feat: deduplicate code review findings across LLM passes

Group findings by file, line proximity, and normalized title keywords,
keeping the highest-severity finding from each group and merging CWE info.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.env.example

@@ -37,3 +37,17 @@ GIT_CLONE_BASE_PATH=/tmp/compliance-scanner/repos
 # Dashboard
 DASHBOARD_PORT=8080
 AGENT_API_URL=http://localhost:3001
+
+# MCP Server
+MCP_ENDPOINT_URL=http://localhost:8090
+
+# Keycloak (required for authentication)
+KEYCLOAK_URL=http://localhost:8080
+KEYCLOAK_REALM=compliance
+KEYCLOAK_CLIENT_ID=compliance-dashboard
+REDIRECT_URI=http://localhost:8080/auth/callback
+APP_URL=http://localhost:8080
+
+# OpenTelemetry (optional - omit to disable)
+# OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
+# OTEL_SERVICE_NAME=compliance-agent

.gitea/workflows/ci.yml

@@ -2,11 +2,9 @@ name: CI
 
 on:
   push:
-    branches:
-      - "**"
-  pull_request:
     branches:
       - main
+  pull_request:
 
 env:
   CARGO_TERM_COLOR: always
@@ -23,13 +21,14 @@ concurrency:
 
 jobs:
   # ---------------------------------------------------------------------------
-  # Stage 1: Code quality checks (run in parallel)
+  # Stage 1: Lint, audit, and test (single job to share cargo cache)
   # ---------------------------------------------------------------------------
-  fmt:
+  check:
-    name: Format
+    name: Check
+    if: github.event_name == 'pull_request'
     runs-on: docker
     container:
-      image: rust:1.89-bookworm
+      image: rust:1.94-bookworm
     steps:
       - name: Checkout
         run: |
@@ -37,90 +36,161 @@ jobs:
           git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
           git fetch --depth=1 origin "${GITHUB_SHA}"
           git checkout FETCH_HEAD
-      - run: rustup component add rustfmt
+      - name: Install tools
-      # Format check does not compile, so sccache is not needed here.
-      - run: cargo fmt --all --check
-        env:
-          RUSTC_WRAPPER: ""
-
-  clippy:
-    name: Clippy
-    runs-on: docker
-    container:
-      image: rust:1.89-bookworm
-    steps:
-      - name: Checkout
-        run: |
-          git init
-          git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
-          git fetch --depth=1 origin "${GITHUB_SHA}"
-          git checkout FETCH_HEAD
-      - name: Install sccache
         run: |
+          rustup component add rustfmt clippy
           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
-      - run: rustup component add clippy
+          cargo install cargo-audit --locked
-      # Lint the agent (native only).
+        env:
+          RUSTC_WRAPPER: ""
+
+      # Format (no compilation needed)
+      - name: Format
+        run: cargo fmt --all --check
+        env:
+          RUSTC_WRAPPER: ""
+
+      # Clippy (compiles once, sccache reuses across feature sets)
       - name: Clippy (agent)
         run: cargo clippy -p compliance-agent -- -D warnings
-      # Lint the dashboard for both feature sets independently.
-      # sccache deduplicates shared crates between the two compilations.
       - name: Clippy (dashboard server)
         run: cargo clippy -p compliance-dashboard --features server --no-default-features -- -D warnings
       - name: Clippy (dashboard web)
         run: cargo clippy -p compliance-dashboard --features web --no-default-features -- -D warnings
+      - name: Clippy (mcp)
+        run: cargo clippy -p compliance-mcp -- -D warnings
+
+      # Security audit
+      - name: Security Audit
+        run: cargo audit
+        env:
+          RUSTC_WRAPPER: ""
+
+      # Tests (reuses compilation artifacts from clippy)
+      - name: Tests (core + agent)
+        run: cargo test -p compliance-core -p compliance-agent
+      - name: Tests (dashboard server)
+        run: cargo test -p compliance-dashboard --features server --no-default-features
+      - name: Tests (dashboard web)
+        run: cargo test -p compliance-dashboard --features web --no-default-features
+
       - name: Show sccache stats
         run: sccache --show-stats
         if: always()
 
-  audit:
+  # ---------------------------------------------------------------------------
-    name: Security Audit
+  # Stage 2: Deploy (only on main, after checks pass)
+  # Each service only deploys when its relevant files changed.
+  # ---------------------------------------------------------------------------
+  detect-changes:
+    name: Detect Changes
     runs-on: docker
     if: github.ref == 'refs/heads/main'
     container:
-      image: rust:1.89-bookworm
+      image: alpine:latest
+    outputs:
+      agent: ${{ steps.changes.outputs.agent }}
+      dashboard: ${{ steps.changes.outputs.dashboard }}
+      docs: ${{ steps.changes.outputs.docs }}
+      mcp: ${{ steps.changes.outputs.mcp }}
     steps:
+      - name: Install git
+        run: apk add --no-cache git
       - name: Checkout
         run: |
           git init
           git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
-          git fetch --depth=1 origin "${GITHUB_SHA}"
+          git fetch --depth=2 origin "${GITHUB_SHA}"
           git checkout FETCH_HEAD
-      - run: cargo install cargo-audit
+      - name: Detect changed paths
-        env:
+        id: changes
-          RUSTC_WRAPPER: ""
+        run: |
-      - run: cargo audit
+          CHANGED=$(git diff --name-only HEAD~1 HEAD 2>/dev/null || echo "")
-        env:
+          echo "Changed files:"
-          RUSTC_WRAPPER: ""
+          echo "$CHANGED"
 
-  # ---------------------------------------------------------------------------
+          # Agent: core libs, agent code, agent Dockerfile
-  # Stage 2: Tests (only after all quality checks pass)
+          if echo "$CHANGED" | grep -qE '^(compliance-core/|compliance-agent/|compliance-graph/|compliance-dast/|Dockerfile\.agent|Cargo\.(toml|lock))'; then
-  # ---------------------------------------------------------------------------
+            echo "agent=true" >> "$GITHUB_OUTPUT"
-  test:
+          else
-    name: Tests
+            echo "agent=false" >> "$GITHUB_OUTPUT"
+          fi
+
+          # Dashboard: core libs, dashboard code, dashboard Dockerfile, assets
+          if echo "$CHANGED" | grep -qE '^(compliance-core/|compliance-dashboard/|Dockerfile\.dashboard|Dioxus\.toml|assets/|bin/|Cargo\.(toml|lock))'; then
+            echo "dashboard=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "dashboard=false" >> "$GITHUB_OUTPUT"
+          fi
+
+          # Docs: docs folder, docs Dockerfile
+          if echo "$CHANGED" | grep -qE '^(docs/|Dockerfile\.docs)'; then
+            echo "docs=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "docs=false" >> "$GITHUB_OUTPUT"
+          fi
+
+          # MCP: core libs, mcp code, mcp Dockerfile
+          if echo "$CHANGED" | grep -qE '^(compliance-core/|compliance-mcp/|Dockerfile\.mcp|Cargo\.(toml|lock))'; then
+            echo "mcp=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "mcp=false" >> "$GITHUB_OUTPUT"
+          fi
+
+  deploy-agent:
+    name: Deploy Agent
     runs-on: docker
-    needs: [fmt, clippy, audit]
+    needs: [detect-changes]
+    if: needs.detect-changes.outputs.agent == 'true'
     container:
-      image: rust:1.89-bookworm
+      image: alpine:latest
     steps:
-      - name: Checkout
+      - name: Trigger Coolify deploy
         run: |
-          git init
+          apk add --no-cache curl
-          git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
+          curl -sf "${{ secrets.COOLIFY_WEBHOOK_AGENT }}" \
-          git fetch --depth=1 origin "${GITHUB_SHA}"
+            -H "Authorization: Bearer ${{ secrets.COOLIFY_TOKEN }}"
-          git checkout FETCH_HEAD
+
-      - name: Install sccache
+  deploy-dashboard:
+    name: Deploy Dashboard
+    runs-on: docker
+    needs: [detect-changes]
+    if: needs.detect-changes.outputs.dashboard == 'true'
+    container:
+      image: alpine:latest
+    steps:
+      - name: Trigger Coolify deploy
         run: |
-          curl -fsSL https://github.com/mozilla/sccache/releases/download/v0.9.1/sccache-v0.9.1-x86_64-unknown-linux-musl.tar.gz \
+          apk add --no-cache curl
-            | tar xz --strip-components=1 -C /usr/local/bin/ sccache-v0.9.1-x86_64-unknown-linux-musl/sccache
+          curl -sf "${{ secrets.COOLIFY_WEBHOOK_DASHBOARD }}" \
-          chmod +x /usr/local/bin/sccache
+            -H "Authorization: Bearer ${{ secrets.COOLIFY_TOKEN }}"
-      - name: Run tests (core + agent)
+
-        run: cargo test -p compliance-core -p compliance-agent
+  deploy-docs:
-      - name: Run tests (dashboard server)
+    name: Deploy Docs
-        run: cargo test -p compliance-dashboard --features server --no-default-features
+    runs-on: docker
-      - name: Run tests (dashboard web)
+    needs: [detect-changes]
-        run: cargo test -p compliance-dashboard --features web --no-default-features
+    if: needs.detect-changes.outputs.docs == 'true'
-      - name: Show sccache stats
+    container:
-        run: sccache --show-stats
+      image: alpine:latest
-        if: always()
+    steps:
+      - name: Trigger Coolify deploy
+        run: |
+          apk add --no-cache curl
+          curl -sf "${{ secrets.COOLIFY_WEBHOOK_DOCS }}" \
+            -H "Authorization: Bearer ${{ secrets.COOLIFY_TOKEN }}"
+
+  deploy-mcp:
+    name: Deploy MCP
+    runs-on: docker
+    needs: [detect-changes]
+    if: needs.detect-changes.outputs.mcp == 'true'
+    container:
+      image: alpine:latest
+    steps:
+      - name: Trigger Coolify deploy
+        run: |
+          apk add --no-cache curl
+          curl -sf "${{ secrets.COOLIFY_WEBHOOK_MCP }}" \
+            -H "Authorization: Bearer ${{ secrets.COOLIFY_TOKEN }}"

.gitignore

@@ -4,3 +4,6 @@
 *.swo
 *~
 .DS_Store
+.playwright-mcp/
+report-preview-full.png
+compliance-dashboard/attack-chain-final.html

Cargo.toml

@@ -5,6 +5,7 @@ members = [
     "compliance-dashboard",
     "compliance-graph",
     "compliance-dast",
+    "compliance-mcp",
 ]
 resolver = "2"
 
@@ -28,3 +29,7 @@ hex = "0.4"
 uuid = { version = "1", features = ["v4", "serde"] }
 secrecy = { version = "0.10", features = ["serde"] }
 regex = "1"
+zip = { version = "2", features = ["aes-crypto", "deflate"] }
+dashmap = "6"
+tokio-stream = { version = "0.1", features = ["sync"] }
+aes-gcm = "0.10"

Dockerfile.agent

@@ -1,17 +1,41 @@
-FROM rust:1.89-bookworm AS builder
+FROM rust:1.94-bookworm AS builder
 
 WORKDIR /app
 COPY . .
 RUN cargo build --release -p compliance-agent
 
 FROM debian:bookworm-slim
-RUN apt-get update && apt-get install -y ca-certificates libssl3 git curl && rm -rf /var/lib/apt/lists/*
+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/*
+
+# Install Cargo (minimal, for cargo metadata / cargo audit / generate-lockfile)
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable --profile minimal
+ENV PATH="/root/.cargo/bin:${PATH}"
+RUN cargo install cargo-audit
+
+# Install Composer for PHP dependency resolution
+RUN curl -sS https://getcomposer.org/installer | php -- --install-dir=/usr/local/bin --filename=composer
+
+# Install Bundler for Ruby dependency resolution
+RUN apt-get update && apt-get install -y ruby && rm -rf /var/lib/apt/lists/* && gem install bundler
 
 # Install syft for SBOM generation
 RUN curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b /usr/local/bin
 
+# Install gitleaks for secret detection
+RUN curl -sSfL https://github.com/gitleaks/gitleaks/releases/download/v8.21.2/gitleaks_8.21.2_linux_x64.tar.gz \
+    | tar -xz -C /usr/local/bin gitleaks
+
+# Install semgrep for static analysis
+RUN pip3 install --break-system-packages semgrep
+
+# Install ruff for Python linting
+RUN pip3 install --break-system-packages ruff
+
 COPY --from=builder /app/target/release/compliance-agent /usr/local/bin/compliance-agent
 
+# Ensure SSH key directory exists
+RUN mkdir -p /data/compliance-scanner/ssh
+
 EXPOSE 3001 3002
 
 ENTRYPOINT ["compliance-agent"]

Dockerfile.dashboard

@@ -1,9 +1,12 @@
-FROM rust:1.89-bookworm AS builder
+FROM rust:1.94-bookworm AS builder
 
 RUN cargo install dioxus-cli --version 0.7.3
 
+ARG DOCS_URL=/docs
+
 WORKDIR /app
 COPY . .
+ENV DOCS_URL=${DOCS_URL}
 RUN dx build --release --package compliance-dashboard
 
 FROM debian:bookworm-slim
@@ -13,6 +16,7 @@ WORKDIR /app
 COPY --from=builder /app/target/dx/compliance-dashboard/release/web/compliance-dashboard /app/compliance-dashboard
 COPY --from=builder /app/target/dx/compliance-dashboard/release/web/public /app/public
 
+ENV IP=0.0.0.0
 EXPOSE 8080
 
 ENTRYPOINT ["./compliance-dashboard"]

Dockerfile.docs

@@ -0,0 +1,14 @@
+FROM node:22-alpine AS builder
+
+WORKDIR /app
+COPY docs/package.json docs/package-lock.json ./
+RUN npm ci
+
+COPY docs/ .
+RUN npm run build
+
+FROM nginx:alpine
+RUN rm /etc/nginx/conf.d/default.conf
+COPY docs/nginx.conf /etc/nginx/conf.d/default.conf
+COPY --from=builder /app/.vitepress/dist /usr/share/nginx/html
+EXPOSE 80

Dockerfile.mcp

@@ -0,0 +1,16 @@
+FROM rust:1.94-bookworm AS builder
+
+WORKDIR /app
+COPY . .
+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/*
+
+COPY --from=builder /app/target/release/compliance-mcp /usr/local/bin/compliance-mcp
+
+EXPOSE 8090
+
+ENV MCP_PORT=8090
+
+ENTRYPOINT ["compliance-mcp"]

README.md

@@ -9,7 +9,7 @@
 </p>
 
 <p align="center">
-  <a href="https://www.rust-lang.org/"><img src="https://img.shields.io/badge/Rust-1.89-orange?logo=rust&logoColor=white" alt="Rust" /></a>
+  <a href="https://www.rust-lang.org/"><img src="https://img.shields.io/badge/Rust-1.94-orange?logo=rust&logoColor=white" alt="Rust" /></a>
   <a href="https://dioxuslabs.com/"><img src="https://img.shields.io/badge/Dioxus-0.7-blue?logo=webassembly&logoColor=white" alt="Dioxus" /></a>
   <a href="https://www.mongodb.com/"><img src="https://img.shields.io/badge/MongoDB-8.0-47A248?logo=mongodb&logoColor=white" alt="MongoDB" /></a>
   <a href="https://axum.rs/"><img src="https://img.shields.io/badge/Axum-0.8-4A4A55?logo=rust&logoColor=white" alt="Axum" /></a>
@@ -94,7 +94,7 @@ Compliance Scanner is an autonomous agent that continuously monitors git reposit
 
 ### Prerequisites
 
-- Rust 1.89+
+- Rust 1.94+
 - [Dioxus CLI](https://dioxuslabs.com/learn/0.7/getting_started) (`dx`)
 - MongoDB
 - Docker & Docker Compose (optional)

assets/main.css

@@ -300,6 +300,84 @@ tr:hover {
     color: var(--text-secondary);
 }
 
+/* Sidebar User Section */
+.sidebar-user {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    padding: 12px 14px;
+    margin: 8px;
+    border-top: 1px solid var(--border);
+    padding-top: 16px;
+}
+
+.sidebar-user-collapsed {
+    flex-direction: column;
+    gap: 8px;
+    padding: 12px 4px;
+    margin: 8px 4px;
+}
+
+.user-avatar {
+    width: 34px;
+    height: 34px;
+    border-radius: 10px;
+    background: linear-gradient(135deg, rgba(56, 189, 248, 0.2), rgba(56, 189, 248, 0.08));
+    border: 1px solid rgba(56, 189, 248, 0.15);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    flex-shrink: 0;
+}
+
+.avatar-initials {
+    font-size: 13px;
+    font-weight: 700;
+    color: var(--accent);
+    line-height: 1;
+}
+
+.avatar-img {
+    width: 100%;
+    height: 100%;
+    border-radius: 10px;
+    object-fit: cover;
+}
+
+.user-name {
+    flex: 1;
+    font-size: 13px;
+    font-weight: 500;
+    color: var(--text-primary);
+    white-space: nowrap;
+    overflow: hidden;
+    text-overflow: ellipsis;
+    min-width: 0;
+}
+
+.logout-btn {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    width: 32px;
+    height: 32px;
+    border-radius: 8px;
+    color: var(--text-secondary);
+    text-decoration: none;
+    flex-shrink: 0;
+    transition: all 0.15s;
+}
+
+.logout-btn:hover {
+    background: rgba(239, 68, 68, 0.12);
+    color: #fca5a5;
+}
+
+.logout-btn-collapsed {
+    width: 34px;
+    height: 34px;
+}
+
 @media (max-width: 768px) {
     .sidebar {
         transform: translateX(-100%);
@@ -313,3 +391,218 @@ tr:hover {
         padding: 16px;
     }
 }
+
+
+/* ── Utility classes ────────────────────────────────────── */
+
+.mb-3 { margin-bottom: 12px; }
+.mb-4 { margin-bottom: 16px; }
+.text-secondary { color: var(--text-secondary); }
+
+.btn-sm {
+    padding: 4px 10px;
+    font-size: 12px;
+}
+
+.btn-danger {
+    background: var(--danger);
+    color: #fff;
+}
+.btn-danger:hover {
+    background: #dc2626;
+}
+
+.btn-secondary {
+    background: var(--bg-secondary);
+    color: var(--text-primary);
+    border: 1px solid var(--border);
+}
+.btn-secondary:hover {
+    background: var(--bg-primary);
+}
+
+/* ── Modal ──────────────────────────────────────────────── */
+
+.modal-overlay {
+    position: fixed;
+    inset: 0;
+    background: rgba(0, 0, 0, 0.6);
+    backdrop-filter: blur(4px);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    z-index: 1000;
+}
+
+.modal-dialog {
+    background: var(--bg-secondary);
+    border: 1px solid var(--border);
+    border-radius: 12px;
+    padding: 24px;
+    max-width: 440px;
+    width: 90%;
+    max-height: 85vh;
+    overflow-y: auto;
+}
+
+.modal-dialog h3 {
+    margin-bottom: 12px;
+}
+
+.modal-dialog p {
+    margin-bottom: 8px;
+    font-size: 14px;
+    color: var(--text-secondary);
+}
+
+.modal-warning {
+    color: var(--warning) !important;
+    font-size: 13px !important;
+}
+
+.modal-actions {
+    display: flex;
+    gap: 8px;
+    justify-content: flex-end;
+    margin-top: 16px;
+}
+
+/* ── MCP Servers ────────────────────────────────────────── */
+
+.mcp-server-card {
+    padding: 20px;
+}
+
+.mcp-server-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: flex-start;
+    margin-bottom: 12px;
+}
+
+.mcp-server-title {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+}
+
+.mcp-server-title h3 {
+    font-size: 16px;
+    font-weight: 600;
+    margin: 0;
+}
+
+.mcp-server-actions {
+    display: flex;
+    gap: 6px;
+}
+
+.mcp-status {
+    display: inline-flex;
+    align-items: center;
+    padding: 2px 10px;
+    border-radius: 20px;
+    font-size: 11px;
+    font-weight: 600;
+    text-transform: uppercase;
+    letter-spacing: 0.5px;
+}
+
+.mcp-status-running {
+    background: rgba(34, 197, 94, 0.15);
+    color: var(--success);
+}
+
+.mcp-status-stopped {
+    background: rgba(148, 163, 184, 0.15);
+    color: var(--text-secondary);
+}
+
+.mcp-status-error {
+    background: rgba(239, 68, 68, 0.15);
+    color: var(--danger);
+}
+
+.mcp-config-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fill, minmax(200px, 1fr));
+    gap: 12px;
+    margin-bottom: 16px;
+}
+
+.mcp-config-item {
+    display: flex;
+    flex-direction: column;
+    gap: 4px;
+}
+
+.mcp-config-label {
+    font-size: 11px;
+    font-weight: 600;
+    text-transform: uppercase;
+    letter-spacing: 0.5px;
+    color: var(--text-secondary);
+}
+
+.mcp-config-value {
+    font-size: 13px;
+    color: var(--text-primary);
+    word-break: break-all;
+}
+
+.mcp-form-grid {
+    display: grid;
+    grid-template-columns: 1fr 1fr;
+    gap: 0 16px;
+}
+
+.mcp-tools-section {
+    margin-bottom: 16px;
+}
+
+.mcp-tools-list {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 6px;
+    margin-top: 6px;
+}
+
+.mcp-tool-badge {
+    display: inline-block;
+    padding: 3px 10px;
+    background: rgba(56, 189, 248, 0.1);
+    border: 1px solid rgba(56, 189, 248, 0.2);
+    border-radius: 6px;
+    font-size: 12px;
+    font-family: 'JetBrains Mono', monospace;
+    color: var(--accent);
+}
+
+.mcp-token-section {
+    margin-bottom: 12px;
+}
+
+.mcp-token-row {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    margin-top: 6px;
+}
+
+.mcp-token-value {
+    flex: 1;
+    padding: 6px 10px;
+    background: var(--bg-primary);
+    border: 1px solid var(--border);
+    border-radius: 6px;
+    font-size: 12px;
+    font-family: 'JetBrains Mono', monospace;
+    color: var(--text-secondary);
+    word-break: break-all;
+}
+
+.mcp-meta {
+    padding-top: 12px;
+    border-top: 1px solid var(--border);
+    font-size: 12px;
+}

bin/main.rs

@@ -2,10 +2,9 @@
 
 #[allow(clippy::expect_used)]
 fn main() {
-    dioxus_logger::init(tracing::Level::DEBUG).expect("Failed to init logger");
-
     #[cfg(feature = "web")]
     {
+        dioxus_logger::init(tracing::Level::DEBUG).expect("Failed to init logger");
         dioxus::web::launch::launch_cfg(
             compliance_dashboard::App,
             dioxus::web::Config::new().hydrate(true),
@@ -14,6 +13,9 @@ fn main() {
 
     #[cfg(feature = "server")]
     {
+        dotenvy::dotenv().ok();
+        let _telemetry_guard = compliance_core::telemetry::init_telemetry("compliance-dashboard");
+
         compliance_dashboard::infrastructure::server_start(compliance_dashboard::App)
             .map_err(|e| {
                 tracing::error!("Unable to start server: {e}");

compliance-agent/Cargo.toml

@@ -7,7 +7,7 @@ edition = "2021"
 workspace = true
 
 [dependencies]
-compliance-core = { workspace = true, features = ["mongodb"] }
+compliance-core = { workspace = true, features = ["mongodb", "telemetry"] }
 compliance-graph = { path = "../compliance-graph" }
 compliance-dast = { path = "../compliance-dast" }
 serde = { workspace = true }
@@ -35,3 +35,10 @@ walkdir = "2"
 base64 = "0.22"
 urlencoding = "2"
 futures-util = "0.3"
+jsonwebtoken = "9"
+zip = { workspace = true }
+aes-gcm = { workspace = true }
+tokio-tungstenite = { version = "0.26", features = ["rustls-tls-webpki-roots"] }
+futures-core = "0.3"
+dashmap = { workspace = true }
+tokio-stream = { workspace = true }

compliance-agent/src/agent.rs

@@ -1,17 +1,30 @@
 use std::sync::Arc;
 
+use dashmap::DashMap;
+use tokio::sync::{broadcast, watch, Semaphore};
+
+use compliance_core::models::pentest::PentestEvent;
 use compliance_core::AgentConfig;
 
 use crate::database::Database;
 use crate::llm::LlmClient;
 use crate::pipeline::orchestrator::PipelineOrchestrator;
 
+/// Default maximum concurrent pentest sessions.
+const DEFAULT_MAX_CONCURRENT_SESSIONS: usize = 5;
+
 #[derive(Clone)]
 pub struct ComplianceAgent {
     pub config: AgentConfig,
     pub db: Database,
     pub llm: Arc<LlmClient>,
     pub http: reqwest::Client,
+    /// Per-session broadcast senders for SSE streaming.
+    pub session_streams: Arc<DashMap<String, broadcast::Sender<PentestEvent>>>,
+    /// Per-session pause controls (true = paused).
+    pub session_pause: Arc<DashMap<String, watch::Sender<bool>>>,
+    /// Semaphore limiting concurrent pentest sessions.
+    pub session_semaphore: Arc<Semaphore>,
 }
 
 impl ComplianceAgent {
@@ -27,6 +40,9 @@ impl ComplianceAgent {
             db,
             llm,
             http: reqwest::Client::new(),
+            session_streams: Arc::new(DashMap::new()),
+            session_pause: Arc::new(DashMap::new()),
+            session_semaphore: Arc::new(Semaphore::new(DEFAULT_MAX_CONCURRENT_SESSIONS)),
         }
     }
 
@@ -43,4 +59,85 @@ impl ComplianceAgent {
         );
         orchestrator.run(repo_id, trigger).await
     }
+
+    /// Run a PR review: scan the diff and post review comments.
+    pub async fn run_pr_review(
+        &self,
+        repo_id: &str,
+        pr_number: u64,
+        base_sha: &str,
+        head_sha: &str,
+    ) -> Result<(), crate::error::AgentError> {
+        let repo = self
+            .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!("Repository {repo_id} not found"))
+            })?;
+
+        let orchestrator = PipelineOrchestrator::new(
+            self.config.clone(),
+            self.db.clone(),
+            self.llm.clone(),
+            self.http.clone(),
+        );
+        orchestrator
+            .run_pr_review(&repo, repo_id, pr_number, base_sha, head_sha)
+            .await
+    }
+
+    // ── Session stream management ──────────────────────────────────
+
+    /// Register a broadcast sender for a session. Returns the sender.
+    pub fn register_session_stream(&self, session_id: &str) -> broadcast::Sender<PentestEvent> {
+        let (tx, _) = broadcast::channel(256);
+        self.session_streams
+            .insert(session_id.to_string(), tx.clone());
+        tx
+    }
+
+    /// Subscribe to a session's broadcast stream.
+    pub fn subscribe_session(&self, session_id: &str) -> Option<broadcast::Receiver<PentestEvent>> {
+        self.session_streams
+            .get(session_id)
+            .map(|tx| tx.subscribe())
+    }
+
+    // ── Session pause/resume management ────────────────────────────
+
+    /// Register a pause control for a session. Returns the watch receiver.
+    pub fn register_pause_control(&self, session_id: &str) -> watch::Receiver<bool> {
+        let (tx, rx) = watch::channel(false);
+        self.session_pause.insert(session_id.to_string(), tx);
+        rx
+    }
+
+    /// Pause a session.
+    pub fn pause_session(&self, session_id: &str) -> bool {
+        if let Some(tx) = self.session_pause.get(session_id) {
+            tx.send(true).is_ok()
+        } else {
+            false
+        }
+    }
+
+    /// Resume a session.
+    pub fn resume_session(&self, session_id: &str) -> bool {
+        if let Some(tx) = self.session_pause.get(session_id) {
+            tx.send(false).is_ok()
+        } else {
+            false
+        }
+    }
+
+    /// Clean up all per-session resources.
+    pub fn cleanup_session(&self, session_id: &str) {
+        self.session_streams.remove(session_id);
+        self.session_pause.remove(session_id);
+    }
 }

compliance-agent/src/api/auth_middleware.rs

@@ -0,0 +1,113 @@
+use std::sync::Arc;
+
+use axum::{
+    extract::Request,
+    middleware::Next,
+    response::{IntoResponse, Response},
+};
+use jsonwebtoken::{decode, decode_header, jwk::JwkSet, DecodingKey, Validation};
+use reqwest::StatusCode;
+use serde::Deserialize;
+use tokio::sync::RwLock;
+
+/// Cached JWKS from Keycloak for token validation.
+#[derive(Clone)]
+pub struct JwksState {
+    pub jwks: Arc<RwLock<Option<JwkSet>>>,
+    pub jwks_url: String,
+}
+
+#[derive(Debug, Deserialize)]
+struct Claims {
+    #[allow(dead_code)]
+    sub: String,
+}
+
+const PUBLIC_ENDPOINTS: &[&str] = &["/api/v1/health"];
+
+/// Middleware that validates Bearer JWT tokens against Keycloak's JWKS.
+///
+/// Skips validation for health check endpoints.
+/// If `JwksState` is not present as an extension (keycloak not configured),
+/// all requests pass through.
+pub async fn require_jwt_auth(request: Request, next: Next) -> Response {
+    let path = request.uri().path();
+
+    if PUBLIC_ENDPOINTS.contains(&path) {
+        return next.run(request).await;
+    }
+
+    let jwks_state = match request.extensions().get::<JwksState>() {
+        Some(s) => s.clone(),
+        None => return next.run(request).await,
+    };
+
+    let auth_header = match request.headers().get("authorization") {
+        Some(h) => h,
+        None => return (StatusCode::UNAUTHORIZED, "Missing authorization header").into_response(),
+    };
+
+    let token = match auth_header.to_str() {
+        Ok(s) if s.starts_with("Bearer ") => &s[7..],
+        _ => return (StatusCode::UNAUTHORIZED, "Invalid authorization header").into_response(),
+    };
+
+    match validate_token(token, &jwks_state).await {
+        Ok(()) => next.run(request).await,
+        Err(e) => {
+            tracing::warn!("JWT validation failed: {e}");
+            (StatusCode::UNAUTHORIZED, "Invalid token").into_response()
+        }
+    }
+}
+
+async fn validate_token(token: &str, state: &JwksState) -> Result<(), String> {
+    let header = decode_header(token).map_err(|e| format!("failed to decode JWT header: {e}"))?;
+
+    let kid = header
+        .kid
+        .ok_or_else(|| "JWT missing kid header".to_string())?;
+
+    let jwks = fetch_or_get_jwks(state).await?;
+
+    let jwk = jwks
+        .keys
+        .iter()
+        .find(|k| k.common.key_id.as_deref() == Some(&kid))
+        .ok_or_else(|| "no matching key found in JWKS".to_string())?;
+
+    let decoding_key =
+        DecodingKey::from_jwk(jwk).map_err(|e| format!("failed to create decoding key: {e}"))?;
+
+    let mut validation = Validation::new(header.alg);
+    validation.validate_exp = true;
+    validation.validate_aud = false;
+
+    decode::<Claims>(token, &decoding_key, &validation)
+        .map_err(|e| format!("token validation failed: {e}"))?;
+
+    Ok(())
+}
+
+async fn fetch_or_get_jwks(state: &JwksState) -> Result<JwkSet, String> {
+    {
+        let cached = state.jwks.read().await;
+        if let Some(ref jwks) = *cached {
+            return Ok(jwks.clone());
+        }
+    }
+
+    let resp = reqwest::get(&state.jwks_url)
+        .await
+        .map_err(|e| format!("failed to fetch JWKS: {e}"))?;
+
+    let jwks: JwkSet = resp
+        .json()
+        .await
+        .map_err(|e| format!("failed to parse JWKS: {e}"))?;
+
+    let mut cached = state.jwks.write().await;
+    *cached = Some(jwks.clone());
+
+    Ok(jwks)
+}

compliance-agent/src/api/handlers/chat.rs

@@ -17,6 +17,7 @@ use super::ApiResponse;
 type AgentExt = Extension<Arc<ComplianceAgent>>;
 
 /// POST /api/v1/chat/:repo_id — Send a chat message with RAG context
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
 pub async fn chat(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,
@@ -126,6 +127,7 @@ pub async fn chat(
 }
 
 /// POST /api/v1/chat/:repo_id/build-embeddings — Trigger embedding build
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
 pub async fn build_embeddings(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,
@@ -187,7 +189,13 @@ pub async fn build_embeddings(
             }
         };
 
-        let git_ops = crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path);
+        let creds = crate::pipeline::git::RepoCredentials {
+            ssh_key_path: Some(agent_clone.config.ssh_key_path.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(&repo.git_url, &repo.name) {
             Ok(p) => p,
             Err(e) => {
@@ -220,6 +228,7 @@ pub async fn build_embeddings(
 }
 
 /// GET /api/v1/chat/:repo_id/status — Get latest embedding build status
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
 pub async fn embedding_status(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,

compliance-agent/src/api/handlers/dast.rs

@@ -42,6 +42,7 @@ fn default_rate_limit() -> u32 {
 }
 
 /// GET /api/v1/dast/targets — List DAST targets
+#[tracing::instrument(skip_all)]
 pub async fn list_targets(
     Extension(agent): AgentExt,
     Query(params): Query<PaginationParams>,
@@ -62,7 +63,10 @@ pub async fn list_targets(
         .await
     {
         Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
+        Err(e) => {
+            tracing::warn!("Failed to fetch DAST targets: {e}");
+            Vec::new()
+        }
     };
 
     Ok(Json(ApiResponse {
@@ -73,6 +77,7 @@ pub async fn list_targets(
 }
 
 /// POST /api/v1/dast/targets — Add a new DAST target
+#[tracing::instrument(skip_all)]
 pub async fn add_target(
     Extension(agent): AgentExt,
     Json(req): Json<AddTargetRequest>,
@@ -99,6 +104,7 @@ pub async fn add_target(
 }
 
 /// POST /api/v1/dast/targets/:id/scan — Trigger DAST scan
+#[tracing::instrument(skip_all, fields(target_id = %id))]
 pub async fn trigger_scan(
     Extension(agent): AgentExt,
     Path(id): Path<String>,
@@ -138,6 +144,7 @@ pub async fn trigger_scan(
 }
 
 /// GET /api/v1/dast/scan-runs — List DAST scan runs
+#[tracing::instrument(skip_all)]
 pub async fn list_scan_runs(
     Extension(agent): AgentExt,
     Query(params): Query<PaginationParams>,
@@ -159,7 +166,10 @@ pub async fn list_scan_runs(
         .await
     {
         Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
+        Err(e) => {
+            tracing::warn!("Failed to fetch DAST scan runs: {e}");
+            Vec::new()
+        }
     };
 
     Ok(Json(ApiResponse {
@@ -170,6 +180,7 @@ pub async fn list_scan_runs(
 }
 
 /// GET /api/v1/dast/findings — List DAST findings
+#[tracing::instrument(skip_all)]
 pub async fn list_findings(
     Extension(agent): AgentExt,
     Query(params): Query<PaginationParams>,
@@ -191,7 +202,10 @@ pub async fn list_findings(
         .await
     {
         Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
+        Err(e) => {
+            tracing::warn!("Failed to fetch DAST findings: {e}");
+            Vec::new()
+        }
     };
 
     Ok(Json(ApiResponse {
@@ -202,6 +216,7 @@ pub async fn list_findings(
 }
 
 /// GET /api/v1/dast/findings/:id — Finding detail with evidence
+#[tracing::instrument(skip_all, fields(finding_id = %id))]
 pub async fn get_finding(
     Extension(agent): AgentExt,
     Path(id): Path<String>,

compliance-agent/src/api/handlers/dto.rs

@@ -0,0 +1,481 @@
+use compliance_core::models::TrackerType;
+use serde::{Deserialize, Serialize};
+
+use compliance_core::models::ScanRun;
+
+#[derive(Deserialize)]
+pub struct PaginationParams {
+    #[serde(default = "default_page")]
+    pub page: u64,
+    #[serde(default = "default_limit")]
+    pub limit: i64,
+}
+
+pub(crate) fn default_page() -> u64 {
+    1
+}
+pub(crate) fn default_limit() -> i64 {
+    50
+}
+
+#[derive(Deserialize)]
+pub struct FindingsFilter {
+    #[serde(default)]
+    pub repo_id: Option<String>,
+    #[serde(default)]
+    pub severity: Option<String>,
+    #[serde(default)]
+    pub scan_type: Option<String>,
+    #[serde(default)]
+    pub status: Option<String>,
+    #[serde(default)]
+    pub q: Option<String>,
+    #[serde(default)]
+    pub sort_by: Option<String>,
+    #[serde(default)]
+    pub sort_order: Option<String>,
+    #[serde(default = "default_page")]
+    pub page: u64,
+    #[serde(default = "default_limit")]
+    pub limit: i64,
+}
+
+#[derive(Serialize)]
+pub struct ApiResponse<T: Serialize> {
+    pub data: T,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub total: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub page: Option<u64>,
+}
+
+#[derive(Serialize)]
+pub struct OverviewStats {
+    pub total_repositories: u64,
+    pub total_findings: u64,
+    pub critical_findings: u64,
+    pub high_findings: u64,
+    pub medium_findings: u64,
+    pub low_findings: u64,
+    pub total_sbom_entries: u64,
+    pub total_cve_alerts: u64,
+    pub total_issues: u64,
+    pub recent_scans: Vec<ScanRun>,
+}
+
+#[derive(Deserialize)]
+pub struct AddRepositoryRequest {
+    pub name: String,
+    pub git_url: String,
+    #[serde(default = "default_branch")]
+    pub default_branch: String,
+    pub auth_token: Option<String>,
+    pub auth_username: Option<String>,
+    pub tracker_type: Option<TrackerType>,
+    pub tracker_owner: Option<String>,
+    pub tracker_repo: Option<String>,
+    pub tracker_token: Option<String>,
+    pub scan_schedule: Option<String>,
+}
+
+#[derive(Deserialize)]
+pub struct UpdateRepositoryRequest {
+    pub name: Option<String>,
+    pub default_branch: Option<String>,
+    pub auth_token: Option<String>,
+    pub auth_username: Option<String>,
+    pub tracker_type: Option<TrackerType>,
+    pub tracker_owner: Option<String>,
+    pub tracker_repo: Option<String>,
+    pub tracker_token: Option<String>,
+    pub scan_schedule: Option<String>,
+}
+
+fn default_branch() -> String {
+    "main".to_string()
+}
+
+#[derive(Deserialize)]
+pub struct UpdateStatusRequest {
+    pub status: String,
+}
+
+#[derive(Deserialize)]
+pub struct BulkUpdateStatusRequest {
+    pub ids: Vec<String>,
+    pub status: String,
+}
+
+#[derive(Deserialize)]
+pub struct UpdateFeedbackRequest {
+    pub feedback: String,
+}
+
+#[derive(Deserialize)]
+pub struct SbomFilter {
+    #[serde(default)]
+    pub repo_id: Option<String>,
+    #[serde(default)]
+    pub package_manager: Option<String>,
+    #[serde(default)]
+    pub q: Option<String>,
+    #[serde(default)]
+    pub has_vulns: Option<bool>,
+    #[serde(default)]
+    pub license: Option<String>,
+    #[serde(default = "default_page")]
+    pub page: u64,
+    #[serde(default = "default_limit")]
+    pub limit: i64,
+}
+
+#[derive(Deserialize)]
+pub struct SbomExportParams {
+    pub repo_id: String,
+    #[serde(default = "default_export_format")]
+    pub format: String,
+}
+
+fn default_export_format() -> String {
+    "cyclonedx".to_string()
+}
+
+#[derive(Deserialize)]
+pub struct SbomDiffParams {
+    pub repo_a: String,
+    pub repo_b: String,
+}
+
+#[derive(Serialize)]
+pub struct LicenseSummary {
+    pub license: String,
+    pub count: u64,
+    pub is_copyleft: bool,
+    pub packages: Vec<String>,
+}
+
+#[derive(Serialize)]
+pub struct SbomDiffResult {
+    pub only_in_a: Vec<SbomDiffEntry>,
+    pub only_in_b: Vec<SbomDiffEntry>,
+    pub version_changed: Vec<SbomVersionDiff>,
+    pub common_count: u64,
+}
+
+#[derive(Serialize)]
+pub struct SbomDiffEntry {
+    pub name: String,
+    pub version: String,
+    pub package_manager: String,
+}
+
+#[derive(Serialize)]
+pub struct SbomVersionDiff {
+    pub name: String,
+    pub package_manager: String,
+    pub version_a: String,
+    pub version_b: String,
+}
+
+pub(crate) type AgentExt = axum::extract::Extension<std::sync::Arc<crate::agent::ComplianceAgent>>;
+pub(crate) type ApiResult<T> = Result<axum::Json<ApiResponse<T>>, axum::http::StatusCode>;
+
+pub(crate) async fn collect_cursor_async<T: serde::de::DeserializeOwned + Unpin + Send>(
+    mut cursor: mongodb::Cursor<T>,
+) -> Vec<T> {
+    use futures_util::StreamExt;
+    let mut items = Vec::new();
+    while let Some(result) = cursor.next().await {
+        match result {
+            Ok(item) => items.push(item),
+            Err(e) => tracing::warn!("Failed to deserialize document: {e}"),
+        }
+    }
+    items
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use serde_json::json;
+
+    // ── PaginationParams ─────────────────────────────────────────
+
+    #[test]
+    fn pagination_params_defaults() {
+        let p: PaginationParams = serde_json::from_str("{}").unwrap();
+        assert_eq!(p.page, 1);
+        assert_eq!(p.limit, 50);
+    }
+
+    #[test]
+    fn pagination_params_custom_values() {
+        let p: PaginationParams = serde_json::from_str(r#"{"page":3,"limit":10}"#).unwrap();
+        assert_eq!(p.page, 3);
+        assert_eq!(p.limit, 10);
+    }
+
+    #[test]
+    fn pagination_params_partial_override() {
+        let p: PaginationParams = serde_json::from_str(r#"{"page":5}"#).unwrap();
+        assert_eq!(p.page, 5);
+        assert_eq!(p.limit, 50);
+    }
+
+    #[test]
+    fn pagination_params_zero_page() {
+        let p: PaginationParams = serde_json::from_str(r#"{"page":0}"#).unwrap();
+        assert_eq!(p.page, 0);
+    }
+
+    // ── FindingsFilter ───────────────────────────────────────────
+
+    #[test]
+    fn findings_filter_all_defaults() {
+        let f: FindingsFilter = serde_json::from_str("{}").unwrap();
+        assert!(f.repo_id.is_none());
+        assert!(f.severity.is_none());
+        assert!(f.scan_type.is_none());
+        assert!(f.status.is_none());
+        assert!(f.q.is_none());
+        assert!(f.sort_by.is_none());
+        assert!(f.sort_order.is_none());
+        assert_eq!(f.page, 1);
+        assert_eq!(f.limit, 50);
+    }
+
+    #[test]
+    fn findings_filter_with_all_fields() {
+        let f: FindingsFilter = serde_json::from_str(
+            r#"{
+            "repo_id": "abc",
+            "severity": "high",
+            "scan_type": "sast",
+            "status": "open",
+            "q": "sql injection",
+            "sort_by": "severity",
+            "sort_order": "desc",
+            "page": 2,
+            "limit": 25
+        }"#,
+        )
+        .unwrap();
+        assert_eq!(f.repo_id.as_deref(), Some("abc"));
+        assert_eq!(f.severity.as_deref(), Some("high"));
+        assert_eq!(f.scan_type.as_deref(), Some("sast"));
+        assert_eq!(f.status.as_deref(), Some("open"));
+        assert_eq!(f.q.as_deref(), Some("sql injection"));
+        assert_eq!(f.sort_by.as_deref(), Some("severity"));
+        assert_eq!(f.sort_order.as_deref(), Some("desc"));
+        assert_eq!(f.page, 2);
+        assert_eq!(f.limit, 25);
+    }
+
+    #[test]
+    fn findings_filter_empty_string_fields() {
+        let f: FindingsFilter = serde_json::from_str(r#"{"repo_id":"","severity":""}"#).unwrap();
+        assert_eq!(f.repo_id.as_deref(), Some(""));
+        assert_eq!(f.severity.as_deref(), Some(""));
+    }
+
+    // ── ApiResponse ──────────────────────────────────────────────
+
+    #[test]
+    fn api_response_serializes_with_all_fields() {
+        let resp = ApiResponse {
+            data: vec!["a", "b"],
+            total: Some(100),
+            page: Some(1),
+        };
+        let v = serde_json::to_value(&resp).unwrap();
+        assert_eq!(v["data"], json!(["a", "b"]));
+        assert_eq!(v["total"], 100);
+        assert_eq!(v["page"], 1);
+    }
+
+    #[test]
+    fn api_response_skips_none_fields() {
+        let resp = ApiResponse {
+            data: "hello",
+            total: None,
+            page: None,
+        };
+        let v = serde_json::to_value(&resp).unwrap();
+        assert_eq!(v["data"], "hello");
+        assert!(v.get("total").is_none());
+        assert!(v.get("page").is_none());
+    }
+
+    #[test]
+    fn api_response_with_nested_struct() {
+        #[derive(Serialize)]
+        struct Item {
+            id: u32,
+        }
+        let resp = ApiResponse {
+            data: Item { id: 42 },
+            total: Some(1),
+            page: None,
+        };
+        let v = serde_json::to_value(&resp).unwrap();
+        assert_eq!(v["data"]["id"], 42);
+        assert_eq!(v["total"], 1);
+        assert!(v.get("page").is_none());
+    }
+
+    #[test]
+    fn api_response_empty_vec() {
+        let resp: ApiResponse<Vec<String>> = ApiResponse {
+            data: vec![],
+            total: Some(0),
+            page: Some(1),
+        };
+        let v = serde_json::to_value(&resp).unwrap();
+        assert!(v["data"].as_array().unwrap().is_empty());
+    }
+
+    // ── SbomFilter ───────────────────────────────────────────────
+
+    #[test]
+    fn sbom_filter_defaults() {
+        let f: SbomFilter = serde_json::from_str("{}").unwrap();
+        assert!(f.repo_id.is_none());
+        assert!(f.package_manager.is_none());
+        assert!(f.q.is_none());
+        assert!(f.has_vulns.is_none());
+        assert!(f.license.is_none());
+        assert_eq!(f.page, 1);
+        assert_eq!(f.limit, 50);
+    }
+
+    #[test]
+    fn sbom_filter_has_vulns_bool() {
+        let f: SbomFilter = serde_json::from_str(r#"{"has_vulns": true}"#).unwrap();
+        assert_eq!(f.has_vulns, Some(true));
+    }
+
+    // ── SbomExportParams ─────────────────────────────────────────
+
+    #[test]
+    fn sbom_export_params_default_format() {
+        let p: SbomExportParams = serde_json::from_str(r#"{"repo_id":"r1"}"#).unwrap();
+        assert_eq!(p.repo_id, "r1");
+        assert_eq!(p.format, "cyclonedx");
+    }
+
+    #[test]
+    fn sbom_export_params_custom_format() {
+        let p: SbomExportParams =
+            serde_json::from_str(r#"{"repo_id":"r1","format":"spdx"}"#).unwrap();
+        assert_eq!(p.format, "spdx");
+    }
+
+    // ── AddRepositoryRequest ─────────────────────────────────────
+
+    #[test]
+    fn add_repository_request_defaults() {
+        let r: AddRepositoryRequest = serde_json::from_str(
+            r#"{
+            "name": "my-repo",
+            "git_url": "https://github.com/x/y.git"
+        }"#,
+        )
+        .unwrap();
+        assert_eq!(r.name, "my-repo");
+        assert_eq!(r.git_url, "https://github.com/x/y.git");
+        assert_eq!(r.default_branch, "main");
+        assert!(r.auth_token.is_none());
+        assert!(r.tracker_type.is_none());
+        assert!(r.scan_schedule.is_none());
+    }
+
+    #[test]
+    fn add_repository_request_custom_branch() {
+        let r: AddRepositoryRequest = serde_json::from_str(
+            r#"{
+            "name": "repo",
+            "git_url": "url",
+            "default_branch": "develop"
+        }"#,
+        )
+        .unwrap();
+        assert_eq!(r.default_branch, "develop");
+    }
+
+    // ── UpdateStatusRequest / BulkUpdateStatusRequest ────────────
+
+    #[test]
+    fn update_status_request() {
+        let r: UpdateStatusRequest = serde_json::from_str(r#"{"status":"resolved"}"#).unwrap();
+        assert_eq!(r.status, "resolved");
+    }
+
+    #[test]
+    fn bulk_update_status_request() {
+        let r: BulkUpdateStatusRequest =
+            serde_json::from_str(r#"{"ids":["a","b"],"status":"dismissed"}"#).unwrap();
+        assert_eq!(r.ids, vec!["a", "b"]);
+        assert_eq!(r.status, "dismissed");
+    }
+
+    #[test]
+    fn bulk_update_status_empty_ids() {
+        let r: BulkUpdateStatusRequest =
+            serde_json::from_str(r#"{"ids":[],"status":"x"}"#).unwrap();
+        assert!(r.ids.is_empty());
+    }
+
+    // ── SbomDiffResult serialization ─────────────────────────────
+
+    #[test]
+    fn sbom_diff_result_serializes() {
+        let r = SbomDiffResult {
+            only_in_a: vec![SbomDiffEntry {
+                name: "pkg-a".to_string(),
+                version: "1.0".to_string(),
+                package_manager: "npm".to_string(),
+            }],
+            only_in_b: vec![],
+            version_changed: vec![SbomVersionDiff {
+                name: "shared".to_string(),
+                package_manager: "cargo".to_string(),
+                version_a: "0.1".to_string(),
+                version_b: "0.2".to_string(),
+            }],
+            common_count: 10,
+        };
+        let v = serde_json::to_value(&r).unwrap();
+        assert_eq!(v["only_in_a"].as_array().unwrap().len(), 1);
+        assert_eq!(v["only_in_b"].as_array().unwrap().len(), 0);
+        assert_eq!(v["version_changed"][0]["version_a"], "0.1");
+        assert_eq!(v["common_count"], 10);
+    }
+
+    // ── LicenseSummary ───────────────────────────────────────────
+
+    #[test]
+    fn license_summary_serializes() {
+        let ls = LicenseSummary {
+            license: "MIT".to_string(),
+            count: 42,
+            is_copyleft: false,
+            packages: vec!["serde".to_string()],
+        };
+        let v = serde_json::to_value(&ls).unwrap();
+        assert_eq!(v["license"], "MIT");
+        assert_eq!(v["is_copyleft"], false);
+        assert_eq!(v["count"], 42);
+    }
+
+    // ── Default helper functions ─────────────────────────────────
+
+    #[test]
+    fn default_page_returns_1() {
+        assert_eq!(default_page(), 1);
+    }
+
+    #[test]
+    fn default_limit_returns_50() {
+        assert_eq!(default_limit(), 50);
+    }
+}

compliance-agent/src/api/handlers/findings.rs

@@ -0,0 +1,172 @@
+use axum::extract::{Extension, Path, Query};
+use axum::http::StatusCode;
+use axum::Json;
+use mongodb::bson::doc;
+
+use super::dto::*;
+use compliance_core::models::Finding;
+
+#[tracing::instrument(skip_all, fields(repo_id = ?filter.repo_id, severity = ?filter.severity, scan_type = ?filter.scan_type))]
+pub async fn list_findings(
+    Extension(agent): AgentExt,
+    Query(filter): Query<FindingsFilter>,
+) -> ApiResult<Vec<Finding>> {
+    let db = &agent.db;
+    let mut query = doc! {};
+    if let Some(repo_id) = &filter.repo_id {
+        query.insert("repo_id", repo_id);
+    }
+    if let Some(severity) = &filter.severity {
+        query.insert("severity", severity);
+    }
+    if let Some(scan_type) = &filter.scan_type {
+        query.insert("scan_type", scan_type);
+    }
+    if let Some(status) = &filter.status {
+        query.insert("status", status);
+    }
+    // Text search across title, description, file_path, rule_id
+    if let Some(q) = &filter.q {
+        if !q.is_empty() {
+            let regex = doc! { "$regex": q, "$options": "i" };
+            query.insert(
+                "$or",
+                mongodb::bson::bson!([
+                    { "title": regex.clone() },
+                    { "description": regex.clone() },
+                    { "file_path": regex.clone() },
+                    { "rule_id": regex },
+                ]),
+            );
+        }
+    }
+
+    // Dynamic sort
+    let sort_field = filter.sort_by.as_deref().unwrap_or("created_at");
+    let sort_dir: i32 = match filter.sort_order.as_deref() {
+        Some("asc") => 1,
+        _ => -1,
+    };
+    let sort_doc = doc! { sort_field: sort_dir };
+
+    let skip = (filter.page.saturating_sub(1)) * filter.limit as u64;
+    let total = db
+        .findings()
+        .count_documents(query.clone())
+        .await
+        .unwrap_or(0);
+
+    let findings = match db
+        .findings()
+        .find(query)
+        .sort(sort_doc)
+        .skip(skip)
+        .limit(filter.limit)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch findings: {e}");
+            Vec::new()
+        }
+    };
+
+    Ok(Json(ApiResponse {
+        data: findings,
+        total: Some(total),
+        page: Some(filter.page),
+    }))
+}
+
+#[tracing::instrument(skip_all, fields(finding_id = %id))]
+pub async fn get_finding(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<Finding>>, StatusCode> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+    let finding = agent
+        .db
+        .findings()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
+        .ok_or(StatusCode::NOT_FOUND)?;
+
+    Ok(Json(ApiResponse {
+        data: finding,
+        total: None,
+        page: None,
+    }))
+}
+
+#[tracing::instrument(skip_all, fields(finding_id = %id))]
+pub async fn update_finding_status(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+    Json(req): Json<UpdateStatusRequest>,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+
+    agent
+        .db
+        .findings()
+        .update_one(
+            doc! { "_id": oid },
+            doc! { "$set": { "status": &req.status, "updated_at": mongodb::bson::DateTime::now() } },
+        )
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+
+    Ok(Json(serde_json::json!({ "status": "updated" })))
+}
+
+#[tracing::instrument(skip_all)]
+pub async fn bulk_update_finding_status(
+    Extension(agent): AgentExt,
+    Json(req): Json<BulkUpdateStatusRequest>,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    let oids: Vec<mongodb::bson::oid::ObjectId> = req
+        .ids
+        .iter()
+        .filter_map(|id| mongodb::bson::oid::ObjectId::parse_str(id).ok())
+        .collect();
+
+    if oids.is_empty() {
+        return Err(StatusCode::BAD_REQUEST);
+    }
+
+    let result = agent
+        .db
+        .findings()
+        .update_many(
+            doc! { "_id": { "$in": oids } },
+            doc! { "$set": { "status": &req.status, "updated_at": mongodb::bson::DateTime::now() } },
+        )
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+
+    Ok(Json(
+        serde_json::json!({ "status": "updated", "modified_count": result.modified_count }),
+    ))
+}
+
+#[tracing::instrument(skip_all)]
+pub async fn update_finding_feedback(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+    Json(req): Json<UpdateFeedbackRequest>,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+
+    agent
+        .db
+        .findings()
+        .update_one(
+            doc! { "_id": oid },
+            doc! { "$set": { "developer_feedback": &req.feedback, "updated_at": mongodb::bson::DateTime::now() } },
+        )
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+
+    Ok(Json(serde_json::json!({ "status": "updated" })))
+}

compliance-agent/src/api/handlers/graph.rs

@@ -33,6 +33,7 @@ fn default_search_limit() -> usize {
 }
 
 /// GET /api/v1/graph/:repo_id — Full graph data
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
 pub async fn get_graph(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,
@@ -54,11 +55,17 @@ pub async fn get_graph(
 
         let all_nodes: Vec<CodeNode> = match db.graph_nodes().find(filter.clone()).await {
             Ok(cursor) => collect_cursor_async(cursor).await,
-            Err(_) => Vec::new(),
+            Err(e) => {
+                tracing::warn!("Failed to fetch graph nodes: {e}");
+                Vec::new()
+            }
         };
         let edges: Vec<CodeEdge> = match db.graph_edges().find(filter).await {
             Ok(cursor) => collect_cursor_async(cursor).await,
-            Err(_) => Vec::new(),
+            Err(e) => {
+                tracing::warn!("Failed to fetch graph edges: {e}");
+                Vec::new()
+            }
         };
 
         // Remove disconnected nodes (no edges) to keep the graph clean
@@ -88,6 +95,7 @@ pub async fn get_graph(
 }
 
 /// GET /api/v1/graph/:repo_id/nodes — List nodes (paginated)
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
 pub async fn get_nodes(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,
@@ -97,7 +105,10 @@ pub async fn get_nodes(
 
     let nodes: Vec<CodeNode> = match db.graph_nodes().find(filter).await {
         Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
+        Err(e) => {
+            tracing::warn!("Failed to fetch graph nodes: {e}");
+            Vec::new()
+        }
     };
 
     let total = nodes.len() as u64;
@@ -109,6 +120,7 @@ pub async fn get_nodes(
 }
 
 /// GET /api/v1/graph/:repo_id/communities — List detected communities
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
 pub async fn get_communities(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,
@@ -118,7 +130,10 @@ pub async fn get_communities(
 
     let nodes: Vec<CodeNode> = match db.graph_nodes().find(filter).await {
         Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
+        Err(e) => {
+            tracing::warn!("Failed to fetch graph nodes for communities: {e}");
+            Vec::new()
+        }
     };
 
     let mut communities: std::collections::HashMap<u32, Vec<String>> =
@@ -158,6 +173,7 @@ pub struct CommunityInfo {
 }
 
 /// GET /api/v1/graph/:repo_id/impact/:finding_id — Impact analysis
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id, finding_id = %finding_id))]
 pub async fn get_impact(
     Extension(agent): AgentExt,
     Path((repo_id, finding_id)): Path<(String, String)>,
@@ -179,6 +195,7 @@ pub async fn get_impact(
 }
 
 /// GET /api/v1/graph/:repo_id/search — BM25 symbol search
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id, query = %params.q))]
 pub async fn search_symbols(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,
@@ -199,7 +216,10 @@ pub async fn search_symbols(
         .await
     {
         Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
+        Err(e) => {
+            tracing::warn!("Failed to search graph nodes: {e}");
+            Vec::new()
+        }
     };
 
     let total = nodes.len() as u64;
@@ -211,6 +231,7 @@ pub async fn search_symbols(
 }
 
 /// GET /api/v1/graph/:repo_id/file-content — Read source file from cloned repo
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
 pub async fn get_file_content(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,
@@ -272,6 +293,7 @@ pub struct FileContent {
 }
 
 /// POST /api/v1/graph/:repo_id/build — Trigger graph rebuild
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
 pub async fn trigger_build(
     Extension(agent): AgentExt,
     Path(repo_id): Path<String>,
@@ -291,7 +313,13 @@ pub async fn trigger_build(
             }
         };
 
