Compare commits

..

3 Commits

Author SHA1 Message Date
Sharang Parnerkar 08c4ec4cff feat(m7.2-D): drop transitional agent.db, add admin helpers
CI / Check (pull_request) Successful in 9m27s
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
Final slice of M7.2. Removes the transitional single-database handle
that M7.2-A introduced alongside the pool, so the compliance-agent
now has a single source of truth for storage: every code path obtains
a tenant-scoped Database from `agent.db_pool.for_tenant_id(...)` or
`for_tenant(&ctx)`. There is no shared "default" database anywhere.

Changes
- ComplianceAgent: `db: Database` field removed. ComplianceAgent::new
  now takes only `(config, db_pool)`. Verified by an earlier grep
  during M7.2-C that no remaining call site reads `agent.db`.
- main.rs: stops constructing the legacy Database. Only the pool is
  built at startup.
- TestServer: same — drops Database::connect/ensure_indexes, builds
  only the pool. cleanup() now drops every `<db_name>_*` per-tenant
  database (no longer touches a bare `<db_name>`).
- DatabasePool::list_tenant_db_names() — lists Mongo databases
  matching the pool's prefix. For admin endpoints + scheduler tenant
  enumeration in a future M7.3 (this PR keeps SCHEDULER_TENANT_IDS
  env config — registry integration is a separate concern).
- DatabasePool::drop_tenant(&str) — idempotent tenant offboarding.
  Drops the per-tenant database and evicts the in-memory `ensured`
  marker so a later re-provision re-runs ensure_indexes.

Test plan
- cargo fmt --all clean
- cargo clippy --workspace --exclude compliance-dashboard
  -- -D warnings clean
- cargo test -p compliance-core --lib — 7 pass
- cargo test -p compliance-agent --lib — 228 pass
- cargo test -p compliance-agent --test tenant_isolation — 6 pass
  including new `admin_helpers_list_and_drop_tenant_dbs`
- cargo test -p compliance-agent --test tenant_status_middleware
  — 6 pass

M7.2 closeout state after this lands
- M7.1 (auth + status) — done
- M7.2-A (pool) — done
- M7.2-B (handlers) — done
- M7.2-C (background paths) — done
- M7.2-D (legacy db removed, admin helpers) — done (this PR)
- Future M7.3: scheduler pulls tenants from tenant-registry instead
  of SCHEDULER_TENANT_IDS env; cross-tenant admin HTTP endpoints
  built on list_tenant_db_names / drop_tenant.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-17 15:05:27 +02:00
Sharang Parnerkar 0f6dd1135e feat(m7.2-C): migrate background paths to per-tenant pool
CI / Check (pull_request) Successful in 10m33s
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
Closes the loop on M7.2 isolation for paths that don't have a JWT
context: scheduler, webhooks, and the agent's `run_scan` / `run_pr_review`
helpers all now take a `tenant_id` at the boundary and resolve to a
tenant-scoped `Database` via `db_pool.for_tenant_id(...)`. Internal
orchestrators (PipelineOrchestrator, PentestOrchestrator) and pipeline
helpers were already DB-agnostic — they take `db: Database` at
construction and don't care which tenant it points to.

Changes
- DatabasePool::for_tenant_id(&str) — same as for_tenant but accepts
  a bare tenant_id. Background paths don't have a full TenantContext.
  for_tenant is now a thin wrapper that delegates.
- agent.run_scan(tenant_id, repo_id, trigger) — pulls the tenant
  database before constructing the PipelineOrchestrator. Was:
  run_scan(repo_id, trigger) reading agent.db.
- agent.run_pr_review(tenant_id, repo_id, ...) — same shape.
- Webhook routes change: /webhook/{tenant_id}/{platform}/{repo_id}.
  Tenant is part of the URL path because webhooks arrive without a
  JWT — they're authenticated via per-repo HMAC, not the tenant gate.
  The dashboard surfaces the full per-tenant URL when the repo is
  registered. All three handlers (gitea, github, gitlab) updated.
- scheduler.rs — iterates tenants from $SCHEDULER_TENANT_IDS
  (comma-separated env), or DEV_TENANT_ID's `dev` default. Both
  scan_all_repos and monitor_cves now run once per configured
  tenant. M7.2-D will replace this static config with a pull from
  the tenant-registry.
- api/handlers/repos.rs::trigger_scan now passes tenant.0.tenant_id.

What's unchanged because it didn't need to change
- PipelineOrchestrator, PentestOrchestrator: take `db: Database` at
  construction — they're tenant-DB-agnostic by design. The caller
  picks the tenant DB.
- pipeline/{dedup,graph_build,issue_creation,sbom/mod}.rs,
  pentest/{context,report/html/*}.rs, trackers/jira.rs, llm/triage.rs:
  take `&Database` or `&mongodb::Database` as args, transitively
  tenant-scoped via the caller.

Test plan
- cargo fmt --all clean
- cargo clippy --workspace --exclude compliance-dashboard
  -- -D warnings clean
- cargo test -p compliance-core --lib — 7 pass
- cargo test -p compliance-agent --lib — 228 pass
- cargo test -p compliance-agent --test tenant_isolation — 5 pass
- cargo test -p compliance-agent --test tenant_status_middleware
  — 6 pass

What's left (PR-D)
- Drop the transitional agent.db field — no remaining call sites
  (verified by `grep -rn "agent\.db\b" compliance-agent/src`).
- main.rs / TestServer stop building the legacy Database; only the
  pool remains.
- Add cross-tenant admin helpers (list tenants, drop tenant DB) on
  the pool for offboarding flows.
- Pull tenants from the tenant-registry instead of an env var.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-17 15:00:37 +02:00
Sharang Parnerkar cdfbb62f9d feat(m7.2-B): migrate API handlers to per-tenant database pool
CI / Check (pull_request) Successful in 8m9s
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
Builds on PR M7.2-A. Every HTTP handler in compliance-agent/src/api/
now takes a TenantCtx extractor and pulls a tenant-scoped Database
from agent.db_pool.for_tenant(&ctx). The query bodies are unchanged —
`db.findings().find(doc! {...})` reads from the tenant's own physical
database, so the filter doc cannot leak data across tenants because
the wrong tenant's data is literally on a different db handle.

Changes
- New `dto::tenant_db(&agent, &tenant) -> Result<Database, StatusCode>`
  helper. Every migrated handler calls it at the top of the body
  instead of `let db = &agent.db;`. 500 on the rare pool failure;
  4xx auth failures are already handled by the M7.1 status gate.
- New `api::server::inject_dev_tenant` middleware mounted only when
  Keycloak is NOT configured. Synthesizes a TenantContext with
  tenant_id = $DEV_TENANT_ID (default `dev`) so `cargo run` against
  a bare Mongo + no KC still serves the API. Logged loudly as
  "DO NOT use in any environment with real customer data".
- Test harness: TestServer mounts inject_dev_tenant so existing E2E
  tests reach handlers; cleanup() now drops every <db_name>_*
  per-tenant database, not just the legacy <db_name>.

Files migrated (handler count, all pass `cargo build`):
- chat.rs (3) — also rewires RagPipeline + EmbeddingStore to the
  tenant DB's inner() so vector search is per-tenant
- dast.rs (5)
- findings.rs (5)
- graph.rs (7) — also rewires GraphStore inside trigger_build's
  spawn to the tenant DB
- health.rs (1) — stats_overview migrated; public /health stays
  un-scoped
- issues.rs (1)
- notifications.rs (5)
- pentest_handlers/session.rs (12) — both wizard + legacy paths,
  plus pause/resume/stop/get_attack_chain/get_messages/
  get_session_findings/lookup_repo. PentestOrchestrator now gets
  the tenant DB clone in its spawn.
- pentest_handlers/export.rs (1) — fans out across sessions,
  attack_chain_nodes, dast_findings, findings, sbom_entries,
  graph_nodes from a single tenant_db acquisition
- pentest_handlers/stats.rs (1)
- pentest_handlers/stream.rs (1) — SSE handler verifies session
  via the tenant DB before subscribing
- repos.rs (6)
- sbom.rs (5)
- scans.rs (1)

help_chat.rs has no DB queries and was skipped.

