> Result<ProvisionedRuntime, AgentError> {
// Best-effort sweep of any container leaked by a crashed earlier run
// before we add another. Only removes instances past their max lifetime,
// so it can never disturb a concurrent run.
@@ -75,7 +75,7 @@ impl SoftPlc for DockerSoftPlc {
let args = run_args(&self.cfg, &name, target_id);
let out = run_docker(&args).await?;
if !out.status.success() {
return Err(ExecError::Other(format!(
return Err(AgentError::Other(format!(
"docker run for soft-PLC {name} failed: {}",
String::from_utf8_lossy(&out.stderr).trim()
)));
@@ -215,12 +215,12 @@ async fn reap_stale(cfg: &PlcRuntimeConfig, now: u64) {
}
/// Run a `docker` subcommand, capturing its output.
async fn run_docker(args: &[String]) -> Result<std::process::Output, ExecError> {
async fn run_docker(args: &[String]) -> Result<std::process::Output, AgentError> {
tokio::process::Command::new("docker")
.args(args)
.output()
.await
.map_err(ExecError::Io)
.map_err(AgentError::Io)
}
#[cfg(test)]
-10
View File
@@ -1,10 +0,0 @@
//! Werkbank control-plane: the dynamic-execution job queue.
//!
//! The control plane enqueues declarative [`Job`](compliance_core::models::werkbank::Job)s
//! and Werkbank runners lease, run, and complete them. [`queue::JobQueue`] is the
//! Mongo-backed queue behind that flow (WB-02); the runner-facing HTTP transport
//! and the runner itself land in later stories.
pub mod queue;
pub use queue::{JobQueue, SweepOutcome};
-309
View File
@@ -1,309 +0,0 @@
//! The Mongo-backed Werkbank job queue (WB-02).
//!
//! A pull queue: the control plane [`enqueue`](JobQueue::enqueue)s jobs; a runner
//! [`lease`](JobQueue::lease)s the oldest queued job it can run (matched by
//! executor + labels), [`heartbeat`](JobQueue::heartbeat)s while it works, and
//! [`complete`](JobQueue::complete)s it. Leases carry a visibility timeout: if a
//! runner dies mid-job its heartbeats stop, the lease expires, and
//! [`sweep_expired`](JobQueue::sweep_expired) returns the job to `queued` (or
//! `expired` once it has been retried too many times).
//!
//! All state transitions are single atomic Mongo updates guarded by the lease
//! token, so two runners can never both own a job. Every operation takes an
//! explicit `now` so the queue's time-dependent behaviour is deterministically
//! testable.
use std::time::Duration;
use chrono::{DateTime, Utc};
use mongodb::bson::{doc, Bson, DateTime as BsonDateTime};
use mongodb::error::{ErrorKind, WriteFailure};
use mongodb::options::ReturnDocument;
use mongodb::Collection;
use compliance_core::models::werkbank::{
Executor, HeartbeatAck, Job, JobRecord, JobResult, JobStatus, LeasedJob,
};
use crate::database::Database;
use crate::error::AgentError;
/// The non-terminal states a job can be swept or cancelled from.
const ACTIVE_STATES: [&str; 2] = ["leased", "running"];
/// Every terminal state (no further transitions).
const TERMINAL_STATES: [&str; 4] = ["succeeded", "failed", "expired", "cancelled"];
/// What a visibility-timeout sweep did.
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
pub struct SweepOutcome {
/// Expired-lease jobs returned to `queued` for another runner.
pub requeued: u64,
/// Jobs that had exhausted their attempts and were marked `expired`.
pub expired: u64,
}
/// The Mongo-backed job queue.
pub struct JobQueue {
coll: Collection<JobRecord>,
}
impl JobQueue {
/// Build a queue over a tenant database's `werkbank_jobs` collection.
pub fn new(db: &Database) -> Self {
Self {
coll: db.werkbank_jobs(),
}
}
/// Enqueue a job. Idempotent by job id: a job that is already present is a
/// no-op. Returns `true` if this call inserted it, `false` if it existed.
pub async fn enqueue(&self, job: Job, now: DateTime<Utc>) -> Result<bool, AgentError> {
let record = JobRecord::queued(job, now);
match self.coll.insert_one(&record).await {
Ok(_) => Ok(true),
Err(e) if is_duplicate_key(&e) => Ok(false),
Err(e) => Err(e.into()),
}
}
/// Atomically lease the oldest `queued` job this runner can run — matched by
/// executor and by labels (every label the job requires must be one the
/// runner advertises). Returns the job plus a lease token, or `None` if
/// nothing is runnable.
pub async fn lease(
&self,
runner_id: &str,
executor: Executor,
runner_labels: &[String],
lease_ttl: Duration,
now: DateTime<Utc>,
) -> Result<Option<LeasedJob>, AgentError> {
let token = uuid::Uuid::new_v4().to_string();
let expires = bson_dt(now + ttl(lease_ttl));
let executor_bson = mongodb::bson::to_bson(&executor).unwrap_or(Bson::Null);
let filter = doc! {
"status": "queued",
"cancel_requested": { "$ne": true },
"job.executor": executor_bson,
// Every label the job requires must be in the runner's set — i.e. the
// job has no label that is not offered by the runner. Absent/empty
// job labels match any runner.
"job.labels": { "$not": { "$elemMatch": { "$nin": runner_labels.to_vec() } } },
};
let update = doc! {
"$set": {
"status": "leased",
"lease_token": &token,
"leased_by": runner_id,
"lease_expires_at": expires,
"heartbeat_at": bson_dt(now),
"updated_at": bson_dt(now),
},
"$inc": { "attempts": 1 },
};
let record = self
.coll
.find_one_and_update(filter, update)
.sort(doc! { "created_at": 1 }) // FIFO
.return_document(ReturnDocument::After)
.await?;
Ok(record.map(|r| LeasedJob {
job: r.job,
lease_token: token,
}))
}
/// Extend a lease and report whether the job has been asked to cancel.
/// Transitions the job to `running` on the first heartbeat. Returns `None`
/// when the lease is no longer valid (token mismatch, or the job is already
/// terminal) — the runner should then abandon the work.
pub async fn heartbeat(
&self,
job_id: &str,
lease_token: &str,
lease_ttl: Duration,
now: DateTime<Utc>,
) -> Result<Option<HeartbeatAck>, AgentError> {
let filter = doc! {
"job.id": job_id,
"lease_token": lease_token,
"status": { "$in": ACTIVE_STATES.to_vec() },
};
let update = doc! {
"$set": {
"status": "running",
"lease_expires_at": bson_dt(now + ttl(lease_ttl)),
"heartbeat_at": bson_dt(now),
"updated_at": bson_dt(now),
},
};
let record = self
.coll
.find_one_and_update(filter, update)
.return_document(ReturnDocument::After)
.await?;
Ok(record.map(|r| HeartbeatAck {
cancelled: r.cancel_requested,
}))
}
/// Record a job's terminal result. Guarded by the lease token and only from
/// an active (`leased`/`running`) state, so it is idempotent — a duplicate or
/// late submission after the job already finished matches nothing. Returns
/// `true` if this call recorded the result.
pub async fn complete(
&self,
job_id: &str,
lease_token: &str,
result: &JobResult,
now: DateTime<Utc>,
) -> Result<bool, AgentError> {
let status = result.status.unwrap_or(JobStatus::Failed);
let status_bson = mongodb::bson::to_bson(&status).unwrap_or(Bson::String("failed".into()));
let result_bson =
mongodb::bson::to_bson(result).map_err(|e| AgentError::Other(e.to_string()))?;
let filter = doc! {
"job.id": job_id,
"lease_token": lease_token,
"status": { "$in": ACTIVE_STATES.to_vec() },
};
let update = doc! {
"$set": {
"status": status_bson,
"result": result_bson,
"lease_token": Bson::Null,
"lease_expires_at": Bson::Null,
"updated_at": bson_dt(now),
},
};
let res = self.coll.update_one(filter, update).await?;
Ok(res.modified_count == 1)
}
/// Request cancellation of a job. A still-`queued` job is cancelled outright;
/// an in-flight one is flagged so the runner sees it on its next heartbeat and
/// tears down. Returns `true` if a non-terminal job matched.
