fix: live progress + concurrency for embedding builds

The embedding build progress was only written to MongoDB after every
batch completed (and the final flush + status update only happened at
the very end), so the dashboard would show "0/N chunks (0%)" for the
entire run, then jump straight to "complete." For a repo with 2k+
chunks this looked like the build was stuck.

Three fixes:
- pipeline: call update_build(Running, embedded_count, ...) after each
  batch so /api/v1/chat/:repo_id/status reflects real progress, and
  flush embeddings to Mongo every 200 records so a partial failure does
  not lose everything.
- pipeline: drive batches with FuturesUnordered at concurrency=4 so
  litellm requests overlap instead of going strictly serial (112
  sequential requests for a 2221-chunk repo were the wall-time floor).
- llm client: give the reqwest client a 300s request timeout and 10s
  connect timeout. Previously LlmClient used reqwest::Client::new()
  with no timeout, so a hung embedding call would block the build
  indefinitely.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.cargo/audit.toml

@@ -0,0 +1,10 @@
+[advisories]
+ignore = [
+    # hickory-proto 0.25.x pulled in transitively via mongodb → hickory-resolver.
+    # MongoDB 3.x has not yet released with hickory-resolver 0.26.x, so we cannot
+    # upgrade past this without a mongodb release. Both are DNS-layer DoS vectors
+    # requiring a MITM/controlled DNS server against MongoDB's hostname resolution —
+    # not a realistic attack surface here. Revisit when mongodb bumps hickory.
+    "RUSTSEC-2026-0118", # NSEC3 loop, no fix available upstream
+    "RUSTSEC-2026-0119", # O(n²) name compression, fixed in hickory-proto >=0.26.1
+]

.gitea/workflows/ci.yml

@@ -145,13 +145,20 @@ jobs:
     needs: [detect-changes]
     if: needs.detect-changes.outputs.agent == 'true'
     container:
-      image: alpine:latest
+      image: docker:27-cli
     steps:
-      - name: Trigger Coolify deploy
+      - name: Build, push and trigger orca redeploy
         run: |
-          apk add --no-cache curl
-          curl -sf "${{ secrets.COOLIFY_WEBHOOK_AGENT }}" \
-            -H "Authorization: Bearer ${{ secrets.COOLIFY_TOKEN }}"
+          apk add --no-cache git curl openssl
+          git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
+          git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
+          IMAGE=registry.meghsakha.com/compliance-agent
+          echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
+          docker build -f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
+          docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
+          PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy agent"}}' "${GITHUB_SHA}")
+          SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
+          RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
 
   deploy-dashboard:
     name: Deploy Dashboard
@@ -159,13 +166,20 @@ jobs:
     needs: [detect-changes]
     if: needs.detect-changes.outputs.dashboard == 'true'
     container:
-      image: alpine:latest
+      image: docker:27-cli
     steps:
-      - name: Trigger Coolify deploy
+      - name: Build, push and trigger orca redeploy
         run: |
-          apk add --no-cache curl
-          curl -sf "${{ secrets.COOLIFY_WEBHOOK_DASHBOARD }}" \
-            -H "Authorization: Bearer ${{ secrets.COOLIFY_TOKEN }}"
+          apk add --no-cache git curl openssl
+          git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
+          git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
+          IMAGE=registry.meghsakha.com/compliance-dashboard
+          echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
+          docker build -f Dockerfile.dashboard -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
+          docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
+          PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy dashboard"}}' "${GITHUB_SHA}")
+          SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
+          RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
 
   deploy-docs:
     name: Deploy Docs
@@ -173,13 +187,20 @@ jobs:
     needs: [detect-changes]
     if: needs.detect-changes.outputs.docs == 'true'
     container:
-      image: alpine:latest
+      image: docker:27-cli
     steps:
-      - name: Trigger Coolify deploy
+      - name: Build, push and trigger orca redeploy
         run: |
-          apk add --no-cache curl
-          curl -sf "${{ secrets.COOLIFY_WEBHOOK_DOCS }}" \
-            -H "Authorization: Bearer ${{ secrets.COOLIFY_TOKEN }}"
+          apk add --no-cache git curl openssl
+          git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
+          git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
+          IMAGE=registry.meghsakha.com/compliance-docs
+          echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
+          docker build -f Dockerfile.docs -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
+          docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
+          PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy docs"}}' "${GITHUB_SHA}")
+          SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
+          RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
 
   deploy-mcp:
     name: Deploy MCP
@@ -187,10 +208,17 @@ jobs:
     needs: [detect-changes]
     if: needs.detect-changes.outputs.mcp == 'true'
     container:
-      image: alpine:latest
+      image: docker:27-cli
     steps:
-      - name: Trigger Coolify deploy
+      - name: Build, push and trigger orca redeploy
         run: |
-          apk add --no-cache curl
-          curl -sf "${{ secrets.COOLIFY_WEBHOOK_MCP }}" \
-            -H "Authorization: Bearer ${{ secrets.COOLIFY_TOKEN }}"
+          apk add --no-cache git curl openssl
+          git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
+          git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
+          IMAGE=registry.meghsakha.com/compliance-mcp
+          echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
+          docker build -f Dockerfile.mcp -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
+          docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
+          PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy mcp"}}' "${GITHUB_SHA}")
+          SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
+          RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"

Cargo.lock

@@ -3524,9 +3524,9 @@ checksum = "224484c5d09285a7b8cb0a0c117e847ebd14cb6e4470ecf68cdb89c503b0edb9"
 
 [[package]]
 name = "mongodb"
-version = "3.5.1"
+version = "3.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "803dd859e8afa084c255a8effd8000ff86f7c8076a50cd6d8c99e8f3496f75c2"
+checksum = "1ef2c933617431ad0246fb5b43c425ebdae18c7f7259c87de0726d93b0e7e91b"
 dependencies = [
  "base64",
  "bitflags",
@@ -3570,9 +3570,9 @@ dependencies = [
 
 [[package]]
 name = "mongodb-internal-macros"
-version = "3.5.1"
+version = "3.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a973ef3dd3dbc6f6e65bbdecfd9ec5e781b9e7493b0f369a7c62e35d8e5ae2c8"
+checksum = "9e5758dc828eb2d02ec30563cba365609d56ddd833190b192beaee2b475a7bb3"
 dependencies = [
  "macro_magic",
  "proc-macro2",
@@ -4699,9 +4699,9 @@ dependencies = [
 
 [[package]]
 name = "rustls-webpki"
-version = "0.103.10"
+version = "0.103.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df33b2b81ac578cabaf06b89b0631153a3f416b0a886e8a7a1707fb51abbd1ef"
+checksum = "61c429a8649f110dddef65e2a5ad240f747e85f7758a6bccc7e5777bd33f756e"
 dependencies = [
  "ring",
  "rustls-pki-types",

Dockerfile.agent

@@ -33,9 +33,15 @@ RUN pip3 install --break-system-packages ruff
 
 COPY --from=builder /app/target/release/compliance-agent /usr/local/bin/compliance-agent
 
+# Copy documentation for the help chat assistant
+COPY --from=builder /app/README.md /app/README.md
+COPY --from=builder /app/docs /app/docs
+ENV HELP_DOCS_PATH=/app
+
 # Ensure SSH key directory exists
 RUN mkdir -p /data/compliance-scanner/ssh
 
 EXPOSE 3001 3002
 
 ENTRYPOINT ["compliance-agent"]
+

Dockerfile.dashboard

@@ -20,3 +20,4 @@ ENV IP=0.0.0.0
 EXPOSE 8080
 
 ENTRYPOINT ["./compliance-dashboard"]
+

Dockerfile.docs

@@ -12,3 +12,4 @@ 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

@@ -14,3 +14,4 @@ EXPOSE 8090
 ENV MCP_PORT=8090
 
 ENTRYPOINT ["compliance-mcp"]
+

compliance-agent/Cargo.toml

@@ -25,7 +25,7 @@ uuid = { workspace = true }
 secrecy = { workspace = true }
 regex = { workspace = true }
 axum = "0.8"
-tower-http = { version = "0.6", features = ["cors", "trace"] }
+tower-http = { version = "0.6", features = ["cors", "trace", "set-header"] }
 git2 = "0.20"
 octocrab = "0.44"
 tokio-cron-scheduler = "0.13"

compliance-agent/src/agent.rs

@@ -35,11 +35,16 @@ impl ComplianceAgent {
             config.litellm_model.clone(),
             config.litellm_embed_model.clone(),
         ));
+        let http = reqwest::Client::builder()
+            .timeout(std::time::Duration::from_secs(30))
+            .connect_timeout(std::time::Duration::from_secs(10))
+            .build()
+            .unwrap_or_default();
         Self {
             config,
             db,
             llm,
-            http: reqwest::Client::new(),
+            http,
             session_streams: Arc::new(DashMap::new()),
             session_pause: Arc::new(DashMap::new()),
             session_semaphore: Arc::new(Semaphore::new(DEFAULT_MAX_CONCURRENT_SESSIONS)),