Test plan
- cargo fmt --all clean
- cargo clippy --workspace --exclude compliance-dashboard
  -- -D warnings clean
- cargo test -p compliance-core --lib — 7 pass
- cargo test -p compliance-agent --lib — 228 pass
- cargo test -p compliance-agent --test tenant_isolation — 5 pass
  (driver-level isolation still holds post-handler migration)
- cargo test -p compliance-agent --test tenant_status_middleware
  — 6 pass

What's not yet migrated (PR-C / PR-D)
- scheduler.rs (6 sites), pipeline/orchestrator.rs (14),
  pentest/orchestrator.rs (13), webhooks (gitea/github/gitlab),
  trackers/jira.rs, pipeline/dedup.rs etc. — background paths
  without a JWT-derived tenant context.
- agent.db is still in the ComplianceAgent struct as a transitional
  handle for those paths. PR-D removes it once PR-C migrates the
  background paths.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-17 13:28:33 +02:00
26 changed files with 628 additions and 273 deletions
+14 -23
View File
@@ -6,7 +6,7 @@ use tokio::sync::{broadcast, watch, Semaphore};
use compliance_core::models::pentest::PentestEvent;
use compliance_core::AgentConfig;
use crate::database::{Database, DatabasePool};
use crate::database::DatabasePool;
use crate::llm::LlmClient;
use crate::pipeline::orchestrator::PipelineOrchestrator;
@@ -16,12 +16,9 @@ const DEFAULT_MAX_CONCURRENT_SESSIONS: usize = 5;
#[derive(Clone)]
pub struct ComplianceAgent {
pub config: AgentConfig,
/// Transitional single-database handle. Used by handlers that have
/// not yet been migrated to `db_pool.for_tenant(&ctx)` (M7.2-B/C).
/// Will be removed once every call site is tenant-scoped (M7.2-D).
pub db: Database,
/// Per-tenant Mongo broker introduced in M7.2-A. Handlers should
/// prefer this and obtain a tenant-scoped [`Database`] from it.
/// Per-tenant Mongo broker. Every code path must obtain a
/// tenant-scoped [`crate::database::Database`] from this pool —
/// there is no single shared database any more.
pub db_pool: DatabasePool,
pub llm: Arc<LlmClient>,
pub http: reqwest::Client,
@@ -34,7 +31,7 @@ pub struct ComplianceAgent {
}
impl ComplianceAgent {
pub fn new(config: AgentConfig, db: Database, db_pool: DatabasePool) -> Self {
pub fn new(config: AgentConfig, db_pool: DatabasePool) -> Self {
let llm = Arc::new(LlmClient::new(
config.litellm_url.clone(),
config.litellm_api_key.clone(),
@@ -48,7 +45,6 @@ impl ComplianceAgent {
.unwrap_or_default();
Self {
config,
db,
db_pool,
llm,
http,
@@ -60,28 +56,27 @@ impl ComplianceAgent {
pub async fn run_scan(
&self,
tenant_id: &str,
repo_id: &str,
trigger: compliance_core::models::ScanTrigger,
) -> Result<(), crate::error::AgentError> {
let orchestrator = PipelineOrchestrator::new(
self.config.clone(),
self.db.clone(),
self.llm.clone(),
self.http.clone(),
);
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());
orchestrator.run(repo_id, trigger).await
}
/// Run a PR review: scan the diff and post review comments.
pub async fn run_pr_review(
&self,
tenant_id: &str,
repo_id: &str,
pr_number: u64,
base_sha: &str,
head_sha: &str,
) -> Result<(), crate::error::AgentError> {
let repo = self
.db
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let repo = db
.repositories()
.find_one(mongodb::bson::doc! {
"_id": mongodb::bson::oid::ObjectId::parse_str(repo_id)
@@ -92,12 +87,8 @@ impl ComplianceAgent {
crate::error::AgentError::Other(format!("Repository {repo_id} not found"))
})?;
let orchestrator = PipelineOrchestrator::new(
self.config.clone(),
self.db.clone(),
self.llm.clone(),
self.http.clone(),
);
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
orchestrator
.run_pr_review(&repo, repo_id, pr_number, base_sha, head_sha)
.await
+30 -26
View File
@@ -7,11 +7,13 @@ use mongodb::bson::doc;
use compliance_core::models::chat::{ChatRequest, ChatResponse, SourceReference};
use compliance_core::models::embedding::EmbeddingBuildRun;
use compliance_core::tenant_ctx::TenantCtx;
use compliance_graph::graph::embedding_store::EmbeddingStore;
use crate::agent::ComplianceAgent;
use crate::rag::pipeline::RagPipeline;
use super::dto::tenant_db;
use super::ApiResponse;
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -20,10 +22,12 @@ type AgentExt = Extension<Arc<ComplianceAgent>>;
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn chat(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
Json(req): Json<ChatRequest>,
) -> Result<Json<ApiResponse<ChatResponse>>, StatusCode> {
let pipeline = RagPipeline::new(agent.llm.clone(), agent.db.inner());
let db = tenant_db(&agent, &tenant).await?;
let pipeline = RagPipeline::new(agent.llm.clone(), db.inner());
// Step 1: Embed the user's message
let query_vectors = agent
@@ -133,12 +137,15 @@ pub async fn chat(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn build_embeddings(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
// Resolve the tenant DB up front so we can move it into the spawn;
// the JWT/dev context isn't available inside detached tasks.
let db = tenant_db(&agent, &tenant).await?;
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match agent_clone
.db
let repo = match db
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
@@ -151,8 +158,7 @@ pub async fn build_embeddings(
};
// Get latest graph build
let build = match agent_clone
.db
let build = match db
.graph_builds()
.find_one(doc! { "repo_id": &repo_id })
.sort(doc! { "started_at": -1 })
@@ -171,26 +177,22 @@ pub async fn build_embeddings(
.unwrap_or_else(|| "unknown".to_string());
// Get nodes
let nodes: Vec<compliance_core::models::graph::CodeNode> = match agent_clone
.db
.graph_nodes()
.find(doc! { "repo_id": &repo_id })
.await
{
Ok(cursor) => {
use futures_util::StreamExt;
let mut items = Vec::new();
let mut cursor = cursor;
while let Some(Ok(item)) = cursor.next().await {
items.push(item);
let nodes: Vec<compliance_core::models::graph::CodeNode> =
match db.graph_nodes().find(doc! { "repo_id": &repo_id }).await {
Ok(cursor) => {
use futures_util::StreamExt;
let mut items = Vec::new();
let mut cursor = cursor;
while let Some(Ok(item)) = cursor.next().await {
items.push(item);
}
items
}
items
}
Err(e) => {
tracing::error!("[{repo_id}] Failed to fetch nodes: {e}");
return;
}
};
Err(e) => {
tracing::error!("[{repo_id}] Failed to fetch nodes: {e}");
return;
}
};
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
@@ -207,7 +209,7 @@ pub async fn build_embeddings(
}
};
let pipeline = RagPipeline::new(agent_clone.llm.clone(), agent_clone.db.inner());
let pipeline = RagPipeline::new(agent_clone.llm.clone(), db.inner());
match pipeline
.build_embeddings(&repo_id, &repo_path, &graph_build_id, &nodes)
.await
@@ -234,9 +236,11 @@ pub async fn build_embeddings(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn embedding_status(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<ApiResponse<Option<EmbeddingBuildRun>>>, StatusCode> {
let store = EmbeddingStore::new(agent.db.inner());
let db = tenant_db(&agent, &tenant).await?;
let store = EmbeddingStore::new(db.inner());
let build = store.get_latest_build(&repo_id).await.map_err(|e| {
tracing::error!("Failed to get embedding status: {e}");
StatusCode::INTERNAL_SERVER_ERROR
+20 -11
View File
@@ -7,9 +7,11 @@ use mongodb::bson::doc;
use serde::Deserialize;
use compliance_core::models::dast::{DastFinding, DastScanRun, DastTarget, DastTargetType};
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::dto::tenant_db;
use super::{collect_cursor_async, ApiResponse, PaginationParams};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -45,9 +47,11 @@ fn default_rate_limit() -> u32 {
#[tracing::instrument(skip_all)]
pub async fn list_targets(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<DastTarget>>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.dast_targets()
@@ -80,6 +84,7 @@ pub async fn list_targets(
#[tracing::instrument(skip_all)]
pub async fn add_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<AddTargetRequest>,
) -> Result<Json<ApiResponse<DastTarget>>, StatusCode> {
let mut target = DastTarget::new(req.name, req.base_url, req.target_type);
@@ -89,9 +94,8 @@ pub async fn add_target(
target.rate_limit = req.rate_limit;
target.allow_destructive = req.allow_destructive;
agent
.db
.dast_targets()
let db = tenant_db(&agent, &tenant).await?;
db.dast_targets()
.insert_one(&target)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
@@ -107,19 +111,19 @@ pub async fn add_target(
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn trigger_scan(
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 target = agent
.db
let target = db
.dast_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let db = agent.db.clone();
tokio::spawn(async move {
let orchestrator = compliance_dast::DastOrchestrator::new(100);
match orchestrator.run_scan(&target, Vec::new()).await {
@@ -147,9 +151,11 @@ pub async fn trigger_scan(
#[tracing::instrument(skip_all)]
pub async fn list_scan_runs(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<DastScanRun>>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.dast_scan_runs()
@@ -183,9 +189,11 @@ pub async fn list_scan_runs(
#[tracing::instrument(skip_all)]
