refactor(cache): cleanup expired cache entries during update operations

Signed-off-by: QIN2DIM <[email protected]>

Author: QIN2DIM

docker/README.md

@@ -11,8 +11,8 @@ This Docker Compose configuration allows you to quickly run Semantic Router + En
 
 1. **Clone the repository and navigate to the project directory**
    ```bash
-   git clone <repository-url>
-   cd semantic_router
+   git clone https://github.com/vllm-project/semantic-router.git
+   cd semantic-router
    ```
 
 2. **Download required models** (if not already present):

src/semantic-router/pkg/cache/cache.go

@@ -108,6 +108,9 @@ func (c *SemanticCache) UpdateWithResponse(query string, responseBody []byte) er
 	c.mu.Lock()
 	defer c.mu.Unlock()
 
+	// Cleanup expired entries while we have the write lock
+	c.cleanupExpiredEntries()
+
 	// Find the pending request by query
 	for i, entry := range c.entries {
 		if entry.Query == query && entry.ResponseBody == nil {