Compare commits

...

6 Commits

Author SHA1 Message Date
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
Sharang Parnerkar 003835764e fixup(m7.2-A): validate db_prefix at connect, bump hash to 16 bytes
CI / Check (pull_request) Successful in 8m29s
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
Addresses review feedback on the hash-fallback path.

The original `debug_assert!(hashed.len() <= MAX_DB_NAME_LEN)` was a
runtime hack that vanished in release builds. With an 8-byte hash
truncation (~2^32 birthday-collision resistance), two tenant_ids
hashing to the same suffix would silently share a database — no
panic, no rollback, just cross-tenant data leak. Not acceptable for
a regulated-industry product.

Changes:
- Bump hash truncation 8 → 16 bytes (32 hex chars). 2^64 birthday
  resistance — collision-impossible at our scale.
- Add MAX_PREFIX_LEN (= 30) and validate db_prefix.len() at
  `DatabasePool::connect`. The runtime hash-fallback arithmetic is
  now provably within Mongo's 63-byte cap; drop the debug_assert!.
- New test `connect_rejects_overlong_db_prefix` exercises the
  inclusive bound (30 passes, 31 fails).
- Existing hash-fallback test now asserts a 32-char hex suffix +
  basic distinctness for two different inputs.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-17 13:16:46 +02:00
Sharang Parnerkar e3aabe7d18 feat(m7.2-A): introduce per-tenant DatabasePool
CI / Check (pull_request) Successful in 8m40s
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
First slice of the M7.2 tenant-isolation work. Adds a `DatabasePool`
that hands out per-tenant `Database` handles physically scoped to
`<prefix>_<tenant_id>` Mongo databases. Isolation is at the driver,
not at "we hope we filter" — a handle for tenant A literally cannot
see tenant B's documents because it's connected to a different db.

What's in this PR
- DatabasePool::connect — pings the cluster, prepares per-tenant lazy
  handles.
- DatabasePool::for_tenant(&TenantContext) — returns a Database scoped
  to that tenant. ensure_indexes runs once per tenant per process via
  a DashMap-backed marker; failure rolls the marker back so the next
  request retries.
- tenant_db_name — `<prefix>_<sanitized_tenant_id>` if it fits in
  Mongo's 63-byte db-name cap, else `<prefix>_<sha256-16hex>` fallback.
- Sanitizer rewrites the Mongo-disallowed chars (`/ \ . " $ <space>
  NUL`) so any future tenant_id shape works.
- ComplianceAgent gains a `db_pool: DatabasePool` field next to the
  existing `db: Database`. Handlers / pipelines / webhooks still use
  `db` — they migrate to `db_pool.for_tenant(&ctx)` in M7.2-B/C and
  `db` goes away in M7.2-D.

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 — 4 pass
  against live mongo on 27017:
    * pool_isolates_tenants_at_driver_level — writes for acme + globex,
      reads through each tenant's handle; each sees exactly its own
      data with no filter doc anywhere.
    * for_tenant_is_idempotent_index_creation — second + third call
      for the same tenant do not error.
    * tenant_db_name_sanitizes_unsafe_characters
    * tenant_db_name_falls_back_to_hash_when_too_long — 100-byte
      tenant_id collapses to a stable 8-byte hex suffix.

Why per-tenant DB vs `tenant_id` field + filter
- Driver-level isolation; impossible to forget the filter on one of
  the 184 query call-sites in compliance-agent.
- Handlers don't change shape at migration — `agent.db.findings()`
  becomes `db.findings()` after pulling `db` from
  `agent.db_pool.for_tenant(&ctx)`.
- GDPR delete = `db.dropDatabase()`.
- On-prem deploy = the same code path, with one tenant.
- Trade-off accepted: index storage duplicated per tenant; Mongo's
  ~thousand-db ceiling is way above the 10s-100s tenants we're
  targeting.

Caveats
- Existing `agent.db` continues to point at the single legacy db.
  Handlers / pipelines that use it are unscoped until M7.2-B/C
  migrate them.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-17 11:58:24 +02:00
sharang 183234f9af feat(m7.1): wire compliance-agent to compliance-core auth + status gate (#85)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 5s
CI / Deploy Agent (push) Successful in 8m38s
CI / Deploy Dashboard (push) Successful in 7m30s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m55s
2026-06-17 09:36:52 +00:00
sharang dbadff0aac fix(m7.1): JWKS refresh-on-failure in auth middleware (#84)
CI / Check (push) Has been skipped
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 11m44s
CI / Deploy Dashboard (push) Successful in 13m1s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Successful in 1m53s
2026-06-04 14:46:14 +00:00
sharang 116293519d M7.1 smoke harness: lift auth to compliance-core + compliance-smoke service (#83)
CI / Check (push) Has been cancelled
CI / Detect Changes (push) Has been cancelled
CI / Deploy Agent (push) Has been cancelled
CI / Deploy Dashboard (push) Has been cancelled
CI / Deploy Docs (push) Has been cancelled
CI / Deploy MCP (push) Has been cancelled
2026-06-04 14:38:35 +00:00
36 changed files with 1904 additions and 301 deletions
Generated
+19
View File
@@ -687,6 +687,7 @@ dependencies = [
"tokio-cron-scheduler",
"tokio-stream",
"tokio-tungstenite 0.26.2",
"tower",
"tower-http",
"tracing",
"tracing-subscriber",
@@ -700,19 +701,23 @@ dependencies = [
name = "compliance-core"
version = "0.1.0"
dependencies = [
"axum",
"bson",
"chrono",
"hex",
"jsonwebtoken",
"mongodb",
"opentelemetry",
"opentelemetry-appender-tracing",
"opentelemetry-otlp",
"opentelemetry_sdk",
"reqwest",
"secrecy",
"serde",
"serde_json",
"sha2",
"thiserror 2.0.18",
"tokio",
"tracing",
"tracing-opentelemetry",
"tracing-subscriber",
@@ -826,6 +831,20 @@ dependencies = [
"tracing-subscriber",
]
[[package]]
name = "compliance-smoke"
version = "0.1.0"
dependencies = [
"axum",
"compliance-core",
"reqwest",
"serde",
"serde_json",
"tokio",
"tracing",
"tracing-subscriber",
]
[[package]]
name = "console_error_panic_hook"
version = "0.1.7"
+1
View File
@@ -6,6 +6,7 @@ members = [
"compliance-graph",
"compliance-dast",
"compliance-mcp",
"compliance-smoke",
]
resolver = "2"
+3 -2
View File
@@ -7,7 +7,7 @@ edition = "2021"
workspace = true
[dependencies]
compliance-core = { workspace = true, features = ["mongodb", "telemetry"] }
compliance-core = { workspace = true, features = ["mongodb", "telemetry", "axum"] }
compliance-graph = { path = "../compliance-graph" }
compliance-dast = { path = "../compliance-dast" }
serde = { workspace = true }
@@ -44,7 +44,8 @@ dashmap = { workspace = true }
tokio-stream = { workspace = true }
[dev-dependencies]
compliance-core = { workspace = true, features = ["mongodb"] }
compliance-core = { workspace = true, features = ["mongodb", "axum"] }
tower = { version = "0.5", features = ["util"] }
reqwest = { workspace = true }
serde_json = { workspace = true }
tokio = { workspace = true }
+9 -2
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;
use crate::database::{Database, DatabasePool};
use crate::llm::LlmClient;
use crate::pipeline::orchestrator::PipelineOrchestrator;
@@ -16,7 +16,13 @@ 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.
pub db_pool: DatabasePool,
pub llm: Arc<LlmClient>,
pub http: reqwest::Client,
/// Per-session broadcast senders for SSE streaming.
@@ -28,7 +34,7 @@ pub struct ComplianceAgent {
}
impl ComplianceAgent {
pub fn new(config: AgentConfig, db: Database) -> Self {
pub fn new(config: AgentConfig, db: Database, db_pool: DatabasePool) -> Self {
let llm = Arc::new(LlmClient::new(
config.litellm_url.clone(),
config.litellm_api_key.clone(),
@@ -43,6 +49,7 @@ impl ComplianceAgent {
Self {
config,
db,
db_pool,
llm,
http,
session_streams: Arc::new(DashMap::new()),
-113
View File
@@ -1,113 +0,0 @@
use std::sync::Arc;
use axum::{
extract::Request,
middleware::Next,
response::{IntoResponse, Response},
};
use jsonwebtoken::{decode, decode_header, jwk::JwkSet, DecodingKey, Validation};
use reqwest::StatusCode;
use serde::Deserialize;
use tokio::sync::RwLock;
/// Cached JWKS from Keycloak for token validation.
