Remove all _write_debug_log occurrences and fix related tests

Author: EmiM

src/mcp_code_indexer/vector_mode/daemon.py

@@ -14,7 +14,7 @@
 import time
 import time
 
-from mcp_code_indexer.vector_mode.monitoring.utils import _write_debug_log
+
 
 from ..database.database import DatabaseManager
 from ..database.models import Project, SyncStatus
@@ -275,7 +275,6 @@ async def _queue_full_project_indexing(
         try:
             # Get or create IndexMeta for the project
             index_meta = await self.db_manager.get_or_create_index_meta(project_name)
-            _write_debug_log(f"Retrieved IndexMeta for {project_name}: {index_meta}")
 
             # If status is 'failed' or 'paused', change it to 'pending'
             if index_meta.sync_status in [SyncStatus.FAILED, SyncStatus.PAUSED]:
@@ -287,7 +286,6 @@ async def _queue_full_project_indexing(
 
             # Only queue initial embedding if status is 'pending'
             if index_meta.sync_status == SyncStatus.PENDING:
-                _write_debug_log(f"Retrieved IndexMeta for {project_name}: 1")
                 task: InitialProjectEmbeddingTask = {
                     "type": VectorDaemonTaskType.INITIAL_PROJECT_EMBEDDING,
                     "project_name": project_name,
@@ -442,18 +440,15 @@ async def _process_initial_project_embedding_task(
         logger.info(
             f"Worker {worker_id}: Starting initial project embedding for {project_name}"
         )
-        _write_debug_log(f"Retrieved IndexMeta for {project_name}: 2")
         try:
             # Update IndexMeta status to in_progress
             index_meta = await self.db_manager.get_or_create_index_meta(project_name)
             index_meta.sync_status = SyncStatus.IN_PROGRESS
             await self.db_manager.update_index_meta(index_meta)
-            _write_debug_log(f"Retrieved IndexMeta for {project_name}: 3")
             # Perform the actual embedding
             stats = await self._perform_initial_project_embedding(
                 project_name, folder_path
             )
-            _write_debug_log(f"Retrieved IndexMeta for {project_name}: 4")
 
             # Update IndexMeta status to completed on success
             index_meta = await self.db_manager.get_or_create_index_meta(project_name)
@@ -466,10 +461,6 @@ async def _process_initial_project_embedding_task(
                 index_meta.sync_status = SyncStatus.COMPLETED
                 index_meta.error_message = None
 
-            _write_debug_log(
-                f"Retrieved IndexMeta for {project_name}: {index_meta.sync_status.value}"
-            )
-
             index_meta.last_sync = datetime.utcnow()
             index_meta.total_files = stats.get("scanned", 0)
             index_meta.indexed_files = stats.get("processed", 0)
@@ -496,9 +487,6 @@ async def _process_initial_project_embedding_task(
                 logger.error(
                     f"Failed to update IndexMeta after embedding error: {meta_error}"
                 )
-                _write_debug_log(
-                    f"Retrieved IndexMeta for {project_name}: error: {meta_error}"
-                )
 
             self.stats["errors_count"] += 1
 
@@ -803,9 +791,6 @@ async def process_batch_with_semaphore(
             for result in batch_results:
                 if isinstance(result, Exception):
                     logger.error(f"Batch processing failed with exception: {result}")
-                    _write_debug_log(
-                        f"Batch processing failed with exception: {result}"
-                    )
                     # Estimate failed files (assuming average batch size)
                     estimated_failed = min(
                         batch_size, len(project_files) - processed_count
@@ -849,7 +834,6 @@ async def process_batch_with_semaphore(
             )
 
         except Exception as e:
-            _write_debug_log(f"Error during initial embedding: {e}")
             logger.error(
                 f"Error during initial project embedding for {project_name}: {e}"
             )

src/mcp_code_indexer/vector_mode/monitoring/file_watcher.py

@@ -7,7 +7,7 @@
 
 import asyncio
 import logging
-from .utils import _write_debug_log
+
 from pathlib import Path
 from typing import Callable, Optional, List, Dict, Any
 import time

src/mcp_code_indexer/vector_mode/monitoring/utils.py

@@ -5,12 +5,4 @@
 logger = logging.getLogger(__name__)
 
 
-def _write_debug_log(message: str) -> None:
-    """Write debug message to temporary file."""
-    try:
-        with open("/tmp/filewatcher_debug.log", "a") as f:
-            timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S.%f")
-            f.write(f"[{timestamp}] {message}\n")
-    except Exception:
-        logger.error("Failed to write debug log. ")
-        pass
+

src/mcp_code_indexer/vector_mode/providers/turbopuffer_client.py

@@ -14,7 +14,7 @@
 from typing import List, Dict, Any, Optional
 import turbopuffer
 
