Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Fable 5 e99c34630e fix(audit): bump crossbeam-epoch to 0.9.20 (RUSTSEC-2026-0204)
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
Invalid pointer dereference in the `fmt::Pointer` impl for `Atomic`/`Shared`
when the underlying pointer is invalid. Lockfile-only bump; no code changes.

Refs #118.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 15:30:45 +02:00
Sharang ParnerkarandClaude Fable 5 def7371d6a feat(onboarding): unified multi-target model + scan matrix foundation
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 / Check (pull_request) Failing after 4m28s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
Backend foundation for the artifact-aware onboarding redesign (epic #118),
replacing the git-only TrackedRepository / DastTarget split with a unified
OnboardedTarget classified by target type and carrying its artifacts.

compliance-core:
- OnboardedTarget model: TargetType (9 families), ArtifactKind (8 kinds),
  Artifact with per-kind config, ArtifactAuth (folds git auth + DastAuthConfig),
  Classification, TargetScanConfig (reuses pentest + tracker config).
- Table-driven scan-applicability matrix: applicable_scans / rules_for /
  supports_pentest, with SAST umbrella + firmware/PLC/mobile/DAST gated on
  artifact presence.
- TargetClassifier port trait, mirroring the Scanner trait.
- Additive ScanType/ScanPhase variants (firmware/PLC/mobile/container);
  ScanType is now Copy.

compliance-agent:
- onboarded_targets collection accessor + indexes (artifacts.source_ref,
  artifacts.kind, target_type).
- Drop a now-redundant ScanType clone surfaced by the Copy derive.

Foundation only (steps 1-2 of the approved plan); legacy scan paths untouched.
17 new unit tests; passes fmt + clippy -D warnings (agent, dashboard, mcp).

Refs #118, #119, #122, #121.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 12:23:51 +02:00
30 changed files with 12 additions and 2837 deletions
+5 -48
View File
@@ -9,25 +9,10 @@ on:
env:
CARGO_TERM_COLOR: always
RUSTFLAGS: "-D warnings"
# Compile cache: sccache -> Hetzner S3 (breakpilot-sccache), runner-independent
# and persistent across CI runs (own key prefix). Reuses the shared cluster S3
# creds (same bucket as werkpilot). Requires repo secrets HETZNER_S3_ACCESS_KEY
# and HETZNER_S3_SECRET_KEY.
# sccache caches compilation artifacts within a job so that compiling
# both --features server and --features web shares common crate work.
RUSTC_WRAPPER: /usr/local/bin/sccache
SCCACHE_BUCKET: breakpilot-sccache
SCCACHE_ENDPOINT: https://nbg1.your-objectstorage.com
SCCACHE_REGION: auto
SCCACHE_S3_USE_SSL: "true"
SCCACHE_S3_KEY_PREFIX: compliance-scanner
AWS_ACCESS_KEY_ID: ${{ secrets.HETZNER_S3_ACCESS_KEY }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.HETZNER_S3_SECRET_KEY }}
# compliance-agent depends on tramiton-core via git; use the system git so the
# credential rewrite below (see "Configure git auth ...") is honored on fetch.
CARGO_NET_GIT_FETCH_WITH_CLI: "true"
# Throttle cargo so a ~670-crate concurrent download burst doesn't 429 the
# Kellnr mirror: fewer concurrent connections (HTTP/1.1) + more retries.
CARGO_NET_RETRY: "10"
CARGO_HTTP_MULTIPLEXING: "false"
SCCACHE_DIR: /tmp/sccache
# Cancel in-progress runs for the same branch/PR
concurrency:
@@ -51,44 +36,16 @@ jobs:
git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}"
git checkout FETCH_HEAD
# Resolve crates.io deps through the self-hosted Kellnr mirror (cached,
# crates.io-independent). Git deps (tramiton-core) are unaffected — source
# replacement only applies to crates.io-sourced crates.
- name: Use Kellnr crates.io mirror
run: |
: "${CARGO_HOME:=/usr/local/cargo}"
mkdir -p "$CARGO_HOME"
{
echo '[source.crates-io]'
echo 'replace-with = "kellnr"'
echo '[registries.kellnr]'
echo 'index = "sparse+https://crates.meghsakha.com/api/v1/cratesio/"'
} >> "$CARGO_HOME/config.toml"
env:
RUSTC_WRAPPER: ""
- name: Install tools
run: |
rustup component add rustfmt clippy
curl -fsSL https://github.com/mozilla/sccache/releases/download/v0.10.0/sccache-v0.10.0-x86_64-unknown-linux-musl.tar.gz \
| tar xz --strip-components=1 -C /usr/local/bin/ sccache-v0.10.0-x86_64-unknown-linux-musl/sccache
curl -fsSL https://github.com/mozilla/sccache/releases/download/v0.9.1/sccache-v0.9.1-x86_64-unknown-linux-musl.tar.gz \
| tar xz --strip-components=1 -C /usr/local/bin/ sccache-v0.9.1-x86_64-unknown-linux-musl/sccache
chmod +x /usr/local/bin/sccache
cargo install cargo-audit --locked
env:
RUSTC_WRAPPER: ""
# compliance-agent has a git dependency on tramiton-core (a private repo on
# this Gitea instance). Rewrite its SSH URL to HTTPS + a PAT so the runner
# can fetch it. Requires the repo secret TRAMITON_FETCH_TOKEN (a Gitea PAT
# with read:repository, owned by a user with access to sharang/tramiton).
# (Honored on fetch because CARGO_NET_GIT_FETCH_WITH_CLI=true uses system git.)
- name: Configure git auth for private tramiton dependency
run: |
git config --global \
url."https://sharang:${{ 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
Generated
+2 -65
View File
@@ -692,7 +692,6 @@ dependencies = [
"tower-http",
"tracing",
"tracing-subscriber",
"tramiton-core",
"urlencoding",
"uuid",
"walkdir",
@@ -4198,7 +4197,7 @@ version = "3.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "219cb19e96be00ab2e37d6e299658a0cfa83e52429179969b0f0121b4ac46983"
dependencies = [
"toml_edit 0.23.10+spec-1.0.0",
"toml_edit",
]
[[package]]
@@ -4997,15 +4996,6 @@ 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"
@@ -5820,27 +5810,6 @@ 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"
@@ -5850,20 +5819,6 @@ 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"
@@ -5871,7 +5826,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "84c8b9f757e028cee9fa244aea147aab2a9ec09d5325a9b01e0a49730c2b5269"
dependencies = [
"indexmap 2.13.0",
"toml_datetime 0.7.5+spec-1.1.0",
"toml_datetime",
"toml_parser",
"winnow",
]
@@ -5885,12 +5840,6 @@ 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"
@@ -6137,18 +6086,6 @@ 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"
-5
View File
@@ -10,11 +10,6 @@ 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 }
-217
View File
@@ -1,217 +0,0 @@
//! Firmware classification via tramiton.
//!
//! tramiton is the company's firmware build/repro engine; we do not re-implement
//! 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 compliance_core::error::CoreError;
use compliance_core::models::{DetectedFact, TargetType};
use compliance_core::traits::ClassifierVerdict;
/// 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`).
pub provider: String,
/// Detection confidence: `low` | `medium` | `high`.
pub confidence: String,
/// Build-system label (e.g. `Zephyr`, `ESP-IDF`, `CMake`).
pub build_system: String,
/// Framework, when known (`zephyr`, `esp-idf`, `bare-metal`, ...).
pub framework: Option<String>,
/// Target board / MCU / arch.
pub target: FirmwareTarget,
/// Unresolved gaps in the plan.
pub gaps: Vec<String>,
}
/// The detected firmware target (board / MCU / arch).
#[derive(Debug, Clone, Default)]
pub struct FirmwareTarget {
/// Board name.
pub board: Option<String>,
/// MCU part.
pub mcu: Option<String>,
/// Architecture.
pub arch: Option<String>,
}
/// A source of tramiton firmware detection.
#[allow(async_fn_in_trait)]
pub trait FirmwareDetector: Send + Sync {
/// 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>;
}
/// 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 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)))
}
}
/// 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 firmware detection to a target type. Framework/build-system signals
/// distinguish RTOS from bare-metal from Yocto.
