feat(inference): S7 Call 1/Call 2 + prompt revision REST + test-inference + Generate text UI

- backend/inference.py: prompt seed (rev 0) + append-only revision REST (POST /prompts/{call}/revisions, /activate, GET; METADATA-105/106). Call 1 vision classification (1024px processed photos + synced taxonomy, 0.7 confidence gate, METADATA-35/40/45), Call 2 long description (user-triggered, METADATA-55/60/65), inference_log per call (METADATA-66), inference-off server_description (METADATA-70), test-inference probe (SETTINGS-45). Stdlib urllib, no new deps. - frontend: create/inference/GenerateText.svelte (control visible only when content enabled + endpoint reachable, METADATA-110; Call 2 + Call 1 buttons) + dev toggle. - tests: 6 inference tests (seed+revision, call1 gate, call2 stores desc, off->409, server desc, test-inference unconfigured). Verified: pytest 54 passed; gates exit 0; npm build ok.
2026-09-19 17:04:01 -07:00
parent 5e03f45660
commit 8a8a89ed3e
5 changed files with 604 additions and 0 deletions
@@ -0,0 +1,128 @@
+"""S7 inference tests (METADATA-105/106, 45, 55, 70, SETTINGS-45)."""
+
+import base64
+import json
+import os
+import shutil
+import tempfile
+
+import pytest
+from fastapi.testclient import TestClient
+
+import backend.db as db_mod
+
+
+@pytest.fixture
+def env(monkeypatch):
+    tmp = tempfile.mkdtemp(prefix="inf_")
+    os.environ["SLAB_DB_PATH"] = os.path.join(tmp, "i.db")
+    os.environ["SLAB_IMAGES_DIR"] = tmp
+    os.environ["WOO_BASE_URL"] = "https://x.com"
+    os.environ["SLAB_AES_KEY"] = base64.b64encode(b"0123456789abcdef0123456789abcdef").decode()
+    db_mod._reset_for_tests()
+    from backend.crypto import encrypt
+
+    conn = db_mod.init_db()
+    conn.execute("INSERT OR REPLACE INTO settings(key,value,value_enc) VALUES ('inference_base_url',NULL,?)", (encrypt("https://infer.example.com"),))
+    conn.execute("INSERT OR REPLACE INTO settings(key,value,value_enc) VALUES ('inference_api_key',NULL,?)", (encrypt("sk-test"),))
+    conn.execute("INSERT OR REPLACE INTO settings(key,value,value_enc) VALUES ('inference_model','gpt-test',NULL)")
+    conn.commit()
+    from backend.app import app
+
+    yield TestClient(app), conn
+    db_mod._reset_for_tests()
+    shutil.rmtree(tmp, ignore_errors=True)
+
+
+def test_prompt_seed_and_revision(env):
+    client, conn = env
+    r = client.get("/api/v1/prompts/call1")
+    assert r.status_code == 200
+    body = r.json()
+    assert body["active_content"] is not None
+    assert len(body["revisions"]) == 1  # seed only
+
+    r = client.post("/api/v1/prompts/call1/revisions", json={"content": "revised prompt v2"})
+    assert r.status_code == 201
+    new_rev = r.json()["id"]
+    # new revision becomes active
+    r = client.get("/api/v1/prompts/call1")
+    assert r.json()["active_revision_id"] == new_rev
+    assert r.json()["active_content"] == "revised prompt v2"
+    assert len(r.json()["revisions"]) == 2
+
+    # activate back to seed
+    seed_rev = 1
+    r = client.post("/api/v1/prompts/call1/activate", json={"revision_id": seed_rev})
+    assert r.status_code == 200
+    assert client.get("/api/v1/prompts/call1").json()["active_content"] is not None
+
+
+def test_call1_confidence_gate(env, monkeypatch):
+    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
+
+    def fake_chat(self, messages):
+        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
+            "figure_term_ids": [2], "figure_confidence": 0.8,          # at/above
+        })
+    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 "wood_category_ids" not in s  # gated out
+    assert "grade_term_id" not in s       # gated out
+    # inference_log written with call=1
+    assert conn.execute("SELECT call FROM inference_log").fetchone()["call"] == 1
+
+
+def test_call2_stores_description(env, monkeypatch):
+    client, conn = env
+    conn.execute("INSERT OR REPLACE INTO settings(key,value,value_enc) VALUES ('content_llm_enabled','true',NULL)")
+    conn.execute("INSERT INTO slabs(id,sku,length_in,thickness_in,width_avg_in,bdft,title,status,server_rev,client_rev,created_at,updated_at) VALUES ('s1','SLAB-01',100,2,20,18,'Walnut Slab','ready',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
+
+    monkeypatch.setattr(InferenceClient, "chat", lambda self, messages: "<p>A fine walnut slab.</p>")
+    r = client.post("/api/v1/slabs/s1/inference/call2")
+    assert r.status_code == 200, r.text
+    assert r.json()["description"] == "<p>A fine walnut slab.</p>"
+    row = conn.execute("SELECT description, content_source FROM slabs WHERE id='s1'").fetchone()
+    assert row["description"] == "<p>A fine walnut slab.</p>"
+    assert row["content_source"] == "llm"
+
+
+def test_inference_off_call1_409(env):
+    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
+
+
+def test_server_description_inference_off(env):
+    from backend.inference import server_description
+
+    d = server_description({"title": "Figured Walnut Slab", "length_in": 114.0, "width_avg_in": 24.0, "thickness_in": 1.75, "bdft": 18.4})
+    assert "114.0in" in d and "18.4" in d
+
+
+def test_test_inference_unconfigured(env):
+    client, conn = env
+    conn.execute("UPDATE settings SET value_enc=NULL WHERE key='inference_api_key'")
+    conn.commit()
+    r = client.post("/api/v1/admin/test-inference")
+    assert r.status_code == 200
+    assert r.json()["ok"] is False and r.json()["mode"] == "fail"