Compare commits

..

1 Commits

Author SHA1 Message Date
Sharang Parnerkar 4d5eedcc8b fix: add HTTP timeout to reqwest client and CVE stage timeout
CI / Check (pull_request) Successful in 9m39s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been skipped
CI / Deploy Dashboard (pull_request) Has been skipped
CI / Deploy Docs (pull_request) Has been skipped
CI / Deploy MCP (pull_request) Has been skipped
Without a timeout on the reqwest client, sequential NVD API calls
for each CVE alert could hang indefinitely. With 1098 SBOM entries
producing hundreds of alerts, this would stall the scan pipeline.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 08:48:03 +02:00
7 changed files with 21 additions and 340 deletions
+1 -6
View File
@@ -19,17 +19,12 @@ impl LlmClient {
model: String, model: String,
embed_model: String, embed_model: String,
) -> Self { ) -> 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 { Self {
base_url, base_url,
api_key, api_key,
model, model,
embed_model, embed_model,
http, http: reqwest::Client::new(),
} }
} }
+19 -87
View File
@@ -6,16 +6,11 @@ use compliance_core::models::embedding::{CodeEmbedding, EmbeddingBuildRun, Embed
use compliance_core::models::graph::CodeNode; use compliance_core::models::graph::CodeNode;
use compliance_graph::graph::chunking::extract_chunks; use compliance_graph::graph::chunking::extract_chunks;
use compliance_graph::graph::embedding_store::EmbeddingStore; use compliance_graph::graph::embedding_store::EmbeddingStore;
use futures_util::stream::{FuturesUnordered, StreamExt};
use tracing::{error, info}; use tracing::{error, info};
use crate::error::AgentError; use crate::error::AgentError;
use crate::llm::LlmClient; 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 /// RAG pipeline for building embeddings and performing retrieval
pub struct RagPipeline { pub struct RagPipeline {
llm: Arc<LlmClient>, llm: Arc<LlmClient>,
@@ -82,33 +77,25 @@ impl RagPipeline {
.await .await
.map_err(|e| AgentError::Other(format!("Failed to delete old embeddings: {e}")))?; .map_err(|e| AgentError::Other(format!("Failed to delete old embeddings: {e}")))?;
// Step 3: Batch embed with bounded concurrency. Flush to Mongo and // Step 3: Batch embed (small batches to stay within model limits)
// update progress periodically so the dashboard can show live status. let batch_size = 20;
let mut pending = Vec::with_capacity(EMBED_FLUSH_EVERY); let mut all_embeddings = Vec::new();
let mut embedded_count = 0u32; let mut embedded_count = 0u32;
// Build the list of batch indices to process. for batch_start in (0..chunks.len()).step_by(batch_size) {
let batches: Vec<(usize, usize)> = (0..chunks.len()) let batch_end = (batch_start + batch_size).min(chunks.len());
.step_by(EMBED_BATCH_SIZE) let batch_chunks = &chunks[batch_start..batch_end];
.map(|start| (start, (start + EMBED_BATCH_SIZE).min(chunks.len())))
.collect();
let mut batch_iter = batches.into_iter(); // Prepare texts: context_header + content
let mut in_flight = FuturesUnordered::new(); let texts: Vec<String> = batch_chunks
.iter()
.map(|c| format!("{}\n{}", c.context_header, c.content))
.collect();
// Prime up to EMBED_CONCURRENCY batches. match self.llm.embed(texts).await {
for _ in 0..EMBED_CONCURRENCY { Ok(vectors) => {
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) { for (chunk, embedding) in batch_chunks.iter().zip(vectors) {
pending.push(CodeEmbedding { all_embeddings.push(CodeEmbedding {