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") {
TargetType::EmbeddedLinuxYocto
} else if RTOS.iter().any(|k| signal.contains(k)) {
TargetType::FirmwareRtos
} else {
TargetType::FirmwareBareMetal
}
}
/// Map tramiton's confidence label to a `[0,1]` score.
fn confidence_score(label: &str) -> f32 {
match label.to_lowercase().as_str() {
"high" => 0.9,
"medium" => 0.6,
"low" => 0.3,
_ => 0.4,
}
}
/// Turn a firmware detection into a classifier verdict, carrying the MCU / board
/// / build-system as facts.
pub fn detection_to_verdict(det: &FirmwareDetection) -> ClassifierVerdict {
let target_type = detection_to_target_type(det);
let mut facts = vec![DetectedFact::new(
"build_system",
det.build_system.clone(),
"tramiton",
)];
if let Some(fw) = &det.framework {
facts.push(DetectedFact::new("framework", fw.clone(), "tramiton"));
}
if let Some(mcu) = &det.target.mcu {
facts.push(DetectedFact::new("mcu", mcu.clone(), "tramiton"));
}
if let Some(board) = &det.target.board {
facts.push(DetectedFact::new("board", board.clone(), "tramiton"));
}
if let Some(arch) = &det.target.arch {
facts.push(DetectedFact::new("arch", arch.clone(), "tramiton"));
}
ClassifierVerdict {
target_type,
confidence: confidence_score(&det.confidence),
facts,
rationale: format!(
"tramiton detected build system '{}'{}",
det.build_system,
det.framework
.as_ref()
.map(|f| format!(" (framework {f})"))
.unwrap_or_default()
),
}
}
/// A deterministic [`FirmwareDetector`] for tests — returns a preset detection.
pub struct MockFirmwareDetector {
/// 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<FirmwareDetection>, CoreError> {
Ok(self.detection.clone())
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
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: FirmwareTarget {
mcu: Some("stm32f429".to_string()),
..Default::default()
},
gaps: Vec::new(),
}
}
#[test]
fn zephyr_maps_to_rtos() {
assert_eq!(
detection_to_target_type(&detection("zephyr", Some("zephyr"))),
TargetType::FirmwareRtos
);
}
#[test]
fn bare_cmake_maps_to_bare_metal() {
assert_eq!(
detection_to_target_type(&detection("cmake", Some("bare-metal"))),
TargetType::FirmwareBareMetal
);
}
#[test]
fn bitbake_maps_to_yocto() {
assert_eq!(
detection_to_target_type(&detection("bitbake", None)),
TargetType::EmbeddedLinuxYocto
);
}
#[test]
fn verdict_carries_mcu_fact_and_confidence() {
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
.facts
.iter()
.any(|f| f.key == "mcu" && f.value == "stm32f429"));
}
}
-357
View File
@@ -1,357 +0,0 @@
//! Heuristic target-type classification from artifact kinds and source markers.
//!
//! Complements the tramiton firmware detector: this handles web / backend /
//! mobile / desktop / PLC by sniffing manifest files and file extensions in the
//! ingested code trees, plus strong priors from the artifact kinds themselves
//! (a PLC-project artifact is a PLC target; an `.ipa` is an iOS app).
use std::collections::HashSet;
use std::fs;
use std::path::Path;
use compliance_core::error::CoreError;
use compliance_core::models::{ArtifactKind, DetectedFact, TargetType};
use compliance_core::traits::{ClassificationInput, ClassifierVerdict, TargetClassifier};
/// Max directory depth scanned for marker files.
const SCAN_DEPTH: usize = 2;
/// Markers collected from a code tree.
#[derive(Default)]
struct Markers {
files: HashSet<String>,
dirs: HashSet<String>,
exts: HashSet<String>,
}
impl Markers {
fn has_file(&self, name: &str) -> bool {
self.files.contains(name)
}
fn has_ext(&self, ext: &str) -> bool {
self.exts.contains(ext)
}
fn any_dir_ends_with(&self, suffix: &str) -> bool {
self.dirs.iter().any(|d| d.ends_with(suffix))
}
}
/// Recursively collect marker file/dir/extension names up to [`SCAN_DEPTH`].
fn collect_markers(root: &Path) -> Markers {
let mut m = Markers::default();
scan_dir(root, 0, &mut m);
m
}
fn scan_dir(dir: &Path, depth: usize, m: &mut Markers) {
let Ok(entries) = fs::read_dir(dir) else {
return;
};
for entry in entries.flatten() {
let path = entry.path();
let name = entry.file_name().to_string_lossy().to_lowercase();
if path.is_dir() {
m.dirs.insert(name);
if depth < SCAN_DEPTH {
scan_dir(&path, depth + 1, m);
}
} else {
if let Some(ext) = path.extension() {
m.exts.insert(ext.to_string_lossy().to_lowercase());
}
m.files.insert(name);
}
}
}
/// Whether a `package.json` at `root` looks like a front-end app.
fn package_json_is_frontend(root: &Path) -> bool {
let Ok(content) = fs::read_to_string(root.join("package.json")) else {
return false;
};
let c = content.to_lowercase();
["react", "next", "vue", "@angular", "svelte", "vite"]
.iter()
.any(|f| c.contains(f))
}
/// The heuristic classifier: artifact-kind priors + source-tree markers.
pub struct HeuristicClassifier;
impl HeuristicClassifier {
/// Verdicts from the artifact kinds alone (no filesystem needed).
fn kind_priors(&self, input: &ClassificationInput<'_>) -> Vec<ClassifierVerdict> {
let mut out = Vec::new();
for a in input.artifacts {
let lower = a.source_ref.to_lowercase();
match a.kind {
ArtifactKind::PlcProject => out.push(verdict(
TargetType::PlcSps,
0.85,
"PLC project artifact",
vec![],
)),
ArtifactKind::MobilePackage => {
let (tt, why) = if lower.ends_with(".ipa") {
(TargetType::IosApp, "iOS package (.ipa)")
} else {
(TargetType::AndroidApp, "Android package (.apk/.aab)")
};
out.push(verdict(tt, 0.85, why, vec![]));
}
ArtifactKind::ContainerImage => out.push(verdict(
TargetType::BackendService,
0.4,
"container image",
vec![],
)),
ArtifactKind::FirmwareImage => out.push(verdict(
TargetType::FirmwareBareMetal,
0.35,
"firmware image (pending tramiton detection)",
vec![],
)),
ArtifactKind::LiveUrl if input.artifacts.len() == 1 => {
out.push(verdict(TargetType::WebApp, 0.3, "live URL only", vec![]))
}
_ => {}
}
}
out
}
/// Verdicts from scanning the ingested code trees for manifest markers.
fn source_verdicts(&self, input: &ClassificationInput<'_>) -> Vec<ClassifierVerdict> {
let mut out = Vec::new();
for a in input.artifacts {
if !matches!(a.kind, ArtifactKind::GitRepo | ArtifactKind::SourceArchive) {
continue;
}
let Some(path) = input.working_paths.get(&a.id) else {
continue;
};
let m = collect_markers(path);
// Mobile (checked first — strongest signal).
if m.has_file("androidmanifest.xml") || m.has_ext("apk") || m.has_ext("aab") {
out.push(verdict(
TargetType::AndroidApp,
0.8,
"Android manifest / gradle",
facts_lang("kotlin/java"),
));
}
if m.any_dir_ends_with(".xcodeproj")
|| m.has_file("info.plist")
|| m.has_file("podfile")
|| m.has_ext("ipa")
{
out.push(verdict(
TargetType::IosApp,
0.8,
"Xcode project / Info.plist",
facts_lang("swift/objc"),
));
}
// Desktop.
if m.has_ext("sln")
|| m.has_ext("csproj")
|| m.has_ext("vcxproj")
|| m.has_ext("desktop")
{
out.push(verdict(
TargetType::DesktopApp,
0.7,
"desktop project files",
facts_lang("dotnet/native"),
));
}
// PLC.
if m.has_ext("st") {
out.push(verdict(
TargetType::PlcSps,
0.8,
"Structured Text sources",
facts_lang("iec-61131-3"),
));
}
// Web vs backend from package.json.
if m.has_file("package.json") {
if package_json_is_frontend(path) {
out.push(verdict(
TargetType::WebApp,
0.65,
"package.json with a front-end framework",
facts_lang("javascript"),
));
} else {
out.push(verdict(
TargetType::BackendService,
0.55,
"package.json (no front-end framework)",
facts_lang("javascript"),
));
}
}
// Backend languages.
for (file, lang) in [
("cargo.toml", "rust"),
("go.mod", "go"),
("pom.xml", "java"),
("requirements.txt", "python"),
("pyproject.toml", "python"),
] {
if m.has_file(file) {
out.push(verdict(
TargetType::BackendService,
0.6,
"backend build manifest",
facts_lang(lang),
));
}
}
// Container-only.