pub async fn list_findings(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<DastFinding>>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.dast_findings()
@@ -219,12 +227,13 @@ pub async fn list_findings(
#[tracing::instrument(skip_all, fields(finding_id = %id))]
pub async fn get_finding(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<DastFinding>>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let finding = agent
.db
let finding = db
.dast_findings()
.find_one(doc! { "_id": oid })
.await
+21
View File
@@ -180,6 +180,27 @@ pub struct SbomVersionDiff {
pub(crate) type AgentExt = axum::extract::Extension<std::sync::Arc<crate::agent::ComplianceAgent>>;
pub(crate) type ApiResult<T> = Result<axum::Json<ApiResponse<T>>, axum::http::StatusCode>;
/// Resolve a tenant-scoped [`Database`] from the request's
/// [`TenantContext`] (inserted by the M7.1 JWT middleware, or by the
/// dev fallback in unsecured environments). The pool ensures the
/// tenant's indexes idempotently.
///
/// Returns 500 on the rare path where Mongo refuses the database
/// handle — the M7.1 auth/status middleware already rejects every
/// other failure mode with 4xx before we get here.
pub(crate) async fn tenant_db(
agent: &crate::agent::ComplianceAgent,
tenant: &compliance_core::tenant_ctx::TenantCtx,
) -> Result<crate::database::Database, axum::http::StatusCode> {
agent.db_pool.for_tenant(&tenant.0).await.map_err(|e| {
tracing::error!(
tenant_id = %tenant.0.tenant_id,
"Failed to acquire tenant database: {e}"
);
axum::http::StatusCode::INTERNAL_SERVER_ERROR
})
}
pub(crate) async fn collect_cursor_async<T: serde::de::DeserializeOwned + Unpin + Send>(
mut cursor: mongodb::Cursor<T>,
) -> Vec<T> {
+16 -11
View File
@@ -5,13 +5,16 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::Finding;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all, fields(repo_id = ?filter.repo_id, severity = ?filter.severity, scan_type = ?filter.scan_type))]
pub async fn list_findings(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(filter): Query<FindingsFilter>,
) -> ApiResult<Vec<Finding>> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let mut query = doc! {};
if let Some(repo_id) = &filter.repo_id {
query.insert("repo_id", repo_id);
@@ -81,11 +84,12 @@ pub async fn list_findings(
#[tracing::instrument(skip_all, fields(finding_id = %id))]
pub async fn get_finding(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<Finding>>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let finding = agent
.db
let db = tenant_db(&agent, &tenant).await?;
let finding = db
.findings()
.find_one(doc! { "_id": oid })
.await
@@ -102,14 +106,14 @@ pub async fn get_finding(
#[tracing::instrument(skip_all, fields(finding_id = %id))]
pub async fn update_finding_status(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateStatusRequest>,
) -> 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?;
agent
.db
.findings()
db.findings()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "status": &req.status, "updated_at": mongodb::bson::DateTime::now() } },
@@ -123,6 +127,7 @@ pub async fn update_finding_status(
#[tracing::instrument(skip_all)]
pub async fn bulk_update_finding_status(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<BulkUpdateStatusRequest>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oids: Vec<mongodb::bson::oid::ObjectId> = req
@@ -135,8 +140,8 @@ pub async fn bulk_update_finding_status(
return Err(StatusCode::BAD_REQUEST);
}
let result = agent
.db
let db = tenant_db(&agent, &tenant).await?;
let result = db
.findings()
.update_many(
doc! { "_id": { "$in": oids } },
@@ -153,14 +158,14 @@ pub async fn bulk_update_finding_status(
#[tracing::instrument(skip_all)]
pub async fn update_finding_feedback(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateFeedbackRequest>,
) -> 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?;
agent
.db
.findings()
db.findings()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "developer_feedback": &req.feedback, "updated_at": mongodb::bson::DateTime::now() } },
+24 -10
View File
@@ -7,9 +7,11 @@ use mongodb::bson::doc;
use serde::{Deserialize, Serialize};
use compliance_core::models::graph::{CodeEdge, CodeNode, GraphBuildRun, ImpactAnalysis};
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::dto::tenant_db;
use super::{collect_cursor_async, ApiResponse};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -36,9 +38,11 @@ fn default_search_limit() -> usize {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn get_graph(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<ApiResponse<GraphData>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
// Get latest build
let build: Option<GraphBuildRun> = db
@@ -98,9 +102,11 @@ pub async fn get_graph(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn get_nodes(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<ApiResponse<Vec<CodeNode>>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let filter = doc! { "repo_id": &repo_id };
let nodes: Vec<CodeNode> = match db.graph_nodes().find(filter).await {
@@ -123,9 +129,11 @@ pub async fn get_nodes(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn get_communities(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<ApiResponse<Vec<CommunityInfo>>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let filter = doc! { "repo_id": &repo_id };
let nodes: Vec<CodeNode> = match db.graph_nodes().find(filter).await {
@@ -176,9 +184,11 @@ pub struct CommunityInfo {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, finding_id = %finding_id))]
pub async fn get_impact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path((repo_id, finding_id)): Path<(String, String)>,
) -> Result<Json<ApiResponse<Option<ImpactAnalysis>>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let filter = doc! { "repo_id": &repo_id, "finding_id": &finding_id };
let impact = db
@@ -198,10 +208,12 @@ pub async fn get_impact(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, query = %params.q))]
pub async fn search_symbols(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
Query(params): Query<SearchParams>,
) -> Result<Json<ApiResponse<Vec<CodeNode>>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
// Simple text search on qualified_name and name fields
let filter = doc! {
@@ -234,10 +246,12 @@ pub async fn search_symbols(
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn get_file_content(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
Query(params): Query<FileContentParams>,
) -> Result<Json<ApiResponse<FileContent>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
// Look up the repository to get repo name
let repo = db
@@ -296,12 +310,13 @@ pub struct FileContent {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub async fn trigger_build(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(repo_id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match agent_clone
.db
let repo = match db
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
@@ -333,8 +348,7 @@ pub async fn trigger_build(
match engine.build_graph(&repo_path, &repo_id, &graph_build_id) {
Ok((code_graph, build_run)) => {
let store =
compliance_graph::graph::persistence::GraphStore::new(agent_clone.db.inner());
let store = compliance_graph::graph::persistence::GraphStore::new(db.inner());
let _ = store.delete_repo_graph(&repo_id).await;
let _ = store
.store_graph(&build_run, &code_graph.nodes, &code_graph.edges)
+7 -2
View File
@@ -3,6 +3,7 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::ScanRun;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn health() -> Json<serde_json::Value> {
@@ -10,8 +11,12 @@ pub async fn health() -> Json<serde_json::Value> {
}
#[tracing::instrument(skip_all)]
pub async fn stats_overview(axum::extract::Extension(agent): AgentExt) -> ApiResult<OverviewStats> {
let db = &agent.db;
pub async fn stats_overview(
axum::extract::Extension(agent): AgentExt,
tenant: TenantCtx,
) -> ApiResult<OverviewStats> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let total_repositories = db
.repositories()
+4 -1
View File
@@ -4,13 +4,16 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::TrackerIssue;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn list_issues(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<TrackerIssue>> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.tracker_issues()
@@ -5,15 +5,18 @@ use mongodb::bson::doc;
use serde::Deserialize;
use compliance_core::models::notification::CveNotification;
use compliance_core::tenant_ctx::TenantCtx;
use super::dto::{AgentExt, ApiResponse};
use super::dto::{tenant_db, AgentExt, ApiResponse};
/// GET /api/v1/notifications — List CVE notifications (newest first)
#[tracing::instrument(skip_all)]
pub async fn list_notifications(
Extension(agent): AgentExt,
tenant: TenantCtx,
axum::extract::Query(params): axum::extract::Query<NotificationFilter>,
) -> Result<Json<ApiResponse<Vec<CveNotification>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let mut filter = doc! {};