#[derive(Clone)]
pub struct JwksState {
pub jwks: Arc<RwLock<Option<JwkSet>>>,
pub jwks_url: String,
}
#[derive(Debug, Deserialize)]
struct Claims {
#[allow(dead_code)]
sub: String,
}
const PUBLIC_ENDPOINTS: &[&str] = &["/api/v1/health"];
/// Middleware that validates Bearer JWT tokens against Keycloak's JWKS.
///
/// Skips validation for health check endpoints.
/// If `JwksState` is not present as an extension (keycloak not configured),
/// all requests pass through.
pub async fn require_jwt_auth(request: Request, next: Next) -> Response {
let path = request.uri().path();
if PUBLIC_ENDPOINTS.contains(&path) {
return next.run(request).await;
}
let jwks_state = match request.extensions().get::<JwksState>() {
Some(s) => s.clone(),
None => return next.run(request).await,
};
let auth_header = match request.headers().get("authorization") {
Some(h) => h,
None => return (StatusCode::UNAUTHORIZED, "Missing authorization header").into_response(),
};
let token = match auth_header.to_str() {
Ok(s) if s.starts_with("Bearer ") => &s[7..],
_ => return (StatusCode::UNAUTHORIZED, "Invalid authorization header").into_response(),
};
match validate_token(token, &jwks_state).await {
Ok(()) => next.run(request).await,
Err(e) => {
tracing::warn!("JWT validation failed: {e}");
(StatusCode::UNAUTHORIZED, "Invalid token").into_response()
}
}
}
async fn validate_token(token: &str, state: &JwksState) -> Result<(), String> {
let header = decode_header(token).map_err(|e| format!("failed to decode JWT header: {e}"))?;
let kid = header
.kid
.ok_or_else(|| "JWT missing kid header".to_string())?;
let jwks = fetch_or_get_jwks(state).await?;
let jwk = jwks
.keys
.iter()
.find(|k| k.common.key_id.as_deref() == Some(&kid))
.ok_or_else(|| "no matching key found in JWKS".to_string())?;
let decoding_key =
DecodingKey::from_jwk(jwk).map_err(|e| format!("failed to create decoding key: {e}"))?;
let mut validation = Validation::new(header.alg);
validation.validate_exp = true;
validation.validate_aud = false;
decode::<Claims>(token, &decoding_key, &validation)
.map_err(|e| format!("token validation failed: {e}"))?;
Ok(())
}
async fn fetch_or_get_jwks(state: &JwksState) -> Result<JwkSet, String> {
{
let cached = state.jwks.read().await;
if let Some(ref jwks) = *cached {
return Ok(jwks.clone());
}
}
let resp = reqwest::get(&state.jwks_url)
.await
.map_err(|e| format!("failed to fetch JWKS: {e}"))?;
let jwks: JwkSet = resp
.json()
.await
.map_err(|e| format!("failed to parse JWKS: {e}"))?;
let mut cached = state.jwks.write().await;
*cached = Some(jwks.clone());
Ok(jwks)
}
+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
+22 -16
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
@@ -170,11 +173,12 @@ 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 +200,12 @@ 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);
-1
View File
@@ -1,4 +1,3 @@
pub mod auth_middleware;
pub mod handlers;
pub mod routes;
pub mod server;
+52 -4
View File
@@ -1,17 +1,54 @@
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;
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::auth_middleware::{require_jwt_auth, JwksState};
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())))
@@ -44,11 +81,22 @@ pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), A
jwks_url,
};
tracing::info!("Keycloak JWT auth enabled for realm '{kc_realm}'");
// Layers execute outermost-first. Extension(jwks_state) must run
// before require_jwt_auth so the middleware can read it; the
// status gate runs after JWT so TenantContext is in extensions.
app = app
.layer(Extension(jwks_state))
.layer(middleware::from_fn(require_jwt_auth));
.layer(middleware::from_fn(require_tenant_status))
.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}");
+146
View File
@@ -1,11 +1,151 @@
use std::sync::Arc;
use dashmap::DashMap;
use mongodb::bson::doc;
use mongodb::options::IndexOptions;
use mongodb::{Client, Collection, IndexModel};
use sha2::{Digest, Sha256};
use compliance_core::models::*;
use compliance_core::TenantContext;
use crate::error::AgentError;
/// Mongo enforces a 63-byte cap on database names (older clusters: 64
/// on Linux, 63 on Windows; we target the conservative limit).
const MAX_DB_NAME_LEN: usize = 63;
/// Hex length of the SHA-256 truncation used for the hash fallback
/// tenant DB name (16 bytes → 32 hex chars). 16 bytes gives ~2^64
/// birthday-collision resistance — at our 10s-100s tenant scale this
/// is effectively impossible to hit.
const HASH_HEX_LEN: usize = 32;
/// Largest `db_prefix` that still guarantees the hash-fallback name
/// fits in the 63-byte cap: `prefix + "_" + 32 hex chars`.
const MAX_PREFIX_LEN: usize = MAX_DB_NAME_LEN - 1 - HASH_HEX_LEN;
/// Per-tenant Mongo connection broker (M7.2 isolation model).
///
/// Holds one [`Client`] and hands out [`Database`] handles physically
/// scoped to `<db_prefix>_<tenant_id>`. The driver is the isolation
/// boundary — a handle for tenant A cannot see tenant B's documents
/// because it is connected to a different database, not because of an
/// application-level filter.
///
/// Index creation runs idempotently the first time each tenant is seen
/// in the process's lifetime. Mongo's `createIndex` is itself idempotent
/// by index name; the in-memory `ensured` set just skips the round-trip.
#[derive(Clone, Debug)]
pub struct DatabasePool {
client: Client,
db_prefix: String,
ensured: Arc<DashMap<String, ()>>,
}
impl DatabasePool {
/// Connect to the cluster and prepare to hand out tenant databases
/// named `<db_prefix>_<tenant_id>`.
///
/// Validates `db_prefix.len() <= MAX_PREFIX_LEN` so the
/// hash-fallback path is provably within Mongo's 63-byte db-name
/// cap. Refuses to construct a pool that could ever produce an
/// over-long name.
pub async fn connect(uri: &str, db_prefix: &str) -> Result<Self, AgentError> {
if db_prefix.len() > MAX_PREFIX_LEN {
return Err(AgentError::Other(format!(
"db_prefix '{db_prefix}' is {} chars; max is {MAX_PREFIX_LEN} so the \
hash-fallback tenant DB name fits Mongo's {MAX_DB_NAME_LEN}-byte cap",
db_prefix.len()
)));
}
let client = Client::with_uri_str(uri).await?;
client
.database("admin")
.run_command(doc! { "ping": 1 })
.await?;
tracing::info!(
"MongoDB cluster reachable; per-tenant pool ready (db prefix '{db_prefix}')"
);
Ok(Self {
client,
db_prefix: db_prefix.to_string(),
ensured: Arc::new(DashMap::new()),
})
}
/// Return a [`Database`] scoped to this tenant. Ensures indexes on
/// 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);
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 let Err(e) = db.ensure_indexes().await {
// Roll the marker back so the next request retries.
self.ensured.remove(&ctx.tenant_id);
return Err(e);
}
tracing::debug!(
tenant_id = %ctx.tenant_id,
db_name = %db_name,
"Indexes ensured for tenant database"
);
}
Ok(db)
}
/// Compute the Mongo database name for a tenant. Public for tests
/// and tenant offboarding (`pool.client().database(name).drop()`).
///
/// Format: `<prefix>_<sanitized_tenant_id>` if it fits the 63-byte
/// cap, else `<prefix>_<sha256-16-byte-hex-of-tenant_id>`. The
/// `db_prefix` length invariant established at [`Self::connect`]
/// guarantees the hash-fallback name always fits — no runtime
/// assertion needed.
