feat: pentest onboarding — streaming, browser automation, reports, user cleanup (#16)

Complete pentest feature overhaul: SSE streaming, session-persistent browser tool (CDP), AES-256 credential encryption, auto-screenshots in reports, code-level remediation correlation, SAST triage chunking, context window optimization, test user cleanup (Keycloak/Auth0/Okta), wizard dropdowns, attack chain improvements, architecture docs with Mermaid diagrams.

Co-authored-by: Sharang Parnerkar <parnerkarsharang@gmail.com>
Reviewed-on: #16

compliance-core/src/config.rs

@@ -27,6 +27,14 @@ pub struct AgentConfig {
     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>,
+    pub pentest_imap_username: Option<String>,
+    pub pentest_imap_password: Option<SecretString>,
 }
 
 #[derive(Clone, Debug, Serialize, Deserialize)]

compliance-core/src/models/mod.rs

@@ -28,8 +28,9 @@ pub use graph::{
 pub use issue::{IssueStatus, TrackerIssue, TrackerType};
 pub use mcp::{McpServerConfig, McpServerStatus, McpTransport};
 pub use pentest::{
-    AttackChainNode, AttackNodeStatus, CodeContextHint, PentestEvent, PentestMessage,
-    PentestSession, PentestStats, PentestStatus, PentestStrategy, SeverityDistribution,
+    AttackChainNode, AttackNodeStatus, AuthMode, CodeContextHint, Environment, IdentityProvider,
+    PentestAuthConfig, PentestConfig, PentestEvent, PentestMessage, PentestSession, PentestStats,
+    PentestStatus, PentestStrategy, SeverityDistribution, TestUserRecord, TesterInfo,
     ToolCallRecord,
 };
 pub use repository::{ScanTrigger, TrackedRepository};

compliance-core/src/models/pentest.rs

@@ -1,3 +1,5 @@
+use std::collections::HashMap;
+
 use chrono::{DateTime, Utc};
 use serde::{Deserialize, Serialize};
 