pub async fn cancel(&self, job_id: &str, now: DateTime<Utc>) -> Result<bool, AgentError> {
let filter = doc! {
"job.id": job_id,
"status": { "$nin": TERMINAL_STATES.to_vec() },
};
// Pipeline update: flag cancellation, and if still queued flip straight to
// cancelled (nothing is running it).
let pipeline = vec![doc! {
"$set": {
"cancel_requested": true,
"status": {
"$cond": [ { "$eq": ["$status", "queued"] }, "cancelled", "$status" ]
},
"updated_at": bson_dt(now),
}
}];
let res = self.coll.update_one(filter, pipeline).await?;
Ok(res.matched_count == 1)
}
/// Sweep leases whose visibility timeout has elapsed: return them to `queued`
/// for another runner, or mark them `expired` once they have been leased
/// `max_attempts` times. This is what makes a crashed runner's job recover.
pub async fn sweep_expired(
&self,
now: DateTime<Utc>,
max_attempts: u32,
// (kept explicit rather than a const so callers can tune retry policy)
) -> Result<SweepOutcome, AgentError> {
let now_bson = bson_dt(now);
let max = i64::from(max_attempts);
let requeue = self
.coll
.update_many(
doc! {
"status": { "$in": ACTIVE_STATES.to_vec() },
"lease_expires_at": { "$lt": &now_bson },
"attempts": { "$lt": max },
},
doc! { "$set": {
"status": "queued",
"lease_token": Bson::Null,
"leased_by": Bson::Null,
"lease_expires_at": Bson::Null,
"updated_at": &now_bson,
} },
)
.await?;
let expire = self
.coll
.update_many(
doc! {
"status": { "$in": ACTIVE_STATES.to_vec() },
"lease_expires_at": { "$lt": &now_bson },
"attempts": { "$gte": max },
},
doc! { "$set": {
"status": "expired",
"lease_token": Bson::Null,
"lease_expires_at": Bson::Null,
"updated_at": &now_bson,
} },
)
.await?;
Ok(SweepOutcome {
requeued: requeue.modified_count,
expired: expire.modified_count,
})
}
/// Fetch a job record by job id (inspection / control-plane reads).
pub async fn get(&self, job_id: &str) -> Result<Option<JobRecord>, AgentError> {
Ok(self.coll.find_one(doc! { "job.id": job_id }).await?)
}
}
/// A `chrono::Duration` for a lease TTL, saturating rather than panicking on an
/// absurd input (`chrono::Duration::seconds` panics past its internal bound).
fn ttl(d: Duration) -> chrono::Duration {
let secs = i64::try_from(d.as_secs()).unwrap_or(i64::MAX);
chrono::Duration::try_seconds(secs).unwrap_or(chrono::Duration::MAX)
}
/// A chrono instant as a BSON date (so Mongo stores/compares it as a real date).
fn bson_dt(dt: DateTime<Utc>) -> BsonDateTime {
BsonDateTime::from_chrono(dt)
}
/// Whether a Mongo error is a duplicate-key (E11000) violation — a job with this
/// id is already enqueued.
fn is_duplicate_key(e: &mongodb::error::Error) -> bool {
match &*e.kind {
ErrorKind::Write(WriteFailure::WriteError(we)) => we.code == 11000,
_ => false,
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn ttl_saturates_and_converts() {
assert_eq!(ttl(Duration::from_secs(30)), chrono::Duration::seconds(30));
// An absurd TTL saturates instead of panicking.
assert_eq!(ttl(Duration::from_secs(u64::MAX)), chrono::Duration::MAX);
}
#[test]
fn state_constants_are_disjoint() {
for s in ACTIVE_STATES {
assert!(
!TERMINAL_STATES.contains(&s),
"{s} cannot be both active and terminal"
);
}
}
}
+39 -54
View File
@@ -2,10 +2,6 @@
//
// Spins up the agent API server on a random port with an isolated test
// database. Each test gets a fresh database that is dropped on cleanup.
//
// Included via `mod common;` in several test binaries; not every binary uses
// every helper, so allow dead code here.
#![allow(dead_code)]
use std::sync::Arc;
@@ -15,55 +11,6 @@ use compliance_agent::database::DatabasePool;
use compliance_core::AgentConfig;
use secrecy::SecretString;
/// The runner bearer token wired into the test config.
pub const TEST_RUNNER_TOKEN: &str = "test-runner-token";
/// A minimal dev [`AgentConfig`] for tests: unauthenticated (no Keycloak), the
/// Werkbank runner API enabled with [`TEST_RUNNER_TOKEN`].
pub fn dev_config(mongodb_uri: String, db_name: String) -> AgentConfig {
AgentConfig {
mongodb_uri,
mongodb_database: db_name,
litellm_url: std::env::var("TEST_LITELLM_URL")
.unwrap_or_else(|_| "http://localhost:4000".into()),
litellm_api_key: SecretString::from(String::new()),
litellm_model: "gpt-4o".into(),
litellm_embed_model: "text-embedding-3-small".into(),
agent_port: 0, // not used — we bind ourselves
scan_schedule: String::new(),
cve_monitor_schedule: String::new(),
git_clone_base_path: "/tmp/compliance-scanner-tests/repos".into(),
artifact_store_base_path: "/tmp/compliance-scanner-tests/artifacts".into(),
ssh_key_path: "/tmp/compliance-scanner-tests/ssh/id_ed25519".into(),
github_token: None,
github_webhook_secret: None,
gitlab_url: None,
gitlab_token: None,
gitlab_webhook_secret: None,
jira_url: None,
jira_email: None,
jira_api_token: None,
jira_project_key: None,
searxng_url: None,
nvd_api_key: None,
keycloak_url: None,
keycloak_realm: None,
keycloak_admin_username: None,
keycloak_admin_password: None,
pentest_verification_email: None,
pentest_imap_host: None,
pentest_imap_port: None,
pentest_imap_tls: false,
pentest_imap_username: None,
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
plc_runtime: compliance_core::PlcRuntimeConfig::default(),
werkbank_runner_token: Some(SecretString::from(TEST_RUNNER_TOKEN.to_string())),
breakpilot: compliance_core::config::BreakpilotConfig::default(),
}
}
/// A running test server with a unique database.
pub struct TestServer {
pub base_url: String,
@@ -86,7 +33,45 @@ impl TestServer {
.await
.expect("Failed to build DatabasePool");
let config = dev_config(mongodb_uri.clone(), db_name.clone());
let config = AgentConfig {
mongodb_uri: mongodb_uri.clone(),
mongodb_database: db_name.clone(),
litellm_url: std::env::var("TEST_LITELLM_URL")
.unwrap_or_else(|_| "http://localhost:4000".into()),
litellm_api_key: SecretString::from(String::new()),
litellm_model: "gpt-4o".into(),
litellm_embed_model: "text-embedding-3-small".into(),
agent_port: 0, // not used — we bind ourselves
scan_schedule: String::new(),
cve_monitor_schedule: String::new(),
git_clone_base_path: "/tmp/compliance-scanner-tests/repos".into(),
artifact_store_base_path: "/tmp/compliance-scanner-tests/artifacts".into(),
ssh_key_path: "/tmp/compliance-scanner-tests/ssh/id_ed25519".into(),
github_token: None,
github_webhook_secret: None,
gitlab_url: None,
gitlab_token: None,
gitlab_webhook_secret: None,
jira_url: None,
jira_email: None,
jira_api_token: None,
jira_project_key: None,
searxng_url: None,
nvd_api_key: None,
keycloak_url: None,
keycloak_realm: None,
keycloak_admin_username: None,
keycloak_admin_password: None,
pentest_verification_email: None,
pentest_imap_host: None,
pentest_imap_port: None,
pentest_imap_tls: false,
pentest_imap_username: None,
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
plc_runtime: compliance_core::PlcRuntimeConfig::default(),
};
let agent = ComplianceAgent::new(config, db_pool);
-291
View File
@@ -1,291 +0,0 @@
//! Integration tests for the Werkbank runner endpoints (WB-05).