// Filter by status (default: show new + read, exclude dismissed)
@@ -41,15 +44,13 @@ pub async fn list_notifications(
let limit = params.limit.unwrap_or(50).min(200);
let skip = (page - 1) * limit as u64;
let total = agent
.db
let total = db
.cve_notifications()
.count_documents(filter.clone())
.await
.unwrap_or(0);
let notifications: Vec<CveNotification> = match agent
.db
let notifications: Vec<CveNotification> = match db
.cve_notifications()
.find(filter)
.sort(doc! { "created_at": -1 })
@@ -83,9 +84,10 @@ pub async fn list_notifications(
#[tracing::instrument(skip_all)]
pub async fn notification_count(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<serde_json::Value>, StatusCode> {
let count = agent
.db
let db = tenant_db(&agent, &tenant).await?;
let count = db
.cve_notifications()
.count_documents(doc! { "status": "new" })
.await
@@ -98,12 +100,13 @@ pub async fn notification_count(
#[tracing::instrument(skip_all, fields(id = %id))]
pub async fn mark_read(
Extension(agent): AgentExt,
tenant: TenantCtx,
axum::extract::Path(id): axum::extract::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 result = agent
.db
let result = db
.cve_notifications()
.update_one(
doc! { "_id": oid },
@@ -125,12 +128,13 @@ pub async fn mark_read(
#[tracing::instrument(skip_all, fields(id = %id))]
pub async fn dismiss_notification(
Extension(agent): AgentExt,
tenant: TenantCtx,
axum::extract::Path(id): axum::extract::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 result = agent
.db
let result = db
.cve_notifications()
.update_one(
doc! { "_id": oid },
@@ -149,9 +153,10 @@ pub async fn dismiss_notification(
#[tracing::instrument(skip_all)]
pub async fn mark_all_read(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<serde_json::Value>, StatusCode> {
let result = agent
.db
let db = tenant_db(&agent, &tenant).await?;
let result = db
.cve_notifications()
.update_many(
doc! { "status": "new" },
@@ -13,10 +13,11 @@ use compliance_core::models::dast::DastFinding;
use compliance_core::models::finding::Finding;
use compliance_core::models::pentest::*;
use compliance_core::models::sbom::SbomEntry;
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::super::dto::collect_cursor_async;
use super::super::dto::{collect_cursor_async, tenant_db};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -35,11 +36,15 @@ pub struct ExportBody {
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn export_session_report(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(body): Json<ExportBody>,
) -> Result<axum::response::Response, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
if body.password.len() < 8 {
return Err((
@@ -49,8 +54,7 @@ pub async fn export_session_report(
}
// Fetch session
let session = agent
.db
let session = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -64,9 +68,7 @@ pub async fn export_session_report(
// Resolve target name
let target = if let Ok(tid) = mongodb::bson::oid::ObjectId::parse_str(&session.target_id) {
agent
.db
.dast_targets()
db.dast_targets()
.find_one(doc! { "_id": tid })
.await
.ok()
@@ -84,8 +86,7 @@ pub async fn export_session_report(
.unwrap_or_default();
// Fetch attack chain nodes
let nodes: Vec<AttackChainNode> = match agent
.db
let nodes: Vec<AttackChainNode> = match db
.attack_chain_nodes()
.find(doc! { "session_id": &id })
.sort(doc! { "started_at": 1 })
@@ -96,8 +97,7 @@ pub async fn export_session_report(
};
// Fetch DAST findings for this session, then deduplicate
let raw_findings: Vec<DastFinding> = match agent
.db
let raw_findings: Vec<DastFinding> = match db
.dast_findings()
.find(doc! { "session_id": &id })
.sort(doc! { "severity": -1, "created_at": -1 })
@@ -122,8 +122,7 @@ pub async fn export_session_report(
.or_else(|| target.as_ref().and_then(|t| t.repo_id.clone()));
let (sast_findings, sbom_entries, code_context) = if let Some(ref rid) = repo_id {
let sast: Vec<Finding> = match agent
.db
let sast: Vec<Finding> = match db
.findings()
.find(doc! {
"repo_id": rid,
@@ -143,8 +142,7 @@ pub async fn export_session_report(
Err(_) => Vec::new(),
};
let sbom: Vec<SbomEntry> = match agent
.db
let sbom: Vec<SbomEntry> = match db
.sbom_entries()
.find(doc! {
"repo_id": rid,
@@ -164,8 +162,7 @@ pub async fn export_session_report(
};
// Build code context from graph nodes
let code_ctx: Vec<CodeContextHint> = match agent
.db
let code_ctx: Vec<CodeContextHint> = match db
.graph_nodes()
.find(doc! { "repo_id": rid, "is_entry_point": true })
.limit(50)
@@ -7,11 +7,12 @@ use mongodb::bson::doc;
use serde::Deserialize;
use compliance_core::models::pentest::*;
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use crate::pentest::PentestOrchestrator;
use super::super::dto::{collect_cursor_async, ApiResponse, PaginationParams};
use super::super::dto::{collect_cursor_async, tenant_db, ApiResponse, PaginationParams};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -43,6 +44,7 @@ pub struct LookupRepoQuery {
#[tracing::instrument(skip_all)]
pub async fn create_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateSessionRequest>,
) -> Result<Json<ApiResponse<PentestSession>>, (StatusCode, String)> {
// Try to acquire a concurrency permit
@@ -57,6 +59,10 @@ pub async fn create_session(
)
})?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
if let Some(ref config) = req.config {
// ── Wizard path ──────────────────────────────────────────────
if !config.disclaimer_accepted {
@@ -67,8 +73,7 @@ pub async fn create_session(
}
// Look up or auto-create DastTarget by app_url
let target = match agent
.db
let target = match db
.dast_targets()
.find_one(doc! { "base_url": &config.app_url })
.await
@@ -87,7 +92,7 @@ pub async fn create_session(
}
t.allow_destructive = config.allow_destructive;
t.excluded_paths = config.scope_exclusions.clone();
let res = agent.db.dast_targets().insert_one(&t).await.map_err(|e| {
let res = db.dast_targets().insert_one(&t).await.map_err(|e| {
(
StatusCode::INTERNAL_SERVER_ERROR,
format!("Failed to create target: {e}"),
@@ -110,8 +115,7 @@ pub async fn create_session(
// Resolve repo_id from git_repo_url if provided
if let Some(ref git_url) = config.git_repo_url {
if let Ok(Some(repo)) = agent
.db
if let Ok(Some(repo)) = db
.repositories()
.find_one(doc! { "git_url": git_url })
.await
@@ -120,8 +124,7 @@ pub async fn create_session(
}
}
let insert_result = agent
.db
let insert_result = db
.pentest_sessions()
.insert_one(&session)
.await
@@ -212,8 +215,7 @@ pub async fn create_session(
// Persist encrypted credentials to DB
if session_for_task.config.is_some() {
if let Some(sid) = session.id {
let _ = agent
.db
let _ = db
.pentest_sessions()
.update_one(
doc! { "_id": sid },
@@ -245,12 +247,13 @@ pub async fn create_session(
});
let llm = agent.llm.clone();
let db = agent.db.clone();
let db_for_orchestrator = db.clone();
let session_clone = session.clone();
let target_clone = target.clone();
let agent_ref = agent.clone();
tokio::spawn(async move {
let orchestrator = PentestOrchestrator::new(llm, db, event_tx, Some(pause_rx));
let orchestrator =
PentestOrchestrator::new(llm, db_for_orchestrator, event_tx, Some(pause_rx));
orchestrator
.run_session_guarded(&session_clone, &target_clone, &initial_message)
.await;
@@ -292,8 +295,7 @@ pub async fn create_session(
)
})?;
let target = agent
.db
let target = db
.dast_targets()
.find_one(doc! { "_id": oid })
.await
@@ -310,8 +312,7 @@ pub async fn create_session(
let mut session = PentestSession::new(target_id, strategy);
session.repo_id = target.repo_id.clone();
let insert_result = agent
.db
let insert_result = db
.pentest_sessions()
.insert_one(&session)
.await
@@ -338,12 +339,13 @@ pub async fn create_session(
});
let llm = agent.llm.clone();
let db = agent.db.clone();
let db_for_orchestrator = db.clone();
let session_clone = session.clone();
let target_clone = target.clone();
let agent_ref = agent.clone();
tokio::spawn(async move {
let orchestrator = PentestOrchestrator::new(llm, db, event_tx, Some(pause_rx));
let orchestrator =
PentestOrchestrator::new(llm, db_for_orchestrator, event_tx, Some(pause_rx));
orchestrator
.run_session_guarded(&session_clone, &target_clone, &initial_message)
.await;
@@ -373,10 +375,11 @@ fn parse_strategy(s: &str) -> PentestStrategy {
#[tracing::instrument(skip_all)]
pub async fn lookup_repo(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<LookupRepoQuery>,
) -> Result<Json<ApiResponse<serde_json::Value>>, StatusCode> {
let repo = agent
.db
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.repositories()
.find_one(doc! { "git_url": &params.url })
.await
@@ -402,9 +405,11 @@ pub async fn lookup_repo(
#[tracing::instrument(skip_all)]
pub async fn list_sessions(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<PentestSession>>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.pentest_sessions()
@@ -438,12 +443,13 @@ pub async fn list_sessions(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn get_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<PentestSession>>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let mut session = agent
.db
