afa2ea0354
- test_safetensors_tool_loop: FakeExecuteTool stub now accepts the tool_context kwarg the loop passes (production is correct). - test_desktop_auth: add rag_router to the health-check router stub so main.py's router import resolves. - test_rag_reingest / test_rag_multimodal: load routes/rag.py by file path instead of `from routes.rag import`, which runs routes/__init__ and eagerly imports the datasets router. On the GPU-less repo-cpu runner the unsloth bootstrap can leave `datasets` half-initialized, making that eager `from datasets import IterableDataset` raise.
81 lines
2.7 KiB
Python
81 lines
2.7 KiB
Python
"""Reingest endpoint tests (Backfill UX).
|
|
|
|
Full end-to-end reingest needs a running studio + a real embedder; that's
|
|
covered manually via the curl smoke flow in the plan. Here we cover the
|
|
parts that are testable without external models: payload validation and
|
|
the (multimodal, late) constraint propagation.
|
|
"""
|
|
|
|
import importlib.util
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
REPO_ROOT = Path(__file__).resolve().parents[2]
|
|
STUDIO_BACKEND = REPO_ROOT / "studio" / "backend"
|
|
if str(STUDIO_BACKEND) not in sys.path:
|
|
sys.path.insert(0, str(STUDIO_BACKEND))
|
|
|
|
|
|
def _rag_route():
|
|
"""Load ``routes/rag.py`` directly, bypassing the ``routes`` package.
|
|
|
|
``from routes.rag import X`` first runs ``routes/__init__.py``, which eagerly
|
|
imports every router — including the datasets router, whose chain does
|
|
``from datasets import IterableDataset`` at import time. On a GPU-less CI
|
|
runner the unsloth bootstrap can leave ``datasets`` half-initialized, so that
|
|
eager import raises. These tests only need pure helpers from rag.py, so load
|
|
the file on its own (it has no intra-``routes`` imports).
|
|
"""
|
|
mod = sys.modules.get("_rag_route_under_test")
|
|
if mod is None:
|
|
spec = importlib.util.spec_from_file_location(
|
|
"_rag_route_under_test", STUDIO_BACKEND / "routes" / "rag.py"
|
|
)
|
|
mod = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(mod)
|
|
sys.modules["_rag_route_under_test"] = mod
|
|
return mod
|
|
|
|
|
|
def test_reingest_request_accepts_all_optional_fields():
|
|
ReingestKBRequest = _rag_route().ReingestKBRequest
|
|
|
|
empty = ReingestKBRequest()
|
|
assert empty.chunking_strategy is None
|
|
assert empty.mode is None
|
|
assert empty.embedding_model is None
|
|
|
|
partial = ReingestKBRequest(chunking_strategy = "late")
|
|
assert partial.chunking_strategy == "late"
|
|
assert partial.mode is None
|
|
|
|
|
|
def test_reingest_request_rejects_unknown_strategy():
|
|
from pydantic import ValidationError
|
|
|
|
ReingestKBRequest = _rag_route().ReingestKBRequest
|
|
|
|
with pytest.raises(ValidationError):
|
|
ReingestKBRequest(chunking_strategy = "telekinetic")
|
|
|
|
|
|
def test_reingest_request_rejects_unknown_mode():
|
|
from pydantic import ValidationError
|
|
|
|
ReingestKBRequest = _rag_route().ReingestKBRequest
|
|
|
|
with pytest.raises(ValidationError):
|
|
ReingestKBRequest(mode = "augmented")
|
|
|
|
|
|
def test_constraint_still_enforced_for_reingest_combos():
|
|
"""The combination guard is shared with create — verify it still bites."""
|
|
from fastapi import HTTPException
|
|
|
|
_validate_mode_combo = _rag_route()._validate_mode_combo
|
|
|
|
with pytest.raises(HTTPException) as excinfo:
|
|
_validate_mode_combo("multimodal", "late")
|
|
assert excinfo.value.status_code == 400
|