Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Opus 4.8 d5ff60d55a feat(core): OSCAL assessment-results emitter + finding->control linker
CI / Check (pull_request) Successful in 7m21s
CI / Detect Changes (pull_request) Skipped
CI / Deploy Agent (pull_request) Skipped
CI / Deploy Dashboard (pull_request) Skipped
CI / Deploy Docs (pull_request) Skipped
CI / Deploy MCP (pull_request) Skipped
CI / Check (push) Skipped
Assess our findings against catalog controls and emit a standard OSCAL 1.1
assessment-results document — the assessment half of the loop (their catalog,
our assessment).

- ControlLinker maps a Finding's CWE -> catalog control-ids (CRA seed mirrors
  breakpilot's _CWE_TO_REQ; extensible via ControlLinker::new)
- assess() builds an observation per linked finding + a per-control
  'not-satisfied' finding; reviewed-controls covers the full catalog set
- deterministic: stable uuid5 ids (adds uuid "v5" feature) + caller-supplied
  timestamp; pure (no DB/network)
- 3 lib tests

Not yet wired into a scan run — that lands with the control-driven router (PR-4).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-20 18:26:01 +02:00
sharang d4884cfe4f feat(oscal): ingest breakpilot OSCAL catalog via OscalControlsProvider (#210)
CI / Deploy Agent (push) Successful in 3m40s
CI / Check (push) Skipped
CI / Detect Changes (push) Successful in 2s
CI / Deploy Docs (push) Skipped
CI / Deploy Dashboard (push) Successful in 2m34s
CI / Deploy MCP (push) Successful in 2m0s
2026-07-20 16:19:09 +00:00
sharang 94c0d51a11 feat(werkbank): make the loop runnable — enqueue + artifact serve/fetch (WB-05b) (#209)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m43s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
2026-07-17 14:34:00 +00:00
sharang 70a4ee55ab refactor(werkbank): extract soft-PLC provisioning + ICS probe into werkbank-exec (WB-04a) (#208)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m46s
CI / Deploy Dashboard (push) Successful in 2m53s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m2s
2026-07-17 12:56:15 +00:00
sharang 91a87677bc feat(werkbank): runner queue endpoints + result persistence (WB-05) (#207)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Successful in 3m44s
CI / Deploy Dashboard (push) Successful in 2m37s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m49s
2026-07-17 11:42:29 +00:00
sharang 633f945a1e feat(werkbank): Mongo-backed job queue with lease + visibility timeout (WB-02) (#206)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m31s
CI / Deploy Dashboard (push) Successful in 2m38s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m47s
2026-07-17 09:15:23 +00:00
sharang 7b218fffef feat(werkbank): job/result contract in compliance-core (WB-01) (#205)
CI / Check (push) Has been skipped
CI / Deploy Dashboard (push) Successful in 2m38s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m47s
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3m51s
2026-07-17 08:54:11 +00:00
sharang 7ad7bce9db feat(plc): dynamic PLC testing via ephemeral soft-PLC (#193)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy MCP (push) Successful in 1m49s
CI / Deploy Agent (push) Successful in 3m55s
CI / Deploy Dashboard (push) Successful in 2m37s
CI / Deploy Docs (push) Has been skipped
2026-07-17 07:47:43 +00:00
sharang 1aba85b28e docs(plc): PLC Runtime Landscape reference + support watch-list (#185)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Has been skipped
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Successful in 49s
CI / Deploy MCP (push) Has been skipped
2026-07-16 22:05:39 +00:00
sharang c6a84b327f docs(plc): soft-PLC architecture + CODESYS/Yocto lifecycle diagram (#184)
CI / Check (push) Waiting to run
CI / Detect Changes (push) Waiting to run
CI / Deploy Agent (push) Blocked by required conditions
CI / Deploy Dashboard (push) Blocked by required conditions
CI / Deploy Docs (push) Blocked by required conditions
CI / Deploy MCP (push) Blocked by required conditions
2026-07-16 22:00:17 +00:00
sharang 0f4c75b6b3 fix(matrix): DAST needs an http(s) endpoint; don't offer/run it on modbus:// (#182)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Successful in 3m34s
CI / Deploy Dashboard (push) Successful in 2m37s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m0s
2026-07-16 21:28:47 +00:00
sharang cd65fa345c feat(onboarding): enable opt-in scans from the wizard success step (#181)
CI / Check (push) Has been skipped
CI / Deploy Dashboard (push) Successful in 2m38s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Has been skipped
2026-07-16 20:52:50 +00:00
49 changed files with 7163 additions and 69 deletions
+18
View File
@@ -34,6 +34,24 @@ SCAN_SCHEDULE=0 0 */6 * * *
CVE_MONITOR_SCHEDULE=0 0 0 * * *
GIT_CLONE_BASE_PATH=/tmp/compliance-scanner/repos
# Dynamic PLC testing — ephemeral soft-PLC provisioning (#183). Off unless
# enabled; requires the agent container to have Docker access (socket mount).
# When on, a PLC/SPS target with control logic but no reachable device gets its
# logic instantiated on a throwaway OpenPLC, probed, then torn down.
PLC_RUNTIME_ENABLED=0
PLC_RUNTIME_IMAGE=registry.meghsakha.com/openplc:latest
PLC_RUNTIME_NETWORK=certifai
PLC_RUNTIME_MEMORY=512m
PLC_RUNTIME_CPUS=0.5
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
+4 -2
View File
@@ -107,6 +107,8 @@ 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
@@ -115,8 +117,8 @@ jobs:
RUSTC_WRAPPER: ""
# Tests (reuses compilation artifacts from clippy)
- name: Tests (core + agent)
run: cargo test -p compliance-core -p compliance-agent --lib
- name: Tests (core + agent + werkbank-exec)
run: cargo test -p compliance-core -p compliance-agent -p werkbank-exec --lib
- name: Tests (dashboard server)
run: cargo test -p compliance-dashboard --features server --no-default-features
- name: Tests (dashboard web)
Generated
+28
View File
@@ -699,6 +699,7 @@ dependencies = [
"urlencoding",
"uuid",
"walkdir",
"werkbank-exec",
"zip",
]
@@ -723,6 +724,7 @@ dependencies = [
"sha2",
"thiserror 2.0.18",
"tokio",
"toml",
"tracing",
"tracing-opentelemetry",
"tracing-subscriber",
@@ -5087,6 +5089,12 @@ 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"
@@ -6470,6 +6478,7 @@ dependencies = [
"getrandom 0.4.1",
"js-sys",
"serde_core",
"sha1_smol",
"wasm-bindgen",
]
@@ -6713,6 +6722,25 @@ 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"
+3 -2
View File
@@ -7,6 +7,7 @@ members = [
"compliance-dast",
"compliance-mcp",
"compliance-smoke",
"werkbank-exec",
]
resolver = "2"
@@ -23,11 +24,11 @@ tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
chrono = { version = "0.4", features = ["serde"] }
mongodb = { version = "3", features = ["rustls-tls", "compat-3-0-0"] }
reqwest = { version = "0.12", features = ["json", "rustls-tls", "multipart"], default-features = false }
reqwest = { version = "0.12", features = ["json", "rustls-tls", "multipart", "cookies"], default-features = false }
thiserror = "2"
sha2 = "0.10"
hex = "0.4"
uuid = { version = "1", features = ["v4", "serde"] }
uuid = { version = "1", features = ["v4", "v5", "serde"] }
secrecy = { version = "0.10", features = ["serde"] }
regex = "1"
zip = { version = "2", features = ["aes-crypto", "deflate"] }
+3
View File
@@ -10,6 +10,9 @@ 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
+1
View File
@@ -14,6 +14,7 @@ pub mod pentest_handlers;
pub use pentest_handlers as pentest;
pub mod sbom;
pub mod scans;
pub mod werkbank_jobs;
// Re-export all handler functions so routes.rs can use `handlers::function_name`
pub use dto::*;
@@ -0,0 +1,289 @@
//! 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"));
}
}
+36 -1
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};
use axum::routing::{delete, get, post};
use axum::{middleware, Extension, Router};
use tokio::sync::RwLock;
use tower_http::cors::CorsLayer;
@@ -72,8 +72,43 @@ 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))
+25
View File
@@ -1,3 +1,4 @@
use compliance_core::config::PlcRuntimeConfig;
use compliance_core::AgentConfig;
use secrecy::SecretString;
@@ -63,5 +64,29 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
pentest_imap_password: env_secret_opt("PENTEST_IMAP_PASSWORD"),
admin_api_token: env_secret_opt("ADMIN_API_TOKEN"),
tenant_registry_url: env_var_opt("TENANT_REGISTRY_URL"),
plc_runtime: load_plc_runtime_config(),
werkbank_runner_token: env_secret_opt("WERKBANK_RUNNER_TOKEN"),
})
}
/// Build the ephemeral soft-PLC provisioning config from the environment,
/// falling back to [`PlcRuntimeConfig::default`] for any unset knob. Disabled
/// unless `PLC_RUNTIME_ENABLED` is truthy — it requires Docker access.
fn load_plc_runtime_config() -> PlcRuntimeConfig {
let d = PlcRuntimeConfig::default();
PlcRuntimeConfig {
enabled: env_var_opt("PLC_RUNTIME_ENABLED")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(d.enabled),
image: env_var_opt("PLC_RUNTIME_IMAGE").unwrap_or(d.image),
network: env_var_opt("PLC_RUNTIME_NETWORK").unwrap_or(d.network),
memory: env_var_opt("PLC_RUNTIME_MEMORY").unwrap_or(d.memory),
cpus: env_var_opt("PLC_RUNTIME_CPUS").unwrap_or(d.cpus),
max_lifetime_secs: env_var_opt("PLC_RUNTIME_MAX_LIFETIME_SECS")
.and_then(|v| v.parse().ok())
.unwrap_or(d.max_lifetime_secs),
openplc_user: env_var_opt("PLC_RUNTIME_OPENPLC_USER").unwrap_or(d.openplc_user),
openplc_password: env_secret_opt("PLC_RUNTIME_OPENPLC_PASSWORD")
.unwrap_or(d.openplc_password),
}
}
+10
View File
@@ -0,0 +1,10 @@
//! 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;
@@ -0,0 +1,233 @@
//! 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
@@ -465,6 +465,34 @@ 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(())
}
@@ -563,6 +591,12 @@ 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
@@ -27,6 +27,9 @@ 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
@@ -32,6 +32,30 @@ 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`).
mod blob;
pub(crate) mod blob;
use std::collections::HashMap;
use std::path::{Path, PathBuf};
+2
View File
@@ -4,6 +4,7 @@ pub mod agent;
pub mod api;
pub mod classify;
pub mod config;
pub mod controls;
pub mod database;
pub mod error;
pub mod ingest;
@@ -16,3 +17,4 @@ pub mod ssh;
#[allow(dead_code)]
pub mod trackers;
pub mod webhooks;
pub mod werkbank;
+2
View File
@@ -342,6 +342,8 @@ mod tests {
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
plc_runtime: compliance_core::PlcRuntimeConfig::default(),
werkbank_runner_token: None,
}
}
-1
View File
@@ -5,7 +5,6 @@ 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;
+118 -6
View File
@@ -404,16 +404,37 @@ impl PipelineOrchestrator {
let ics = plan.has(ScanType::IcsProbe);
if plc {
new_count += self.run_plc_scan(target, &target_id, scan_run_id).await?;
// Provision-and-test (#183): with the control logic but no reachable
// device, instantiate it on an ephemeral soft-PLC and probe that
// instead of the customer's OT network. Opt-in (needs Docker) and only
// when there is no live URL to probe directly. Never fails the scan.
if self.config.plc_runtime.enabled && target.live_url().is_none() {
match self
.run_provisioned_plc_test(target, &target_id, scan_run_id)
.await
{
Ok(n) => new_count += n,
Err(e) => {
tracing::warn!(target_id = %target_id, error = %e, "provision-and-test failed")
}
}
}
}
if ics {
new_count += self.run_ics_probe(target, &target_id, scan_run_id).await?;
}
if plc || ics {
// PLC/SPS device: also DAST against a WebVisu / exposed endpoint. The
// control-logic scan already consumed the code artifact, so the SAST
// pipeline is not re-run.