-        let git_ops = crate::pipeline::git::GitOps::new(&agent_clone.config.git_clone_base_path);
+        let creds = crate::pipeline::git::RepoCredentials {
+            ssh_key_path: Some(agent_clone.config.ssh_key_path.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(&repo.git_url, &repo.name) {
             Ok(p) => p,
             Err(e) => {

compliance-agent/src/api/handlers/health.rs

@@ -0,0 +1,84 @@
+use axum::Json;
+use mongodb::bson::doc;
+
+use super::dto::*;
+use compliance_core::models::ScanRun;
+
+#[tracing::instrument(skip_all)]
+pub async fn health() -> Json<serde_json::Value> {
+    Json(serde_json::json!({ "status": "ok" }))
+}
+
+#[tracing::instrument(skip_all)]
+pub async fn stats_overview(axum::extract::Extension(agent): AgentExt) -> ApiResult<OverviewStats> {
+    let db = &agent.db;
+
+    let total_repositories = db
+        .repositories()
+        .count_documents(doc! {})
+        .await
+        .unwrap_or(0);
+    let total_findings = db.findings().count_documents(doc! {}).await.unwrap_or(0);
+    let critical_findings = db
+        .findings()
+        .count_documents(doc! { "severity": "critical" })
+        .await
+        .unwrap_or(0);
+    let high_findings = db
+        .findings()
+        .count_documents(doc! { "severity": "high" })
+        .await
+        .unwrap_or(0);
+    let medium_findings = db
+        .findings()
+        .count_documents(doc! { "severity": "medium" })
+        .await
+        .unwrap_or(0);
+    let low_findings = db
+        .findings()
+        .count_documents(doc! { "severity": "low" })
+        .await
+        .unwrap_or(0);
+    let total_sbom_entries = db
+        .sbom_entries()
+        .count_documents(doc! {})
+        .await
+        .unwrap_or(0);
+    let total_cve_alerts = db.cve_alerts().count_documents(doc! {}).await.unwrap_or(0);
+    let total_issues = db
+        .tracker_issues()
+        .count_documents(doc! {})
+        .await
+        .unwrap_or(0);
+
+    let recent_scans: Vec<ScanRun> = match db
+        .scan_runs()
+        .find(doc! {})
+        .sort(doc! { "started_at": -1 })
+        .limit(10)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch recent scans: {e}");
+            Vec::new()
+        }
+    };
+
+    Ok(Json(ApiResponse {
+        data: OverviewStats {
+            total_repositories,
+            total_findings,
+            critical_findings,
+            high_findings,
+            medium_findings,
+            low_findings,
+            total_sbom_entries,
+            total_cve_alerts,
+            total_issues,
+            recent_scans,
+        },
+        total: None,
+        page: None,
+    }))
+}

compliance-agent/src/api/handlers/issues.rs

@@ -0,0 +1,41 @@
+use axum::extract::{Extension, Query};
+use axum::Json;
+use mongodb::bson::doc;
+
+use super::dto::*;
+use compliance_core::models::TrackerIssue;
+
+#[tracing::instrument(skip_all)]
+pub async fn list_issues(
+    Extension(agent): AgentExt,
+    Query(params): Query<PaginationParams>,
+) -> ApiResult<Vec<TrackerIssue>> {
+    let db = &agent.db;
+    let skip = (params.page.saturating_sub(1)) * params.limit as u64;
+    let total = db
+        .tracker_issues()
+        .count_documents(doc! {})
+        .await
+        .unwrap_or(0);
+
+    let issues = match db
+        .tracker_issues()
+        .find(doc! {})
+        .sort(doc! { "created_at": -1 })
+        .skip(skip)
+        .limit(params.limit)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch tracker issues: {e}");
+            Vec::new()
+        }
+    };
+
+    Ok(Json(ApiResponse {
+        data: issues,
+        total: Some(total),
+        page: Some(params.page),
+    }))
+}

compliance-agent/src/api/handlers/mod.rs

@@ -1,827 +1,21 @@
 pub mod chat;
 pub mod dast;
+pub mod dto;
+pub mod findings;
 pub mod graph;
-
+pub mod health;
-use std::sync::Arc;
+pub mod issues;
-
+pub mod pentest_handlers;
-#[allow(unused_imports)]
+pub use pentest_handlers as pentest;
-use axum::extract::{Extension, Path, Query};
+pub mod repos;
-use axum::http::{header, StatusCode};
+pub mod sbom;
-use axum::response::IntoResponse;
+pub mod scans;
-use axum::Json;
+
-use mongodb::bson::doc;
+// Re-export all handler functions so routes.rs can use `handlers::function_name`
-use serde::{Deserialize, Serialize};
+pub use dto::*;
-
+pub use findings::*;
-use compliance_core::models::*;
+pub use health::*;
-
+pub use issues::*;
-use crate::agent::ComplianceAgent;
+pub use repos::*;
-
+pub use sbom::*;
-#[derive(Deserialize)]
+pub use scans::*;
-pub struct PaginationParams {
-    #[serde(default = "default_page")]
-    pub page: u64,
-    #[serde(default = "default_limit")]
-    pub limit: i64,
-}
-
-fn default_page() -> u64 {
-    1
-}
-fn default_limit() -> i64 {
-    50
-}
-
-#[derive(Deserialize)]
-pub struct FindingsFilter {
-    #[serde(default)]
-    pub repo_id: Option<String>,
-    #[serde(default)]
-    pub severity: Option<String>,
-    #[serde(default)]
-    pub scan_type: Option<String>,
-    #[serde(default)]
-    pub status: Option<String>,
-    #[serde(default = "default_page")]
-    pub page: u64,
-    #[serde(default = "default_limit")]
-    pub limit: i64,
-}
-
-#[derive(Serialize)]
-pub struct ApiResponse<T: Serialize> {
-    pub data: T,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub total: Option<u64>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub page: Option<u64>,
-}
-
-#[derive(Serialize)]
-pub struct OverviewStats {
-    pub total_repositories: u64,
-    pub total_findings: u64,
-    pub critical_findings: u64,
-    pub high_findings: u64,
-    pub medium_findings: u64,
-    pub low_findings: u64,
-    pub total_sbom_entries: u64,
-    pub total_cve_alerts: u64,
-    pub total_issues: u64,
-    pub recent_scans: Vec<ScanRun>,
-}
-
-#[derive(Deserialize)]
-pub struct AddRepositoryRequest {
-    pub name: String,
-    pub git_url: String,
-    #[serde(default = "default_branch")]
-    pub default_branch: String,
-    pub tracker_type: Option<TrackerType>,
-    pub tracker_owner: Option<String>,
-    pub tracker_repo: Option<String>,
-    pub scan_schedule: Option<String>,
-}
-
-fn default_branch() -> String {
-    "main".to_string()
-}
-
-#[derive(Deserialize)]
-pub struct UpdateStatusRequest {
-    pub status: String,
-}
-
-#[derive(Deserialize)]
-pub struct SbomFilter {
-    #[serde(default)]
-    pub repo_id: Option<String>,
-    #[serde(default)]
-    pub package_manager: Option<String>,
-    #[serde(default)]
-    pub q: Option<String>,
-    #[serde(default)]
-    pub has_vulns: Option<bool>,
-    #[serde(default)]
-    pub license: Option<String>,
-    #[serde(default = "default_page")]
-    pub page: u64,
-    #[serde(default = "default_limit")]
-    pub limit: i64,
-}
-
-#[derive(Deserialize)]
-pub struct SbomExportParams {
-    pub repo_id: String,
-    #[serde(default = "default_export_format")]
-    pub format: String,
-}
-
-fn default_export_format() -> String {
-    "cyclonedx".to_string()
-}
-
-#[derive(Deserialize)]
-pub struct SbomDiffParams {
-    pub repo_a: String,
-    pub repo_b: String,
-}
-
-#[derive(Serialize)]
-pub struct LicenseSummary {
-    pub license: String,
-    pub count: u64,
-    pub is_copyleft: bool,
-    pub packages: Vec<String>,
-}
-
-#[derive(Serialize)]
-pub struct SbomDiffResult {
-    pub only_in_a: Vec<SbomDiffEntry>,
-    pub only_in_b: Vec<SbomDiffEntry>,
-    pub version_changed: Vec<SbomVersionDiff>,
-    pub common_count: u64,
-}
-
-#[derive(Serialize)]
-pub struct SbomDiffEntry {
-    pub name: String,
-    pub version: String,
-    pub package_manager: String,
-}
-
-#[derive(Serialize)]
-pub struct SbomVersionDiff {
-    pub name: String,
-    pub package_manager: String,
-    pub version_a: String,
-    pub version_b: String,
-}
-
-type AgentExt = Extension<Arc<ComplianceAgent>>;
-type ApiResult<T> = Result<Json<ApiResponse<T>>, StatusCode>;
-
-pub async fn health() -> Json<serde_json::Value> {
-    Json(serde_json::json!({ "status": "ok" }))
-}
-
-pub async fn stats_overview(Extension(agent): AgentExt) -> ApiResult<OverviewStats> {
-    let db = &agent.db;
-
-    let total_repositories = db
-        .repositories()
-        .count_documents(doc! {})
-        .await
-        .unwrap_or(0);
-    let total_findings = db.findings().count_documents(doc! {}).await.unwrap_or(0);
-    let critical_findings = db
-        .findings()
-        .count_documents(doc! { "severity": "critical" })
-        .await
-        .unwrap_or(0);
-    let high_findings = db
-        .findings()
-        .count_documents(doc! { "severity": "high" })
-        .await
-        .unwrap_or(0);
-    let medium_findings = db
-        .findings()
-        .count_documents(doc! { "severity": "medium" })
-        .await
-        .unwrap_or(0);
-    let low_findings = db
-        .findings()
-        .count_documents(doc! { "severity": "low" })
-        .await
-        .unwrap_or(0);
-    let total_sbom_entries = db
-        .sbom_entries()
-        .count_documents(doc! {})
-        .await
-        .unwrap_or(0);
-    let total_cve_alerts = db.cve_alerts().count_documents(doc! {}).await.unwrap_or(0);
-    let total_issues = db
-        .tracker_issues()
-        .count_documents(doc! {})
-        .await
-        .unwrap_or(0);
-
-    let recent_scans: Vec<ScanRun> = match db
-        .scan_runs()
-        .find(doc! {})
-        .sort(doc! { "started_at": -1 })
-        .limit(10)
-        .await
-    {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    Ok(Json(ApiResponse {
-        data: OverviewStats {
-            total_repositories,
-            total_findings,
-            critical_findings,
-            high_findings,
-            medium_findings,
-            low_findings,
-            total_sbom_entries,
-            total_cve_alerts,
-            total_issues,
-            recent_scans,
-        },
-        total: None,
-        page: None,
-    }))
-}
-
-pub async fn list_repositories(
-    Extension(agent): AgentExt,
-    Query(params): Query<PaginationParams>,
-) -> ApiResult<Vec<TrackedRepository>> {
-    let db = &agent.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(_) => Vec::new(),
-    };
-
-    Ok(Json(ApiResponse {
-        data: repos,
-        total: Some(total),
-        page: Some(params.page),
-    }))
-}
-
-pub async fn add_repository(
-    Extension(agent): AgentExt,
-    Json(req): Json<AddRepositoryRequest>,
-) -> Result<Json<ApiResponse<TrackedRepository>>, StatusCode> {
-    let mut repo = TrackedRepository::new(req.name, req.git_url);
-    repo.default_branch = req.default_branch;
-    repo.tracker_type = req.tracker_type;
-    repo.tracker_owner = req.tracker_owner;
-    repo.tracker_repo = req.tracker_repo;
-    repo.scan_schedule = req.scan_schedule;
-
-    agent
-        .db
-        .repositories()
-        .insert_one(&repo)
-        .await
-        .map_err(|_| StatusCode::CONFLICT)?;
-
-    Ok(Json(ApiResponse {
-        data: repo,
-        total: None,
-        page: None,
-    }))
-}
-
-pub async fn trigger_scan(
-    Extension(agent): AgentExt,
-    Path(id): Path<String>,
-) -> Result<Json<serde_json::Value>, StatusCode> {
-    let agent_clone = (*agent).clone();
-    tokio::spawn(async move {
-        if let Err(e) = agent_clone.run_scan(&id, ScanTrigger::Manual).await {
-            tracing::error!("Manual scan failed for {id}: {e}");
-        }
-    });
-
-    Ok(Json(serde_json::json!({ "status": "scan_triggered" })))
-}
-
-pub async fn delete_repository(
-    Extension(agent): AgentExt,
-    Path(id): Path<String>,
-) -> Result<Json<serde_json::Value>, StatusCode> {
-    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
-    let db = &agent.db;
-
-    // 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;
-
-    Ok(Json(serde_json::json!({ "status": "deleted" })))
-}
-
-pub async fn list_findings(
-    Extension(agent): AgentExt,
-    Query(filter): Query<FindingsFilter>,
-) -> ApiResult<Vec<Finding>> {
-    let db = &agent.db;
-    let mut query = doc! {};
-    if let Some(repo_id) = &filter.repo_id {
-        query.insert("repo_id", repo_id);
-    }
-    if let Some(severity) = &filter.severity {
-        query.insert("severity", severity);
-    }
-    if let Some(scan_type) = &filter.scan_type {
-        query.insert("scan_type", scan_type);
-    }
-    if let Some(status) = &filter.status {
-        query.insert("status", status);
-    }
-
-    let skip = (filter.page.saturating_sub(1)) * filter.limit as u64;
-    let total = db
-        .findings()
-        .count_documents(query.clone())
-        .await
-        .unwrap_or(0);
-
-    let findings = match db
-        .findings()
-        .find(query)
-        .sort(doc! { "created_at": -1 })
-        .skip(skip)
-        .limit(filter.limit)
-        .await
-    {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    Ok(Json(ApiResponse {
-        data: findings,
-        total: Some(total),
-        page: Some(filter.page),
-    }))
-}
-
-pub async fn get_finding(
-    Extension(agent): AgentExt,
-    Path(id): Path<String>,
-) -> Result<Json<ApiResponse<Finding>>, StatusCode> {
-    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
-    let finding = agent
-        .db
-        .findings()
-        .find_one(doc! { "_id": oid })
-        .await
-        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
-        .ok_or(StatusCode::NOT_FOUND)?;
-
-    Ok(Json(ApiResponse {
-        data: finding,
-        total: None,
-        page: None,
-    }))
-}
-
-pub async fn update_finding_status(
-    Extension(agent): AgentExt,
-    Path(id): Path<String>,
-    Json(req): Json<UpdateStatusRequest>,
-) -> Result<Json<serde_json::Value>, StatusCode> {
-    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
-
-    agent
-        .db
-        .findings()
-        .update_one(
-            doc! { "_id": oid },
-            doc! { "$set": { "status": &req.status, "updated_at": mongodb::bson::DateTime::now() } },
-        )
-        .await
-        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
-
-    Ok(Json(serde_json::json!({ "status": "updated" })))
-}
-
-pub async fn list_sbom(
-    Extension(agent): AgentExt,
-    Query(filter): Query<SbomFilter>,
-) -> ApiResult<Vec<SbomEntry>> {
-    let db = &agent.db;
-    let mut query = doc! {};
-
-    if let Some(repo_id) = &filter.repo_id {
-        query.insert("repo_id", repo_id);
-    }
-    if let Some(pm) = &filter.package_manager {
-        query.insert("package_manager", pm);
-    }
-    if let Some(q) = &filter.q {
-        if !q.is_empty() {
-            query.insert("name", doc! { "$regex": q, "$options": "i" });
-        }
-    }
-    if let Some(has_vulns) = filter.has_vulns {
-        if has_vulns {
-            query.insert("known_vulnerabilities", doc! { "$exists": true, "$ne": [] });
-        } else {
-            query.insert("known_vulnerabilities", doc! { "$size": 0 });
-        }
-    }
-    if let Some(license) = &filter.license {
-        query.insert("license", license);
-    }
-
-    let skip = (filter.page.saturating_sub(1)) * filter.limit as u64;
-    let total = db
-        .sbom_entries()
-        .count_documents(query.clone())
-        .await
-        .unwrap_or(0);
-
-    let entries = match db
-        .sbom_entries()
-        .find(query)
-        .sort(doc! { "name": 1 })
-        .skip(skip)
-        .limit(filter.limit)
-        .await
-    {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    Ok(Json(ApiResponse {
-        data: entries,
-        total: Some(total),
-        page: Some(filter.page),
-    }))
-}
-
-pub async fn export_sbom(
-    Extension(agent): AgentExt,
-    Query(params): Query<SbomExportParams>,
-) -> Result<impl IntoResponse, StatusCode> {
-    let db = &agent.db;
-    let entries: Vec<SbomEntry> = match db
-        .sbom_entries()
-        .find(doc! { "repo_id": &params.repo_id })
-        .await
-    {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    let body = if params.format == "spdx" {
-        // SPDX 2.3 format
-        let packages: Vec<serde_json::Value> = entries
-            .iter()
-            .enumerate()
-            .map(|(i, e)| {
-                serde_json::json!({
-                    "SPDXID": format!("SPDXRef-Package-{i}"),
-                    "name": e.name,
-                    "versionInfo": e.version,
-                    "downloadLocation": "NOASSERTION",
-                    "licenseConcluded": e.license.as_deref().unwrap_or("NOASSERTION"),
-                    "externalRefs": e.purl.as_ref().map(|p| vec![serde_json::json!({
-                        "referenceCategory": "PACKAGE-MANAGER",
-                        "referenceType": "purl",
-                        "referenceLocator": p,
-                    })]).unwrap_or_default(),
-                })
-            })
-            .collect();
-
-        serde_json::json!({
-            "spdxVersion": "SPDX-2.3",
-            "dataLicense": "CC0-1.0",
-            "SPDXID": "SPDXRef-DOCUMENT",
-            "name": format!("sbom-{}", params.repo_id),
-            "documentNamespace": format!("https://compliance-scanner/sbom/{}", params.repo_id),
-            "packages": packages,
-        })
-    } else {
-        // CycloneDX 1.5 format
-        let components: Vec<serde_json::Value> = entries
-            .iter()
-            .map(|e| {
-                let mut comp = serde_json::json!({
-                    "type": "library",
-                    "name": e.name,
-                    "version": e.version,
-                    "group": e.package_manager,
-                });
-                if let Some(purl) = &e.purl {
-                    comp["purl"] = serde_json::Value::String(purl.clone());
-                }
-                if let Some(license) = &e.license {
-                    comp["licenses"] = serde_json::json!([{ "license": { "id": license } }]);
-                }
-                if !e.known_vulnerabilities.is_empty() {
-                    comp["vulnerabilities"] = serde_json::json!(
-                        e.known_vulnerabilities.iter().map(|v| serde_json::json!({
-                            "id": v.id,
-                            "source": { "name": v.source },
-                            "ratings": v.severity.as_ref().map(|s| vec![serde_json::json!({"severity": s})]).unwrap_or_default(),
-                        })).collect::<Vec<_>>()
-                    );
-                }
-                comp
-            })
-            .collect();
-
-        serde_json::json!({
-            "bomFormat": "CycloneDX",
-            "specVersion": "1.5",
-            "version": 1,
-            "metadata": {
-                "component": {
-                    "type": "application",
-                    "name": format!("repo-{}", params.repo_id),
-                }
-            },
-            "components": components,
-        })
-    };
-
-    let json_str =
-        serde_json::to_string_pretty(&body).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
-    let filename = if params.format == "spdx" {
-        format!("sbom-{}-spdx.json", params.repo_id)
-    } else {
-        format!("sbom-{}-cyclonedx.json", params.repo_id)
-    };
-
-    let disposition = format!("attachment; filename=\"{filename}\"");
-    Ok((
-        [
-            (
-                header::CONTENT_TYPE,
-                header::HeaderValue::from_static("application/json"),
-            ),
-            (
-                header::CONTENT_DISPOSITION,
-                header::HeaderValue::from_str(&disposition)
-                    .unwrap_or_else(|_| header::HeaderValue::from_static("attachment")),
-            ),
-        ],
-        json_str,
-    ))
-}
-
-const COPYLEFT_LICENSES: &[&str] = &[
-    "GPL-2.0",
-    "GPL-2.0-only",
-    "GPL-2.0-or-later",
-    "GPL-3.0",
-    "GPL-3.0-only",
-    "GPL-3.0-or-later",
-    "AGPL-3.0",
-    "AGPL-3.0-only",
-    "AGPL-3.0-or-later",
-    "LGPL-2.1",
-    "LGPL-2.1-only",
-    "LGPL-2.1-or-later",
-    "LGPL-3.0",
-    "LGPL-3.0-only",
-    "LGPL-3.0-or-later",
-    "MPL-2.0",
-];
-
-pub async fn license_summary(
-    Extension(agent): AgentExt,
-    Query(params): Query<SbomFilter>,
-) -> ApiResult<Vec<LicenseSummary>> {
-    let db = &agent.db;
-    let mut query = doc! {};
-    if let Some(repo_id) = &params.repo_id {
-        query.insert("repo_id", repo_id);
-    }
-
-    let entries: Vec<SbomEntry> = match db.sbom_entries().find(query).await {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    let mut license_map: std::collections::HashMap<String, Vec<String>> =
-        std::collections::HashMap::new();
-    for entry in &entries {
-        let lic = entry.license.as_deref().unwrap_or("Unknown").to_string();
-        license_map.entry(lic).or_default().push(entry.name.clone());
-    }
-
-    let mut summaries: Vec<LicenseSummary> = license_map
-        .into_iter()
-        .map(|(license, packages)| {
-            let is_copyleft = COPYLEFT_LICENSES
-                .iter()
-                .any(|c| license.to_uppercase().contains(&c.to_uppercase()));
-            LicenseSummary {
-                license,
-                count: packages.len() as u64,
-                is_copyleft,
-                packages,
-            }
-        })
-        .collect();
-    summaries.sort_by(|a, b| b.count.cmp(&a.count));
-
-    Ok(Json(ApiResponse {
-        data: summaries,
-        total: None,
-        page: None,
-    }))
-}
-
-pub async fn sbom_diff(
-    Extension(agent): AgentExt,
-    Query(params): Query<SbomDiffParams>,
-) -> ApiResult<SbomDiffResult> {
-    let db = &agent.db;
-
-    let entries_a: Vec<SbomEntry> = match db
-        .sbom_entries()
-        .find(doc! { "repo_id": &params.repo_a })
-        .await
-    {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    let entries_b: Vec<SbomEntry> = match db
-        .sbom_entries()
-        .find(doc! { "repo_id": &params.repo_b })
-        .await
-    {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    // Build maps by (name, package_manager) -> version
-    let map_a: std::collections::HashMap<(String, String), String> = entries_a
-        .iter()
-        .map(|e| {
-            (
-                (e.name.clone(), e.package_manager.clone()),
-                e.version.clone(),
-            )
-        })
-        .collect();
-    let map_b: std::collections::HashMap<(String, String), String> = entries_b
-        .iter()
-        .map(|e| {
-            (
-                (e.name.clone(), e.package_manager.clone()),
-                e.version.clone(),
-            )
-        })
-        .collect();
-
-    let mut only_in_a = Vec::new();
-    let mut version_changed = Vec::new();
-    let mut common_count: u64 = 0;
-
-    for (key, ver_a) in &map_a {
-        match map_b.get(key) {
-            None => only_in_a.push(SbomDiffEntry {
-                name: key.0.clone(),
-                version: ver_a.clone(),
-                package_manager: key.1.clone(),
-            }),
-            Some(ver_b) if ver_a != ver_b => {
-                version_changed.push(SbomVersionDiff {
-                    name: key.0.clone(),
-                    package_manager: key.1.clone(),
-                    version_a: ver_a.clone(),
-                    version_b: ver_b.clone(),
-                });
-            }
-            Some(_) => common_count += 1,
-        }
-    }
-
-    let only_in_b: Vec<SbomDiffEntry> = map_b
-        .iter()
-        .filter(|(key, _)| !map_a.contains_key(key))
-        .map(|(key, ver)| SbomDiffEntry {
-            name: key.0.clone(),
-            version: ver.clone(),
-            package_manager: key.1.clone(),
-        })
-        .collect();
-
-    Ok(Json(ApiResponse {
-        data: SbomDiffResult {
-            only_in_a,
-            only_in_b,
-            version_changed,
-            common_count,
-        },
-        total: None,
-        page: None,
-    }))
-}
-
-pub async fn list_issues(
-    Extension(agent): AgentExt,
-    Query(params): Query<PaginationParams>,
-) -> ApiResult<Vec<TrackerIssue>> {
-    let db = &agent.db;
-    let skip = (params.page.saturating_sub(1)) * params.limit as u64;
-    let total = db
-        .tracker_issues()
-        .count_documents(doc! {})
-        .await
-        .unwrap_or(0);
-
-    let issues = match db
-        .tracker_issues()
-        .find(doc! {})
-        .sort(doc! { "created_at": -1 })
-        .skip(skip)
-        .limit(params.limit)
-        .await
-    {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    Ok(Json(ApiResponse {
-        data: issues,
-        total: Some(total),
-        page: Some(params.page),
-    }))
-}
-
-pub async fn list_scan_runs(
-    Extension(agent): AgentExt,
-    Query(params): Query<PaginationParams>,
-) -> ApiResult<Vec<ScanRun>> {
-    let db = &agent.db;
-    let skip = (params.page.saturating_sub(1)) * params.limit as u64;
-    let total = db.scan_runs().count_documents(doc! {}).await.unwrap_or(0);
-
-    let scans = match db
-        .scan_runs()
-        .find(doc! {})
-        .sort(doc! { "started_at": -1 })
-        .skip(skip)
-        .limit(params.limit)
-        .await
-    {
-        Ok(cursor) => collect_cursor_async(cursor).await,
-        Err(_) => Vec::new(),
-    };
-
-    Ok(Json(ApiResponse {
-        data: scans,
-        total: Some(total),
-        page: Some(params.page),
-    }))
-}
-
-async fn collect_cursor_async<T: serde::de::DeserializeOwned + Unpin + Send>(
-    mut cursor: mongodb::Cursor<T>,
-) -> Vec<T> {
-    use futures_util::StreamExt;
-    let mut items = Vec::new();
-    while let Some(result) = cursor.next().await {
-        match result {
-            Ok(item) => items.push(item),
-            Err(e) => tracing::warn!("Failed to deserialize document: {e}"),
-        }
-    }
-    items
-}

compliance-agent/src/api/handlers/pentest_handlers/export.rs

@@ -0,0 +1,230 @@
+use std::sync::Arc;
+
+use axum::extract::{Extension, Path};
+use axum::http::StatusCode;
+use axum::response::IntoResponse;
+use axum::Json;
+use mongodb::bson::doc;
+use serde::Deserialize;
+
+use futures_util::StreamExt;
+
+use compliance_core::models::dast::DastFinding;
+use compliance_core::models::finding::Finding;
+use compliance_core::models::pentest::*;
+use compliance_core::models::sbom::SbomEntry;
+
+use crate::agent::ComplianceAgent;
+
+use super::super::dto::collect_cursor_async;
+
+type AgentExt = Extension<Arc<ComplianceAgent>>;
+
+#[derive(Deserialize)]
+pub struct ExportBody {
+    pub password: String,
+    /// Requester display name (from auth)
+    #[serde(default)]
+    pub requester_name: String,
+    /// Requester email (from auth)
+    #[serde(default)]
+    pub requester_email: String,
+}
+
+/// POST /api/v1/pentest/sessions/:id/export — Export an encrypted pentest report archive
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn export_session_report(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+    Json(body): Json<ExportBody>,
+) -> Result<axum::response::Response, (StatusCode, String)> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
+        .map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
+
+    if body.password.len() < 8 {
+        return Err((
+            StatusCode::BAD_REQUEST,
+            "Password must be at least 8 characters".to_string(),
+        ));
+    }
+
+    // Fetch session
+    let session = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {e}"),
+            )
+        })?
+        .ok_or_else(|| (StatusCode::NOT_FOUND, "Session not found".to_string()))?;
+
+    // Resolve target name
+    let target = if let Ok(tid) = mongodb::bson::oid::ObjectId::parse_str(&session.target_id) {
+        agent
+            .db
+            .dast_targets()
+            .find_one(doc! { "_id": tid })
+            .await
+            .ok()
+            .flatten()
+    } else {
+        None
+    };
+    let target_name = target
+        .as_ref()
+        .map(|t| t.name.clone())
+        .unwrap_or_else(|| "Unknown Target".to_string());
+    let target_url = target
+        .as_ref()
+        .map(|t| t.base_url.clone())
+        .unwrap_or_default();
+
+    // Fetch attack chain nodes
+    let nodes: Vec<AttackChainNode> = match agent
+        .db
+        .attack_chain_nodes()
+        .find(doc! { "session_id": &id })
+        .sort(doc! { "started_at": 1 })
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(_) => Vec::new(),
+    };
+
+    // Fetch DAST findings for this session
+    let findings: Vec<DastFinding> = match agent
+        .db
+        .dast_findings()
+        .find(doc! { "session_id": &id })
+        .sort(doc! { "severity": -1, "created_at": -1 })
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(_) => Vec::new(),
+    };
+
+    // Fetch SAST findings, SBOM, and code context for the linked repository
+    let repo_id = session
+        .repo_id
+        .clone()
+        .or_else(|| target.as_ref().and_then(|t| t.repo_id.clone()));
+
+    let (sast_findings, sbom_entries, code_context) = if let Some(ref rid) = repo_id {
+        let sast: Vec<Finding> = match agent
+            .db
+            .findings()
+            .find(doc! {
+                "repo_id": rid,
+                "status": { "$in": ["open", "triaged"] },
+            })
+            .sort(doc! { "severity": -1 })
+            .limit(100)
+            .await
+        {
+            Ok(mut cursor) => {
+                let mut results = Vec::new();
+                while let Some(Ok(f)) = cursor.next().await {
+                    results.push(f);
+                }
+                results
+            }
+            Err(_) => Vec::new(),
+        };
+
+        let sbom: Vec<SbomEntry> = match agent
+            .db
+            .sbom_entries()
+            .find(doc! {
+                "repo_id": rid,
+                "known_vulnerabilities": { "$exists": true, "$ne": [] },
+            })
+            .limit(50)
+            .await
+        {
+            Ok(mut cursor) => {
+                let mut results = Vec::new();
+                while let Some(Ok(e)) = cursor.next().await {
+                    results.push(e);
+                }
+                results
+            }
+            Err(_) => Vec::new(),
+        };
+
+        // Build code context from graph nodes
+        let code_ctx: Vec<CodeContextHint> = match agent
+            .db
+            .graph_nodes()
+            .find(doc! { "repo_id": rid, "is_entry_point": true })
+            .limit(50)
+            .await
+        {
+            Ok(mut cursor) => {
+                let mut nodes_vec = Vec::new();
+                while let Some(Ok(n)) = cursor.next().await {
+                    let linked_vulns: Vec<String> = sast
+                        .iter()
+                        .filter(|f| f.file_path.as_deref() == Some(&n.file_path))
+                        .map(|f| {
+                            format!(
+                                "[{}] {}: {} (line {})",
+                                f.severity,
+                                f.scanner,
+                                f.title,
+                                f.line_number.unwrap_or(0)
+                            )
+                        })
+                        .collect();
+                    nodes_vec.push(CodeContextHint {
+                        endpoint_pattern: n.qualified_name.clone(),
+                        handler_function: n.name.clone(),
+                        file_path: n.file_path.clone(),
+                        code_snippet: String::new(),
+                        known_vulnerabilities: linked_vulns,
+                    });
+                }
+                nodes_vec
+            }
+            Err(_) => Vec::new(),
+        };
+
+        (sast, sbom, code_ctx)
+    } else {
+        (Vec::new(), Vec::new(), Vec::new())
+    };
+
+    let config = session.config.clone();
+    let ctx = crate::pentest::report::ReportContext {
+        session,
+        target_name,
+        target_url,
+        findings,
+        attack_chain: nodes,
+        requester_name: if body.requester_name.is_empty() {
+            "Unknown".to_string()
+        } else {
+            body.requester_name
+        },
+        requester_email: body.requester_email,
+        config,
+        sast_findings,
+        sbom_entries,
+        code_context,
+    };
+
+    let report = crate::pentest::generate_encrypted_report(&ctx, &body.password)
+        .await
+        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e))?;
+
+    let response = serde_json::json!({
+        "archive_base64": base64::Engine::encode(&base64::engine::general_purpose::STANDARD, &report.archive),
+        "sha256": report.sha256,
+        "filename": format!("pentest-report-{id}.zip"),
+    });
+
+    Ok(Json(response).into_response())
+}

compliance-agent/src/api/handlers/pentest_handlers/mod.rs

@@ -0,0 +1,9 @@
+mod export;
+mod session;
+mod stats;
+mod stream;
+
+pub use export::*;
+pub use session::*;
+pub use stats::*;
+pub use stream::*;

compliance-agent/src/api/handlers/pentest_handlers/session.rs

@@ -0,0 +1,834 @@
+use std::sync::Arc;
+
+use axum::extract::{Extension, Path, Query};
+use axum::http::StatusCode;
+use axum::Json;
+use mongodb::bson::doc;
+use serde::Deserialize;
+
+use compliance_core::models::pentest::*;
+
+use crate::agent::ComplianceAgent;
+use crate::pentest::PentestOrchestrator;
+
+use super::super::dto::{collect_cursor_async, ApiResponse, PaginationParams};
+
+type AgentExt = Extension<Arc<ComplianceAgent>>;
+
+#[derive(Deserialize)]
+pub struct CreateSessionRequest {
+    pub target_id: Option<String>,
+    #[serde(default = "default_strategy")]
+    pub strategy: String,
+    pub message: Option<String>,
+    /// Wizard configuration — if present, takes precedence over legacy fields
+    pub config: Option<PentestConfig>,
+}
+
+fn default_strategy() -> String {
+    "comprehensive".to_string()
+}
+
+#[derive(Deserialize)]
+pub struct SendMessageRequest {
+    pub message: String,
+}
+
+#[derive(Deserialize)]
+pub struct LookupRepoQuery {
+    pub url: String,
+}
+
+/// POST /api/v1/pentest/sessions — Create a new pentest session and start the orchestrator
+#[tracing::instrument(skip_all)]
+pub async fn create_session(
+    Extension(agent): AgentExt,
+    Json(req): Json<CreateSessionRequest>,
+) -> Result<Json<ApiResponse<PentestSession>>, (StatusCode, String)> {
+    // Try to acquire a concurrency permit
+    let permit = agent
+        .session_semaphore
+        .clone()
+        .try_acquire_owned()
+        .map_err(|_| {
+            (
+                StatusCode::TOO_MANY_REQUESTS,
+                "Maximum concurrent pentest sessions reached. Try again later.".to_string(),
+            )
+        })?;
+
+    if let Some(ref config) = req.config {
+        // ── Wizard path ──────────────────────────────────────────────
+        if !config.disclaimer_accepted {
+            return Err((
+                StatusCode::BAD_REQUEST,
+                "Disclaimer must be accepted".to_string(),
+            ));
+        }
+
+        // Look up or auto-create DastTarget by app_url
+        let target = match agent
+            .db
+            .dast_targets()
+            .find_one(doc! { "base_url": &config.app_url })
+            .await
+            .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, format!("DB error: {e}")))?
+        {
+            Some(t) => t,
+            None => {
+                use compliance_core::models::dast::{DastTarget, DastTargetType};
+                let mut t = DastTarget::new(
+                    config.app_url.clone(),
+                    config.app_url.clone(),
+                    DastTargetType::WebApp,
+                );
+                if let Some(rl) = config.rate_limit {
+                    t.rate_limit = rl;
+                }
+                t.allow_destructive = config.allow_destructive;
+                t.excluded_paths = config.scope_exclusions.clone();
+                let res = agent.db.dast_targets().insert_one(&t).await.map_err(|e| {
+                    (
+                        StatusCode::INTERNAL_SERVER_ERROR,
+                        format!("Failed to create target: {e}"),
+                    )
+                })?;
+                t.id = res.inserted_id.as_object_id();
+                t
+            }
+        };
+
+        let target_id = target.id.map(|oid| oid.to_hex()).unwrap_or_default();
+
+        // Parse strategy from config or request
+        let strat_str = config.strategy.as_deref().unwrap_or(req.strategy.as_str());
+        let strategy = parse_strategy(strat_str);
+
+        let mut session = PentestSession::new(target_id, strategy);
+        session.config = Some(config.clone());
+        session.repo_id = target.repo_id.clone();
+
+        // Resolve repo_id from git_repo_url if provided
+        if let Some(ref git_url) = config.git_repo_url {
+            if let Ok(Some(repo)) = agent
+                .db
+                .repositories()
+                .find_one(doc! { "git_url": git_url })
+                .await
+            {
+                session.repo_id = repo.id.map(|oid| oid.to_hex());
+            }
+        }
+
+        let insert_result = agent
+            .db
+            .pentest_sessions()
+            .insert_one(&session)
+            .await
+            .map_err(|e| {
+                (
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                    format!("Failed to create session: {e}"),
+                )
+            })?;
+        session.id = insert_result.inserted_id.as_object_id();
+
+        let session_id_str = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
+
+        // Register broadcast stream and pause control
+        let event_tx = agent.register_session_stream(&session_id_str);
+        let pause_rx = agent.register_pause_control(&session_id_str);
+
+        // Merge server-default IMAP/email settings where wizard left blanks
+        if let Some(ref mut cfg) = session.config {
+            if cfg.auth.mode == AuthMode::AutoRegister {
+                if cfg.auth.verification_email.is_none() {
+                    cfg.auth.verification_email = agent.config.pentest_verification_email.clone();
+                }
+                if cfg.auth.imap_host.is_none() {
+                    cfg.auth.imap_host = agent.config.pentest_imap_host.clone();
+                }
+                if cfg.auth.imap_port.is_none() {
+                    cfg.auth.imap_port = agent.config.pentest_imap_port;
+                }
+                if cfg.auth.imap_username.is_none() {
+                    cfg.auth.imap_username = agent.config.pentest_imap_username.clone();
+                }
+                if cfg.auth.imap_password.is_none() {
+                    cfg.auth.imap_password = agent.config.pentest_imap_password.as_ref().map(|s| {
+                        use secrecy::ExposeSecret;
+                        s.expose_secret().to_string()
+                    });
+                }
+            }
+        }
+
+        // Pre-populate test user record for auto-register sessions
+        if let Some(ref cfg) = session.config {
+            if cfg.auth.mode == AuthMode::AutoRegister {
+                let verification_email = cfg.auth.verification_email.clone();
+                // Build plus-addressed email for this session
+                let test_email = verification_email.as_deref().map(|email| {
+                    let parts: Vec<&str> = email.splitn(2, '@').collect();
+                    if parts.len() == 2 {
+                        format!("{}+{}@{}", parts[0], session_id_str, parts[1])
+                    } else {
+                        email.to_string()
+                    }
+                });
+
+                // Detect identity provider from keycloak config
+                let provider = if agent.config.keycloak_url.is_some() {
+                    Some(compliance_core::models::pentest::IdentityProvider::Keycloak)
+                } else {
+                    None
+                };
+
+                session.test_user = Some(compliance_core::models::pentest::TestUserRecord {
+                    username: None, // LLM will choose; updated after registration
+                    email: test_email,
+                    provider_user_id: None,
+                    provider,
+                    cleaned_up: false,
+                });
+            }
+        }
+
+        // Encrypt credentials before they linger in memory
+        let mut session_for_task = session.clone();
+        if let Some(ref mut cfg) = session_for_task.config {
+            cfg.auth.username = cfg
+                .auth
+                .username
+                .as_ref()
+                .map(|u| crate::pentest::crypto::encrypt(u));
+            cfg.auth.password = cfg
+                .auth
+                .password
+                .as_ref()
+                .map(|p| crate::pentest::crypto::encrypt(p));
+        }
+
+        // Persist encrypted credentials to DB
+        if session_for_task.config.is_some() {
+            if let Some(sid) = session.id {
+                let _ = agent
+                    .db
+                    .pentest_sessions()
+                    .update_one(
+                        doc! { "_id": sid },
+                        doc! { "$set": {
+                            "config.auth.username": session_for_task.config.as_ref()
+                                .and_then(|c| c.auth.username.as_deref())
+                                .map(|s| mongodb::bson::Bson::String(s.to_string()))
+                                .unwrap_or(mongodb::bson::Bson::Null),
+                            "config.auth.password": session_for_task.config.as_ref()
+                                .and_then(|c| c.auth.password.as_deref())
+                                .map(|s| mongodb::bson::Bson::String(s.to_string()))
+                                .unwrap_or(mongodb::bson::Bson::Null),
+                        }},
+                    )
+                    .await;
+            }
+        }
+
+        let initial_message = config
+            .initial_instructions
+            .clone()
+            .or(req.message.clone())
+            .unwrap_or_else(|| {
+                format!(
+                    "Begin a {} penetration test against {} ({}). \
+                     Identify vulnerabilities and provide evidence for each finding.",
+                    session.strategy, target.name, target.base_url,
+                )
+            });
+
+        let llm = agent.llm.clone();
+        let db = agent.db.clone();
+        let session_clone = session.clone();
+        let target_clone = target.clone();
+        let agent_ref = agent.clone();
+        tokio::spawn(async move {
+            let orchestrator = PentestOrchestrator::new(llm, db, event_tx, Some(pause_rx));
+            orchestrator
+                .run_session_guarded(&session_clone, &target_clone, &initial_message)
+                .await;
+            // Clean up session resources
+            agent_ref.cleanup_session(&session_id_str);
+            // Release concurrency permit
+            drop(permit);
+        });
+
+        // Redact credentials in response
+        let mut response_session = session;
+        if let Some(ref mut cfg) = response_session.config {
+            if cfg.auth.username.is_some() {
+                cfg.auth.username = Some("********".to_string());
+            }
+            if cfg.auth.password.is_some() {
+                cfg.auth.password = Some("********".to_string());
+            }
+        }
+
+        Ok(Json(ApiResponse {
+            data: response_session,
+            total: None,
+            page: None,
+        }))
+    } else {
+        // ── Legacy path ──────────────────────────────────────────────
+        let target_id = req.target_id.clone().ok_or_else(|| {
+            (
+                StatusCode::BAD_REQUEST,
+                "target_id is required for legacy creation".to_string(),
+            )
+        })?;
+
+        let oid = mongodb::bson::oid::ObjectId::parse_str(&target_id).map_err(|_| {
+            (
+                StatusCode::BAD_REQUEST,
+                "Invalid target_id format".to_string(),
+            )
+        })?;
+
+        let target = agent
+            .db
+            .dast_targets()
+            .find_one(doc! { "_id": oid })
+            .await
+            .map_err(|e| {
+                (
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                    format!("Database error: {e}"),
+                )
+            })?
+            .ok_or_else(|| (StatusCode::NOT_FOUND, "Target not found".to_string()))?;
+
+        let strategy = parse_strategy(&req.strategy);
+
+        let mut session = PentestSession::new(target_id, strategy);
+        session.repo_id = target.repo_id.clone();
+
+        let insert_result = agent
+            .db
+            .pentest_sessions()
+            .insert_one(&session)
+            .await
+            .map_err(|e| {
+                (
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                    format!("Failed to create session: {e}"),
+                )
+            })?;
+        session.id = insert_result.inserted_id.as_object_id();
+
+        let session_id_str = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
+
+        // Register broadcast stream and pause control
+        let event_tx = agent.register_session_stream(&session_id_str);
+        let pause_rx = agent.register_pause_control(&session_id_str);
+
+        let initial_message = req.message.unwrap_or_else(|| {
+            format!(
+                "Begin a {} penetration test against {} ({}). \
+                 Identify vulnerabilities and provide evidence for each finding.",
+                session.strategy, target.name, target.base_url,
+            )
+        });
+
+        let llm = agent.llm.clone();
+        let db = agent.db.clone();
+        let session_clone = session.clone();
+        let target_clone = target.clone();
+        let agent_ref = agent.clone();
+        tokio::spawn(async move {
+            let orchestrator = PentestOrchestrator::new(llm, db, event_tx, Some(pause_rx));
+            orchestrator
+                .run_session_guarded(&session_clone, &target_clone, &initial_message)
+                .await;
+            agent_ref.cleanup_session(&session_id_str);
+            drop(permit);
+        });
+
+        Ok(Json(ApiResponse {
+            data: session,
+            total: None,
+            page: None,
+        }))
+    }
+}
+
+fn parse_strategy(s: &str) -> PentestStrategy {
+    match s {
+        "quick" => PentestStrategy::Quick,
+        "targeted" => PentestStrategy::Targeted,
+        "aggressive" => PentestStrategy::Aggressive,
+        "stealth" => PentestStrategy::Stealth,
+        _ => PentestStrategy::Comprehensive,
+    }
+}
+
+/// GET /api/v1/pentest/lookup-repo — Look up a tracked repository by git URL
+#[tracing::instrument(skip_all)]
+pub async fn lookup_repo(
+    Extension(agent): AgentExt,
+    Query(params): Query<LookupRepoQuery>,
+) -> Result<Json<ApiResponse<serde_json::Value>>, StatusCode> {
+    let repo = agent
+        .db
+        .repositories()
+        .find_one(doc! { "git_url": &params.url })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+
+    let data = match repo {
+        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,
+    };
+
+    Ok(Json(ApiResponse {
+        data,
+        total: None,
+        page: None,
+    }))
+}
+
+/// GET /api/v1/pentest/sessions — List pentest sessions
+#[tracing::instrument(skip_all)]
+pub async fn list_sessions(
+    Extension(agent): AgentExt,
+    Query(params): Query<PaginationParams>,
+) -> Result<Json<ApiResponse<Vec<PentestSession>>>, StatusCode> {
+    let db = &agent.db;
+    let skip = (params.page.saturating_sub(1)) * params.limit as u64;
+    let total = db
+        .pentest_sessions()
+        .count_documents(doc! {})
+        .await
+        .unwrap_or(0);
+
+    let sessions = match db
+        .pentest_sessions()
+        .find(doc! {})
+        .sort(doc! { "started_at": -1 })
+        .skip(skip)
+        .limit(params.limit)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch pentest sessions: {e}");
+            Vec::new()
+        }
+    };
+
+    Ok(Json(ApiResponse {
+        data: sessions,
+        total: Some(total),
+        page: Some(params.page),
+    }))
+}
+
+/// GET /api/v1/pentest/sessions/:id — Get a single pentest session
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn get_session(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<PentestSession>>, StatusCode> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+
+    let mut session = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
+        .ok_or(StatusCode::NOT_FOUND)?;
+
+    // Redact credentials in response
+    if let Some(ref mut cfg) = session.config {
+        if cfg.auth.username.is_some() {
+            cfg.auth.username = Some("********".to_string());
+        }
+        if cfg.auth.password.is_some() {
+            cfg.auth.password = Some("********".to_string());
+        }
+    }
+
+    Ok(Json(ApiResponse {
+        data: session,
+        total: None,
+        page: None,
+    }))
+}
+
+/// POST /api/v1/pentest/sessions/:id/chat — Send a user message and trigger next orchestrator iteration
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn send_message(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+    Json(req): Json<SendMessageRequest>,
+) -> Result<Json<ApiResponse<PentestMessage>>, (StatusCode, String)> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
+        .map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
+
+    // Verify session exists and is running
+    let session = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {e}"),
+            )
+        })?
+        .ok_or_else(|| (StatusCode::NOT_FOUND, "Session not found".to_string()))?;
+
+    if session.status != PentestStatus::Running && session.status != PentestStatus::Paused {
+        return Err((
+            StatusCode::BAD_REQUEST,
+            format!("Session is {}, cannot send messages", session.status),
+        ));
+    }
+
+    // Look up the target
+    let target_oid = mongodb::bson::oid::ObjectId::parse_str(&session.target_id).map_err(|_| {
+        (
+            StatusCode::INTERNAL_SERVER_ERROR,
+            "Invalid target_id in session".to_string(),
+        )
+    })?;
+
+    let target = agent
+        .db
+        .dast_targets()
+        .find_one(doc! { "_id": target_oid })
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {e}"),
+            )
+        })?
+        .ok_or_else(|| {
+            (
+                StatusCode::NOT_FOUND,
+                "Target for session not found".to_string(),
+            )
+        })?;
+
+    // Store user message
+    let session_id = id.clone();
+    let user_msg = PentestMessage::user(session_id.clone(), req.message.clone());
+    let _ = agent.db.pentest_messages().insert_one(&user_msg).await;
+
+    let response_msg = user_msg.clone();
+
+    // Spawn orchestrator to continue the session
+    let llm = agent.llm.clone();
+    let db = agent.db.clone();
+    let message = req.message.clone();
+
+    // Use existing broadcast sender if available, otherwise create a new one
+    let event_tx = agent
+        .subscribe_session(&session_id)
+        .and_then(|_| {
+            agent
+                .session_streams
+                .get(&session_id)
+                .map(|entry| entry.value().clone())
+        })
+        .unwrap_or_else(|| agent.register_session_stream(&session_id));
+
+    tokio::spawn(async move {
+        let orchestrator = PentestOrchestrator::new(llm, db, event_tx, None);
+        orchestrator
+            .run_session_guarded(&session, &target, &message)
+            .await;
+    });
+
+    Ok(Json(ApiResponse {
+        data: response_msg,
+        total: None,
+        page: None,
+    }))
+}
+
+/// POST /api/v1/pentest/sessions/:id/stop — Stop a running pentest session
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn stop_session(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<PentestSession>>, (StatusCode, String)> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
+        .map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
+
+    let session = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {e}"),
+            )
+        })?
+        .ok_or_else(|| (StatusCode::NOT_FOUND, "Session not found".to_string()))?;
+
+    if session.status != PentestStatus::Running && session.status != PentestStatus::Paused {
+        return Err((
+            StatusCode::BAD_REQUEST,
+            format!("Session is {}, not running or paused", session.status),
+        ));
+    }
+
+    agent
+        .db
+        .pentest_sessions()
+        .update_one(
+            doc! { "_id": oid },
+            doc! { "$set": {
+                "status": "failed",
+                "completed_at": mongodb::bson::DateTime::now(),
+                "error_message": "Stopped by user",
+            }},
+        )
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {e}"),
+            )
+        })?;
+
+    // Clean up session resources
+    agent.cleanup_session(&id);
+
+    let updated = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {e}"),
+            )
+        })?
+        .ok_or_else(|| {
+            (
+                StatusCode::NOT_FOUND,
+                "Session not found after update".to_string(),
+            )
+        })?;
+
+    Ok(Json(ApiResponse {
+        data: updated,
+        total: None,
+        page: None,
+    }))
+}
+
+/// POST /api/v1/pentest/sessions/:id/pause — Pause a running pentest session
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn pause_session(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<serde_json::Value>>, (StatusCode, String)> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
+        .map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
+
+    let session = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {e}"),
+            )
+        })?
+        .ok_or_else(|| (StatusCode::NOT_FOUND, "Session not found".to_string()))?;
+
+    if session.status != PentestStatus::Running {
+        return Err((
+            StatusCode::BAD_REQUEST,
+            format!("Session is {}, not running", session.status),
+        ));
+    }
+
+    if !agent.pause_session(&id) {
+        return Err((
+            StatusCode::INTERNAL_SERVER_ERROR,
+            "Failed to send pause signal".to_string(),
+        ));
+    }
+
+    Ok(Json(ApiResponse {
+        data: serde_json::json!({ "status": "paused" }),
+        total: None,
+        page: None,
+    }))
+}
+
+/// POST /api/v1/pentest/sessions/:id/resume — Resume a paused pentest session
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn resume_session(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<serde_json::Value>>, (StatusCode, String)> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id)
+        .map_err(|_| (StatusCode::BAD_REQUEST, "Invalid session ID".to_string()))?;
+
+    let session = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {e}"),
+            )
+        })?
+        .ok_or_else(|| (StatusCode::NOT_FOUND, "Session not found".to_string()))?;
+
+    if session.status != PentestStatus::Paused {
+        return Err((
+            StatusCode::BAD_REQUEST,
+            format!("Session is {}, not paused", session.status),
+        ));
+    }
+
+    if !agent.resume_session(&id) {
+        return Err((
+            StatusCode::INTERNAL_SERVER_ERROR,
+            "Failed to send resume signal".to_string(),
+        ));
+    }
+
+    Ok(Json(ApiResponse {
+        data: serde_json::json!({ "status": "running" }),
+        total: None,
+        page: None,
+    }))
+}
+
+/// GET /api/v1/pentest/sessions/:id/attack-chain — Get attack chain nodes for a session
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn get_attack_chain(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+) -> Result<Json<ApiResponse<Vec<AttackChainNode>>>, StatusCode> {
+    let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+
+    let nodes = match agent
+        .db
+        .attack_chain_nodes()
+        .find(doc! { "session_id": &id })
+        .sort(doc! { "started_at": 1 })
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch attack chain nodes: {e}");
+            Vec::new()
+        }
+    };
+
+    let total = nodes.len() as u64;
+    Ok(Json(ApiResponse {
+        data: nodes,
+        total: Some(total),
+        page: None,
+    }))
+}
+
+/// GET /api/v1/pentest/sessions/:id/messages — Get messages for a session
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn get_messages(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+    Query(params): Query<PaginationParams>,
+) -> Result<Json<ApiResponse<Vec<PentestMessage>>>, StatusCode> {
+    let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+
+    let skip = (params.page.saturating_sub(1)) * params.limit as u64;
+    let total = agent
+        .db
+        .pentest_messages()
+        .count_documents(doc! { "session_id": &id })
+        .await
+        .unwrap_or(0);
+
+    let messages = match agent
+        .db
+        .pentest_messages()
+        .find(doc! { "session_id": &id })
+        .sort(doc! { "created_at": 1 })
+        .skip(skip)
+        .limit(params.limit)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch pentest messages: {e}");
+            Vec::new()
+        }
+    };
+
+    Ok(Json(ApiResponse {
+        data: messages,
+        total: Some(total),
+        page: Some(params.page),
+    }))
+}
+
+/// GET /api/v1/pentest/sessions/:id/findings — Get DAST findings for a pentest session
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn get_session_findings(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+    Query(params): Query<PaginationParams>,
+) -> Result<Json<ApiResponse<Vec<compliance_core::models::dast::DastFinding>>>, StatusCode> {
+    let _oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+
+    let skip = (params.page.saturating_sub(1)) * params.limit as u64;
+    let total = agent
+        .db
+        .dast_findings()
+        .count_documents(doc! { "session_id": &id })
+        .await
+        .unwrap_or(0);
+
+    let findings = match agent
+        .db
+        .dast_findings()
+        .find(doc! { "session_id": &id })
+        .sort(doc! { "created_at": -1 })
+        .skip(skip)
+        .limit(params.limit)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch pentest session findings: {e}");
+            Vec::new()
+        }
+    };
+
+    Ok(Json(ApiResponse {
+        data: findings,
+        total: Some(total),
+        page: Some(params.page),
+    }))
+}

compliance-agent/src/api/handlers/pentest_handlers/stats.rs

@@ -0,0 +1,102 @@
+use std::sync::Arc;
+
+use axum::extract::Extension;
+use axum::http::StatusCode;
+use axum::Json;
+use mongodb::bson::doc;
+
+use compliance_core::models::pentest::*;
+
+use crate::agent::ComplianceAgent;
+
+use super::super::dto::{collect_cursor_async, ApiResponse};
+
+type AgentExt = Extension<Arc<ComplianceAgent>>;
+
+/// GET /api/v1/pentest/stats — Aggregated pentest statistics
+#[tracing::instrument(skip_all)]
+pub async fn pentest_stats(
+    Extension(agent): AgentExt,
+) -> Result<Json<ApiResponse<PentestStats>>, StatusCode> {
+    let db = &agent.db;
+
+    let running_sessions = db
+        .pentest_sessions()
+        .count_documents(doc! { "status": "running" })
+        .await
+        .unwrap_or(0) as u32;
+
+    // Count DAST findings from pentest sessions
+    let total_vulnerabilities = db
+        .dast_findings()
+        .count_documents(doc! { "session_id": { "$exists": true, "$ne": null } })
+        .await
+        .unwrap_or(0) as u32;
+
+    // Aggregate tool invocations from all sessions
+    let sessions: Vec<PentestSession> = match db.pentest_sessions().find(doc! {}).await {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(_) => Vec::new(),
+    };
+
+    let total_tool_invocations: u32 = sessions.iter().map(|s| s.tool_invocations).sum();
+    let total_successes: u32 = sessions.iter().map(|s| s.tool_successes).sum();
+    let tool_success_rate = if total_tool_invocations == 0 {
+        100.0
+    } else {
+        (total_successes as f64 / total_tool_invocations as f64) * 100.0
+    };
+
+    // Severity distribution from pentest-related DAST findings
+    let critical = db
+        .dast_findings()
+        .count_documents(
+            doc! { "session_id": { "$exists": true, "$ne": null }, "severity": "critical" },
+        )
+        .await
+        .unwrap_or(0) as u32;
+    let high = db
+        .dast_findings()
+        .count_documents(
+            doc! { "session_id": { "$exists": true, "$ne": null }, "severity": "high" },
+        )
+        .await
+        .unwrap_or(0) as u32;
+    let medium = db
+        .dast_findings()
+        .count_documents(
+            doc! { "session_id": { "$exists": true, "$ne": null }, "severity": "medium" },
+        )
+        .await
+        .unwrap_or(0) as u32;
+    let low = db
+        .dast_findings()
+        .count_documents(doc! { "session_id": { "$exists": true, "$ne": null }, "severity": "low" })
+        .await
+        .unwrap_or(0) as u32;
+    let info = db
+        .dast_findings()
+        .count_documents(
+            doc! { "session_id": { "$exists": true, "$ne": null }, "severity": "info" },
+        )
+        .await
+        .unwrap_or(0) as u32;
+
+    Ok(Json(ApiResponse {
+        data: PentestStats {
+            running_sessions,
+            total_vulnerabilities,
+            total_tool_invocations,
+            tool_success_rate,
+            severity_distribution: SeverityDistribution {
+                critical,
+                high,
+                medium,
+                low,
+                info,
+            },
+        },
+        total: None,
+        page: None,
+    }))
+}

compliance-agent/src/api/handlers/pentest_handlers/stream.rs

@@ -0,0 +1,158 @@
+use std::convert::Infallible;
+use std::sync::Arc;
+use std::time::Duration;
+
+use axum::extract::{Extension, Path};
+use axum::http::StatusCode;
+use axum::response::sse::{Event, KeepAlive, Sse};
+use futures_util::stream;
+use mongodb::bson::doc;
+use tokio_stream::wrappers::BroadcastStream;
+use tokio_stream::StreamExt;
+
+use compliance_core::models::pentest::*;
+
+use crate::agent::ComplianceAgent;
+
+use super::super::dto::collect_cursor_async;
+
+type AgentExt = Extension<Arc<ComplianceAgent>>;
+
+/// GET /api/v1/pentest/sessions/:id/stream — SSE endpoint for real-time events
+///
+/// Replays stored messages/nodes as initial burst, then subscribes to the
+/// broadcast channel for live updates. Sends keepalive comments every 15s.
+#[tracing::instrument(skip_all, fields(session_id = %id))]
+pub async fn session_stream(
+    Extension(agent): AgentExt,
+    Path(id): Path<String>,
+) -> Result<Sse<impl futures_util::Stream<Item = Result<Event, Infallible>>>, StatusCode> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+
+    // Verify session exists
+    let _session = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?
+        .ok_or(StatusCode::NOT_FOUND)?;
+
+    // ── Initial burst: replay stored data ──────────────────────────
+
+    let mut initial_events: Vec<Result<Event, Infallible>> = Vec::new();
+
+    // Fetch recent messages for this session
+    let messages: Vec<PentestMessage> = match agent
+        .db
+        .pentest_messages()
+        .find(doc! { "session_id": &id })
+        .sort(doc! { "created_at": 1 })
+        .limit(100)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(_) => Vec::new(),
+    };
+
+    // Fetch recent attack chain nodes
+    let nodes: Vec<AttackChainNode> = match agent
+        .db
+        .attack_chain_nodes()
+        .find(doc! { "session_id": &id })
+        .sort(doc! { "started_at": 1 })
+        .limit(100)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(_) => Vec::new(),
+    };
+
+    for msg in &messages {
+        let event_data = serde_json::json!({
+            "type": "message",
+            "role": msg.role,
+            "content": msg.content,
+            "created_at": msg.created_at.to_rfc3339(),
+        });
+        if let Ok(data) = serde_json::to_string(&event_data) {
+            initial_events.push(Ok(Event::default().event("message").data(data)));
+        }
+    }
+
+    for node in &nodes {
+        let event_data = serde_json::json!({
+            "type": "tool_execution",
+            "node_id": node.node_id,
+            "tool_name": node.tool_name,
+            "status": node.status,
+            "findings_produced": node.findings_produced,
+        });
+        if let Ok(data) = serde_json::to_string(&event_data) {
+            initial_events.push(Ok(Event::default().event("tool").data(data)));
+        }
+    }
+
+    // Add current session status event
+    let session = agent
+        .db
+        .pentest_sessions()
+        .find_one(doc! { "_id": oid })
+        .await
+        .ok()
+        .flatten();
+
+    if let Some(s) = session {
+        let status_data = serde_json::json!({
+            "type": "status",
+            "status": s.status,
+            "findings_count": s.findings_count,
+            "tool_invocations": s.tool_invocations,
+        });
+        if let Ok(data) = serde_json::to_string(&status_data) {
+            initial_events.push(Ok(Event::default().event("status").data(data)));
+        }
+    }
+
+    // ── Live stream: subscribe to broadcast ────────────────────────
+
+    let live_stream = if let Some(rx) = agent.subscribe_session(&id) {
+        let broadcast = BroadcastStream::new(rx).filter_map(|result| match result {
+            Ok(event) => {
+                if let Ok(data) = serde_json::to_string(&event) {
+                    let event_type = match &event {
+                        PentestEvent::ToolStart { .. } => "tool_start",
+                        PentestEvent::ToolComplete { .. } => "tool_complete",
+                        PentestEvent::Finding { .. } => "finding",
+                        PentestEvent::Message { .. } => "message",
+                        PentestEvent::Complete { .. } => "complete",
+                        PentestEvent::Error { .. } => "error",
+                        PentestEvent::Thinking { .. } => "thinking",
+                        PentestEvent::Paused => "paused",
+                        PentestEvent::Resumed => "resumed",
+                    };
+                    Some(Ok(Event::default().event(event_type).data(data)))
+                } else {
+                    None
+                }
+            }
+            Err(_) => None,
+        });
+        // Box to unify types
+        Box::pin(broadcast)
+            as std::pin::Pin<Box<dyn futures_util::Stream<Item = Result<Event, Infallible>> + Send>>
+    } else {
+        // No active broadcast — return empty stream
+        Box::pin(stream::empty())
+            as std::pin::Pin<Box<dyn futures_util::Stream<Item = Result<Event, Infallible>> + Send>>
+    };
+
+    // Chain initial burst + live stream
+    let combined = stream::iter(initial_events).chain(live_stream);
+
+    Ok(Sse::new(combined).keep_alive(
+        KeepAlive::new()
+            .interval(Duration::from_secs(15))
+            .text("keepalive"),
+    ))
+}

compliance-agent/src/api/handlers/repos.rs

@@ -0,0 +1,241 @@
+use axum::extract::{Extension, Path, Query};
+use axum::http::StatusCode;
+use axum::Json;
+use mongodb::bson::doc;
+
+use super::dto::*;
+use compliance_core::models::*;
+
+#[tracing::instrument(skip_all)]
+pub async fn list_repositories(
+    Extension(agent): AgentExt,
+    Query(params): Query<PaginationParams>,
+) -> ApiResult<Vec<TrackedRepository>> {
+    let db = &agent.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,
+    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;
+
+    agent
+        .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,
+    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 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 = agent
+        .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,
+    Path(id): Path<String>,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    let agent_clone = (*agent).clone();
+    tokio::spawn(async move {
+        if let Err(e) = agent_clone.run_scan(&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,
+    Path(id): Path<String>,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+    let repo = agent
+        .db
+        .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,
+    Path(id): Path<String>,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    let oid = mongodb::bson::oid::ObjectId::parse_str(&id).map_err(|_| StatusCode::BAD_REQUEST)?;
+    let db = &agent.db;
+
+    // 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;
+
+    Ok(Json(serde_json::json!({ "status": "deleted" })))
+}