//!
//! Drives the real HTTP handlers (lease/heartbeat/complete) against a live Mongo:
//! a runner leases a seeded job, completes it, and the result's findings are
//! persisted against the job's target. Also checks the bearer-token gate. Skips
//! cleanly when no Mongo is reachable.
#![allow(clippy::expect_used, clippy::unwrap_used)]
mod common;
use std::sync::Arc;
use axum::routing::{get, post};
use axum::{middleware, Extension, Router};
use compliance_agent::agent::ComplianceAgent;
use compliance_agent::api::handlers::werkbank_jobs;
use compliance_agent::database::DatabasePool;
use compliance_agent::werkbank::JobQueue;
use compliance_core::models::werkbank::{InputRef, Job, JobResult, JobStatus, LeasedJob};
use compliance_core::models::{
Artifact, Finding, OnboardedTarget, PlcFormat, ScanType, Severity, TargetType,
};
use common::{dev_config, TEST_RUNNER_TOKEN};
const TENANT: &str = "dev";
/// A running werkbank API on a random port, or `None` if no Mongo.
struct Harness {
base_url: String,
client: reqwest::Client,
pool: DatabasePool,
db_name: String,
}
async fn start() -> Option<Harness> {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let db_name = format!("wba_{}", &uuid::Uuid::new_v4().simple().to_string()[..12]);
let pool = match DatabasePool::connect(&uri, &db_name).await {
Ok(p) => p,
Err(_) => {
eprintln!("SKIP werkbank_api: no MongoDB reachable at {uri}");
return None;
}
};
// Touch the tenant DB so indexes are ensured before the queue is used.
pool.for_tenant_id(TENANT).await.expect("tenant db");
let agent = ComplianceAgent::new(dev_config(uri, db_name.clone()), pool.clone());
let app = Router::new()
.route("/api/v1/werkbank/jobs/lease", post(werkbank_jobs::lease))
.route(
"/api/v1/werkbank/jobs/heartbeat",
post(werkbank_jobs::heartbeat),
)
.route(
"/api/v1/werkbank/jobs/complete",
post(werkbank_jobs::complete),
)
.route(
"/api/v1/werkbank/jobs/enqueue",
post(werkbank_jobs::enqueue),
)
.route(
"/api/v1/werkbank/artifacts/{hash}",
get(werkbank_jobs::serve_artifact),
)
.layer(middleware::from_fn(werkbank_jobs::require_runner_token))
.layer(Extension(Arc::new(agent)));
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
let port = listener.local_addr().unwrap().port();
tokio::spawn(async move {
axum::serve(listener, app).await.ok();
});
Some(Harness {
base_url: format!("http://127.0.0.1:{port}"),
client: reqwest::Client::new(),
pool,
db_name,
})
}
impl Harness {
fn post(
&self,
path: &str,
token: Option<&str>,
body: serde_json::Value,
) -> reqwest::RequestBuilder {
let mut r = self
.client
.post(format!("{}{path}", self.base_url))
.json(&body);
if let Some(t) = token {
r = r.bearer_auth(t);
}
r
}
async fn cleanup(&self) {
let _ = self
.pool
.client()
.database(&format!("{}_{TENANT}", self.db_name))
.drop()
.await;
}
}
fn finding_for(target: &str, fp: &str) -> Finding {
let mut f = Finding::new(
target.to_string(),
fp.to_string(),
"ics-probe".to_string(),
ScanType::IcsProbe,
"Modbus exposed".to_string(),
"unauthenticated".to_string(),
Severity::Critical,
);
f.rule_id = Some("ics-modbus-exposed".to_string());
f
}
#[tokio::test]
async fn lease_complete_persists_findings_against_the_target() {
let Some(h) = start().await else { return };
let db = h.pool.for_tenant_id(TENANT).await.unwrap();
let queue = JobQueue::new(&db);
// Seed a queued job.
let job = Job::plc_provision("job-1", TENANT, "target-1", InputRef::blob("sha256:x"), 180);
assert!(queue.enqueue(job, chrono::Utc::now()).await.unwrap());
// Lease it over HTTP.
let resp = h
.post(
"/api/v1/werkbank/jobs/lease",
Some(TEST_RUNNER_TOKEN),
serde_json::json!({
"tenant": TENANT, "runner_id": "r1", "executor": "docker",
"labels": [], "lease_ttl_secs": 60
}),
)
.send()
.await
.unwrap();
assert_eq!(resp.status(), 200, "lease should return a job");
let leased: LeasedJob = resp.json().await.unwrap();
assert_eq!(leased.job.id, "job-1");
// Complete it with a finding.
let mut result = JobResult::succeeded("job-1");
result.findings = vec![finding_for("target-1", "fp-abc")];
let resp = h
.post(
"/api/v1/werkbank/jobs/complete",
Some(TEST_RUNNER_TOKEN),
serde_json::json!({
"tenant": TENANT, "job_id": "job-1",
"lease_token": leased.lease_token, "result": result
}),
)
.send()
.await
.unwrap();
assert_eq!(resp.status(), 200);
assert!(resp.json::<serde_json::Value>().await.unwrap()["recorded"]
.as_bool()
.unwrap());
// The job is now succeeded, and the finding was persisted to the target.
assert_eq!(
queue.get("job-1").await.unwrap().unwrap().status,
JobStatus::Succeeded
);
let stored = db
.findings()
.find_one(mongodb::bson::doc! { "fingerprint": "fp-abc" })
.await
.unwrap();
assert!(stored.is_some(), "finding should be persisted");
h.cleanup().await;
}
#[tokio::test]
async fn enqueue_extracts_program_stores_a_blob_and_serves_it() {
let Some(h) = start().await else { return };
let db = h.pool.for_tenant_id(TENANT).await.unwrap();
// A PlcSps target with a single complete ST program uploaded.
let dir = std::env::temp_dir().join(format!("wbq-prog-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&dir).unwrap();
let st = dir.join("main.st");
std::fs::write(
&st,
"PROGRAM Main\nEND_PROGRAM\nCONFIGURATION C\n RESOURCE R\nEND_CONFIGURATION\n",
)
.unwrap();
let mut target = OnboardedTarget::new("plc".into(), TargetType::PlcSps);
let mut art = Artifact::plc_project("main.st", PlcFormat::StructuredText);
art.stored_path = Some(st.to_string_lossy().to_string());
target.artifacts.push(art);
let ins = db.onboarded_targets().insert_one(&target).await.unwrap();
let target_id = ins.inserted_id.as_object_id().unwrap().to_hex();
// Enqueue → a plc-provision job whose program is a content-addressed blob.
let resp = h
.post(
"/api/v1/werkbank/jobs/enqueue",
Some(TEST_RUNNER_TOKEN),
serde_json::json!({ "tenant": TENANT, "target_id": target_id }),
)
.send()
.await
.unwrap();
assert_eq!(resp.status(), 200, "enqueue should succeed");
let body: serde_json::Value = resp.json().await.unwrap();
let job_id = body["job_id"].as_str().unwrap().to_string();
let rec = JobQueue::new(&db).get(&job_id).await.unwrap().unwrap();
let hash = rec
.job
.inputs
.get("program")
.and_then(|i| i.blob.clone())
.expect("program blob");
// Serve the blob back and confirm it's the program source (what the runner
// would fetch).