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
// PLC/SPS device: also DAST against a WebVisu / exposed endpoint, but
// only when DAST is actually planned — a device reachable only over an
// industrial protocol (e.g. modbus://) has no web surface to crawl, and
// running DAST there just fails at reconnaissance. Gating here (not only
// at provisioning) also stops a DAST target left over from an earlier
// run from re-triggering. The control-logic scan already consumed the
// code artifact, so the SAST pipeline is not re-run.
if plan.has(ScanType::Dast) {
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
}
return Ok(new_count);
}
@@ -534,6 +555,97 @@ impl PipelineOrchestrator {
Ok(new_count)
}
/// Provision-and-test (#183): instantiate the target's control logic on an
/// ephemeral soft-PLC (OpenPLC), start it, probe the provisioned Modbus
/// endpoint, and tear the instance down. Used when a PLC/SPS target has the
/// control logic but no reachable live device to probe directly. Guarded by
/// `plc_runtime.enabled` (needs Docker); persists the same [`ScanType::IcsProbe`]
/// findings as a live probe.
async fn run_provisioned_plc_test(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) -> Result<u32, AgentError> {
self.update_phase(scan_run_id, "plc_provision").await;
// Locate a loadable control-logic program among the PLC-source artifacts
// (same selection as the static PLC scan: dedicated PLC projects plus code
// artifacts holding PLCopen XML / ST exports).
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = crate::ingest::ingest_all(target, &ctx)?;
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)
});
let Some(program) = program else {
tracing::info!(
target_id,
"provision-and-test: no loadable control-logic program"
);
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(
&provisioner,
&http,
&self.config.plc_runtime,
&program,
target_id,
)
.await?;
tracing::info!(
target_id,
found = outcome.findings.len(),
dast = outcome.dast.is_some(),
"provision-and-test complete"
);
let mut new_count = 0u32;
for mut finding in outcome.findings {
finding.scan_run_id = Some(scan_run_id.to_string());
if self
.db
.findings()
.find_one(doc! { "fingerprint": &finding.fingerprint })
.await?
.is_none()
{
self.db.findings().insert_one(&finding).await?;
new_count += 1;
}
}
// Persist the DAST scan of the provisioned web endpoint, linked to this
// scan run (mirrors `maybe_trigger_dast`).
if let Some(dast) = outcome.dast {
let mut scan_run = dast.scan_run;
scan_run.sast_scan_run_id = Some(scan_run_id.to_string());
if let Err(e) = self.db.dast_scan_runs().insert_one(&scan_run).await {
tracing::warn!(target_id, error = %e, "failed to store provisioned DAST scan run");
}
for finding in &dast.findings {
if let Err(e) = self.db.dast_findings().insert_one(finding).await {
tracing::warn!(target_id, error = %e, "failed to store provisioned DAST finding");
}
}
}
Ok(new_count)
}
/// Probe a running PLC/SPS device over industrial protocols (Modbus/TCP, …)
/// and persist findings for exposed / unauthenticated control access. The
/// probe is read-only; it targets the Modbus port of the target's live URL.
@@ -550,7 +662,7 @@ 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 = crate::pipeline::ics::probe_target(&endpoint, target_id, budget).await;
let findings = werkbank_exec::ics::probe_target(&endpoint, target_id, budget).await;
tracing::info!(
target_id,
endpoint = %endpoint,
+10
View File
@@ -0,0 +1,10 @@
//! 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
@@ -0,0 +1,309 @@
//! 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"
);
}
}
}
+53 -38
View File
@@ -2,6 +2,10 @@
//
// 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;
@@ -11,6 +15,54 @@ 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())),
}
}
/// A running test server with a unique database.
pub struct TestServer {
pub base_url: String,
@@ -33,44 +85,7 @@ impl TestServer {
.await
.expect("Failed to build DatabasePool");
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,
};
let config = dev_config(mongodb_uri.clone(), db_name.clone());
let agent = ComplianceAgent::new(config, db_pool);
+291
View File
@@ -0,0 +1,291 @@
//! 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
@@ -0,0 +1,258 @@
//! 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();
}
+4
View File
@@ -50,3 +50,7 @@ axum = { version = "0.8", optional = true }
jsonwebtoken = { version = "9", optional = true }
reqwest = { workspace = true, optional = true }
tokio = { workspace = true, optional = true }
[dev-dependencies]
# Parse the declarative TOML job specs in the Werkbank contract tests.
toml = "0.8"
+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/*`) 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/"];
/// (`/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/"];
/// Middleware that validates Bearer JWT tokens against Keycloak's JWKS
/// and attaches a `TenantContext` extension on success.
+56
View File
@@ -49,6 +49,62 @@ pub struct AgentConfig {
/// of tenants to iterate. When `None` or unreachable, scheduler
/// falls back to `SCHEDULER_TENANT_IDS` env (M7.2-C).
pub tenant_registry_url: Option<String>,
/// Ephemeral soft-PLC provisioning for dynamic PLC testing (#183). Off by
/// 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>,
}
/// Configuration for the ephemeral soft-PLC "provision-and-test" path (#183).
///
/// When a PLC/SPS target ships control logic but no reachable live device, the
/// agent can instantiate that logic itself: spin up a throwaway soft-PLC
/// (OpenPLC) container in-cluster, load the program, start the runtime, probe it
/// over industrial protocols, then tear it down. This struct carries the knobs
/// for that container's lifecycle and the OpenPLC web-UI credentials used to
/// upload the program.
#[derive(Clone, Debug)]
pub struct PlcRuntimeConfig {
/// Master switch. Provision-and-test does nothing unless this is set — it
/// shells out to `docker`, which requires the agent container to have Docker
/// access (socket mount), an explicit deployment decision.
pub enabled: bool,
/// Container image for the ephemeral soft-PLC (OpenPLC).
pub image: String,
/// Docker network the instance joins. Must be the agent's own network so it
/// is reachable in-cluster by container name and never published to the host.
pub network: String,
/// Memory cap passed to `docker run --memory` (e.g. `512m`).
pub memory: String,
/// CPU cap passed to `docker run --cpus` (e.g. `0.5`).
pub cpus: String,
/// Hard ceiling on a provisioned instance's lifetime. Teardown is guaranteed
/// no later than this even if a load/probe step hangs.
pub max_lifetime_secs: u64,
/// OpenPLC web-UI username for the program upload (image default `openplc`).
pub openplc_user: String,
/// OpenPLC web-UI password (image default `openplc`).
pub openplc_password: SecretString,
}
impl Default for PlcRuntimeConfig {
fn default() -> Self {
Self {
enabled: false,
image: "registry.meghsakha.com/openplc:latest".to_string(),
network: "certifai".to_string(),
memory: "512m".to_string(),
cpus: "0.5".to_string(),
max_lifetime_secs: 180,
openplc_user: "openplc".to_string(),
openplc_password: SecretString::from("openplc".to_string()),
}
}
}
#[derive(Clone, Debug, Serialize, Deserialize)]
+1 -1
View File
@@ -13,6 +13,6 @@ pub mod auth;
#[cfg(feature = "axum")]
pub mod tenant_ctx;
pub use config::{AgentConfig, DashboardConfig};
pub use config::{AgentConfig, DashboardConfig, PlcRuntimeConfig};
pub use error::CoreError;
pub use tenant::{OrgRole, TenantContext, TenantStatus};
+10
View File
@@ -10,11 +10,14 @@ 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;
pub mod scan;
pub(crate) mod serde_helpers;
pub mod werkbank;
pub use auth::AuthInfo;
pub use chat::{ChatMessage, ChatRequest, ChatResponse, SourceReference};
@@ -38,6 +41,8 @@ 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,
@@ -47,3 +52,8 @@ pub use pentest::{
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,
};
+250
View File
@@ -0,0 +1,250 @@
//! 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));
}
}
@@ -0,0 +1,402 @@
//! 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\""));
}
}
+514
View File
@@ -0,0 +1,514 @@
//! The Werkbank job/result contract (WB-01).
//!
//! The shared, dependency-free vocabulary the control plane and the Werkbank
//! execution runner agree on: what a [`Job`] is, which [`Executor`] runs it, how
//! it moves through the queue ([`JobStatus`]), and what a [`JobResult`] carries
//! back. Jobs are declarative — TOML on disk, JSON on the wire — and results
//! reuse the existing scanner result types ([`Finding`], [`DastFinding`],
//! [`SbomEntry`]) so the runner produces exactly what the control plane persists.
//!
//! This module is intentionally free of the `mongodb`/`axum` features so the
//! runner can depend on `compliance-core` without pulling the server stack.
use std::collections::BTreeMap;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use super::dast::DastFinding;
use super::finding::Finding;
use super::sbom::SbomEntry;
/// The kind of dynamic-execution job.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "kebab-case")]
pub enum JobType {
/// Instantiate control logic on an ephemeral soft-PLC and probe it.
PlcProvision,
/// Boot a firmware image under QEMU and run dynamic checks.
QemuBoot,
/// Crawl and dynamically test a running web endpoint.
Dast,
/// Run an active penetration test against a running target.
Pentest,
}
/// How a runner executes a job — the CI-runner-style classification. A runner
/// advertises exactly one; a job requires one.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum Executor {
/// A subprocess on the runner host (dev / trusted single-node).
Shell,
/// One or more containers on the runner's Docker (default; QEMU runs here).
Docker,
/// A Pod/Job in a Kubernetes cluster (scale-out / multi-tenant).
K8s,
}
/// Lifecycle state of a job in the queue.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum JobStatus {
/// Waiting to be leased.
Queued,
/// Leased by a runner but not yet started.