if m.has_file("dockerfile") && out.is_empty() {
out.push(verdict(
TargetType::BackendService,
0.4,
"Dockerfile",
facts_lang("container"),
));
}
}
out
}
}
impl TargetClassifier for HeuristicClassifier {
fn name(&self) -> &str {
"heuristic"
}
async fn classify(
&self,
input: &ClassificationInput<'_>,
) -> Result<Vec<ClassifierVerdict>, CoreError> {
let mut out = self.kind_priors(input);
out.extend(self.source_verdicts(input));
Ok(out)
}
}
fn verdict(
target_type: TargetType,
confidence: f32,
rationale: &str,
facts: Vec<DetectedFact>,
) -> ClassifierVerdict {
ClassifierVerdict {
target_type,
confidence,
facts,
rationale: rationale.to_string(),
}
}
fn facts_lang(lang: &str) -> Vec<DetectedFact> {
vec![DetectedFact::new("language", lang, "heuristic")]
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::Artifact;
use std::collections::HashMap;
use std::path::PathBuf;
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-classify-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
async fn classify_tree(setup: impl FnOnce(&Path)) -> Vec<ClassifierVerdict> {
let scratch = Scratch::new();
setup(&scratch.0);
let artifact = Artifact::git_repo("https://git/x", "main");
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let artifacts = vec![artifact];
let input = ClassificationInput {
artifacts: &artifacts,
working_paths: &wp,
description: None,
};
HeuristicClassifier
.classify(&input)
.await
.expect("classify")
}
#[tokio::test]
async fn frontend_package_json_is_webapp() {
let v = classify_tree(|root| {
fs::write(
root.join("package.json"),
r#"{"dependencies":{"react":"18"}}"#,
)
.unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::WebApp));
}
#[tokio::test]
async fn cargo_toml_is_backend() {
let v = classify_tree(|root| {
fs::write(root.join("Cargo.toml"), "[package]\nname='x'").unwrap();
})
.await;
assert!(v
.iter()
.any(|x| x.target_type == TargetType::BackendService));
}
#[tokio::test]
async fn android_manifest_is_android() {
let v = classify_tree(|root| {
fs::write(root.join("AndroidManifest.xml"), "<manifest/>").unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::AndroidApp));
}
#[tokio::test]
async fn structured_text_is_plc() {
let v = classify_tree(|root| {
fs::write(root.join("main.st"), "PROGRAM main END_PROGRAM").unwrap();
})
.await;
assert!(v.iter().any(|x| x.target_type == TargetType::PlcSps));
}
#[tokio::test]
async fn ipa_artifact_prior_is_ios() {
let artifacts = vec![Artifact::mobile_package("app.ipa")];
let wp = HashMap::new();
let input = ClassificationInput {
artifacts: &artifacts,
working_paths: &wp,
description: None,
};
let v = HeuristicClassifier
.classify(&input)
.await
.expect("classify");
assert!(v.iter().any(|x| x.target_type == TargetType::IosApp));
}
}
-226
View File
@@ -1,226 +0,0 @@
//! Target classification.
//!
//! Runs the classifier registry over a target's artifacts and their ingested
//! working paths, then merges and ranks the verdicts into a [`Classification`].
//! The registry is the heuristic classifier (artifact kinds + source markers)
//! plus the tramiton firmware detector (behind a [`FirmwareDetector`] port).
mod firmware;
mod language;
pub use firmware::{
FirmwareDetection, FirmwareDetector, FirmwareTarget, MockFirmwareDetector, TramitonNative,
};
pub use language::HeuristicClassifier;
use std::collections::HashMap;
use std::path::PathBuf;
use compliance_core::error::CoreError;
use compliance_core::models::{
ArtifactKind, Classification, DetectedFact, OnboardedTarget, TargetType, TargetTypeCandidate,
};
use compliance_core::traits::{ClassificationInput, ClassifierVerdict, TargetClassifier};
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
/// merged (max confidence per target type) and ranked into a [`Classification`].
pub async fn classify_target<D: FirmwareDetector>(
target: &OnboardedTarget,
working_paths: &HashMap<String, PathBuf>,
firmware_detector: &D,
) -> Result<Classification, CoreError> {
let input = ClassificationInput {
artifacts: &target.artifacts,
working_paths,
description: target.description.as_deref(),
};
let mut verdicts = Vec::new();
let mut detected_by = Vec::new();
let heuristic = HeuristicClassifier.classify(&input).await?;
if !heuristic.is_empty() {
detected_by.push("heuristic".to_string());
}
verdicts.extend(heuristic);
// Tramiton firmware detection over firmware / code working paths.
let mut tramiton_used = false;
for artifact in &target.artifacts {
if !matches!(
artifact.kind,
ArtifactKind::FirmwareImage | ArtifactKind::GitRepo | ArtifactKind::SourceArchive
) {
continue;
}
let Some(path) = working_paths.get(&artifact.id) else {
continue;
};
if let Some(detection) = firmware_detector.detect(path).await? {
verdicts.push(detection_to_verdict(&detection));
tramiton_used = true;
}
}
if tramiton_used {
detected_by.push("tramiton".to_string());
}
Ok(rank(verdicts, detected_by, target.target_type))
}
/// Merge verdicts by target type (keeping the max confidence and its rationale),
/// dedupe facts, rank by descending confidence, and assemble a [`Classification`].
/// Falls back to the declared type when no verdict is produced.
fn rank(
verdicts: Vec<ClassifierVerdict>,
detected_by: Vec<String>,
fallback: TargetType,
) -> Classification {
let mut best: HashMap<TargetType, (f32, String)> = HashMap::new();
let mut facts: Vec<DetectedFact> = Vec::new();
for verdict in verdicts {
for fact in verdict.facts {
if !facts
.iter()
.any(|e| e.key == fact.key && e.value == fact.value)
{
facts.push(fact);
}
}
let entry = best
.entry(verdict.target_type)
.or_insert((0.0, String::new()));
if verdict.confidence > entry.0 {
*entry = (verdict.confidence, verdict.rationale);
}
}
let mut candidates: Vec<TargetTypeCandidate> = best
.into_iter()
.map(
|(target_type, (confidence, rationale))| TargetTypeCandidate {
target_type,
confidence,
rationale,
},
)
.collect();
// Descending confidence; ties broken by type name for deterministic ordering.
candidates.sort_by(|a, b| {
b.confidence
.partial_cmp(&a.confidence)
.unwrap_or(std::cmp::Ordering::Equal)
.then_with(|| a.target_type.to_string().cmp(&b.target_type.to_string()))
});
let suggested = candidates
.first()
.map(|c| c.target_type)
.unwrap_or(fallback);
Classification {
suggested,
candidates,
facts,
detected_by,
detected_at: chrono::Utc::now(),
confirmed: false,
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::Artifact;
use std::fs;
use std::path::Path;
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-classify-mod-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
fn no_firmware() -> MockFirmwareDetector {
MockFirmwareDetector { detection: None }
}
#[tokio::test]
async fn backend_repo_classifies_as_backend() {
let scratch = Scratch::new();
fs::write(scratch.0.join("go.mod"), "module x").unwrap();
let artifact = Artifact::git_repo("https://git/x", "main");
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let mut target = OnboardedTarget::new("x".to_string(), TargetType::WebApp);
target.artifacts.push(artifact);
let c = classify_target(&target, &wp, &no_firmware())
.await
.expect("classify");
assert_eq!(c.suggested, TargetType::BackendService);
assert!(c.detected_by.contains(&"heuristic".to_string()));
assert!(!c.confirmed);
}
#[tokio::test]
async fn firmware_detector_verdict_ranks_top() {
let scratch = Scratch::new();
fs::write(scratch.0.join("fw.bin"), b"x").unwrap();
let artifact =
Artifact::firmware_image(scratch.0.join("fw.bin").to_string_lossy().to_string());
let mut wp = HashMap::new();
wp.insert(artifact.id.clone(), scratch.0.clone());
let mut target = OnboardedTarget::new("fw".to_string(), TargetType::FirmwareBareMetal);
target.artifacts.push(artifact);
let detector = MockFirmwareDetector {
detection: Some(FirmwareDetection {
provider: "zephyr".to_string(),
confidence: "high".to_string(),
build_system: "zephyr".to_string(),
framework: Some("zephyr".to_string()),
target: FirmwareTarget {
mcu: Some("nrf52840".to_string()),
..Default::default()
},
gaps: vec![],
}),
};
let c = classify_target(&target, &wp, &detector)
.await
.expect("classify");
// tramiton's high-confidence RTOS verdict beats the weak firmware prior.
assert_eq!(c.suggested, TargetType::FirmwareRtos);
assert!(c.detected_by.contains(&"tramiton".to_string()));
assert!(c.facts.iter().any(|f| f.key == "mcu"));
}
#[tokio::test]
async fn no_signal_falls_back_to_declared_type() {
let scratch = Scratch::new();
let _ = Path::new(&scratch.0);
let target = OnboardedTarget::new("empty".to_string(), TargetType::DesktopApp);
let wp = HashMap::new();
let c = classify_target(&target, &wp, &no_firmware())
.await
.expect("classify");
assert_eq!(c.suggested, TargetType::DesktopApp);
assert!(c.candidates.is_empty());
}
}
-2
View File
@@ -45,8 +45,6 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
.unwrap_or_else(|| "0 0 * * * *".to_string()),
git_clone_base_path: env_var_opt("GIT_CLONE_BASE_PATH")
.unwrap_or_else(|| "/tmp/compliance-scanner/repos".to_string()),
artifact_store_base_path: env_var_opt("ARTIFACT_STORE_BASE_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/artifacts".to_string()),
ssh_key_path: env_var_opt("SSH_KEY_PATH")
.unwrap_or_else(|| "/data/compliance-scanner/ssh/id_ed25519".to_string()),
keycloak_url: env_var_opt("KEYCLOAK_URL"),
-24
View File
@@ -179,23 +179,6 @@ 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.