compliance-agent/src/api/handlers/sbom.rs

@@ -0,0 +1,379 @@
+use axum::extract::{Extension, Query};
+use axum::http::{header, StatusCode};
+use axum::response::IntoResponse;
+use axum::Json;
+use mongodb::bson::doc;
+
+use super::dto::*;
+use compliance_core::models::SbomEntry;
+
+const COPYLEFT_LICENSES: &[&str] = &[
+    "GPL-2.0",
+    "GPL-2.0-only",
+    "GPL-2.0-or-later",
+    "GPL-3.0",
+    "GPL-3.0-only",
+    "GPL-3.0-or-later",
+    "AGPL-3.0",
+    "AGPL-3.0-only",
+    "AGPL-3.0-or-later",
+    "LGPL-2.1",
+    "LGPL-2.1-only",
+    "LGPL-2.1-or-later",
+    "LGPL-3.0",
+    "LGPL-3.0-only",
+    "LGPL-3.0-or-later",
+    "MPL-2.0",
+];
+
+#[tracing::instrument(skip_all)]
+pub async fn sbom_filters(
+    Extension(agent): AgentExt,
+) -> Result<Json<serde_json::Value>, StatusCode> {
+    let db = &agent.db;
+
+    let managers: Vec<String> = db
+        .sbom_entries()
+        .distinct("package_manager", doc! {})
+        .await
+        .unwrap_or_default()
+        .into_iter()
+        .filter_map(|v| v.as_str().map(|s| s.to_string()))
+        .filter(|s| !s.is_empty() && s != "unknown" && s != "file")
+        .collect();
+
+    let licenses: Vec<String> = db
+        .sbom_entries()
+        .distinct("license", doc! {})
+        .await
+        .unwrap_or_default()
+        .into_iter()
+        .filter_map(|v| v.as_str().map(|s| s.to_string()))
+        .filter(|s| !s.is_empty())
+        .collect();
+
+    Ok(Json(serde_json::json!({
+        "package_managers": managers,
+        "licenses": licenses,
+    })))
+}
+
+#[tracing::instrument(skip_all, fields(repo_id = ?filter.repo_id, package_manager = ?filter.package_manager))]
+pub async fn list_sbom(
+    Extension(agent): AgentExt,
+    Query(filter): Query<SbomFilter>,
+) -> ApiResult<Vec<SbomEntry>> {
+    let db = &agent.db;
+    let mut query = doc! {};
+
+    if let Some(repo_id) = &filter.repo_id {
+        query.insert("repo_id", repo_id);
+    }
+    if let Some(pm) = &filter.package_manager {
+        query.insert("package_manager", pm);
+    }
+    if let Some(q) = &filter.q {
+        if !q.is_empty() {
+            query.insert("name", doc! { "$regex": q, "$options": "i" });
+        }
+    }
+    if let Some(has_vulns) = filter.has_vulns {
+        if has_vulns {
+            query.insert("known_vulnerabilities", doc! { "$exists": true, "$ne": [] });
+        } else {
+            query.insert("known_vulnerabilities", doc! { "$size": 0 });
+        }
+    }
+    if let Some(license) = &filter.license {
+        query.insert("license", license);
+    }
+
+    let skip = (filter.page.saturating_sub(1)) * filter.limit as u64;
+    let total = db
+        .sbom_entries()
+        .count_documents(query.clone())
+        .await
+        .unwrap_or(0);
+
+    let entries = match db
+        .sbom_entries()
+        .find(query)
+        .sort(doc! { "name": 1 })
+        .skip(skip)
+        .limit(filter.limit)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch SBOM entries: {e}");
+            Vec::new()
+        }
+    };
+
+    Ok(Json(ApiResponse {
+        data: entries,
+        total: Some(total),
+        page: Some(filter.page),
+    }))
+}
+
+#[tracing::instrument(skip_all)]
+pub async fn export_sbom(
+    Extension(agent): AgentExt,
+    Query(params): Query<SbomExportParams>,
+) -> Result<impl IntoResponse, StatusCode> {
+    let db = &agent.db;
+    let entries: Vec<SbomEntry> = match db
+        .sbom_entries()
+        .find(doc! { "repo_id": &params.repo_id })
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch SBOM entries for export: {e}");
+            Vec::new()
+        }
+    };
+
+    let body = if params.format == "spdx" {
+        // SPDX 2.3 format
+        let packages: Vec<serde_json::Value> = entries
+            .iter()
+            .enumerate()
+            .map(|(i, e)| {
+                serde_json::json!({
+                    "SPDXID": format!("SPDXRef-Package-{i}"),
+                    "name": e.name,
+                    "versionInfo": e.version,
+                    "downloadLocation": "NOASSERTION",
+                    "licenseConcluded": e.license.as_deref().unwrap_or("NOASSERTION"),
+                    "externalRefs": e.purl.as_ref().map(|p| vec![serde_json::json!({
+                        "referenceCategory": "PACKAGE-MANAGER",
+                        "referenceType": "purl",
+                        "referenceLocator": p,
+                    })]).unwrap_or_default(),
+                })
+            })
+            .collect();
+
+        serde_json::json!({
+            "spdxVersion": "SPDX-2.3",
+            "dataLicense": "CC0-1.0",
+            "SPDXID": "SPDXRef-DOCUMENT",
+            "name": format!("sbom-{}", params.repo_id),
+            "documentNamespace": format!("https://compliance-scanner/sbom/{}", params.repo_id),
+            "packages": packages,
+        })
+    } else {
+        // CycloneDX 1.5 format
+        let components: Vec<serde_json::Value> = entries
+            .iter()
+            .map(|e| {
+                let mut comp = serde_json::json!({
+                    "type": "library",
+                    "name": e.name,
+                    "version": e.version,
+                    "group": e.package_manager,
+                });
+                if let Some(purl) = &e.purl {
+                    comp["purl"] = serde_json::Value::String(purl.clone());
+                }
+                if let Some(license) = &e.license {
+                    comp["licenses"] = serde_json::json!([{ "license": { "id": license } }]);
+                }
+                if !e.known_vulnerabilities.is_empty() {
+                    comp["vulnerabilities"] = serde_json::json!(
+                        e.known_vulnerabilities.iter().map(|v| serde_json::json!({
+                            "id": v.id,
+                            "source": { "name": v.source },
+                            "ratings": v.severity.as_ref().map(|s| vec![serde_json::json!({"severity": s})]).unwrap_or_default(),
+                        })).collect::<Vec<_>>()
+                    );
+                }
+                comp
+            })
+            .collect();
+
+        serde_json::json!({
+            "bomFormat": "CycloneDX",
+            "specVersion": "1.5",
+            "version": 1,
+            "metadata": {
+                "component": {
+                    "type": "application",
+                    "name": format!("repo-{}", params.repo_id),
+                }
+            },
+            "components": components,
+        })
+    };
+
+    let json_str =
+        serde_json::to_string_pretty(&body).map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
+    let filename = if params.format == "spdx" {
+        format!("sbom-{}-spdx.json", params.repo_id)
+    } else {
+        format!("sbom-{}-cyclonedx.json", params.repo_id)
+    };
+
+    let disposition = format!("attachment; filename=\"{filename}\"");
+    Ok((
+        [
+            (
+                header::CONTENT_TYPE,
+                header::HeaderValue::from_static("application/json"),
+            ),
+            (
+                header::CONTENT_DISPOSITION,
+                header::HeaderValue::from_str(&disposition)
+                    .unwrap_or_else(|_| header::HeaderValue::from_static("attachment")),
+            ),
+        ],
+        json_str,
+    ))
+}
+
+#[tracing::instrument(skip_all)]
+pub async fn license_summary(
+    Extension(agent): AgentExt,
+    Query(params): Query<SbomFilter>,
+) -> ApiResult<Vec<LicenseSummary>> {
+    let db = &agent.db;
+    let mut query = doc! {};
+    if let Some(repo_id) = &params.repo_id {
+        query.insert("repo_id", repo_id);
+    }
+
+    let entries: Vec<SbomEntry> = match db.sbom_entries().find(query).await {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch SBOM entries for license summary: {e}");
+            Vec::new()
+        }
+    };
+
+    let mut license_map: std::collections::HashMap<String, Vec<String>> =
+        std::collections::HashMap::new();
+    for entry in &entries {
+        let lic = entry.license.as_deref().unwrap_or("Unknown").to_string();
+        license_map.entry(lic).or_default().push(entry.name.clone());
+    }
+
+    let mut summaries: Vec<LicenseSummary> = license_map
+        .into_iter()
+        .map(|(license, packages)| {
+            let is_copyleft = COPYLEFT_LICENSES
+                .iter()
+                .any(|c| license.to_uppercase().contains(&c.to_uppercase()));
+            LicenseSummary {
+                license,
+                count: packages.len() as u64,
+                is_copyleft,
+                packages,
+            }
+        })
+        .collect();
+    summaries.sort_by(|a, b| b.count.cmp(&a.count));
+
+    Ok(Json(ApiResponse {
+        data: summaries,
+        total: None,
+        page: None,
+    }))
+}
+
+#[tracing::instrument(skip_all)]
+pub async fn sbom_diff(
+    Extension(agent): AgentExt,
+    Query(params): Query<SbomDiffParams>,
+) -> ApiResult<SbomDiffResult> {
+    let db = &agent.db;
+
+    let entries_a: Vec<SbomEntry> = match db
+        .sbom_entries()
+        .find(doc! { "repo_id": &params.repo_a })
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch SBOM entries for repo_a: {e}");
+            Vec::new()
+        }
+    };
+
+    let entries_b: Vec<SbomEntry> = match db
+        .sbom_entries()
+        .find(doc! { "repo_id": &params.repo_b })
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch SBOM entries for repo_b: {e}");
+            Vec::new()
+        }
+    };
+
+    // Build maps by (name, package_manager) -> version
+    let map_a: std::collections::HashMap<(String, String), String> = entries_a
+        .iter()
+        .map(|e| {
+            (
+                (e.name.clone(), e.package_manager.clone()),
+                e.version.clone(),
+            )
+        })
+        .collect();
+    let map_b: std::collections::HashMap<(String, String), String> = entries_b
+        .iter()
+        .map(|e| {
+            (
+                (e.name.clone(), e.package_manager.clone()),
+                e.version.clone(),
+            )
+        })
+        .collect();
+
+    let mut only_in_a = Vec::new();
+    let mut version_changed = Vec::new();
+    let mut common_count: u64 = 0;
+
+    for (key, ver_a) in &map_a {
+        match map_b.get(key) {
+            None => only_in_a.push(SbomDiffEntry {
+                name: key.0.clone(),
+                version: ver_a.clone(),
+                package_manager: key.1.clone(),
+            }),
+            Some(ver_b) if ver_a != ver_b => {
+                version_changed.push(SbomVersionDiff {
+                    name: key.0.clone(),
+                    package_manager: key.1.clone(),
+                    version_a: ver_a.clone(),
+                    version_b: ver_b.clone(),
+                });
+            }
+            Some(_) => common_count += 1,
+        }
+    }
+
+    let only_in_b: Vec<SbomDiffEntry> = map_b
+        .iter()
+        .filter(|(key, _)| !map_a.contains_key(key))
+        .map(|(key, ver)| SbomDiffEntry {
+            name: key.0.clone(),
+            version: ver.clone(),
+            package_manager: key.1.clone(),
+        })
+        .collect();
+
+    Ok(Json(ApiResponse {
+        data: SbomDiffResult {
+            only_in_a,
+            only_in_b,
+            version_changed,
+            common_count,
+        },
+        total: None,
+        page: None,
+    }))
+}

compliance-agent/src/api/handlers/scans.rs

@@ -0,0 +1,37 @@
+use axum::extract::{Extension, Query};
+use axum::Json;
+use mongodb::bson::doc;
+
+use super::dto::*;
+use compliance_core::models::ScanRun;
+
+#[tracing::instrument(skip_all)]
+pub async fn list_scan_runs(
+    Extension(agent): AgentExt,
+    Query(params): Query<PaginationParams>,
+) -> ApiResult<Vec<ScanRun>> {
+    let db = &agent.db;
+    let skip = (params.page.saturating_sub(1)) * params.limit as u64;
+    let total = db.scan_runs().count_documents(doc! {}).await.unwrap_or(0);
+
+    let scans = match db
+        .scan_runs()
+        .find(doc! {})
+        .sort(doc! { "started_at": -1 })
+        .skip(skip)
+        .limit(params.limit)
+        .await
+    {
+        Ok(cursor) => collect_cursor_async(cursor).await,
+        Err(e) => {
+            tracing::warn!("Failed to fetch scan runs: {e}");
+            Vec::new()
+        }
+    };
+
+    Ok(Json(ApiResponse {
+        data: scans,
+        total: Some(total),
+        page: Some(params.page),
+    }))
+}

compliance-agent/src/api/mod.rs

@@ -1,3 +1,4 @@
+pub mod auth_middleware;
 pub mod handlers;
 pub mod routes;
 pub mod server;

compliance-agent/src/api/routes.rs

@@ -2,11 +2,16 @@ use axum::routing::{delete, get, patch, post};
 use axum::Router;
 
 use crate::api::handlers;
+use crate::webhooks;
 
 pub fn build_router() -> Router {
     Router::new()
         .route("/api/v1/health", get(handlers::health))
         .route("/api/v1/stats/overview", get(handlers::stats_overview))
+        .route(
+            "/api/v1/settings/ssh-public-key",
+            get(handlers::get_ssh_public_key),
+        )
         .route("/api/v1/repositories", get(handlers::list_repositories))
         .route("/api/v1/repositories", post(handlers::add_repository))
         .route(
@@ -15,7 +20,11 @@ pub fn build_router() -> Router {
         )
         .route(
             "/api/v1/repositories/{id}",
-            delete(handlers::delete_repository),
+            delete(handlers::delete_repository).patch(handlers::update_repository),
+        )
+        .route(
+            "/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))
@@ -23,7 +32,16 @@ pub fn build_router() -> Router {
             "/api/v1/findings/{id}/status",
             patch(handlers::update_finding_status),
         )
+        .route(
+            "/api/v1/findings/bulk-status",
+            patch(handlers::bulk_update_finding_status),
+        )
+        .route(
+            "/api/v1/findings/{id}/feedback",
+            patch(handlers::update_finding_feedback),
+        )
         .route("/api/v1/sbom", get(handlers::list_sbom))
+        .route("/api/v1/sbom/filters", get(handlers::sbom_filters))
         .route("/api/v1/sbom/export", get(handlers::export_sbom))
         .route("/api/v1/sbom/licenses", get(handlers::license_summary))
         .route("/api/v1/sbom/diff", get(handlers::sbom_diff))
@@ -81,4 +99,70 @@ pub fn build_router() -> Router {
             "/api/v1/chat/{repo_id}/status",
             get(handlers::chat::embedding_status),
         )
+        // Pentest API endpoints
+        .route(
+            "/api/v1/pentest/lookup-repo",
+            get(handlers::pentest::lookup_repo),
+        )
+        .route(
+            "/api/v1/pentest/sessions",
+            get(handlers::pentest::list_sessions).post(handlers::pentest::create_session),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}",
+            get(handlers::pentest::get_session),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/chat",
+            post(handlers::pentest::send_message),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/stop",
+            post(handlers::pentest::stop_session),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/pause",
+            post(handlers::pentest::pause_session),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/resume",
+            post(handlers::pentest::resume_session),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/stream",
+            get(handlers::pentest::session_stream),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/attack-chain",
+            get(handlers::pentest::get_attack_chain),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/messages",
+            get(handlers::pentest::get_messages),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/findings",
+            get(handlers::pentest::get_session_findings),
+        )
+        .route(
+            "/api/v1/pentest/sessions/{id}/export",
+            post(handlers::pentest::export_session_report),
+        )
+        .route(
+            "/api/v1/pentest/stats",
+            get(handlers::pentest::pentest_stats),
+        )
+        // Webhook endpoints (proxied through dashboard)
+        .route(
+            "/webhook/github/{repo_id}",
+            post(webhooks::github::handle_github_webhook),
+        )
+        .route(
+            "/webhook/gitlab/{repo_id}",
+            post(webhooks::gitlab::handle_gitlab_webhook),
+        )
+        .route(
+            "/webhook/gitea/{repo_id}",
+            post(webhooks::gitea::handle_gitea_webhook),
+        )
 }

compliance-agent/src/api/server.rs

@@ -1,19 +1,37 @@
 use std::sync::Arc;
 
-use axum::Extension;
+use axum::{middleware, Extension};
+use tokio::sync::RwLock;
 use tower_http::cors::CorsLayer;
 use tower_http::trace::TraceLayer;
 
 use crate::agent::ComplianceAgent;
+use crate::api::auth_middleware::{require_jwt_auth, JwksState};
 use crate::api::routes;
 use crate::error::AgentError;
 
 pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), AgentError> {
-    let app = routes::build_router()
+    let mut app = routes::build_router()
-        .layer(Extension(Arc::new(agent)))
+        .layer(Extension(Arc::new(agent.clone())))
         .layer(CorsLayer::permissive())
         .layer(TraceLayer::new_for_http());
 
+    if let (Some(kc_url), Some(kc_realm)) =
+        (&agent.config.keycloak_url, &agent.config.keycloak_realm)
+    {
+        let jwks_url = format!("{kc_url}/realms/{kc_realm}/protocol/openid-connect/certs");
+        let jwks_state = JwksState {
+            jwks: Arc::new(RwLock::new(None)),
+            jwks_url,
+        };
+        tracing::info!("Keycloak JWT auth enabled for realm '{kc_realm}'");
+        app = app
+            .layer(Extension(jwks_state))
+            .layer(middleware::from_fn(require_jwt_auth));
+    } else {
+        tracing::warn!("Keycloak not configured - API endpoints are unprotected");
+    }
+
     let addr = format!("0.0.0.0:{port}");
     let listener = tokio::net::TcpListener::bind(&addr)
         .await

compliance-agent/src/config.rs

@@ -45,5 +45,19 @@ pub fn load_config() -> Result<AgentConfig, AgentError> {
             .unwrap_or_else(|| "0 0 0 * * *".to_string()),
         git_clone_base_path: env_var_opt("GIT_CLONE_BASE_PATH")
             .unwrap_or_else(|| "/tmp/compliance-scanner/repos".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"),
+        keycloak_realm: env_var_opt("KEYCLOAK_REALM"),
+        keycloak_admin_username: env_var_opt("KEYCLOAK_ADMIN_USERNAME"),
+        keycloak_admin_password: env_secret_opt("KEYCLOAK_ADMIN_PASSWORD"),
+        pentest_verification_email: env_var_opt("PENTEST_VERIFICATION_EMAIL"),
+        pentest_imap_host: env_var_opt("PENTEST_IMAP_HOST"),
+        pentest_imap_port: env_var_opt("PENTEST_IMAP_PORT").and_then(|p| p.parse().ok()),
+        pentest_imap_tls: env_var_opt("PENTEST_IMAP_TLS")
+            .map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
+            .unwrap_or(true),
+        pentest_imap_username: env_var_opt("PENTEST_IMAP_USERNAME"),
+        pentest_imap_password: env_secret_opt("PENTEST_IMAP_PASSWORD"),
     })
 }

compliance-agent/src/database.rs

@@ -166,6 +166,38 @@ impl Database {
             )
             .await?;
 
+        // pentest_sessions: compound (target_id, started_at DESC)
+        self.pentest_sessions()
+            .create_index(
+                IndexModel::builder()
+                    .keys(doc! { "target_id": 1, "started_at": -1 })
+                    .build(),
+            )
+            .await?;
+
+        // pentest_sessions: status index
+        self.pentest_sessions()
+            .create_index(IndexModel::builder().keys(doc! { "status": 1 }).build())
+            .await?;
+
+        // attack_chain_nodes: compound (session_id, node_id)
+        self.attack_chain_nodes()
+            .create_index(
+                IndexModel::builder()
+                    .keys(doc! { "session_id": 1, "node_id": 1 })
+                    .build(),
+            )
+            .await?;
+
+        // pentest_messages: compound (session_id, created_at)
+        self.pentest_messages()
+            .create_index(
+                IndexModel::builder()
+                    .keys(doc! { "session_id": 1, "created_at": 1 })
+                    .build(),
+            )
+            .await?;
+
         tracing::info!("Database indexes ensured");
         Ok(())
     }
@@ -235,6 +267,19 @@ impl Database {
         self.inner.collection("embedding_builds")
     }
 
+    // Pentest collections
+    pub fn pentest_sessions(&self) -> Collection<PentestSession> {
+        self.inner.collection("pentest_sessions")
+    }
+
+    pub fn attack_chain_nodes(&self) -> Collection<AttackChainNode> {
+        self.inner.collection("attack_chain_nodes")
+    }
+
+    pub fn pentest_messages(&self) -> Collection<PentestMessage> {
+        self.inner.collection("pentest_messages")
+    }
+
     #[allow(dead_code)]
     pub fn raw_collection(&self, name: &str) -> Collection<mongodb::bson::Document> {
         self.inner.collection(name)

compliance-agent/src/llm/client.rs

@@ -1,66 +1,15 @@
 use secrecy::{ExposeSecret, SecretString};
-use serde::{Deserialize, Serialize};
 
+use super::types::*;
 use crate::error::AgentError;
 
 #[derive(Clone)]
 pub struct LlmClient {
-    base_url: String,
+    pub(crate) base_url: String,
-    api_key: SecretString,
+    pub(crate) api_key: SecretString,
-    model: String,
+    pub(crate) model: String,
-    embed_model: String,
+    pub(crate) embed_model: String,
-    http: reqwest::Client,
+    pub(crate) http: reqwest::Client,
-}
-
-#[derive(Serialize)]
-struct ChatMessage {
-    role: String,
-    content: String,
-}
-
-#[derive(Serialize)]
-struct ChatCompletionRequest {
-    model: String,
-    messages: Vec<ChatMessage>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    temperature: Option<f64>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    max_tokens: Option<u32>,
-}
-
-#[derive(Deserialize)]
-struct ChatCompletionResponse {
-    choices: Vec<ChatChoice>,
-}
-
-#[derive(Deserialize)]
-struct ChatChoice {
-    message: ChatResponseMessage,
-}
-
-#[derive(Deserialize)]
-struct ChatResponseMessage {
-    content: String,
-}
-
-/// Request body for the embeddings API
-#[derive(Serialize)]
-struct EmbeddingRequest {
-    model: String,
-    input: Vec<String>,
-}
-
-/// Response from the embeddings API
-#[derive(Deserialize)]
-struct EmbeddingResponse {
-    data: Vec<EmbeddingData>,
-}
-
-/// A single embedding result
-#[derive(Deserialize)]
-struct EmbeddingData {
-    embedding: Vec<f64>,
-    index: usize,
 }
 
 impl LlmClient {
@@ -79,102 +28,142 @@ impl LlmClient {
         }
     }
 
-    pub fn embed_model(&self) -> &str {
+    pub(crate) fn chat_url(&self) -> String {
-        &self.embed_model
+        format!(
+            "{}/v1/chat/completions",
+            self.base_url.trim_end_matches('/')
+        )
     }
 
+    pub(crate) fn auth_header(&self) -> Option<String> {
+        let key = self.api_key.expose_secret();
+        if key.is_empty() {
+            None
+        } else {
+            Some(format!("Bearer {key}"))
+        }
+    }
+
+    /// Simple chat: system + user prompt → text response
     pub async fn chat(
         &self,
         system_prompt: &str,
         user_prompt: &str,
         temperature: Option<f64>,
     ) -> Result<String, AgentError> {
-        let url = format!(
+        let messages = vec![
-            "{}/v1/chat/completions",
+            ChatMessage {
-            self.base_url.trim_end_matches('/')
+                role: "system".to_string(),
-        );
+                content: Some(system_prompt.to_string()),
+                tool_calls: None,
+                tool_call_id: None,
+            },
+            ChatMessage {
+                role: "user".to_string(),
+                content: Some(user_prompt.to_string()),
+                tool_calls: None,
+                tool_call_id: None,
+            },
+        ];
 
         let request_body = ChatCompletionRequest {
             model: self.model.clone(),
-            messages: vec![
+            messages,
-                ChatMessage {
-                    role: "system".to_string(),
-                    content: system_prompt.to_string(),
-                },
-                ChatMessage {
-                    role: "user".to_string(),
-                    content: user_prompt.to_string(),
-                },
-            ],
             temperature,
             max_tokens: Some(4096),
+            tools: None,
         };
 
-        let mut req = self
+        self.send_chat_request(&request_body).await.map(|resp| {
-            .http
+            match resp {
-            .post(&url)
+                LlmResponse::Content(c) => c,
-            .header("content-type", "application/json")
+                LlmResponse::ToolCalls { .. } => String::new(), // shouldn't happen without tools
-            .json(&request_body);
+            }
-
+        })
-        let key = self.api_key.expose_secret();
-        if !key.is_empty() {
-            req = req.header("Authorization", format!("Bearer {key}"));
-        }
-
-        let resp = req
-            .send()
-            .await
-            .map_err(|e| AgentError::Other(format!("LiteLLM request failed: {e}")))?;
-
-        if !resp.status().is_success() {
-            let status = resp.status();
-            let body = resp.text().await.unwrap_or_default();
-            return Err(AgentError::Other(format!(
-                "LiteLLM returned {status}: {body}"
-            )));
-        }
-
-        let body: ChatCompletionResponse = resp
-            .json()
-            .await
-            .map_err(|e| AgentError::Other(format!("Failed to parse LiteLLM response: {e}")))?;
-
-        body.choices
-            .first()
-            .map(|c| c.message.content.clone())
-            .ok_or_else(|| AgentError::Other("Empty response from LiteLLM".to_string()))
     }
 
+    /// Chat with a list of (role, content) messages → text response
     #[allow(dead_code)]
     pub async fn chat_with_messages(
         &self,
         messages: Vec<(String, String)>,
         temperature: Option<f64>,
     ) -> Result<String, AgentError> {
-        let url = format!(
+        let messages = messages
-            "{}/v1/chat/completions",
+            .into_iter()
-            self.base_url.trim_end_matches('/')
+            .map(|(role, content)| ChatMessage {
-        );
+                role,
+                content: Some(content),
+                tool_calls: None,
+                tool_call_id: None,
+            })
+            .collect();
 
         let request_body = ChatCompletionRequest {
             model: self.model.clone(),
-            messages: messages
+            messages,
-                .into_iter()
-                .map(|(role, content)| ChatMessage { role, content })
-                .collect(),
             temperature,
             max_tokens: Some(4096),
+            tools: None,
         };
 
+        self.send_chat_request(&request_body)
+            .await
+            .map(|resp| match resp {
+                LlmResponse::Content(c) => c,
+                LlmResponse::ToolCalls { .. } => String::new(),
+            })
+    }
+
+    /// Chat with tool definitions — returns either content or tool calls.
+    /// Use this for the AI pentest orchestrator loop.
+    pub async fn chat_with_tools(
+        &self,
+        messages: Vec<ChatMessage>,
+        tools: &[ToolDefinition],
+        temperature: Option<f64>,
+        max_tokens: Option<u32>,
+    ) -> Result<LlmResponse, AgentError> {
+        let tool_payloads: Vec<ToolDefinitionPayload> = tools
+            .iter()
+            .map(|t| ToolDefinitionPayload {
+                r#type: "function".to_string(),
+                function: ToolFunctionPayload {
+                    name: t.name.clone(),
+                    description: t.description.clone(),
+                    parameters: t.parameters.clone(),
+                },
+            })
+            .collect();
+
+        let request_body = ChatCompletionRequest {
+            model: self.model.clone(),
+            messages,
+            temperature,
+            max_tokens: Some(max_tokens.unwrap_or(8192)),
+            tools: if tool_payloads.is_empty() {
+                None
+            } else {
+                Some(tool_payloads)
+            },
+        };
+
+        self.send_chat_request(&request_body).await
+    }
+
+    /// Internal method to send a chat completion request and parse the response
+    async fn send_chat_request(
+        &self,
+        request_body: &ChatCompletionRequest,
+    ) -> Result<LlmResponse, AgentError> {
         let mut req = self
             .http
-            .post(&url)
+            .post(self.chat_url())
             .header("content-type", "application/json")
-            .json(&request_body);
+            .json(request_body);
 
-        let key = self.api_key.expose_secret();
+        if let Some(auth) = self.auth_header() {
-        if !key.is_empty() {
+            req = req.header("Authorization", auth);
-            req = req.header("Authorization", format!("Bearer {key}"));
         }
 
         let resp = req
@@ -195,54 +184,34 @@ impl LlmClient {
             .await
             .map_err(|e| AgentError::Other(format!("Failed to parse LiteLLM response: {e}")))?;
 
-        body.choices
+        let choice = body
+            .choices
             .first()
-            .map(|c| c.message.content.clone())
+            .ok_or_else(|| AgentError::Other("Empty response from LiteLLM".to_string()))?;
-            .ok_or_else(|| AgentError::Other("Empty response from LiteLLM".to_string()))
-    }
 
-    /// Generate embeddings for a batch of texts
+        // Check for tool calls first
-    pub async fn embed(&self, texts: Vec<String>) -> Result<Vec<Vec<f64>>, AgentError> {
+        if let Some(tool_calls) = &choice.message.tool_calls {
-        let url = format!("{}/v1/embeddings", self.base_url.trim_end_matches('/'));
+            if !tool_calls.is_empty() {
-
+                let calls: Vec<LlmToolCall> = tool_calls
-        let request_body = EmbeddingRequest {
+                    .iter()
-            model: self.embed_model.clone(),
+                    .map(|tc| {
-            input: texts,
+                        let arguments = serde_json::from_str(&tc.function.arguments)
-        };
+                            .unwrap_or(serde_json::Value::Object(serde_json::Map::new()));
-
+                        LlmToolCall {
-        let mut req = self
+                            id: tc.id.clone(),
-            .http
+                            name: tc.function.name.clone(),
-            .post(&url)
+                            arguments,
-            .header("content-type", "application/json")
+                        }
-            .json(&request_body);
+                    })
-
+                    .collect();
-        let key = self.api_key.expose_secret();
+                // Capture any reasoning text the LLM included alongside tool calls
-        if !key.is_empty() {
+                let reasoning = choice.message.content.clone().unwrap_or_default();
-            req = req.header("Authorization", format!("Bearer {key}"));
+                return Ok(LlmResponse::ToolCalls { calls, reasoning });
+            }
         }
 
-        let resp = req
+        // Otherwise return content
-            .send()
+        let content = choice.message.content.clone().unwrap_or_default();
-            .await
+        Ok(LlmResponse::Content(content))
-            .map_err(|e| AgentError::Other(format!("Embedding request failed: {e}")))?;
-
-        if !resp.status().is_success() {
-            let status = resp.status();
-            let body = resp.text().await.unwrap_or_default();
-            return Err(AgentError::Other(format!(
-                "Embedding API returned {status}: {body}"
-            )));
-        }
-
-        let body: EmbeddingResponse = resp
-            .json()
-            .await
-            .map_err(|e| AgentError::Other(format!("Failed to parse embedding response: {e}")))?;
-
-        // Sort by index to maintain input order
-        let mut data = body.data;
-        data.sort_by_key(|d| d.index);
-
-        Ok(data.into_iter().map(|d| d.embedding).collect())
     }
 }

compliance-agent/src/llm/embedding.rs

@@ -0,0 +1,74 @@
+use serde::{Deserialize, Serialize};
+
+use super::client::LlmClient;
+use crate::error::AgentError;
+
+// ── Embedding types ────────────────────────────────────────────
+
+#[derive(Serialize)]
+struct EmbeddingRequest {
+    model: String,
+    input: Vec<String>,
+}
+
+#[derive(Deserialize)]
+struct EmbeddingResponse {
+    data: Vec<EmbeddingData>,
+}
+
+#[derive(Deserialize)]
+struct EmbeddingData {
+    embedding: Vec<f64>,
+    index: usize,
+}
+
+// ── Embedding implementation ───────────────────────────────────
+
+impl LlmClient {
+    pub fn embed_model(&self) -> &str {
+        &self.embed_model
+    }
+
+    /// Generate embeddings for a batch of texts
+    pub async fn embed(&self, texts: Vec<String>) -> Result<Vec<Vec<f64>>, AgentError> {
+        let url = format!("{}/v1/embeddings", self.base_url.trim_end_matches('/'));
+
+        let request_body = EmbeddingRequest {
+            model: self.embed_model.clone(),
+            input: texts,
+        };
+
+        let mut req = self
+            .http
+            .post(&url)
+            .header("content-type", "application/json")
+            .json(&request_body);
+
+        if let Some(auth) = self.auth_header() {
+            req = req.header("Authorization", auth);
+        }
+
+        let resp = req
+            .send()
+            .await
+            .map_err(|e| AgentError::Other(format!("Embedding request failed: {e}")))?;
+
+        if !resp.status().is_success() {
+            let status = resp.status();
+            let body = resp.text().await.unwrap_or_default();
+            return Err(AgentError::Other(format!(
+                "Embedding API returned {status}: {body}"
+            )));
+        }
+
+        let body: EmbeddingResponse = resp
+            .json()
+            .await
+            .map_err(|e| AgentError::Other(format!("Failed to parse embedding response: {e}")))?;
+
+        let mut data = body.data;
+        data.sort_by_key(|d| d.index);
+
+        Ok(data.into_iter().map(|d| d.embedding).collect())
+    }
+}

compliance-agent/src/llm/mod.rs

@@ -1,10 +1,16 @@
 pub mod client;
 #[allow(dead_code)]
 pub mod descriptions;
+pub mod embedding;
 #[allow(dead_code)]
 pub mod fixes;
 #[allow(dead_code)]
 pub mod pr_review;
+pub mod review_prompts;
 pub mod triage;
+pub mod types;
 
 pub use client::LlmClient;
+pub use types::{
+    ChatMessage, LlmResponse, ToolCallRequest, ToolCallRequestFunction, ToolDefinition,
+};

compliance-agent/src/llm/review_prompts.rs

@@ -0,0 +1,77 @@
+// System prompts for multi-pass LLM code review.
+// Each pass focuses on a different aspect to avoid overloading a single prompt.
+
+pub const LOGIC_REVIEW_PROMPT: &str = r#"You are a senior software engineer reviewing code changes. Focus ONLY on logic and correctness issues.
+
+Look for:
+- Off-by-one errors, wrong comparisons, missing edge cases
+- Incorrect control flow (unreachable code, missing returns, wrong loop conditions)
+- Race conditions or concurrency bugs
+- Resource leaks (unclosed handles, missing cleanup)
+- Wrong variable used (copy-paste errors)
+- Incorrect error handling (swallowed errors, wrong error type)
+
+Ignore: style, naming, formatting, documentation, minor improvements.
+
+For each issue found, respond with a JSON array:
+[{"title": "...", "description": "...", "severity": "high|medium|low", "file": "...", "line": N, "suggestion": "..."}]
+
+If no issues found, respond with: []"#;
+
+pub const SECURITY_REVIEW_PROMPT: &str = r#"You are a security engineer reviewing code changes. Focus ONLY on security vulnerabilities.
+
+Look for:
+- Injection vulnerabilities (SQL, command, XSS, template injection)
+- Authentication/authorization bypasses
+- Sensitive data exposure (logging secrets, hardcoded credentials)
+- Insecure cryptography (weak algorithms, predictable randomness)
+- Path traversal, SSRF, open redirects
+- Unsafe deserialization
+- Missing input validation at trust boundaries
+
+Ignore: code style, performance, general quality.
+
+For each issue found, respond with a JSON array:
+[{"title": "...", "description": "...", "severity": "critical|high|medium", "file": "...", "line": N, "cwe": "CWE-XXX", "suggestion": "..."}]
+
+If no issues found, respond with: []"#;
+
+pub const CONVENTION_REVIEW_PROMPT: &str = r#"You are a code reviewer checking adherence to project conventions. Focus ONLY on patterns that indicate likely bugs or maintenance problems.
+
+Look for:
+- Inconsistent error handling patterns within the same module
+- Public API that doesn't follow the project's established patterns
+- Missing or incorrect type annotations that could cause runtime issues
+- Anti-patterns specific to the language (e.g. unwrap in Rust library code, any in TypeScript)
+
+Do NOT report: minor style preferences, documentation gaps, formatting.
+Only report issues with HIGH confidence that they deviate from the visible codebase conventions.
+
+For each issue found, respond with a JSON array:
+[{"title": "...", "description": "...", "severity": "medium|low", "file": "...", "line": N, "suggestion": "..."}]
+
+If no issues found, respond with: []"#;
+
+pub const COMPLEXITY_REVIEW_PROMPT: &str = r#"You are reviewing code changes for excessive complexity that could lead to bugs.
+
+Look for:
+- Functions over 50 lines that should be decomposed
+- Deeply nested control flow (4+ levels)
+- Complex boolean expressions that are hard to reason about
+- Functions with 5+ parameters
+- Code duplication within the changed files
+
+Only report complexity issues that are HIGH risk for future bugs. Ignore acceptable complexity in configuration, CLI argument parsing, or generated code.
+
+For each issue found, respond with a JSON array:
+[{"title": "...", "description": "...", "severity": "medium|low", "file": "...", "line": N, "suggestion": "..."}]
+
+If no issues found, respond with: []"#;
+
+/// All review types with their prompts
+pub const REVIEW_PASSES: &[(&str, &str)] = &[
+    ("logic", LOGIC_REVIEW_PROMPT),
+    ("security", SECURITY_REVIEW_PROMPT),
+    ("convention", CONVENTION_REVIEW_PROMPT),
+    ("complexity", COMPLEXITY_REVIEW_PROMPT),
+];

compliance-agent/src/llm/triage.rs

@@ -5,13 +5,25 @@ use compliance_core::models::{Finding, FindingStatus};
 use crate::llm::LlmClient;
 use crate::pipeline::orchestrator::GraphContext;
 
-const TRIAGE_SYSTEM_PROMPT: &str = r#"You are a security finding triage expert. Analyze the following security finding and determine:
+/// Maximum number of findings to include in a single LLM triage call.
-1. Is this a true positive? (yes/no)
+const TRIAGE_CHUNK_SIZE: usize = 30;
-2. Confidence score (0-10, where 10 is highest confidence this is a real issue)
-3. Brief remediation suggestion (1-2 sentences)
 
-Respond in JSON format:
+const TRIAGE_SYSTEM_PROMPT: &str = r#"You are a security finding triage expert. Analyze each of the following security findings with its code context and determine the appropriate action.
-{"true_positive": true/false, "confidence": N, "remediation": "..."}"#;
+
+Actions:
+- "confirm": The finding is a true positive at the reported severity. Keep as-is.
+- "downgrade": The finding is real but over-reported. Lower severity recommended.
+- "upgrade": The finding is under-reported. Higher severity recommended.
+- "dismiss": The finding is a false positive. Should be removed.
+
+Consider:
+- Is the code in a test, example, or generated file? (lower confidence for test code)
+- Does the surrounding code context confirm or refute the finding?
+- Is the finding actionable by a developer?
+- Would a real attacker be able to exploit this?
+
+Respond with a JSON array, one entry per finding in the same order they were presented:
+[{"id": "<fingerprint>", "action": "confirm|downgrade|upgrade|dismiss", "confidence": 0-10, "rationale": "brief explanation", "remediation": "optional fix suggestion"}, ...]"#;
 
 pub async fn triage_findings(
     llm: &Arc<LlmClient>,
@@ -20,94 +32,162 @@ pub async fn triage_findings(
 ) -> usize {
     let mut passed = 0;
 
-    for finding in findings.iter_mut() {
+    // Process findings in chunks to avoid overflowing the LLM context window.
-        let mut user_prompt = format!(
+    for chunk_start in (0..findings.len()).step_by(TRIAGE_CHUNK_SIZE) {
-            "Scanner: {}\nRule: {}\nSeverity: {}\nTitle: {}\nDescription: {}\nFile: {}\nLine: {}\nCode: {}",
+        let chunk_end = (chunk_start + TRIAGE_CHUNK_SIZE).min(findings.len());
-            finding.scanner,
+        let chunk = &mut findings[chunk_start..chunk_end];
-            finding.rule_id.as_deref().unwrap_or("N/A"),
-            finding.severity,
-            finding.title,
-            finding.description,
-            finding.file_path.as_deref().unwrap_or("N/A"),
-            finding.line_number.map(|n| n.to_string()).unwrap_or_else(|| "N/A".to_string()),
-            finding.code_snippet.as_deref().unwrap_or("N/A"),
-        );
 
-        // Enrich with graph context if available
+        // Build a combined prompt for the entire chunk.
-        if let Some(ctx) = graph_context {
+        let mut user_prompt = String::new();
-            if let Some(impact) = ctx
+        let mut file_classifications: Vec<String> = Vec::new();
-                .impacts
+
-                .iter()
+        for (i, finding) in chunk.iter().enumerate() {
-                .find(|i| i.finding_id == finding.fingerprint)
+            let file_classification = classify_file_path(finding.file_path.as_deref());
-            {
+
+            user_prompt.push_str(&format!(
+                "\n--- Finding {} (id: {}) ---\nScanner: {}\nRule: {}\nSeverity: {}\nTitle: {}\nDescription: {}\nFile: {}\nLine: {}\nCode: {}\nFile classification: {}",
+                i + 1,
+                finding.fingerprint,
+                finding.scanner,
+                finding.rule_id.as_deref().unwrap_or("N/A"),
+                finding.severity,
+                finding.title,
+                finding.description,
+                finding.file_path.as_deref().unwrap_or("N/A"),
+                finding.line_number.map(|n| n.to_string()).unwrap_or_else(|| "N/A".to_string()),
+                finding.code_snippet.as_deref().unwrap_or("N/A"),
+                file_classification,
+            ));
+
+            // Enrich with surrounding code context if possible
+            if let Some(context) = read_surrounding_context(finding) {
                 user_prompt.push_str(&format!(
-                    "\n\n--- Code Graph Context ---\n\
+                    "\n\n--- Surrounding Code (50 lines) ---\n{context}"
-                     Blast radius: {} nodes affected\n\
-                     Entry points affected: {}\n\
-                     Direct callers: {}\n\
-                     Communities affected: {}\n\
-                     Call chains: {}",
-                    impact.blast_radius,
-                    if impact.affected_entry_points.is_empty() {
-                        "none".to_string()
-                    } else {
-                        impact.affected_entry_points.join(", ")
-                    },
-                    if impact.direct_callers.is_empty() {
-                        "none".to_string()
-                    } else {
-                        impact.direct_callers.join(", ")
-                    },
-                    impact.affected_communities.len(),
-                    impact.call_chains.len(),
                 ));
             }
+
+            // Enrich with graph context if available
+            if let Some(ctx) = graph_context {
+                if let Some(impact) = ctx
+                    .impacts
+                    .iter()
+                    .find(|im| im.finding_id == finding.fingerprint)
+                {
+                    user_prompt.push_str(&format!(
+                        "\n\n--- Code Graph Context ---\n\
+                         Blast radius: {} nodes affected\n\
+                         Entry points affected: {}\n\
+                         Direct callers: {}\n\
+                         Communities affected: {}\n\
+                         Call chains: {}",
+                        impact.blast_radius,
+                        if impact.affected_entry_points.is_empty() {
+                            "none".to_string()
+                        } else {
+                            impact.affected_entry_points.join(", ")
+                        },
+                        if impact.direct_callers.is_empty() {
+                            "none".to_string()
+                        } else {
+                            impact.direct_callers.join(", ")
+                        },
+                        impact.affected_communities.len(),
+                        impact.call_chains.len(),
+                    ));
+                }
+            }
+
+            user_prompt.push('\n');
+            file_classifications.push(file_classification);
         }
 
+        // Send the batch to the LLM.
         match llm
             .chat(TRIAGE_SYSTEM_PROMPT, &user_prompt, Some(0.1))
             .await
         {
             Ok(response) => {
-                // Strip markdown code fences if present (e.g. ```json ... ```)
                 let cleaned = response.trim();
                 let cleaned = if cleaned.starts_with("```") {
-                    let inner = cleaned
+                    cleaned
                         .trim_start_matches("```json")
                         .trim_start_matches("```")
                         .trim_end_matches("```")
-                        .trim();
+                        .trim()
-                    inner
                 } else {
                     cleaned
                 };
-                if let Ok(result) = serde_json::from_str::<TriageResult>(cleaned) {
-                    finding.confidence = Some(result.confidence);
-                    if let Some(remediation) = result.remediation {
-                        finding.remediation = Some(remediation);
-                    }
 
-                    if result.confidence >= 3.0 {
+                match serde_json::from_str::<Vec<TriageResult>>(cleaned) {
-                        finding.status = FindingStatus::Triaged;
+                    Ok(results) => {
-                        passed += 1;
+                        for (idx, finding) in chunk.iter_mut().enumerate() {
-                    } else {
+                            // Match result by position; fall back to keeping the finding.
-                        finding.status = FindingStatus::FalsePositive;
+                            let Some(result) = results.get(idx) else {
+                                finding.status = FindingStatus::Triaged;
+                                passed += 1;
+                                continue;
+                            };
+
+                            let file_classification = file_classifications
+                                .get(idx)
+                                .map(|s| s.as_str())
+                                .unwrap_or("unknown");
+
+                            let adjusted_confidence =
+                                adjust_confidence(result.confidence, file_classification);
+                            finding.confidence = Some(adjusted_confidence);
+                            finding.triage_action = Some(result.action.clone());
+                            finding.triage_rationale = Some(result.rationale.clone());
+
+                            if let Some(ref remediation) = result.remediation {
+                                finding.remediation = Some(remediation.clone());
+                            }
+
+                            match result.action.as_str() {
+                                "dismiss" => {
+                                    finding.status = FindingStatus::FalsePositive;
+                                }
+                                "downgrade" => {
+                                    finding.severity = downgrade_severity(&finding.severity);
+                                    finding.status = FindingStatus::Triaged;
+                                    passed += 1;
+                                }
+                                "upgrade" => {
+                                    finding.severity = upgrade_severity(&finding.severity);
+                                    finding.status = FindingStatus::Triaged;
+                                    passed += 1;
+                                }
+                                _ => {
+                                    // "confirm" or unknown — keep as-is
+                                    if adjusted_confidence >= 3.0 {
+                                        finding.status = FindingStatus::Triaged;
+                                        passed += 1;
+                                    } else {
+                                        finding.status = FindingStatus::FalsePositive;
+                                    }
+                                }
+                            }
+                        }
+                    }
+                    Err(_) => {
+                        // Batch parse failure — keep all findings in the chunk.
+                        tracing::warn!(
+                            "Failed to parse batch triage response for chunk starting at {chunk_start}: {cleaned}"
+                        );
+                        for finding in chunk.iter_mut() {
+                            finding.status = FindingStatus::Triaged;
+                            passed += 1;
+                        }
                     }
-                } else {
-                    // If LLM response doesn't parse, keep the finding
-                    finding.status = FindingStatus::Triaged;
-                    passed += 1;
-                    tracing::warn!(
-                        "Failed to parse triage response for {}: {response}",
-                        finding.fingerprint
-                    );
                 }
             }
             Err(e) => {
-                // On LLM error, keep the finding
+                // On LLM error, keep all findings in the chunk.
-                tracing::warn!("LLM triage failed for {}: {e}", finding.fingerprint);
+                tracing::warn!("LLM batch triage failed for chunk starting at {chunk_start}: {e}");
-                finding.status = FindingStatus::Triaged;
+                for finding in chunk.iter_mut() {
-                passed += 1;
+                    finding.status = FindingStatus::Triaged;
+                    passed += 1;
+                }
             }
         }
     }
@@ -117,12 +197,343 @@ pub async fn triage_findings(
     passed
 }
 
+/// Read ~50 lines of surrounding code from the file at the finding's location
+fn read_surrounding_context(finding: &Finding) -> Option<String> {
+    let file_path = finding.file_path.as_deref()?;
+    let line = finding.line_number? as usize;
+
+    // Try to read the file — this works because the repo is cloned locally
+    let content = std::fs::read_to_string(file_path).ok()?;
+    let lines: Vec<&str> = content.lines().collect();
+
+    let start = line.saturating_sub(25);
+    let end = (line + 25).min(lines.len());
+
+    Some(
+        lines[start..end]
+            .iter()
+            .enumerate()
+            .map(|(i, l)| format!("{:>4} | {}", start + i + 1, l))
+            .collect::<Vec<_>>()
+            .join("\n"),
+    )
+}
+
+/// Classify a file path to inform triage confidence adjustment
+fn classify_file_path(path: Option<&str>) -> String {
+    let path = match path {
+        Some(p) => p.to_lowercase(),
+        None => return "unknown".to_string(),
+    };
+
+    if path.contains("/test/")
+        || path.contains("/tests/")
+        || path.contains("_test.")
+        || path.contains(".test.")
+        || path.contains(".spec.")
+        || path.contains("/fixtures/")
+        || path.contains("/testdata/")
+    {
+        return "test".to_string();
+    }
+
+    if path.contains("/example")
+        || path.contains("/examples/")
+        || path.contains("/demo/")
+        || path.contains("/sample")
+    {
+        return "example".to_string();
+    }
+
+    if path.contains("/generated/")
+        || path.contains("/gen/")
+        || path.contains(".generated.")
+        || path.contains(".pb.go")
+        || path.contains("_generated.rs")
+    {
+        return "generated".to_string();
+    }
+
+    if path.contains("/vendor/")
+        || path.contains("/node_modules/")
+        || path.contains("/third_party/")
+    {
+        return "vendored".to_string();
+    }
+
+    "production".to_string()
+}
+
+/// Adjust confidence based on file classification
+fn adjust_confidence(raw_confidence: f64, classification: &str) -> f64 {
+    let multiplier = match classification {
+        "test" => 0.5,
+        "example" => 0.6,
+        "generated" => 0.3,
+        "vendored" => 0.4,
+        _ => 1.0,
+    };
+    raw_confidence * multiplier
+}
+
+fn downgrade_severity(
+    severity: &compliance_core::models::Severity,
+) -> compliance_core::models::Severity {
+    use compliance_core::models::Severity;
+    match severity {
+        Severity::Critical => Severity::High,
+        Severity::High => Severity::Medium,
+        Severity::Medium => Severity::Low,
+        Severity::Low => Severity::Info,
+        Severity::Info => Severity::Info,
+    }
+}
+
+fn upgrade_severity(
+    severity: &compliance_core::models::Severity,
+) -> compliance_core::models::Severity {
+    use compliance_core::models::Severity;
+    match severity {
+        Severity::Info => Severity::Low,
+        Severity::Low => Severity::Medium,
+        Severity::Medium => Severity::High,
+        Severity::High => Severity::Critical,
+        Severity::Critical => Severity::Critical,
+    }
+}
+
 #[derive(serde::Deserialize)]
 struct TriageResult {
+    /// Finding fingerprint echoed back by the LLM (optional).
     #[serde(default)]
     #[allow(dead_code)]
-    true_positive: bool,
+    id: String,
+    #[serde(default = "default_action")]
+    action: String,
     #[serde(default)]
     confidence: f64,
+    #[serde(default)]
+    rationale: String,
     remediation: Option<String>,
 }
+
+fn default_action() -> String {
+    "confirm".to_string()
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::models::Severity;
+
+    // ── classify_file_path ───────────────────────────────────────
+
+    #[test]
+    fn classify_none_path() {
+        assert_eq!(classify_file_path(None), "unknown");
+    }
+
+    #[test]
+    fn classify_production_path() {
+        assert_eq!(classify_file_path(Some("src/main.rs")), "production");
+        assert_eq!(classify_file_path(Some("lib/core/engine.py")), "production");
+    }
+
+    #[test]
+    fn classify_test_paths() {
+        assert_eq!(classify_file_path(Some("src/test/helper.rs")), "test");
+        assert_eq!(classify_file_path(Some("src/tests/unit.rs")), "test");
+        assert_eq!(classify_file_path(Some("foo_test.go")), "test");
+        assert_eq!(classify_file_path(Some("bar.test.js")), "test");
+        assert_eq!(classify_file_path(Some("baz.spec.ts")), "test");
+        assert_eq!(
+            classify_file_path(Some("data/fixtures/sample.json")),
+            "test"
+        );
+        assert_eq!(classify_file_path(Some("src/testdata/input.txt")), "test");
+    }
+
+    #[test]
+    fn classify_example_paths() {
+        assert_eq!(
+            classify_file_path(Some("docs/examples/basic.rs")),
+            "example"
+        );
+        // /example matches because contains("/example")
+        assert_eq!(classify_file_path(Some("src/example/main.py")), "example");
+        assert_eq!(classify_file_path(Some("src/demo/run.sh")), "example");
+        assert_eq!(classify_file_path(Some("src/sample/lib.rs")), "example");
+    }
+
+    #[test]
+    fn classify_generated_paths() {
+        assert_eq!(
+            classify_file_path(Some("src/generated/api.rs")),
+            "generated"
+        );
+        assert_eq!(
+            classify_file_path(Some("proto/gen/service.go")),
+            "generated"
+        );
+        assert_eq!(classify_file_path(Some("api.generated.ts")), "generated");
+        assert_eq!(classify_file_path(Some("service.pb.go")), "generated");
+        assert_eq!(classify_file_path(Some("model_generated.rs")), "generated");
+    }
+
+    #[test]
+    fn classify_vendored_paths() {
+        // Implementation checks for /vendor/, /node_modules/, /third_party/ (with slashes)
+        assert_eq!(
+            classify_file_path(Some("src/vendor/lib/foo.go")),
+            "vendored"
+        );
+        assert_eq!(
+            classify_file_path(Some("src/node_modules/pkg/index.js")),
+            "vendored"
+        );
+        assert_eq!(
+            classify_file_path(Some("src/third_party/lib.c")),
+            "vendored"
+        );
+    }
+
+    #[test]
+    fn classify_is_case_insensitive() {
+        assert_eq!(classify_file_path(Some("src/TEST/Helper.rs")), "test");
+        assert_eq!(classify_file_path(Some("src/VENDOR/lib.go")), "vendored");
+        assert_eq!(
+            classify_file_path(Some("src/GENERATED/foo.ts")),
+            "generated"
+        );
+    }
+
+    // ── adjust_confidence ────────────────────────────────────────
+
+    #[test]
+    fn adjust_confidence_production() {
+        assert_eq!(adjust_confidence(8.0, "production"), 8.0);
+    }
+
+    #[test]
+    fn adjust_confidence_test() {
+        assert_eq!(adjust_confidence(10.0, "test"), 5.0);
+    }
+
+    #[test]
+    fn adjust_confidence_example() {
+        assert_eq!(adjust_confidence(10.0, "example"), 6.0);
+    }
+
+    #[test]
+    fn adjust_confidence_generated() {
+        assert_eq!(adjust_confidence(10.0, "generated"), 3.0);
+    }
+
+    #[test]
+    fn adjust_confidence_vendored() {
+        assert_eq!(adjust_confidence(10.0, "vendored"), 4.0);
+    }
+
+    #[test]
+    fn adjust_confidence_unknown_classification() {
+        assert_eq!(adjust_confidence(7.0, "unknown"), 7.0);
+        assert_eq!(adjust_confidence(7.0, "something_else"), 7.0);
+    }
+
+    #[test]
+    fn adjust_confidence_zero() {
+        assert_eq!(adjust_confidence(0.0, "test"), 0.0);
+        assert_eq!(adjust_confidence(0.0, "production"), 0.0);
+    }
+
+    // ── downgrade_severity ───────────────────────────────────────
+
+    #[test]
+    fn downgrade_severity_all_levels() {
+        assert_eq!(downgrade_severity(&Severity::Critical), Severity::High);
+        assert_eq!(downgrade_severity(&Severity::High), Severity::Medium);
+        assert_eq!(downgrade_severity(&Severity::Medium), Severity::Low);
+        assert_eq!(downgrade_severity(&Severity::Low), Severity::Info);
+        assert_eq!(downgrade_severity(&Severity::Info), Severity::Info);
+    }
+
+    #[test]
+    fn downgrade_severity_info_is_floor() {
+        // Downgrading Info twice should still be Info
+        let s = downgrade_severity(&Severity::Info);
+        assert_eq!(downgrade_severity(&s), Severity::Info);
+    }
+
+    // ── upgrade_severity ─────────────────────────────────────────
+
+    #[test]
+    fn upgrade_severity_all_levels() {
+        assert_eq!(upgrade_severity(&Severity::Info), Severity::Low);
+        assert_eq!(upgrade_severity(&Severity::Low), Severity::Medium);
+        assert_eq!(upgrade_severity(&Severity::Medium), Severity::High);
+        assert_eq!(upgrade_severity(&Severity::High), Severity::Critical);
+        assert_eq!(upgrade_severity(&Severity::Critical), Severity::Critical);
+    }
+
+    #[test]
+    fn upgrade_severity_critical_is_ceiling() {
+        let s = upgrade_severity(&Severity::Critical);
+        assert_eq!(upgrade_severity(&s), Severity::Critical);
+    }
+
+    // ── upgrade/downgrade roundtrip ──────────────────────────────
+
+    #[test]
+    fn upgrade_then_downgrade_is_identity_for_middle_values() {
+        for sev in [Severity::Low, Severity::Medium, Severity::High] {
+            assert_eq!(downgrade_severity(&upgrade_severity(&sev)), sev);
+        }
+    }
+
+    // ── TriageResult deserialization ─────────────────────────────
+
+    #[test]
+    fn triage_result_full() {
+        let json = r#"{"action":"dismiss","confidence":8.5,"rationale":"false positive","remediation":"remove code"}"#;
+        let r: TriageResult = serde_json::from_str(json).unwrap();
+        assert_eq!(r.action, "dismiss");
+        assert_eq!(r.confidence, 8.5);
+        assert_eq!(r.rationale, "false positive");
+        assert_eq!(r.remediation.as_deref(), Some("remove code"));
+    }
+
+    #[test]
+    fn triage_result_defaults() {
+        let json = r#"{}"#;
+        let r: TriageResult = serde_json::from_str(json).unwrap();
+        assert_eq!(r.action, "confirm");
+        assert_eq!(r.confidence, 0.0);
+        assert_eq!(r.rationale, "");
+        assert!(r.remediation.is_none());
+    }
+
+    #[test]
+    fn triage_result_partial() {
+        let json = r#"{"action":"downgrade","confidence":6.0}"#;
+        let r: TriageResult = serde_json::from_str(json).unwrap();
+        assert_eq!(r.action, "downgrade");
+        assert_eq!(r.confidence, 6.0);
+        assert_eq!(r.rationale, "");
+        assert!(r.remediation.is_none());
+    }
+
+    #[test]
+    fn triage_result_with_markdown_fences() {
+        // Simulate LLM wrapping response in markdown code fences
+        let raw = "```json\n{\"action\":\"upgrade\",\"confidence\":9,\"rationale\":\"critical\",\"remediation\":null}\n```";
+        let cleaned = raw
+            .trim()
+            .trim_start_matches("```json")
+            .trim_start_matches("```")
+            .trim_end_matches("```")
+            .trim();
+        let r: TriageResult = serde_json::from_str(cleaned).unwrap();
+        assert_eq!(r.action, "upgrade");
+        assert_eq!(r.confidence, 9.0);
+    }
+}

compliance-agent/src/llm/types.rs

@@ -0,0 +1,369 @@
+use serde::{Deserialize, Serialize};
+
+// ── Request types ──────────────────────────────────────────────
+
+#[derive(Serialize, Clone, Debug)]
+pub struct ChatMessage {
+    pub role: String,
+    pub content: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub tool_calls: Option<Vec<ToolCallRequest>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub tool_call_id: Option<String>,
+}
+
+#[derive(Serialize)]
+pub(crate) struct ChatCompletionRequest {
+    pub(crate) model: String,
+    pub(crate) messages: Vec<ChatMessage>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(crate) temperature: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(crate) max_tokens: Option<u32>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(crate) tools: Option<Vec<ToolDefinitionPayload>>,
+}
+
+#[derive(Serialize)]
+pub(crate) struct ToolDefinitionPayload {
+    pub(crate) r#type: String,
+    pub(crate) function: ToolFunctionPayload,
+}
+
+#[derive(Serialize)]
+pub(crate) struct ToolFunctionPayload {
+    pub(crate) name: String,
+    pub(crate) description: String,
+    pub(crate) parameters: serde_json::Value,
+}
+
+// ── Response types ─────────────────────────────────────────────
+
+#[derive(Deserialize)]
+pub(crate) struct ChatCompletionResponse {
+    pub(crate) choices: Vec<ChatChoice>,
+}
+
+#[derive(Deserialize)]
+pub(crate) struct ChatChoice {
+    pub(crate) message: ChatResponseMessage,
+}
+
+#[derive(Deserialize)]
+pub(crate) struct ChatResponseMessage {
+    #[serde(default)]
+    pub(crate) content: Option<String>,
+    #[serde(default)]
+    pub(crate) tool_calls: Option<Vec<ToolCallResponse>>,
+}
+
+#[derive(Deserialize)]
+pub(crate) struct ToolCallResponse {
+    pub(crate) id: String,
+    pub(crate) function: ToolCallFunction,
+}
+
+#[derive(Deserialize)]
+pub(crate) struct ToolCallFunction {
+    pub(crate) name: String,
+    pub(crate) arguments: String,
+}
+
+// ── Public types for tool calling ──────────────────────────────
+
+/// Definition of a tool that the LLM can invoke
+#[derive(Debug, Clone, Serialize)]
+pub struct ToolDefinition {
+    pub name: String,
+    pub description: String,
+    pub parameters: serde_json::Value,
+}
+
+/// A tool call request from the LLM
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct LlmToolCall {
+    pub id: String,
+    pub name: String,
+    pub arguments: serde_json::Value,
+}
+
+/// A tool call in the request message format (for sending back tool_calls in assistant messages)
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ToolCallRequest {
+    pub id: String,
+    pub r#type: String,
+    pub function: ToolCallRequestFunction,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ToolCallRequestFunction {
+    pub name: String,
+    pub arguments: String,
+}
+
+/// Response from the LLM — either content or tool calls
+#[derive(Debug, Clone)]
+pub enum LlmResponse {
+    Content(String),
+    /// Tool calls with optional reasoning text from the LLM
+    ToolCalls {
+        calls: Vec<LlmToolCall>,
+        reasoning: String,
+    },
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use serde_json::json;
+
+    // ── ChatMessage ──────────────────────────────────────────────
+
+    #[test]
+    fn chat_message_serializes_minimal() {
+        let msg = ChatMessage {
+            role: "user".to_string(),
+            content: Some("hello".to_string()),
+            tool_calls: None,
+            tool_call_id: None,
+        };
+        let v = serde_json::to_value(&msg).unwrap();
+        assert_eq!(v["role"], "user");
+        assert_eq!(v["content"], "hello");
+        // None fields with skip_serializing_if should be absent
+        assert!(v.get("tool_calls").is_none());
+        assert!(v.get("tool_call_id").is_none());
+    }
+
+    #[test]
+    fn chat_message_serializes_with_tool_calls() {
+        let msg = ChatMessage {
+            role: "assistant".to_string(),
+            content: None,
+            tool_calls: Some(vec![ToolCallRequest {
+                id: "call_1".to_string(),
+                r#type: "function".to_string(),
+                function: ToolCallRequestFunction {
+                    name: "get_weather".to_string(),
+                    arguments: r#"{"city":"NYC"}"#.to_string(),
+                },
+            }]),
+            tool_call_id: None,
+        };
+        let v = serde_json::to_value(&msg).unwrap();
+        assert!(v["tool_calls"].is_array());
+        assert_eq!(v["tool_calls"][0]["function"]["name"], "get_weather");
+    }
+
+    #[test]
+    fn chat_message_content_null_when_none() {
+        let msg = ChatMessage {
+            role: "assistant".to_string(),
+            content: None,
+            tool_calls: None,
+            tool_call_id: None,
+        };
+        let v = serde_json::to_value(&msg).unwrap();
+        assert!(v["content"].is_null());
+    }
+
+    // ── ToolDefinition ───────────────────────────────────────────
+
+    #[test]
+    fn tool_definition_serializes() {
+        let td = ToolDefinition {
+            name: "search".to_string(),
+            description: "Search the web".to_string(),
+            parameters: json!({"type": "object", "properties": {"q": {"type": "string"}}}),
+        };
+        let v = serde_json::to_value(&td).unwrap();
+        assert_eq!(v["name"], "search");
+        assert_eq!(v["parameters"]["type"], "object");
+    }
+
+    #[test]
+    fn tool_definition_empty_parameters() {
+        let td = ToolDefinition {
+            name: "noop".to_string(),
+            description: "".to_string(),
+            parameters: json!({}),
+        };
+        let v = serde_json::to_value(&td).unwrap();
+        assert_eq!(v["parameters"], json!({}));
+    }
+
+    // ── LlmToolCall ──────────────────────────────────────────────
+
+    #[test]
+    fn llm_tool_call_roundtrip() {
+        let call = LlmToolCall {
+            id: "tc_42".to_string(),
+            name: "run_scan".to_string(),
+            arguments: json!({"path": "/tmp", "verbose": true}),
+        };
+        let serialized = serde_json::to_string(&call).unwrap();
+        let deserialized: LlmToolCall = serde_json::from_str(&serialized).unwrap();
+        assert_eq!(deserialized.id, "tc_42");
+        assert_eq!(deserialized.name, "run_scan");
+        assert_eq!(deserialized.arguments["path"], "/tmp");
+        assert_eq!(deserialized.arguments["verbose"], true);
+    }
+
+    #[test]
+    fn llm_tool_call_empty_arguments() {
+        let call = LlmToolCall {
+            id: "tc_0".to_string(),
+            name: "noop".to_string(),
+            arguments: json!({}),
+        };
+        let rt: LlmToolCall = serde_json::from_str(&serde_json::to_string(&call).unwrap()).unwrap();
+        assert!(rt.arguments.as_object().unwrap().is_empty());
+    }
+
+    // ── ToolCallRequest / ToolCallRequestFunction ────────────────
+
+    #[test]
+    fn tool_call_request_roundtrip() {
+        let req = ToolCallRequest {
+            id: "call_abc".to_string(),
+            r#type: "function".to_string(),
+            function: ToolCallRequestFunction {
+                name: "my_func".to_string(),
+                arguments: r#"{"x":1}"#.to_string(),
+            },
+        };
+        let json_str = serde_json::to_string(&req).unwrap();
+        let back: ToolCallRequest = serde_json::from_str(&json_str).unwrap();
+        assert_eq!(back.id, "call_abc");
+        assert_eq!(back.r#type, "function");
+        assert_eq!(back.function.name, "my_func");
+        assert_eq!(back.function.arguments, r#"{"x":1}"#);
+    }
+
+    #[test]
+    fn tool_call_request_type_field_serializes_as_type() {
+        let req = ToolCallRequest {
+            id: "id".to_string(),
+            r#type: "function".to_string(),
+            function: ToolCallRequestFunction {
+                name: "f".to_string(),
+                arguments: "{}".to_string(),
+            },
+        };
+        let v = serde_json::to_value(&req).unwrap();
+        // The field should be "type" in JSON, not "r#type"
+        assert!(v.get("type").is_some());
+        assert!(v.get("r#type").is_none());
+    }
+
+    // ── ChatCompletionRequest ────────────────────────────────────
+
+    #[test]
+    fn chat_completion_request_skips_none_fields() {
+        let req = ChatCompletionRequest {
+            model: "gpt-4".to_string(),
+            messages: vec![],
+            temperature: None,
+            max_tokens: None,
+            tools: None,
+        };
+        let v = serde_json::to_value(&req).unwrap();
+        assert_eq!(v["model"], "gpt-4");
+        assert!(v.get("temperature").is_none());
+        assert!(v.get("max_tokens").is_none());
+        assert!(v.get("tools").is_none());
+    }
+
+    #[test]
+    fn chat_completion_request_includes_set_fields() {
+        let req = ChatCompletionRequest {
+            model: "gpt-4".to_string(),
+            messages: vec![],
+            temperature: Some(0.7),
+            max_tokens: Some(1024),
+            tools: Some(vec![]),
+        };
+        let v = serde_json::to_value(&req).unwrap();
+        assert_eq!(v["temperature"], 0.7);
+        assert_eq!(v["max_tokens"], 1024);
+        assert!(v["tools"].is_array());
+    }
+
+    // ── ChatCompletionResponse deserialization ───────────────────
+
+    #[test]
+    fn chat_completion_response_deserializes_content() {
+        let json_str = r#"{"choices":[{"message":{"content":"Hello!"}}]}"#;
+        let resp: ChatCompletionResponse = serde_json::from_str(json_str).unwrap();
+        assert_eq!(resp.choices.len(), 1);
+        assert_eq!(resp.choices[0].message.content.as_deref(), Some("Hello!"));
+        assert!(resp.choices[0].message.tool_calls.is_none());
+    }
+
+    #[test]
+    fn chat_completion_response_deserializes_tool_calls() {
+        let json_str = r#"{
+            "choices": [{
+                "message": {
+                    "tool_calls": [{
+                        "id": "call_1",
+                        "function": {"name": "search", "arguments": "{\"q\":\"rust\"}"}
+                    }]
+                }
+            }]
+        }"#;
+        let resp: ChatCompletionResponse = serde_json::from_str(json_str).unwrap();
+        let tc = resp.choices[0].message.tool_calls.as_ref().unwrap();
+        assert_eq!(tc.len(), 1);
+        assert_eq!(tc[0].id, "call_1");
+        assert_eq!(tc[0].function.name, "search");
+    }
+
+    #[test]
+    fn chat_completion_response_defaults_missing_fields() {
+        // content and tool_calls are both missing — should default to None
+        let json_str = r#"{"choices":[{"message":{}}]}"#;
+        let resp: ChatCompletionResponse = serde_json::from_str(json_str).unwrap();
+        assert!(resp.choices[0].message.content.is_none());
+        assert!(resp.choices[0].message.tool_calls.is_none());
+    }
+
+    // ── LlmResponse ─────────────────────────────────────────────
+
+    #[test]
+    fn llm_response_content_variant() {
+        let resp = LlmResponse::Content("answer".to_string());
+        match resp {
+            LlmResponse::Content(s) => assert_eq!(s, "answer"),
+            _ => panic!("expected Content variant"),
+        }
+    }
+
+    #[test]
+    fn llm_response_tool_calls_variant() {
+        let resp = LlmResponse::ToolCalls {
+            calls: vec![LlmToolCall {
+                id: "1".to_string(),
+                name: "f".to_string(),
+                arguments: json!({}),
+            }],
+            reasoning: "because".to_string(),
+        };
+        match resp {
+            LlmResponse::ToolCalls { calls, reasoning } => {
+                assert_eq!(calls.len(), 1);
+                assert_eq!(reasoning, "because");
+            }
+            _ => panic!("expected ToolCalls variant"),
+        }
+    }
+
+    #[test]
+    fn llm_response_empty_content() {
+        let resp = LlmResponse::Content(String::new());
+        match resp {
+            LlmResponse::Content(s) => assert!(s.is_empty()),
+            _ => panic!("expected Content variant"),
+        }
+    }
+}

compliance-agent/src/main.rs

@@ -1,31 +1,42 @@
-use tracing_subscriber::EnvFilter;
-
 mod agent;
 mod api;
-mod config;
+pub(crate) mod config;
 mod database;
 mod error;
 mod llm;
+mod pentest;
 mod pipeline;
 mod rag;
 mod scheduler;
+mod ssh;
 #[allow(dead_code)]
 mod trackers;
 mod webhooks;
 
