feat(semantic_search): make embedding model configurable (#22)

google/gemini-embedding-001 became paid on OpenRouter, leaving
users without credit unable to run the semantic_search tool. The
old code hardcoded the model and 3072 dimensions in three places.

Make OpenRouterEmbedder accept model/dimension via constructor
args or OPENROUTER_EMBEDDING_MODEL / OPENROUTER_EMBEDDING_DIMENSION
env vars, with the previous values as backward-compatible defaults.
Switch the VectorStore and the response payload in mcp_server_main
to read embedder.dimension instead of the hardcoded 3072 so a
configured non-Gemini model does not produce shape mismatches.

Bad dimension input (non-int or non-positive) now raises a clear
ValueError instead of a downstream shape error.

Documented the new env vars in .env.example.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

mcp_server_main.py

@@ -1281,7 +1281,7 @@ YANLIŞ KULLANIM:
         try:
             # Initialize components
             embedder = OpenRouterEmbedder()
-            vector_store = VectorStore(dimension=3072)  # Gemini embedding dimension
+            vector_store = VectorStore(dimension=embedder.dimension)
             processor = DocumentProcessor(chunk_size=1500, chunk_overlap=300)
 
             # Step 1: Initial keyword search to get document IDs
@@ -1437,7 +1437,8 @@ YANLIŞ KULLANIM:
                 "query": query,
                 "initial_keyword": initial_keyword,
                 "total_documents_processed": len(documents_data),
-                "embedding_dimension": 3072,
+                "embedding_model": embedder.model,
+                "embedding_dimension": embedder.dimension,
                 "results": formatted_results,
                 "stats": {
                     "documents_in_store": stats["num_documents"],