id: None, id: None,
repo_id: repo_id.to_string(), repo_id: repo_id.to_string(),
graph_build_id: graph_build_id.to_string(), graph_build_id: graph_build_id.to_string(),
@@ -126,45 +113,9 @@ impl RagPipeline {
}); });
} }
embedded_count += batch_chunks.len() as u32; 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) => { Err(e) => {
error!("[{repo_id}] Embedding batch failed: {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.status = EmbeddingBuildStatus::Failed;
build.error_message = Some(e.to_string()); build.error_message = Some(e.to_string());
build.completed_at = Some(Utc::now()); build.completed_at = Some(Utc::now());
@@ -183,13 +134,11 @@ impl RagPipeline {
} }
} }
// Step 4: Flush any remaining embeddings // Step 4: Store all embeddings
if !pending.is_empty() { self.embedding_store
self.embedding_store .store_embeddings(&all_embeddings)
.store_embeddings(&pending) .await
.await .map_err(|e| AgentError::Other(format!("Failed to store embeddings: {e}")))?;
.map_err(|e| AgentError::Other(format!("Failed to store embeddings: {e}")))?;
}
// Step 5: Update build status // Step 5: Update build status
build.status = EmbeddingBuildStatus::Completed; build.status = EmbeddingBuildStatus::Completed;
@@ -212,21 +161,4 @@ impl RagPipeline {
); );
Ok(build) 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))
}
} }
+1 -1
View File
@@ -51,7 +51,7 @@ thiserror = { workspace = true }
# Web-only # Web-only
reqwest = { workspace = true, optional = true } reqwest = { workspace = true, optional = true }
web-sys = { version = "0.3", optional = true, features = ["Blob", "BlobPropertyBag", "HtmlAnchorElement", "Url", "Document", "Element", "Window", "Storage", "MediaQueryList"] } web-sys = { version = "0.3", optional = true, features = ["Blob", "BlobPropertyBag", "HtmlAnchorElement", "Url", "Document", "Window"] }
js-sys = { version = "0.3", optional = true } js-sys = { version = "0.3", optional = true }
wasm-bindgen = { version = "0.2", optional = true } wasm-bindgen = { version = "0.2", optional = true }
gloo-timers = { version = "0.3", features = ["futures"], optional = true } gloo-timers = { version = "0.3", features = ["futures"], optional = true }
-139
View File
@@ -61,77 +61,6 @@
--ease-spring: cubic-bezier(0.34, 1.56, 0.64, 1); --ease-spring: cubic-bezier(0.34, 1.56, 0.64, 1);
} }
/* ── Light theme tokens ──
Applied when the user has explicitly chosen light (`data-theme="light"`)
OR when their OS prefers light AND they have made no explicit choice. */
:root[data-theme="light"] {
--bg-primary: #f5f7fb;
--bg-secondary: #ffffff;
--bg-card: rgba(255, 255, 255, 0.85);
--bg-card-solid: #ffffff;
--bg-card-hover: #f1f5fb;
--bg-elevated: #f8fafc;
--text-primary: #0c1426;
--text-secondary: #475569;
--text-tertiary: #8a9bb4;
--accent: #0070d4;
--accent-hover: #0080f0;
--accent-muted: rgba(0, 112, 212, 0.10);
--accent-glow: 0 0 20px rgba(0, 112, 212, 0.10);
--border: #e2e8f0;
--border-bright: #cbd5e1;
--border-accent: rgba(0, 112, 212, 0.30);
--danger: #dc2626;
--danger-bg: rgba(220, 38, 38, 0.08);
--warning: #d97706;
--warning-bg: rgba(217, 119, 6, 0.08);
--success: #16a34a;
--success-bg: rgba(22, 163, 74, 0.08);
--info: #2563eb;
--info-bg: rgba(37, 99, 235, 0.08);
--orange: #ea580c;
--orange-bg: rgba(234, 88, 12, 0.08);
}
@media (prefers-color-scheme: light) {
:root:not([data-theme="dark"]) {
--bg-primary: #f5f7fb;
--bg-secondary: #ffffff;
--bg-card: rgba(255, 255, 255, 0.85);