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

@@ -104,28 +104,58 @@ fn load_docs(root: &Path) -> String {
 
 /// Returns a reference to the cached doc context string, initialised on
 /// first call via `OnceLock`.
+///
+/// Discovery order:
+/// 1. `HELP_DOCS_PATH` env var (explicit override)
+/// 2. Walk up from the binary location
+/// 3. Current working directory
+/// 4. Common Docker paths (/app, /opt/compliance-scanner)
 fn doc_context() -> &'static str {
     DOC_CONTEXT.get_or_init(|| {
+        // 1. Explicit env var
+        if let Ok(path) = std::env::var("HELP_DOCS_PATH") {
+            let p = PathBuf::from(&path);
+            if p.join("README.md").is_file() || p.join("docs").is_dir() {
+                tracing::info!("help_chat: loading docs from HELP_DOCS_PATH={path}");
+                return load_docs(&p);
+            }
+            tracing::warn!("help_chat: HELP_DOCS_PATH={path} has no README.md or docs/");
+        }
+
+        // 2. Walk up from binary location
         let start = std::env::current_exe()
             .ok()
             .and_then(|p| p.parent().map(Path::to_path_buf))
             .unwrap_or_else(|| PathBuf::from("."));
 
-        match find_project_root(&start) {
-            Some(root) => load_docs(&root),
-            None => {
-                // Fallback: try current working directory
-                let cwd = std::env::current_dir().unwrap_or_else(|_| PathBuf::from("."));
+        if let Some(root) = find_project_root(&start) {
+            return load_docs(&root);
+        }
+
+        // 3. Current working directory
+        if let Ok(cwd) = std::env::current_dir() {
+            if let Some(root) = find_project_root(&cwd) {
+                return load_docs(&root);
+            }
             if cwd.join("README.md").is_file() {
                 return load_docs(&cwd);
             }
+        }
+
+        // 4. Common Docker/deployment paths
+        for candidate in ["/app", "/opt/compliance-scanner", "/srv/compliance-scanner"] {
+            let p = PathBuf::from(candidate);
+            if p.join("README.md").is_file() || p.join("docs").is_dir() {
+                tracing::info!("help_chat: found docs at {candidate}");
+                return load_docs(&p);
+            }
+        }
+
         tracing::error!(
-                    "help_chat: could not locate project root from {}; doc context will be empty",
-                    start.display()
+            "help_chat: could not locate project root; doc context will be empty. \
+             Set HELP_DOCS_PATH to the directory containing README.md and docs/"
         );
         String::new()
-            }
-        }
     })
 }
 

compliance-agent/src/api/server.rs

@@ -1,8 +1,10 @@
 use std::sync::Arc;
 
+use axum::http::HeaderValue;
 use axum::{middleware, Extension};
 use tokio::sync::RwLock;
 use tower_http::cors::CorsLayer;
+use tower_http::set_header::SetResponseHeaderLayer;
 use tower_http::trace::TraceLayer;
 
 use crate::agent::ComplianceAgent;
@@ -14,7 +16,24 @@ pub async fn start_api_server(agent: ComplianceAgent, port: u16) -> Result<(), A
     let mut app = routes::build_router()
         .layer(Extension(Arc::new(agent.clone())))
         .layer(CorsLayer::permissive())
-        .layer(TraceLayer::new_for_http());
+        .layer(TraceLayer::new_for_http())
+        // Security headers (defense-in-depth, primary enforcement via Traefik)
+        .layer(SetResponseHeaderLayer::overriding(
+            axum::http::header::STRICT_TRANSPORT_SECURITY,
+            HeaderValue::from_static("max-age=31536000; includeSubDomains"),
+        ))
+        .layer(SetResponseHeaderLayer::overriding(
+            axum::http::header::X_FRAME_OPTIONS,
+            HeaderValue::from_static("DENY"),
+        ))
+        .layer(SetResponseHeaderLayer::overriding(
+            axum::http::header::X_CONTENT_TYPE_OPTIONS,
+            HeaderValue::from_static("nosniff"),
+        ))
+        .layer(SetResponseHeaderLayer::overriding(
+            axum::http::header::REFERRER_POLICY,
+            HeaderValue::from_static("strict-origin-when-cross-origin"),
+        ));
 