let mut session = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -471,15 +477,18 @@ pub async fn get_session(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn send_message(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<SendMessageRequest>,
) -> Result<Json<ApiResponse<PentestMessage>>, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
// Verify session exists and is running
let session = agent
.db
let session = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -506,8 +515,7 @@ pub async fn send_message(
)
})?;
let target = agent
.db
let target = db
.dast_targets()
.find_one(doc! { "_id": target_oid })
.await
@@ -527,13 +535,13 @@ pub async fn send_message(
// Store user message
let session_id = id.clone();
let user_msg = PentestMessage::user(session_id.clone(), req.message.clone());
let _ = agent.db.pentest_messages().insert_one(&user_msg).await;
let _ = db.pentest_messages().insert_one(&user_msg).await;
let response_msg = user_msg.clone();
// Spawn orchestrator to continue the session
let llm = agent.llm.clone();
let db = agent.db.clone();
let db_for_orchestrator = db.clone();
let message = req.message.clone();
// Use existing broadcast sender if available, otherwise create a new one
@@ -548,7 +556,7 @@ pub async fn send_message(
.unwrap_or_else(|| agent.register_session_stream(&session_id));
tokio::spawn(async move {
let orchestrator = PentestOrchestrator::new(llm, db, event_tx, None);
let orchestrator = PentestOrchestrator::new(llm, db_for_orchestrator, event_tx, None);
orchestrator
.run_session_guarded(&session, &target, &message)
.await;
@@ -565,13 +573,16 @@ pub async fn send_message(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn stop_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<PentestSession>>, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
let session = agent
.db
let session = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -590,9 +601,7 @@ pub async fn stop_session(
));
}
agent
.db
.pentest_sessions()
db.pentest_sessions()
.update_one(
doc! { "_id": oid },
doc! { "$set": {
@@ -612,8 +621,7 @@ pub async fn stop_session(
// Clean up session resources
agent.cleanup_session(&id);
let updated = agent
.db
let updated = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -641,13 +649,16 @@ pub async fn stop_session(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn pause_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<serde_json::Value>>, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
let session = agent
.db
let session = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -684,13 +695,16 @@ pub async fn pause_session(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn resume_session(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<serde_json::Value>>, (StatusCode, String)> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
let session = agent
.db
let session = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -727,12 +741,13 @@ pub async fn resume_session(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn get_attack_chain(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<Vec<AttackChainNode>>>, StatusCode> {
let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let nodes = match agent
.db
let nodes = match db
.attack_chain_nodes()
.find(doc! { "session_id": &id })
.sort(doc! { "started_at": 1 })
@@ -757,21 +772,21 @@ pub async fn get_attack_chain(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn get_messages(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<PentestMessage>>>, StatusCode> {
let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = agent
.db
let total = db
.pentest_messages()
.count_documents(doc! { "session_id": &id })
.await
.unwrap_or(0);
let messages = match agent
.db
let messages = match db
.pentest_messages()
.find(doc! { "session_id": &id })
.sort(doc! { "created_at": 1 })
@@ -797,21 +812,21 @@ pub async fn get_messages(
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn get_session_findings(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<compliance_core::models::dast::DastFinding>>>, StatusCode> {
let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = agent
.db
let total = db
.dast_findings()
.count_documents(doc! { "session_id": &id })
.await
.unwrap_or(0);
let findings = match agent
.db
let findings = match db
.dast_findings()
.find(doc! { "session_id": &id })
.sort(doc! { "created_at": -1 })
@@ -6,10 +6,11 @@ use axum::Json;
use mongodb::bson::doc;
use compliance_core::models::pentest::*;
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::super::dto::{collect_cursor_async, ApiResponse};
use super::super::dto::{collect_cursor_async, tenant_db, ApiResponse};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -17,8 +18,10 @@ type AgentExt = Extension<Arc<ComplianceAgent>>;
#[tracing::instrument(skip_all)]
pub async fn pentest_stats(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<ApiResponse<PentestStats>>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let running_sessions = db
.pentest_sessions()
@@ -11,10 +11,11 @@ use tokio_stream::wrappers::BroadcastStream;
use tokio_stream::StreamExt;
use compliance_core::models::pentest::*;
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use super::super::dto::collect_cursor_async;
use super::super::dto::{collect_cursor_async, tenant_db};
type AgentExt = Extension<Arc<ComplianceAgent>>;
@@ -25,13 +26,14 @@ type AgentExt = Extension<Arc<ComplianceAgent>>;
#[tracing::instrument(skip_all, fields(session_id = %id))]
pub async fn session_stream(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Sse<impl futures_util::Stream<Item = Result<Event, Infallible>>>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
// Verify session exists
let _session = agent
.db
let _session = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
@@ -43,8 +45,7 @@ pub async fn session_stream(
let mut initial_events: Vec<Result<Event, Infallible>> = Vec::new();
// Fetch recent messages for this session
let messages: Vec<PentestMessage> = match agent
.db
let messages: Vec<PentestMessage> = match db
.pentest_messages()
.find(doc! { "session_id": &id })
.sort(doc! { "created_at": 1 })
@@ -56,8 +57,7 @@ pub async fn session_stream(
};
// Fetch recent attack chain nodes
let nodes: Vec<AttackChainNode> = match agent
.db
let nodes: Vec<AttackChainNode> = match db
.attack_chain_nodes()
.find(doc! { "session_id": &id })
.sort(doc! { "started_at": 1 })
@@ -94,8 +94,7 @@ pub async fn session_stream(
}
// Add current session status event
let session = agent
.db
let session = db
.pentest_sessions()
.find_one(doc! { "_id": oid })
.await
+28 -17
View File
@@ -5,13 +5,16 @@ 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 = &agent.db;
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()
@@ -43,6 +46,7 @@ pub async fn list_repositories(
#[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
@@ -69,17 +73,15 @@ pub async fn add_repository(
repo.tracker_token = req.tracker_token;
repo.scan_schedule = req.scan_schedule;
agent
.db
.repositories()
.insert_one(&repo)
let db = tenant_db(&agent, &tenant)
.await
.map_err(|_| {
(
StatusCode::CONFLICT,
"Repository already exists".to_string(),
)
})?;
.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,
@@ -91,10 +93,12 @@ pub async fn add_repository(
#[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() };
@@ -126,8 +130,7 @@ pub async fn update_repository(
set_doc.insert("scan_schedule", schedule);
}
let result = agent
.db
let result = db
.repositories()
.update_one(doc! { "_id": oid }, doc! { "$set": set_doc })
.await
@@ -155,11 +158,16 @@ pub async fn get_ssh_public_key(
#[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(&id, ScanTrigger::Manual).await {
if let Err(e) = agent_clone
.run_scan(&tenant_id, &id, ScanTrigger::Manual)
.await
{
tracing::error!("Manual scan failed for {id}: {e}");
}
});
@@ -170,11 +178,12 @@ pub async fn trigger_scan(
/// 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 repo = agent
.db
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.repositories()
.find_one(doc! { "_id": oid })
.await
@@ -196,10 +205,12 @@ pub async fn get_webhook_config(
#[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 = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
// Delete the repository
let result = db
+16 -5
View File
@@ -6,6 +6,7 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::SbomEntry;
use compliance_core::tenant_ctx::TenantCtx;
const COPYLEFT_LICENSES: &[&str] = &[
"GPL-2.0",
@@ -29,8 +30,10 @@ const COPYLEFT_LICENSES: &[&str] = &[
#[tracing::instrument(skip_all)]
pub async fn sbom_filters(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<serde_json::Value>, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let managers: Vec<String> = db
.sbom_entries()
@@ -61,9 +64,11 @@ pub async fn sbom_filters(
#[tracing::instrument(skip_all, fields(repo_id = ?filter.repo_id, package_manager = ?filter.package_manager))]
pub async fn list_sbom(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(filter): Query<SbomFilter>,
) -> ApiResult<Vec<SbomEntry>> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let mut query = doc! {};
