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>

.gitea/workflows/ci.yml

@@ -13,6 +13,9 @@ env:
   # both --features server and --features web shares common crate work.
   RUSTC_WRAPPER: /usr/local/bin/sccache
   SCCACHE_DIR: /tmp/sccache
+  # compliance-agent depends on tramiton-core via git; use the system git so the
+  # credential rewrite below (see "Configure git auth ...") is honored on fetch.
+  CARGO_NET_GIT_FETCH_WITH_CLI: "true"
 
 # Cancel in-progress runs for the same branch/PR
 concurrency:
@@ -46,6 +49,19 @@ jobs:
         env:
           RUSTC_WRAPPER: ""
 
+      # compliance-agent has a git dependency on tramiton-core (a private repo on
+      # this Gitea instance). Rewrite its SSH URL to HTTPS + a PAT so the runner
+      # can fetch it. Requires the repo secret TRAMITON_FETCH_TOKEN (a Gitea PAT
+      # with read:repository, owned by a user with access to sharang/tramiton).
+      # (Honored on fetch because CARGO_NET_GIT_FETCH_WITH_CLI=true uses system git.)
+      - name: Configure git auth for private tramiton dependency
+        run: |
+          git config --global \
+            url."https://sharang:${{ secrets.TRAMITON_FETCH_TOKEN }}@gitea.meghsakha.com/".insteadOf \
+            "ssh://git@gitea.meghsakha.com:22222/"
+        env:
+          RUSTC_WRAPPER: ""
+
       # Format (no compilation needed)
       - name: Format
         run: cargo fmt --all --check

Cargo.lock

@@ -692,6 +692,7 @@ dependencies = [
  "tower-http",
  "tracing",
  "tracing-subscriber",
+ "tramiton-core",
  "urlencoding",
  "uuid",
  "walkdir",
@@ -4197,7 +4198,7 @@ version = "3.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "219cb19e96be00ab2e37d6e299658a0cfa83e52429179969b0f0121b4ac46983"
 dependencies = [
- "toml_edit",
+ "toml_edit 0.23.10+spec-1.0.0",
 ]
 
 [[package]]
@@ -4996,6 +4997,15 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "serde_spanned"
+version = "0.6.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf41e0cfaf7226dca15e8197172c295a782857fcb97fad1808a166870dee75a3"
+dependencies = [
+ "serde",
+]
+
 [[package]]
 name = "serde_urlencoded"
 version = "0.7.1"
@@ -5810,6 +5820,27 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "toml"
+version = "0.8.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc1beb996b9d83529a9e75c17a1686767d148d70663143c7854d8b4a09ced362"
+dependencies = [
+ "serde",
+ "serde_spanned",
+ "toml_datetime 0.6.11",
+ "toml_edit 0.22.27",
+]
+
+[[package]]
+name = "toml_datetime"
+version = "0.6.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22cddaf88f4fbc13c51aebbf5f8eceb5c7c5a9da2ac40a13519eb5b0a0e8f11c"
+dependencies = [
+ "serde",
+]
+
 [[package]]
 name = "toml_datetime"
 version = "0.7.5+spec-1.1.0"
@@ -5819,6 +5850,20 @@ dependencies = [
  "serde_core",
 ]
 
+[[package]]
+name = "toml_edit"
+version = "0.22.27"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41fe8c660ae4257887cf66394862d21dbca4a6ddd26f04a3560410406a2f819a"
+dependencies = [
+ "indexmap 2.13.0",
+ "serde",
+ "serde_spanned",
+ "toml_datetime 0.6.11",
+ "toml_write",
+ "winnow",
+]
+
 [[package]]
 name = "toml_edit"
 version = "0.23.10+spec-1.0.0"
@@ -5826,7 +5871,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "84c8b9f757e028cee9fa244aea147aab2a9ec09d5325a9b01e0a49730c2b5269"
 dependencies = [
  "indexmap 2.13.0",
- "toml_datetime",
+ "toml_datetime 0.7.5+spec-1.1.0",
  "toml_parser",
  "winnow",
 ]
@@ -5840,6 +5885,12 @@ dependencies = [
  "winnow",
 ]
 
+[[package]]
+name = "toml_write"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801"
+
 [[package]]
 name = "tonic"
 version = "0.12.3"
@@ -6086,6 +6137,18 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "tramiton-core"
+version = "0.4.0"
+source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.0#e3dc1bf7027a2f6d7b1fe43043d6dfa887ce4af3"
+dependencies = [
+ "serde",
+ "tempfile",
+ "thiserror 1.0.69",
+ "toml",
+ "walkdir",
+]
+
 [[package]]
 name = "tree-sitter"
 version = "0.24.7"

compliance-agent/Cargo.toml

@@ -10,6 +10,11 @@ workspace = true
 compliance-core = { workspace = true, features = ["mongodb", "telemetry", "axum"] }
 compliance-graph = { path = "../compliance-graph" }
 compliance-dast = { path = "../compliance-dast" }
+# Native firmware build/target detection for bare-metal & RTOS artifacts.
+# Same-company IP, used directly (not via CLI) so the whole tramiton suite is
+# available to the onboarding classifier. NOTE: CI must be able to fetch this
+# private repo (see the git-auth step in .gitea/workflows/ci.yml).
+tramiton-core = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.0" }
 serde = { workspace = true }
 serde_json = { workspace = true }
 tokio = { workspace = true }

compliance-agent/src/classify/firmware.rs

@@ -1,55 +1,40 @@
 //! Firmware classification via tramiton.
 //!
 //! tramiton is the company's firmware build/repro engine; we do not re-implement
-//! its detection. This module shells out to `tramiton detect --json` behind a
-//! [`FirmwareDetector`] port (so a future in-process or cloud impl can slot in)
-//! and maps the resulting build plan onto a [`TargetType`]. A deterministic
-//! [`MockFirmwareDetector`] backs the tests so CI never needs the binary.
-//!
-//! The parsed structs mirror a *subset* of tramiton's `BuildPlan` JSON — we
-//! deliberately do not depend on the proprietary `tramiton-core` crate.
+//! its detection. We depend on `tramiton-core` directly (same-company IP) and run
+//! its provider analysis in-process behind a [`FirmwareDetector`] port, mapping
+//! tramiton's `BuildPlan` onto a [`TargetType`]. A deterministic
+//! [`MockFirmwareDetector`] backs the tests so CI unit tests need neither the
+//! tramiton sources nor a real firmware tree.
 
