Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Opus 4.7 0e1ce44146 feat(m7.3): scheduler pulls tenants from registry, env as fallback
CI / Check (pull_request) Failing after 4m27s
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
Replaces the M7.2-C static `SCHEDULER_TENANT_IDS` env enumeration with
a live query to the tenant-registry at every tick. New tenants get
picked up without an agent restart; the env stays as the fallback
when the registry is unreachable so the scheduler is never silenced
by a registry outage.

Resolution order
1. agent.config.tenant_registry_url → GET <url>/v1/tenants
   - 5s timeout (kept short — we'd rather fall back than block the
     tick)
   - Frozen and Archived tenants filtered out (the M7.1 status gate
     would 402/410 them anyway, no point scanning their repos)
   - Accepts either {"id"} or {"tenant_id"} for forward compatibility
     with whatever shape the registry settles on
2. SCHEDULER_TENANT_IDS env (comma-separated) — fallback when the
   registry URL is unset OR the fetch fails OR the parsed response is
   empty. Each failure mode logs a warn with the url so operators see
   the problem.
3. DEFAULT_SCHEDULER_TENANT_ID ("dev") — last-ditch fallback so a
   bare `cargo run` against a clean Mongo still scans the dev tenant.

Why each tick instead of caching
- Tick frequency is every few hours (scan_schedule default
  "0 0 */6 * * *"). The registry call is at most 4 times a day per
  agent — cheap.
- Caching introduces a staleness window for newly provisioned
  tenants. The whole point of registry integration is to pick them
  up fast.

Startup log
- Includes "tenant source=tenant-registry" or "env" so operators can
  tell at a glance which mode the scheduler is in.

Test plan
- cargo fmt --all clean
- cargo clippy -p compliance-agent -- -D warnings clean
- cargo test -p compliance-agent --lib — 232 pass (+3 new):
    * filter_active_keeps_running_skips_frozen_archived
    * deserialize_registry_response_accepts_id_or_tenant_id (covers
      the {"id"|"tenant_id"} alias)
    * tenants_from_env_resolution (single test covering unset →
      default, csv → splits, "" → default — collapsed to one to
      avoid env-var test races)

Production
- Set TENANT_REGISTRY_URL in orca-infra alongside KEYCLOAK_URL when
  the registry is ready to serve. Until then, scheduler keeps using
  SCHEDULER_TENANT_IDS — no operator action needed.
- Future M7.4 cleanup: once tenant-registry adoption is universal,
  delete SCHEDULER_TENANT_IDS env support entirely.

Stacked on #95 (admin endpoints) since that PR added
tenant_registry_url to AgentConfig. Once #95 lands this auto-
retargets to main.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-30 17:24:18 +02:00
84 changed files with 1746 additions and 6871 deletions
-13
View File
@@ -7,17 +7,4 @@ ignore = [
# not a realistic attack surface here. Revisit when mongodb bumps hickory.
"RUSTSEC-2026-0118", # NSEC3 loop, no fix available upstream
"RUSTSEC-2026-0119", # O(n²) name compression, fixed in hickory-proto >=0.26.1
# rmcp 0.16.0 — DNS rebinding in Streamable HTTP server transport (missing
# Host header validation). Patched in rmcp >= 1.4.0, which is a major API
# version jump from our pin; rmcp shipped 0.x → 1.x → 2.x in three months
# and the migration touches every tool handler + the auth middleware we
# just landed in #92. Threat model in our deployment: the MCP server is
# exposed at a public hostname (comp-mcp-dev.meghsakha.com) behind orca's
# TLS-terminating ingress with per-tenant bearer auth — the attack model
# (browser DNS-rebinding into localhost MCP server) doesn't directly apply.
# Defense-in-depth Host-header check is still a worthwhile follow-up.
# FOLLOW-UP: bump rmcp to 2.x in a dedicated PR (M7.3 follow-up, sized
# multi-hour due to API surface change).
"RUSTSEC-2026-0189",
]
+10 -67
View File
@@ -9,33 +9,15 @@ 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 superseded PR runs, but NEVER cancel main-branch runs — those build and
# deploy per-service images, and cancelling one merge's deploy when the next
# merge lands leaves a service un-deployed (as happened between two back-to-back
# merges). So cancel-in-progress only for pull_request events.
# Cancel in-progress runs for the same branch/PR
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
cancel-in-progress: true
jobs:
# ---------------------------------------------------------------------------
@@ -54,44 +36,16 @@ jobs:
git remote add origin "${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
@@ -194,18 +148,13 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
# PAT for fetching the private tramiton-core git dependency during the
# image build (injected as a BuildKit secret, never baked into a layer).
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-agent
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker build -f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy agent"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
@@ -220,16 +169,13 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-dashboard
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.dashboard -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker build -f Dockerfile.dashboard -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy dashboard"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
@@ -265,16 +211,13 @@ jobs:
image: docker:27-cli
steps:
- name: Build, push and trigger orca redeploy
env:
TRAMITON_FETCH_TOKEN: ${{ secrets.TRAMITON_FETCH_TOKEN }}
run: |
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=registry.meghsakha.com/compliance-mcp
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.mcp -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker build -f Dockerfile.mcp -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy mcp"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
Generated
+13 -119
View File
@@ -676,7 +676,6 @@ dependencies = [
"jsonwebtoken",
"mongodb",
"octocrab",
"rand 0.9.2",
"regex",
"reqwest",
"secrecy",
@@ -692,9 +691,6 @@ dependencies = [
"tower-http",
"tracing",
"tracing-subscriber",
"tramiton-core",
"tramiton-repro",
"tramiton-sbom",
"urlencoding",
"uuid",
"walkdir",
@@ -822,15 +818,12 @@ dependencies = [
"bson",
"chrono",
"compliance-core",
"dashmap",
"dotenvy",
"hex",
"mongodb",
"rmcp",
"schemars 1.2.1",
"serde",
"serde_json",
"sha2",
"thiserror 2.0.18",
"tokio",
"tower-http",
@@ -1121,9 +1114,9 @@ dependencies = [
[[package]]
name = "crossbeam-epoch"
version = "0.9.20"
version = "0.9.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2d6914041f254d6e9176c01941b21115dcfb7089e55135a35411081bd106ef3f"
checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
dependencies = [
"crossbeam-utils",
]
@@ -2103,7 +2096,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
dependencies = [
"libc",
"windows-sys 0.52.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -3698,7 +3691,7 @@ version = "0.50.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
dependencies = [
"windows-sys 0.60.2",
"windows-sys 0.61.2",
]
[[package]]
@@ -3769,15 +3762,6 @@ dependencies = [
"syn",
]
[[package]]
name = "object"
version = "0.36.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62948e14d923ea95ea2c7c86c71013138b66525b86bdc08d2dcc262bdb497b87"
dependencies = [
"memchr",
]
[[package]]
name = "octocrab"
version = "0.44.1"
@@ -4209,7 +4193,7 @@ 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]]
@@ -4294,9 +4278,9 @@ dependencies = [
[[package]]
name = "quinn-proto"
version = "0.11.15"
version = "0.11.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4fcb935c5bec503c2f0e306bdd3e58bb9029dcb14fa8d9ac76e3a5256ac0763e"
checksum = "434b42fec591c96ef50e21e886936e66d3cc3f737104fdb9b737c40ffb94c098"
dependencies = [
"bytes",
"getrandom 0.3.4",
@@ -4679,7 +4663,7 @@ dependencies = [
"errno",
"libc",
"linux-raw-sys 0.4.15",
"windows-sys 0.52.0",
"windows-sys 0.59.0",
]
[[package]]
@@ -4692,7 +4676,7 @@ dependencies = [
"errno",
"libc",
"linux-raw-sys 0.12.1",
"windows-sys 0.52.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -5008,15 +4992,6 @@ 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"
@@ -5570,10 +5545,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "82a72c767771b47409d2345987fda8628641887d5466101319899796367354a0"
dependencies = [
"fastrand",
"getrandom 0.3.4",
"getrandom 0.4.1",
"once_cell",
"rustix 1.1.4",
"windows-sys 0.52.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -5831,27 +5806,6 @@ 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"
@@ -5861,20 +5815,6 @@ 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"
@@ -5882,7 +5822,7 @@ 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",
]
@@ -5896,12 +5836,6 @@ 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"
@@ -6148,46 +6082,6 @@ dependencies = [
"wasm-bindgen",
]
[[package]]
name = "tramiton-core"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"serde",
"tempfile",
"thiserror 1.0.69",
"toml",
"walkdir",
]
[[package]]
name = "tramiton-repro"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"serde",
"serde_json",
"sha2",
"tempfile",
"thiserror 1.0.69",
"toml",
"tramiton-core",
"walkdir",
]
[[package]]
name = "tramiton-sbom"
version = "0.4.1"
source = "git+ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git?tag=v0.4.1#ae4fc1376279f9edb9882605b20877335e7ba8ba"
dependencies = [
"object",
"serde",
"serde_json",
"sha2",
"tramiton-core",
"tramiton-repro",
]
[[package]]
name = "tree-sitter"
version = "0.24.7"
@@ -6746,7 +6640,7 @@ version = "0.1.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
dependencies = [
"windows-sys 0.48.0",
"windows-sys 0.61.2",
]
[[package]]
-2
View File
@@ -34,5 +34,3 @@ zip = { version = "2", features = ["aes-crypto", "deflate"] }
dashmap = "6"
tokio-stream = { version = "0.1", features = ["sync"] }
aes-gcm = "0.10"
rand = "0.9"
base64 = "0.22"
+2 -41
View File
@@ -2,22 +2,7 @@ FROM rust:1.94-bookworm AS builder
WORKDIR /app
COPY . .
# compliance-agent depends on the private tramiton-core git repo. Authenticate
# the fetch with a PAT passed as a BuildKit secret (never baked into a layer).
# Build with: DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN ...
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true cargo build --release -p compliance-agent
# A throwaway stage that packs a real nix store (store paths + the validity DB)
# into a compressed bootstrap tarball. Only the tarball is copied into the final
# image, so we don't carry a raw /nix copy layer.
FROM nixos/nix:latest AS nixseed
RUN tar -C / -czf /nix-bootstrap.tar.gz nix
RUN cargo build --release -p compliance-agent
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 git curl python3 python3-pip npm golang-go php-cli && rm -rf /var/lib/apt/lists/*
@@ -46,30 +31,7 @@ RUN pip3 install --break-system-packages semgrep
# Install ruff for Python linting
RUN pip3 install --break-system-packages ruff
# Real nix for the tramiton reproducible-build firmware SBOM.
#
# nix-portable's proot fallback can't run here: user namespaces are blocked by
# the container's default seccomp/apparmor profile, and orca exposes no way to
# relax it. So ship a *real* nix and disable its build sandbox
# (`sandbox = false`) — a plain gcc/make firmware build needs no user namespace,
# so it runs fine under the locked-down profile with no proot involved.
#
# The store is shipped as a bootstrap tarball and seeded onto /nix at first
# start (see docker/agent-entrypoint.sh), so a persistent /nix volume survives
# redeploys. A missing/broken nix just falls back to the analysis-only SBOM.
COPY --from=nixseed /nix-bootstrap.tar.gz /opt/nix-bootstrap.tar.gz
ENV PATH="/nix/var/nix/profiles/default/bin:${PATH}"
RUN mkdir -p /etc/nix && printf '%s\n' \
'experimental-features = nix-command flakes' \
'sandbox = false' \
'build-users-group =' \
'substituters = https://cache.nixos.org' \
'trusted-public-keys = cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY=' \
> /etc/nix/nix.conf
COPY --from=builder /app/target/release/compliance-agent /usr/local/bin/compliance-agent
COPY docker/agent-entrypoint.sh /usr/local/bin/agent-entrypoint.sh
RUN chmod +x /usr/local/bin/agent-entrypoint.sh
# Copy documentation for the help chat assistant
COPY --from=builder /app/README.md /app/README.md
@@ -81,6 +43,5 @@ RUN mkdir -p /data/compliance-scanner/ssh
EXPOSE 3001 3002
# Seeds /nix (fresh volume) from the bootstrap tarball, then runs the agent.
ENTRYPOINT ["/usr/local/bin/agent-entrypoint.sh"]
ENTRYPOINT ["compliance-agent"]
+1 -10
View File
@@ -7,16 +7,7 @@ ARG DOCS_URL=/docs
WORKDIR /app
COPY . .
ENV DOCS_URL=${DOCS_URL}
# compliance-agent (a workspace member) depends on the private tramiton-core git
# repo, so the workspace resolve needs it even to build the dashboard.
# Authenticate the fetch with a PAT passed as a BuildKit secret.
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true dx build --release --package compliance-dashboard
RUN dx build --release --package compliance-dashboard
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 && rm -rf /var/lib/apt/lists/*
+1 -10
View File
@@ -2,16 +2,7 @@ FROM rust:1.94-bookworm AS builder
WORKDIR /app
COPY . .
# compliance-agent (a workspace member) depends on the private tramiton-core git
# repo, so the workspace resolve needs it even to build the mcp binary.
# Authenticate the fetch with a PAT passed as a BuildKit secret.
RUN --mount=type=secret,id=tramiton_token \
if [ -s /run/secrets/tramiton_token ]; then \
git config --global \
url."https://sharang:$(cat /run/secrets/tramiton_token)@gitea.meghsakha.com/".insteadOf \
"ssh://git@gitea.meghsakha.com:22222/"; \
fi && \
CARGO_NET_GIT_FETCH_WITH_CLI=true cargo build --release -p compliance-mcp
RUN cargo build --release -p compliance-mcp
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y ca-certificates libssl3 && rm -rf /var/lib/apt/lists/*
-11
View File
@@ -10,16 +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 = "v0.4.1" }
# tramiton-repro drives the reproducible build (NixBackend seal_and_build) that
# yields a sealed lock; `libraries_from_inputs` is the analysis-only fallback.
tramiton-repro = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.1" }
# tramiton-sbom renders the bill of materials from a sealed lock (+ binary SCA).
tramiton-sbom = { git = "ssh://git@gitea.meghsakha.com:22222/sharang/tramiton.git", tag = "v0.4.1" }
serde = { workspace = true }
serde_json = { workspace = true }
tokio = { workspace = true }
@@ -52,7 +42,6 @@ tokio-tungstenite = { version = "0.26", features = ["rustls-tls-webpki-roots"] }
futures-core = "0.3"
dashmap = { workspace = true }
tokio-stream = { workspace = true }
rand = { workspace = true }
[dev-dependencies]
compliance-core = { workspace = true, features = ["mongodb", "axum"] }
+8 -26
View File
@@ -63,22 +63,7 @@ impl ComplianceAgent {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
orchestrator.run_target(repo_id, trigger).await
}
/// Alias for [`Self::run_scan`] — every scan runs the unified onboarded-target
/// pipeline. Kept as a distinct name for the `/targets/{id}/scan` endpoint's
/// intent.
pub async fn run_target_scan(
&self,
tenant_id: &str,
target_id: &str,
trigger: compliance_core::models::ScanTrigger,
) -> Result<(), crate::error::AgentError> {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
orchestrator.run_target(target_id, trigger).await
orchestrator.run(repo_id, trigger).await
}
/// Run a PR review: scan the diff and post review comments.
@@ -91,19 +76,16 @@ impl ComplianceAgent {
head_sha: &str,
) -> Result<(), crate::error::AgentError> {
let db = self.db_pool.for_tenant_id(tenant_id).await?;
let oid = mongodb::bson::oid::ObjectId::parse_str(repo_id)
.map_err(|e| crate::error::AgentError::Other(e.to_string()))?;
let target = db
.onboarded_targets()
.find_one(mongodb::bson::doc! { "_id": oid })
let repo = db
.repositories()
.find_one(mongodb::bson::doc! {
"_id": mongodb::bson::oid::ObjectId::parse_str(repo_id)
.map_err(|e| crate::error::AgentError::Other(e.to_string()))?
})
.await?
.ok_or_else(|| {
crate::error::AgentError::Other(format!("Target {repo_id} not found"))
crate::error::AgentError::Other(format!("Repository {repo_id} not found"))
})?;
let code = target.code_artifact().ok_or_else(|| {
crate::error::AgentError::Other(format!("Target {repo_id} has no code artifact"))
})?;
let repo = crate::pipeline::repo_view::RepoView::from_target(&target, code);
let orchestrator =
PipelineOrchestrator::new(self.config.clone(), db, self.llm.clone(), self.http.clone());
+4 -12
View File
@@ -146,7 +146,7 @@ pub async fn build_embeddings(
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match db
.onboarded_targets()
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
{
@@ -194,22 +194,14 @@ pub async fn build_embeddings(
}
};
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for embedding build");
return;
}
};
let view = crate::pipeline::repo_view::RepoView::from_target(&repo, code);
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
auth_token: view.auth_token.clone(),
auth_username: view.auth_username.clone(),
auth_token: repo.auth_token.clone(),
auth_username: repo.auth_username.clone(),
};
let git_ops =
crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds);
let repo_path = match git_ops.clone_or_fetch(&view.git_url, &view.name) {
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) {
Ok(p) => p,
Err(e) => {
tracing::error!("Failed to clone repo for embedding build: {e}");
+5 -13
View File
@@ -255,7 +255,7 @@ pub async fn get_file_content(
// Look up the repository to get repo name
let repo = db
.onboarded_targets()
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
@@ -317,7 +317,7 @@ pub async fn trigger_build(
let agent_clone = (*agent).clone();
tokio::spawn(async move {
let repo = match db
.onboarded_targets()
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(&repo_id).ok() })
.await
{
@@ -328,22 +328,14 @@ pub async fn trigger_build(
}
};
let code = match repo.code_artifact() {
Some(c) => c,
None => {
tracing::error!("Target {repo_id} has no code artifact for graph build");
return;
}
};
let view = crate::pipeline::repo_view::RepoView::from_target(&repo, code);
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent_clone.config.ssh_key_path.clone()),
auth_token: view.auth_token.clone(),
auth_username: view.auth_username.clone(),
auth_token: repo.auth_token.clone(),
auth_username: repo.auth_username.clone(),
};
let git_ops =
crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path, creds);
let repo_path = match git_ops.clone_or_fetch(&view.git_url, &view.name) {
let repo_path = match git_ops.clone_or_fetch(&repo.git_url, &repo.name) {
Ok(p) => p,
Err(e) => {
tracing::error!("Failed to clone repo for graph build: {e}");
+1 -13
View File
@@ -10,18 +10,6 @@ pub async fn health() -> Json<serde_json::Value> {
Json(serde_json::json!({ "status": "ok" }))
}
/// GET /api/v1/settings/ssh-public-key — the agent's SSH deploy public key,
/// for adding as a read-only deploy key on private git targets.
#[tracing::instrument(skip_all)]
pub async fn get_ssh_public_key(
axum::extract::Extension(agent): AgentExt,
) -> Result<Json<serde_json::Value>, axum::http::StatusCode> {
let public_path = format!("{}.pub", agent.config.ssh_key_path);
let public_key =
std::fs::read_to_string(&public_path).map_err(|_| axum::http::StatusCode::NOT_FOUND)?;
Ok(Json(serde_json::json!({ "public_key": public_key.trim() })))
}
#[tracing::instrument(skip_all)]
pub async fn stats_overview(
axum::extract::Extension(agent): AgentExt,
@@ -31,7 +19,7 @@ pub async fn stats_overview(
let db = &db;
let total_repositories = db
.onboarded_targets()
.repositories()
.count_documents(doc! {})
.await
.unwrap_or(0);
@@ -1,186 +0,0 @@
//! `/api/v1/mcp-tokens` — per-tenant API tokens for the MCP server.
//!
//! These are opaque static bearers issued via the dashboard (or a
//! direct curl with a KC JWT) and copied into LLM clients (Claude
//! Desktop / Cursor / ChatGPT). The MCP server hashes incoming bearers
//! and looks them up in the cross-tenant `<prefix>__admin.mcp_tokens`
//! collection to derive the tenant_id for routing.
//!
//! The raw token is shown to the caller exactly once at creation; the
//! database only ever stores the SHA-256 hash. Revocation is a soft
//! delete (sets `revoked: true`) so the audit log keeps the record.
use axum::extract::{Extension, Path};
use axum::http::StatusCode;
use axum::Json;
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine as _};
use compliance_core::models::{McpToken, McpTokenView};
use compliance_core::tenant_ctx::TenantCtx;
use mongodb::bson::doc;
use rand::RngCore;
use sha2::{Digest, Sha256};
use super::dto::{AgentExt, ApiResponse};
/// Mongo collection name inside the admin DB.
const COLLECTION: &str = "mcp_tokens";
/// Token prefix the MCP server expects on every bearer.
const TOKEN_PREFIX: &str = "mcpt_";
/// Bytes of randomness behind each token. 32 → ~256 bits.
/// Encoded as URL-safe base64 without padding → 43 chars.
/// Combined with `mcpt_` → 48-char tokens.
const TOKEN_RAND_BYTES: usize = 32;
#[derive(serde::Deserialize)]
pub struct CreateMcpTokenRequest {
pub name: String,
}
/// Returned exactly once at creation. The `token` field is gone from
/// the listing endpoint — the user must save it now.
#[derive(serde::Serialize)]
pub struct CreateMcpTokenResponse {
pub token: String,
pub view: McpTokenView,
}
/// `POST /api/v1/mcp-tokens` — mint a new token for the caller's tenant.
#[tracing::instrument(skip_all)]
pub async fn create_mcp_token(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateMcpTokenRequest>,
) -> Result<Json<CreateMcpTokenResponse>, StatusCode> {
if req.name.trim().is_empty() {
return Err(StatusCode::BAD_REQUEST);
}
let raw = generate_token();
let token_hash = sha256_hex(&raw);
let token_prefix: String = raw.chars().take(12).collect();
let mut token = McpToken {
id: None,
token_hash,
token_prefix,
tenant_id: tenant.0.tenant_id.clone(),
name: req.name.trim().to_string(),
created_by: tenant.0.user_id.clone(),
created_at: chrono::Utc::now(),
last_used_at: None,
revoked: false,
};
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let res = col.insert_one(&token).await.map_err(|e| {
tracing::error!("Failed to insert MCP token: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
token.id = res.inserted_id.as_object_id();
Ok(Json(CreateMcpTokenResponse {
view: McpTokenView::from(&token),
token: raw,
}))
}
/// `GET /api/v1/mcp-tokens` — list tokens for the caller's tenant.
/// Hash is never returned; only metadata + the 12-char prefix so the
/// user can identify which row is which.
#[tracing::instrument(skip_all)]
pub async fn list_mcp_tokens(
Extension(agent): AgentExt,
tenant: TenantCtx,
) -> Result<Json<ApiResponse<Vec<McpTokenView>>>, StatusCode> {
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let mut cursor = col
.find(doc! { "tenant_id": &tenant.0.tenant_id })
.sort(doc! { "created_at": -1 })
.await
.map_err(|e| {
tracing::error!("Failed to list MCP tokens: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
let mut out = Vec::new();
while cursor.advance().await.map_err(|e| {
tracing::warn!("MCP tokens cursor advance failed: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})? {
match cursor.deserialize_current() {
Ok(t) => out.push(McpTokenView::from(&t)),
Err(e) => tracing::warn!("Failed to deserialize MCP token: {e}"),
}
}
Ok(Json(ApiResponse {
data: out,
total: None,
page: None,
}))
}
/// `DELETE /api/v1/mcp-tokens/{id}` — revoke (soft delete).
/// Scoped to the caller's tenant: a user can't revoke another tenant's
/// token even if they guess its id.
#[tracing::instrument(skip_all, fields(id = %id))]
pub async fn revoke_mcp_token(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let col = agent.db_pool.admin_db().collection::<McpToken>(COLLECTION);
let result = col
.update_one(
doc! { "_id": oid, "tenant_id": &tenant.0.tenant_id },
doc! { "$set": { "revoked": true } },
)
.await
.map_err(|e| {
tracing::error!("Failed to revoke MCP token: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
if result.matched_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
Ok(Json(serde_json::json!({ "status": "revoked" })))
}
/// 32 bytes random → URL-safe base64 → 43 chars, no padding.
/// Prefixed with `mcpt_` so the MCP server can sniff the format
/// before bothering with the DB lookup.
fn generate_token() -> String {
let mut bytes = [0u8; TOKEN_RAND_BYTES];
rand::rng().fill_bytes(&mut bytes);
format!("{TOKEN_PREFIX}{}", URL_SAFE_NO_PAD.encode(bytes))
}
fn sha256_hex(s: &str) -> String {
let mut h = Sha256::new();
h.update(s.as_bytes());
hex::encode(h.finalize())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn generated_tokens_are_unique_and_prefixed() {
let a = generate_token();
let b = generate_token();
assert_ne!(a, b);
assert!(a.starts_with(TOKEN_PREFIX));
assert!(b.starts_with(TOKEN_PREFIX));
// 5 + 43 = 48 chars
assert_eq!(a.len(), 5 + 43);
}
#[test]
fn sha256_is_stable_and_64_hex() {
let h = sha256_hex("mcpt_abc");
assert_eq!(h.len(), 64);
assert!(h.chars().all(|c| c.is_ascii_hexdigit()));
assert_eq!(sha256_hex("mcpt_abc"), h);
}
}
+2 -2
View File
@@ -7,11 +7,10 @@ pub mod graph;
pub mod health;
pub mod help_chat;
pub mod issues;
pub mod mcp_tokens;
pub mod notifications;
pub mod onboarding;
pub mod pentest_handlers;
pub use pentest_handlers as pentest;
pub mod repos;
pub mod sbom;
pub mod scans;
@@ -20,5 +19,6 @@ pub use dto::*;
pub use findings::*;
pub use health::*;
pub use issues::*;
pub use repos::*;
pub use sbom::*;
pub use scans::*;
@@ -1,504 +0,0 @@
//! Onboarding API — CRUD for unified targets, artifact add, classification, and
//! the scan-applicability matrix. The wizard (and future integrations) drive
//! onboarding through these endpoints.
use std::collections::HashMap;
use std::sync::Arc;
use axum::extract::{Extension, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::{doc, oid::ObjectId, to_bson};
use serde::{Deserialize, Serialize};
use compliance_core::models::{
Artifact, ArtifactKind, ComplianceProfile, OnboardedTarget, PlcFormat, TargetScanConfig,
TargetType,
};
use compliance_core::scan_matrix::{applicable_scans, supports_pentest};
use compliance_core::tenant_ctx::TenantCtx;
use crate::agent::ComplianceAgent;
use crate::classify::{classify_target, MockFirmwareDetector};
use super::dto::tenant_db;
use super::{collect_cursor_async, ApiResponse, PaginationParams};
type AgentExt = Extension<Arc<ComplianceAgent>>;
/// A client-supplied artifact spec. The server builds the [`Artifact`] (and its
/// id) from it, so clients never set internal fields.
