refactor: rip out the legacy TrackedRepository / repositories path (#161)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 8m20s
CI / Deploy Dashboard (push) Successful in 3m13s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 2m7s

This commit was merged in pull request #161.
This commit is contained in:
2026-07-16 07:25:45 +00:00
parent 87f240b26f
commit a981311413
46 changed files with 386 additions and 2123 deletions
+12 -4
View File
@@ -146,7 +146,7 @@ pub async fn build_embeddings(
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match db
.repositories()
.onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
{
@@ -194,14 +194,22 @@ pub async fn build_embeddings(
}
};
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for embedding build");
return;
}
};
let view = crate::pipeline::repo_view::RepoView::from_target(&repo, code);
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
auth_token: repo.auth_token.clone(),
auth_username: repo.auth_username.clone(),
auth_token: view.auth_token.clone(),
auth_username: view.auth_username.clone(),
};
let git_ops =
crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds);
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) {
let repo_path = match git_ops.clone_or_fetch(&view.git_url, &view.name) {
Ok(p) => p,
Err(e) => {
tracing::error!("Failed to clone repo for embedding build: {e}");
+13 -5
View File
@@ -255,7 +255,7 @@ pub async fn get_file_content(
// Look up the repository to get repo name
let repo = db
.repositories()
.onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
@@ -317,7 +317,7 @@ pub async fn trigger_build(
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match db
.repositories()
.onboarded_targets()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
{
@@ -328,14 +328,22 @@ pub async fn trigger_build(
}
};
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for graph build");
return;
}
};
let view = crate::pipeline::repo_view::RepoView::from_target(&repo, code);
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
auth_token: repo.auth_token.clone(),
auth_username: repo.auth_username.clone(),
auth_token: view.auth_token.clone(),
auth_username: view.auth_username.clone(),
};
let git_ops =
crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds);
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) {
let repo_path = match git_ops.clone_or_fetch(&view.git_url, &view.name) {
Ok(p) => p,
Err(e) => {
tracing::error!("Failed to clone repo for graph build: {e}");
+13 -1
View File
@@ -10,6 +10,18 @@ pub async fn health() -> Json<serde_json::Value> {
Json(serde_json::json!({ "status": "ok" }))
}
/// GET /api/v1/settings/ssh-public-key — the agent's SSH deploy public key,
/// for adding as a read-only deploy key on private git targets.
#[tracing::instrument(skip_all)]
pub async fn get_ssh_public_key(
axum::extract::Extension(agent): AgentExt,
) -> Result<Json<serde_json::Value>, axum::http::StatusCode> {
let public_path = format!("{}.pub", agent.config.ssh_key_path);
let public_key =
std::fs::read_to_string(&public_path).map_err(|_| axum::http::StatusCode::NOT_FOUND)?;
Ok(Json(serde_json::json!({ "public_key": public_key.trim() })))
}
#[tracing::instrument(skip_all)]
pub async fn stats_overview(
axum::extract::Extension(agent): AgentExt,
@@ -19,7 +31,7 @@ pub async fn stats_overview(
let db = &db;
let total_repositories = db
.repositories()
.onboarded_targets()
.count_documents(doc! {})
.await
.unwrap_or(0);
-2
View File
@@ -12,7 +12,6 @@ pub mod notifications;
pub mod onboarding;
pub mod pentest_handlers;
pub use pentest_handlers as pentest;
pub mod repos;
pub mod sbom;
pub mod scans;
@@ -21,6 +20,5 @@ pub use dto::*;
pub use findings::*;
pub use health::*;
pub use issues::*;
pub use repos::*;
pub use sbom::*;
pub use scans::*;
+107 -6
View File
@@ -246,15 +246,116 @@ pub async fn delete_target(
.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;
// Cascade all data keyed by repo_id == target id (best-effort).
let db = &db;
let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.tracker_issues()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db.graph_nodes().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_edges().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_builds().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.impact_analyses()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.code_embeddings()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.embedding_builds()
.delete_many(doc! { "repo_id": &id })
.await;
// DAST targets linked to this target, and all their downstream data.
if let Ok(mut cursor) = db.dast_targets().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(dt)) = cursor.next().await {
let dast_target_id = dt.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !dast_target_id.is_empty() {
cascade_delete_dast_target(db, &dast_target_id).await;
}
}
}
// Pentest sessions linked directly to this target (not via a DAST target).