-from mcp_code_indexer.vector_mode.monitoring.utils import _write_debug_log
+
 from turbopuffer.types import Row
 
 from ..config import VectorConfig
@@ -126,7 +126,6 @@ def upsert_vectors(
 
         except Exception as e:
             logger.error(f"Failed to upsert vectors: {e}")
-            _write_debug_log(f"Failed to upsert vectors: {e}")
             raise RuntimeError(f"Vector upsert failed: {e}")
 
     def upsert_vectors_batch(
@@ -211,7 +210,6 @@ def upsert_vectors_batch(
 
         except Exception as e:
             logger.error(f"Failed to batch upsert vectors: {e}")
-            _write_debug_log(f"Failed to batch upsert vectors: {e}")
             raise RuntimeError(f"Batch vector upsert failed: {e}")
 
     def search_vectors(
@@ -243,7 +241,6 @@ def search_vectors(
 
         except Exception as e:
             logger.error(f"Vector search failed: {e}")
-            _write_debug_log(f"Vector search failed: {e}, filters value: {filters}")
             raise RuntimeError(f"Vector search failed: {e}")
 
     def delete_vectors(
@@ -393,8 +390,6 @@ def search_with_metadata_filter(
             # Multiple conditions - use And format
             filters = ("And", filter_conditions)
 
-        _write_debug_log(f"Search filters: {filters}")
-
         return self.search_vectors(
             query_vector=query_vector,
             top_k=top_k,

src/mcp_code_indexer/vector_mode/providers/voyage_client.py

@@ -9,7 +9,7 @@
 from typing import List, Dict, Any, Tuple
 import voyageai
 
-from mcp_code_indexer.vector_mode.monitoring.utils import _write_debug_log
+
 
 from ..config import VectorConfig, DEFAULT_EMBEDDING_MODEL
 from ..const import MODEL_DIMENSIONS
@@ -93,11 +93,6 @@ def generate_embeddings(
 
         logger.info(f"Generating embeddings for {len(texts)} texts using {self.model}")
 
-        _write_debug_log(
-            f"generating embeddings, estimated cost: {self.count_tokens(texts)}. len(texts)={len(texts)}"
-        )
-        _write_debug_log(f"sample text: {texts[0][:100]}...")
-
         try:
             result = self.client.embed(
                 texts=texts, model=self.model, input_type=input_type, truncation=True
@@ -111,7 +106,6 @@ def generate_embeddings(
             return result.embeddings
 
         except Exception as e:
-            _write_debug_log(f"Failed to generate embeddings: {e}")
             logger.error(f"Failed to generate embeddings: {e}")
             raise RuntimeError(f"Embedding generation failed: {e}")
 

src/mcp_code_indexer/vector_mode/services/embedding_service.py

@@ -10,7 +10,7 @@
 from pathlib import Path
 from typing import List, Dict, Tuple
 
-from mcp_code_indexer.vector_mode.monitoring.utils import _write_debug_log
+
 
 from ..chunking.ast_chunker import CodeChunk
 from ..providers.voyage_client import VoyageClient
@@ -305,9 +305,6 @@ async def _build_token_aware_batches(
             logger.debug(
                 f"File {file_path}: {len(file_texts)} texts, {file_tokens} tokens"
             )
-            _write_debug_log(
-                f"File {file_path}: {len(file_texts)} texts, {file_tokens} tokens"
-            )
 
             # If adding this file would exceed token limit OR text count limit, finalize current batch
             if (
@@ -332,11 +329,6 @@ async def _build_token_aware_batches(
                     f"{current_batch_tokens} tokens (limit exceeded: "
                     f"tokens={token_exceeded}, count={count_exceeded})"
                 )
-                _write_debug_log(
-                    f"BATCH ANALYSIS: current_batch_texts={len(current_batch_texts)}, "
-                    f"file_texts={len(file_texts)}, total={len(current_batch_texts) + len(file_texts)}, "
-                    f"limit={self.config.voyage_batch_size_limit}"
-                )
 
                 batches.append((current_batch_texts, current_batch_boundaries))
 
@@ -354,11 +346,6 @@ async def _build_token_aware_batches(
             current_batch_tokens += file_tokens
             batch_idx = end_idx
 
-            _write_debug_log(
-                f"AFTER ADDING: batch now has {len(current_batch_texts)} texts, "
-                f"{current_batch_tokens} tokens"
-            )
-
         # Add final batch if it has content
         if current_batch_texts:
             logger.info(

src/mcp_code_indexer/vector_mode/services/vector_storage_service.py

@@ -10,8 +10,6 @@
 from pathlib import Path
 from typing import List, Dict, Any, Optional
 
-from mcp_code_indexer.vector_mode.monitoring.utils import _write_debug_log
-
 from turbopuffer.types import Row
 
 from ..chunking.ast_chunker import CodeChunk

tests/unit/vector_mode/test_vector_storage_service.py

@@ -562,7 +562,7 @@ def __init__(self, file_path: str, file_mtime: str, **kwargs):
             query_vector=[0.0] * embedding_dim,  # dummy vector with embedding_dimension
             top_k=1200,
             namespace="mcp_code_test_project",
-            filters=(("project_id", "Eq", project_name),),
+            filters=("project_id", "Eq", project_name),
         )
 
     async def test_get_file_metadata_specific_files(
@@ -761,5 +761,5 @@ def __init__(self, file_path: str, file_mtime: str):
             query_vector=[0.0] * embedding_dim,
             top_k=1200,
             namespace="mcp_code_test_project",
-            filters=(("project_id", "Eq", project_name),),
+            filters=("project_id", "Eq", project_name),
         )