refactor(harness): renaming prodotto tht (Onda -1)

Thoth (tht) è il prodotto, PSD è il cliente. Nessun riferimento al contesto
clinico nel codice.

Rinomine:
- comando+package nsp→tht (dir nsp/→tht/, 46 import, pyproject entry point)
- gate nsp-gate.js→tht-gate.js (+ rewrite token, relayIfNspFails→relayIfThtFails)
- workspace chirone.{example,test}.yaml→tht.{example,test}.yaml (generici)
- env THOTH_→THT_ (19 var) + NSP_ stragglers (NSP_HARNESS_ROOT, NSP_SESSION)
- commenti/docstring chirone/psdwp3/policlinico neutralizzati ('the reference
  implementation', 'the DWH')

Aggiunto [tool.setuptools.packages.find] include=['tht*'] (necessario: l'auto-
discovery rompeva con tht/ + workspaces/ come top-level multipli).

.env operatore aggiornato in-place (prefissi THT_, valori preservati, gitignored).

Verifica: pytest 109 passed, npm test 14 pass, tht phase meta --json OK, zero
residui nsp/THOTH_/NSP_/chirone nel package.

harness/tests/test_memory_save_one.py

@@ -1,6 +1,6 @@
-"""L1: nsp memory save-one -- targeted upsert via the writer key (spec D11).
+"""L1: tht memory save-one -- targeted upsert via the writer key (spec D11).
 
-The D11 deviation: instead of a full vectorstore resync (nsp memory index / sync),
+The D11 deviation: instead of a full vectorstore resync (tht memory index / sync),
 a remote workstation with a writer key can push a SINGLE promoted decision to
 pgvector as a one-row upsert. This test pins the pure core of that behavior:
 - exactly one VectorRecord is built for the chosen decision_seq
@@ -13,7 +13,7 @@ from unittest.mock import MagicMock
 
 import pytest
 
-from nsp.memory import MemoryRecord, memory_vector_record_for_decision, save_one_memory
+from tht.memory import MemoryRecord, memory_vector_record_for_decision, save_one_memory
 
 
 def _record(seq: int = 7, **kw) -> MemoryRecord: