code-graph-context 2.12.0 → 2.12.2

package/dist/cli/cli.js

@@ -264,7 +264,7 @@ const preDownloadModel = async (sidecarDir, python, modelName) => {
         return new Promise((resolve) => {
             const proc = spawnProcess(python, [
                 '-c',
-                `from sentence_transformers import SentenceTransformer; m = SentenceTransformer("${modelName}"); print(f"dims:{len(m.encode(['test'])[0])}")`,
+                `from sentence_transformers import SentenceTransformer; m = SentenceTransformer("${modelName}", trust_remote_code=True); print(f"dims:{len(m.encode(['test'])[0])}")`,
             ], { cwd: sidecarDir, stdio: ['pipe', 'pipe', 'pipe'], timeout: 30_000 });
             let stdout = '';
             proc.stdout?.on('data', (d) => (stdout += d.toString()));
@@ -286,7 +286,7 @@ const preDownloadModel = async (sidecarDir, python, modelName) => {
     const downloaded = await new Promise((resolve) => {
         const proc = spawnProcess(python, [
             '-c',
-            `from sentence_transformers import SentenceTransformer; print("downloading..."); m = SentenceTransformer("${modelName}"); print(f"done dims:{len(m.encode(['test'])[0])}")`,
+            `from sentence_transformers import SentenceTransformer; print("downloading..."); m = SentenceTransformer("${modelName}", trust_remote_code=True); print(f"done dims:{len(m.encode(['test'])[0])}")`,
         ], { cwd: sidecarDir, stdio: ['pipe', 'pipe', 'inherit'] });
         let stdout = '';
         proc.stdout?.on('data', (d) => {
@@ -302,7 +302,7 @@ const preDownloadModel = async (sidecarDir, python, modelName) => {
     }
     else {
         log(sym.warn, 'Model download failed — it will retry on first use');
-        console.log(`  ${c.dim}You can download manually: ${python} -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('${modelName}')"${c.reset}`);
+        console.log(`  ${c.dim}You can download manually: ${python} -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('${modelName}', trust_remote_code=True)"${c.reset}`);
     }
 };
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "code-graph-context",
-  "version": "2.12.0",
+  "version": "2.12.2",
   "description": "MCP server that builds code graphs to provide rich context to LLMs",
   "type": "module",
   "homepage": "https://github.com/drewdrewH/code-graph-context#readme",

package/sidecar/embedding_server.py

@@ -58,10 +58,10 @@ def load_model():
 
         use_half = os.environ.get("EMBEDDING_HALF_PRECISION", "").lower() == "true"
         if use_half:
-            model = SentenceTransformer(model_name, device=device, model_kwargs={"torch_dtype": "float16"})
+            model = SentenceTransformer(model_name, device=device, trust_remote_code=True, model_kwargs={"torch_dtype": "float16"})
             logger.info(f"Model loaded in float16 (half precision)")
         else:
-            model = SentenceTransformer(model_name, device=device)
+            model = SentenceTransformer(model_name, device=device, trust_remote_code=True)
             logger.info(f"Model loaded in float32 (full precision)")
         logger.info(f"Running warmup...")