if let Ok(mut cursor) = db.pentest_sessions().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "repo_id": &id })
.await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// Delete a DAST target and everything downstream of it (pentest sessions +
/// their attack chains / messages / findings, DAST scan runs + findings).
async fn cascade_delete_dast_target(db: &crate::database::Database, target_id: &str) {
use futures_util::StreamExt;
if let Ok(mut cursor) = db
.pentest_sessions()
.find(doc! { "target_id": target_id })
.await
{
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_scan_runs()
.delete_many(doc! { "target_id": target_id })
.await;
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(target_id) {
let _ = db.dast_targets().delete_one(doc! { "_id": oid }).await;
}
}
/// POST /api/v1/targets/{id}/artifacts — attach an artifact (by reference).
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn add_artifact(
@@ -113,14 +113,14 @@ pub async fn create_session(
session.config = Some(config.clone());
session.repo_id = target.repo_id.clone();
// Resolve repo_id from git_repo_url if provided
// Resolve repo_id (target id) from git_repo_url if provided
if let Some(ref git_url) = config.git_repo_url {
if let Ok(Some(repo)) = db
.repositories()
.find_one(doc! { "git_url": git_url })
if let Ok(Some(target)) = db
.onboarded_targets()
.find_one(doc! { "artifacts.source_ref": git_url })
.await
{
session.repo_id = repo.id.map(|oid| oid.to_hex());
session.repo_id = target.id.map(|oid| oid.to_hex());
}
}
@@ -380,17 +380,20 @@ pub async fn lookup_repo(
) -> Result<Json<ApiResponse<serde_json::Value>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.repositories()
.find_one(doc! { "git_url": &params.url })
.onboarded_targets()
.find_one(doc! { "artifacts.source_ref": &params.url })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let data = match repo {
Some(r) => serde_json::json!({
"name": r.name,
"default_branch": r.default_branch,
"last_scanned_commit": r.last_scanned_commit,
}),
Some(r) => {
let git = r.code_artifact().and_then(|c| c.git.as_ref());
serde_json::json!({
"name": r.name,
"default_branch": git.map(|g| g.default_branch.clone()),
"last_scanned_commit": git.and_then(|g| g.last_scanned_commit.clone()),
})
}
None => serde_json::Value::Null,
};
-339
View File
@@ -1,339 +0,0 @@
use axum::extract::{Extension, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::*;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn list_repositories(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<TrackedRepository>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.repositories()
.count_documents(doc! {})
.await
.unwrap_or(0);
let repos = match db
.repositories()
.find(doc! {})
.skip(skip)
.limit(params.limit)
.await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!("Failed to fetch repositories: {e}");
Vec::new()
}
};
Ok(Json(ApiResponse {
data: repos,
total: Some(total),
page: Some(params.page),
}))
}
#[tracing::instrument(skip_all)]
pub async fn add_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<AddRepositoryRequest>,
) -> Result<Json<ApiResponse<TrackedRepository>>, (StatusCode, String)> {
// Validate repository access before saving
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent.config.ssh_key_path.clone()),
auth_token: req.auth_token.clone(),
auth_username: req.auth_username.clone(),
};
if let Err(e) = crate::pipeline::git::GitOps::test_access(&req.git_url, &creds) {
return Err((
StatusCode::BAD_REQUEST,
format!("Cannot access repository: {e}"),
));
}
let mut repo = TrackedRepository::new(req.name, req.git_url);
repo.default_branch = req.default_branch;
repo.auth_token = req.auth_token;
repo.auth_username = req.auth_username;
repo.tracker_type = req.tracker_type;
repo.tracker_owner = req.tracker_owner;
repo.tracker_repo = req.tracker_repo;
repo.tracker_token = req.tracker_token;
repo.scan_schedule = req.scan_schedule;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
db.repositories().insert_one(&repo).await.map_err(|_| {
(
StatusCode::CONFLICT,
"Repository already exists".to_string(),
)
})?;
Ok(Json(ApiResponse {
data: repo,
total: None,
page: None,
}))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn update_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateRepositoryRequest>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let mut set_doc = doc! { "updated_at": mongodb::bson::DateTime::now() };
if let Some(name) = &req.name {
set_doc.insert("name", name);
}
if let Some(branch) = &req.default_branch {
set_doc.insert("default_branch", branch);
}
if let Some(token) = &req.auth_token {
set_doc.insert("auth_token", token);
}
if let Some(username) = &req.auth_username {
set_doc.insert("auth_username", username);
}
if let Some(tracker_type) = &req.tracker_type {
set_doc.insert("tracker_type", tracker_type.to_string());
}
if let Some(owner) = &req.tracker_owner {