     if let (Some(kc_url), Some(kc_realm)) =
         (&agent.config.keycloak_url, &agent.config.keycloak_realm)

compliance-agent/src/llm/client.rs

@@ -19,12 +19,17 @@ impl LlmClient {
         model: String,
         embed_model: String,
     ) -> Self {
+        let http = reqwest::Client::builder()
+            .timeout(std::time::Duration::from_secs(300))
+            .connect_timeout(std::time::Duration::from_secs(10))
+            .build()
+            .unwrap_or_default();
         Self {
             base_url,
             api_key,
             model,
             embed_model,
-            http: reqwest::Client::new(),
+            http,
         }
     }
 

compliance-agent/src/main.rs

@@ -4,7 +4,7 @@ use compliance_agent::{agent, api, config, database, scheduler, ssh, webhooks};
 async fn main() -> Result<(), Box<dyn std::error::Error>> {
     match dotenvy::dotenv() {
         Ok(path) => eprintln!("[dotenv] Loaded from: {}", path.display()),
-        Err(e) => eprintln!("[dotenv] FAILED: {e}"),
+        Err(_) => eprintln!("[dotenv] No .env file found, using environment variables"),
     }
 
     let _telemetry_guard = compliance_core::telemetry::init_telemetry("compliance-agent");

compliance-agent/src/pipeline/gitleaks.rs

@@ -19,7 +19,9 @@ impl Scanner for GitleaksScanner {
 
     #[tracing::instrument(skip_all)]
     async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
-        let output = tokio::process::Command::new("gitleaks")
+        let output = tokio::time::timeout(
+            std::time::Duration::from_secs(300),
+            tokio::process::Command::new("gitleaks")
                 .args([
                     "detect",
                     "--source",
@@ -33,8 +35,13 @@ impl Scanner for GitleaksScanner {
                     "0",
                 ])
                 .current_dir(repo_path)
-            .output()
+                .output(),
+        )
         .await
+        .map_err(|_| CoreError::Scanner {
+            scanner: "gitleaks".to_string(),
+            source: "timed out after 5 minutes".into(),
+        })?
         .map_err(|e| CoreError::Scanner {
             scanner: "gitleaks".to_string(),
             source: Box::new(e),

compliance-agent/src/pipeline/orchestrator.rs

@@ -174,19 +174,26 @@ impl PipelineOrchestrator {
                 k.expose_secret().to_string()
             }),
         );
-        let cve_alerts = match async {
+        let cve_alerts = match tokio::time::timeout(
+            std::time::Duration::from_secs(600),
+            async {
                 cve_scanner
                     .scan_dependencies(&repo_id, &mut sbom_entries)
                     .await
             }
-        .instrument(tracing::info_span!("stage_cve_scanning"))
+            .instrument(tracing::info_span!("stage_cve_scanning")),
+        )
         .await
         {
-            Ok(alerts) => alerts,
-            Err(e) => {
+            Ok(Ok(alerts)) => alerts,
+            Ok(Err(e)) => {
                 tracing::warn!("[{repo_id}] CVE scanning failed: {e}");
                 Vec::new()
             }
+            Err(_) => {
+                tracing::warn!("[{repo_id}] CVE scanning timed out after 10 minutes");
+                Vec::new()
+            }
         };
 
         // Stage 4: Pattern Scanning (GDPR + OAuth)
@@ -315,8 +322,15 @@ impl PipelineOrchestrator {
                 .await?;
         }
 
-        // Persist CVE alerts (upsert by cve_id + repo_id)
+        // Persist CVE alerts and create notifications
+        {
+            use compliance_core::models::notification::{parse_severity, CveNotification};
+
+            let repo_name = repo.name.clone();
+            let mut new_notif_count = 0u32;
+
             for alert in &cve_alerts {
+                // Upsert the alert
                 let filter = doc! {
                     "cve_id": &alert.cve_id,
                     "repo_id": &alert.repo_id,
@@ -329,6 +343,46 @@ impl PipelineOrchestrator {
                     .update_one(filter, update)
                     .upsert(true)
                     .await?;
+
+                // Create notification (dedup by cve_id + repo + package + version)
+                let notif_filter = doc! {
+                    "cve_id": &alert.cve_id,
+                    "repo_id": &alert.repo_id,
+                    "package_name": &alert.affected_package,
+                    "package_version": &alert.affected_version,
+                };
+                let severity = parse_severity(alert.severity.as_deref(), alert.cvss_score);
+                let mut notification = CveNotification::new(
+                    alert.cve_id.clone(),
+                    repo_id.clone(),
+                    repo_name.clone(),
+                    alert.affected_package.clone(),
+                    alert.affected_version.clone(),
+                    severity,
+                );
+                notification.cvss_score = alert.cvss_score;
+                notification.summary = alert.summary.clone();
+                notification.url = Some(format!("https://osv.dev/vulnerability/{}", alert.cve_id));
+
+                let notif_update = doc! {
+                    "$setOnInsert": mongodb::bson::to_bson(&notification).unwrap_or_default()
+                };
+                if let Ok(result) = self
+                    .db
+                    .cve_notifications()
+                    .update_one(notif_filter, notif_update)
+                    .upsert(true)
+                    .await
+                {
+                    if result.upserted_id.is_some() {
+                        new_notif_count += 1;
+                    }
+                }
+            }
+
+            if new_notif_count > 0 {
+                tracing::info!("[{repo_id}] Created {new_notif_count} CVE notification(s)");
+            }
         }
 
         // Stage 6: Issue Creation

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

@@ -5,16 +5,22 @@ 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")
+    let output = tokio::time::timeout(
+        std::time::Duration::from_secs(300),
+        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()
+            .output(),
+    )
     .await
+    .map_err(|_| CoreError::Scanner {
+        scanner: "syft".to_string(),
+        source: "timed out after 5 minutes".into(),
+    })?
     .map_err(|e| CoreError::Scanner {
         scanner: "syft".to_string(),
         source: Box::new(e),

compliance-agent/src/pipeline/semgrep.rs

@@ -19,11 +19,26 @@ impl Scanner for SemgrepScanner {
 
     #[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"])
+        let output = tokio::time::timeout(
+            std::time::Duration::from_secs(600),
+            tokio::process::Command::new("semgrep")
+                .args([
+                    "--config=auto",
+                    "--json",
+                    "--quiet",
+                    "--max-memory",
+                    "500",
+                    "--jobs",
+                    "1",
+                ])
                 .arg(repo_path)
-            .output()
+                .output(),
+        )
         .await
+        .map_err(|_| CoreError::Scanner {
+            scanner: "semgrep".to_string(),
+            source: "timed out after 10 minutes".into(),
+        })?
         .map_err(|e| CoreError::Scanner {
             scanner: "semgrep".to_string(),
             source: Box::new(e),

compliance-agent/src/rag/pipeline.rs

@@ -6,11 +6,16 @@ use compliance_core::models::embedding::{CodeEmbedding, EmbeddingBuildRun, Embed
 use compliance_core::models::graph::CodeNode;
 use compliance_graph::graph::chunking::extract_chunks;
 use compliance_graph::graph::embedding_store::EmbeddingStore;
+use futures_util::stream::{FuturesUnordered, StreamExt};
 use tracing::{error, info};
 
 use crate::error::AgentError;
 use crate::llm::LlmClient;
 
+const EMBED_BATCH_SIZE: usize = 20;
+const EMBED_CONCURRENCY: usize = 4;
+const EMBED_FLUSH_EVERY: usize = 200;
+
 /// RAG pipeline for building embeddings and performing retrieval
 pub struct RagPipeline {
     llm: Arc<LlmClient>,
@@ -77,25 +82,33 @@ impl RagPipeline {
             .await
             .map_err(|e| AgentError::Other(format!("Failed to delete old embeddings: {e}")))?;
 
-        // Step 3: Batch embed (small batches to stay within model limits)
-        let batch_size = 20;
-        let mut all_embeddings = Vec::new();
+        // Step 3: Batch embed with bounded concurrency. Flush to Mongo and
+        // update progress periodically so the dashboard can show live status.
+        let mut pending = Vec::with_capacity(EMBED_FLUSH_EVERY);
         let mut embedded_count = 0u32;
 