let served = h
.client
.get(format!("{}/api/v1/werkbank/artifacts/{hash}", h.base_url))
.bearer_auth(TEST_RUNNER_TOKEN)
.send()
.await
.unwrap();
assert_eq!(served.status(), 200);
assert!(served.text().await.unwrap().contains("CONFIGURATION"));
h.cleanup().await;
let _ = std::fs::remove_dir_all(&dir);
}
#[tokio::test]
async fn empty_queue_leases_nothing() {
let Some(h) = start().await else { return };
let resp = h
.post(
"/api/v1/werkbank/jobs/lease",
Some(TEST_RUNNER_TOKEN),
serde_json::json!({
"tenant": TENANT, "runner_id": "r1", "executor": "docker",
"labels": [], "lease_ttl_secs": 60
}),
)
.send()
.await
.unwrap();
assert_eq!(resp.status(), 204, "no job → 204");
h.cleanup().await;
}
#[tokio::test]
async fn runner_endpoints_require_the_bearer_token() {
let Some(h) = start().await else { return };
let body = serde_json::json!({
"tenant": TENANT, "runner_id": "r1", "executor": "docker",
"labels": [], "lease_ttl_secs": 60
});
let no_token = h
.post("/api/v1/werkbank/jobs/lease", None, body.clone())
.send()
.await
.unwrap();
assert_eq!(no_token.status(), 401, "missing token → 401");
let bad_token = h
.post("/api/v1/werkbank/jobs/lease", Some("wrong"), body)
.send()
.await
.unwrap();
assert_eq!(bad_token.status(), 401, "wrong token → 401");
h.cleanup().await;
}
-258
View File
@@ -1,258 +0,0 @@
//! Integration tests for the Werkbank job queue (WB-02).
//!
//! Exercises the atomic lease/heartbeat/complete/sweep flow against a real
//! MongoDB — the guarantees (idempotent enqueue, single-owner lease, visibility
//! timeout) are Mongo-semantics-dependent and can't be unit-tested in isolation.
//! Skips cleanly when no Mongo is reachable (set `TEST_MONGODB_URI` to point at
//! one; defaults to the local dev cluster).
#![allow(clippy::expect_used, clippy::unwrap_used)]
use std::time::Duration;
use chrono::{DateTime, TimeZone, Utc};
use compliance_agent::database::Database;
use compliance_agent::werkbank::JobQueue;
use compliance_core::models::werkbank::{Executor, InputRef, Job, JobResult};
/// Connect + ensure indexes on a throwaway database, or `None` if no Mongo.
async fn setup() -> Option<(JobQueue, mongodb::Database)> {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let db_name = format!("wbq_{}", &uuid::Uuid::new_v4().simple().to_string()[..12]);
let db = match Database::connect(&uri, &db_name).await {
Ok(d) => d,
Err(_) => {
eprintln!("SKIP werkbank_queue: no MongoDB reachable at {uri}");
return None;
}
};
db.ensure_indexes().await.expect("ensure indexes");
let queue = JobQueue::new(&db);
Some((queue, db.inner().clone()))
}
fn base_time() -> DateTime<Utc> {
Utc.timestamp_opt(1_700_000_000, 0).unwrap()
}
fn job(id: &str) -> Job {
Job::plc_provision(id, "acme", "target-1", InputRef::blob("sha256:abc"), 180)
}
fn job_with_labels(id: &str, labels: &[&str]) -> Job {
let mut j = job(id);
j.labels = labels.iter().map(|s| s.to_string()).collect();
j
}
macro_rules! skip_if_no_mongo {
() => {
match setup().await {
Some(v) => v,
None => return,
}
};
}
#[tokio::test]
async fn enqueue_is_idempotent() {
let (q, db) = skip_if_no_mongo!();
let now = base_time();
assert!(q.enqueue(job("j1"), now).await.expect("enqueue"));
// Same id again — no duplicate row, reports "already present".
assert!(!q.enqueue(job("j1"), now).await.expect("enqueue2"));
let rec = q.get("j1").await.expect("get").expect("exists");
assert_eq!(
rec.status,
compliance_core::models::werkbank::JobStatus::Queued
);
assert_eq!(rec.attempts, 0);
db.drop().await.ok();
}
#[tokio::test]
async fn lease_matches_executor_and_labels_and_is_fifo() {
let (q, db) = skip_if_no_mongo!();
let t0 = base_time();
// Two docker jobs (j_old older than j_new) + one requiring a kvm label.
q.enqueue(job("j_old"), t0).await.unwrap();
q.enqueue(job("j_new"), t0 + chrono::Duration::seconds(5))
.await
.unwrap();
q.enqueue(job_with_labels("j_kvm", &["kvm=true"]), t0)
.await
.unwrap();
// Wrong executor: a shell runner leases nothing.
assert!(q
.lease("r-shell", Executor::Shell, &[], Duration::from_secs(30), t0)
.await
.unwrap()
.is_none());
// A docker runner without the kvm label gets the oldest label-free job (FIFO).
let leased = q
.lease("r1", Executor::Docker, &[], Duration::from_secs(30), t0)
.await
.unwrap()
.expect("leased");
assert_eq!(leased.job.id, "j_old", "oldest matching job first");
assert!(!leased.lease_token.is_empty());
// The kvm job stays unleased for that runner (missing label)...
let none = q
.lease("r1", Executor::Docker, &[], Duration::from_secs(30), t0)
.await
.unwrap()
.expect("next");
assert_eq!(none.job.id, "j_new", "label-free job, not the kvm one");
// ...but a runner advertising kvm can take it.
let kvm = q
.lease(
"r2",
Executor::Docker,
&["kvm=true".to_string(), "arch=amd64".to_string()],
Duration::from_secs(30),
t0,
)
.await
.unwrap()
.expect("kvm leased");
assert_eq!(kvm.job.id, "j_kvm");
// A leased job increments attempts and is no longer queued.
let rec = q.get("j_old").await.unwrap().unwrap();
assert_eq!(rec.attempts, 1);
assert_eq!(rec.leased_by.as_deref(), Some("r1"));
db.drop().await.ok();
}
#[tokio::test]
async fn heartbeat_extends_lease_and_surfaces_cancel() {
let (q, db) = skip_if_no_mongo!();
let now = base_time();
q.enqueue(job("j1"), now).await.unwrap();
let leased = q
.lease("r1", Executor::Docker, &[], Duration::from_secs(30), now)
.await
.unwrap()
.unwrap();
// A valid heartbeat moves it to running and reports not-cancelled.
let ack = q
.heartbeat("j1", &leased.lease_token, Duration::from_secs(30), now)
.await
.unwrap()
.expect("valid lease");
assert!(!ack.cancelled);
assert_eq!(
q.get("j1").await.unwrap().unwrap().status,
compliance_core::models::werkbank::JobStatus::Running
);
// A wrong token is a lost lease.
assert!(q
.heartbeat("j1", "wrong-token", Duration::from_secs(30), now)
.await
.unwrap()
.is_none());
// Cancelling an in-flight job flags it; the next heartbeat reports cancelled.
assert!(q.cancel("j1", now).await.unwrap());
let ack = q
.heartbeat("j1", &leased.lease_token, Duration::from_secs(30), now)
.await
.unwrap()
.expect("still leased");
assert!(ack.cancelled);
db.drop().await.ok();
}
#[tokio::test]
async fn complete_is_idempotent_and_token_guarded() {
let (q, db) = skip_if_no_mongo!();
let now = base_time();
q.enqueue(job("j1"), now).await.unwrap();
let leased = q
.lease("r1", Executor::Docker, &[], Duration::from_secs(30), now)
.await
.unwrap()
.unwrap();
// Wrong token cannot complete.
let mut result = JobResult::succeeded("j1");
result.findings = Vec::new();
assert!(!q.complete("j1", "nope", &result, now).await.unwrap());
// The lease holder completes it once...
assert!(q
.complete("j1", &leased.lease_token, &result, now)
.await
.unwrap());
let rec = q.get("j1").await.unwrap().unwrap();
assert_eq!(
rec.status,
compliance_core::models::werkbank::JobStatus::Succeeded
);
assert!(rec.result.is_some());
assert!(rec.lease_token.is_none(), "lease cleared on completion");
// ...and a second (duplicate) completion is a no-op.
