generated from john/python-template
Baseline was 207 diagnostics. Two real bugs were hiding in the noise: - tools/run_destructive_tests.py imported ctypes.wintypes at module scope, which raises on non-Windows, and called fcntl unconditionally. The Windows and POSIX implementations now live under a module-level sys.platform split. - tests/ui/test_sources_page.py constructed Source(...) without document_id. Structural fixes, not suppressions: - New src/transcription/db/loading.py owns the SQLModel-field to QueryableAttribute reinterpretation via orm_attribute()/selectinload()/ defer(). This removed 42 "# pyright: ignore[reportArgumentType]" comments across documents/jobs/people/sources. Its docstring records that selectinload(A.b, B.c) is NOT equivalent to the chained form: varargs applies the selectin strategy only to the last path element, which under lazy="raise" raises InvalidRequestError at render time. - db/session.py transaction_scope no longer accepts or yields AsyncSessionTransaction. No caller ever passed one, sessionmaker.begin() yields an AsyncSession, and the dead branch was latently buggy because services call .exec(). Cleared 7 workflows.py diagnostics. - services/registry.py RegistryService is bound by a new RegistryEntry Protocol instead of bare SQLModel, so the shared implementation can read id/label/normalized_label/is_active. Cleared 9 diagnostics. - Column expressions in sources.py/jobs.py/test_store.py wrap in sqlmodel col(), the idiom already used in registry.py. - read_source_navigation wraps its literal tuple bounds in literal(). - normalization.py narrows with isinstance(image, TiffImageFile) rather than comparing image.format, since tag_v2 is TIFF-only. - linked_people.render uses @ui.refreshable_method, the NiceGUI API for bound methods. - The OpenRouter capturing client re-raises ResponseNotRead when the response stream is not async rather than mis-wrapping it. Tooling gate: - New .pre-commit-config.yaml runs ruff check and ty check as blocking hooks. No pre-commit config previously existed. Negative-tested: injecting a type error fails both hooks. - The last two "# pyright: ignore" comments (config.py) are removed; ty does not honor pyright directives. One "# ty: ignore" remains, in tests/test_prompts.py, where the test deliberately assigns to a frozen field to assert ValidationError. - asyncio_default_fixture_loop_scope is pinned to "function" so pytest-asyncio behavior does not shift on upgrade. Verification: ruff check clean, ty check reports 0 diagnostics, 292 passed and 4 skipped, pre-commit passes and demonstrably fails on a regression, and tools/run_destructive_tests.py runs on Windows. Co-authored-by: Copilot App <[email protected]>
111 lines
4.1 KiB
Python
111 lines
4.1 KiB
Python
"""Tests for prompt artifacts in prompts/."""
|
|
|
|
import hashlib
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from pydantic import ValidationError
|
|
|
|
from transcription.config import Settings
|
|
from transcription.services.sources import PromptExecution
|
|
from transcription.services.sources import PromptLoadError
|
|
from transcription.services.sources import build_prompt_execution
|
|
from transcription.services.sources import load_prompt_text
|
|
|
|
PROMPT_PATH = Path("prompts/transcribe_document.md")
|
|
|
|
|
|
def _prompt_text() -> str:
|
|
"""Read prompt text from the canonical prompt file."""
|
|
return PROMPT_PATH.read_text(encoding="utf-8")
|
|
|
|
|
|
class TestPromptArtifact:
|
|
"""Verify prompt artifact presence and baseline semantics."""
|
|
|
|
def test_prompt_file_exists(self):
|
|
"""Canonical transcription prompt file exists."""
|
|
assert PROMPT_PATH.exists()
|
|
|
|
def test_prompt_file_is_not_empty(self):
|
|
"""Canonical prompt file has non-whitespace content."""
|
|
text = _prompt_text()
|
|
assert text.strip()
|
|
|
|
def test_prompt_mentions_verbatim_behavior(self):
|
|
"""Prompt explicitly enforces verbatim transcription behavior."""
|
|
text = _prompt_text().lower()
|
|
assert "verbatim" in text
|
|
assert "do not summarize" in text
|
|
|
|
def test_prompt_includes_uncertainty_and_illegible_markers(self):
|
|
"""Prompt contains conventions for uncertainty and illegible text."""
|
|
text = _prompt_text().lower()
|
|
assert "[boston?]" in text
|
|
assert "[illegible]" in text
|
|
|
|
def test_prompt_includes_deleted_and_inserted_conventions(self):
|
|
"""Prompt contains conventions for deleted and inserted text."""
|
|
text = _prompt_text().lower()
|
|
assert "[deleted:" in text
|
|
assert "[inserted:" in text
|
|
|
|
def test_prompt_defines_exactly_one_body_medium_marker(self):
|
|
text = _prompt_text().lower()
|
|
for marker in (
|
|
"[document body handwritten]",
|
|
"[document body typewritten]",
|
|
"[document body typeset]",
|
|
"[document body mixed]",
|
|
):
|
|
assert marker in text
|
|
assert "exactly one" in text
|
|
assert "typewriter defects are not handwriting" in text
|
|
|
|
def test_prompt_preserves_structured_layout_associations(self):
|
|
text = _prompt_text().lower()
|
|
for phrase in ("tables of contents", "dotted-leader", "page-reference", "tables and forms", "columns"):
|
|
assert phrase in text
|
|
|
|
|
|
class TestPromptConfiguration:
|
|
def test_builds_validated_immutable_prompt_provenance(self, tmp_path):
|
|
prompt_text = "Transcribe this document verbatim."
|
|
(tmp_path / "custom.md").write_text(prompt_text, encoding="utf-8")
|
|
settings = Settings(
|
|
openrouter_api_key="test-key",
|
|
prompt_dir=tmp_path,
|
|
default_prompt_name="custom.md",
|
|
transcription_temperature=0.2,
|
|
transcription_top_p=0.9,
|
|
)
|
|
|
|
execution = build_prompt_execution(settings=settings)
|
|
|
|
assert execution.prompt_hash == hashlib.sha256(prompt_text.encode()).hexdigest()
|
|
assert execution.temperature == 0.2
|
|
assert execution.top_p == 0.9
|
|
with pytest.raises(ValidationError):
|
|
execution.prompt_name = "changed.md" # ty: ignore[invalid-assignment]
|
|
|
|
def test_rejects_prompt_path_traversal_even_with_direct_loader_call(self, tmp_path):
|
|
outside_prompt = tmp_path / "outside.md"
|
|
prompt_dir = tmp_path / "prompts"
|
|
prompt_dir.mkdir()
|
|
outside_prompt.write_text("secret", encoding="utf-8")
|
|
settings = Settings(openrouter_api_key="test-key", prompt_dir=prompt_dir)
|
|
|
|
with pytest.raises(PromptLoadError):
|
|
load_prompt_text(prompt_name="../outside.md", settings=settings)
|
|
|
|
def test_prompt_execution_rejects_invalid_provenance_hash(self):
|
|
with pytest.raises(ValidationError):
|
|
PromptExecution(
|
|
prompt_name="prompt.md",
|
|
prompt_hash="not-a-sha256",
|
|
system_prompt=None,
|
|
user_prompt="text",
|
|
temperature=None,
|
|
top_p=None,
|
|
)
|