From f10367ecd0286b288132a869c6b7d9371359899f Mon Sep 17 00:00:00 2001
From: Sam Valladares <samvalladares21@gmail.com>
Date: Tue, 27 Jan 2026 01:04:06 -0600
Subject: [PATCH] fix: add explicit embedding initialization with error logging

When embeddings fail to initialize in the MCP server context (e.g., due
to working directory issues), the error was silently swallowed and
smart_ingest would fall back to regular ingest without explanation.

Changes:
- Add init_embeddings() method to Storage for explicit initialization
- Initialize embeddings at MCP server startup with error logging
- Add check_ready() method to EmbeddingService for error access
- Log warning when is_ready() returns false

Now users will see clear error messages like:
"Failed to initialize embedding service: ..."
"Hint: Check FASTEMBED_CACHE_PATH or ensure ~/.fastembed_cache exists"

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---
 crates/vestige-core/src/embeddings/local.rs | 13 ++++++++++++-
 crates/vestige-core/src/storage/sqlite.rs   | 14 ++++++++++++++
 crates/vestige-mcp/src/main.rs              | 15 ++++++++++++++-
 3 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/crates/vestige-core/src/embeddings/local.rs b/crates/vestige-core/src/embeddings/local.rs
index 98e0985..9fe20c7 100644
--- a/crates/vestige-core/src/embeddings/local.rs
+++ b/crates/vestige-core/src/embeddings/local.rs
@@ -186,7 +186,18 @@ impl EmbeddingService {
 
     /// Check if the model is ready
     pub fn is_ready(&self) -> bool {
-        get_model().is_ok()
+        match get_model() {
+            Ok(_) => true,
+            Err(e) => {
+                tracing::warn!("Embedding model not ready: {}", e);
+                false
+            }
+        }
+    }
+
+    /// Check if the model is ready and return the error if not
+    pub fn check_ready(&self) -> Result<(), EmbeddingError> {
+        get_model().map(|_| ())
     }
 
     /// Initialize the model (downloads if necessary)
diff --git a/crates/vestige-core/src/storage/sqlite.rs b/crates/vestige-core/src/storage/sqlite.rs
index 32e457a..7843cc3 100644
--- a/crates/vestige-core/src/storage/sqlite.rs
+++ b/crates/vestige-core/src/storage/sqlite.rs
@@ -1072,6 +1072,20 @@ impl Storage {
         false
     }
 
+    /// Initialize the embedding service explicitly
+    /// Call this at startup to catch initialization errors early
+    #[cfg(feature = "embeddings")]
+    pub fn init_embeddings(&mut self) -> Result<()> {
+        self.embedding_service.init().map_err(|e| {
+            StorageError::Init(format!("Embedding service initialization failed: {}", e))
+        })
+    }
+
+    #[cfg(not(feature = "embeddings"))]
+    pub fn init_embeddings(&mut self) -> Result<()> {
+        Ok(()) // No-op when embeddings feature is disabled
+    }
+
     /// Get query embedding from cache or compute it
     #[cfg(feature = "embeddings")]
     fn get_query_embedding(&self, query: &str) -> Result<Vec<f32>> {
diff --git a/crates/vestige-mcp/src/main.rs b/crates/vestige-mcp/src/main.rs
index f490f24..ef16924 100644
--- a/crates/vestige-mcp/src/main.rs
+++ b/crates/vestige-mcp/src/main.rs
@@ -133,8 +133,21 @@ async fn main() {
 
     // Initialize storage with optional custom data directory
     let storage = match Storage::new(data_dir) {
-        Ok(s) => {
+        Ok(mut s) => {
             info!("Storage initialized successfully");
+
+            // Try to initialize embeddings early and log any issues
+            #[cfg(feature = "embeddings")]
+            {
+                if let Err(e) = s.init_embeddings() {
+                    error!("Failed to initialize embedding service: {}", e);
+                    error!("Smart ingest will fall back to regular ingest without deduplication");
+                    error!("Hint: Check FASTEMBED_CACHE_PATH or ensure ~/.fastembed_cache exists");
+                } else {
+                    info!("Embedding service initialized successfully");
+                }
+            }
+
             Arc::new(Mutex::new(s))
         }
         Err(e) => {