///
/// Collision resistance: the hash fallback is a 16-byte SHA-256
/// truncation, which gives ~2^64 birthday-collision resistance. At
/// our 10s100s tenant scale the probability of two tenant_ids
/// colliding is effectively zero. (8-byte truncation would have
/// been ~2^32 — too close for comfort on a regulated product.)
pub fn tenant_db_name(&self, tenant_id: &str) -> String {
let sanitized = sanitize_tenant_id(tenant_id);
let natural = format!("{}_{}", self.db_prefix, sanitized);
if natural.len() <= MAX_DB_NAME_LEN {
natural
} else {
let mut hasher = Sha256::new();
hasher.update(tenant_id.as_bytes());
let digest = hasher.finalize();
let suffix = hex::encode(&digest[..HASH_HEX_LEN / 2]);
format!("{}_{}", self.db_prefix, suffix)
}
}
/// Raw client handle. Reserved for cross-tenant admin flows that
/// must opt in explicitly (tenant listing, drop-on-offboard).
pub fn client(&self) -> &Client {
&self.client
}
}
/// Mongo database names disallow `/`, `\`, `.`, `"`, `$`, ` `, and NUL.
/// breakpilot-dev tenant_ids are UUIDs so this is belt-and-braces, but
/// it lets the pool tolerate any future tenant_id shape without surprise.
fn sanitize_tenant_id(tenant_id: &str) -> String {
tenant_id
.chars()
.map(|c| match c {
'/' | '\\' | '.' | '"' | '$' | ' ' | '\0' => '_',
c => c,
})
.collect()
}
#[derive(Clone, Debug)]
pub struct Database {
inner: mongodb::Database,
@@ -20,6 +160,12 @@ impl Database {
Ok(Self { inner: db })
}
/// Wrap an already-resolved Mongo database. Used by [`DatabasePool`]
/// to hand out tenant-scoped handles without a fresh client per tenant.
pub(crate) fn from_database(inner: mongodb::Database) -> Self {
Self { inner }
}
pub async fn ensure_indexes(&self) -> Result<(), AgentError> {
// repositories: unique git_url
self.repositories()
+7 -1
View File
@@ -28,7 +28,13 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
let db = database::Database::connect(&config.mongodb_uri, &config.mongodb_database).await?;
db.ensure_indexes().await?;
let agent = agent::ComplianceAgent::new(config.clone(), db.clone());
// 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.
let db_pool =
database::DatabasePool::connect(&config.mongodb_uri, &config.mongodb_database).await?;
let agent = agent::ComplianceAgent::new(config.clone(), db.clone(), db_pool);
tracing::info!("Starting scheduler...");
let scheduler_agent = agent.clone();
+22 -4
View File
@@ -7,7 +7,7 @@ use std::sync::Arc;
use compliance_agent::agent::ComplianceAgent;
use compliance_agent::api;
use compliance_agent::database::Database;
use compliance_agent::database::{Database, DatabasePool};
use compliance_core::AgentConfig;
use secrecy::SecretString;
@@ -33,6 +33,10 @@ impl TestServer {
.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");
let config = AgentConfig {
mongodb_uri: mongodb_uri.clone(),
mongodb_database: db_name.clone(),
@@ -69,11 +73,15 @@ impl TestServer {
pentest_imap_password: None,
};
let agent = ComplianceAgent::new(config, db);
let agent = ComplianceAgent::new(config, db, 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
@@ -156,10 +164,20 @@ impl TestServer {
&self.db_name
}
/// Drop the test database on cleanup
/// Drop the test database on cleanup. Post-M7.2-B the actual data
/// lives in `<db_name>_<tenant>` per-tenant databases; list those
/// off the cluster and drop them too.
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();
}
}
}
}
}
}
+234
View File
@@ -0,0 +1,234 @@
//! M7.2-A — `DatabasePool` isolation proof.
//!
//! Two `TenantContext`s, two databases, one client. Insert on A, query
//! on B → empty. Insert on B, query on A → only A's docs. Proves that
//! the per-tenant database split actually isolates at the driver level
//! and not at "we hope we filter."
//!
//! Requires MongoDB. Set `TEST_MONGODB_URI` to override the default
//! `mongodb://root:example@localhost:27017/?authSource=admin`.
#![allow(clippy::expect_used, clippy::unwrap_used)]
use compliance_agent::database::DatabasePool;
use compliance_core::models::TrackedRepository;
use compliance_core::{OrgRole, TenantContext, TenantStatus};
use mongodb::bson::doc;
fn ctx(tenant_id: &str, slug: &str) -> TenantContext {
TenantContext {
tenant_id: tenant_id.to_string(),
tenant_slug: slug.to_string(),
org_roles: vec![OrgRole::ItAdmin],
products: vec!["compliance-scanner".to_string()],
plan: "starter".to_string(),
status: TenantStatus::Active,
user_id: "u-1".to_string(),
user_name: None,
}
}
fn fixture_repo(name: &str, git_url: &str) -> TrackedRepository {
TrackedRepository {
id: None,
name: name.to_string(),
git_url: git_url.to_string(),
default_branch: "main".to_string(),
local_path: None,
scan_schedule: None,
webhook_enabled: false,
webhook_secret: None,
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
auth_token: None,
auth_username: None,
last_scanned_commit: None,
findings_count: 0,
created_at: chrono::Utc::now(),
updated_at: chrono::Utc::now(),
}
}
#[tokio::test]
async fn pool_isolates_tenants_at_driver_level() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// Unique per run so parallel test invocations don't collide. Kept
// short because Mongo caps db names at 63 bytes (prefix + tenant_id).
let prefix = format!("m72a_{}", short_id());
let pool = DatabasePool::connect(&uri, &prefix)
.await
.expect("Failed to connect to MongoDB — is it running?");
let acme = ctx("00000000-0000-0000-0000-00000000acme", "acme");
let globex = ctx("00000000-0000-0000-0000-0000globex000", "globex");
let acme_db = pool.for_tenant(&acme).await.expect("acme db");
let globex_db = pool.for_tenant(&globex).await.expect("globex db");
// Write distinct repos into each tenant's database.
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-platform",
"git@example.com:globex/platform.git",
))
.await
.expect("insert globex");
// The point of the whole exercise: acme can ONLY see acme's repo
// and globex can ONLY see globex's, with no filter doc anywhere
// because the isolation is at the database handle, not in the query.
let acme_seen = collect(&acme_db).await;
let globex_seen = collect(&globex_db).await;
assert_eq!(acme_seen.len(), 1, "acme should see exactly its own repo");
assert_eq!(acme_seen[0].name, "acme-app");
assert_eq!(
globex_seen.len(),
1,
"globex should see exactly its own repo"
);
assert_eq!(globex_seen[0].name, "globex-platform");
// Sanity: the two databases really are different by name.
let acme_db_name = pool.tenant_db_name(&acme.tenant_id);
let globex_db_name = pool.tenant_db_name(&globex.tenant_id);
assert_ne!(acme_db_name, globex_db_name);
assert!(acme_db_name.starts_with(&prefix));
// Cleanup — drop both per-tenant databases.
pool.client()
.database(&acme_db_name)
.drop()
.await
.expect("drop acme");
pool.client()
.database(&globex_db_name)
.drop()
.await
.expect("drop globex");
}
#[tokio::test]
async fn for_tenant_is_idempotent_index_creation() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let prefix = format!("m72a_{}", short_id());
let pool = DatabasePool::connect(&uri, &prefix).await.expect("connect");
let acme = ctx("00000000-0000-0000-0000-00000000acme", "acme");
// Second call must not fail (ensure_indexes already ran, in-memory
// marker is set, Mongo's createIndex is idempotent by name anyway).
let _ = pool.for_tenant(&acme).await.expect("first call");
let _ = pool.for_tenant(&acme).await.expect("second call");
let _ = pool.for_tenant(&acme).await.expect("third call");
// Cleanup
let db_name = pool.tenant_db_name(&acme.tenant_id);
pool.client().database(&db_name).drop().await.expect("drop");
}
#[tokio::test]
async fn tenant_db_name_sanitizes_unsafe_characters() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let pool = DatabasePool::connect(&uri, "m72a_sanitize")
.await
.expect("connect");
// Mongo db names cannot contain `/ \ . " $ <space> NUL`. The pool
// must rewrite these without exploding on connect.
let funky = "te/n.a\\nt$id\" with spaces";
let name = pool.tenant_db_name(funky);
for c in ['/', '\\', '.', '"', '$', ' '] {
assert!(
!name.contains(c),
"sanitized db name still contains {c:?}: {name}"
);
}
}
#[tokio::test]
async fn tenant_db_name_falls_back_to_hash_when_too_long() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
let pool = DatabasePool::connect(&uri, "m72a_long")
.await
.expect("connect");
// 100-byte tenant_id would overflow the 63-byte db-name cap with
// any reasonable prefix. The pool must hash it down.
