Files
AI/ontology_platform/tests/unit/test_platform_config.py

121 lines
4.3 KiB
Python
Raw Normal View History

2026-05-13 19:57:34 +09:00
"""Tests for `platform.config`.
Covers:
- Phase 0 forces filesystem backend even when NEO4J_*/FUSEKI_* are set
- `build_ontocast_config` clears Neo4j/Fuseki on filesystem backend
- Phase < 4 with non-filesystem storage_backend raises eagerly
- working_directory is auto-created
"""
from __future__ import annotations
import sys
from pathlib import Path
import pytest
REPO_ROOT = Path(__file__).resolve().parents[2]
PLATFORM_ROOT = REPO_ROOT
if str(PLATFORM_ROOT) not in sys.path:
sys.path.insert(0, str(PLATFORM_ROOT))
# Importing `platform.config` here works because the `platform/` package
# directory has an `__init__.py`. (Avoid the stdlib module of the same name
# by relying on the package being on sys.path before site-packages.)
import importlib
Phase 0.7 — Acceptance Gate 자동화 + LM Studio 통합 + OntoCast 버그 수정 - platform/ → ont_platform/ rename Python 내장 platform 모듈과 이름 충돌. numpy/scipy가 platform.machine() 호출 시 우리 패키지를 가져와 AttributeError. ont_platform으로 변경하고 pyproject.toml, ont_platform/**, tests/** import 경로 모두 업데이트. - ont_platform/config.py: lenient LLM builder 추가 LM Studio/vLLM 등 OpenAI-호환 로컬 서버가 임의 모델 식별자(예: deepseek-r1-distill- qwen-7b)를 쓸 수 있도록 OntoCast의 OpenAIModel enum validation을 Pydantic model_construct로 우회. ToolConfig() 생성 시 충돌을 막기 위해 LLM_MODEL_NAME을 잠시 비웠다가 lenient 인스턴스로 교체. - ont_platform/api/deps.py: ToolBox 초기화를 asyncio.to_thread로 격리 LLMTool.create()가 내부에서 asyncio.run()을 부르는데 lifespan/테스트가 이미 async 컨텍스트라 이중 loop 충돌. 별도 스레드에서 sync 생성자 실행. - 테스트 인프라 정비 * tests/integration/test_api_smoke.py: TestClient 구버전 starlette 호환을 위해 lifespan='off' 대신 app.router.lifespan_context = noop 패턴 적용. * tests/unit/test_convert_document.py, test_select_ontology.py: ontocast.agent __init__.py가 re-export한 함수가 서브모듈을 가리는 문제로 sys.modules에서 실제 모듈 객체 직접 추출. * tests/e2e/conftest.py: .env 자동 로드 + provider별 skip 조건 (Ollama는 LLM_API_KEY 불필요). * tests/e2e/test_phase0_full_pipeline.py: provider별 키 분기, HDBSCAN 클러스터링이 동작하도록 fixture 페이로드 16문장으로 확장. - vendored OntoCast 버그 수정 3건 (VENDORED_MODIFICATIONS.md 기록): * agent/render_ontology.py: render_ontology_fresh()의 .format() 호출에 누락된 ontology_prefix 인자 추가 (Bootstrap 단계에서 KeyError: 'ontology_prefix'). * stategraph/node_factories.py: render_ontology/render_facts 노드의 state.model_copy(deep=True)로 budget_tracker가 deep-copy되어 root state의 BudgetTracker가 영원히 0인 채로 남던 버그 수정. 원본 인스턴스 공유로 변경. - 문서 갱신 README.md (Phase 0.7 부분완료 + ont_platform 폴더 이름), docs/phases/PHASE0_ACCEPTANCE_GATE.md (검증 이력 + Ollama/LM Studio 옵션), .env.example (LM Studio/Ollama/OpenAI 세 옵션 명시). 검증 - unit + integration 26/26 통과. - e2e (LM Studio + Qwen3-8B / DeepSeek-R1-Distill-Qwen-7B): 워크플로우 끝까지 실행 + 5번 LLM 호출 + LangGraph 전 노드 traceable 확인. 7-8B 로컬 모델은 strict structured output(Turtle RDF in JSON) 한계로 ontology/facts TTL 자동 생성 부분 성공. 클라우드 LLM 환경에서 재검증 필요. Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-05-14 09:05:24 +09:00
platform_config = importlib.import_module("ont_platform.config")
2026-05-13 19:57:34 +09:00
def _clear_settings_env(monkeypatch: pytest.MonkeyPatch) -> None:
"""Wipe all env vars that PlatformSettings or OntoCast Config might read."""
