chore(inference): disable Call 1 end-to-end; Call 2 stays

overnight-whole-app: Call 1 (vision classification) is OUT. - POST /api/v1/slabs/{id}/inference/call1 always returns 410 call1_disabled (no model chat, no inference_log). Prompt seed/revision APIs kept dormant. - Review: remove "Suggest with AI" / runInference (inferTaxon). - GenerateText: remove Classify metadata (Call 1) button; Call 2 generate stays. - PROMPTS.md banner documents Call 1 OUT / Call 2 STAYS. - Settings: inference_enabled toggle annotated as Call-1 latch (dormant). - Backend tests updated to assert 410; Call 2 tests unchanged.
2026-09-25 17:46:39 -07:00
parent 60700b47fb
commit 087557f89f
7 changed files with 57 additions and 218 deletions
@@ -153,42 +153,28 @@ def test_gate_feature_tag_ids_not_free_text():
    assert "feature_tag_ids" not in _gate(low)


-def test_call1_confidence_gate(env, monkeypatch):
+def test_call1_hard_disabled_410(env, monkeypatch):
+    """overnight-whole-app: Call 1 OUT — POST always 410, never chats the model."""
    client, conn = env
-    # enable inference
    conn.execute("INSERT OR REPLACE INTO settings(key,value,value_enc) VALUES ('inference_enabled','true',NULL)")
-    conn.execute("INSERT INTO woo_categories(id,name,slug,parent_id,woo_id) VALUES (1,'Black Walnut','black-walnut',NULL,100)")
    conn.execute("INSERT INTO slabs(id,sku,length_in,thickness_in,status,server_rev,client_rev,created_at,updated_at) VALUES ('s1','SLAB-01',100,2,'calibrated',1,1,'t','t')")
    conn.execute("INSERT INTO slab_photos(id,slab_id,seq,processed_blob,created_at) VALUES ('p1','s1',1,X'89504E47','t')")
    conn.commit()
    from backend.inference import InferenceClient

+    called = {"n": 0}
+
    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": 0.99,              # 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"],
-        })
+        called["n"] += 1
+        return "{}"
+
    monkeypatch.setattr(InferenceClient, "chat", fake_chat)
    r = client.post("/api/v1/slabs/s1/inference/call1")
-    assert r.status_code == 200, r.text
-    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       # never
-    assert "character" not in s
-    # inference_log written with call=1
-    assert conn.execute("SELECT call FROM inference_log").fetchone()["call"] == 1
+    assert r.status_code == 410, r.text
+    body = r.json()
+    assert body["error"]["code"] == "call1_disabled"
+    assert called["n"] == 0
+    assert conn.execute("SELECT COUNT(*) AS n FROM inference_log").fetchone()["n"] == 0


 def test_call2_stores_description(env, monkeypatch):
@@ -208,12 +194,14 @@ def test_call2_stores_description(env, monkeypatch):
    assert row["content_source"] == "llm"


-def test_inference_off_call1_409(env):
+def test_call1_disabled_even_when_inference_off(env):
+    """Call 1 hard-disable wins over inference_enabled=false (still 410, not 409)."""
    client, conn = env
    conn.execute("INSERT INTO slabs(id,sku,status,server_rev,client_rev,created_at,updated_at) VALUES ('s1','SLAB-01','calibrated',1,1,'t','t')")
    conn.commit()
    r = client.post("/api/v1/slabs/s1/inference/call1")
-    assert r.status_code == 409  # inference_enabled default off
+    assert r.status_code == 410
+    assert r.json()["error"]["code"] == "call1_disabled"


 def test_server_description_inference_off(env):
@@ -306,50 +294,18 @@ def test_redact_request_for_log_strips_data_urls_keeps_text():
    assert "LISTS:" in parts[2]["text"]