--bg-card-solid: #ffffff;
--bg-card-hover: #f1f5fb;
--bg-elevated: #f8fafc;
--text-primary: #0c1426;
--text-secondary: #475569;
--text-tertiary: #8a9bb4;
--accent: #0070d4;
--accent-hover: #0080f0;
--accent-muted: rgba(0, 112, 212, 0.10);
--accent-glow: 0 0 20px rgba(0, 112, 212, 0.10);
--border: #e2e8f0;
--border-bright: #cbd5e1;
--border-accent: rgba(0, 112, 212, 0.30);
--danger: #dc2626;
--danger-bg: rgba(220, 38, 38, 0.08);
--warning: #d97706;
--warning-bg: rgba(217, 119, 6, 0.08);
--success: #16a34a;
--success-bg: rgba(22, 163, 74, 0.08);
--info: #2563eb;
--info-bg: rgba(37, 99, 235, 0.08);
--orange: #ea580c;
--orange-bg: rgba(234, 88, 12, 0.08);
}
}
/* ── Reset & Base ── */ /* ── Reset & Base ── */
@@ -467,44 +396,6 @@ code {
background: rgba(0, 200, 255, 0.06); background: rgba(0, 200, 255, 0.06);
} }
.theme-toggle {
background: none;
border: none;
border-top: 1px solid var(--border);
color: var(--text-secondary);
padding: 11px 18px;
cursor: pointer;
display: flex;
align-items: center;
gap: 11px;
font-family: var(--font-body);
font-size: 13.5px;
font-weight: 500;
transition: color 0.2s, background 0.2s;
width: 100%;
text-align: left;
}
.theme-toggle:hover {
color: var(--accent);
background: var(--accent-muted);
}
.theme-toggle svg {
flex-shrink: 0;
opacity: 0.75;
transition: opacity 0.2s;
}
.theme-toggle:hover svg {
opacity: 1;
}
.sidebar.collapsed .theme-toggle {
justify-content: center;
padding: 11px 0;
}
.sidebar.collapsed .sidebar-header { .sidebar.collapsed .sidebar-header {
padding: 22px 0; padding: 22px 0;
justify-content: center; justify-content: center;
@@ -3998,33 +3889,3 @@ tbody tr:last-child td {
.copyable code, .copyable .mono { flex: 1; min-width: 0; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; } .copyable code, .copyable .mono { flex: 1; min-width: 0; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }
.code-snippet-wrapper { position: relative; } .code-snippet-wrapper { position: relative; }
.code-snippet-header { display: flex; align-items: center; justify-content: space-between; margin-bottom: 4px; gap: 8px; } .code-snippet-header { display: flex; align-items: center; justify-content: space-between; margin-bottom: 4px; gap: 8px; }
/* ═══════════════════════════════════════════════════════════════
LIGHT THEME — surface overrides for the few hardcoded dark
colors that don't go through CSS custom properties.
═══════════════════════════════════════════════════════════════ */
:root[data-theme="light"] .main-content {
background-image: radial-gradient(circle at 1px 1px, rgba(100, 116, 139, 0.18) 1px, transparent 0);
}
:root[data-theme="light"] .code-block {
background: #f8fafc;
color: #0c1426;
}
:root[data-theme="light"] .graph-stab-overlay {
background: radial-gradient(ellipse at center, rgba(245, 247, 251, 0.92) 0%, rgba(245, 247, 251, 0.98) 100%);
}
@media (prefers-color-scheme: light) {
:root:not([data-theme="dark"]) .main-content {
background-image: radial-gradient(circle at 1px 1px, rgba(100, 116, 139, 0.18) 1px, transparent 0);
}
:root:not([data-theme="dark"]) .code-block {
background: #f8fafc;
color: #0c1426;
}
:root:not([data-theme="dark"]) .graph-stab-overlay {
background: radial-gradient(ellipse at center, rgba(245, 247, 251, 0.92) 0%, rgba(245, 247, 251, 0.98) 100%);
}
}
@@ -12,5 +12,4 @@ pub mod pentest_wizard;
pub mod severity_badge; pub mod severity_badge;
pub mod sidebar; pub mod sidebar;
pub mod stat_card; pub mod stat_card;
pub mod theme_toggle;