#[derive(Deserialize)]
pub struct ArtifactInput {
pub kind: ArtifactKind,
pub source_ref: String,
#[serde(default)]
pub branch: Option<String>,
#[serde(default)]
pub plc_format: Option<PlcFormat>,
}
impl ArtifactInput {
fn build(&self) -> Artifact {
let s = self.source_ref.clone();
match self.kind {
ArtifactKind::GitRepo => {
Artifact::git_repo(s, self.branch.clone().unwrap_or_else(|| "main".to_string()))
}
ArtifactKind::LiveUrl => Artifact::live_url(s),
ArtifactKind::FirmwareImage => Artifact::firmware_image(s),
ArtifactKind::SourceArchive => Artifact::source_archive(s),
ArtifactKind::MobilePackage => Artifact::mobile_package(s),
ArtifactKind::ContainerImage => Artifact::container_image(s),
ArtifactKind::PlcProject => {
Artifact::plc_project(s, self.plc_format.unwrap_or(PlcFormat::PlcopenXml))
}
ArtifactKind::PlaintextDescription => Artifact::plaintext(s),
}
}
}
#[derive(Deserialize)]
pub struct CreateTargetRequest {
pub name: String,
pub target_type: TargetType,
#[serde(default)]
pub description: Option<String>,
#[serde(default)]
pub artifacts: Vec<ArtifactInput>,
}
#[derive(Deserialize)]
pub struct UpdateTargetRequest {
pub name: Option<String>,
pub target_type: Option<TargetType>,
pub scan_config: Option<TargetScanConfig>,
pub compliance_profile: Option<ComplianceProfile>,
pub scan_schedule: Option<String>,
/// Replace the target's artifacts wholesale (used by the dashboard editor).
#[serde(default)]
pub artifacts: Option<Vec<ArtifactInput>>,
}
/// One applicable-scan option, serialized for the wizard.
#[derive(Serialize)]
pub struct ScanOptionDto {
pub scan: String,
pub default_on: bool,
pub rationale: String,
pub required_artifact: Option<String>,
pub blocked_reason: Option<String>,
}
#[derive(Serialize)]
pub struct ApplicableScansResponse {
pub scans: Vec<ScanOptionDto>,
pub pentest_supported: bool,
}
fn parse_oid(id: &str) -> Result<ObjectId, StatusCode> {
ObjectId::parse_str(id).map_err(|_| StatusCode::BAD_REQUEST)
}
/// GET /api/v1/targets — list onboarded targets (paginated).
#[tracing::instrument(skip_all)]
pub async fn list_targets(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> Result<Json<ApiResponse<Vec<OnboardedTarget>>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.onboarded_targets()
.count_documents(doc! {})
.await
.unwrap_or(0);
let targets = match db
.onboarded_targets()
.find(doc! {})
.skip(skip)
.limit(params.limit)
.await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!("Failed to fetch onboarded targets: {e}");
Vec::new()
}
};
Ok(Json(ApiResponse {
data: targets,
total: Some(total),
page: Some(params.page),
}))
}
/// POST /api/v1/targets — create an onboarded target.
#[tracing::instrument(skip_all)]
pub async fn create_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<CreateTargetRequest>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let mut target = OnboardedTarget::new(req.name, req.target_type);
target.description = req.description;
target.artifacts = req.artifacts.iter().map(ArtifactInput::build).collect();
let db = tenant_db(&agent, &tenant).await?;
let res = db
.onboarded_targets()
.insert_one(&target)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
target.id = res.inserted_id.as_object_id();
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// GET /api/v1/targets/{id} — fetch one target.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn get_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// PATCH /api/v1/targets/{id} — update mutable fields.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn update_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateTargetRequest>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let mut set = doc! { "updated_at": mongodb::bson::DateTime::now() };
if let Some(name) = req.name {
set.insert("name", name);
}
if let Some(tt) = req.target_type {
set.insert(
"target_type",
to_bson(&tt).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(sc) = req.scan_config {
set.insert(
"scan_config",
to_bson(&sc).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(cp) = req.compliance_profile {
set.insert(
"compliance_profile",
to_bson(&cp).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
if let Some(ss) = req.scan_schedule {
set.insert("scan_schedule", ss);
}
if let Some(arts) = req.artifacts {
let built: Vec<Artifact> = arts.iter().map(ArtifactInput::build).collect();
set.insert(
"artifacts",
to_bson(&built).map_err(|_| StatusCode::BAD_REQUEST)?,
);
}
db.onboarded_targets()
.update_one(doc! { "_id": oid }, doc! { "$set": set })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// DELETE /api/v1/targets/{id} — remove the target and its findings/scans.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn delete_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
db.onboarded_targets()
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
// Cascade all data keyed by repo_id == target id (best-effort).
let db = &db;
let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.tracker_issues()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db.graph_nodes().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_edges().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_builds().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.impact_analyses()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.code_embeddings()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.embedding_builds()
.delete_many(doc! { "repo_id": &id })
.await;
// DAST targets linked to this target, and all their downstream data.
if let Ok(mut cursor) = db.dast_targets().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(dt)) = cursor.next().await {
let dast_target_id = dt.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !dast_target_id.is_empty() {
cascade_delete_dast_target(db, &dast_target_id).await;
}
}
}
// Pentest sessions linked directly to this target (not via a DAST target).
if let Ok(mut cursor) = db.pentest_sessions().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "repo_id": &id })
.await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// Delete a DAST target and everything downstream of it (pentest sessions +
/// their attack chains / messages / findings, DAST scan runs + findings).
async fn cascade_delete_dast_target(db: &crate::database::Database, target_id: &str) {
use futures_util::StreamExt;
if let Ok(mut cursor) = db
.pentest_sessions()
.find(doc! { "target_id": target_id })
.await
{
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_scan_runs()
.delete_many(doc! { "target_id": target_id })
.await;
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(target_id) {
let _ = db.dast_targets().delete_one(doc! { "_id": oid }).await;
}
}
/// POST /api/v1/targets/{id}/artifacts — attach an artifact (by reference).
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn add_artifact(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(input): Json<ArtifactInput>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let artifact = to_bson(&input.build()).map_err(|_| StatusCode::BAD_REQUEST)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$push": { "artifacts": artifact }, "$set": { "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
get_target(Extension(agent), tenant, Path(id)).await
}
/// GET /api/v1/targets/{id}/applicable-scans — the scan-applicability matrix.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn applicable_scans_for_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<ApplicableScansResponse>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let scans = applicable_scans(&target)
.into_iter()
.map(|o| ScanOptionDto {
scan: o.scan.to_string(),
default_on: o.default_on,
rationale: o.rationale,
required_artifact: o.required_artifact.map(|k| k.to_string()),
blocked_reason: o.blocked_reason,
})
.collect();
Ok(Json(ApiResponse {
data: ApplicableScansResponse {
scans,
pentest_supported: supports_pentest(target.target_type),
},
total: None,
page: None,
}))
}
/// POST /api/v1/targets/{id}/detect — classify the target from its artifacts.
///
/// This is the lightweight pass: it classifies from artifact kinds without
/// ingesting (cloning) sources, so it returns immediately. Deep detection (after
/// ingest, with tramiton firmware analysis) is a follow-up background step.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn detect_target(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<ApiResponse<OnboardedTarget>>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
let mut target = db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
// No ingested working paths here → kind-based classification only; the mock
// firmware detector is never invoked (no firmware working path present).
let empty = HashMap::new();
let detector = MockFirmwareDetector { detection: None };
let classification = classify_target(&target, &empty, &detector)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let classification_bson =
to_bson(&classification).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
db.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "classification": classification_bson, "updated_at": mongodb::bson::DateTime::now() } },
)
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
target.classification = Some(classification);
Ok(Json(ApiResponse {
data: target,
total: None,
page: None,
}))
}
/// POST /api/v1/targets/{id}/scan — trigger a scan for the target.
///
/// Dispatches to the unified pipeline when `UNIFIED_PIPELINE` is set (else the
/// legacy path). Runs in the background and returns immediately.
#[tracing::instrument(skip_all, fields(target_id = %id))]
pub async fn trigger_target_scan(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = parse_oid(&id)?;
let db = tenant_db(&agent, &tenant).await?;
// 404 if the target doesn't exist for this tenant.
if db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.is_none()
{
return Err(StatusCode::NOT_FOUND);
}
let agent_clone = (*agent).clone();
let tenant_id = tenant.0.tenant_id.clone();
tokio::spawn(async move {
// Always the unified target pipeline — this endpoint is about an
// onboarded target by construction, independent of the global
// `unified_pipeline` transition flag used by the legacy paths.
if let Err(e) = agent_clone
.run_target_scan(
&tenant_id,
&id,
compliance_core::models::ScanTrigger::Manual,
)
.await
{
tracing::error!("Manual target scan failed for {id}: {e}");
}
});
Ok(Json(serde_json::json!({ "status": "scan_triggered" })))
}
@@ -113,14 +113,14 @@ pub async fn create_session(
session.config = Some(config.clone());
session.repo_id = target.repo_id.clone();
// Resolve repo_id (target id) from git_repo_url if provided
// Resolve repo_id from git_repo_url if provided
if let Some(ref git_url) = config.git_repo_url {
if let Ok(Some(target)) = db
.onboarded_targets()
.find_one(doc! { "artifacts.source_ref": git_url })
if let Ok(Some(repo)) = db
.repositories()
.find_one(doc! { "git_url": git_url })
.await
{
session.repo_id = target.id.map(|oid| oid.to_hex());
session.repo_id = repo.id.map(|oid| oid.to_hex());
}
}
@@ -380,20 +380,17 @@ pub async fn lookup_repo(
) -> Result<Json<ApiResponse<serde_json::Value>>, StatusCode> {
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.onboarded_targets()
.find_one(doc! { "artifacts.source_ref": &params.url })
.repositories()
.find_one(doc! { "git_url": &params.url })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
let data = match repo {
Some(r) => {
let git = r.code_artifact().and_then(|c| c.git.as_ref());
serde_json::json!({
"name": r.name,
"default_branch": git.map(|g| g.default_branch.clone()),
"last_scanned_commit": git.and_then(|g| g.last_scanned_commit.clone()),
})
}
Some(r) => serde_json::json!({
"name": r.name,
"default_branch": r.default_branch,
"last_scanned_commit": r.last_scanned_commit,
}),
None => serde_json::Value::Null,
};
+339
View File
@@ -0,0 +1,339 @@
use axum::extract::{Extension, Path, Query};
use axum::http::StatusCode;
use axum::Json;
use mongodb::bson::doc;
use super::dto::*;
use compliance_core::models::*;
use compliance_core::tenant_ctx::TenantCtx;
#[tracing::instrument(skip_all)]
pub async fn list_repositories(
Extension(agent): AgentExt,
tenant: TenantCtx,
Query(params): Query<PaginationParams>,
) -> ApiResult<Vec<TrackedRepository>> {
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
let skip = (params.page.saturating_sub(1)) * params.limit as u64;
let total = db
.repositories()
.count_documents(doc! {})
.await
.unwrap_or(0);
let repos = match db
.repositories()
.find(doc! {})
.skip(skip)
.limit(params.limit)
.await
{
Ok(cursor) => collect_cursor_async(cursor).await,
Err(e) => {
tracing::warn!("Failed to fetch repositories: {e}");
Vec::new()
}
};
Ok(Json(ApiResponse {
data: repos,
total: Some(total),
page: Some(params.page),
}))
}
#[tracing::instrument(skip_all)]
pub async fn add_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Json(req): Json<AddRepositoryRequest>,
) -> Result<Json<ApiResponse<TrackedRepository>>, (StatusCode, String)> {
// Validate repository access before saving
let creds = crate::pipeline::git::RepoCredentials {
ssh_key_path: Some(agent.config.ssh_key_path.clone()),
auth_token: req.auth_token.clone(),
auth_username: req.auth_username.clone(),
};
if let Err(e) = crate::pipeline::git::GitOps::test_access(&req.git_url, &creds) {
return Err((
StatusCode::BAD_REQUEST,
format!("Cannot access repository: {e}"),
));
}
let mut repo = TrackedRepository::new(req.name, req.git_url);
repo.default_branch = req.default_branch;
repo.auth_token = req.auth_token;
repo.auth_username = req.auth_username;
repo.tracker_type = req.tracker_type;
repo.tracker_owner = req.tracker_owner;
repo.tracker_repo = req.tracker_repo;
repo.tracker_token = req.tracker_token;
repo.scan_schedule = req.scan_schedule;
let db = tenant_db(&agent, &tenant)
.await
.map_err(|s| (s, "failed to acquire tenant database".to_string()))?;
db.repositories().insert_one(&repo).await.map_err(|_| {
(
StatusCode::CONFLICT,
"Repository already exists".to_string(),
)
})?;
Ok(Json(ApiResponse {
data: repo,
total: None,
page: None,
}))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn update_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
Json(req): Json<UpdateRepositoryRequest>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let mut set_doc = doc! { "updated_at": mongodb::bson::DateTime::now() };
if let Some(name) = &req.name {
set_doc.insert("name", name);
}
if let Some(branch) = &req.default_branch {
set_doc.insert("default_branch", branch);
}
if let Some(token) = &req.auth_token {
set_doc.insert("auth_token", token);
}
if let Some(username) = &req.auth_username {
set_doc.insert("auth_username", username);
}
if let Some(tracker_type) = &req.tracker_type {
set_doc.insert("tracker_type", tracker_type.to_string());
}
if let Some(owner) = &req.tracker_owner {
set_doc.insert("tracker_owner", owner);
}
if let Some(repo) = &req.tracker_repo {
set_doc.insert("tracker_repo", repo);
}
if let Some(token) = &req.tracker_token {
set_doc.insert("tracker_token", token);
}
if let Some(schedule) = &req.scan_schedule {
set_doc.insert("scan_schedule", schedule);
}
let result = db
.repositories()
.update_one(doc! { "_id": oid }, doc! { "$set": set_doc })
.await
.map_err(|e| {
tracing::warn!("Failed to update repository: {e}");
StatusCode::INTERNAL_SERVER_ERROR
})?;
if result.matched_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
Ok(Json(serde_json::json!({ "status": "updated" })))
}
#[tracing::instrument(skip_all)]
pub async fn get_ssh_public_key(
Extension(agent): AgentExt,
) -> Result<Json<serde_json::Value>, StatusCode> {
let public_path = format!("{}.pub", agent.config.ssh_key_path);
let public_key = std::fs::read_to_string(&public_path).map_err(|_| StatusCode::NOT_FOUND)?;
Ok(Json(serde_json::json!({ "public_key": public_key.trim() })))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn trigger_scan(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let agent_clone = (*agent).clone();
let tenant_id = tenant.0.tenant_id.clone();
tokio::spawn(async move {
if let Err(e) = agent_clone
.run_scan(&tenant_id, &id, ScanTrigger::Manual)
.await
{
tracing::error!("Manual scan failed for {id}: {e}");
}
});
Ok(Json(serde_json::json!({ "status": "scan_triggered" })))
}
/// Return the webhook secret for a repository (used by dashboard to display it)
pub async fn get_webhook_config(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let repo = db
.repositories()
.find_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
.ok_or(StatusCode::NOT_FOUND)?;
let tracker_type = repo
.tracker_type
.as_ref()
.map(|t| t.to_string())
.unwrap_or_else(|| "gitea".to_string());
Ok(Json(serde_json::json!({
"webhook_secret": repo.webhook_secret,
"tracker_type": tracker_type,
})))
}
#[tracing::instrument(skip_all, fields(repo_id = %id))]
pub async fn delete_repository(
Extension(agent): AgentExt,
tenant: TenantCtx,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, StatusCode> {
let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
let db = tenant_db(&agent, &tenant).await?;
let db = &db;
// Delete the repository
let result = db
.repositories()
.delete_one(doc! { "_id": oid })
.await
.map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
if result.deleted_count == 0 {
return Err(StatusCode::NOT_FOUND);
}
// Cascade delete all related data
let _ = db.findings().delete_many(doc! { "repo_id": &id }).await;
let _ = db.sbom_entries().delete_many(doc! { "repo_id": &id }).await;
let _ = db.scan_runs().delete_many(doc! { "repo_id": &id }).await;
let _ = db.cve_alerts().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.tracker_issues()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db.graph_nodes().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_edges().delete_many(doc! { "repo_id": &id }).await;
let _ = db.graph_builds().delete_many(doc! { "repo_id": &id }).await;
let _ = db
.impact_analyses()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.code_embeddings()
.delete_many(doc! { "repo_id": &id })
.await;
let _ = db
.embedding_builds()
.delete_many(doc! { "repo_id": &id })
.await;
// Cascade delete DAST targets linked to this repo, and all their downstream data
// (scan runs, findings, pentest sessions, attack chains, messages)
if let Ok(mut cursor) = db.dast_targets().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(target)) = cursor.next().await {
let target_id = target.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !target_id.is_empty() {
cascade_delete_dast_target(db, &target_id).await;
}
}
}
// Also delete pentest sessions linked directly to this repo (not via target)
if let Ok(mut cursor) = db.pentest_sessions().find(doc! { "repo_id": &id }).await {
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
// Delete DAST findings produced by this session
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "repo_id": &id })
.await;
Ok(Json(serde_json::json!({ "status": "deleted" })))
}
/// Cascade-delete a DAST target and all its downstream data.
async fn cascade_delete_dast_target(db: &crate::database::Database, target_id: &str) {
// Delete pentest sessions for this target (and their attack chains + messages)
if let Ok(mut cursor) = db
.pentest_sessions()
.find(doc! { "target_id": target_id })
.await
{
use futures_util::StreamExt;
while let Some(Ok(session)) = cursor.next().await {
let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
if !session_id.is_empty() {
let _ = db
.attack_chain_nodes()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.pentest_messages()
.delete_many(doc! { "session_id": &session_id })
.await;
let _ = db
.dast_findings()
.delete_many(doc! { "session_id": &session_id })
.await;
}
}
}
let _ = db
.pentest_sessions()
.delete_many(doc! { "target_id": target_id })
.await;
// Delete DAST scan runs and their findings
let _ = db
.dast_findings()
.delete_many(doc! { "target_id": target_id })
.await;
let _ = db
.dast_scan_runs()
.delete_many(doc! { "target_id": target_id })
.await;
// Delete the target itself
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(target_id) {
let _ = db.dast_targets().delete_one(doc! { "_id": oid }).await;
}
}
+1 -1
View File
@@ -282,7 +282,7 @@ pub async fn license_summary(
}
})
.collect();
summaries.sort_by_key(|s| std::cmp::Reverse(s.count));
summaries.sort_by(|a, b| b.count.cmp(&a.count));
Ok(Json(ApiResponse {
data: summaries,
+8 -30
View File
@@ -11,32 +11,19 @@ pub fn build_router() -> Router {
"/api/v1/settings/ssh-public-key",
get(handlers::get_ssh_public_key),
)
// Unified onboarding targets (#131).
.route("/api/v1/repositories", get(handlers::list_repositories))
.route("/api/v1/repositories", post(handlers::add_repository))
.route(
"/api/v1/targets",
get(handlers::onboarding::list_targets).post(handlers::onboarding::create_target),
"/api/v1/repositories/{id}/scan",
post(handlers::trigger_scan),
)
.route(
"/api/v1/targets/{id}",
get(handlers::onboarding::get_target)
.patch(handlers::onboarding::update_target)
.delete(handlers::onboarding::delete_target),
"/api/v1/repositories/{id}",
delete(handlers::delete_repository).patch(handlers::update_repository),
)
.route(
"/api/v1/targets/{id}/artifacts",
post(handlers::onboarding::add_artifact),
)
.route(
"/api/v1/targets/{id}/applicable-scans",
get(handlers::onboarding::applicable_scans_for_target),
)
.route(
"/api/v1/targets/{id}/detect",
post(handlers::onboarding::detect_target),
)
.route(
"/api/v1/targets/{id}/scan",
post(handlers::onboarding::trigger_target_scan),
"/api/v1/repositories/{id}/webhook-config",
get(handlers::get_webhook_config),
)
.route("/api/v1/findings", get(handlers::list_findings))
.route("/api/v1/findings/{id}", get(handlers::get_finding))
@@ -59,15 +46,6 @@ pub fn build_router() -> Router {
.route("/api/v1/sbom/diff", get(handlers::sbom_diff))
.route("/api/v1/issues", get(handlers::list_issues))
.route("/api/v1/scan-runs", get(handlers::list_scan_runs))
// MCP token management (per-tenant API tokens for the MCP server)
.route(
"/api/v1/mcp-tokens",
get(handlers::mcp_tokens::list_mcp_tokens).post(handlers::mcp_tokens::create_mcp_token),
)
.route(
"/api/v1/mcp-tokens/{id}",
delete(handlers::mcp_tokens::revoke_mcp_token),
)
// Graph API endpoints
.route("/api/v1/graph/{repo_id}", get(handlers::graph::get_graph))
.route(
-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"),
+14 -80
View File
@@ -141,25 +141,6 @@ impl DatabasePool {
&self.client
}
/// Cross-tenant admin database used by features that intentionally
/// span tenants (today: MCP bearer tokens — each token row carries
/// a `tenant_id` and the MCP server reads them to route requests).
///
/// The name `<db_prefix>__admin` (double underscore) is reserved —
/// the sanitizer never produces it for a normal tenant DB because
/// the natural format is `<db_prefix>_<sanitized_tenant_id>` (one
/// underscore) and tenant_ids would have to start with `_admin` to
/// collide. New tenant provisioning should reject such ids.
pub fn admin_db(&self) -> mongodb::Database {
self.client.database(&self.admin_db_name())
}
/// Name of the admin database — public so tests / operators can
/// drop it via the raw client.
pub fn admin_db_name(&self) -> String {
format!("{}__admin", self.db_prefix)
}
/// List every Mongo database currently belonging to this pool,
/// identified by the `<db_prefix>_` prefix. The result is the raw
/// database names — opening one for offboarding/cleanup goes
@@ -179,23 +160,6 @@ 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.
@@ -249,6 +213,16 @@ impl Database {
}
pub async fn ensure_indexes(&self) -> Result<(), AgentError> {
// repositories: unique git_url
self.repositories()
.create_index(
IndexModel::builder()
.keys(doc! { "git_url": 1 })
.options(IndexOptions::builder().unique(true).build())
.build(),
)
.await?;
// findings: unique fingerprint
self.findings()
.create_index(
@@ -435,40 +409,14 @@ impl Database {
)
.await?;
// onboarded_targets: multikey on artifact source ref (webhook + dedupe
// lookup). Non-unique — "one git URL per tenant" is enforced in the
// create handler, since a unique multikey index on an array field has
// null-collision caveats.
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "artifacts.source_ref": 1 })
.build(),
)
.await?;
// onboarded_targets: multikey on artifact kind
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "artifacts.kind": 1 })
.build(),
)
.await?;
// onboarded_targets: target_type filter
self.onboarded_targets()
.create_index(
IndexModel::builder()
.keys(doc! { "target_type": 1 })
.build(),
)
.await?;
tracing::info!("Database indexes ensured");
Ok(())
}
pub fn repositories(&self) -> Collection<TrackedRepository> {
self.inner.collection("repositories")
}
pub fn findings(&self) -> Collection<Finding> {
self.inner.collection("findings")
}
@@ -517,20 +465,6 @@ impl Database {
self.inner.collection("dast_targets")
}
/// The unified onboarding targets that replace `repositories` and
/// `dast_targets`. Ids are preserved from the legacy collections during
/// migration so downstream `repo_id` / `target_id` references keep resolving.
pub fn onboarded_targets(&self) -> Collection<OnboardedTarget> {
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());
}
}
-2
View File
@@ -2,11 +2,9 @@
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 pentest;
pub mod pipeline;
-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,
@@ -1,152 +0,0 @@
//! Firmware SBOM via tramiton.
//!
//! Phase 2 (full, the default): drive a **reproducible build** with tramiton's
//! `NixBackend` — `analyze` → `seal_and_build` → a sealed lock whose libraries
//! are pinned and whose firmware artifact carries a content hash — then render
//! the SBOM from the lock plus deep binary SCA of pre-compiled inputs. This is
//! the complete bill of materials (toolchain + every fetched library + the
//! firmware image), the same one `tramiton sbom` produces.
//!
//! Phase 1 fallback (analysis-only): when no nix backend is available or the
//! build fails, fall back to the resolvable libraries + toolchain from the build
//! plan alone (no build). A scan therefore always yields *something*, and a nix
//! that can't run in the deployment never breaks a scan.
use std::path::Path;
use compliance_core::models::{SbomEntry, TargetType};
use tramiton_repro::ReproBackend;
use tramiton_sbom::ComponentKind;
/// Whether firmware SBOM applies to this target family.
pub fn is_firmware_target(target_type: TargetType) -> bool {
matches!(
target_type,
TargetType::FirmwareBareMetal | TargetType::FirmwareRtos | TargetType::EmbeddedLinuxYocto
)
}
/// Build SBOM entries for a firmware target from its source tree. Prefers a full
/// reproducible build (sealed lock); falls back to analysis-only. Returns an
/// empty vector when tramiton cannot even form a build plan.
pub async fn firmware_sbom_entries(path: &Path, repo_id: &str) -> Vec<SbomEntry> {
let p = path.to_path_buf();
let repo = repo_id.to_string();
// The whole analyze → seal → build → render sequence is blocking (it shells
// out to nix), so keep it off the async runtime. Bound it: a firmware build
// that hangs must not wedge the scan (the orphaned task is abandoned).
let handle = tokio::task::spawn_blocking(move || build_sbom_blocking(&p, &repo));
match tokio::time::timeout(std::time::Duration::from_secs(900), handle).await {
Ok(Ok(entries)) => entries,
Ok(Err(e)) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: task join error");
Vec::new()
}
Err(_) => {
tracing::warn!(repo_id, "Firmware SBOM: build exceeded 15m; skipping");
Vec::new()
}
}
}
fn build_sbom_blocking(path: &Path, repo_id: &str) -> Vec<SbomEntry> {
let repo = tramiton_core::Repo::new(path);
let plan = match tramiton_core::provider::analyze(&repo) {
Ok(Some(bp)) => bp,
Ok(None) => return Vec::new(),
Err(e) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: tramiton analyze failed");
return Vec::new();
}
};
// Phase 2: reproducible build → sealed lock → complete SBOM.
if let Some(backend) = tramiton_repro::NixBackend::detect() {
match tramiton_repro::seal_and_build(&backend, &plan, path) {
Ok(lock) => {
let mut sbom = tramiton_sbom::Sbom::from_lock(&lock, repo_id);
// Deep binary SCA of any pre-compiled inputs in the tree.
sbom.components.extend(tramiton_sbom::binary::scan(path));
let entries = sbom_to_entries(&sbom, repo_id);
tracing::info!(
repo_id,
backend = backend.name(),
count = entries.len(),
"Firmware SBOM: sealed reproducible build"
);
return entries;
}
Err(e) => {
tracing::warn!(repo_id, error = %e, "Firmware SBOM: reproducible build failed; falling back to analysis-only")
}
}
} else {
tracing::info!(
repo_id,
"Firmware SBOM: no nix backend available; analysis-only SBOM"
);
}
// Phase 1 fallback: analysis-only (toolchain + resolvable libraries).
analysis_entries(&plan, repo_id)
}
/// Map a rendered [`tramiton_sbom::Sbom`] (primary firmware + components) into
/// our [`SbomEntry`] rows. Source-file (`File`) components are dropped — they are
/// build inputs, not a dependency inventory.
fn sbom_to_entries(sbom: &tramiton_sbom::Sbom, repo_id: &str) -> Vec<SbomEntry> {
let mut entries = Vec::new();
if let Some(primary) = &sbom.primary {
entries.push(component_to_entry(primary, repo_id));
}
for c in &sbom.components {
if matches!(c.kind, ComponentKind::File) {
continue;
}
entries.push(component_to_entry(c, repo_id));
}
entries
}
fn component_to_entry(c: &tramiton_sbom::Component, repo_id: &str) -> SbomEntry {
let manager = match c.kind {
ComponentKind::Firmware => "firmware",
ComponentKind::Library => "library",
ComponentKind::Toolchain => "toolchain",
ComponentKind::File => "file",
};
let mut entry = SbomEntry::new(
repo_id.to_string(),
c.name.clone(),
c.version.clone().unwrap_or_default(),
manager.to_string(),
);
entry.purl = c.source.clone();
entry
}
/// Analysis-only components from the build plan: the cross-toolchain plus the
/// resolvable fetched libraries, without a build.
fn analysis_entries(bp: &tramiton_core::BuildPlan, repo_id: &str) -> Vec<SbomEntry> {
let mut entries = Vec::new();
if let Some(id) = bp.toolchain.id.clone() {
let version = bp.toolchain.version.clone().unwrap_or_default();
entries.push(SbomEntry::new(
repo_id.to_string(),
id,
version,
"toolchain".to_string(),
));
}
for lib in tramiton_repro::lock::libraries_from_inputs(&bp.inputs) {
let mut entry = SbomEntry::new(
repo_id.to_string(),
lib.name,
lib.revision,
"library".to_string(),
);
entry.purl = lib.source;
entries.push(entry);
}
entries
}
+2 -48
View File
@@ -80,10 +80,7 @@ impl GitOps {
#[tracing::instrument(skip_all, fields(repo_name = %repo_name))]
pub fn clone_or_fetch(&self, git_url: &str, repo_name: &str) -> Result<PathBuf, AgentError> {
// Names can contain slashes or other path-hostile characters (a target
// named after a repo path, say); collapse to one safe directory segment
// so the clone path never nests or breaks.
let repo_path = self.base_path.join(sanitize_repo_dir(repo_name));
let repo_path = self.base_path.join(repo_name);
if repo_path.exists() {
tracing::info!("fetching updates for existing repo");
@@ -138,7 +135,7 @@ impl GitOps {
/// Build credentials from agent config + per-repo overrides
pub fn make_repo_credentials(
config: &compliance_core::AgentConfig,
repo: &crate::pipeline::repo_view::RepoView,
repo: &compliance_core::models::TrackedRepository,
) -> RepoCredentials {
RepoCredentials {
ssh_key_path: Some(config.ssh_key_path.clone()),
@@ -256,46 +253,3 @@ pub struct DiffFile {
pub path: String,
pub hunks: String,
}
/// Collapse a repository name into a single filesystem-safe directory segment.
