ontology

ontology_platform/tests/e2e/conftest.py

@@ -0,0 +1,45 @@
+"""E2E test configuration.
+
+These tests are SKIPPED by default. To run them set ``LLM_API_KEY`` and
+``LLM_PROVIDER`` (and any model overrides) in the environment, then run:
+
+    pytest tests/e2e -m e2e
+
+They exercise the full OntoCast workflow end-to-end — LLM calls included —
+and so they cost real money. Keep them out of CI default runs.
+"""
+
+from __future__ import annotations
+
+import os
+import sys
+from pathlib import Path
+
+import pytest
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+for p in (REPO_ROOT, REPO_ROOT / "vendored" / "ontocast"):
+    if str(p) not in sys.path:
+        sys.path.insert(0, str(p))
+
+
+def pytest_collection_modifyitems(
+    config: pytest.Config, items: list[pytest.Item]
+) -> None:
+    """Skip all e2e tests when LLM_API_KEY is not configured."""
+    if os.environ.get("LLM_API_KEY"):
+        return
+    skip_marker = pytest.mark.skip(
+        reason="E2E tests require LLM_API_KEY in environment."
+    )
+    for item in items:
+        # Only apply to tests in this directory tree.
+        if "tests/e2e" in str(item.fspath).replace("\\", "/"):
+            item.add_marker(skip_marker)
+
+
+def pytest_configure(config: pytest.Config) -> None:
+    config.addinivalue_line(
+        "markers",
+        "e2e: end-to-end test that requires a real LLM and may cost money",
+    )

ontology_platform/tests/e2e/test_phase0_full_pipeline.py

@@ -0,0 +1,93 @@
+"""Phase 0 end-to-end pipeline test.
+
+Runs the actual OntoCast workflow through the FastAPI ``/process`` endpoint
+with a tiny JSON input. Verifies Acceptance Gate 0 evidence:
+
+- /health, /info, /process respond OK
+- ontology + facts Turtle are produced
+- BudgetTracker reports non-zero LLM call/triple counts
+- Filesystem TripleStoreManager writes artifacts under working_directory
+
+Skipped unless ``LLM_API_KEY`` is set (see ``conftest.py``).
+"""
+
+from __future__ import annotations
+
+import importlib
+import json
+import os
+import sys
+from pathlib import Path
+
+import pytest
+from fastapi.testclient import TestClient
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+if str(REPO_ROOT) not in sys.path:
+    sys.path.insert(0, str(REPO_ROOT))
+
+main_module = importlib.import_module("platform.api.main")
+deps_module = importlib.import_module("platform.api.deps")
+platform_config = importlib.import_module("platform.config")
+
+
+@pytest.mark.e2e
+@pytest.mark.asyncio
+async def test_full_pipeline_writes_ontology_and_facts(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    # Point the working directory at the test's tmp_path so artifacts don't
+    # leak between runs.
+    monkeypatch.setenv("ONTOCAST_WORKING_DIRECTORY", str(tmp_path / "work"))
+    # Honor whatever LLM provider the operator configured.
+    assert os.environ.get("LLM_API_KEY"), "LLM_API_KEY must be set for e2e"
+
+    # Force a fresh AppContext so the new working_directory wins.
+    deps_module.reset_app_context_for_testing()
+    settings = platform_config.load_settings()
+    await deps_module.initialize_app_context(settings, head_chunks=1)
+
+    app = main_module.create_app()
+
+    # Tiny but ontology-rich payload.
+    payload = {
+        "text": (
+            "Alice works at Acme Corporation in Berlin. "
+            "Acme Corporation manufactures bicycles."
+        ),
+        "ontology_user_instruction": "Focus on person-organization-location relations.",
+        "facts_user_instruction": "Extract employment and manufacturing facts.",
+    }
+
+    with TestClient(app) as client:
+        # /health & /info first as smoke
+        assert client.get("/health").status_code == 200
+        assert client.get("/info").status_code == 200
+
+        response = client.post(
+            "/process",
+            content=json.dumps(payload),
+            headers={"Content-Type": "application/json"},
+        )
+
+    assert response.status_code == 200, response.text
+    body = response.json()
+    assert body["status"] == "success"
+    assert body["data"]["ontology"], "ontology TTL must not be empty"
+    assert body["data"]["facts"], "facts TTL must not be empty"
+
+    budget = body["metadata"]["budget"]
+    assert budget["calls_count"] > 0, "BudgetTracker must record at least one LLM call"
+    assert (
+        budget["ontology_triples_generated"] > 0
+        or budget["facts_triples_generated"] > 0
+    ), "BudgetTracker must record triple generation"
+
+    # The filesystem manager should have created artifacts somewhere under
+    # working_directory. We don't assert exact filenames (those depend on
+    # the document hash) — just that the directory is non-empty.
+    work_dir = tmp_path / "work"
+    written = list(work_dir.rglob("*"))
+    assert any(p.suffix in {".ttl", ".rdf"} for p in written if p.is_file()), (
+        f"No RDF artifacts produced under {work_dir}"
+    )