 #[tokio::main]
 async fn main() -> Result<(), Box<dyn std::error::Error>> {
-    tracing_subscriber::fmt()
+    match dotenvy::dotenv() {
-        .with_env_filter(
+        Ok(path) => eprintln!("[dotenv] Loaded from: {}", path.display()),
-            EnvFilter::try_from_default_env().unwrap_or_else(|_| EnvFilter::new("info")),
+        Err(e) => eprintln!("[dotenv] FAILED: {e}"),
-        )
+    }
-        .init();
 
-    dotenvy::dotenv().ok();
+    let _telemetry_guard = compliance_core::telemetry::init_telemetry("compliance-agent");
 
-    tracing::info!("Loading configuration...");
+    // Log critical env vars at startup
+    tracing::info!(
+        chrome_ws_url = std::env::var("CHROME_WS_URL").ok().as_deref(),
+        pentest_email = std::env::var("PENTEST_VERIFICATION_EMAIL").ok().as_deref(),
+        encryption_key_set = std::env::var("PENTEST_ENCRYPTION_KEY").is_ok(),
+        "Loading configuration..."
+    );
     let config = config::load_config()?;
 
+    // Ensure SSH key pair exists for cloning private repos
+    match ssh::ensure_ssh_key(&config.ssh_key_path) {
+        Ok(pubkey) => tracing::info!("SSH public key: {}", pubkey.trim()),
+        Err(e) => tracing::warn!("SSH key generation skipped: {e}"),
+    }
+
     tracing::info!("Connecting to MongoDB...");
     let db = database::Database::connect(&config.mongodb_uri, &config.mongodb_database).await?;
     db.ensure_indexes().await?;

compliance-agent/src/pentest/cleanup.rs

@@ -0,0 +1,484 @@
+use compliance_core::models::pentest::{IdentityProvider, TestUserRecord};
+use compliance_core::AgentConfig;
+use secrecy::ExposeSecret;
+use tracing::{info, warn};
+
+/// Attempt to delete a test user created during a pentest session.
+///
+/// Routes to the appropriate identity provider based on `TestUserRecord.provider`.
+/// Falls back to browser-based cleanup if no API credentials are available.
+///
+/// Returns `Ok(true)` if the user was deleted, `Ok(false)` if skipped, `Err` on failure.
+pub async fn cleanup_test_user(
+    user: &TestUserRecord,
+    config: &AgentConfig,
+    http: &reqwest::Client,
+) -> Result<bool, String> {
+    if user.cleaned_up {
+        return Ok(false);
+    }
+
+    let provider = user.provider.as_ref();
+
+    match provider {
+        Some(IdentityProvider::Keycloak) => cleanup_keycloak(user, config, http).await,
+        Some(IdentityProvider::Auth0) => cleanup_auth0(user, config, http).await,
+        Some(IdentityProvider::Okta) => cleanup_okta(user, config, http).await,
+        Some(IdentityProvider::Firebase) => {
+            warn!("Firebase user cleanup not yet implemented");
+            Ok(false)
+        }
+        Some(IdentityProvider::Custom) | None => {
+            // For custom/unknown providers, try Keycloak if configured, else skip
+            if config.keycloak_url.is_some() && config.keycloak_admin_username.is_some() {
+                cleanup_keycloak(user, config, http).await
+            } else {
+                warn!(
+                    username = user.username.as_deref(),
+                    "No identity provider configured for cleanup — skipping"
+                );
+                Ok(false)
+            }
+        }
+    }
+}
+
+/// Delete a user from Keycloak via the Admin REST API.
+///
+/// Flow: get admin token → search user by username → delete by ID.
+async fn cleanup_keycloak(
+    user: &TestUserRecord,
+    config: &AgentConfig,
+    http: &reqwest::Client,
+) -> Result<bool, String> {
+    let base_url = config
+        .keycloak_url
+        .as_deref()
+        .ok_or("KEYCLOAK_URL not configured")?;
+    let realm = config
+        .keycloak_realm
+        .as_deref()
+        .ok_or("KEYCLOAK_REALM not configured")?;
+    let admin_user = config
+        .keycloak_admin_username
+        .as_deref()
+        .ok_or("KEYCLOAK_ADMIN_USERNAME not configured")?;
+    let admin_pass = config
+        .keycloak_admin_password
+        .as_ref()
+        .ok_or("KEYCLOAK_ADMIN_PASSWORD not configured")?;
+
+    let username = user
+        .username
+        .as_deref()
+        .ok_or("No username in test user record")?;
+
+    info!(username, realm, "Cleaning up Keycloak test user");
+
+    // Step 1: Get admin access token
+    let token_url = format!("{base_url}/realms/master/protocol/openid-connect/token");
+    let token_resp = http
+        .post(&token_url)
+        .form(&[
+            ("grant_type", "password"),
+            ("client_id", "admin-cli"),
+            ("username", admin_user),
+            ("password", admin_pass.expose_secret()),
+        ])
+        .send()
+        .await
+        .map_err(|e| format!("Keycloak token request failed: {e}"))?;
+
+    if !token_resp.status().is_success() {
+        let status = token_resp.status();
+        let body = token_resp.text().await.unwrap_or_default();
+        return Err(format!("Keycloak admin auth failed ({status}): {body}"));
+    }
+
+    let token_body: serde_json::Value = token_resp
+        .json()
+        .await
+        .map_err(|e| format!("Failed to parse Keycloak token: {e}"))?;
+    let access_token = token_body
+        .get("access_token")
+        .and_then(|v| v.as_str())
+        .ok_or("No access_token in Keycloak response")?;
+
+    // Step 2: Search for user by username
+    let search_url =
+        format!("{base_url}/admin/realms/{realm}/users?username={username}&exact=true");
+    let search_resp = http
+        .get(&search_url)
+        .bearer_auth(access_token)
+        .send()
+        .await
+        .map_err(|e| format!("Keycloak user search failed: {e}"))?;
+
+    if !search_resp.status().is_success() {
+        let status = search_resp.status();
+        let body = search_resp.text().await.unwrap_or_default();
+        return Err(format!("Keycloak user search failed ({status}): {body}"));
+    }
+
+    let users: Vec<serde_json::Value> = search_resp
+        .json()
+        .await
+        .map_err(|e| format!("Failed to parse Keycloak users: {e}"))?;
+
+    let user_id = users
+        .first()
+        .and_then(|u| u.get("id"))
+        .and_then(|v| v.as_str())
+        .ok_or_else(|| format!("User '{username}' not found in Keycloak realm '{realm}'"))?;
+
+    // Step 3: Delete the user
+    let delete_url = format!("{base_url}/admin/realms/{realm}/users/{user_id}");
+    let delete_resp = http
+        .delete(&delete_url)
+        .bearer_auth(access_token)
+        .send()
+        .await
+        .map_err(|e| format!("Keycloak user delete failed: {e}"))?;
+
+    if delete_resp.status().is_success() || delete_resp.status().as_u16() == 204 {
+        info!(username, user_id, "Keycloak test user deleted");
+        Ok(true)
+    } else {
+        let status = delete_resp.status();
+        let body = delete_resp.text().await.unwrap_or_default();
+        Err(format!("Keycloak delete failed ({status}): {body}"))
+    }
+}
+
+/// Delete a user from Auth0 via the Management API.
+///
+/// Requires `AUTH0_DOMAIN`, `AUTH0_CLIENT_ID`, `AUTH0_CLIENT_SECRET` env vars.
+async fn cleanup_auth0(
+    user: &TestUserRecord,
+    _config: &AgentConfig,
+    http: &reqwest::Client,
+) -> Result<bool, String> {
+    let domain = std::env::var("AUTH0_DOMAIN").map_err(|_| "AUTH0_DOMAIN not set")?;
+    let client_id = std::env::var("AUTH0_CLIENT_ID").map_err(|_| "AUTH0_CLIENT_ID not set")?;
+    let client_secret =
+        std::env::var("AUTH0_CLIENT_SECRET").map_err(|_| "AUTH0_CLIENT_SECRET not set")?;
+
+    let email = user
+        .email
+        .as_deref()
+        .ok_or("No email in test user record for Auth0 lookup")?;
+
+    info!(email, "Cleaning up Auth0 test user");
+
+    // Get management API token
+    let token_resp = http
+        .post(format!("https://{domain}/oauth/token"))
+        .json(&serde_json::json!({
+            "grant_type": "client_credentials",
+            "client_id": client_id,
+            "client_secret": client_secret,
+            "audience": format!("https://{domain}/api/v2/"),
+        }))
+        .send()
+        .await
+        .map_err(|e| format!("Auth0 token request failed: {e}"))?;
+
+    let token_body: serde_json::Value = token_resp
+        .json()
+        .await
+        .map_err(|e| format!("Failed to parse Auth0 token: {e}"))?;
+    let access_token = token_body
+        .get("access_token")
+        .and_then(|v| v.as_str())
+        .ok_or("No access_token in Auth0 response")?;
+
+    // Search for user by email
+    let encoded_email = urlencoding::encode(email);
+    let search_url = format!("https://{domain}/api/v2/users-by-email?email={encoded_email}");
+    let search_resp = http
+        .get(&search_url)
+        .bearer_auth(access_token)
+        .send()
+        .await
+        .map_err(|e| format!("Auth0 user search failed: {e}"))?;
+
+    let users: Vec<serde_json::Value> = search_resp
+        .json()
+        .await
+        .map_err(|e| format!("Failed to parse Auth0 users: {e}"))?;
+
+    let user_id = users
+        .first()
+        .and_then(|u| u.get("user_id"))
+        .and_then(|v| v.as_str())
+        .ok_or_else(|| format!("User with email '{email}' not found in Auth0"))?;
+
+    // Delete
+    let encoded_id = urlencoding::encode(user_id);
+    let delete_resp = http
+        .delete(format!("https://{domain}/api/v2/users/{encoded_id}"))
+        .bearer_auth(access_token)
+        .send()
+        .await
+        .map_err(|e| format!("Auth0 user delete failed: {e}"))?;
+
+    if delete_resp.status().is_success() || delete_resp.status().as_u16() == 204 {
+        info!(email, user_id, "Auth0 test user deleted");
+        Ok(true)
+    } else {
+        let status = delete_resp.status();
+        let body = delete_resp.text().await.unwrap_or_default();
+        Err(format!("Auth0 delete failed ({status}): {body}"))
+    }
+}
+
+/// Delete a user from Okta via the Users API.
+///
+/// Requires `OKTA_DOMAIN`, `OKTA_API_TOKEN` env vars.
+async fn cleanup_okta(
+    user: &TestUserRecord,
+    _config: &AgentConfig,
+    http: &reqwest::Client,
+) -> Result<bool, String> {
+    let domain = std::env::var("OKTA_DOMAIN").map_err(|_| "OKTA_DOMAIN not set")?;
+    let api_token = std::env::var("OKTA_API_TOKEN").map_err(|_| "OKTA_API_TOKEN not set")?;
+
+    let username = user
+        .username
+        .as_deref()
+        .or(user.email.as_deref())
+        .ok_or("No username/email in test user record for Okta lookup")?;
+
+    info!(username, "Cleaning up Okta test user");
+
+    // Search user
+    let encoded = urlencoding::encode(username);
+    let search_url = format!("https://{domain}/api/v1/users?search=profile.login+eq+\"{encoded}\"");
+    let search_resp = http
+        .get(&search_url)
+        .header("Authorization", format!("SSWS {api_token}"))
+        .send()
+        .await
+        .map_err(|e| format!("Okta user search failed: {e}"))?;
+
+    let users: Vec<serde_json::Value> = search_resp
+        .json()
+        .await
+        .map_err(|e| format!("Failed to parse Okta users: {e}"))?;
+
+    let user_id = users
+        .first()
+        .and_then(|u| u.get("id"))
+        .and_then(|v| v.as_str())
+        .ok_or_else(|| format!("User '{username}' not found in Okta"))?;
+
+    // Deactivate first (required by Okta before delete)
+    let _ = http
+        .post(format!(
+            "https://{domain}/api/v1/users/{user_id}/lifecycle/deactivate"
+        ))
+        .header("Authorization", format!("SSWS {api_token}"))
+        .send()
+        .await;
+
+    // Delete
+    let delete_resp = http
+        .delete(format!("https://{domain}/api/v1/users/{user_id}"))
+        .header("Authorization", format!("SSWS {api_token}"))
+        .send()
+        .await
+        .map_err(|e| format!("Okta user delete failed: {e}"))?;
+
+    if delete_resp.status().is_success() || delete_resp.status().as_u16() == 204 {
+        info!(username, user_id, "Okta test user deleted");
+        Ok(true)
+    } else {
+        let status = delete_resp.status();
+        let body = delete_resp.text().await.unwrap_or_default();
+        Err(format!("Okta delete failed ({status}): {body}"))
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::models::pentest::{IdentityProvider, TestUserRecord};
+    use secrecy::SecretString;
+
+    fn make_config_no_keycloak() -> AgentConfig {
+        AgentConfig {
+            mongodb_uri: String::new(),
+            mongodb_database: String::new(),
+            litellm_url: String::new(),
+            litellm_api_key: SecretString::from(String::new()),
+            litellm_model: String::new(),
+            litellm_embed_model: String::new(),
+            github_token: None,
+            github_webhook_secret: None,
+            gitlab_url: None,
+            gitlab_token: None,
+            gitlab_webhook_secret: None,
+            jira_url: None,
+            jira_email: None,
+            jira_api_token: None,
+            jira_project_key: None,
+            searxng_url: None,
+            nvd_api_key: None,
+            agent_port: 3001,
+            scan_schedule: String::new(),
+            cve_monitor_schedule: String::new(),
+            git_clone_base_path: String::new(),
+            ssh_key_path: String::new(),
+            keycloak_url: None,
+            keycloak_realm: None,
+            keycloak_admin_username: None,
+            keycloak_admin_password: None,
+            pentest_verification_email: None,
+            pentest_imap_host: None,
+            pentest_imap_port: None,
+            pentest_imap_tls: true,
+            pentest_imap_username: None,
+            pentest_imap_password: None,
+        }
+    }
+
+    #[tokio::test]
+    async fn already_cleaned_up_returns_false() {
+        let user = TestUserRecord {
+            username: Some("test".into()),
+            email: None,
+            provider_user_id: None,
+            provider: Some(IdentityProvider::Keycloak),
+            cleaned_up: true,
+        };
+        let config = make_config_no_keycloak();
+        let http = reqwest::Client::new();
+        let result = cleanup_test_user(&user, &config, &http).await;
+        assert_eq!(result, Ok(false));
+    }
+
+    #[tokio::test]
+    async fn firebase_returns_false_not_implemented() {
+        let user = TestUserRecord {
+            username: Some("test".into()),
+            email: None,
+            provider_user_id: None,
+            provider: Some(IdentityProvider::Firebase),
+            cleaned_up: false,
+        };
+        let config = make_config_no_keycloak();
+        let http = reqwest::Client::new();
+        let result = cleanup_test_user(&user, &config, &http).await;
+        assert_eq!(result, Ok(false));
+    }
+
+    #[tokio::test]
+    async fn no_provider_no_keycloak_skips() {
+        let user = TestUserRecord {
+            username: Some("test".into()),
+            email: None,
+            provider_user_id: None,
+            provider: None,
+            cleaned_up: false,
+        };
+        let config = make_config_no_keycloak();
+        let http = reqwest::Client::new();
+        let result = cleanup_test_user(&user, &config, &http).await;
+        assert_eq!(result, Ok(false));
+    }
+
+    #[tokio::test]
+    async fn custom_provider_no_keycloak_skips() {
+        let user = TestUserRecord {
+            username: Some("test".into()),
+            email: None,
+            provider_user_id: None,
+            provider: Some(IdentityProvider::Custom),
+            cleaned_up: false,
+        };
+        let config = make_config_no_keycloak();
+        let http = reqwest::Client::new();
+        let result = cleanup_test_user(&user, &config, &http).await;
+        assert_eq!(result, Ok(false));
+    }
+
+    #[tokio::test]
+    async fn keycloak_missing_config_returns_error() {
+        let user = TestUserRecord {
+            username: Some("test".into()),
+            email: None,
+            provider_user_id: None,
+            provider: Some(IdentityProvider::Keycloak),
+            cleaned_up: false,
+        };
+        let config = make_config_no_keycloak();
+        let http = reqwest::Client::new();
+        let result = cleanup_test_user(&user, &config, &http).await;
+        assert!(result.is_err());
+        assert!(result
+            .as_ref()
+            .err()
+            .is_some_and(|e| e.contains("KEYCLOAK_URL")));
+    }
+
+    #[tokio::test]
+    async fn keycloak_missing_username_returns_error() {
+        let user = TestUserRecord {
+            username: None,
+            email: Some("test@example.com".into()),
+            provider_user_id: None,
+            provider: Some(IdentityProvider::Keycloak),
+            cleaned_up: false,
+        };
+        let mut config = make_config_no_keycloak();
+        config.keycloak_url = Some("http://localhost:8080".into());
+        config.keycloak_realm = Some("test".into());
+        config.keycloak_admin_username = Some("admin".into());
+        config.keycloak_admin_password = Some(SecretString::from("pass".to_string()));
+        let http = reqwest::Client::new();
+        let result = cleanup_test_user(&user, &config, &http).await;
+        assert!(result.is_err());
+        assert!(result
+            .as_ref()
+            .err()
+            .is_some_and(|e| e.contains("username")));
+    }
+
+    #[tokio::test]
+    async fn auth0_missing_env_returns_error() {
+        let user = TestUserRecord {
+            username: None,
+            email: Some("test@example.com".into()),
+            provider_user_id: None,
+            provider: Some(IdentityProvider::Auth0),
+            cleaned_up: false,
+        };
+        let config = make_config_no_keycloak();
+        let http = reqwest::Client::new();
+        let result = cleanup_test_user(&user, &config, &http).await;
+        assert!(result.is_err());
+        assert!(result
+            .as_ref()
+            .err()
+            .is_some_and(|e| e.contains("AUTH0_DOMAIN")));
+    }
+
+    #[tokio::test]
+    async fn okta_missing_env_returns_error() {
+        let user = TestUserRecord {
+            username: Some("test".into()),
+            email: None,
+            provider_user_id: None,
+            provider: Some(IdentityProvider::Okta),
+            cleaned_up: false,
+        };
+        let config = make_config_no_keycloak();
+        let http = reqwest::Client::new();
+        let result = cleanup_test_user(&user, &config, &http).await;
+        assert!(result.is_err());
+        assert!(result
+            .as_ref()
+            .err()
+            .is_some_and(|e| e.contains("OKTA_DOMAIN")));
+    }
+}

compliance-agent/src/pentest/context.rs

@@ -0,0 +1,150 @@
+use futures_util::StreamExt;
+use mongodb::bson::doc;
+
+use compliance_core::models::dast::DastTarget;
+use compliance_core::models::finding::Finding;
+use compliance_core::models::pentest::CodeContextHint;
+use compliance_core::models::sbom::SbomEntry;
+
+use super::orchestrator::PentestOrchestrator;
+
+impl PentestOrchestrator {
+    /// Fetch SAST findings, SBOM entries (with CVEs), and code graph entry points
+    /// for the repo linked to this DAST target.
+    pub(crate) async fn gather_repo_context(
+        &self,
+        target: &DastTarget,
+    ) -> (Vec<Finding>, Vec<SbomEntry>, Vec<CodeContextHint>) {
+        let Some(repo_id) = &target.repo_id else {
+            return (Vec::new(), Vec::new(), Vec::new());
+        };
+
+        let sast_findings = self.fetch_sast_findings(repo_id).await;
+        let sbom_entries = self.fetch_vulnerable_sbom(repo_id).await;
+        let code_context = self.fetch_code_context(repo_id, &sast_findings).await;
+
+        tracing::info!(
+            repo_id,
+            sast_findings = sast_findings.len(),
+            vulnerable_deps = sbom_entries.len(),
+            code_hints = code_context.len(),
+            "Gathered code-awareness context for pentest"
+        );
+
+        (sast_findings, sbom_entries, code_context)
+    }
+
+    /// Fetch open/triaged SAST findings for the repo (not false positives or resolved)
+    async fn fetch_sast_findings(&self, repo_id: &str) -> Vec<Finding> {
+        let cursor = self
+            .db
+            .findings()
+            .find(doc! {
+                "repo_id": repo_id,
+                "status": { "$in": ["open", "triaged"] },
+            })
+            .sort(doc! { "severity": -1 })
+            .limit(100)
+            .await;
+
+        match cursor {
+            Ok(mut c) => {
+                let mut results = Vec::new();
+                while let Some(Ok(f)) = c.next().await {
+                    results.push(f);
+                }
+                results
+            }
+            Err(e) => {
+                tracing::warn!("Failed to fetch SAST findings for pentest: {e}");
+                Vec::new()
+            }
+        }
+    }
+
+    /// Fetch SBOM entries that have known vulnerabilities
+    async fn fetch_vulnerable_sbom(&self, repo_id: &str) -> Vec<SbomEntry> {
+        let cursor = self
+            .db
+            .sbom_entries()
+            .find(doc! {
+                "repo_id": repo_id,
+                "known_vulnerabilities": { "$exists": true, "$ne": [] },
+            })
+            .limit(50)
+            .await;
+
+        match cursor {
+            Ok(mut c) => {
+                let mut results = Vec::new();
+                while let Some(Ok(e)) = c.next().await {
+                    results.push(e);
+                }
+                results
+            }
+            Err(e) => {
+                tracing::warn!("Failed to fetch vulnerable SBOM entries: {e}");
+                Vec::new()
+            }
+        }
+    }
+
+    /// Build CodeContextHint objects from the code knowledge graph.
+    /// Maps entry points to their source files and links SAST findings.
+    async fn fetch_code_context(
+        &self,
+        repo_id: &str,
+        sast_findings: &[Finding],
+    ) -> Vec<CodeContextHint> {
+        // Get entry point nodes from the code graph
+        let cursor = self
+            .db
+            .graph_nodes()
+            .find(doc! {
+                "repo_id": repo_id,
+                "is_entry_point": true,
+            })
+            .limit(50)
+            .await;
+
+        let nodes = match cursor {
+            Ok(mut c) => {
+                let mut results = Vec::new();
+                while let Some(Ok(n)) = c.next().await {
+                    results.push(n);
+                }
+                results
+            }
+            Err(_) => return Vec::new(),
+        };
+
+        // Build hints by matching graph nodes to SAST findings by file path
+        nodes
+            .into_iter()
+            .map(|node| {
+                // Find SAST findings in the same file
+                let linked_vulns: Vec<String> = sast_findings
+                    .iter()
+                    .filter(|f| f.file_path.as_deref() == Some(&node.file_path))
+                    .map(|f| {
+                        format!(
+                            "[{}] {}: {} (line {})",
+                            f.severity,
+                            f.scanner,
+                            f.title,
+                            f.line_number.unwrap_or(0)
+                        )
+                    })
+                    .collect();
+
+                CodeContextHint {
+                    endpoint_pattern: node.qualified_name.clone(),
+                    handler_function: node.name.clone(),
+                    file_path: node.file_path.clone(),
+                    code_snippet: String::new(), // Could fetch from embeddings
+                    known_vulnerabilities: linked_vulns,
+                }
+            })
+            .collect()
+    }
+}

compliance-agent/src/pentest/crypto.rs

@@ -0,0 +1,117 @@
+use aes_gcm::aead::AeadCore;
+use aes_gcm::{
+    aead::{Aead, KeyInit, OsRng},
+    Aes256Gcm, Nonce,
+};
+use base64::Engine;
+
+/// Load the 32-byte encryption key from PENTEST_ENCRYPTION_KEY env var.
+/// Returns None if not set or invalid length.
+pub fn load_encryption_key() -> Option<[u8; 32]> {
+    let hex_key = std::env::var("PENTEST_ENCRYPTION_KEY").ok()?;
+    let bytes = hex::decode(hex_key).ok()?;
+    if bytes.len() != 32 {
+        return None;
+    }
+    let mut key = [0u8; 32];
+    key.copy_from_slice(&bytes);
+    Some(key)
+}
+
+/// Encrypt a plaintext string. Returns base64-encoded nonce+ciphertext.
+/// Returns the original string if no encryption key is available.
+pub fn encrypt(plaintext: &str) -> String {
+    let Some(key_bytes) = load_encryption_key() else {
+        return plaintext.to_string();
+    };
+    let Ok(cipher) = Aes256Gcm::new_from_slice(&key_bytes) else {
+        return plaintext.to_string();
+    };
+    let nonce = Aes256Gcm::generate_nonce(&mut OsRng);
+    let Ok(ciphertext) = cipher.encrypt(&nonce, plaintext.as_bytes()) else {
+        return plaintext.to_string();
+    };
+    let mut combined = nonce.to_vec();
+    combined.extend_from_slice(&ciphertext);
+    base64::engine::general_purpose::STANDARD.encode(&combined)
+}
+
+/// Decrypt a base64-encoded nonce+ciphertext string.
+/// Returns None if decryption fails.
+pub fn decrypt(encrypted: &str) -> Option<String> {
+    let key_bytes = load_encryption_key()?;
+    let cipher = Aes256Gcm::new_from_slice(&key_bytes).ok()?;
+    let combined = base64::engine::general_purpose::STANDARD
+        .decode(encrypted)
+        .ok()?;
+    if combined.len() < 12 {
+        return None;
+    }
+    let (nonce_bytes, ciphertext) = combined.split_at(12);
+    let nonce = Nonce::from_slice(nonce_bytes);
+    let plaintext = cipher.decrypt(nonce, ciphertext).ok()?;
+    String::from_utf8(plaintext).ok()
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::sync::Mutex;
+
+    // Guard to serialize tests that touch env vars
+    static ENV_LOCK: Mutex<()> = Mutex::new(());
+
+    fn with_key<F: FnOnce()>(hex_key: &str, f: F) {
+        let _guard = ENV_LOCK.lock();
+        unsafe { std::env::set_var("PENTEST_ENCRYPTION_KEY", hex_key) };
+        f();
+        unsafe { std::env::remove_var("PENTEST_ENCRYPTION_KEY") };
+    }
+
+    #[test]
+    fn round_trip() {
+        let key = "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef";
+        with_key(key, || {
+            let plaintext = "my_secret_password";
+            let encrypted = encrypt(plaintext);
+            assert_ne!(encrypted, plaintext);
+            let decrypted = decrypt(&encrypted);
+            assert_eq!(decrypted, Some(plaintext.to_string()));
+        });
+    }
+
+    #[test]
+    fn wrong_key_fails() {
+        let _guard = ENV_LOCK.lock();
+        let key1 = "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef";
+        let key2 = "abcdef0123456789abcdef0123456789abcdef0123456789abcdef0123456789";
+        let encrypted = {
+            unsafe { std::env::set_var("PENTEST_ENCRYPTION_KEY", key1) };
+            let e = encrypt("secret");
+            unsafe { std::env::remove_var("PENTEST_ENCRYPTION_KEY") };
+            e
+        };
+        unsafe { std::env::set_var("PENTEST_ENCRYPTION_KEY", key2) };
+        assert!(decrypt(&encrypted).is_none());
+        unsafe { std::env::remove_var("PENTEST_ENCRYPTION_KEY") };
+    }
+
+    #[test]
+    fn no_key_passthrough() {
+        let _guard = ENV_LOCK.lock();
+        unsafe { std::env::remove_var("PENTEST_ENCRYPTION_KEY") };
+        let result = encrypt("plain");
+        assert_eq!(result, "plain");
+    }
+
+    #[test]
+    fn corrupted_ciphertext() {
+        let key = "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef";
+        with_key(key, || {
+            assert!(decrypt("not-valid-base64!!!").is_none());
+            // Valid base64 but wrong content
+            let garbage = base64::engine::general_purpose::STANDARD.encode(b"tooshort");
+            assert!(decrypt(&garbage).is_none());
+        });
+    }
+}

compliance-agent/src/pentest/mod.rs

@@ -0,0 +1,9 @@
+pub mod cleanup;
+mod context;
+pub mod crypto;
+pub mod orchestrator;
+mod prompt_builder;
+pub mod report;
+
+pub use orchestrator::PentestOrchestrator;
+pub use report::generate_encrypted_report;

compliance-agent/src/pentest/orchestrator.rs

@@ -0,0 +1,706 @@
+use std::sync::Arc;
+use std::time::Duration;
+
+use mongodb::bson::doc;
+use tokio::sync::{broadcast, watch};
+
+use compliance_core::models::dast::DastTarget;
+use compliance_core::models::pentest::*;
+use compliance_core::traits::pentest_tool::PentestToolContext;
+use compliance_dast::ToolRegistry;
+
+use crate::database::Database;
+use crate::llm::{
+    ChatMessage, LlmClient, LlmResponse, ToolCallRequest, ToolCallRequestFunction, ToolDefinition,
+};
+
+/// Maximum duration for a single pentest session before timeout
+const SESSION_TIMEOUT: Duration = Duration::from_secs(30 * 60); // 30 minutes
+
+pub struct PentestOrchestrator {
+    pub(crate) tool_registry: ToolRegistry,
+    pub(crate) llm: Arc<LlmClient>,
+    pub(crate) db: Database,
+    pub(crate) event_tx: broadcast::Sender<PentestEvent>,
+    pub(crate) pause_rx: Option<watch::Receiver<bool>>,
+}
+
+impl PentestOrchestrator {
+    /// Create a new orchestrator with an externally-provided broadcast sender
+    /// and an optional pause receiver.
+    pub fn new(
+        llm: Arc<LlmClient>,
+        db: Database,
+        event_tx: broadcast::Sender<PentestEvent>,
+        pause_rx: Option<watch::Receiver<bool>>,
+    ) -> Self {
+        Self {
+            tool_registry: ToolRegistry::new(),
+            llm,
+            db,
+            event_tx,
+            pause_rx,
+        }
+    }
+
+    /// Run a pentest session with timeout and automatic failure marking on errors.
+    pub async fn run_session_guarded(
+        &self,
+        session: &PentestSession,
+        target: &DastTarget,
+        initial_message: &str,
+    ) {
+        let session_id = session.id;
+
+        // Use config-specified timeout or default
+        let timeout_duration = session
+            .config
+            .as_ref()
+            .and_then(|c| c.max_duration_minutes)
+            .map(|m| Duration::from_secs(m as u64 * 60))
+            .unwrap_or(SESSION_TIMEOUT);
+
+        let timeout_minutes = timeout_duration.as_secs() / 60;
+
+        match tokio::time::timeout(
+            timeout_duration,
+            self.run_session(session, target, initial_message),
+        )
+        .await
+        {
+            Ok(Ok(())) => {
+                tracing::info!(?session_id, "Pentest session completed successfully");
+            }
+            Ok(Err(e)) => {
+                tracing::error!(?session_id, error = %e, "Pentest session failed");
+                self.mark_session_failed(session_id, &format!("Error: {e}"))
+                    .await;
+                let _ = self.event_tx.send(PentestEvent::Error {
+                    message: format!("Session failed: {e}"),
+                });
+            }
+            Err(_) => {
+                let msg = format!("Session timed out after {timeout_minutes} minutes");
+                tracing::warn!(?session_id, "{msg}");
+                self.mark_session_failed(session_id, &msg).await;
+                let _ = self.event_tx.send(PentestEvent::Error { message: msg });
+            }
+        }
+    }
+
+    async fn mark_session_failed(
+        &self,
+        session_id: Option<mongodb::bson::oid::ObjectId>,
+        reason: &str,
+    ) {
+        if let Some(sid) = session_id {
+            let _ = self
+                .db
+                .pentest_sessions()
+                .update_one(
+                    doc! { "_id": sid },
+                    doc! { "$set": {
+                        "status": "failed",
+                        "completed_at": mongodb::bson::DateTime::now(),
+                        "error_message": reason,
+                    }},
+                )
+                .await;
+        }
+    }
+
+    /// Check if the session is paused; if so, update DB status and wait until resumed.
+    async fn wait_if_paused(&self, session: &PentestSession) {
+        let Some(ref pause_rx) = self.pause_rx else {
+            return;
+        };
+        let mut rx = pause_rx.clone();
+
+        if !*rx.borrow() {
+            return;
+        }
+
+        // We are paused — update DB status
+        if let Some(sid) = session.id {
+            let _ = self
+                .db
+                .pentest_sessions()
+                .update_one(doc! { "_id": sid }, doc! { "$set": { "status": "paused" }})
+                .await;
+        }
+        let _ = self.event_tx.send(PentestEvent::Paused);
+
+        // Wait until unpaused
+        while *rx.borrow() {
+            if rx.changed().await.is_err() {
+                break;
+            }
+        }
+
+        // Resumed — update DB status back to running
+        if let Some(sid) = session.id {
+            let _ = self
+                .db
+                .pentest_sessions()
+                .update_one(doc! { "_id": sid }, doc! { "$set": { "status": "running" }})
+                .await;
+        }
+        let _ = self.event_tx.send(PentestEvent::Resumed);
+    }
+
+    async fn run_session(
+        &self,
+        session: &PentestSession,
+        target: &DastTarget,
+        initial_message: &str,
+    ) -> Result<(), crate::error::AgentError> {
+        let session_id = session.id.map(|oid| oid.to_hex()).unwrap_or_default();
+
+        // Gather code-awareness context from linked repo
+        let (sast_findings, sbom_entries, code_context) = self.gather_repo_context(target).await;
+
+        // Build system prompt with code context
+        let system_prompt = self
+            .build_system_prompt(
+                session,
+                target,
+                &sast_findings,
+                &sbom_entries,
+                &code_context,
+            )
+            .await;
+
+        // Build tool definitions for LLM
+        let tool_defs: Vec<ToolDefinition> = self
+            .tool_registry
+            .all_definitions()
+            .into_iter()
+            .map(|td| ToolDefinition {
+                name: td.name,
+                description: td.description,
+                parameters: td.input_schema,
+            })
+            .collect();
+
+        // Initialize messages
+        let mut messages = vec![
+            ChatMessage {
+                role: "system".to_string(),
+                content: Some(system_prompt),
+                tool_calls: None,
+                tool_call_id: None,
+            },
+            ChatMessage {
+                role: "user".to_string(),
+                content: Some(initial_message.to_string()),
+                tool_calls: None,
+                tool_call_id: None,
+            },
+        ];
+
+        // Store user message
+        let user_msg = PentestMessage::user(session_id.clone(), initial_message.to_string());
+        let _ = self.db.pentest_messages().insert_one(&user_msg).await;
+
+        // Build tool context with real data
+        let tool_context = PentestToolContext {
+            target: target.clone(),
+            session_id: session_id.clone(),
+            sast_findings,
+            sbom_entries,
+            code_context,
+            rate_limit: target.rate_limit,
+            allow_destructive: target.allow_destructive,
+        };
+
+        let max_iterations = 50;
+        let mut total_findings = 0u32;
+        let mut total_tool_calls = 0u32;
+        let mut total_successes = 0u32;
+        let mut prev_node_ids: Vec<String> = Vec::new();
+
+        for _iteration in 0..max_iterations {
+            // Check pause state at top of each iteration
+            self.wait_if_paused(session).await;
+
+            let response = self
+                .llm
+                .chat_with_tools(messages.clone(), &tool_defs, Some(0.2), Some(8192))
+                .await?;
+
+            match response {
+                LlmResponse::Content(content) => {
+                    let msg = PentestMessage::assistant(session_id.clone(), content.clone());
+                    let _ = self.db.pentest_messages().insert_one(&msg).await;
+                    let _ = self.event_tx.send(PentestEvent::Message {
+                        content: content.clone(),
+                    });
+
+                    messages.push(ChatMessage {
+                        role: "assistant".to_string(),
+                        content: Some(content.clone()),
+                        tool_calls: None,
+                        tool_call_id: None,
+                    });
+
+                    let done_indicators = [
+                        "pentest complete",
+                        "testing complete",
+                        "scan complete",
+                        "analysis complete",
+                        "finished",
+                        "that concludes",
+                    ];
+                    let content_lower = content.to_lowercase();
+                    if done_indicators
+                        .iter()
+                        .any(|ind| content_lower.contains(ind))
+                    {
+                        break;
+                    }
+                    break;
+                }
+                LlmResponse::ToolCalls {
+                    calls: tool_calls,
+                    reasoning,
+                } => {
+                    let tc_requests: Vec<ToolCallRequest> = tool_calls
+                        .iter()
+                        .map(|tc| ToolCallRequest {
+                            id: tc.id.clone(),
+                            r#type: "function".to_string(),
+                            function: ToolCallRequestFunction {
+                                name: tc.name.clone(),
+                                arguments: serde_json::to_string(&tc.arguments).unwrap_or_default(),
+                            },
+                        })
+                        .collect();
+
+                    messages.push(ChatMessage {
+                        role: "assistant".to_string(),
+                        content: if reasoning.is_empty() {
+                            None
+                        } else {
+                            Some(reasoning.clone())
+                        },
+                        tool_calls: Some(tc_requests),
+                        tool_call_id: None,
+                    });
+
+                    let mut current_batch_node_ids: Vec<String> = Vec::new();
+
+                    for tc in &tool_calls {
+                        total_tool_calls += 1;
+                        let node_id = uuid::Uuid::new_v4().to_string();
+
+                        let mut node = AttackChainNode::new(
+                            session_id.clone(),
+                            node_id.clone(),
+                            tc.name.clone(),
+                            tc.arguments.clone(),
+                            reasoning.clone(),
+                        );
+                        // Link to previous iteration's nodes
+                        node.parent_node_ids = prev_node_ids.clone();
+                        node.status = AttackNodeStatus::Running;
+                        node.started_at = Some(chrono::Utc::now());
+                        let _ = self.db.attack_chain_nodes().insert_one(&node).await;
+                        current_batch_node_ids.push(node_id.clone());
+
+                        let _ = self.event_tx.send(PentestEvent::ToolStart {
+                            node_id: node_id.clone(),
+                            tool_name: tc.name.clone(),
+                            input: tc.arguments.clone(),
+                        });
+
+                        let result = if let Some(tool) = self.tool_registry.get(&tc.name) {
+                            match tool.execute(tc.arguments.clone(), &tool_context).await {
+                                Ok(result) => {
+                                    total_successes += 1;
+                                    let findings_count = result.findings.len() as u32;
+                                    total_findings += findings_count;
+
+                                    let mut finding_ids: Vec<String> = Vec::new();
+                                    for mut finding in result.findings {
+                                        finding.scan_run_id = session_id.clone();
+                                        finding.session_id = Some(session_id.clone());
+                                        let insert_result =
+                                            self.db.dast_findings().insert_one(&finding).await;
+                                        if let Ok(res) = &insert_result {
+                                            finding_ids.push(
+                                                res.inserted_id
+                                                    .as_object_id()
+                                                    .map(|oid| oid.to_hex())
+                                                    .unwrap_or_default(),
+                                            );
+                                        }
+                                        let _ = self.event_tx.send(PentestEvent::Finding {
+                                            finding_id: finding
+                                                .id
+                                                .map(|oid| oid.to_hex())
+                                                .unwrap_or_default(),
+                                            title: finding.title.clone(),
+                                            severity: finding.severity.to_string(),
+                                        });
+                                    }
+
+                                    // Compute risk score based on findings severity
+                                    let risk_score: Option<u8> = if findings_count > 0 {
+                                        Some(std::cmp::min(
+                                            100,
+                                            (findings_count as u8)
+                                                .saturating_mul(15)
+                                                .saturating_add(20),
+                                        ))
+                                    } else {
+                                        None
+                                    };
+
+                                    let _ = self.event_tx.send(PentestEvent::ToolComplete {
+                                        node_id: node_id.clone(),
+                                        summary: result.summary.clone(),
+                                        findings_count,
+                                    });
+
+                                    let finding_ids_bson: Vec<mongodb::bson::Bson> = finding_ids
+                                        .iter()
+                                        .map(|id| mongodb::bson::Bson::String(id.clone()))
+                                        .collect();
+
+                                    let mut update_doc = doc! {
+                                        "status": "completed",
+                                        "tool_output": mongodb::bson::to_bson(&result.data)
+                                            .unwrap_or(mongodb::bson::Bson::Null),
+                                        "completed_at": mongodb::bson::DateTime::now(),
+                                        "findings_produced": finding_ids_bson,
+                                    };
+                                    if let Some(rs) = risk_score {
+                                        update_doc.insert("risk_score", rs as i32);
+                                    }
+
+                                    let _ = self
+                                        .db
+                                        .attack_chain_nodes()
+                                        .update_one(
+                                            doc! {
+                                                "session_id": &session_id,
+                                                "node_id": &node_id,
+                                            },
+                                            doc! { "$set": update_doc },
+                                        )
+                                        .await;
+
+                                    // Build LLM-facing summary: strip large fields
+                                    // (screenshots, raw HTML) to save context window
+                                    let llm_data = summarize_tool_output(&result.data);
+                                    serde_json::json!({
+                                        "summary": result.summary,
+                                        "findings_count": findings_count,
+                                        "data": llm_data,
+                                    })
+                                    .to_string()
+                                }
+                                Err(e) => {
+                                    let _ = self
+                                        .db
+                                        .attack_chain_nodes()
+                                        .update_one(
+                                            doc! {
+                                                "session_id": &session_id,
+                                                "node_id": &node_id,
+                                            },
+                                            doc! { "$set": {
+                                                "status": "failed",
+                                                "completed_at": mongodb::bson::DateTime::now(),
+                                            }},
+                                        )
+                                        .await;
+                                    format!("Tool execution failed: {e}")
+                                }
+                            }
+                        } else {
+                            format!("Unknown tool: {}", tc.name)
+                        };
+
+                        messages.push(ChatMessage {
+                            role: "tool".to_string(),
+                            content: Some(result),
+                            tool_calls: None,
+                            tool_call_id: Some(tc.id.clone()),
+                        });
+                    }
+
+                    // Advance parent links so next iteration's nodes connect to this batch
+                    prev_node_ids = current_batch_node_ids;
+
+                    if let Some(sid) = session.id {
+                        let _ = self
+                            .db
+                            .pentest_sessions()
+                            .update_one(
+                                doc! { "_id": sid },
+                                doc! { "$set": {
+                                    "tool_invocations": total_tool_calls as i64,
+                                    "tool_successes": total_successes as i64,
+                                    "findings_count": total_findings as i64,
+                                }},
+                            )
+                            .await;
+                    }
+                }
+            }
+        }
+
+        if let Some(sid) = session.id {
+            let _ = self
+                .db
+                .pentest_sessions()
+                .update_one(
+                    doc! { "_id": sid },
+                    doc! { "$set": {
+                        "status": "completed",
+                        "completed_at": mongodb::bson::DateTime::now(),
+                        "tool_invocations": total_tool_calls as i64,
+                        "tool_successes": total_successes as i64,
+                        "findings_count": total_findings as i64,
+                    }},
+                )
+                .await;
+        }
+
+        // Clean up test user via identity provider API if requested
+        if session
+            .config
+            .as_ref()
+            .is_some_and(|c| c.auth.cleanup_test_user)
+        {
+            if let Some(ref test_user) = session.test_user {
+                let http = reqwest::Client::new();
+                // We need the AgentConfig — read from env since orchestrator doesn't hold it
+                let config = crate::config::load_config();
+                match config {
+                    Ok(cfg) => {
+                        match crate::pentest::cleanup::cleanup_test_user(test_user, &cfg, &http)
+                            .await
+                        {
+                            Ok(true) => {
+                                tracing::info!(
+                                    username = test_user.username.as_deref(),
+                                    "Test user cleaned up via provider API"
+                                );
+                                // Mark as cleaned up in DB
+                                if let Some(sid) = session.id {
+                                    let _ = self
+                                        .db
+                                        .pentest_sessions()
+                                        .update_one(
+                                            doc! { "_id": sid },
+                                            doc! { "$set": { "test_user.cleaned_up": true } },
+                                        )
+                                        .await;
+                                }
+                            }
+                            Ok(false) => {
+                                tracing::info!(
+                                    "Test user cleanup skipped (no provider configured)"
+                                );
+                            }
+                            Err(e) => {
+                                tracing::warn!(error = %e, "Test user cleanup failed");
+                                let _ = self.event_tx.send(PentestEvent::Error {
+                                    message: format!("Test user cleanup failed: {e}"),
+                                });
+                            }
+                        }
+                    }
+                    Err(e) => {
+                        tracing::warn!(error = %e, "Could not load config for cleanup");
+                    }
+                }
+            }
+        }
+
+        // Clean up the persistent browser session for this pentest
+        compliance_dast::tools::browser::cleanup_browser_session(&session_id).await;
+
+        let _ = self.event_tx.send(PentestEvent::Complete {
+            summary: format!(
+                "Pentest complete. {} findings from {} tool invocations.",
+                total_findings, total_tool_calls
+            ),
+        });
+
+        Ok(())
+    }
+}
+
+/// Strip large fields from tool output before sending to the LLM.
+/// Screenshots, raw HTML, and other bulky data are replaced with short summaries.
+/// The full data is still stored in the DB for the report.
+fn summarize_tool_output(data: &serde_json::Value) -> serde_json::Value {
+    let Some(obj) = data.as_object() else {
+        return data.clone();
+    };
+
+    let mut summarized = serde_json::Map::new();
+    for (key, value) in obj {
+        match key.as_str() {
+            // Replace screenshot base64 with a placeholder
+            "screenshot_base64" => {
+                if let Some(s) = value.as_str() {
+                    if !s.is_empty() {
+                        summarized.insert(
+                            key.clone(),
+                            serde_json::Value::String(
+                                "[screenshot captured and saved to report]".to_string(),
+                            ),
+                        );
+                        continue;
+                    }
+                }
+                summarized.insert(key.clone(), value.clone());
+            }
+            // Truncate raw HTML content
+            "html" => {
+                if let Some(s) = value.as_str() {
+                    if s.len() > 2000 {
+                        summarized.insert(
+                            key.clone(),
+                            serde_json::Value::String(format!(
+                                "{}... [truncated, {} chars total]",
+                                &s[..2000],
+                                s.len()
+                            )),
+                        );
+                        continue;
+                    }
+                }
+                summarized.insert(key.clone(), value.clone());
+            }
+            // Truncate page text
+            "text" if value.as_str().is_some_and(|s| s.len() > 1500) => {
+                let s = value.as_str().unwrap_or_default();
+                summarized.insert(
+                    key.clone(),
+                    serde_json::Value::String(format!("{}... [truncated]", &s[..1500])),
+                );
+            }
+            // Trim large arrays (e.g., "elements", "links", "inputs")
+            "elements" | "links" | "inputs" => {
+                if let Some(arr) = value.as_array() {
+                    if arr.len() > 15 {
+                        let mut trimmed: Vec<serde_json::Value> = arr[..15].to_vec();
+                        trimmed.push(serde_json::json!(format!(
+                            "... and {} more",
+                            arr.len() - 15
+                        )));
+                        summarized.insert(key.clone(), serde_json::Value::Array(trimmed));
+                        continue;
+                    }
+                }
+                summarized.insert(key.clone(), value.clone());
+            }
+            // Recursively summarize nested objects (e.g., "page" in get_content)
+            _ if value.is_object() => {
+                summarized.insert(key.clone(), summarize_tool_output(value));
+            }
+            // Keep everything else as-is
+            _ => {
+                summarized.insert(key.clone(), value.clone());
+            }
+        }
+    }
+    serde_json::Value::Object(summarized)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use serde_json::json;
+
+    #[test]
+    fn test_summarize_strips_screenshot() {
+        let input = json!({
+            "screenshot_base64": "iVBOR...",
+            "url": "https://example.com"
+        });
+        let result = summarize_tool_output(&input);
+        assert_eq!(
+            result["screenshot_base64"],
+            "[screenshot captured and saved to report]"
+        );
+        assert_eq!(result["url"], "https://example.com");
+    }
+
+    #[test]
+    fn test_summarize_truncates_html() {
+        let long_html = "x".repeat(3000);
+        let input = json!({ "html": long_html });
+        let result = summarize_tool_output(&input);
+        let s = result["html"].as_str().unwrap_or_default();
+        assert!(s.contains("[truncated, 3000 chars total]"));
+        assert!(s.starts_with(&"x".repeat(2000)));
+        assert!(s.len() < 3000);
+    }
+
+    #[test]
+    fn test_summarize_truncates_text() {
+        let long_text = "a".repeat(2000);
+        let input = json!({ "text": long_text });
+        let result = summarize_tool_output(&input);
+        let s = result["text"].as_str().unwrap_or_default();
+        assert!(s.contains("[truncated]"));
+        assert!(s.starts_with(&"a".repeat(1500)));
+        assert!(s.len() < 2000);
+    }
+
+    #[test]
+    fn test_summarize_trims_large_arrays() {
+        let elements: Vec<serde_json::Value> = (0..20).map(|i| json!(format!("el-{i}"))).collect();
+        let input = json!({ "elements": elements });
+        let result = summarize_tool_output(&input);
+        let arr = result["elements"].as_array();
+        assert!(arr.is_some());
+        if let Some(arr) = arr {
+            // 15 kept + 1 summary entry
+            assert_eq!(arr.len(), 16);
+            assert_eq!(arr[15], json!("... and 5 more"));
+        }
+    }
+
+    #[test]
+    fn test_summarize_preserves_small_data() {
+        let input = json!({
+            "url": "https://example.com",
+            "status": 200,
+            "title": "Example"
+        });
+        let result = summarize_tool_output(&input);
+        assert_eq!(result, input);
+    }
+
+    #[test]
+    fn test_summarize_recursive() {
+        let input = json!({
+            "page": {
+                "screenshot_base64": "iVBORw0KGgoAAAA...",
+                "url": "https://example.com"
+            }
+        });
+        let result = summarize_tool_output(&input);
+        assert_eq!(
+            result["page"]["screenshot_base64"],
+            "[screenshot captured and saved to report]"
+        );
+        assert_eq!(result["page"]["url"], "https://example.com");
+    }
+
+    #[test]
+    fn test_summarize_non_object() {
+        let string_val = json!("just a string");
+        assert_eq!(summarize_tool_output(&string_val), string_val);
+
+        let num_val = json!(42);
+        assert_eq!(summarize_tool_output(&num_val), num_val);
+    }
+}

compliance-agent/src/pentest/prompt_builder.rs

@@ -0,0 +1,622 @@
+use compliance_core::models::dast::DastTarget;
+use compliance_core::models::finding::{Finding, FindingStatus, Severity};
+use compliance_core::models::pentest::*;
+use compliance_core::models::sbom::SbomEntry;
+
+use super::orchestrator::PentestOrchestrator;
+
+/// Attempt to decrypt a field; if decryption fails, return the original value
+/// (which may be plaintext from before encryption was enabled).
+fn decrypt_field(value: &str) -> String {
+    super::crypto::decrypt(value).unwrap_or_else(|| value.to_string())
+}
+
+/// Build additional prompt sections from PentestConfig when present.
+fn build_config_sections(config: &PentestConfig) -> String {
+    let mut sections = String::new();
+
+    // Authentication section
+    match config.auth.mode {
+        AuthMode::Manual => {
+            sections.push_str("\n## Authentication\n");
+            sections.push_str("- **Mode**: Manual credentials\n");
+            if let Some(ref u) = config.auth.username {
+                let decrypted = decrypt_field(u);
+                sections.push_str(&format!("- **Username**: {decrypted}\n"));
+            }
+            if let Some(ref p) = config.auth.password {
+                let decrypted = decrypt_field(p);
+                sections.push_str(&format!("- **Password**: {decrypted}\n"));
+            }
+            sections.push_str(
+                "Use these credentials to log in before testing authenticated endpoints.\n",
+            );
+        }
+        AuthMode::AutoRegister => {
+            sections.push_str("\n## Authentication\n");
+            sections.push_str("- **Mode**: Auto-register\n");
+            if let Some(ref url) = config.auth.registration_url {
+                sections.push_str(&format!("- **Registration URL**: {url}\n"));
+            } else {
+                sections.push_str(
+                    "- **Registration URL**: Not provided — use Playwright to discover the registration page.\n",
+                );
+            }
+            if let Some(ref email) = config.auth.verification_email {
+                sections.push_str(&format!(
+                    "- **Verification Email**: Use plus-addressing from `{email}` \
+                     (e.g. `{base}+{{session_id}}@{domain}`) for email verification. \
+                     The system will poll the IMAP mailbox for verification links.\n",
+                    base = email.split('@').next().unwrap_or(email),
+                    domain = email.split('@').nth(1).unwrap_or("example.com"),
+                ));
+            }
+            sections.push_str(
+                "Register a new test account using the registration page, then use it for testing.\n",
+            );
+        }
+        AuthMode::None => {}
+    }
+
+    // Custom headers
+    if !config.custom_headers.is_empty() {
+        sections.push_str("\n## Custom HTTP Headers\n");
+        sections.push_str("Include these headers in all HTTP requests:\n");
+        for (k, v) in &config.custom_headers {
+            sections.push_str(&format!("- `{k}: {v}`\n"));
+        }
+    }
+
+    // Scope exclusions
+    if !config.scope_exclusions.is_empty() {
+        sections.push_str("\n## Scope Exclusions\n");
+        sections.push_str("Do NOT test the following paths:\n");
+        for path in &config.scope_exclusions {
+            sections.push_str(&format!("- `{path}`\n"));
+        }
+    }
+
+    // Git context
+    if config.git_repo_url.is_some() || config.branch.is_some() || config.commit_hash.is_some() {
+        sections.push_str("\n## Git Context\n");
+        if let Some(ref url) = config.git_repo_url {
+            sections.push_str(&format!("- **Repository**: {url}\n"));
+        }
+        if let Some(ref branch) = config.branch {
+            sections.push_str(&format!("- **Branch**: {branch}\n"));
+        }
+        if let Some(ref commit) = config.commit_hash {
+            sections.push_str(&format!("- **Commit**: {commit}\n"));
+        }
+    }
+
+    // Environment
+    sections.push_str(&format!(
+        "\n## Environment\n- **Target environment**: {}\n",
+        config.environment
+    ));
+
+    sections
+}
+
+/// Return strategy guidance text for the given strategy.
+fn strategy_guidance(strategy: &PentestStrategy) -> &'static str {
+    match strategy {
+        PentestStrategy::Quick => {
+            "Focus on the most common and impactful vulnerabilities. Run a quick recon, then target the highest-risk areas."
+        }
+        PentestStrategy::Comprehensive => {
+            "Perform a thorough assessment covering all vulnerability types. Start with recon, then systematically test each attack surface."
+        }
+        PentestStrategy::Targeted => {
+            "Focus specifically on areas highlighted by SAST findings and known CVEs. Prioritize exploiting known weaknesses."
+        }
+        PentestStrategy::Aggressive => {
+            "Use all available tools aggressively. Test with maximum payloads and attempt full exploitation."
+        }
+        PentestStrategy::Stealth => {
+            "Minimize noise. Use fewer requests, avoid aggressive payloads. Focus on passive analysis and targeted probes."
+        }
+    }
+}
+
+/// Build the SAST findings section for the system prompt.
+fn build_sast_section(sast_findings: &[Finding]) -> String {
+    if sast_findings.is_empty() {
+        return String::from("No SAST findings available for this target.");
+    }
+
+    let critical = sast_findings
+        .iter()
+        .filter(|f| f.severity == Severity::Critical)
+        .count();
+    let high = sast_findings
+        .iter()
+        .filter(|f| f.severity == Severity::High)
+        .count();
+
+    let mut section = format!(
+        "{} open findings ({} critical, {} high):\n",
+        sast_findings.len(),
+        critical,
+        high
+    );
+
+    // List the most important findings (critical/high first, up to 20)
+    for f in sast_findings.iter().take(20) {
+        let file_info = f
+            .file_path
+            .as_ref()
+            .map(|p| format!(" in {}:{}", p, f.line_number.unwrap_or(0)))
+            .unwrap_or_default();
+        let status_note = match f.status {
+            FindingStatus::Triaged => " [TRIAGED]",
+            _ => "",
+        };
+        section.push_str(&format!(
+            "- [{sev}] {title}{file}{status}\n",
+            sev = f.severity,
+            title = f.title,
+            file = file_info,
+            status = status_note,
+        ));
+        if let Some(cwe) = &f.cwe {
+            section.push_str(&format!("  CWE: {cwe}\n"));
+        }
+    }
+    if sast_findings.len() > 20 {
+        section.push_str(&format!(
+            "... and {} more findings\n",
+            sast_findings.len() - 20
+        ));
+    }
+    section
+}
+
+/// Build the SBOM/CVE section for the system prompt.
+fn build_sbom_section(sbom_entries: &[SbomEntry]) -> String {
+    if sbom_entries.is_empty() {
+        return String::from("No vulnerable dependencies identified.");
+    }
+
+    let mut section = format!(
+        "{} dependencies with known vulnerabilities:\n",
+        sbom_entries.len()
+    );
+    for entry in sbom_entries.iter().take(15) {
+        let cve_ids: Vec<&str> = entry
+            .known_vulnerabilities
+            .iter()
+            .map(|v| v.id.as_str())
+            .collect();
+        section.push_str(&format!(
+            "- {} {} ({}): {}\n",
+            entry.name,
+            entry.version,
+            entry.package_manager,
+            cve_ids.join(", ")
+        ));
+    }
+    if sbom_entries.len() > 15 {
+        section.push_str(&format!(
+            "... and {} more vulnerable dependencies\n",
+            sbom_entries.len() - 15
+        ));
+    }
+    section
+}
+
+/// Build the code context section for the system prompt.
+fn build_code_section(code_context: &[CodeContextHint]) -> String {
+    if code_context.is_empty() {
+        return String::from("No code knowledge graph available for this target.");
+    }
+
+    let with_vulns = code_context
+        .iter()
+        .filter(|c| !c.known_vulnerabilities.is_empty())
+        .count();
+
+    let mut section = format!(
+        "{} entry points identified ({} with linked SAST findings):\n",
+        code_context.len(),
+        with_vulns
+    );
+
+    for hint in code_context.iter().take(20) {
+        section.push_str(&format!(
+            "- {} ({})\n",
+            hint.endpoint_pattern, hint.file_path
+        ));
+        for vuln in &hint.known_vulnerabilities {
+            section.push_str(&format!("  SAST: {vuln}\n"));
+        }
+    }
+    section
+}
+
+impl PentestOrchestrator {
+    pub(crate) async fn build_system_prompt(
+        &self,
+        session: &PentestSession,
+        target: &DastTarget,
+        sast_findings: &[Finding],
+        sbom_entries: &[SbomEntry],
+        code_context: &[CodeContextHint],
+    ) -> String {
+        let tool_names = self.tool_registry.list_names().join(", ");
+        let guidance = strategy_guidance(&session.strategy);
+        let sast_section = build_sast_section(sast_findings);
+        let sbom_section = build_sbom_section(sbom_entries);
+        let code_section = build_code_section(code_context);
+        let config_sections = session
+            .config
+            .as_ref()
+            .map(build_config_sections)
+            .unwrap_or_default();
+
+        format!(
+            r#"You are an expert penetration tester conducting an authorized security assessment.
+
+## Target
+- **Name**: {target_name}
+- **URL**: {base_url}
+- **Type**: {target_type}
+- **Rate Limit**: {rate_limit} req/s
+- **Destructive Tests Allowed**: {allow_destructive}
+- **Linked Repository**: {repo_linked}
+
+## Strategy
+{strategy_guidance}
+
+## SAST Findings (Static Analysis)
+{sast_section}
+
+## Vulnerable Dependencies (SBOM)
+{sbom_section}
+
+## Code Entry Points (Knowledge Graph)
+{code_section}
+{config_sections}
+## Available Tools
+{tool_names}
+
+## Instructions
+1. Start by running reconnaissance (recon tool) to fingerprint the target and discover technologies.
+2. Run the OpenAPI parser to discover API endpoints from specs.
+3. Check infrastructure: DNS, DMARC, TLS, security headers, cookies, CSP, CORS.
+4. If the target requires authentication (auto-register mode), use the browser tool to:
+   a. Navigate to the target — it will redirect to the login page.
+   b. Click the "Register" link to reach the registration form.
+   c. Fill all form fields (username, email with plus-addressing, password, name) one by one.
+   d. Click submit. If a Terms & Conditions page appears, accept it.
+   e. After registration, use the browser to navigate through the application pages.
+   f. **Take a screenshot after each major page** for evidence in the report.
+5. Use the browser tool to explore the authenticated application — navigate to each section,
+   use get_content to understand the page structure, and take screenshots.
+6. Based on SAST findings, prioritize testing endpoints where vulnerabilities were found in code.
+7. For each vulnerability type found in SAST, use the corresponding DAST tool to verify exploitability.
+8. If vulnerable dependencies are listed, try to trigger known CVE conditions against the running application.
+9. Test rate limiting on critical endpoints (login, API).
+10. Check for console.log leakage in frontend JavaScript.
+11. Analyze tool results and chain findings — if one vulnerability enables others, explore the chain.
+12. When testing is complete, provide a structured summary with severity and remediation.
+13. Always explain your reasoning before invoking each tool.
+14. When done, say "Testing complete" followed by a final summary.
+
+## Browser Tool Usage
+- The browser tab **persists** between calls — cookies and login state are preserved.
+- After navigate, the response includes `elements` (links, inputs, buttons on the page).
+- Use `get_content` to see forms, links, buttons, headings, and page text.
+- Use `click` with CSS selectors to interact (e.g., `a:text('Register')`, `input[type='submit']`).
+- Use `fill` with selector + value to fill form fields (e.g., `input[name='email']`).
+- **Take screenshots** (`action: screenshot`) after important actions for evidence.
+- For SPA apps: a 200 HTTP status does NOT mean the page is accessible — check the actual
+  page content with the browser tool to verify if it shows real data or a login redirect.
+
+## Important
+- This is an authorized penetration test. All testing is permitted within the target scope.
+- Respect the rate limit of {rate_limit} requests per second.
+- Only use destructive tests if explicitly allowed ({allow_destructive}).
+- Use SAST findings to guide your testing — they tell you WHERE in the code vulnerabilities exist.
+- Use SBOM data to understand what technologies and versions the target runs.
+"#,
+            target_name = target.name,
+            base_url = target.base_url,
+            target_type = target.target_type,
+            rate_limit = target.rate_limit,
+            allow_destructive = target.allow_destructive,
+            repo_linked = target.repo_id.as_deref().unwrap_or("None"),
+            strategy_guidance = guidance,
+        )
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::models::finding::Severity;
+    use compliance_core::models::sbom::VulnRef;
+    use compliance_core::models::scan::ScanType;
+
+    fn make_finding(
+        severity: Severity,
+        title: &str,
+        file_path: Option<&str>,
+        line: Option<u32>,
+        status: FindingStatus,
+        cwe: Option<&str>,
+    ) -> Finding {
+        let mut f = Finding::new(
+            "repo-1".into(),
+            format!("fp-{title}"),
+            "semgrep".into(),
+            ScanType::Sast,
+            title.into(),
+            "desc".into(),
+            severity,
+        );
+        f.file_path = file_path.map(|s| s.to_string());
+        f.line_number = line;
+        f.status = status;
+        f.cwe = cwe.map(|s| s.to_string());
+        f
+    }
+
+    fn make_sbom_entry(name: &str, version: &str, cves: &[&str]) -> SbomEntry {
+        let mut entry = SbomEntry::new("repo-1".into(), name.into(), version.into(), "npm".into());
+        entry.known_vulnerabilities = cves
+            .iter()
+            .map(|id| VulnRef {
+                id: id.to_string(),
+                source: "nvd".into(),
+                severity: None,
+                url: None,
+            })
+            .collect();
+        entry
+    }
+
+    fn make_code_hint(endpoint: &str, file: &str, vulns: Vec<String>) -> CodeContextHint {
+        CodeContextHint {
+            endpoint_pattern: endpoint.into(),
+            handler_function: "handler".into(),
+            file_path: file.into(),
+            code_snippet: String::new(),
+            known_vulnerabilities: vulns,
+        }
+    }
+
+    // ── strategy_guidance ────────────────────────────────────────────
+
+    #[test]
+    fn strategy_guidance_quick() {
+        let g = strategy_guidance(&PentestStrategy::Quick);
+        assert!(g.contains("most common"));
+        assert!(g.contains("quick recon"));
+    }
+
+    #[test]
+    fn strategy_guidance_comprehensive() {
+        let g = strategy_guidance(&PentestStrategy::Comprehensive);
+        assert!(g.contains("thorough assessment"));
+    }
+
+    #[test]
+    fn strategy_guidance_targeted() {
+        let g = strategy_guidance(&PentestStrategy::Targeted);
+        assert!(g.contains("SAST findings"));
+        assert!(g.contains("known CVEs"));
+    }
+
+    #[test]
+    fn strategy_guidance_aggressive() {
+        let g = strategy_guidance(&PentestStrategy::Aggressive);
+        assert!(g.contains("aggressively"));
+        assert!(g.contains("full exploitation"));
+    }
+
+    #[test]
+    fn strategy_guidance_stealth() {
+        let g = strategy_guidance(&PentestStrategy::Stealth);
+        assert!(g.contains("Minimize noise"));
+        assert!(g.contains("passive analysis"));
+    }
+
+    // ── build_sast_section ───────────────────────────────────────────
+
+    #[test]
+    fn sast_section_empty() {
+        let section = build_sast_section(&[]);
+        assert_eq!(section, "No SAST findings available for this target.");
+    }
+
+    #[test]
+    fn sast_section_single_critical() {
+        let findings = vec![make_finding(
+            Severity::Critical,
+            "SQL Injection",
+            Some("src/db.rs"),
+            Some(42),
+            FindingStatus::Open,
+            Some("CWE-89"),
+        )];
+        let section = build_sast_section(&findings);
+        assert!(section.contains("1 open findings (1 critical, 0 high)"));
+        assert!(section.contains("[critical] SQL Injection in src/db.rs:42"));
+        assert!(section.contains("CWE: CWE-89"));
+    }
+
+    #[test]
+    fn sast_section_triaged_finding_shows_marker() {
+        let findings = vec![make_finding(
+            Severity::High,
+            "XSS",
+            None,
+            None,
+            FindingStatus::Triaged,
+            None,
+        )];
+        let section = build_sast_section(&findings);
+        assert!(section.contains("[TRIAGED]"));
+    }
+
+    #[test]
+    fn sast_section_no_file_path_omits_location() {
+        let findings = vec![make_finding(
+            Severity::Medium,
+            "Open Redirect",
+            None,
+            None,
+            FindingStatus::Open,
+            None,
+        )];
+        let section = build_sast_section(&findings);
+        assert!(section.contains("- [medium] Open Redirect\n"));
+        assert!(!section.contains(" in "));
+    }
+
+    #[test]
+    fn sast_section_counts_critical_and_high() {
+        let findings = vec![
+            make_finding(
+                Severity::Critical,
+                "F1",
+                None,
+                None,
+                FindingStatus::Open,
+                None,
+            ),
+            make_finding(
+                Severity::Critical,
+                "F2",
+                None,
+                None,
+                FindingStatus::Open,
+                None,
+            ),
+            make_finding(Severity::High, "F3", None, None, FindingStatus::Open, None),
+            make_finding(
+                Severity::Medium,
+                "F4",
+                None,
+                None,
+                FindingStatus::Open,
+                None,
+            ),
+        ];
+        let section = build_sast_section(&findings);
+        assert!(section.contains("4 open findings (2 critical, 1 high)"));
+    }
+
+    #[test]
+    fn sast_section_truncates_at_20() {
+        let findings: Vec<Finding> = (0..25)
+            .map(|i| {
+                make_finding(
+                    Severity::Low,
+                    &format!("Finding {i}"),
+                    None,
+                    None,
+                    FindingStatus::Open,
+                    None,
+                )
+            })
+            .collect();
+        let section = build_sast_section(&findings);
+        assert!(section.contains("... and 5 more findings"));
+        // Should contain Finding 19 (the 20th) but not Finding 20 (the 21st)
+        assert!(section.contains("Finding 19"));
+        assert!(!section.contains("Finding 20"));
+    }
+
+    // ── build_sbom_section ───────────────────────────────────────────
+
+    #[test]
+    fn sbom_section_empty() {
+        let section = build_sbom_section(&[]);
+        assert_eq!(section, "No vulnerable dependencies identified.");
+    }
+
+    #[test]
+    fn sbom_section_single_entry() {
+        let entries = vec![make_sbom_entry("lodash", "4.17.20", &["CVE-2021-23337"])];
+        let section = build_sbom_section(&entries);
+        assert!(section.contains("1 dependencies with known vulnerabilities"));
+        assert!(section.contains("- lodash 4.17.20 (npm): CVE-2021-23337"));
+    }
+
+    #[test]
+    fn sbom_section_multiple_cves() {
+        let entries = vec![make_sbom_entry(
+            "openssl",
+            "1.1.1",
+            &["CVE-2022-0001", "CVE-2022-0002"],
+        )];
+        let section = build_sbom_section(&entries);
+        assert!(section.contains("CVE-2022-0001, CVE-2022-0002"));
+    }
+
+    #[test]
+    fn sbom_section_truncates_at_15() {
+        let entries: Vec<SbomEntry> = (0..18)
+            .map(|i| make_sbom_entry(&format!("pkg-{i}"), "1.0.0", &["CVE-2024-0001"]))
+            .collect();
+        let section = build_sbom_section(&entries);
+        assert!(section.contains("... and 3 more vulnerable dependencies"));
+        assert!(section.contains("pkg-14"));
+        assert!(!section.contains("pkg-15"));
+    }
+
+    // ── build_code_section ───────────────────────────────────────────
+
+    #[test]
+    fn code_section_empty() {
+        let section = build_code_section(&[]);
+        assert_eq!(
+            section,
+            "No code knowledge graph available for this target."
+        );
+    }
+
+    #[test]
+    fn code_section_single_entry_no_vulns() {
+        let hints = vec![make_code_hint("GET /api/users", "src/routes.rs", vec![])];
+        let section = build_code_section(&hints);
+        assert!(section.contains("1 entry points identified (0 with linked SAST findings)"));
+        assert!(section.contains("- GET /api/users (src/routes.rs)"));
+    }
+
+    #[test]
+    fn code_section_with_linked_vulns() {
+        let hints = vec![make_code_hint(
+            "POST /login",
+            "src/auth.rs",
+            vec!["[critical] semgrep: SQL Injection (line 15)".into()],
+        )];
+        let section = build_code_section(&hints);
+        assert!(section.contains("1 entry points identified (1 with linked SAST findings)"));
+        assert!(section.contains("SAST: [critical] semgrep: SQL Injection (line 15)"));
+    }
+
+    #[test]
+    fn code_section_counts_entries_with_vulns() {
+        let hints = vec![
+            make_code_hint("GET /a", "a.rs", vec!["vuln1".into()]),
+            make_code_hint("GET /b", "b.rs", vec![]),
+            make_code_hint("GET /c", "c.rs", vec!["vuln2".into(), "vuln3".into()]),
+        ];
+        let section = build_code_section(&hints);
+        assert!(section.contains("3 entry points identified (2 with linked SAST findings)"));
+    }
+
+    #[test]
+    fn code_section_truncates_at_20() {
+        let hints: Vec<CodeContextHint> = (0..25)
+            .map(|i| make_code_hint(&format!("GET /ep{i}"), &format!("f{i}.rs"), vec![]))
+            .collect();
+        let section = build_code_section(&hints);
+        assert!(section.contains("GET /ep19"));
+        assert!(!section.contains("GET /ep20"));
+    }
+}