 use std::path::Path;
 
-use serde::Deserialize;
-
 use compliance_core::error::CoreError;
 use compliance_core::models::{DetectedFact, TargetType};
 use compliance_core::traits::ClassifierVerdict;
 
-/// The top-level `tramiton detect --json` document (fields we use).
-#[derive(Debug, Clone, Deserialize)]
-pub struct TramitonDetect {
-    /// The selected build plan, if tramiton could form one.
-    #[serde(default)]
-    pub plan: Option<TramitonBuildPlan>,
-}
-
-/// The subset of tramiton's `BuildPlan` we consume for classification.
-#[derive(Debug, Clone, Default, Deserialize)]
-pub struct TramitonBuildPlan {
+/// A minimal firmware-detection summary, mapped from tramiton's `BuildPlan`.
+/// Kept small and tramiton-independent so the classifier and the test mock don't
+/// need to construct a full tramiton plan.
+#[derive(Debug, Clone, Default)]
+pub struct FirmwareDetection {
     /// The detecting provider (e.g. `zephyr`, `cmake`, `source-archaeology`).
-    #[serde(default)]
     pub provider: String,
     /// Detection confidence: `low` | `medium` | `high`.
-    #[serde(default)]
     pub confidence: String,
-    /// Build system (kebab-case: `zephyr`, `esp-idf`, `cmake`, `make`, ...).
-    #[serde(default)]
+    /// Build-system label (e.g. `Zephyr`, `ESP-IDF`, `CMake`).
     pub build_system: String,
-    /// Framework, when known (`zephyr`, `esp-idf`, `mbed`, `bare-metal`, ...).
+    /// Framework, when known (`zephyr`, `esp-idf`, `bare-metal`, ...).
     pub framework: Option<String>,
     /// Target board / MCU / arch.
-    #[serde(default)]
-    pub target: TramitonTarget,
+    pub target: FirmwareTarget,
     /// Unresolved gaps in the plan.
-    #[serde(default)]
     pub gaps: Vec<String>,
 }
 
-/// tramiton's target descriptor.
-#[derive(Debug, Clone, Default, Deserialize)]
-pub struct TramitonTarget {
+/// The detected firmware target (board / MCU / arch).
+#[derive(Debug, Clone, Default)]
+pub struct FirmwareTarget {
     /// Board name.
     pub board: Option<String>,
     /// MCU part.
@@ -61,57 +46,52 @@ pub struct TramitonTarget {
 /// A source of tramiton firmware detection.
 #[allow(async_fn_in_trait)]
 pub trait FirmwareDetector: Send + Sync {
-    /// Run detection over a path, returning tramiton's build plan if any.
-    async fn detect(&self, path: &Path) -> Result<Option<TramitonBuildPlan>, CoreError>;
+    /// Run detection over a path, returning a firmware detection if tramiton
+    /// could form a build plan.
+    async fn detect(&self, path: &Path) -> Result<Option<FirmwareDetection>, CoreError>;
 }
 
-/// Shells out to the `tramiton` CLI. A missing binary or a non-zero exit is
-/// treated as "no detection" rather than an error, so firmware classification
-/// degrades gracefully when tramiton is not installed.
-pub struct TramitonCli {
-    /// The `tramiton` binary to invoke.
-    pub bin: String,
-}
+/// Uses `tramiton-core` in-process. The analysis is blocking (filesystem walk),
+/// so it runs on a blocking thread to avoid stalling the async runtime. A path
+/// with no recognizable build system yields `Ok(None)`.
+pub struct TramitonNative;
 
-impl TramitonCli {
-    /// Construct from `TRAMITON_BIN` (default `tramiton`).
-    pub fn from_env() -> Self {
-        Self {
-            bin: std::env::var("TRAMITON_BIN").unwrap_or_else(|_| "tramiton".to_string()),
-        }
+impl FirmwareDetector for TramitonNative {
+    async fn detect(&self, path: &Path) -> Result<Option<FirmwareDetection>, CoreError> {
+        let path = path.to_path_buf();
+        let plan = tokio::task::spawn_blocking(move || {
+            let repo = tramiton_core::Repo::new(&path);
+            tramiton_core::provider::analyze(&repo)
+        })
+        .await
+        .map_err(|e| CoreError::Other(format!("tramiton detect task join error: {e}")))?
+        .map_err(|e| CoreError::Other(format!("tramiton analyze error: {e}")))?;
+        Ok(plan.map(|bp| detection_from_build_plan(&bp)))
     }
 }
 
-impl FirmwareDetector for TramitonCli {
-    async fn detect(&self, path: &Path) -> Result<Option<TramitonBuildPlan>, CoreError> {
-        let output = tokio::process::Command::new(&self.bin)
-            .arg("detect")
-            .arg("--json")
-            .arg(path)
-            .output()
-            .await;
-        match output {
-            Ok(o) if o.status.success() => {
-                let parsed: TramitonDetect = serde_json::from_slice(&o.stdout)?;
-                Ok(parsed.plan)
-            }
-            // Non-zero exit: tramiton ran but formed no plan.
-            Ok(_) => Ok(None),
-            // Binary not found / not executable: degrade gracefully.
-            Err(_) => Ok(None),
-        }
+/// Map tramiton's `BuildPlan` onto our minimal detection summary.
+fn detection_from_build_plan(bp: &tramiton_core::BuildPlan) -> FirmwareDetection {
+    FirmwareDetection {
+        provider: bp.provider.clone(),
+        confidence: bp.confidence.to_string(),
+        build_system: bp.build_system.label().to_string(),
+        framework: bp.framework.clone(),
+        target: FirmwareTarget {
+            board: bp.target.board.clone(),
+            mcu: bp.target.mcu.clone(),
+            arch: bp.target.arch.clone(),
+        },
+        gaps: bp.gaps.clone(),
     }
 }
 
