Compare commits

..
Author SHA1 Message Date
Sharang Parnerkar 6d95070f7b style(wizard): rustfmt infrastructure/onboarding.rs
CI / Check (pull_request) Successful in 5m37s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been skipped
CI / Deploy Dashboard (pull_request) Has been skipped
CI / Deploy Docs (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
2026-07-12 23:16:17 +02:00
Sharang ParnerkarandClaude Fable 5 616e97ff71 feat(dashboard): onboarding wizard UI (#123-127)
CI / Check (pull_request) Failing after 1m34s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been skipped
CI / Deploy Dashboard (pull_request) Has been skipped
CI / Deploy Docs (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
A dedicated multi-step onboarding flow at /onboard (new "Onboard" sidebar entry),
wired to the #131 target endpoints:
- Step 1 — target type: card grid of the 9 families + name.
- Step 2 — artifacts: type-aware add-a-row form (git/live-url/firmware/mobile/
  container/PLC/archive/text) with a removable list.
- Step 3 — review: summary of type + artifacts.
- Step 4 — done: creates the target, runs kind-based detection, and shows the
  applicable-scans matrix (default-on / blocked with rationale).

Server fns in infrastructure/onboarding.rs proxy to /api/v1/targets (create,
detect, applicable-scans). Compiles clean under both --features web and
--features server; fmt + clippy -D warnings pass.

Full scan-selection toggling and a "launch scan" action are follow-ups (launch
needs the unified pipeline, #133).

Closes #123, #124, #125. Refs #126, #127, #118.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-12 22:34:42 +02:00
Sharang Parnerkar 6e3c42a14d wip(wizard): onboarding server fns (infrastructure/onboarding.rs) 2026-07-12 22:15:21 +02:00
15 changed files with 5 additions and 1052 deletions
+1 -6
View File
@@ -191,18 +191,13 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
# PAT for fetching the private tramiton-core git dependency during the
# image build (injected as a BuildKit secret, never baked into a layer).
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-agent
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker build -f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy agent"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
+1 -10
View File
@@ -2,16 +2,7 @@ FROM rust:1.94-bookworm AS builder
WORKDIR /app
COPY . .
# compliance-agent depends on the private tramiton-core git repo. Authenticate
# the fetch with a PAT passed as a BuildKit secret (never baked into a layer).
# Build with: DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN ...
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true cargo build --release -p compliance-agent
RUN cargo build --release -p compliance-agent
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 git curl python3 python3-pip npm golang-go php-cli && rm -rf /var/lib/apt/lists/*
+1 -5
View File
@@ -63,11 +63,7 @@ impl ComplianceAgent {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
if self.config.unified_pipeline {
orchestrator.run_target(repo_id, trigger).await
} else {
orchestrator.run(repo_id, trigger).await
}
orchestrator.run(repo_id, trigger).await
}
/// Run a PR review: scan the diff and post review comments.
-1
View File
@@ -9,7 +9,6 @@ pub mod help_chat;
pub mod issues;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod pentest_handlers;
pub use pentest_handlers as pentest;
pub mod repos;
@@ -1,350 +0,0 @@
//! Onboarding API — CRUD for unified targets, artifact add, classification, and
//! the scan-applicability matrix. The wizard (and future integrations) drive
//! onboarding through these endpoints.
use std::collections::HashMap;
use std::sync::Arc;
use axum::extract::{Extension, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::{doc, oid::ObjectId, to_bson};
use serde::{Deserialize, Serialize};
use compliance_core::models::{
Artifact, ArtifactKind, ComplianceProfile, OnboardedTarget, PlcFormat, TargetScanConfig,
TargetType,
};
use compliance_core::scan_matrix::{applicable_scans, supports_pentest};
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use crate::classify::{classify_target, MockFirmwareDetector};
use super::dto::tenant_db;
use super::{collect_cursor_async, ApiResponse, PaginationParams};
type AgentExt = Extension<Arc<ComplianceAgent>>;
/// A client-supplied artifact spec. The server builds the [`Artifact`] (and its
/// id) from it, so clients never set internal fields.