for var in [
"PHASE",
"STORAGE_BACKEND",
"ONTOCAST_WORKING_DIRECTORY",
"ONTOCAST_ONTOLOGY_DIRECTORY",
"HOST",
"PORT",
"LOG_LEVEL",
"ROBOTS_POLICY",
"NEO4J_URI",
"NEO4J_AUTH",
"FUSEKI_URI",
"FUSEKI_AUTH",
"LLM_PROVIDER",
"LLM_API_KEY",
"LLM_MODEL_NAME",
]:
monkeypatch.delenv(var, raising=False)
def test_default_phase_is_base_with_filesystem(
monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
_clear_settings_env(monkeypatch)
monkeypatch.setenv("ONTOCAST_WORKING_DIRECTORY", str(tmp_path / "work"))
settings = platform_config.PlatformSettings() # type: ignore[call-arg]
assert settings.phase == platform_config.Phase.BASE
assert settings.storage_backend == "filesystem"
assert (tmp_path / "work").exists(), "working_directory should be created"
def test_phase0_rejects_neo4j_backend(monkeypatch: pytest.MonkeyPatch) -> None:
_clear_settings_env(monkeypatch)
monkeypatch.setenv("PHASE", "0")
monkeypatch.setenv("STORAGE_BACKEND", "neo4j")
with pytest.raises(ValueError, match="requires Phase 4"):
platform_config.PlatformSettings() # type: ignore[call-arg]
def test_phase0_rejects_fuseki_backend(monkeypatch: pytest.MonkeyPatch) -> None:
_clear_settings_env(monkeypatch)
monkeypatch.setenv("PHASE", "0")
monkeypatch.setenv("STORAGE_BACKEND", "fuseki")
with pytest.raises(ValueError, match="requires Phase 4"):
platform_config.PlatformSettings() # type: ignore[call-arg]
def test_build_ontocast_config_clears_neo4j_and_fuseki(
monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
"""Even if NEO4J_*/FUSEKI_* env vars are set, Phase 0 must hand
OntoCast a config with both backends disabled."""
_clear_settings_env(monkeypatch)
monkeypatch.setenv("ONTOCAST_WORKING_DIRECTORY", str(tmp_path / "work"))
# Set fake credentials that would otherwise enable both backends.
monkeypatch.setenv("NEO4J_URI", "bolt://localhost:7687")
monkeypatch.setenv("NEO4J_AUTH", "neo4j/changeme")
monkeypatch.setenv("FUSEKI_URI", "http://localhost:3030")
monkeypatch.setenv("FUSEKI_AUTH", "admin:changeme")
# LLM must be valid enough for validate_llm_config to pass.
monkeypatch.setenv("LLM_PROVIDER", "openai")
monkeypatch.setenv("LLM_API_KEY", "test-key")
settings = platform_config.PlatformSettings() # type: ignore[call-arg]
cfg = platform_config.build_ontocast_config(settings)
assert cfg.tool_config.neo4j.uri is None
assert cfg.tool_config.neo4j.auth is None
assert cfg.tool_config.fuseki.uri is None
assert cfg.tool_config.fuseki.auth is None
# Paths must be the platform-overridden value.
assert cfg.tool_config.path_config.working_directory == (tmp_path / "work")
def test_build_ontocast_config_validates_llm_eagerly(
monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
_clear_settings_env(monkeypatch)
monkeypatch.setenv("ONTOCAST_WORKING_DIRECTORY", str(tmp_path / "work"))
monkeypatch.setenv("LLM_PROVIDER", "openai")
# Intentionally omit LLM_API_KEY so validate_llm_config raises.
settings = platform_config.PlatformSettings() # type: ignore[call-arg]
with pytest.raises(ValueError, match="LLM_API_KEY"):
platform_config.build_ontocast_config(settings)