pub mod toast; pub mod toast;
@@ -4,7 +4,6 @@ use dioxus_free_icons::icons::bs_icons::*;
use dioxus_free_icons::Icon; use dioxus_free_icons::Icon;
use crate::app::Route; use crate::app::Route;
use crate::components::theme_toggle::ThemeToggle;
struct NavItem { struct NavItem {
label: &'static str, label: &'static str,
@@ -107,7 +106,6 @@ pub fn Sidebar() -> Element {
} }
// Spacer pushes footer to the bottom // Spacer pushes footer to the bottom
div { class: "sidebar-spacer" } div { class: "sidebar-spacer" }
ThemeToggle { collapsed: collapsed() }
button { button {
class: "sidebar-toggle", class: "sidebar-toggle",
onclick: move |_| collapsed.set(!collapsed()), onclick: move |_| collapsed.set(!collapsed()),
@@ -1,104 +0,0 @@
use dioxus::prelude::*;
use dioxus_free_icons::icons::bs_icons::{BsMoonStars, BsSun};
use dioxus_free_icons::Icon;
#[cfg(feature = "web")]
const STORAGE_KEY: &str = "compliance-scanner.theme";
/// Sidebar-footer theme toggle. Reads the initial state on mount from
/// localStorage (explicit user choice) or `prefers-color-scheme` (OS default),
/// then writes back to both the `<html data-theme="...">` attribute and
/// localStorage on every click.
#[component]
pub fn ThemeToggle(collapsed: bool) -> Element {
// `None` until the on-mount effect resolves the real value, so SSR doesn't
// render the wrong icon for the user's actual theme.
let mut is_dark = use_signal(|| None::<bool>);
use_effect(move || {
let (dark, from_storage) = initial_theme();
is_dark.set(Some(dark));
// If the user already made an explicit choice (in localStorage), assert it
// on the DOM so an OS-vs-stored mismatch can't briefly show the wrong theme.
if from_storage {
apply_theme(dark);
}
});
let label = if collapsed {
""
} else if is_dark().unwrap_or(true) {
"Light mode"
} else {
"Dark mode"
};
let title = if is_dark().unwrap_or(true) {
"Switch to light mode"
} else {
"Switch to dark mode"
};
rsx! {
button {
class: "theme-toggle",
r#type: "button",
title: "{title}",
"aria-label": "{title}",
onclick: move |_| {
let next_dark = !is_dark().unwrap_or(true);
is_dark.set(Some(next_dark));
apply_theme(next_dark);
},
if is_dark().unwrap_or(true) {
Icon { icon: BsSun, width: 16, height: 16 }
} else {
Icon { icon: BsMoonStars, width: 16, height: 16 }
}
if !collapsed {
span { class: "theme-toggle-label", "{label}" }
}
}
}
}
/// Returns `(is_dark, from_storage)`. `from_storage` is true when an explicit
/// user choice is in localStorage; false when we fell back to OS preference
/// (or to the dark default).
#[cfg(feature = "web")]
fn initial_theme() -> (bool, bool) {
if let Some(window) = web_sys::window() {
if let Ok(Some(storage)) = window.local_storage() {
if let Ok(Some(value)) = storage.get_item(STORAGE_KEY) {
return (value == "dark", true);
}
}
if let Ok(Some(mql)) = window.match_media("(prefers-color-scheme: dark)") {
return (mql.matches(), false);
}
}
(true, false)
}
#[cfg(not(feature = "web"))]
fn initial_theme() -> (bool, bool) {
(true, false)
}
#[cfg(feature = "web")]
fn apply_theme(dark: bool) {
let theme = if dark { "dark" } else { "light" };
if let Some(window) = web_sys::window() {
if let Some(document) = window.document() {
if let Some(root) = document.document_element() {
let _ = root.set_attribute("data-theme", theme);
}
}
if let Ok(Some(storage)) = window.local_storage() {
let _ = storage.set_item(STORAGE_KEY, theme);
}
}
}
#[cfg(not(feature = "web"))]
fn apply_theme(_dark: bool) {}