fix(inference): #86 tighten Call 1 prompt and closed lists

Ship locked expert Call 1 seed: order cats before edge, species=best
confidence, mill-count edge rules, Wild for cookies/burl, multi figure,
feature_tag_ids only (no free-text bags, no grade). LISTS keys match the
seed; feat- prefix stripped for the model. Gate and review UI apply
feature_tag_ids. Seed auto-activates on deploy when still seed-authored.

backend/tests/test_inference.py

@@ -58,6 +58,101 @@ def test_prompt_seed_and_revision(env):
     assert client.get("/api/v1/prompts/call1").json()["active_content"] is not None
 
 
+def test_call1_seed_is_locked_expert_prompt(env):
+    """#86: shipped Call 1 seed is the locked expert prompt (no free-text bags, no grade)."""
+    client, _conn = env
+    from backend.inference import CALL1_SEED
+
+    body = client.get("/api/v1/prompts/call1").json()
+    assert body["active_content"] == CALL1_SEED
+    assert "wood identification expert" in CALL1_SEED
+    assert "feature_tag_ids" in CALL1_SEED
+    assert "Decide wood categories before edge type" in CALL1_SEED
+    assert "highest-confidence" in CALL1_SEED
+    assert "Wild edge" in CALL1_SEED
+    assert "cookies and burl" in CALL1_SEED.lower() or "cookies and burl" in CALL1_SEED
+    assert "grade_term_id" not in CALL1_SEED
+    assert '"character"' not in CALL1_SEED
+    assert '"inclusions"' not in CALL1_SEED
+    assert "character\":" not in CALL1_SEED.replace(" ", "")
+
+
+def test_taxonomy_lists_call1_closed_shape():
+    """#86: Call 1 lists are closed Woo picks only — no grade/thickness/moisture; feat names stripped."""
+    import tempfile, os, shutil
+    tmp = tempfile.mkdtemp(prefix="tax_")
+    os.environ["SLAB_DB_PATH"] = os.path.join(tmp, "t.db")
+    os.environ["SLAB_IMAGES_DIR"] = tmp
+    os.environ.setdefault("WOO_BASE_URL", "https://x.com")
+    os.environ.setdefault(
+        "SLAB_AES_KEY",
+        base64.b64encode(b"0123456789abcdef0123456789abcdef").decode(),
+    )
+    db_mod._reset_for_tests()
+    conn = db_mod.init_db()
+    conn.execute("INSERT INTO woo_categories(id,name,slug,parent_id,woo_id) VALUES (10,'Species','species',NULL,10)")
+    conn.execute("INSERT INTO woo_categories(id,name,slug,parent_id,woo_id) VALUES (11,'Walnut','walnut',10,11)")
+    conn.execute("INSERT INTO woo_categories(id,name,slug,parent_id,woo_id) VALUES (20,'Wcat','wcat',NULL,20)")
+    conn.execute("INSERT INTO woo_categories(id,name,slug,parent_id,woo_id) VALUES (21,'Live edge wood','liveedge',20,21)")
+    conn.execute("INSERT INTO woo_attributes(id,name,slug,woo_id) VALUES (6,'Edge type','pa_etype',6)")
+    conn.execute("INSERT INTO woo_attributes(id,name,slug,woo_id) VALUES (8,'Figure','pa_fig',8)")
+    conn.execute("INSERT INTO woo_attributes(id,name,slug,woo_id) VALUES (9,'Grade','pa_gr',9)")
+    conn.execute("INSERT INTO woo_attributes(id,name,slug,woo_id) VALUES (10,'Thickness','pa_thk',10)")
+    conn.execute("INSERT INTO woo_attributes(id,name,slug,woo_id) VALUES (7,'Moisture','pa_mst',7)")
+    conn.execute("INSERT INTO woo_attribute_terms(id,attribute_id,name,slug,woo_id) VALUES (321,6,'Square edge','sqe',321)")
+    conn.execute("INSERT INTO woo_attribute_terms(id,attribute_id,name,slug,woo_id) VALUES (328,8,'Plain','pl',328)")
+    conn.execute("INSERT INTO woo_attribute_terms(id,attribute_id,name,slug,woo_id) VALUES (342,9,'Fancy','fnc',342)")
+    conn.execute("INSERT INTO woo_attribute_terms(id,attribute_id,name,slug,woo_id) VALUES (350,10,'1\"- 1 1/2\"','4-6qtr',350)")
+    conn.execute("INSERT INTO woo_attribute_terms(id,attribute_id,name,slug,woo_id) VALUES (326,7,'Kiln dried','kd',326)")
+    conn.execute("INSERT INTO woo_tags(id,name,slug,woo_id) VALUES (1,'feat-knot','feat-knot',1)")
+    conn.execute("INSERT INTO woo_tags(id,name,slug,woo_id) VALUES (2,'fig-curl','fig-curl',2)")
+    conn.commit()
+    from backend.inference import _taxonomy_lists
+
+    tax = _taxonomy_lists(conn)
+    assert set(tax.keys()) == {"species", "wood_categories", "edge_terms", "figure_terms", "feature_tags"}
+    assert tax["species"] == [{"id": 11, "name": "Walnut"}]
+    assert tax["wood_categories"] == [{"id": 21, "name": "Live edge wood"}]
+    assert tax["edge_terms"] == [{"id": 321, "name": "Square edge"}]
+    assert tax["figure_terms"] == [{"id": 328, "name": "Plain"}]
+    # feat- prefix stripped for the model; fig- tags are not feature_tags
+    assert tax["feature_tags"] == [{"id": 1, "name": "knot"}]
+    assert "grade_terms" not in tax
+    assert "thickness_terms" not in tax
+    assert "moisture_terms" not in tax
+    db_mod._reset_for_tests()
+    shutil.rmtree(tmp, ignore_errors=True)
+
+
+def test_gate_feature_tag_ids_not_free_text():
+    """#86: gate keeps feature_tag_ids at threshold; drops free-text bags and grade."""
+    from backend.inference import _gate
+
+    parsed = {
+        "species_id": 11, "species_confidence": 0.9,
+        "wood_category_ids": [21], "wood_category_confidence": 0.8,
+        "edge_type_term_id": 321, "edge_confidence": 0.85,
+        "figure_term_ids": [328, 335], "figure_confidence": 0.75,
+        "feature_tag_ids": [1], "feature_tag_confidence": 0.8,
+        "grade_term_id": 342, "grade_confidence": 0.99,
+        "character": ["rustic"], "inclusions": ["bark"], "voids": [], "checks": ["end"],
+    }
+    out = _gate(parsed)
+    assert out["species_id"] == 11
+    assert out["wood_category_ids"] == [21]
+    assert out["edge_type_term_id"] == 321
+    assert out["figure_term_ids"] == [328, 335]
+    assert out["feature_tag_ids"] == [1]
+    assert "grade_term_id" not in out
+    assert "character" not in out
+    assert "inclusions" not in out
+    assert "voids" not in out
+    assert "checks" not in out
+    # below threshold feature tags dropped
+    low = {**parsed, "feature_tag_confidence": 0.2}
+    assert "feature_tag_ids" not in _gate(low)
+
+
 def test_call1_confidence_gate(env, monkeypatch):
     client, conn = env
     # enable inference
@@ -69,11 +164,18 @@ def test_call1_confidence_gate(env, monkeypatch):
     from backend.inference import InferenceClient
 