-/// Map a tramiton build plan to a target type. Framework/build-system signals
+/// Map a firmware detection to a target type. Framework/build-system signals
 /// distinguish RTOS from bare-metal from Yocto.
-pub fn plan_to_target_type(plan: &TramitonBuildPlan) -> TargetType {
-    let framework = plan.framework.as_deref().unwrap_or("").to_lowercase();
-    let build_system = plan.build_system.to_lowercase();
-    let signal = format!(
-        "{framework} {build_system} {}",
-        plan.provider.to_lowercase()
-    );
+pub fn detection_to_target_type(det: &FirmwareDetection) -> TargetType {
+    let framework = det.framework.as_deref().unwrap_or("").to_lowercase();
+    let build_system = det.build_system.to_lowercase();
+    let signal = format!("{framework} {build_system} {}", det.provider.to_lowercase());
 
     const RTOS: [&str; 6] = ["zephyr", "esp-idf", "freertos", "nuttx", "riot", "chibios"];
     if signal.contains("bitbake") || signal.contains("yocto") || signal.contains("openembedded") {
@@ -133,35 +113,35 @@ fn confidence_score(label: &str) -> f32 {
     }
 }
 
-/// Turn a tramiton build plan into a classifier verdict, carrying the MCU / board
+/// Turn a firmware detection into a classifier verdict, carrying the MCU / board
 /// / build-system as facts.
-pub fn plan_to_verdict(plan: &TramitonBuildPlan) -> ClassifierVerdict {
-    let target_type = plan_to_target_type(plan);
+pub fn detection_to_verdict(det: &FirmwareDetection) -> ClassifierVerdict {
+    let target_type = detection_to_target_type(det);
     let mut facts = vec![DetectedFact::new(
         "build_system",
-        plan.build_system.clone(),
+        det.build_system.clone(),
         "tramiton",
     )];
-    if let Some(fw) = &plan.framework {
+    if let Some(fw) = &det.framework {
         facts.push(DetectedFact::new("framework", fw.clone(), "tramiton"));
     }
-    if let Some(mcu) = &plan.target.mcu {
+    if let Some(mcu) = &det.target.mcu {
         facts.push(DetectedFact::new("mcu", mcu.clone(), "tramiton"));
     }
-    if let Some(board) = &plan.target.board {
+    if let Some(board) = &det.target.board {
         facts.push(DetectedFact::new("board", board.clone(), "tramiton"));
     }
-    if let Some(arch) = &plan.target.arch {
+    if let Some(arch) = &det.target.arch {
         facts.push(DetectedFact::new("arch", arch.clone(), "tramiton"));
     }
     ClassifierVerdict {
         target_type,
-        confidence: confidence_score(&plan.confidence),
+        confidence: confidence_score(&det.confidence),
         facts,
         rationale: format!(
             "tramiton detected build system '{}'{}",
-            plan.build_system,
-            plan.framework
+            det.build_system,
+            det.framework
                 .as_ref()
                 .map(|f| format!(" (framework {f})"))
                 .unwrap_or_default()
@@ -169,15 +149,15 @@ pub fn plan_to_verdict(plan: &TramitonBuildPlan) -> ClassifierVerdict {
     }
 }
 
-/// A deterministic [`FirmwareDetector`] for tests — returns a preset plan.
+/// A deterministic [`FirmwareDetector`] for tests — returns a preset detection.
 pub struct MockFirmwareDetector {
-    /// The plan to return (or `None` for "no detection").
-    pub plan: Option<TramitonBuildPlan>,
+    /// The detection to return (or `None` for "no detection").
+    pub detection: Option<FirmwareDetection>,
 }
 
 impl FirmwareDetector for MockFirmwareDetector {
-    async fn detect(&self, _path: &Path) -> Result<Option<TramitonBuildPlan>, CoreError> {
-        Ok(self.plan.clone())
+    async fn detect(&self, _path: &Path) -> Result<Option<FirmwareDetection>, CoreError> {
+        Ok(self.detection.clone())
     }
 }
 
@@ -186,13 +166,13 @@ impl FirmwareDetector for MockFirmwareDetector {
 mod tests {
     use super::*;
 
-    fn plan(build_system: &str, framework: Option<&str>) -> TramitonBuildPlan {
-        TramitonBuildPlan {
+    fn detection(build_system: &str, framework: Option<&str>) -> FirmwareDetection {
+        FirmwareDetection {
             provider: build_system.to_string(),
             confidence: "high".to_string(),
             build_system: build_system.to_string(),
             framework: framework.map(|s| s.to_string()),
-            target: TramitonTarget {
+            target: FirmwareTarget {
                 mcu: Some("stm32f429".to_string()),
                 ..Default::default()
             },
@@ -203,7 +183,7 @@ mod tests {
     #[test]
     fn zephyr_maps_to_rtos() {
         assert_eq!(
-            plan_to_target_type(&plan("zephyr", Some("zephyr"))),
+            detection_to_target_type(&detection("zephyr", Some("zephyr"))),
             TargetType::FirmwareRtos
         );
     }
@@ -211,7 +191,7 @@ mod tests {
     #[test]
     fn bare_cmake_maps_to_bare_metal() {
         assert_eq!(
-            plan_to_target_type(&plan("cmake", Some("bare-metal"))),
+            detection_to_target_type(&detection("cmake", Some("bare-metal"))),
             TargetType::FirmwareBareMetal
         );
     }
@@ -219,14 +199,14 @@ mod tests {
     #[test]
     fn bitbake_maps_to_yocto() {
         assert_eq!(
-            plan_to_target_type(&plan("bitbake", None)),
+            detection_to_target_type(&detection("bitbake", None)),
             TargetType::EmbeddedLinuxYocto
         );
     }
 