assert!(!q
.complete("j1", &leased.lease_token, &result, now)
.await
.unwrap());
db.drop().await.ok();
}
#[tokio::test]
async fn sweep_requeues_expired_then_expires_after_max_attempts() {
let (q, db) = skip_if_no_mongo!();
let t0 = base_time();
q.enqueue(job("j1"), t0).await.unwrap();
// Lease #1 with a 10s TTL; then time jumps past expiry.
q.lease("r1", Executor::Docker, &[], Duration::from_secs(10), t0)
.await
.unwrap()
.unwrap();
let past = t0 + chrono::Duration::seconds(60);
// attempts=1 < max=2 → requeued.
let swept = q.sweep_expired(past, 2).await.unwrap();
assert_eq!(swept.requeued, 1);
assert_eq!(swept.expired, 0);
assert_eq!(
q.get("j1").await.unwrap().unwrap().status,
compliance_core::models::werkbank::JobStatus::Queued
);
// Lease #2 (attempts=2), let it expire again → now expired (>= max).
q.lease("r2", Executor::Docker, &[], Duration::from_secs(10), past)
.await
.unwrap()
.unwrap();
let later = past + chrono::Duration::seconds(60);
let swept = q.sweep_expired(later, 2).await.unwrap();
assert_eq!(swept.requeued, 0);
assert_eq!(swept.expired, 1);
assert_eq!(
q.get("j1").await.unwrap().unwrap().status,
compliance_core::models::werkbank::JobStatus::Expired
);
db.drop().await.ok();
}
+5 -5
View File
@@ -64,11 +64,11 @@ struct Claims {
const PUBLIC_ENDPOINTS: &[&str] = &["/api/v1/health"];
/// Path prefixes that bypass JWT validation. The admin sub-router
/// (`/api/v1/admin/*`) and the Werkbank runner API (`/api/v1/werkbank/*`)
/// have their 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 these cross-tenant / machine operations.
const PUBLIC_PREFIXES: &[&str] = &["/api/v1/admin/", "/api/v1/werkbank/"];
/// (`/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.
-32
View File
@@ -53,38 +53,6 @@ pub struct AgentConfig {
/// default: it needs Docker access in the agent's runtime, which is a
/// deployment opt-in.
pub plc_runtime: PlcRuntimeConfig,
/// Static bearer for the Werkbank runner endpoints
/// (`/api/v1/werkbank/jobs/*`). Machine auth for runners leasing/completing
/// jobs — NOT a Keycloak JWT, since a runner acts across tenants. When
/// `None`, those endpoints are not mounted at all.
pub werkbank_runner_token: Option<SecretString>,
/// Source for the OSCAL control catalog pulled from breakpilot-compliance
/// (drives the [`crate::traits::ControlsProvider`]). Disabled when
/// `base_url` is `None`.
pub breakpilot: BreakpilotConfig,
}
/// Where to pull the OSCAL control catalog from breakpilot-compliance, and where
/// to snapshot it for deterministic / offline reuse.
#[derive(Debug, Clone)]
pub struct BreakpilotConfig {
/// Backend base URL (e.g. `http://backend-compliance:8002`). `None` disables
/// the OSCAL controls provider.
pub base_url: Option<String>,
/// Optional bearer token for the catalog endpoint.
pub token: Option<SecretString>,
/// Directory for catalog snapshots.
pub snapshot_dir: String,
}
impl Default for BreakpilotConfig {
fn default() -> Self {
Self {
base_url: None,
token: None,
snapshot_dir: "/data/compliance-scanner/oscal".to_string(),
}
}
}
/// Configuration for the ephemeral soft-PLC "provision-and-test" path (#183).
+1 -7
View File
@@ -10,8 +10,6 @@ pub mod mcp;
pub mod mcp_token;
pub mod notification;
pub mod onboarding;
pub mod oscal;
pub mod oscal_assessment;
pub mod pentest;
pub mod repository;
pub mod sbom;
@@ -41,8 +39,6 @@ pub use onboarding::{
GitArtifactConfig, IssueTrackerConfig, OnboardedTarget, PlcArtifactConfig, PlcFormat,
TargetScanConfig, TargetType, TargetTypeCandidate, WebArtifactConfig,
};
pub use oscal::OscalDocument;
pub use oscal_assessment::{assess, AssessmentResultsDoc, ControlLinker};
pub use pentest::{
AttackChainNode, AttackNodeStatus, AuthMode, CodeContextHint, Environment, IdentityProvider,
PentestAuthConfig, PentestConfig, PentestEvent, PentestMessage, PentestSession, PentestStats,
@@ -53,7 +49,5 @@ pub use repository::ScanTrigger;
pub use sbom::{SbomEntry, VulnRef};
pub use scan::{ScanPhase, ScanRun, ScanRunStatus, ScanType};
pub use werkbank::{
CompleteRequest, CompleteResponse, DastCollect, Executor, HeartbeatAck, HeartbeatRequest,
InputRef, Job, JobCollect, JobRecord, JobResult, JobRuntime, JobStatus, JobType, LeaseRequest,
LeasedJob,
DastCollect, Executor, InputRef, Job, JobCollect, JobResult, JobRuntime, JobStatus, JobType,
};
-250
View File
@@ -1,250 +0,0 @@
//! OSCAL 1.1 catalog types + mapping into the controls corpus.
//!
//! Deserialises the OSCAL catalog served by breakpilot-compliance
//! (`GET /api/compliance/v1/oscal/catalog`) and maps its controls into the
//! framework-agnostic [`crate::traits::Control`] that the mapping engine consumes.
//! Only the fields we use are modelled; unknown OSCAL fields are ignored so the
//! producer can add detail without breaking us.
//!
//! Scope boundary: this is the *catalog* (domain content). Assessment objectives
//! and scanner routing live in our assessment layer, not here — see
//! [`crate::traits::ControlsProvider`].
use serde::Deserialize;
use crate::models::onboarding::ComplianceFramework;
use crate::traits::Control as CorpusControl;
/// A parsed OSCAL catalog document (`{"catalog": {...}}`).
#[derive(Debug, Clone, Deserialize)]
pub struct OscalDocument {
pub catalog: Catalog,
}
/// An OSCAL catalog: metadata + a tree of control groups.
#[derive(Debug, Clone, Deserialize)]
pub struct Catalog {
pub uuid: String,
pub metadata: Metadata,
#[serde(default)]
pub groups: Vec<Group>,
#[serde(rename = "back-matter", default)]
pub back_matter: Option<BackMatter>,
}
/// Catalog metadata (title/version + provenance props).
#[derive(Debug, Clone, Deserialize)]
pub struct Metadata {
pub title: String,
pub version: String,
#[serde(rename = "oscal-version")]
pub oscal_version: String,
#[serde(default)]
pub props: Vec<Prop>,
}
/// A name/value property, optionally namespaced.
#[derive(Debug, Clone, Deserialize)]
pub struct Prop {
pub name: String,
pub value: String,
#[serde(default)]
pub ns: Option<String>,
}
/// A control group (may nest sub-groups and controls).
#[derive(Debug, Clone, Deserialize)]
pub struct Group {
#[serde(default)]
pub id: String,
#[serde(default)]
pub title: String,
#[serde(default)]
pub controls: Vec<Control>,
#[serde(default)]
pub groups: Vec<Group>,
}
/// An OSCAL control (may nest enhancement controls).
#[derive(Debug, Clone, Deserialize)]
pub struct Control {
pub id: String,
#[serde(default)]
pub title: String,
#[serde(default)]
pub props: Vec<Prop>,
#[serde(default)]
pub parts: Vec<Part>,
#[serde(default)]
pub links: Vec<Link>,
#[serde(default)]
pub controls: Vec<Control>,
}
/// A control part (e.g. the `statement`), may nest sub-parts.