     def fake_chat(self, messages):
+        # Capture list header for #86 shape
+        text = messages[0]["content"][-1]["text"]
+        assert "LISTS:" in text
+        assert "grade_terms" not in text
+        assert "species_leaves" not in text
         return json.dumps({
             "species_id": 1, "species_confidence": 0.9,
             "wood_category_ids": [1], "wood_category_confidence": 0.5,  # below threshold
-            "grade_term_id": 7, "grade_confidence": 0.3,               # below
+            "grade_term_id": 7, "grade_confidence": 0.99,              # never suggested
             "figure_term_ids": [2], "figure_confidence": 0.8,          # at/above
+            "feature_tag_ids": [9], "feature_tag_confidence": 0.9,
+            "character": ["x"], "inclusions": ["y"],
         })
     monkeypatch.setattr(InferenceClient, "chat", fake_chat)
     r = client.post("/api/v1/slabs/s1/inference/call1")
@@ -81,8 +183,10 @@ def test_call1_confidence_gate(env, monkeypatch):
     s = r.json()["suggestions"]
     assert s.get("species_id") == 1
     assert s.get("figure_term_ids") == [2]
+    assert s.get("feature_tag_ids") == [9]
     assert "wood_category_ids" not in s  # gated out
-    assert "grade_term_id" not in s       # gated out
+    assert "grade_term_id" not in s       # never
+    assert "character" not in s
     # inference_log written with call=1
     assert conn.execute("SELECT call FROM inference_log").fetchone()["call"] == 1
 

backend/tests/test_slabs_api.py

@@ -206,14 +206,18 @@ def test_gate_reads_flat_confidence_keys(client, db):
     # etc., NOT f'{field}_confidence' (field 'species_id' would give the wrong key). A
     # high-confidence response must surface its picks; low-confidence ones must not.
     from backend.inference import _gate, _parse_json
-    good = '```json\n{"species_id": 284, "species_confidence": 0.85, "wood_category_ids": [251], "wood_category_confidence": 1.0, "edge_type_term_id": 323, "edge_confidence": 0.95, "figure_term_ids": [332], "figure_confidence": 0.9, "character": [], "inclusions": ["bark"], "voids": [], "checks": []}\n```'
+    good = '```json\n{"species_id": 284, "species_confidence": 0.85, "wood_category_ids": [251], "wood_category_confidence": 1.0, "edge_type_term_id": 323, "edge_confidence": 0.95, "figure_term_ids": [332], "figure_confidence": 0.9, "feature_tag_ids": [1], "feature_tag_confidence": 0.8, "character": [], "inclusions": ["bark"], "voids": [], "checks": []}\n```'
     out = _gate(_parse_json(good))
     assert out["species_id"] == 284
     assert out["wood_category_ids"] == [251]
     assert out["edge_type_term_id"] == 323
     assert out["figure_term_ids"] == [332]
+    assert out["feature_tag_ids"] == [1]
     # grade must never be gated in (METADATA-40)
     assert "grade_term_id" not in out
+    # free-text bags dropped (#86)
+    assert "character" not in out
+    assert "inclusions" not in out
     # low-confidence fields are dropped (METADATA-45)
     low = '```json\n{"species_id": 284, "species_confidence": 0.4, "wood_category_ids": [251], "wood_category_confidence": 0.8, "edge_type_term_id": 323, "edge_confidence": 0.2, "figure_term_ids": [332], "figure_confidence": 0.9}\n```'
     out2 = _gate(_parse_json(low))