Leased,
/// Executing on a runner.
Running,
/// Completed successfully.
Succeeded,
/// Completed with an error.
Failed,
/// The lease/lifetime deadline elapsed before completion.
Expired,
/// Cancelled by the control plane.
Cancelled,
}
impl JobStatus {
/// Whether the job has reached a terminal state (no further transitions).
pub fn is_terminal(self) -> bool {
matches!(
self,
JobStatus::Succeeded | JobStatus::Failed | JobStatus::Expired | JobStatus::Cancelled
)
}
}
/// A reference to an input artifact. Resolved by the runner from a source it can
/// reach; the blob itself never flows through the control plane (so an on-prem
/// runner keeps customer data local). Exactly one of `blob`/`url` should be set.
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct InputRef {
/// Content-addressed blob (e.g. `sha256:…`) the runner fetches from its store.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub blob: Option<String>,
/// A URL the runner can reach (git repo, internal artifact store, …).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub url: Option<String>,
}
impl InputRef {
/// A content-addressed blob reference.
pub fn blob(id: impl Into<String>) -> Self {
Self {
blob: Some(id.into()),
url: None,
}
}
}
/// Sandbox runtime knobs. Fields are executor/job-type specific and all optional;
/// `extra` carries anything not modelled explicitly.
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct JobRuntime {
/// Container image (Docker executor).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub image: Option<String>,
/// Memory cap (e.g. `512m`).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub memory: Option<String>,
/// CPU cap (e.g. `0.5`).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub cpus: Option<String>,
/// Network to join (e.g. `isolated`).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub network: Option<String>,
/// QEMU machine type (qemu-boot).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub machine: Option<String>,
/// QEMU target architecture (qemu-boot).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub arch: Option<String>,
/// Executor-specific extras not modelled above.
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub extra: BTreeMap<String, String>,
}
/// DAST collection settings for jobs that scan a web endpoint.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct DastCollect {
/// Maximum crawl depth (kept shallow for ephemeral instances).
pub max_crawl_depth: u32,
}
/// What to collect from a run.
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct JobCollect {
/// Run the industrial-protocol probe (Modbus/OPC-UA/EtherNet-IP).
#[serde(default)]
pub ics_probe: bool,
/// Run DAST against the provisioned/booted web endpoint.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub dast: Option<DastCollect>,
/// Run an active pentest.
#[serde(default)]
pub pentest: bool,
/// Collect an SBOM.
#[serde(default)]
pub sbom: bool,
}
/// A declarative dynamic-execution job the control plane enqueues and a Werkbank
/// runner leases and executes.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct Job {
/// Unique job id (assigned by the control plane on enqueue).
pub id: String,
/// What kind of job this is.
#[serde(rename = "type")]
pub job_type: JobType,
/// Owning tenant.
pub tenant: String,
/// The onboarded target this job tests.
pub target_id: String,
/// The executor a runner must provide to run this job.
pub executor: Executor,
/// Runner capabilities this job requires (e.g. `arch=amd64`, `kvm=true`).
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub labels: Vec<String>,
/// Hard lifetime deadline for the whole job.
pub timeout_secs: u64,
/// Named input artifacts (e.g. `program`, `firmware`), by reference.
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub inputs: BTreeMap<String, InputRef>,
/// Sandbox runtime knobs.
#[serde(default)]
pub runtime: JobRuntime,
/// What to collect from the run.
#[serde(default)]
pub collect: JobCollect,
}
impl Job {
/// A `plc-provision` job: instantiate the control logic named `program` on an
/// ephemeral soft-PLC (Docker executor) and collect the ICS probe + DAST.
pub fn plc_provision(
id: impl Into<String>,
tenant: impl Into<String>,
target_id: impl Into<String>,
program: InputRef,
timeout_secs: u64,
) -> Self {
let mut inputs = BTreeMap::new();
inputs.insert("program".to_string(), program);
Self {
id: id.into(),
job_type: JobType::PlcProvision,
tenant: tenant.into(),
target_id: target_id.into(),
executor: Executor::Docker,
labels: Vec::new(),
timeout_secs,
inputs,
runtime: JobRuntime::default(),
collect: JobCollect {
ics_probe: true,
dast: Some(DastCollect { max_crawl_depth: 2 }),
pentest: false,
sbom: false,
},
}
}
}
/// The outcome of running a job, posted back to the control plane. Findings and
/// SBOM reuse the shared scanner types, so the control plane persists them
/// unchanged. Submission is idempotent — keyed by [`JobResult::job_id`].
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct JobResult {
/// The job this result is for.
pub job_id: String,
/// Terminal status of the job.
pub status: Option<JobStatus>,
/// General scanner findings (e.g. ICS-probe findings).
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub findings: Vec<Finding>,
/// DAST findings from a web-endpoint scan.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub dast_findings: Vec<DastFinding>,
/// SBOM components collected from the run.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub sbom: Vec<SbomEntry>,
/// Error message when the job failed.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub error: Option<String>,
/// Captured execution log (truncated by the runner).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub logs: Option<String>,
/// When execution started on the runner.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub started_at: Option<DateTime<Utc>>,
/// When execution finished.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub finished_at: Option<DateTime<Utc>>,
}
impl JobResult {
/// A successful result for a job.
pub fn succeeded(job_id: impl Into<String>) -> Self {
Self {
job_id: job_id.into(),
status: Some(JobStatus::Succeeded),
..Default::default()
}
}
/// A failed result carrying an error message.
pub fn failed(job_id: impl Into<String>, error: impl Into<String>) -> Self {
Self {
job_id: job_id.into(),
status: Some(JobStatus::Failed),
error: Some(error.into()),
..Default::default()
}
}
}
/// 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 {
use super::*;
#[test]
fn job_round_trips_through_json() {
let job = Job::plc_provision("job_1", "acme", "64f0aa", InputRef::blob("sha256:abc"), 180);
let json = serde_json::to_string(&job).expect("serialize");
let back: Job = serde_json::from_str(&json).expect("deserialize");
assert_eq!(job, back);
// Enum wire forms are the kebab/lowercase the contract documents.
assert!(json.contains("\"type\":\"plc-provision\""));
assert!(json.contains("\"executor\":\"docker\""));
}
#[test]
fn parses_the_design_doc_plc_provision_toml() {
// The exact shape from docs/DESIGN.md §5 (wrapped in a [job] table).
#[derive(Deserialize)]
struct JobFile {
job: Job,
}
let src = r#"
[job]
id = "job_01H"
type = "plc-provision"
tenant = "acme"
target_id = "64f0"
executor = "docker"
labels = ["arch=amd64"]
timeout_secs = 180
[job.inputs]
program = { blob = "sha256:deadbeef" }
[job.runtime]
image = "openplc:latest"
memory = "512m"
cpus = "0.5"
network = "isolated"
[job.collect]
ics_probe = true
dast = { max_crawl_depth = 2 }
"#;
let file: JobFile = toml::from_str(src).expect("parse job toml");
let job = file.job;
assert_eq!(job.job_type, JobType::PlcProvision);
assert_eq!(job.executor, Executor::Docker);
assert_eq!(job.labels, vec!["arch=amd64".to_string()]);
assert_eq!(
job.inputs.get("program").and_then(|i| i.blob.as_deref()),
Some("sha256:deadbeef")
);
assert_eq!(job.runtime.image.as_deref(), Some("openplc:latest"));
assert!(job.collect.ics_probe);
assert_eq!(job.collect.dast.map(|d| d.max_crawl_depth), Some(2));
}
#[test]
fn qemu_boot_runtime_fields_parse() {
#[derive(Deserialize)]
struct JobFile {
job: Job,
}
let src = r#"
[job]
id = "j2"
type = "qemu-boot"
tenant = "acme"
target_id = "t"
executor = "docker"
labels = ["kvm=true"]
timeout_secs = 600
[job.inputs]
firmware = { blob = "sha256:cafe" }
[job.runtime]
machine = "virt"
arch = "arm"
memory = "1g"
"#;
let file: JobFile = toml::from_str(src).expect("parse");
assert_eq!(file.job.job_type, JobType::QemuBoot);
assert_eq!(file.job.runtime.arch.as_deref(), Some("arm"));
assert_eq!(
file.job
.inputs
.get("firmware")
.and_then(|i| i.blob.as_deref()),
Some("sha256:cafe")
);
}
#[test]
fn status_terminality() {
assert!(JobStatus::Succeeded.is_terminal());
assert!(JobStatus::Expired.is_terminal());
assert!(!JobStatus::Queued.is_terminal());
assert!(!JobStatus::Running.is_terminal());
}
#[test]
fn result_constructors() {
assert_eq!(JobResult::succeeded("j").status, Some(JobStatus::Succeeded));
let f = JobResult::failed("j", "boom");
assert_eq!(f.status, Some(JobStatus::Failed));
assert_eq!(f.error.as_deref(), Some("boom"));
}
}
+70 -6
View File
@@ -14,8 +14,12 @@ use crate::models::{ArtifactKind, OnboardedTarget, ScanType, TargetType};
pub enum ArtifactRequirement {
/// Source code — a git repo or a source archive.
Code,
/// A reachable running instance (live URL / endpoint).
/// A reachable running instance (any live URL / endpoint, scheme-agnostic —
/// e.g. the ICS probe works off the host:port of a modbus:// or http:// ref).
RunningUrl,
/// A reachable **web** endpoint — a live URL with an http(s) scheme. DAST is
/// an HTTP crawler, so a modbus:// / opc.tcp:// endpoint does not satisfy it.
HttpUrl,
/// A firmware image / binary blob.
Firmware,
/// A PLC project (PLCopen XML or Structured Text).