#[derive(Debug, Clone, Deserialize)]
pub struct Part {
#[serde(default)]
pub name: String,
#[serde(default)]
pub prose: Option<String>,
#[serde(default)]
pub parts: Vec<Part>,
}
/// A link, e.g. a `reference` to a back-matter resource.
#[derive(Debug, Clone, Deserialize)]
pub struct Link {
pub href: String,
#[serde(default)]
pub rel: Option<String>,
}
/// Back-matter holding referenced resources (e.g. the CRA measures).
#[derive(Debug, Clone, Deserialize)]
pub struct BackMatter {
#[serde(default)]
pub resources: Vec<Resource>,
}
/// A back-matter resource referenced by control links.
#[derive(Debug, Clone, Deserialize)]
pub struct Resource {
pub uuid: String,
#[serde(default)]
pub title: Option<String>,
#[serde(default)]
pub description: Option<String>,
}
impl Metadata {
/// First prop value with the given name.
pub fn prop(&self, name: &str) -> Option<&str> {
self.props
.iter()
.find(|p| p.name == name)
.map(|p| p.value.as_str())
}
}
impl Control {
/// First prop value with the given name.
pub fn prop(&self, name: &str) -> Option<&str> {
self.props
.iter()
.find(|p| p.name == name)
.map(|p| p.value.as_str())
}
/// The control's `statement` prose, if present.
pub fn statement(&self) -> Option<&str> {
self.parts
.iter()
.find(|p| p.name == "statement")
.and_then(|p| p.prose.as_deref())
}
}
impl OscalDocument {
/// The framework this catalog declares (`metadata.props[name="framework"]`).
pub fn framework(&self) -> Option<ComplianceFramework> {
framework_from_str(self.catalog.metadata.prop("framework")?)
}
/// The catalog `content-hash` prop — consumers pin this to snapshot/detect drift.
pub fn content_hash(&self) -> Option<&str> {
self.catalog.metadata.prop("content-hash")
}
/// Flatten the catalog into the corpus controls the mapping engine consumes.
pub fn to_controls(&self) -> Vec<CorpusControl> {
let framework = self.framework().unwrap_or(ComplianceFramework::Cra);
let source_label = self.catalog.metadata.title.as_str();
let mut out = Vec::new();
for group in &self.catalog.groups {
collect_group(group, framework, source_label, &mut out);
}
out
}
}
/// Map an OSCAL framework token (e.g. `"cra"`) to [`ComplianceFramework`] via its
/// serde snake_case representation.
fn framework_from_str(raw: &str) -> Option<ComplianceFramework> {
serde_json::from_value(serde_json::Value::String(raw.to_string())).ok()
}
fn collect_group(
group: &Group,
framework: ComplianceFramework,
source_label: &str,
out: &mut Vec<CorpusControl>,
) {
for control in &group.controls {
collect_control(control, framework, source_label, out);
}
for sub in &group.groups {
collect_group(sub, framework, source_label, out);
}
}
fn collect_control(
control: &Control,
framework: ComplianceFramework,
source_label: &str,
out: &mut Vec<CorpusControl>,
) {
let source = match control.prop("annex-anchor") {
Some(anchor) => Some(format!("{source_label} · {anchor}")),
None => Some(source_label.to_string()),
};
out.push(CorpusControl {
id: control.id.clone(),
framework,
title: control.title.clone(),
text: control.statement().unwrap_or_default().to_string(),
source,
});
for enhancement in &control.controls {
collect_control(enhancement, framework, source_label, out);
}
}
#[cfg(test)]
#[allow(clippy::unwrap_used)]
mod tests {
use super::*;
const CATALOG: &str = include_str!("../../tests/data/cra_catalog.json");
fn parse() -> OscalDocument {
serde_json::from_str(CATALOG).unwrap()
}
#[test]
fn parses_full_catalog() {
let doc = parse();
assert_eq!(doc.catalog.metadata.oscal_version, "1.1.2");
assert!(!doc.catalog.groups.is_empty());
assert!(doc.catalog.back_matter.is_some());
}
#[test]
fn maps_all_controls_to_corpus() {
let doc = parse();
let controls = doc.to_controls();
assert_eq!(controls.len(), 40);
assert_eq!(doc.framework(), Some(ComplianceFramework::Cra));
let c8 = controls.iter().find(|c| c.id == "cra-ai-8").unwrap();
assert_eq!(c8.framework, ComplianceFramework::Cra);
assert!(!c8.title.is_empty());
assert!(!c8.text.is_empty(), "statement prose should map into text");
assert!(c8.source.as_deref().unwrap_or_default().contains("Annex I"));
}
#[test]
fn exposes_content_hash_for_snapshotting() {
assert_eq!(parse().content_hash().map(str::len), Some(64));
}
}
@@ -1,402 +0,0 @@
//! OSCAL 1.1 assessment-results — assess our findings against catalog controls.
//!
//! The catalog (domain content) comes from the producer; the **assessment** is
//! ours. This links compliance [`Finding`]s to catalog control-ids and emits a
//! standard OSCAL assessment-results document: an observation per linked finding,
//! and a per-control finding with a `not-satisfied` status. `reviewed-controls`
//! records the full catalog set we considered.
//!
//! Deterministic: stable `uuid5` ids; the caller supplies the assessment
//! timestamp. Pure — no DB, no network.
use std::collections::HashMap;
use chrono::{DateTime, Utc};
use serde::Serialize;
use uuid::Uuid;
use crate::models::finding::Finding;
use crate::traits::Control;
const OSCAL_VERSION: &str = "1.1.2";
/// Same namespace as the catalog exporter, so ids are stable and correlatable.
const NAMESPACE: Uuid = Uuid::from_bytes([
0x6f, 0x1e, 0x7c, 0x2a, 0x3b, 0x4d, 0x5e, 0x6f, 0x8a, 0x9b, 0x0c, 0x1d, 0x2e, 0x3f, 0x4a, 0x5b,
]);
fn det_uuid(name: &str) -> String {
Uuid::new_v5(&NAMESPACE, name.as_bytes()).to_string()
}
/// Links findings to the catalog control-ids they provide evidence for.
pub struct ControlLinker {
cwe_to_controls: HashMap<u32, Vec<String>>,
}
impl ControlLinker {
/// Build a linker from an explicit CWE → control-id map.
pub fn new(cwe_to_controls: HashMap<u32, Vec<String>>) -> Self {
Self { cwe_to_controls }
}
/// Seed of CWE → CRA Annex I control mappings (mirrors breakpilot's
/// `_CWE_TO_REQ`; extend as scanner coverage grows).
pub fn cra_seed() -> Self {
let pairs: &[(u32, &str)] = &[
(798, "cra-ai-8"),
(259, "cra-ai-8"),
(1392, "cra-ai-8"),
(327, "cra-ai-13"),
(326, "cra-ai-13"),
(319, "cra-ai-15"),
(311, "cra-ai-15"),
(89, "cra-ai-20"),
(79, "cra-ai-20"),
(78, "cra-ai-20"),
(22, "cra-ai-20"),
];
let mut map: HashMap<u32, Vec<String>> = HashMap::new();
for (cwe, id) in pairs {
map.entry(*cwe).or_default().push((*id).to_string());
}
Self::new(map)
}
/// Parse a CWE token such as `"CWE-798"` or `"798"` into its number.
fn parse_cwe(raw: &str) -> Option<u32> {
raw.trim_start_matches(|c: char| !c.is_ascii_digit())
.split(|c: char| !c.is_ascii_digit())
.next()
.filter(|s| !s.is_empty())
.and_then(|s| s.parse().ok())
}
/// The control-ids a finding provides evidence for (via its CWE).
pub fn controls_for(&self, finding: &Finding) -> Vec<String> {
finding
.cwe
.as_deref()
.and_then(Self::parse_cwe)
.and_then(|cwe| self.cwe_to_controls.get(&cwe))
.cloned()
.unwrap_or_default()
}
}
/// Assess `findings` against `controls`: link findings to control-ids and build a
/// standard OSCAL assessment-results document. `at` is the assessment timestamp.