#[derive(Deserialize)]
pub struct ArtifactInput {
pub kind: ArtifactKind,
pub source_ref: String,
#[serde(default)]
pub branch: Option<String>,
#[serde(default)]
pub plc_format: Option<PlcFormat>,
}
impl ArtifactInput {
fn build(&self) -> Artifact {
let s = self.source_ref.clone();
match self.kind {
ArtifactKind::GitRepo => {
Artifact::git_repo(s, self.branch.clone().unwrap_or_else(|| "main".to_string()))
}
ArtifactKind::LiveUrl => Artifact::live_url(s),
ArtifactKind::FirmwareImage => Artifact::firmware_image(s),
ArtifactKind::SourceArchive => Artifact::source_archive(s),
ArtifactKind::MobilePackage => Artifact::mobile_package(s),
ArtifactKind::ContainerImage => Artifact::container_image(s),
ArtifactKind::PlcProject => {
Artifact::plc_project(s, self.plc_format.unwrap_or(PlcFormat::PlcopenXml))
}
ArtifactKind::PlaintextDescription => Artifact::plaintext(s),
}
}
}
#[derive(Deserialize)]
pub struct CreateTargetRequest {
pub name: String,
pub target_type: TargetType,
#[serde(default)]
pub description: Option<String>,
#[serde(default)]
pub artifacts: Vec<ArtifactInput>,
}
#[derive(Deserialize)]
pub struct UpdateTargetRequest {
pub name: Option<String>,
pub target_type: Option<TargetType>,
pub scan_config: Option<TargetScanConfig>,
pub compliance_profile: Option<ComplianceProfile>,
pub scan_schedule: Option<String>,
}
/// One applicable-scan option, serialized for the wizard.
#[derive(Serialize)]
pub struct ScanOptionDto {
pub scan: String,
pub default_on: bool,
pub rationale: String,
pub required_artifact: Option<String>,
pub blocked_reason: Option<String>,
}
#[derive(Serialize)]
pub struct ApplicableScansResponse {
pub scans: Vec<ScanOptionDto>,
pub pentest_supported: bool,
}
fn parse_oid(id: &str) -> Result<ObjectId, StatusCode> {
ObjectId::parse_str(id).map_err(|_| StatusCode::BAD_REQUEST)
}
/// GET /api/v1/targets — list onboarded targets (paginated).
#[tracing::instrument(skip_all)]
pub async fn list_targets(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<OnboardedTarget>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.onboarded_targets()
.count_documents(doc! {})
.await
.unwrap_or(0);
let targets = match db
.onboarded_targets()
.find(doc! {})
.skip(skip)
.limit(params.limit)
.await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!("Failed to fetch onboarded targets: {e}");
Vec::new()
}
};
Ok(Json(ApiResponse {
data: targets,
total: Some(total),
page: Some(params.page),
}))
}
/// POST /api/v1/targets — create an onboarded target.
#[tracing::instrument(skip_all)]
pub async fn create_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateTargetRequest>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let mut target = OnboardedTarget::new(req.name, req.target_type);
target.description = req.description;
target.artifacts = req.artifacts.iter().map(ArtifactInput::build).collect();
let db = tenant_db(&agent, &tenant).await?;
let res = db
.onboarded_targets()
.insert_one(&target)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
target.id = res.inserted_id.as_object_id();
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// GET /api/v1/targets/{id} — fetch one target.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn get_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// PATCH /api/v1/targets/{id} — update mutable fields.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn update_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateTargetRequest>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let mut set = doc! { "updated_at": mongodb::bson::DateTime::now() };
if let Some(name) = req.name {
set.insert("name", name);
}
if let Some(tt) = req.target_type {
set.insert(
"target_type",
to_bson(&tt).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(sc) = req.scan_config {
set.insert(
"scan_config",
to_bson(&sc).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(cp) = req.compliance_profile {
set.insert(
"compliance_profile",
to_bson(&cp).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(ss) = req.scan_schedule {
set.insert("scan_schedule", ss);
}
db.onboarded_targets()
.update_one(doc! { "_id": oid }, doc! { "$set": set })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// DELETE /api/v1/targets/{id} — remove the target and its findings/scans.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn delete_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
db.onboarded_targets()
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Cascade the collections keyed by repo_id == target id (best-effort).
let by_repo = doc! { "repo_id": &id };
let _ = db.findings().delete_many(by_repo.clone()).await;
let _ = db.scan_runs().delete_many(by_repo.clone()).await;
let _ = db.sbom_entries().delete_many(by_repo.clone()).await;
let _ = db.cve_alerts().delete_many(by_repo).await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// POST /api/v1/targets/{id}/artifacts — attach an artifact (by reference).