let huge = "x".repeat(100);
let name = pool.tenant_db_name(&huge);
assert!(name.len() <= 63, "hashed name should fit: {name}");
assert!(name.starts_with("m72a_long_"));
// The hash suffix is 32 hex chars (16-byte SHA-256 truncation).
let suffix = name.trim_start_matches("m72a_long_");
assert_eq!(
suffix.len(),
32,
"expected 32-hex suffix (16-byte hash), got {suffix:?}"
);
assert!(suffix.chars().all(|c| c.is_ascii_hexdigit()));
// Stable: same input → same output.
assert_eq!(name, pool.tenant_db_name(&huge));
// Different inputs → different outputs (collision check on a tiny
// sample — full birthday-resistance is a proof not a test).
let huge2 = "y".repeat(100);
assert_ne!(pool.tenant_db_name(&huge), pool.tenant_db_name(&huge2));
}
#[tokio::test]
async fn connect_rejects_overlong_db_prefix() {
let uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// MAX_PREFIX_LEN is 30 (= 63 - 1 - 32). A 31-char prefix MUST be
// rejected at construction so the hash-fallback path can never
// produce an over-long db name at runtime.
let too_long = "a".repeat(31);
let err = DatabasePool::connect(&uri, &too_long).await.unwrap_err();
let msg = format!("{err}");
assert!(
msg.contains("max is 30") || msg.contains(&too_long),
"error should explain the cap: {msg}"
);
// Exactly 30 chars is the inclusive bound — must succeed.
let just_right = "a".repeat(30);
let _ = DatabasePool::connect(&uri, &just_right)
.await
.expect("30-char prefix should be accepted");
}
/// Short UUID slug for keeping test prefixes well under Mongo's 63-byte
/// db-name cap.
fn short_id() -> String {
uuid::Uuid::new_v4().simple().to_string()[..8].to_string()
}
/// Drain a `repositories` find cursor on the given tenant database.
async fn collect(db: &compliance_agent::database::Database) -> Vec<TrackedRepository> {
let mut cursor = db
.repositories()
.find(doc! {})
.await
.expect("find repositories");
let mut out = Vec::new();
while cursor.advance().await.expect("advance") {
out.push(cursor.deserialize_current().expect("deserialize"));
}
out
}
@@ -0,0 +1,122 @@
//! M7.1 — integration tests for `compliance_core::auth::require_tenant_status`.
//!
//! Exercises the middleware end-to-end through an Axum router so we
//! catch wiring bugs (extension propagation, method matching) that pure
//! unit tests would miss.
#![allow(clippy::expect_used, clippy::unwrap_used)]
use axum::{
body::Body,
extract::Request,
http::{Method, StatusCode},
middleware::{from_fn, Next},
response::Response,
routing::{get, post},
Router,
};
use compliance_core::{auth::require_tenant_status, TenantContext, TenantStatus};
use tower::ServiceExt;
fn ctx_with(status: TenantStatus) -> TenantContext {
TenantContext {
tenant_id: "t-1".to_string(),
tenant_slug: "acme".to_string(),
org_roles: vec![],
products: vec![],
plan: "starter".to_string(),
status,
user_id: "u-1".to_string(),
user_name: None,
}
}
fn router_with_ctx(ctx: Option<TenantContext>) -> Router {
let injector = move |mut req: Request, next: Next| {
let ctx = ctx.clone();
async move {
if let Some(c) = ctx {
req.extensions_mut().insert(c);
}
next.run(req).await
}
};
Router::new()
.route("/r", get(|| async { "read" }))
.route("/w", post(|| async { "write" }))
.layer(from_fn(require_tenant_status))
.layer(from_fn(injector))
}
async fn call(router: Router, method: Method, path: &str) -> Response {
let req = Request::builder()
.method(method)
.uri(path)
.body(Body::empty())
.expect("request build");
router.oneshot(req).await.expect("oneshot")
}
#[tokio::test]
async fn active_tenant_can_read_and_write() {
let r = router_with_ctx(Some(ctx_with(TenantStatus::Active)));
assert_eq!(
call(r.clone(), Method::GET, "/r").await.status(),
StatusCode::OK
);
assert_eq!(call(r, Method::POST, "/w").await.status(), StatusCode::OK);
}
#[tokio::test]
async fn trial_tenant_can_read_and_write() {
let r = router_with_ctx(Some(ctx_with(TenantStatus::Trial)));
assert_eq!(
call(r.clone(), Method::GET, "/r").await.status(),
StatusCode::OK
);
assert_eq!(call(r, Method::POST, "/w").await.status(), StatusCode::OK);
}
#[tokio::test]
async fn demo_tenant_can_read_and_write() {
let r = router_with_ctx(Some(ctx_with(TenantStatus::Demo)));
assert_eq!(
call(r.clone(), Method::GET, "/r").await.status(),
StatusCode::OK
);
assert_eq!(call(r, Method::POST, "/w").await.status(), StatusCode::OK);
}
#[tokio::test]
async fn frozen_tenant_can_read_but_not_write() {
let r = router_with_ctx(Some(ctx_with(TenantStatus::Frozen)));
assert_eq!(
call(r.clone(), Method::GET, "/r").await.status(),
StatusCode::OK
);
assert_eq!(
call(r, Method::POST, "/w").await.status(),
StatusCode::PAYMENT_REQUIRED
);
}
#[tokio::test]
async fn archived_tenant_is_gone_on_every_method() {
let r = router_with_ctx(Some(ctx_with(TenantStatus::Archived)));
assert_eq!(
call(r.clone(), Method::GET, "/r").await.status(),
StatusCode::GONE
);
assert_eq!(call(r, Method::POST, "/w").await.status(), StatusCode::GONE);
}
#[tokio::test]
async fn no_context_passes_through() {
let r = router_with_ctx(None);
assert_eq!(
call(r.clone(), Method::GET, "/r").await.status(),
StatusCode::OK
);
assert_eq!(call(r, Method::POST, "/w").await.status(), StatusCode::OK);
}
+13
View File
@@ -18,6 +18,15 @@ telemetry = [
"dep:tracing-subscriber",
"dep:tracing",
]
# Pulls in the M7.1 Axum middleware + extractor. Consumers that don't
# embed an HTTP server (e.g. the wasm dashboard frontend) leave it off.
axum = [
"dep:axum",
"dep:jsonwebtoken",
"dep:reqwest",
"dep:tokio",
"dep:tracing",
]
[dependencies]
serde = { workspace = true }
@@ -37,3 +46,7 @@ opentelemetry-appender-tracing = { version = "0.29", optional = true }
tracing-opentelemetry = { version = "0.30", optional = true }
tracing-subscriber = { workspace = true, optional = true }
tracing = { workspace = true, optional = true }
axum = { version = "0.8", optional = true }
jsonwebtoken = { version = "9", optional = true }
reqwest = { workspace = true, optional = true }
tokio = { workspace = true, optional = true }
+390
View File
@@ -0,0 +1,390 @@
//! M7.1 — JWT validation + tenant context propagation.
//!
//! `require_jwt_auth` validates a Bearer JWT against Keycloak's JWKS and
//! attaches a [`TenantContext`] to the request extensions. Downstream
//! middleware ([`require_tenant_status`]) and Axum extractors
//! ([`crate::tenant_ctx::TenantCtx`]) read it from there.
//!
//! Skipped paths:
//! * `/api/v1/health` — Kubernetes liveness; never authenticated.
//!
//! Failure modes:
//! * No `JwksState` extension → pass-through (single-tenant dev mode).
//! * Missing / malformed Bearer header → 401.
//! * Signature / expiry invalid → 401.
//! * Claims present but tenant_id missing → 401 (treated as a malformed
//! token; the realm must always issue tenant_id).
use std::sync::Arc;
use axum::{
extract::Request,
http::Method,
middleware::Next,
response::{IntoResponse, Response},
};
use jsonwebtoken::{decode, decode_header, jwk::JwkSet, DecodingKey, Validation};
use reqwest::StatusCode;
use serde::Deserialize;
use tokio::sync::RwLock;
use crate::{OrgRole, TenantContext, TenantStatus};
/// Cached JWKS from Keycloak for token validation.
