mirror of
https://github.com/yusufipk/dikte.git
synced 2026-09-11 10:56:10 +00:00
yusufipk
034c2bec7e
Cleanup was the one step with only one place to run. Speech to text has three providers behind a setting and the agent has three behind another, but the model that drops the "eee"s out of a sentence was always a request to OpenRouter, which meant a second key on a machine that already pays for a model and already hands whole dictations to it as commands. Claude Code and Codex can rewrite a sentence as easily as they can put something in your calendar, and now they may. cleanup.py is where that choice lives, so worker, the file transcriber and the meeting all ask the same question rather than each building the same OpenRouter request. What comes out of a CLI that failed is a CleanupError, which is an ApiError, because to the chain a cleanup that failed is a cleanup that failed however it was run: the raw transcript is still pasted and the reason still shows in the corner, unchanged. Neither CLI is given anything it does not need for the job. No tools, no MCP servers, no session to resume, and the home directory rather than wherever the agent is pointed, since a project's instructions have opinions about how text should be written and none of them are about this transcript. The transcript goes in fenced the same way the OpenRouter call fences it, because it is material rather than an instruction however much of it reads like one. Claude takes the cleanup rules as its whole system prompt; Codex has no system prompt of its own, so they ride in front of the text, and its answer is read from the file it writes on the way out rather than from a stdout that also carries a header, its thinking and a token count. The cost is seconds. OpenRouter answers in about one, a CLI in six or seven, because each one opens a whole session to do it. That is the trade the box says out loud, and the default has not moved: OpenRouter cleans up until you say otherwise. Codex's two lowest thinking levels now ask for "low". "minimal" was its bottom rung until the newer models replaced it with "none", and each of them answers the other's word with a 400, which the agent has been quietly hitting too. In the settings window the model box belongs to whoever is chosen rather than meaning three different things in turn, since an OpenRouter id and a Claude alias do not belong in the same field, and under it is the same "found it or not" line the agent tab has. dikte doctor asks about the program instead of the key when a CLI does the cleaning, and the history records which model actually did it.
338 lines
14 KiB
Python
338 lines
14 KiB
Python
"""The two windows, on Qt's offscreen platform.
|
||
|
||
Not a look at the pixels: what these hold onto is the round trip through the
|
||
settings window. Every tab loads a setting into a widget and writes it back on
|
||
save, so a setting added to one half and not the other is silently reset the
|
||
next time anybody presses Save. That is the failure this catches.
|
||
"""
|
||
|
||
import unittest
|
||
from unittest import mock
|
||
|
||
from PyQt6.QtWidgets import QApplication, QMessageBox
|
||
|
||
import config as cfg
|
||
import hotkey
|
||
import overlay as overlay_module
|
||
import settings_ui
|
||
from tests.support import DikteTest, only_these_tools
|
||
|
||
# One application for the whole run; Qt allows no second one.
|
||
_app = QApplication.instance() or QApplication([])
|
||
|
||
|
||
# A valid non-default value for every setting the window shows. Anything the
|
||
# window does not touch is left out: the round trip cannot lose what it never
|
||
# reads.
|
||
CHANGED = {
|
||
"ui_language": "tr",
|
||
"language": "tr",
|
||
"auto_paste": False,
|
||
"paste_shortcut": "ctrl+shift+v",
|
||
"restore_clipboard": True,
|
||
"overlay_corner": "top-right",
|
||
"max_seconds": 120,
|
||
"skip_silent": False,
|
||
"silence_db": -42.0,
|
||
"filter_hallucinations": False,
|
||
"keep_audio": True,
|
||
"openai_api_key": "sk-test-key",
|
||
"groq_api_key": "gsk-test-key",
|
||
"openrouter_api_key": "sk-or-test-key",
|
||
"transcribe_provider": "openrouter",
|
||
"transcribe_model": "whisper-1",
|
||
