ci: improve GitHub workflows with Rust caching, linting, and tests

- Add Swatinem/rust-cache for faster CI builds
- Add cargo fmt --check to enforce code formatting
- Add cargo clippy with -D warnings for strict linting
- Add cargo test to run Rust unit tests in CI
- Consolidate test and lint into single CI job
- Fix Node version inconsistency (use 22 everywhere)
- Fix clippy warnings in Rust code (too_many_arguments, redundant_closure)
- Format all Rust code with cargo fmt

Author: Helweg

.github/workflows/build.yml

@@ -41,6 +41,12 @@ jobs:
         with:
           targets: ${{ matrix.target }}
 
+      - name: Cache Cargo
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: native -> target
+          key: ${{ matrix.target }}
+
       - name: Install cross-compilation tools (Linux ARM64)
         if: matrix.target == 'aarch64-unknown-linux-gnu'
         run: |
@@ -76,7 +82,7 @@ jobs:
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: '24'
+          node-version: '22'
           cache: 'npm'
           registry-url: 'https://registry.npmjs.org'
 
@@ -97,3 +103,5 @@ jobs:
 
       - name: Publish to npm
         run: npm publish --provenance --access public
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}

.github/workflows/ci.yml

@@ -20,10 +20,29 @@ jobs:
 
       - name: Setup Rust
         uses: dtolnay/rust-toolchain@stable
+        with:
+          components: clippy, rustfmt
+
+      - name: Cache Cargo
+        uses: Swatinem/rust-cache@v2
+        with:
+          workspaces: native -> target
 
       - name: Install dependencies
         run: npm ci
 
+      - name: Check Rust formatting
+        working-directory: native
+        run: cargo fmt --check
+
+      - name: Run Clippy
+        working-directory: native
+        run: cargo clippy -- -D warnings
+
+      - name: Run Rust tests
+        working-directory: native
+        run: cargo test
+
       - name: Build native module
         working-directory: native
         run: |
@@ -36,22 +55,8 @@ jobs:
       - name: Run typecheck
         run: npm run typecheck
 
-      - name: Run tests
-        run: npm run test:run
-
-  lint:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: '22'
-          cache: 'npm'
-
-      - name: Install dependencies
-        run: npm ci
-
       - name: Run lint
         run: npm run lint
+
+      - name: Run tests
+        run: npm run test:run

native/src/db.rs

@@ -1,4 +1,4 @@
-use rusqlite::{Connection, params, OptionalExtension};
+use rusqlite::{params, Connection, OptionalExtension};
 use std::path::Path;
 use thiserror::Error;
 
@@ -189,7 +189,11 @@ pub fn get_embeddings_batch(
         return Ok(vec![]);
     }
 
-    let placeholders: String = content_hashes.iter().map(|_| "?").collect::<Vec<_>>().join(",");
+    let placeholders: String = content_hashes
+        .iter()
+        .map(|_| "?")
+        .collect::<Vec<_>>()
+        .join(",");
     let query = format!(
         "SELECT content_hash, embedding FROM embeddings WHERE content_hash IN ({})",
         placeholders
@@ -221,7 +225,11 @@ pub fn get_missing_embeddings(
         return Ok(vec![]);
     }
 
-    let placeholders: String = content_hashes.iter().map(|_| "?").collect::<Vec<_>>().join(",");
+    let placeholders: String = content_hashes
+        .iter()
+        .map(|_| "?")
+        .collect::<Vec<_>>()
+        .join(",");
     let query = format!(
         "SELECT content_hash FROM embeddings WHERE content_hash IN ({})",
         placeholders
@@ -250,6 +258,7 @@ pub fn get_missing_embeddings(
 // ============================================================================
 
 /// Insert or update a chunk
+#[allow(clippy::too_many_arguments)]
 pub fn upsert_chunk(
     conn: &Connection,
     chunk_id: &str,
@@ -280,10 +289,7 @@ pub fn upsert_chunk(
 }
 
 /// Batch insert or update chunks within a single transaction
-pub fn upsert_chunks_batch(
-    conn: &mut Connection,
-    chunks: &[ChunkRow],
-) -> DbResult<()> {
+pub fn upsert_chunks_batch(conn: &mut Connection, chunks: &[ChunkRow]) -> DbResult<()> {
     if chunks.is_empty() {
         return Ok(());
     }
@@ -406,9 +412,8 @@ pub fn add_chunks_to_branch(conn: &Connection, branch: &str, chunk_ids: &[String
         return Ok(());
     }
 
-    let mut stmt = conn.prepare(
-        "INSERT OR IGNORE INTO branch_chunks (branch, chunk_id) VALUES (?, ?)",
-    )?;
+    let mut stmt =
+        conn.prepare("INSERT OR IGNORE INTO branch_chunks (branch, chunk_id) VALUES (?, ?)")?;
 
     for chunk_id in chunk_ids {
         stmt.execute(params![branch, chunk_id])?;
@@ -428,9 +433,8 @@ pub fn add_chunks_to_branch_batch(
 
     let tx = conn.transaction()?;
     {
-        let mut stmt = tx.prepare(
-            "INSERT OR IGNORE INTO branch_chunks (branch, chunk_id) VALUES (?, ?)",
-        )?;
+        let mut stmt =
+            tx.prepare("INSERT OR IGNORE INTO branch_chunks (branch, chunk_id) VALUES (?, ?)")?;
 
         for chunk_id in chunk_ids {
             stmt.execute(params![branch, chunk_id])?;

native/src/hasher.rs

@@ -1,7 +1,7 @@
-use xxhash_rust::xxh3::xxh3_64;
+use anyhow::Result;
 use std::fs;
 use std::path::Path;
-use anyhow::Result;
+use xxhash_rust::xxh3::xxh3_64;
 
 pub fn xxhash_content(content: &str) -> String {
     format!("{:016x}", xxh3_64(content.as_bytes()))
@@ -21,7 +21,7 @@ mod tests {
         let hash1 = xxhash_content("hello world");
         let hash2 = xxhash_content("hello world");
         let hash3 = xxhash_content("different content");
-        
+
         assert_eq!(hash1, hash2);
         assert_ne!(hash1, hash3);
         assert_eq!(hash1.len(), 16);

native/src/inverted_index.rs

@@ -150,15 +150,11 @@ impl InvertedIndexInner {
                     continue;
                 }
 
-                let df = self
-                    .term_to_chunks
-                    .get(term)
-                    .map(|s| s.len())
-                    .unwrap_or(0) as f64;
+                let df = self.term_to_chunks.get(term).map(|s| s.len()).unwrap_or(0) as f64;
                 let idf = ((n - df + 0.5) / (df + 0.5) + 1.0).ln();
 
-                let tf_norm =
-                    (tf * (k1 + 1.0)) / (tf + k1 * (1.0 - b + b * (doc_length as f64 / avg_doc_length)));
+                let tf_norm = (tf * (k1 + 1.0))
+                    / (tf + k1 * (1.0 - b + b * (doc_length as f64 / avg_doc_length)));
                 score += idf * tf_norm;
             }