#[derive(Clone)]
pub struct JwksState {
pub jwks: Arc<RwLock<Option<JwkSet>>>,
pub jwks_url: String,
}
/// Raw shape of the JWT payload — matches the breakpilot-dev realm's
/// protocol-mapper output. Missing fields default to "" / empty so a
/// realm that hasn't been fully wired yet still validates.
#[derive(Debug, Deserialize)]
struct Claims {
sub: String,
#[serde(default)]
name: Option<String>,
#[serde(default)]
preferred_username: Option<String>,
#[serde(default)]
tenant_id: String,
#[serde(default)]
tenant_slug: String,
#[serde(default)]
org_roles: Vec<String>,
#[serde(default)]
products: Vec<String>,
#[serde(default)]
plan: String,
#[serde(default)]
tenant_status: Option<TenantStatus>,
}
const PUBLIC_ENDPOINTS: &[&str] = &["/api/v1/health"];
/// Middleware that validates Bearer JWT tokens against Keycloak's JWKS
/// and attaches a `TenantContext` extension on success.
///
/// Skips validation for the health endpoint.
/// If `JwksState` is not present (Keycloak not configured), requests
/// pass through and downstream code must handle the missing context.
pub async fn require_jwt_auth(mut request: Request, next: Next) -> Response {
let path = request.uri().path();
if PUBLIC_ENDPOINTS.contains(&path) {
return next.run(request).await;
}
let jwks_state = match request.extensions().get::<JwksState>() {
Some(s) => s.clone(),
None => return next.run(request).await,
};
let auth_header = match request.headers().get("authorization") {
Some(h) => h,
None => return (StatusCode::UNAUTHORIZED, "Missing authorization header").into_response(),
};
let token = match auth_header.to_str() {
Ok(s) if s.starts_with("Bearer ") => &s[7..],
_ => return (StatusCode::UNAUTHORIZED, "Invalid authorization header").into_response(),
};
match validate_token(token, &jwks_state).await {
Ok(ctx) => {
request.extensions_mut().insert(ctx);
next.run(request).await
}
Err(e) => {
tracing::warn!("JWT validation failed: {e}");
(StatusCode::UNAUTHORIZED, "Invalid token").into_response()
}
}
}
/// Middleware that enforces the M7.1 `tenant_status` contract.
///
/// * `Active` / `Trial` / `Demo` — pass through.
/// * `Frozen` — read-only after cancel / non-payment. Writes return 402.
/// * `Archived` — data-retention window closed. Every request returns 410.
///
/// Pass-through when no `TenantContext` is present (single-tenant dev or
/// the upstream JWT middleware ran without `JwksState`).
pub async fn require_tenant_status(request: Request, next: Next) -> Response {
let ctx = match request.extensions().get::<TenantContext>() {
Some(c) => c.clone(),
None => return next.run(request).await,
};
if ctx.status.is_archived() {
return (
StatusCode::GONE,
"Tenant archived — data retention window closed",
)
.into_response();
}
if ctx.status.is_frozen() && is_write(request.method()) {
return (
StatusCode::PAYMENT_REQUIRED,
"Tenant frozen — read-only. Re-activate to resume writes.",
)
.into_response();
}
next.run(request).await
}
/// Treat anything other than GET/HEAD/OPTIONS as a write. Good enough for
/// REST. The few exceptions (e.g. read-side POSTs) can opt out at the
/// handler level once we have them.
fn is_write(m: &Method) -> bool {
!matches!(m, &Method::GET | &Method::HEAD | &Method::OPTIONS)
}
async fn validate_token(token: &str, state: &JwksState) -> Result<TenantContext, String> {
let header = decode_header(token).map_err(|e| format!("failed to decode JWT header: {e}"))?;
let kid = header
.kid
.clone()
.ok_or_else(|| "JWT missing kid header".to_string())?;
// First try against whatever's currently cached. If the kid isn't
// there or the signature doesn't verify, the cached JWKS is most
// likely stale (KC rotated keys) — refresh once and retry before
// giving up. Without this every key rotation produces a silent 401
// storm that only goes away when the agent restarts.
let jwks = fetch_or_get_jwks(state, false).await?;
match try_validate(token, &header, &kid, &jwks) {
Ok(ctx) => Ok(ctx),
Err(ValidationError::Permanent(e)) => Err(e),
Err(ValidationError::Stale(reason)) => {
tracing::info!(
kid = %kid,
reason = %reason,
"JWKS appears stale — forcing refresh and retrying"
);
let jwks = fetch_or_get_jwks(state, true).await?;
try_validate(token, &header, &kid, &jwks).map_err(|e| match e {
ValidationError::Stale(s) | ValidationError::Permanent(s) => s,
})
}
}
}
#[derive(Debug)]
enum ValidationError {
/// Refresh-eligible: cached JWKS may be stale.
Stale(String),
/// Refusing the token regardless of JWKS freshness.
Permanent(String),
}
fn try_validate(
token: &str,
header: &jsonwebtoken::Header,
kid: &str,
jwks: &JwkSet,
) -> Result<TenantContext, ValidationError> {
let jwk = match jwks
.keys
.iter()
.find(|k| k.common.key_id.as_deref() == Some(kid))
{
Some(j) => j,
None => {
return Err(ValidationError::Stale(
"no matching key found in JWKS".to_string(),
))
}
};
let decoding_key = DecodingKey::from_jwk(jwk)
.map_err(|e| ValidationError::Permanent(format!("failed to create decoding key: {e}")))?;
let mut validation = Validation::new(header.alg);
validation.validate_exp = true;
validation.validate_aud = false;
let data = match decode::<Claims>(token, &decoding_key, &validation) {
Ok(d) => d,
Err(e) => {
// Signature mismatch is the other refresh-eligible failure:
// the matching kid is present but the key bytes don't match.
// Everything else (expired, malformed, etc.) is permanent.
return Err(
if matches!(e.kind(), jsonwebtoken::errors::ErrorKind::InvalidSignature) {
ValidationError::Stale(format!("token validation failed: {e}"))
} else {
ValidationError::Permanent(format!("token validation failed: {e}"))
},
);
}
};
claims_to_context(data.claims).map_err(ValidationError::Permanent)
}
/// Map the decoded JWT payload into the platform-wide `TenantContext`.
/// Pulled out for unit testing — no I/O.
fn claims_to_context(c: Claims) -> Result<TenantContext, String> {
if c.tenant_id.is_empty() {
return Err("JWT is missing tenant_id claim".to_string());
}
let status = c.tenant_status.unwrap_or_else(|| {
tracing::warn!(
"JWT missing tenant_status claim for tenant {} — defaulting to Trial",
c.tenant_id
);
TenantStatus::Trial
});
Ok(TenantContext {
tenant_id: c.tenant_id,
tenant_slug: c.tenant_slug,
org_roles: c.org_roles.iter().map(|r| OrgRole::parse(r)).collect(),
products: c.products,
plan: c.plan,
status,
user_id: c.sub,
user_name: c.name.or(c.preferred_username),
})
}
async fn fetch_or_get_jwks(state: &JwksState, force: bool) -> Result<JwkSet, String> {
if !force {
let cached = state.jwks.read().await;
if let Some(ref jwks) = *cached {
return Ok(jwks.clone());
}
}
// Hold the write lock across the fetch so concurrent refreshers
// don't all hammer Keycloak when keys rotate. If another writer
// already populated a fresh JWKS while we were waiting (and we
// weren't asked to force), use theirs.