"groq_transcribe_model": "whisper-large-v3",
|
||
"openrouter_transcribe_model": "openai/whisper-1",
|
||
"cleanup_enabled": False,
|
||
"cleanup_provider": "claude",
|
||
"cleanup_model": "some/other-model",
|
||
"cleanup_claude_model": "opus",
|
||
"cleanup_codex_model": "gpt-5",
|
||
"cleanup_reasoning": "high",
|
||
"cleanup_prompt": "Only fix the punctuation.",
|
||
"file_cleanup_prompt": "Keep the stamps where they are.",
|
||
"transcribe_prompt": "Paraşüt, OpenFrame",
|
||
"assistant_provider": "codex",
|
||
"assistant_model": "opus",
|
||
"assistant_permission_mode": "manual",
|
||
"assistant_codex_model": "gpt-5",
|
||
"assistant_codex_sandbox": "read-only",
|
||
"assistant_openrouter_model": "some/agent-model",
|
||
"assistant_reasoning": "high",
|
||
"assistant_dir": "/tmp",
|
||
"assistant_timeout": 600,
|
||
"assistant_session_minutes": 90,
|
||
"assistant_paste": False,
|
||
"assistant_cleanup": True,
|
||
"assistant_prompt": "Answer in one sentence.",
|
||
"assistant_shortcut": "Meta+A",
|
||
"meeting_self_name": "Yusuf",
|
||
"meeting_other_name": "Ayşe",
|
||
"meeting_participants": "Mehmet",
|
||
"meeting_model": "some/meeting-model",
|
||
"meeting_reasoning": "medium",
|
||
"meeting_language": "tr",
|
||
"meeting_cleanup": False,
|
||
"meeting_max_seconds": 7200,
|
||
"meeting_keep_audio": True,
|
||
"meeting_shortcut": "Meta+M",
|
||
"meeting_prompt": "Write it as bullet points.",
|
||
"file_timestamps": True,
|
||
"file_cleanup": False,
|
||
"shortcut": "Ctrl+Alt+Space",
|
||
"cancel_shortcut": "Meta+Shift+Space",
|
||
"evdev_hotkey": True,
|
||
"history_limit": 50,
|
||
}
|
||
|
||
|
||
class Settings(DikteTest):
|
||
def setUp(self):
|
||
super().setUp()
|
||
# No pactl, no model lists over the network, and no modal dialogue
|
||
# waiting for somebody to press OK.
|
||
self.enterContext(only_these_tools())
|
||
self.enterContext(mock.patch.object(QMessageBox, "information"))
|
||
self.enterContext(mock.patch.object(settings_ui.SettingsWindow,
|
||
"_load_models"))
|
||
self.enterContext(mock.patch.object(settings_ui.SettingsWindow,
|
||
"_load_transcribe_models"))
|
||
self.enterContext(mock.patch.object(settings_ui.hotkey, "APPLICATIONS_DIR",
|
||
self.path("applications")))
|
||
self.enterContext(mock.patch.object(settings_ui.hotkey, "SHORTCUTS_FILE",
|
||
self.path("kglobalshortcutsrc")))
|
||
|
||
def window(self, conf):
|
||
window = settings_ui.SettingsWindow(conf)
|
||
self.addCleanup(window.deleteLater)
|
||
self.addCleanup(window.close)
|
||
return window
|
||
|
||
def test_the_window_opens_with_every_tab_on_it(self):
|
||
window = self.window(cfg.Config())
|
||
tabs = window.findChildren(settings_ui.QTabWidget)[0]
|
||
self.assertEqual(tabs.count(), 9)
|
||
self.assertEqual(window.windowTitle(), "Dikte Settings")
|
||
|
||
def test_saving_without_touching_anything_changes_nothing(self):
|
||
"""Every widget has to load what is stored, or Save writes its default
|
||
over it. This says so for the whole table at once."""
|
||
conf = cfg.Config()
|
||
before = dict(conf.data)
|
||
self.window(conf)._save()
|
||
self.assertEqual(conf.data, before)
|
||
|
||
def test_a_setting_of_your_own_survives_the_round_trip(self):
|
||
self.write_config(CHANGED)
|
||
conf = cfg.Config()
|
||
self.window(conf)._save()
|
||
stored = self.read_config_file()
|
||
for key, value in CHANGED.items():
|
||
with self.subTest(key=key):
|
||
self.assertEqual(stored[key], value)
|
||
|
||
def test_the_model_box_on_screen_belongs_to_whoever_cleans_up(self):
|
||
"""An OpenRouter id and a Claude alias are not the same field."""
|
||
window = self.window(cfg.Config())
|
||
boxes = {"openrouter": window.cleanup_model_row,
|
||
"claude": window.cleanup_claude_model,
|
||
"codex": window.cleanup_codex_model}
|
||
for provider, box in boxes.items():
|
||
with self.subTest(provider=provider):
|
||
window._select_data(window.cleanup_provider, provider)
|
||
shown = [name for name, other in boxes.items()
|
||
if not other.isHidden()]
|
||
self.assertEqual(shown, [provider])
|
||
self.assertFalse(box.isHidden())
|
||
|
||
def test_the_settings_the_window_does_not_show_are_left_alone(self):
|
||
"""A tab nobody wrote must not reset what the command line set."""
