generated from john/python-template
Claim jobs atomically [CRIT-01] - Replace JobService.read_next_queued_job with claim_next_queued_job, which selects and transitions QUEUED -> PROCESSING inside one transaction. The old read-then-write sequence left a window in which two workers could observe the same QUEUED row. - Add the missing .limit(1). The poll previously ordered the entire queued set and discarded all but the first row. - Drop the eager loads from the hot poll entirely. They were pure waste: process_queued_job immediately re-reads the job through read_job with the relationships it actually needs. - Guard the row with with_for_update(skip_locked=True) on PostgreSQL so the claim stays correct once more than one worker exists. On SQLite the claim is a bounded single-writer transaction. - Correct the comment at the remaining direct-call claim site, which described the hazard rather than the guarantee. Reuse the provider connection [HIGH-02] - Build the ServiceBundle once per worker loop instead of once per job, and close it at loop shutdown. Every job previously constructed a new SourceService, and with it a new provider adapter and a new httpx.AsyncClient, paying a full TLS handshake per page and discarding the connection pool. - process_next_queued_job now accepts an optional caller-owned bundle and only closes bundles it created itself. Uncap the provider timeout [HIGH-03] - Remove le=20.0 from worker_provider_timeout_seconds. The cap equalled the default, so the ceiling could never be raised, and dense-page vision transcription routinely needs longer. Default raised to 180s. - Pass an explicit httpx.Timeout to the OpenRouter AsyncClient. httpx defaults every phase to 5 seconds, so the real read budget was 5s regardless of the configured value; the outer asyncio.wait_for could never be the binding constraint. Connect stays at 10s. Tighten the provider boundary [MED-03] - Declare model, current_request_manifest, current_transport_evidence, and aclose on the TranscriptionProvider Protocol. - Delete the per-call inspect.signature(adapter.transcribe).parameters reflection and the untyped kwargs dict it fed. The Protocol had declared requested_model all along, so the reflection was dead defensive weight on the hot path. - Replace the three getattr probes for aclose and the evidence attributes with direct typed access. Deduplicate bundle construction [MED-06] - Add ServiceBundle.from_session_factory and ServiceBundle.aclose, replacing the duplicated four-service instantiation blocks in app.py and worker.py. - _recover_stale_processing_jobs now uses the bundle built moments earlier instead of constructing a second JobService. Tests - Claiming returns the oldest job, marks it PROCESSING, never hands the same job out twice, and emits exactly one unadorned SELECT carrying LIMIT and no JOIN. - The worker loop threads one bundle through consecutive jobs and closes it once at shutdown; a caller-owned bundle is left open. - Settings accepts a timeout above 20 seconds and still rejects zero. - The OpenRouter client's read, write, and pool timeouts track the configured budget rather than the httpx default. Note: .env in this checkout still pins WORKER_PROVIDER_TIMEOUT_SECONDS=20 and should be raised to pick up this fix. Verified: 268 passed, 4 skipped; ruff check clean. Co-authored-by: Copilot App <[email protected]>
177 lines
6.7 KiB
Python
177 lines
6.7 KiB
Python
"""Tests for transcription.config — settings loading, provider defaults, and paths."""
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from pydantic import ValidationError
|
|
|
|
from transcription.config import Provider
|
|
from transcription.config import Settings
|
|
from transcription.config import parse_cli_settings
|
|
|
|
|
|
def _make_settings(**overrides) -> Settings:
|
|
"""Build a Settings instance with a dummy API key unless overridden."""
|
|
defaults = {"openrouter_api_key": "test-key-abc123", "provider_models": None}
|
|
defaults.update(overrides)
|
|
return Settings(**defaults)
|
|
|
|
|
|
class TestSettingsLoading:
|
|
"""Verify Settings construction and required-field validation."""
|
|
|
|
def test_loads_from_env(self, monkeypatch):
|
|
"""Settings constructs when OPENROUTER_API_KEY is provided."""
|
|
monkeypatch.setenv("OPENROUTER_API_KEY", "test-key-xyz")
|
|
settings = Settings()
|
|
assert settings.openrouter_api_key.get_secret_value() == "test-key-xyz"
|
|
|
|
def test_requires_api_key(self, monkeypatch):
|
|
"""Settings raises ValidationError when OPENROUTER_API_KEY is missing."""
|
|
monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
|
|
with pytest.raises(ValidationError):
|
|
Settings(_env_file=None)
|
|
|
|
def test_ignores_process_cli_arguments(self, monkeypatch):
|
|
"""Ordinary settings construction does not consume tooling arguments."""
|
|
monkeypatch.setattr("sys.argv", ["pytest", "--rootdir=/tmp/project"])
|
|
|
|
settings = _make_settings()
|
|
|
|
assert settings.port == 8000
|
|
|
|
def test_explicit_cli_parser_reads_arguments(self):
|
|
"""The executable settings boundary accepts application CLI flags."""
|
|
settings = parse_cli_settings(
|
|
[
|
|
"--openrouter-api-key",
|
|
"test-key",
|
|
"--port",
|
|
"8123",
|
|
"--reload",
|
|
]
|
|
)
|
|
|
|
assert settings.openrouter_api_key.get_secret_value() == "test-key"
|
|
assert settings.port == 8123
|
|
assert settings.reload is True
|
|
|
|
|
|
class TestProviderSettings:
|
|
"""Verify provider enum defaults and validation."""