-        for batch_start in (0..chunks.len()).step_by(batch_size) {
-            let batch_end = (batch_start + batch_size).min(chunks.len());
-            let batch_chunks = &chunks[batch_start..batch_end];
-
-            // Prepare texts: context_header + content
-            let texts: Vec<String> = batch_chunks
-                .iter()
-                .map(|c| format!("{}\n{}", c.context_header, c.content))
+        // Build the list of batch indices to process.
+        let batches: Vec<(usize, usize)> = (0..chunks.len())
+            .step_by(EMBED_BATCH_SIZE)
+            .map(|start| (start, (start + EMBED_BATCH_SIZE).min(chunks.len())))
             .collect();
 
-            match self.llm.embed(texts).await {
-                Ok(vectors) => {
+        let mut batch_iter = batches.into_iter();
+        let mut in_flight = FuturesUnordered::new();
+
+        // Prime up to EMBED_CONCURRENCY batches.
+        for _ in 0..EMBED_CONCURRENCY {
+            if let Some((start, end)) = batch_iter.next() {
+                in_flight.push(self.embed_batch(&chunks[start..end], start, end));
+            }
+        }
+
+        while let Some(result) = in_flight.next().await {
+            match result {
+                Ok((start, end, vectors)) => {
+                    let batch_chunks = &chunks[start..end];
                     for (chunk, embedding) in batch_chunks.iter().zip(vectors) {
-                        all_embeddings.push(CodeEmbedding {
+                        pending.push(CodeEmbedding {
                             id: None,
                             repo_id: repo_id.to_string(),
                             graph_build_id: graph_build_id.to_string(),
@@ -113,9 +126,45 @@ impl RagPipeline {
                         });
                     }
                     embedded_count += batch_chunks.len() as u32;
+
+                    // Flush pending embeddings to Mongo periodically and update progress.
+                    if pending.len() >= EMBED_FLUSH_EVERY {
+                        self.embedding_store
+                            .store_embeddings(&pending)
+                            .await
+                            .map_err(|e| {
+                                AgentError::Other(format!("Failed to store embeddings: {e}"))
+                            })?;
+                        pending.clear();
+                    }
+
+                    // Always update the progress counter on the build doc — even if
+                    // we haven't flushed embeddings yet — so the UI shows movement.
+                    if let Err(e) = self
+                        .embedding_store
+                        .update_build(
+                            repo_id,
+                            graph_build_id,
+                            EmbeddingBuildStatus::Running,
+                            embedded_count,
+                            None,
+                        )
+                        .await
+                    {
+                        error!("[{repo_id}] Failed to update build progress: {e}");
+                    }
+
+                    // Queue the next batch to keep concurrency saturated.
+                    if let Some((s, e)) = batch_iter.next() {
+                        in_flight.push(self.embed_batch(&chunks[s..e], s, e));
+                    }
                 }
                 Err(e) => {
                     error!("[{repo_id}] Embedding batch failed: {e}");
+                    // Flush whatever we have so partial progress isn't lost.
+                    if !pending.is_empty() {
+                        let _ = self.embedding_store.store_embeddings(&pending).await;
+                    }
                     build.status = EmbeddingBuildStatus::Failed;
                     build.error_message = Some(e.to_string());
                     build.completed_at = Some(Utc::now());
@@ -134,11 +183,13 @@ impl RagPipeline {
             }
         }
 
-        // Step 4: Store all embeddings
+        // Step 4: Flush any remaining embeddings
+        if !pending.is_empty() {
             self.embedding_store
-            .store_embeddings(&all_embeddings)
+                .store_embeddings(&pending)
                 .await
                 .map_err(|e| AgentError::Other(format!("Failed to store embeddings: {e}")))?;
+        }
 
         // Step 5: Update build status
         build.status = EmbeddingBuildStatus::Completed;
@@ -161,4 +212,21 @@ impl RagPipeline {
         );
         Ok(build)
     }
+
+    /// Embed one batch of chunks. Returns the (start, end, vectors) tuple so
+    /// out-of-order completion from `FuturesUnordered` can still be reconciled
+    /// against the original chunk slice.
+    async fn embed_batch(
+        &self,
+        batch_chunks: &[compliance_graph::graph::chunking::CodeChunk],
+        start: usize,
+        end: usize,
+    ) -> Result<(usize, usize, Vec<Vec<f64>>), AgentError> {
+        let texts: Vec<String> = batch_chunks
+            .iter()
+            .map(|c| format!("{}\n{}", c.context_header, c.content))
+            .collect();
+        let vectors = self.llm.embed(texts).await?;
+        Ok((start, end, vectors))
+    }
 }