     #[test]
     fn verdict_carries_mcu_fact_and_confidence() {
-        let v = plan_to_verdict(&plan("esp-idf", Some("esp-idf")));
+        let v = detection_to_verdict(&detection("esp-idf", Some("esp-idf")));
         assert_eq!(v.target_type, TargetType::FirmwareRtos);
         assert!((v.confidence - 0.9).abs() < f32::EPSILON);
         assert!(v
@@ -234,13 +214,4 @@ mod tests {
             .iter()
             .any(|f| f.key == "mcu" && f.value == "stm32f429"));
     }
-
-    #[test]
-    fn detect_json_parses() {
-        let json = r#"{"repo":"/x","detections":[],"plan":{"provider":"zephyr","confidence":"high","build_system":"zephyr","framework":"zephyr","target":{"mcu":"nrf52840","board":"nrf52840dk","arch":"arm"},"gaps":[]}}"#;
-        let parsed: TramitonDetect = serde_json::from_str(json).expect("parse");
-        let plan = parsed.plan.expect("plan present");
-        assert_eq!(plan.target.mcu.as_deref(), Some("nrf52840"));
-        assert_eq!(plan_to_target_type(&plan), TargetType::FirmwareRtos);
-    }
 }

compliance-agent/src/classify/mod.rs

@@ -9,8 +9,7 @@ mod firmware;
 mod language;
 
 pub use firmware::{
-    FirmwareDetector, MockFirmwareDetector, TramitonBuildPlan, TramitonCli, TramitonDetect,
-    TramitonTarget,
+    FirmwareDetection, FirmwareDetector, FirmwareTarget, MockFirmwareDetector, TramitonNative,
 };
 pub use language::HeuristicClassifier;
 
@@ -23,7 +22,7 @@ use compliance_core::models::{
 };
 use compliance_core::traits::{ClassificationInput, ClassifierVerdict, TargetClassifier};
 
-use firmware::plan_to_verdict;
+use firmware::detection_to_verdict;
 
 /// Classify a target from its artifacts and their ingested working paths, using
 /// the heuristic classifier plus the tramiton firmware detector. Verdicts are
@@ -60,8 +59,8 @@ pub async fn classify_target<D: FirmwareDetector>(
         let Some(path) = working_paths.get(&artifact.id) else {
             continue;
         };
-        if let Some(plan) = firmware_detector.detect(path).await? {
-            verdicts.push(plan_to_verdict(&plan));
+        if let Some(detection) = firmware_detector.detect(path).await? {
+            verdicts.push(detection_to_verdict(&detection));
             tramiton_used = true;
         }
     }
@@ -155,7 +154,7 @@ mod tests {
     }
 
     fn no_firmware() -> MockFirmwareDetector {
-        MockFirmwareDetector { plan: None }
+        MockFirmwareDetector { detection: None }
     }
 
     #[tokio::test]
@@ -190,12 +189,12 @@ mod tests {
         target.artifacts.push(artifact);
 
         let detector = MockFirmwareDetector {
-            plan: Some(TramitonBuildPlan {
+            detection: Some(FirmwareDetection {
                 provider: "zephyr".to_string(),
                 confidence: "high".to_string(),
                 build_system: "zephyr".to_string(),
                 framework: Some("zephyr".to_string()),
-                target: TramitonTarget {
+                target: FirmwareTarget {
                     mcu: Some("nrf52840".to_string()),
                     ..Default::default()
                 },

compliance-agent/src/database.rs

@@ -179,6 +179,23 @@ impl DatabasePool {
             .collect())
     }
 
+    /// Tenant ids for every provisioned tenant database, derived by stripping
+    /// the `<prefix>_` from the database names. Skips the admin database
+    /// (`<prefix>__admin`). Hash-fallback names (very long tenant_ids) are lost
+    /// at the cluster level and cannot be recovered here — in practice tenant
+    /// ids are UUIDs and never hit that path. Used by the migration CLI's
+    /// `--all` mode.
+    pub async fn list_tenant_ids(&self) -> Result<Vec<String>, AgentError> {
+        let prefix = format!("{}_", self.db_prefix);
+        Ok(self
+            .list_tenant_db_names()
+            .await?
+            .into_iter()
+            .filter_map(|n| n.strip_prefix(&prefix).map(str::to_string))
+            .filter(|id| !id.starts_with('_'))
+            .collect())
+    }
+
     /// Drop the database for a specific tenant. Used by GDPR delete
     /// and tenant offboarding. Idempotent — dropping a non-existent
     /// database is a no-op at the driver level.
@@ -521,6 +538,13 @@ impl Database {
         self.inner.collection("onboarded_targets")
     }
 
