AI/ontology_platform/tests/e2e/test_phase0_full_pipeline.py

"""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("ont_platform.api.main")
deps_module = importlib.import_module("ont_platform.api.deps")
platform_config = importlib.import_module("ont_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.
    # OpenAI는 API 키 필수, Ollama는 로컬 데몬만 떠 있으면 됨.
    provider = os.environ.get("LLM_PROVIDER", "openai").lower()
    if provider == "openai":
        assert os.environ.get("LLM_API_KEY"), (
            "LLM_API_KEY must be set for e2e with OpenAI provider"
        )

    # 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()

    # OntoCast SemanticChunker가 HDBSCAN + UMAP을 쓰므로 최소 문장 수가
    # 필요하다. 2문장짜리 toy 입력은 "k must be ≤ training points"로 실패한다.
    # Acceptance Gate #1은 "단일 PDF/JSON → TTL 생성"이지 문장 수와 무관하므로,
    # ontology-rich한 짧은 단락을 충분한 문장 수로 늘려준다.
    payload = {
        "text": (
            "Alice Carter works at Acme Corporation in Berlin. "
            "Acme Corporation is a manufacturing company founded in 1992. "
            "Acme manufactures bicycles and electric scooters. "
            "Bob Lee is the chief engineer at Acme Corporation. "
            "He reports to Alice Carter, who heads the engineering division. "
            "Acme's main factory is located in Berlin, Germany. "
            "The company also operates a research center in Munich. "
            "Carol Schmidt leads research at the Munich center. "
            "She previously worked at Globex Industries in Hamburg. "
            "Globex Industries is a competitor in the bicycle market. "
            "Acme exports bicycles to France, Italy, and Spain. "
            "The product line includes road bikes, mountain bikes, and city bikes. "
            "Alice Carter graduated from the Technical University of Berlin. "
            "Bob Lee holds a doctorate in mechanical engineering. "
            "Acme employs around 450 people across its three sites. "
            "The company reported annual revenue of 120 million euros last year."
        ),
        "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}"
    )