compliance-agent/src/pentest/report/archive.rs

@@ -0,0 +1,43 @@
+use std::io::{Cursor, Write};
+
+use zip::write::SimpleFileOptions;
+use zip::AesMode;
+
+use super::ReportContext;
+
+pub(super) fn build_zip(
+    ctx: &ReportContext,
+    password: &str,
+    html: &str,
+    pdf: &[u8],
+) -> Result<Vec<u8>, zip::result::ZipError> {
+    let buf = Cursor::new(Vec::new());
+    let mut zip = zip::ZipWriter::new(buf);
+
+    let options = SimpleFileOptions::default()
+        .compression_method(zip::CompressionMethod::Deflated)
+        .with_aes_encryption(AesMode::Aes256, password);
+
+    // report.pdf (primary)
+    zip.start_file("report.pdf", options)?;
+    zip.write_all(pdf)?;
+
+    // report.html (fallback)
+    zip.start_file("report.html", options)?;
+    zip.write_all(html.as_bytes())?;
+
+    // findings.json
+    let findings_json =
+        serde_json::to_string_pretty(&ctx.findings).unwrap_or_else(|_| "[]".to_string());
+    zip.start_file("findings.json", options)?;
+    zip.write_all(findings_json.as_bytes())?;
+
+    // attack-chain.json
+    let chain_json =
+        serde_json::to_string_pretty(&ctx.attack_chain).unwrap_or_else(|_| "[]".to_string());
+    zip.start_file("attack-chain.json", options)?;
+    zip.write_all(chain_json.as_bytes())?;
+
+    let cursor = zip.finish()?;
+    Ok(cursor.into_inner())
+}

compliance-agent/src/pentest/report/html/appendix.rs

@@ -0,0 +1,40 @@
+use super::html_escape;
+
+pub(super) fn appendix(session_id: &str) -> String {
+    format!(
+        r##"<!-- ═══════════════ 5. APPENDIX ═══════════════ -->
+<div class="page-break"></div>
+<h2><span class="section-num">5.</span> Appendix</h2>
+
+<h3>Severity Definitions</h3>
+<table class="info">
+    <tr><td style="color: var(--sev-critical); font-weight: 700;">Critical</td><td>Vulnerabilities that can be exploited remotely without authentication to execute arbitrary code, exfiltrate sensitive data, or fully compromise the system.</td></tr>
+    <tr><td style="color: var(--sev-high); font-weight: 700;">High</td><td>Vulnerabilities that allow significant unauthorized access or data exposure, typically requiring minimal user interaction or privileges.</td></tr>
+    <tr><td style="color: var(--sev-medium); font-weight: 700;">Medium</td><td>Vulnerabilities that may lead to limited data exposure or require specific conditions to exploit, but still represent meaningful risk.</td></tr>
+    <tr><td style="color: var(--sev-low); font-weight: 700;">Low</td><td>Minor issues with limited direct impact. May contribute to broader attack chains or indicate defense-in-depth weaknesses.</td></tr>
+    <tr><td style="color: var(--sev-info); font-weight: 700;">Info</td><td>Observations and best-practice recommendations that do not represent direct security vulnerabilities.</td></tr>
+</table>
+
+<h3>Disclaimer</h3>
+<p style="font-size: 9pt; color: var(--text-secondary);">
+    This report was generated by an automated AI-powered penetration testing engine. While the system
+    employs advanced techniques to identify vulnerabilities, no automated assessment can guarantee
+    complete coverage. The results should be reviewed by qualified security professionals and validated
+    in the context of the target application's threat model. Findings are point-in-time observations
+    and may change as the application evolves.
+</p>
+
+<!-- ═══════════════ FOOTER ═══════════════ -->
+<div class="report-footer">
+    <div class="footer-company">Compliance Scanner</div>
+    <div>AI-Powered Security Assessment Platform</div>
+    <div style="margin-top: 6px;">This document is confidential and intended solely for the named recipient.</div>
+    <div>Report ID: {session_id}</div>
+</div>
+
+</div><!-- .report-body -->
+</body>
+</html>"##,
+        session_id = html_escape(session_id),
+    )
+}

compliance-agent/src/pentest/report/html/attack_chain.rs

@@ -0,0 +1,193 @@
+use super::html_escape;
+use compliance_core::models::pentest::AttackChainNode;
+
+pub(super) fn attack_chain(chain: &[AttackChainNode]) -> String {
+    let chain_section = if chain.is_empty() {
+        r#"<p style="color: var(--text-muted);">No attack chain steps recorded.</p>"#.to_string()
+    } else {
+        build_chain_html(chain)
+    };
+
+    format!(
+        r##"<!-- ═══════════════ 4. ATTACK CHAIN ═══════════════ -->
+<div class="page-break"></div>
+<h2><span class="section-num">4.</span> Attack Chain Timeline</h2>
+
+<p>
+    The following sequence shows each tool invocation made by the AI orchestrator during the assessment,
+    grouped by phase. Each step includes the tool's name, execution status, and the AI's reasoning
+    for choosing that action.
+</p>
+
+<div style="margin-top: 16px;">
+    {chain_section}
+</div>"##
+    )
+}
+
+fn build_chain_html(chain: &[AttackChainNode]) -> String {
+    let mut chain_html = String::new();
+
+    // Compute phases via BFS from root nodes
+    let mut phase_map: std::collections::HashMap<String, usize> = std::collections::HashMap::new();
+    let mut queue: std::collections::VecDeque<String> = std::collections::VecDeque::new();
+
+    for node in chain {
+        if node.parent_node_ids.is_empty() {
+            let nid = node.node_id.clone();
+            if !nid.is_empty() {
+                phase_map.insert(nid.clone(), 0);
+                queue.push_back(nid);
+            }
+        }
+    }
+
+    while let Some(nid) = queue.pop_front() {
+        let parent_phase = phase_map.get(&nid).copied().unwrap_or(0);
+        for node in chain {
+            if node.parent_node_ids.contains(&nid) {
+                let child_id = node.node_id.clone();
+                if !child_id.is_empty() && !phase_map.contains_key(&child_id) {
+                    phase_map.insert(child_id.clone(), parent_phase + 1);
+                    queue.push_back(child_id);
+                }
+            }
+        }
+    }
+
+    // Assign phase 0 to any unassigned nodes
+    for node in chain {
+        let nid = node.node_id.clone();
+        if !nid.is_empty() && !phase_map.contains_key(&nid) {
+            phase_map.insert(nid, 0);
+        }
+    }
+
+    // Group nodes by phase
+    let max_phase = phase_map.values().copied().max().unwrap_or(0);
+    let phase_labels = [
+        "Reconnaissance",
+        "Enumeration",
+        "Exploitation",
+        "Validation",
+        "Post-Exploitation",
+    ];
+
+    for phase_idx in 0..=max_phase {
+        let phase_nodes: Vec<&AttackChainNode> = chain
+            .iter()
+            .filter(|n| {
+                let nid = n.node_id.clone();
+                phase_map.get(&nid).copied().unwrap_or(0) == phase_idx
+            })
+            .collect();
+
+        if phase_nodes.is_empty() {
+            continue;
+        }
+
+        let label = if phase_idx < phase_labels.len() {
+            phase_labels[phase_idx]
+        } else {
+            "Additional Testing"
+        };
+
+        chain_html.push_str(&format!(
+            r#"<div class="phase-block">
+                    <div class="phase-header">
+                        <span class="phase-num">Phase {}</span>
+                        <span class="phase-label">{}</span>
+                        <span class="phase-count">{} step{}</span>
+                    </div>
+                    <div class="phase-steps">"#,
+            phase_idx + 1,
+            label,
+            phase_nodes.len(),
+            if phase_nodes.len() == 1 { "" } else { "s" },
+        ));
+
+        for (i, node) in phase_nodes.iter().enumerate() {
+            let status_label = format!("{:?}", node.status);
+            let status_class = match status_label.to_lowercase().as_str() {
+                "completed" => "step-completed",
+                "failed" => "step-failed",
+                _ => "step-running",
+            };
+            let findings_badge = if !node.findings_produced.is_empty() {
+                format!(
+                    r#"<span class="step-findings">{} finding{}</span>"#,
+                    node.findings_produced.len(),
+                    if node.findings_produced.len() == 1 {
+                        ""
+                    } else {
+                        "s"
+                    },
+                )
+            } else {
+                String::new()
+            };
+            let risk_badge = node
+                .risk_score
+                .map(|r| {
+                    let risk_class = if r >= 70 {
+                        "risk-high"
+                    } else if r >= 40 {
+                        "risk-med"
+                    } else {
+                        "risk-low"
+                    };
+                    format!(r#"<span class="step-risk {risk_class}">Risk: {r}</span>"#)
+                })
+                .unwrap_or_default();
+
+            let reasoning_html = if node.llm_reasoning.is_empty() {
+                String::new()
+            } else {
+                format!(
+                    r#"<div class="step-reasoning">{}</div>"#,
+                    html_escape(&node.llm_reasoning)
+                )
+            };
+
+            // Render inline screenshot if this is a browser screenshot action
+            let screenshot_html = if node.tool_name == "browser" {
+                node.tool_output
+                    .as_ref()
+                    .and_then(|out| out.get("screenshot_base64"))
+                    .and_then(|v| v.as_str())
+                    .filter(|s| !s.is_empty())
+                    .map(|b64| {
+                        format!(
+                            r#"<div class="step-screenshot"><img src="data:image/png;base64,{b64}" alt="Browser screenshot" style="max-width:100%;border:1px solid #e2e8f0;border-radius:6px;margin-top:8px;"/></div>"#
+                        )
+                    })
+                    .unwrap_or_default()
+            } else {
+                String::new()
+            };
+
+            chain_html.push_str(&format!(
+                r#"<div class="step-row">
+                        <div class="step-num">{num}</div>
+                        <div class="step-connector"></div>
+                        <div class="step-content">
+                            <div class="step-header">
+                                <span class="step-tool">{tool_name}</span>
+                                <span class="step-status {status_class}">{status_label}</span>
+                                {findings_badge}
+                                {risk_badge}
+                            </div>
+                            {reasoning_html}
+                            {screenshot_html}
+                        </div>
+                    </div>"#,
+                num = i + 1,
+                tool_name = html_escape(&node.tool_name),
+            ));
+        }
+
+        chain_html.push_str("</div></div>");
+    }
+
+    chain_html
+}

compliance-agent/src/pentest/report/html/cover.rs

@@ -0,0 +1,69 @@
+use super::html_escape;
+
+pub(super) fn cover(
+    target_name: &str,
+    session_id: &str,
+    date_short: &str,
+    target_url: &str,
+    requester_name: &str,
+    requester_email: &str,
+    app_screenshot_b64: Option<&str>,
+) -> String {
+    let screenshot_html = app_screenshot_b64
+        .filter(|s| !s.is_empty())
+        .map(|b64| {
+            format!(
+                r#"<div style="margin: 20px auto; max-width: 560px; border: 1px solid #cbd5e1; border-radius: 8px; overflow: hidden; box-shadow: 0 4px 12px rgba(0,0,0,0.08);">
+    <img src="data:image/png;base64,{b64}" alt="Application screenshot" style="width:100%;display:block;"/>
+</div>"#
+            )
+        })
+        .unwrap_or_default();
+    format!(
+        r##"<!-- ═══════════════ COVER PAGE ═══════════════ -->
+<div class="cover">
+    <svg class="cover-shield" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 96 96">
+        <defs>
+            <linearGradient id="sg" x1="0%" y1="0%" x2="100%" y2="100%">
+                <stop offset="0%" stop-color="#0d2137"/>
+                <stop offset="100%" stop-color="#1a56db"/>
+            </linearGradient>
+        </defs>
+        <path d="M48 6 L22 22 L22 48 C22 66 34 80 48 86 C62 80 74 66 74 48 L74 22 Z"
+              fill="none" stroke="url(#sg)" stroke-width="3.5" stroke-linejoin="round"/>
+        <path d="M48 12 L26 26 L26 47 C26 63 36 76 48 82 C60 76 70 63 70 47 L70 26 Z"
+              fill="url(#sg)" opacity="0.07"/>
+        <circle cx="44" cy="44" r="11" fill="none" stroke="#0d2137" stroke-width="2.5"/>
+        <line x1="52" y1="52" x2="62" y2="62" stroke="#0d2137" stroke-width="2.5" stroke-linecap="round"/>
+        <path d="M39 44 L42.5 47.5 L49 41" fill="none" stroke="#166534" stroke-width="2.5"
+              stroke-linecap="round" stroke-linejoin="round"/>
+    </svg>
+
+    <div class="cover-tag">CONFIDENTIAL</div>
+
+    <div class="cover-title">Penetration Test Report</div>
+    <div class="cover-subtitle">{target_name}</div>
+
+    <div class="cover-divider"></div>
+
+    <div class="cover-meta">
+        <strong>Report ID:</strong> {session_id}<br>
+        <strong>Date:</strong> {date_short}<br>
+        <strong>Target:</strong> {target_url}<br>
+        <strong>Prepared for:</strong> {requester_name} ({requester_email})
+    </div>
+
+    {screenshot_html}
+
+    <div class="cover-footer">
+        Compliance Scanner &mdash; AI-Powered Security Assessment Platform
+    </div>
+</div>"##,
+        target_name = html_escape(target_name),
+        session_id = html_escape(session_id),
+        date_short = date_short,
+        target_url = html_escape(target_url),
+        requester_name = html_escape(requester_name),
+        requester_email = html_escape(requester_email),
+    )
+}

compliance-agent/src/pentest/report/html/executive_summary.rs

@@ -0,0 +1,238 @@
+use super::html_escape;
+use compliance_core::models::dast::DastFinding;
+
+pub(super) fn executive_summary(
+    findings: &[DastFinding],
+    target_name: &str,
+    target_url: &str,
+    tool_count: usize,
+    tool_invocations: u32,
+    success_rate: f64,
+) -> String {
+    let critical = findings
+        .iter()
+        .filter(|f| f.severity.to_string() == "critical")
+        .count();
+    let high = findings
+        .iter()
+        .filter(|f| f.severity.to_string() == "high")
+        .count();
+    let medium = findings
+        .iter()
+        .filter(|f| f.severity.to_string() == "medium")
+        .count();
+    let low = findings
+        .iter()
+        .filter(|f| f.severity.to_string() == "low")
+        .count();
+    let info = findings
+        .iter()
+        .filter(|f| f.severity.to_string() == "info")
+        .count();
+    let exploitable = findings.iter().filter(|f| f.exploitable).count();
+    let total = findings.len();
+
+    let overall_risk = if critical > 0 {
+        "CRITICAL"
+    } else if high > 0 {
+        "HIGH"
+    } else if medium > 0 {
+        "MEDIUM"
+    } else if low > 0 {
+        "LOW"
+    } else {
+        "INFORMATIONAL"
+    };
+
+    let risk_color = match overall_risk {
+        "CRITICAL" => "#991b1b",
+        "HIGH" => "#c2410c",
+        "MEDIUM" => "#a16207",
+        "LOW" => "#1d4ed8",
+        _ => "#4b5563",
+    };
+
+    let risk_score: usize =
+        std::cmp::min(100, critical * 25 + high * 15 + medium * 8 + low * 3 + info);
+
+    let severity_bar = build_severity_bar(critical, high, medium, low, info, total);
+
+    // Table of contents finding sub-entries
+    let severity_order = ["critical", "high", "medium", "low", "info"];
+    let toc_findings_sub = if !findings.is_empty() {
+        let mut sub = String::new();
+        let mut fnum = 0usize;
+        for &sev_key in severity_order.iter() {
+            let count = findings
+                .iter()
+                .filter(|f| f.severity.to_string() == sev_key)
+                .count();
+            if count == 0 {
+                continue;
+            }
+            for f in findings
+                .iter()
+                .filter(|f| f.severity.to_string() == sev_key)
+            {
+                fnum += 1;
+                sub.push_str(&format!(
+                    r#"<div class="toc-sub">F-{:03} — {}</div>"#,
+                    fnum,
+                    html_escape(&f.title),
+                ));
+            }
+        }
+        sub
+    } else {
+        String::new()
+    };
+
+    let critical_high_str = format!("{} / {}", critical, high);
+    let escaped_target_name = html_escape(target_name);
+    let escaped_target_url = html_escape(target_url);
+
+    format!(
+        r##"<!-- ═══════════════ TABLE OF CONTENTS ═══════════════ -->
+<div class="report-body">
+
+<div class="toc">
+    <h2>Table of Contents</h2>
+    <div class="toc-entry"><span class="toc-num">1</span><span class="toc-label">Executive Summary</span></div>
+    <div class="toc-entry"><span class="toc-num">2</span><span class="toc-label">Scope &amp; Methodology</span></div>
+    <div class="toc-entry"><span class="toc-num">3</span><span class="toc-label">Findings ({total_findings})</span></div>
+    {toc_findings_sub}
+    <div class="toc-entry"><span class="toc-num">4</span><span class="toc-label">Attack Chain Timeline</span></div>
+    <div class="toc-entry"><span class="toc-num">5</span><span class="toc-label">Appendix</span></div>
+</div>
+
+<!-- ═══════════════ 1. EXECUTIVE SUMMARY ═══════════════ -->
+<h2><span class="section-num">1.</span> Executive Summary</h2>
+
+<div class="risk-gauge">
+    <div class="risk-gauge-meter">
+        <div class="risk-gauge-track">
+            <div class="risk-gauge-fill" style="width: {risk_score}%; background: {risk_color};"></div>
+        </div>
+        <div class="risk-gauge-score" style="color: {risk_color};">{risk_score} / 100</div>
+    </div>
+    <div class="risk-gauge-text">
+        <div class="risk-gauge-label" style="color: {risk_color};">Overall Risk: {overall_risk}</div>
+        <div class="risk-gauge-desc">
+            Based on {total_findings} finding{findings_plural} identified across the target application.
+        </div>
+    </div>
+</div>
+
+<div class="exec-grid">
+    <div class="kpi-card">
+        <div class="kpi-value">{total_findings}</div>
+        <div class="kpi-label">Total Findings</div>
+    </div>
+    <div class="kpi-card">
+        <div class="kpi-value" style="color: var(--sev-critical);">{critical_high}</div>
+        <div class="kpi-label">Critical / High</div>
+    </div>
+    <div class="kpi-card">
+        <div class="kpi-value" style="color: var(--sev-critical);">{exploitable_count}</div>
+        <div class="kpi-label">Exploitable</div>
+    </div>
+    <div class="kpi-card">
+        <div class="kpi-value">{tool_count}</div>
+        <div class="kpi-label">Tools Used</div>
+    </div>
+</div>
+
+<h3>Severity Distribution</h3>
+{severity_bar}
+
+<p>
+    This report presents the results of an automated penetration test conducted against
+    <strong>{target_name}</strong> (<code>{target_url}</code>) using the Compliance Scanner
+    AI-powered testing engine. A total of <strong>{total_findings} vulnerabilities</strong> were
+    identified, of which <strong>{exploitable_count}</strong> were confirmed exploitable with
+    working proof-of-concept payloads. The assessment employed <strong>{tool_count} security tools</strong>
+    across <strong>{tool_invocations} invocations</strong> ({success_rate:.0}% success rate).
+</p>"##,
+        total_findings = total,
+        findings_plural = if total == 1 { "" } else { "s" },
+        critical_high = critical_high_str,
+        exploitable_count = exploitable,
+        target_name = escaped_target_name,
+        target_url = escaped_target_url,
+    )
+}
+
+fn build_severity_bar(
+    critical: usize,
+    high: usize,
+    medium: usize,
+    low: usize,
+    info: usize,
+    total: usize,
+) -> String {
+    if total == 0 {
+        return String::new();
+    }
+
+    let crit_pct = (critical as f64 / total as f64 * 100.0) as usize;
+    let high_pct = (high as f64 / total as f64 * 100.0) as usize;
+    let med_pct = (medium as f64 / total as f64 * 100.0) as usize;
+    let low_pct = (low as f64 / total as f64 * 100.0) as usize;
+    let info_pct = 100_usize.saturating_sub(crit_pct + high_pct + med_pct + low_pct);
+
+    let mut bar = String::from(r#"<div class="sev-bar">"#);
+    if critical > 0 {
+        bar.push_str(&format!(
+            r#"<div class="sev-bar-seg sev-bar-critical" style="width:{}%"><span>{}</span></div>"#,
+            std::cmp::max(crit_pct, 4),
+            critical
+        ));
+    }
+    if high > 0 {
+        bar.push_str(&format!(
+            r#"<div class="sev-bar-seg sev-bar-high" style="width:{}%"><span>{}</span></div>"#,
+            std::cmp::max(high_pct, 4),
+            high
+        ));
+    }
+    if medium > 0 {
+        bar.push_str(&format!(
+            r#"<div class="sev-bar-seg sev-bar-medium" style="width:{}%"><span>{}</span></div>"#,
+            std::cmp::max(med_pct, 4),
+            medium
+        ));
+    }
+    if low > 0 {
+        bar.push_str(&format!(
+            r#"<div class="sev-bar-seg sev-bar-low" style="width:{}%"><span>{}</span></div>"#,
+            std::cmp::max(low_pct, 4),
+            low
+        ));
+    }
+    if info > 0 {
+        bar.push_str(&format!(
+            r#"<div class="sev-bar-seg sev-bar-info" style="width:{}%"><span>{}</span></div>"#,
+            std::cmp::max(info_pct, 4),
+            info
+        ));
+    }
+    bar.push_str("</div>");
+    bar.push_str(r#"<div class="sev-bar-legend">"#);
+    if critical > 0 {
+        bar.push_str(r#"<span><i class="sev-dot" style="background:#991b1b"></i> Critical</span>"#);
+    }
+    if high > 0 {
+        bar.push_str(r#"<span><i class="sev-dot" style="background:#c2410c"></i> High</span>"#);
+    }
+    if medium > 0 {
+        bar.push_str(r#"<span><i class="sev-dot" style="background:#a16207"></i> Medium</span>"#);
+    }
+    if low > 0 {
+        bar.push_str(r#"<span><i class="sev-dot" style="background:#1d4ed8"></i> Low</span>"#);
+    }
+    if info > 0 {
+        bar.push_str(r#"<span><i class="sev-dot" style="background:#4b5563"></i> Info</span>"#);
+    }
+    bar.push_str("</div>");
+    bar
+}

compliance-agent/src/pentest/report/html/findings.rs

@@ -0,0 +1,522 @@
+use super::html_escape;
+use compliance_core::models::dast::DastFinding;
+use compliance_core::models::finding::Finding;
+use compliance_core::models::pentest::CodeContextHint;
+use compliance_core::models::sbom::SbomEntry;
+
+/// Render the findings section with code-level correlation.
+///
+/// For each DAST finding, if a linked SAST finding exists (via `linked_sast_finding_id`)
+/// or if we can match the endpoint to a code entry point, we render a "Code-Level
+/// Remediation" block showing the exact file, line, code snippet, and suggested fix.
+pub(super) fn findings(
+    findings_list: &[DastFinding],
+    sast_findings: &[Finding],
+    code_context: &[CodeContextHint],
+    sbom_entries: &[SbomEntry],
+) -> String {
+    if findings_list.is_empty() {
+        return r#"<!-- ═══════════════ 3. FINDINGS ═══════════════ -->
+<div class="page-break"></div>
+<h2><span class="section-num">3.</span> Findings</h2>
+
+<p style="color: var(--text-muted);">No vulnerabilities were identified during this assessment.</p>"#.to_string();
+    }
+
+    let severity_order = ["critical", "high", "medium", "low", "info"];
+    let severity_labels = ["Critical", "High", "Medium", "Low", "Informational"];
+    let severity_colors = ["#991b1b", "#c2410c", "#a16207", "#1d4ed8", "#4b5563"];
+
+    // Build SAST lookup by ObjectId hex string
+    let sast_by_id: std::collections::HashMap<String, &Finding> = sast_findings
+        .iter()
+        .filter_map(|f| {
+            let id = f.id.as_ref()?.to_hex();
+            Some((id, f))
+        })
+        .collect();
+
+    let mut findings_html = String::new();
+    let mut finding_num = 0usize;
+
+    for (si, &sev_key) in severity_order.iter().enumerate() {
+        let sev_findings: Vec<&DastFinding> = findings_list
+            .iter()
+            .filter(|f| f.severity.to_string() == sev_key)
+            .collect();
+        if sev_findings.is_empty() {
+            continue;
+        }
+
+        findings_html.push_str(&format!(
+            r#"<h4 class="sev-group-title" style="border-color: {color}">{label} ({count})</h4>"#,
+            color = severity_colors[si],
+            label = severity_labels[si],
+            count = sev_findings.len(),
+        ));
+
+        for f in sev_findings {
+            finding_num += 1;
+            let sev_color = severity_colors[si];
+            let exploitable_badge = if f.exploitable {
+                r#"<span class="badge badge-exploit">EXPLOITABLE</span>"#
+            } else {
+                ""
+            };
+            let cwe_cell = f
+                .cwe
+                .as_deref()
+                .map(|c| format!("<tr><td>CWE</td><td>{}</td></tr>", html_escape(c)))
+                .unwrap_or_default();
+            let param_row = f
+                .parameter
+                .as_deref()
+                .map(|p| {
+                    format!(
+                        "<tr><td>Parameter</td><td><code>{}</code></td></tr>",
+                        html_escape(p)
+                    )
+                })
+                .unwrap_or_default();
+            let remediation = f
+                .remediation
+                .as_deref()
+                .unwrap_or("Refer to industry best practices for this vulnerability class.");
+
+            let evidence_html = build_evidence_html(f);
+
+            // ── Code-level correlation ──────────────────────────────
+            let code_correlation =
+                build_code_correlation(f, &sast_by_id, code_context, sbom_entries);
+
+            findings_html.push_str(&format!(
+                r#"
+                <div class="finding" style="border-left-color: {sev_color}">
+                    <div class="finding-header">
+                        <span class="finding-id">F-{num:03}</span>
+                        <span class="finding-title">{title}</span>
+                        {exploitable_badge}
+                    </div>
+                    <table class="finding-meta">
+                        <tr><td>Type</td><td>{vuln_type}</td></tr>
+                        <tr><td>Endpoint</td><td><code>{method} {endpoint}</code></td></tr>
+                        {param_row}
+                        {cwe_cell}
+                    </table>
+                    <div class="finding-desc">{description}</div>
+                    {evidence_html}
+                    {code_correlation}
+                    <div class="remediation">
+                        <div class="remediation-label">Recommendation</div>
+                        {remediation}
+                    </div>
+                </div>
+                "#,
+                num = finding_num,
+                title = html_escape(&f.title),
+                vuln_type = f.vuln_type,
+                method = f.method,
+                endpoint = html_escape(&f.endpoint),
+                description = html_escape(&f.description),
+            ));
+        }
+    }
+
+    format!(
+        r##"<!-- ═══════════════ 3. FINDINGS ═══════════════ -->
+<div class="page-break"></div>
+<h2><span class="section-num">3.</span> Findings</h2>
+
+{findings_html}"##
+    )
+}
+
+/// Build the evidence table HTML for a finding.
+fn build_evidence_html(f: &DastFinding) -> String {
+    if f.evidence.is_empty() {
+        return String::new();
+    }
+
+    let mut eh = String::from(
+        r#"<div class="evidence-block"><div class="evidence-title">Evidence</div><table class="evidence-table"><thead><tr><th>Request</th><th>Status</th><th>Details</th></tr></thead><tbody>"#,
+    );
+    for ev in &f.evidence {
+        let payload_info = ev
+            .payload
+            .as_deref()
+            .map(|p| {
+                format!(
+                    "<br><span class=\"evidence-payload\">Payload: <code>{}</code></span>",
+                    html_escape(p)
+                )
+            })
+            .unwrap_or_default();
+        eh.push_str(&format!(
+            "<tr><td><code>{} {}</code></td><td>{}</td><td>{}{}</td></tr>",
+            html_escape(&ev.request_method),
+            html_escape(&ev.request_url),
+            ev.response_status,
+            ev.response_snippet
+                .as_deref()
+                .map(html_escape)
+                .unwrap_or_default(),
+            payload_info,
+        ));
+    }
+    eh.push_str("</tbody></table></div>");
+    eh
+}
+
+/// Build the code-level correlation block for a DAST finding.
+///
+/// Attempts correlation in priority order:
+/// 1. Direct link via `linked_sast_finding_id` → shows exact file, line, snippet, suggested fix
+/// 2. Endpoint match via code context → shows handler function, file, known SAST vulns
+/// 3. CWE/CVE match to SBOM → shows vulnerable dependency + version to upgrade
+fn build_code_correlation(
+    dast_finding: &DastFinding,
+    sast_by_id: &std::collections::HashMap<String, &Finding>,
+    code_context: &[CodeContextHint],
+    sbom_entries: &[SbomEntry],
+) -> String {
+    let mut sections: Vec<String> = Vec::new();
+
+    // 1. Direct SAST link
+    if let Some(ref sast_id) = dast_finding.linked_sast_finding_id {
+        if let Some(sast) = sast_by_id.get(sast_id) {
+            let mut s = String::new();
+            s.push_str(r#"<div class="code-correlation-item">"#);
+            s.push_str(r#"<div class="code-correlation-badge">SAST Correlation</div>"#);
+            s.push_str("<table class=\"code-meta\">");
+
+            if let Some(ref fp) = sast.file_path {
+                let line_info = sast
+                    .line_number
+                    .map(|l| format!(":{l}"))
+                    .unwrap_or_default();
+                s.push_str(&format!(
+                    "<tr><td>Location</td><td><code>{}{}</code></td></tr>",
+                    html_escape(fp),
+                    line_info,
+                ));
+            }
+            s.push_str(&format!(
+                "<tr><td>Scanner</td><td>{} &mdash; {}</td></tr>",
+                html_escape(&sast.scanner),
+                html_escape(&sast.title),
+            ));
+            if let Some(ref cwe) = sast.cwe {
+                s.push_str(&format!(
+                    "<tr><td>CWE</td><td>{}</td></tr>",
+                    html_escape(cwe)
+                ));
+            }
+            if let Some(ref rule) = sast.rule_id {
+                s.push_str(&format!(
+                    "<tr><td>Rule</td><td><code>{}</code></td></tr>",
+                    html_escape(rule)
+                ));
+            }
+            s.push_str("</table>");
+
+            // Code snippet
+            if let Some(ref snippet) = sast.code_snippet {
+                if !snippet.is_empty() {
+                    s.push_str(&format!(
+                        "<div class=\"code-snippet-block\"><div class=\"code-snippet-label\">Vulnerable Code</div><pre class=\"code-snippet\">{}</pre></div>",
+                        html_escape(snippet)
+                    ));
+                }
+            }
+
+            // Suggested fix
+            if let Some(ref fix) = sast.suggested_fix {
+                if !fix.is_empty() {
+                    s.push_str(&format!(
+                        "<div class=\"code-fix-block\"><div class=\"code-fix-label\">Suggested Fix</div><pre class=\"code-fix\">{}</pre></div>",
+                        html_escape(fix)
+                    ));
+                }
+            }
+
+            // Remediation from SAST
+            if let Some(ref rem) = sast.remediation {
+                if !rem.is_empty() {
+                    s.push_str(&format!(
+                        "<div class=\"code-remediation\">{}</div>",
+                        html_escape(rem)
+                    ));
+                }
+            }
+
+            s.push_str("</div>");
+            sections.push(s);
+        }
+    }
+
+    // 2. Endpoint match via code context
+    let endpoint_lower = dast_finding.endpoint.to_lowercase();
+    let matching_hints: Vec<&CodeContextHint> = code_context
+        .iter()
+        .filter(|hint| {
+            // Match by endpoint pattern overlap
+            let pattern_lower = hint.endpoint_pattern.to_lowercase();
+            endpoint_lower.contains(&pattern_lower)
+                || pattern_lower.contains(&endpoint_lower)
+                || hint.file_path.to_lowercase().contains(
+                    &endpoint_lower
+                        .split('/')
+                        .next_back()
+                        .unwrap_or("")
+                        .replace(".html", "")
+                        .replace(".php", ""),
+                )
+        })
+        .collect();
+
+    for hint in &matching_hints {
+        let mut s = String::new();
+        s.push_str(r#"<div class="code-correlation-item">"#);
+        s.push_str(r#"<div class="code-correlation-badge">Code Entry Point</div>"#);
+        s.push_str("<table class=\"code-meta\">");
+        s.push_str(&format!(
+            "<tr><td>Handler</td><td><code>{}</code></td></tr>",
+            html_escape(&hint.handler_function),
+        ));
+        s.push_str(&format!(
+            "<tr><td>File</td><td><code>{}</code></td></tr>",
+            html_escape(&hint.file_path),
+        ));
+        s.push_str(&format!(
+            "<tr><td>Route</td><td><code>{}</code></td></tr>",
+            html_escape(&hint.endpoint_pattern),
+        ));
+        s.push_str("</table>");
+
+        if !hint.known_vulnerabilities.is_empty() {
+            s.push_str("<div class=\"code-linked-vulns\"><strong>Known SAST issues in this file:</strong><ul>");
+            for vuln in &hint.known_vulnerabilities {
+                s.push_str(&format!("<li>{}</li>", html_escape(vuln)));
+            }
+            s.push_str("</ul></div>");
+        }
+
+        s.push_str("</div>");
+        sections.push(s);
+    }
+
+    // 3. SBOM match — if a linked SAST finding has a CVE, or we can match by CWE
+    let linked_cve = dast_finding
+        .linked_sast_finding_id
+        .as_deref()
+        .and_then(|id| sast_by_id.get(id))
+        .and_then(|f| f.cve.as_deref());
+
+    if let Some(cve_id) = linked_cve {
+        let matching_deps: Vec<&SbomEntry> = sbom_entries
+            .iter()
+            .filter(|e| e.known_vulnerabilities.iter().any(|v| v.id == cve_id))
+            .collect();
+
+        for dep in &matching_deps {
+            let mut s = String::new();
+            s.push_str(r#"<div class="code-correlation-item">"#);
+            s.push_str(r#"<div class="code-correlation-badge">Vulnerable Dependency</div>"#);
+            s.push_str("<table class=\"code-meta\">");
+            s.push_str(&format!(
+                "<tr><td>Package</td><td><code>{} {}</code> ({})</td></tr>",
+                html_escape(&dep.name),
+                html_escape(&dep.version),
+                html_escape(&dep.package_manager),
+            ));
+            let cve_ids: Vec<&str> = dep
+                .known_vulnerabilities
+                .iter()
+                .map(|v| v.id.as_str())
+                .collect();
+            s.push_str(&format!(
+                "<tr><td>CVEs</td><td>{}</td></tr>",
+                cve_ids.join(", "),
+            ));
+            if let Some(ref purl) = dep.purl {
+                s.push_str(&format!(
+                    "<tr><td>PURL</td><td><code>{}</code></td></tr>",
+                    html_escape(purl),
+                ));
+            }
+            s.push_str("</table>");
+            s.push_str(&format!(
+                "<div class=\"code-remediation\">Upgrade <code>{}</code> to the latest patched version to resolve {}.</div>",
+                html_escape(&dep.name),
+                html_escape(cve_id),
+            ));
+            s.push_str("</div>");
+            sections.push(s);
+        }
+    }
+
+    if sections.is_empty() {
+        return String::new();
+    }
+
+    format!(
+        r#"<div class="code-correlation">
+    <div class="code-correlation-title">Code-Level Remediation</div>
+    {}
+</div>"#,
+        sections.join("\n")
+    )
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::models::dast::{DastEvidence, DastVulnType};
+    use compliance_core::models::finding::Severity;
+    use compliance_core::models::scan::ScanType;
+
+    /// Helper: create a minimal `DastFinding`.
+    fn make_dast(title: &str, severity: Severity, endpoint: &str) -> DastFinding {
+        DastFinding::new(
+            "run1".into(),
+            "target1".into(),
+            DastVulnType::Xss,
+            title.into(),
+            "desc".into(),
+            severity,
+            endpoint.into(),
+            "GET".into(),
+        )
+    }
+
+    /// Helper: create a minimal SAST `Finding` with an ObjectId.
+    fn make_sast(title: &str) -> Finding {
+        let mut f = Finding::new(
+            "repo1".into(),
+            "fp1".into(),
+            "semgrep".into(),
+            ScanType::Sast,
+            title.into(),
+            "sast desc".into(),
+            Severity::High,
+        );
+        f.id = Some(mongodb::bson::oid::ObjectId::new());
+        f
+    }
+
+    #[test]
+    fn test_findings_empty() {
+        let result = findings(&[], &[], &[], &[]);
+        assert!(
+            result.contains("No vulnerabilities were identified"),
+            "Empty findings should contain the no-vulns message"
+        );
+    }
+
+    #[test]
+    fn test_findings_grouped_by_severity() {
+        let f_high = make_dast("High vuln", Severity::High, "/a");
+        let f_low = make_dast("Low vuln", Severity::Low, "/b");
+        let f_critical = make_dast("Crit vuln", Severity::Critical, "/c");
+
+        let result = findings(&[f_high, f_low, f_critical], &[], &[], &[]);
+
+        // All severity group headers should appear
+        assert!(
+            result.contains("Critical (1)"),
+            "should have Critical header"
+        );
+        assert!(result.contains("High (1)"), "should have High header");
+        assert!(result.contains("Low (1)"), "should have Low header");
+
+        // Critical should appear before High, High before Low
+        let crit_pos = result.find("Critical (1)");
+        let high_pos = result.find("High (1)");
+        let low_pos = result.find("Low (1)");
+        assert!(crit_pos < high_pos, "Critical should come before High");
+        assert!(high_pos < low_pos, "High should come before Low");
+    }
+
+    #[test]
+    fn test_code_correlation_sast_link() {
+        let mut sast = make_sast("SQL Injection in query");
+        sast.file_path = Some("src/db/query.rs".into());
+        sast.line_number = Some(42);
+        sast.code_snippet =
+            Some("let q = format!(\"SELECT * FROM {} WHERE id={}\", table, id);".into());
+
+        let sast_id = sast.id.as_ref().map(|oid| oid.to_hex()).unwrap_or_default();
+
+        let mut dast = make_dast("SQLi on /api/users", Severity::High, "/api/users");
+        dast.linked_sast_finding_id = Some(sast_id);
+
+        let result = findings(&[dast], &[sast], &[], &[]);
+
+        assert!(
+            result.contains("SAST Correlation"),
+            "should render SAST Correlation badge"
+        );
+        assert!(
+            result.contains("src/db/query.rs"),
+            "should contain the file path"
+        );
+        assert!(result.contains(":42"), "should contain the line number");
+        assert!(
+            result.contains("Vulnerable Code"),
+            "should render code snippet block"
+        );
+    }
+
+    #[test]
+    fn test_code_correlation_no_match() {
+        let dast = make_dast("XSS in search", Severity::Medium, "/search");
+        // No linked_sast_finding_id, no code context, no sbom
+        let result = findings(&[dast], &[], &[], &[]);
+
+        assert!(
+            !result.contains("code-correlation"),
+            "should not contain any code-correlation div"
+        );
+    }
+
+    #[test]
+    fn test_evidence_html_empty() {
+        let f = make_dast("No evidence", Severity::Low, "/x");
+        let result = build_evidence_html(&f);
+        assert!(result.is_empty(), "no evidence should yield empty string");
+    }
+
+    #[test]
+    fn test_evidence_html_with_entries() {
+        let mut f = make_dast("Has evidence", Severity::High, "/y");
+        f.evidence.push(DastEvidence {
+            request_method: "POST".into(),
+            request_url: "https://example.com/login".into(),
+            request_headers: None,
+            request_body: None,
+            response_status: 200,
+            response_headers: None,
+            response_snippet: Some("OK".into()),
+            screenshot_path: None,
+            payload: Some("<script>alert(1)</script>".into()),
+            response_time_ms: None,
+        });
+
+        let result = build_evidence_html(&f);
+
+        assert!(
+            result.contains("evidence-table"),
+            "should render the evidence table"
+        );
+        assert!(result.contains("POST"), "should contain request method");
+        assert!(
+            result.contains("https://example.com/login"),
+            "should contain request URL"
+        );
+        assert!(result.contains("200"), "should contain response status");
+        assert!(
+            result.contains("&lt;script&gt;alert(1)&lt;/script&gt;"),
+            "payload should be HTML-escaped"
+        );
+    }
+}

compliance-agent/src/pentest/report/html/mod.rs

@@ -0,0 +1,518 @@
+mod appendix;
+mod attack_chain;
+mod cover;
+mod executive_summary;
+mod findings;
+mod scope;
+mod styles;
+
+use super::ReportContext;
+
+#[allow(clippy::format_in_format_args)]
+pub(super) fn build_html_report(ctx: &ReportContext) -> String {
+    let session = &ctx.session;
+    let session_id = session
+        .id
+        .map(|oid| oid.to_hex())
+        .unwrap_or_else(|| "-".to_string());
+    let date_str = session
+        .started_at
+        .format("%B %d, %Y at %H:%M UTC")
+        .to_string();
+    let date_short = session.started_at.format("%B %d, %Y").to_string();
+    let completed_str = session
+        .completed_at
+        .map(|d| d.format("%B %d, %Y at %H:%M UTC").to_string())
+        .unwrap_or_else(|| "In Progress".to_string());
+
+    // Collect unique tool names used
+    let tool_names: Vec<String> = {
+        let mut names: Vec<String> = ctx
+            .attack_chain
+            .iter()
+            .map(|n| n.tool_name.clone())
+            .collect();
+        names.sort();
+        names.dedup();
+        names
+    };
+
+    // Find the best app screenshot for the cover page:
+    // prefer the first navigate to the target URL that has a screenshot,
+    // falling back to any navigate with a screenshot
+    let app_screenshot: Option<String> = ctx
+        .attack_chain
+        .iter()
+        .filter(|n| n.tool_name == "browser")
+        .filter_map(|n| {
+            n.tool_output
+                .as_ref()?
+                .get("screenshot_base64")?
+                .as_str()
+                .filter(|s| !s.is_empty())
+                .map(|s| s.to_string())
+        })
+        // Skip the Keycloak login page screenshots — prefer one that shows the actual app
+        .find(|_| {
+            ctx.attack_chain
+                .iter()
+                .filter(|n| n.tool_name == "browser")
+                .any(|n| {
+                    n.tool_output
+                        .as_ref()
+                        .and_then(|o| o.get("title"))
+                        .and_then(|t| t.as_str())
+                        .is_some_and(|t| t.contains("Compliance") || t.contains("Dashboard"))
+                })
+        })
+        .or_else(|| {
+            // Fallback: any screenshot
+            ctx.attack_chain
+                .iter()
+                .filter(|n| n.tool_name == "browser")
+                .filter_map(|n| {
+                    n.tool_output
+                        .as_ref()?
+                        .get("screenshot_base64")?
+                        .as_str()
+                        .filter(|s| !s.is_empty())
+                        .map(|s| s.to_string())
+                })
+                .next()
+        });
+
+    let styles_html = styles::styles();
+    let cover_html = cover::cover(
+        &ctx.target_name,
+        &session_id,
+        &date_short,
+        &ctx.target_url,
+        &ctx.requester_name,
+        &ctx.requester_email,
+        app_screenshot.as_deref(),
+    );
+    let exec_html = executive_summary::executive_summary(
+        &ctx.findings,
+        &ctx.target_name,
+        &ctx.target_url,
+        tool_names.len(),
+        session.tool_invocations,
+        session.success_rate(),
+    );
+    let scope_html = scope::scope(
+        session,
+        &ctx.target_name,
+        &ctx.target_url,
+        &date_str,
+        &completed_str,
+        &tool_names,
+        ctx.config.as_ref(),
+    );
+    let findings_html = findings::findings(
+        &ctx.findings,
+        &ctx.sast_findings,
+        &ctx.code_context,
+        &ctx.sbom_entries,
+    );
+    let chain_html = attack_chain::attack_chain(&ctx.attack_chain);
+    let appendix_html = appendix::appendix(&session_id);
+
+    format!(
+        r#"<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>Penetration Test Report — {target_name}</title>
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+<link href="https://fonts.googleapis.com/css2?family=Libre+Baskerville:ital,wght@0,400;0,700;1,400&family=Source+Sans+3:ital,wght@0,300;0,400;0,600;0,700&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet">
+{styles_html}
+</head>
+<body>
+
+{cover_html}
+
+{exec_html}
+
+{scope_html}
+
+{findings_html}
+
+{chain_html}
+
+{appendix_html}
+"#,
+        target_name = html_escape(&ctx.target_name),
+    )
+}
+
+fn tool_category(tool_name: &str) -> &'static str {
+    let name = tool_name.to_lowercase();
+    if name.contains("nmap") || name.contains("port") {
+        return "Network Reconnaissance";
+    }
+    if name.contains("nikto") || name.contains("header") {
+        return "Web Server Analysis";
+    }
+    if name.contains("zap") || name.contains("spider") || name.contains("crawl") {
+        return "Web Application Scanning";
+    }
+    if name.contains("sqlmap") || name.contains("sqli") || name.contains("sql") {
+        return "SQL Injection Testing";
+    }
+    if name.contains("xss") || name.contains("cross-site") {
+        return "Cross-Site Scripting Testing";
+    }
+    if name.contains("dir")
+        || name.contains("brute")
+        || name.contains("fuzz")
+        || name.contains("gobuster")
+    {
+        return "Directory Enumeration";
+    }
+    if name.contains("ssl") || name.contains("tls") || name.contains("cert") {
+        return "SSL/TLS Analysis";
+    }
+    if name.contains("api") || name.contains("endpoint") {
+        return "API Security Testing";
+    }
+    if name.contains("auth") || name.contains("login") || name.contains("credential") {
+        return "Authentication Testing";
+    }
+    if name.contains("cors") {
+        return "CORS Testing";
+    }
+    if name.contains("csrf") {
+        return "CSRF Testing";
+    }
+    if name.contains("nuclei") || name.contains("template") {
+        return "Vulnerability Scanning";
+    }
+    if name.contains("whatweb") || name.contains("tech") || name.contains("wappalyzer") {
+        return "Technology Fingerprinting";
+    }
+    "Security Testing"
+}
+
+fn html_escape(s: &str) -> String {
+    s.replace('&', "&amp;")
+        .replace('<', "&lt;")
+        .replace('>', "&gt;")
+        .replace('"', "&quot;")
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use compliance_core::models::dast::{DastFinding, DastVulnType};
+    use compliance_core::models::finding::Severity;
+    use compliance_core::models::pentest::{
+        AttackChainNode, AttackNodeStatus, PentestSession, PentestStrategy,
+    };
+
+    // ── html_escape ──────────────────────────────────────────────────
+
+    #[test]
+    fn html_escape_handles_ampersand() {
+        assert_eq!(html_escape("a & b"), "a &amp; b");
+    }
+
+    #[test]
+    fn html_escape_handles_angle_brackets() {
+        assert_eq!(html_escape("<script>"), "&lt;script&gt;");
+    }
+
+    #[test]
+    fn html_escape_handles_quotes() {
+        assert_eq!(html_escape(r#"key="val""#), "key=&quot;val&quot;");
+    }
+
+    #[test]
+    fn html_escape_handles_all_special_chars() {
+        assert_eq!(
+            html_escape(r#"<a href="x">&y</a>"#),
+            "&lt;a href=&quot;x&quot;&gt;&amp;y&lt;/a&gt;"
+        );
+    }
+
+    #[test]
+    fn html_escape_no_change_for_plain_text() {
+        assert_eq!(html_escape("hello world"), "hello world");
+    }
+
+    #[test]
+    fn html_escape_empty_string() {
+        assert_eq!(html_escape(""), "");
+    }
+
+    // ── tool_category ────────────────────────────────────────────────
+
+    #[test]
+    fn tool_category_nmap() {
+        assert_eq!(tool_category("nmap_scan"), "Network Reconnaissance");
+    }
+
+    #[test]
+    fn tool_category_port_scanner() {
+        assert_eq!(tool_category("port_scanner"), "Network Reconnaissance");
+    }
+
+    #[test]
+    fn tool_category_nikto() {
+        assert_eq!(tool_category("nikto"), "Web Server Analysis");
+    }
+
+    #[test]
+    fn tool_category_header_check() {
+        assert_eq!(
+            tool_category("security_header_check"),
+            "Web Server Analysis"
+        );
+    }
+
+    #[test]
+    fn tool_category_zap_spider() {
+        assert_eq!(tool_category("zap_spider"), "Web Application Scanning");
+    }
+
+    #[test]
+    fn tool_category_sqlmap() {
+        assert_eq!(tool_category("sqlmap"), "SQL Injection Testing");
+    }
+
+    #[test]
+    fn tool_category_xss_scanner() {
+        assert_eq!(tool_category("xss_scanner"), "Cross-Site Scripting Testing");
+    }
+
+    #[test]
+    fn tool_category_dir_bruteforce() {
+        assert_eq!(tool_category("dir_bruteforce"), "Directory Enumeration");
+    }
+
+    #[test]
+    fn tool_category_gobuster() {
+        assert_eq!(tool_category("gobuster"), "Directory Enumeration");
+    }
+
+    #[test]
+    fn tool_category_ssl_check() {
+        assert_eq!(tool_category("ssl_check"), "SSL/TLS Analysis");
+    }
+
+    #[test]
+    fn tool_category_tls_scan() {
+        assert_eq!(tool_category("tls_scan"), "SSL/TLS Analysis");
+    }
+
+    #[test]
+    fn tool_category_api_test() {
+        assert_eq!(tool_category("api_endpoint_test"), "API Security Testing");
+    }
+
+    #[test]
+    fn tool_category_auth_bypass() {
+        assert_eq!(tool_category("auth_bypass_check"), "Authentication Testing");
+    }
+
+    #[test]
+    fn tool_category_cors() {
+        assert_eq!(tool_category("cors_check"), "CORS Testing");
+    }
+
+    #[test]
+    fn tool_category_csrf() {
+        assert_eq!(tool_category("csrf_scanner"), "CSRF Testing");
+    }
+
+    #[test]
+    fn tool_category_nuclei() {
+        assert_eq!(tool_category("nuclei"), "Vulnerability Scanning");
+    }
+
+    #[test]
+    fn tool_category_whatweb() {
+        assert_eq!(tool_category("whatweb"), "Technology Fingerprinting");
+    }
+
+    #[test]
+    fn tool_category_unknown_defaults_to_security_testing() {
+        assert_eq!(tool_category("custom_tool"), "Security Testing");
+    }
+
+    #[test]
+    fn tool_category_is_case_insensitive() {
+        assert_eq!(tool_category("NMAP_Scanner"), "Network Reconnaissance");
+        assert_eq!(tool_category("SQLMap"), "SQL Injection Testing");
+    }
+
+    // ── build_html_report ────────────────────────────────────────────
+
+    fn make_session(strategy: PentestStrategy) -> PentestSession {
+        let mut s = PentestSession::new("target-1".into(), strategy);
+        s.tool_invocations = 5;
+        s.tool_successes = 4;
+        s.findings_count = 2;
+        s.exploitable_count = 1;
+        s
+    }
+
+    fn make_finding(severity: Severity, title: &str, exploitable: bool) -> DastFinding {
+        let mut f = DastFinding::new(
+            "run-1".into(),
+            "target-1".into(),
+            DastVulnType::Xss,
+            title.into(),
+            "description".into(),
+            severity,
+            "https://example.com/test".into(),
+            "GET".into(),
+        );
+        f.exploitable = exploitable;
+        f
+    }
+
+    fn make_attack_node(tool_name: &str) -> AttackChainNode {
+        let mut node = AttackChainNode::new(
+            "session-1".into(),
+            "node-1".into(),
+            tool_name.into(),
+            serde_json::json!({}),
+            "Testing this tool".into(),
+        );
+        node.status = AttackNodeStatus::Completed;
+        node
+    }
+
+    fn make_report_context(
+        findings: Vec<DastFinding>,
+        chain: Vec<AttackChainNode>,
+    ) -> ReportContext {
+        ReportContext {
+            session: make_session(PentestStrategy::Comprehensive),
+            target_name: "Test App".into(),
+            target_url: "https://example.com".into(),
+            findings,
+            attack_chain: chain,
+            requester_name: "Alice".into(),
+            requester_email: "alice@example.com".into(),
+            config: None,
+            sast_findings: Vec::new(),
+            sbom_entries: Vec::new(),
+            code_context: Vec::new(),
+        }
+    }
+
+    #[test]
+    fn report_contains_target_info() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("Test App"));
+        assert!(html.contains("https://example.com"));
+    }
+
+    #[test]
+    fn report_contains_requester_info() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("Alice"));
+        assert!(html.contains("alice@example.com"));
+    }
+
+    #[test]
+    fn report_shows_informational_risk_when_no_findings() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("INFORMATIONAL"));
+    }
+
+    #[test]
+    fn report_shows_critical_risk_with_critical_finding() {
+        let findings = vec![make_finding(Severity::Critical, "Critical XSS", true)];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("CRITICAL"));
+    }
+
+    #[test]
+    fn report_shows_high_risk_without_critical() {
+        let findings = vec![make_finding(Severity::High, "High SQLi", false)];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        // Should show HIGH, not CRITICAL
+        assert!(html.contains("HIGH"));
+    }
+
+    #[test]
+    fn report_shows_medium_risk_level() {
+        let findings = vec![make_finding(Severity::Medium, "Medium Issue", false)];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("MEDIUM"));
+    }
+
+    #[test]
+    fn report_includes_finding_title() {
+        let findings = vec![make_finding(
+            Severity::High,
+            "Reflected XSS in /search",
+            true,
+        )];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("Reflected XSS in /search"));
+    }
+
+    #[test]
+    fn report_shows_exploitable_badge() {
+        let findings = vec![make_finding(Severity::Critical, "SQLi", true)];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        // The report should mark exploitable findings
+        assert!(html.contains("EXPLOITABLE"));
+    }
+
+    #[test]
+    fn report_includes_attack_chain_tool_names() {
+        let chain = vec![make_attack_node("nmap_scan"), make_attack_node("sqlmap")];
+        let ctx = make_report_context(vec![], chain);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("nmap_scan"));
+        assert!(html.contains("sqlmap"));
+    }
+
+    #[test]
+    fn report_is_valid_html_structure() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        assert!(html.contains("<!DOCTYPE html>") || html.contains("<html"));
+        assert!(html.contains("</html>"));
+    }
+
+    #[test]
+    fn report_strategy_appears() {
+        let ctx = make_report_context(vec![], vec![]);
+        let html = build_html_report(&ctx);
+        // PentestStrategy::Comprehensive => "comprehensive"
+        assert!(html.contains("comprehensive") || html.contains("Comprehensive"));
+    }
+
+    #[test]
+    fn report_finding_count_is_correct() {
+        let findings = vec![
+            make_finding(Severity::Critical, "F1", true),
+            make_finding(Severity::High, "F2", false),
+            make_finding(Severity::Low, "F3", false),
+        ];
+        let ctx = make_report_context(findings, vec![]);
+        let html = build_html_report(&ctx);
+        // The total count "3" should appear somewhere
+        assert!(
+            html.contains(">3<")
+                || html.contains(">3 ")
+                || html.contains("3 findings")
+                || html.contains("3 Total")
+        );
+    }
+}

