refactor: remove pgvector runtime

harness/tht/vectorstore/reader.py

@@ -1,18 +1,4 @@
-"""Lettura del pgvector dietro un'unica interfaccia `.search(query_vec, top_n, kinds)`, così
-`search.combined_search` resta agnostico al transport. Due implementazioni:
-
-- `RestSearcher`  → produzione: similarity search via REST (`search_similar`).
-- `DirectSearcher` → dev/test: connessione diretta a Postgres/pgvector.
-
-Entrambe mappano i `kind` sulle tabelle per-dominio dello schema `vectors`.
-"""
-
-from sqlalchemy import Engine
-
-from tht.adapters.vector.legacy_direct import LegacyDirectVectorStore
-from tht.adapters.vector.thoth_http import ThothHttpVectorStore
-from tht.vectorstore.rest_client import VectorRestClient
-from tht.vectorstore.store import VectorHit
+"""Collection mapping helpers for the workspace semantic store."""
 
 # kind Thoth → tabella dello schema `vectors`.
 KIND_TO_TABLE = {
@@ -30,35 +16,4 @@ def tables_for_kinds(kinds: list[str] | None) -> list[str]:
     if not kinds:
         return list(ALL_TABLES)
     return sorted({KIND_TO_TABLE[k] for k in kinds if k in KIND_TO_TABLE})
-
-
-class RestSearcher:
-    """Similarity search via REST: una chiamata `search_similar` per tabella, poi fusione."""
-
-    def __init__(self, client: VectorRestClient):
-        self.client = client
-        self._store = ThothHttpVectorStore(reader=client, writer=None)
-
-    def search(
-        self, query_vec: list[float], top_n: int = 10, kinds: list[str] | None = None
-    ) -> list[VectorHit]:
-        return self._store.search(
-            tables_for_kinds(kinds), query_vec, limit=top_n, kinds=kinds
-        )
-
-
-class DirectSearcher:
-    """Similarity search diretta su Postgres/pgvector, interrogando le tabelle per-dominio."""
-
-    def __init__(self, engine: Engine, schema: str = "vectors", dim: int = 768):
-        self.engine = engine
-        self.schema = schema
-        self.dim = dim
-        self._store = LegacyDirectVectorStore(engine, schema=schema, dim=dim)
-
-    def search(
-        self, query_vec: list[float], top_n: int = 10, kinds: list[str] | None = None
-    ) -> list[VectorHit]:
-        return self._store.search(
-            tables_for_kinds(kinds), query_vec, limit=top_n, kinds=kinds
-        )
+__all__ = ["ALL_TABLES", "KIND_TO_TABLE", "tables_for_kinds"]