/// Names may carry slashes or other path-hostile characters (a target named
/// after a repo path, for instance); those would otherwise nest or break the
/// clone path, so map anything outside `[A-Za-z0-9._-]` to `_`.
fn sanitize_repo_dir(name: &str) -> String {
let mapped: String = name
.chars()
.map(|c| {
if c.is_ascii_alphanumeric() || c == '-' || c == '_' || c == '.' {
c
} else {
'_'
}
})
.collect();
let trimmed = mapped.trim_matches(|c| c == '.' || c == '_');
if trimmed.is_empty() {
"repo".to_string()
} else {
trimmed.to_string()
}
}
#[cfg(test)]
mod tests {
use super::sanitize_repo_dir;
#[test]
fn sanitizes_path_hostile_names() {
assert_eq!(
sanitize_repo_dir("zephyr-example-app"),
"zephyr-example-app"
);
assert_eq!(
sanitize_repo_dir("ChristianRinn/bare_metal_stm32f411xe"),
"ChristianRinn_bare_metal_stm32f411xe"
);
assert_eq!(sanitize_repo_dir("../../etc/passwd"), "etc_passwd");
assert_eq!(sanitize_repo_dir("a b:c"), "a_b_c");
assert_eq!(sanitize_repo_dir("///"), "repo");
}
}
@@ -1,6 +1,5 @@
use mongodb::bson::doc;
use crate::pipeline::repo_view::RepoView;
use compliance_core::models::*;
use super::orchestrator::{extract_base_url, PipelineOrchestrator};
@@ -11,7 +10,7 @@ use crate::trackers;
impl PipelineOrchestrator {
/// Build an issue tracker client from a repository's tracker configuration.
/// Returns `None` if the repo has no tracker configured.
pub(super) fn build_tracker(&self, repo: &RepoView) -> Option<TrackerDispatch> {
pub(super) fn build_tracker(&self, repo: &TrackedRepository) -> Option<TrackerDispatch> {
let tracker_type = repo.tracker_type.as_ref()?;
// Per-repo token takes precedence, fall back to global config
match tracker_type {
@@ -82,7 +81,7 @@ impl PipelineOrchestrator {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
pub(super) async fn create_tracker_issues(
&self,
repo: &RepoView,
repo: &TrackedRepository,
repo_id: &str,
new_findings: &[Finding],
) -> Result<(), AgentError> {
-3
View File
@@ -1,7 +1,6 @@
pub mod code_review;
pub mod cve;
pub mod dedup;
pub mod firmware_sbom;
pub mod git;
pub mod gitleaks;
mod graph_build;
@@ -9,9 +8,7 @@ mod issue_creation;
pub mod lint;
pub mod orchestrator;
pub mod patterns;
pub mod plan;
mod pr_review;
pub mod repo_view;
pub mod sbom;
pub mod semgrep;
mod tracker_dispatch;
+80 -367
View File
@@ -15,8 +15,6 @@ use crate::pipeline::git::GitOps;
use crate::pipeline::gitleaks::GitleaksScanner;
use crate::pipeline::lint::LintScanner;
use crate::pipeline::patterns::{GdprPatternScanner, OAuthPatternScanner};
use crate::pipeline::plan::build_scan_plan;
use crate::pipeline::repo_view::RepoView;
use crate::pipeline::sbom::SbomScanner;
use crate::pipeline::semgrep::SemgrepScanner;
@@ -52,8 +50,72 @@ impl PipelineOrchestrator {
}
}
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, trigger = ?trigger))]
pub async fn run(&self, repo_id: &str, trigger: ScanTrigger) -> Result<(), AgentError> {
// Look up the repository
let repo = self
.db
.repositories()
.find_one(doc! { "_id": mongodb::bson::oid::ObjectId::parse_str(repo_id).map_err(|e| AgentError::Other(e.to_string()))? })
.await?
.ok_or_else(|| AgentError::Other(format!("Repository {repo_id} not found")))?;
// Create scan run
let scan_run = ScanRun::new(repo_id.to_string(), trigger);
let insert = self.db.scan_runs().insert_one(&scan_run).await?;
let scan_run_id = insert
.inserted_id
.as_object_id()
.map(|id| id.to_hex())
.unwrap_or_default();
let result = self.run_pipeline(&repo, &scan_run_id).await;
// Update scan run status
match &result {
Ok(count) => {
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
}
},
)
.await?;
}
Err(e) => {
tracing::error!(repo_id, error = %e, "Scan pipeline failed");
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! {
"$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
}
},
)
.await?;
}
}
result.map(|_| ())
}
#[tracing::instrument(skip_all, fields(repo_id = repo.name.as_str()))]
async fn run_pipeline(&self, repo: &RepoView, scan_run_id: &str) -> Result<u32, AgentError> {
async fn run_pipeline(
&self,
repo: &TrackedRepository,
scan_run_id: &str,
) -> Result<u32, AgentError> {
let repo_id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
// Stage 0: Change detection
@@ -67,6 +129,7 @@ impl PipelineOrchestrator {
return Ok(0);
}
let current_sha = GitOps::get_head_sha(&repo_path)?;
let mut all_findings: Vec<Finding> = Vec::new();
// Stage 1: Semgrep SAST
@@ -332,9 +395,20 @@ impl PipelineOrchestrator {
tracing::warn!("[{repo_id}] Issue creation failed: {e}");
}
// The onboarded target's findings_count and the git artifact's
// last_scanned_commit watermark are persisted by `finalize_target` after
// `run_pipeline` returns.
// Stage 7: Update repository
self.db
.repositories()
.update_one(
doc! { "_id": repo.id },
doc! {
"$set": {
"last_scanned_commit": &current_sha,
"updated_at": mongodb::bson::DateTime::now(),
},
"$inc": { "findings_count": new_count as i64 },
},
)
.await?;
// Stage 8: DAST (async, optional — only if a DastTarget is configured)
tracing::info!("[{repo_id}] Stage 8: Checking for DAST targets");
@@ -345,320 +419,6 @@ impl PipelineOrchestrator {
Ok(new_count)
}
/// Unified entry point (behind `UNIFIED_PIPELINE`): run a scan for an
/// `OnboardedTarget`. Mirrors [`Self::run`] but sources the target from
/// `onboarded_targets` and dispatches by the scan plan.
#[tracing::instrument(skip_all, fields(target_id = %target_id, trigger = ?trigger))]
pub async fn run_target(
&self,
target_id: &str,
trigger: ScanTrigger,
) -> Result<(), AgentError> {
let oid = mongodb::bson::oid::ObjectId::parse_str(target_id)
.map_err(|e| AgentError::Other(e.to_string()))?;
let target = self
.db
.onboarded_targets()
.find_one(doc! { "_id": oid })
.await?
.ok_or_else(|| AgentError::Other(format!("Onboarded target {target_id} not found")))?;
let scan_run = ScanRun::new(target_id.to_string(), trigger);
let insert = self.db.scan_runs().insert_one(&scan_run).await?;
let scan_run_id = insert
.inserted_id
.as_object_id()
.map(|id| id.to_hex())
.unwrap_or_default();
let result = self.run_target_pipeline(&target, &scan_run_id).await;
match &result {
Ok(count) => {
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! { "$set": {
"status": "completed",
"current_phase": "completed",
"new_findings_count": *count as i64,
"completed_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
// Refresh the target's cached findings count. The shared pipeline
// (Stage 7) increments `repositories`, which the unified path does
// not use, so set the accurate total on the target itself.
let total = self
.db
.findings()
.count_documents(doc! { "repo_id": target_id })
.await
.unwrap_or(*count as u64);
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": {
"findings_count": total as i64,
"updated_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
}
Err(e) => {
tracing::error!(target_id, error = %e, "Unified scan pipeline failed");
self.db
.scan_runs()
.update_one(
doc! { "_id": &insert.inserted_id },
doc! { "$set": {
"status": "failed",
"error_message": e.to_string(),
"completed_at": mongodb::bson::DateTime::now(),
} },
)
.await?;
}
}
result.map(|_| ())
}
/// Run the applicable scans for a target. For a code target this reuses the
/// full legacy pipeline over the code artifact (clone → SAST umbrella →
/// triage → persist → issues → DAST); firmware/PLC/mobile scanners are
/// follow-ups (#128/#129/#130). Returns the number of new findings.
async fn run_target_pipeline(
&self,
target: &OnboardedTarget,
scan_run_id: &str,
) -> Result<u32, AgentError> {
let target_id = target.id.map(|id| id.to_hex()).unwrap_or_default();
let plan = build_scan_plan(target);
tracing::info!(
target_id = %target_id,
target_type = %target.target_type,
planned_steps = plan.steps.len(),
"Unified pipeline: scan plan built"
);
// Ingest + classify (tramiton for firmware) and store the detected type.
self.classify_and_store(target, &target_id, scan_run_id)
.await;
// Provision a DAST target from a LiveUrl artifact so DAST fires for
// wizard-created targets, not just migrated ones.
self.ensure_dast_target(target, &plan).await;
match target.code_artifact() {
Some(code) if code.kind == ArtifactKind::GitRepo => {
let repo = RepoView::from_target(target, code);
let new_count = self.run_pipeline(&repo, scan_run_id).await?;
self.finalize_target(target, &repo, new_count).await?;
Ok(new_count)
}
Some(_) => {
tracing::warn!(
target_id = %target_id,
"Unified pipeline: source-archive scanning not yet wired; skipping"
);
Ok(0)
}
None => {
// No code to scan. Firmware/PLC/mobile static scanners land in
// #128/#129/#130; DAST for a running URL still works when a
// DastTarget row exists (migrated targets).
tracing::info!(
target_id = %target_id,
"Unified pipeline: no code artifact; attempting DAST only"
);
self.update_phase(scan_run_id, "dast_scanning").await;
self.maybe_trigger_dast(&target_id, scan_run_id).await;
Ok(0)
}
}
}
/// Ingest the target's artifacts, classify (tramiton for firmware/RTOS/Yocto,
/// heuristics otherwise), and store the detected classification on the target.
/// Best-effort — never fails the scan.
async fn classify_and_store(
&self,
target: &OnboardedTarget,
target_id: &str,
scan_run_id: &str,
) {
self.update_phase(scan_run_id, "classification").await;
let ctx = crate::ingest::IngestContext::from_config(&self.config, target_id);
let ingest_set = match crate::ingest::ingest_all(target, &ctx) {
Ok(set) => set,
Err(e) => {
tracing::warn!(target_id, error = %e, "Unified pipeline: ingest for classification failed");
return;
}
};
let working_paths = ingest_set.working_paths();
match crate::classify::classify_target(
target,
&working_paths,
&crate::classify::TramitonNative,
)
.await
{
Ok(classification) => {
tracing::info!(
target_id,
suggested = %classification.suggested,
"Unified pipeline: classified target"
);
if let (Some(oid), Ok(bson)) = (target.id, mongodb::bson::to_bson(&classification))
{
let _ = self
.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! { "$set": { "classification": bson } },
)
.await;
}
}
Err(e) => {
tracing::warn!(target_id, error = %e, "Unified pipeline: classification failed")
}
}
// Analysis-based firmware SBOM: for embedded targets, derive components
// (resolved libraries + cross-toolchain) from tramiton's build-plan
// analysis over the already-ingested source — no build, no binary
// upload. Best-effort; empty when no build plan forms.
if crate::pipeline::firmware_sbom::is_firmware_target(target.target_type) {
if let Some(code) = target.code_artifact() {
if let Some(path) = working_paths.get(&code.id) {
let entries =
crate::pipeline::firmware_sbom::firmware_sbom_entries(path, target_id)
.await;
if !entries.is_empty() {
let _ = self
.db
.sbom_entries()
.delete_many(doc! { "repo_id": target_id })
.await;
for entry in &entries {
let filter = doc! {
"repo_id": &entry.repo_id,
"name": &entry.name,
"version": &entry.version,
};
if let Ok(d) = mongodb::bson::to_document(entry) {
let _ = self
.db
.sbom_entries()
.update_one(filter, doc! { "$set": d })
.upsert(true)
.await;
}
}
tracing::info!(
target_id,
count = entries.len(),
"Firmware SBOM: stored components from tramiton analysis"
);
}
}
}
}
}
/// If the target has a `LiveUrl` artifact and DAST is planned, provision a
/// `DastTarget` (keyed by `repo_id` = target id) so the existing DAST trigger
/// fires for wizard-created targets. Idempotent.
async fn ensure_dast_target(
&self,
target: &OnboardedTarget,
plan: &crate::pipeline::plan::ScanPlan,
) {
if !plan.has(ScanType::Dast) {
return;
}
let (Some(url), Some(oid)) = (target.live_url(), target.id) else {
return;
};
let target_id = oid.to_hex();
if self
.db
.dast_targets()
.find_one(doc! { "repo_id": &target_id })
.await
.ok()
.flatten()
.is_some()
{
return; // already provisioned
}
let kind = url
.web
.as_ref()
.map(|w| w.target_kind.clone())
.unwrap_or(DastTargetType::WebApp);
let mut dast = DastTarget::new(target.name.clone(), url.source_ref.clone(), kind);
dast.repo_id = Some(target_id);
if let Some(web) = &url.web {
dast.excluded_paths = web.excluded_paths.clone();
dast.max_crawl_depth = web.max_crawl_depth;
dast.rate_limit = web.rate_limit;
dast.allow_destructive = web.allow_destructive;
}
if let Some(auth) = &url.auth {
dast.auth_config = Some(DastAuthConfig {
method: auth.method.clone(),
login_url: auth.login_url.clone(),
username: auth.username.clone(),
password: None,
token: auth.secret.clone(),
headers: auth.headers.clone(),
});
}
if let Err(e) = self.db.dast_targets().insert_one(&dast).await {
tracing::warn!(error = %e, "Unified pipeline: failed to provision DAST target");
}
}
/// Sync the onboarded-target document after a scan: bump `findings_count`
/// and advance the git artifact's `last_scanned_commit` watermark.
async fn finalize_target(
&self,
target: &OnboardedTarget,
repo: &RepoView,
new_count: u32,
) -> Result<(), AgentError> {
let oid = match target.id {
Some(id) => id,
None => return Ok(()),
};
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid },
doc! {
"$inc": { "findings_count": new_count as i64 },
"$set": { "updated_at": mongodb::bson::DateTime::now() },
},
)
.await?;
let repo_path = std::path::Path::new(&self.config.git_clone_base_path).join(&repo.name);
if let (Ok(sha), Some(code)) = (GitOps::get_head_sha(&repo_path), target.code_artifact()) {
self.db
.onboarded_targets()
.update_one(
doc! { "_id": oid, "artifacts.id": &code.id },
doc! { "$set": { "artifacts.$.git.last_scanned_commit": sha } },
)
.await?;
}
Ok(())
}
pub(super) async fn update_phase(&self, scan_run_id: &str, phase: &str) {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(scan_run_id) {
let _ = self
@@ -700,50 +460,3 @@ pub(super) fn extract_base_url(git_url: &str) -> Option<String> {
None
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{
Artifact, ArtifactAuth, IssueTrackerConfig, TargetType, TrackerType,
};
#[test]
fn repo_view_preserves_id_git_auth_and_tracker() {
let mut target = OnboardedTarget::new("acme".to_string(), TargetType::WebApp);
target.id = Some(mongodb::bson::oid::ObjectId::new());
target.findings_count = 3;
target.scan_config.issue_tracker = Some(IssueTrackerConfig {
tracker_type: Some(TrackerType::Gitea),
owner: Some("acme".to_string()),
repo: Some("web".to_string()),
token: Some("tt".to_string()),
});
let mut artifact = Artifact::git_repo("https://git/acme.git", "develop");
if let Some(git) = artifact.git.as_mut() {
git.last_scanned_commit = Some("abc123".to_string());
}
artifact.auth = Some(ArtifactAuth {
method: "token".to_string(),
username: Some("bob".to_string()),
secret: Some("pat".to_string()),
..Default::default()
});
target.artifacts.push(artifact);
let code = target.code_artifact().expect("code artifact");
let repo = RepoView::from_target(&target, code);
assert_eq!(repo.id, target.id); // preserved
assert_eq!(repo.git_url, "https://git/acme.git");
assert_eq!(repo.default_branch, "develop");
assert_eq!(repo.last_scanned_commit.as_deref(), Some("abc123"));
assert_eq!(repo.auth_token.as_deref(), Some("pat"));
assert_eq!(repo.auth_username.as_deref(), Some("bob"));
assert_eq!(repo.tracker_type, Some(TrackerType::Gitea));
assert_eq!(repo.tracker_owner.as_deref(), Some("acme"));
assert_eq!(repo.findings_count, 3);
}
}
+1 -1
View File
@@ -215,7 +215,7 @@ fn scan_with_patterns(
repo_id.to_string(),
fingerprint,
scanner_name.to_string(),
scan_type,
scan_type.clone(),
pattern.title.clone(),
pattern.description.clone(),
pattern.severity.clone(),
-195
View File
@@ -1,195 +0,0 @@
//! The scan plan.
//!
//! [`build_scan_plan`] turns an [`OnboardedTarget`] into the concrete ordered
//! list of scans to run, each bound to the artifact it consumes. It intersects
//! the scan-applicability matrix ([`applicable_scans`]) with the target's
//! `scan_config` overrides: a scan runs when its required artifact is present and
//! it is either on by default or explicitly enabled, and is not explicitly
//! disabled. This is the decision engine the unified pipeline (`run_target`)
//! executes.
use compliance_core::models::{Artifact, ArtifactKind, OnboardedTarget, ScanPhase, ScanType};
use compliance_core::scan_matrix::applicable_scans;
/// One scan to run, bound to the artifact it operates on.
#[derive(Debug, Clone, PartialEq)]
pub struct ScanStep {
/// The scan to run.
pub scan_type: ScanType,
/// The pipeline phase to report while it runs.
pub phase: ScanPhase,
/// The id of the artifact this scan consumes ([`Artifact::id`]).
pub artifact_id: String,
}
/// The ordered set of scans to run for a target.
#[derive(Debug, Clone, Default, PartialEq)]
pub struct ScanPlan {
/// The scans, in matrix order.
pub steps: Vec<ScanStep>,
}
impl ScanPlan {
/// Whether the plan contains a step for the given scan type.
pub fn has(&self, scan: ScanType) -> bool {
self.steps.iter().any(|s| s.scan_type == scan)
}
/// Whether the plan is empty (nothing to run).
pub fn is_empty(&self) -> bool {
self.steps.is_empty()
}
}
/// Build the scan plan for a target: matrix defaults ∩ `scan_config`, each scan
/// bound to the artifact it consumes. Scans whose required artifact is absent, or
/// that are disabled, or off-by-default and not explicitly enabled, are dropped.
pub fn build_scan_plan(target: &OnboardedTarget) -> ScanPlan {
let enabled = &target.scan_config.enabled_scans;
let disabled = &target.scan_config.disabled_scans;
let mut steps = Vec::new();
for option in applicable_scans(target) {
// Required artifact missing → not runnable.
if option.blocked_reason.is_some() {
continue;
}
// Explicit opt-out wins.
if disabled.contains(&option.scan) {
continue;
}
// Run if on by default, or explicitly enabled.
if !option.default_on && !enabled.contains(&option.scan) {
continue;
}
let Some(artifact) = resolve_artifact(target, option.required_artifact) else {
continue;
};
steps.push(ScanStep {
scan_type: option.scan,
phase: phase_for(option.scan),
artifact_id: artifact.id.clone(),
});
}
ScanPlan { steps }
}
/// Resolve the artifact a scan consumes. A "code" requirement (represented by
/// `GitRepo`) is satisfied by a git repo *or* a source archive.
fn resolve_artifact(target: &OnboardedTarget, required: Option<ArtifactKind>) -> Option<&Artifact> {
match required {
Some(ArtifactKind::GitRepo) => target.code_artifact(),
Some(kind) => target.first_of(kind),
None => target.code_artifact().or_else(|| target.artifacts.first()),
}
}
/// The pipeline phase reported while a given scan runs.
fn phase_for(scan: ScanType) -> ScanPhase {
match scan {
ScanType::Sast => ScanPhase::Sast,
ScanType::Sbom => ScanPhase::SbomGeneration,
ScanType::Cve => ScanPhase::CveScanning,
ScanType::Gdpr | ScanType::OAuth => ScanPhase::PatternScanning,
ScanType::SecretDetection => ScanPhase::SecretDetection,
ScanType::Lint => ScanPhase::LintScanning,
ScanType::CodeReview => ScanPhase::CodeReview,
ScanType::Graph => ScanPhase::GraphBuilding,
ScanType::Dast => ScanPhase::DastScanning,
ScanType::FirmwareStatic => ScanPhase::FirmwareStatic,
ScanType::PlcControlLogic => ScanPhase::PlcAnalysis,
ScanType::MobileStatic => ScanPhase::MobileStatic,
ScanType::ContainerScan => ScanPhase::ContainerScan,
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use compliance_core::models::{PlcFormat, TargetType};
fn target(target_type: TargetType, artifacts: Vec<Artifact>) -> OnboardedTarget {
let mut t = OnboardedTarget::new("t".to_string(), target_type);
t.artifacts = artifacts;
t
}
fn step_for<'a>(plan: &'a ScanPlan, scan: ScanType) -> Option<&'a ScanStep> {
plan.steps.iter().find(|s| s.scan_type == scan)
}
#[test]
fn webapp_with_code_and_url_runs_sast_and_dast_bound_to_the_right_artifacts() {
let code = Artifact::git_repo("https://git/x", "main");
let url = Artifact::live_url("https://x");
let (code_id, url_id) = (code.id.clone(), url.id.clone());
let t = target(TargetType::WebApp, vec![code, url]);
let plan = build_scan_plan(&t);
let sast = step_for(&plan, ScanType::Sast).expect("sast planned");
assert_eq!(sast.artifact_id, code_id);
assert_eq!(sast.phase, ScanPhase::Sast);
let dast = step_for(&plan, ScanType::Dast).expect("dast planned");
assert_eq!(dast.artifact_id, url_id);
}
#[test]
fn webapp_without_url_omits_dast() {
let t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
let plan = build_scan_plan(&t);
assert!(plan.has(ScanType::Sast));
assert!(!plan.has(ScanType::Dast));
}
#[test]
fn code_scan_binds_to_source_archive_when_no_git_repo() {
let arc = Artifact::source_archive("src.zip");
let arc_id = arc.id.clone();
let t = target(TargetType::BackendService, vec![arc]);
let plan = build_scan_plan(&t);
let sast = step_for(&plan, ScanType::Sast).expect("sast planned");
assert_eq!(sast.artifact_id, arc_id);
}
#[test]
fn firmware_sbom_and_cve_bind_to_the_firmware_image() {
let fw = Artifact::firmware_image("fw.bin");
let fw_id = fw.id.clone();
let t = target(TargetType::FirmwareBareMetal, vec![fw]);
let plan = build_scan_plan(&t);
let sbom = step_for(&plan, ScanType::Sbom).expect("sbom planned");
assert_eq!(sbom.artifact_id, fw_id);
assert!(step_for(&plan, ScanType::FirmwareStatic).is_some());
assert!(!plan.has(ScanType::Dast));
}
#[test]
fn plc_plans_only_control_logic() {
let plc = Artifact::plc_project("p.xml", PlcFormat::PlcopenXml);
let t = target(TargetType::PlcSps, vec![plc]);
let plan = build_scan_plan(&t);
assert_eq!(plan.steps.len(), 1);
assert_eq!(plan.steps[0].scan_type, ScanType::PlcControlLogic);
assert_eq!(plan.steps[0].phase, ScanPhase::PlcAnalysis);
}
#[test]
fn disabled_scan_is_dropped_and_off_by_default_can_be_enabled() {
let mut t = target(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
t.scan_config.disabled_scans = vec![ScanType::Lint];
// CodeReview is off by default for web; enable it explicitly.
t.scan_config.enabled_scans = vec![ScanType::CodeReview];
let plan = build_scan_plan(&t);
assert!(!plan.has(ScanType::Lint));
assert!(plan.has(ScanType::CodeReview));
assert!(plan.has(ScanType::Sast));
}
#[test]
fn no_code_artifact_yields_empty_plan_for_web() {
let t = target(TargetType::WebApp, vec![]);
let plan = build_scan_plan(&t);
assert!(plan.is_empty());
}
}
+1 -2
View File
@@ -1,4 +1,3 @@
use crate::pipeline::repo_view::RepoView;
use compliance_core::models::*;
use super::dedup::compute_fingerprint;
@@ -15,7 +14,7 @@ impl PipelineOrchestrator {
#[tracing::instrument(skip_all, fields(repo_id = %repo_id, pr_number))]
pub async fn run_pr_review(
&self,
repo: &RepoView,
repo: &TrackedRepository,
repo_id: &str,
pr_number: u64,
base_sha: &str,
@@ -1,74 +0,0 @@
//! `RepoView` — an internal, non-persisted view of a code target for the scan
//! pipeline.
//!
//! It replaces the old persisted `TrackedRepository` model. The pipeline
//! (SAST → SBOM → CVE → triage → issues → DAST, and PR review) only ever needs a
//! flat bundle of git + issue-tracker + auth fields; those are projected from an
//! [`OnboardedTarget`] and its code [`Artifact`] by [`RepoView::from_target`].
//! Nothing here is written to Mongo — onboarded targets are the sole persisted
//! entity.
use compliance_core::models::{Artifact, OnboardedTarget, TrackerType};
/// A flat, pipeline-facing view of a code target. Built from an onboarded
/// target; never persisted.
#[derive(Debug, Clone)]
pub struct RepoView {
/// The onboarded target's id (used as `repo_id` across findings/sbom/etc.).
pub id: Option<mongodb::bson::oid::ObjectId>,
pub name: String,
pub git_url: String,
pub default_branch: String,
pub local_path: Option<String>,
pub scan_schedule: Option<String>,
pub webhook_enabled: bool,
pub webhook_secret: Option<String>,
pub tracker_type: Option<TrackerType>,
pub tracker_owner: Option<String>,
pub tracker_repo: Option<String>,
pub tracker_token: Option<String>,
pub auth_token: Option<String>,
pub auth_username: Option<String>,
pub last_scanned_commit: Option<String>,
pub findings_count: u32,
}
impl RepoView {
/// Project an onboarded target + its code artifact into a pipeline view.
pub fn from_target(target: &OnboardedTarget, code: &Artifact) -> Self {
let mut view = Self {
id: target.id,
name: target.name.clone(),
git_url: code.source_ref.clone(),
default_branch: "main".to_string(),
local_path: None,
scan_schedule: target.scan_schedule.clone(),
webhook_enabled: target.webhook_enabled,
webhook_secret: target.webhook_secret.clone(),
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
auth_token: None,
auth_username: None,
last_scanned_commit: None,
findings_count: target.findings_count,
};
if let Some(git) = &code.git {
view.default_branch = git.default_branch.clone();
view.last_scanned_commit = git.last_scanned_commit.clone();
view.local_path = git.local_path.clone();
}
if let Some(auth) = &code.auth {
view.auth_token = auth.secret.clone();
view.auth_username = auth.username.clone();
}
if let Some(it) = &target.scan_config.issue_tracker {
view.tracker_type = it.tracker_type.clone();
view.tracker_owner = it.owner.clone();
view.tracker_repo = it.repo.clone();
view.tracker_token = it.token.clone();
}
view
}
}
+8 -8
View File
@@ -288,25 +288,25 @@ async fn scan_all_repos(agent: &ComplianceAgent, tenant_id: &str) {
None => return,
};
let cursor = match db.onboarded_targets().find(doc! {}).await {
let cursor = match db.repositories().find(doc! {}).await {
Ok(c) => c,
Err(e) => {
tracing::error!("Failed to list targets for tenant '{tenant_id}': {e}");
tracing::error!("Failed to list repos for tenant '{tenant_id}': {e}");
return;
}
};
let targets: Vec<_> = cursor.filter_map(|r| async { r.ok() }).collect().await;
let repos: Vec<_> = cursor.filter_map(|r| async { r.ok() }).collect().await;
for target in targets {
let target_id = target.id.map(|id| id.to_hex()).unwrap_or_default();
for repo in repos {
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
if let Err(e) = agent
.run_target_scan(tenant_id, &target_id, ScanTrigger::Scheduled)
.run_scan(tenant_id, &repo_id, ScanTrigger::Scheduled)
.await
{
tracing::error!(
"Scheduled scan failed for {} (tenant '{tenant_id}'): {e}",
target.name
repo.name
);
}
}
@@ -348,7 +348,7 @@ async fn monitor_cves(agent: &ComplianceAgent, tenant_id: &str) {
std::collections::HashMap::new();
for rid in &repo_ids {
if let Ok(oid) = mongodb::bson::oid::ObjectId::parse_str(rid) {
if let Ok(Some(repo)) = db.onboarded_targets().find_one(doc! { "_id": oid }).await {
if let Ok(Some(repo)) = db.repositories().find_one(doc! { "_id": oid }).await {
repo_names.insert(rid.clone(), repo.name.clone());
}
}
+1 -1
View File
@@ -31,7 +31,7 @@ pub async fn handle_gitea_webhook(
}
};
let repo = match db
.onboarded_targets()
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
+1 -1
View File
@@ -31,7 +31,7 @@ pub async fn handle_github_webhook(
}
};
let repo = match db
.onboarded_targets()
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
+1 -1
View File
@@ -27,7 +27,7 @@ pub async fn handle_gitlab_webhook(
}
};
let repo = match db
.onboarded_targets()
.repositories()
.find_one(mongodb::bson::doc! { "_id": oid })
.await
{
+2 -4
View File
@@ -25,9 +25,8 @@ impl TestServer {
let mongodb_uri = std::env::var("TEST_MONGODB_URI")
.unwrap_or_else(|_| "mongodb://root:example@localhost:27017/?authSource=admin".into());
// Unique db-name prefix per run. Must fit the pool's 30-char cap
// (`<prefix>_<32 hex>` <= 63), so use a 16-hex-char suffix.
let db_name = format!("t_{}", &uuid::Uuid::new_v4().simple().to_string()[..16]);
// Unique database name per test run to avoid collisions
let db_name = format!("test_{}", uuid::Uuid::new_v4().simple());
let db_pool = DatabasePool::connect(&mongodb_uri, &db_name)
.await
@@ -45,7 +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,
@@ -113,16 +113,15 @@ async fn delete_repo_cascades_to_dast_and_pentest_data() {
// Create a repo
let resp = server
.post(
"/api/v1/targets",
"/api/v1/repositories",
&json!({
"name": "cascade-test",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/cascade-test.git", "branch": "main" }],
"git_url": "https://github.com/example/cascade-test.git",
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
// Insert DAST target linked to repo
let target_id = insert_dast_target(&server, &repo_id, "cascade-target").await;
@@ -141,7 +140,9 @@ async fn delete_repo_cascades_to_dast_and_pentest_data() {
assert_eq!(count_docs(&server, "dast_findings").await, 1);
// Delete the repo
let resp = server.delete(&format!("/api/v1/targets/{repo_id}")).await;
let resp = server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
assert_eq!(resp.status(), 200);
// All downstream data should be gone
@@ -160,16 +161,15 @@ async fn delete_repo_cascades_sast_findings_and_sbom() {
// Create a repo
let resp = server
.post(
"/api/v1/targets",
"/api/v1/repositories",
&json!({
"name": "sast-cascade",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/sast-cascade.git", "branch": "main" }],
"git_url": "https://github.com/example/sast-cascade.git",
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
// Insert SAST finding and SBOM entry
let mongodb_uri = std::env::var("TEST_MONGODB_URI")
@@ -209,7 +209,9 @@ async fn delete_repo_cascades_sast_findings_and_sbom() {
assert_eq!(count_docs(&server, "sbom_entries").await, 1);
// Delete repo
server.delete(&format!("/api/v1/targets/{repo_id}")).await;
server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
// Both should be gone
assert_eq!(count_docs(&server, "findings").await, 0);
@@ -2,5 +2,5 @@ mod cascade_delete;
mod dast;
mod findings;
mod health;
mod onboarding;
mod repositories;
mod stats;
@@ -1,115 +0,0 @@
use crate::common::TestServer;
use serde_json::json;
#[tokio::test]
async fn create_list_and_applicable_scans() {
let server = TestServer::start().await;
// Initially empty.
let resp = server.get("/api/v1/targets").await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
// Create a web-app target with a git repo + a live URL.
let resp = server
.post(
"/api/v1/targets",
&json!({
"name": "acme-web",
"target_type": "web_app",
"artifacts": [
{ "kind": "git_repo", "source_ref": "https://git/acme.git", "branch": "main" },
{ "kind": "live_url", "source_ref": "https://acme.example.com" }
]
}),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
assert!(!id.is_empty());
assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 2);
// List returns it.
let resp = server.get("/api/v1/targets").await;
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 1);
// Applicable scans: SAST present + DAST offered (live URL present), pentest supported.
let resp = server
.get(&format!("/api/v1/targets/{id}/applicable-scans"))
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let scans = body["data"]["scans"].as_array().unwrap();
let names: Vec<&str> = scans.iter().filter_map(|s| s["scan"].as_str()).collect();
assert!(names.contains(&"sast"));
assert!(names.contains(&"dast"));
assert_eq!(body["data"]["pentest_supported"], true);
server.cleanup().await;
}
#[tokio::test]
async fn detect_classifies_a_plc_target() {
let server = TestServer::start().await;
// A PLC project artifact is a strong kind-based signal.
let resp = server
.post(
"/api/v1/targets",
&json!({
"name": "line-controller",
"target_type": "backend_service", // deliberately wrong; detect should suggest PLC
"artifacts": [
{ "kind": "plc_project", "source_ref": "line.xml", "plc_format": "plcopen_xml" }
]
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
let resp = server
.post(&format!("/api/v1/targets/{id}/detect"), &json!({}))
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"]["classification"]["suggested"], "plc_sps");
server.cleanup().await;
}
#[tokio::test]
async fn add_artifact_and_delete_target() {
let server = TestServer::start().await;
let resp = server
.post(
"/api/v1/targets",
&json!({ "name": "svc", "target_type": "backend_service" }),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let id = body["data"]["_id"]["$oid"].as_str().unwrap().to_string();
// Attach a git repo.
let resp = server
.post(
&format!("/api/v1/targets/{id}/artifacts"),
&json!({ "kind": "git_repo", "source_ref": "https://git/svc.git" }),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"]["artifacts"].as_array().unwrap().len(), 1);
// Delete it.
let resp = server.delete(&format!("/api/v1/targets/{id}")).await;
assert_eq!(resp.status(), 200);
let resp = server.get(&format!("/api/v1/targets/{id}")).await;
assert_eq!(resp.status(), 404);
server.cleanup().await;
}
@@ -0,0 +1,110 @@
use crate::common::TestServer;
use serde_json::json;
#[tokio::test]
async fn add_and_list_repository() {
let server = TestServer::start().await;
// Initially empty
let resp = server.get("/api/v1/repositories").await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
// Add a repository
let resp = server
.post(
"/api/v1/repositories",
&json!({
"name": "test-repo",
"git_url": "https://github.com/example/test-repo.git",
}),
)
.await;
assert_eq!(resp.status(), 200);
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap().to_string();
assert!(!repo_id.is_empty());
// List should now return 1
let resp = server.get("/api/v1/repositories").await;
let body: serde_json::Value = resp.json().await.unwrap();
let repos = body["data"].as_array().unwrap();
assert_eq!(repos.len(), 1);
assert_eq!(repos[0]["name"], "test-repo");
server.cleanup().await;
}
#[tokio::test]
async fn add_duplicate_repository_fails() {
let server = TestServer::start().await;
let payload = json!({
"name": "dup-repo",
"git_url": "https://github.com/example/dup-repo.git",
});
// First add succeeds
let resp = server.post("/api/v1/repositories", &payload).await;
assert_eq!(resp.status(), 200);
// Second add with same git_url should fail (unique index)
let resp = server.post("/api/v1/repositories", &payload).await;
assert_ne!(resp.status(), 200);
server.cleanup().await;
}
#[tokio::test]
async fn delete_repository() {
let server = TestServer::start().await;
// Add a repo
let resp = server
.post(
"/api/v1/repositories",
&json!({
"name": "to-delete",
"git_url": "https://github.com/example/to-delete.git",
}),
)
.await;
let body: serde_json::Value = resp.json().await.unwrap();
let repo_id = body["data"]["id"].as_str().unwrap();
// Delete it
let resp = server
.delete(&format!("/api/v1/repositories/{repo_id}"))
.await;
assert_eq!(resp.status(), 200);
// List should be empty again
let resp = server.get("/api/v1/repositories").await;
let body: serde_json::Value = resp.json().await.unwrap();
assert_eq!(body["data"].as_array().unwrap().len(), 0);
server.cleanup().await;
}
#[tokio::test]
async fn delete_nonexistent_repository_returns_404() {
let server = TestServer::start().await;
let resp = server
.delete("/api/v1/repositories/000000000000000000000000")
.await;
assert_eq!(resp.status(), 404);
server.cleanup().await;
}
#[tokio::test]
async fn delete_invalid_id_returns_400() {
let server = TestServer::start().await;
let resp = server.delete("/api/v1/repositories/not-a-valid-id").await;
assert_eq!(resp.status(), 400);
server.cleanup().await;
}
@@ -5,14 +5,13 @@ use serde_json::json;
async fn stats_overview_reflects_inserted_data() {
let server = TestServer::start().await;
// Add a target
// Add a repo
server
.post(
"/api/v1/targets",
"/api/v1/repositories",
&json!({
"name": "stats-repo",
"target_type": "web_app",
"artifacts": [{ "kind": "git_repo", "source_ref": "https://github.com/example/stats-repo.git", "branch": "main" }],
"git_url": "https://github.com/example/stats-repo.git",
}),
)
.await;
+28 -13
View File
@@ -11,7 +11,7 @@
#![allow(clippy::expect_used, clippy::unwrap_used)]
use compliance_agent::database::DatabasePool;
use compliance_core::models::{Artifact, OnboardedTarget, TargetType};
use compliance_core::models::TrackedRepository;
use compliance_core::{OrgRole, TenantContext, TenantStatus};
use mongodb::bson::doc;
@@ -28,12 +28,27 @@ fn ctx(tenant_id: &str, slug: &str) -> TenantContext {
}
}
fn fixture_repo(name: &str, git_url: &str) -> OnboardedTarget {
let mut target = OnboardedTarget::new(name.to_string(), TargetType::WebApp);
target
.artifacts
.push(Artifact::git_repo(git_url.to_string(), "main".to_string()));
target
fn fixture_repo(name: &str, git_url: &str) -> TrackedRepository {
TrackedRepository {
id: None,
name: name.to_string(),
git_url: git_url.to_string(),
default_branch: "main".to_string(),
local_path: None,
scan_schedule: None,
webhook_enabled: false,
webhook_secret: None,
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
auth_token: None,
auth_username: None,
last_scanned_commit: None,
findings_count: 0,
created_at: chrono::Utc::now(),
updated_at: chrono::Utc::now(),
}
}
#[tokio::test]
@@ -56,12 +71,12 @@ async fn pool_isolates_tenants_at_driver_level() {
// Write distinct repos into each tenant's database.
acme_db
.onboarded_targets()
.repositories()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await
.expect("insert acme");
globex_db
.onboarded_targets()
.repositories()
.insert_one(fixture_repo(
"globex-platform",
"git@example.com:globex/platform.git",
@@ -158,12 +173,12 @@ async fn admin_helpers_list_and_drop_tenant_dbs() {
let acme_db = pool.for_tenant(&acme).await.expect("acme db");
let globex_db = pool.for_tenant(&globex).await.expect("globex db");
acme_db
.onboarded_targets()
.repositories()
.insert_one(fixture_repo("acme-app", "git@example.com:acme/app.git"))
.await
.expect("insert acme");
globex_db
.onboarded_targets()
.repositories()
.insert_one(fixture_repo("globex-app", "git@example.com:globex/app.git"))
.await
.expect("insert globex");
@@ -269,9 +284,9 @@ fn short_id() -> String {
}
/// Drain a `repositories` find cursor on the given tenant database.
async fn collect(db: &compliance_agent::database::Database) -> Vec<OnboardedTarget> {
async fn collect(db: &compliance_agent::database::Database) -> Vec<TrackedRepository> {
let mut cursor = db
.onboarded_targets()
.repositories()
.find(doc! {})
.await
.expect("find repositories");
-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>,
-1
View File
@@ -2,7 +2,6 @@ pub mod config;
pub mod db;
pub mod error;
pub mod models;
pub mod scan_matrix;
#[cfg(feature = "telemetry")]
pub mod telemetry;
pub mod tenant;
-69
View File
@@ -1,69 +0,0 @@
//! Per-tenant API tokens used by `compliance-mcp` to authenticate MCP
//! HTTP requests on behalf of LLM clients (Claude Desktop, Cursor,
//! ChatGPT, etc.) that can't run a Keycloak OIDC flow.
//!
//! Tokens are opaque strings of the form `mcpt_<44 url-safe random
//! chars>`. The raw value is shown to the user exactly once at
//! creation; the database only ever sees the SHA-256 hash. Lookups go
//! through the cross-tenant `<prefix>__admin.mcp_tokens` collection
//! and return the `tenant_id` the MCP server should route to.
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
/// Persisted token metadata. `token_hash` is the SHA-256 hex of the
/// raw token; the raw token itself is never stored.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct McpToken {
#[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
pub id: Option<bson::oid::ObjectId>,
/// SHA-256 hex of the raw token. Unique index in the collection.
pub token_hash: String,
/// First 8 chars of the raw token — purely for UI display so users
/// can identify which token is which without re-issuing.
pub token_prefix: String,
/// Routes to `<db_prefix>_<tenant_id>` on MCP requests.
pub tenant_id: String,
/// User-given label, e.g. "Claude Desktop" or "Sharang's laptop".
pub name: String,
/// Keycloak `sub` of the user who created this token, for audit.
pub created_by: String,
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_used_at: Option<DateTime<Utc>>,
/// Soft-delete flag. A revoked token doc stays around for audit
/// but never authenticates.
#[serde(default)]
pub revoked: bool,
}
/// Public projection of a token — never includes the hash.
/// Returned by `GET /api/v1/mcp-tokens`.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct McpTokenView {
pub id: String,
pub name: String,
/// `mcpt_xxxx…` so the user can identify which row is which.
pub token_prefix: String,
pub created_by: String,
#[serde(with = "super::serde_helpers::bson_datetime")]
pub created_at: DateTime<Utc>,
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub last_used_at: Option<DateTime<Utc>>,
pub revoked: bool,
}
impl From<&McpToken> for McpTokenView {
fn from(t: &McpToken) -> Self {
Self {
id: t.id.map(|o| o.to_hex()).unwrap_or_default(),
name: t.name.clone(),
token_prefix: t.token_prefix.clone(),
created_by: t.created_by.clone(),
created_at: t.created_at,
last_used_at: t.last_used_at,
revoked: t.revoked,
}
}
}
+1 -10
View File
@@ -7,9 +7,7 @@ pub mod finding;
pub mod graph;
pub mod issue;
pub mod mcp;
pub mod mcp_token;
pub mod notification;
pub mod onboarding;
pub mod pentest;
pub mod repository;
pub mod sbom;
@@ -30,20 +28,13 @@ pub use graph::{
};
pub use issue::{IssueStatus, TrackerIssue, TrackerType};
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,
};
pub use pentest::{
AttackChainNode, AttackNodeStatus, AuthMode, CodeContextHint, Environment, IdentityProvider,
PentestAuthConfig, PentestConfig, PentestEvent, PentestMessage, PentestSession, PentestStats,
PentestStatus, PentestStrategy, SeverityDistribution, TestUserRecord, TesterInfo,
ToolCallRecord,
};
pub use repository::ScanTrigger;
pub use repository::{ScanTrigger, TrackedRepository};
pub use sbom::{SbomEntry, VulnRef};
pub use scan::{ScanPhase, ScanRun, ScanRunStatus, ScanType};
-753
View File
@@ -1,753 +0,0 @@
//! The unified onboarding model.
//!
//! An [`OnboardedTarget`] is the single source of truth for anything the scanner
//! can analyze. It records *what kind of software* the target is ([`TargetType`]),
//! the concrete [`Artifact`]s that were provided for it (a git repo, a firmware
//! image, a live URL, a PLC project, ...), the classifier's verdict, and the scan
//! configuration. It replaces the older git-only `TrackedRepository` and the
//! standalone `DastTarget`, both of which fold into this type as artifacts.
use std::collections::HashMap;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use super::dast::{DastAuthConfig, DastTargetType};
use super::issue::TrackerType;
use super::pentest::{Environment, PentestConfig, PentestStrategy};
use super::scan::ScanType;
/// The family of software a target belongs to.
///
/// 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)]
#[serde(rename_all = "snake_case")]
pub enum TargetType {
/// Browser-facing web application (front end + server).
WebApp,
/// Headless backend service / API (REST, GraphQL, gRPC).
BackendService,
/// Desktop application (Windows/macOS/Linux GUI or CLI binary).
DesktopApp,
/// Android application (APK / AAB).
AndroidApp,
/// iOS application (IPA).
IosApp,
/// Bare-metal embedded firmware (no operating system).
FirmwareBareMetal,
/// Embedded firmware running on an RTOS (Zephyr, FreeRTOS, ...).
FirmwareRtos,
/// Embedded Linux built with Yocto / OpenEmbedded (BSP + image).
EmbeddedLinuxYocto,
/// Programmable logic controller software (IEC 61131-3, PLCopen / SPS).
PlcSps,
}
impl std::fmt::Display for TargetType {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::WebApp => write!(f, "web_app"),
Self::BackendService => write!(f, "backend_service"),
Self::DesktopApp => write!(f, "desktop_app"),
Self::AndroidApp => write!(f, "android_app"),
Self::IosApp => write!(f, "ios_app"),
Self::FirmwareBareMetal => write!(f, "firmware_bare_metal"),
Self::FirmwareRtos => write!(f, "firmware_rtos"),
Self::EmbeddedLinuxYocto => write!(f, "embedded_linux_yocto"),
Self::PlcSps => write!(f, "plc_sps"),
}
}
}
/// The kind of artifact provided for a target.
///
/// Which scans are possible is a function of the target type *and* which of
/// these are present (SAST needs code, DAST needs a running URL, and so on).
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ArtifactKind {
/// A git repository (cloned for static analysis).
GitRepo,
/// A source archive (zip / tarball) with no live git remote.
SourceArchive,
/// A firmware image or binary blob.
FirmwareImage,
/// A mobile package: Android APK/AAB or iOS IPA.
MobilePackage,
/// An OCI/Docker container image reference.
ContainerImage,
/// A reachable running instance (base URL / endpoint) for dynamic testing.
LiveUrl,
/// A PLC project: PLCopen XML or Structured Text source.
PlcProject,
/// Free-form plaintext describing the target (feeds classification only).
PlaintextDescription,
}
impl std::fmt::Display for ArtifactKind {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::GitRepo => write!(f, "git_repo"),
Self::SourceArchive => write!(f, "source_archive"),
Self::FirmwareImage => write!(f, "firmware_image"),
Self::MobilePackage => write!(f, "mobile_package"),
Self::ContainerImage => write!(f, "container_image"),
Self::LiveUrl => write!(f, "live_url"),
Self::PlcProject => write!(f, "plc_project"),
Self::PlaintextDescription => write!(f, "plaintext_description"),
}
}
}
/// Credentials attached to an artifact.
///
/// This folds both `TrackedRepository`'s git auth (`auth_token` / `auth_username`
/// / SSH key) and `DastAuthConfig`'s HTTP auth (form / bearer / cookie) into one
/// shape so a single artifact carries whatever it needs to be fetched or probed.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct ArtifactAuth {
/// Auth method: `none` | `token` | `basic` | `bearer` | `cookie` | `form` | `ssh`.
#[serde(default)]
pub method: String,
/// Username (git user, basic-auth user, or `x-access-token` for PATs).
pub username: Option<String>,
/// The secret credential: PAT, password, or bearer token. Encrypted at rest.
pub secret: Option<String>,
/// Path to an SSH private key for git-over-SSH.
pub ssh_key_path: Option<String>,
/// Login URL for form-based authentication.
pub login_url: Option<String>,
/// Extra headers to send when authenticating / probing.
pub headers: Option<HashMap<String, String>>,
}
impl From<DastAuthConfig> for ArtifactAuth {
fn from(c: DastAuthConfig) -> Self {
Self {
method: c.method,
username: c.username,
// Prefer a bearer token; otherwise fall back to the password.
secret: c.token.or(c.password),
ssh_key_path: None,
login_url: c.login_url,
headers: c.headers,
}
}
}
/// Git-specific configuration for a [`ArtifactKind::GitRepo`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct GitArtifactConfig {
/// Branch to scan.
pub default_branch: String,
/// Commit SHA of the last completed scan (change-detection watermark).
pub last_scanned_commit: Option<String>,
/// Local clone path once the repo has been fetched.
pub local_path: Option<String>,
}
impl GitArtifactConfig {
/// Config for a fresh git artifact on the given branch.
pub fn on_branch(branch: impl Into<String>) -> Self {
Self {
default_branch: branch.into(),
last_scanned_commit: None,
local_path: None,
}
}
}
impl Default for GitArtifactConfig {
fn default() -> Self {
Self::on_branch("main")
}
}
/// Dynamic-analysis configuration for a [`ArtifactKind::LiveUrl`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct WebArtifactConfig {
/// Whether the endpoint is a web app, REST API, or GraphQL API.
pub target_kind: DastTargetType,
/// URL paths to exclude from crawling / scanning.
#[serde(default)]
pub excluded_paths: Vec<String>,
/// Maximum crawl depth.
pub max_crawl_depth: u32,
/// Rate limit in requests per second.
pub rate_limit: u32,
/// Whether destructive methods (DELETE / PUT) are permitted.
#[serde(default)]
pub allow_destructive: bool,
}
impl Default for WebArtifactConfig {
fn default() -> Self {
Self {
target_kind: DastTargetType::WebApp,
excluded_paths: Vec::new(),
max_crawl_depth: 3,
rate_limit: 10,
allow_destructive: false,
}
}
}
/// The source format of a PLC project artifact.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum PlcFormat {
/// PLCopen XML project export.
PlcopenXml,
/// IEC 61131-3 Structured Text source.
StructuredText,
}
/// PLC-specific configuration for a [`ArtifactKind::PlcProject`] artifact.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct PlcArtifactConfig {
/// The project source format.
pub format: PlcFormat,
}
/// A single fact discovered about a target by ingest or classification
/// (e.g. `language=rust`, `build_system=cmake`, `mcu=stm32f429`).
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct DetectedFact {
/// The fact name.
pub key: String,
/// The fact value.
pub value: String,
/// What produced the fact (e.g. `tramiton`, `language-fingerprint`).
pub source: String,
}
impl DetectedFact {
/// Build a fact from its parts.
pub fn new(
key: impl Into<String>,
value: impl Into<String>,
source: impl Into<String>,
) -> Self {
Self {
key: key.into(),
value: value.into(),
source: source.into(),
}
}
}
/// One concrete thing provided for a target: code, a binary, a URL, etc.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Artifact {
/// Stable per-artifact id (UUID v4) — scan steps reference this.
pub id: String,
/// What kind of artifact this is.
pub kind: ArtifactKind,
/// The source reference: git URL, blob id, live URL, or image ref.
pub source_ref: String,
/// Optional human-friendly label.
pub display_name: Option<String>,
/// Content-addressed storage path once ingested (blobs only).
pub stored_path: Option<String>,
/// SHA-256 of the ingested content (git artifacts store the head SHA).
pub content_hash: Option<String>,
/// Size of the stored blob in bytes.
pub size_bytes: Option<u64>,
/// Credentials for fetching or probing this artifact.
pub auth: Option<ArtifactAuth>,
/// Git configuration (present for [`ArtifactKind::GitRepo`]).
pub git: Option<GitArtifactConfig>,
/// Dynamic-analysis configuration (present for [`ArtifactKind::LiveUrl`]).
pub web: Option<WebArtifactConfig>,
/// PLC configuration (present for [`ArtifactKind::PlcProject`]).
pub plc: Option<PlcArtifactConfig>,
/// Facts discovered about this artifact by ingest / classification.