if let Some(repo_id) = &filter.repo_id {
@@ -120,9 +125,11 @@ pub async fn list_sbom(
#[tracing::instrument(skip_all)]
pub async fn export_sbom(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<SbomExportParams>,
) -> Result<impl IntoResponse, StatusCode> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let entries: Vec<SbomEntry> = match db
.sbom_entries()
.find(doc! { "repo_id": &params.repo_id })
@@ -236,9 +243,11 @@ pub async fn export_sbom(
#[tracing::instrument(skip_all)]
pub async fn license_summary(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<SbomFilter>,
) -> ApiResult<Vec<LicenseSummary>> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let mut query = doc! {};
if let Some(repo_id) = &params.repo_id {
query.insert("repo_id", repo_id);
@@ -285,9 +294,11 @@ pub async fn license_summary(
#[tracing::instrument(skip_all)]
pub async fn sbom_diff(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<SbomDiffParams>,
) -> ApiResult<SbomDiffResult> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let entries_a: Vec<SbomEntry> = match db
.sbom_entries()
+4 -1
View File
@@ -4,13 +4,16 @@ use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::ScanRun;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn list_scan_runs(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<ScanRun>> {
let db = &agent.db;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db.scan_runs().count_documents(doc! {}).await.unwrap_or(0);
+44 -1
View File
@@ -1,6 +1,9 @@
use std::sync::Arc;
use axum::extract::Request;
use axum::http::HeaderValue;
use axum::middleware::Next;
use axum::response::Response;
use axum::{middleware, Extension};
use tokio::sync::RwLock;
use tower_http::cors::CorsLayer;
@@ -8,11 +11,44 @@ use tower_http::set_header::SetResponseHeaderLayer;
use tower_http::trace::TraceLayer;
use compliance_core::auth::{require_jwt_auth, require_tenant_status, JwksState};
use compliance_core::{TenantContext, TenantStatus};
use crate::agent::ComplianceAgent;
use crate::api::routes;
use crate::error::AgentError;
/// Synthetic tenant id used when Keycloak isn't configured (local dev,
/// `cargo run` against a bare Mongo). Lets the handler stack stay
/// uniformly tenant-scoped without the operator having to spin up KC
/// just to poke at the API. Override via `DEV_TENANT_ID`.
const DEFAULT_DEV_TENANT_ID: &str = "dev";
/// Inject a synthetic [`TenantContext`] for any request that lacks one.
/// Only mounted when Keycloak is NOT configured; with KC, the real
/// `require_jwt_auth` middleware owns this and we never reach here
/// without a context.
///
/// Public so the integration-test harness can mount it without
/// duplicating the synthetic-context shape.
pub async fn inject_dev_tenant(mut request: Request, next: Next) -> Response {
if request.extensions().get::<TenantContext>().is_none() {
let tenant_id =
std::env::var("DEV_TENANT_ID").unwrap_or_else(|_| DEFAULT_DEV_TENANT_ID.to_string());
let ctx = TenantContext {
tenant_slug: tenant_id.clone(),
tenant_id,
org_roles: vec![],
products: vec![],
plan: "dev".to_string(),
status: TenantStatus::Active,
user_id: "dev-user".to_string(),
user_name: None,
};
request.extensions_mut().insert(ctx);
}
next.run(request).await
}
pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), AgentError> {
let mut app = routes::build_router()
.layer(Extension(Arc::new(agent.clone())))
@@ -53,7 +89,14 @@ pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), A
.layer(middleware::from_fn(require_jwt_auth))
.layer(Extension(jwks_state));
} else {
tracing::warn!("Keycloak not configured - API endpoints are unprotected");
let tenant_id =
std::env::var("DEV_TENANT_ID").unwrap_or_else(|_| DEFAULT_DEV_TENANT_ID.to_string());
tracing::warn!(
tenant_id = %tenant_id,
"Keycloak not configured — running unauthenticated against the dev tenant. \
DO NOT use in any environment with real customer data."
);
app = app.layer(middleware::from_fn(inject_dev_tenant));
}
let addr = format!("0.0.0.0:{port}");
+50 -4
View File
@@ -78,19 +78,28 @@ impl DatabasePool {
/// first call per tenant (per process). Cheap on the hot path —
/// subsequent calls skip the round-trip.
pub async fn for_tenant(&self, ctx: &TenantContext) -> Result<Database, AgentError> {
let db_name = self.tenant_db_name(&ctx.tenant_id);
self.for_tenant_id(&ctx.tenant_id).await
}
/// Like [`Self::for_tenant`] but accepts a bare tenant_id.
/// For background paths (scheduler, webhooks, pipeline orchestrators)
/// that don't have a full [`TenantContext`] but know which tenant
/// they're operating on (typically resolved from a URL path, a job
/// argument, or the registry).
pub async fn for_tenant_id(&self, tenant_id: &str) -> Result<Database, AgentError> {
let db_name = self.tenant_db_name(tenant_id);
let db = Database::from_database(self.client.database(&db_name));
// `DashMap::insert` returns the previous value; `None` means we
// were the first writer for this tenant_id and own the
// index-ensure work.
if self.ensured.insert(ctx.tenant_id.clone(), ()).is_none() {
if self.ensured.insert(tenant_id.to_string(), ()).is_none() {
if let Err(e) = db.ensure_indexes().await {
// Roll the marker back so the next request retries.
self.ensured.remove(&ctx.tenant_id);
self.ensured.remove(tenant_id);
return Err(e);
}
tracing::debug!(
tenant_id = %ctx.tenant_id,
tenant_id = %tenant_id,
db_name = %db_name,
"Indexes ensured for tenant database"
);
@@ -131,6 +140,43 @@ impl DatabasePool {
pub fn client(&self) -> &Client {
&self.client
}
/// List every Mongo database currently belonging to this pool,
/// identified by the `<db_prefix>_` prefix. The result is the raw
/// database names — opening one for offboarding/cleanup goes
/// through [`Self::client`].
///
/// Note: hashed-fallback names (very long tenant_ids) lose the
/// original tenant_id at the cluster level — we know a database
/// exists for *some* tenant but not which one. In practice
/// tenant_ids are UUIDs (36 chars) and never hit the fallback,
/// so this is a theoretical concern, not an operational one.
pub async fn list_tenant_db_names(&self) -> Result<Vec<String>, AgentError> {
let prefix = format!("{}_", self.db_prefix);
let names = self.client.list_database_names().await?;
Ok(names
.into_iter()
.filter(|n| n.starts_with(&prefix))
.collect())
}
/// Drop the database for a specific tenant. Used by GDPR delete
/// and tenant offboarding. Idempotent — dropping a non-existent
/// database is a no-op at the driver level.
///
/// Also evicts the tenant from the in-memory `ensured` set so a
/// later re-provision triggers fresh `ensure_indexes`.
pub async fn drop_tenant(&self, tenant_id: &str) -> Result<(), AgentError> {
let db_name = self.tenant_db_name(tenant_id);
self.client.database(&db_name).drop().await?;
self.ensured.remove(tenant_id);
tracing::info!(
tenant_id = %tenant_id,
db_name = %db_name,
"Dropped tenant database"
);
Ok(())
}
}
/// Mongo database names disallow `/`, `\`, `.`, `"`, `$`, ` `, and NUL.
+4 -7
View File
@@ -25,16 +25,13 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
}
tracing::info!("Connecting to MongoDB...");
let db = database::Database::connect(&config.mongodb_uri, &config.mongodb_database).await?;
db.ensure_indexes().await?;
// M7.2-A: per-tenant pool. Uses `mongodb_database` as the db-name
// prefix so tenant databases land as `<prefix>_<tenant_id>` next to
// the legacy single-tenant database.
// Per-tenant pool only — the agent has no shared "default" database
// after M7.2-D. `mongodb_database` is now the db-name prefix used
// for tenant databases (`<prefix>_<tenant_id>`).
let db_pool =
database::DatabasePool::connect(&config.mongodb_uri, &config.mongodb_database).await?;
let agent = agent::ComplianceAgent::new(config.clone(), db.clone(), db_pool);
let agent = agent::ComplianceAgent::new(config.clone(), db_pool);
tracing::info!("Starting scheduler...");
let scheduler_agent = agent.clone();
+77 -22
View File
@@ -4,8 +4,14 @@ use tokio_cron_scheduler::{Job, JobScheduler};
use compliance_core::models::ScanTrigger;
use crate::agent::ComplianceAgent;
use crate::database::Database;
use crate::error::AgentError;
/// Default tenant the scheduler runs against when `SCHEDULER_TENANT_IDS`
/// isn't set. Matches the dev-injector default so a bare `cargo run` has
/// the scheduler scanning whatever lives in `<prefix>_dev`.
const DEFAULT_SCHEDULER_TENANT_ID: &str = "dev";
pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError> {
let sched = JobScheduler::new()
.await
@@ -18,7 +24,9 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
let agent = scan_agent.clone();
Box::pin(async move {
tracing::info!("Scheduled scan triggered");
scan_all_repos(&agent).await;
for tenant_id in scheduler_tenants() {
scan_all_repos(&agent, &tenant_id).await;
}
})
})
.map_err(|e| AgentError::Scheduler(format!("Failed to create scan job: {e}")))?;
@@ -34,7 +42,9 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
let agent = cve_agent.clone();
Box::pin(async move {
tracing::info!("CVE monitor triggered");
monitor_cves(&agent).await;
for tenant_id in scheduler_tenants() {