@@ -50,6 +52,132 @@ impl std::fmt::Display for PentestStrategy {
     }
 }
 
+/// Authentication mode for the pentest target
+#[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq)]
+#[serde(rename_all = "snake_case")]
+pub enum AuthMode {
+    #[default]
+    None,
+    Manual,
+    AutoRegister,
+}
+
+/// Target environment classification
+#[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq)]
+#[serde(rename_all = "snake_case")]
+pub enum Environment {
+    #[default]
+    Development,
+    Staging,
+    Production,
+}
+
+impl std::fmt::Display for Environment {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Self::Development => write!(f, "Development"),
+            Self::Staging => write!(f, "Staging"),
+            Self::Production => write!(f, "Production"),
+        }
+    }
+}
+
+/// Tester identity for the engagement record
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
+pub struct TesterInfo {
+    pub name: String,
+    pub email: String,
+}
+
+/// Authentication configuration for the pentest session
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
+pub struct PentestAuthConfig {
+    pub mode: AuthMode,
+    pub username: Option<String>,
+    pub password: Option<String>,
+    /// Optional — if omitted the orchestrator uses Playwright to discover it.
+    pub registration_url: Option<String>,
+    /// Base email for plus-addressing (e.g. `pentest@scanner.example.com`).
+    /// The orchestrator generates `base+{session_id}@domain` per session.
+    pub verification_email: Option<String>,
+    /// IMAP server to poll for verification emails (e.g. `imap.example.com`).
+    pub imap_host: Option<String>,
+    /// IMAP port (default 993 for TLS).
+    pub imap_port: Option<u16>,
+    /// IMAP username (defaults to `verification_email` if omitted).
+    pub imap_username: Option<String>,
+    /// IMAP password / app-specific password.
+    pub imap_password: Option<String>,
+    #[serde(default)]
+    pub cleanup_test_user: bool,
+}
+
+/// Full wizard configuration for a pentest session
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct PentestConfig {
+    // Step 1: Target & Scope
+    pub app_url: String,
+    pub git_repo_url: Option<String>,
+    pub branch: Option<String>,
+    pub commit_hash: Option<String>,
+    pub app_type: Option<String>,
+    pub rate_limit: Option<u32>,
+
+    // Step 2: Authentication
+    #[serde(default)]
+    pub auth: PentestAuthConfig,
+    #[serde(default)]
+    pub custom_headers: HashMap<String, String>,
+
+    // Step 3: Strategy & Instructions
+    pub strategy: Option<String>,
+    #[serde(default)]
+    pub allow_destructive: bool,
+    pub initial_instructions: Option<String>,
+    #[serde(default)]
+    pub scope_exclusions: Vec<String>,
+
+    // Step 4: Disclaimer & Confirm
+    #[serde(default)]
+    pub disclaimer_accepted: bool,
+    pub disclaimer_accepted_at: Option<DateTime<Utc>>,
+    #[serde(default)]
+    pub environment: Environment,
+    #[serde(default)]
+    pub tester: TesterInfo,
+    pub max_duration_minutes: Option<u32>,
+    #[serde(default)]
+    pub skip_mode: bool,
+}
+
+/// Identity provider type for cleanup routing
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
+#[serde(rename_all = "snake_case")]
+pub enum IdentityProvider {
+    Keycloak,
+    Auth0,
+    Okta,
+    Firebase,
+    Custom,
+}
+
+/// Details of a test user created during a pentest session.
+/// Stored so the cleanup step knows exactly what to delete and where.
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
+pub struct TestUserRecord {
+    /// Username used to register
+    pub username: Option<String>,
+    /// Email used to register
+    pub email: Option<String>,
+    /// User ID returned by the identity provider (if known)
+    pub provider_user_id: Option<String>,
+    /// Which identity provider holds this user
+    pub provider: Option<IdentityProvider>,
+    /// Whether cleanup has been completed
+    #[serde(default)]
+    pub cleaned_up: bool,
+}
+
 /// A pentest session initiated via the chat interface
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct PentestSession {
@@ -60,7 +188,12 @@ pub struct PentestSession {
     pub repo_id: Option<String>,
     pub status: PentestStatus,
     pub strategy: PentestStrategy,
+    /// Wizard configuration (None for legacy sessions)
+    pub config: Option<PentestConfig>,
     pub created_by: Option<String>,
+    /// Test user created during auto-register (for cleanup)
+    #[serde(default)]
+    pub test_user: Option<TestUserRecord>,
     /// Total number of tool invocations in this session
     pub tool_invocations: u32,
     /// Total successful tool invocations
@@ -83,7 +216,9 @@ impl PentestSession {
             repo_id: None,
             status: PentestStatus::Running,
             strategy,
+            config: None,
             created_by: None,
+            test_user: None,
             tool_invocations: 0,
             tool_successes: 0,
             findings_count: 0,
@@ -261,6 +396,10 @@ pub enum PentestEvent {
     Complete { summary: String },
     /// Error occurred
     Error { message: String },
+    /// Session paused
+    Paused,
+    /// Session resumed
+    Resumed,
 }
 