|
|
|
|
def test_defaults_to_openrouter(self):
|
|
"""Default provider is openrouter when not explicitly set."""
|
|
settings = _make_settings()
|
|
assert settings.provider == Provider.OPENROUTER
|
|
assert settings.provider == "openrouter"
|
|
|
|
def test_rejects_invalid_value(self):
|
|
"""Setting PROVIDER to an invalid value raises ValidationError."""
|
|
with pytest.raises(ValidationError):
|
|
_make_settings(provider="not-a-provider")
|
|
|
|
def test_optional_provider_header_fields_default_to_none(self):
|
|
"""openrouter_http_referer and openrouter_app_title are None when unset."""
|
|
settings = _make_settings()
|
|
assert settings.openrouter_http_referer is None
|
|
assert settings.openrouter_app_title is None
|
|
|
|
@pytest.mark.parametrize(
|
|
("field", "value"),
|
|
[
|
|
("transcription_temperature", -0.1),
|
|
("transcription_temperature", 2.1),
|
|
("transcription_top_p", -0.1),
|
|
("transcription_top_p", 1.1),
|
|
],
|
|
)
|
|
def test_rejects_sampling_values_outside_provider_ranges(self, field, value):
|
|
with pytest.raises(ValidationError):
|
|
_make_settings(**{field: value})
|
|
|
|
def test_rejects_prompt_paths_outside_prompt_directory(self):
|
|
with pytest.raises(ValidationError):
|
|
_make_settings(default_prompt_name="../secret.md")
|
|
|
|
def test_settings_are_immutable_runtime_snapshots(self):
|
|
settings = _make_settings()
|
|
|
|
with pytest.raises(ValidationError):
|
|
settings.port = 9000
|
|
|
|
def test_provider_model_accepts_env_default(self, monkeypatch):
|
|
"""provider_model is sourced when provided through environment configuration."""
|
|
monkeypatch.setenv("PROVIDER_MODEL", "google/gemini-2.5-flash")
|
|
settings = Settings(openrouter_api_key="test-key-abc123")
|
|
assert settings.provider_model == "google/gemini-2.5-flash"
|
|
|
|
def test_provider_models_defaults_to_default_model(self):
|
|
settings = _make_settings(provider_model="vendor/default")
|
|
|
|
assert settings.provider_models == ("vendor/default",)
|
|
|
|
def test_provider_models_are_default_first_trimmed_and_deduplicated(self):
|
|
settings = _make_settings(
|
|
provider_model=" vendor/default ",
|
|
provider_models=["vendor/alternate", "vendor/default", " vendor/other "],
|
|
)
|
|
|
|
assert settings.provider_models == ("vendor/default", "vendor/alternate", "vendor/other")
|
|
|
|
def test_provider_models_rejects_empty_list(self):
|
|
with pytest.raises(ValidationError):
|
|
_make_settings(provider_models=[])
|
|
|
|
def test_provider_models_loads_json_from_environment(self, monkeypatch):
|
|
monkeypatch.setenv("PROVIDER_MODEL", "vendor/default")
|
|
monkeypatch.setenv("PROVIDER_MODELS", '["vendor/alternate","vendor/default"]')
|
|
|
|
settings = Settings(openrouter_api_key="test-key-abc123")
|
|
|
|
assert settings.provider_models == ("vendor/default", "vendor/alternate")
|
|
|
|
|
|
class TestPathSettings:
|
|
"""Verify filesystem path field types."""
|
|
|
|
def test_path_fields_are_path_objects(self):
|
|
"""upload_dir and prompt_dir are Path instances."""
|
|
settings = _make_settings()
|
|
assert isinstance(settings.upload_dir, Path)
|
|
assert isinstance(settings.prompt_dir, Path)
|
|
|
|
|
|
class TestWorkerReliabilitySettings:
|
|
"""Verify worker retry settings defaults."""
|
|
|
|
def test_worker_retry_defaults(self):
|
|
"""worker retry settings default to no retries."""
|
|
settings = _make_settings()
|
|
assert settings.worker_max_retries == 0
|
|
|
|
|
|
def test_provider_timeout_is_not_capped_at_twenty_seconds():
|
|
"""HIGH-03: vision transcription regularly runs past the old le=20.0 ceiling."""
|
|
settings = Settings(openrouter_api_key="test-key", worker_provider_timeout_seconds=300.0)
|
|
assert settings.worker_provider_timeout_seconds == 300.0
|
|
|
|
|
|
def test_provider_timeout_must_still_be_positive():
|
|
with pytest.raises(ValidationError):
|
|
Settings(openrouter_api_key="test-key", worker_provider_timeout_seconds=0.0)
|
|
|
|
|
|
def test_openrouter_client_timeout_tracks_the_configured_budget():
|
|
"""HIGH-03: httpx defaults every phase to 5s, silently capping the provider call."""
|
|
from transcription.providers.openrouter import OpenRouterTranscriptionProvider
|
|
|
|
settings = Settings(openrouter_api_key="test-key", worker_provider_timeout_seconds=123.0)
|
|
provider = OpenRouterTranscriptionProvider(settings=settings)
|
|
timeout = provider._capturing_client._client.timeout
|
|
|
|
assert timeout.read == 123.0
|
|
assert timeout.write == 123.0
|
|
assert timeout.pool == 123.0
|
|
assert timeout.connect == 10.0
|