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn add_artifact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(input): Json<ArtifactInput>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let artifact = to_bson(&input.build()).map_err(|_| StatusCode::BAD_REQUEST)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$push": { "artifacts": artifact }, "$set": { "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// GET /api/v1/targets/{id}/applicable-scans — the scan-applicability matrix.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn applicable_scans_for_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<ApplicableScansResponse>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let scans = applicable_scans(&target)
.into_iter()
.map(|o| ScanOptionDto {
scan: o.scan.to_string(),
default_on: o.default_on,
rationale: o.rationale,
required_artifact: o.required_artifact.map(|k| k.to_string()),
blocked_reason: o.blocked_reason,
})
.collect();
Ok(Json(ApiResponse {
data: ApplicableScansResponse {
scans,
pentest_supported: supports_pentest(target.target_type),
},
total: None,
page: None,
}))
}
/// POST /api/v1/targets/{id}/detect — classify the target from its artifacts.
///
/// This is the lightweight pass: it classifies from artifact kinds without
/// ingesting (cloning) sources, so it returns immediately. Deep detection (after
/// ingest, with tramiton firmware analysis) is a follow-up background step.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn detect_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let mut target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
// No ingested working paths here → kind-based classification only; the mock
// firmware detector is never invoked (no firmware working path present).
let empty = HashMap::new();
let detector = MockFirmwareDetector { detection: None };
let classification = classify_target(&target, &empty, &detector)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let classification_bson =
to_bson(&classification).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "classification": classification_bson, "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
target.classification = Some(classification);
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
-23
View File
@@ -25,29 +25,6 @@ pub fn build_router() -> Router {
"/api/v1/repositories/{id}/webhook-config",
get(handlers::get_webhook_config),
)
// Unified onboarding targets (#131).
.route(
"/api/v1/targets",
get(handlers::onboarding::list_targets).post(handlers::onboarding::create_target),
)
.route(
"/api/v1/targets/{id}",
get(handlers::onboarding::get_target)
.patch(handlers::onboarding::update_target)
.delete(handlers::onboarding::delete_target),
)
.route(
"/api/v1/targets/{id}/artifacts",
post(handlers::onboarding::add_artifact),
)
.route(
"/api/v1/targets/{id}/applicable-scans",
get(handlers::onboarding::applicable_scans_for_target),
)
.route(
"/api/v1/targets/{id}/detect",
post(handlers::onboarding::detect_target),
)
.route("/api/v1/findings", get(handlers::list_findings))
.route("/api/v1/findings/{id}", get(handlers::get_finding))
.route(
-3
View File
@@ -47,9 +47,6 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
.unwrap_or_else(|| "/tmp/compliance-scanner/repos".to_string()),
artifact_store_base_path: env_var_opt("ARTIFACT_STORE_BASE_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/artifacts".to_string()),
unified_pipeline: env_var_opt("UNIFIED_PIPELINE")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(false),
ssh_key_path: env_var_opt("SSH_KEY_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/ssh/id_ed25519".to_string()),
keycloak_url: env_var_opt("KEYCLOAK_URL"),
-1
View File
@@ -342,7 +342,6 @@ mod tests {
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
unified_pipeline: false,
}
}
-1
View File
@@ -8,7 +8,6 @@ mod issue_creation;
pub mod lint;
pub mod orchestrator;
pub mod patterns;
pub mod plan;
mod pr_review;
pub mod sbom;
pub mod semgrep;
@@ -15,7 +15,6 @@ use crate::pipeline::git::GitOps;
use crate::pipeline::gitleaks::GitleaksScanner;
use crate::pipeline::lint::LintScanner;
use crate::pipeline::patterns::{GdprPatternScanner, OAuthPatternScanner};
use crate::pipeline::plan::build_scan_plan;
use crate::pipeline::sbom::SbomScanner;
use crate::pipeline::semgrep::SemgrepScanner;
@@ -420,260 +419,6 @@ impl PipelineOrchestrator {
Ok(new_count)
}
/// Unified entry point (behind `UNIFIED_PIPELINE`): run a scan for an
/// `OnboardedTarget`. Mirrors [`Self::run`] but sources the target from
/// `onboarded_targets` and dispatches by the scan plan.