compliance-agent/src/pentest/report/html/scope.rs

@@ -0,0 +1,127 @@
+use super::{html_escape, tool_category};
+use compliance_core::models::pentest::{AuthMode, PentestConfig, PentestSession};
+
+pub(super) fn scope(
+    session: &PentestSession,
+    target_name: &str,
+    target_url: &str,
+    date_str: &str,
+    completed_str: &str,
+    tool_names: &[String],
+    config: Option<&PentestConfig>,
+) -> String {
+    let tools_table: String = tool_names
+        .iter()
+        .enumerate()
+        .map(|(i, t)| {
+            let category = tool_category(t);
+            format!(
+                "<tr><td>{}</td><td><code>{}</code></td><td>{}</td></tr>",
+                i + 1,
+                html_escape(t),
+                category,
+            )
+        })
+        .collect::<Vec<_>>()
+        .join("\n");
+
+    let engagement_config_section = if let Some(cfg) = config {
+        let mut rows = String::new();
+        rows.push_str(&format!(
+            "<tr><td>Environment</td><td>{}</td></tr>",
+            html_escape(&cfg.environment.to_string())
+        ));
+        if let Some(ref app_type) = cfg.app_type {
+            rows.push_str(&format!(
+                "<tr><td>Application Type</td><td>{}</td></tr>",
+                html_escape(app_type)
+            ));
+        }
+        let auth_mode = match cfg.auth.mode {
+            AuthMode::None => "No authentication",
+            AuthMode::Manual => "Manual credentials",
+            AuthMode::AutoRegister => "Auto-register",
+        };
+        rows.push_str(&format!("<tr><td>Auth Mode</td><td>{auth_mode}</td></tr>"));
+        if !cfg.scope_exclusions.is_empty() {
+            let excl = cfg
+                .scope_exclusions
+                .iter()
+                .map(|s| html_escape(s))
+                .collect::<Vec<_>>()
+                .join(", ");
+            rows.push_str(&format!(
+                "<tr><td>Scope Exclusions</td><td><code>{excl}</code></td></tr>"
+            ));
+        }
+        if !cfg.tester.name.is_empty() {
+            rows.push_str(&format!(
+                "<tr><td>Tester</td><td>{} ({})</td></tr>",
+                html_escape(&cfg.tester.name),
+                html_escape(&cfg.tester.email)
+            ));
+        }
+        if let Some(ref ts) = cfg.disclaimer_accepted_at {
+            rows.push_str(&format!(
+                "<tr><td>Disclaimer Accepted</td><td>{}</td></tr>",
+                ts.format("%B %d, %Y at %H:%M UTC")
+            ));
+        }
+        if let Some(ref branch) = cfg.branch {
+            rows.push_str(&format!(
+                "<tr><td>Git Branch</td><td>{}</td></tr>",
+                html_escape(branch)
+            ));
+        }
+        if let Some(ref commit) = cfg.commit_hash {
+            rows.push_str(&format!(
+                "<tr><td>Git Commit</td><td><code>{}</code></td></tr>",
+                html_escape(commit)
+            ));
+        }
+        format!("<h3>Engagement Configuration</h3>\n<table class=\"info\">\n{rows}\n</table>")
+    } else {
+        String::new()
+    };
+
+    format!(
+        r##"
+<!-- ═══════════════ 2. SCOPE & METHODOLOGY ═══════════════ -->
+<div class="page-break"></div>
+<h2><span class="section-num">2.</span> Scope &amp; Methodology</h2>
+
+<p>
+    The assessment was performed using an AI-driven orchestrator that autonomously selects and
+    executes security testing tools based on the target's attack surface, technology stack, and
+    any available static analysis (SAST) findings and SBOM data.
+</p>
+
+<h3>Engagement Details</h3>
+<table class="info">
+    <tr><td>Target</td><td><strong>{target_name}</strong></td></tr>
+    <tr><td>URL</td><td><code>{target_url}</code></td></tr>
+    <tr><td>Strategy</td><td>{strategy}</td></tr>
+    <tr><td>Status</td><td>{status}</td></tr>
+    <tr><td>Started</td><td>{date_str}</td></tr>
+    <tr><td>Completed</td><td>{completed_str}</td></tr>
+    <tr><td>Tool Invocations</td><td>{tool_invocations} ({tool_successes} successful, {success_rate:.1}% success rate)</td></tr>
+</table>
+
+{engagement_config_section}
+
+<h3>Tools Employed</h3>
+<table class="tools-table">
+    <thead><tr><th>#</th><th>Tool</th><th>Category</th></tr></thead>
+    <tbody>{tools_table}</tbody>
+</table>"##,
+        target_name = html_escape(target_name),
+        target_url = html_escape(target_url),
+        strategy = session.strategy,
+        status = session.status,
+        date_str = date_str,
+        completed_str = completed_str,
+        tool_invocations = session.tool_invocations,
+        tool_successes = session.tool_successes,
+        success_rate = session.success_rate(),
+    )
+}

compliance-agent/src/pentest/report/html/styles.rs

@@ -0,0 +1,889 @@
+pub(super) fn styles() -> String {
+    r##"<style>
+/* ──────────────── Base / Print-first ──────────────── */
+@page {
+    size: A4;
+    margin: 20mm 18mm 25mm 18mm;
+}
+@page :first {
+    margin: 0;
+}
+
+*, *::before, *::after { margin: 0; padding: 0; box-sizing: border-box; }
+
+:root {
+    --text: #1a1a2e;
+    --text-secondary: #475569;
+    --text-muted: #64748b;
+    --heading: #0d2137;
+    --accent: #1a56db;
+    --accent-light: #dbeafe;
+    --border: #d1d5db;
+    --border-light: #e5e7eb;
+    --bg-subtle: #f8fafc;
+    --bg-section: #f1f5f9;
+    --sev-critical: #991b1b;
+    --sev-high: #c2410c;
+    --sev-medium: #a16207;
+    --sev-low: #1d4ed8;
+    --sev-info: #4b5563;
+    --font-serif: 'Libre Baskerville', 'Georgia', serif;
+    --font-sans: 'Source Sans 3', 'Helvetica Neue', sans-serif;
+    --font-mono: 'JetBrains Mono', 'Consolas', monospace;
+}
+
+body {
+    font-family: var(--font-sans);
+    color: var(--text);
+    background: #fff;
+    line-height: 1.65;
+    font-size: 10.5pt;
+    -webkit-print-color-adjust: exact;
+    print-color-adjust: exact;
+}
+
+.report-body {
+    max-width: 190mm;
+    margin: 0 auto;
+    padding: 0 16px;
+}
+
+/* ──────────────── Cover Page ──────────────── */
+.cover {
+    height: 100vh;
+    min-height: 297mm;
+    display: flex;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+    text-align: center;
+    padding: 40mm 30mm;
+    page-break-after: always;
+    break-after: page;
+    position: relative;
+    background: #fff;
+}
+
+.cover-shield {
+    width: 72px;
+    height: 72px;
+    margin-bottom: 32px;
+}
+
+.cover-tag {
+    display: inline-block;
+    background: var(--sev-critical);
+    color: #fff;
+    font-family: var(--font-sans);
+    font-size: 8pt;
+    font-weight: 700;
+    letter-spacing: 0.15em;
+    text-transform: uppercase;
+    padding: 4px 16px;
+    border-radius: 2px;
+    margin-bottom: 28px;
+}
+
+.cover-title {
+    font-family: var(--font-serif);
+    font-size: 28pt;
+    font-weight: 700;
+    color: var(--heading);
+    line-height: 1.2;
+    margin-bottom: 8px;
+}
+
+.cover-subtitle {
+    font-family: var(--font-serif);
+    font-size: 14pt;
+    color: var(--text-secondary);
+    font-weight: 400;
+    font-style: italic;
+    margin-bottom: 48px;
+}
+
+.cover-meta {
+    font-size: 10pt;
+    color: var(--text-secondary);
+    line-height: 2;
+}
+
+.cover-meta strong {
+    color: var(--text);
+}
+
+.cover-divider {
+    width: 60px;
+    height: 2px;
+    background: var(--accent);
+    margin: 24px auto;
+}
+
+.cover-footer {
+    position: absolute;
+    bottom: 30mm;
+    left: 0;
+    right: 0;
+    text-align: center;
+    font-size: 8pt;
+    color: var(--text-muted);
+    letter-spacing: 0.05em;
+}
+
+/* ──────────────── Typography ──────────────── */
+h2 {
+    font-family: var(--font-serif);
+    font-size: 16pt;
+    font-weight: 700;
+    color: var(--heading);
+    margin: 36px 0 16px;
+    padding-bottom: 8px;
+    border-bottom: 2px solid var(--heading);
+    page-break-after: avoid;
+    break-after: avoid;
+}
+
+h3 {
+    font-family: var(--font-serif);
+    font-size: 12pt;
+    font-weight: 700;
+    color: var(--heading);
+    margin: 24px 0 10px;
+    page-break-after: avoid;
+    break-after: avoid;
+}
+
+h4 {
+    font-family: var(--font-sans);
+    font-size: 10pt;
+    font-weight: 700;
+    color: var(--text-secondary);
+    margin: 16px 0 8px;
+}
+
+p {
+    margin: 8px 0;
+    font-size: 10.5pt;
+}
+
+code {
+    font-family: var(--font-mono);
+    font-size: 9pt;
+    background: var(--bg-section);
+    padding: 1px 5px;
+    border-radius: 3px;
+    border: 1px solid var(--border-light);
+    word-break: break-all;
+}
+
+/* ──────────────── Section Numbers ──────────────── */
+.section-num {
+    color: var(--accent);
+    margin-right: 8px;
+}
+
+/* ──────────────── Table of Contents ──────────────── */
+.toc {
+    page-break-after: always;
+    break-after: page;
+    padding-top: 24px;
+}
+
+.toc h2 {
+    border-bottom-color: var(--accent);
+    margin-top: 0;
+}
+
+.toc-entry {
+    display: flex;
+    justify-content: space-between;
+    align-items: baseline;
+    padding: 6px 0;
+    border-bottom: 1px dotted var(--border);
+    font-size: 11pt;
+}
+
+.toc-entry .toc-num {
+    font-weight: 700;
+    color: var(--accent);
+    min-width: 24px;
+    margin-right: 10px;
+}
+
+.toc-entry .toc-label {
+    flex: 1;
+    font-weight: 600;
+    color: var(--heading);
+}
+
+.toc-sub {
+    padding: 3px 0 3px 34px;
+    font-size: 9.5pt;
+    color: var(--text-secondary);
+}
+
+/* ──────────────── Executive Summary ──────────────── */
+.exec-grid {
+    display: grid;
+    grid-template-columns: 1fr 1fr 1fr 1fr;
+    gap: 12px;
+    margin: 16px 0 20px;
+}
+
+.kpi-card {
+    border: 1px solid var(--border);
+    border-radius: 6px;
+    padding: 14px 12px;
+    text-align: center;
+    background: var(--bg-subtle);
+}
+
+.kpi-value {
+    font-family: var(--font-serif);
+    font-size: 22pt;
+    font-weight: 700;
+    line-height: 1.1;
+}
+
+.kpi-label {
+    font-size: 8pt;
+    text-transform: uppercase;
+    letter-spacing: 0.08em;
+    color: var(--text-muted);
+    margin-top: 4px;
+    font-weight: 600;
+}
+
+/* Risk gauge */
+.risk-gauge {
+    display: flex;
+    align-items: center;
+    gap: 16px;
+    padding: 16px 20px;
+    border: 1px solid var(--border);
+    border-radius: 6px;
+    background: var(--bg-subtle);
+    margin: 16px 0;
+}
+
+.risk-gauge-meter {
+    width: 140px;
+    flex-shrink: 0;
+}
+
+.risk-gauge-track {
+    height: 10px;
+    background: var(--border-light);
+    border-radius: 5px;
+    overflow: hidden;
+    position: relative;
+}
+
+.risk-gauge-fill {
+    height: 100%;
+    border-radius: 5px;
+    transition: width 0.3s;
+}
+
+.risk-gauge-score {
+    font-family: var(--font-serif);
+    font-size: 9pt;
+    font-weight: 700;
+    text-align: center;
+    margin-top: 3px;
+}
+
+.risk-gauge-text {
+    flex: 1;
+}
+
+.risk-gauge-label {
+    font-family: var(--font-serif);
+    font-size: 14pt;
+    font-weight: 700;
+}
+
+.risk-gauge-desc {
+    font-size: 9.5pt;
+    color: var(--text-secondary);
+    margin-top: 2px;
+}
+
+/* Severity bar */
+.sev-bar {
+    display: flex;
+    height: 28px;
+    border-radius: 4px;
+    overflow: hidden;
+    margin: 12px 0 6px;
+    border: 1px solid var(--border);
+}
+
+.sev-bar-seg {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    color: #fff;
+    font-size: 8.5pt;
+    font-weight: 700;
+    min-width: 24px;
+}
+
+.sev-bar-critical { background: var(--sev-critical); }
+.sev-bar-high { background: var(--sev-high); }
+.sev-bar-medium { background: var(--sev-medium); }
+.sev-bar-low { background: var(--sev-low); }
+.sev-bar-info { background: var(--sev-info); }
+
+.sev-bar-legend {
+    display: flex;
+    gap: 16px;
+    font-size: 8.5pt;
+    color: var(--text-secondary);
+    margin-bottom: 16px;
+}
+
+.sev-dot {
+    display: inline-block;
+    width: 8px;
+    height: 8px;
+    border-radius: 2px;
+    margin-right: 4px;
+    vertical-align: middle;
+}
+
+/* ──────────────── Info Tables ──────────────── */
+table.info {
+    width: 100%;
+    border-collapse: collapse;
+    margin: 10px 0;
+    font-size: 10pt;
+}
+
+table.info td,
+table.info th {
+    padding: 7px 12px;
+    border: 1px solid var(--border);
+    text-align: left;
+    vertical-align: top;
+}
+
+table.info td:first-child,
+table.info th:first-child {
+    width: 160px;
+    font-weight: 600;
+    color: var(--text-secondary);
+    background: var(--bg-subtle);
+}
+
+/* Methodology tools table */
+table.tools-table {
+    width: 100%;
+    border-collapse: collapse;
+    margin: 10px 0;
+    font-size: 10pt;
+}
+
+table.tools-table th {
+    background: var(--heading);
+    color: #fff;
+    padding: 8px 12px;
+    text-align: left;
+    font-weight: 600;
+    font-size: 9pt;
+    text-transform: uppercase;
+    letter-spacing: 0.04em;
+}
+
+table.tools-table td {
+    padding: 6px 12px;
+    border-bottom: 1px solid var(--border-light);
+}
+
+table.tools-table tr:nth-child(even) td {
+    background: var(--bg-subtle);
+}
+
+table.tools-table td:first-child {
+    width: 32px;
+    text-align: center;
+    color: var(--text-muted);
+    font-weight: 600;
+}
+
+/* ──────────────── Badges ──────────────── */
+.badge {
+    display: inline-block;
+    padding: 2px 8px;
+    border-radius: 3px;
+    font-size: 7.5pt;
+    font-weight: 700;
+    text-transform: uppercase;
+    letter-spacing: 0.03em;
+    vertical-align: middle;
+}
+
+.badge-exploit {
+    background: var(--sev-critical);
+    color: #fff;
+}
+
+/* ──────────────── Findings ──────────────── */
+.sev-group-title {
+    font-family: var(--font-sans);
+    font-size: 11pt;
+    font-weight: 700;
+    color: var(--heading);
+    padding: 8px 0 6px 12px;
+    margin: 20px 0 8px;
+    border-left: 4px solid;
+    page-break-after: avoid;
+    break-after: avoid;
+}
+
+.finding {
+    border: 1px solid var(--border);
+    border-left: 4px solid;
+    border-radius: 0 4px 4px 0;
+    padding: 14px 16px;
+    margin-bottom: 12px;
+    background: #fff;
+    page-break-inside: avoid;
+    break-inside: avoid;
+}
+
+.finding-header {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    margin-bottom: 8px;
+}
+
+.finding-id {
+    font-family: var(--font-mono);
+    font-size: 9pt;
+    font-weight: 500;
+    color: var(--text-muted);
+    background: var(--bg-section);
+    padding: 2px 6px;
+    border-radius: 3px;
+    border: 1px solid var(--border-light);
+}
+
+.finding-title {
+    font-family: var(--font-serif);
+    font-weight: 700;
+    font-size: 11pt;
+    flex: 1;
+    color: var(--heading);
+}
+
+.finding-meta {
+    border-collapse: collapse;
+    margin: 6px 0;
+    font-size: 9.5pt;
+    width: 100%;
+}
+
+.finding-meta td {
+    padding: 3px 10px 3px 0;
+    vertical-align: top;
+}
+
+.finding-meta td:first-child {
+    color: var(--text-muted);
+    font-weight: 600;
+    width: 90px;
+    white-space: nowrap;
+}
+
+.finding-desc {
+    margin: 8px 0;
+    font-size: 10pt;
+    color: var(--text);
+    line-height: 1.6;
+}
+
+.remediation {
+    margin-top: 10px;
+    padding: 10px 14px;
+    background: var(--accent-light);
+    border-left: 3px solid var(--accent);
+    border-radius: 0 4px 4px 0;
+    font-size: 9.5pt;
+    line-height: 1.55;
+}
+
+.remediation-label {
+    font-weight: 700;
+    font-size: 8.5pt;
+    text-transform: uppercase;
+    letter-spacing: 0.06em;
+    color: var(--accent);
+    margin-bottom: 3px;
+}
+
+.evidence-block {
+    margin: 10px 0;
+    page-break-inside: avoid;
+    break-inside: avoid;
+}
+
+.evidence-title {
+    font-weight: 700;
+    font-size: 8.5pt;
+    text-transform: uppercase;
+    letter-spacing: 0.06em;
+    color: var(--text-muted);
+    margin-bottom: 4px;
+}
+
+.evidence-table {
+    width: 100%;
+    border-collapse: collapse;
+    font-size: 9pt;
+}
+
+.evidence-table th {
+    background: var(--bg-section);
+    padding: 5px 8px;
+    text-align: left;
+    font-weight: 600;
+    font-size: 8.5pt;
+    text-transform: uppercase;
+    letter-spacing: 0.03em;
+    color: var(--text-secondary);
+    border: 1px solid var(--border-light);
+}
+
+.evidence-table td {
+    padding: 5px 8px;
+    border: 1px solid var(--border-light);
+    vertical-align: top;
+    word-break: break-word;
+}
+
+.evidence-payload {
+    font-size: 8.5pt;
+    color: var(--sev-critical);
+}
+
+.linked-sast {
+    font-size: 9pt;
+    color: var(--text-muted);
+    margin: 6px 0;
+    font-style: italic;
+}
+
+/* ──────────────── Code-Level Correlation ──────────────── */
+.code-correlation {
+    margin: 12px 0;
+    border: 1px solid #e2e8f0;
+    border-radius: 6px;
+    overflow: hidden;
+}
+.code-correlation-title {
+    background: #1e293b;
+    color: #f8fafc;
+    padding: 6px 12px;
+    font-size: 9pt;
+    font-weight: 700;
+    text-transform: uppercase;
+    letter-spacing: 0.05em;
+}
+.code-correlation-item {
+    padding: 10px 12px;
+    border-bottom: 1px solid #e2e8f0;
+}
+.code-correlation-item:last-child { border-bottom: none; }
+.code-correlation-badge {
+    display: inline-block;
+    background: #3b82f6;
+    color: #fff;
+    font-size: 7pt;
+    font-weight: 600;
+    padding: 2px 8px;
+    border-radius: 3px;
+    text-transform: uppercase;
+    letter-spacing: 0.04em;
+    margin-bottom: 6px;
+}
+.code-meta {
+    width: 100%;
+    font-size: 8.5pt;
+    border-collapse: collapse;
+    margin-bottom: 6px;
+}
+.code-meta td:first-child {
+    width: 80px;
+    font-weight: 600;
+    color: var(--text-muted);
+    padding: 2px 8px 2px 0;
+    vertical-align: top;
+}
+.code-meta td:last-child {
+    padding: 2px 0;
+}
+.code-snippet-block, .code-fix-block {
+    margin: 6px 0;
+}
+.code-snippet-label, .code-fix-label {
+    font-size: 7.5pt;
+    font-weight: 700;
+    text-transform: uppercase;
+    letter-spacing: 0.04em;
+    color: var(--text-muted);
+    margin-bottom: 3px;
+}
+.code-snippet-label { color: #dc2626; }
+.code-fix-label { color: #16a34a; }
+.code-snippet {
+    background: #fef2f2;
+    border: 1px solid #fecaca;
+    border-left: 3px solid #dc2626;
+    padding: 8px 10px;
+    font-family: 'JetBrains Mono', monospace;
+    font-size: 8pt;
+    line-height: 1.5;
+    white-space: pre-wrap;
+    word-break: break-word;
+    border-radius: 0 4px 4px 0;
+    margin: 0;
+}
+.code-fix {
+    background: #f0fdf4;
+    border: 1px solid #bbf7d0;
+    border-left: 3px solid #16a34a;
+    padding: 8px 10px;
+    font-family: 'JetBrains Mono', monospace;
+    font-size: 8pt;
+    line-height: 1.5;
+    white-space: pre-wrap;
+    word-break: break-word;
+    border-radius: 0 4px 4px 0;
+    margin: 0;
+}
+.code-remediation {
+    font-size: 8.5pt;
+    color: var(--text-secondary);
+    margin-top: 4px;
+    padding: 4px 0;
+}
+.code-linked-vulns {
+    font-size: 8.5pt;
+    margin-top: 4px;
+}
+.code-linked-vulns ul {
+    margin: 2px 0 0 16px;
+    padding: 0;
+}
+.code-linked-vulns li {
+    margin-bottom: 2px;
+}
+
+/* ──────────────── Attack Chain ──────────────── */
+.phase-block {
+    margin-bottom: 20px;
+    page-break-inside: avoid;
+    break-inside: avoid;
+}
+
+.phase-header {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    padding: 8px 14px;
+    background: var(--heading);
+    color: #fff;
+    border-radius: 4px 4px 0 0;
+    font-size: 9.5pt;
+}
+
+.phase-num {
+    font-weight: 700;
+    font-size: 8pt;
+    text-transform: uppercase;
+    letter-spacing: 0.1em;
+    background: rgba(255,255,255,0.15);
+    padding: 2px 8px;
+    border-radius: 3px;
+}
+
+.phase-label {
+    font-weight: 600;
+    flex: 1;
+}
+
+.phase-count {
+    font-size: 8.5pt;
+    opacity: 0.7;
+}
+
+.phase-steps {
+    border: 1px solid var(--border);
+    border-top: none;
+    border-radius: 0 0 4px 4px;
+}
+
+.step-row {
+    display: flex;
+    align-items: flex-start;
+    gap: 10px;
+    padding: 8px 14px;
+    border-bottom: 1px solid var(--border-light);
+    position: relative;
+}
+
+.step-row:last-child {
+    border-bottom: none;
+}
+
+.step-num {
+    width: 22px;
+    height: 22px;
+    border-radius: 50%;
+    background: var(--bg-section);
+    border: 1px solid var(--border);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    font-size: 8pt;
+    font-weight: 700;
+    color: var(--text-secondary);
+    flex-shrink: 0;
+    margin-top: 1px;
+}
+
+.step-connector {
+    display: none;
+}
+
+.step-content {
+    flex: 1;
+    min-width: 0;
+}
+
+.step-header {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    flex-wrap: wrap;
+}
+
+.step-tool {
+    font-family: var(--font-mono);
+    font-size: 9.5pt;
+    font-weight: 500;
+    color: var(--heading);
+}
+
+.step-status {
+    font-size: 7.5pt;
+    font-weight: 700;
+    text-transform: uppercase;
+    letter-spacing: 0.04em;
+    padding: 1px 7px;
+    border-radius: 3px;
+}
+
+.step-completed { background: #dcfce7; color: #166534; }
+.step-failed { background: #fef2f2; color: #991b1b; }
+.step-running { background: #fef9c3; color: #854d0e; }
+
+.step-findings {
+    font-size: 8pt;
+    font-weight: 600;
+    color: var(--sev-high);
+    background: #fff7ed;
+    padding: 1px 7px;
+    border-radius: 3px;
+    border: 1px solid #fed7aa;
+}
+
+.step-risk {
+    font-size: 7.5pt;
+    font-weight: 700;
+    padding: 1px 6px;
+    border-radius: 3px;
+}
+
+.risk-high { background: #fef2f2; color: var(--sev-critical); border: 1px solid #fecaca; }
+.risk-med { background: #fffbeb; color: var(--sev-medium); border: 1px solid #fde68a; }
+.risk-low { background: #f0fdf4; color: #166534; border: 1px solid #bbf7d0; }
+
+.step-reasoning {
+    font-size: 9pt;
+    color: var(--text-muted);
+    margin-top: 3px;
+    line-height: 1.5;
+    font-style: italic;
+}
+
+/* ──────────────── Footer ──────────────── */
+.report-footer {
+    margin-top: 48px;
+    padding-top: 14px;
+    border-top: 2px solid var(--heading);
+    font-size: 8pt;
+    color: var(--text-muted);
+    text-align: center;
+    line-height: 1.8;
+}
+
+.report-footer .footer-company {
+    font-weight: 700;
+    color: var(--text-secondary);
+}
+
+/* ──────────────── Page Break Utilities ──────────────── */
+.page-break {
+    page-break-before: always;
+    break-before: page;
+}
+
+.avoid-break {
+    page-break-inside: avoid;
+    break-inside: avoid;
+}
+
+/* ──────────────── Print Overrides ──────────────── */
+@media print {
+    body {
+        font-size: 10pt;
+    }
+    .cover {
+        height: auto;
+        min-height: 250mm;
+        padding: 50mm 20mm;
+    }
+    .report-body {
+        padding: 0;
+    }
+    .no-print {
+        display: none !important;
+    }
+    a {
+        color: var(--accent);
+        text-decoration: none;
+    }
+}
+
+/* ──────────────── Screen Enhancements ──────────────── */
+@media screen {
+    body {
+        background: #e2e8f0;
+    }
+    .cover {
+        background: #fff;
+        box-shadow: 0 1px 4px rgba(0,0,0,0.08);
+    }
+    .report-body {
+        background: #fff;
+        padding: 20px 32px 40px;
+        box-shadow: 0 1px 4px rgba(0,0,0,0.08);
+        margin-bottom: 40px;
+    }
+}
+</style>"##
+        .to_string()
+}

compliance-agent/src/pentest/report/mod.rs

@@ -0,0 +1,69 @@
+mod archive;
+mod html;
+mod pdf;
+
+use compliance_core::models::dast::DastFinding;
+use compliance_core::models::finding::Finding;
+use compliance_core::models::pentest::{
+    AttackChainNode, CodeContextHint, PentestConfig, PentestSession,
+};
+use compliance_core::models::sbom::SbomEntry;
+use sha2::{Digest, Sha256};
+
+/// Report archive with metadata
+pub struct ReportArchive {
+    /// The password-protected ZIP bytes
+    pub archive: Vec<u8>,
+    /// SHA-256 hex digest of the archive
+    pub sha256: String,
+}
+
+/// Report context gathered from the database
+pub struct ReportContext {
+    pub session: PentestSession,
+    pub target_name: String,
+    pub target_url: String,
+    pub findings: Vec<DastFinding>,
+    pub attack_chain: Vec<AttackChainNode>,
+    pub requester_name: String,
+    pub requester_email: String,
+    pub config: Option<PentestConfig>,
+    /// SAST findings for the linked repository (for code-level correlation)
+    pub sast_findings: Vec<Finding>,
+    /// Vulnerable dependencies from SBOM
+    pub sbom_entries: Vec<SbomEntry>,
+    /// Code knowledge graph entry points linked to SAST findings
+    pub code_context: Vec<CodeContextHint>,
+}
+
+/// Generate a password-protected ZIP archive containing the pentest report.
+///
+/// The archive contains:
+/// - `report.pdf` — Professional pentest report (PDF)
+/// - `report.html` — HTML source (fallback)
+/// - `findings.json` — Raw findings data
+/// - `attack-chain.json` — Attack chain timeline
+///
+/// Files are encrypted with AES-256 inside the ZIP (standard WinZip AES format,
+/// supported by 7-Zip, WinRAR, macOS Archive Utility, etc.).
+pub async fn generate_encrypted_report(
+    ctx: &ReportContext,
+    password: &str,
+) -> Result<ReportArchive, String> {
+    let html = html::build_html_report(ctx);
+
+    // Convert HTML to PDF via headless Chrome
+    let pdf_bytes = pdf::html_to_pdf(&html).await?;
+
+    let zip_bytes = archive::build_zip(ctx, password, &html, &pdf_bytes)
+        .map_err(|e| format!("Failed to create archive: {e}"))?;
+
+    let mut hasher = Sha256::new();
+    hasher.update(&zip_bytes);
+    let sha256 = hex::encode(hasher.finalize());
+
+    Ok(ReportArchive {
+        archive: zip_bytes,
+        sha256,
+    })
+}

compliance-agent/src/pentest/report/pdf.rs

@@ -0,0 +1,289 @@
+use futures_util::SinkExt;
+use tokio_tungstenite::tungstenite::Message;
+
+type WsStream =
+    tokio_tungstenite::WebSocketStream<tokio_tungstenite::MaybeTlsStream<tokio::net::TcpStream>>;
+
+/// Convert HTML string to PDF bytes.
+///
+/// If `CHROME_WS_URL` is set (e.g. `ws://host:3000`), connects to a remote
+/// headless Chrome via the Chrome DevTools Protocol over WebSocket.
+/// Otherwise falls back to a local Chrome/Chromium binary.
+pub(super) async fn html_to_pdf(html: &str) -> Result<Vec<u8>, String> {
+    if let Ok(ws_url) = std::env::var("CHROME_WS_URL") {
+        tracing::info!(url = %ws_url, "Generating PDF via remote Chrome (CDP)");
+        cdp_print_to_pdf(&ws_url, html).await
+    } else {
+        tracing::info!("Generating PDF via local Chrome binary");
+        local_chrome_pdf(html).await
+    }
+}
+
+/// Send a CDP command (no session) and return the response.
+async fn cdp_send(
+    ws: &mut WsStream,
+    id: u64,
+    method: &str,
+    params: serde_json::Value,
+) -> Result<serde_json::Value, String> {
+    let msg = serde_json::json!({ "id": id, "method": method, "params": params });
+    ws.send(Message::Text(msg.to_string().into()))
+        .await
+        .map_err(|e| format!("WS send failed: {e}"))?;
+    read_until_result(ws, id).await
+}
+
+/// Send a CDP command on a session and return the response.
+async fn cdp_send_session(
+    ws: &mut WsStream,
+    id: u64,
+    session_id: &str,
+    method: &str,
+    params: serde_json::Value,
+) -> Result<serde_json::Value, String> {
+    let msg = serde_json::json!({
+        "id": id,
+        "sessionId": session_id,
+        "method": method,
+        "params": params,
+    });
+    ws.send(Message::Text(msg.to_string().into()))
+        .await
+        .map_err(|e| format!("WS send failed: {e}"))?;
+    read_until_result(ws, id).await
+}
+
+/// Generate PDF by connecting to a remote Chrome instance over CDP WebSocket.
+async fn cdp_print_to_pdf(base_ws_url: &str, html: &str) -> Result<Vec<u8>, String> {
+    use base64::Engine;
+
+    // Step 1: Discover browser WS endpoint via /json/version
+    let http_url = base_ws_url
+        .replace("ws://", "http://")
+        .replace("wss://", "https://");
+    let version_url = format!("{http_url}/json/version");
+
+    let version: serde_json::Value = reqwest::get(&version_url)
+        .await
+        .map_err(|e| format!("Failed to reach Chrome at {version_url}: {e}"))?
+        .json()
+        .await
+        .map_err(|e| format!("Invalid /json/version response: {e}"))?;
+
+    let browser_ws = version["webSocketDebuggerUrl"]
+        .as_str()
+        .ok_or_else(|| "No webSocketDebuggerUrl in /json/version".to_string())?;
+
+    // Step 2: Connect to browser WS endpoint
+    let (mut ws, _) = tokio_tungstenite::connect_async(browser_ws)
+        .await
+        .map_err(|e| format!("WebSocket connect failed: {e}"))?;
+
+    let mut id: u64 = 1;
+
+    // Step 3: Create a new target (tab)
+    let resp = cdp_send(
+        &mut ws,
+        id,
+        "Target.createTarget",
+        serde_json::json!({ "url": "about:blank" }),
+    )
+    .await?;
+    id += 1;
+
+    let target_id = resp
+        .get("result")
+        .and_then(|r| r.get("targetId"))
+        .and_then(|t| t.as_str())
+        .ok_or("No targetId in createTarget response")?
+        .to_string();
+
+    // Step 4: Attach to target
+    let resp = cdp_send(
+        &mut ws,
+        id,
+        "Target.attachToTarget",
+        serde_json::json!({ "targetId": target_id, "flatten": true }),
+    )
+    .await?;
+    id += 1;
+
+    let session_id = resp
+        .get("result")
+        .and_then(|r| r.get("sessionId"))
+        .and_then(|s| s.as_str())
+        .ok_or("No sessionId in attachToTarget response")?
+        .to_string();
+
+    // Step 5: Enable Page domain
+    cdp_send_session(
+        &mut ws,
+        id,
+        &session_id,
+        "Page.enable",
+        serde_json::json!({}),
+    )
+    .await?;
+    id += 1;
+
+    // Step 6: Set page content with the HTML
+    cdp_send_session(
+        &mut ws,
+        id,
+        &session_id,
+        "Page.setDocumentContent",
+        serde_json::json!({ "frameId": target_id, "html": html }),
+    )
+    .await?;
+    id += 1;
+
+    // Brief pause for rendering
+    tokio::time::sleep(std::time::Duration::from_millis(500)).await;
+
+    // Step 7: Print to PDF
+    let pdf_response = cdp_send_session(
+        &mut ws,
+        id,
+        &session_id,
+        "Page.printToPDF",
+        serde_json::json!({
+            "printBackground": true,
+            "preferCSSPageSize": true,
+            "displayHeaderFooter": false,
+        }),
+    )
+    .await?;
+    id += 1;
+
+    let pdf_b64 = pdf_response
+        .get("result")
+        .and_then(|r| r.get("data"))
+        .and_then(|d| d.as_str())
+        .ok_or("No PDF data in printToPDF response")?;
+
+    let pdf_bytes = base64::engine::general_purpose::STANDARD
+        .decode(pdf_b64)
+        .map_err(|e| format!("Failed to decode PDF base64: {e}"))?;
+
+    // Step 8: Close the target
+    let _ = cdp_send(
+        &mut ws,
+        id,
+        "Target.closeTarget",
+        serde_json::json!({ "targetId": target_id }),
+    )
+    .await;
+
+    let _ = ws.close(None).await;
+
+    if pdf_bytes.is_empty() {
+        return Err("Chrome produced an empty PDF".to_string());
+    }
+
+    tracing::info!(
+        size_kb = pdf_bytes.len() / 1024,
+        "PDF report generated via CDP"
+    );
+    Ok(pdf_bytes)
+}
+
+/// Read WebSocket messages until we get a response matching the given id.
+async fn read_until_result(ws: &mut WsStream, id: u64) -> Result<serde_json::Value, String> {
+    use futures_util::StreamExt;
+
+    let deadline = tokio::time::Instant::now() + std::time::Duration::from_secs(30);
+    loop {
+        let msg = tokio::time::timeout_at(deadline, ws.next())
+            .await
+            .map_err(|_| format!("Timeout waiting for CDP response id={id}"))?
+            .ok_or_else(|| "WebSocket closed unexpectedly".to_string())?
+            .map_err(|e| format!("WebSocket read error: {e}"))?;
+
+        if let Message::Text(text) = msg {
+            if let Ok(val) = serde_json::from_str::<serde_json::Value>(&text) {
+                if val.get("id").and_then(|i| i.as_u64()) == Some(id) {
+                    if let Some(err) = val.get("error") {
+                        return Err(format!("CDP error: {err}"));
+                    }
+                    return Ok(val);
+                }
+            }
+        }
+    }
+}
+
+/// Fallback: generate PDF using a local Chrome/Chromium binary.
+async fn local_chrome_pdf(html: &str) -> Result<Vec<u8>, String> {
+    let tmp_dir = std::env::temp_dir();
+    let run_id = uuid::Uuid::new_v4().to_string();
+    let html_path = tmp_dir.join(format!("pentest-report-{run_id}.html"));
+    let pdf_path = tmp_dir.join(format!("pentest-report-{run_id}.pdf"));
+
+    std::fs::write(&html_path, html).map_err(|e| format!("Failed to write temp HTML: {e}"))?;
+
+    let chrome_bin = find_chrome_binary().ok_or_else(|| {
+        "Chrome/Chromium not found. Set CHROME_WS_URL for remote Chrome or install chromium locally."
+            .to_string()
+    })?;
+
+    tracing::info!(chrome = %chrome_bin, "Generating PDF report via headless Chrome");
+
+    let html_url = format!("file://{}", html_path.display());
+
+    let output = tokio::process::Command::new(&chrome_bin)
+        .args([
+            "--headless",
+            "--disable-gpu",
+            "--no-sandbox",
+            "--disable-software-rasterizer",
+            "--run-all-compositor-stages-before-draw",
+            "--disable-dev-shm-usage",
+            &format!("--print-to-pdf={}", pdf_path.display()),
+            "--no-pdf-header-footer",
+            &html_url,
+        ])
+        .output()
+        .await
+        .map_err(|e| format!("Failed to run Chrome: {e}"))?;
+
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        let _ = std::fs::remove_file(&html_path);
+        let _ = std::fs::remove_file(&pdf_path);
+        return Err(format!("Chrome PDF generation failed: {stderr}"));
+    }
+
+    let pdf_bytes =
+        std::fs::read(&pdf_path).map_err(|e| format!("Failed to read generated PDF: {e}"))?;
+
+    let _ = std::fs::remove_file(&html_path);
+    let _ = std::fs::remove_file(&pdf_path);
+
+    if pdf_bytes.is_empty() {
+        return Err("Chrome produced an empty PDF".to_string());
+    }
+
+    tracing::info!(size_kb = pdf_bytes.len() / 1024, "PDF report generated");
+    Ok(pdf_bytes)
+}
+
+/// Search for Chrome/Chromium binary on the system.
+fn find_chrome_binary() -> Option<String> {
+    let candidates = [
+        "google-chrome-stable",
+        "google-chrome",
+        "chromium-browser",
+        "chromium",
+    ];
+    for name in &candidates {
+        if let Ok(output) = std::process::Command::new("which").arg(name).output() {
+            if output.status.success() {
+                let path = String::from_utf8_lossy(&output.stdout).trim().to_string();
+                if !path.is_empty() {
+                    return Some(path);
+                }
+            }
+        }
+    }
+    None
+}

compliance-agent/src/pipeline/code_review.rs

@@ -0,0 +1,236 @@
+use std::path::Path;
+use std::sync::Arc;
+
+use compliance_core::models::{Finding, ScanType, Severity};
+use compliance_core::traits::ScanOutput;
+
+use crate::llm::review_prompts::REVIEW_PASSES;
+use crate::llm::LlmClient;
+use crate::pipeline::dedup;
+use crate::pipeline::git::{DiffFile, GitOps};
+
+pub struct CodeReviewScanner {
+    llm: Arc<LlmClient>,
+}
+
+impl CodeReviewScanner {
+    pub fn new(llm: Arc<LlmClient>) -> Self {
+        Self { llm }
+    }
+
+    /// Run multi-pass LLM code review on the diff between old and new commits.
+    pub async fn review_diff(
+        &self,
+        repo_path: &Path,
+        repo_id: &str,
+        old_sha: &str,
+        new_sha: &str,
+    ) -> ScanOutput {
+        let diff_files = match GitOps::get_diff_content(repo_path, old_sha, new_sha) {
+            Ok(files) => files,
+            Err(e) => {
+                tracing::warn!("Failed to extract diff for code review: {e}");
+                return ScanOutput::default();
+            }
+        };
+
+        if diff_files.is_empty() {
+            return ScanOutput::default();
+        }
+
+        let mut all_findings = Vec::new();
+
+        // Chunk diff files into groups to avoid exceeding context limits
+        let chunks = chunk_diff_files(&diff_files, 8000);
+
+        for (pass_name, system_prompt) in REVIEW_PASSES {
+            for chunk in &chunks {
+                let user_prompt = format!(
+                    "Review the following code changes:\n\n{}",
+                    chunk
+                        .iter()
+                        .map(|f| format!("--- {} ---\n{}", f.path, f.hunks))
+                        .collect::<Vec<_>>()
+                        .join("\n\n")
+                );
+
+                match self.llm.chat(system_prompt, &user_prompt, Some(0.1)).await {
+                    Ok(response) => {
+                        let parsed = parse_review_response(&response, pass_name, repo_id, chunk);
+                        all_findings.extend(parsed);
+                    }
+                    Err(e) => {
+                        tracing::warn!("Code review pass '{pass_name}' failed: {e}");
+                    }
+                }
+            }
+        }
+
+        let deduped = dedup_cross_pass(all_findings);
+
+        ScanOutput {
+            findings: deduped,
+            sbom_entries: Vec::new(),
+        }
+    }
+}
+
+/// Group diff files into chunks that fit within a token budget (rough char estimate)
+fn chunk_diff_files(files: &[DiffFile], max_chars: usize) -> Vec<Vec<&DiffFile>> {
+    let mut chunks: Vec<Vec<&DiffFile>> = Vec::new();
+    let mut current_chunk: Vec<&DiffFile> = Vec::new();
+    let mut current_size = 0;
+
+    for file in files {
+        if current_size + file.hunks.len() > max_chars && !current_chunk.is_empty() {
+            chunks.push(std::mem::take(&mut current_chunk));
+            current_size = 0;
+        }
+        current_chunk.push(file);
+        current_size += file.hunks.len();
+    }
+
+    if !current_chunk.is_empty() {
+        chunks.push(current_chunk);
+    }
+
+    chunks
+}
+
+fn parse_review_response(
+    response: &str,
+    pass_name: &str,
+    repo_id: &str,
+    chunk: &[&DiffFile],
+) -> Vec<Finding> {
+    let cleaned = response.trim();
+    let cleaned = if cleaned.starts_with("```") {
+        cleaned
+            .trim_start_matches("```json")
+            .trim_start_matches("```")
+            .trim_end_matches("```")
+            .trim()
+    } else {
+        cleaned
+    };
+
+    let issues: Vec<ReviewIssue> = match serde_json::from_str(cleaned) {
+        Ok(v) => v,
+        Err(_) => {
+            if cleaned != "[]" {
+                tracing::debug!("Failed to parse {pass_name} review response: {cleaned}");
+            }
+            return Vec::new();
+        }
+    };
+
+    issues
+        .into_iter()
+        .filter(|issue| {
+            // Verify the file exists in the diff chunk
+            chunk.iter().any(|f| f.path == issue.file)
+        })
+        .map(|issue| {
+            let severity = match issue.severity.as_str() {
+                "critical" => Severity::Critical,
+                "high" => Severity::High,
+                "medium" => Severity::Medium,
+                "low" => Severity::Low,
+                _ => Severity::Info,
+            };
+
+            let fingerprint = dedup::compute_fingerprint(&[
+                repo_id,
+                "code-review",
+                pass_name,
+                &issue.file,
+                &issue.line.to_string(),
+                &issue.title,
+            ]);
+
+            let description = if let Some(suggestion) = &issue.suggestion {
+                format!("{}\n\nSuggested fix: {}", issue.description, suggestion)
+            } else {
+                issue.description.clone()
+            };
+
+            let mut finding = Finding::new(
+                repo_id.to_string(),
+                fingerprint,
+                format!("code-review/{pass_name}"),
+                ScanType::CodeReview,
+                issue.title,
+                description,
+                severity,
+            );
+            finding.rule_id = Some(format!("review/{pass_name}"));
+            finding.file_path = Some(issue.file);
+            finding.line_number = Some(issue.line);
+            finding.cwe = issue.cwe;
+            finding.suggested_fix = issue.suggestion;
+            finding
+        })
+        .collect()
+}
+
+#[derive(serde::Deserialize)]
+struct ReviewIssue {
+    title: String,
+    description: String,
+    severity: String,
+    file: String,
+    #[serde(default)]
+    line: u32,
+    #[serde(default)]
+    cwe: Option<String>,
+    #[serde(default)]
+    suggestion: Option<String>,
+}
+
+/// Deduplicate findings across review passes.
+///
+/// Multiple passes often flag the same issue (e.g. SQL injection reported by
+/// logic, security, and convention passes). We group by file + nearby line +
+/// normalized title keywords and keep the highest-severity finding.
+fn dedup_cross_pass(findings: Vec<Finding>) -> Vec<Finding> {
+    use std::collections::HashMap;
+
+    // Build a dedup key: (file, line bucket, normalized title words)
+    fn dedup_key(f: &Finding) -> String {
+        let file = f.file_path.as_deref().unwrap_or("");
+        // Group lines within 3 of each other
+        let line_bucket = f.line_number.unwrap_or(0) / 4;
+        // Normalize: lowercase, keep only alphanumeric, sort words for order-independence
+        let title_lower = f.title.to_lowercase();
+        let mut words: Vec<&str> = title_lower
+            .split(|c: char| !c.is_alphanumeric())
+            .filter(|w| w.len() > 2)
+            .collect();
+        words.sort();
+        format!("{file}:{line_bucket}:{}", words.join(","))
+    }
+
+    let mut groups: HashMap<String, Finding> = HashMap::new();
+
+    for finding in findings {
+        let key = dedup_key(&finding);
+        groups
+            .entry(key)
+            .and_modify(|existing| {
+                // Keep the higher severity; on tie, keep the one with more detail
+                if finding.severity > existing.severity
+                    || (finding.severity == existing.severity
+                        && finding.description.len() > existing.description.len())
+                {
+                    *existing = finding.clone();
+                }
+                // Merge CWE if the existing one is missing it
+                if existing.cwe.is_none() {
+                    existing.cwe = finding.cwe.clone();
+                }
+            })
+            .or_insert(finding);
+    }
+
+    groups.into_values().collect()
+}

compliance-agent/src/pipeline/cve.rs

@@ -21,11 +21,13 @@ impl CveScanner {
         }
     }
 
+    #[tracing::instrument(skip_all)]
     pub async fn scan_dependencies(
         &self,
         repo_id: &str,
         entries: &mut [SbomEntry],
     ) -> Result<Vec<CveAlert>, CoreError> {
+        tracing::info!("scanning {} SBOM entries for known CVEs", entries.len());
         let mut alerts = Vec::new();
 
         // Batch query OSV.dev
@@ -64,6 +66,8 @@ impl CveScanner {
     }
 
     async fn query_osv_batch(&self, entries: &[SbomEntry]) -> Result<Vec<Vec<OsvVuln>>, CoreError> {
+        const OSV_BATCH_SIZE: usize = 500;
+
         let queries: Vec<_> = entries
             .iter()
             .filter_map(|e| {
@@ -79,32 +83,37 @@ impl CveScanner {
             return Ok(Vec::new());
         }
 
-        let body = serde_json::json!({ "queries": queries });
+        let mut all_vulns: Vec<Vec<OsvVuln>> = Vec::with_capacity(queries.len());
 
-        let resp = self
+        for chunk in queries.chunks(OSV_BATCH_SIZE) {
-            .http
+            let body = serde_json::json!({ "queries": chunk });
-            .post("https://api.osv.dev/v1/querybatch")
-            .json(&body)
-            .send()
-            .await
-            .map_err(|e| CoreError::Http(format!("OSV.dev request failed: {e}")))?;
 
-        if !resp.status().is_success() {
+            let resp = self
-            let status = resp.status();
+                .http
-            let body = resp.text().await.unwrap_or_default();
+                .post("https://api.osv.dev/v1/querybatch")
-            tracing::warn!("OSV.dev returned {status}: {body}");
+                .json(&body)
-            return Ok(Vec::new());
+                .send()
-        }
+                .await
+                .map_err(|e| {
+                    tracing::warn!("OSV.dev API call failed: {e}");
+                    CoreError::Http(format!("OSV.dev request failed: {e}"))
+                })?;
 
-        let result: OsvBatchResponse = resp
+            if !resp.status().is_success() {
-            .json()
+                let status = resp.status();
-            .await
+                let body = resp.text().await.unwrap_or_default();
-            .map_err(|e| CoreError::Http(format!("Failed to parse OSV.dev response: {e}")))?;
+                tracing::warn!("OSV.dev returned {status}: {body}");
+                // Push empty results for this chunk so indices stay aligned
+                all_vulns.extend(std::iter::repeat_with(Vec::new).take(chunk.len()));
+                continue;
+            }
 
-        let vulns = result
+            let result: OsvBatchResponse = resp.json().await.map_err(|e| {
-            .results
+                tracing::warn!("failed to parse OSV.dev response: {e}");
-            .into_iter()
+                CoreError::Http(format!("Failed to parse OSV.dev response: {e}"))
-            .map(|r| {
+            })?;
+
+            let chunk_vulns = result.results.into_iter().map(|r| {
                 r.vulns
                     .unwrap_or_default()
                     .into_iter()
@@ -116,10 +125,12 @@ impl CveScanner {
                         }),
                     })
                     .collect()
-            })
+            });
-            .collect();
 
-        Ok(vulns)
+            all_vulns.extend(chunk_vulns);
+        }
+
+        Ok(all_vulns)
     }
 
     async fn query_nvd(&self, cve_id: &str) -> Result<Option<f64>, CoreError> {

compliance-agent/src/pipeline/dedup.rs

@@ -8,3 +8,51 @@ pub fn compute_fingerprint(parts: &[&str]) -> String {
     }
     hex::encode(hasher.finalize())
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn fingerprint_is_deterministic() {
+        let a = compute_fingerprint(&["repo1", "rule-x", "src/main.rs", "42"]);
+        let b = compute_fingerprint(&["repo1", "rule-x", "src/main.rs", "42"]);
+        assert_eq!(a, b);
+    }
+
+    #[test]
+    fn fingerprint_changes_with_different_input() {
+        let a = compute_fingerprint(&["repo1", "rule-x", "src/main.rs", "42"]);
+        let b = compute_fingerprint(&["repo1", "rule-x", "src/main.rs", "43"]);
+        assert_ne!(a, b);
+    }
+
+    #[test]
+    fn fingerprint_is_valid_hex_sha256() {
+        let fp = compute_fingerprint(&["hello"]);
+        assert_eq!(fp.len(), 64, "SHA-256 hex should be 64 chars");
+        assert!(fp.chars().all(|c| c.is_ascii_hexdigit()));
+    }
+
+    #[test]
+    fn fingerprint_empty_parts() {
+        let fp = compute_fingerprint(&[]);
+        // Should still produce a valid hash (of empty input)
+        assert_eq!(fp.len(), 64);
+    }
+
+    #[test]
+    fn fingerprint_order_matters() {
+        let a = compute_fingerprint(&["a", "b"]);
+        let b = compute_fingerprint(&["b", "a"]);
+        assert_ne!(a, b);
+    }
+
+    #[test]
+    fn fingerprint_separator_prevents_collision() {
+        // "ab" + "c" vs "a" + "bc" should differ because of the "|" separator
+        let a = compute_fingerprint(&["ab", "c"]);
+        let b = compute_fingerprint(&["a", "bc"]);
+        assert_ne!(a, b);
+    }
+}

compliance-agent/src/pipeline/git.rs

@@ -1,38 +1,113 @@
 use std::path::{Path, PathBuf};
 
-use git2::{FetchOptions, Repository};
+use git2::{Cred, FetchOptions, RemoteCallbacks, Repository};
 
 use crate::error::AgentError;
 
+/// Credentials for accessing a private repository
+#[derive(Debug, Clone, Default)]
+pub struct RepoCredentials {
+    /// Path to the SSH private key (for SSH URLs)
+    pub ssh_key_path: Option<String>,
+    /// Auth token / password (for HTTPS URLs)
+    pub auth_token: Option<String>,
+    /// Username for HTTPS auth (defaults to "x-access-token")
+    pub auth_username: Option<String>,
+}
+
+impl RepoCredentials {
+    pub(crate) fn make_callbacks(&self) -> RemoteCallbacks<'_> {
+        let mut callbacks = RemoteCallbacks::new();
+        let ssh_key = self.ssh_key_path.clone();
+        let token = self.auth_token.clone();
+        let username = self.auth_username.clone();
+
+        callbacks.credentials(move |_url, username_from_url, allowed_types| {
+            // SSH key authentication
+            if allowed_types.contains(git2::CredentialType::SSH_KEY) {
+                if let Some(ref key_path) = ssh_key {
+                    let key = Path::new(key_path);
+                    if key.exists() {
+                        let user = username_from_url.unwrap_or("git");
+                        return Cred::ssh_key(user, None, key, None);
+                    }
+                }
+            }
+
+            // HTTPS userpass authentication
+            if allowed_types.contains(git2::CredentialType::USER_PASS_PLAINTEXT) {
+                if let Some(ref tok) = token {
+                    let user = username.as_deref().unwrap_or("x-access-token");
+                    return Cred::userpass_plaintext(user, tok);
+                }
+            }
+
+            Cred::default()
+        });
+
+        callbacks
+    }
+
+    fn fetch_options(&self) -> FetchOptions<'_> {
+        let mut fetch_opts = FetchOptions::new();
+        if self.has_credentials() {
+            fetch_opts.remote_callbacks(self.make_callbacks());
+        }
+        fetch_opts
+    }
+
+    fn has_credentials(&self) -> bool {
+        self.ssh_key_path
+            .as_ref()
+            .map(|p| Path::new(p).exists())
+            .unwrap_or(false)
+            || self.auth_token.is_some()
+    }
+}
+
 pub struct GitOps {
     base_path: PathBuf,
+    credentials: RepoCredentials,
 }
 
 impl GitOps {
-    pub fn new(base_path: &str) -> Self {
+    pub fn new(base_path: &str, credentials: RepoCredentials) -> Self {
         Self {
             base_path: PathBuf::from(base_path),
+            credentials,
         }
     }
 
+    #[tracing::instrument(skip_all, fields(repo_name = %repo_name))]
     pub fn clone_or_fetch(&self, git_url: &str, repo_name: &str) -> Result<PathBuf, AgentError> {
         let repo_path = self.base_path.join(repo_name);
 
         if repo_path.exists() {
+            tracing::info!("fetching updates for existing repo");
             self.fetch(&repo_path)?;
         } else {
             std::fs::create_dir_all(&repo_path)?;
-            Repository::clone(git_url, &repo_path)?;
+            self.clone_repo(git_url, &repo_path)?;
             tracing::info!("Cloned {git_url} to {}", repo_path.display());
         }
 
         Ok(repo_path)
     }
 
+    #[tracing::instrument(skip_all)]
+    fn clone_repo(&self, git_url: &str, repo_path: &Path) -> Result<(), AgentError> {
+        tracing::info!("cloning repo from {}", git_url);
+        let mut builder = git2::build::RepoBuilder::new();
+        let fetch_opts = self.credentials.fetch_options();
+        builder.fetch_options(fetch_opts);
+        builder.clone(git_url, repo_path)?;
+        Ok(())
+    }
+
     fn fetch(&self, repo_path: &Path) -> Result<(), AgentError> {
         let repo = Repository::open(repo_path)?;
         let mut remote = repo.find_remote("origin")?;
-        let mut fetch_opts = FetchOptions::new();
+        let mut fetch_opts = self.credentials.fetch_options();
         remote.fetch(&[] as &[&str], Some(&mut fetch_opts), None)?;
 
         // Fast-forward to origin/HEAD
@@ -48,6 +123,27 @@ impl GitOps {
         Ok(())
     }
 
+    /// Test that we can access a remote repository (used during add validation)
+    pub fn test_access(git_url: &str, credentials: &RepoCredentials) -> Result<(), AgentError> {
+        let mut remote = git2::Remote::create_detached(git_url)?;
+        let callbacks = credentials.make_callbacks();
+        remote.connect_auth(git2::Direction::Fetch, Some(callbacks), None)?;
+        remote.disconnect()?;
+        Ok(())
+    }
+
+    /// Build credentials from agent config + per-repo overrides
+    pub fn make_repo_credentials(
+        config: &compliance_core::AgentConfig,
+        repo: &compliance_core::models::TrackedRepository,
+    ) -> RepoCredentials {
+        RepoCredentials {
+            ssh_key_path: Some(config.ssh_key_path.clone()),
+            auth_token: repo.auth_token.clone(),
+            auth_username: repo.auth_username.clone(),
+        }
+    }
+
     pub fn get_head_sha(repo_path: &Path) -> Result<String, AgentError> {
         let repo = Repository::open(repo_path)?;
         let head = repo.head()?;
@@ -63,6 +159,62 @@ impl GitOps {
         }
     }
 