let mut cached = state.jwks.write().await;
if !force {
if let Some(ref jwks) = *cached {
return Ok(jwks.clone());
}
}
let resp = reqwest::get(&state.jwks_url)
.await
.map_err(|e| format!("failed to fetch JWKS: {e}"))?;
let jwks: JwkSet = resp
.json()
.await
.map_err(|e| format!("failed to parse JWKS: {e}"))?;
*cached = Some(jwks.clone());
Ok(jwks)
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
fn base_claims() -> Claims {
Claims {
sub: "user-123".to_string(),
name: Some("Alice Acme".to_string()),
preferred_username: None,
tenant_id: "00000000-0000-0000-0000-000000000001".to_string(),
tenant_slug: "acme".to_string(),
org_roles: vec!["IT_ADMIN".to_string()],
products: vec!["compliance".to_string()],
plan: "professional".to_string(),
tenant_status: Some(TenantStatus::Active),
}
}
#[test]
fn claims_to_context_happy_path() {
let ctx = claims_to_context(base_claims()).expect("should map");
assert_eq!(ctx.tenant_id, "00000000-0000-0000-0000-000000000001");
assert_eq!(ctx.tenant_slug, "acme");
assert_eq!(ctx.org_roles, vec![OrgRole::ItAdmin]);
assert_eq!(ctx.products, vec!["compliance"]);
assert_eq!(ctx.plan, "professional");
assert_eq!(ctx.status, TenantStatus::Active);
assert_eq!(ctx.user_id, "user-123");
assert_eq!(ctx.user_name.as_deref(), Some("Alice Acme"));
}
#[test]
fn claims_to_context_rejects_missing_tenant_id() {
let mut c = base_claims();
c.tenant_id = "".to_string();
let err = claims_to_context(c).expect_err("should reject");
assert!(err.contains("tenant_id"));
}
#[test]
fn claims_to_context_defaults_status_when_missing() {
let mut c = base_claims();
c.tenant_status = None;
let ctx = claims_to_context(c).expect("should map");
assert_eq!(ctx.status, TenantStatus::Trial);
}
#[test]
fn claims_to_context_falls_back_to_preferred_username() {
let mut c = base_claims();
c.name = None;
c.preferred_username = Some("alice@acme.dev".to_string());
let ctx = claims_to_context(c).expect("should map");
assert_eq!(ctx.user_name.as_deref(), Some("alice@acme.dev"));
}
#[test]
fn claims_to_context_parses_multiple_roles() {
let mut c = base_claims();
c.org_roles = vec![
"IT_ADMIN".to_string(),
"CXO".to_string(),
"GARBAGE".to_string(),
];
let ctx = claims_to_context(c).expect("should map");
assert_eq!(
ctx.org_roles,
vec![OrgRole::ItAdmin, OrgRole::Cxo, OrgRole::Unknown]
);
}
#[test]
fn try_validate_returns_stale_when_kid_missing_from_jwks() {
// Empty JWKS — the kid we ask for can't possibly match. The error
// must classify as Stale so the caller refreshes JWKS and retries.
let jwks = JwkSet { keys: vec![] };
let header = jsonwebtoken::Header {
alg: jsonwebtoken::Algorithm::RS256,
kid: Some("kid-rotated-out".to_string()),
..Default::default()
};
let err = try_validate("ignored.token.value", &header, "kid-rotated-out", &jwks)
.expect_err("should fail");
match err {
ValidationError::Stale(s) => assert!(s.contains("no matching key")),
ValidationError::Permanent(s) => panic!("must be Stale, got Permanent: {s}"),
}
}
#[test]
fn is_write_detects_methods() {
assert!(!is_write(&Method::GET));
assert!(!is_write(&Method::HEAD));
assert!(!is_write(&Method::OPTIONS));
assert!(is_write(&Method::POST));
assert!(is_write(&Method::PUT));
assert!(is_write(&Method::PATCH));
assert!(is_write(&Method::DELETE));
}
}
+75
View File
@@ -0,0 +1,75 @@
//! Database helpers shared across the workspace.
//!
//! `tenant_filter` returns the BSON filter that every query and update
//! against a tenant-scoped collection MUST include. Centralising it here
//! makes the rule grep-able and keeps query call-sites from accidentally
//! omitting it.
//!
//! Future work (M7.2+): each collection model grows a `tenant_id` field
//! and every `find` / `update_*` / `delete_*` call gets this filter
//! merged in. The migration to per-collection scoping is tracked
//! separately — this helper is the building block.
use bson::{doc, Document};
use crate::TenantContext;
/// Returns `{ "tenant_id": <ctx.tenant_id> }`. Merge this into every
/// query filter against a tenant-scoped collection.
///
/// Use [`tenant_filter_merge`] when you need to combine it with other
/// query conditions — it preserves both halves without overwriting.
pub fn tenant_filter(ctx: &TenantContext) -> Document {
doc! { "tenant_id": &ctx.tenant_id }
}
/// Returns the tenant filter merged with caller-supplied conditions.
/// The tenant_id always wins on key conflict — callers cannot
/// accidentally override the scoping.
pub fn tenant_filter_merge(ctx: &TenantContext, mut extra: Document) -> Document {
extra.insert("tenant_id", &ctx.tenant_id);
extra
}
#[cfg(test)]
mod tests {
use super::*;
use crate::TenantStatus;
fn ctx() -> TenantContext {
TenantContext {
tenant_id: "t-abc".to_string(),
tenant_slug: "acme".to_string(),
org_roles: vec![],
products: vec![],
plan: "starter".to_string(),
status: TenantStatus::Active,
user_id: "u-1".to_string(),
user_name: None,
}
}
#[test]
fn produces_tenant_id_filter() {
let f = tenant_filter(&ctx());
assert_eq!(f.get_str("tenant_id"), Ok("t-abc"));
assert_eq!(f.len(), 1);
}
#[test]
fn merge_preserves_extra_conditions() {
let extra = doc! { "status": "open", "severity": "high" };
let f = tenant_filter_merge(&ctx(), extra);
assert_eq!(f.get_str("tenant_id"), Ok("t-abc"));
assert_eq!(f.get_str("status"), Ok("open"));
assert_eq!(f.get_str("severity"), Ok("high"));
}
#[test]
fn merge_overrides_caller_tenant_id() {
let extra = doc! { "tenant_id": "evil-other", "status": "open" };
let f = tenant_filter_merge(&ctx(), extra);
assert_eq!(f.get_str("tenant_id"), Ok("t-abc"));
assert_eq!(f.get_str("status"), Ok("open"));
}
}
+8
View File
@@ -1,9 +1,17 @@
pub mod config;
pub mod db;
pub mod error;
pub mod models;
#[cfg(feature = "telemetry")]
pub mod telemetry;
pub mod tenant;
pub mod traits;
#[cfg(feature = "axum")]
pub mod auth;
#[cfg(feature = "axum")]
pub mod tenant_ctx;
pub use config::{AgentConfig, DashboardConfig};
pub use error::CoreError;
pub use tenant::{OrgRole, TenantContext, TenantStatus};
+165
View File
@@ -0,0 +1,165 @@
//! Tenant context propagated through every authenticated request.
//!
//! M7.1 single source of truth for "who is this request for". Claims come
//! from a Keycloak-issued JWT and land here via [`crate::auth::require_jwt_auth`]
//! (enabled with the `axum` feature). Handlers reach into the request
//! extensions with the [`crate::tenant_ctx::TenantCtx`] extractor.
//!
//! The shape mirrors the JWT claim names the breakpilot-platform realm
//! emits (see `platform/orca-platform/dev/keycloak/realm-export.json`).
//! Stable contract — adding fields is fine; renaming is a breaking
//! change for every downstream product.
use serde::{Deserialize, Serialize};
/// Tenant lifecycle status from `PLATFORM_ARCHITECTURE.md §5c`.
///
/// Drives the `tenant_status` middleware:
/// * `Demo` / `Trial` / `Active` — full access.
/// * `Frozen` — read-only after cancel / non-payment. Mutating endpoints
/// return 402.
/// * `Archived` — data-retention window closed. Every endpoint returns 410.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "lowercase")]
pub enum TenantStatus {
Demo,
Trial,
Active,
Frozen,
Archived,
}
impl TenantStatus {
/// True for statuses that block write paths.
pub fn is_frozen(&self) -> bool {
matches!(self, TenantStatus::Frozen)
}
/// True for statuses that block every request.
pub fn is_archived(&self) -> bool {
matches!(self, TenantStatus::Archived)
}
/// True for the shared demo tenant — metering, billing, and audit
/// export are skipped.
pub fn is_demo(&self) -> bool {
matches!(self, TenantStatus::Demo)
}
}
impl std::fmt::Display for TenantStatus {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::Demo => write!(f, "demo"),
Self::Trial => write!(f, "trial"),
Self::Active => write!(f, "active"),
Self::Frozen => write!(f, "frozen"),
Self::Archived => write!(f, "archived"),
}
}
}
/// Org-level role baked into the JWT by the realm's protocol mapper.