+    /// A typed handle to an arbitrary collection by name. For bookkeeping
+    /// collections without a dedicated model (e.g. `schema_migrations`,
+    /// `onboarding_migration_log`).
+    pub fn collection_named<T: Send + Sync>(&self, name: &str) -> Collection<T> {
+        self.inner.collection(name)
+    }
+
     pub fn dast_scan_runs(&self) -> Collection<DastScanRun> {
         self.inner.collection("dast_scan_runs")
     }

compliance-agent/src/lib.rs

@@ -8,6 +8,7 @@ pub mod database;
 pub mod error;
 pub mod ingest;
 pub mod llm;
+pub mod migrate;
 pub mod pentest;
 pub mod pipeline;
 pub mod rag;

compliance-agent/src/main.rs

@@ -1,4 +1,50 @@
-use compliance_agent::{agent, api, config, database, scheduler, ssh, webhooks};
+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>> {
@@ -31,6 +77,13 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
     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...");

compliance-agent/src/migrate/mod.rs

@@ -0,0 +1,8 @@
+//! One-time data migrations.
+//!
+//! Currently just the onboarding backfill ([`onboarding`]), which folds the
+//! legacy `repositories` and `dast_targets` collections into the unified
+//! `onboarded_targets` collection, preserving `_id` so every downstream record
+//! keyed by `repo_id` / `target_id` keeps resolving.
+
+pub mod onboarding;