monitor_cves(&agent, &tenant_id).await;
}
})
})
.map_err(|e| AgentError::Scheduler(format!("Failed to create CVE monitor job: {e}")))?;
@@ -48,8 +58,9 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
.await
.map_err(|e| AgentError::Scheduler(format!("Failed to start scheduler: {e}")))?;
let tenants = scheduler_tenants();
tracing::info!(
"Scheduler started: scans='{}', CVE monitor='{}'",
"Scheduler started: scans='{}', CVE monitor='{}', tenants={tenants:?}",
agent.config.scan_schedule,
agent.config.cve_monitor_schedule,
);
@@ -60,13 +71,47 @@ pub async fn start_scheduler(agent: &ComplianceAgent) -> Result<(), AgentError>
}
}
async fn scan_all_repos(agent: &ComplianceAgent) {
/// Tenants the scheduler iterates each tick. From `SCHEDULER_TENANT_IDS`
/// (comma-separated), or `DEFAULT_SCHEDULER_TENANT_ID` if unset. M7.2-D
/// will replace this with a pull from the tenant-registry.
fn scheduler_tenants() -> Vec<String> {
std::env::var("SCHEDULER_TENANT_IDS")
.ok()
.map(|s| {
s.split(',')
.map(str::trim)
.filter(|s| !s.is_empty())
.map(String::from)
.collect::<Vec<_>>()
})
.filter(|v| !v.is_empty())
.unwrap_or_else(|| vec![DEFAULT_SCHEDULER_TENANT_ID.to_string()])
}
/// Resolve the per-tenant database. Logs and returns `None` on failure
/// so the loop in the caller can continue with other tenants.
async fn tenant_db(agent: &ComplianceAgent, tenant_id: &str) -> Option<Database> {
match agent.db_pool.for_tenant_id(tenant_id).await {
Ok(db) => Some(db),
Err(e) => {
tracing::error!("Scheduler: cannot open tenant database '{tenant_id}': {e}");
None
}
}
}
async fn scan_all_repos(agent: &ComplianceAgent, tenant_id: &str) {
use futures_util::StreamExt;
let cursor = match agent.db.repositories().find(doc! {}).await {
let db = match tenant_db(agent, tenant_id).await {
Some(db) => db,
None => return,
};
let cursor = match db.repositories().find(doc! {}).await {
Ok(c) => c,
Err(e) => {
tracing::error!("Failed to list repos for scheduled scan: {e}");
tracing::error!("Failed to list repos for tenant '{tenant_id}': {e}");
return;
}
};
@@ -75,33 +120,44 @@ async fn scan_all_repos(agent: &ComplianceAgent) {
for repo in repos {
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
if let Err(e) = agent.run_scan(&repo_id, ScanTrigger::Scheduled).await {
tracing::error!("Scheduled scan failed for {}: {e}", repo.name);
if let Err(e) = agent
.run_scan(tenant_id, &repo_id, ScanTrigger::Scheduled)
.await
{
tracing::error!(
"Scheduled scan failed for {} (tenant '{tenant_id}'): {e}",
repo.name
);
}
}
}
async fn monitor_cves(agent: &ComplianceAgent) {
async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
use compliance_core::models::notification::{parse_severity, CveNotification};
use compliance_core::models::SbomEntry;
use futures_util::StreamExt;
let db = match tenant_db(agent, tenant_id).await {
Some(db) => db,
None => return,
};
// Fetch all SBOM entries grouped by repo
let cursor = match agent.db.sbom_entries().find(doc! {}).await {
let cursor = match db.sbom_entries().find(doc! {}).await {
Ok(c) => c,
Err(e) => {
tracing::error!("CVE monitor: failed to list SBOM entries: {e}");
tracing::error!("CVE monitor: failed to list SBOM entries for '{tenant_id}': {e}");
return;
}
};
let entries: Vec<SbomEntry> = cursor.filter_map(|r| async { r.ok() }).collect().await;
if entries.is_empty() {
tracing::debug!("CVE monitor: no SBOM entries, skipping");
tracing::debug!("CVE monitor: no SBOM entries for tenant '{tenant_id}', skipping");
return;
}
tracing::info!(
"CVE monitor: checking {} dependencies for new CVEs",
"CVE monitor: checking {} dependencies for new CVEs (tenant '{tenant_id}')",
entries.len()
);
@@ -112,7 +168,7 @@ async fn monitor_cves(agent: &ComplianceAgent) {
std::collections::HashMap::new();
for rid in &repo_ids {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(rid) {
if let Ok(Some(repo)) = agent.db.repositories().find_one(doc! { "_id": oid }).await {
if let Ok(Some(repo)) = db.repositories().find_one(doc! { "_id": oid }).await {
repo_names.insert(rid.clone(), repo.name.clone());
}
}
@@ -160,8 +216,7 @@ async fn monitor_cves(agent: &ComplianceAgent) {
for alert in &alerts {
let filter = doc! { "cve_id": &alert.cve_id, "repo_id": &alert.repo_id };
let update = doc! { "$setOnInsert": mongodb::bson::to_bson(alert).unwrap_or_default() };
let _ = agent
.db
let _ = db
.cve_alerts()
.update_one(filter, update)
.upsert(true)
@@ -174,8 +229,7 @@ async fn monitor_cves(agent: &ComplianceAgent) {
continue;
}
if let Some(entry_id) = &entry.id {
let _ = agent
.db
let _ = db
.sbom_entries()
.update_one(
doc! { "_id": entry_id },
@@ -213,8 +267,7 @@ async fn monitor_cves(agent: &ComplianceAgent) {
let update = doc! {
"$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
};
match agent
.db
match db
.cve_notifications()
.update_one(filter, update)
.upsert(true)
@@ -232,8 +285,10 @@ async fn monitor_cves(agent: &ComplianceAgent) {
}
if new_notifications > 0 {
tracing::info!("CVE monitor: created {new_notifications} new notification(s)");
tracing::info!(
"CVE monitor: created {new_notifications} new notification(s) for tenant '{tenant_id}'"
);
} else {
tracing::info!("CVE monitor: no new CVEs found");
tracing::info!("CVE monitor: no new CVEs found for tenant '{tenant_id}'");
}
}
+23 -9
View File
@@ -14,24 +14,30 @@ type HmacSha256 = Hmac<Sha256>;
pub async fn handle_gitea_webhook(
Extension(agent): Extension<Arc<ComplianceAgent>>,
Path(repo_id): Path<String>,
Path((tenant_id, repo_id)): Path<(String, String)>,
headers: HeaderMap,
body: Bytes,
) -> StatusCode {
// Look up the repo to get its webhook secret
// Look up the repo in the tenant's database to get its webhook secret
let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
Ok(oid) => oid,
Err(_) => return StatusCode::NOT_FOUND,
};
let repo = match agent
.db
let db = match agent.db_pool.for_tenant_id(&tenant_id).await {
Ok(db) => db,
Err(e) => {
tracing::warn!("Gitea webhook: cannot open tenant database '{tenant_id}': {e}");
return StatusCode::NOT_FOUND;
}
};
let repo = match db
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
Ok(Some(repo)) => repo,
_ => {
tracing::warn!("Gitea webhook: repo {repo_id} not found");
tracing::warn!("Gitea webhook: repo {repo_id} not found in tenant '{tenant_id}'");
return StatusCode::NOT_FOUND;
}
};
@@ -66,15 +72,21 @@ pub async fn handle_gitea_webhook(
"push" => {
let agent_clone = (*agent).clone();
let repo_id = repo_id.clone();
let tenant_id = tenant_id.clone();
tokio::spawn(async move {
tracing::info!("Gitea push webhook: triggering scan for {repo_id}");
if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
tracing::info!(
"Gitea push webhook: triggering scan for {repo_id} in tenant {tenant_id}"
);
if let Err(e) = agent_clone
.run_scan(&tenant_id, &repo_id, ScanTrigger::Webhook)
.await
{
tracing::error!("Webhook-triggered scan failed: {e}");
}
});
StatusCode::OK
}
"pull_request" => handle_pull_request(agent, &repo_id, &payload).await,
"pull_request" => handle_pull_request(agent, &tenant_id, &repo_id, &payload).await,
_ => {
tracing::debug!("Gitea webhook: ignoring event '{event}'");
StatusCode::OK
@@ -84,6 +96,7 @@ pub async fn handle_gitea_webhook(
async fn handle_pull_request(
agent: Arc<ComplianceAgent>,
tenant_id: &str,
repo_id: &str,
payload: &serde_json::Value,
) -> StatusCode {
@@ -106,13 +119,14 @@ async fn handle_pull_request(
}
let repo_id = repo_id.to_string();
let tenant_id = tenant_id.to_string();
let head_sha = head_sha.to_string();
let base_sha = base_sha.to_string();
let agent_clone = (*agent).clone();
tokio::spawn(async move {
tracing::info!("Gitea PR webhook: reviewing PR #{pr_number} on {repo_id}");
if let Err(e) = agent_clone
.run_pr_review(&repo_id, pr_number, &base_sha, &head_sha)
.run_pr_review(&tenant_id, &repo_id, pr_number, &base_sha, &head_sha)
.await
{
tracing::error!("PR review failed for #{pr_number}: {e}");
+23 -9
View File
@@ -14,24 +14,30 @@ type HmacSha256 = Hmac<Sha256>;
pub async fn handle_github_webhook(
Extension(agent): Extension<Arc<ComplianceAgent>>,
Path(repo_id): Path<String>,
Path((tenant_id, repo_id)): Path<(String, String)>,
headers: HeaderMap,
body: Bytes,
) -> StatusCode {
// Look up the repo to get its webhook secret
// Look up the repo in the tenant's database to get its webhook secret
let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
Ok(oid) => oid,
Err(_) => return StatusCode::NOT_FOUND,
};
let repo = match agent
.db
let db = match agent.db_pool.for_tenant_id(&tenant_id).await {
Ok(db) => db,
Err(e) => {
tracing::warn!("GitHub webhook: cannot open tenant database '{tenant_id}': {e}");
return StatusCode::NOT_FOUND;
}
};
let repo = match db
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
Ok(Some(repo)) => repo,
_ => {
tracing::warn!("GitHub webhook: repo {repo_id} not found");
tracing::warn!("GitHub webhook: repo {repo_id} not found in tenant '{tenant_id}'");
return StatusCode::NOT_FOUND;
}
};
@@ -66,15 +72,21 @@ pub async fn handle_github_webhook(
"push" => {
let agent_clone = (*agent).clone();
let repo_id = repo_id.clone();
let tenant_id = tenant_id.clone();
tokio::spawn(async move {