@@ -538,13 +521,6 @@ 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")
}
-154
View File
@@ -1,154 +0,0 @@
//! Content-addressed blob storage and archive extraction for ingest.
//!
//! Blobs are stored at `<base>/blobs/<sha[0:2]>/<sha>` and deduplicated by
//! digest; per-run working directories live under `<base>/work/`.
use std::fs::{self, File};
use std::io::{self, Read};
use std::path::{Path, PathBuf};
use sha2::{Digest, Sha256};
use crate::error::AgentError;
/// Read buffer size for streaming hashes/copies (64 KiB).
const BUF_LEN: usize = 64 * 1024;
/// Stream-hash a file with SHA-256, returning the lowercase-hex digest and the
/// byte length. Streams so large firmware images never load fully into memory.
pub fn hash_file(path: &Path) -> Result<(String, u64), AgentError> {
let mut file = File::open(path)?;
let mut hasher = Sha256::new();
let mut buf = [0u8; BUF_LEN];
let mut total: u64 = 0;
loop {
let n = file.read(&mut buf)?;
if n == 0 {
break;
}
hasher.update(&buf[..n]);
total += n as u64;
}
Ok((hex::encode(hasher.finalize()), total))
}
/// Copy `src` into the content-addressed blob store under `base`, returning the
/// stored path. Idempotent: an already-present blob is not rewritten.
pub fn store_file(base: &Path, src: &Path, sha: &str) -> Result<PathBuf, AgentError> {
if sha.len() < 2 {
return Err(AgentError::Other(format!("invalid content hash '{sha}'")));
}
let dir = base.join("blobs").join(&sha[0..2]);
fs::create_dir_all(&dir)?;
let dest = dir.join(sha);
if !dest.exists() {
fs::copy(src, &dest)?;
}
Ok(dest)
}
/// Extract a zip archive into `dest` (created if needed). `enclosed_name`
/// sanitizes each entry path, so this is safe against zip-slip traversal.
pub fn extract_zip(archive: &Path, dest: &Path) -> Result<(), AgentError> {
let file = File::open(archive)?;
let mut zip =
zip::ZipArchive::new(file).map_err(|e| AgentError::Other(format!("open zip: {e}")))?;
fs::create_dir_all(dest)?;
for i in 0..zip.len() {
let mut entry = zip
.by_index(i)
.map_err(|e| AgentError::Other(format!("read zip entry: {e}")))?;
// `enclosed_name` returns `None` for traversal-unsafe paths — skip them.
let Some(rel) = entry.enclosed_name() else {
continue;
};
let out = dest.join(rel);
if entry.is_dir() {
fs::create_dir_all(&out)?;
} else {
if let Some(parent) = out.parent() {
fs::create_dir_all(parent)?;
}
let mut outfile = File::create(&out)?;
io::copy(&mut entry, &mut outfile)?;
}
}
Ok(())
}
/// The working directory for one artifact of a target: `<base>/work/<target>/<artifact>`.
pub fn work_dir(base: &Path, target_id: &str, artifact_id: &str) -> PathBuf {
base.join("work").join(target_id).join(artifact_id)
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
/// A unique scratch directory, removed on drop.
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-ingest-{}", uuid::Uuid::new_v4()));
fs::create_dir_all(&p).expect("mkdir scratch");
Self(p)
}
fn path(&self) -> &Path {
&self.0
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
#[test]
fn hash_is_stable_and_reports_size() {
let dir = Scratch::new();
let f = dir.path().join("a.bin");
fs::write(&f, b"hello world").expect("write");
let (sha, size) = hash_file(&f).expect("hash");
assert_eq!(size, 11);
// Known SHA-256 of "hello world".
assert_eq!(
sha,
"b94d27b9934d3e08a52e52d7da7dabfac484efe37a5380ee9088f7ace2efcde9"
);
}
#[test]
fn store_is_content_addressed_and_idempotent() {
let base = Scratch::new();
let src = base.path().join("src.bin");
fs::write(&src, b"payload").expect("write");
let (sha, _) = hash_file(&src).expect("hash");
let p1 = store_file(base.path(), &src, &sha).expect("store");
let p2 = store_file(base.path(), &src, &sha).expect("store again");
assert_eq!(p1, p2);
assert!(p1.ends_with(&sha));
assert!(p1.starts_with(base.path().join("blobs").join(&sha[0..2])));
assert_eq!(fs::read(&p1).expect("read"), b"payload");
}
#[test]
fn extract_zip_writes_entries() {
let base = Scratch::new();
let archive = base.path().join("a.zip");
{
let file = File::create(&archive).expect("create");
let mut w = zip::ZipWriter::new(file);
let opts: zip::write::SimpleFileOptions = Default::default();
w.start_file("dir/hello.txt", opts).expect("start");
io::Write::write_all(&mut w, b"hi").expect("write");
w.finish().expect("finish");
}
let dest = base.path().join("out");
extract_zip(&archive, &dest).expect("extract");
assert_eq!(
fs::read_to_string(dest.join("dir/hello.txt")).expect("read"),
"hi"
);
}
}
-334
View File
@@ -1,334 +0,0 @@
//! Artifact ingest.
//!
//! Normalizes each [`Artifact`] on an [`OnboardedTarget`] into a local working
//! path plus recorded metadata (content hash, size, discovered facts) that the
//! classifier and scanners consume. Every blob is SHA-256 hashed — that digest
//! is also the reconciliation key against sibling products (a firmware sha256
//! matches tramiton's `Artifact.sha256`).
mod blob;
use std::collections::HashMap;
use std::path::{Path, PathBuf};
use compliance_core::models::{Artifact, ArtifactKind, DetectedFact, OnboardedTarget};
use compliance_core::AgentConfig;
use crate::error::AgentError;
use crate::pipeline::git::{GitOps, RepoCredentials};
/// The paths and identifiers an ingest needs. Decoupled from the full
/// [`AgentConfig`] so ingest is testable without a complete config.
pub struct IngestContext<'a> {
/// Base directory for content-addressed blobs and working dirs.
pub artifact_store_base: &'a Path,
/// Base directory for git clones.
pub git_clone_base: &'a str,
/// Default SSH key path (used when an artifact provides none).
pub ssh_key_path: &'a str,
/// The id of the target these artifacts belong to (namespaces working dirs).
pub target_id: &'a str,
}
impl<'a> IngestContext<'a> {
/// Build an ingest context from the agent config for a given target.
pub fn from_config(config: &'a AgentConfig, target_id: &'a str) -> Self {
Self {
artifact_store_base: Path::new(&config.artifact_store_base_path),
git_clone_base: &config.git_clone_base_path,
ssh_key_path: &config.ssh_key_path,
target_id,
}
}
}
/// The result of ingesting one artifact.
pub struct IngestedArtifact {
/// The artifact this corresponds to ([`Artifact::id`]).
pub artifact_id: String,
/// The artifact kind.
pub kind: ArtifactKind,
/// Local working path (clone dir, extracted dir, or blob file). `None` for
/// artifacts with no on-disk form (live URL, plaintext, container ref).
pub working_path: Option<PathBuf>,
/// SHA-256 of the content (blobs) or git head SHA (git repos).
pub content_hash: Option<String>,
/// Stored blob size in bytes, when applicable.
pub size_bytes: Option<u64>,
/// Facts discovered during ingest.
pub facts: Vec<DetectedFact>,
}
/// All ingested artifacts for a target, keyed by artifact id.
pub struct IngestSet {
/// The ingested artifacts, keyed by [`Artifact::id`].
pub by_artifact: HashMap<String, IngestedArtifact>,
}
impl IngestSet {
/// The working paths of every ingested artifact that has one — the input the
/// classifier expects.
pub fn working_paths(&self) -> HashMap<String, PathBuf> {
self.by_artifact
.iter()
.filter_map(|(id, a)| a.working_path.clone().map(|p| (id.clone(), p)))
.collect()
}
/// The ingest result for a specific artifact.
pub fn get(&self, artifact_id: &str) -> Option<&IngestedArtifact> {
self.by_artifact.get(artifact_id)
}
}
/// Ingest every artifact on a target.
pub fn ingest_all(
target: &OnboardedTarget,
ctx: &IngestContext<'_>,
) -> Result<IngestSet, AgentError> {
let mut by_artifact = HashMap::new();
for artifact in &target.artifacts {
let ingested = ingest_artifact(artifact, ctx)?;
by_artifact.insert(artifact.id.clone(), ingested);
}
Ok(IngestSet { by_artifact })
}
/// Ingest a single artifact, dispatching on its kind.