@@ -134,7 +138,7 @@ fn sast_umbrella() -> Vec<ScanRule> {
/// The rule set for a target type. Scans that are never applicable to a type are
/// simply absent (e.g. DAST is not listed for a PLC target).
pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
use ArtifactRequirement::{Firmware, Mobile, Plc, RunningUrl};
use ArtifactRequirement::{Firmware, HttpUrl, Mobile, Plc, RunningUrl};
match target_type {
TargetType::WebApp | TargetType::BackendService => {
let mut r = sast_umbrella();
@@ -142,7 +146,7 @@ pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
ScanType::Dast,
true,
"Dynamic scan of the running endpoint",
RunningUrl,
HttpUrl,
));
r
}
@@ -203,7 +207,7 @@ pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
ScanType::Dast,
false,
"Dynamic scan of exposed network services (if any)",
RunningUrl,
HttpUrl,
));
r
}
@@ -249,7 +253,7 @@ pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
ScanType::Dast,
false,
"Dynamic scan of the running device (WebVisu / exposed services)",
RunningUrl,
HttpUrl,
),
ScanRule::new(
ScanType::IcsProbe,
@@ -285,7 +289,9 @@ pub fn supports_pentest(target_type: TargetType) -> bool {
fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
match req {
ArtifactRequirement::Code => Some(ArtifactKind::GitRepo),
ArtifactRequirement::RunningUrl => Some(ArtifactKind::LiveUrl),
ArtifactRequirement::RunningUrl | ArtifactRequirement::HttpUrl => {
Some(ArtifactKind::LiveUrl)
}
ArtifactRequirement::Firmware => Some(ArtifactKind::FirmwareImage),
ArtifactRequirement::Plc => Some(ArtifactKind::PlcProject),
ArtifactRequirement::Mobile => Some(ArtifactKind::MobilePackage),
@@ -294,11 +300,22 @@ fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
}
}
/// Whether a live-URL reference is an http(s) web endpoint (vs. an industrial
/// endpoint like `modbus://` / `opc.tcp://`, which DAST cannot crawl).
fn is_http_url(source_ref: &str) -> bool {
let s = source_ref.trim();
s.starts_with("http://") || s.starts_with("https://")
}
/// Whether the target carries an artifact that satisfies the requirement.
fn requirement_satisfied(req: ArtifactRequirement, target: &OnboardedTarget) -> bool {
match req {
ArtifactRequirement::Code => target.code_artifact().is_some(),
ArtifactRequirement::RunningUrl => target.has(ArtifactKind::LiveUrl),
ArtifactRequirement::HttpUrl => target
.artifacts
.iter()
.any(|a| a.kind == ArtifactKind::LiveUrl && is_http_url(&a.source_ref)),
ArtifactRequirement::Firmware => target.has(ArtifactKind::FirmwareImage),
// A PLC project artifact, or a code artifact (git repo / source archive)
// holding the control logic as PLCopen XML / ST exports — the common way
@@ -322,6 +339,10 @@ pub fn applicable_scans(target: &OnboardedTarget) -> Vec<ScanOption> {
let required_artifact = representative_kind(rule.requires);
let blocked_reason = if satisfied {
None
} else if rule.requires == ArtifactRequirement::HttpUrl {
// A live URL may be present but non-HTTP (e.g. modbus://): be
// specific so the user knows DAST needs a web endpoint.
Some("no http(s) live URL — DAST needs a web endpoint".to_string())
} else {
Some(match required_artifact {
Some(kind) => format!("no {kind} artifact provided"),
@@ -462,6 +483,49 @@ mod tests {
.is_none());
}
#[test]
fn plc_with_modbus_url_offers_ics_probe_but_blocks_dast() {
// A soft-PLC reachable only over Modbus/TCP (no WebVisu). The ICS probe
// is applicable (it works off host:port), but DAST — an HTTP crawler —
// must be blocked so it isn't offered/run against a non-web endpoint.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::live_url("modbus://plc-sim:502")],
);
let opts = applicable_scans(&t);
let ics = option(&opts, ScanType::IcsProbe).expect("ics probe offered");
assert!(
ics.blocked_reason.is_none(),
"ICS probe should be unblocked for a modbus:// endpoint"
);
assert!(!ics.default_on, "ICS probe stays opt-in (default-off)");
let dast = option(&opts, ScanType::Dast).expect("dast listed");
assert!(
dast.blocked_reason.is_some(),
"DAST must be blocked without an http(s) endpoint"
);
assert!(!dast.default_on);
}
#[test]
fn plc_with_http_webvisu_offers_both_dast_and_ics_probe() {
// A PLC exposing a WebVisu over HTTP: both DAST (web) and the ICS probe
// (OT ports on the same host) are applicable.
let t = target_with(
TargetType::PlcSps,
vec![Artifact::live_url("http://plc.local/webvisu")],
);
let opts = applicable_scans(&t);
assert!(option(&opts, ScanType::Dast)
.expect("dast offered")
.blocked_reason
.is_none());
assert!(option(&opts, ScanType::IcsProbe)
.expect("ics probe offered")
.blocked_reason
.is_none());
}
#[test]
fn pentest_support_matches_reachable_families() {
assert!(supports_pentest(TargetType::WebApp));
File diff suppressed because it is too large Load Diff
+1
View File
@@ -44,6 +44,7 @@ export default withMermaid(defineConfig({
items: [
{ text: 'Glossary', link: '/reference/glossary' },
{ text: 'Tools & Scanners', link: '/reference/tools' },
{ text: 'PLC Runtime Landscape', link: '/reference/plc-runtimes' },
],
},
],
+66
View File
@@ -11,6 +11,72 @@ the control application *and* the device it runs on.
| A device firmware image | Firmware SBOM / CVE (opt-in) |
| A reachable endpoint (WebVisu, OPC UA) | DAST / pentest (opt-in) |
## Anatomy: a soft PLC is a SoC + Linux + runtime
A CODESYS controller is **not** a monolithic appliance like a classic Siemens
S7. It is **PC-based ("soft") control** — commodity silicon running a
general-purpose Linux, with a **software PLC runtime** as just another process:
| Classic PLC (e.g. Siemens S7) | Soft PLC (CODESYS-on-Yocto, OpenPLC-on-Raspbian) |
| --- | --- |
| Proprietary hardware + firmware | Commodity SoC (x86 / ARM) |
| Proprietary OS | General-purpose Linux (a **Yocto** image, or Raspbian) |
| Proprietary runtime | Software runtime (**CODESYS Control**, or OpenPLC) |
| STEP7 / TIA project | IEC 61131-3 control app (ST / LD / FBD / SFC) |
Because of this, the device is built along **two independent tracks**, by
different people, on different timelines, and shipped separately. It also
inherits the **entire Linux / IT attack surface on top of** the OT / control
one — which is exactly why a PLC/SPS target is treated as a **composite**:
Certifai ingests one artifact per layer and scans each with the right pipeline.
```mermaid
flowchart TB
subgraph TA["Track A · Device platform — built by the hardware OEM / vendor"]
direction LR
A1["Yocto / OpenEmbedded<br/>BSP + RT kernel"] --> A2["Bake in the CODESYS<br/>Control for Linux runtime"] --> A3["bitbake → device image<br/>.wic / .tar + manifest"]
end
subgraph TB2["Track B · Control application — built by the machine builder / customer"]
direction LR
B1["CODESYS IDE<br/>ST / LD / FBD / SFC + WebVisu"] --> B2["Reference CODESYS +<br/>vendor libraries"] --> B3["Compile → download<br/>to device (gateway 11740)"]
end
A3 --> DEV(["Running soft-PLC device<br/>SoC + Linux + runtime + control app<br/>Modbus · OPC UA · EtherNet/IP · WebVisu"])
B3 --> DEV
subgraph CERT["What Certifai scans — one layer per artifact"]
direction LR
S1["Firmware layer<br/>FirmwareStatic · SBOM · CVE"]
S2["Control-logic layer<br/>PLC SAST — ST + FBD/LD"]
S3["Control-app SBOM<br/>libraries + runtime → CVE"]
S4["Running layer<br/>ICS probe · DAST (WebVisu)"]
end
A3 -. firmware image .-> S1
B1 -. PLCopen XML / ST via git .-> S2
B2 -. projectarchive (zip) .-> S3
DEV -. live URL / provisioned .-> S4
classDef yocto fill:#fde68a,stroke:#b45309,color:#111
classDef codesys fill:#bfdbfe,stroke:#1d4ed8,color:#111
classDef dev fill:#e9d5ff,stroke:#7e22ce,color:#111
classDef cert fill:#bbf7d0,stroke:#15803d,color:#111
class A1,A2,A3 yocto
class B1,B2,B3 codesys
class DEV dev
class S1,S2,S3,S4 cert
```
::: tip Where Yocto fits
Yocto is **Track A** — the *build system* for the device platform. It produces
the Linux image and bakes in the CODESYS runtime, so it is the **firmware
layer**, entirely separate from the control application. Hand it to Certifai as
its own **firmware image** artifact (scanned by the firmware pipeline, not the
PLC pipeline). The device OS need not be Yocto — Raspbian/Debian/Buildroot, or
even an RTOS / bare-metal, are all possible — but Yocto is the common,
product-grade industrial choice.
:::
## Two ways to deliver the project
You can either **upload** the project when onboarding, or point Certifai at a
+97
View File
@@ -0,0 +1,97 @@
# PLC Runtime Landscape & Support
A soft PLC is a **SoC + Linux + a software runtime + an IEC 61131-3 control app**
(see [PLC / SPS Projects](/guide/plc)).
The **runtime** is what defines the device — it provides the IEC engine, the
Modbus / OPC UA / EtherNet/IP servers, and the WebVisu. This page tracks the
runtime ecosystems Certifai may encounter.
We do **not** aim to support every runtime up front. Certifai supports the
**CODESYS family** today; everything else is a **watch-list** — when a customer
shows up using one, we add the parser/support for it then. The dynamic OT probe
(Modbus / OPC UA / EtherNet/IP) is **vendor-agnostic** and works regardless of
the runtime.
## Support status
| Status | Meaning |
| --- | --- |
| ✅ **Supported** | Static analysis works today (control-logic SAST + library/runtime SBOM + CVE). |
| 🟡 **Covered via CODESYS** | A rebranded CODESYS runtime — our CODESYS parsing applies (may need minor per-vendor tweaks). |
| 🔭 **Watch-list** | Own project format — we add a format parser when a customer needs it. The dynamic OT probe already applies. |
| 🧪 **Test-bench** | A free runtime we use to *reconstruct and dynamically test* a device (see epic: provision-and-test). |
## 1. CODESYS and rebranded CODESYS (the largest slice)
Much of the market licenses the CODESYS runtime and rebrands the IDE. If a
customer "doesn't use CODESYS", they often do — under another name.
| Product / vendor | Based on | Status |
| --- | --- | --- |
| **CODESYS** (3S-Smart Software Solutions) | CODESYS | ✅ Supported |
| Schneider **EcoStruxure Machine Expert** (ex-SoMachine) | CODESYS | 🟡 Covered via CODESYS |
| **WAGO** e!COCKPIT / PFC controllers | CODESYS | 🟡 Covered via CODESYS |
| **ABB** AC500 / Automation Builder | CODESYS | 🟡 Covered via CODESYS |
| **Bosch Rexroth** ctrlX / IndraLogic | CODESYS | 🟡 Covered via CODESYS |
| **Eaton** XSoft-CODESYS, **KEBA** KeStudio, Berghof, Kontron, Festo (CPX-E), IFM, Turck, … | CODESYS | 🟡 Covered via CODESYS |
## 2. Other embeddable IEC 61131-3 runtime toolkits
Same model as CODESYS (an OEM licenses a runtime + IDE and bakes it into a
device), but with **different project formats and libraries**.
| Toolkit | Vendor | Status |
| --- | --- | --- |
| **ProConOS / MULTIPROG** | Phoenix Contact / KW-Software | 🔭 Watch-list |
| **ISaGRAF** (also does IEC 61499) | Rockwell | 🔭 Watch-list |
| **straton** | COPA-DATA | 🔭 Watch-list |
| **logi.CAD** | logi.cals | 🔭 Watch-list |
## 3. Fully proprietary ecosystems (own runtime + IDE + protocols)
Static analysis here needs a **per-vendor project parser**; the **dynamic OT
probe still works** (they speak Modbus / OPC UA / EtherNet/IP, plus vendor
protocols like S7comm / CIP).