pub fn assess(
controls: &[Control],
findings: &[Finding],
linker: &ControlLinker,
at: DateTime<Utc>,
) -> AssessmentResultsDoc {
let ts = at.to_rfc3339();
let mut observations = Vec::new();
let mut obs_by_control: HashMap<String, Vec<String>> = HashMap::new();
for finding in findings {
let targets = linker.controls_for(finding);
if targets.is_empty() {
continue;
}
let obs_uuid = det_uuid(&format!("obs:{}", finding.fingerprint));
let location = match (&finding.file_path, finding.line_number) {
(Some(f), Some(l)) => Some(format!("{f}:{l}")),
(Some(f), None) => Some(f.clone()),
_ => None,
};
observations.push(Observation {
uuid: obs_uuid.clone(),
description: finding.title.clone(),
methods: vec!["TEST".to_string()],
collected: ts.clone(),
relevant_evidence: vec![RelevantEvidence {
href: location.map(|l| format!("file://{l}")),
description: format!("[{}] {}", finding.scanner, finding.title),
}],
});
for control_id in targets {
obs_by_control
.entry(control_id)
.or_default()
.push(obs_uuid.clone());
}
}
let titles: HashMap<&str, &str> = controls
.iter()
.map(|c| (c.id.as_str(), c.title.as_str()))
.collect();
let mut hit_controls: Vec<&String> = obs_by_control.keys().collect();
hit_controls.sort();
let ar_findings: Vec<ArFinding> = hit_controls
.into_iter()
.map(|control_id| {
let title = titles.get(control_id.as_str()).copied().unwrap_or("");
ArFinding {
uuid: det_uuid(&format!("finding:{control_id}")),
title: format!("Findings affect {control_id}: {title}"),
target: FindingTarget {
target_type: "statement-id".to_string(),
target_id: format!("{control_id}_smt"),
status: TargetStatus {
state: "not-satisfied".to_string(),
},
},
related_observations: obs_by_control[control_id]
.iter()
.map(|u| RelatedObservation {
observation_uuid: u.clone(),
})
.collect(),
}
})
.collect();
let include_controls = controls
.iter()
.map(|c| SelectControlById {
control_id: c.id.clone(),
})
.collect();
let result = ArResult {
uuid: det_uuid("result:cra"),
title: "Automated code-compliance assessment".to_string(),
description: format!(
"{} finding-linked observation(s) across {} reviewed control(s)",
observations.len(),
controls.len()
),
start: ts.clone(),
reviewed_controls: ReviewedControls {
control_selections: vec![ControlSelection { include_controls }],
},
observations,
findings: ar_findings,
};
AssessmentResultsDoc {
assessment_results: AssessmentResults {
uuid: det_uuid("assessment-results:cra"),
metadata: ArMetadata {
title: "Compliance scanner — OSCAL assessment results".to_string(),
last_modified: ts,
version: "1.0.0".to_string(),
oscal_version: OSCAL_VERSION.to_string(),
},
import_ap: ImportAp {
href: "#cra-annex-i".to_string(),
},
results: vec![result],
},
}
}
// ── OSCAL assessment-results document (serialise) ────────────────────────────
/// The root OSCAL assessment-results document.
#[derive(Debug, Clone, Serialize)]
pub struct AssessmentResultsDoc {
#[serde(rename = "assessment-results")]
pub assessment_results: AssessmentResults,
}
#[derive(Debug, Clone, Serialize)]
pub struct AssessmentResults {
pub uuid: String,
pub metadata: ArMetadata,
#[serde(rename = "import-ap")]
pub import_ap: ImportAp,
pub results: Vec<ArResult>,
}
#[derive(Debug, Clone, Serialize)]
pub struct ArMetadata {
pub title: String,
#[serde(rename = "last-modified")]
pub last_modified: String,
pub version: String,
#[serde(rename = "oscal-version")]
pub oscal_version: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct ImportAp {
pub href: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct ArResult {
pub uuid: String,
pub title: String,
pub description: String,
pub start: String,
#[serde(rename = "reviewed-controls")]
pub reviewed_controls: ReviewedControls,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub observations: Vec<Observation>,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub findings: Vec<ArFinding>,
}
#[derive(Debug, Clone, Serialize)]
pub struct ReviewedControls {
#[serde(rename = "control-selections")]
pub control_selections: Vec<ControlSelection>,
}
#[derive(Debug, Clone, Serialize)]
pub struct ControlSelection {
#[serde(rename = "include-controls", skip_serializing_if = "Vec::is_empty")]
pub include_controls: Vec<SelectControlById>,
}
#[derive(Debug, Clone, Serialize)]
pub struct SelectControlById {
#[serde(rename = "control-id")]
pub control_id: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct Observation {
pub uuid: String,
pub description: String,
pub methods: Vec<String>,
pub collected: String,
#[serde(rename = "relevant-evidence", skip_serializing_if = "Vec::is_empty")]
pub relevant_evidence: Vec<RelevantEvidence>,
}
#[derive(Debug, Clone, Serialize)]
pub struct RelevantEvidence {
#[serde(skip_serializing_if = "Option::is_none")]
pub href: Option<String>,
pub description: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct ArFinding {
pub uuid: String,
pub title: String,
pub target: FindingTarget,
#[serde(rename = "related-observations", skip_serializing_if = "Vec::is_empty")]
pub related_observations: Vec<RelatedObservation>,
}
#[derive(Debug, Clone, Serialize)]
pub struct FindingTarget {
#[serde(rename = "type")]
pub target_type: String,
#[serde(rename = "target-id")]
pub target_id: String,
pub status: TargetStatus,
}
#[derive(Debug, Clone, Serialize)]
pub struct TargetStatus {
pub state: String,
}
#[derive(Debug, Clone, Serialize)]
pub struct RelatedObservation {
#[serde(rename = "observation-uuid")]
pub observation_uuid: String,
}
#[cfg(test)]
#[allow(clippy::unwrap_used)]
mod tests {
use super::*;
use crate::models::finding::Severity;
use crate::models::onboarding::ComplianceFramework;
use crate::models::scan::ScanType;
fn control(id: &str, title: &str) -> Control {
Control {
id: id.into(),
framework: ComplianceFramework::Cra,
title: title.into(),
text: String::new(),
source: None,
}
}
fn finding(fp: &str, cwe: Option<&str>) -> Finding {
let mut f = Finding::new(
"repo".into(),
fp.into(),
"semgrep".into(),
ScanType::Sast,
"hardcoded credential".into(),
"desc".into(),
Severity::High,
);
f.cwe = cwe.map(Into::into);
f.file_path = Some("src/auth.rs".into());
f.line_number = Some(42);
f
}
fn at() -> DateTime<Utc> {
DateTime::parse_from_rfc3339("2026-07-20T00:00:00Z")
.unwrap()
.with_timezone(&Utc)
}
#[test]
fn links_cwe_finding_to_control_not_satisfied() {
let controls = vec![
control("cra-ai-8", "No default passwords"),
control("cra-ai-13", "Crypto"),
];
let findings = vec![finding("f1", Some("CWE-798"))];
let doc = assess(&controls, &findings, &ControlLinker::cra_seed(), at());
let r = &doc.assessment_results.results[0];
assert_eq!(r.observations.len(), 1);
assert_eq!(r.findings.len(), 1);
assert_eq!(r.findings[0].target.target_id, "cra-ai-8_smt");
assert_eq!(r.findings[0].target.status.state, "not-satisfied");
assert_eq!(r.findings[0].related_observations.len(), 1);
assert_eq!(
r.reviewed_controls.control_selections[0]
.include_controls
.len(),
2
);
}
#[test]
fn unlinked_finding_yields_no_control_finding() {
let controls = vec![control("cra-ai-8", "x")];
let findings = vec![finding("f1", Some("CWE-99999"))];
let doc = assess(&controls, &findings, &ControlLinker::cra_seed(), at());
let r = &doc.assessment_results.results[0];
assert!(r.observations.is_empty());
assert!(r.findings.is_empty());
}
#[test]
fn output_is_deterministic_and_valid_oscal() {
let controls = vec![control("cra-ai-8", "x")];
let findings = vec![finding("f1", Some("798"))];
let a = serde_json::to_string(&assess(
&controls,
&findings,
&ControlLinker::cra_seed(),
at(),
))
.unwrap();
let b = serde_json::to_string(&assess(
&controls,
&findings,
&ControlLinker::cra_seed(),
at(),
))
.unwrap();
assert_eq!(a, b);
assert!(a.contains("\"oscal-version\":\"1.1.2\""));
assert!(a.contains("\"not-satisfied\""));
}
}
-136
View File
@@ -266,142 +266,6 @@ impl JobResult {
}
}
/// A queued job as persisted by the control plane (WB-02): the [`Job`] contract
/// plus the queue bookkeeping — status, lease ownership, attempt count, and the
/// eventual result. The runner never sees this record; on lease it receives a
/// [`LeasedJob`] (the job plus a token it presents to heartbeat/complete).