pub fn ingest_artifact(
artifact: &Artifact,
ctx: &IngestContext<'_>,
) -> Result<IngestedArtifact, AgentError> {
match artifact.kind {
ArtifactKind::GitRepo => ingest_git(artifact, ctx),
ArtifactKind::SourceArchive | ArtifactKind::MobilePackage | ArtifactKind::PlcProject => {
ingest_blob(artifact, ctx, true)
}
ArtifactKind::FirmwareImage => ingest_blob(artifact, ctx, false),
ArtifactKind::ContainerImage => Ok(metadata_only(
artifact,
DetectedFact::new("container_ref", artifact.source_ref.as_str(), "ingest"),
)),
ArtifactKind::LiveUrl => Ok(metadata_only(
artifact,
DetectedFact::new("live_url", artifact.source_ref.as_str(), "ingest"),
)),
ArtifactKind::PlaintextDescription => Ok(metadata_only(
artifact,
DetectedFact::new(
"description_len",
artifact.source_ref.len().to_string(),
"ingest",
),
)),
}
}
/// Clone (or fetch) a git artifact, recording the head SHA as the content hash.
fn ingest_git(
artifact: &Artifact,
ctx: &IngestContext<'_>,
) -> Result<IngestedArtifact, AgentError> {
let creds = credentials_for(artifact, ctx.ssh_key_path);
let git_ops = GitOps::new(ctx.git_clone_base, creds);
let repo_path = git_ops.clone_or_fetch(&artifact.source_ref, &artifact.id)?;
let head = GitOps::get_head_sha(&repo_path).ok();
Ok(IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: Some(repo_path),
content_hash: head,
size_bytes: None,
facts: Vec::new(),
})
}
/// Store a blob artifact content-addressed. When `extract` is set and the blob
/// is a zip container (source archive, APK/AAB/IPA), also unpack it into a
/// working directory; otherwise the working path is the stored blob.
fn ingest_blob(
artifact: &Artifact,
ctx: &IngestContext<'_>,
extract: bool,
) -> Result<IngestedArtifact, AgentError> {
let base = ctx.artifact_store_base;
let src = local_source(artifact)?;
let (sha, size) = blob::hash_file(&src)?;
let stored = blob::store_file(base, &src, &sha)?;
let mut facts = Vec::new();
let working_path = if extract {
let dest = blob::work_dir(base, ctx.target_id, &artifact.id);
match blob::extract_zip(&stored, &dest) {
Ok(()) => dest,
Err(e) => {
// Not a zip (e.g. a tar.gz source archive) — keep the blob and
// note it so later stages can decide what to do.
facts.push(DetectedFact::new(
"archive_unextracted",
e.to_string(),
"ingest",
));
stored.clone()
}
}
} else {
stored.clone()
};
Ok(IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: Some(working_path),
content_hash: Some(sha),
size_bytes: Some(size),
facts,
})
}
/// An artifact with no on-disk form: record a single fact, no hash/path.
fn metadata_only(artifact: &Artifact, fact: DetectedFact) -> IngestedArtifact {
IngestedArtifact {
artifact_id: artifact.id.clone(),
kind: artifact.kind,
working_path: None,
content_hash: None,
size_bytes: None,
facts: vec![fact],
}
}
/// The local file backing a blob artifact: its `stored_path` if already
/// uploaded, else its `source_ref` interpreted as a filesystem path.
fn local_source(artifact: &Artifact) -> Result<PathBuf, AgentError> {
let path = artifact
.stored_path
.as_deref()
.unwrap_or(artifact.source_ref.as_str());
let path = PathBuf::from(path);
if !path.exists() {
return Err(AgentError::Other(format!(
"artifact {} source not found at {}",
artifact.id,
path.display()
)));
}
Ok(path)
}
/// Build git credentials from an artifact's auth plus a default SSH key path.
fn credentials_for(artifact: &Artifact, default_ssh_key_path: &str) -> RepoCredentials {
let auth = artifact.auth.as_ref();
RepoCredentials {
ssh_key_path: auth
.and_then(|a| a.ssh_key_path.clone())
.or_else(|| Some(default_ssh_key_path.to_string())),
auth_token: auth.and_then(|a| a.secret.clone()),
auth_username: auth.and_then(|a| a.username.clone()),
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{ArtifactAuth, TargetType};
/// A unique scratch directory, removed on drop.
struct Scratch(PathBuf);
impl Scratch {
fn new() -> Self {
let p = std::env::temp_dir().join(format!("cs-ingest-mod-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&p).expect("mkdir scratch");
Self(p)
}
}
impl Drop for Scratch {
fn drop(&mut self) {
let _ = std::fs::remove_dir_all(&self.0);
}
}
fn ctx_for<'a>(store: &'a Path, target_id: &'a str) -> IngestContext<'a> {
IngestContext {
artifact_store_base: store,
git_clone_base: "/tmp/cs-ingest-test-repos",
ssh_key_path: "/tmp/cs-ingest-test-ssh",
target_id,
}
}
#[test]
fn firmware_blob_is_hashed_and_stored() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let fw = scratch.0.join("fw.bin");
std::fs::write(&fw, b"firmware-bytes").expect("write");
let ctx = ctx_for(&store, "t1");
let artifact = Artifact::firmware_image(fw.to_string_lossy().to_string());
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
assert_eq!(out.kind, ArtifactKind::FirmwareImage);
assert_eq!(out.size_bytes, Some(14));
let sha = out.content_hash.expect("hash");
assert_eq!(sha.len(), 64);
// working path is the content-addressed blob
let wp = out.working_path.expect("working path");
assert!(wp.starts_with(store.join("blobs")));
}
#[test]
fn live_url_has_no_blob() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let ctx = ctx_for(&store, "t1");
let artifact = Artifact::live_url("https://example.com");
let out = ingest_artifact(&artifact, &ctx).expect("ingest");
assert!(out.working_path.is_none());
assert!(out.content_hash.is_none());
assert!(out.facts.iter().any(|f| f.key == "live_url"));
}
#[test]
fn ingest_all_collects_working_paths() {
let scratch = Scratch::new();
let store = scratch.0.join("store");
let fw = scratch.0.join("fw.bin");
std::fs::write(&fw, b"abc").expect("write");
let ctx = ctx_for(&store, "t1");
let mut target = OnboardedTarget::new("t".to_string(), TargetType::FirmwareBareMetal);
target
.artifacts
.push(Artifact::firmware_image(fw.to_string_lossy().to_string()));
target.artifacts.push(Artifact::live_url("https://x"));
let set = ingest_all(&target, &ctx).expect("ingest all");
assert_eq!(set.by_artifact.len(), 2);
// Only the firmware artifact yields a working path.
assert_eq!(set.working_paths().len(), 1);
}
#[test]
fn credentials_prefer_artifact_auth() {
let mut artifact = Artifact::git_repo("https://git/x", "main");
artifact.auth = Some(ArtifactAuth {
method: "token".to_string(),
username: Some("bob".to_string()),
secret: Some("pat".to_string()),
..Default::default()
});
let creds = credentials_for(&artifact, "/default/ssh/key");
assert_eq!(creds.auth_token.as_deref(), Some("pat"));
assert_eq!(creds.auth_username.as_deref(), Some("bob"));
}
#[test]
fn credentials_fall_back_to_default_ssh_key() {
let artifact = Artifact::git_repo("git@host:x.git", "main");
let creds = credentials_for(&artifact, "/default/ssh/key");
assert_eq!(creds.ssh_key_path.as_deref(), Some("/default/ssh/key"));
assert!(creds.auth_token.is_none());
}
}
-3
View File
@@ -2,13 +2,10 @@
pub mod agent;
pub mod api;
pub mod classify;
pub mod config;
pub mod database;
pub mod error;
pub mod ingest;
pub mod llm;
pub mod migrate;
pub mod pentest;
pub mod pipeline;
pub mod rag;
+1 -54
View File
@@ -1,50 +1,4 @@
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(())
}
use compliance_agent::{agent, api, config, database, scheduler, ssh, webhooks};
#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
@@ -77,13 +31,6 @@ 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...");
-8
View File
@@ -1,8 +0,0 @@
//! 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;
-406
View File
@@ -1,406 +0,0 @@
//! 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);
}
}
-1
View File
@@ -328,7 +328,6 @@ mod tests {
scan_schedule: String::new(),
cve_monitor_schedule: String::new(),
git_clone_base_path: String::new(),
artifact_store_base_path: String::new(),
ssh_key_path: String::new(),
keycloak_url: None,
keycloak_realm: None,
-1
View File
@@ -44,7 +44,6 @@ impl TestServer {
scan_schedule: String::new(),
cve_monitor_schedule: String::new(),
git_clone_base_path: "/tmp/compliance-scanner-tests/repos".into(),
artifact_store_base_path: "/tmp/compliance-scanner-tests/artifacts".into(),
ssh_key_path: "/tmp/compliance-scanner-tests/ssh/id_ed25519".into(),
github_token: None,
github_webhook_secret: None,
@@ -1,156 +0,0 @@
// 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;
}
@@ -7,4 +7,3 @@
// Or nightly: (via CI with MongoDB service container)
mod api;
mod migration;
-3
View File
@@ -24,9 +24,6 @@ pub struct AgentConfig {
pub scan_schedule: String,
pub cve_monitor_schedule: String,
pub git_clone_base_path: String,
/// Base directory for content-addressed artifact blobs and per-run working
/// dirs (`<base>/blobs/<sha[0:2]>/<sha>`, `<base>/work/<target>/<artifact>/`).