#[tracing::instrument(skip_all, fields(target_id = %target_id, trigger = ?trigger))]
pub async fn run_target(
&self,
target_id: &str,
trigger: ScanTrigger,
) -> Result<(), AgentError> {
let oid = mongodb::bson::oid::ObjectId::parse_str(target_id)
.map_err(|e| AgentError::Other(e.to_string()))?;
let target = self
.db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await?
.ok_or_else(|| AgentError::Other(format!("Onboarded target {target_id} not found")))?;
let scan_run = ScanRun::new(target_id.to_string(), trigger);
let insert = self.db.scan_runs().insert_one(&scan_run).await?;
let scan_run_id = insert
.inserted_id
.as_object_id()
.map(|id| id.to_hex())
.unwrap_or_default();
let result = self.run_target_pipeline(&target, &scan_run_id).await;
match &result {
Ok(count) => {
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! { "$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
}
Err(e) => {
tracing::error!(target_id, error = %e, "Unified scan pipeline failed");
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! { "$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
}
}
result.map(|_| ())
}
/// Run the applicable scans for a target. For a code target this reuses the
/// full legacy pipeline over the code artifact (clone → SAST umbrella →
/// triage → persist → issues → DAST); firmware/PLC/mobile scanners are
/// follow-ups (#128/#129/#130). Returns the number of new findings.
async fn run_target_pipeline(
&self,
target: &OnboardedTarget,
scan_run_id: &str,
) -> Result<u32, AgentError> {
let target_id = target.id.map(|id| id.to_hex()).unwrap_or_default();
let plan = build_scan_plan(target);
tracing::info!(
target_id = %target_id,
target_type = %target.target_type,
planned_steps = plan.steps.len(),
"Unified pipeline: scan plan built"
);
// Ingest + classify (tramiton for firmware) and store the detected type.
self.classify_and_store(target, &target_id, scan_run_id)
.await;
// Provision a DAST target from a LiveUrl artifact so DAST fires for
// wizard-created targets, not just migrated ones.
self.ensure_dast_target(target, &plan).await;
match target.code_artifact() {
Some(code) if code.kind == ArtifactKind::GitRepo => {
let repo = repo_view_from_target(target, code);
let new_count = self.run_pipeline(&repo, scan_run_id).await?;
self.finalize_target(target, &repo, new_count).await?;
Ok(new_count)
}
Some(_) => {
tracing::warn!(
target_id = %target_id,
"Unified pipeline: source-archive scanning not yet wired; skipping"
);
Ok(0)
}
None => {
// No code to scan. Firmware/PLC/mobile static scanners land in
// #128/#129/#130; DAST for a running URL still works when a
// DastTarget row exists (migrated targets).
tracing::info!(
target_id = %target_id,
"Unified pipeline: no code artifact; attempting DAST only"
);
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
Ok(0)
}
}
}
/// Ingest the target's artifacts, classify (tramiton for firmware/RTOS/Yocto,
/// heuristics otherwise), and store the detected classification on the target.
/// Best-effort — never fails the scan.
async fn classify_and_store(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) {
self.update_phase(scan_run_id, "classification").await;
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = match crate::ingest::ingest_all(target, &ctx) {
Ok(set) => set,
Err(e) => {
tracing::warn!(target_id, error = %e, "Unified pipeline: ingest for classification failed");
return;
}
};
let working_paths = ingest_set.working_paths();
match crate::classify::classify_target(
target,
&working_paths,
&crate::classify::TramitonNative,
)
.await
{
Ok(classification) => {
tracing::info!(
target_id,
suggested = %classification.suggested,
"Unified pipeline: classified target"
);
if let (Some(oid), Ok(bson)) = (target.id, mongodb::bson::to_bson(&classification))
{
let _ = self
.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "classification": bson } },
)
.await;
}
}
Err(e) => {
tracing::warn!(target_id, error = %e, "Unified pipeline: classification failed")
}
}
}
/// If the target has a `LiveUrl` artifact and DAST is planned, provision a
/// `DastTarget` (keyed by `repo_id` = target id) so the existing DAST trigger
/// fires for wizard-created targets. Idempotent.