/// `PLATFORM_ARCHITECTURE.md §6` is the canonical list.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "UPPERCASE")]
pub enum OrgRole {
ItAdmin,
Cxo,
Finance,
Legal,
User,
/// Anything we haven't enumerated yet — forwards-compatible.
#[serde(other)]
Unknown,
}
impl OrgRole {
/// Parses a single role string (Keycloak emits these as `IT_ADMIN`,
/// `CXO`, etc.). Round-trips with the JSON layer.
pub fn parse(s: &str) -> Self {
match s {
"IT_ADMIN" => OrgRole::ItAdmin,
"CXO" => OrgRole::Cxo,
"FINANCE" => OrgRole::Finance,
"LEGAL" => OrgRole::Legal,
"USER" => OrgRole::User,
_ => OrgRole::Unknown,
}
}
}
/// Everything we know about the requesting tenant at the moment a request
/// lands. Cheap to clone (every field is owned + small).
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TenantContext {
/// `tenants.id` from the platform's tenant-registry (UUID).
pub tenant_id: String,
/// Lowercase URL-safe slug. Useful for log lines + audit emit.
pub tenant_slug: String,
/// Org-level roles the authenticated user holds inside this tenant.
/// Drives the per-handler RBAC in `M7.1-followup` PRs.
pub org_roles: Vec<OrgRole>,
/// Products this tenant is currently entitled to. Used to short-circuit
/// MCP / API calls for unsubscribed products.
pub products: Vec<String>,
/// Customer plan (`starter` / `professional` / `enterprise`) — gates
/// per-plan feature flags (e.g., MCP server is enterprise-only).
pub plan: String,
/// Lifecycle status — read by `require_tenant_status` middleware.
pub status: TenantStatus,
/// Keycloak user id of the requester (`sub` claim). Required for audit
/// emit so we know WHO did the thing, not just WHICH tenant.
pub user_id: String,
/// Optional user-facing name from the `name` / `preferred_username`
/// claim. Only used in audit + log lines.
pub user_name: Option<String>,
}
impl TenantContext {
/// True if the caller holds at least one of the listed roles.
pub fn has_any_role(&self, roles: &[OrgRole]) -> bool {
self.org_roles.iter().any(|r| roles.contains(r))
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn org_role_parses_known_values() {
assert_eq!(OrgRole::parse("IT_ADMIN"), OrgRole::ItAdmin);
assert_eq!(OrgRole::parse("CXO"), OrgRole::Cxo);
assert_eq!(OrgRole::parse("USER"), OrgRole::User);
}
#[test]
fn org_role_unknown_is_forward_compat() {
assert_eq!(OrgRole::parse("FUTURE_ROLE"), OrgRole::Unknown);
}
#[test]
fn tenant_status_predicates() {
assert!(TenantStatus::Frozen.is_frozen());
assert!(!TenantStatus::Active.is_frozen());
assert!(TenantStatus::Archived.is_archived());
assert!(TenantStatus::Demo.is_demo());
assert!(!TenantStatus::Active.is_demo());
}
#[test]
fn has_any_role_matches() {
let ctx = TenantContext {
tenant_id: "t1".into(),
tenant_slug: "acme".into(),
org_roles: vec![OrgRole::ItAdmin],
products: vec![],
plan: "professional".into(),
status: TenantStatus::Active,
user_id: "u".into(),
user_name: None,
};
assert!(ctx.has_any_role(&[OrgRole::ItAdmin]));
assert!(ctx.has_any_role(&[OrgRole::Cxo, OrgRole::ItAdmin]));
assert!(!ctx.has_any_role(&[OrgRole::User, OrgRole::Cxo]));
}
}
+95
View File
@@ -0,0 +1,95 @@
//! Axum extractor for the per-request `TenantContext`.
//!
//! Handlers consume it as a normal extractor argument:
//!
//! ```ignore
//! async fn list_findings(TenantCtx(ctx): TenantCtx) -> Json<...> {
//! let filter = compliance_core::db::tenant_filter(&ctx);
//! ...
//! }
//! ```
//!
//! The middleware ([`crate::auth::require_jwt_auth`]) is responsible for
//! inserting the context into the request extensions. If it's missing on
//! a route that uses this extractor, that's a bug in the wiring — we
//! return 401 so the caller sees an auth failure rather than a 500.
use axum::{
extract::FromRequestParts,
http::{request::Parts, StatusCode},
response::{IntoResponse, Response},
};
use crate::TenantContext;
#[derive(Debug, Clone)]
pub struct TenantCtx(pub TenantContext);
#[derive(Debug)]
pub struct TenantCtxRejection;
impl IntoResponse for TenantCtxRejection {
fn into_response(self) -> Response {
(
StatusCode::UNAUTHORIZED,
"Missing tenant context — request was not authenticated",
)
.into_response()
}
}
impl<S> FromRequestParts<S> for TenantCtx
where
S: Send + Sync,
{
type Rejection = TenantCtxRejection;
async fn from_request_parts(parts: &mut Parts, _state: &S) -> Result<Self, Self::Rejection> {
parts
.extensions
.get::<TenantContext>()
.cloned()
.map(TenantCtx)
.ok_or(TenantCtxRejection)
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use crate::TenantStatus;
use axum::http::Request;
fn ctx() -> TenantContext {
TenantContext {
tenant_id: "t-1".to_string(),
tenant_slug: "acme".to_string(),
org_roles: vec![],
products: vec![],
plan: "starter".to_string(),
status: TenantStatus::Active,
user_id: "u-1".to_string(),
user_name: None,
}
}
#[tokio::test]
async fn extracts_context_when_present() {
let mut req = Request::new(());
req.extensions_mut().insert(ctx());
let (mut parts, _) = req.into_parts();
let TenantCtx(found) = TenantCtx::from_request_parts(&mut parts, &())
.await
.expect("extractor should succeed");
assert_eq!(found.tenant_id, "t-1");
}
#[tokio::test]
async fn rejects_when_missing() {
let req: Request<()> = Request::new(());
let (mut parts, _) = req.into_parts();
let err = TenantCtx::from_request_parts(&mut parts, &()).await;
assert!(err.is_err());
}
}
+22
View File
@@ -0,0 +1,22 @@
[package]
name = "compliance-smoke"
version = "0.1.0"
edition = "2021"
description = "Tiny Axum service exercising compliance-core M7.1 tenant gating. Run smoke.sh against it before merging anything that touches the auth/tenant path."
[lints]
workspace = true
[[bin]]
name = "compliance-smoke"
path = "src/main.rs"
[dependencies]
compliance-core = { workspace = true, features = ["axum"] }
axum = "0.8"
tokio = { workspace = true }
tracing = { workspace = true }
tracing-subscriber = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
reqwest = { workspace = true }
+111
View File
@@ -0,0 +1,111 @@
//! M7.1 smoke service.
//!
//! A standalone Axum binary whose only job is to host the
//! [`compliance_core::auth`] middleware + [`compliance_core::tenant_ctx`]
//! extractor on three endpoints, so `scripts/smoke.sh` can prove the
//! tenant-gating contract end-to-end before any auth-path PR merges.
//!
//! Endpoints:
//! * `GET /api/v1/health` — public, never authenticated.
//! * `GET /api/v1/echo` — protected read; returns the [`TenantContext`].
//! * `POST /api/v1/echo` — protected write; exercises the `Frozen → 402`
//! gate on the same handler.
//!
//! Configuration (env):
//! * `KEYCLOAK_URL` — e.g. `http://localhost:8080`. Required.
//! * `KEYCLOAK_REALM` — e.g. `certifai`. Required.