compliance-agent/src/migrate/onboarding.rs

@@ -0,0 +1,406 @@
+//! Backfill: legacy `repositories` + `dast_targets` → `onboarded_targets`.
+//!
+//! The transforms here are **id-preserving**: an [`OnboardedTarget`] keeps the
+//! same `_id` as the `TrackedRepository` / `DastTarget` it came from, so every
+//! downstream collection keyed by that hex id (findings, sbom, scan_runs,
+//! graph, dast_*, pentest_*) keeps resolving with zero row rewrites, and
+//! existing webhook URLs keep working. The mapping functions are pure and unit
+//! tested; the DB orchestration (idempotent per-tenant backfill + revert) is a
+//! thin driver over them.
+
+use compliance_core::models::{
+    Artifact, ArtifactKind, DastTarget, DastTargetType, GitArtifactConfig, IssueTrackerConfig,
+    OnboardedTarget, TargetType, TrackedRepository, WebArtifactConfig,
+};
+use futures_util::TryStreamExt;
+use mongodb::bson::{doc, Document};
+
+use crate::database::Database;
+use crate::error::AgentError;
+
+/// Marker id in `schema_migrations` recording that the backfill has run.
+const MIGRATION_MARKER: &str = "onboarding_backfill_v1";
+
+/// Summary of a backfill run.
+#[derive(Debug, Clone, Default, PartialEq, Eq)]
+pub struct MigrationReport {
+    /// Repositories turned into onboarded targets.
+    pub repos_migrated: u64,
+    /// DAST targets folded into an existing (repo-linked) target as a LiveUrl.
+    pub dast_targets_folded: u64,
+    /// DAST targets with no repo link, migrated as standalone targets.
+    pub dast_targets_standalone: u64,
+    /// Records skipped because a target with that `_id` already existed.
+    pub skipped_existing: u64,
+}
+
+/// Map a legacy `DastTargetType` to a unified [`TargetType`]. REST/GraphQL APIs
+/// are backend services; a browser app is a web app.
+fn target_type_for_dast(kind: &DastTargetType) -> TargetType {
+    match kind {
+        DastTargetType::WebApp => TargetType::WebApp,
+        DastTargetType::RestApi | DastTargetType::GraphQl => TargetType::BackendService,
+    }
+}
+
+/// Build the LiveUrl artifact for a DAST target (its base URL + crawl config +
+/// auth). Shared by fold-in and standalone migration.
+pub fn dast_to_artifact(dast: &DastTarget) -> Artifact {
+    let mut artifact = Artifact::live_url(dast.base_url.clone());
+    artifact.web = Some(WebArtifactConfig {
+        target_kind: dast.target_type.clone(),
+        excluded_paths: dast.excluded_paths.clone(),
+        max_crawl_depth: dast.max_crawl_depth,
+        rate_limit: dast.rate_limit,
+        allow_destructive: dast.allow_destructive,
+    });
+    artifact.auth = dast.auth_config.clone().map(Into::into);
+    artifact
+}
+
+/// Map a `TrackedRepository` to an onboarded target, preserving `_id`. The git
+/// remote becomes a `GitRepo` artifact carrying the repo's branch, watermark,
+/// and auth; tracker config folds into `scan_config`.
+///
+/// `target_type` is a safe default (`BackendService`) — the classifier can
+/// refine it later; `classification` is left `None` (unconfirmed).
+pub fn repo_to_target(repo: &TrackedRepository) -> OnboardedTarget {
+    let mut target = OnboardedTarget::new(repo.name.clone(), TargetType::BackendService);
+    target.id = repo.id;
+
+    let mut artifact = Artifact::git_repo(repo.git_url.clone(), repo.default_branch.clone());
+    artifact.git = Some(GitArtifactConfig {
+        default_branch: repo.default_branch.clone(),
+        last_scanned_commit: repo.last_scanned_commit.clone(),
+        local_path: repo.local_path.clone(),
+    });
+    if repo.auth_token.is_some() || repo.auth_username.is_some() {
+        artifact.auth = Some(compliance_core::models::ArtifactAuth {
+            method: "token".to_string(),
+            username: repo.auth_username.clone(),
+            secret: repo.auth_token.clone(),
+            ..Default::default()
+        });
+    }
+    target.artifacts.push(artifact);
+
+    if repo.tracker_type.is_some() {
+        target.scan_config.issue_tracker = Some(IssueTrackerConfig {
+            tracker_type: repo.tracker_type.clone(),
+            owner: repo.tracker_owner.clone(),
+            repo: repo.tracker_repo.clone(),
+            token: repo.tracker_token.clone(),
+        });
+    }
+
+    target.scan_schedule = repo.scan_schedule.clone();
+    target.webhook_enabled = repo.webhook_enabled;
+    target.webhook_secret = repo.webhook_secret.clone();
+    target.findings_count = repo.findings_count;
+    target.created_at = repo.created_at;
+    target.updated_at = repo.updated_at;
+    target
+}
+
+/// Append a DAST target's LiveUrl artifact onto an existing (repo-derived)
+/// target. If the repo default was `BackendService` but the DAST target is a
+/// browser web app, promote the type to `WebApp`.
+pub fn fold_dast_into_target(target: &mut OnboardedTarget, dast: &DastTarget) {
+    if matches!(dast.target_type, DastTargetType::WebApp)
+        && target.target_type == TargetType::BackendService
+    {
+        target.target_type = TargetType::WebApp;
+    }
+    if !target.has(ArtifactKind::LiveUrl) {
+        target.artifacts.push(dast_to_artifact(dast));
+    }
+}
+
+/// Map a repo-less DAST target to a standalone onboarded target, preserving `_id`.
+pub fn dast_to_standalone_target(dast: &DastTarget) -> OnboardedTarget {
+    let mut target =
+        OnboardedTarget::new(dast.name.clone(), target_type_for_dast(&dast.target_type));
+    target.id = dast.id;
+    target.artifacts.push(dast_to_artifact(dast));
+    target.created_at = dast.created_at;
+    target.updated_at = dast.updated_at;
+    target
+}
+
+/// Whether the onboarding backfill has already been applied to this database.
+pub async fn already_applied(db: &Database) -> Result<bool, AgentError> {
+    let found = db
+        .collection_named::<Document>("schema_migrations")
+        .find_one(doc! { "_id": MIGRATION_MARKER })
+        .await?;
+    Ok(found.is_some())
+}
+
+/// Backfill `onboarded_targets` from `repositories` + `dast_targets` for one
+/// tenant database.
+///
+/// Id-preserving and **idempotent**: targets that already exist (by `_id`) are
+/// skipped, so re-running is safe. With `dry_run`, computes the report without
+/// writing. The legacy collections are never deleted; the only mutation outside
+/// `onboarded_targets` is the history relink of folded DAST targets, which is
+/// logged so [`revert`] can undo it.
+pub async fn backfill_onboarded_targets(
+    db: &Database,
+    dry_run: bool,
+) -> Result<MigrationReport, AgentError> {
+    let mut report = MigrationReport::default();
+
+    // 1. repositories -> onboarded_targets (preserve _id, skip existing).
+    let mut repos = db.repositories().find(doc! {}).await?;
+    while let Some(repo) = repos.try_next().await? {
+        let Some(id) = repo.id else { continue };
+        if db
+            .onboarded_targets()
+            .find_one(doc! { "_id": id })
+            .await?
+            .is_some()
+        {
+            report.skipped_existing += 1;
+            continue;
+        }
+        if !dry_run {
+            db.onboarded_targets()
+                .insert_one(repo_to_target(&repo))
+                .await?;
+        }
+        report.repos_migrated += 1;
+    }
+
+    // 2. dast_targets -> fold into the linked repo target, or migrate standalone.
+    let mut dasts = db.dast_targets().find(doc! {}).await?;
+    while let Some(dast) = dasts.try_next().await? {
+        let Some(dast_id) = dast.id else { continue };
+        let repo_oid = dast
+            .repo_id
+            .as_deref()
+            .and_then(|r| mongodb::bson::oid::ObjectId::parse_str(r).ok());
+        let linked = match repo_oid {
+            Some(oid) => db.onboarded_targets().find_one(doc! { "_id": oid }).await?,
+            None => None,
+        };
+
+        match (linked, repo_oid) {
+            // Fold into an existing repo-derived target.
+            (Some(mut target), Some(oid)) => {
+                if target.has(ArtifactKind::LiveUrl) {
