fix(harness): workspace + write-URL + L2 tests per accesso REST reale

Bug trovato provando la connessione reale col .env: il write endpoint vive su un
PATH DEDICATO /vector/write/v1/ (non /vector/v1/), e il modello Config ha write_rest/
vector_write_rest a TOP-LEVEL (non nidificati in vector_db).

- .env.example: aggiunge THOTH_VEC_WRITE_REST_URL (path dedicato del writer, con
  avviso che le due chiavi valgono su path separati).
- workspaces/chirone-test.yaml: riscritto allineato a chirone.example.yaml + config.py
  (vector_rest/vector_write_rest top-level; write_rest punta a THOTH_VEC_WRITE_REST_URL).
- tests/l2/*: corretti gli accessi strutturali (ws.vector_write_rest invece di
  ws.vector_db.write_rest; ws.vector_rest invece di ws.vector_db.rest).
  test_value_grounding_real skip-when-import-fails su nsp.lshindex (modulo deferred da B3).

Verificato end-to-end: save_one_memory (embeddings -> writer REST /vector/write/v1/
-> upsert pgvector -> read-back reader) PASSED. Suite L0+L1: 109 passed. Suite L2:
4 passed, 1 skipped (lshindex deferred).

Nota operativa: THOTH_SSL_CA va lasciato VUOTO sulla workstation (cert GoDaddy
pubblico in certifi). I campi direct-transport (THOTH_DB_*, THOTH_VEC_PASSWORD)
sono obbligatori per il modello ma inutilizzati in transport=rest: riempiti con
dummy nel .env locale (come faceva ChironeWp3).

harness/.env.example

@@ -20,6 +20,9 @@ THOTH_VEC_REST_URL=https://host/vector/v1/
 THOTH_VEC_API_KEY=
 
 # Vector REST — SCRITTURA controllata (upsert only) da client remoti autorizzati
+# Path DEDICATO: /vector/write/v1/ (NON /vector/v1/). Le due chiavi valgono su path
+# separati: la writer key su /vector/v1/ -> 401, e viceversa. Solo postazioni che indicizzano.
+THOTH_VEC_WRITE_REST_URL=https://host/vector/write/v1/
 THOTH_VEC_WRITE_API_KEY=
 
 # Vector direct loading (server-only)

harness/tests/l2/test_memory_save_one_real.py

@@ -27,10 +27,10 @@ def test_save_one_upserts_to_real_pgvector(l2_env):
     from nsp.vectorstore.rest_client import VectorRestClient
 
     ws = load_workspace(WORKSPACE)
-    if not ws.vector_db.write_rest or not ws.vector_db.write_rest.api_key.strip():
+    if not ws.vector_write_rest or not ws.vector_write_rest.api_key.strip():
-        pytest.skip("vector_db.write_rest not configured (no writer key)")
+        pytest.skip("vector_write_rest not configured (no writer key)")
 
-    writer = VectorRestClient(ws.vector_db.write_rest)
+    writer = VectorRestClient(ws.vector_write_rest)
     embedder = OllamaEmbeddings(ws.embeddings)
 
     record = MemoryRecord(
@@ -42,8 +42,8 @@ def test_save_one_upserts_to_real_pgvector(l2_env):
     upserted = save_one_memory([record], decision_seq=999, writer=writer, embedder=embedder)
     assert upserted >= 0  # idempotent: 0 on unchanged, >=1 on new/updated
 
-    # read it back via the READER key
+    # read it back via the READER key (vector_rest, path /vector/v1/)
-    reader = VectorRestClient(ws.vector_db.rest)
+    reader = VectorRestClient(ws.vector_rest)
     qvec = embedder.embed_query("ablazione")
     hits = reader.search_similar("memory", qvec, 10)
     ids = {h.get("metadata", {}).get("record_key", "") for h in hits}

harness/tests/l2/test_session_ablazione.py

@@ -40,8 +40,9 @@ def test_workspace_chirone_test_loads(l2_env):
 
     ws = load_workspace(WORKSPACE)
     # secrets must be expanded (not the literal ${...} token)
-    assert not ws.vector_db.rest.api_key.startswith("${")
+    assert not ws.rest.api_key.startswith("${")
-    assert not ws.vector_db.write_rest.api_key.startswith("${")
+    assert not ws.vector_rest.api_key.startswith("${")
+    assert not ws.vector_write_rest.api_key.startswith("${")
 
 
 def test_pi_binary_available(l2_env):

harness/tests/l2/test_value_grounding_real.py

@@ -21,7 +21,10 @@ def test_ablazione_returns_multiple_columns(l2_env):
     a flag and a free-text patologia field) -- the whole point of D14a's
     non-collapsing aggregation. Requires a built LSH index (nsp lsh build)."""
     from nsp.config import LshConfig
-    from nsp.lshindex import load_index, query_index  # ported with the lsh build path
+    try:
+        from nsp.lshindex import load_index, query_index  # ported with the lsh build path
+    except ModuleNotFoundError:
+        pytest.skip("nsp.lshindex not yet ported (deferred from B3; lands with nsp lsh build)")
     from nsp.search import aggregate_lsh_multi
 