///
/// Timestamps persist as native BSON dates so the queue's range queries (lease
/// FIFO by `created_at`, visibility-timeout sweep by `lease_expires_at`) compare
/// correctly.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct JobRecord {
/// The job to run.
pub job: Job,
/// Current queue state.
pub status: JobStatus,
/// The lease token held by the current runner (proves lease ownership).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub lease_token: Option<String>,
/// Id of the runner holding the lease.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub leased_by: Option<String>,
/// When the current lease expires — the visibility timeout after which a
/// crashed runner's job is swept back to `queued`.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub lease_expires_at: Option<DateTime<Utc>>,
/// Last heartbeat from the runner.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub heartbeat_at: Option<DateTime<Utc>>,
/// How many times the job has been leased (incremented on each lease).
#[serde(default)]
pub attempts: u32,
/// Set when the control plane requests cancellation; the runner sees it on
/// its next heartbeat and aborts.
#[serde(default)]
pub cancel_requested: bool,
/// The result, once the job reaches a terminal state.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub result: Option<JobResult>,
/// When the job was enqueued.
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
/// Last modification.
#[serde(with = "super::serde_helpers::bson_datetime")]
pub updated_at: DateTime<Utc>,
}
impl JobRecord {
/// A freshly-enqueued (`queued`) record for a job.
pub fn queued(job: Job, now: DateTime<Utc>) -> Self {
Self {
job,
status: JobStatus::Queued,
lease_token: None,
leased_by: None,
lease_expires_at: None,
heartbeat_at: None,
attempts: 0,
cancel_requested: false,
result: None,
created_at: now,
updated_at: now,
}
}
}
/// A job handed to a runner on lease: what to run plus the token the runner must
/// present to heartbeat and complete it.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct LeasedJob {
/// The job to execute.
pub job: Job,
/// The lease token proving ownership (opaque to the runner).
pub lease_token: String,
}
/// The runner's view of a heartbeat: whether the control plane has asked the job
/// to stop. `None` from the queue means the lease was lost (token mismatch or the
/// job already terminal) and the runner should abandon the work.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
pub struct HeartbeatAck {
/// The control plane requested cancellation — the runner should tear down.
pub cancelled: bool,
}
// --- Runner ↔ control-plane transport (the pull API wire types) ---------------
// Shared so the runner (client) and the control plane (server) agree on shapes.
/// Runner → control plane: lease the oldest runnable job for this runner.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct LeaseRequest {
/// The tenant queue to lease from.
pub tenant: String,
/// The runner id (advertised for attribution).
pub runner_id: String,
/// The executor this runner provides.
pub executor: Executor,
/// The capability labels this runner advertises.
#[serde(default)]
pub labels: Vec<String>,
/// Requested lease lifetime (the visibility timeout), in seconds.
pub lease_ttl_secs: u64,
}
/// Runner → control plane: prove lease ownership and extend it.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct HeartbeatRequest {
/// The tenant queue.
pub tenant: String,
/// The job being worked.
pub job_id: String,
/// The lease token from the [`LeasedJob`].
pub lease_token: String,
/// Lease lifetime to extend to, in seconds.
pub lease_ttl_secs: u64,
}
/// Runner → control plane: record a job's terminal result.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct CompleteRequest {
/// The tenant queue.
pub tenant: String,
/// The job being completed.
pub job_id: String,
/// The lease token proving ownership.
pub lease_token: String,
/// The result to record.
pub result: JobResult,
}
/// Control plane → runner: whether the completion was recorded (false if the
/// lease was already lost — token mismatch or the job had become terminal).
#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
pub struct CompleteResponse {
/// Whether the result was recorded.
pub recorded: bool,
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
File diff suppressed because it is too large Load Diff
-23
View File
@@ -1,23 +0,0 @@
[package]
name = "werkbank-exec"
version = "0.1.0"
edition = "2021"
description = "Shared dynamic-execution logic: soft-PLC provisioning + industrial-protocol probing, used by the compliance agent and the Werkbank runner."
[lints]
workspace = true
[dependencies]
compliance-core = { workspace = true }
compliance-dast = { path = "../compliance-dast" }
tokio = { workspace = true }
reqwest = { workspace = true }
uuid = { workspace = true }
regex = { workspace = true }
secrecy = { workspace = true }
sha2 = { workspace = true }
hex = { workspace = true }
tracing = { workspace = true }
thiserror = { workspace = true }
walkdir = "2"
futures-util = "0.3"
-16
View File
@@ -1,16 +0,0 @@
//! Error type for the dynamic-execution logic.
/// Anything that can go wrong provisioning and testing a soft-PLC. The compliance
/// agent maps this into its own `AgentError` at the call boundary.
#[derive(thiserror::Error, Debug)]
pub enum ExecError {
/// An HTTP request (to OpenPLC) failed.
#[error("HTTP error: {0}")]
Http(#[from] reqwest::Error),
/// A local IO / process error (e.g. invoking `docker`).
#[error("IO error: {0}")]
Io(#[from] std::io::Error),
/// Any other failure, with a message.
#[error("{0}")]
Other(String),
}
-32
View File
@@ -1,32 +0,0 @@
//! Finding fingerprint helper (a SHA-256 over the salient parts), shared by the
//! probe modules for stable dedup keys. Mirrors the agent's `dedup` helper.
use sha2::{Digest, Sha256};
/// A stable fingerprint over the given parts (order-sensitive, separated so
/// `["ab","c"]` and `["a","bc"]` differ).
pub fn compute_fingerprint(parts: &[&str]) -> String {
let mut hasher = Sha256::new();
for part in parts {
hasher.update(part.as_bytes());
hasher.update(b"|");
}
hex::encode(hasher.finalize())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn deterministic_and_hex() {
let a = compute_fingerprint(&["repo", "rule", "1"]);
assert_eq!(a, compute_fingerprint(&["repo", "rule", "1"]));
assert_eq!(a.len(), 64);
assert!(a.chars().all(|c| c.is_ascii_hexdigit()));
assert_ne!(
compute_fingerprint(&["ab", "c"]),
compute_fingerprint(&["a", "bc"])
);
}
}
-18
View File
@@ -1,18 +0,0 @@
//! Shared dynamic-execution logic for Werkbank.
//!
//! The soft-PLC provisioning + industrial-protocol probing that turns a control-
//! logic artifact into findings: provision an ephemeral OpenPLC, load the program,
//! start it, probe it over Modbus/OPC-UA/EtherNet-IP, DAST its web endpoint, tear
//! it down. Extracted from the compliance agent (#183) so both the agent (in
//! process) and the Werkbank runner (WB-04) run identical logic.
//!
//! - [`ics`] — read-only industrial-protocol probing.
//! - [`plc`] — ephemeral soft-PLC provisioning + the provision-and-test loop.
pub mod error;
pub mod ics;
pub mod plc;
mod fingerprint;
pub use error::ExecError;