compliance-dashboard/assets/main.css

@@ -3877,3 +3877,15 @@ tbody tr:last-child td {
 .notification-item-pkg { font-size: 12px; color: var(--text-primary); font-family: 'JetBrains Mono', monospace; }
 .notification-item-repo { font-size: 11px; color: var(--text-secondary); margin-bottom: 4px; }
 .notification-item-summary { font-size: 11px; color: var(--text-secondary); line-height: 1.4; display: -webkit-box; -webkit-line-clamp: 2; -webkit-box-orient: vertical; overflow: hidden; }
+
+/* ═══════════════════════════════════════════════════════════════
+   COPY BUTTON — Reusable clipboard copy component
+   ═══════════════════════════════════════════════════════════════ */
+.copy-btn { background: none; border: 1px solid var(--border); border-radius: 6px; padding: 5px 7px; color: var(--text-secondary); cursor: pointer; display: inline-flex; align-items: center; transition: color 0.15s, border-color 0.15s, background 0.15s; flex-shrink: 0; }
+.copy-btn:hover { color: var(--accent); border-color: var(--accent); background: var(--accent-muted); }
+.copy-btn-sm { padding: 3px 5px; border-radius: 4px; }
+/* Copyable inline field pattern: value + copy button side by side */
+.copyable { display: flex; align-items: center; gap: 6px; }
+.copyable code, .copyable .mono { flex: 1; min-width: 0; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }
+.code-snippet-wrapper { position: relative; }
+.code-snippet-header { display: flex; align-items: center; justify-content: space-between; margin-bottom: 4px; gap: 8px; }

compliance-dashboard/src/components/app_shell.rs

@@ -32,7 +32,7 @@ pub fn AppShell() -> Element {
             // Not authenticated — redirect to Keycloak login
             rsx! {
                 document::Script {
-                    dangerous_inner_html: "window.location.href = '/auth';"
+                    "window.location.href = '/auth';"
                 }
             }
         }

compliance-dashboard/src/components/code_snippet.rs

@@ -1,5 +1,7 @@
 use dioxus::prelude::*;
 
+use crate::components::copy_button::CopyButton;
+
 #[component]
 pub fn CodeSnippet(
     code: String,
@@ -7,16 +9,19 @@ pub fn CodeSnippet(
     #[props(default)] line_number: u32,
 ) -> Element {
     rsx! {
-        div {
+        div { class: "code-snippet-wrapper",
+            div { class: "code-snippet-header",
                 if !file_path.is_empty() {
-                div {
-                    style: "font-size: 12px; color: var(--text-secondary); margin-bottom: 4px; font-family: monospace;",
+                    span {
+                        style: "font-size: 12px; color: var(--text-secondary); font-family: monospace;",
                         "{file_path}"
                         if line_number > 0 {
                             ":{line_number}"
                         }
                     }
                 }
+                CopyButton { value: code.clone(), small: true }
+            }
             pre { class: "code-block", "{code}" }
         }
     }

compliance-dashboard/src/components/copy_button.rs

@@ -0,0 +1,49 @@
+use dioxus::prelude::*;
+use dioxus_free_icons::icons::bs_icons::*;
+use dioxus_free_icons::Icon;
+
+/// A small copy-to-clipboard button that shows a checkmark after copying.
+///
+/// Usage: `CopyButton { value: "text to copy" }`
+#[component]
+pub fn CopyButton(value: String, #[props(default = false)] small: bool) -> Element {
+    let mut copied = use_signal(|| false);
+
+    let size = if small { 12 } else { 14 };
+    let class = if small {
+        "copy-btn copy-btn-sm"
+    } else {
+        "copy-btn"
+    };
+
+    rsx! {
+        button {
+            class: class,
+            title: if copied() { "Copied!" } else { "Copy to clipboard" },
+            onclick: move |_| {
+                let val = value.clone();
+                // Escape for JS single-quoted string
+                let escaped = val
+                    .replace('\\', "\\\\")
+                    .replace('\'', "\\'")
+                    .replace('\n', "\\n")
+                    .replace('\r', "\\r");
+                let js = format!("navigator.clipboard.writeText('{escaped}')");
+                document::eval(&js);
+                copied.set(true);
+                spawn(async move {
+                    #[cfg(feature = "web")]
+                    gloo_timers::future::TimeoutFuture::new(2000).await;
+                    #[cfg(not(feature = "web"))]
+                    tokio::time::sleep(std::time::Duration::from_secs(2)).await;
+                    copied.set(false);
+                });
+            },
+            if copied() {
+                Icon { icon: BsCheckLg, width: size, height: size }
+            } else {
+                Icon { icon: BsClipboard, width: size, height: size }
+            }
+        }
+    }
+}