     # NOTE: this test assumes the LSH index was built (nsp lsh build --workspace

harness/workspaces/chirone-test.yaml

@@ -1,31 +1,20 @@
-# Workspace ThothII -- Chirone (DWH remoto) per i test L2.
+# Workspace ThothII — Chirone (DWH remoto) per i test L2.
-# I segreti vivono SOLO in .env (${THOTH_*}). Endpoint + ruolo dai parametri di
+# Struttura allineata a workspaces/chirone.example.yaml e nsp/config.py.
-# connessione L2 (spec Testing Strategy): DWH read-only via PostgREST, pgvector
+# I segreti vivono SOLO in .env (${THOTH_*}).
-# con doppia key (reader/writer) sullo stesso endpoint, TLS self-signed (CA = leaf).
-
-name: chirone-test
-description: "Chirone DWH -- L2 test workspace"
 
 database:
-  database: postgres
+  host: ${THOTH_DB_HOST}
+  port: ${THOTH_DB_PORT}
+  database: ${THOTH_DB_NAME}
   schema: datawarehouse
+  user: ${THOTH_DB_USER}
+  password: ${THOTH_DB_PASSWORD}
   transport: rest
-  rest:
-    base_url: ${THOTH_DWH_REST_URL}
-    api_key: ${THOTH_DWH_API_KEY}
-    ssl_ca: ${THOTH_SSL_CA}
 
-vector_db:
+rest:
-  collection: chirone_docs
+  base_url: ${THOTH_DWH_REST_URL}
-  dim: 768
+  api_key: ${THOTH_DWH_API_KEY}
-  rest:
+  ssl_ca: ${THOTH_SSL_CA}
-    base_url: ${THOTH_VEC_REST_URL}
-    api_key: ${THOTH_VEC_API_KEY}
-    ssl_ca: ${THOTH_SSL_CA}
-  write_rest:
-    base_url: ${THOTH_VEC_REST_URL}
-    api_key: ${THOTH_VEC_WRITE_API_KEY}
-    ssl_ca: ${THOTH_SSL_CA}
 
 paths:
   artifacts: artifacts
@@ -33,12 +22,43 @@ paths:
   sessions: sessions
 
 embeddings:
-  provider: ollama
   base_url: ${THOTH_OLLAMA_URL}
   model: nomic-embed-text-v2-moe
   dim: 768
   batch_size: 64
 
+# LOADING diretto del pgvector (server-only). Su workstation la lettura passa da
+# vector_rest; i campi direct-transport non sono usati ma il modello DatabaseConfig
+# li richiede, per cui si appoggiano alle stesse variabili del server (popolate nel
+# .env del server; sul workstation restano dummy/inediti finche' transport=rest).
+vector_db:
+  host: ${THOTH_VEC_HOST}
+  port: ${THOTH_VEC_PORT}
+  database: postgres
+  schema: vectors
+  user: ${THOTH_VEC_USER}
+  password: ${THOTH_VEC_PASSWORD}
+
+# LETTURA del pgvector via REST remota (rpc search_similar), ruolo vector_reader.
+vector_rest:
+  base_url: ${THOTH_VEC_REST_URL}
+  api_key: ${THOTH_VEC_API_KEY}
+  ssl_ca: ${THOTH_SSL_CA}
+
+# SCRITTURA controllata del pgvector via REST remota (upsert/hash via RPC allowlist),
+# ruolo vector_writer. Path DEDICATO /vector/write/v1/ (diverso dal reader): la chiave
+# writer vale solo qui, la reader solo su /vector/v1/. Key SEPARATA dalla lettura.
+vector_write_rest:
+  base_url: ${THOTH_VEC_WRITE_REST_URL}
+  api_key: ${THOTH_VEC_WRITE_API_KEY}
+  ssl_ca: ${THOTH_SSL_CA}
+
+vector:
+  max_chunk_chars: 4000
+
+search:
+  rrf_k: 60
+
 execution:
   allow: [cte_test, explain, preview, aggregate, export]
   max_preview_rows: 10