pub artifact_store_base_path: String,
pub ssh_key_path: String,
pub keycloak_url: Option<String>,
pub keycloak_realm: Option<String>,
+3 -4
View File
@@ -33,10 +33,9 @@ pub use mcp::{McpServerConfig, McpServerStatus, McpTransport};
pub use mcp_token::{McpToken, McpTokenView};
pub use notification::{CveNotification, NotificationSeverity, NotificationStatus};
pub use onboarding::{
default_compliance_profile, Artifact, ArtifactAuth, ArtifactKind, Classification,
ComplianceFramework, ComplianceProfile, DetectedFact, ExternalRef, ExternalSystem,
GitArtifactConfig, IssueTrackerConfig, OnboardedTarget, PlcArtifactConfig, PlcFormat,
TargetScanConfig, TargetType, TargetTypeCandidate, WebArtifactConfig,
Artifact, ArtifactAuth, ArtifactKind, Classification, DetectedFact, GitArtifactConfig,
IssueTrackerConfig, OnboardedTarget, PlcArtifactConfig, PlcFormat, TargetScanConfig,
TargetType, TargetTypeCandidate, WebArtifactConfig,
};
pub use pentest::{
AttackChainNode, AttackNodeStatus, AuthMode, CodeContextHint, Environment, IdentityProvider,
+1 -167
View File
@@ -22,7 +22,7 @@ use super::scan::ScanType;
/// Targets look endlessly varied but fall into a small enumerable set classified
/// by where the analyzable signal lives. This drives the scan-applicability
/// matrix and the onboarding wizard's type selection.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum TargetType {
/// Browser-facing web application (front end + server).
@@ -411,134 +411,6 @@ pub struct TargetScanConfig {
pub issue_tracker: Option<IssueTrackerConfig>,
}
/// A sibling product in the company suite that may already hold authoritative
/// data for a target. compliance-scanner reconciles with these rather than
/// recomputing what they already know.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ExternalSystem {
/// Reproducible-build & firmware compliance engine (build plan, SBOM, VEX,
/// attestation).
Tramiton,
/// Code assistant (downstream remediation consumer).
Werkpilot,
/// Compliance-controls RAG (atomic controls derived from laws).
BreakpilotCompliance,
}
impl std::fmt::Display for ExternalSystem {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::Tramiton => write!(f, "tramiton"),
Self::Werkpilot => write!(f, "werkpilot"),
Self::BreakpilotCompliance => write!(f, "breakpilot_compliance"),
}
}
}
/// A link from this target to a record in a sibling product, used to reconcile
/// existing evidence instead of recomputing it.
///
/// For tramiton, `project_id` is the shared cross-product key and
/// `subject_sha256` matches a firmware artifact's [`Artifact::content_hash`]
/// (which equals tramiton's `Artifact.sha256`).
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ExternalRef {
/// Which sibling product this reference points at.
pub system: ExternalSystem,
/// The sibling product's project identifier, if known.
pub project_id: Option<String>,
/// Content digest of the subject artifact (firmware sha256), if known.
pub subject_sha256: Option<String>,
/// Reconciliation status: `linked` | `reconciled` | `unavailable`.
#[serde(default)]
pub status: String,
/// Opaque, offline-verifiable entitlement grant (e.g. tramiton's signed
/// `LicenseGrant`), if the tenant provided one.
pub license_grant: Option<String>,
/// When evidence was last reconciled from this system.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_reconciled_at: Option<DateTime<Utc>>,
}
impl ExternalRef {
/// A freshly linked (not yet reconciled) reference to a sibling system.
pub fn linked(system: ExternalSystem) -> Self {
Self {
system,
project_id: None,
subject_sha256: None,
status: "linked".to_string(),
license_grant: None,
last_reconciled_at: None,
}
}
}
/// A regulatory / standards framework a target must comply with. Drives which
/// controls the mapping engine pulls from the [`crate::traits::ControlsProvider`].
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ComplianceFramework {
/// EU Cyber Resilience Act.
Cra,
/// IEC 62443 (industrial automation & control systems security).
Iec62443,
/// EU General Data Protection Regulation.
Gdpr,
/// SOC 2.
Soc2,
/// ISO/IEC 27001.
Iso27001,
/// EU Radio Equipment Directive (RED) cybersecurity articles.
RedDirective,
}
impl std::fmt::Display for ComplianceFramework {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::Cra => write!(f, "cra"),
Self::Iec62443 => write!(f, "iec_62443"),
Self::Gdpr => write!(f, "gdpr"),
Self::Soc2 => write!(f, "soc2"),
Self::Iso27001 => write!(f, "iso_27001"),
Self::RedDirective => write!(f, "red_directive"),
}
}
}
/// The compliance scope of a target: which frameworks apply and, optionally, the
/// jurisdiction. Captured at onboarding (with per-target-type defaults from
/// [`default_compliance_profile`]).
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct ComplianceProfile {
/// Applicable frameworks.
#[serde(default)]
pub frameworks: Vec<ComplianceFramework>,
/// Free-form jurisdiction (e.g. `eu`, `us`, `de`).
pub jurisdiction: Option<String>,
}
/// The sensible default compliance scope for a target type. Firmware / PLC /
/// embedded default to CRA + IEC 62443; software defaults to GDPR + SOC 2.
pub fn default_compliance_profile(target_type: TargetType) -> ComplianceProfile {
use ComplianceFramework::{Cra, Gdpr, Iec62443, Soc2};
let frameworks = match target_type {
TargetType::PlcSps
| TargetType::FirmwareBareMetal
| TargetType::FirmwareRtos
| TargetType::EmbeddedLinuxYocto => vec![Cra, Iec62443],
TargetType::WebApp | TargetType::BackendService => vec![Gdpr, Soc2],
TargetType::DesktopApp | TargetType::AndroidApp | TargetType::IosApp => {
vec![Gdpr, Cra]
}
};
ComplianceProfile {
frameworks,
jurisdiction: None,
}
}
/// A target onboarded for scanning: the unified replacement for the legacy
/// `TrackedRepository` (SAST) and `DastTarget` (DAST) records.
#[derive(Debug, Clone, Serialize, Deserialize)]
@@ -562,12 +434,6 @@ pub struct OnboardedTarget {
/// How this target should be scanned.
#[serde(default)]
pub scan_config: TargetScanConfig,
/// The compliance scope (applicable frameworks / jurisdiction).
#[serde(default)]
pub compliance_profile: ComplianceProfile,
/// Links to sibling products (tramiton, ...) holding reconcilable evidence.
#[serde(default)]
pub external_refs: Vec<ExternalRef>,
/// Cron schedule for recurring scans, if any.
pub scan_schedule: Option<String>,
/// Whether inbound webhooks are enabled for this target.
@@ -606,8 +472,6 @@ impl OnboardedTarget {
artifacts: Vec::new(),
classification: None,
scan_config: TargetScanConfig::default(),
compliance_profile: default_compliance_profile(target_type),
external_refs: Vec::new(),
scan_schedule: None,
webhook_enabled: false,
webhook_secret: Some(webhook_secret),
@@ -720,34 +584,4 @@ mod tests {
let b = Artifact::firmware_image("fw.bin");
assert_ne!(a.id, b.id);
}
#[test]
fn firmware_default_profile_is_cra_and_62443() {
let p = default_compliance_profile(TargetType::FirmwareBareMetal);
assert!(p.frameworks.contains(&ComplianceFramework::Cra));
assert!(p.frameworks.contains(&ComplianceFramework::Iec62443));
}
#[test]
fn webapp_default_profile_is_gdpr_and_soc2() {
let p = default_compliance_profile(TargetType::WebApp);
assert!(p.frameworks.contains(&ComplianceFramework::Gdpr));
assert!(p.frameworks.contains(&ComplianceFramework::Soc2));
}
#[test]
fn new_target_gets_default_profile_and_no_external_refs() {
let t = OnboardedTarget::new("fw".to_string(), TargetType::FirmwareRtos);
assert!(!t.compliance_profile.frameworks.is_empty());
assert!(t.external_refs.is_empty());
}
#[test]
fn external_ref_linked_defaults() {
let r = ExternalRef::linked(ExternalSystem::Tramiton);
assert_eq!(r.system, ExternalSystem::Tramiton);
assert_eq!(r.status, "linked");
assert!(r.project_id.is_none());
assert!(r.last_reconciled_at.is_none());
}
}
-45
View File
@@ -1,45 +0,0 @@
//! The compliance-controls provider port.
//!
//! The mapping engine turns findings into compliance status against a corpus of
//! controls. That corpus is pluggable: the built-in OSCAL catalog by default, or
//! a tenant-owned RAG of atomic controls derived from laws
//! (`breakpilot-compliance`) when available. A [`ControlsProvider`] abstracts the
//! source so the mapping engine does not hardcode a catalog.
use crate::error::CoreError;
use crate::models::ComplianceFramework;
/// A control retrieved from a controls corpus.