| Ecosystem | Vendor | Notes | Status |
| --- | --- | --- | --- |
| **TIA Portal / STEP 7** (S7-1200/1500), S7-1500 **Software Controller**, **Virtual PLC** | Siemens | Largest install base; the soft/virtual variants are Linux/container | 🔭 Watch-list |
| **Studio 5000** (ControlLogix / CompactLogix) | Rockwell / Allen-Bradley | Strong in North America | 🔭 Watch-list |
| **TwinCAT 3** | Beckhoff | Genuine PC-based control on Windows / TwinCAT-BSD; IEC 61131-3 **+ C++ + Simulink** | 🔭 Watch-list |
| **Automation Studio** | B&R (ABB) | Own Automation Runtime | 🔭 Watch-list |
| **GX Works** (MELSEC) | Mitsubishi | | 🔭 Watch-list |
| **Sysmac Studio** (NX / NJ) | Omron | | 🔭 Watch-list |
| **Proficy Machine Edition** (PACSystems) | Emerson / GE | | 🔭 Watch-list |
## 4. Linux-native / containerized soft-PLC (the direction of travel)
| Product | Vendor | Notes | Status |
| --- | --- | --- | --- |
| **PLCnext** | Phoenix Contact | Open, Linux-based; native runtime is eCLR (not CODESYS), but can also run CODESYS as an app | 🔭 Watch-list |
| **ctrlX** | Bosch Rexroth | Ubuntu-core, app-store model (CODESYS runtime inside) | 🟡 Covered via CODESYS |
| **Virtual PLC** / **CODESYS Virtual Control** | Siemens / CODESYS | Containerized PLCs (Docker / K8s) | 🟡 / 🔭 |
## 5. Open-source runtimes (free — our test-bench substrates)
Used to **reconstruct and dynamically test** a customer device without touching
their network (provision-and-test).
| Runtime | Standard | Notes | Status |
| --- | --- | --- | --- |
| **OpenPLC** | IEC 61131-3 | Modbus-centric, education/small automation; uses MatIEC | 🧪 Test-bench (current) |
| **Beremiz + MatIEC** | IEC 61131-3 | Fuller open-source IDE; compiles ST/IL → C. Natural fidelity step-up from OpenPLC | 🧪 Test-bench (candidate) |
| **Eclipse 4diac (FORTE)** | IEC **61499** | Distributed, event-driven — a *different paradigm* from 61131-3's scan cycle | 🔭 Watch-list |
| **ProView** | — | Open-source process control + SCADA | 🔭 Watch-list |
## How we add support for a new runtime
- **Static (SAST / SBOM):** needs a parser for that runtime's **project format**
(and its library/package convention). This is the per-vendor work.
- **Dynamic (ICS probe / DAST):** already **vendor-agnostic** — it targets the
device's OT ports and WebVisu, not the runtime's file format. So a brand-new
ecosystem still gets dynamic coverage on day one.
::: tip Rule of thumb
Confirm whether a "non-CODESYS" controller is actually a **rebranded CODESYS**
runtime (Section 1) before assuming new work — most of the long tail is.
:::
+23
View File
@@ -0,0 +1,23 @@
[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
@@ -0,0 +1,16 @@
//! 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
@@ -0,0 +1,32 @@
//! 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"])
);
}
}
@@ -14,7 +14,7 @@ use std::time::Duration;
use compliance_core::models::{Finding, ScanType, Severity};
use crate::pipeline::dedup;
use crate::fingerprint as dedup;
/// Well-known deep-probe ports (each independent of any WebVisu HTTP port).
const MODBUS_PORT: u16 = 502;
@@ -103,6 +103,39 @@ async fn modbus_findings(host: &str, port: u16, repo_id: &str, budget: Duration)
);
findings.push(f);
}
// Exposed process points: coils / holding registers that a read enumerated
// and that, over unauthenticated Modbus/TCP, are also writable. This is the
// concrete attack surface behind the exposure — the live variables an
// attacker can overwrite. (Read-only to detect: we never write.)
let coils = probe.coils_readable.unwrap_or(0);
let registers = probe.holding_registers_readable.unwrap_or(0);
if coils > 0 || registers > 0 {
let fp = dedup::compute_fingerprint(&[repo_id, "ics-modbus-exposed-points", &target]);
let mut f = Finding::new(
repo_id.to_string(),
fp,
"ics-probe".to_string(),
ScanType::IcsProbe,
"Writable process points exposed over unauthenticated Modbus/TCP".to_string(),
format!(
"Reading the device at {target} enumerated {coils} coil(s) and {registers} \
holding register(s). Coils and holding registers are read/write process points \
in Modbus, so any host that can reach this port can not only read but overwrite \
live process state (force coils, change setpoints) without authentication."
),
Severity::High,
);
f.rule_id = Some("ics-modbus-exposed-points".to_string());
f.cwe = Some("CWE-306".to_string());
f.remediation = Some(
"Segment the Modbus/TCP port to a trusted control network; where the device \
supports it use Modbus/TLS or an authenticating protocol gateway; restrict which \
function codes and register ranges are reachable from outside the control zone."
.to_string(),
);
findings.push(f);
}
findings
}
@@ -21,6 +21,13 @@ pub struct ModbusProbe {
pub speaks_modbus: bool,
/// Device identity, if disclosed via Read Device Identification (FC 43 / 14).
pub device: Option<DeviceId>,
/// Coils returned by a Read Coils of the first block, if that address range
/// exists. Coils are read/write process bits, so an exposed block is an
/// unauthenticated write surface on the live process.
pub coils_readable: Option<u16>,
/// Holding registers returned by a Read Holding Registers of the first block,
/// if that range exists. Holding registers are read/write process words.
pub holding_registers_readable: Option<u16>,
}
/// Vendor / product / revision from Read Device Identification.
@@ -31,8 +38,13 @@ pub struct DeviceId {
pub revision: Option<String>,
}
/// Probe a Modbus/TCP endpoint. Read-only: issues a Read Holding Registers and a
/// Read Device Identification request; never writes to the device.
/// How many coils / holding registers to request when enumerating the exposed
/// process surface. Read-only: a normal reply means the block exists and is,
/// over unauthenticated Modbus/TCP, also writable.
const ENUM_QTY: u16 = 16;
/// Probe a Modbus/TCP endpoint. Read-only: issues Read Holding Registers, Read
/// Coils, and Read Device Identification requests; never writes to the device.
pub async fn probe(host: &str, port: u16, budget: Duration) -> ModbusProbe {
let mut out = ModbusProbe::default();
let Ok(Ok(mut stream)) = timeout(budget, TcpStream::connect((host, port))).await else {
@@ -40,13 +52,28 @@ pub async fn probe(host: &str, port: u16, budget: Duration) -> ModbusProbe {
};
out.reachable = true;
// Read Holding Registers (FC 0x03), unit 1, addr 0, qty 1 — a benign read.
let rhr = [0x03u8, 0x00, 0x00, 0x00, 0x01];
// Read Holding Registers (FC 0x03), unit 1, addr 0 — a benign read that also
// enumerates the exposed register block.
let rhr = [0x03u8, 0x00, 0x00, (ENUM_QTY >> 8) as u8, ENUM_QTY as u8];
if let Some(resp) = txn(&mut stream, 1, &rhr, budget).await {
// A normal reply (0x03) or an exception (0x83) both prove it speaks Modbus.
if matches!(resp.first(), Some(0x03) | Some(0x83)) {
out.speaks_modbus = true;
}
if resp.first() == Some(&0x03) {
out.holding_registers_readable = Some(register_count_from_reply(&resp));
}
}
// Read Coils (FC 0x01), addr 0 — enumerates the exposed coil (bit) block.
let rc = [0x01u8, 0x00, 0x00, (ENUM_QTY >> 8) as u8, ENUM_QTY as u8];
if let Some(resp) = txn(&mut stream, 1, &rc, budget).await {
if matches!(resp.first(), Some(0x01) | Some(0x81)) {
out.speaks_modbus = true;
}
if resp.first() == Some(&0x01) {
out.coils_readable = Some(coil_count_from_reply(&resp));
}
}
// Read Device Identification (FC 0x2B / MEI 0x0E), basic (0x01), object 0.
@@ -60,6 +87,17 @@ pub async fn probe(host: &str, port: u16, budget: Duration) -> ModbusProbe {
out
}
/// Coils reported by a Read Coils reply `[0x01, byte_count, data…]` (8 per byte).
fn coil_count_from_reply(pdu: &[u8]) -> u16 {
pdu.get(1).map(|&b| u16::from(b) * 8).unwrap_or(0)
}
/// Registers reported by a Read Holding Registers reply `[0x03, byte_count,
/// data…]` (2 bytes per register).
fn register_count_from_reply(pdu: &[u8]) -> u16 {
pdu.get(1).map(|&b| u16::from(b) / 2).unwrap_or(0)
}
/// Send one Modbus PDU and return the response PDU (function code + data), or
/// `None` on timeout / malformed reply.
async fn txn(stream: &mut TcpStream, unit: u8, pdu: &[u8], budget: Duration) -> Option<Vec<u8>> {
@@ -154,7 +192,8 @@ mod tests {
break;
}
let reply_pdu: Vec<u8> = match pdu.first() {
Some(0x03) => vec![0x03, 0x02, 0x00, 0x00], // 1 register = 0
Some(0x03) => vec![0x03, 0x02, 0x00, 0x00], // 1 register (byte_count 2)
Some(0x01) => vec![0x01, 0x02, 0xFF, 0xFF], // 16 coils (byte_count 2)
Some(0x2B) if with_device => vec![
0x2B, 0x0E, 0x01, 0x81, 0x00, 0x00, 0x02, // 2 objects
0x00, 0x04, b'A', b'C', b'M', b'E', // vendor
@@ -185,6 +224,24 @@ mod tests {
assert_eq!(dev.product.as_deref(), Some("PLC"));
}
#[tokio::test]
async fn probe_enumerates_exposed_process_points() {
let addr = mock_server(false).await;
let p = probe(&addr.ip().to_string(), addr.port(), Duration::from_secs(2)).await;
assert!(p.speaks_modbus);
// The mock returns a 2-byte holding-register block (1 register) and a
// 2-byte coil block (16 coils).
assert_eq!(p.holding_registers_readable, Some(1));
assert_eq!(p.coils_readable, Some(16));
}
#[test]
fn reply_counts_decode_byte_counts() {
assert_eq!(register_count_from_reply(&[0x03, 0x08]), 4); // 8 bytes → 4 regs
assert_eq!(coil_count_from_reply(&[0x01, 0x03]), 24); // 3 bytes → 24 coils
assert_eq!(register_count_from_reply(&[0x03]), 0); // malformed → 0
}
#[tokio::test]
async fn probe_reports_unreachable_for_a_closed_port() {
// 127.0.0.1:1 is (almost certainly) closed.