#[serde(default)]
pub detected: Vec<DetectedFact>,
/// When this artifact was last ingested.
#[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
pub ingested_at: Option<DateTime<Utc>>,
}
impl Artifact {
/// A bare artifact of the given kind and source reference.
fn bare(kind: ArtifactKind, source_ref: impl Into<String>) -> Self {
Self {
id: uuid::Uuid::new_v4().to_string(),
kind,
source_ref: source_ref.into(),
display_name: None,
stored_path: None,
content_hash: None,
size_bytes: None,
auth: None,
git: None,
web: None,
plc: None,
detected: Vec::new(),
ingested_at: None,
}
}
/// A git-repository artifact tracking the given branch.
pub fn git_repo(url: impl Into<String>, branch: impl Into<String>) -> Self {
let mut a = Self::bare(ArtifactKind::GitRepo, url);
a.git = Some(GitArtifactConfig::on_branch(branch));
a
}
/// A live-URL artifact with default crawl settings.
pub fn live_url(url: impl Into<String>) -> Self {
let mut a = Self::bare(ArtifactKind::LiveUrl, url);
a.web = Some(WebArtifactConfig::default());
a
}
/// A firmware-image artifact referenced by name (blob ingested later).
pub fn firmware_image(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::FirmwareImage, source_ref)
}
/// A source-archive artifact referenced by name (blob ingested later).
pub fn source_archive(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::SourceArchive, source_ref)
}
/// A mobile-package artifact (APK/AAB/IPA) referenced by name.
pub fn mobile_package(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::MobilePackage, source_ref)
}
/// A container-image artifact referenced by OCI ref.
pub fn container_image(source_ref: impl Into<String>) -> Self {
Self::bare(ArtifactKind::ContainerImage, source_ref)
}
/// A PLC-project artifact in the given format.
pub fn plc_project(source_ref: impl Into<String>, format: PlcFormat) -> Self {
let mut a = Self::bare(ArtifactKind::PlcProject, source_ref);
a.plc = Some(PlcArtifactConfig { format });
a
}
/// A plaintext-description artifact (classification input only).
pub fn plaintext(text: impl Into<String>) -> Self {
Self::bare(ArtifactKind::PlaintextDescription, text)
}
}
/// One ranked candidate produced by the classifier.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TargetTypeCandidate {
/// The candidate target type.
pub target_type: TargetType,
/// Confidence in `[0.0, 1.0]`.
pub confidence: f32,
/// Why this candidate was proposed.
pub rationale: String,
}
/// The classifier's verdict for a target: a suggested type plus ranked
/// alternatives and the facts the decision rested on.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Classification {
/// The top-ranked target type.
pub suggested: TargetType,
/// All candidates, sorted by descending confidence.
#[serde(default)]
pub candidates: Vec<TargetTypeCandidate>,
/// Facts gathered during classification.
#[serde(default)]
pub facts: Vec<DetectedFact>,
/// Which classifiers contributed (e.g. `["tramiton", "language-fingerprint"]`).
#[serde(default)]
pub detected_by: Vec<String>,
/// When classification ran.
#[serde(with = "super::serde_helpers::bson_datetime")]
pub detected_at: DateTime<Utc>,
/// Whether a human confirmed the suggestion.
#[serde(default)]
pub confirmed: bool,
}
/// Issue-tracker linkage, migrated from `TrackedRepository`'s `tracker_*` fields.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct IssueTrackerConfig {
/// The tracker platform.
pub tracker_type: Option<TrackerType>,
/// Tracker owner / organization.
pub owner: Option<String>,
/// Tracker repository / project.
pub repo: Option<String>,
/// Per-target tracker access token.
pub token: Option<String>,
}
/// How a target should be scanned.
///
/// `enabled_scans` / `disabled_scans` override the scan-applicability matrix
/// defaults; the pentest and tracker blocks reuse the existing wizard config.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct TargetScanConfig {
/// Scans explicitly turned on (empty means "use matrix defaults").
#[serde(default)]
pub enabled_scans: Vec<ScanType>,
/// Scans explicitly turned off.
#[serde(default)]
pub disabled_scans: Vec<ScanType>,
/// Target environment (gates destructive / active testing).
#[serde(default)]
pub environment: Environment,
/// Whether destructive tests are permitted for this target.
#[serde(default)]
pub allow_destructive: bool,
/// Pentest strategy selector.
pub strategy: Option<PentestStrategy>,
/// Full pentest wizard configuration.
pub pentest: Option<PentestConfig>,
/// Issue-tracker linkage.
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)]
pub struct OnboardedTarget {
/// Mongo id. Preserved from the legacy record during migration so every
/// downstream collection keyed by `repo_id` / `target_id` keeps resolving.
#[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
pub id: Option<bson::oid::ObjectId>,
/// Human-friendly name.
#[serde(default)]
pub name: String,
/// The software family this target belongs to.
pub target_type: TargetType,
/// Optional free-form description (also a classification input).
pub description: Option<String>,
/// The artifacts provided for this target.
#[serde(default)]
pub artifacts: Vec<Artifact>,
/// The classifier's verdict, once run.
pub classification: Option<Classification>,
/// 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.
#[serde(default)]
pub webhook_enabled: bool,
/// HMAC secret for verifying inbound webhooks.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub webhook_secret: Option<String>,
/// Cached count of findings across this target's scans.
#[serde(default)]
pub findings_count: u32,
/// Creation timestamp.
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub created_at: DateTime<Utc>,
/// Last-update timestamp.
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub updated_at: DateTime<Utc>,
}
impl OnboardedTarget {
/// A new target of the given type with a freshly generated webhook secret.
pub fn new(name: String, target_type: TargetType) -> Self {
let now = Utc::now();
let webhook_secret = uuid::Uuid::new_v4().to_string().replace('-', "");
Self {
id: None,
name,
target_type,
description: None,
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),
findings_count: 0,
created_at: now,
updated_at: now,
}
}
/// The first artifact of the given kind, if present.
pub fn first_of(&self, kind: ArtifactKind) -> Option<&Artifact> {
self.artifacts.iter().find(|a| a.kind == kind)
}
/// Whether the target has at least one artifact of the given kind.
pub fn has(&self, kind: ArtifactKind) -> bool {
self.artifacts.iter().any(|a| a.kind == kind)
}
/// The primary code artifact (git repo or source archive), if any.
pub fn code_artifact(&self) -> Option<&Artifact> {
self.artifacts
.iter()
.find(|a| matches!(a.kind, ArtifactKind::GitRepo | ArtifactKind::SourceArchive))
}
/// The live-URL artifact, if any.
pub fn live_url(&self) -> Option<&Artifact> {
self.first_of(ArtifactKind::LiveUrl)
}
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
fn sample_target() -> OnboardedTarget {
let mut t = OnboardedTarget::new("acme-web".to_string(), TargetType::WebApp);
t.artifacts.push(Artifact::git_repo(
"https://git.example.com/acme.git",
"main",
));
t.artifacts
.push(Artifact::live_url("https://acme.example.com"));
t
}
#[test]
fn onboarded_target_bson_round_trip() {
let t = sample_target();
let b = bson::to_bson(&t).expect("serialize");
let back: OnboardedTarget = bson::from_bson(b.clone()).expect("deserialize");
let b2 = bson::to_bson(&back).expect("re-serialize");
assert_eq!(b, b2);
}
#[test]
fn enum_display_is_snake_case() {
assert_eq!(
TargetType::FirmwareBareMetal.to_string(),
"firmware_bare_metal"
);
assert_eq!(TargetType::PlcSps.to_string(), "plc_sps");
assert_eq!(ArtifactKind::PlcProject.to_string(), "plc_project");
assert_eq!(ArtifactKind::MobilePackage.to_string(), "mobile_package");
}
#[test]
fn helpers_locate_artifacts() {
let t = sample_target();
assert!(t.has(ArtifactKind::GitRepo));
assert!(t.live_url().is_some());
assert!(t.code_artifact().is_some());
assert!(!t.has(ArtifactKind::FirmwareImage));
assert_eq!(
t.first_of(ArtifactKind::GitRepo).map(|a| a.kind),
Some(ArtifactKind::GitRepo)
);
}
#[test]
fn new_target_generates_webhook_secret() {
let t = OnboardedTarget::new("t".to_string(), TargetType::BackendService);
let secret = t.webhook_secret.expect("secret present");
assert_eq!(secret.len(), 32);
assert!(!secret.contains('-'));
}
#[test]
fn dast_auth_folds_into_artifact_auth() {
let dast = DastAuthConfig {
method: "bearer".to_string(),
login_url: Some("https://x/login".to_string()),
username: Some("user".to_string()),
password: Some("pw".to_string()),
token: Some("tok".to_string()),
headers: None,
};
let auth = ArtifactAuth::from(dast);
assert_eq!(auth.method, "bearer");
// Bearer token wins over password.
assert_eq!(auth.secret.as_deref(), Some("tok"));
assert_eq!(auth.login_url.as_deref(), Some("https://x/login"));
}
#[test]
fn each_artifact_gets_a_unique_id() {
let a = Artifact::firmware_image("fw.bin");
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());
}
}
+93 -2
View File
@@ -1,6 +1,8 @@
use serde::{Deserialize, Serialize};
use chrono::{DateTime, Utc};
use serde::{Deserialize, Deserializer, Serialize};
use super::issue::TrackerType;
/// What initiated a scan.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "snake_case")]
pub enum ScanTrigger {
@@ -8,3 +10,92 @@ pub enum ScanTrigger {
Webhook,
Manual,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TrackedRepository {
#[serde(rename = "_id", skip_serializing_if = "Option::is_none")]
pub id: Option<bson::oid::ObjectId>,
#[serde(default)]
pub name: String,
#[serde(default)]
pub git_url: String,
#[serde(default = "default_branch")]
pub default_branch: String,
pub local_path: Option<String>,
pub scan_schedule: Option<String>,
#[serde(default)]
pub webhook_enabled: bool,
/// Auto-generated HMAC secret for verifying incoming webhooks
#[serde(default, skip_serializing_if = "Option::is_none")]
pub webhook_secret: Option<String>,
pub tracker_type: Option<TrackerType>,
pub tracker_owner: Option<String>,
pub tracker_repo: Option<String>,
/// Optional per-repo PAT for the issue tracker (GitHub/GitLab/Jira)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub tracker_token: Option<String>,
/// Optional auth token for HTTPS private repos (PAT or password)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub auth_token: Option<String>,
/// Optional username for HTTPS auth (defaults to "x-access-token" for PATs)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub auth_username: Option<String>,
pub last_scanned_commit: Option<String>,
#[serde(default, deserialize_with = "deserialize_findings_count")]
pub findings_count: u32,
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub created_at: DateTime<Utc>,
#[serde(
default = "chrono::Utc::now",
with = "super::serde_helpers::bson_datetime"
)]
pub updated_at: DateTime<Utc>,
}
fn default_branch() -> String {
"main".to_string()
}
fn deserialize_findings_count<'de, D>(deserializer: D) -> Result<u32, D::Error>
where
D: Deserializer<'de>,
{
let bson = bson::Bson::deserialize(deserializer)?;
match &bson {
bson::Bson::Int32(n) => Ok(*n as u32),
bson::Bson::Int64(n) => Ok(*n as u32),
bson::Bson::Double(n) => Ok(*n as u32),
_ => Ok(0),
}
}
impl TrackedRepository {
pub fn new(name: String, git_url: String) -> Self {
let now = Utc::now();
// Generate a random webhook secret (hex-encoded UUID v4, no dashes)
let webhook_secret = uuid::Uuid::new_v4().to_string().replace('-', "");
Self {
id: None,
name,
git_url,
default_branch: "main".to_string(),
local_path: None,
scan_schedule: None,
auth_token: None,
auth_username: None,
webhook_enabled: false,
webhook_secret: Some(webhook_secret),
tracker_type: None,
tracker_owner: None,
tracker_repo: None,
tracker_token: None,
last_scanned_commit: None,
findings_count: 0,
created_at: now,
updated_at: now,
}
}
}
+1 -19
View File
@@ -3,7 +3,7 @@ use serde::{Deserialize, Serialize};
use super::repository::ScanTrigger;
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "lowercase")]
pub enum ScanType {
Sast,
@@ -16,14 +16,6 @@ pub enum ScanType {
SecretDetection,
Lint,
CodeReview,
/// Static analysis of a firmware image (unpack + component CVE).
FirmwareStatic,
/// Control-logic security analysis of PLC / SPS programs.
PlcControlLogic,
/// Static analysis of a mobile package (APK / AAB / IPA).
MobileStatic,
/// Static analysis of a container image.
ContainerScan,
}
impl std::fmt::Display for ScanType {
@@ -39,10 +31,6 @@ impl std::fmt::Display for ScanType {
Self::SecretDetection => write!(f, "secret_detection"),
Self::Lint => write!(f, "lint"),
Self::CodeReview => write!(f, "code_review"),
Self::FirmwareStatic => write!(f, "firmware_static"),
Self::PlcControlLogic => write!(f, "plc_control_logic"),
Self::MobileStatic => write!(f, "mobile_static"),
Self::ContainerScan => write!(f, "container_scan"),
}
}
}
@@ -59,8 +47,6 @@ pub enum ScanRunStatus {
#[serde(rename_all = "snake_case")]
pub enum ScanPhase {
ChangeDetection,
ArtifactIngest,
Classification,
Sast,
SbomGeneration,
CveScanning,
@@ -69,10 +55,6 @@ pub enum ScanPhase {
LintScanning,
CodeReview,
GraphBuilding,
FirmwareStatic,
PlcAnalysis,
MobileStatic,
ContainerScan,
LlmTriage,
IssueCreation,
DastScanning,
-379
View File
@@ -1,379 +0,0 @@
//! The scan-applicability matrix.
//!
//! Which scans are possible for a target is a function of its [`TargetType`] and
//! which [`ArtifactKind`]s are actually present: SAST needs code, DAST needs a
//! running URL, firmware-static analysis needs a firmware image, and so on. This
//! module encodes that as a table — one rule set per target type — and resolves
//! it against a concrete [`OnboardedTarget`] into a list of [`ScanOption`]s the
//! onboarding wizard and the scan pipeline both consume.
use crate::models::{ArtifactKind, OnboardedTarget, ScanType, TargetType};
/// What an artifact a scan needs in order to run.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum ArtifactRequirement {
/// Source code — a git repo or a source archive.
Code,
/// A reachable running instance (live URL / endpoint).
RunningUrl,
/// A firmware image / binary blob.
Firmware,
/// A PLC project (PLCopen XML or Structured Text).
Plc,
/// A mobile package (APK / AAB / IPA).
Mobile,
/// A container image.
Container,
/// No specific artifact required.
Any,
}
/// A static rule: this scan applies to a target type, needs this artifact, and
/// defaults on/off. The rationale explains the entry to the user.
#[derive(Debug, Clone, Copy)]
pub struct ScanRule {
/// The scan this rule governs.
pub scan: ScanType,
/// Whether the scan is on by default (only when its artifact is present).
pub default_on: bool,
/// Human-readable explanation of what the scan does here.
pub rationale: &'static str,
/// The artifact the scan consumes.
pub requires: ArtifactRequirement,
}
impl ScanRule {
const fn new(
scan: ScanType,
default_on: bool,
rationale: &'static str,
requires: ArtifactRequirement,
) -> Self {
Self {
scan,
default_on,
rationale,
requires,
}
}
}
/// A resolved scan choice for a specific target: a rule intersected with the
/// artifacts actually present. `blocked_reason` is `Some` when the required
/// artifact is missing.
#[derive(Debug, Clone)]
pub struct ScanOption {
/// The scan.
pub scan: ScanType,
/// Whether to pre-select the scan (false when blocked).
pub default_on: bool,
/// Why the scan is offered.
pub rationale: String,
/// The artifact kind the scan needs, if any specific one.
pub required_artifact: Option<ArtifactKind>,
/// Set when the required artifact is absent, explaining the block.
pub blocked_reason: Option<String>,
}
/// The SAST umbrella: every static-analysis sub-scan that runs over source code.
fn sast_umbrella() -> Vec<ScanRule> {
use ArtifactRequirement::Code;
vec![
ScanRule::new(
ScanType::Sast,
true,
"Static analysis (Semgrep) over source",
Code,
),
ScanRule::new(
ScanType::Sbom,
true,
"Software bill of materials from source",
Code,
),
ScanRule::new(
ScanType::Cve,
true,
"Match dependencies against known CVEs",
Code,
),
ScanRule::new(
ScanType::SecretDetection,
true,
"Scan source for committed secrets",
Code,
),
ScanRule::new(ScanType::Lint, true, "Language linters over source", Code),
ScanRule::new(
ScanType::Gdpr,
true,
"GDPR data-handling pattern checks",
Code,
),
ScanRule::new(
ScanType::OAuth,
true,
"OAuth misconfiguration patterns",
Code,
),
ScanRule::new(
ScanType::Graph,
true,
"Build the code graph for impact analysis",
Code,
),
ScanRule::new(
ScanType::CodeReview,
false,
"LLM code review over changed source",
Code,
),
]
}
/// The rule set for a target type. Scans that are never applicable to a type are
/// simply absent (e.g. DAST is not listed for a PLC target).
pub fn rules_for(target_type: TargetType) -> Vec<ScanRule> {
use ArtifactRequirement::{Firmware, Mobile, Plc, RunningUrl};
match target_type {
TargetType::WebApp | TargetType::BackendService => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::Dast,
true,
"Dynamic scan of the running endpoint",
RunningUrl,
));
r
}
TargetType::DesktopApp => sast_umbrella(),
TargetType::AndroidApp | TargetType::IosApp => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::MobileStatic,
true,
"Static analysis of the mobile package (manifest, permissions, libs)",
Mobile,
));
r
}
TargetType::FirmwareBareMetal | TargetType::FirmwareRtos => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::FirmwareStatic,
true,
"Unpack and statically analyze the firmware image",
Firmware,
));
r.push(ScanRule::new(
ScanType::Sbom,
true,
"SBOM from the firmware image (binwalk / tramiton)",
Firmware,
));
r.push(ScanRule::new(
ScanType::Cve,
true,
"Match firmware components against known CVEs",
Firmware,
));
r
}
TargetType::EmbeddedLinuxYocto => {
let mut r = sast_umbrella();
r.push(ScanRule::new(
ScanType::FirmwareStatic,
true,
"EMBA / binwalk static analysis of the image",
Firmware,
));
r.push(ScanRule::new(
ScanType::Sbom,
true,
"SBOM from image layers / recipes",
Firmware,
));
r.push(ScanRule::new(
ScanType::Cve,
true,
"Match image components against known CVEs",
Firmware,
));
r.push(ScanRule::new(
ScanType::Dast,
false,
"Dynamic scan of exposed network services (if any)",
RunningUrl,
));
r
}
TargetType::PlcSps => vec![ScanRule::new(
ScanType::PlcControlLogic,
true,
"Control-logic security rules over the PLC program",
Plc,
)],
}
}
/// Whether an active penetration test is applicable to this target type.
///
/// Pentest runs as its own session (not a [`ScanType`] scan) and needs a
/// reachable running target, so it is offered only for the network-reachable
/// families.
pub fn supports_pentest(target_type: TargetType) -> bool {
matches!(
target_type,
TargetType::WebApp
| TargetType::BackendService
| TargetType::AndroidApp
| TargetType::IosApp
| TargetType::EmbeddedLinuxYocto
)
}
/// The representative artifact kind a requirement is satisfied by.
fn representative_kind(req: ArtifactRequirement) -> Option<ArtifactKind> {
match req {
ArtifactRequirement::Code => Some(ArtifactKind::GitRepo),
ArtifactRequirement::RunningUrl => Some(ArtifactKind::LiveUrl),
ArtifactRequirement::Firmware => Some(ArtifactKind::FirmwareImage),
ArtifactRequirement::Plc => Some(ArtifactKind::PlcProject),
ArtifactRequirement::Mobile => Some(ArtifactKind::MobilePackage),
ArtifactRequirement::Container => Some(ArtifactKind::ContainerImage),
ArtifactRequirement::Any => None,
}
}
/// Whether the target carries an artifact that satisfies the requirement.
fn requirement_satisfied(req: ArtifactRequirement, target: &OnboardedTarget) -> bool {
match req {
ArtifactRequirement::Code => target.code_artifact().is_some(),
ArtifactRequirement::RunningUrl => target.has(ArtifactKind::LiveUrl),
ArtifactRequirement::Firmware => target.has(ArtifactKind::FirmwareImage),
ArtifactRequirement::Plc => target.has(ArtifactKind::PlcProject),
ArtifactRequirement::Mobile => target.has(ArtifactKind::MobilePackage),
ArtifactRequirement::Container => target.has(ArtifactKind::ContainerImage),
ArtifactRequirement::Any => true,
}
}
/// Resolve the matrix for a concrete target into the scans it can run, marking
/// any whose required artifact is missing as blocked.
pub fn applicable_scans(target: &OnboardedTarget) -> Vec<ScanOption> {
rules_for(target.target_type)
.into_iter()
.map(|rule| {
let satisfied = requirement_satisfied(rule.requires, target);
let required_artifact = representative_kind(rule.requires);
let blocked_reason = if satisfied {
None
} else {
Some(match required_artifact {
Some(kind) => format!("no {kind} artifact provided"),
None => "required artifact missing".to_string(),
})
};
ScanOption {
scan: rule.scan,
default_on: rule.default_on && satisfied,
rationale: rule.rationale.to_string(),
required_artifact,
blocked_reason,
}
})
.collect()
}
#[cfg(test)]
#[allow(clippy::expect_used, clippy::unwrap_used)]
mod tests {
use super::*;
use crate::models::{Artifact, PlcFormat};
fn target_with(target_type: TargetType, artifacts: Vec<Artifact>) -> OnboardedTarget {
let mut t = OnboardedTarget::new("t".to_string(), target_type);
t.artifacts = artifacts;
t
}
fn option<'a>(opts: &'a [ScanOption], scan: ScanType) -> Option<&'a ScanOption> {
opts.iter().find(|o| o.scan == scan)
}
#[test]
fn webapp_with_code_and_url_offers_sast_and_dast() {
let t = target_with(
TargetType::WebApp,
vec![
Artifact::git_repo("u", "main"),
Artifact::live_url("http://x"),
],
);
let opts = applicable_scans(&t);
let sast = option(&opts, ScanType::Sast).expect("sast offered");
assert!(sast.default_on && sast.blocked_reason.is_none());
let dast = option(&opts, ScanType::Dast).expect("dast offered");
assert!(dast.default_on && dast.blocked_reason.is_none());
}
#[test]
fn webapp_without_url_blocks_dast() {
let t = target_with(TargetType::WebApp, vec![Artifact::git_repo("u", "main")]);
let opts = applicable_scans(&t);
let dast = option(&opts, ScanType::Dast).expect("dast listed");
assert!(!dast.default_on);
assert!(dast.blocked_reason.is_some());
assert_eq!(dast.required_artifact, Some(ArtifactKind::LiveUrl));
}
#[test]
fn firmware_offers_firmware_static_and_not_dast() {
let t = target_with(
TargetType::FirmwareBareMetal,
vec![Artifact::firmware_image("fw.bin")],
);
let opts = applicable_scans(&t);
let fw = option(&opts, ScanType::FirmwareStatic).expect("firmware static offered");
assert!(fw.default_on && fw.blocked_reason.is_none());
assert!(option(&opts, ScanType::Dast).is_none());
}
#[test]
fn plc_offers_only_control_logic() {
let t = target_with(
TargetType::PlcSps,
vec![Artifact::plc_project("p.xml", PlcFormat::PlcopenXml)],
);
let opts = applicable_scans(&t);
assert_eq!(opts.len(), 1);
assert_eq!(opts[0].scan, ScanType::PlcControlLogic);
assert!(opts[0].default_on);
}
#[test]
fn pentest_support_matches_reachable_families() {
assert!(supports_pentest(TargetType::WebApp));
assert!(supports_pentest(TargetType::BackendService));
assert!(!supports_pentest(TargetType::PlcSps));
assert!(!supports_pentest(TargetType::FirmwareBareMetal));
assert!(!supports_pentest(TargetType::DesktopApp));
}
#[test]
fn every_target_type_has_at_least_one_rule() {
for tt in [
TargetType::WebApp,
TargetType::BackendService,
TargetType::DesktopApp,
TargetType::AndroidApp,
TargetType::IosApp,
TargetType::FirmwareBareMetal,
TargetType::FirmwareRtos,
TargetType::EmbeddedLinuxYocto,
TargetType::PlcSps,
] {
assert!(!rules_for(tt).is_empty(), "{tt} has no rules");
}
}
}
-51
View File
@@ -1,51 +0,0 @@
//! The target-classification port.
//!
//! A [`TargetClassifier`] inspects a target's artifacts (and optionally their
//! ingested working directories) and proposes one or more [`ClassifierVerdict`]s
//! — a target type, a confidence, and the facts the decision rested on. Concrete
//! classifiers live in the agent (language/build-system fingerprinting, a
//! firmware detector backed by tramiton, etc.); a registry merges and ranks
//! their verdicts. This mirrors the [`crate::traits::Scanner`] port so the two
//! read the same way.
use std::collections::HashMap;
use std::path::PathBuf;
use crate::error::CoreError;
use crate::models::{Artifact, DetectedFact, TargetType};
/// Everything a classifier needs to reason about a target.
pub struct ClassificationInput<'a> {
/// The artifacts declared for the target.
pub artifacts: &'a [Artifact],
/// Ingested working paths, keyed by [`Artifact::id`]. Absent for artifacts
/// with no on-disk form (e.g. a live URL).
pub working_paths: &'a HashMap<String, PathBuf>,
/// Free-form description of the target, if provided.
pub description: Option<&'a str>,
}
/// A single classifier's proposal for a target.
pub struct ClassifierVerdict {
/// The proposed target type.
pub target_type: TargetType,
/// Confidence in `[0.0, 1.0]`.
pub confidence: f32,
/// Facts that informed the proposal.
pub facts: Vec<DetectedFact>,
/// Human-readable explanation.
pub rationale: String,
}
/// A source of target-type classification.