async fn ensure_dast_target(
&self,
target: &OnboardedTarget,
plan: &crate::pipeline::plan::ScanPlan,
) {
if !plan.has(ScanType::Dast) {
return;
}
let (Some(url), Some(oid)) = (target.live_url(), target.id) else {
return;
};
let target_id = oid.to_hex();
if self
.db
.dast_targets()
.find_one(doc! { "repo_id": &target_id })
.await
.ok()
.flatten()
.is_some()
{
return; // already provisioned
}
let kind = url
.web
.as_ref()
.map(|w| w.target_kind.clone())
.unwrap_or(DastTargetType::WebApp);
let mut dast = DastTarget::new(target.name.clone(), url.source_ref.clone(), kind);
dast.repo_id = Some(target_id);
if let Some(web) = &url.web {
dast.excluded_paths = web.excluded_paths.clone();
dast.max_crawl_depth = web.max_crawl_depth;
dast.rate_limit = web.rate_limit;
dast.allow_destructive = web.allow_destructive;
}
if let Some(auth) = &url.auth {
dast.auth_config = Some(DastAuthConfig {
method: auth.method.clone(),
login_url: auth.login_url.clone(),
username: auth.username.clone(),
password: None,
token: auth.secret.clone(),
headers: auth.headers.clone(),
});
}
if let Err(e) = self.db.dast_targets().insert_one(&dast).await {
tracing::warn!(error = %e, "Unified pipeline: failed to provision DAST target");
}
}
/// Sync the onboarded-target document after a scan: bump `findings_count`
/// and advance the git artifact's `last_scanned_commit` watermark.
async fn finalize_target(
&self,
target: &OnboardedTarget,
repo: &TrackedRepository,
new_count: u32,
) -> Result<(), AgentError> {
let oid = match target.id {
Some(id) => id,
None => return Ok(()),
};
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! {
"$inc": { "findings_count": new_count as i64 },
"$set": { "updated_at": mongodb::bson::DateTime::now() },
},
)
.await?;
let repo_path = std::path::Path::new(&self.config.git_clone_base_path).join(&repo.name);
if let (Ok(sha), Some(code)) = (GitOps::get_head_sha(&repo_path), target.code_artifact()) {
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid, "artifacts.id": &code.id },
doc! { "$set": { "artifacts.$.git.last_scanned_commit": sha } },
)
.await?;
}
Ok(())
}
pub(super) async fn update_phase(&self, scan_run_id: &str, phase: &str) {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(scan_run_id) {
let _ = self
@@ -691,37 +436,6 @@ impl PipelineOrchestrator {
}
}
/// Build a legacy `TrackedRepository` view from an onboarded target's code
/// artifact, so the unified pipeline can reuse the existing repo pipeline. The
/// inverse of the migration's `repo_to_target`. `_id` is preserved so findings
/// and DAST lookups resolve against the same key.
fn repo_view_from_target(target: &OnboardedTarget, code: &Artifact) -> TrackedRepository {
let mut repo = TrackedRepository::new(target.name.clone(), code.source_ref.clone());
repo.id = target.id;
if let Some(git) = &code.git {
repo.default_branch = git.default_branch.clone();
repo.last_scanned_commit = git.last_scanned_commit.clone();
repo.local_path = git.local_path.clone();
}
if let Some(auth) = &code.auth {
repo.auth_token = auth.secret.clone();
repo.auth_username = auth.username.clone();
}
if let Some(it) = &target.scan_config.issue_tracker {
repo.tracker_type = it.tracker_type.clone();
repo.tracker_owner = it.owner.clone();
repo.tracker_repo = it.repo.clone();
repo.tracker_token = it.token.clone();
}
repo.scan_schedule = target.scan_schedule.clone();
repo.webhook_enabled = target.webhook_enabled;
repo.webhook_secret = target.webhook_secret.clone();
repo.findings_count = target.findings_count;
repo.created_at = target.created_at;
repo.updated_at = target.updated_at;
repo
}
/// Extract the scheme + host from a git URL.