|
||
self.write_config({"silence_db": -42.0, "speech_margin_db": 15.0,
|
||
"openrouter_base_url": "http://localhost:1234/v1"})
|
||
conf = cfg.Config()
|
||
self.window(conf)._save()
|
||
stored = self.read_config_file()
|
||
self.assertEqual(stored["speech_margin_db"], 15.0)
|
||
self.assertEqual(stored["openrouter_base_url"], "http://localhost:1234/v1")
|
||
|
||
def test_every_global_shortcut_has_a_row_of_its_own(self):
|
||
window = self.window(cfg.Config())
|
||
self.assertEqual(set(window._shortcut_rows), set(hotkey.SHORTCUTS))
|
||
|
||
def test_emptying_a_shortcut_turns_it_off_but_not_the_toggle(self):
|
||
"""The application is unusable without the toggle, so that one box
|
||
falls back. The rest stay empty, which is how they are switched off."""
|
||
conf = cfg.Config()
|
||
window = self.window(conf)
|
||
for box, _status, _missing in window._shortcut_rows.values():
|
||
box.setCurrentText("")
|
||
window._save()
|
||
self.assertEqual(conf["shortcut"], "Ctrl+Space")
|
||
self.assertEqual(conf["cancel_shortcut"], "")
|
||
self.assertEqual(conf["assistant_shortcut"], "")
|
||
self.assertEqual(conf["meeting_shortcut"], "")
|
||
|
||
def test_installing_the_discard_key_writes_its_own_entry(self):
|
||
conf = cfg.Config()
|
||
window = self.window(conf)
|
||
window._shortcut_rows["cancel"][0].setCurrentText("Meta+Shift+Space")
|
||
with mock.patch.object(settings_ui.hotkey, "install_shortcut",
|
||
return_value=(True, "saved")) as install:
|
||
window._install_shortcut("cancel")
|
||
combo, command = install.call_args.args
|
||
self.assertEqual(combo, "Meta+Shift+Space")
|
||
self.assertTrue(command.endswith(" cancel"))
|
||
self.assertEqual(install.call_args.kwargs["desktop_id"],
|
||
hotkey.CANCEL_DESKTOP_ID)
|
||
self.assertEqual(conf["cancel_shortcut"], "Meta+Shift+Space")
|
||
|
||
def test_a_prompt_left_at_its_default_is_stored_as_empty(self):
|
||
"""So that switching the interface language switches the prompt too."""
|
||
conf = cfg.Config()
|
||
self.window(conf)._save()
|
||
self.assertEqual(conf["cleanup_prompt"], "")
|
||
self.assertEqual(conf["meeting_prompt"], "")
|
||
self.assertEqual(conf["assistant_prompt"], "")
|
||
|
||
def test_each_provider_keeps_its_own_transcription_model(self):
|
||
self.write_config({"transcribe_provider": "openai",
|
||
"transcribe_model": "gpt-4o-transcribe",
|
||
"groq_transcribe_model": "whisper-large-v3",
|
||
"openrouter_transcribe_model": "openai/whisper-1"})
|
||
conf = cfg.Config()
|
||
window = self.window(conf)
|
||
for provider in ("groq", "openrouter"):
|
||
window.transcribe_provider.setCurrentIndex(
|
||
window.transcribe_provider.findData(provider))
|
||
window._save()
|
||
self.assertEqual(conf["transcribe_provider"], "openrouter")
|
||
self.assertEqual(conf["transcribe_model"], "gpt-4o-transcribe")
|
||
self.assertEqual(conf["groq_transcribe_model"], "whisper-large-v3")
|
||
|
||
def test_the_provider_box_offers_every_provider_config_knows(self):
|
||
window = self.window(cfg.Config())
|
||
offered = [window.transcribe_provider.itemData(i)
|
||
for i in range(window.transcribe_provider.count())]
|
||
self.assertEqual(offered, list(cfg.TRANSCRIBERS))
|
||
|
||
def test_the_answer_to_a_test_lands_under_the_key_it_was_asked_about(self):
|
||
"""One signal serves all three buttons, so it carries which one asked."""