set_doc.insert("tracker_owner", owner);
}
if let Some(repo) = &req.tracker_repo {
set_doc.insert("tracker_repo", repo);
}
if let Some(token) = &req.tracker_token {
set_doc.insert("tracker_token", token);
}
if let Some(schedule) = &req.scan_schedule {
set_doc.insert("scan_schedule", schedule);
}
let result = db
.repositories()
.update_one(doc! { "_id": oid }, doc! { "$set": set_doc })
.await
.map_err(|e| {
tracing::warn!("Failed to update repository: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
if result.matched_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
Ok(Json(serde_json::json!({ "status": "updated" })))
}
#[tracing::instrument(skip_all)]
pub async fn get_ssh_public_key(
Extension(agent): AgentExt,
) -> Result<Json<serde_json::Value>, StatusCode> {
let public_path = format!("{}.pub", agent.config.ssh_key_path);
let public_key = std::fs::read_to_string(&public_path).map_err(|_| StatusCode::NOT_FOUND)?;
Ok(Json(serde_json::json!({ "public_key": public_key.trim() })))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn trigger_scan(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let agent_clone = (*agent).clone();
let tenant_id = tenant.0.tenant_id.clone();
tokio::spawn(async move {
if let Err(e) = agent_clone
.run_scan(&tenant_id, &id, ScanTrigger::Manual)
.await
{
tracing::error!("Manual scan failed for {id}: {e}");
}
});
Ok(Json(serde_json::json!({ "status": "scan_triggered" })))
}
/// Return the webhook secret for a repository (used by dashboard to display it)
pub async fn get_webhook_config(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.repositories()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let tracker_type = repo
.tracker_type
.as_ref()
.map(|t| t.to_string())
.unwrap_or_else(|| "gitea".to_string());
Ok(Json(serde_json::json!({
"webhook_secret": repo.webhook_secret,
"tracker_type": tracker_type,
})))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn delete_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
// Delete the repository
let result = db
.repositories()
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
if result.deleted_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
// Cascade delete all related data
let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.tracker_issues()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db.graph_nodes().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_edges().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_builds().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.impact_analyses()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.code_embeddings()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.embedding_builds()
.delete_many(doc! { "repo_id": &id })
.await;
// Cascade delete DAST targets linked to this repo, and all their downstream data
// (scan runs, findings, pentest sessions, attack chains, messages)
if let Ok(mut cursor) = db.dast_targets().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(target)) = cursor.next().await {
let target_id = target.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !target_id.is_empty() {
cascade_delete_dast_target(db, &target_id).await;
}
}
}
// Also delete pentest sessions linked directly to this repo (not via target)
if let Ok(mut cursor) = db.pentest_sessions().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
// Delete DAST findings produced by this session
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "repo_id": &id })
.await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// Cascade-delete a DAST target and all its downstream data.
async fn cascade_delete_dast_target(db: &crate::database::Database, target_id: &str) {
// Delete pentest sessions for this target (and their attack chains + messages)
if let Ok(mut cursor) = db
.pentest_sessions()
.find(doc! { "target_id": target_id })
.await
{
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "target_id": target_id })
.await;
// Delete DAST scan runs and their findings
let _ = db
.dast_findings()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_scan_runs()
.delete_many(doc! { "target_id": target_id })
.await;
// Delete the target itself
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(target_id) {
let _ = db.dast_targets().delete_one(doc! { "_id": oid }).await;
}
}
-14
View File
@@ -11,20 +11,6 @@ pub fn build_router() -> Router {
"/api/v1/settings/ssh-public-key",
get(handlers::get_ssh_public_key),
)
.route("/api/v1/repositories", get(handlers::list_repositories))
.route("/api/v1/repositories", post(handlers::add_repository))
.route(
"/api/v1/repositories/{id}/scan",
post(handlers::trigger_scan),
)
.route(
"/api/v1/repositories/{id}",
delete(handlers::delete_repository).patch(handlers::update_repository),
)
.route(
"/api/v1/repositories/{id}/webhook-config",
get(handlers::get_webhook_config),
)
// Unified onboarding targets (#131).
.route(
"/api/v1/targets",