+18
View File
@@ -0,0 +1,18 @@
//! 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;
+422
View File
@@ -0,0 +1,422 @@
//! Dynamic PLC testing via an ephemeral soft-PLC (#183).
//!
//! When a PLC/SPS target ships control logic but no reachable live device, the
//! agent instantiates that logic itself instead of trying to reach the customer's
//! OT network: it provisions a throwaway soft-PLC (OpenPLC) container in-cluster,
//! loads the program, starts the runtime, probes it over industrial protocols,
//! then tears the instance down. No customer network access, sandboxed, and
//! reproducible — destructive tests become safe because the target is ours.
//!
//! - [`provision`] owns the container lifecycle (sub-task 1 + 5).
//! - [`openplc`] loads the program into the running instance (sub-task 2).
//! - [`provision_and_test`] composes them with a hard deadline and guaranteed
//! teardown, and runs the ICS probe against the provisioned endpoint.
pub mod openplc;
pub mod provision;
use std::path::Path;
use std::time::Duration;
use secrecy::ExposeSecret;
use compliance_core::models::dast::{DastFinding, DastScanRun, DastTarget, DastTargetType};
use compliance_core::models::Finding;
use compliance_core::PlcRuntimeConfig;
use crate::error::ExecError;
pub use provision::{DockerSoftPlc, ProvisionedRuntime, SoftPlc};
/// The result of a DAST scan against a provisioned web endpoint.
#[derive(Debug)]
pub struct DastRunResult {
/// The scan-run record (linked to the onboarded target).
pub scan_run: DastScanRun,
/// The DAST findings.
pub findings: Vec<DastFinding>,
}
/// Everything a provision-and-test run produced: the ICS-probe findings plus, if
/// it ran, the DAST scan of the provisioned web endpoint. The caller persists
/// both — keeping this a plain data return means the whole run is portable to a
/// remote execution backend that just hands the results back.
#[derive(Debug, Default)]
pub struct ProvisionOutcome {
/// ICS-probe findings from the provisioned Modbus endpoint.
pub findings: Vec<Finding>,
/// DAST scan of the provisioned web endpoint, if it ran.
pub dast: Option<DastRunResult>,
}
/// A control-logic program ready to load into a soft-PLC: the source text plus a
/// cosmetic file name (OpenPLC re-stores it under its own name).
#[derive(Debug, Clone)]
pub struct PlcProgram {
/// The original file name (for the upload form; OpenPLC renames on storage).
pub file_name: String,
/// The program source — Structured Text or PLCopen XML.
pub source: String,
}
/// 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> {
reqwest::Client::builder()
.cookie_store(true)
.timeout(Duration::from_secs(30))
.build()
.map_err(ExecError::Http)
}
/// Pick the control-logic program to run from an ingested PLC source tree.
///
/// OpenPLC runs one program, so we choose the best single candidate: a complete
/// Structured Text program (one carrying a `CONFIGURATION` block) is ideal;
/// failing that the largest ST file; failing that a PLCopen XML export. Returns
/// `None` when the tree holds no loadable control logic.
pub fn extract_program(root: &Path) -> Option<PlcProgram> {
let mut st: Vec<(String, String)> = Vec::new();
let mut xml: Vec<(String, String)> = Vec::new();
for entry in walkdir::WalkDir::new(root)
.into_iter()
.filter_map(Result::ok)
{
if !entry.file_type().is_file() {
continue;
}
let path = entry.path();
let ext = path
.extension()
.and_then(|e| e.to_str())
.unwrap_or("")
.to_ascii_lowercase();
let is_st = matches!(ext.as_str(), "st" | "iecst" | "scl" | "exp" | "il");
let is_xml = matches!(ext.as_str(), "xml" | "plcopen" | "project");
if !is_st && !is_xml {
continue;
}
let Ok(content) = std::fs::read_to_string(path) else {
continue;
};
let name = path
.file_name()
.and_then(|n| n.to_str())
.unwrap_or("program")
.to_string();
if is_st {
st.push((name, content));
} else if looks_like_plcopen(&content) {
xml.push((name, content));
}
}
if let Some((name, source)) = st.iter().find(|(_, c)| has_configuration(c)) {
return Some(PlcProgram {
file_name: name.clone(),
source: source.clone(),
});
}
if let Some((name, source)) = st.iter().max_by_key(|(_, c)| c.len()) {
return Some(PlcProgram {
file_name: name.clone(),
source: source.clone(),
});
}
xml.into_iter()
.max_by_key(|(_, c)| c.len())
.map(|(file_name, source)| PlcProgram { file_name, source })
}
/// Whether an ST source is a complete, runnable program (has a `CONFIGURATION`).
fn has_configuration(source: &str) -> bool {
source.to_ascii_uppercase().contains("CONFIGURATION")
}
/// Whether an XML file looks like a PLCopen project export.
fn looks_like_plcopen(source: &str) -> bool {
let lower = source.to_ascii_lowercase();
lower.contains("<project") || lower.contains("plcopen")
}
/// Provision an ephemeral soft-PLC, load `program`, start it, probe it over
/// industrial protocols, and tear it down. Returns the ICS-probe findings.
///
/// Teardown is guaranteed: the load/probe work runs under a hard deadline
/// (`max_lifetime_secs`) and the instance is removed afterwards on every path —
/// success, error, or deadline expiry.
pub async fn provision_and_test<P: SoftPlc>(
provisioner: &P,
http: &reqwest::Client,
cfg: &PlcRuntimeConfig,
program: &PlcProgram,
target_id: &str,
) -> Result<ProvisionOutcome, ExecError> {
let handle = provisioner.provision(target_id).await?;
tracing::info!(
target_id,
instance = %handle.name,
modbus = %handle.modbus_endpoint,
"provisioned ephemeral soft-PLC"
);
let deadline = Duration::from_secs(cfg.max_lifetime_secs);
let result = tokio::time::timeout(
deadline,
run_dynamic_test(http, cfg, program, target_id, &handle),
)
.await;
// Guaranteed teardown — runs on success, error, and deadline expiry. The
// inner future is panic-free (the workspace lint bans unwrap/expect), so no
// unwind can skip this; a container leaked by an agent *crash* is swept by
// the next run's stale reaper.
provisioner.teardown(&handle).await;
match result {
Ok(inner) => inner,
Err(_) => {
tracing::warn!(
target_id,
instance = %handle.name,
"provision-and-test hit the lifetime deadline; torn down"
);
Ok(ProvisionOutcome::default())
}
}
}
/// The load → start → probe → DAST body, run under the caller's deadline.
async fn run_dynamic_test(
http: &reqwest::Client,
cfg: &PlcRuntimeConfig,
program: &PlcProgram,
target_id: &str,
handle: &ProvisionedRuntime,
) -> Result<ProvisionOutcome, ExecError> {
let ready_budget = Duration::from_secs((cfg.max_lifetime_secs / 3).clamp(10, 60));
openplc::wait_ready(http, &handle.webvisu_url, ready_budget).await?;
let compile_budget = Duration::from_secs((cfg.max_lifetime_secs / 2).clamp(20, 120));
openplc::load_and_start(
http,
&handle.webvisu_url,
&cfg.openplc_user,
cfg.openplc_password.expose_secret(),
program,
compile_budget,
)
.await?;
// Give the runtime a moment to open the Modbus/TCP server before probing.
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;
tracing::info!(
target_id,
instance = %handle.name,
found = findings.len(),
"provision-and-test probe complete"
);
// DAST the provisioned web endpoint (independently bounded so it can't eat
// the whole lifetime). On the OpenPLC substrate this is OpenPLC's own web UI,
// not a customer HMI — the CODESYS-runtime follow-up raises the fidelity —
// but it proves the deploy→run→probe→DAST loop end to end.
let dast_budget = Duration::from_secs((cfg.max_lifetime_secs / 2).clamp(20, 120));
let dast = match tokio::time::timeout(dast_budget, run_webvisu_dast(handle, target_id)).await {
Ok(d) => d,
Err(_) => {
tracing::warn!(target_id, instance = %handle.name, "provision-and-test DAST timed out");
None
}
};
Ok(ProvisionOutcome { findings, dast })
}
/// Run a bounded DAST scan against the provisioned web endpoint and tag the
/// results with our target id. Best-effort — a DAST failure never fails the run.
async fn run_webvisu_dast(handle: &ProvisionedRuntime, target_id: &str) -> Option<DastRunResult> {
let mut dt = DastTarget::new(
"provisioned-webvisu".to_string(),
handle.webvisu_url.clone(),
DastTargetType::WebApp,
);
dt.repo_id = Some(target_id.to_string());
dt.max_crawl_depth = 2; // shallow — the instance is ephemeral
let orchestrator = compliance_dast::DastOrchestrator::new(100);
match orchestrator.run_scan(&dt, Vec::new()).await {
Ok((mut scan_run, mut findings)) => {
scan_run.target_id = target_id.to_string();
for f in &mut findings {
f.target_id = target_id.to_string();
}
tracing::info!(
target_id,
instance = %handle.name,
dast_findings = findings.len(),
"provision-and-test DAST complete"
);
Some(DastRunResult { scan_run, findings })
}
Err(e) => {
tracing::warn!(target_id, instance = %handle.name, error = %e, "provision-and-test DAST failed");
None
}
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::Arc;
/// A scratch dir removed on drop.
struct Scratch(std::path::PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-plc-rt-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&p).expect("mkdir");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = std::fs::remove_dir_all(&self.0);
}
}
#[test]
fn extract_prefers_a_complete_st_program() {
let s = Scratch::new();
std::fs::write(s.0.join("fragment.st"), "PROGRAM P\nEND_PROGRAM\n").expect("w");
std::fs::write(
s.0.join("full.st"),
"PROGRAM Main\nEND_PROGRAM\nCONFIGURATION Config0\n RESOURCE R\nEND_CONFIGURATION\n",
)
.expect("w");
let prog = extract_program(&s.0).expect("program");
assert_eq!(prog.file_name, "full.st");
assert!(prog.source.contains("CONFIGURATION"));
}
#[test]
fn extract_falls_back_to_largest_st_then_plcopen() {
let s = Scratch::new();
std::fs::write(s.0.join("small.st"), "PROGRAM A\nEND_PROGRAM\n").expect("w");
std::fs::write(
s.0.join("big.st"),
"PROGRAM B\nVAR x : INT; y : INT; z : INT; END_VAR\nEND_PROGRAM\n",
)
.expect("w");
let prog = extract_program(&s.0).expect("program");
assert_eq!(
prog.file_name, "big.st",
"largest ST wins when none complete"
);
// Only a PLCopen XML present.
let s2 = Scratch::new();
std::fs::write(
s2.0.join("proj.xml"),
"<?xml version='1.0'?><project xmlns='http://www.plcopen.org/xml/tc6_0201'><pou/></project>",
)
.expect("w");
let prog2 = extract_program(&s2.0).expect("program");
assert_eq!(prog2.file_name, "proj.xml");
}
#[test]
fn extract_returns_none_without_control_logic() {
let s = Scratch::new();
std::fs::write(s.0.join("readme.md"), "# not a plc program").expect("w");
std::fs::write(s.0.join("data.xml"), "<config><db/></config>").expect("w");
assert!(extract_program(&s.0).is_none());
}
/// A fake provisioner recording provision/teardown calls, for lifecycle tests.
struct FakeSoftPlc {
provisions: Arc<AtomicUsize>,
teardowns: Arc<AtomicUsize>,
fail_provision: bool,
}
impl SoftPlc for FakeSoftPlc {
async fn provision(&self, _target_id: &str) -> Result<ProvisionedRuntime, ExecError> {
self.provisions.fetch_add(1, Ordering::SeqCst);
if self.fail_provision {
return Err(ExecError::Other("provision failed".into()));
}
// Unreachable address so run_dynamic_test blocks on readiness until the
// deadline fires — exercising the teardown-on-deadline path.