+    /// Extract structured diff content between two commits
+    pub fn get_diff_content(
+        repo_path: &Path,
+        old_sha: &str,
+        new_sha: &str,
+    ) -> Result<Vec<DiffFile>, AgentError> {
+        let repo = Repository::open(repo_path)?;
+        let old_commit = repo.find_commit(git2::Oid::from_str(old_sha)?)?;
+        let new_commit = repo.find_commit(git2::Oid::from_str(new_sha)?)?;
+
+        let old_tree = old_commit.tree()?;
+        let new_tree = new_commit.tree()?;
+
+        let diff = repo.diff_tree_to_tree(Some(&old_tree), Some(&new_tree), None)?;
+
+        let mut diff_files: Vec<DiffFile> = Vec::new();
+
+        diff.print(git2::DiffFormat::Patch, |delta, _hunk, line| {
+            let file_path = delta
+                .new_file()
+                .path()
+                .map(|p| p.to_string_lossy().to_string())
+                .unwrap_or_default();
+
+            // Find or create the DiffFile entry
+            let idx = if let Some(pos) = diff_files.iter().position(|f| f.path == file_path) {
+                pos
+            } else {
+                diff_files.push(DiffFile {
+                    path: file_path,
+                    hunks: String::new(),
+                });
+                diff_files.len() - 1
+            };
+            let diff_file = &mut diff_files[idx];
+
+            let prefix = match line.origin() {
+                '+' => "+",
+                '-' => "-",
+                ' ' => " ",
+                _ => "",
+            };
+
+            let content = std::str::from_utf8(line.content()).unwrap_or("");
+            diff_file.hunks.push_str(prefix);
+            diff_file.hunks.push_str(content);
+
+            true
+        })?;
+
+        // Filter out binary files and very large diffs
+        diff_files.retain(|f| !f.hunks.is_empty() && f.hunks.len() < 50_000);
+
+        Ok(diff_files)
+    }
+
     #[allow(dead_code)]
     pub fn get_changed_files(
         repo_path: &Path,
@@ -94,3 +246,10 @@ impl GitOps {
         Ok(files)
     }
 }
+
+/// A file changed between two commits with its diff content
+#[derive(Debug, Clone)]
+pub struct DiffFile {
+    pub path: String,
+    pub hunks: String,
+}

compliance-agent/src/pipeline/gitleaks.rs

@@ -0,0 +1,238 @@
+use std::path::Path;
+
+use compliance_core::models::{Finding, ScanType, Severity};
+use compliance_core::traits::{ScanOutput, Scanner};
+use compliance_core::CoreError;
+
+use crate::pipeline::dedup;
+
+pub struct GitleaksScanner;
+
+impl Scanner for GitleaksScanner {
+    fn name(&self) -> &str {
+        "gitleaks"
+    }
+
+    fn scan_type(&self) -> ScanType {
+        ScanType::SecretDetection
+    }
+
+    #[tracing::instrument(skip_all)]
+    async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
+        let output = tokio::process::Command::new("gitleaks")
+            .args([
+                "detect",
+                "--source",
+                ".",
+                "--report-format",
+                "json",
+                "--report-path",
+                "/dev/stdout",
+                "--no-banner",
+                "--exit-code",
+                "0",
+            ])
+            .current_dir(repo_path)
+            .output()
+            .await
+            .map_err(|e| CoreError::Scanner {
+                scanner: "gitleaks".to_string(),
+                source: Box::new(e),
+            })?;
+
+        if output.stdout.is_empty() {
+            return Ok(ScanOutput::default());
+        }
+
+        let results: Vec<GitleaksResult> =
+            serde_json::from_slice(&output.stdout).unwrap_or_default();
+
+        let findings = results
+            .into_iter()
+            .filter(|r| !is_allowlisted(&r.file))
+            .map(|r| {
+                let severity = match r.rule_id.as_str() {
+                    s if s.contains("private-key") => Severity::Critical,
+                    s if s.contains("token") || s.contains("password") || s.contains("secret") => {
+                        Severity::High
+                    }
+                    s if s.contains("api-key") => Severity::High,
+                    _ => Severity::Medium,
+                };
+
+                let fingerprint = dedup::compute_fingerprint(&[
+                    repo_id,
+                    &r.rule_id,
+                    &r.file,
+                    &r.start_line.to_string(),
+                ]);
+
+                let title = format!("Secret detected: {}", r.description);
+                let description = format!(
+                    "Potential secret ({}) found in {}:{}. Match: {}",
+                    r.rule_id,
+                    r.file,
+                    r.start_line,
+                    r.r#match.chars().take(80).collect::<String>(),
+                );
+
+                let mut finding = Finding::new(
+                    repo_id.to_string(),
+                    fingerprint,
+                    "gitleaks".to_string(),
+                    ScanType::SecretDetection,
+                    title,
+                    description,
+                    severity,
+                );
+                finding.rule_id = Some(r.rule_id);
+                finding.file_path = Some(r.file);
+                finding.line_number = Some(r.start_line);
+                finding.code_snippet = Some(r.r#match);
+                finding
+            })
+            .collect();
+
+        Ok(ScanOutput {
+            findings,
+            sbom_entries: Vec::new(),
+        })
+    }
+}
+
+/// Skip files that commonly contain example/placeholder secrets
+fn is_allowlisted(file_path: &str) -> bool {
+    let lower = file_path.to_lowercase();
+    lower.ends_with(".env.example")
+        || lower.ends_with(".env.sample")
+        || lower.ends_with(".env.template")
+        || lower.contains("/test/")
+        || lower.contains("/tests/")
+        || lower.contains("/fixtures/")
+        || lower.contains("/testdata/")
+        || lower.contains("mock")
+        || lower.ends_with("_test.go")
+        || lower.ends_with(".test.ts")
+        || lower.ends_with(".test.js")
+        || lower.ends_with(".spec.ts")
+        || lower.ends_with(".spec.js")
+}
+
+#[derive(serde::Deserialize)]
+#[serde(rename_all = "PascalCase")]
+struct GitleaksResult {
+    description: String,
+    #[serde(rename = "RuleID")]
+    rule_id: String,
+    file: String,
+    start_line: u32,
+    #[serde(rename = "Match")]
+    r#match: String,
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    // --- is_allowlisted tests ---
+
+    #[test]
+    fn allowlisted_env_example_files() {
+        assert!(is_allowlisted(".env.example"));
+        assert!(is_allowlisted("config/.env.sample"));
+        assert!(is_allowlisted("deploy/.ENV.TEMPLATE"));
+    }
+
+    #[test]
+    fn allowlisted_test_directories() {
+        assert!(is_allowlisted("src/test/config.json"));
+        assert!(is_allowlisted("src/tests/fixtures.rs"));
+        assert!(is_allowlisted("data/fixtures/secret.txt"));
+        assert!(is_allowlisted("pkg/testdata/key.pem"));
+    }
+
+    #[test]
+    fn allowlisted_mock_files() {
+        assert!(is_allowlisted("src/mock_service.py"));
+        assert!(is_allowlisted("lib/MockAuth.java"));
+    }
+
+    #[test]
+    fn allowlisted_test_suffixes() {
+        assert!(is_allowlisted("auth_test.go"));
+        assert!(is_allowlisted("auth.test.ts"));
+        assert!(is_allowlisted("auth.test.js"));
+        assert!(is_allowlisted("auth.spec.ts"));
+        assert!(is_allowlisted("auth.spec.js"));
+    }
+
+    #[test]
+    fn not_allowlisted_regular_files() {
+        assert!(!is_allowlisted("src/main.rs"));
+        assert!(!is_allowlisted("config/.env"));
+        assert!(!is_allowlisted("lib/auth.ts"));
+        assert!(!is_allowlisted("deploy/secrets.yaml"));
+    }
+
+    #[test]
+    fn not_allowlisted_partial_matches() {
+        // "test" as substring in a non-directory context should not match
+        assert!(!is_allowlisted("src/attestation.rs"));
+        assert!(!is_allowlisted("src/contest/data.json"));
+    }
+
+    // --- GitleaksResult deserialization tests ---
+
+    #[test]
+    fn deserialize_gitleaks_result() {
+        let json = r#"{
+            "Description": "AWS Access Key",
+            "RuleID": "aws-access-key",
+            "File": "src/config.rs",
+            "StartLine": 10,
+            "Match": "AKIAIOSFODNN7EXAMPLE"
+        }"#;
+        let result: GitleaksResult = serde_json::from_str(json).unwrap();
+        assert_eq!(result.description, "AWS Access Key");
+        assert_eq!(result.rule_id, "aws-access-key");
+        assert_eq!(result.file, "src/config.rs");
+        assert_eq!(result.start_line, 10);
+        assert_eq!(result.r#match, "AKIAIOSFODNN7EXAMPLE");
+    }
+
+    #[test]
+    fn deserialize_gitleaks_result_array() {
+        let json = r#"[
+            {
+                "Description": "Generic Secret",
+                "RuleID": "generic-secret",
+                "File": "app.py",
+                "StartLine": 5,
+                "Match": "password=hunter2"
+            }
+        ]"#;
+        let results: Vec<GitleaksResult> = serde_json::from_str(json).unwrap();
+        assert_eq!(results.len(), 1);
+        assert_eq!(results[0].rule_id, "generic-secret");
+    }
+
+    #[test]
+    fn severity_mapping_private_key() {
+        // Verify the severity logic from the scan method
+        let rule_id = "some-private-key-rule";
+        assert!(rule_id.contains("private-key"));
+    }
+
+    #[test]
+    fn severity_mapping_token_password_secret() {
+        for keyword in &["token", "password", "secret"] {
+            let rule_id = format!("some-{}-rule", keyword);
+            assert!(
+                rule_id.contains("token")
+                    || rule_id.contains("password")
+                    || rule_id.contains("secret"),
+                "Expected '{rule_id}' to match token/password/secret"
+            );
+        }
+    }
+}

compliance-agent/src/pipeline/graph_build.rs

@@ -0,0 +1,106 @@
+use compliance_core::models::Finding;
+
+use super::orchestrator::{GraphContext, PipelineOrchestrator};
+use crate::error::AgentError;
+
+impl PipelineOrchestrator {
+    /// Build the code knowledge graph for a repo and compute impact analyses
+    pub(super) async fn build_code_graph(
+        &self,
+        repo_path: &std::path::Path,
+        repo_id: &str,
+        findings: &[Finding],
+    ) -> Result<GraphContext, AgentError> {
+        let graph_build_id = uuid::Uuid::new_v4().to_string();
+        let engine = compliance_graph::GraphEngine::new(50_000);
+
+        let (mut code_graph, build_run) =
+            engine
+                .build_graph(repo_path, repo_id, &graph_build_id)
+                .map_err(|e| AgentError::Other(format!("Graph build error: {e}")))?;
+
+        // Apply community detection
+        compliance_graph::graph::community::apply_communities(&mut code_graph);
+
+        // Store graph in MongoDB
+        let store = compliance_graph::graph::persistence::GraphStore::new(self.db.inner());
+        store
+            .delete_repo_graph(repo_id)
+            .await
+            .map_err(|e| AgentError::Other(format!("Graph cleanup error: {e}")))?;
+        store
+            .store_graph(&build_run, &code_graph.nodes, &code_graph.edges)
+            .await
+            .map_err(|e| AgentError::Other(format!("Graph store error: {e}")))?;
+
+        // Compute impact analysis for each finding
+        let analyzer = compliance_graph::GraphEngine::impact_analyzer(&code_graph);
+        let mut impacts = Vec::new();
+
+        for finding in findings {
+            if let Some(file_path) = &finding.file_path {
+                let impact = analyzer.analyze(
+                    repo_id,
+                    &finding.fingerprint,
+                    &graph_build_id,
+                    file_path,
+                    finding.line_number,
+                );
+                store
+                    .store_impact(&impact)
+                    .await
+                    .map_err(|e| AgentError::Other(format!("Impact store error: {e}")))?;
+                impacts.push(impact);
+            }
+        }
+
+        Ok(GraphContext {
+            node_count: build_run.node_count,
+            edge_count: build_run.edge_count,
+            community_count: build_run.community_count,
+            impacts,
+        })
+    }
+
+    /// Trigger DAST scan if a target is configured for this repo
+    pub(super) async fn maybe_trigger_dast(&self, repo_id: &str, scan_run_id: &str) {
+        use futures_util::TryStreamExt;
+
+        let filter = mongodb::bson::doc! { "repo_id": repo_id };
+        let targets: Vec<compliance_core::models::DastTarget> =
+            match self.db.dast_targets().find(filter).await {
+                Ok(cursor) => cursor.try_collect().await.unwrap_or_default(),
+                Err(_) => return,
+            };
+
+        if targets.is_empty() {
+            tracing::info!("[{repo_id}] No DAST targets configured, skipping");
+            return;
+        }
+
+        for target in targets {
+            let db = self.db.clone();
+            let scan_run_id = scan_run_id.to_string();
+            tokio::spawn(async move {
+                let orchestrator = compliance_dast::DastOrchestrator::new(100);
+                match orchestrator.run_scan(&target, Vec::new()).await {
+                    Ok((mut scan_run, findings)) => {
+                        scan_run.sast_scan_run_id = Some(scan_run_id);
+                        if let Err(e) = db.dast_scan_runs().insert_one(&scan_run).await {
+                            tracing::error!("Failed to store DAST scan run: {e}");
+                        }
+                        for finding in &findings {
+                            if let Err(e) = db.dast_findings().insert_one(finding).await {
+                                tracing::error!("Failed to store DAST finding: {e}");
+                            }
+                        }
+                        tracing::info!("DAST scan complete: {} findings", findings.len());
+                    }
+                    Err(e) => {
+                        tracing::error!("DAST scan failed: {e}");
+                    }
+                }
+            });
+        }
+    }
+}

compliance-agent/src/pipeline/issue_creation.rs

@@ -0,0 +1,259 @@
+use mongodb::bson::doc;
+
+use compliance_core::models::*;
+
+use super::orchestrator::{extract_base_url, PipelineOrchestrator};
+use super::tracker_dispatch::TrackerDispatch;
+use crate::error::AgentError;
+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: &TrackedRepository) -> Option<TrackerDispatch> {
+        let tracker_type = repo.tracker_type.as_ref()?;
+        // Per-repo token takes precedence, fall back to global config
+        match tracker_type {
+            TrackerType::GitHub => {
+                let token = repo.tracker_token.clone().or_else(|| {
+                    self.config.github_token.as_ref().map(|t| {
+                        use secrecy::ExposeSecret;
+                        t.expose_secret().to_string()
+                    })
+                })?;
+                let secret = secrecy::SecretString::from(token);
+                match trackers::github::GitHubTracker::new(&secret) {
+                    Ok(t) => Some(TrackerDispatch::GitHub(t)),
+                    Err(e) => {
+                        tracing::warn!("Failed to build GitHub tracker: {e}");
+                        None
+                    }
+                }
+            }
+            TrackerType::GitLab => {
+                let base_url = self
+                    .config
+                    .gitlab_url
+                    .clone()
+                    .unwrap_or_else(|| "https://gitlab.com".to_string());
+                let token = repo.tracker_token.clone().or_else(|| {
+                    self.config.gitlab_token.as_ref().map(|t| {
+                        use secrecy::ExposeSecret;
+                        t.expose_secret().to_string()
+                    })
+                })?;
+                let secret = secrecy::SecretString::from(token);
+                Some(TrackerDispatch::GitLab(
+                    trackers::gitlab::GitLabTracker::new(base_url, secret),
+                ))
+            }
+            TrackerType::Gitea => {
+                let token = repo.tracker_token.clone()?;
+                let base_url = extract_base_url(&repo.git_url)?;
+                let secret = secrecy::SecretString::from(token);
+                Some(TrackerDispatch::Gitea(trackers::gitea::GiteaTracker::new(
+                    base_url, secret,
+                )))
+            }
+            TrackerType::Jira => {
+                let base_url = self.config.jira_url.clone()?;
+                let email = self.config.jira_email.clone()?;
+                let project_key = self.config.jira_project_key.clone()?;
+                let token = repo.tracker_token.clone().or_else(|| {
+                    self.config.jira_api_token.as_ref().map(|t| {
+                        use secrecy::ExposeSecret;
+                        t.expose_secret().to_string()
+                    })
+                })?;
+                let secret = secrecy::SecretString::from(token);
+                Some(TrackerDispatch::Jira(trackers::jira::JiraTracker::new(
+                    base_url,
+                    email,
+                    secret,
+                    project_key,
+                )))
+            }
+        }
+    }
+
+    /// Create tracker issues for new findings (severity >= Medium).
+    /// Checks for duplicates via fingerprint search before creating.
+    #[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
+    pub(super) async fn create_tracker_issues(
+        &self,
+        repo: &TrackedRepository,
+        repo_id: &str,
+        new_findings: &[Finding],
+    ) -> Result<(), AgentError> {
+        let tracker = match self.build_tracker(repo) {
+            Some(t) => t,
+            None => {
+                tracing::info!("[{repo_id}] No issue tracker configured, skipping");
+                return Ok(());
+            }
+        };
+
+        let owner = match repo.tracker_owner.as_deref() {
+            Some(o) => o,
+            None => {
+                tracing::warn!("[{repo_id}] tracker_owner not set, skipping issue creation");
+                return Ok(());
+            }
+        };
+        let tracker_repo_name = match repo.tracker_repo.as_deref() {
+            Some(r) => r,
+            None => {
+                tracing::warn!("[{repo_id}] tracker_repo not set, skipping issue creation");
+                return Ok(());
+            }
+        };
+
+        // Only create issues for medium+ severity findings
+        let actionable: Vec<&Finding> = new_findings
+            .iter()
+            .filter(|f| {
+                matches!(
+                    f.severity,
+                    Severity::Medium | Severity::High | Severity::Critical
+                )
+            })
+            .collect();
+
+        if actionable.is_empty() {
+            tracing::info!("[{repo_id}] No medium+ findings, skipping issue creation");
+            return Ok(());
+        }
+
+        tracing::info!(
+            "[{repo_id}] Creating issues for {} findings via {}",
+            actionable.len(),
+            tracker.name()
+        );
+
+        let mut created = 0u32;
+        for finding in actionable {
+            let title = format!(
+                "[{}] {}: {}",
+                finding.severity, finding.scanner, finding.title
+            );
+
+            // Check if an issue already exists by fingerprint first, then by title
+            let mut found_existing = false;
+            for search_term in [&finding.fingerprint, &title] {
+                match tracker
+                    .find_existing_issue(owner, tracker_repo_name, search_term)
+                    .await
+                {
+                    Ok(Some(existing)) => {
+                        tracing::debug!(
+                            "[{repo_id}] Issue already exists for '{}': {}",
+                            search_term,
+                            existing.external_url
+                        );
+                        found_existing = true;
+                        break;
+                    }
+                    Ok(None) => {}
+                    Err(e) => {
+                        tracing::warn!("[{repo_id}] Failed to search for existing issue: {e}");
+                    }
+                }
+            }
+            if found_existing {
+                continue;
+            }
+            let body = format_issue_body(finding);
+            let labels = vec![
+                format!("severity:{}", finding.severity),
+                format!("scanner:{}", finding.scanner),
+                "compliance-scanner".to_string(),
+            ];
+
+            match tracker
+                .create_issue(owner, tracker_repo_name, &title, &body, &labels)
+                .await
+            {
+                Ok(mut issue) => {
+                    issue.finding_id = finding
+                        .id
+                        .as_ref()
+                        .map(|id| id.to_hex())
+                        .unwrap_or_default();
+
+                    // Update the finding with the issue URL
+                    if let Some(finding_id) = &finding.id {
+                        let _ = self
+                            .db
+                            .findings()
+                            .update_one(
+                                doc! { "_id": finding_id },
+                                doc! { "$set": { "tracker_issue_url": &issue.external_url } },
+                            )
+                            .await;
+                    }
+
+                    // Store the tracker issue record
+                    if let Err(e) = self.db.tracker_issues().insert_one(&issue).await {
+                        tracing::warn!("[{repo_id}] Failed to store tracker issue: {e}");
+                    }
+
+                    created += 1;
+                }
+                Err(e) => {
+                    tracing::warn!(
+                        "[{repo_id}] Failed to create issue for {}: {e}",
+                        finding.fingerprint
+                    );
+                }
+            }
+        }
+
+        tracing::info!("[{repo_id}] Created {created} tracker issues");
+        Ok(())
+    }
+}
+
+/// Format a finding into a markdown issue body for the tracker.
+pub(super) fn format_issue_body(finding: &Finding) -> String {
+    let mut body = String::new();
+
+    body.push_str(&format!("## {} Finding\n\n", finding.severity));
+    body.push_str(&format!("**Scanner:** {}\n", finding.scanner));
+    body.push_str(&format!("**Severity:** {}\n", finding.severity));
+
+    if let Some(rule) = &finding.rule_id {
+        body.push_str(&format!("**Rule:** {}\n", rule));
+    }
+    if let Some(cwe) = &finding.cwe {
+        body.push_str(&format!("**CWE:** {}\n", cwe));
+    }
+
+    body.push_str(&format!("\n### Description\n\n{}\n", finding.description));
+
+    if let Some(file_path) = &finding.file_path {
+        body.push_str(&format!("\n### Location\n\n**File:** `{}`", file_path));
+        if let Some(line) = finding.line_number {
+            body.push_str(&format!(" (line {})", line));
+        }
+        body.push('\n');
+    }
+
+    if let Some(snippet) = &finding.code_snippet {
+        body.push_str(&format!("\n### Code\n\n```\n{}\n```\n", snippet));
+    }
+
+    if let Some(remediation) = &finding.remediation {
+        body.push_str(&format!("\n### Remediation\n\n{}\n", remediation));
+    }
+
+    if let Some(fix) = &finding.suggested_fix {
+        body.push_str(&format!("\n### Suggested Fix\n\n```\n{}\n```\n", fix));
+    }
+
+    body.push_str(&format!(
+        "\n---\n*Fingerprint:* `{}`\n*Generated by compliance-scanner*",
+        finding.fingerprint
+    ));
+
+    body
+}

compliance-agent/src/pipeline/lint/clippy.rs

@@ -0,0 +1,251 @@
+use std::path::Path;
+
+use compliance_core::models::{Finding, ScanType, Severity};
+use compliance_core::CoreError;
+use tokio::process::Command;
+
+use crate::pipeline::dedup;
+
+use super::run_with_timeout;
+
+pub(super) async fn run_clippy(repo_path: &Path, repo_id: &str) -> Result<Vec<Finding>, CoreError> {
+    let child = Command::new("cargo")
+        .args([
+            "clippy",
+            "--message-format=json",
+            "--quiet",
+            "--",
+            "-W",
+            "clippy::all",
+        ])
+        .current_dir(repo_path)
+        .env("RUSTC_WRAPPER", "")
+        .stdout(std::process::Stdio::piped())
+        .stderr(std::process::Stdio::piped())
+        .spawn()
+        .map_err(|e| CoreError::Scanner {
+            scanner: "clippy".to_string(),
+            source: Box::new(e),
+        })?;
+
+    let output = run_with_timeout(child, "clippy").await?;
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    let mut findings = Vec::new();
+
+    for line in stdout.lines() {
+        let msg: serde_json::Value = match serde_json::from_str(line) {
+            Ok(v) => v,
+            Err(_) => continue,
+        };
+
+        if msg.get("reason").and_then(|v| v.as_str()) != Some("compiler-message") {
+            continue;
+        }
+
+        let message = match msg.get("message") {
+            Some(m) => m,
+            None => continue,
+        };
+
+        let level = message.get("level").and_then(|v| v.as_str()).unwrap_or("");
+
+        if level != "warning" && level != "error" {
+            continue;
+        }
+
+        let text = message
+            .get("message")
+            .and_then(|v| v.as_str())
+            .unwrap_or("")
+            .to_string();
+
+        let code = message
+            .get("code")
+            .and_then(|v| v.get("code"))
+            .and_then(|v| v.as_str())
+            .unwrap_or("")
+            .to_string();
+
+        if text.starts_with("aborting due to") || code.is_empty() {
+            continue;
+        }
+
+        let (file_path, line_number) = extract_primary_span(message);
+
+        let severity = if level == "error" {
+            Severity::High
+        } else {
+            Severity::Low
+        };
+
+        let fingerprint = dedup::compute_fingerprint(&[
+            repo_id,
+            "clippy",
+            &code,
+            &file_path,
+            &line_number.to_string(),
+        ]);
+
+        let mut finding = Finding::new(
+            repo_id.to_string(),
+            fingerprint,
+            "clippy".to_string(),
+            ScanType::Lint,
+            format!("[clippy] {text}"),
+            text,
+            severity,
+        );
+        finding.rule_id = Some(code);
+        if !file_path.is_empty() {
+            finding.file_path = Some(file_path);
+        }
+        if line_number > 0 {
+            finding.line_number = Some(line_number);
+        }
+        findings.push(finding);
+    }
+
+    Ok(findings)
+}
+
+fn extract_primary_span(message: &serde_json::Value) -> (String, u32) {
+    let spans = match message.get("spans").and_then(|v| v.as_array()) {
+        Some(s) => s,
+        None => return (String::new(), 0),
+    };
+
+    for span in spans {
+        if span.get("is_primary").and_then(|v| v.as_bool()) == Some(true) {
+            let file = span
+                .get("file_name")
+                .and_then(|v| v.as_str())
+                .unwrap_or("")
+                .to_string();
+            let line = span.get("line_start").and_then(|v| v.as_u64()).unwrap_or(0) as u32;
+            return (file, line);
+        }
+    }
+
+    (String::new(), 0)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn extract_primary_span_with_primary() {
+        let msg = serde_json::json!({
+            "spans": [
+                {
+                    "file_name": "src/lib.rs",
+                    "line_start": 42,
+                    "is_primary": true
+                }
+            ]
+        });
+        let (file, line) = extract_primary_span(&msg);
+        assert_eq!(file, "src/lib.rs");
+        assert_eq!(line, 42);
+    }
+
+    #[test]
+    fn extract_primary_span_no_primary() {
+        let msg = serde_json::json!({
+            "spans": [
+                {
+                    "file_name": "src/lib.rs",
+                    "line_start": 42,
+                    "is_primary": false
+                }
+            ]
+        });
+        let (file, line) = extract_primary_span(&msg);
+        assert_eq!(file, "");
+        assert_eq!(line, 0);
+    }
+
+    #[test]
+    fn extract_primary_span_multiple_spans() {
+        let msg = serde_json::json!({
+            "spans": [
+                {
+                    "file_name": "src/other.rs",
+                    "line_start": 10,
+                    "is_primary": false
+                },
+                {
+                    "file_name": "src/main.rs",
+                    "line_start": 99,
+                    "is_primary": true
+                }
+            ]
+        });
+        let (file, line) = extract_primary_span(&msg);
+        assert_eq!(file, "src/main.rs");
+        assert_eq!(line, 99);
+    }
+
+    #[test]
+    fn extract_primary_span_no_spans() {
+        let msg = serde_json::json!({});
+        let (file, line) = extract_primary_span(&msg);
+        assert_eq!(file, "");
+        assert_eq!(line, 0);
+    }
+
+    #[test]
+    fn extract_primary_span_empty_spans() {
+        let msg = serde_json::json!({ "spans": [] });
+        let (file, line) = extract_primary_span(&msg);
+        assert_eq!(file, "");
+        assert_eq!(line, 0);
+    }
+
+    #[test]
+    fn parse_clippy_compiler_message_line() {
+        let line = r#"{"reason":"compiler-message","message":{"level":"warning","message":"unused variable","code":{"code":"unused_variables"},"spans":[{"file_name":"src/main.rs","line_start":5,"is_primary":true}]}}"#;
+        let msg: serde_json::Value = serde_json::from_str(line).unwrap();
+
+        assert_eq!(
+            msg.get("reason").and_then(|v| v.as_str()),
+            Some("compiler-message")
+        );
+        let message = msg.get("message").unwrap();
+        assert_eq!(
+            message.get("level").and_then(|v| v.as_str()),
+            Some("warning")
+        );
+        assert_eq!(
+            message.get("message").and_then(|v| v.as_str()),
+            Some("unused variable")
+        );
+        assert_eq!(
+            message
+                .get("code")
+                .and_then(|v| v.get("code"))
+                .and_then(|v| v.as_str()),
+            Some("unused_variables")
+        );
+
+        let (file, line_num) = extract_primary_span(message);
+        assert_eq!(file, "src/main.rs");
+        assert_eq!(line_num, 5);
+    }
+
+    #[test]
+    fn skip_non_compiler_message() {
+        let line = r#"{"reason":"build-script-executed","package_id":"foo 0.1.0"}"#;
+        let msg: serde_json::Value = serde_json::from_str(line).unwrap();
+        assert_ne!(
+            msg.get("reason").and_then(|v| v.as_str()),
+            Some("compiler-message")
+        );
+    }
+
+    #[test]
+    fn skip_aborting_message() {
+        let text = "aborting due to 3 previous errors";
+        assert!(text.starts_with("aborting due to"));
+    }
+}

compliance-agent/src/pipeline/lint/eslint.rs

@@ -0,0 +1,183 @@
+use std::path::Path;
+
+use compliance_core::models::{Finding, ScanType, Severity};
+use compliance_core::CoreError;
+use tokio::process::Command;
+
+use crate::pipeline::dedup;
+
+use super::run_with_timeout;
+
+pub(super) async fn run_eslint(repo_path: &Path, repo_id: &str) -> Result<Vec<Finding>, CoreError> {
+    // Use the project-local eslint binary directly, not npx (which can hang downloading)
+    let eslint_bin = repo_path.join("node_modules/.bin/eslint");
+    let child = Command::new(eslint_bin)
+        .args([".", "--format", "json", "--no-error-on-unmatched-pattern"])
+        .current_dir(repo_path)
+        .stdout(std::process::Stdio::piped())
+        .stderr(std::process::Stdio::piped())
+        .spawn()
+        .map_err(|e| CoreError::Scanner {
+            scanner: "eslint".to_string(),
+            source: Box::new(e),
+        })?;
+
+    let output = run_with_timeout(child, "eslint").await?;
+
+    if output.stdout.is_empty() {
+        return Ok(Vec::new());
+    }
+
+    let results: Vec<EslintFileResult> = serde_json::from_slice(&output.stdout).unwrap_or_default();
+
+    let mut findings = Vec::new();
+    for file_result in results {
+        for msg in file_result.messages {
+            let severity = match msg.severity {
+                2 => Severity::Medium,
+                _ => Severity::Low,
+            };
+
+            let rule_id = msg.rule_id.unwrap_or_default();
+            let fingerprint = dedup::compute_fingerprint(&[
+                repo_id,
+                "eslint",
+                &rule_id,
+                &file_result.file_path,
+                &msg.line.to_string(),
+            ]);
+
+            let mut finding = Finding::new(
+                repo_id.to_string(),
+                fingerprint,
+                "eslint".to_string(),
+                ScanType::Lint,
+                format!("[eslint] {}", msg.message),
+                msg.message,
+                severity,
+            );
+            finding.rule_id = Some(rule_id);
+            finding.file_path = Some(file_result.file_path.clone());
+            finding.line_number = Some(msg.line);
+            findings.push(finding);
+        }
+    }
+
+    Ok(findings)
+}
+
+#[derive(serde::Deserialize)]
+struct EslintFileResult {
+    #[serde(rename = "filePath")]
+    file_path: String,
+    messages: Vec<EslintMessage>,
+}
+
+#[derive(serde::Deserialize)]
+struct EslintMessage {
+    #[serde(rename = "ruleId")]
+    rule_id: Option<String>,
+    severity: u8,
+    message: String,
+    line: u32,
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn deserialize_eslint_output() {
+        let json = r#"[
+            {
+                "filePath": "/home/user/project/src/app.js",
+                "messages": [
+                    {
+                        "ruleId": "no-unused-vars",
+                        "severity": 2,
+                        "message": "'x' is defined but never used.",
+                        "line": 10
+                    },
+                    {
+                        "ruleId": "semi",
+                        "severity": 1,
+                        "message": "Missing semicolon.",
+                        "line": 15
+                    }
+                ]
+            }
+        ]"#;
+        let results: Vec<EslintFileResult> = serde_json::from_str(json).unwrap();
+        assert_eq!(results.len(), 1);
+        assert_eq!(results[0].file_path, "/home/user/project/src/app.js");
+        assert_eq!(results[0].messages.len(), 2);
+
+        assert_eq!(
+            results[0].messages[0].rule_id,
+            Some("no-unused-vars".to_string())
+        );
+        assert_eq!(results[0].messages[0].severity, 2);
+        assert_eq!(results[0].messages[0].line, 10);
+
+        assert_eq!(results[0].messages[1].severity, 1);
+    }
+
+    #[test]
+    fn deserialize_eslint_null_rule_id() {
+        let json = r#"[
+            {
+                "filePath": "src/index.js",
+                "messages": [
+                    {
+                        "ruleId": null,
+                        "severity": 2,
+                        "message": "Parsing error: Unexpected token",
+                        "line": 1
+                    }
+                ]
+            }
+        ]"#;
+        let results: Vec<EslintFileResult> = serde_json::from_str(json).unwrap();
+        assert_eq!(results[0].messages[0].rule_id, None);
+    }
+
+    #[test]
+    fn deserialize_eslint_empty_messages() {
+        let json = r#"[{"filePath": "src/clean.js", "messages": []}]"#;
+        let results: Vec<EslintFileResult> = serde_json::from_str(json).unwrap();
+        assert_eq!(results[0].messages.len(), 0);
+    }
+
+    #[test]
+    fn deserialize_eslint_empty_array() {
+        let json = "[]";
+        let results: Vec<EslintFileResult> = serde_json::from_str(json).unwrap();
+        assert!(results.is_empty());
+    }
+
+    #[test]
+    fn eslint_severity_mapping() {
+        // severity 2 = error -> Medium, anything else -> Low
+        assert_eq!(
+            match 2u8 {
+                2 => "Medium",
+                _ => "Low",
+            },
+            "Medium"
+        );
+        assert_eq!(
+            match 1u8 {
+                2 => "Medium",
+                _ => "Low",
+            },
+            "Low"
+        );
+        assert_eq!(
+            match 0u8 {
+                2 => "Medium",
+                _ => "Low",
+            },
+            "Low"
+        );
+    }
+}

compliance-agent/src/pipeline/lint/mod.rs

@@ -0,0 +1,97 @@
+mod clippy;
+mod eslint;
+mod ruff;
+
+use std::path::Path;
+use std::time::Duration;
+
+use compliance_core::models::ScanType;
+use compliance_core::traits::{ScanOutput, Scanner};
+use compliance_core::CoreError;
+
+/// Timeout for each individual lint command
+pub(crate) const LINT_TIMEOUT: Duration = Duration::from_secs(120);
+
+pub struct LintScanner;
+
+impl Scanner for LintScanner {
+    fn name(&self) -> &str {
+        "lint"
+    }
+
+    fn scan_type(&self) -> ScanType {
+        ScanType::Lint
+    }
+
+    #[tracing::instrument(skip_all)]
+    async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
+        let mut all_findings = Vec::new();
+
+        // Detect which languages are present and run appropriate linters
+        if has_rust_project(repo_path) {
+            match clippy::run_clippy(repo_path, repo_id).await {
+                Ok(findings) => all_findings.extend(findings),
+                Err(e) => tracing::warn!("Clippy failed: {e}"),
+            }
+        }
+
+        if has_js_project(repo_path) {
+            match eslint::run_eslint(repo_path, repo_id).await {
+                Ok(findings) => all_findings.extend(findings),
+                Err(e) => tracing::warn!("ESLint failed: {e}"),
+            }
+        }
+
+        if has_python_project(repo_path) {
+            match ruff::run_ruff(repo_path, repo_id).await {
+                Ok(findings) => all_findings.extend(findings),
+                Err(e) => tracing::warn!("Ruff failed: {e}"),
+            }
+        }
+
+        Ok(ScanOutput {
+            findings: all_findings,
+            sbom_entries: Vec::new(),
+        })
+    }
+}
+
+fn has_rust_project(repo_path: &Path) -> bool {
+    repo_path.join("Cargo.toml").exists()
+}
+
+fn has_js_project(repo_path: &Path) -> bool {
+    // Only run if eslint is actually installed in the project
+    repo_path.join("package.json").exists() && repo_path.join("node_modules/.bin/eslint").exists()
+}
+
+fn has_python_project(repo_path: &Path) -> bool {
+    repo_path.join("pyproject.toml").exists()
+        || repo_path.join("setup.py").exists()
+        || repo_path.join("requirements.txt").exists()
+}
+
+/// Run a command with a timeout, returning its output or an error
+pub(crate) async fn run_with_timeout(
+    child: tokio::process::Child,
+    scanner_name: &str,
+) -> Result<std::process::Output, CoreError> {
+    let result = tokio::time::timeout(LINT_TIMEOUT, child.wait_with_output()).await;
+    match result {
+        Ok(Ok(output)) => Ok(output),
+        Ok(Err(e)) => Err(CoreError::Scanner {
+            scanner: scanner_name.to_string(),
+            source: Box::new(e),
+        }),
+        Err(_) => {
+            // Process is dropped here which sends SIGKILL on Unix
+            Err(CoreError::Scanner {
+                scanner: scanner_name.to_string(),
+                source: Box::new(std::io::Error::new(
+                    std::io::ErrorKind::TimedOut,
+                    format!("{scanner_name} timed out after {}s", LINT_TIMEOUT.as_secs()),
+                )),
+            })
+        }
+    }
+}

compliance-agent/src/pipeline/lint/ruff.rs

@@ -0,0 +1,150 @@
+use std::path::Path;
+
+use compliance_core::models::{Finding, ScanType, Severity};
+use compliance_core::CoreError;
+use tokio::process::Command;
+
+use crate::pipeline::dedup;
+
+use super::run_with_timeout;
+
+pub(super) async fn run_ruff(repo_path: &Path, repo_id: &str) -> Result<Vec<Finding>, CoreError> {
+    let child = Command::new("ruff")
+        .args(["check", ".", "--output-format", "json", "--exit-zero"])
+        .current_dir(repo_path)
+        .stdout(std::process::Stdio::piped())
+        .stderr(std::process::Stdio::piped())
+        .spawn()
+        .map_err(|e| CoreError::Scanner {
+            scanner: "ruff".to_string(),
+            source: Box::new(e),
+        })?;
+
+    let output = run_with_timeout(child, "ruff").await?;
+
+    if output.stdout.is_empty() {
+        return Ok(Vec::new());
+    }
+
+    let results: Vec<RuffResult> = serde_json::from_slice(&output.stdout).unwrap_or_default();
+
+    let findings = results
+        .into_iter()
+        .map(|r| {
+            let severity = if r.code.starts_with('E') || r.code.starts_with('F') {
+                Severity::Medium
+            } else {
+                Severity::Low
+            };
+
+            let fingerprint = dedup::compute_fingerprint(&[
+                repo_id,
+                "ruff",
+                &r.code,
+                &r.filename,
+                &r.location.row.to_string(),
+            ]);
+
+            let mut finding = Finding::new(
+                repo_id.to_string(),
+                fingerprint,
+                "ruff".to_string(),
+                ScanType::Lint,
+                format!("[ruff] {}: {}", r.code, r.message),
+                r.message,
+                severity,
+            );
+            finding.rule_id = Some(r.code);
+            finding.file_path = Some(r.filename);
+            finding.line_number = Some(r.location.row);
+            finding
+        })
+        .collect();
+
+    Ok(findings)
+}
+
+#[derive(serde::Deserialize)]
+struct RuffResult {
+    code: String,
+    message: String,
+    filename: String,
+    location: RuffLocation,
+}
+
+#[derive(serde::Deserialize)]
+struct RuffLocation {
+    row: u32,
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn deserialize_ruff_output() {
+        let json = r#"[
+            {
+                "code": "E501",
+                "message": "Line too long (120 > 79 characters)",
+                "filename": "src/main.py",
+                "location": {"row": 42}
+            },
+            {
+                "code": "F401",
+                "message": "`os` imported but unused",
+                "filename": "src/utils.py",
+                "location": {"row": 1}
+            }
+        ]"#;
+        let results: Vec<RuffResult> = serde_json::from_str(json).unwrap();
+        assert_eq!(results.len(), 2);
+
+        assert_eq!(results[0].code, "E501");
+        assert_eq!(results[0].filename, "src/main.py");
+        assert_eq!(results[0].location.row, 42);
+
+        assert_eq!(results[1].code, "F401");
+        assert_eq!(results[1].location.row, 1);
+    }
+
+    #[test]
+    fn deserialize_ruff_empty() {
+        let json = "[]";
+        let results: Vec<RuffResult> = serde_json::from_str(json).unwrap();
+        assert!(results.is_empty());
+    }
+
+    #[test]
+    fn ruff_severity_e_and_f_are_medium() {
+        for code in &["E501", "E302", "F401", "F811"] {
+            let is_medium = code.starts_with('E') || code.starts_with('F');
+            assert!(is_medium, "Expected {code} to be Medium severity");
+        }
+    }
+
+    #[test]
+    fn ruff_severity_others_are_low() {
+        for code in &["W291", "I001", "D100", "C901", "N801"] {
+            let is_medium = code.starts_with('E') || code.starts_with('F');
+            assert!(!is_medium, "Expected {code} to be Low severity");
+        }
+    }
+
+    #[test]
+    fn deserialize_ruff_with_extra_fields() {
+        // Ruff output may contain additional fields we don't use
+        let json = r#"[{
+            "code": "W291",
+            "message": "Trailing whitespace",
+            "filename": "app.py",
+            "location": {"row": 3, "column": 10},
+            "end_location": {"row": 3, "column": 11},
+            "fix": null,
+            "noqa_row": 3
+        }]"#;
+        let results: Vec<RuffResult> = serde_json::from_str(json).unwrap();
+        assert_eq!(results.len(), 1);
+        assert_eq!(results[0].code, "W291");
+    }
+}

compliance-agent/src/pipeline/mod.rs

@@ -1,7 +1,14 @@
+pub mod code_review;
 pub mod cve;
 pub mod dedup;
 pub mod git;
+pub mod gitleaks;
+mod graph_build;
+mod issue_creation;
+pub mod lint;
 pub mod orchestrator;
 pub mod patterns;
+mod pr_review;
 pub mod sbom;
 pub mod semgrep;
+mod tracker_dispatch;

compliance-agent/src/pipeline/orchestrator.rs

@@ -1,6 +1,7 @@
 use std::sync::Arc;
 
 use mongodb::bson::doc;
+use tracing::Instrument;
 
 use compliance_core::models::*;
 use compliance_core::traits::Scanner;
@@ -11,6 +12,8 @@ use crate::error::AgentError;
 use crate::llm::LlmClient;
 use crate::pipeline::cve::CveScanner;
 use crate::pipeline::git::GitOps;
+use crate::pipeline::gitleaks::GitleaksScanner;
+use crate::pipeline::lint::LintScanner;
 use crate::pipeline::patterns::{GdprPatternScanner, OAuthPatternScanner};
 use crate::pipeline::sbom::SbomScanner;
 use crate::pipeline::semgrep::SemgrepScanner;
@@ -26,10 +29,10 @@ pub struct GraphContext {
 }
 
 pub struct PipelineOrchestrator {
-    config: AgentConfig,
+    pub(super) config: AgentConfig,
-    db: Database,
+    pub(super) db: Database,
-    llm: Arc<LlmClient>,
+    pub(super) llm: Arc<LlmClient>,
-    http: reqwest::Client,
+    pub(super) http: reqwest::Client,
 }
 
 impl PipelineOrchestrator {
@@ -47,6 +50,7 @@ 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
@@ -86,6 +90,7 @@ impl PipelineOrchestrator {
                     .await?;
             }
             Err(e) => {
+                tracing::error!(repo_id, error = %e, "Scan pipeline failed");
                 self.db
                     .scan_runs()
                     .update_one(
@@ -105,6 +110,7 @@ impl PipelineOrchestrator {
         result.map(|_| ())
     }
 
+    #[tracing::instrument(skip_all, fields(repo_id = repo.name.as_str()))]
     async fn run_pipeline(
         &self,
         repo: &TrackedRepository,
@@ -114,7 +120,8 @@ impl PipelineOrchestrator {
 
         // Stage 0: Change detection
         tracing::info!("[{repo_id}] Stage 0: Change detection");
-        let git_ops = GitOps::new(&self.config.git_clone_base_path);
+        let creds = GitOps::make_repo_credentials(&self.config, repo);
+        let git_ops = GitOps::new(&self.config.git_clone_base_path, creds);
         let repo_path = git_ops.clone_or_fetch(&repo.git_url, &repo.name)?;
 
         if !GitOps::has_new_commits(&repo_path, repo.last_scanned_commit.as_deref())? {
@@ -128,8 +135,13 @@ impl PipelineOrchestrator {
         // Stage 1: Semgrep SAST
         tracing::info!("[{repo_id}] Stage 1: Semgrep SAST");
         self.update_phase(scan_run_id, "sast").await;
-        let semgrep = SemgrepScanner;
+        match async {
-        match semgrep.scan(&repo_path, &repo_id).await {
+            let semgrep = SemgrepScanner;
+            semgrep.scan(&repo_path, &repo_id).await
+        }
+        .instrument(tracing::info_span!("stage_sast"))
+        .await
+        {
             Ok(output) => all_findings.extend(output.findings),
             Err(e) => tracing::warn!("[{repo_id}] Semgrep failed: {e}"),
         }
@@ -137,8 +149,13 @@ impl PipelineOrchestrator {
         // Stage 2: SBOM Generation
         tracing::info!("[{repo_id}] Stage 2: SBOM Generation");
         self.update_phase(scan_run_id, "sbom_generation").await;
-        let sbom_scanner = SbomScanner;
+        let mut sbom_entries = match async {
-        let mut sbom_entries = match sbom_scanner.scan(&repo_path, &repo_id).await {
+            let sbom_scanner = SbomScanner;
+            sbom_scanner.scan(&repo_path, &repo_id).await
+        }
+        .instrument(tracing::info_span!("stage_sbom_generation"))
+        .await
+        {
             Ok(output) => output.sbom_entries,
             Err(e) => {
                 tracing::warn!("[{repo_id}] SBOM generation failed: {e}");
@@ -157,9 +174,13 @@ impl PipelineOrchestrator {
                 k.expose_secret().to_string()
             }),
         );
-        let cve_alerts = match cve_scanner
+        let cve_alerts = match async {
-            .scan_dependencies(&repo_id, &mut sbom_entries)
+            cve_scanner
-            .await
+                .scan_dependencies(&repo_id, &mut sbom_entries)
+                .await
+        }
+        .instrument(tracing::info_span!("stage_cve_scanning"))
+        .await
         {
             Ok(alerts) => alerts,
             Err(e) => {
@@ -171,23 +192,63 @@ impl PipelineOrchestrator {
         // Stage 4: Pattern Scanning (GDPR + OAuth)
         tracing::info!("[{repo_id}] Stage 4: Pattern Scanning");
         self.update_phase(scan_run_id, "pattern_scanning").await;
-        let gdpr = GdprPatternScanner::new();
+        {
-        match gdpr.scan(&repo_path, &repo_id).await {
+            let pattern_findings = async {
-            Ok(output) => all_findings.extend(output.findings),
+                let mut findings = Vec::new();
-            Err(e) => tracing::warn!("[{repo_id}] GDPR pattern scan failed: {e}"),
+                let gdpr = GdprPatternScanner::new();
+                match gdpr.scan(&repo_path, &repo_id).await {
+                    Ok(output) => findings.extend(output.findings),
+                    Err(e) => tracing::warn!("[{repo_id}] GDPR pattern scan failed: {e}"),
+                }
+                let oauth = OAuthPatternScanner::new();
+                match oauth.scan(&repo_path, &repo_id).await {
+                    Ok(output) => findings.extend(output.findings),
+                    Err(e) => tracing::warn!("[{repo_id}] OAuth pattern scan failed: {e}"),
+                }
+                findings
+            }
+            .instrument(tracing::info_span!("stage_pattern_scanning"))
+            .await;
+            all_findings.extend(pattern_findings);
         }
-        let oauth = OAuthPatternScanner::new();
+
-        match oauth.scan(&repo_path, &repo_id).await {
+        // Stage 4a: Secret Detection (Gitleaks)
+        tracing::info!("[{repo_id}] Stage 4a: Secret Detection");
+        self.update_phase(scan_run_id, "secret_detection").await;
+        match async {
+            let gitleaks = GitleaksScanner;
+            gitleaks.scan(&repo_path, &repo_id).await
+        }
+        .instrument(tracing::info_span!("stage_secret_detection"))
+        .await
+        {
             Ok(output) => all_findings.extend(output.findings),
-            Err(e) => tracing::warn!("[{repo_id}] OAuth pattern scan failed: {e}"),
+            Err(e) => tracing::warn!("[{repo_id}] Gitleaks failed: {e}"),
+        }
+
+        // Stage 4b: Lint Scanning
+        tracing::info!("[{repo_id}] Stage 4b: Lint Scanning");
+        self.update_phase(scan_run_id, "lint_scanning").await;
+        match async {
+            let lint = LintScanner;
+            lint.scan(&repo_path, &repo_id).await
+        }
+        .instrument(tracing::info_span!("stage_lint_scanning"))
+        .await
+        {
+            Ok(output) => all_findings.extend(output.findings),
+            Err(e) => tracing::warn!("[{repo_id}] Lint scanning failed: {e}"),
         }
 
         // Stage 4.5: Graph Building
         tracing::info!("[{repo_id}] Stage 4.5: Graph Building");
         self.update_phase(scan_run_id, "graph_building").await;
-        let graph_context = match self
+        let graph_context = match async {
-            .build_code_graph(&repo_path, &repo_id, &all_findings)
+            self.build_code_graph(&repo_path, &repo_id, &all_findings)
-            .await
+                .await
+        }
+        .instrument(tracing::info_span!("stage_graph_building"))
+        .await
         {
             Ok(ctx) => Some(ctx),
             Err(e) => {
@@ -212,6 +273,7 @@ impl PipelineOrchestrator {
 
         // Dedup against existing findings and insert new ones
         let mut new_count = 0u32;
+        let mut new_findings: Vec<Finding> = Vec::new();
         for mut finding in all_findings {
             finding.scan_run_id = Some(scan_run_id.to_string());
             // Check if fingerprint already exists
@@ -221,12 +283,22 @@ impl PipelineOrchestrator {
                 .find_one(doc! { "fingerprint": &finding.fingerprint })
                 .await?;
             if existing.is_none() {
-                self.db.findings().insert_one(&finding).await?;
+                let result = self.db.findings().insert_one(&finding).await?;
+                finding.id = result.inserted_id.as_object_id();
+                new_findings.push(finding);
                 new_count += 1;
             }
         }
 
-        // Persist SBOM entries (upsert by repo_id + name + version)
+        // Remove stale SBOM entries for this repo before reinserting
+        if !sbom_entries.is_empty() {
+            self.db
+                .sbom_entries()
+                .delete_many(doc! { "repo_id": &repo.id })
+                .await?;
+        }
+
+        // Persist SBOM entries
         for entry in &sbom_entries {
             let filter = doc! {
                 "repo_id": &entry.repo_id,
@@ -262,7 +334,12 @@ impl PipelineOrchestrator {
         // Stage 6: Issue Creation
         tracing::info!("[{repo_id}] Stage 6: Issue Creation");
         self.update_phase(scan_run_id, "issue_creation").await;
-        // Issue creation is handled by the trackers module - deferred to agent
+        if let Err(e) = self
+            .create_tracker_issues(repo, &repo_id, &new_findings)
+            .await
+        {
+            tracing::warn!("[{repo_id}] Issue creation failed: {e}");
+        }
 
         // Stage 7: Update repository
         self.db
@@ -288,107 +365,7 @@ impl PipelineOrchestrator {
         Ok(new_count)
     }
 
-    /// Build the code knowledge graph for a repo and compute impact analyses
+    pub(super) async fn update_phase(&self, scan_run_id: &str, phase: &str) {
-    async fn build_code_graph(
-        &self,
-        repo_path: &std::path::Path,
-        repo_id: &str,
-        findings: &[Finding],
-    ) -> Result<GraphContext, AgentError> {
-        let graph_build_id = uuid::Uuid::new_v4().to_string();
-        let engine = compliance_graph::GraphEngine::new(50_000);
-
-        let (mut code_graph, build_run) =
-            engine
-                .build_graph(repo_path, repo_id, &graph_build_id)
-                .map_err(|e| AgentError::Other(format!("Graph build error: {e}")))?;
-
-        // Apply community detection
-        compliance_graph::graph::community::apply_communities(&mut code_graph);
-
-        // Store graph in MongoDB
-        let store = compliance_graph::graph::persistence::GraphStore::new(self.db.inner());
-        store
-            .delete_repo_graph(repo_id)
-            .await
-            .map_err(|e| AgentError::Other(format!("Graph cleanup error: {e}")))?;
-        store
-            .store_graph(&build_run, &code_graph.nodes, &code_graph.edges)
-            .await
-            .map_err(|e| AgentError::Other(format!("Graph store error: {e}")))?;
-
-        // Compute impact analysis for each finding
-        let analyzer = compliance_graph::GraphEngine::impact_analyzer(&code_graph);
-        let mut impacts = Vec::new();
-
-        for finding in findings {
-            if let Some(file_path) = &finding.file_path {
-                let impact = analyzer.analyze(
-                    repo_id,
-                    &finding.fingerprint,
-                    &graph_build_id,
-                    file_path,
-                    finding.line_number,
-                );
-                store
-                    .store_impact(&impact)
-                    .await
-                    .map_err(|e| AgentError::Other(format!("Impact store error: {e}")))?;
-                impacts.push(impact);
-            }
-        }
-
-        Ok(GraphContext {
-            node_count: build_run.node_count,
-            edge_count: build_run.edge_count,
-            community_count: build_run.community_count,
-            impacts,
-        })
-    }
-
-    /// Trigger DAST scan if a target is configured for this repo
-    async fn maybe_trigger_dast(&self, repo_id: &str, scan_run_id: &str) {
-        use futures_util::TryStreamExt;
-
-        let filter = mongodb::bson::doc! { "repo_id": repo_id };
-        let targets: Vec<compliance_core::models::DastTarget> =
-            match self.db.dast_targets().find(filter).await {
-                Ok(cursor) => cursor.try_collect().await.unwrap_or_default(),
-                Err(_) => return,
-            };
-
-        if targets.is_empty() {
-            tracing::info!("[{repo_id}] No DAST targets configured, skipping");
-            return;
-        }
-
-        for target in targets {
-            let db = self.db.clone();
-            let scan_run_id = scan_run_id.to_string();
-            tokio::spawn(async move {
-                let orchestrator = compliance_dast::DastOrchestrator::new(100);
-                match orchestrator.run_scan(&target, Vec::new()).await {
-                    Ok((mut scan_run, findings)) => {
-                        scan_run.sast_scan_run_id = Some(scan_run_id);
-                        if let Err(e) = db.dast_scan_runs().insert_one(&scan_run).await {
-                            tracing::error!("Failed to store DAST scan run: {e}");
-                        }
-                        for finding in &findings {
-                            if let Err(e) = db.dast_findings().insert_one(finding).await {
-                                tracing::error!("Failed to store DAST finding: {e}");
-                            }
-                        }
-                        tracing::info!("DAST scan complete: {} findings", findings.len());
-                    }
-                    Err(e) => {
-                        tracing::error!("DAST scan failed: {e}");
-                    }
-                }
-            });
-        }
-    }
-
-    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
                 .db
@@ -404,3 +381,28 @@ impl PipelineOrchestrator {
         }
     }
 }
+
+/// Extract the scheme + host from a git URL.
+/// e.g. "https://gitea.example.com/owner/repo.git" -> "https://gitea.example.com"
+/// e.g. "ssh://git@gitea.example.com:22/owner/repo.git" -> "https://gitea.example.com"
+pub(super) fn extract_base_url(git_url: &str) -> Option<String> {
+    if let Some(rest) = git_url.strip_prefix("https://") {
+        let host = rest.split('/').next()?;
+        Some(format!("https://{host}"))
+    } else if let Some(rest) = git_url.strip_prefix("http://") {
+        let host = rest.split('/').next()?;
+        Some(format!("http://{host}"))
+    } else if let Some(rest) = git_url.strip_prefix("ssh://") {
+        // ssh://git@host:port/path -> extract host
+        let after_at = rest.find('@').map(|i| &rest[i + 1..]).unwrap_or(rest);
+        let host = after_at.split(&[':', '/'][..]).next()?;
+        Some(format!("https://{host}"))
+    } else if let Some(at_pos) = git_url.find('@') {
+        // SCP-style: git@host:owner/repo.git
+        let after_at = &git_url[at_pos + 1..];
+        let host = after_at.split(':').next()?;
+        Some(format!("https://{host}"))
+    } else {
+        None
+    }
+}

compliance-agent/src/pipeline/patterns.rs

@@ -82,6 +82,7 @@ impl Scanner for GdprPatternScanner {
         ScanType::Gdpr
     }
 
+    #[tracing::instrument(skip_all)]
     async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
         let findings = scan_with_patterns(
             repo_path,
@@ -146,6 +147,7 @@ impl Scanner for OAuthPatternScanner {
         ScanType::OAuth
     }
 
+    #[tracing::instrument(skip_all)]
     async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
         let findings = scan_with_patterns(
             repo_path,
@@ -254,3 +256,159 @@ fn walkdir(path: &Path) -> Result<Vec<walkdir::DirEntry>, CoreError> {
 
     Ok(entries)
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    // --- compile_regex tests ---
+
+    #[test]
+    fn compile_regex_valid_pattern() {
+        let re = compile_regex(r"\bfoo\b");
+        assert!(re.is_match("hello foo bar"));
+        assert!(!re.is_match("foobar"));
+    }
+
+    #[test]
+    fn compile_regex_invalid_pattern_returns_fallback() {
+        // An invalid regex should return the fallback "^$" that only matches empty strings
+        let re = compile_regex(r"[invalid");
+        assert!(re.is_match(""));
+        assert!(!re.is_match("anything"));
+    }
+
+    // --- GDPR pattern tests ---
+
+    #[test]
+    fn gdpr_pii_logging_matches() {
+        let scanner = GdprPatternScanner::new();
+        let pattern = &scanner.patterns[0]; // gdpr-pii-logging
+                                            // Regex: (log|print|console\.|logger\.|tracing::)\s*[\.(].*\b(pii_keyword)\b
+        assert!(pattern.pattern.is_match("console.log(email)"));
+        assert!(pattern.pattern.is_match("console.log(user.ssn)"));
+        assert!(pattern.pattern.is_match("print(phone_number)"));
+        assert!(pattern.pattern.is_match("tracing::(ip_addr)"));
+        assert!(pattern.pattern.is_match("log.debug(credit_card)"));
+    }
+
+    #[test]
+    fn gdpr_pii_logging_no_false_positive() {
+        let scanner = GdprPatternScanner::new();
+        let pattern = &scanner.patterns[0];
+        // Regular logging without PII fields should not match
+        assert!(!pattern
+            .pattern
+            .is_match("logger.info(\"request completed\")"));
+        assert!(!pattern.pattern.is_match("let email = user.email;"));
+    }
+
+    #[test]
+    fn gdpr_no_consent_matches() {
+        let scanner = GdprPatternScanner::new();
+        let pattern = &scanner.patterns[1]; // gdpr-no-consent
+        assert!(pattern.pattern.is_match("collect personal data"));
+        assert!(pattern.pattern.is_match("store user_data in db"));
+        assert!(pattern.pattern.is_match("save pii to disk"));
+    }
+
+    #[test]
+    fn gdpr_user_model_matches() {
+        let scanner = GdprPatternScanner::new();
+        let pattern = &scanner.patterns[2]; // gdpr-no-delete-endpoint
+        assert!(pattern.pattern.is_match("struct User {"));
+        assert!(pattern.pattern.is_match("class User(Model):"));
+    }
+
+    #[test]
+    fn gdpr_hardcoded_retention_matches() {
+        let scanner = GdprPatternScanner::new();
+        let pattern = &scanner.patterns[3]; // gdpr-hardcoded-retention
+        assert!(pattern.pattern.is_match("retention = 30"));
+        assert!(pattern.pattern.is_match("ttl: 3600"));
+        assert!(pattern.pattern.is_match("expire = 86400"));
+    }
+
+    // --- OAuth pattern tests ---
+
+    #[test]
+    fn oauth_implicit_grant_matches() {
+        let scanner = OAuthPatternScanner::new();
+        let pattern = &scanner.patterns[0]; // oauth-implicit-grant
+        assert!(pattern.pattern.is_match("response_type = \"token\""));
+        assert!(pattern.pattern.is_match("grant_type: implicit"));
+        assert!(pattern.pattern.is_match("response_type='token'"));
+    }
+
+    #[test]
+    fn oauth_implicit_grant_no_false_positive() {
+        let scanner = OAuthPatternScanner::new();
+        let pattern = &scanner.patterns[0];
+        assert!(!pattern.pattern.is_match("response_type = \"code\""));
+        assert!(!pattern.pattern.is_match("grant_type: authorization_code"));
+    }
+
+    #[test]
+    fn oauth_authorization_code_matches() {
+        let scanner = OAuthPatternScanner::new();
+        let pattern = &scanner.patterns[1]; // oauth-missing-pkce
+        assert!(pattern.pattern.is_match("uses authorization_code flow"));
+        assert!(pattern.pattern.is_match("authorization code grant"));
+    }
+
+    #[test]
+    fn oauth_token_localstorage_matches() {
+        let scanner = OAuthPatternScanner::new();
+        let pattern = &scanner.patterns[2]; // oauth-token-localstorage
+        assert!(pattern
+            .pattern
+            .is_match("localStorage.setItem('access_token', tok)"));
+        assert!(pattern
+            .pattern
+            .is_match("localStorage.getItem(\"refresh_token\")"));
+    }
+
+    #[test]
+    fn oauth_token_localstorage_no_false_positive() {
+        let scanner = OAuthPatternScanner::new();
+        let pattern = &scanner.patterns[2];
+        assert!(!pattern
+            .pattern
+            .is_match("localStorage.setItem('theme', 'dark')"));
+        assert!(!pattern
+            .pattern
+            .is_match("sessionStorage.setItem('token', t)"));
+    }
+
+    #[test]
+    fn oauth_token_url_matches() {
+        let scanner = OAuthPatternScanner::new();
+        let pattern = &scanner.patterns[3]; // oauth-token-url
+        assert!(pattern.pattern.is_match("access_token = build_url(query)"));
+        assert!(pattern.pattern.is_match("bearer = url.param"));
+    }
+
+    // --- Pattern rule file extension filtering ---
+
+    #[test]
+    fn gdpr_patterns_cover_common_languages() {
+        let scanner = GdprPatternScanner::new();
+        for pattern in &scanner.patterns {
+            assert!(
+                pattern.file_extensions.contains(&"rs".to_string()),
+                "Pattern {} should cover .rs files",
+                pattern.id
+            );
+        }
+    }
+
+    #[test]
+    fn oauth_localstorage_only_js_ts() {
+        let scanner = OAuthPatternScanner::new();
+        let pattern = &scanner.patterns[2]; // oauth-token-localstorage
+        assert!(pattern.file_extensions.contains(&"js".to_string()));
+        assert!(pattern.file_extensions.contains(&"ts".to_string()));
+        assert!(!pattern.file_extensions.contains(&"rs".to_string()));
+        assert!(!pattern.file_extensions.contains(&"py".to_string()));
+    }
+}

compliance-agent/src/pipeline/pr_review.rs

@@ -0,0 +1,146 @@
+use compliance_core::models::*;
+
+use super::orchestrator::PipelineOrchestrator;
+use crate::error::AgentError;
+use crate::pipeline::code_review::CodeReviewScanner;
+use crate::pipeline::git::GitOps;
+use crate::pipeline::semgrep::SemgrepScanner;
+
+use compliance_core::traits::Scanner;
+
+impl PipelineOrchestrator {
+    /// Run an incremental scan on a PR diff and post review comments.
+    #[tracing::instrument(skip_all, fields(repo_id = %repo_id, pr_number))]
+    pub async fn run_pr_review(
+        &self,
+        repo: &TrackedRepository,
+        repo_id: &str,
+        pr_number: u64,
+        base_sha: &str,
+        head_sha: &str,
+    ) -> Result<(), AgentError> {
+        let tracker = match self.build_tracker(repo) {
+            Some(t) => t,
+            None => {
+                tracing::warn!("[{repo_id}] No tracker configured, cannot post PR review");
+                return Ok(());
+            }
+        };
+        let owner = repo.tracker_owner.as_deref().unwrap_or("");
+        let tracker_repo_name = repo.tracker_repo.as_deref().unwrap_or("");
+        if owner.is_empty() || tracker_repo_name.is_empty() {
+            tracing::warn!("[{repo_id}] tracker_owner or tracker_repo not set");
+            return Ok(());
+        }
+
+        // Clone/fetch the repo
+        let creds = GitOps::make_repo_credentials(&self.config, repo);
+        let git_ops = GitOps::new(&self.config.git_clone_base_path, creds);
+        let repo_path = git_ops.clone_or_fetch(&repo.git_url, &repo.name)?;
+
+        // Get diff between base and head
+        let diff_files = GitOps::get_diff_content(&repo_path, base_sha, head_sha)?;
+        if diff_files.is_empty() {
+            tracing::info!("[{repo_id}] PR #{pr_number}: no diff files, skipping review");
+            return Ok(());
+        }
+
+        // Run semgrep on the full repo but we'll filter findings to changed files
+        let changed_paths: std::collections::HashSet<String> =
+            diff_files.iter().map(|f| f.path.clone()).collect();
+
+        let mut pr_findings: Vec<Finding> = Vec::new();
+
+        // SAST scan (semgrep)
+        match SemgrepScanner.scan(&repo_path, repo_id).await {
+            Ok(output) => {
+                for f in output.findings {
+                    if let Some(fp) = &f.file_path {
+                        if changed_paths.contains(fp.as_str()) {
+                            pr_findings.push(f);
+                        }
+                    }
+                }
+            }
+            Err(e) => tracing::warn!("[{repo_id}] PR semgrep failed: {e}"),
+        }
+
+        // LLM code review on the diff
+        let reviewer = CodeReviewScanner::new(self.llm.clone());
+        let review_output = reviewer
+            .review_diff(&repo_path, repo_id, base_sha, head_sha)
+            .await;
+        pr_findings.extend(review_output.findings);
+
+        if pr_findings.is_empty() {
+            // Post a clean review
+            if let Err(e) = tracker
+                .create_pr_review(
+                    owner,
+                    tracker_repo_name,
+                    pr_number,
+                    "Compliance scan: no issues found in this PR.",
+                    Vec::new(),
+                )
+                .await
+            {
+                tracing::warn!("[{repo_id}] Failed to post clean PR review: {e}");
+            }
+            return Ok(());
+        }
+
+        // Build review comments from findings
+        let mut review_comments = Vec::new();
+        for finding in &pr_findings {
+            if let (Some(path), Some(line)) = (&finding.file_path, finding.line_number) {
+                let comment_body = format!(
+                    "**[{}] {}**\n\n{}\n\n*Scanner: {} | {}*",
+                    finding.severity,
+                    finding.title,
+                    finding.description,
+                    finding.scanner,
+                    finding
+                        .cwe
+                        .as_deref()
+                        .map(|c| format!("CWE: {c}"))
+                        .unwrap_or_default(),
+                );
+                review_comments.push(compliance_core::traits::issue_tracker::ReviewComment {
+                    path: path.clone(),
+                    line,
+                    body: comment_body,
+                });
+            }
+        }
+
+        let summary = format!(
+            "Compliance scan found **{}** issue(s) in this PR:\n\n{}",
+            pr_findings.len(),
+            pr_findings
+                .iter()
+                .map(|f| format!("- **[{}]** {}: {}", f.severity, f.scanner, f.title))
+                .collect::<Vec<_>>()
+                .join("\n"),
+        );
+
+        if let Err(e) = tracker
+            .create_pr_review(
+                owner,
+                tracker_repo_name,
+                pr_number,
+                &summary,
+                review_comments,
+            )
+            .await
+        {
+            tracing::warn!("[{repo_id}] Failed to post PR review: {e}");
+        } else {
+            tracing::info!(
+                "[{repo_id}] Posted PR review on #{pr_number} with {} findings",
+                pr_findings.len()
+            );
+        }
+
+        Ok(())
+    }
+}

compliance-agent/src/pipeline/sbom.rs

@@ -1,190 +0,0 @@
-use std::path::Path;
-
-use compliance_core::models::{SbomEntry, ScanType, VulnRef};
-use compliance_core::traits::{ScanOutput, Scanner};
-use compliance_core::CoreError;
-
-pub struct SbomScanner;
-
-impl Scanner for SbomScanner {
-    fn name(&self) -> &str {
-        "sbom"
-    }
-
-    fn scan_type(&self) -> ScanType {
-        ScanType::Sbom
-    }
-
-    async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
-        let mut entries = Vec::new();
-
-        // Run syft for SBOM generation
-        match run_syft(repo_path, repo_id).await {
-            Ok(syft_entries) => entries.extend(syft_entries),
-            Err(e) => tracing::warn!("syft failed: {e}"),
-        }
-
-        // Run cargo-audit for Rust-specific vulns
-        match run_cargo_audit(repo_path, repo_id).await {
-            Ok(vulns) => merge_audit_vulns(&mut entries, vulns),
-            Err(e) => tracing::warn!("cargo-audit skipped: {e}"),
-        }
-
-        Ok(ScanOutput {
-            findings: Vec::new(),
-            sbom_entries: entries,
-        })
-    }
-}
-
-async fn run_syft(repo_path: &Path, repo_id: &str) -> Result<Vec<SbomEntry>, CoreError> {
-    let output = tokio::process::Command::new("syft")
-        .arg(repo_path)
-        .args(["-o", "cyclonedx-json"])
-        .output()
-        .await
-        .map_err(|e| CoreError::Scanner {
-            scanner: "syft".to_string(),
-            source: Box::new(e),
-        })?;
-
-    if !output.status.success() {
-        let stderr = String::from_utf8_lossy(&output.stderr);
-        return Err(CoreError::Scanner {
-            scanner: "syft".to_string(),
-            source: format!("syft exited with {}: {stderr}", output.status).into(),
-        });
-    }
-
-    let cdx: CycloneDxBom = serde_json::from_slice(&output.stdout)?;
-    let entries = cdx
-        .components
-        .unwrap_or_default()
-        .into_iter()
-        .map(|c| {
-            let mut entry = SbomEntry::new(
-                repo_id.to_string(),
-                c.name,
-                c.version.unwrap_or_else(|| "unknown".to_string()),
-                c.component_type.unwrap_or_else(|| "library".to_string()),
-            );
-            entry.purl = c.purl;
-            entry.license = c.licenses.and_then(|ls| {
-                ls.first().and_then(|l| {
-                    l.license.as_ref().map(|lic| {
-                        lic.id
-                            .clone()
-                            .unwrap_or_else(|| lic.name.clone().unwrap_or_default())
-                    })
-                })
-            });
-            entry
-        })
-        .collect();
-
-    Ok(entries)
-}
-
-async fn run_cargo_audit(repo_path: &Path, _repo_id: &str) -> Result<Vec<AuditVuln>, CoreError> {
-    let cargo_lock = repo_path.join("Cargo.lock");
-    if !cargo_lock.exists() {
-        return Ok(Vec::new());
-    }
-
-    let output = tokio::process::Command::new("cargo")
-        .args(["audit", "--json"])
-        .current_dir(repo_path)
-        .output()
-        .await
-        .map_err(|e| CoreError::Scanner {
-            scanner: "cargo-audit".to_string(),
-            source: Box::new(e),
-        })?;
-
-    let result: CargoAuditOutput =
-        serde_json::from_slice(&output.stdout).unwrap_or_else(|_| CargoAuditOutput {
-            vulnerabilities: CargoAuditVulns { list: Vec::new() },
-        });
-
-    let vulns = result
-        .vulnerabilities
-        .list
-        .into_iter()
-        .map(|v| AuditVuln {
-            package: v.advisory.package,
-            id: v.advisory.id,
-            url: v.advisory.url,
-        })
-        .collect();
-
-    Ok(vulns)
-}
-
-fn merge_audit_vulns(entries: &mut [SbomEntry], vulns: Vec<AuditVuln>) {
-    for vuln in vulns {
-        if let Some(entry) = entries.iter_mut().find(|e| e.name == vuln.package) {
-            entry.known_vulnerabilities.push(VulnRef {
-                id: vuln.id.clone(),
-                source: "cargo-audit".to_string(),
-                severity: None,
-                url: Some(vuln.url),
-            });
-        }
-    }
-}
-
-// CycloneDX JSON types
-#[derive(serde::Deserialize)]
-struct CycloneDxBom {
-    components: Option<Vec<CdxComponent>>,
-}
-
-#[derive(serde::Deserialize)]
-struct CdxComponent {
-    name: String,
-    version: Option<String>,
-    #[serde(rename = "type")]
-    component_type: Option<String>,
-    purl: Option<String>,
-    licenses: Option<Vec<CdxLicenseWrapper>>,
-}
-
-#[derive(serde::Deserialize)]
-struct CdxLicenseWrapper {
-    license: Option<CdxLicense>,
-}
-
-#[derive(serde::Deserialize)]
-struct CdxLicense {
-    id: Option<String>,
-    name: Option<String>,
-}
-
-// Cargo audit types
-#[derive(serde::Deserialize)]
-struct CargoAuditOutput {
-    vulnerabilities: CargoAuditVulns,
-}
-
-#[derive(serde::Deserialize)]
-struct CargoAuditVulns {
-    list: Vec<CargoAuditEntry>,
-}
-
-#[derive(serde::Deserialize)]
-struct CargoAuditEntry {
-    advisory: CargoAuditAdvisory,
-}
-
-#[derive(serde::Deserialize)]
-struct CargoAuditAdvisory {
-    id: String,
-    package: String,
-    url: String,
-}
-
-struct AuditVuln {
-    package: String,
-    id: String,
-    url: String,
-}