compliance-dashboard/src/components/mod.rs

@@ -2,6 +2,7 @@ pub mod app_shell;
 pub mod attack_chain;
 pub mod code_inspector;
 pub mod code_snippet;
+pub mod copy_button;
 pub mod file_tree;
 pub mod help_chat;
 pub mod notification_bell;

compliance-dashboard/src/pages/mcp_servers.rs

@@ -259,7 +259,10 @@ pub fn McpServersPage() -> Element {
                                                 div { class: "mcp-detail-row",
                                                     Icon { icon: BsGlobe, width: 13, height: 13 }
                                                     span { class: "mcp-detail-label", "Endpoint" }
+                                                    div { class: "copyable",
                                                         code { class: "mcp-detail-value", "{server.endpoint_url}" }
+                                                        crate::components::copy_button::CopyButton { value: server.endpoint_url.clone(), small: true }
+                                                    }
                                                 }
                                                 div { class: "mcp-detail-row",
                                                     Icon { icon: BsHddNetwork, width: 13, height: 13 }

compliance-dashboard/src/pages/repositories.rs

@@ -137,13 +137,20 @@ pub fn RepositoriesPage() -> Element {
                                 "For SSH URLs: add this deploy key (read-only) to your repository"
                             }
                             div {
-                                style: "margin-top: 4px; padding: 8px; background: var(--bg-secondary); border-radius: 4px; font-family: monospace; font-size: 11px; word-break: break-all; user-select: all;",
+                                class: "copyable",
+                                style: "margin-top: 4px; padding: 8px; background: var(--bg-secondary); border-radius: 4px;",
+                                code {
+                                    style: "font-size: 11px; word-break: break-all; user-select: all;",
                                     if ssh_public_key().is_empty() {
                                         "Loading..."
                                     } else {
                                         "{ssh_public_key}"
                                     }
                                 }
+                                if !ssh_public_key().is_empty() {
+                                    crate::components::copy_button::CopyButton { value: ssh_public_key(), small: true }
+                                }
+                            }
                         }
 
                         // HTTPS auth fields
@@ -390,29 +397,38 @@ pub fn RepositoriesPage() -> Element {
                         }
                         div { class: "form-group",
                             label { "Webhook URL" }
-                            input {
-                                r#type: "text",
-                                readonly: true,
-                                style: "font-family: monospace; font-size: 12px;",
-                                value: {
+                            {
                                 #[cfg(feature = "web")]
                                 let origin = web_sys::window()
                                     .and_then(|w: web_sys::Window| w.location().origin().ok())
                                     .unwrap_or_default();
                                 #[cfg(not(feature = "web"))]
                                 let origin = String::new();
-                                    format!("{origin}/webhook/{}/{eid}", edit_webhook_tracker())
-                                },
+                                let webhook_url = format!("{origin}/webhook/{}/{eid}", edit_webhook_tracker());
+                                rsx! {
+                                    div { class: "copyable",
+                                        input {
+                                            r#type: "text",
+                                            readonly: true,
+                                            style: "font-family: monospace; font-size: 12px; flex: 1;",
+                                            value: "{webhook_url}",
+                                        }
+                                        crate::components::copy_button::CopyButton { value: webhook_url.clone() }
+                                    }
+                                }
                             }
                         }
                         div { class: "form-group",
                             label { "Webhook Secret" }
+                            div { class: "copyable",
                                 input {
                                     r#type: "text",
                                     readonly: true,
-                                style: "font-family: monospace; font-size: 12px;",
+                                    style: "font-family: monospace; font-size: 12px; flex: 1;",
                                     value: "{secret}",
                                 }
+                                crate::components::copy_button::CopyButton { value: secret.clone() }
+                            }
                         }
                     }
                     div { class: "modal-actions",