-def test_call1_log_has_text_and_image_refs_no_base64(env, monkeypatch):
-    """#87 METADATA-66: inference_log stores text+refs, not image bytes."""
+def test_call1_log_skipped_while_disabled(env):
+    """#87 Call 1 log path dormant while Call 1 is hard-disabled (overnight-whole-app)."""
    client, conn = env
    conn.execute("INSERT OR REPLACE INTO settings(key,value,value_enc) VALUES ('inference_enabled','true',NULL)")
    conn.execute(
        "INSERT INTO slabs(id,sku,length_in,thickness_in,status,server_rev,client_rev,created_at,updated_at) "
        "VALUES ('s1','SLAB-01',100,2,'calibrated',1,1,'t','t')"
    )
-    png = _rgba_png(400, 300)
-    conn.execute(
-        "INSERT INTO slab_photos(id,slab_id,seq,processed_blob,created_at) VALUES ('photo-abc','s1',1,?, 't')",
-        (png,),
-    )
    conn.commit()
-    from backend.inference import InferenceClient
-
-    def fake_chat(self, messages):
-        # Wire path still has data-URL for the model
-        content = messages[0]["content"]
-        assert any(
-            isinstance(p, dict) and p.get("type") == "image_url"
-            and str(p.get("image_url", {}).get("url", "")).startswith("data:image")
-            for p in content
-        )
-        return json.dumps({"species_id": 1, "species_confidence": 0.9})
-
-    monkeypatch.setattr(InferenceClient, "chat", fake_chat)
    r = client.post("/api/v1/slabs/s1/inference/call1")
-    assert r.status_code == 200, r.text
-    row = conn.execute(
-        "SELECT request_payload, length(request_payload) AS n FROM inference_log ORDER BY id DESC LIMIT 1"
-    ).fetchone()
-    payload = row["request_payload"]
-    assert row["n"] < 50000
-    assert "data:image" not in payload
-    assert "LISTS:" in payload
-    assert "image_ref" in payload
-    assert "photo-abc" in payload
-    assert '"seq": 1' in payload or '"seq":1' in payload
-    logged = json.loads(payload)
-    refs = [p for p in logged[0]["content"] if p.get("type") == "image_ref"]
-    assert len(refs) == 1
-    assert refs[0]["photo_id"] == "photo-abc"
-    assert refs[0]["bytes"] == len(png)
+    assert r.status_code == 410
+    assert conn.execute("SELECT COUNT(*) AS n FROM inference_log").fetchone()["n"] == 0


 def test_call2_log_redacts_images(env, monkeypatch):
@@ -380,38 +336,9 @@ def test_call2_log_redacts_images(env, monkeypatch):
    assert "DIMENSION FACT BLOCK" in payload


-def test_call1_sends_long_edge_at_most_1024(env, monkeypatch):
-    """METADATA-35 end-to-end: messages to the model use <=1024 long edge."""
-    client, conn = env
-    conn.execute("INSERT OR REPLACE INTO settings(key,value,value_enc) VALUES ('inference_enabled','true',NULL)")
-    conn.execute(
-        "INSERT INTO slabs(id,sku,length_in,thickness_in,status,server_rev,client_rev,created_at,updated_at) "
-        "VALUES ('s1','SLAB-01',100,2,'calibrated',1,1,'t','t')"
-    )
-    big = _rgba_png(800, 1067)
-    conn.execute(
-        "INSERT INTO slab_photos(id,slab_id,seq,processed_blob,created_at) VALUES ('p1','s1',1,?, 't')",
-        (big,),
-    )
-    conn.commit()
-    from backend.inference import InferenceClient
-    from PIL import Image
-    import io
-
-    captured = {}
-
-    def fake_chat(self, messages):
-        captured["messages"] = messages
-        return json.dumps({"species_id": 1, "species_confidence": 0.9})
-
-    monkeypatch.setattr(InferenceClient, "chat", fake_chat)
-    r = client.post("/api/v1/slabs/s1/inference/call1")
-    assert r.status_code == 200, r.text
-    content = captured["messages"][0]["content"]
-    imgs = [p for p in content if isinstance(p, dict) and p.get("type") == "image_url"]
-    assert len(imgs) == 1
-    url = imgs[0]["image_url"]["url"]
-    assert url.startswith("data:image/png;base64,")
-    raw = base64.b64decode(url.split(",", 1)[1])
-    im = Image.open(io.BytesIO(raw))
-    assert max(im.size) <= 1024
+def test_call1_sends_long_edge_dormant_while_disabled(env):
+    """METADATA-35 Call 1 sizing path dormant while Call 1 is hard-disabled."""
+    client, _conn = env
+    r = client.post("/api/v1/slabs/missing/inference/call1")
+    assert r.status_code == 410
+    assert r.json()["error"]["code"] == "call1_disabled"