#[derive(Debug, Clone)]
pub struct Control {
/// Stable control identifier (e.g. an OSCAL control id or a RAG chunk id).
pub id: String,
/// The framework this control belongs to.
pub framework: ComplianceFramework,
/// Short human-readable title.
pub title: String,
/// The control text / requirement.
pub text: String,
/// Free-form source reference (catalog name, law citation, ...).
pub source: Option<String>,
}
/// A query for relevant controls.
pub struct ControlQuery<'a> {
/// Frameworks in scope for the target.
pub frameworks: &'a [ComplianceFramework],
/// Free-text describing what to map (a finding summary, a component, ...).
pub context: &'a str,
/// Maximum number of controls to return.
pub limit: usize,
}
/// A source of compliance controls (built-in OSCAL catalog, breakpilot RAG, ...).
#[allow(async_fn_in_trait)]
pub trait ControlsProvider: Send + Sync {
/// Stable identifier for this provider.
fn name(&self) -> &str;
/// Retrieve the controls most relevant to the query.
async fn controls(&self, query: &ControlQuery<'_>) -> Result<Vec<Control>, CoreError>;
}
-58
View File
@@ -1,58 +0,0 @@
//! The external-evidence provider port.
//!
//! A sibling product (tramiton, for firmware) may already hold authoritative
//! analysis for an artifact. An [`EvidenceProvider`] lets compliance-scanner
//! *reconcile* that evidence — a build plan, an SBOM, a VEX document, a
//! reproducible-build lock, an attestation — instead of recomputing it. The key
//! used to match is the artifact content digest (a firmware sha256, which equals
//! [`crate::models::Artifact::content_hash`]).
//!
//! Concrete providers live in the agent (a tramiton CLI shell-out today, a cloud
//! client later) plus a deterministic mock for tests, so nothing here depends on
//! an external binary.
use std::path::Path;
use crate::error::CoreError;
use crate::models::{Artifact, ExternalSystem};
/// A single reconcilable evidence document fetched from a sibling product.
#[derive(Debug, Clone)]
pub struct EvidenceDocument {
/// What the document is: `build_plan` | `sbom` | `vex` | `lock` | `attestation`.
pub kind: String,
/// The document's format (e.g. `cyclonedx-1.5`, `openvex-0.2.0`, `toml`, `json`).
pub format: String,
/// The raw document payload.
pub content: String,
}
/// The evidence a provider could return for a target's artifact.
#[derive(Debug, Clone, Default)]
pub struct ReconciledEvidence {
/// The sibling's project identifier, if resolved.
pub project_id: Option<String>,
/// The subject content digest the evidence pertains to.
pub subject_sha256: Option<String>,
/// The documents fetched (any of build plan / SBOM / VEX / lock / attestation).
pub documents: Vec<EvidenceDocument>,
}
/// A source of externally-held, reconcilable evidence for an artifact.
#[allow(async_fn_in_trait)]
pub trait EvidenceProvider: Send + Sync {
/// Which sibling product this provider integrates.
fn system(&self) -> ExternalSystem;
/// Whether this provider can handle the given artifact + working path
/// (e.g. tramiton handles firmware images / embedded source trees).
fn handles(&self, artifact: &Artifact, working_path: Option<&Path>) -> bool;
/// Reconcile existing evidence for the artifact, keyed by its content digest.
/// Returns `Ok(None)` when the provider has nothing for this artifact.
async fn reconcile(
&self,
artifact: &Artifact,
working_path: Option<&Path>,
) -> Result<Option<ReconciledEvidence>, CoreError>;
}
-4
View File
@@ -1,16 +1,12 @@
pub mod classifier;
pub mod controls;
pub mod dast_agent;
pub mod evidence;
pub mod graph_builder;
pub mod issue_tracker;
pub mod pentest_tool;
pub mod scanner;
pub use classifier::{ClassificationInput, ClassifierVerdict, TargetClassifier};
pub use controls::{Control, ControlQuery, ControlsProvider};
pub use dast_agent::{DastAgent, DastContext, DiscoveredEndpoint, EndpointParameter};
pub use evidence::{EvidenceDocument, EvidenceProvider, ReconciledEvidence};
pub use graph_builder::{LanguageParser, ParseOutput};
pub use issue_tracker::IssueTracker;
pub use pentest_tool::{PentestTool, PentestToolContext, PentestToolResult};
-2
View File
@@ -12,8 +12,6 @@ pub enum Route {
OverviewPage {},
#[route("/repositories")]
RepositoriesPage {},
#[route("/onboard")]
OnboardingPage {},
#[route("/findings")]
FindingsPage {},
#[route("/findings/:id")]
@@ -28,11 +28,6 @@ pub fn Sidebar() -> Element {
route: Route::RepositoriesPage {},
icon: rsx! { Icon { icon: BsFolder2Open, width: 18, height: 18 } },
},
NavItem {
label: "Onboard",
route: Route::OnboardingPage {},
icon: rsx! { Icon { icon: BsPlusCircle, width: 18, height: 18 } },
},
NavItem {
label: "Findings",
route: Route::FindingsPage {},
@@ -10,7 +10,6 @@ pub mod issues;
pub mod mcp;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod pentest;
#[allow(clippy::too_many_arguments)]
pub mod repositories;
@@ -1,107 +0,0 @@
//! Server functions for the onboarding wizard — proxy to the agent's
//! `/api/v1/targets` endpoints.
use dioxus::prelude::*;
use serde::{Deserialize, Serialize};
/// One artifact the wizard collects for a target.
#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq)]
pub struct ArtifactInputDto {
pub kind: String,
pub source_ref: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub branch: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub plc_format: Option<String>,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct TargetsResponse {
pub data: Vec<serde_json::Value>,
pub total: Option<u64>,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct TargetResponse {
pub data: serde_json::Value,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct ApplicableScansData {
#[serde(default)]
pub scans: Vec<serde_json::Value>,
#[serde(default)]
pub pentest_supported: bool,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct ApplicableScansResponse {
pub data: ApplicableScansData,
}
/// List onboarded targets.
#[server]
pub async fn fetch_targets() -> Result<TargetsResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/targets")
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Create a target with the collected artifacts.
#[server]
pub async fn create_target(
name: String,
target_type: String,
description: Option<String>,
artifacts: Vec<ArtifactInputDto>,
) -> Result<TargetResponse, ServerFnError> {
let body = serde_json::json!({
"name": name,
"target_type": target_type,
"description": description,
"artifacts": artifacts,
});
let resp = super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/targets")
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Run kind-based classification on a target.
#[server]
pub async fn detect_target(id: String) -> Result<TargetResponse, ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/targets/{id}/detect"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Fetch the scan-applicability matrix for a target.
#[server]
pub async fn fetch_applicable_scans(id: String) -> Result<ApplicableScansResponse, ServerFnError> {
let resp = super::agent_client::agent_get(&format!("/api/v1/targets/{id}/applicable-scans"))
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
-2
View File
@@ -12,7 +12,6 @@ pub mod impact_analysis;
pub mod issues;
pub mod mcp_servers;
pub mod mcp_tokens;
pub mod onboarding;
pub mod overview;
pub mod pentest_dashboard;
pub mod pentest_session;
@@ -33,7 +32,6 @@ pub use impact_analysis::ImpactAnalysisPage;
pub use issues::IssuesPage;
pub use mcp_servers::McpServersPage;
pub use mcp_tokens::McpTokensPage;
pub use onboarding::OnboardingPage;
pub use overview::OverviewPage;
pub use pentest_dashboard::PentestDashboardPage;
pub use pentest_session::PentestSessionPage;
@@ -1,377 +0,0 @@
use dioxus::prelude::*;
use crate::components::page_header::PageHeader;
use crate::infrastructure::onboarding::{
create_target, detect_target, fetch_applicable_scans, ArtifactInputDto,
};
/// (value, label, one-line description) for the 9 target families.
const TARGET_TYPES: &[(&str, &str, &str)] = &[
("web_app", "Web Application", "Front end + server"),
("backend_service", "Backend / API", "REST, GraphQL, gRPC"),
("desktop_app", "Desktop App", "Windows / macOS / Linux"),
("android_app", "Android App", "APK / AAB"),
("ios_app", "iOS App", "IPA"),
(
"firmware_bare_metal",
"Firmware — bare metal",
"No operating system",
),
("firmware_rtos", "Firmware — RTOS", "Zephyr, FreeRTOS, ..."),
(
"embedded_linux_yocto",
"Embedded Linux / Yocto",
"BSP + image",
),
("plc_sps", "PLC / SPS", "IEC 61131-3"),
];
/// (value, label) for the artifact kinds a user can attach.
const ARTIFACT_KINDS: &[(&str, &str)] = &[
("git_repo", "Git repository"),
("source_archive", "Source archive (zip)"),
("firmware_image", "Firmware image"),
("mobile_package", "Mobile package (APK/IPA)"),
("container_image", "Container image"),
("live_url", "Live URL"),
("plc_project", "PLC project"),
("plaintext_description", "Description (text)"),
];
const STEP_LABELS: &[&str] = &["Target type", "Artifacts", "Review", "Done"];
/// One row in the applicable-scans list on the success step.