#[allow(async_fn_in_trait)]
pub trait TargetClassifier: Send + Sync {
/// Stable identifier for this classifier (recorded in `detected_by`).
fn name(&self) -> &str;
/// Propose zero or more ranked verdicts for the given input.
async fn classify(
&self,
input: &ClassificationInput<'_>,
) -> Result<Vec<ClassifierVerdict>, CoreError>;
}
-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>;
}
-6
View File
@@ -1,16 +1,10 @@
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 -6
View File
@@ -10,10 +10,8 @@ pub enum Route {
#[layout(AppShell)]
#[route("/")]
OverviewPage {},
#[route("/targets")]
TargetsPage {},
#[route("/onboard")]
OnboardingPage {},
#[route("/repositories")]
RepositoriesPage {},
#[route("/findings")]
FindingsPage {},
#[route("/findings/:id")]
@@ -46,8 +44,6 @@ pub enum Route {
PentestSessionPage { session_id: String },
#[route("/mcp-servers")]
McpServersPage {},
#[route("/mcp-tokens")]
McpTokensPage {},
}
const FAVICON: Asset = asset!("/assets/favicon.svg");
@@ -4,9 +4,8 @@ use dioxus_free_icons::Icon;
use crate::app::Route;
use crate::infrastructure::dast::fetch_dast_targets;
use crate::infrastructure::onboarding::fetch_targets;
use crate::infrastructure::pentest::{create_pentest_session_wizard, lookup_repo_by_url};
use crate::infrastructure::repositories::fetch_ssh_public_key;
use crate::infrastructure::repositories::{fetch_repositories, fetch_ssh_public_key};
const DISCLAIMER_TEXT: &str = "I confirm that I have authorization to perform security testing \
against the specified target. I understand that penetration testing may cause disruption to the \
@@ -40,7 +39,7 @@ pub fn PentestWizard(show: Signal<bool>) -> Element {
let mut show_target_dropdown = use_signal(|| false);
let mut show_repo_dropdown = use_signal(|| false);
let existing_targets = use_resource(|| async { fetch_dast_targets().await.ok() });
let existing_repos = use_resource(|| async { fetch_targets().await.ok() });
let existing_repos = use_resource(|| async { fetch_repositories(1).await.ok() });
// SSH key state for private repos
let mut ssh_public_key = use_signal(String::new);
@@ -212,25 +211,7 @@ pub fn PentestWizard(show: Signal<bool>) -> Element {
Some(Some(data)) => data
.data
.iter()
.filter_map(|t| {
let name = t
.get("name")
.and_then(|v| v.as_str())
.unwrap_or_default()
.to_string();
let git_url = t
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())?
.to_string();
Some((git_url, name))
})
.map(|r| (r.git_url.clone(), r.name.clone()))
.collect(),
_ => Vec::new(),
}
@@ -24,15 +24,10 @@ pub fn Sidebar() -> Element {
icon: rsx! { Icon { icon: BsSpeedometer2, width: 18, height: 18 } },
},
NavItem {
label: "Targets",
route: Route::TargetsPage {},
label: "Repositories",
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 {},
@@ -19,6 +19,10 @@ impl Database {
Ok(Self { inner: db })
}
pub fn repositories(&self) -> Collection<TrackedRepository> {
self.inner.collection("repositories")
}
pub fn findings(&self) -> Collection<Finding> {
self.inner.collection("findings")
}
@@ -1,90 +0,0 @@
//! Server-functions for the MCP-tokens management UI.
//!
//! These wrap the agent's `/api/v1/mcp-tokens` CRUD endpoints. The raw
//! token returned by `create_mcp_token` is only visible at creation
//! time — the agent's storage never holds the plaintext.
use dioxus::prelude::*;
use serde::{Deserialize, Serialize};
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct McpTokenView {
pub id: String,
pub name: String,
pub token_prefix: String,
pub created_by: String,
pub created_at: serde_json::Value,
#[serde(default)]
pub last_used_at: Option<serde_json::Value>,
#[serde(default)]
pub revoked: bool,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct McpTokensListResponse {
pub data: Vec<McpTokenView>,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct CreateMcpTokenResponse {
/// Raw token. Shown ONCE — the user must copy it now.
pub token: String,
pub view: McpTokenView,
}
#[server]
pub async fn fetch_mcp_tokens() -> Result<McpTokensListResponse, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/mcp-tokens")
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: McpTokensListResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn create_mcp_token(name: String) -> Result<CreateMcpTokenResponse, ServerFnError> {
if name.trim().is_empty() {
return Err(ServerFnError::new("Name is required"));
}
let resp = super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/mcp-tokens")
.await?
.json(&serde_json::json!({ "name": name.trim() }))
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to create token: {body}"
)));
}
let body: CreateMcpTokenResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn revoke_mcp_token(id: String) -> Result<(), ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::DELETE,
&format!("/api/v1/mcp-tokens/{id}"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to revoke token: {body}"
)));
}
Ok(())
}
@@ -8,9 +8,7 @@ pub mod graph;
pub mod help_chat;
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;
@@ -1,227 +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,
}
/// Validate a target name. The name is used as the clone directory downstream,
/// so it must be a single safe segment (no slashes) and free of stray spaces.
pub fn validate_target_name(name: &str) -> Option<String> {
let n = name.trim();
if n.is_empty() {
return Some("Enter a name".to_string());
}
if name != n {
return Some("Remove the leading/trailing spaces".to_string());
}
if n.contains('/') || n.contains('\\') {
return Some("No slashes — the name becomes a folder (e.g. stm32f411-blinky)".to_string());
}
None
}
/// Client-side validation of an artifact reference for its kind. Returns an
/// error message when the value is obviously wrong for its category, so the
/// wizard / editor can flag it up front instead of the scan discovering it.
pub fn validate_artifact_ref(kind: &str, source_ref: &str) -> Option<String> {
let s = source_ref;
if s.trim().is_empty() {
return Some("Cannot be empty".to_string());
}
if s != s.trim() {
return Some("Remove the leading/trailing spaces".to_string());
}
let no_space = !s.contains(char::is_whitespace);
match kind {
"git_repo" => {
let looks_git = s.starts_with("https://")
|| s.starts_with("http://")
|| s.starts_with("ssh://")
|| s.starts_with("git://")
|| (s.contains('@') && s.contains(':'));
(!(looks_git && no_space))
.then(|| "Enter a git URL — https://…, ssh://…, or git@host:path".to_string())
}
"live_url" => {
let ok = (s.starts_with("https://") || s.starts_with("http://")) && no_space;
(!ok).then(|| "Enter an http(s) URL, e.g. https://app.example.com".to_string())
}
"container_image" => {
(!no_space).then(|| "Enter an image ref, e.g. registry/name:tag".to_string())
}
"source_archive" | "firmware_image" | "mobile_package" | "plc_project" => {
(!no_space).then(|| "Enter a path or URL (no spaces)".to_string())
}
// plaintext_description (and anything unknown): accept free-form text.
_ => None,
}
}
/// 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()))
}
/// Update a target's name / type / artifacts (dashboard editor).
#[server]
pub async fn update_target(
id: String,
name: Option<String>,
target_type: Option<String>,
artifacts: Option<Vec<ArtifactInputDto>>,
) -> Result<TargetResponse, ServerFnError> {
let mut body = serde_json::Map::new();
if let Some(n) = name {
body.insert("name".to_string(), serde_json::json!(n));
}
if let Some(t) = target_type {
body.insert("target_type".to_string(), serde_json::json!(t));
}
if let Some(a) = artifacts {
body.insert(
"artifacts".to_string(),
serde_json::to_value(a).map_err(|e| ServerFnError::new(e.to_string()))?,
);
}
let resp = super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/targets/{id}"),
)
.await?
.json(&serde_json::Value::Object(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()))
}
/// Delete a target (and cascade its findings / SBOM / scan runs / CVE alerts).
#[server]
pub async fn delete_target(id: String) -> Result<serde_json::Value, ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::DELETE,
&format!("/api/v1/targets/{id}"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
/// Trigger a scan for a target.
#[server]
pub async fn trigger_target_scan(id: String) -> Result<serde_json::Value, ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/targets/{id}/scan"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
resp.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))
}
@@ -1,10 +1,145 @@
//! The agent's SSH deploy public key — shown so a read-only deploy key can be
//! added to private git targets. (The legacy repositories CRUD moved to the
//! unified onboarding/targets API.)
use dioxus::prelude::*;
use serde::{Deserialize, Serialize};
use compliance_core::models::TrackedRepository;
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct RepositoryListResponse {
pub data: Vec<TrackedRepository>,
pub total: Option<u64>,
pub page: Option<u64>,
}
#[server]
pub async fn fetch_repositories(page: u64) -> Result<RepositoryListResponse, ServerFnError> {
let path = format!("/api/v1/repositories?page={page}&limit=20");
let resp = super::agent_client::agent_get(&path)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: RepositoryListResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
#[server]
pub async fn add_repository(
name: String,
git_url: String,
default_branch: String,
auth_token: Option<String>,
auth_username: Option<String>,
tracker_type: Option<String>,
tracker_owner: Option<String>,
tracker_repo: Option<String>,
tracker_token: Option<String>,
) -> Result<(), ServerFnError> {
let mut body = serde_json::json!({
"name": name,
"git_url": git_url,
"default_branch": default_branch,
});
if let Some(token) = auth_token.filter(|t| !t.is_empty()) {
body["auth_token"] = serde_json::Value::String(token);
}
if let Some(username) = auth_username.filter(|u| !u.is_empty()) {
body["auth_username"] = serde_json::Value::String(username);
}
if let Some(tt) = tracker_type.filter(|t| !t.is_empty()) {
body["tracker_type"] = serde_json::Value::String(tt);
}
if let Some(to) = tracker_owner.filter(|t| !t.is_empty()) {
body["tracker_owner"] = serde_json::Value::String(to);
}
if let Some(tr) = tracker_repo.filter(|t| !t.is_empty()) {
body["tracker_repo"] = serde_json::Value::String(tr);
}
if let Some(tk) = tracker_token.filter(|t| !t.is_empty()) {
body["tracker_token"] = serde_json::Value::String(tk);
}
let resp = super::agent_client::agent_request(reqwest::Method::POST, "/api/v1/repositories")
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to add repository: {body}"
)));
}
Ok(())
}
#[server]
pub async fn update_repository(
repo_id: String,
name: Option<String>,
default_branch: Option<String>,
auth_token: Option<String>,
auth_username: Option<String>,
tracker_type: Option<String>,
tracker_owner: Option<String>,
tracker_repo: Option<String>,
tracker_token: Option<String>,
scan_schedule: Option<String>,
) -> Result<(), ServerFnError> {
let mut body = serde_json::Map::new();
if let Some(v) = name.filter(|s| !s.is_empty()) {
body.insert("name".into(), serde_json::Value::String(v));
}
if let Some(v) = default_branch.filter(|s| !s.is_empty()) {
body.insert("default_branch".into(), serde_json::Value::String(v));
}
if let Some(v) = auth_token {
body.insert("auth_token".into(), serde_json::Value::String(v));
}
if let Some(v) = auth_username {
body.insert("auth_username".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_type {
body.insert("tracker_type".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_owner {
body.insert("tracker_owner".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_repo {
body.insert("tracker_repo".into(), serde_json::Value::String(v));
}
if let Some(v) = tracker_token {
body.insert("tracker_token".into(), serde_json::Value::String(v));
}
if let Some(v) = scan_schedule {
body.insert("scan_schedule".into(), serde_json::Value::String(v));
}
let resp = super::agent_client::agent_request(
reqwest::Method::PATCH,
&format!("/api/v1/repositories/{repo_id}"),
)
.await?
.json(&body)
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let text = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to update repository: {text}"
)));
}
Ok(())
}
/// Fetch the agent's SSH deploy public key.
#[server]
pub async fn fetch_ssh_public_key() -> Result<String, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/settings/ssh-public-key")
@@ -28,3 +163,86 @@ pub async fn fetch_ssh_public_key() -> Result<String, ServerFnError> {
.unwrap_or("")
.to_string())
}
#[server]
pub async fn delete_repository(repo_id: String) -> Result<(), ServerFnError> {
let resp = super::agent_client::agent_request(
reqwest::Method::DELETE,
&format!("/api/v1/repositories/{repo_id}"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
if !resp.status().is_success() {
let body = resp.text().await.unwrap_or_default();
return Err(ServerFnError::new(format!(
"Failed to delete repository: {body}"
)));
}
Ok(())
}
#[server]
pub async fn trigger_repo_scan(repo_id: String) -> Result<(), ServerFnError> {
super::agent_client::agent_request(
reqwest::Method::POST,
&format!("/api/v1/repositories/{repo_id}/scan"),
)
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(())
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct WebhookConfigResponse {
pub webhook_secret: Option<String>,
pub tracker_type: String,
}
#[server]
pub async fn fetch_webhook_config(repo_id: String) -> Result<WebhookConfigResponse, ServerFnError> {
let resp =
super::agent_client::agent_get(&format!("/api/v1/repositories/{repo_id}/webhook-config"))
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: WebhookConfigResponse = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
Ok(body)
}
/// Check if a repository has any running scans
#[server]
pub async fn check_repo_scanning(repo_id: String) -> Result<bool, ServerFnError> {
let resp = super::agent_client::agent_get("/api/v1/scan-runs?page=1&limit=1")
.await?
.send()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
let body: serde_json::Value = resp
.json()
.await
.map_err(|e| ServerFnError::new(e.to_string()))?;
// Check if the most recent scan for this repo is still running
if let Some(scans) = body.get("data").and_then(|d| d.as_array()) {
for scan in scans {
let scan_repo = scan.get("repo_id").and_then(|v| v.as_str()).unwrap_or("");
let status = scan.get("status").and_then(|v| v.as_str()).unwrap_or("");
if scan_repo == repo_id && status == "running" {
return Ok(true);
}
}
}
Ok(false)
}
+6 -28
View File
@@ -2,11 +2,11 @@ use dioxus::prelude::*;
use crate::app::Route;
use crate::components::page_header::PageHeader;
use crate::infrastructure::onboarding::fetch_targets;
use crate::infrastructure::repositories::fetch_repositories;
#[component]
pub fn ChatIndexPage() -> Element {
let repos = use_resource(|| async { fetch_targets().await.ok() });
let repos = use_resource(|| async { fetch_repositories(1).await.ok() });
rsx! {
PageHeader {
@@ -28,32 +28,10 @@ pub fn ChatIndexPage() -> Element {
div { class: "graph-index-grid",
for repo in repo_list {
{
let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let url = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string();
let branch = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find_map(|a| {
a.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
})
})
.unwrap_or("main")
.to_string();
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let url = repo.git_url.clone();
let branch = repo.default_branch.clone();
rsx! {
Link {
to: Route::ChatPage { repo_id },
+5 -5
View File
@@ -20,7 +20,7 @@ pub fn FindingsPage() -> Element {
let mut selected_ids = use_signal(Vec::<String>::new);
let repos = use_resource(|| async {
crate::infrastructure::onboarding::fetch_targets()
crate::infrastructure::repositories::fetch_repositories(1)
.await
.ok()
});
@@ -86,14 +86,14 @@ pub fn FindingsPage() -> Element {
}
select {
onchange: move |e| { repo_filter.set(e.value()); page.set(1); },
option { value: "", "All Targets" }
option { value: "", "All Repositories" }
{
match &*repos.read() {
Some(Some(resp)) => rsx! {
for t in &resp.data {
for repo in &resp.data {
{
let id = t.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = t.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
rsx! {
option { value: "{id}", "{name}" }
}
+25 -29
View File
@@ -2,11 +2,11 @@ use dioxus::prelude::*;
use crate::app::Route;
use crate::components::page_header::PageHeader;
use crate::infrastructure::onboarding::fetch_targets;
use crate::infrastructure::repositories::fetch_repositories;
#[component]
pub fn GraphIndexPage() -> Element {
let repos = use_resource(|| async { fetch_targets().await.ok() });
let repos = use_resource(|| async { fetch_repositories(1).await.ok() });
rsx! {
PageHeader {
@@ -28,34 +28,27 @@ pub fn GraphIndexPage() -> Element {
div { class: "graph-index-grid",
for repo in repo_list {
{
let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let url = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find(|a| {
a.get("kind").and_then(|k| k.as_str()) == Some("git_repo")
})
})
.and_then(|a| a.get("source_ref"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string();
let branch = repo
.get("artifacts")
.and_then(|a| a.as_array())
.and_then(|arr| {
arr.iter().find_map(|a| {
a.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
})
})
.unwrap_or("main")
.to_string();
let findings = repo.get("findings_count").and_then(|n| n.as_u64()).unwrap_or(0);
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
let url = repo.git_url.clone();
let branch = repo.default_branch.clone();
let findings = repo.findings_count;
let findings_label = if findings != 1 { format!("{findings} findings") } else { "1 finding".to_string() };
let updated = {
let now = chrono::Utc::now();
let diff = now.signed_duration_since(repo.updated_at);
if diff.num_minutes() < 1 {
"just now".to_string()
} else if diff.num_hours() < 1 {
format!("{}m ago", diff.num_minutes())
} else if diff.num_days() < 1 {
format!("{}h ago", diff.num_hours())
} else if diff.num_days() < 30 {
format!("{}d ago", diff.num_days())
} else {
repo.updated_at.format("%Y-%m-%d").to_string()
}
};
rsx! {
Link {
to: Route::GraphExplorerPage { repo_id },
@@ -74,6 +67,9 @@ pub fn GraphIndexPage() -> Element {
span { class: "graph-repo-card-tag graph-repo-card-tag-findings",
"{findings_label}"
}
span { class: "graph-repo-card-tag",
"Updated {updated}"
}
}
}
}
@@ -1,271 +0,0 @@
use dioxus::prelude::*;
use dioxus_free_icons::icons::bs_icons::*;
use dioxus_free_icons::Icon;
use crate::components::page_header::PageHeader;
use crate::components::toast::{ToastType, Toasts};
use crate::infrastructure::mcp_tokens::{
create_mcp_token, fetch_mcp_tokens, revoke_mcp_token, CreateMcpTokenResponse,
};
#[component]
pub fn McpTokensPage() -> Element {
let mut tokens = use_resource(|| async { fetch_mcp_tokens().await.ok() });
let mut toasts = use_context::<Toasts>();
// Create-form state
let mut show_form = use_signal(|| false);
let mut new_name = use_signal(String::new);
let mut submitting = use_signal(|| false);
// After creation, the raw token shows once in a banner
let mut just_created: Signal<Option<CreateMcpTokenResponse>> = use_signal(|| None);
// Revoke confirmation: (id, name)
let mut confirm_revoke: Signal<Option<(String, String)>> = use_signal(|| None);
rsx! {
PageHeader {
title: "MCP Tokens",
description: "Static bearer tokens for the MCP server. Use in your LLM client (Claude Desktop, Cursor, etc.) — one token per tool/device.",
}
// ── Just-created banner ────────────────────────────────────
if let Some(resp) = just_created() {
div { class: "card mb-4", style: "border: 1px solid var(--accent-warning); background: var(--bg-warning-subtle);",
div { class: "card-header", style: "color: var(--accent-warning);",
Icon { icon: BsExclamationTriangle, width: 14, height: 14 }
" Copy this token now — it won't be shown again"
}
div { style: "padding: 1rem;",
p { style: "margin-bottom: 0.5rem; color: var(--text-secondary);",
"Token for "
strong { "{resp.view.name}" }
}
div { class: "copyable", style: "background: var(--bg-secondary); padding: 0.75rem; border-radius: 4px;",
code { style: "font-family: var(--font-mono); word-break: break-all; flex: 1;", "{resp.token}" }
crate::components::copy_button::CopyButton { value: resp.token.clone(), small: false }
}
div { style: "margin-top: 0.75rem;",
button {
class: "btn btn-sm btn-ghost",
onclick: move |_| just_created.set(None),
"Dismiss"
}
}
}
}
}
// ── Create form ────────────────────────────────────────────
div { class: "mb-4",
button {
class: "btn btn-primary",
onclick: move |_| {
show_form.set(!show_form());
new_name.set(String::new());
},
if show_form() { "Cancel" } else {
Icon { icon: BsPlusLg, width: 14, height: 14 }
" Create Token"
}
}
}
if show_form() {
div { class: "card mb-4",
div { class: "card-header", "New MCP Token" }
div { style: "padding: 1rem;",
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
placeholder: "Claude Desktop on my laptop",
value: "{new_name}",
oninput: move |e| new_name.set(e.value()),
}
small { style: "color: var(--text-secondary);", "A label so you can identify this token in the list. Not visible to LLM clients." }
}
div { style: "margin-top: 1rem;",
button {
class: "btn btn-primary",
disabled: submitting() || new_name().trim().is_empty(),
onclick: move |_| {
let name = new_name().trim().to_string();
if name.is_empty() {
return;
}
spawn(async move {
submitting.set(true);
match create_mcp_token(name).await {
Ok(resp) => {
toasts.push(ToastType::Success, "Token created. Copy it now — it won't be shown again.");
just_created.set(Some(resp));
show_form.set(false);
new_name.set(String::new());
tokens.restart();
}
Err(e) => {
toasts.push(ToastType::Error, format!("Failed to create token: {e}"));
}
}
submitting.set(false);
});
},
if submitting() { "Creating..." } else { "Create" }
}
}
}
}
}
// ── Tokens list ────────────────────────────────────────────
match &*tokens.read() {
Some(Some(resp)) => {
if resp.data.is_empty() {
rsx! {
div { class: "card",
p { style: "padding: 1rem; color: var(--text-secondary);", "No MCP tokens yet. Create one to start using the MCP server from an LLM client." }
}
}
} else {
rsx! {
div { class: "mcp-cards-grid",
for token in resp.data.iter() {
{
let id = token.id.clone();
let name = token.name.clone();
let prefix = token.token_prefix.clone();
let created_str = format_timestamp(&token.created_at);
let last_used_str = token
.last_used_at
.as_ref()
.map(format_timestamp)
.unwrap_or_else(|| "never".to_string());
let revoked = token.revoked;
rsx! {
div { class: "mcp-card", style: if revoked { "opacity: 0.55;" } else { "" },
div { class: "mcp-card-header",
div { class: "mcp-card-title",
Icon { icon: BsKey, width: 14, height: 14 }
h3 { "{name}" }
if revoked {
span { class: "mcp-card-status stopped", "revoked" }
}
}
if !revoked {
button {
class: "btn btn-sm btn-ghost btn-ghost-danger",
title: "Revoke token",
onclick: {
let id = id.clone();
let name = name.clone();
move |_| {
confirm_revoke.set(Some((id.clone(), name.clone())));
}
},
Icon { icon: BsTrash, width: 14, height: 14 }
}
}
}
div { class: "mcp-card-details",
div { class: "mcp-detail-row",
Icon { icon: BsKey, width: 13, height: 13 }
span { class: "mcp-detail-label", "Prefix" }
code { class: "mcp-detail-value", "{prefix}…" }
}
div { class: "mcp-detail-row",
Icon { icon: BsCalendar, width: 13, height: 13 }
span { class: "mcp-detail-label", "Created" }
span { class: "mcp-detail-value", "{created_str}" }
}
div { class: "mcp-detail-row",
Icon { icon: BsClockHistory, width: 13, height: 13 }
span { class: "mcp-detail-label", "Last used" }
span { class: "mcp-detail-value", "{last_used_str}" }
}
}
}
}
}
}
}
}
}
}
Some(None) => rsx! {
div { class: "card",
p { style: "padding: 1rem; color: var(--accent-danger);", "Failed to load MCP tokens." }
}
},
None => rsx! {
div { class: "card",
p { style: "padding: 1rem; color: var(--text-secondary);", "Loading..." }
}
},
}
// ── Revoke confirmation modal ──────────────────────────────
if let Some((id, name)) = confirm_revoke() {
div { class: "modal-overlay",
div { class: "modal",
h3 { "Revoke token?" }
p {
"The token "
strong { "{name}" }
" will stop working immediately. This cannot be undone. Any LLM client using it will start getting 401."