Ok(ProvisionedRuntime {
name: "fake-plc".into(),
modbus_endpoint: "fake-plc:502".into(),
webvisu_url: "http://fake-plc.invalid:8080".into(),
})
}
async fn teardown(&self, _handle: &ProvisionedRuntime) {
self.teardowns.fetch_add(1, Ordering::SeqCst);
}
}
fn short_cfg() -> PlcRuntimeConfig {
PlcRuntimeConfig {
enabled: true,
max_lifetime_secs: 1, // keep the deadline path fast
..PlcRuntimeConfig::default()
}
}
#[tokio::test]
async fn teardown_runs_even_when_the_test_never_completes() {
let provisions = Arc::new(AtomicUsize::new(0));
let teardowns = Arc::new(AtomicUsize::new(0));
let fake = FakeSoftPlc {
provisions: provisions.clone(),
teardowns: teardowns.clone(),
fail_provision: false,
};
let http = http_client().expect("client");
let prog = PlcProgram {
file_name: "p.st".into(),
source: "PROGRAM P\nEND_PROGRAM\n".into(),
};
let out = provision_and_test(&fake, &http, &short_cfg(), &prog, "t1")
.await
.expect("ok on deadline");
assert!(out.findings.is_empty(), "deadline path yields no findings");
assert!(out.dast.is_none(), "deadline path runs no DAST");
assert_eq!(provisions.load(Ordering::SeqCst), 1);
assert_eq!(teardowns.load(Ordering::SeqCst), 1, "teardown must run");
}
#[tokio::test]
async fn provision_failure_propagates_and_skips_teardown() {
let provisions = Arc::new(AtomicUsize::new(0));
let teardowns = Arc::new(AtomicUsize::new(0));
let fake = FakeSoftPlc {
provisions: provisions.clone(),
teardowns: teardowns.clone(),
fail_provision: true,
};
let http = http_client().expect("client");
let prog = PlcProgram {
file_name: "p.st".into(),
source: String::new(),
};
let err = provision_and_test(&fake, &http, &short_cfg(), &prog, "t1").await;
assert!(err.is_err(), "provision failure propagates");
assert_eq!(provisions.load(Ordering::SeqCst), 1);
assert_eq!(
teardowns.load(Ordering::SeqCst),
0,
"nothing to tear down when provisioning failed"
);
}
}
+254
View File
@@ -0,0 +1,254 @@
//! Loading a control-logic program into a provisioned OpenPLC (#183, sub-task 2).
//!
//! Drives the OpenPLC v3 web UI over HTTP to turn a static control-logic artifact
//! into a *running* PLC: log in, upload the program, save it, compile it (MatIEC),
//! and start the runtime — at which point OpenPLC opens its Modbus/TCP server on
//! 502 and the ICS probe has something to talk to. The endpoint sequence mirrors
//! the OpenPLC web UI: `POST /login` → `POST /upload-program` (which hands back a
//! server-assigned `prog_file`) → `POST /upload-program-action` →
//! `GET /compile-program?file=<prog_file>` → `GET /start_plc`.
use std::time::Duration;
use crate::error::ExecError;
use super::PlcProgram;
/// Default OpenPLC program name/description recorded in its UI.
const PROG_NAME: &str = "certifai-provisioned";
const PROG_DESCR: &str = "Uploaded by the Certifai provision-and-test scan";
/// Poll interval while waiting for readiness / compilation.
const POLL_INTERVAL: Duration = Duration::from_secs(2);
/// Wait until the OpenPLC web UI answers (any non-5xx reply to `/login`), or the
/// budget elapses. A freshly-started container needs a few seconds to boot.
pub async fn wait_ready(
http: &reqwest::Client,
base_url: &str,
budget: Duration,
) -> Result<(), ExecError> {
let login = format!("{base_url}/login");
let outcome = tokio::time::timeout(budget, async {
loop {
if let Ok(resp) = http.get(&login).send().await {
if !resp.status().is_server_error() {
return;
}
}
tokio::time::sleep(POLL_INTERVAL).await;
}
})
.await;
outcome.map_err(|_| ExecError::Other(format!("OpenPLC at {base_url} did not become ready")))
}
/// Log in, upload the program, compile it, and start the runtime. On success the
/// OpenPLC Modbus/TCP server is listening on 502.
pub async fn load_and_start(
http: &reqwest::Client,
base_url: &str,
user: &str,
password: &str,
program: &PlcProgram,
compile_budget: Duration,
) -> Result<(), ExecError> {
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?;
compile(http, base_url, &prog_file, compile_budget).await?;
start(http, base_url).await?;
Ok(())
}
/// `POST /login` — establishes the session cookie (the client must have a cookie
/// store; see the provision-and-test entry point).
async fn login(
http: &reqwest::Client,
base_url: &str,
user: &str,
password: &str,
) -> Result<(), ExecError> {
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!(
"OpenPLC login failed: HTTP {}",
resp.status()
)));
}
Ok(())
}
/// `POST /upload-program` (multipart `file`) — OpenPLC stores the program under a
/// server-assigned name and returns it in a hidden `prog_file` form field, which
/// we parse out for the follow-up save/compile steps.
async fn upload_program(
http: &reqwest::Client,
base_url: &str,
program: &PlcProgram,
) -> Result<String, ExecError> {
let part = reqwest::multipart::Part::text(program.source.clone())
.file_name(program.file_name.clone())
.mime_str("application/octet-stream")?;
let form = reqwest::multipart::Form::new().part("file", part);
let resp = http
.post(format!("{base_url}/upload-program"))
.multipart(form)
.send()
.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())
})
}
/// `POST /upload-program-action` — records the uploaded program in OpenPLC's
/// program list. `epoch_time` must be close to the server's clock (OpenPLC
/// rejects stale timestamps), so we send the current time.
async fn save_program(
http: &reqwest::Client,
base_url: &str,
prog_file: &str,
) -> Result<(), ExecError> {
let epoch = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.map(|d| d.as_secs())
.unwrap_or(0)
.to_string();
let resp = http
.post(format!("{base_url}/upload-program-action"))
.form(&[
("prog_name", PROG_NAME),
("prog_descr", PROG_DESCR),
("prog_file", prog_file),
("epoch_time", &epoch),
])
.send()
.await?;
if resp.status().is_server_error() {
return Err(ExecError::Other(format!(
"OpenPLC save-program failed: HTTP {}",
resp.status()
)));
}
Ok(())
}
/// `GET /compile-program?file=<prog_file>` then poll `/compilation-logs` until
/// MatIEC reports it finished (or the budget elapses). Errors if compilation
/// finishes with errors — a program that won't compile can't be started.
async fn compile(
http: &reqwest::Client,
base_url: &str,
prog_file: &str,
budget: Duration,
) -> Result<(), ExecError> {
http.get(format!("{base_url}/compile-program"))
.query(&[("file", prog_file)])
.send()
.await?;
let logs_url = format!("{base_url}/compilation-logs");
let outcome = tokio::time::timeout(budget, async {
loop {
if let Ok(resp) = http.get(&logs_url).send().await {
if let Ok(text) = resp.text().await {
if compilation_finished(&text) {
return !compilation_failed(&text);
}
}
}
tokio::time::sleep(POLL_INTERVAL).await;
}
})
.await;
match outcome {
Ok(true) => Ok(()),
Ok(false) => Err(ExecError::Other(
"OpenPLC compilation finished with errors".to_string(),
)),
Err(_) => Err(ExecError::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> {
let resp = http.get(format!("{base_url}/start_plc")).send().await?;
if resp.status().is_server_error() {
return Err(ExecError::Other(format!(
"OpenPLC start_plc failed: HTTP {}",
resp.status()
)));
}
Ok(())
}
/// Extract the server-assigned `prog_file` from the `/upload-program` response,
/// which embeds it in a hidden input. Attribute order varies, so accept both
/// `value=… name='prog_file'` and `name='prog_file' … value=…`.
fn parse_prog_file(html: &str) -> Option<String> {
// The OpenPLC template renders `value='<name>.st' id='prog_file'
// name='prog_file'`. Match the value bound to that input, either order.
let value_then_name =
regex::Regex::new(r#"(?is)value=['"]([^'"]+)['"][^>]*name=['"]prog_file['"]"#).ok()?;
if let Some(c) = value_then_name.captures(html) {
return c.get(1).map(|m| m.as_str().to_string());
}
let name_then_value =
regex::Regex::new(r#"(?is)name=['"]prog_file['"][^>]*value=['"]([^'"]+)['"]"#).ok()?;
name_then_value
.captures(html)
.and_then(|c| c.get(1))
.map(|m| m.as_str().to_string())
}
/// Whether the MatIEC compilation log shows the build has finished (either way).
fn compilation_finished(log: &str) -> bool {
log.contains("Compilation finished")
}
/// Whether a finished compilation ended in failure.
fn compilation_failed(log: &str) -> bool {
log.contains("Compilation finished with errors")
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
#[test]
fn parses_prog_file_value_then_name() {
let html = "<form><input type='hidden' value='483927.st' id='prog_file' \
name='prog_file'/></form>";
assert_eq!(parse_prog_file(html), Some("483927.st".to_string()));
}
#[test]
fn parses_prog_file_name_then_value() {
let html = r#"<input name="prog_file" id="prog_file" value="12.st" />"#;
assert_eq!(parse_prog_file(html), Some("12.st".to_string()));
}
#[test]
fn parse_prog_file_none_when_absent() {
assert_eq!(parse_prog_file("<html>no form here</html>"), None);
}
#[test]
fn compilation_predicates() {
assert!(!compilation_finished("Compiling..."));
assert!(compilation_finished(
"...\nCompilation finished successfully!\n"
));
assert!(compilation_finished("Compilation finished with errors!"));
assert!(compilation_failed("Compilation finished with errors!"));
assert!(!compilation_failed("Compilation finished successfully!"));
}
}
+306
View File
@@ -0,0 +1,306 @@
//! Ephemeral soft-PLC container lifecycle (#183, sub-task 1 + 5).
