Revert "feat(knowledgebase): replace litellm-pgvector connector with memory-retrieval"

This reverts commit abeadc49c8.

Restores vendor/litellm-pgvector/ and the vector_store_registry wiring
(in-band file_search tool-call support) at the user's request, after
re-confirming against docs.litellm.ai/docs/completion/knowledgebase and
litellm-pgvector's own README that pg_vector is still not an in-process
vector_store_registry backend -- it requires this same standalone
connector service either way, so there is no simpler 'native' path that
was missed. Trading back in: 793 lines of vendored code, the untested
Prisma migration, and the git-context build risk noted in VENDORED.md
(all flagged as unverified against real hardware in issue #24), in
exchange for the file_search in-band tool call memory-retrieval did not
support.

Conflicts resolved on top of later commits (Redis, update.sh key-minting
fold-in):
- .env.example / docs/memory-knowledgebase.md: kept the auto-mint-via-
  update.sh language, renamed MEMORY_RETRIEVAL_* back to
  LITELLM_PGVECTOR_*.
- scripts/generate-secrets.sh: left deleted -- its job was folded into
  update.sh in 24d749b, unrelated to this revert.
- scripts/update.sh: renamed the MEMORY_RETRIEVAL_* secret/mint calls to
  LITELLM_PGVECTOR_* to match.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018WHfjWrSEcGhCoeu6dQfDa

vendor/litellm-pgvector/config.py

@@ -0,0 +1,60 @@
+from typing import Dict, Optional
+from pydantic import BaseModel
+from pydantic_settings import BaseSettings
+
+
+class DatabaseFieldConfig(BaseModel):
+    """Configuration for database field mappings"""
+    id_field: str = "id"
+    content_field: str = "content"
+    metadata_field: str = "metadata"
+    embedding_field: str = "embedding"
+    vector_store_id_field: str = "vector_store_id"
+    created_at_field: str = "created_at"
+
+
+class EmbeddingConfig(BaseModel):
+    """Configuration for embedding generation via LiteLLM proxy"""
+    model: str = "text-embedding-ada-002"
+    base_url: str = "http://localhost:4000"  # LiteLLM proxy URL
+    api_key: str = "sk-1234"  # LiteLLM proxy API key
+    dimensions: int = 1536
+
+
+class Settings(BaseSettings):
+    """Application settings"""
+    # Database configuration
+    database_url: str = "postgresql://username:password@localhost:5432/vectordb?schema=public"
+    
+    # API configuration
+    server_api_key: str = "your-api-key-here"
+    port: int = 8000
+    host: str = "0.0.0.0"
+    
+    # Database field mappings
+    db_fields: DatabaseFieldConfig = DatabaseFieldConfig()
+    
+    # Embedding configuration
+    embedding: EmbeddingConfig = EmbeddingConfig()
+    
+    class Config:
+        env_file = ".env"
+        env_nested_delimiter = "__"
+        case_sensitive = False
+        
+        # Allow environment variables like:
+        # DB_FIELDS__ID_FIELD=custom_id
+        # EMBEDDING__MODEL=text-embedding-3-small
+        # EMBEDDING__API_BASE=https://api.openai.com/v1
+        
+    @property
+    def table_names(self) -> Dict[str, str]:
+        """Get table names"""
+        return {
+            "vector_stores": "vector_stores",
+            "embeddings": "embeddings"
+        }
+
+
+# Global settings instance
+settings = Settings()