Merge remote-tracking branch 'origin/feat/v3-pipeline' into feat/v3-pipeline

# Conflicts:
#	mem0-ts/src/oss/src/utils/factory.ts
#	mem0/vector_stores/milvus.py
#	mem0/vector_stores/qdrant.py

mem0-ts/src/oss/src/utils/factory.ts

@@ -1,6 +1,5 @@
 import { OpenAIEmbedder } from "../embeddings/openai";
 import { OllamaEmbedder } from "../embeddings/ollama";
-import { LMStudioEmbedder } from "../embeddings/lmstudio";
 import { OpenAILLM } from "../llms/openai";
 import { OpenAIStructuredLLM } from "../llms/openai_structured";
 import { AnthropicLLM } from "../llms/anthropic";
@@ -20,7 +19,6 @@ import { Qdrant } from "../vector_stores/qdrant";
 import { VectorizeDB } from "../vector_stores/vectorize";
 import { RedisDB } from "../vector_stores/redis";
 import { OllamaLLM } from "../llms/ollama";
-import { LMStudioLLM } from "../llms/lmstudio";
 import { SupabaseDB } from "../vector_stores/supabase";
 import { SQLiteManager } from "../storage/SQLiteManager";
 import { MemoryHistoryManager } from "../storage/MemoryHistoryManager";
@@ -35,7 +33,6 @@ import { LangchainEmbedder } from "../embeddings/langchain";
 import { LangchainVectorStore } from "../vector_stores/langchain";
 import { AzureAISearch } from "../vector_stores/azure_ai_search";
 import { PGVector } from "../vector_stores/pgvector";
-import { DeepSeekLLM } from "../llms/deepseek";
 
 export class EmbedderFactory {
   static create(provider: string, config: EmbeddingConfig): Embedder {
@@ -44,8 +41,6 @@ export class EmbedderFactory {
         return new OpenAIEmbedder(config);
       case "ollama":
         return new OllamaEmbedder(config);
-      case "lmstudio":
-        return new LMStudioEmbedder(config);
       case "google":
       case "gemini":
         return new GoogleEmbedder(config);
@@ -72,8 +67,6 @@ export class LLMFactory {
         return new GroqLLM(config);
       case "ollama":
         return new OllamaLLM(config);
-      case "lmstudio":
-        return new LMStudioLLM(config);
       case "google":
       case "gemini":
         return new GoogleLLM(config);
@@ -83,8 +76,6 @@ export class LLMFactory {
         return new MistralLLM(config);
       case "langchain":
         return new LangchainLLM(config);
-      case "deepseek":
-        return new DeepSeekLLM(config);
       default:
         throw new Error(`Unsupported LLM provider: ${provider}`);
     }

mem0/memory/main.py

@@ -995,6 +995,13 @@ class Memory(MemoryBase):
         # Apply enhanced metadata filtering if advanced operators are detected
         if filters and self._has_advanced_operators(filters):
             processed_filters = self._process_metadata_filters(filters)
+            # Remove original logical/operator keys that _build_filters_and_metadata
+            # copied verbatim from input_filters — they have now been reprocessed.
+            for logical_key in ("AND", "OR", "NOT"):
+                effective_filters.pop(logical_key, None)
+            for fk in list(filters.keys()):
+                if fk not in ("AND", "OR", "NOT") and fk in effective_filters and isinstance(filters[fk], dict):
+                    effective_filters.pop(fk, None)
             effective_filters.update(processed_filters)
         elif filters:
             # Simple filters, merge directly
@@ -1235,7 +1242,7 @@ class Memory(MemoryBase):
 
             additional_metadata = {k: v for k, v in payload.items() if k not in core_and_promoted_keys}
             if additional_metadata:
-                if "metadata" not in memory_item_dict:
+                if not memory_item_dict.get("metadata"):
                     memory_item_dict["metadata"] = {}
                 memory_item_dict["metadata"].update(additional_metadata)
 
@@ -2332,6 +2339,13 @@ class AsyncMemory(MemoryBase):
         # Apply enhanced metadata filtering if advanced operators are detected
         if filters and self._has_advanced_operators(filters):
             processed_filters = self._process_metadata_filters(filters)
+            # Remove original logical/operator keys that _build_filters_and_metadata
+            # copied verbatim from input_filters — they have now been reprocessed.
+            for logical_key in ("AND", "OR", "NOT"):
+                effective_filters.pop(logical_key, None)
+            for fk in list(filters.keys()):
+                if fk not in ("AND", "OR", "NOT") and fk in effective_filters and isinstance(filters[fk], dict):
+                    effective_filters.pop(fk, None)
             effective_filters.update(processed_filters)
         elif filters:
             # Simple filters, merge directly
@@ -2572,7 +2586,7 @@ class AsyncMemory(MemoryBase):
 
             additional_metadata = {k: v for k, v in payload.items() if k not in core_and_promoted_keys}
             if additional_metadata:
-                if "metadata" not in memory_item_dict:
+                if not memory_item_dict.get("metadata"):
                     memory_item_dict["metadata"] = {}
                 memory_item_dict["metadata"].update(additional_metadata)