claude-self-reflect 2.4.1 → 2.4.2

package/mcp-server/run-mcp-docker.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+# Run the MCP server in the Docker container with stdin attached
+# Using python -u for unbuffered output
+# Using server.py which supports local embeddings (not server_v2.py)
+docker exec -i claude-reflection-mcp python -u -m src

package/mcp-server/src/server_v2.py

@@ -42,11 +42,11 @@ DECAY_SCALE_DAYS = float(os.getenv('DECAY_SCALE_DAYS', '90'))
 # Initialize Voyage AI client
 voyage_client = voyageai.Client(api_key=VOYAGE_API_KEY) if VOYAGE_API_KEY else None
 
-# Debug environment loading
-print(f"[DEBUG] Qdrant Native Decay Server v2.0.0")
-print(f"[DEBUG] ENABLE_MEMORY_DECAY: {ENABLE_MEMORY_DECAY}")
-print(f"[DEBUG] DECAY_WEIGHT: {DECAY_WEIGHT}")
-print(f"[DEBUG] DECAY_SCALE_DAYS: {DECAY_SCALE_DAYS}")
+# Debug environment loading (disabled for production)
+# print(f"[DEBUG] Qdrant Native Decay Server v2.0.0")
+# print(f"[DEBUG] ENABLE_MEMORY_DECAY: {ENABLE_MEMORY_DECAY}")
+# print(f"[DEBUG] DECAY_WEIGHT: {DECAY_WEIGHT}")
+# print(f"[DEBUG] DECAY_SCALE_DAYS: {DECAY_SCALE_DAYS}")
 
 
 class SearchResult(BaseModel):
@@ -246,5 +246,9 @@ async def store_reflection(
         return f"Failed to store reflection: {str(e)}"
 
 
-# Debug output
-print(f"[DEBUG] FastMCP server v2.0.0 created with native Qdrant decay")
+# Debug output (disabled for production)
+# print(f"[DEBUG] FastMCP server v2.0.0 created with native Qdrant decay")
+
+# Run the server when executed as main module
+if __name__ == "__main__":
+    mcp.run(transport="stdio", show_banner=False)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-self-reflect",
-  "version": "2.4.1",
+  "version": "2.4.2",
   "description": "Give Claude perfect memory of all your conversations - Installation wizard for Python MCP server",
   "keywords": [
     "claude",
@@ -32,8 +32,12 @@
     "mcp-server/src/**/*.py",
     "mcp-server/pyproject.toml",
     "mcp-server/run-mcp.sh",
+    "mcp-server/run-mcp-docker.sh",
     "scripts/import-*.py",
     ".claude/agents/*.md",
+    "docker-compose.yaml",
+    "Dockerfile.*",
+    ".env.example",
     "README.md",
     "LICENSE"
   ],

package/scripts/import-conversations-unified.py

@@ -19,6 +19,12 @@ from qdrant_client.models import (
     Filter, FieldCondition, MatchValue
 )
 
+from tenacity import (
+    retry,
+    stop_after_attempt,
+    wait_random_exponential,
+)
+
 # Configuration
 QDRANT_URL = os.getenv("QDRANT_URL", "http://localhost:6333")
 LOGS_DIR = os.getenv("LOGS_DIR", "/logs")
@@ -54,6 +60,15 @@ else:
 # Initialize Qdrant client
 client = QdrantClient(url=QDRANT_URL)
 
+
+def log_retry_state(retry_state):
+    print(f"Retrying function '{retry_state.fn.__name__}' for the {retry_state.attempt_number} time.")
+    print(f"----> Waiting for {retry_state.next_action.sleep} seconds before next attempt.")
+
+@retry(wait=wait_random_exponential(multiplier=2, min=30, max=120), stop=stop_after_attempt(6), before_sleep=log_retry_state)
+def embed_with_backoff(**kwargs):
+    return voyage_client.embed(**kwargs)
+
 def generate_embeddings(texts: List[str]) -> List[List[float]]:
     """Generate embeddings for a list of texts."""
     if PREFER_LOCAL_EMBEDDINGS or not VOYAGE_API_KEY:
@@ -62,7 +77,7 @@ def generate_embeddings(texts: List[str]) -> List[List[float]]:
         return [embedding.tolist() for embedding in embeddings]
     else:
         # Voyage AI embeddings
-        result = voyage_client.embed(
+        result = embed_with_backoff(
             texts=texts,
             model="voyage-3-large",
             input_type="document"