tracing::info!("GitHub push webhook: triggering scan for {repo_id}");
if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
tracing::info!(
"GitHub push webhook: triggering scan for {repo_id} in tenant {tenant_id}"
);
if let Err(e) = agent_clone
.run_scan(&tenant_id, &repo_id, ScanTrigger::Webhook)
.await
{
tracing::error!("Webhook-triggered scan failed: {e}");
}
});
StatusCode::OK
}
"pull_request" => handle_pull_request(agent, &repo_id, &payload).await,
"pull_request" => handle_pull_request(agent, &tenant_id, &repo_id, &payload).await,
_ => {
tracing::debug!("GitHub webhook: ignoring event '{event}'");
StatusCode::OK
@@ -84,6 +96,7 @@ pub async fn handle_github_webhook(
async fn handle_pull_request(
agent: Arc<ComplianceAgent>,
tenant_id: &str,
repo_id: &str,
payload: &serde_json::Value,
) -> StatusCode {
@@ -105,13 +118,14 @@ async fn handle_pull_request(
}
let repo_id = repo_id.to_string();
let tenant_id = tenant_id.to_string();
let head_sha = head_sha.to_string();
let base_sha = base_sha.to_string();
let agent_clone = (*agent).clone();
tokio::spawn(async move {
tracing::info!("GitHub PR webhook: reviewing PR #{pr_number} on {repo_id}");
if let Err(e) = agent_clone
.run_pr_review(&repo_id, pr_number, &base_sha, &head_sha)
.run_pr_review(&tenant_id, &repo_id, pr_number, &base_sha, &head_sha)
.await
{
tracing::error!("PR review failed for #{pr_number}: {e}");
+23 -9
View File
@@ -10,24 +10,30 @@ use crate::agent::ComplianceAgent;
pub async fn handle_gitlab_webhook(
Extension(agent): Extension<Arc<ComplianceAgent>>,
Path(repo_id): Path<String>,
Path((tenant_id, repo_id)): Path<(String, String)>,
headers: HeaderMap,
body: Bytes,
) -> StatusCode {
// Look up the repo to get its webhook secret
// Look up the repo in the tenant's database to get its webhook secret
let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
Ok(oid) => oid,
Err(_) => return StatusCode::NOT_FOUND,
};
let repo = match agent
.db
let db = match agent.db_pool.for_tenant_id(&tenant_id).await {
Ok(db) => db,
Err(e) => {
tracing::warn!("GitLab webhook: cannot open tenant database '{tenant_id}': {e}");
return StatusCode::NOT_FOUND;
}
};
let repo = match db
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
Ok(Some(repo)) => repo,
_ => {
tracing::warn!("GitLab webhook: repo {repo_id} not found");
tracing::warn!("GitLab webhook: repo {repo_id} not found in tenant '{tenant_id}'");
return StatusCode::NOT_FOUND;
}
};
@@ -59,15 +65,21 @@ pub async fn handle_gitlab_webhook(
"push" => {
let agent_clone = (*agent).clone();
let repo_id = repo_id.clone();
let tenant_id = tenant_id.clone();
tokio::spawn(async move {
tracing::info!("GitLab push webhook: triggering scan for {repo_id}");
if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
tracing::info!(
"GitLab push webhook: triggering scan for {repo_id} in tenant {tenant_id}"
);
if let Err(e) = agent_clone
.run_scan(&tenant_id, &repo_id, ScanTrigger::Webhook)
.await
{
tracing::error!("Webhook-triggered scan failed: {e}");
}
});
StatusCode::OK
}
"merge_request" => handle_merge_request(agent, &repo_id, &payload).await,
"merge_request" => handle_merge_request(agent, &tenant_id, &repo_id, &payload).await,
_ => {
tracing::debug!("GitLab webhook: ignoring event '{event_type}'");
StatusCode::OK
@@ -77,6 +89,7 @@ pub async fn handle_gitlab_webhook(
async fn handle_merge_request(
agent: Arc<ComplianceAgent>,
tenant_id: &str,
repo_id: &str,
payload: &serde_json::Value,
) -> StatusCode {
@@ -101,13 +114,14 @@ async fn handle_merge_request(
}
let repo_id = repo_id.to_string();
let tenant_id = tenant_id.to_string();
let head_sha = head_sha.to_string();
let base_sha = base_sha.to_string();
let agent_clone = (*agent).clone();
tokio::spawn(async move {
tracing::info!("GitLab MR webhook: reviewing MR !{mr_iid} on {repo_id}");
if let Err(e) = agent_clone
.run_pr_review(&repo_id, mr_iid, &base_sha, &head_sha)
.run_pr_review(&tenant_id, &repo_id, mr_iid, &base_sha, &head_sha)
.await
{
tracing::error!("MR review failed for !{mr_iid}: {e}");
+8 -4
View File
@@ -9,17 +9,21 @@ use crate::webhooks::{gitea, github, gitlab};
pub async fn start_webhook_server(agent: &ComplianceAgent) -> Result<(), AgentError> {
let app = Router::new()
// Per-repo webhook URLs: /webhook/{platform}/{repo_id}
// Per-tenant per-repo webhook URLs: /webhook/{tenant_id}/{platform}/{repo_id}
// The tenant_id is resolved from the URL path because webhooks
// arrive without a JWT — they're authenticated via per-repo HMAC,
// not via the tenant gate. The dashboard surfaces the full URL
// including the tenant_id when the repo is registered.
.route(
"/webhook/github/{repo_id}",
"/webhook/{tenant_id}/github/{repo_id}",
post(github::handle_github_webhook),
)
.route(
"/webhook/gitlab/{repo_id}",
"/webhook/{tenant_id}/gitlab/{repo_id}",
post(gitlab::handle_gitlab_webhook),
)
.route(
"/webhook/gitea/{repo_id}",
"/webhook/{tenant_id}/gitea/{repo_id}",
post(gitea::handle_gitea_webhook),
)
.layer(Extension(Arc::new(agent.clone())));
+18 -10
View File
@@ -7,7 +7,7 @@ use std::sync::Arc;
use compliance_agent::agent::ComplianceAgent;
use compliance_agent::api;
use compliance_agent::database::{Database, DatabasePool};
use compliance_agent::database::DatabasePool;
use compliance_core::AgentConfig;
use secrecy::SecretString;
@@ -28,11 +28,6 @@ impl TestServer {
// Unique database name per test run to avoid collisions
let db_name = format!("test_{}", uuid::Uuid::new_v4().simple());
let db = Database::connect(&mongodb_uri, &db_name)
.await
.expect("Failed to connect to MongoDB — is it running?");
db.ensure_indexes().await.expect("Failed to create indexes");
let db_pool = DatabasePool::connect(&mongodb_uri, &db_name)
.await
.expect("Failed to build DatabasePool");
@@ -73,11 +68,15 @@ impl TestServer {
pentest_imap_password: None,
};
let agent = ComplianceAgent::new(config, db, db_pool);
let agent = ComplianceAgent::new(config, db_pool);
// Build the router with the agent extension
// Build the router with the agent extension. After M7.2-B every
// handler takes a TenantCtx extractor; without KC in the test
// harness, the dev-tenant injector mounts a synthetic context so
// tests run end-to-end against `<db_name>_dev`.
let app = api::routes::build_router()
.layer(axum::extract::Extension(Arc::new(agent)))
.layer(axum::middleware::from_fn(api::server::inject_dev_tenant))
.layer(tower_http::cors::CorsLayer::permissive());
// Bind to port 0 to get a random available port
@@ -160,10 +159,19 @@ impl TestServer {
&self.db_name
}
/// Drop the test database on cleanup
/// Drop every per-tenant database belonging to this test run.
/// Post-M7.2-D the agent never opens a `db_name` directly —
/// data lives only in `<db_name>_<tenant>` per-tenant databases.
pub async fn cleanup(&self) {
if let Ok(client) = mongodb::Client::with_uri_str(&self.mongodb_uri).await {
client.database(&self.db_name).drop().await.ok();
if let Ok(names) = client.list_database_names().await {
let prefix = format!("{}_", self.db_name);
for name in names {
if name.starts_with(&prefix) {
client.database(&name).drop().await.ok();
}
}
}
}
}
}
@@ -158,6 +158,70 @@ async fn tenant_db_name_sanitizes_unsafe_characters() {
}
}
#[tokio::test]
async fn admin_helpers_list_and_drop_tenant_dbs() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let prefix = format!("m72d_{}", short_id());
let pool = DatabasePool::connect(&uri, &prefix).await.expect("connect");
let acme = ctx("00000000-0000-0000-0000-00000000acme", "acme");
let globex = ctx("00000000-0000-0000-0000-0000globex000", "globex");
// Provision two tenants and write a doc into each so the databases
// actually materialize on the cluster (Mongo lazily creates DBs).
let acme_db = pool.for_tenant(&acme).await.expect("acme db");
let globex_db = pool.for_tenant(&globex).await.expect("globex db");
acme_db
.repositories()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await
.expect("insert acme");
globex_db
.repositories()
.insert_one(fixture_repo("globex-app", "git@example.com:globex/app.git"))
.await
.expect("insert globex");
// list_tenant_db_names sees both, filtered by prefix
let names = pool.list_tenant_db_names().await.expect("list tenants");
let acme_name = pool.tenant_db_name(&acme.tenant_id);
let globex_name = pool.tenant_db_name(&globex.tenant_id);
assert!(
names.contains(&acme_name),
"expected {acme_name} in {names:?}"
);
assert!(
names.contains(&globex_name),
"expected {globex_name} in {names:?}"
);
for name in &names {
assert!(name.starts_with(&format!("{prefix}_")));
}
// drop_tenant removes acme's DB
pool.drop_tenant(&acme.tenant_id)
.await
.expect("drop acme tenant");
let after = pool
.list_tenant_db_names()
.await
.expect("list tenants after drop");
assert!(
!after.contains(&acme_name),
"acme should be gone after drop, got {after:?}"
);
assert!(
after.contains(&globex_name),
"globex should still be present, got {after:?}"
);
// Cleanup remaining
pool.drop_tenant(&globex.tenant_id)
.await
.expect("drop globex tenant");
}
#[tokio::test]
async fn tenant_db_name_falls_back_to_hash_when_too_long() {
let uri = std::env::var("TEST_MONGODB_URI")