/// e.g. "https://gitea.example.com/owner/repo.git" -> "https://gitea.example.com"
/// e.g. "ssh://git@gitea.example.com:22/owner/repo.git" -> "https://gitea.example.com"
@@ -746,50 +460,3 @@ pub(super) fn extract_base_url(git_url: &str) -> Option<String> {
None
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{
Artifact, ArtifactAuth, IssueTrackerConfig, TargetType, TrackerType,
};
#[test]
fn repo_view_preserves_id_git_auth_and_tracker() {
let mut target = OnboardedTarget::new("acme".to_string(), TargetType::WebApp);
target.id = Some(mongodb::bson::oid::ObjectId::new());
target.findings_count = 3;
target.scan_config.issue_tracker = Some(IssueTrackerConfig {
tracker_type: Some(TrackerType::Gitea),
owner: Some("acme".to_string()),
repo: Some("web".to_string()),
token: Some("tt".to_string()),
});
let mut artifact = Artifact::git_repo("https://git/acme.git", "develop");
if let Some(git) = artifact.git.as_mut() {
git.last_scanned_commit = Some("abc123".to_string());
}
artifact.auth = Some(ArtifactAuth {
method: "token".to_string(),
username: Some("bob".to_string()),
secret: Some("pat".to_string()),
..Default::default()
});
target.artifacts.push(artifact);
let code = target.code_artifact().expect("code artifact");
let repo = repo_view_from_target(&target, code);
assert_eq!(repo.id, target.id); // preserved
assert_eq!(repo.git_url, "https://git/acme.git");
assert_eq!(repo.default_branch, "develop");
assert_eq!(repo.last_scanned_commit.as_deref(), Some("abc123"));
assert_eq!(repo.auth_token.as_deref(), Some("pat"));
assert_eq!(repo.auth_username.as_deref(), Some("bob"));
assert_eq!(repo.tracker_type, Some(TrackerType::Gitea));
assert_eq!(repo.tracker_owner.as_deref(), Some("acme"));
assert_eq!(repo.findings_count, 3);
}
}
-195
View File
@@ -1,195 +0,0 @@
//! The scan plan.
//!
//! [`build_scan_plan`] turns an [`OnboardedTarget`] into the concrete ordered
//! list of scans to run, each bound to the artifact it consumes. It intersects
//! the scan-applicability matrix ([`applicable_scans`]) with the target's
//! `scan_config` overrides: a scan runs when its required artifact is present and
//! it is either on by default or explicitly enabled, and is not explicitly
//! disabled. This is the decision engine the unified pipeline (`run_target`)
//! executes.
use compliance_core::models::{Artifact, ArtifactKind, OnboardedTarget, ScanPhase, ScanType};
use compliance_core::scan_matrix::applicable_scans;
/// One scan to run, bound to the artifact it operates on.
#[derive(Debug, Clone, PartialEq)]
pub struct ScanStep {
/// The scan to run.
pub scan_type: ScanType,
/// The pipeline phase to report while it runs.
pub phase: ScanPhase,
/// The id of the artifact this scan consumes ([`Artifact::id`]).
pub artifact_id: String,
}
/// The ordered set of scans to run for a target.
#[derive(Debug, Clone, Default, PartialEq)]
pub struct ScanPlan {
/// The scans, in matrix order.
pub steps: Vec<ScanStep>,
}
impl ScanPlan {
/// Whether the plan contains a step for the given scan type.
pub fn has(&self, scan: ScanType) -> bool {
self.steps.iter().any(|s| s.scan_type == scan)
}
/// Whether the plan is empty (nothing to run).
pub fn is_empty(&self) -> bool {
self.steps.is_empty()
}
}
/// Build the scan plan for a target: matrix defaults ∩ `scan_config`, each scan
/// bound to the artifact it consumes. Scans whose required artifact is absent, or
/// that are disabled, or off-by-default and not explicitly enabled, are dropped.
pub fn build_scan_plan(target: &OnboardedTarget) -> ScanPlan {
let enabled = &target.scan_config.enabled_scans;
let disabled = &target.scan_config.disabled_scans;
let mut steps = Vec::new();
for option in applicable_scans(target) {
// Required artifact missing → not runnable.
if option.blocked_reason.is_some() {
continue;
}
// Explicit opt-out wins.
if disabled.contains(&option.scan) {
continue;
}
// Run if on by default, or explicitly enabled.
if !option.default_on && !enabled.contains(&option.scan) {
continue;
}
let Some(artifact) = resolve_artifact(target, option.required_artifact) else {
continue;
};
steps.push(ScanStep {
scan_type: option.scan,
phase: phase_for(option.scan),
artifact_id: artifact.id.clone(),
});
}
ScanPlan { steps }
}
/// Resolve the artifact a scan consumes. A "code" requirement (represented by
/// `GitRepo`) is satisfied by a git repo *or* a source archive.