 /// Aggregated stats for the pentest dashboard

compliance-core/tests/models.rs

@@ -436,6 +436,150 @@ fn pentest_event_serde_finding() {
     }
 }
 
+// ─── PentestEvent Paused/Resumed ───
+
+#[test]
+fn pentest_event_serde_paused() {
+    let event = pentest::PentestEvent::Paused;
+    let json = serde_json::to_string(&event).unwrap();
+    assert!(json.contains(r#""type":"paused""#));
+    let back: pentest::PentestEvent = serde_json::from_str(&json).unwrap();
+    assert!(matches!(back, pentest::PentestEvent::Paused));
+}
+
+#[test]
+fn pentest_event_serde_resumed() {
+    let event = pentest::PentestEvent::Resumed;
+    let json = serde_json::to_string(&event).unwrap();
+    assert!(json.contains(r#""type":"resumed""#));
+    let back: pentest::PentestEvent = serde_json::from_str(&json).unwrap();
+    assert!(matches!(back, pentest::PentestEvent::Resumed));
+}
+
+// ─── PentestConfig serde ───
+
+#[test]
+fn pentest_config_serde_roundtrip() {
+    let config = pentest::PentestConfig {
+        app_url: "https://example.com".into(),
+        git_repo_url: Some("https://github.com/org/repo".into()),
+        branch: Some("main".into()),
+        commit_hash: None,
+        app_type: Some("web".into()),
+        rate_limit: Some(10),
+        auth: pentest::PentestAuthConfig {
+            mode: pentest::AuthMode::Manual,
+            username: Some("admin".into()),
+            password: Some("pass123".into()),
+            registration_url: None,
+            verification_email: None,
+            imap_host: None,
+            imap_port: None,
+            imap_username: None,
+            imap_password: None,
+            cleanup_test_user: true,
+        },
+        custom_headers: [("X-Token".to_string(), "abc".to_string())]
+            .into_iter()
+            .collect(),
+        strategy: Some("comprehensive".into()),
+        allow_destructive: false,
+        initial_instructions: Some("Test the login flow".into()),
+        scope_exclusions: vec!["/admin".into()],
+        disclaimer_accepted: true,
+        disclaimer_accepted_at: Some(chrono::Utc::now()),
+        environment: pentest::Environment::Staging,
+        tester: pentest::TesterInfo {
+            name: "Alice".into(),
+            email: "alice@example.com".into(),
+        },
+        max_duration_minutes: Some(30),
+        skip_mode: false,
+    };
+    let json = serde_json::to_string(&config).unwrap();
+    let back: pentest::PentestConfig = serde_json::from_str(&json).unwrap();
+    assert_eq!(back.app_url, "https://example.com");
+    assert_eq!(back.auth.mode, pentest::AuthMode::Manual);
+    assert_eq!(back.auth.username, Some("admin".into()));
+    assert!(back.auth.cleanup_test_user);
+    assert_eq!(back.scope_exclusions, vec!["/admin".to_string()]);
+    assert_eq!(back.environment, pentest::Environment::Staging);
+}
+
+#[test]
+fn pentest_auth_config_default() {
+    let auth = pentest::PentestAuthConfig::default();
+    assert_eq!(auth.mode, pentest::AuthMode::None);
+    assert!(auth.username.is_none());
+    assert!(auth.password.is_none());
+    assert!(auth.verification_email.is_none());
+    assert!(auth.imap_host.is_none());
+    assert!(!auth.cleanup_test_user);
+}
+
+// ─── TestUserRecord ───
+
+#[test]
+fn test_user_record_default() {
+    let r = pentest::TestUserRecord::default();
+    assert!(r.username.is_none());
+    assert!(r.email.is_none());
+    assert!(r.provider_user_id.is_none());
+    assert!(r.provider.is_none());
+    assert!(!r.cleaned_up);
+}
+
+#[test]
+fn test_user_record_serde_roundtrip() {
+    let r = pentest::TestUserRecord {
+        username: Some("pentestuser".into()),
+        email: Some("pentest+abc@scanner.example.com".into()),
+        provider_user_id: Some("kc-uuid-123".into()),
+        provider: Some(pentest::IdentityProvider::Keycloak),
+        cleaned_up: false,
+    };
+    let json = serde_json::to_string(&r).unwrap();
+    let back: pentest::TestUserRecord = serde_json::from_str(&json).unwrap();
+    assert_eq!(back.username, Some("pentestuser".into()));
+    assert_eq!(back.provider, Some(pentest::IdentityProvider::Keycloak));
+    assert!(!back.cleaned_up);
+}
+
+#[test]
+fn identity_provider_serde_all_variants() {
+    for (variant, expected) in [
+        (pentest::IdentityProvider::Keycloak, "\"keycloak\""),
+        (pentest::IdentityProvider::Auth0, "\"auth0\""),
+        (pentest::IdentityProvider::Okta, "\"okta\""),
+        (pentest::IdentityProvider::Firebase, "\"firebase\""),
+        (pentest::IdentityProvider::Custom, "\"custom\""),
+    ] {
+        let json = serde_json::to_string(&variant).unwrap();
+        assert_eq!(json, expected);
+        let back: pentest::IdentityProvider = serde_json::from_str(&json).unwrap();
+        assert_eq!(back, variant);
+    }
+}
+
+#[test]
+fn pentest_session_with_test_user() {
+    let mut s = pentest::PentestSession::new("t".into(), pentest::PentestStrategy::Quick);
+    assert!(s.test_user.is_none());
+    s.test_user = Some(pentest::TestUserRecord {
+        username: Some("pentester".into()),
+        email: Some("pentest+123@example.com".into()),
+        provider_user_id: None,
+        provider: Some(pentest::IdentityProvider::Auth0),
+        cleaned_up: false,
+    });
+    let bson_doc = bson::to_document(&s).unwrap();
+    let back: pentest::PentestSession = bson::from_document(bson_doc).unwrap();
+    assert!(back.test_user.is_some());
+    let tu = back.test_user.as_ref().unwrap();
+    assert_eq!(tu.username, Some("pentester".into()));
+    assert_eq!(tu.provider, Some(pentest::IdentityProvider::Auth0));
+}
+
 // ─── Serde helpers (BSON datetime) ───
 
 #[test]