}
div { style: "display: flex; gap: 0.5rem; margin-top: 1rem; justify-content: flex-end;",
button {
class: "btn btn-ghost",
onclick: move |_| confirm_revoke.set(None),
"Cancel"
}
button {
class: "btn btn-danger",
onclick: {
let id = id.clone();
move |_| {
let id = id.clone();
spawn(async move {
match revoke_mcp_token(id).await {
Ok(()) => {
toasts.push(ToastType::Success, "Token revoked");
tokens.restart();
}
Err(e) => {
toasts.push(ToastType::Error, format!("Failed to revoke: {e}"));
}
}
confirm_revoke.set(None);
});
}
},
"Revoke"
}
}
}
}
}
}
}
/// Best-effort timestamp formatter. The agent serializes BSON DateTime
/// as `{"$date":{"$numberLong":"..."}}` in extended JSON. We accept
/// that shape, plain ISO strings, or anything else (best-effort).
fn format_timestamp(v: &serde_json::Value) -> String {
if let Some(s) = v.as_str() {
return s.to_string();
}
if let Some(ms) = v
.get("$date")
.and_then(|d| d.get("$numberLong"))
.and_then(|s| s.as_str())
.and_then(|s| s.parse::<i64>().ok())
{
return chrono::DateTime::<chrono::Utc>::from_timestamp_millis(ms)
.map(|d| d.format("%Y-%m-%d %H:%M").to_string())
.unwrap_or_else(|| ms.to_string());
}
"".to_string()
}
+2 -6
View File
@@ -11,13 +11,11 @@ pub mod graph_index;
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;
pub mod repositories;
pub mod sbom;
pub mod targets;
pub use chat::ChatPage;
pub use chat_index::ChatIndexPage;
@@ -32,10 +30,8 @@ pub use graph_index::GraphIndexPage;
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;
pub use repositories::RepositoriesPage;
pub use sbom::SbomPage;
pub use targets::TargetsPage;
@@ -1,421 +0,0 @@
use dioxus::prelude::*;
use crate::components::page_header::PageHeader;
use crate::infrastructure::onboarding::{
create_target, detect_target, fetch_applicable_scans, trigger_target_scan,
validate_artifact_ref, validate_target_name, 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 mut created_id = use_signal(|| Option::<String>::None);
let mut scan_msg = use_signal(|| Option::<String>::None);
let step_now = step();
let name_error = validate_target_name(&name());
let can_advance_type = name_error.is_none() && !target_type().trim().is_empty();
let has_artifacts = !artifacts().is_empty();
// Live validation of the artifact reference being typed (empty = no error yet).
let new_source_error = if new_source().is_empty() {
None
} else {
validate_artifact_ref(&new_kind(), &new_source())
};
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()),
}
if !name().is_empty() {
if let Some(err) = name_error.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em; margin-top: 4px;", "{err}" }
}
}
}
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",
disabled: new_source().trim().is_empty() || new_source_error.is_some(),
onclick: move |_| {
let kind = new_kind();
if !new_source().trim().is_empty()
&& validate_artifact_ref(&kind, &new_source()).is_none()
{
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"
}
}
if let Some(err) = new_source_error.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em; margin-top: 6px;", "{err}" }
}
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 }
}
}
if let Some(msg) = scan_msg() {
div { style: "margin-top: 8px; color: var(--success, #2a2);", "{msg}" }
}
div { style: "margin-top: 16px; display: flex; gap: 8px;",
button {
class: "btn btn-primary",
onclick: move |_| {
if let Some(id) = created_id() {
scan_msg.set(Some("Scan triggered...".to_string()));
spawn(async move {
match trigger_target_scan(id).await {
Ok(_) => scan_msg.set(Some(
"Scan started — findings will appear as it runs.".to_string(),
)),
Err(e) => scan_msg.set(Some(format!("Failed to start scan: {e}"))),
}
});
}
},
"Run scan"
}
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);
created_id.set(None);
scan_msg.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 {
created_id.set(Some(id.clone()));
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" }
}
}
}
}
}
}
+4 -4
View File
@@ -6,7 +6,7 @@ use crate::app::Route;
use crate::components::page_header::PageHeader;
use crate::components::stat_card::StatCard;
use crate::infrastructure::mcp::fetch_mcp_servers;
use crate::infrastructure::onboarding::fetch_targets;
use crate::infrastructure::repositories::fetch_repositories;
#[cfg(feature = "server")]
use crate::infrastructure::stats::fetch_overview_stats;
@@ -26,7 +26,7 @@ pub fn OverviewPage() -> Element {
}
});
let repos = use_resource(|| async { fetch_targets().await.ok() });
let repos = use_resource(|| async { fetch_repositories(1).await.ok() });
let mcp_servers = use_resource(|| async { fetch_mcp_servers().await.ok() });
rsx! {
@@ -94,8 +94,8 @@ pub fn OverviewPage() -> Element {
style: "display: grid; grid-template-columns: repeat(3, 1fr); gap: 1rem; padding: 1rem;",
for repo in repo_list {
{
let repo_id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
rsx! {
Link {
to: Route::ChatPage { repo_id },
@@ -0,0 +1,657 @@
use dioxus::prelude::*;
use dioxus_free_icons::icons::bs_icons::*;
#[allow(unused_imports)]
use dioxus_free_icons::icons::bs_icons::{BsGear, BsPencil};
use dioxus_free_icons::Icon;
use crate::components::page_header::PageHeader;
use crate::components::pagination::Pagination;
use crate::components::toast::{ToastType, Toasts};
use crate::pages::graph_explorer::GraphExplorerInline;
async fn async_sleep_5s() {
#[cfg(feature = "web")]
{
gloo_timers::future::TimeoutFuture::new(5_000).await;
}
#[cfg(not(feature = "web"))]
{
tokio::time::sleep(std::time::Duration::from_secs(5)).await;
}
}
#[component]
pub fn RepositoriesPage() -> Element {
let mut page = use_signal(|| 1u64);
let mut show_add_form = use_signal(|| false);
let mut name = use_signal(String::new);
let mut git_url = use_signal(String::new);
let mut branch = use_signal(|| "main".to_string());
let mut auth_token = use_signal(String::new);
let mut auth_username = use_signal(String::new);
let mut show_auth = use_signal(|| false);
let mut ssh_public_key = use_signal(String::new);
let mut show_tracker = use_signal(|| false);
let mut tracker_type_val = use_signal(String::new);
let mut tracker_owner_val = use_signal(String::new);
let mut tracker_repo_val = use_signal(String::new);
let mut tracker_token_val = use_signal(String::new);
let mut adding = use_signal(|| false);
let mut toasts = use_context::<Toasts>();
let mut confirm_delete = use_signal(|| Option::<(String, String)>::None); // (id, name)
let mut edit_repo_id = use_signal(|| Option::<String>::None);
let mut edit_name = use_signal(String::new);
let mut edit_branch = use_signal(String::new);
let mut edit_tracker_type = use_signal(String::new);
let mut edit_tracker_owner = use_signal(String::new);
let mut edit_tracker_repo = use_signal(String::new);
let mut edit_tracker_token = use_signal(String::new);
let mut edit_saving = use_signal(|| false);
let mut edit_webhook_secret = use_signal(|| Option::<String>::None);
let mut edit_webhook_tracker = use_signal(String::new);
let mut scanning_ids = use_signal(Vec::<String>::new);
let mut graph_repo_id = use_signal(|| Option::<String>::None);
let mut repos = use_resource(move || {
let p = page();
async move {
crate::infrastructure::repositories::fetch_repositories(p)
.await
.ok()
}
});
rsx! {
PageHeader {
title: "Repositories",
description: "Tracked git repositories",
}
div { style: "margin-bottom: 16px;",
button {
class: "btn btn-primary",
onclick: move |_| show_add_form.toggle(),
if show_add_form() { "Cancel" } else { "+ Add Repository" }
}
}
if show_add_form() {
div { class: "card",
div { class: "card-header", "Add Repository" }
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
placeholder: "my-project",
value: "{name}",
oninput: move |e| name.set(e.value()),
}
}
div { class: "form-group",
label { "Git URL" }
input {
r#type: "text",
placeholder: "https://github.com/org/repo.git or git@github.com:org/repo.git",
value: "{git_url}",
oninput: move |e| git_url.set(e.value()),
}
}
div { class: "form-group",
label { "Default Branch" }
input {
r#type: "text",
placeholder: "main",
value: "{branch}",
oninput: move |e| branch.set(e.value()),
}
}
// Private repo auth section
div { style: "margin-top: 8px;",
button {
class: "btn btn-ghost",
style: "font-size: 12px; padding: 4px 8px;",
onclick: move |_| {
let opening = !show_auth();
show_auth.toggle();
if opening {
// Fetch SSH key every time the section opens
ssh_public_key.set(String::new());
spawn(async move {
match crate::infrastructure::repositories::fetch_ssh_public_key().await {
Ok(key) => ssh_public_key.set(key),
Err(_) => ssh_public_key.set("(not available)".to_string()),
}
});
}
},
if show_auth() { "Hide auth options" } else { "Private repository?" }
}
}
if show_auth() {
div { class: "auth-section", style: "margin-top: 12px; padding: 12px; border: 1px solid var(--border-subtle); border-radius: 8px;",
// SSH deploy key display
div { style: "margin-bottom: 12px;",
label { style: "font-size: 12px; color: var(--text-secondary);",
"For SSH URLs: add this deploy key (read-only) to your repository"
}
div {
class: "copyable",
style: "margin-top: 4px; padding: 8px; background: var(--bg-secondary); border-radius: 4px;",
code {
style: "font-size: 11px; word-break: break-all; user-select: all;",
if ssh_public_key().is_empty() {
"Loading..."
} else {
"{ssh_public_key}"
}
}
if !ssh_public_key().is_empty() {
crate::components::copy_button::CopyButton { value: ssh_public_key(), small: true }
}
}
}
// HTTPS auth fields
p { style: "font-size: 12px; color: var(--text-secondary); margin-bottom: 8px;",
"For HTTPS URLs: provide an access token (PAT) or username/password"
}
div { class: "form-group",
label { "Auth Token / Password" }
input {
r#type: "password",
placeholder: "ghp_xxxx or personal access token",
value: "{auth_token}",
oninput: move |e| auth_token.set(e.value()),
}
}
div { class: "form-group",
label { "Username (optional, defaults to x-access-token)" }
input {
r#type: "text",
placeholder: "x-access-token",
value: "{auth_username}",
oninput: move |e| auth_username.set(e.value()),
}
}
}
}
// Issue tracker config section
div { style: "margin-top: 8px;",
button {
class: "btn btn-ghost",
style: "font-size: 12px; padding: 4px 8px;",
onclick: move |_| show_tracker.toggle(),
if show_tracker() { "Hide tracker options" } else { "Issue tracker?" }
}
}
if show_tracker() {
div { class: "auth-section", style: "margin-top: 12px; padding: 12px; border: 1px solid var(--border-subtle); border-radius: 8px;",
p { style: "font-size: 12px; color: var(--text-secondary); margin-bottom: 8px;",
"Configure an issue tracker to auto-create issues from findings"
}
div { class: "form-group",
label { "Tracker Type" }
select {
value: "{tracker_type_val}",
onchange: move |e| tracker_type_val.set(e.value()),
option { value: "", "None" }
option { value: "github", "GitHub" }
option { value: "gitlab", "GitLab" }
option { value: "gitea", "Gitea" }
option { value: "jira", "Jira" }
}
}
div { class: "form-group",
label { "Owner / Namespace" }
input {
r#type: "text",
placeholder: "org-name",
value: "{tracker_owner_val}",
oninput: move |e| tracker_owner_val.set(e.value()),
}
}
div { class: "form-group",
label { "Repository / Project" }
input {
r#type: "text",
placeholder: "repo-name",
value: "{tracker_repo_val}",
oninput: move |e| tracker_repo_val.set(e.value()),
}
}
div { class: "form-group",
label { "Tracker Token (PAT)" }
input {
r#type: "password",
placeholder: "ghp_xxxx / glpat-xxxx",
value: "{tracker_token_val}",
oninput: move |e| tracker_token_val.set(e.value()),
}
}
}
}
button {
class: "btn btn-primary",
disabled: adding(),
onclick: move |_| {
let n = name();
let u = git_url();
let b = branch();
let tok = {
let v = auth_token();
if v.is_empty() { None } else { Some(v) }
};
let usr = {
let v = auth_username();
if v.is_empty() { None } else { Some(v) }
};
let tt = { let v = tracker_type_val(); if v.is_empty() { None } else { Some(v) } };
let t_owner = { let v = tracker_owner_val(); if v.is_empty() { None } else { Some(v) } };
let t_repo = { let v = tracker_repo_val(); if v.is_empty() { None } else { Some(v) } };
let t_tok = { let v = tracker_token_val(); if v.is_empty() { None } else { Some(v) } };
adding.set(true);
spawn(async move {
match crate::infrastructure::repositories::add_repository(n, u, b, tok, usr, tt, t_owner, t_repo, t_tok).await {
Ok(_) => {
toasts.push(ToastType::Success, "Repository added");
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
adding.set(false);
});
show_add_form.set(false);
show_auth.set(false);
show_tracker.set(false);
name.set(String::new());
git_url.set(String::new());
auth_token.set(String::new());
auth_username.set(String::new());
tracker_type_val.set(String::new());
tracker_owner_val.set(String::new());
tracker_repo_val.set(String::new());
tracker_token_val.set(String::new());
},
if adding() { "Validating..." } else { "Add" }
}
}
}
// ── Delete confirmation dialog ──
if let Some((del_id, del_name)) = confirm_delete() {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Delete Repository" }
p {
"Are you sure you want to delete "
strong { "{del_name}" }
"?"
}
p { class: "modal-warning",
"This will permanently remove all associated findings, SBOM entries, scan runs, graph data, embeddings, and CVE alerts."
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| confirm_delete.set(None),
"Cancel"
}
button {
class: "btn btn-danger",
onclick: move |_| {
let id = del_id.clone();
let name = del_name.clone();
confirm_delete.set(None);
spawn(async move {
match crate::infrastructure::repositories::delete_repository(id).await {
Ok(_) => {
toasts.push(ToastType::Success, format!("{name} deleted"));
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
});
},
"Delete"
}
}
}
}
}
// ── Edit repository dialog ──
if let Some(eid) = edit_repo_id() {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Edit Repository" }
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
value: "{edit_name}",
oninput: move |e| edit_name.set(e.value()),
}
}
div { class: "form-group",
label { "Default Branch" }
input {
r#type: "text",
value: "{edit_branch}",
oninput: move |e| edit_branch.set(e.value()),
}
}
h4 { style: "margin-top: 16px; margin-bottom: 8px; font-size: 14px; color: var(--text-secondary);", "Issue Tracker" }
div { class: "form-group",
label { "Tracker Type" }
select {
value: "{edit_tracker_type}",
onchange: move |e| edit_tracker_type.set(e.value()),
option { value: "", "None" }
option { value: "github", "GitHub" }
option { value: "gitlab", "GitLab" }
option { value: "gitea", "Gitea" }
option { value: "jira", "Jira" }
}
}
div { class: "form-group",
label { "Owner / Namespace" }
input {
r#type: "text",
placeholder: "org-name",
value: "{edit_tracker_owner}",
oninput: move |e| edit_tracker_owner.set(e.value()),
}
}
div { class: "form-group",
label { "Repository / Project" }
input {
r#type: "text",
placeholder: "repo-name",
value: "{edit_tracker_repo}",
oninput: move |e| edit_tracker_repo.set(e.value()),
}
}
div { class: "form-group",
label { "Tracker Token (leave empty to keep existing)" }
input {
r#type: "password",
placeholder: "Enter new token to change",
value: "{edit_tracker_token}",
oninput: move |e| edit_tracker_token.set(e.value()),
}
}
// Webhook configuration section
if let Some(secret) = edit_webhook_secret() {
h4 {
style: "margin-top: 16px; margin-bottom: 8px; font-size: 14px; color: var(--text-secondary);",
"Webhook Configuration"
}
p {
style: "font-size: 12px; color: var(--text-secondary); margin-bottom: 8px;",
"Add this webhook in your repository settings to enable push-triggered scans and PR reviews."
}
div { class: "form-group",
label { "Webhook URL" }
{
#[cfg(feature = "web")]
let origin = web_sys::window()
.and_then(|w: web_sys::Window| w.location().origin().ok())
.unwrap_or_default();
#[cfg(not(feature = "web"))]
let origin = String::new();
let webhook_url = format!("{origin}/webhook/{}/{eid}", edit_webhook_tracker());
rsx! {
div { class: "copyable",
input {
r#type: "text",
readonly: true,
style: "font-family: monospace; font-size: 12px; flex: 1;",
value: "{webhook_url}",
}
crate::components::copy_button::CopyButton { value: webhook_url.clone() }
}
}
}
}
div { class: "form-group",
label { "Webhook Secret" }
div { class: "copyable",
input {
r#type: "text",
readonly: true,
style: "font-family: monospace; font-size: 12px; flex: 1;",
value: "{secret}",
}
crate::components::copy_button::CopyButton { value: secret.clone() }
}
}
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| edit_repo_id.set(None),
"Cancel"
}
button {
class: "btn btn-primary",
disabled: edit_saving(),
onclick: move |_| {
let id = eid.clone();
let nm = { let v = edit_name(); if v.is_empty() { None } else { Some(v) } };
let br = { let v = edit_branch(); if v.is_empty() { None } else { Some(v) } };
let tt = { let v = edit_tracker_type(); if v.is_empty() { None } else { Some(v) } };
let t_owner = { let v = edit_tracker_owner(); if v.is_empty() { None } else { Some(v) } };
let t_repo = { let v = edit_tracker_repo(); if v.is_empty() { None } else { Some(v) } };
let t_tok = { let v = edit_tracker_token(); if v.is_empty() { None } else { Some(v) } };
edit_saving.set(true);
spawn(async move {
match crate::infrastructure::repositories::update_repository(
id, nm, br, None, None, tt, t_owner, t_repo, t_tok, None,
).await {
Ok(_) => {
toasts.push(ToastType::Success, "Repository updated");
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
edit_saving.set(false);
edit_repo_id.set(None);
});
},
if edit_saving() { "Saving..." } else { "Save" }
}
}
}
}
}
match &*repos.read() {
Some(Some(resp)) => {
let total_pages = resp.total.unwrap_or(0).div_ceil(20).max(1);
rsx! {
div { class: "card",
div { class: "table-wrapper",
table {
thead {
tr {
th { "Name" }
th { "Git URL" }
th { "Branch" }
th { "Findings" }
th { "Last Scanned" }
th { "Actions" }
}
}
tbody {
for repo in &resp.data {
{
let repo_id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let repo_id_scan = repo_id.clone();
let repo_id_del = repo_id.clone();
let repo_id_edit = repo_id.clone();
let repo_name_del = repo.name.clone();
let edit_repo_data = repo.clone();
let is_scanning = scanning_ids().contains(&repo_id);
rsx! {
tr {
td { "{repo.name}" }
td {
style: "font-size: 12px; font-family: monospace;",
"{repo.git_url}"
}
td { "{repo.default_branch}" }
td { "{repo.findings_count}" }
td {
{
let now = chrono::Utc::now();
let diff = now.signed_duration_since(repo.updated_at);
let label = if diff.num_minutes() < 1 {
"just now".to_string()
} else if diff.num_hours() < 1 {
format!("{}m ago", diff.num_minutes())
} else if diff.num_days() < 1 {
format!("{}h ago", diff.num_hours())
} else if diff.num_days() < 30 {
format!("{}d ago", diff.num_days())
} else {
repo.updated_at.format("%Y-%m-%d").to_string()
};
rsx! { span { style: "font-size: 12px;", "{label}" } }
}
}
td { style: "display: flex; gap: 4px;",
button {
class: if graph_repo_id().as_deref() == Some(repo_id.as_str()) { "btn btn-ghost btn-active" } else { "btn btn-ghost" },
title: "View graph",
onclick: {
let rid = repo_id.clone();
move |_| {
if graph_repo_id().as_deref() == Some(rid.as_str()) {
graph_repo_id.set(None);
} else {
graph_repo_id.set(Some(rid.clone()));
}
}
},
Icon { icon: BsDiagram3, width: 16, height: 16 }
}
button {
class: "btn btn-ghost",
title: "Edit repository",
onclick: move |_| {
edit_name.set(edit_repo_data.name.clone());
edit_branch.set(edit_repo_data.default_branch.clone());
edit_tracker_type.set(
edit_repo_data.tracker_type.as_ref().map(|t| t.to_string()).unwrap_or_default()
);
edit_tracker_owner.set(edit_repo_data.tracker_owner.clone().unwrap_or_default());
edit_tracker_repo.set(edit_repo_data.tracker_repo.clone().unwrap_or_default());
edit_tracker_token.set(String::new());
edit_webhook_secret.set(None);
edit_webhook_tracker.set(String::new());
edit_repo_id.set(Some(repo_id_edit.clone()));
// Fetch webhook config in background
let rid = repo_id_edit.clone();
spawn(async move {
if let Ok(cfg) = crate::infrastructure::repositories::fetch_webhook_config(rid).await {
edit_webhook_secret.set(cfg.webhook_secret);
edit_webhook_tracker.set(cfg.tracker_type);
}
});
},
Icon { icon: BsPencil, width: 16, height: 16 }
}
button {
class: if is_scanning { "btn btn-ghost btn-scanning" } else { "btn btn-ghost" },
title: "Trigger scan",
disabled: is_scanning,
onclick: move |_| {
let id = repo_id_scan.clone();
// Add to scanning set
let mut ids = scanning_ids();
ids.push(id.clone());
scanning_ids.set(ids);
spawn(async move {
match crate::infrastructure::repositories::trigger_repo_scan(id.clone()).await {
Ok(_) => {
toasts.push(ToastType::Success, "Scan triggered");
// Poll until scan completes
loop {
async_sleep_5s().await;
match crate::infrastructure::repositories::check_repo_scanning(id.clone()).await {
Ok(false) => break,
Ok(true) => continue,
Err(_) => break,
}
}
toasts.push(ToastType::Success, "Scan complete");
repos.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
// Remove from scanning set
let mut ids = scanning_ids();
ids.retain(|i| i != &id);
scanning_ids.set(ids);
});
},
if is_scanning {
span { class: "spinner" }
} else {
Icon { icon: BsPlayCircle, width: 16, height: 16 }
}
}
button {
class: "btn btn-ghost btn-ghost-danger",
title: "Delete repository",
onclick: move |_| {
confirm_delete.set(Some((repo_id_del.clone(), repo_name_del.clone())));
},
Icon { icon: BsTrash, width: 16, height: 16 }
}
}
}
}
}
}
}
}
}
Pagination {
current_page: page(),
total_pages: total_pages,
on_page_change: move |p| page.set(p),
}
}
// Inline graph explorer
if let Some(rid) = graph_repo_id() {
div { class: "card", style: "margin-top: 16px;",
div { class: "card-header", style: "display: flex; justify-content: space-between; align-items: center;",
span { "Code Graph" }
button {
class: "btn btn-sm btn-ghost",
title: "Close graph",
onclick: move |_| { graph_repo_id.set(None); },
Icon { icon: BsX, width: 18, height: 18 }
}
}
GraphExplorerInline { repo_id: rid }
}
}
}
},
Some(None) => rsx! {
div { class: "card", p { "Failed to load repositories." } }
},
None => rsx! {
div { class: "loading", "Loading repositories..." }
},
}
}
}
+9 -9
View File
@@ -28,9 +28,9 @@ pub fn SbomPage() -> Element {
let mut diff_repo_a = use_signal(String::new);
let mut diff_repo_b = use_signal(String::new);
// ── Targets for dropdowns ──
// ── Repos for dropdowns ──
let repos = use_resource(|| async {
crate::infrastructure::onboarding::fetch_targets()
crate::infrastructure::repositories::fetch_repositories(1)
.await
.ok()
});
@@ -114,14 +114,14 @@ pub fn SbomPage() -> Element {
select {
class: "sbom-filter-select",
onchange: move |e| { repo_filter.set(e.value()); page.set(1); },
option { value: "", "All Targets" }
option { value: "", "All Repositories" }
{
match &*repos.read() {
Some(Some(resp)) => rsx! {
for repo in &resp.data {
{
let id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
rsx! { option { value: "{id}", "{name}" } }
}
}
@@ -476,8 +476,8 @@ pub fn SbomPage() -> Element {
Some(Some(resp)) => rsx! {
for repo in &resp.data {
{
let id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
rsx! { option { value: "{id}", "{name}" } }
}
}
@@ -498,8 +498,8 @@ pub fn SbomPage() -> Element {
Some(Some(resp)) => rsx! {
for repo in &resp.data {
{
let id = repo.get("_id").and_then(|o| o.get("$oid")).and_then(|s| s.as_str()).unwrap_or_default().to_string();
let name = repo.get("name").and_then(|n| n.as_str()).unwrap_or_default().to_string();
let id = repo.id.as_ref().map(|id| id.to_hex()).unwrap_or_default();
let name = repo.name.clone();
rsx! { option { value: "{id}", "{name}" } }
}
}
-544
View File
@@ -1,544 +0,0 @@
//! Targets page — lists onboarded targets (the unified `OnboardedTarget`
//! records the wizard creates) and lets the user run a scan, inspect the
//! classification / applicable scans, or delete a target.
//!
//! Creation lives in the Onboard wizard (`/onboard`); this page is the
//! "where is my target, and what did the scan find" surface.
use dioxus::prelude::*;
use dioxus_free_icons::icons::bs_icons::*;
use dioxus_free_icons::Icon;
use crate::components::page_header::PageHeader;
use crate::components::toast::{ToastType, Toasts};
use crate::infrastructure::onboarding::{
delete_target, fetch_applicable_scans, fetch_targets, trigger_target_scan, update_target,
validate_artifact_ref, validate_target_name, ArtifactInputDto,
};
/// The nine target families (value, label) for the edit form's type selector.
const TARGET_TYPES: &[(&str, &str)] = &[
("web_app", "Web Application"),
("backend_service", "Backend / API"),
("desktop_app", "Desktop App"),
("android_app", "Android App"),
("ios_app", "iOS App"),
("firmware_bare_metal", "Firmware — bare metal"),
("firmware_rtos", "Firmware — RTOS"),
("embedded_linux_yocto", "Embedded Linux / Yocto"),
("plc_sps", "PLC / SPS"),
];
/// The artifact kinds (value, label) for the edit form.
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)"),
];
/// Prettify a snake_case target-type value into a human label.
fn pretty_type(v: &str) -> String {
match v {
"web_app" => "Web Application".into(),
"backend_service" => "Backend / API".into(),
"desktop_app" => "Desktop App".into(),
"android_app" => "Android App".into(),
"ios_app" => "iOS App".into(),
"firmware_bare_metal" => "Firmware — bare metal".into(),
"firmware_rtos" => "Firmware — RTOS".into(),
"embedded_linux_yocto" => "Embedded Linux / Yocto".into(),
"plc_sps" => "PLC / SPS".into(),
other => other.replace('_', " "),
}
}
fn str_at<'a>(v: &'a serde_json::Value, key: &str) -> &'a str {
v.get(key).and_then(|x| x.as_str()).unwrap_or("")
}
fn target_id(t: &serde_json::Value) -> String {
t.get("_id")
.and_then(|o| o.get("$oid"))
.and_then(|s| s.as_str())
.unwrap_or_default()
.to_string()
}
/// The applicable-scans matrix for one target, fetched on expand.
#[component]
fn TargetScans(id: String) -> Element {
let scan_id = id.clone();
let scans = use_resource(move || {
let id = scan_id.clone();
async move { fetch_applicable_scans(id).await.ok() }
});
let snapshot = scans.read().clone();
match &snapshot {
Some(Some(resp)) => {
let rows = resp.data.scans.clone();
let pentest = resp.data.pentest_supported;
rsx! {
div { style: "margin-top: 8px;",
if rows.is_empty() {
div { style: "opacity: 0.6;", "No scans available (no code / URL / firmware artifact present)." }
}
for s in rows {
{
let name = str_at(&s, "scan").to_string();
let rationale = str_at(&s, "rationale").to_string();
let blocked = s.get("blocked_reason").and_then(|b| b.as_str()).map(String::from);
let default_on = s.get("default_on").and_then(|b| b.as_bool()).unwrap_or(false);
let badge = 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: 4px 0;",
span { class: "{badge}", "{name}" }
span { style: "opacity: 0.8; font-size: 0.9em;", "{rationale}" }
if let Some(b) = blocked {
span { style: "opacity: 0.6; font-style: italic; font-size: 0.9em;", "— {b}" }
}
}
}
}
}
if pentest {
div { style: "margin-top: 6px; opacity: 0.75; font-size: 0.85em;",
"Active pentest is supported for this target type."
}
}
}
}
}
Some(None) => rsx! { div { style: "opacity: 0.6;", "Failed to load applicable scans." } },
None => rsx! { div { style: "opacity: 0.6;", "Loading scans..." } },
}
}
#[component]
pub fn TargetsPage() -> Element {
let mut toasts = use_context::<Toasts>();
let mut scanning_ids = use_signal(Vec::<String>::new);
let mut expanded_ids = use_signal(Vec::<String>::new);
let mut confirm_delete = use_signal(|| Option::<(String, String)>::None);
// Edit-target modal state.
let mut edit_id = use_signal(|| Option::<String>::None);
let mut edit_name = use_signal(String::new);
let mut edit_type = use_signal(String::new);
let mut edit_arts = use_signal(Vec::<ArtifactInputDto>::new);
let mut edit_saving = use_signal(|| false);
// In-modal "add artifact" mini-form.
let mut e_kind = use_signal(|| "git_repo".to_string());
let mut e_source = use_signal(String::new);
let mut e_branch = use_signal(|| "main".to_string());
let mut targets = use_resource(move || async move { fetch_targets().await.ok() });
rsx! {
PageHeader {
title: "Targets",
description: "Onboarded targets and what their scans found. Add new targets from Onboard.",
}
div { style: "margin-bottom: 16px; display: flex; gap: 8px;",
Link { to: crate::app::Route::OnboardingPage {}, class: "btn btn-primary",
"+ Onboard a target"
}
button {
class: "btn btn-secondary",
onclick: move |_| targets.restart(),
"Refresh"
}
}
// ── Delete confirmation ──
if let Some((del_id, del_name)) = confirm_delete() {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Delete Target" }
p { "Delete " strong { "{del_name}" } "?" }
p { class: "modal-warning",
"This permanently removes the target and its findings, SBOM entries, scan runs, and CVE alerts."