fn resolve_artifact(target: &OnboardedTarget, required: Option<ArtifactKind>) -> Option<&Artifact> {
match required {
Some(ArtifactKind::GitRepo) => target.code_artifact(),
Some(kind) => target.first_of(kind),
None => target.code_artifact().or_else(|| target.artifacts.first()),
}
}
/// The pipeline phase reported while a given scan runs.
fn phase_for(scan: ScanType) -> ScanPhase {
match scan {
ScanType::Sast => ScanPhase::Sast,
ScanType::Sbom => ScanPhase::SbomGeneration,
ScanType::Cve => ScanPhase::CveScanning,
ScanType::Gdpr | ScanType::OAuth => ScanPhase::PatternScanning,
ScanType::SecretDetection => ScanPhase::SecretDetection,
ScanType::Lint => ScanPhase::LintScanning,
ScanType::CodeReview => ScanPhase::CodeReview,
ScanType::Graph => ScanPhase::GraphBuilding,
ScanType::Dast => ScanPhase::DastScanning,
ScanType::FirmwareStatic => ScanPhase::FirmwareStatic,
ScanType::PlcControlLogic => ScanPhase::PlcAnalysis,
ScanType::MobileStatic => ScanPhase::MobileStatic,
ScanType::ContainerScan => ScanPhase::ContainerScan,
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{PlcFormat, TargetType};
fn target(target_type: TargetType, artifacts: Vec<Artifact>) -> OnboardedTarget {
let mut t = OnboardedTarget::new("t".to_string(), target_type);
t.artifacts = artifacts;
t
}
fn step_for<'a>(plan: &'a ScanPlan, scan: ScanType) -> Option<&'a ScanStep> {
plan.steps.iter().find(|s| s.scan_type == scan)
}
#[test]
fn webapp_with_code_and_url_runs_sast_and_dast_bound_to_the_right_artifacts() {
let code = Artifact::git_repo("https://git/x", "main");
let url = Artifact::live_url("https://x");
let (code_id, url_id) = (code.id.clone(), url.id.clone());
let t = target(TargetType::WebApp, vec![code, url]);
let plan = build_scan_plan(&t);
let sast = step_for(&plan, ScanType::Sast).expect("sast planned");
assert_eq!(sast.artifact_id, code_id);
assert_eq!(sast.phase, ScanPhase::Sast);
let dast = step_for(&plan, ScanType::Dast).expect("dast planned");
assert_eq!(dast.artifact_id, url_id);
}
#[test]
fn webapp_without_url_omits_dast() {
let t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
let plan = build_scan_plan(&t);
assert!(plan.has(ScanType::Sast));
assert!(!plan.has(ScanType::Dast));
}
#[test]
fn code_scan_binds_to_source_archive_when_no_git_repo() {
let arc = Artifact::source_archive("src.zip");
let arc_id = arc.id.clone();
let t = target(TargetType::BackendService, vec![arc]);
let plan = build_scan_plan(&t);
let sast = step_for(&plan, ScanType::Sast).expect("sast planned");
assert_eq!(sast.artifact_id, arc_id);
}
#[test]
fn firmware_sbom_and_cve_bind_to_the_firmware_image() {
let fw = Artifact::firmware_image("fw.bin");
let fw_id = fw.id.clone();
let t = target(TargetType::FirmwareBareMetal, vec![fw]);
let plan = build_scan_plan(&t);
let sbom = step_for(&plan, ScanType::Sbom).expect("sbom planned");
assert_eq!(sbom.artifact_id, fw_id);
assert!(step_for(&plan, ScanType::FirmwareStatic).is_some());
assert!(!plan.has(ScanType::Dast));
}
#[test]
fn plc_plans_only_control_logic() {
let plc = Artifact::plc_project("p.xml", PlcFormat::PlcopenXml);
let t = target(TargetType::PlcSps, vec![plc]);
let plan = build_scan_plan(&t);
assert_eq!(plan.steps.len(), 1);
assert_eq!(plan.steps[0].scan_type, ScanType::PlcControlLogic);
assert_eq!(plan.steps[0].phase, ScanPhase::PlcAnalysis);
}
#[test]
fn disabled_scan_is_dropped_and_off_by_default_can_be_enabled() {
let mut t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
t.scan_config.disabled_scans = vec![ScanType::Lint];
// CodeReview is off by default for web; enable it explicitly.