//!
//! Provisions a throwaway OpenPLC container per scan, isolated on the agent's own
//! Docker network with hard resource caps and **no host port exposure**, then
//! guarantees teardown. The container is reachable in-cluster only, by its name
//! (the shared user-defined network's embedded DNS resolves it); it is never
//! published to the host.
//!
//! The `docker` argv is produced by pure functions so provisioning is unit-tested
//! without a Docker daemon — only the thin [`run_docker`] wrapper touches the OS.
//! It requires the agent's runtime to have Docker access (a socket mount), which
//! is why the whole path is gated behind [`PlcRuntimeConfig::enabled`].
use std::time::{SystemTime, UNIX_EPOCH};
use compliance_core::PlcRuntimeConfig;
use crate::error::ExecError;
/// The Modbus/TCP port an OpenPLC instance opens once a program is running.
const MODBUS_PORT: u16 = 502;
/// The OpenPLC web-UI / WebVisu port.
const WEBVISU_PORT: u16 = 8080;
/// Label key marking a container as an ephemeral PLC runtime we own.
const OWNER_LABEL_KEY: &str = "certifai.ephemeral";
/// Label value for our ephemeral PLC runtimes.
const OWNER_LABEL_VALUE: &str = "plc-runtime";
/// A running ephemeral soft-PLC instance. Reachable in-cluster by `name`.
#[derive(Debug, Clone)]
pub struct ProvisionedRuntime {
/// The container name — also its in-network DNS alias.
pub name: String,
/// `name:502` — the Modbus/TCP endpoint the ICS probe targets.
pub modbus_endpoint: String,
/// `http://name:8080` — the WebVisu / OpenPLC web UI.
pub webvisu_url: String,
}
/// A source of ephemeral soft-PLC instances. Abstracted so the provision-and-test
/// orchestration is unit-testable with a fake that never touches Docker.
pub trait SoftPlc {
/// Start a fresh instance for a target and return its handle.
fn provision(
&self,
target_id: &str,
) -> impl std::future::Future<Output = Result<ProvisionedRuntime, ExecError>> + Send;
/// Tear an instance down. Best-effort and idempotent — never fails the scan.
fn teardown(&self, handle: &ProvisionedRuntime)
-> impl std::future::Future<Output = ()> + Send;
}
/// Provisions OpenPLC instances by shelling out to the Docker CLI.
pub struct DockerSoftPlc {
cfg: PlcRuntimeConfig,
}
impl DockerSoftPlc {
/// Build a provisioner from the PLC-runtime config.
pub fn new(cfg: PlcRuntimeConfig) -> Self {
Self { cfg }
}
}
impl SoftPlc for DockerSoftPlc {
async fn provision(&self, target_id: &str) -> Result<ProvisionedRuntime, ExecError> {
// 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.
reap_stale(&self.cfg, now_epoch()).await;
let name = instance_name(target_id, now_epoch(), &random_suffix());
let args = run_args(&self.cfg, &name, target_id);
let out = run_docker(&args).await?;
if !out.status.success() {
return Err(ExecError::Other(format!(
"docker run for soft-PLC {name} failed: {}",
String::from_utf8_lossy(&out.stderr).trim()
)));
}
Ok(ProvisionedRuntime {
modbus_endpoint: format!("{name}:{MODBUS_PORT}"),
webvisu_url: format!("http://{name}:{WEBVISU_PORT}"),
name,
})
}
async fn teardown(&self, handle: &ProvisionedRuntime) {
match run_docker(&rm_args(&handle.name)).await {
Ok(out) if out.status.success() => {
tracing::info!(instance = %handle.name, "soft-PLC instance torn down");
}
Ok(out) => tracing::warn!(
instance = %handle.name,
"soft-PLC teardown non-zero exit: {}",
String::from_utf8_lossy(&out.stderr).trim()
),
Err(e) => {
tracing::warn!(instance = %handle.name, error = %e, "soft-PLC teardown failed")
}
}
}
}
/// Seconds since the Unix epoch (0 if the clock is before 1970, which never
/// happens in practice).
fn now_epoch() -> u64 {
SystemTime::now()
.duration_since(UNIX_EPOCH)
.map(|d| d.as_secs())
.unwrap_or(0)
}
/// A short random, docker-name-safe suffix.
fn random_suffix() -> String {
uuid::Uuid::new_v4().simple().to_string()
}
/// A unique, docker-safe container name that encodes the creation epoch (for the
/// stale reaper) and the target it belongs to. Shape:
/// `certifai-plc-<epoch>-<target12>-<rand6>`.
fn instance_name(target_id: &str, epoch: u64, rand: &str) -> String {
let short: String = target_id
.chars()
.filter(char::is_ascii_alphanumeric)
.take(12)
.collect();
let rand: String = rand
.chars()
.filter(char::is_ascii_alphanumeric)
.take(6)
.collect();
format!("certifai-plc-{epoch}-{short}-{rand}")
}
/// The creation epoch encoded in an instance name, if it is one of ours.
fn parse_epoch(name: &str) -> Option<u64> {
name.strip_prefix("certifai-plc-")?
.split('-')
.next()?
.parse()
.ok()
}
/// The `docker run` argv for an ephemeral soft-PLC: detached, joined to the
/// agent's network, resource-capped, hardened, labelled for reaping, and — by
/// omitting any `-p` — never published to the host.
fn run_args(cfg: &PlcRuntimeConfig, name: &str, target_id: &str) -> Vec<String> {
vec![
"run".into(),
"-d".into(),
"--name".into(),
name.into(),
"--network".into(),
cfg.network.clone(),
"--memory".into(),
cfg.memory.clone(),
"--cpus".into(),
cfg.cpus.clone(),
"--pids-limit".into(),
"512".into(),
"--security-opt".into(),
"no-new-privileges".into(),
"--stop-timeout".into(),
"5".into(),
"--label".into(),
format!("{OWNER_LABEL_KEY}={OWNER_LABEL_VALUE}"),
"--label".into(),
format!("certifai.target={target_id}"),
cfg.image.clone(),
]
}
/// The `docker rm -f` argv that stops and removes an instance.
fn rm_args(name: &str) -> Vec<String> {
vec!["rm".into(), "-f".into(), name.into()]
}
/// The `docker ps` argv listing the names of every ephemeral PLC container we own.
fn reap_list_args() -> Vec<String> {
vec![
"ps".into(),
"-a".into(),
"--filter".into(),
format!("label={OWNER_LABEL_KEY}={OWNER_LABEL_VALUE}"),
"--format".into(),
"{{.Names}}".into(),
]
}
/// Remove any ephemeral PLC container older than twice the configured max
/// lifetime — i.e. one a crashed run leaked. The generous threshold guarantees a
/// container from a *live* run (still within its own deadline) is never swept.
/// Best-effort: any Docker error (e.g. no daemon) is ignored.
async fn reap_stale(cfg: &PlcRuntimeConfig, now: u64) {
let cutoff = cfg.max_lifetime_secs.saturating_mul(2);
let Ok(out) = run_docker(&reap_list_args()).await else {
return;
};
if !out.status.success() {
return;
}
let names = String::from_utf8_lossy(&out.stdout);
for name in names.lines().map(str::trim).filter(|n| !n.is_empty()) {
let Some(epoch) = parse_epoch(name) else {
continue;
};
if now.saturating_sub(epoch) > cutoff {
tracing::warn!(instance = %name, "reaping stale soft-PLC instance");
let _ = run_docker(&rm_args(name)).await;
}
}
}
/// Run a `docker` subcommand, capturing its output.
async fn run_docker(args: &[String]) -> Result<std::process::Output, ExecError> {
tokio::process::Command::new("docker")
.args(args)
.output()
.await
.map_err(ExecError::Io)
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
fn cfg() -> PlcRuntimeConfig {
PlcRuntimeConfig {
enabled: true,
image: "registry.example.com/openplc:latest".into(),
network: "certifai".into(),
memory: "512m".into(),
cpus: "0.5".into(),
max_lifetime_secs: 180,
..PlcRuntimeConfig::default()
}
}
#[test]
fn instance_name_is_unique_docker_safe_and_reaper_parseable() {
let a = instance_name("64f0aabbccddeeff00112233", 1_700_000_000, "abcdef123456");
assert_eq!(a, "certifai-plc-1700000000-64f0aabbccdd-abcdef");
assert_eq!(parse_epoch(&a), Some(1_700_000_000));
// Docker names: only [A-Za-z0-9_.-].
assert!(a
.chars()
.all(|c| c.is_ascii_alphanumeric() || matches!(c, '_' | '.' | '-')));
// A different random suffix yields a different name for the same target.
let b = instance_name("64f0aabbccddeeff00112233", 1_700_000_000, "zzzzzz999999");
assert_ne!(a, b);
}
#[test]
fn parse_epoch_rejects_foreign_names() {
assert_eq!(parse_epoch("some-other-container"), None);
assert_eq!(parse_epoch("certifai-plc-notanumber-x"), None);
}
#[test]
fn run_args_cap_resources_harden_label_and_never_publish_a_port() {
let args = run_args(&cfg(), "certifai-plc-1-t-r", "target-123");
// No host port publishing.
assert!(!args.iter().any(|a| a == "-p" || a == "--publish"));
// Detached.
assert!(args.contains(&"-d".to_string()));
// Joined to the agent's own network.
let net = args.iter().position(|a| a == "--network").expect("network");
assert_eq!(args[net + 1], "certifai");
// Resource caps.
let mem = args.iter().position(|a| a == "--memory").expect("memory");
assert_eq!(args[mem + 1], "512m");
let cpu = args.iter().position(|a| a == "--cpus").expect("cpus");
assert_eq!(args[cpu + 1], "0.5");
assert!(args.iter().any(|a| a == "--pids-limit"));
// Hardening.
let so = args
.iter()
.position(|a| a == "--security-opt")
.expect("secopt");
assert_eq!(args[so + 1], "no-new-privileges");
// Ownership + target labels for reaping / attribution.
assert!(args.contains(&"certifai.ephemeral=plc-runtime".to_string()));
assert!(args.contains(&"certifai.target=target-123".to_string()));
// Image is last.
assert_eq!(
args.last().map(String::as_str),
Some("registry.example.com/openplc:latest")
);
}
#[test]
fn rm_args_force_remove() {
assert_eq!(rm_args("x"), vec!["rm", "-f", "x"]);
}
#[test]
fn reap_list_filters_by_owner_label() {
let args = reap_list_args();
assert!(args.contains(&"label=certifai.ephemeral=plc-runtime".to_string()));
assert!(args.contains(&"{{.Names}}".to_string()));
}
}