Files
compliance-scanner-agent/compliance-agent/src/main.rs
T
Sharang ParnerkarandClaude Fable 5 0d83859bcf
CI / Check (pull_request) Successful in 8m15s
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
feat(migrate): per-tenant onboarding backfill + revert + CLI (#132 part 2)
Wire the id-preserving mappers into a runnable, idempotent, reversible migration:
- backfill_onboarded_targets(db, dry_run): repositories -> onboarded_targets;
  dast_targets fold into the linked repo target (append LiveUrl, promote type,
  relink dast_scan_runs/pentest_sessions history) or migrate standalone. Skips
  existing (by _id), writes a schema_migrations marker; dry-run computes the
  report without writing. Legacy collections are never deleted.
- revert(db): replay the relink log, drop onboarded_targets + the log, clear the
  marker — restores the pre-migration state.
- CLI: `compliance-agent migrate onboarding [--all | --tenant <id>] [--dry-run]
  [--revert]`, with DatabasePool::list_tenant_ids for --all.
- database.rs: collection_named<T> accessor + list_tenant_ids helper.

Integration test (real Mongo, local-only — CI is --lib) covers fold + relink +
idempotency + revert end to end. 5 mapper unit tests run in CI.

Closes #132.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 19:49:52 +02:00

111 lines
4.1 KiB
Rust

use compliance_agent::{agent, api, config, database, migrate, scheduler, ssh, webhooks};
/// Run the `migrate onboarding` subcommand and exit. Backfills (or reverts) the
/// unified `onboarded_targets` collection per tenant.
///
/// Usage: `compliance-agent migrate onboarding [--all | --tenant <id>] [--dry-run] [--revert]`
async fn run_migration(
args: &[String],
pool: &database::DatabasePool,
) -> Result<(), compliance_agent::error::AgentError> {
if args.get(2).map(String::as_str) != Some("onboarding") {
eprintln!(
"usage: compliance-agent migrate onboarding [--all | --tenant <id>] [--dry-run] [--revert]"
);
std::process::exit(2);
}
let has = |flag: &str| args.iter().any(|a| a == flag);
let dry_run = has("--dry-run");
let revert = has("--revert");
let tenant = args
.iter()
.position(|a| a == "--tenant")
.and_then(|i| args.get(i + 1))
.cloned();
let tenants: Vec<String> = if has("--all") {
pool.list_tenant_ids().await?
} else if let Some(t) = tenant {
vec![t]
} else {
eprintln!("specify --all or --tenant <id>");
std::process::exit(2);
};
for tenant_id in tenants {
let db = pool.for_tenant_id(&tenant_id).await?;
if revert {
migrate::onboarding::revert(&db).await?;
println!("[{tenant_id}] reverted onboarding backfill");
} else {
let report = migrate::onboarding::backfill_onboarded_targets(&db, dry_run).await?;
let prefix = if dry_run { "(dry-run) " } else { "" };
println!("[{tenant_id}] {prefix}{report:?}");
}
}
Ok(())
}
#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
match dotenvy::dotenv() {
Ok(path) => eprintln!("[dotenv] Loaded from: {}", path.display()),
Err(_) => eprintln!("[dotenv] No .env file found, using environment variables"),
}
let _telemetry_guard = compliance_core::telemetry::init_telemetry("compliance-agent");
// Log critical env vars at startup
tracing::info!(
chrome_ws_url = std::env::var("CHROME_WS_URL").ok().as_deref(),
pentest_email = std::env::var("PENTEST_VERIFICATION_EMAIL").ok().as_deref(),
encryption_key_set = std::env::var("PENTEST_ENCRYPTION_KEY").is_ok(),
"Loading configuration..."
);
let config = config::load_config()?;
// Ensure SSH key pair exists for cloning private repos
match ssh::ensure_ssh_key(&config.ssh_key_path) {
Ok(pubkey) => tracing::info!("SSH public key: {}", pubkey.trim()),
Err(e) => tracing::warn!("SSH key generation skipped: {e}"),
}
tracing::info!("Connecting to MongoDB...");
// Per-tenant pool only — the agent has no shared "default" database
// after M7.2-D. `mongodb_database` is now the db-name prefix used
// for tenant databases (`<prefix>_<tenant_id>`).
let db_pool =
database::DatabasePool::connect(&config.mongodb_uri, &config.mongodb_database).await?;
// One-shot subcommands run and exit without starting the servers.
let args: Vec<String> = std::env::args().collect();
if args.get(1).map(String::as_str) == Some("migrate") {
run_migration(&args, &db_pool).await?;
return Ok(());
}
let agent = agent::ComplianceAgent::new(config.clone(), db_pool);
tracing::info!("Starting scheduler...");
let scheduler_agent = agent.clone();
let scheduler_handle = tokio::spawn(async move {
if let Err(e) = scheduler::start_scheduler(&scheduler_agent).await {
tracing::error!("Scheduler error: {e}");
}
});
tracing::info!("Starting webhook server...");
let webhook_agent = agent.clone();
let webhook_handle = tokio::spawn(async move {
if let Err(e) = webhooks::start_webhook_server(&webhook_agent).await {
tracing::error!("Webhook server error: {e}");
}
});
tracing::info!("Starting REST API on port {}...", config.agent_port);
api::start_api_server(agent, config.agent_port).await?;
let _ = tokio::join!(scheduler_handle, webhook_handle);
Ok(())
}