t.scan_config.enabled_scans = vec![ScanType::CodeReview];
let plan = build_scan_plan(&t);
assert!(!plan.has(ScanType::Lint));
assert!(plan.has(ScanType::CodeReview));
assert!(plan.has(ScanType::Sast));
}
#[test]
fn no_code_artifact_yields_empty_plan_for_web() {
let t = target(TargetType::WebApp, vec![]);
let plan = build_scan_plan(&t);
assert!(plan.is_empty());
}
}
+2 -4
View File
@@ -25,9 +25,8 @@ impl TestServer {
let mongodb_uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// Unique db-name prefix per run. Must fit the pool's 30-char cap
// (`<prefix>_<32 hex>` <= 63), so use a 16-hex-char suffix.
let db_name = format!("t_{}", &uuid::Uuid::new_v4().simple().to_string()[..16]);
// Unique database name per test run to avoid collisions
let db_name = format!("test_{}", uuid::Uuid::new_v4().simple());
let db_pool = DatabasePool::connect(&mongodb_uri, &db_name)
.await
@@ -70,7 +69,6 @@ impl TestServer {
pentest_imap_password: None,
admin_api_token: None,
tenant_registry_url: None,
unified_pipeline: false,
};
let agent = ComplianceAgent::new(config, db_pool);
@@ -2,6 +2,5 @@ mod cascade_delete;
mod dast;
mod findings;
mod health;
mod onboarding;
mod repositories;
mod stats;
@@ -1,115 +0,0 @@
use crate::common::TestServer;
use serde_json::json;
#[tokio::test]
async fn create_list_and_applicable_scans() {
let server = TestServer::start().await;
// Initially empty.
let resp = server.get("/api/v1/targets").await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
// Create a web-app target with a git repo + a live URL.
let resp = server
.post(
"/api/v1/targets",
&json!({
"name": "acme-web",
"target_type": "web_app",
"artifacts": [
{ "kind": "git_repo", "source_ref": "https://git/acme.git", "branch": "main" },
{ "kind": "live_url", "source_ref": "https://acme.example.com" }
]
}),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
assert!(!id.is_empty());
assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 2);
// List returns it.
let resp = server.get("/api/v1/targets").await;
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 1);
// Applicable scans: SAST present + DAST offered (live URL present), pentest supported.
let resp = server
.get(&format!("/api/v1/targets/{id}/applicable-scans"))
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let scans = body["data"]["scans"].as_array().unwrap();
let names: Vec<&str> = scans.iter().filter_map(|s| s["scan"].as_str()).collect();
assert!(names.contains(&"sast"));
assert!(names.contains(&"dast"));
assert_eq!(body["data"]["pentest_supported"], true);
server.cleanup().await;
}
#[tokio::test]
async fn detect_classifies_a_plc_target() {
let server = TestServer::start().await;
// A PLC project artifact is a strong kind-based signal.
let resp = server
.post(
"/api/v1/targets",
&json!({
"name": "line-controller",
"target_type": "backend_service", // deliberately wrong; detect should suggest PLC
"artifacts": [
{ "kind": "plc_project", "source_ref": "line.xml", "plc_format": "plcopen_xml" }
]
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
let resp = server
.post(&format!("/api/v1/targets/{id}/detect"), &json!({}))
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"]["classification"]["suggested"], "plc_sps");
server.cleanup().await;
}
#[tokio::test]
async fn add_artifact_and_delete_target() {
let server = TestServer::start().await;
let resp = server
.post(
"/api/v1/targets",
&json!({ "name": "svc", "target_type": "backend_service" }),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
// Attach a git repo.
let resp = server
.post(
&format!("/api/v1/targets/{id}/artifacts"),
&json!({ "kind": "git_repo", "source_ref": "https://git/svc.git" }),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 1);
// Delete it.
let resp = server.delete(&format!("/api/v1/targets/{id}")).await;
assert_eq!(resp.status(), 200);
let resp = server.get(&format!("/api/v1/targets/{id}")).await;
assert_eq!(resp.status(), 404);
server.cleanup().await;
}
-4
View File
@@ -49,10 +49,6 @@ 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>,
/// When true, `run_scan` dispatches to the unified `run_target` pipeline
/// (reads `onboarded_targets`) instead of the legacy repository pipeline.
/// Env `UNIFIED_PIPELINE`. Defaults off during the transition.
pub unified_pipeline: bool,
}
#[derive(Clone, Debug, Serialize, Deserialize)]