feat(harness): Onda 0b — setup workspace per-cliente + build LSH (D14a validato)

Repo workspace per-cliente tht-workspace-psd/ (git separato): 35 evidence Thoth
frontmatturate (da etl/docs/evidence/, non tutto etl/docs), psd.yaml con path
assoluti ancorati al repo, THT_DOCS_ROOT -> radice repo cliente. README documeta
il deployment shape (2 checkout + .env).

LSH build sul DWH reale (REST, VPN): 75737 valori / 491 colonne eligible -> indice
175M nel repo cliente. tht lsh query 'ablazione' -> 8 colonne (D14a non-collapsing
validato end-to-end: procedure_type, descrizione_procedura, intervento, ...).

Correzioni al piano eseguite durante l'implementazione:
- aggiunto 'tht schema introspect' (prerequisito di lsh build, omesso nel piano)
- uso -c (il cmd ha --config, non --workspace residuo)
- path assoluti nel psd.yaml (paths sono relativi alla CWD, non al file YAML)
- evidence corretta: solo etl/docs/evidence/ (35), non tutto etl/docs (895)

Test L2 riallineato: WORKSPACE -> psd.yaml nel repo cliente (non tht-test.yaml),
index_dir -> paths.indexes/'lsh', nome -> db_schema (non letterale 'datawarehouse').
Bug latente del test (path mismatch) mai emerso prima: ora PASS invece di SKIP.

Verifica: pytest 165 passed, 5 deselected; pytest -m l2 test_value_grounding_real PASS.

harness/README.md

@@ -33,6 +33,33 @@ Keys are never logged; URLs are fine. Rotate any key that appeared in chat.
 A workspace wires the relational DWH + the pgvector (dual-key) + embeddings + evidence.
 See `workspaces/tht.example.yaml`. `${THT_*}}` tokens expand from `.env`.
 
+### Per-customer workspace repo (deployment shape)
+
+ThothII is generic; **evidence content and LSH indexes are per-customer** and live in a
+**separate repo**, not copied into `harness/`. The deployment is two checkouts + one `.env`:
+
+```
+ThothII/                      generic harness (this repo)
+└── harness/                  tht CLI + .env (THT_* secrets, points at the customer repo)
+
+tht-workspace-<customer>/     per-customer workspace repo (separate git repo)
+├── <customer>.yaml           workspace YAML (paths ABSOLUTE, anchored here)
+├── evidence/                 curated evidence markdown (frontmatter-structured, by domain)
+├── artifacts/                derived artifacts (gitignored; regenerated by tht)
+├── indexes/                  LSH index (gitignored; regenerated by `tht lsh build`)
+└── sessions/                 per-session artifacts (gitignored)
+```
+
+`THT_DOCS_ROOT` in `.env` points at the **root** of the customer repo
+(`evidence.source_root` + `evidence.evidence_dir` resolve the curated folder).
+All `tht` commands take the customer workspace via `-c`:
+
+```bash
+tht schema introspect -c /path/to/tht-workspace-<customer>/<customer>.yaml
+tht lsh build        -c /path/to/tht-workspace-<customer>/<customer>.yaml
+tht session new      -c /path/to/tht-workspace-<customer>/<customer>.yaml
+```
+
 ## The workflow
 
 `workflow.yaml` is the **single source of workflow truth** (spec F2). Eight phases

harness/tests/l2/test_value_grounding_real.py

@@ -13,13 +13,17 @@ import pytest
 from tht.workspace import load_workspace
 
 pytestmark = [pytest.mark.l2]
-WORKSPACE = Path(__file__).resolve().parents[2] / "workspaces" / "tht-test.yaml"
+# Per-customer workspace repo (spec D7): the LSH index lives in the customer repo,
+# not in harness/. PSD is the reference customer for L2. Skip cleanly if absent.
+WORKSPACE = Path("/Users/mp/projects/tht-workspace-psd/psd.yaml")
 
 
 def test_ablazione_returns_multiple_columns(l2_env):
     """On the real schema, 'ablazione' should ground to more than one column (e.g.
     a flag and a free-text patologia field) -- the whole point of D14a's
     non-collapsing aggregation. Requires a built LSH index (tht lsh build)."""
+    if not WORKSPACE.exists():
+        pytest.skip(f"per-customer workspace repo not found: {WORKSPACE} (clone tht-workspace-psd)")
     from tht.config import LshConfig
     try:
         from tht.lshindex import load_index, query_index  # ported with the lsh build path
@@ -27,14 +31,15 @@ def test_ablazione_returns_multiple_columns(l2_env):
         pytest.skip("tht.lshindex not yet ported (deferred from B3; lands with tht lsh build)")
     from tht.search import aggregate_lsh_multi
 
-    # NOTE: this test assumes the LSH index was built (tht lsh build --workspace
-    # tht-test). If absent, build it first. The index path comes from the config.
+    # The index lives at <indexes>/lsh/<schema>_*.pkl (same convention as tht lsh build/query),
+    # and is keyed by the database schema name (cfg.database.db_schema), not a hard-coded literal.
     ws = load_workspace(WORKSPACE)
-    index_dir = ws.paths.indexes
+    index_dir = ws.paths.indexes / "lsh"
+    schema_name = ws.database.db_schema
     try:
-        lsh, minhashes, meta = load_index(index_dir, "datawarehouse")
+        lsh, minhashes, meta = load_index(index_dir, schema_name)
     except Exception as e:
-        pytest.skip(f"LSH index not built yet (run tht lsh build): {e}")
+        pytest.skip(f"LSH index not built yet (run tht lsh build -c {WORKSPACE}): {e}")
 
     hits = query_index(lsh, minhashes, "ablazione", meta, top_n=20)
     grouped = aggregate_lsh_multi(