+                    report.skipped_existing += 1; // already folded on a prior run
+                    continue;
+                }
+                fold_dast_into_target(&mut target, &dast);
+                if !dry_run {
+                    db.onboarded_targets()
+                        .replace_one(doc! { "_id": oid }, &target)
+                        .await?;
+                    relink_history(db, &dast_id.to_hex(), &oid.to_hex()).await?;
+                }
+                report.dast_targets_folded += 1;
+            }
+            // No linked repo target: migrate as a standalone target (keeps _id).
+            _ => {
+                if db
+                    .onboarded_targets()
+                    .find_one(doc! { "_id": dast_id })
+                    .await?
+                    .is_some()
+                {
+                    report.skipped_existing += 1;
+                    continue;
+                }
+                if !dry_run {
+                    db.onboarded_targets()
+                        .insert_one(dast_to_standalone_target(&dast))
+                        .await?;
+                }
+                report.dast_targets_standalone += 1;
+            }
+        }
+    }
+
+    if !dry_run {
+        db.collection_named::<Document>("schema_migrations")
+            .update_one(
+                doc! { "_id": MIGRATION_MARKER },
+                doc! { "$set": { "applied_at": mongodb::bson::DateTime::now() } },
+            )
+            .upsert(true)
+            .await?;
+    }
+    Ok(report)
+}
+
+/// Relink DAST scan runs and pentest sessions from the old DAST target id to the
+/// unified target id, logging each move so [`revert`] can undo it.
+///
+/// Note: if multiple DAST targets fold into the same repo target, revert
+/// restores only the last-logged mapping — a rare edge. The source collections
+/// (`repositories`, `dast_targets`) are never deleted, so no data is lost.
+async fn relink_history(db: &Database, old_id: &str, new_id: &str) -> Result<(), AgentError> {
+    db.dast_scan_runs()
+        .update_many(
+            doc! { "target_id": old_id },
+            doc! { "$set": { "target_id": new_id } },
+        )
+        .await?;
+    db.pentest_sessions()
+        .update_many(
+            doc! { "target_id": old_id },
+            doc! { "$set": { "target_id": new_id } },
+        )
+        .await?;
+    db.collection_named::<Document>("onboarding_migration_log")
+        .insert_one(doc! { "old_target_id": old_id, "new_target_id": new_id })
+        .await?;
+    Ok(())
+}
+
+/// Undo the backfill: replay the relink log in reverse, drop `onboarded_targets`
+/// and the log, and clear the marker. The legacy collections are untouched, so
+/// this restores the pre-migration state.
+pub async fn revert(db: &Database) -> Result<(), AgentError> {
+    let log = db.collection_named::<Document>("onboarding_migration_log");
+    let mut cursor = log.find(doc! {}).await?;
+    while let Some(entry) = cursor.try_next().await? {
+        if let (Ok(old), Ok(new)) = (
+            entry.get_str("old_target_id"),
+            entry.get_str("new_target_id"),
+        ) {
+            db.dast_scan_runs()
+                .update_many(
+                    doc! { "target_id": new },
+                    doc! { "$set": { "target_id": old } },
+                )
+                .await?;
+            db.pentest_sessions()
+                .update_many(
+                    doc! { "target_id": new },
+                    doc! { "$set": { "target_id": old } },
+                )
+                .await?;
+        }
+    }
+    db.onboarded_targets().drop().await?;
+    log.drop().await?;
+    db.collection_named::<Document>("schema_migrations")
+        .delete_one(doc! { "_id": MIGRATION_MARKER })
+        .await?;
+    Ok(())
+}
+
+#[cfg(test)]
+#[allow(clippy::expect_used, clippy::unwrap_used)]
+mod tests {
+    use super::*;
+    use compliance_core::models::{DastAuthConfig, TrackerType};
+
+    fn repo() -> TrackedRepository {
+        let mut r = TrackedRepository::new("acme".to_string(), "https://git/acme.git".to_string());
+        r.id = Some(mongodb::bson::oid::ObjectId::new());
+        r.default_branch = "develop".to_string();
+        r.last_scanned_commit = Some("abc123".to_string());
+        r.auth_token = Some("pat".to_string());
+        r.auth_username = Some("bob".to_string());
+        r.tracker_type = Some(TrackerType::Gitea);
+        r.tracker_owner = Some("acme".to_string());
+        r.findings_count = 7;
+        r
+    }
+
+    fn dast(repo_id: Option<String>, kind: DastTargetType) -> DastTarget {
+        let mut d = DastTarget::new(
+            "acme-web".to_string(),
+            "https://acme.example.com".to_string(),
+            kind,
+        );
+        d.id = Some(mongodb::bson::oid::ObjectId::new());
+        d.repo_id = repo_id;
+        d.max_crawl_depth = 5;
+        d.auth_config = Some(DastAuthConfig {
+            method: "bearer".to_string(),
+            login_url: None,
+            username: None,
+            password: None,
+            token: Some("tok".to_string()),
+            headers: None,
+        });
+        d
+    }
+
+    #[test]
+    fn repo_maps_preserving_id_and_git_artifact() {
+        let r = repo();
+        let t = repo_to_target(&r);
+        assert_eq!(t.id, r.id); // id preserved
+        assert_eq!(t.findings_count, 7);
+        assert_eq!(t.scan_schedule, r.scan_schedule);
+        let git = t.code_artifact().expect("git artifact");
+        assert_eq!(git.kind, ArtifactKind::GitRepo);
+        assert_eq!(git.source_ref, "https://git/acme.git");
+        let gc = git.git.as_ref().expect("git config");
+        assert_eq!(gc.default_branch, "develop");
+        assert_eq!(gc.last_scanned_commit.as_deref(), Some("abc123"));
+        let auth = git.auth.as_ref().expect("auth");
+        assert_eq!(auth.secret.as_deref(), Some("pat"));
+        assert_eq!(auth.username.as_deref(), Some("bob"));
+        assert_eq!(
+            t.scan_config
+                .issue_tracker
+                .as_ref()
+                .and_then(|it| it.tracker_type.clone()),
+            Some(TrackerType::Gitea)
+        );
+    }
+
+    #[test]
+    fn standalone_dast_maps_preserving_id_and_live_url() {
+        let d = dast(None, DastTargetType::WebApp);
+        let t = dast_to_standalone_target(&d);
+        assert_eq!(t.id, d.id);
+        assert_eq!(t.target_type, TargetType::WebApp);
+        let url = t.live_url().expect("live url");
+        assert_eq!(url.source_ref, "https://acme.example.com");
+        let web = url.web.as_ref().expect("web config");
+        assert_eq!(web.max_crawl_depth, 5);
+        assert_eq!(
+            url.auth.as_ref().and_then(|a| a.secret.clone()),
+            Some("tok".to_string())
+        );
+    }
+
+    #[test]
+    fn rest_api_dast_maps_to_backend_service() {
+        let d = dast(None, DastTargetType::RestApi);
+        assert_eq!(
+            dast_to_standalone_target(&d).target_type,
+            TargetType::BackendService
+        );
+    }
+
+    #[test]
+    fn fold_adds_live_url_and_promotes_webapp() {
+        let mut t = repo_to_target(&repo());
+        assert_eq!(t.target_type, TargetType::BackendService);
+        fold_dast_into_target(&mut t, &dast(Some("x".to_string()), DastTargetType::WebApp));
+        assert_eq!(t.target_type, TargetType::WebApp); // promoted
+        assert!(t.has(ArtifactKind::LiveUrl));
+        assert!(t.has(ArtifactKind::GitRepo));
+    }
+
+    #[test]
+    fn fold_is_idempotent_on_live_url() {
+        let mut t = repo_to_target(&repo());
+        let d = dast(Some("x".to_string()), DastTargetType::WebApp);
+        fold_dast_into_target(&mut t, &d);
+        fold_dast_into_target(&mut t, &d);
+        let live_urls = t
+            .artifacts
+            .iter()
+            .filter(|a| a.kind == ArtifactKind::LiveUrl)
+            .count();
+        assert_eq!(live_urls, 1);
+    }
+}

compliance-agent/tests/integration/migration.rs

@@ -0,0 +1,156 @@
+// Integration tests for the onboarding backfill migration.
+//
+// Requires MongoDB (set TEST_MONGODB_URI if not at the default).
+// Not run in CI (which is `--lib` only) — run locally:
+//   cargo test -p compliance-agent --test e2e migration
+
+use compliance_agent::database::{Database, DatabasePool};
+use compliance_agent::migrate::onboarding;
+use compliance_core::models::{
+    ArtifactKind, DastTarget, DastTargetType, TargetType, TrackedRepository,
+};
+use mongodb::bson::{doc, Document};
+
+async fn fresh_db() -> (DatabasePool, String, Database) {
+    let uri = std::env::var("TEST_MONGODB_URI")
+        .unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
+    // Prefix must fit the pool's 30-char cap (`<prefix>_<32 hex>` <= 63).
+    let prefix = format!("t_{}", &uuid::Uuid::new_v4().simple().to_string()[..16]);
+    let pool = DatabasePool::connect(&uri, &prefix)
+        .await
+        .expect("connect mongo");
+    let db = pool.for_tenant_id("t1").await.expect("tenant db");
+    (pool, prefix, db)
+}
+
+async fn cleanup(pool: &DatabasePool, prefix: &str) {
+    if let Ok(names) = pool.client().list_database_names().await {
+        for n in names {
+            if n.starts_with(prefix) {
+                pool.client().database(&n).drop().await.ok();
+            }
+        }
+    }
+}
+
+#[tokio::test]
+async fn backfill_folds_relinks_is_idempotent_and_reversible() {
+    let (pool, prefix, db) = fresh_db().await;
+
+    // Seed a repo.
+    let repo = TrackedRepository::new("acme".into(), "https://git/acme.git".into());
+    let repo_id = db
+        .repositories()
+        .insert_one(repo)
+        .await
+        .expect("insert repo")
+        .inserted_id
+        .as_object_id()
+        .expect("repo oid");
+
+    // A DAST target linked to the repo (folds + promotes to WebApp + relinks).
+    let mut linked = DastTarget::new(
+        "acme-web".into(),
+        "https://acme.example.com".into(),
+        DastTargetType::WebApp,
+    );
+    linked.repo_id = Some(repo_id.to_hex());
+    let linked_id = db
+        .dast_targets()
+        .insert_one(linked)
+        .await
+        .expect("insert linked dast")
+        .inserted_id
+        .as_object_id()
+        .expect("linked oid");
+
+    // A repo-less DAST target (standalone).
+    let standalone = DastTarget::new(
+        "acme-api".into(),
+        "https://api.acme.com".into(),
+        DastTargetType::RestApi,
+    );
+    let standalone_id = db
+        .dast_targets()
+        .insert_one(standalone)
+        .await
+        .expect("insert standalone dast")
+        .inserted_id
+        .as_object_id()
+        .expect("standalone oid");
+
+    // A DAST scan run pointing at the linked target — should be relinked to the repo.
+    db.collection_named::<Document>("dast_scan_runs")
+        .insert_one(doc! { "target_id": linked_id.to_hex(), "status": "completed" })
+        .await
+        .expect("insert dast run");
+
+    // --- Backfill ---
+    assert!(!onboarding::already_applied(&db).await.unwrap());
+    let report = onboarding::backfill_onboarded_targets(&db, false)
+        .await
+        .expect("backfill");
+    assert_eq!(report.repos_migrated, 1);
+    assert_eq!(report.dast_targets_folded, 1);
+    assert_eq!(report.dast_targets_standalone, 1);
+    assert!(onboarding::already_applied(&db).await.unwrap());
+
+    // Repo target: preserved _id, has git + folded live-url, promoted to WebApp.
+    let repo_target = db
+        .onboarded_targets()
+        .find_one(doc! { "_id": repo_id })
+        .await
+        .unwrap()
+        .expect("repo target");
+    assert!(repo_target.has(ArtifactKind::GitRepo));
+    assert!(repo_target.has(ArtifactKind::LiveUrl));
+    assert_eq!(repo_target.target_type, TargetType::WebApp);
+
+    // Standalone target: preserved _id, live-url, backend service.
+    let standalone_target = db
+        .onboarded_targets()
+        .find_one(doc! { "_id": standalone_id })
+        .await
+        .unwrap()
+        .expect("standalone target");
+    assert!(standalone_target.has(ArtifactKind::LiveUrl));
+    assert_eq!(standalone_target.target_type, TargetType::BackendService);
+
+    // The DAST run was relinked from the old dast id to the repo (unified) id.
+    let run = db
+        .collection_named::<Document>("dast_scan_runs")
+        .find_one(doc! {})
+        .await
+        .unwrap()
+        .expect("run");
+    assert_eq!(run.get_str("target_id").unwrap(), repo_id.to_hex());
+
+    // --- Idempotent: re-run migrates nothing new ---
+    let again = onboarding::backfill_onboarded_targets(&db, false)
+        .await
+        .expect("backfill again");
+    assert_eq!(again.repos_migrated, 0);
+    assert_eq!(again.dast_targets_folded, 0);
+    assert_eq!(again.dast_targets_standalone, 0);
+    assert!(again.skipped_existing >= 2);
+
+    // --- Revert: onboarded targets gone, relink undone, marker cleared ---
+    onboarding::revert(&db).await.expect("revert");
+    assert_eq!(
+        db.onboarded_targets()
+            .count_documents(doc! {})
+            .await
+            .unwrap(),
+        0
+    );
+    let run_after = db
+        .collection_named::<Document>("dast_scan_runs")
+        .find_one(doc! {})
+        .await
+        .unwrap()
+        .expect("run");
+    assert_eq!(run_after.get_str("target_id").unwrap(), linked_id.to_hex());
+    assert!(!onboarding::already_applied(&db).await.unwrap());
+
+    cleanup(&pool, &prefix).await;
+}

compliance-agent/tests/integration/mod.rs

@@ -7,3 +7,4 @@
 // Or nightly: (via CI with MongoDB service container)
 
 mod api;
+mod migration;