#[component]
fn ScanRow(scan: serde_json::Value) -> Element {
let name = scan
.get("scan")
.and_then(|v| v.as_str())
.unwrap_or("?")
.to_string();
let rationale = scan
.get("rationale")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
let blocked = scan
.get("blocked_reason")
.and_then(|v| v.as_str())
.map(String::from);
let default_on = scan
.get("default_on")
.and_then(|v| v.as_bool())
.unwrap_or(false);
let badge_class = if blocked.is_some() {
"badge badge-info"
} else if default_on {
"badge badge-success"
} else {
"badge"
};
rsx! {
div { style: "display: flex; gap: 8px; align-items: center; padding: 6px 0;",
span { class: "{badge_class}", "{name}" }
span { style: "opacity: 0.8;", "{rationale}" }
if let Some(b) = blocked {
span { style: "opacity: 0.6; font-style: italic;", "— {b}" }
}
}
}
}
fn kind_label(kind: &str) -> &str {
ARTIFACT_KINDS
.iter()
.find(|(v, _)| *v == kind)
.map(|(_, l)| *l)
.unwrap_or(kind)
}
fn type_label(value: &str) -> &str {
TARGET_TYPES
.iter()
.find(|(v, _, _)| *v == value)
.map(|(_, l, _)| *l)
.unwrap_or(value)
}
#[component]
pub fn OnboardingPage() -> Element {
let mut step = use_signal(|| 0usize);
let mut name = use_signal(String::new);
let mut target_type = use_signal(String::new);
let mut description = use_signal(String::new);
let mut artifacts = use_signal(Vec::<ArtifactInputDto>::new);
// "Add artifact" mini-form.
let mut new_kind = use_signal(|| "git_repo".to_string());
let mut new_source = use_signal(String::new);
let mut new_branch = use_signal(|| "main".to_string());
// Create + result state.
let mut creating = use_signal(|| false);
let mut error = use_signal(|| Option::<String>::None);
let mut scans = use_signal(Vec::<serde_json::Value>::new);
let mut suggested = use_signal(|| Option::<String>::None);
let step_now = step();
let can_advance_type = !name().trim().is_empty() && !target_type().trim().is_empty();
let has_artifacts = !artifacts().is_empty();
rsx! {
PageHeader {
title: "Onboard a target",
description: "Add a target, attach its artifacts, and see which scans apply.",
}
// Stepper.
div { class: "wizard-steps",
for (i, label) in STEP_LABELS.iter().enumerate() {
div {
class: if i == step_now { "wizard-step wizard-step-active" } else { "wizard-step" },
span { class: "wizard-step-dot", "{i + 1}" }
span { class: "wizard-step-label", "{label}" }
}
}
}
if let Some(err) = error() {
div { class: "card", style: "border-color: var(--danger, #d33); margin-bottom: 12px;",
div { class: "card-header", "Error" }
div { style: "padding: 12px;", "{err}" }
}
}
div { class: "card",
// ---- Step 0: target type + name ----
if step_now == 0 {
div { class: "card-header", "What kind of software is this?" }
div { style: "padding: 16px;",
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
placeholder: "acme-web",
value: "{name}",
oninput: move |e| name.set(e.value()),
}
}
div {
style: "display: grid; grid-template-columns: repeat(auto-fill, minmax(200px, 1fr)); gap: 12px; margin-top: 12px;",
for (value, tlabel, tdesc) in TARGET_TYPES.iter().copied() {
div {
class: "card",
style: if target_type() == value {
"padding: 12px; cursor: pointer; border: 2px solid var(--accent, #3b82f6);"
} else {
"padding: 12px; cursor: pointer;"
},
onclick: move |_| target_type.set(value.to_string()),
div { style: "font-weight: 600;", "{tlabel}" }
div { style: "font-size: 0.85em; opacity: 0.7;", "{tdesc}" }
}
}
}
}
}
// ---- Step 1: artifacts ----
if step_now == 1 {
div { class: "card-header", "Attach artifacts" }
div { style: "padding: 16px;",
div { style: "display: flex; gap: 8px; flex-wrap: wrap; align-items: flex-end;",
div { class: "form-group", style: "margin: 0;",
label { "Kind" }
select {
value: "{new_kind}",
oninput: move |e| new_kind.set(e.value()),
for (value, klabel) in ARTIFACT_KINDS.iter().copied() {
option { value: "{value}", "{klabel}" }
}
}
}
div { class: "form-group", style: "margin: 0; flex: 1; min-width: 240px;",
label { "Reference (URL / path / text)" }
input {
r#type: "text",
placeholder: "https://git.example.com/acme.git",
value: "{new_source}",
oninput: move |e| new_source.set(e.value()),
}
}
if new_kind() == "git_repo" {
div { class: "form-group", style: "margin: 0;",
label { "Branch" }
input {
r#type: "text",
value: "{new_branch}",
oninput: move |e| new_branch.set(e.value()),
}
}
}
button {
class: "btn btn-secondary",
onclick: move |_| {
let kind = new_kind();
if !new_source().trim().is_empty() {
let branch = if kind == "git_repo" { Some(new_branch()) } else { None };
artifacts.write().push(ArtifactInputDto {
kind,
source_ref: new_source(),
branch,
plc_format: None,
});
new_source.set(String::new());
}
},
"+ Add"
}
}
div { style: "margin-top: 16px;",
if has_artifacts {
for (i, a) in artifacts().iter().enumerate() {
div {
style: "display: flex; justify-content: space-between; align-items: center; padding: 8px 12px; border: 1px solid var(--border, #333); border-radius: 6px; margin-bottom: 6px;",
span {
span { style: "opacity: 0.7;", "{kind_label(&a.kind)}: " }
"{a.source_ref}"
}
button {
class: "btn btn-ghost-danger btn-sm",
onclick: move |_| { artifacts.write().remove(i); },
"Remove"
}
}
}
} else {
div { style: "opacity: 0.6;", "No artifacts yet. Add at least one." }
}
}
}
}
// ---- Step 2: review + create ----
if step_now == 2 {
div { class: "card-header", "Review" }
div { style: "padding: 16px;",
div { class: "wizard-summary",
div { strong { "Name: " } "{name()}" }
div { strong { "Type: " } "{type_label(&target_type())}" }
div { strong { "Artifacts:" } }
ul {
for a in artifacts() {
li { "{kind_label(&a.kind)}: {a.source_ref}" }
}
}
}
div { style: "margin-top: 12px; opacity: 0.7; font-size: 0.9em;",
"The applicable scans (SAST / DAST / firmware / PLC) are shown after the target is created."
}
}
}
// ---- Step 3: created ----
if step_now == 3 {
div { class: "card-header", "Target onboarded" }
div { style: "padding: 16px;",
p {
strong { "{name()}" }
" was created."
if let Some(s) = suggested() {
span { " Suggested type from detection: " strong { "{type_label(&s)}" } "." }
}
}
h4 { style: "margin-top: 16px;", "Applicable scans" }
if scans().is_empty() {
div { style: "opacity: 0.6;", "No scans available (no code / URL / firmware artifact present)." }
} else {
for s in scans() {
ScanRow { scan: s }
}
}
div { style: "margin-top: 16px;",
button {
class: "btn btn-secondary",
onclick: move |_| {
step.set(0);
name.set(String::new());
target_type.set(String::new());
description.set(String::new());
artifacts.write().clear();
scans.write().clear();
suggested.set(None);
error.set(None);
},
"Onboard another"
}
}
}
}
}
// ---- Footer navigation ----
if step_now < 3 {
div { style: "display: flex; justify-content: space-between; margin-top: 16px;",
button {
class: "btn btn-back",
disabled: step_now == 0,
onclick: move |_| { if step() > 0 { step.set(step() - 1); } },
"Back"
}
if step_now < 2 {
button {
class: "btn btn-primary",
disabled: (step_now == 0 && !can_advance_type) || (step_now == 1 && !has_artifacts),
onclick: move |_| step.set(step() + 1),
"Next"
}
} else {
button {
class: "btn btn-primary",
disabled: creating(),
onclick: move |_| {
let n = name();
let tt = target_type();
let desc = description();
let arts = artifacts();
let d = if desc.trim().is_empty() { None } else { Some(desc) };
creating.set(true);
error.set(None);
spawn(async move {
match create_target(n, tt, d, arts).await {
Ok(resp) => {
let id = resp
.data
.get("_id")
.and_then(|o| o.get("$oid"))
.and_then(|s| s.as_str())
.map(String::from);
if let Some(id) = id {
if let Ok(sc) = fetch_applicable_scans(id.clone()).await {
scans.set(sc.data.scans);
}
if let Ok(det) = detect_target(id).await {
suggested.set(
det.data
.get("classification")
.and_then(|c| c.get("suggested"))
.and_then(|s| s.as_str())
.map(String::from),
);
}
}
step.set(3);
}
Err(e) => error.set(Some(e.to_string())),
}
creating.set(false);
});
},
if creating() { "Creating..." } else { "Create target" }
}
}
}
}
}
}