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| confirm_delete.set(None),
"Cancel"
}
button {
class: "btn btn-danger",
onclick: move |_| {
let id = del_id.clone();
let name = del_name.clone();
confirm_delete.set(None);
spawn(async move {
match delete_target(id).await {
Ok(_) => {
toasts.push(ToastType::Success, format!("{name} deleted"));
targets.restart();
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
});
},
"Delete"
}
}
}
}
}
// ── Edit target ──
if let Some(eid) = edit_id() {
{
let name_err = validate_target_name(&edit_name());
let e_source_err = if e_source().is_empty() {
None
} else {
validate_artifact_ref(&e_kind(), &e_source())
};
rsx! {
div { class: "modal-overlay",
div { class: "modal-dialog",
h3 { "Edit target" }
div { class: "form-group",
label { "Name" }
input {
r#type: "text",
value: "{edit_name}",
oninput: move |e| edit_name.set(e.value()),
}
if !edit_name().is_empty() {
if let Some(err) = name_err.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em;", "{err}" }
}
}
}
div { class: "form-group",
label { "Type" }
select {
value: "{edit_type}",
oninput: move |e| edit_type.set(e.value()),
for (v, l) in TARGET_TYPES.iter().copied() {
option { value: "{v}", "{l}" }
}
}
}
label { style: "font-weight: 600;", "Artifacts" }
for (i, a) in edit_arts().iter().enumerate() {
div { style: "display: flex; justify-content: space-between; align-items: center; padding: 4px 0;",
span { style: "font-size: 0.9em;",
span { style: "opacity: 0.7;", "{a.kind}: " }
span { style: "font-family: monospace;", "{a.source_ref}" }
}
button {
class: "btn btn-ghost btn-ghost-danger btn-sm",
onclick: move |_| { edit_arts.write().remove(i); },
"Remove"
}
}
}
div { style: "display: flex; gap: 8px; align-items: flex-end; margin-top: 8px;",
div { class: "form-group", style: "margin: 0;",
label { "Kind" }
select {
value: "{e_kind}",
oninput: move |e| e_kind.set(e.value()),
for (v, l) in ARTIFACT_KINDS.iter().copied() {
option { value: "{v}", "{l}" }
}
}
}
div { class: "form-group", style: "margin: 0; flex: 1;",
label { "Reference" }
input {
r#type: "text",
value: "{e_source}",
oninput: move |e| e_source.set(e.value()),
}
}
if e_kind() == "git_repo" {
div { class: "form-group", style: "margin: 0;",
label { "Branch" }
input {
r#type: "text",
value: "{e_branch}",
oninput: move |e| e_branch.set(e.value()),
}
}
}
button {
class: "btn btn-secondary",
disabled: e_source().trim().is_empty() || e_source_err.is_some(),
onclick: move |_| {
let kind = e_kind();
if !e_source().trim().is_empty()
&& validate_artifact_ref(&kind, &e_source()).is_none()
{
let branch = if kind == "git_repo" { Some(e_branch()) } else { None };
edit_arts.write().push(ArtifactInputDto {
kind,
source_ref: e_source(),
branch,
plc_format: None,
});
e_source.set(String::new());
}
},
"+ Add"
}
}
if let Some(err) = e_source_err.clone() {
div { style: "color: var(--danger, #d33); font-size: 0.85em;", "{err}" }
}
div { class: "modal-actions",
button {
class: "btn btn-secondary",
onclick: move |_| edit_id.set(None),
"Cancel"
}
button {
class: "btn btn-primary",
disabled: edit_saving() || name_err.is_some(),
onclick: move |_| {
let id = eid.clone();
let nm = edit_name();
let tt = edit_type();
let arts = edit_arts();
edit_saving.set(true);
spawn(async move {
match update_target(id, Some(nm), Some(tt), Some(arts)).await {
Ok(_) => {
toasts.push(ToastType::Success, "Target updated");
targets.restart();
edit_id.set(None);
}
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
edit_saving.set(false);
});
},
if edit_saving() { "Saving..." } else { "Save" }
}
}
}
}
}
}
}
{
let targets_snapshot = targets.read().clone();
match &targets_snapshot {
Some(Some(resp)) => {
let rows = resp.data.clone();
if rows.is_empty() {
rsx! {
div { class: "card", style: "padding: 24px; text-align: center;",
p { style: "opacity: 0.7;", "No targets yet." }
Link { to: crate::app::Route::OnboardingPage {}, class: "btn btn-primary",
"Onboard your first target"
}
}
}
} else {
rsx! {
div { class: "card",
div { class: "table-wrapper",
table {
thead {
tr {
th { "Name" }
th { "Type" }
th { "Detected" }
th { "Artifacts" }
th { "Findings" }
th { "Actions" }
}
}
tbody {
for t in rows {
{
let id = target_id(&t);
let name = str_at(&t, "name").to_string();
let ttype = pretty_type(str_at(&t, "target_type"));
let suggested = t
.get("classification")
.and_then(|c| c.get("suggested"))
.and_then(|s| s.as_str())
.map(pretty_type);
let artifacts = t
.get("artifacts")
.and_then(|a| a.as_array())
.cloned()
.unwrap_or_default();
let findings = t
.get("findings_count")
.and_then(|n| n.as_u64())
.unwrap_or(0);
let facts = t
.get("classification")
.and_then(|c| c.get("facts"))
.and_then(|f| f.as_array())
.cloned()
.unwrap_or_default();
let is_scanning = scanning_ids().contains(&id);
let is_expanded = expanded_ids().contains(&id);
let id_scan = id.clone();
let id_exp = id.clone();
let id_del = id.clone();
let id_edit = id.clone();
let name_del = name.clone();
let name_edit = name.clone();
let ttype_raw = str_at(&t, "target_type").to_string();
let artifacts_detail = artifacts.clone();
let artifacts_edit = artifacts.clone();
rsx! {
tr {
td { strong { "{name}" } }
td { "{ttype}" }
td {
if let Some(sug) = suggested.clone() {
span { class: "badge badge-success", "{sug}" }
} else {
span { style: "opacity: 0.5;", "" }
}
}
td { "{artifacts.len()}" }
td { "{findings}" }
td { style: "display: flex; gap: 4px;",
button {
class: "btn btn-ghost",
title: "Details",
onclick: move |_| {
let mut ids = expanded_ids();
if ids.contains(&id_exp) {
ids.retain(|i| i != &id_exp);
} else {
ids.push(id_exp.clone());
}
expanded_ids.set(ids);
},
Icon { icon: BsInfoCircle, width: 16, height: 16 }
}
button {
class: "btn btn-ghost",
title: "Edit target",
onclick: move |_| {
edit_name.set(name_edit.clone());
edit_type.set(ttype_raw.clone());
let arts: Vec<ArtifactInputDto> = artifacts_edit
.iter()
.map(|a| ArtifactInputDto {
kind: str_at(a, "kind").to_string(),
source_ref: str_at(a, "source_ref").to_string(),
branch: a
.get("git")
.and_then(|g| g.get("default_branch"))
.and_then(|b| b.as_str())
.map(String::from),
plc_format: None,
})
.collect();
edit_arts.set(arts);
e_source.set(String::new());
edit_id.set(Some(id_edit.clone()));
},
Icon { icon: BsPencil, width: 16, height: 16 }
}
button {
class: if is_scanning { "btn btn-ghost btn-scanning" } else { "btn btn-ghost" },
title: "Run scan",
disabled: is_scanning,
onclick: move |_| {
let id = id_scan.clone();
let mut ids = scanning_ids();
ids.push(id.clone());
scanning_ids.set(ids);
spawn(async move {
match trigger_target_scan(id.clone()).await {
Ok(_) => toasts.push(ToastType::Success, "Scan triggered — findings appear as it runs. Use Refresh."),
Err(e) => toasts.push(ToastType::Error, e.to_string()),
}
let mut ids = scanning_ids();
ids.retain(|i| i != &id);
scanning_ids.set(ids);
});
},
if is_scanning {
span { class: "spinner" }
} else {
Icon { icon: BsPlayCircle, width: 16, height: 16 }
}
}
button {
class: "btn btn-ghost btn-ghost-danger",
title: "Delete target",
onclick: move |_| {
confirm_delete.set(Some((id_del.clone(), name_del.clone())));
},
Icon { icon: BsTrash, width: 16, height: 16 }
}
}
}
if is_expanded {
tr {
td { colspan: "6",
div { style: "padding: 12px 8px;",
h4 { style: "margin: 0 0 6px;", "Artifacts" }
if artifacts_detail.is_empty() {
div { style: "opacity: 0.6;", "No artifacts." }
}
for a in artifacts_detail {
div { style: "font-size: 0.9em; padding: 2px 0;",
span { style: "opacity: 0.7;", "{str_at(&a, \"kind\")}: " }
span { style: "font-family: monospace;", "{str_at(&a, \"source_ref\")}" }
}
}
if !facts.is_empty() {
h4 { style: "margin: 12px 0 6px;", "Detected facts" }
for f in facts {
div { style: "font-size: 0.9em; padding: 2px 0;",
span { style: "font-family: monospace;", "{str_at(&f, \"key\")}={str_at(&f, \"value\")}" }
span { style: "opacity: 0.5;", " ({str_at(&f, \"source\")})" }
}
}
}
h4 { style: "margin: 12px 0 6px;", "Applicable scans" }
TargetScans { id: id.clone() }
}
}
}
}
}
}
}
}
}
}
}
}
}
}
Some(None) => rsx! {
div { class: "card", p { "Failed to load targets." } }
},
None => rsx! {
div { class: "loading", "Loading targets..." }
},
}
}
}
}
+1 -4
View File
@@ -4,7 +4,7 @@ version = "0.1.0"
edition = "2021"
[dependencies]
compliance-core = { workspace = true, features = ["mongodb", "axum"] }
compliance-core = { workspace = true, features = ["mongodb"] }
rmcp = { version = "0.16", features = ["server", "macros", "transport-io", "transport-streamable-http-server"] }
tokio = { workspace = true }
serde = { workspace = true }
@@ -19,6 +19,3 @@ bson = { version = "2", features = ["chrono-0_4"] }
schemars = "1.0"
axum = "0.8"
tower-http = { version = "0.6", features = ["cors"] }
sha2 = { workspace = true }
hex = { workspace = true }
dashmap = { workspace = true }
-129
View File
@@ -1,129 +0,0 @@
//! Bearer-token authentication for incoming MCP HTTP requests.
//!
//! LLM clients (Claude Desktop / Cursor / ChatGPT / etc.) can't run
//! Keycloak OIDC, so the MCP server uses opaque static tokens minted
//! per-tenant via the agent's `POST /api/v1/mcp-tokens` endpoint.
//!
//! Flow per request:
//! 1. Extract `Authorization: Bearer <token>`. Missing → 401.
//! 2. SHA-256 hash the token.
//! 3. Look up the hash in `<prefix>__admin.mcp_tokens`. Missing or
//! revoked → 401.
//! 4. Fire-and-forget update of `last_used_at` so the dashboard can
//! show staleness without blocking the handler.
//! 5. Stash the tenant_id in [`TENANT_ID`] (a `tokio::task_local`) so
//! the MCP tool handlers can read it without modifying rmcp's
//! handler signatures.
//!
//! The `task_local` is scoped around the inner service call via
//! [`bearer_auth`], so every handler invoked downstream sees the
//! tenant_id without us having to thread it through the macro-
//! generated tool router.
use axum::body::Body;
use axum::extract::{Request, State};
use axum::http::StatusCode;
use axum::middleware::Next;
use axum::response::{IntoResponse, Response};
use mongodb::bson::doc;
use sha2::{Digest, Sha256};
use crate::database::DatabasePool;
tokio::task_local! {
/// Tenant id resolved from the bearer for this request. Set by
/// [`bearer_auth`] before the inner service runs; read by the
/// MCP tool handlers via [`current_tenant_id`].
pub static TENANT_ID: String;
}
/// Mongo collection name in `<prefix>__admin`.
const COLLECTION: &str = "mcp_tokens";
/// Returns the tenant_id set by the auth middleware. `None` outside a
/// request scope (e.g. unit tests that bypass the middleware).
pub fn current_tenant_id() -> Option<String> {
TENANT_ID.try_with(|s| s.clone()).ok()
}
/// Axum middleware: validate bearer → set [`TENANT_ID`] → call inner.
pub async fn bearer_auth(
State(pool): State<DatabasePool>,
request: Request,
next: Next,
) -> Response {
let Some(token) = extract_bearer(&request) else {
return (StatusCode::UNAUTHORIZED, "Missing bearer token").into_response();
};
if !token.starts_with("mcpt_") {
return (StatusCode::UNAUTHORIZED, "Invalid token format").into_response();
}
let token_hash = sha256_hex(&token);
let col = pool.admin_db().collection::<TokenLookup>(COLLECTION);
let found = match col
.find_one(doc! { "token_hash": &token_hash, "revoked": false })
.await
{
Ok(Some(t)) => t,
Ok(None) => {
return (StatusCode::UNAUTHORIZED, "Invalid or revoked token").into_response();
}
Err(e) => {
tracing::error!("MCP token lookup failed: {e}");
return (StatusCode::INTERNAL_SERVER_ERROR, "Token lookup error").into_response();
}
};
// Fire-and-forget last_used_at update — never block the handler.
let col2 = pool.admin_db().collection::<TokenLookup>(COLLECTION);
let hash_for_update = token_hash.clone();
tokio::spawn(async move {
let _ = col2
.update_one(
doc! { "token_hash": &hash_for_update },
doc! { "$set": { "last_used_at": mongodb::bson::DateTime::now() } },
)
.await;
});
let tenant_id = found.tenant_id;
let inner = next.run(request);
TENANT_ID.scope(tenant_id, inner).await
}
/// Bare-bones projection — we don't need the whole `McpToken` here,
/// just enough to route and confirm validity.
#[derive(serde::Deserialize)]
struct TokenLookup {
tenant_id: String,
}
fn extract_bearer(req: &Request<Body>) -> Option<String> {
req.headers()
.get(axum::http::header::AUTHORIZATION)
.and_then(|v| v.to_str().ok())
.and_then(|s| s.strip_prefix("Bearer "))
.map(|s| s.trim().to_string())
.filter(|s| !s.is_empty())
}
fn sha256_hex(s: &str) -> String {
let mut h = Sha256::new();
h.update(s.as_bytes());
hex::encode(h.finalize())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn sha256_known_value() {
// python -c 'import hashlib; print(hashlib.sha256(b"mcpt_known").hexdigest())'
assert_eq!(
sha256_hex("mcpt_known"),
"27cf6cf678a44244106863c1c031be8e57b84c2b3019d742f755f8e7afa75dfd"
);
}
}
+7 -115
View File
@@ -1,127 +1,19 @@
//! Per-tenant Mongo broker for the MCP server.
//!
//! Mirror of the agent's `compliance_agent::database::DatabasePool` —
//! duplicated here rather than lifted into `compliance-core` to keep
//! this PR focused. If a third consumer ever needs it, lift then.
//!
//! Bearer tokens (validated by the auth middleware) carry a tenant_id
//! and the handler resolves the per-tenant database via
//! [`DatabasePool::for_tenant_id`]. The admin database
//! (`<db_prefix>__admin`) holds the cross-tenant `mcp_tokens`
//! collection that the middleware queries on every request.
use std::sync::Arc;
use dashmap::DashMap;
use mongodb::{bson::doc, Client, Collection};
use sha2::{Digest, Sha256};
use mongodb::{Client, Collection};
use compliance_core::models::*;
/// 63-byte Mongo db-name cap; same invariant as the agent's pool.
const MAX_DB_NAME_LEN: usize = 63;
/// 16-byte SHA-256 truncation, hex-encoded → 32 chars.
const HASH_HEX_LEN: usize = 32;
const MAX_PREFIX_LEN: usize = MAX_DB_NAME_LEN - 1 - HASH_HEX_LEN;
#[derive(Clone, Debug)]
pub struct DatabasePool {
client: Client,
db_prefix: String,
/// Tenants we've handed out a [`Database`] for. The MCP server
/// doesn't ensure indexes (the agent owns that side of the
/// schema), so the marker exists only to satisfy the parallel
/// shape — current code never reads it.
#[allow(dead_code)]
seen: Arc<DashMap<String, ()>>,
}
#[derive(Debug, thiserror::Error)]
pub enum DbError {
#[error("db_prefix '{prefix}' is {len} chars; max is {max} so the hash-fallback DB name fits Mongo's 63-byte cap")]
PrefixTooLong {
prefix: String,
len: usize,
max: usize,
},
#[error(transparent)]
Mongo(#[from] mongodb::error::Error),
}
impl DatabasePool {
pub async fn connect(uri: &str, db_prefix: &str) -> Result<Self, DbError> {
if db_prefix.len() > MAX_PREFIX_LEN {
return Err(DbError::PrefixTooLong {
prefix: db_prefix.to_string(),
len: db_prefix.len(),
max: MAX_PREFIX_LEN,
});
}
let client = Client::with_uri_str(uri).await?;
client
.database("admin")
.run_command(doc! { "ping": 1 })
.await?;
tracing::info!(
"MCP MongoDB cluster reachable; per-tenant pool ready (db prefix '{db_prefix}')"
);
Ok(Self {
client,
db_prefix: db_prefix.to_string(),
seen: Arc::new(DashMap::new()),
})
}
/// Read-only handle to the tenant's database. No indexes are
/// ensured here — the agent owns writes, MCP only reads.
pub fn for_tenant_id(&self, tenant_id: &str) -> Database {
let db_name = self.tenant_db_name(tenant_id);
self.seen.insert(tenant_id.to_string(), ());
Database::new(self.client.database(&db_name))
}
/// Cross-tenant admin DB — holds the `mcp_tokens` collection that
/// the auth middleware queries to map bearer → tenant_id.
pub fn admin_db(&self) -> mongodb::Database {
self.client.database(&format!("{}__admin", self.db_prefix))
}
pub fn tenant_db_name(&self, tenant_id: &str) -> String {
let sanitized = sanitize_tenant_id(tenant_id);
let natural = format!("{}_{}", self.db_prefix, sanitized);
if natural.len() <= MAX_DB_NAME_LEN {
natural
} else {
let mut h = Sha256::new();
h.update(tenant_id.as_bytes());
let digest = h.finalize();
let suffix = hex::encode(&digest[..HASH_HEX_LEN / 2]);
format!("{}_{}", self.db_prefix, suffix)
}
}
}
fn sanitize_tenant_id(tenant_id: &str) -> String {
tenant_id
.chars()
.map(|c| match c {
'/' | '\\' | '.' | '"' | '$' | ' ' | '\0' => '_',
c => c,
})
.collect()
}
/// Typed accessors for the MCP-readable collections in a tenant DB.
/// Matches the agent's `Database` shape but only exposes what the MCP
/// tool handlers actually need.
#[derive(Clone, Debug)]
pub struct Database {
inner: mongodb::Database,
}
impl Database {
pub(crate) fn new(inner: mongodb::Database) -> Self {
Self { inner }
pub async fn connect(uri: &str, db_name: &str) -> Result<Self, mongodb::error::Error> {
let client = Client::with_uri_str(uri).await?;
let db = client.database(db_name);
db.run_command(mongodb::bson::doc! { "ping": 1 }).await?;
tracing::info!("MCP server connected to MongoDB '{db_name}'");
Ok(Self { inner: db })
}
pub fn findings(&self) -> Collection<Finding> {
+10 -35
View File
@@ -1,11 +1,10 @@
mod auth;
mod database;
mod server;
mod tools;
use std::sync::Arc;
use database::DatabasePool;
use database::Database;
use rmcp::transport::{
streamable_http_server::session::local::LocalSessionManager, StreamableHttpServerConfig,
StreamableHttpService,
@@ -25,60 +24,36 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
let mongo_uri =
std::env::var("MONGODB_URI").unwrap_or_else(|_| "mongodb://localhost:27017".to_string());
// MONGODB_DATABASE is reused as the per-tenant DB-name prefix —
// same convention as the agent so `<prefix>__admin.mcp_tokens`
// and `<prefix>_<tenant_id>` line up across services.
let db_prefix =
let db_name =
std::env::var("MONGODB_DATABASE").unwrap_or_else(|_| "compliance_scanner".to_string());
let pool = DatabasePool::connect(&mongo_uri, &db_prefix).await?;
let db = Database::connect(&mongo_uri, &db_name).await?;
// HTTP transport: bind a small axum router with bearer-auth in
// front of the rmcp service. `/health` stays public for orca's
// container probe.
// If MCP_PORT is set, run as Streamable HTTP server; otherwise use stdio.
if let Ok(port_str) = std::env::var("MCP_PORT") {
let port: u16 = port_str.parse()?;
tracing::info!("Starting MCP server on HTTP port {port}");
let pool_for_factory = pool.clone();
let db_clone = db.clone();
let service = StreamableHttpService::new(
move || Ok(ComplianceMcpServer::new(pool_for_factory.clone())),
move || Ok(ComplianceMcpServer::new(db_clone.clone())),
Arc::new(LocalSessionManager::default()),
StreamableHttpServerConfig::default(),
);
let router = axum::Router::new()
.route("/health", axum::routing::get(|| async { "ok" }))
.nest_service(
"/mcp",
axum::Router::new().fallback_service(service).layer(
axum::middleware::from_fn_with_state(pool.clone(), auth::bearer_auth),
),
);
.nest_service("/mcp", service);
let listener = tokio::net::TcpListener::bind(("0.0.0.0", port)).await?;
tracing::info!("MCP HTTP server listening on 0.0.0.0:{port}");
axum::serve(listener, router).await?;
} else {
// stdio transport — used when run as a local MCP server next
// to the LLM client. There's no HTTP layer to do bearer auth,
// so we synthesize a tenant_id from STDIO_TENANT_ID for local
// development. NEVER use this in production.
tracing::info!("Starting MCP server on stdio");
let synth_tenant = std::env::var("STDIO_TENANT_ID").unwrap_or_else(|_| "dev".to_string());
tracing::warn!(
tenant_id = %synth_tenant,
"stdio transport — using synthetic tenant id; DO NOT use in production"
);
let server = ComplianceMcpServer::new(pool);
let server = ComplianceMcpServer::new(db);
let transport = rmcp::transport::stdio();
use rmcp::ServiceExt;
auth::TENANT_ID
.scope(synth_tenant, async {
let handle = server.serve(transport).await?;
handle.waiting().await?;
Ok::<_, Box<dyn std::error::Error>>(())
})
.await?;
let handle = server.serve(transport).await?;
handle.waiting().await?;
}
Ok(())
+17 -46
View File
@@ -2,37 +2,20 @@ use rmcp::{
handler::server::wrapper::Parameters, model::*, tool, tool_handler, tool_router, ServerHandler,
};
use crate::auth::current_tenant_id;
use crate::database::{Database, DatabasePool};
use crate::database::Database;
use crate::tools::{dast, findings, pentest, sbom};
pub struct ComplianceMcpServer {
pool: DatabasePool,
db: Database,
#[allow(dead_code)]
tool_router: rmcp::handler::server::router::tool::ToolRouter<Self>,
}
impl ComplianceMcpServer {
/// Resolve the per-tenant `Database` from the bearer-set
/// `task_local`. Every tool handler calls this; missing context
/// surfaces as `internal_error` because it means the auth
/// middleware was misconfigured (handler ran without scope).
fn tenant_db(&self) -> Result<Database, rmcp::ErrorData> {
let tenant_id = current_tenant_id().ok_or_else(|| {
rmcp::ErrorData::internal_error(
"no tenant context — bearer middleware not in chain".to_string(),
None,
)
})?;
Ok(self.pool.for_tenant_id(&tenant_id))
}
}
#[tool_router]
impl ComplianceMcpServer {
pub fn new(pool: DatabasePool) -> Self {
pub fn new(db: Database) -> Self {
Self {
pool,
db,
tool_router: Self::tool_router(),
}
}
@@ -46,8 +29,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<findings::ListFindingsParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
findings::list_findings(&db, params).await
findings::list_findings(&self.db, params).await
}
#[tool(description = "Get a single finding by its ID")]
@@ -55,8 +37,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<findings::GetFindingParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
findings::get_finding(&db, params).await
findings::get_finding(&self.db, params).await
}
#[tool(description = "Get a summary of findings counts grouped by severity and status")]
@@ -64,8 +45,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<findings::FindingsSummaryParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
findings::findings_summary(&db, params).await
findings::findings_summary(&self.db, params).await
}
// ── SBOM ──────────────────────────────────────────────
@@ -77,8 +57,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<sbom::ListSbomPackagesParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
sbom::list_sbom_packages(&db, params).await
sbom::list_sbom_packages(&self.db, params).await
}
#[tool(
@@ -88,8 +67,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<sbom::SbomVulnReportParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
sbom::sbom_vuln_report(&db, params).await
sbom::sbom_vuln_report(&self.db, params).await
}
// ── DAST ──────────────────────────────────────────────
@@ -101,8 +79,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<dast::ListDastFindingsParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
dast::list_dast_findings(&db, params).await
dast::list_dast_findings(&self.db, params).await
}
#[tool(description = "Get a summary of recent DAST scan runs and finding counts")]
@@ -110,8 +87,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<dast::DastScanSummaryParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
dast::dast_scan_summary(&db, params).await
dast::dast_scan_summary(&self.db, params).await
}
// ── Pentest ─────────────────────────────────────────────
@@ -123,8 +99,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<pentest::ListPentestSessionsParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
pentest::list_pentest_sessions(&db, params).await
pentest::list_pentest_sessions(&self.db, params).await
}
#[tool(description = "Get a single AI pentest session by its ID")]
@@ -132,8 +107,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<pentest::GetPentestSessionParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
pentest::get_pentest_session(&db, params).await
pentest::get_pentest_session(&self.db, params).await
}
#[tool(
@@ -143,8 +117,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<pentest::GetAttackChainParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
pentest::get_attack_chain(&db, params).await
pentest::get_attack_chain(&self.db, params).await
}
#[tool(description = "Get chat messages from a pentest session")]
@@ -152,8 +125,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<pentest::GetPentestMessagesParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
pentest::get_pentest_messages(&db, params).await
pentest::get_pentest_messages(&self.db, params).await
}
#[tool(
@@ -163,8 +135,7 @@ impl ComplianceMcpServer {
&self,
Parameters(params): Parameters<pentest::PentestStatsParams>,
) -> Result<CallToolResult, rmcp::ErrorData> {
let db = self.tenant_db()?;
pentest::pentest_stats(&db, params).await
pentest::pentest_stats(&self.db, params).await
}
}
@@ -178,7 +149,7 @@ impl ServerHandler for ComplianceMcpServer {
.build(),
server_info: Implementation::from_build_env(),
instructions: Some(
"Compliance Scanner MCP server. Query security findings, SBOM data, DAST results, and AI pentest sessions for your tenant."
"Compliance Scanner MCP server. Query security findings, SBOM data, DAST results, and AI pentest sessions."
.to_string(),
),
}
-19
View File
@@ -1,19 +0,0 @@
#!/usr/bin/env bash
# Seed the nix store on first start, then run the agent.
#
# The firmware-SBOM pipeline drives a real `nix` build (tramiton NixBackend).
# The image ships the store as a bootstrap tarball rather than baking /nix, so a
# persistent /nix volume (mounted empty on first deploy) gets populated once and
# then survives redeploys. Seeding is best-effort: if it fails, the agent still
# starts and firmware SBOMs fall back to analysis-only.
if [ ! -e /nix/store ]; then
echo "agent-entrypoint: seeding /nix store from image bootstrap..."
mkdir -p /nix
if tar -C / -xzf /opt/nix-bootstrap.tar.gz; then
echo "agent-entrypoint: /nix store seeded."
else
echo "agent-entrypoint: WARN nix seed failed; firmware SBOM will use analysis-only fallback."
fi
fi
exec compliance-agent "$@"