//! * `SMOKE_PORT` — defaults to `3010`.
use std::sync::Arc;
use axum::{middleware, routing::get, Extension, Json, Router};
use compliance_core::{
auth::{require_jwt_auth, require_tenant_status, JwksState},
tenant_ctx::TenantCtx,
};
use serde::Serialize;
use tokio::sync::RwLock;
#[derive(Serialize)]
struct EchoResponse {
method: &'static str,
tenant_id: String,
tenant_slug: String,
plan: String,
status: String,
products: Vec<String>,
org_roles: Vec<String>,
user_id: String,
user_name: Option<String>,
}
async fn health() -> Json<serde_json::Value> {
Json(serde_json::json!({ "ok": true }))
}
async fn echo_read(TenantCtx(ctx): TenantCtx) -> Json<EchoResponse> {
Json(echo(ctx, "GET"))
}
async fn echo_write(TenantCtx(ctx): TenantCtx) -> Json<EchoResponse> {
Json(echo(ctx, "POST"))
}
fn echo(ctx: compliance_core::TenantContext, method: &'static str) -> EchoResponse {
EchoResponse {
method,
tenant_id: ctx.tenant_id,
tenant_slug: ctx.tenant_slug,
plan: ctx.plan,
status: ctx.status.to_string(),
products: ctx.products,
org_roles: ctx.org_roles.iter().map(|r| format!("{r:?}")).collect(),
user_id: ctx.user_id,
user_name: ctx.user_name,
}
}
#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
tracing_subscriber::fmt()
.with_env_filter(
tracing_subscriber::EnvFilter::try_from_default_env()
.unwrap_or_else(|_| tracing_subscriber::EnvFilter::new("info")),
)
.init();
let kc_url = std::env::var("KEYCLOAK_URL")
.map_err(|_| "KEYCLOAK_URL is required (e.g. http://localhost:8080)")?;
let kc_realm = std::env::var("KEYCLOAK_REALM")
.map_err(|_| "KEYCLOAK_REALM is required (e.g. certifai)")?;
let port: u16 = std::env::var("SMOKE_PORT")
.ok()
.and_then(|s| s.parse().ok())
.unwrap_or(3010);
let jwks_url = format!("{kc_url}/realms/{kc_realm}/protocol/openid-connect/certs");
let jwks_state = JwksState {
jwks: Arc::new(RwLock::new(None)),
jwks_url: jwks_url.clone(),
};
// Layers execute outermost-first. The Extension must be registered
// before `require_jwt_auth` so the middleware can read JwksState; the
// status gate must run after JWT so `TenantContext` is in extensions.
let app = Router::new()
.route("/api/v1/health", get(health))
.route("/api/v1/echo", get(echo_read).post(echo_write))
.layer(middleware::from_fn(require_tenant_status))
.layer(middleware::from_fn(require_jwt_auth))
.layer(Extension(jwks_state));
let addr = format!("0.0.0.0:{port}");
let listener = tokio::net::TcpListener::bind(&addr).await?;
tracing::info!(
port,
jwks = %jwks_url,
"compliance-smoke listening — try `scripts/smoke.sh`"
);
axum::serve(listener, app).await?;
Ok(())
}
+136
View File
@@ -0,0 +1,136 @@
#!/usr/bin/env bash
# M7.1 tenant-gating smoke test.
#
# Drives compliance-smoke against a live Keycloak realm with five test
# users (one per tenant_status), asserts the response code on each
# endpoint, and exits non-zero on any mismatch.
#
# Pre-reqs (one-time):
# * KC up at $KC_URL with realm $KC_REALM
# * Client $KC_CLIENT has direct-access-grants enabled
# * Users + tenant_status mappers per certifai/keycloak/realm-export.json
# * compliance-smoke binary running and reachable at $SMOKE_URL
#
# Usage:
# scripts/smoke.sh # uses defaults below
# SMOKE_URL=... scripts/smoke.sh
set -euo pipefail
KC_URL="${KC_URL:-http://localhost:8080}"
KC_REALM="${KC_REALM:-certifai}"
KC_CLIENT="${KC_CLIENT:-certifai-dashboard}"
SMOKE_URL="${SMOKE_URL:-http://localhost:3010}"
readonly TOKEN_ENDPOINT="${KC_URL}/realms/${KC_REALM}/protocol/openid-connect/token"
PASS=0
FAIL=0
red() { printf '\033[31m%s\033[0m' "$*"; }
green() { printf '\033[32m%s\033[0m' "$*"; }
yellow() { printf '\033[33m%s\033[0m' "$*"; }
# Fetches an access token via direct access grant. Echoes the raw token.
get_token() {
local user="$1" pass="$2"
curl -sS -X POST "$TOKEN_ENDPOINT" \
-H 'Content-Type: application/x-www-form-urlencoded' \
-d "grant_type=password" \
-d "client_id=${KC_CLIENT}" \
-d "username=${user}" \
-d "password=${pass}" \
-d "scope=openid" \
| sed -n 's/.*"access_token":"\([^"]*\)".*/\1/p'
}
# Hits SMOKE_URL$path with the given method and (optional) bearer token,
# asserts the response status code matches $want.
assert_status() {
local label="$1" method="$2" path="$3" want="$4" token="${5:-}"
local args=(-sS -o /dev/null -w '%{http_code}' -X "$method" "${SMOKE_URL}${path}")
if [[ -n "$token" ]]; then
args+=(-H "Authorization: Bearer ${token}")
fi
local got
got=$(curl "${args[@]}")
if [[ "$got" == "$want" ]]; then
printf ' %s %s %-4s %-15s → %s\n' "$(green PASS)" "$label" "$method" "$path" "$got"
PASS=$((PASS + 1))
else
printf ' %s %s %-4s %-15s → got %s, want %s\n' "$(red FAIL)" "$label" "$method" "$path" "$got" "$want"
FAIL=$((FAIL + 1))
fi
}
header() {
printf '\n%s %s\n' "$(yellow '##')" "$1"
}
# ---- Pre-flight ----------------------------------------------------------
header "Pre-flight"
if ! curl -sS -o /dev/null -w '%{http_code}\n' "${SMOKE_URL}/api/v1/health" | grep -q '^200$'; then
printf ' %s smoke service not reachable at %s\n' "$(red ERR)" "$SMOKE_URL"
exit 2
fi
if ! curl -sS -o /dev/null -w '%{http_code}\n' "${KC_URL}/realms/${KC_REALM}/.well-known/openid-configuration" | grep -q '^200$'; then
printf ' %s Keycloak realm %s not reachable at %s\n' "$(red ERR)" "$KC_REALM" "$KC_URL"
exit 2
fi
printf ' %s smoke service + Keycloak both up\n' "$(green OK)"
# ---- Public endpoint --------------------------------------------------
header "Public endpoint (no auth required)"
assert_status anon GET /api/v1/health 200
# ---- Anonymous access to protected endpoints ----------------------------
header "Anonymous → 401 on protected endpoints"
assert_status anon GET /api/v1/echo 401
assert_status anon POST /api/v1/echo 401
# ---- Bad token ----------------------------------------------------------
header "Bad token → 401"
assert_status bogus GET /api/v1/echo 401 "not-a-real-jwt"
assert_status bogus POST /api/v1/echo 401 "not-a-real-jwt"
# ---- Active tenant (admin user) -----------------------------------------
header "admin@certifai.local (active) → full access"
TOKEN=$(get_token admin@certifai.local admin)
if [[ -z "$TOKEN" ]]; then
printf ' %s failed to fetch token for admin\n' "$(red ERR)"
exit 2
fi
assert_status active GET /api/v1/echo 200 "$TOKEN"
assert_status active POST /api/v1/echo 200 "$TOKEN"
# ---- Active tenant (USER role) ------------------------------------------
header "user@certifai.local (active) → full access"
TOKEN=$(get_token user@certifai.local user)
assert_status active GET /api/v1/echo 200 "$TOKEN"
assert_status active POST /api/v1/echo 200 "$TOKEN"
# ---- Trial tenant -------------------------------------------------------
header "trial@acme.local (trial) → full access"
TOKEN=$(get_token trial@acme.local trial)
assert_status trial GET /api/v1/echo 200 "$TOKEN"
assert_status trial POST /api/v1/echo 200 "$TOKEN"
# ---- Frozen tenant ------------------------------------------------------
header "frozen@acme.local (frozen) → read-only, writes 402"
TOKEN=$(get_token frozen@acme.local frozen)
assert_status frozen GET /api/v1/echo 200 "$TOKEN"
assert_status frozen POST /api/v1/echo 402 "$TOKEN"
# ---- Archived tenant ----------------------------------------------------
header "archived@acme.local (archived) → 410 everywhere"
TOKEN=$(get_token archived@acme.local archived)
assert_status archived GET /api/v1/echo 410 "$TOKEN"
assert_status archived POST /api/v1/echo 410 "$TOKEN"
# ---- Summary ------------------------------------------------------------
printf '\n'
if [[ "$FAIL" -gt 0 ]]; then
printf '%s %d passed, %d failed\n' "$(red FAIL)" "$PASS" "$FAIL"
exit 1
fi
printf '%s %d/%d assertions passed\n' "$(green PASS)" "$PASS" "$PASS"