compliance-agent/src/pipeline/sbom/cargo_audit.rs

@@ -0,0 +1,72 @@
+use std::path::Path;
+
+use compliance_core::CoreError;
+
+pub(super) struct AuditVuln {
+    pub package: String,
+    pub id: String,
+    pub url: String,
+}
+
+#[tracing::instrument(skip_all)]
+pub(super) async fn run_cargo_audit(
+    repo_path: &Path,
+    _repo_id: &str,
+) -> Result<Vec<AuditVuln>, CoreError> {
+    let cargo_lock = repo_path.join("Cargo.lock");
+    if !cargo_lock.exists() {
+        return Ok(Vec::new());
+    }
+
+    let output = tokio::process::Command::new("cargo")
+        .args(["audit", "--json"])
+        .current_dir(repo_path)
+        .env("RUSTC_WRAPPER", "")
+        .output()
+        .await
+        .map_err(|e| CoreError::Scanner {
+            scanner: "cargo-audit".to_string(),
+            source: Box::new(e),
+        })?;
+
+    let result: CargoAuditOutput =
+        serde_json::from_slice(&output.stdout).unwrap_or_else(|_| CargoAuditOutput {
+            vulnerabilities: CargoAuditVulns { list: Vec::new() },
+        });
+
+    let vulns = result
+        .vulnerabilities
+        .list
+        .into_iter()
+        .map(|v| AuditVuln {
+            package: v.advisory.package,
+            id: v.advisory.id,
+            url: v.advisory.url,
+        })
+        .collect();
+
+    Ok(vulns)
+}
+
+// Cargo audit types
+#[derive(serde::Deserialize)]
+struct CargoAuditOutput {
+    vulnerabilities: CargoAuditVulns,
+}
+
+#[derive(serde::Deserialize)]
+struct CargoAuditVulns {
+    list: Vec<CargoAuditEntry>,
+}
+
+#[derive(serde::Deserialize)]
+struct CargoAuditEntry {
+    advisory: CargoAuditAdvisory,
+}
+
+#[derive(serde::Deserialize)]
+struct CargoAuditAdvisory {
+    id: String,
+    package: String,
+    url: String,
+}

compliance-agent/src/pipeline/sbom/mod.rs

@@ -0,0 +1,216 @@
+mod cargo_audit;
+mod syft;
+
+use std::path::Path;
+
+use compliance_core::models::{SbomEntry, ScanType, VulnRef};
+use compliance_core::traits::{ScanOutput, Scanner};
+use compliance_core::CoreError;
+
+pub struct SbomScanner;
+
+impl Scanner for SbomScanner {
+    fn name(&self) -> &str {
+        "sbom"
+    }
+
+    fn scan_type(&self) -> ScanType {
+        ScanType::Sbom
+    }
+
+    #[tracing::instrument(skip_all)]
+    async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
+        let mut entries = Vec::new();
+
+        // Generate missing lock files so Syft can resolve the full dependency tree
+        generate_lockfiles(repo_path).await;
+
+        // Run syft for SBOM generation
+        match syft::run_syft(repo_path, repo_id).await {
+            Ok(syft_entries) => entries.extend(syft_entries),
+            Err(e) => tracing::warn!("syft failed: {e}"),
+        }
+
+        // Enrich Cargo entries with license info from cargo metadata
+        enrich_cargo_licenses(repo_path, &mut entries).await;
+
+        // Run cargo-audit for Rust-specific vulns
+        match cargo_audit::run_cargo_audit(repo_path, repo_id).await {
+            Ok(vulns) => merge_audit_vulns(&mut entries, vulns),
+            Err(e) => tracing::warn!("cargo-audit skipped: {e}"),
+        }
+
+        Ok(ScanOutput {
+            findings: Vec::new(),
+            sbom_entries: entries,
+        })
+    }
+}
+
+/// Generate missing lock files so Syft can resolve the full dependency tree.
+/// This handles repos that gitignore their lock files (common for Rust libraries).
+#[tracing::instrument(skip_all)]
+async fn generate_lockfiles(repo_path: &Path) {
+    // Cargo: generate Cargo.lock if Cargo.toml exists without it
+    if repo_path.join("Cargo.toml").exists() && !repo_path.join("Cargo.lock").exists() {
+        tracing::info!("generating Cargo.lock for SBOM scan");
+        let result = tokio::process::Command::new("cargo")
+            .args(["generate-lockfile"])
+            .current_dir(repo_path)
+            .env("RUSTC_WRAPPER", "")
+            .output()
+            .await;
+        match result {
+            Ok(o) if o.status.success() => tracing::info!("Cargo.lock generated"),
+            Ok(o) => tracing::warn!(
+                "cargo generate-lockfile failed: {}",
+                String::from_utf8_lossy(&o.stderr)
+            ),
+            Err(e) => tracing::warn!("cargo generate-lockfile error: {e}"),
+        }
+    }
+
+    // pip: generate a requirements lock if only pyproject.toml / setup.py exists
+    let has_pip_manifest = repo_path.join("pyproject.toml").exists()
+        || repo_path.join("setup.py").exists()
+        || repo_path.join("setup.cfg").exists();
+    let has_pip_lock = repo_path.join("requirements.txt").exists()
+        || repo_path.join("requirements-lock.txt").exists()
+        || repo_path.join("poetry.lock").exists()
+        || repo_path.join("Pipfile.lock").exists();
+    if has_pip_manifest && !has_pip_lock {
+        // Try pip-compile (pip-tools) first, fall back to pip freeze approach
+        tracing::info!("attempting to generate pip requirements for SBOM scan");
+        if repo_path.join("pyproject.toml").exists() {
+            let result = tokio::process::Command::new("pip-compile")
+                .args([
+                    "--quiet",
+                    "--output-file",
+                    "requirements.txt",
+                    "pyproject.toml",
+                ])
+                .current_dir(repo_path)
+                .output()
+                .await;
+            match result {
+                Ok(o) if o.status.success() => {
+                    tracing::info!("requirements.txt generated via pip-compile")
+                }
+                _ => tracing::warn!(
+                    "pip-compile not available or failed, Syft will parse pyproject.toml directly"
+                ),
+            }
+        }
+    }
+
+    // npm: generate package-lock.json if package.json exists without it
+    let has_npm_lock = repo_path.join("package-lock.json").exists()
+        || repo_path.join("yarn.lock").exists()
+        || repo_path.join("pnpm-lock.yaml").exists();
+    if repo_path.join("package.json").exists() && !has_npm_lock {
+        tracing::info!("generating package-lock.json for SBOM scan");
+        let result = tokio::process::Command::new("npm")
+            .args(["install", "--package-lock-only", "--ignore-scripts"])
+            .current_dir(repo_path)
+            .output()
+            .await;
+        match result {
+            Ok(o) if o.status.success() => tracing::info!("package-lock.json generated"),
+            Ok(o) => tracing::warn!(
+                "npm install --package-lock-only failed: {}",
+                String::from_utf8_lossy(&o.stderr)
+            ),
+            Err(e) => tracing::warn!("npm lock generation error: {e}"),
+        }
+    }
+}
+
+/// Enrich Cargo SBOM entries with license info from `cargo metadata`.
+/// Syft doesn't read license data from Cargo.lock, so we fill it in.
+#[tracing::instrument(skip_all)]
+async fn enrich_cargo_licenses(repo_path: &Path, entries: &mut [SbomEntry]) {
+    if !repo_path.join("Cargo.toml").exists() {
+        return;
+    }
+
+    let has_cargo_entries = entries.iter().any(|e| e.package_manager == "cargo");
+    if !has_cargo_entries {
+        return;
+    }
+
+    let output = match tokio::process::Command::new("cargo")
+        .args(["metadata", "--format-version", "1"])
+        .current_dir(repo_path)
+        .env("RUSTC_WRAPPER", "")
+        .output()
+        .await
+    {
+        Ok(o) if o.status.success() => o,
+        Ok(o) => {
+            tracing::warn!(
+                "cargo metadata failed: {}",
+                String::from_utf8_lossy(&o.stderr)
+            );
+            return;
+        }
+        Err(e) => {
+            tracing::warn!("cargo metadata error: {e}");
+            return;
+        }
+    };
+
+    let meta: CargoMetadata = match serde_json::from_slice(&output.stdout) {
+        Ok(m) => m,
+        Err(e) => {
+            tracing::warn!("failed to parse cargo metadata: {e}");
+            return;
+        }
+    };
+
+    // Build a lookup: (name, version) -> license
+    let license_map: std::collections::HashMap<(&str, &str), &str> = meta
+        .packages
+        .iter()
+        .filter_map(|p| {
+            p.license
+                .as_deref()
+                .map(|l| (p.name.as_str(), p.version.as_str(), l))
+        })
+        .map(|(n, v, l)| ((n, v), l))
+        .collect();
+
+    for entry in entries.iter_mut() {
+        if entry.package_manager != "cargo" || entry.license.is_some() {
+            continue;
+        }
+        if let Some(license) = license_map.get(&(entry.name.as_str(), entry.version.as_str())) {
+            entry.license = Some(license.to_string());
+        }
+    }
+}
+
+fn merge_audit_vulns(entries: &mut [SbomEntry], vulns: Vec<cargo_audit::AuditVuln>) {
+    for vuln in vulns {
+        if let Some(entry) = entries.iter_mut().find(|e| e.name == vuln.package) {
+            entry.known_vulnerabilities.push(VulnRef {
+                id: vuln.id.clone(),
+                source: "cargo-audit".to_string(),
+                severity: None,
+                url: Some(vuln.url),
+            });
+        }
+    }
+}
+
+// Cargo metadata types
+#[derive(serde::Deserialize)]
+struct CargoMetadata {
+    packages: Vec<CargoPackage>,
+}
+
+#[derive(serde::Deserialize)]
+struct CargoPackage {
+    name: String,
+    version: String,
+    license: Option<String>,
+}

compliance-agent/src/pipeline/sbom/syft.rs

@@ -0,0 +1,355 @@
+use std::path::Path;
+
+use compliance_core::models::SbomEntry;
+use compliance_core::CoreError;
+
+#[tracing::instrument(skip_all, fields(repo_id = %repo_id))]
+pub(super) async fn run_syft(repo_path: &Path, repo_id: &str) -> Result<Vec<SbomEntry>, CoreError> {
+    let output = tokio::process::Command::new("syft")
+        .arg(repo_path)
+        .args(["-o", "cyclonedx-json"])
+        // Enable remote license lookups for all ecosystems
+        .env("SYFT_GOLANG_SEARCH_REMOTE_LICENSES", "true")
+        .env("SYFT_JAVASCRIPT_SEARCH_REMOTE_LICENSES", "true")
+        .env("SYFT_PYTHON_SEARCH_REMOTE_LICENSES", "true")
+        .env("SYFT_JAVA_USE_NETWORK", "true")
+        .output()
+        .await
+        .map_err(|e| CoreError::Scanner {
+            scanner: "syft".to_string(),
+            source: Box::new(e),
+        })?;
+
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        return Err(CoreError::Scanner {
+            scanner: "syft".to_string(),
+            source: format!("syft exited with {}: {stderr}", output.status).into(),
+        });
+    }
+
+    let cdx: CycloneDxBom = serde_json::from_slice(&output.stdout)?;
+    let entries = cdx
+        .components
+        .unwrap_or_default()
+        .into_iter()
+        .map(|c| {
+            let package_manager = c
+                .purl
+                .as_deref()
+                .and_then(extract_ecosystem_from_purl)
+                .unwrap_or_else(|| "unknown".to_string());
+            let mut entry = SbomEntry::new(
+                repo_id.to_string(),
+                c.name,
+                c.version.unwrap_or_else(|| "unknown".to_string()),
+                package_manager,
+            );
+            entry.purl = c.purl;
+            entry.license = c.licenses.and_then(|ls| extract_license(&ls));
+            entry
+        })
+        .collect();
+
+    Ok(entries)
+}
+
+// CycloneDX JSON types
+#[derive(serde::Deserialize)]
+struct CycloneDxBom {
+    components: Option<Vec<CdxComponent>>,
+}
+
+#[derive(serde::Deserialize)]
+struct CdxComponent {
+    name: String,
+    version: Option<String>,
+    #[serde(rename = "type")]
+    #[allow(dead_code)]
+    component_type: Option<String>,
+    purl: Option<String>,
+    licenses: Option<Vec<CdxLicenseWrapper>>,
+}
+
+#[derive(serde::Deserialize)]
+struct CdxLicenseWrapper {
+    license: Option<CdxLicense>,
+    /// SPDX license expression (e.g. "MIT OR Apache-2.0")
+    expression: Option<String>,
+}
+
+#[derive(serde::Deserialize)]
+struct CdxLicense {
+    id: Option<String>,
+    name: Option<String>,
+}
+
+/// Extract the best license string from CycloneDX license entries.
+/// Handles three formats: expression ("MIT OR Apache-2.0"), license.id ("MIT"), license.name ("MIT License").
+fn extract_license(entries: &[CdxLicenseWrapper]) -> Option<String> {
+    // First pass: look for SPDX expressions (most precise for dual-licensed packages)
+    for entry in entries {
+        if let Some(ref expr) = entry.expression {
+            if !expr.is_empty() {
+                return Some(expr.clone());
+            }
+        }
+    }
+    // Second pass: collect license.id or license.name from all entries
+    let parts: Vec<String> = entries
+        .iter()
+        .filter_map(|e| {
+            e.license.as_ref().and_then(|lic| {
+                lic.id
+                    .clone()
+                    .or_else(|| lic.name.clone())
+                    .filter(|s| !s.is_empty())
+            })
+        })
+        .collect();
+    if parts.is_empty() {
+        return None;
+    }
+    Some(parts.join(" OR "))
+}
+
+/// Extract the ecosystem/package-manager from a PURL string.
+/// e.g. "pkg:npm/lodash@4.17.21" -> "npm", "pkg:cargo/serde@1.0" -> "cargo"
+fn extract_ecosystem_from_purl(purl: &str) -> Option<String> {
+    let rest = purl.strip_prefix("pkg:")?;
+    let ecosystem = rest.split('/').next()?;
+    if ecosystem.is_empty() {
+        return None;
+    }
+    // Normalise common PURL types to user-friendly names
+    let normalised = match ecosystem {
+        "golang" => "go",
+        "pypi" => "pip",
+        _ => ecosystem,
+    };
+    Some(normalised.to_string())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    // --- extract_ecosystem_from_purl tests ---
+
+    #[test]
+    fn purl_npm() {
+        assert_eq!(
+            extract_ecosystem_from_purl("pkg:npm/lodash@4.17.21"),
+            Some("npm".to_string())
+        );
+    }
+
+    #[test]
+    fn purl_cargo() {
+        assert_eq!(
+            extract_ecosystem_from_purl("pkg:cargo/serde@1.0.197"),
+            Some("cargo".to_string())
+        );
+    }
+
+    #[test]
+    fn purl_golang_normalised() {
+        assert_eq!(
+            extract_ecosystem_from_purl("pkg:golang/github.com/gin-gonic/gin@1.9.1"),
+            Some("go".to_string())
+        );
+    }
+
+    #[test]
+    fn purl_pypi_normalised() {
+        assert_eq!(
+            extract_ecosystem_from_purl("pkg:pypi/requests@2.31.0"),
+            Some("pip".to_string())
+        );
+    }
+
+    #[test]
+    fn purl_maven() {
+        assert_eq!(
+            extract_ecosystem_from_purl("pkg:maven/org.apache.commons/commons-lang3@3.14.0"),
+            Some("maven".to_string())
+        );
+    }
+
+    #[test]
+    fn purl_missing_prefix() {
+        assert_eq!(extract_ecosystem_from_purl("npm/lodash@4.17.21"), None);
+    }
+
+    #[test]
+    fn purl_empty_ecosystem() {
+        assert_eq!(extract_ecosystem_from_purl("pkg:/lodash@4.17.21"), None);
+    }
+
+    #[test]
+    fn purl_empty_string() {
+        assert_eq!(extract_ecosystem_from_purl(""), None);
+    }
+
+    #[test]
+    fn purl_just_prefix() {
+        assert_eq!(extract_ecosystem_from_purl("pkg:"), None);
+    }
+
+    // --- extract_license tests ---
+
+    #[test]
+    fn license_from_expression() {
+        let entries = vec![CdxLicenseWrapper {
+            license: None,
+            expression: Some("MIT OR Apache-2.0".to_string()),
+        }];
+        assert_eq!(
+            extract_license(&entries),
+            Some("MIT OR Apache-2.0".to_string())
+        );
+    }
+
+    #[test]
+    fn license_from_id() {
+        let entries = vec![CdxLicenseWrapper {
+            license: Some(CdxLicense {
+                id: Some("MIT".to_string()),
+                name: None,
+            }),
+            expression: None,
+        }];
+        assert_eq!(extract_license(&entries), Some("MIT".to_string()));
+    }
+
+    #[test]
+    fn license_from_name_fallback() {
+        let entries = vec![CdxLicenseWrapper {
+            license: Some(CdxLicense {
+                id: None,
+                name: Some("MIT License".to_string()),
+            }),
+            expression: None,
+        }];
+        assert_eq!(extract_license(&entries), Some("MIT License".to_string()));
+    }
+
+    #[test]
+    fn license_expression_preferred_over_id() {
+        let entries = vec![
+            CdxLicenseWrapper {
+                license: Some(CdxLicense {
+                    id: Some("MIT".to_string()),
+                    name: None,
+                }),
+                expression: None,
+            },
+            CdxLicenseWrapper {
+                license: None,
+                expression: Some("MIT AND Apache-2.0".to_string()),
+            },
+        ];
+        // Expression should be preferred (first pass finds it)
+        assert_eq!(
+            extract_license(&entries),
+            Some("MIT AND Apache-2.0".to_string())
+        );
+    }
+
+    #[test]
+    fn license_multiple_ids_joined() {
+        let entries = vec![
+            CdxLicenseWrapper {
+                license: Some(CdxLicense {
+                    id: Some("MIT".to_string()),
+                    name: None,
+                }),
+                expression: None,
+            },
+            CdxLicenseWrapper {
+                license: Some(CdxLicense {
+                    id: Some("Apache-2.0".to_string()),
+                    name: None,
+                }),
+                expression: None,
+            },
+        ];
+        assert_eq!(
+            extract_license(&entries),
+            Some("MIT OR Apache-2.0".to_string())
+        );
+    }
+
+    #[test]
+    fn license_empty_entries() {
+        let entries: Vec<CdxLicenseWrapper> = vec![];
+        assert_eq!(extract_license(&entries), None);
+    }
+
+    #[test]
+    fn license_all_empty_strings() {
+        let entries = vec![CdxLicenseWrapper {
+            license: Some(CdxLicense {
+                id: Some(String::new()),
+                name: Some(String::new()),
+            }),
+            expression: Some(String::new()),
+        }];
+        assert_eq!(extract_license(&entries), None);
+    }
+
+    #[test]
+    fn license_none_fields() {
+        let entries = vec![CdxLicenseWrapper {
+            license: None,
+            expression: None,
+        }];
+        assert_eq!(extract_license(&entries), None);
+    }
+
+    // --- CycloneDX deserialization tests ---
+
+    #[test]
+    fn deserialize_cyclonedx_bom() {
+        let json = r#"{
+            "components": [
+                {
+                    "name": "serde",
+                    "version": "1.0.197",
+                    "type": "library",
+                    "purl": "pkg:cargo/serde@1.0.197",
+                    "licenses": [
+                        {"expression": "MIT OR Apache-2.0"}
+                    ]
+                }
+            ]
+        }"#;
+        let bom: CycloneDxBom = serde_json::from_str(json).unwrap();
+        let components = bom.components.unwrap();
+        assert_eq!(components.len(), 1);
+        assert_eq!(components[0].name, "serde");
+        assert_eq!(components[0].version, Some("1.0.197".to_string()));
+        assert_eq!(
+            components[0].purl,
+            Some("pkg:cargo/serde@1.0.197".to_string())
+        );
+    }
+
+    #[test]
+    fn deserialize_cyclonedx_no_components() {
+        let json = r#"{}"#;
+        let bom: CycloneDxBom = serde_json::from_str(json).unwrap();
+        assert!(bom.components.is_none());
+    }
+
+    #[test]
+    fn deserialize_cyclonedx_minimal_component() {
+        let json = r#"{"components": [{"name": "foo"}]}"#;
+        let bom: CycloneDxBom = serde_json::from_str(json).unwrap();
+        let c = &bom.components.unwrap()[0];
+        assert_eq!(c.name, "foo");
+        assert!(c.version.is_none());
+        assert!(c.purl.is_none());
+        assert!(c.licenses.is_none());
+    }
+}

compliance-agent/src/pipeline/semgrep.rs

@@ -17,6 +17,7 @@ impl Scanner for SemgrepScanner {
         ScanType::Sast
     }
 
+    #[tracing::instrument(skip_all)]
     async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
         let output = tokio::process::Command::new("semgrep")
             .args(["--config=auto", "--json", "--quiet"])
@@ -107,3 +108,124 @@ struct SemgrepExtra {
     #[serde(default)]
     metadata: Option<serde_json::Value>,
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn deserialize_semgrep_output() {
+        let json = r#"{
+            "results": [
+                {
+                    "check_id": "python.lang.security.audit.exec-detected",
+                    "path": "src/main.py",
+                    "start": {"line": 15},
+                    "extra": {
+                        "message": "Detected use of exec()",
+                        "severity": "ERROR",
+                        "lines": "exec(user_input)",
+                        "metadata": {"cwe": "CWE-78"}
+                    }
+                }
+            ]
+        }"#;
+        let output: SemgrepOutput = serde_json::from_str(json).unwrap();
+        assert_eq!(output.results.len(), 1);
+
+        let r = &output.results[0];
+        assert_eq!(r.check_id, "python.lang.security.audit.exec-detected");
+        assert_eq!(r.path, "src/main.py");
+        assert_eq!(r.start.line, 15);
+        assert_eq!(r.extra.message, "Detected use of exec()");
+        assert_eq!(r.extra.severity, "ERROR");
+        assert_eq!(r.extra.lines, "exec(user_input)");
+        assert_eq!(
+            r.extra
+                .metadata
+                .as_ref()
+                .unwrap()
+                .get("cwe")
+                .unwrap()
+                .as_str(),
+            Some("CWE-78")
+        );
+    }
+
+    #[test]
+    fn deserialize_semgrep_empty_results() {
+        let json = r#"{"results": []}"#;
+        let output: SemgrepOutput = serde_json::from_str(json).unwrap();
+        assert!(output.results.is_empty());
+    }
+
+    #[test]
+    fn deserialize_semgrep_no_metadata() {
+        let json = r#"{
+            "results": [
+                {
+                    "check_id": "rule-1",
+                    "path": "app.py",
+                    "start": {"line": 1},
+                    "extra": {
+                        "message": "found something",
+                        "severity": "WARNING",
+                        "lines": "import os"
+                    }
+                }
+            ]
+        }"#;
+        let output: SemgrepOutput = serde_json::from_str(json).unwrap();
+        assert!(output.results[0].extra.metadata.is_none());
+    }
+
+    #[test]
+    fn semgrep_severity_mapping() {
+        let cases = vec![
+            ("ERROR", "High"),
+            ("WARNING", "Medium"),
+            ("INFO", "Low"),
+            ("UNKNOWN", "Info"),
+        ];
+        for (input, expected) in cases {
+            let result = match input {
+                "ERROR" => "High",
+                "WARNING" => "Medium",
+                "INFO" => "Low",
+                _ => "Info",
+            };
+            assert_eq!(result, expected, "Severity for '{input}'");
+        }
+    }
+
+    #[test]
+    fn deserialize_semgrep_multiple_results() {
+        let json = r#"{
+            "results": [
+                {
+                    "check_id": "rule-a",
+                    "path": "a.py",
+                    "start": {"line": 1},
+                    "extra": {
+                        "message": "msg a",
+                        "severity": "ERROR",
+                        "lines": "line a"
+                    }
+                },
+                {
+                    "check_id": "rule-b",
+                    "path": "b.py",
+                    "start": {"line": 99},
+                    "extra": {
+                        "message": "msg b",
+                        "severity": "INFO",
+                        "lines": "line b"
+                    }
+                }
+            ]
+        }"#;
+        let output: SemgrepOutput = serde_json::from_str(json).unwrap();
+        assert_eq!(output.results.len(), 2);
+        assert_eq!(output.results[1].start.line, 99);
+    }
+}

compliance-agent/src/pipeline/tracker_dispatch.rs

@@ -0,0 +1,81 @@
+use compliance_core::models::TrackerIssue;
+use compliance_core::traits::issue_tracker::IssueTracker;
+
+use crate::trackers;
+
+/// Enum dispatch for issue trackers (async traits aren't dyn-compatible).
+pub(crate) enum TrackerDispatch {
+    GitHub(trackers::github::GitHubTracker),
+    GitLab(trackers::gitlab::GitLabTracker),
+    Gitea(trackers::gitea::GiteaTracker),
+    Jira(trackers::jira::JiraTracker),
+}
+
+impl TrackerDispatch {
+    pub(crate) fn name(&self) -> &str {
+        match self {
+            Self::GitHub(t) => t.name(),
+            Self::GitLab(t) => t.name(),
+            Self::Gitea(t) => t.name(),
+            Self::Jira(t) => t.name(),
+        }
+    }
+
+    pub(crate) async fn create_issue(
+        &self,
+        owner: &str,
+        repo: &str,
+        title: &str,
+        body: &str,
+        labels: &[String],
+    ) -> Result<TrackerIssue, compliance_core::error::CoreError> {
+        match self {
+            Self::GitHub(t) => t.create_issue(owner, repo, title, body, labels).await,
+            Self::GitLab(t) => t.create_issue(owner, repo, title, body, labels).await,
+            Self::Gitea(t) => t.create_issue(owner, repo, title, body, labels).await,
+            Self::Jira(t) => t.create_issue(owner, repo, title, body, labels).await,
+        }
+    }
+
+    pub(crate) async fn find_existing_issue(
+        &self,
+        owner: &str,
+        repo: &str,
+        fingerprint: &str,
+    ) -> Result<Option<TrackerIssue>, compliance_core::error::CoreError> {
+        match self {
+            Self::GitHub(t) => t.find_existing_issue(owner, repo, fingerprint).await,
+            Self::GitLab(t) => t.find_existing_issue(owner, repo, fingerprint).await,
+            Self::Gitea(t) => t.find_existing_issue(owner, repo, fingerprint).await,
+            Self::Jira(t) => t.find_existing_issue(owner, repo, fingerprint).await,
+        }
+    }
+
+    pub(crate) async fn create_pr_review(
+        &self,
+        owner: &str,
+        repo: &str,
+        pr_number: u64,
+        body: &str,
+        comments: Vec<compliance_core::traits::issue_tracker::ReviewComment>,
+    ) -> Result<(), compliance_core::error::CoreError> {
+        match self {
+            Self::GitHub(t) => {
+                t.create_pr_review(owner, repo, pr_number, body, comments)
+                    .await
+            }
+            Self::GitLab(t) => {
+                t.create_pr_review(owner, repo, pr_number, body, comments)
+                    .await
+            }
+            Self::Gitea(t) => {
+                t.create_pr_review(owner, repo, pr_number, body, comments)
+                    .await
+            }
+            Self::Jira(t) => {
+                t.create_pr_review(owner, repo, pr_number, body, comments)
+                    .await
+            }
+        }
+    }
+}

compliance-agent/src/ssh.rs

@@ -0,0 +1,53 @@
+use std::path::Path;
+
+use crate::error::AgentError;
+
+/// Ensure the SSH key pair exists at the given path, generating it if missing.
+/// Returns the public key contents.
+pub fn ensure_ssh_key(key_path: &str) -> Result<String, AgentError> {
+    let private_path = Path::new(key_path);
+    let public_path = private_path.with_extension("pub");
+
+    if private_path.exists() && public_path.exists() {
+        return std::fs::read_to_string(&public_path)
+            .map_err(|e| AgentError::Config(format!("Failed to read SSH public key: {e}")));
+    }
+
+    // Create parent directory
+    if let Some(parent) = private_path.parent() {
+        std::fs::create_dir_all(parent)?;
+    }
+
+    // Generate ed25519 key pair using ssh-keygen
+    let output = std::process::Command::new("ssh-keygen")
+        .args([
+            "-t",
+            "ed25519",
+            "-f",
+            key_path,
+            "-N",
+            "", // no passphrase
+            "-C",
+            "compliance-scanner-agent",
+        ])
+        .output()
+        .map_err(|e| AgentError::Config(format!("Failed to run ssh-keygen: {e}")))?;
+
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        return Err(AgentError::Config(format!("ssh-keygen failed: {stderr}")));
+    }
+
+    // Set correct permissions
+    #[cfg(unix)]
+    {
+        use std::os::unix::fs::PermissionsExt;
+        std::fs::set_permissions(private_path, std::fs::Permissions::from_mode(0o600))?;
+    }
+
+    let public_key = std::fs::read_to_string(&public_path)
+        .map_err(|e| AgentError::Config(format!("Failed to read generated SSH public key: {e}")))?;
+
+    tracing::info!("Generated new SSH key pair at {key_path}");
+    Ok(public_key)
+}

compliance-agent/src/trackers/gitea.rs

@@ -0,0 +1,274 @@
+use compliance_core::error::CoreError;
+use compliance_core::models::{TrackerIssue, TrackerType};
+use compliance_core::traits::issue_tracker::{IssueTracker, ReviewComment};
+use secrecy::{ExposeSecret, SecretString};
+
+pub struct GiteaTracker {
+    base_url: String,
+    http: reqwest::Client,
+    token: SecretString,
+}
+
+impl GiteaTracker {
+    pub fn new(base_url: String, token: SecretString) -> Self {
+        Self {
+            base_url: base_url.trim_end_matches('/').to_string(),
+            http: reqwest::Client::new(),
+            token,
+        }
+    }
+
+    fn api_url(&self, path: &str) -> String {
+        format!("{}/api/v1{}", self.base_url, path)
+    }
+}
+
+impl IssueTracker for GiteaTracker {
+    fn name(&self) -> &str {
+        "gitea"
+    }
+
+    async fn create_issue(
+        &self,
+        owner: &str,
+        repo: &str,
+        title: &str,
+        body: &str,
+        labels: &[String],
+    ) -> Result<TrackerIssue, CoreError> {
+        let url = self.api_url(&format!("/repos/{owner}/{repo}/issues"));
+
+        // Gitea expects label IDs (integers), not names. Append label names
+        // to the body instead since resolving IDs would require extra API calls.
+        let mut full_body = body.to_string();
+        if !labels.is_empty() {
+            full_body.push_str("\n\n**Labels:** ");
+            full_body.push_str(&labels.join(", "));
+        }
+        let payload = serde_json::json!({
+            "title": title,
+            "body": full_body,
+        });
+
+        let resp = self
+            .http
+            .post(&url)
+            .header(
+                "Authorization",
+                format!("token {}", self.token.expose_secret()),
+            )
+            .json(&payload)
+            .send()
+            .await
+            .map_err(|e| CoreError::IssueTracker(format!("Gitea create issue failed: {e}")))?;
+
+        if !resp.status().is_success() {
+            let status = resp.status();
+            let text = resp.text().await.unwrap_or_default();
+            return Err(CoreError::IssueTracker(format!(
+                "Gitea returned {status}: {text}"
+            )));
+        }
+
+        let issue: serde_json::Value = resp
+            .json()
+            .await
+            .map_err(|e| CoreError::IssueTracker(format!("Failed to parse Gitea response: {e}")))?;
+
+        Ok(TrackerIssue::new(
+            String::new(),
+            TrackerType::Gitea,
+            issue["number"].to_string(),
+            issue["html_url"].as_str().unwrap_or("").to_string(),
+            title.to_string(),
+        ))
+    }
+
+    async fn update_issue_status(
+        &self,
+        owner: &str,
+        repo: &str,
+        external_id: &str,
+        status: &str,
+    ) -> Result<(), CoreError> {
+        let url = self.api_url(&format!("/repos/{owner}/{repo}/issues/{external_id}"));
+
+        let state = match status {
+            "closed" | "resolved" => "closed",
+            _ => "open",
+        };
+
+        let resp = self
+            .http
+            .patch(&url)
+            .header(
+                "Authorization",
+                format!("token {}", self.token.expose_secret()),
+            )
+            .json(&serde_json::json!({ "state": state }))
+            .send()
+            .await
+            .map_err(|e| CoreError::IssueTracker(format!("Gitea update issue failed: {e}")))?;
+
+        if !resp.status().is_success() {
+            let status = resp.status();
+            let text = resp.text().await.unwrap_or_default();
+            return Err(CoreError::IssueTracker(format!(
+                "Gitea update issue returned {status}: {text}"
+            )));
+        }
+
+        Ok(())
+    }
+
+    async fn add_comment(
+        &self,
+        owner: &str,
+        repo: &str,
+        external_id: &str,
+        body: &str,
+    ) -> Result<(), CoreError> {
+        let url = self.api_url(&format!(
+            "/repos/{owner}/{repo}/issues/{external_id}/comments"
+        ));
+
+        let resp = self
+            .http
+            .post(&url)
+            .header(
+                "Authorization",
+                format!("token {}", self.token.expose_secret()),
+            )
+            .json(&serde_json::json!({ "body": body }))
+            .send()
+            .await
+            .map_err(|e| CoreError::IssueTracker(format!("Gitea add comment failed: {e}")))?;
+
+        if !resp.status().is_success() {
+            let status = resp.status();
+            let text = resp.text().await.unwrap_or_default();
+            return Err(CoreError::IssueTracker(format!(
+                "Gitea add comment returned {status}: {text}"
+            )));
+        }
+
+        Ok(())
+    }
+
+    async fn create_pr_review(
+        &self,
+        owner: &str,
+        repo: &str,
+        pr_number: u64,
+        body: &str,
+        comments: Vec<ReviewComment>,
+    ) -> Result<(), CoreError> {
+        let url = self.api_url(&format!("/repos/{owner}/{repo}/pulls/{pr_number}/reviews"));
+
+        let review_comments: Vec<serde_json::Value> = comments
+            .iter()
+            .map(|c| {
+                serde_json::json!({
+                    "path": c.path,
+                    "new_position": c.line,
+                    "body": c.body,
+                })
+            })
+            .collect();
+
+        let resp = self
+            .http
+            .post(&url)
+            .header(
+                "Authorization",
+                format!("token {}", self.token.expose_secret()),
+            )
+            .json(&serde_json::json!({
+                "body": body,
+                "event": "COMMENT",
+                "comments": review_comments,
+            }))
+            .send()
+            .await
+            .map_err(|e| CoreError::IssueTracker(format!("Gitea PR review failed: {e}")))?;
+
+        if !resp.status().is_success() {
+            let status = resp.status();
+            let text = resp.text().await.unwrap_or_default();
+
+            // If inline comments caused the failure, retry with just the summary body
+            if !comments.is_empty() {
+                tracing::warn!(
+                    "Gitea PR review with inline comments failed ({status}): {text}, retrying as plain comment"
+                );
+                let fallback_url = self.api_url(&format!(
+                    "/repos/{owner}/{repo}/issues/{pr_number}/comments"
+                ));
+                let fallback_resp = self
+                    .http
+                    .post(&fallback_url)
+                    .header(
+                        "Authorization",
+                        format!("token {}", self.token.expose_secret()),
+                    )
+                    .json(&serde_json::json!({ "body": body }))
+                    .send()
+                    .await
+                    .map_err(|e| {
+                        CoreError::IssueTracker(format!("Gitea PR comment fallback failed: {e}"))
+                    })?;
+
+                if !fallback_resp.status().is_success() {
+                    let fb_status = fallback_resp.status();
+                    let fb_text = fallback_resp.text().await.unwrap_or_default();
+                    return Err(CoreError::IssueTracker(format!(
+                        "Gitea PR comment fallback returned {fb_status}: {fb_text}"
+                    )));
+                }
+
+                return Ok(());
+            }
+
+            return Err(CoreError::IssueTracker(format!(
+                "Gitea PR review returned {status}: {text}"
+            )));
+        }
+
+        Ok(())
+    }
+
+    async fn find_existing_issue(
+        &self,
+        owner: &str,
+        repo: &str,
+        fingerprint: &str,
+    ) -> Result<Option<TrackerIssue>, CoreError> {
+        let url = self.api_url(&format!(
+            "/repos/{owner}/{repo}/issues?type=issues&state=all&q={fingerprint}"
+        ));
+
+        let resp = self
+            .http
+            .get(&url)
+            .header(
+                "Authorization",
+                format!("token {}", self.token.expose_secret()),
+            )
+            .send()
+            .await
+            .map_err(|e| CoreError::IssueTracker(format!("Gitea search failed: {e}")))?;
+
+        let issues: Vec<serde_json::Value> = resp.json().await.unwrap_or_default();
+        if let Some(issue) = issues.first() {
+            Ok(Some(TrackerIssue::new(
+                String::new(),
+                TrackerType::Gitea,
+                issue["number"].to_string(),
+                issue["html_url"].as_str().unwrap_or("").to_string(),
+                issue["title"].as_str().unwrap_or("").to_string(),
+            )))
+        } else {
+            Ok(None)
+        }
+    }
+}

compliance-agent/src/trackers/mod.rs

@@ -1,3 +1,4 @@
+pub mod gitea;
 pub mod github;
 pub mod gitlab;
 pub mod jira;

compliance-agent/src/webhooks/gitea.rs

@@ -0,0 +1,138 @@
+use std::sync::Arc;
+
+use axum::body::Bytes;
+use axum::extract::{Extension, Path};
+use axum::http::{HeaderMap, StatusCode};
+use hmac::{Hmac, Mac};
+use sha2::Sha256;
+
+use compliance_core::models::ScanTrigger;
+
+use crate::agent::ComplianceAgent;
+
+type HmacSha256 = Hmac<Sha256>;
+
+pub async fn handle_gitea_webhook(
+    Extension(agent): Extension<Arc<ComplianceAgent>>,
+    Path(repo_id): Path<String>,
+    headers: HeaderMap,
+    body: Bytes,
+) -> StatusCode {
+    // Look up the repo to get its webhook secret
+    let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
+        Ok(oid) => oid,
+        Err(_) => return StatusCode::NOT_FOUND,
+    };
+    let repo = match agent
+        .db
+        .repositories()
+        .find_one(mongodb::bson::doc! { "_id": oid })
+        .await
+    {
+        Ok(Some(repo)) => repo,
+        _ => {
+            tracing::warn!("Gitea webhook: repo {repo_id} not found");
+            return StatusCode::NOT_FOUND;
+        }
+    };
+
+    // Verify HMAC-SHA256 signature using the per-repo secret
+    if let Some(secret) = &repo.webhook_secret {
+        let signature = headers
+            .get("x-gitea-signature")
+            .and_then(|v| v.to_str().ok())
+            .unwrap_or("");
+
+        if !verify_signature(secret, &body, signature) {
+            tracing::warn!("Gitea webhook: invalid signature for repo {repo_id}");
+            return StatusCode::UNAUTHORIZED;
+        }
+    }
+
+    let event = headers
+        .get("x-gitea-event")
+        .and_then(|v| v.to_str().ok())
+        .unwrap_or("");
+
+    let payload: serde_json::Value = match serde_json::from_slice(&body) {
+        Ok(v) => v,
+        Err(e) => {
+            tracing::warn!("Gitea webhook: invalid JSON: {e}");
+            return StatusCode::BAD_REQUEST;
+        }
+    };
+
+    match event {
+        "push" => {
+            let agent_clone = (*agent).clone();
+            let repo_id = repo_id.clone();
+            tokio::spawn(async move {
+                tracing::info!("Gitea push webhook: triggering scan for {repo_id}");
+                if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
+                    tracing::error!("Webhook-triggered scan failed: {e}");
+                }
+            });
+            StatusCode::OK
+        }
+        "pull_request" => handle_pull_request(agent, &repo_id, &payload).await,
+        _ => {
+            tracing::debug!("Gitea webhook: ignoring event '{event}'");
+            StatusCode::OK
+        }
+    }
+}
+
+async fn handle_pull_request(
+    agent: Arc<ComplianceAgent>,
+    repo_id: &str,
+    payload: &serde_json::Value,
+) -> StatusCode {
+    let action = payload["action"].as_str().unwrap_or("");
+    if action != "opened" && action != "synchronized" {
+        return StatusCode::OK;
+    }
+
+    let pr_number = payload["pull_request"]["number"].as_u64().unwrap_or(0);
+    let head_sha = payload["pull_request"]["head"]["sha"]
+        .as_str()
+        .unwrap_or("");
+    let base_sha = payload["pull_request"]["base"]["sha"]
+        .as_str()
+        .unwrap_or("");
+
+    if pr_number == 0 || head_sha.is_empty() || base_sha.is_empty() {
+        tracing::warn!("Gitea PR webhook: missing required fields");
+        return StatusCode::BAD_REQUEST;
+    }
+
+    let repo_id = repo_id.to_string();
+    let head_sha = head_sha.to_string();
+    let base_sha = base_sha.to_string();
+    let agent_clone = (*agent).clone();
+    tokio::spawn(async move {
+        tracing::info!("Gitea PR webhook: reviewing PR #{pr_number} on {repo_id}");
+        if let Err(e) = agent_clone
+            .run_pr_review(&repo_id, pr_number, &base_sha, &head_sha)
+            .await
+        {
+            tracing::error!("PR review failed for #{pr_number}: {e}");
+        }
+    });
+
+    StatusCode::OK
+}
+
+fn verify_signature(secret: &str, body: &[u8], signature: &str) -> bool {
+    // Gitea sends raw hex (no sha256= prefix)
+    let sig_bytes = match hex::decode(signature) {
+        Ok(b) => b,
+        Err(_) => return false,
+    };
+
+    let mut mac = match HmacSha256::new_from_slice(secret.as_bytes()) {
+        Ok(m) => m,
+        Err(_) => return false,
+    };
+    mac.update(body);
+    mac.verify_slice(&sig_bytes).is_ok()
+}

compliance-agent/src/webhooks/github.rs

@@ -1,10 +1,9 @@
 use std::sync::Arc;
 
 use axum::body::Bytes;
-use axum::extract::Extension;
+use axum::extract::{Extension, Path};
 use axum::http::{HeaderMap, StatusCode};
 use hmac::{Hmac, Mac};
-use secrecy::ExposeSecret;
 use sha2::Sha256;
 
 use compliance_core::models::ScanTrigger;
@@ -15,18 +14,37 @@ type HmacSha256 = Hmac<Sha256>;
 
 pub async fn handle_github_webhook(
     Extension(agent): Extension<Arc<ComplianceAgent>>,
+    Path(repo_id): Path<String>,
     headers: HeaderMap,
     body: Bytes,
 ) -> StatusCode {
-    // Verify HMAC signature
+    // Look up the repo to get its webhook secret
-    if let Some(secret) = &agent.config.github_webhook_secret {
+    let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
+        Ok(oid) => oid,
+        Err(_) => return StatusCode::NOT_FOUND,
+    };
+    let repo = match agent
+        .db
+        .repositories()
+        .find_one(mongodb::bson::doc! { "_id": oid })
+        .await
+    {
+        Ok(Some(repo)) => repo,
+        _ => {
+            tracing::warn!("GitHub webhook: repo {repo_id} not found");
+            return StatusCode::NOT_FOUND;
+        }
+    };
+
+    // Verify HMAC-SHA256 signature using the per-repo secret
+    if let Some(secret) = &repo.webhook_secret {
         let signature = headers
             .get("x-hub-signature-256")
             .and_then(|v| v.to_str().ok())
             .unwrap_or("");
 
-        if !verify_signature(secret.expose_secret(), &body, signature) {
+        if !verify_signature(secret, &body, signature) {
-            tracing::warn!("GitHub webhook: invalid signature");
+            tracing::warn!("GitHub webhook: invalid signature for repo {repo_id}");
             return StatusCode::UNAUTHORIZED;
         }
     }
@@ -45,8 +63,18 @@ pub async fn handle_github_webhook(
     };
 
     match event {
-        "push" => handle_push(agent, &payload).await,
+        "push" => {
-        "pull_request" => handle_pull_request(agent, &payload).await,
+            let agent_clone = (*agent).clone();
+            let repo_id = repo_id.clone();
+            tokio::spawn(async move {
+                tracing::info!("GitHub push webhook: triggering scan for {repo_id}");
+                if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
+                    tracing::error!("Webhook-triggered scan failed: {e}");
+                }
+            });
+            StatusCode::OK
+        }
+        "pull_request" => handle_pull_request(agent, &repo_id, &payload).await,
         _ => {
             tracing::debug!("GitHub webhook: ignoring event '{event}'");
             StatusCode::OK
@@ -54,43 +82,9 @@ pub async fn handle_github_webhook(
     }
 }
 
-async fn handle_push(agent: Arc<ComplianceAgent>, payload: &serde_json::Value) -> StatusCode {
-    let repo_url = payload["repository"]["clone_url"]
-        .as_str()
-        .or_else(|| payload["repository"]["html_url"].as_str())
-        .unwrap_or("");
-
-    if repo_url.is_empty() {
-        return StatusCode::BAD_REQUEST;
-    }
-
-    // Find matching tracked repository
-    let repo = agent
-        .db
-        .repositories()
-        .find_one(mongodb::bson::doc! { "git_url": repo_url })
-        .await
-        .ok()
-        .flatten();
-
-    if let Some(repo) = repo {
-        let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
-        let agent_clone = (*agent).clone();
-        tokio::spawn(async move {
-            tracing::info!("GitHub push webhook: triggering scan for {repo_id}");
-            if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
-                tracing::error!("Webhook-triggered scan failed: {e}");
-            }
-        });
-    } else {
-        tracing::debug!("GitHub push webhook: no tracked repo for {repo_url}");
-    }
-
-    StatusCode::OK
-}
-
 async fn handle_pull_request(
-    _agent: Arc<ComplianceAgent>,
+    agent: Arc<ComplianceAgent>,
+    repo_id: &str,
     payload: &serde_json::Value,
 ) -> StatusCode {
     let action = payload["action"].as_str().unwrap_or("");
@@ -98,21 +92,37 @@ async fn handle_pull_request(
         return StatusCode::OK;
     }
 
-    let repo_url = payload["repository"]["clone_url"].as_str().unwrap_or("");
     let pr_number = payload["pull_request"]["number"].as_u64().unwrap_or(0);
+    let head_sha = payload["pull_request"]["head"]["sha"]
+        .as_str()
+        .unwrap_or("");
+    let base_sha = payload["pull_request"]["base"]["sha"]
+        .as_str()
+        .unwrap_or("");
 
-    if repo_url.is_empty() || pr_number == 0 {
+    if pr_number == 0 || head_sha.is_empty() || base_sha.is_empty() {
         return StatusCode::BAD_REQUEST;
     }
 
-    tracing::info!("GitHub PR webhook: PR #{pr_number} {action} on {repo_url}");
+    let repo_id = repo_id.to_string();
-    // PR review scan would be triggered here - runs incremental SAST on diff
+    let head_sha = head_sha.to_string();
-    // and posts review comments via the GitHub tracker
+    let base_sha = base_sha.to_string();
+    let agent_clone = (*agent).clone();
+    tokio::spawn(async move {
+        tracing::info!("GitHub PR webhook: reviewing PR #{pr_number} on {repo_id}");
+        if let Err(e) = agent_clone
+            .run_pr_review(&repo_id, pr_number, &base_sha, &head_sha)
+            .await
+        {
+            tracing::error!("PR review failed for #{pr_number}: {e}");
+        }
+    });
 
     StatusCode::OK
 }
 
 fn verify_signature(secret: &str, body: &[u8], signature: &str) -> bool {
+    // GitHub sends sha256=<hex>
     let sig = signature.strip_prefix("sha256=").unwrap_or(signature);
     let sig_bytes = match hex::decode(sig) {
         Ok(b) => b,

compliance-agent/src/webhooks/gitlab.rs

@@ -1,9 +1,8 @@
 use std::sync::Arc;
 
 use axum::body::Bytes;
-use axum::extract::Extension;
+use axum::extract::{Extension, Path};
 use axum::http::{HeaderMap, StatusCode};
-use secrecy::ExposeSecret;
 
 use compliance_core::models::ScanTrigger;
 
@@ -11,18 +10,37 @@ use crate::agent::ComplianceAgent;
 
 pub async fn handle_gitlab_webhook(
     Extension(agent): Extension<Arc<ComplianceAgent>>,
+    Path(repo_id): Path<String>,
     headers: HeaderMap,
     body: Bytes,
 ) -> StatusCode {
-    // Verify GitLab token
+    // Look up the repo to get its webhook secret
-    if let Some(secret) = &agent.config.gitlab_webhook_secret {
+    let oid = match mongodb::bson::oid::ObjectId::parse_str(&repo_id) {
+        Ok(oid) => oid,
+        Err(_) => return StatusCode::NOT_FOUND,
+    };
+    let repo = match agent
+        .db
+        .repositories()
+        .find_one(mongodb::bson::doc! { "_id": oid })
+        .await
+    {
+        Ok(Some(repo)) => repo,
+        _ => {
+            tracing::warn!("GitLab webhook: repo {repo_id} not found");
+            return StatusCode::NOT_FOUND;
+        }
+    };
+
+    // GitLab sends the secret token in X-Gitlab-Token header (plain text comparison)
+    if let Some(secret) = &repo.webhook_secret {
         let token = headers
             .get("x-gitlab-token")
             .and_then(|v| v.to_str().ok())
             .unwrap_or("");
 
-        if token != secret.expose_secret() {
+        if token != secret {
-            tracing::warn!("GitLab webhook: invalid token");
+            tracing::warn!("GitLab webhook: invalid token for repo {repo_id}");
             return StatusCode::UNAUTHORIZED;
         }
     }
@@ -38,8 +56,18 @@ pub async fn handle_gitlab_webhook(
     let event_type = payload["object_kind"].as_str().unwrap_or("");
 
     match event_type {
-        "push" => handle_push(agent, &payload).await,
+        "push" => {
-        "merge_request" => handle_merge_request(agent, &payload).await,
+            let agent_clone = (*agent).clone();
+            let repo_id = repo_id.clone();
+            tokio::spawn(async move {
+                tracing::info!("GitLab push webhook: triggering scan for {repo_id}");
+                if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
+                    tracing::error!("Webhook-triggered scan failed: {e}");
+                }
+            });
+            StatusCode::OK
+        }
+        "merge_request" => handle_merge_request(agent, &repo_id, &payload).await,
         _ => {
             tracing::debug!("GitLab webhook: ignoring event '{event_type}'");
             StatusCode::OK
@@ -47,40 +75,9 @@ pub async fn handle_gitlab_webhook(
     }
 }
 
-async fn handle_push(agent: Arc<ComplianceAgent>, payload: &serde_json::Value) -> StatusCode {
-    let repo_url = payload["project"]["git_http_url"]
-        .as_str()
-        .or_else(|| payload["project"]["web_url"].as_str())
-        .unwrap_or("");
-
-    if repo_url.is_empty() {
-        return StatusCode::BAD_REQUEST;
-    }
-
-    let repo = agent
-        .db
-        .repositories()
-        .find_one(mongodb::bson::doc! { "git_url": repo_url })
-        .await
-        .ok()
-        .flatten();
-
-    if let Some(repo) = repo {
-        let repo_id = repo.id.map(|id| id.to_hex()).unwrap_or_default();
-        let agent_clone = (*agent).clone();
-        tokio::spawn(async move {
-            tracing::info!("GitLab push webhook: triggering scan for {repo_id}");
-            if let Err(e) = agent_clone.run_scan(&repo_id, ScanTrigger::Webhook).await {
-                tracing::error!("Webhook-triggered scan failed: {e}");
-            }
-        });
-    }
-
-    StatusCode::OK
-}
-
 async fn handle_merge_request(
-    _agent: Arc<ComplianceAgent>,
+    agent: Arc<ComplianceAgent>,
+    repo_id: &str,
     payload: &serde_json::Value,
 ) -> StatusCode {
     let action = payload["object_attributes"]["action"]
@@ -91,7 +88,31 @@ async fn handle_merge_request(
     }
 
     let mr_iid = payload["object_attributes"]["iid"].as_u64().unwrap_or(0);
-    tracing::info!("GitLab MR webhook: MR !{mr_iid} {action}");
+    let head_sha = payload["object_attributes"]["last_commit"]["id"]
+        .as_str()
+        .unwrap_or("");
+    let base_sha = payload["object_attributes"]["diff_refs"]["base_sha"]
+        .as_str()
+        .unwrap_or("");
+
+    if mr_iid == 0 || head_sha.is_empty() || base_sha.is_empty() {
+        tracing::warn!("GitLab MR webhook: missing required fields");
+        return StatusCode::BAD_REQUEST;
+    }
+
+    let repo_id = repo_id.to_string();
+    let head_sha = head_sha.to_string();
+    let base_sha = base_sha.to_string();
+    let agent_clone = (*agent).clone();
+    tokio::spawn(async move {
+        tracing::info!("GitLab MR webhook: reviewing MR !{mr_iid} on {repo_id}");
+        if let Err(e) = agent_clone
+            .run_pr_review(&repo_id, mr_iid, &base_sha, &head_sha)
+            .await
+        {
+            tracing::error!("MR review failed for !{mr_iid}: {e}");
+        }
+    });
 
     StatusCode::OK
 }

compliance-agent/src/webhooks/mod.rs

@@ -1,3 +1,4 @@
+pub mod gitea;
 pub mod github;
 pub mod gitlab;
 pub mod server;

compliance-agent/src/webhooks/server.rs

@@ -5,12 +5,23 @@ use axum::{Extension, Router};
 
 use crate::agent::ComplianceAgent;
 use crate::error::AgentError;
-use crate::webhooks::{github, gitlab};
+use crate::webhooks::{gitea, github, gitlab};
 
 pub async fn start_webhook_server(agent: &ComplianceAgent) -> Result<(), AgentError> {
     let app = Router::new()
-        .route("/webhook/github", post(github::handle_github_webhook))
+        // Per-repo webhook URLs: /webhook/{platform}/{repo_id}
-        .route("/webhook/gitlab", post(gitlab::handle_gitlab_webhook))
+        .route(
+            "/webhook/github/{repo_id}",
+            post(github::handle_github_webhook),
+        )
+        .route(
+            "/webhook/gitlab/{repo_id}",
+            post(gitlab::handle_gitlab_webhook),
+        )
+        .route(
+            "/webhook/gitea/{repo_id}",
+            post(gitea::handle_gitea_webhook),
+        )
         .layer(Extension(Arc::new(agent.clone())));
 
     let addr = "0.0.0.0:3002";

compliance-agent/tests/common/mod.rs

@@ -0,0 +1,3 @@
+// Shared test helpers for compliance-agent integration tests.
+//
+// Add database mocks, fixtures, and test utilities here.

compliance-agent/tests/integration/mod.rs

@@ -0,0 +1,4 @@
+// Integration tests for the compliance-agent crate.
+//
+// Add tests that exercise the full pipeline, API handlers,
+// and cross-module interactions here.

compliance-core/Cargo.toml

@@ -9,6 +9,15 @@ workspace = true
 [features]
 default = ["mongodb"]
 mongodb = ["dep:mongodb"]
+telemetry = [
+    "dep:opentelemetry",
+    "dep:opentelemetry_sdk",
+    "dep:opentelemetry-otlp",
+    "dep:opentelemetry-appender-tracing",
+    "dep:tracing-opentelemetry",
+    "dep:tracing-subscriber",
+    "dep:tracing",
+]
 
 [dependencies]
 serde = { workspace = true }
@@ -21,3 +30,10 @@ uuid = { workspace = true }
 secrecy = { workspace = true }
 bson = { version = "2", features = ["chrono-0_4"] }
 mongodb = { workspace = true, optional = true }
+opentelemetry = { version = "0.29", optional = true }
+opentelemetry_sdk = { version = "0.29", features = ["rt-tokio"], optional = true }
+opentelemetry-otlp = { version = "0.29", features = ["http", "reqwest-rustls"], optional = true }
+opentelemetry-appender-tracing = { version = "0.29", optional = true }
+tracing-opentelemetry = { version = "0.30", optional = true }
+tracing-subscriber = { workspace = true, optional = true }
+tracing = { workspace = true, optional = true }

compliance-core/src/config.rs

@@ -24,6 +24,19 @@ pub struct AgentConfig {
     pub scan_schedule: String,
     pub cve_monitor_schedule: String,
     pub git_clone_base_path: String,
+    pub ssh_key_path: String,
+    pub keycloak_url: Option<String>,
+    pub keycloak_realm: Option<String>,
+    pub keycloak_admin_username: Option<String>,
+    pub keycloak_admin_password: Option<SecretString>,
+    // Pentest defaults
+    pub pentest_verification_email: Option<String>,
+    pub pentest_imap_host: Option<String>,
+    pub pentest_imap_port: Option<u16>,
+    /// Use implicit TLS (IMAPS, port 993) instead of plain IMAP.
+    pub pentest_imap_tls: bool,
+    pub pentest_imap_username: Option<String>,
+    pub pentest_imap_password: Option<SecretString>,
 }
 
 #[derive(Clone, Debug, Serialize, Deserialize)]
@@ -32,4 +45,5 @@ pub struct DashboardConfig {
     pub mongodb_database: String,
     pub agent_api_url: String,
     pub dashboard_port: u16,
+    pub mcp_endpoint_url: Option<String>,
 }

compliance-core/src/lib.rs

@@ -1,6 +1,8 @@
 pub mod config;
 pub mod error;
 pub mod models;
+#[cfg(feature = "telemetry")]
+pub mod telemetry;
 pub mod traits;
 
 pub use config::{AgentConfig, DashboardConfig};

compliance-core/src/models/auth.rs

@@ -0,0 +1,14 @@
+use serde::{Deserialize, Serialize};
+
+/// Authentication state returned by the `check_auth` server function.
+///
+/// When no valid session exists, `authenticated` is `false` and all
+/// other fields are empty strings.
+#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq)]
+pub struct AuthInfo {
+    pub authenticated: bool,
+    pub sub: String,
+    pub email: String,
+    pub name: String,
+    pub avatar_url: String,
+}

compliance-core/src/models/cve.rs

@@ -23,6 +23,7 @@ pub struct CveAlert {
     pub summary: Option<String>,
     pub llm_impact_summary: Option<String>,
     pub references: Vec<String>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub created_at: DateTime<Utc>,
 }
 

compliance-core/src/models/dast.rs

@@ -58,7 +58,9 @@ pub struct DastTarget {
     pub rate_limit: u32,
     /// Whether destructive tests (DELETE, PUT) are allowed
     pub allow_destructive: bool,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub created_at: DateTime<Utc>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub updated_at: DateTime<Utc>,
 }
 
@@ -135,7 +137,9 @@ pub struct DastScanRun {
     pub error_message: Option<String>,
     /// Linked SAST scan run ID (if triggered as part of pipeline)
     pub sast_scan_run_id: Option<String>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub started_at: DateTime<Utc>,
+    #[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
     pub completed_at: Option<DateTime<Utc>>,
 }
 
@@ -172,6 +176,16 @@ pub enum DastVulnType {
     InformationDisclosure,
     SecurityMisconfiguration,
     BrokenAuth,
+    DnsMisconfiguration,
+    EmailSecurity,
+    TlsMisconfiguration,
+    CookieSecurity,
+    CspIssue,
+    CorsMisconfiguration,
+    RateLimitAbsent,
+    ConsoleLogLeakage,
+    SecurityHeaderMissing,
+    KnownCveExploit,
     Other,
 }
 
@@ -188,6 +202,16 @@ impl std::fmt::Display for DastVulnType {
             Self::InformationDisclosure => write!(f, "information_disclosure"),
             Self::SecurityMisconfiguration => write!(f, "security_misconfiguration"),
             Self::BrokenAuth => write!(f, "broken_auth"),
+            Self::DnsMisconfiguration => write!(f, "dns_misconfiguration"),
+            Self::EmailSecurity => write!(f, "email_security"),
+            Self::TlsMisconfiguration => write!(f, "tls_misconfiguration"),
+            Self::CookieSecurity => write!(f, "cookie_security"),
+            Self::CspIssue => write!(f, "csp_issue"),
+            Self::CorsMisconfiguration => write!(f, "cors_misconfiguration"),
+            Self::RateLimitAbsent => write!(f, "rate_limit_absent"),
+            Self::ConsoleLogLeakage => write!(f, "console_log_leakage"),
+            Self::SecurityHeaderMissing => write!(f, "security_header_missing"),
+            Self::KnownCveExploit => write!(f, "known_cve_exploit"),
             Self::Other => write!(f, "other"),
         }
     }
@@ -240,6 +264,9 @@ pub struct DastFinding {
     pub remediation: Option<String>,
     /// Linked SAST finding ID (if correlated)
     pub linked_sast_finding_id: Option<String>,
+    /// Pentest session that produced this finding (if AI-driven)
+    pub session_id: Option<String>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub created_at: DateTime<Utc>,
 }
 
@@ -271,6 +298,7 @@ impl DastFinding {
             evidence: Vec::new(),
             remediation: None,
             linked_sast_finding_id: None,
+            session_id: None,
             created_at: Utc::now(),
         }
     }

compliance-core/src/models/finding.rs

@@ -71,7 +71,14 @@ pub struct Finding {
     pub status: FindingStatus,
     pub tracker_issue_url: Option<String>,
     pub scan_run_id: Option<String>,
+    /// LLM triage action and reasoning
+    pub triage_action: Option<String>,
+    pub triage_rationale: Option<String>,
+    /// Developer feedback on finding quality
+    pub developer_feedback: Option<String>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub created_at: DateTime<Utc>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub updated_at: DateTime<Utc>,
 }
 
@@ -108,6 +115,9 @@ impl Finding {
             status: FindingStatus::Open,
             tracker_issue_url: None,
             scan_run_id: None,
+            triage_action: None,
+            triage_rationale: None,
+            developer_feedback: None,
             created_at: now,
             updated_at: now,
         }

compliance-core/src/models/graph.rs

@@ -122,7 +122,9 @@ pub struct GraphBuildRun {
     pub community_count: u32,
     pub languages_parsed: Vec<String>,
     pub error_message: Option<String>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub started_at: DateTime<Utc>,
+    #[serde(default, with = "super::serde_helpers::opt_bson_datetime")]
     pub completed_at: Option<DateTime<Utc>>,
 }
 
@@ -164,6 +166,7 @@ pub struct ImpactAnalysis {
     pub direct_callers: Vec<String>,
     /// Direct callees of the affected function
     pub direct_callees: Vec<String>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub created_at: DateTime<Utc>,
 }
 

compliance-core/src/models/issue.rs

@@ -6,6 +6,7 @@ use serde::{Deserialize, Serialize};
 pub enum TrackerType {
     GitHub,
     GitLab,
+    Gitea,
     Jira,
 }
 
@@ -14,6 +15,7 @@ impl std::fmt::Display for TrackerType {
         match self {
             Self::GitHub => write!(f, "github"),
             Self::GitLab => write!(f, "gitlab"),
+            Self::Gitea => write!(f, "gitea"),
             Self::Jira => write!(f, "jira"),
         }
     }
@@ -49,7 +51,9 @@ pub struct TrackerIssue {
     pub external_url: String,
     pub title: String,
     pub status: IssueStatus,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub created_at: DateTime<Utc>,
+    #[serde(with = "super::serde_helpers::bson_datetime")]
     pub updated_at: DateTime<Utc>,
 }