|
||
window = self.window(cfg.Config())
|
||
window._on_test_done("groq", True, "it works")
|
||
button, answer = window._testers["groq"]
|
||
self.assertEqual(answer.text(), "✓ it works")
|
||
self.assertTrue(button.isEnabled())
|
||
self.assertEqual(window._testers["openai"][1].text(), "")
|
||
|
||
def test_a_key_lands_in_the_field_of_its_own_provider(self):
|
||
self.write_config({"groq_api_key": "gsk-mine"})
|
||
window = self.window(cfg.Config())
|
||
self.assertEqual(window.groq_key.text(), "gsk-mine")
|
||
self.assertEqual(window.openai_key.text(), "")
|
||
|
||
def test_saving_applies_the_lowered_history_limit_at_once(self):
|
||
for index in range(10):
|
||
cfg.append_history({"ts": "now", "text": str(index)})
|
||
self.write_config({"history_limit": 3})
|
||
self.window(cfg.Config())._save()
|
||
self.assertEqual(len(cfg.read_history()), 3)
|
||
|
||
def test_saving_tells_whoever_is_listening(self):
|
||
conf = cfg.Config()
|
||
window = self.window(conf)
|
||
applied = []
|
||
window.applied.connect(lambda: applied.append(True))
|
||
window._save()
|
||
self.assertEqual(applied, [True])
|
||
|
||
def test_the_window_is_readable_in_turkish_too(self):
|
||
self.write_config({"ui_language": "tr"})
|
||
window = self.window(cfg.Config())
|
||
self.assertEqual(window.windowTitle(), "Dikte Ayarları")
|
||
|
||
|
||
class Overlay(DikteTest):
|
||
def overlay(self, **kwargs):
|
||
widget = overlay_module.Overlay(**kwargs)
|
||
self.addCleanup(widget.deleteLater)
|
||
self.addCleanup(widget.close)
|
||
return widget
|
||
|
||
def test_it_never_takes_focus(self):
|
||
"""It appears while you are typing; stealing the keyboard would be rude."""
|
||
from PyQt6.QtCore import Qt
|
||
flags = self.overlay().windowFlags()
|
||
self.assertTrue(flags & Qt.WindowType.WindowDoesNotAcceptFocus)
|
||
self.assertTrue(flags & Qt.WindowType.WindowStaysOnTopHint)
|
||
|
||
def test_recording_then_working_then_done(self):
|
||
widget = self.overlay()
|
||
widget.show_recording()
|
||
self.assertTrue(widget.showing)
|
||
widget.push_level(0.5)
|
||
widget.set_seconds(3)
|
||
widget.show_busy("Transcribing…")
|
||
widget.show_done("Pasted")
|
||
widget._conceal()
|
||
self.assertFalse(widget.showing)
|
||
|
||
def test_a_meeting_shows_both_sides(self):
|
||
widget = self.overlay()
|
||
widget.show_meeting()
|
||
widget.push_levels(0.4, 0.7)
|
||
self.assertTrue(widget.showing)
|
||
|
||
def test_every_corner_is_understood(self):
|
||
for corner in ("top-left", "top-right", "bottom-left", "bottom-right"):
|
||
with self.subTest(corner=corner):
|
||
widget = self.overlay(corner=corner)
|
||
widget.show_recording()
|
||
widget._reposition()
|
||
|
||
def test_a_warning_and_an_error_both_show(self):
|
||
widget = self.overlay()
|
||
widget.show_warning("cleanup failed")
|
||
widget.show_error("no microphone")
|
||
|
||
def test_one_indicator_can_stack_above_another(self):
|
||
first = self.overlay()
|
||
first.show_recording()
|
||
second = self.overlay(below=first)
|
||
second.show_busy("Asking Claude…")
|
||
self.assertTrue(second.showing)
|
||
|
||
def test_a_job_in_progress_can_be_waved_away(self):
|
||
"""Ten minutes of work should not have to be watched for ten minutes."""
|
||
widget = self.overlay(dismissable=True)
|
||
widget.show_busy("Asking Claude…")
|
||
widget.dismiss()
|
||
self.assertFalse(widget.showing)
|
||
|
||
def test_progress_stays_away_once_it_was_waved_off(self):
|
||
widget = self.overlay(dismissable=True)
|
||
widget.show_busy("Asking Claude…")
|
||
widget.muted = True
|
||
widget.dismiss()
|
||
widget.show_busy("Reading a web page…")
|
||
self.assertFalse(widget.showing)
|
||
|
||
def test_the_outcome_shows_even_so(self):
|
||
"""Waving it away asks not to be watched, not to be kept in the dark."""
|
||
widget = self.overlay(dismissable=True)
|
||
widget.show_busy("Asking Claude…")
|
||
widget.muted = True
|
||
widget.dismiss()
|
||
widget.show_done("Pasted")
|
||
self.assertTrue(widget.showing)
|
||
|
||
def test_a_new_run_starts_visible_whatever_the_last_one_did(self):
|
||
widget = self.overlay(dismissable=True)
|
||
widget.muted = True
|
||
widget.show_recording()
|
||
self.assertTrue(widget.showing)
|
||
self.assertFalse(widget.muted)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|