mirror of
https://github.com/yusufipk/dikte.git
synced 2026-09-11 10:56:10 +00:00
Clean the transcript up on the subscription you already have
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.
This commit is contained in:
yusufipk
@@ -0,0 +1,211 @@
|
||||
"""Who cleans the transcript up, and what they are asked.
|
||||
|
||||
The CLIs are faked at subprocess.run: what the tests read is the argument list
|
||||
each one is given, where the answer is picked up from, and what happens to the
|
||||
chain when the program is missing, slow or unhappy. The OpenRouter path is the
|
||||
one that was always there and is checked here only for still being taken.
|
||||
"""
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
import unittest
|
||||
from unittest import mock
|
||||
|
||||
import api
|
||||
import cleanup
|
||||
from tests.support import DikteTest
|
||||
|
||||
|
||||
def fake_run(stdout="", code=0, stderr="", last_message=""):
|
||||
"""Stand in for subprocess.run, writing the file Codex would have written."""
|
||||
calls = []
|
||||
|
||||
def run(cmd, **kwargs):
|
||||
calls.append(cmd)
|
||||
if last_message and "-o" in cmd:
|
||||
with open(cmd[cmd.index("-o") + 1], "w", encoding="utf-8") as fh:
|
||||
fh.write(last_message)
|
||||
return subprocess.CompletedProcess(cmd, code, stdout, stderr)
|
||||
|
||||
return mock.patch.object(subprocess, "run", side_effect=run), calls
|
||||
|
||||
|
||||
class Provider(DikteTest):
|
||||
def test_the_default_is_still_openrouter(self):
|
||||
self.assertEqual(cleanup.provider(self.config()), "openrouter")
|
||||
|
||||
def test_a_provider_this_version_does_not_have(self):
|
||||
self.assertEqual(
|
||||
cleanup.provider(self.config(cleanup_provider="ollama")), "openrouter")
|
||||
|
||||
def test_each_one_is_recognised(self):
|
||||
for name in cleanup.PROVIDERS:
|
||||
with self.subTest(name=name):
|
||||
self.assertEqual(
|
||||
cleanup.provider(self.config(cleanup_provider=name)), name)
|
||||
|
||||
def test_what_each_one_runs(self):
|
||||
self.assertEqual(cleanup.executable("claude"), "claude")
|
||||
self.assertEqual(cleanup.executable("codex"), "codex")
|
||||
self.assertEqual(cleanup.executable("openrouter"), "")
|
||||
|
||||
def test_the_model_named_in_the_history_is_the_one_that_did_it(self):
|
||||
self.assertEqual(cleanup.model(self.config(cleanup_model="some/model")),
|
||||
"some/model")
|
||||
self.assertEqual(
|
||||
cleanup.model(self.config(cleanup_provider="claude")), "haiku")
|
||||
self.assertEqual(
|
||||
cleanup.model(self.config(cleanup_provider="claude",
|
||||
cleanup_claude_model="opus")), "opus")
|
||||
# Codex on its own default has no model id to report, only a name.
|
||||
self.assertEqual(
|
||||
cleanup.model(self.config(cleanup_provider="codex")), "codex")
|
||||
self.assertEqual(
|
||||
cleanup.model(self.config(cleanup_provider="codex",
|
||||
cleanup_codex_model="gpt-5.4")), "gpt-5.4")
|
||||
|
||||
|
||||
class OpenRouter(DikteTest):
|
||||
def test_it_is_still_one_request_with_the_settings_as_they_were(self):
|
||||
conf = self.config(openrouter_api_key="sk-or-test",
|
||||
cleanup_model="some/model", cleanup_reasoning="low")
|
||||
with mock.patch.object(api, "cleanup", return_value="Done.") as call:
|
||||
self.assertEqual(cleanup.run("uh, done", conf, "the rules"), "Done.")
|
||||
text, key, model, prompt = call.call_args.args
|
||||
self.assertEqual((text, key, model, prompt),
|
||||
("uh, done", "sk-or-test", "some/model", "the rules"))
|
||||
self.assertEqual(call.call_args.kwargs["reasoning"], "low")
|
||||
|
||||
def test_no_cli_is_started_for_it(self):
|
||||
conf = self.config(openrouter_api_key="sk-or-test")
|
||||
patcher, calls = fake_run(stdout="never")
|
||||
with patcher, mock.patch.object(api, "cleanup", return_value="Done."):
|
||||
cleanup.run("uh, done", conf, "the rules")
|
||||
self.assertEqual(calls, [])
|
||||
|
||||
|
||||
class ClaudeCode(DikteTest):
|
||||
def setUp(self):
|
||||
super().setUp()
|
||||
self.conf = self.config(cleanup_provider="claude")
|
||||
self.patch_attr(cleanup.shutil, "which", lambda name: f"/usr/bin/{name}")
|
||||
|
||||
def run_cleanup(self, text="uh, book it", **kwargs):
|
||||
patcher, calls = fake_run(**kwargs)
|
||||
with patcher:
|
||||
answer = cleanup.run(text, self.conf, "the rules")
|
||||
return answer, calls[0]
|
||||
|
||||
def test_the_transcript_goes_in_fenced_and_the_rules_go_in_as_the_prompt(self):
|
||||
answer, cmd = self.run_cleanup(stdout="Book it.\n")
|
||||
self.assertEqual(answer, "Book it.")
|
||||
self.assertEqual(cmd[0], "claude")
|
||||
self.assertIn("<transcript>\nuh, book it\n</transcript>", cmd)
|
||||
self.assertEqual(cmd[cmd.index("--system-prompt") + 1], "the rules")
|
||||
self.assertEqual(cmd[cmd.index("--model") + 1], "haiku")
|
||||
|
||||
def test_it_is_given_nothing_to_run_and_nothing_to_remember(self):
|
||||
_, cmd = self.run_cleanup(stdout="Book it.")
|
||||
self.assertEqual(cmd[cmd.index("--tools") + 1], "")
|
||||
self.assertIn("--strict-mcp-config", cmd)
|
||||
self.assertIn("--no-session-persistence", cmd)
|
||||
|
||||
def test_the_thinking_setting_is_carried_over_in_its_own_words(self):
|
||||
self.conf["cleanup_reasoning"] = "none"
|
||||
_, cmd = self.run_cleanup(stdout="Book it.")
|
||||
self.assertEqual(cmd[cmd.index("--effort") + 1], "low")
|
||||
|
||||
def test_no_thinking_setting_means_no_flag(self):
|
||||
_, cmd = self.run_cleanup(stdout="Book it.")
|
||||
self.assertNotIn("--effort", cmd)
|
||||
|
||||
def test_a_model_of_your_own(self):
|
||||
self.conf["cleanup_claude_model"] = "claude-sonnet-5"
|
||||
_, cmd = self.run_cleanup(stdout="Book it.")
|
||||
self.assertEqual(cmd[cmd.index("--model") + 1], "claude-sonnet-5")
|
||||
|
||||
def test_an_answer_of_nothing_is_a_failure_rather_than_an_empty_paste(self):
|
||||
with self.assertRaises(cleanup.CleanupError):
|
||||
self.run_cleanup(stdout=" \n")
|
||||
|
||||
def test_the_last_line_of_the_complaint_is_what_gets_shown(self):
|
||||
with self.assertRaises(cleanup.CleanupError) as caught:
|
||||
self.run_cleanup(code=1, stderr="a warning\nout of credit\n")
|
||||
self.assertEqual(str(caught.exception), "out of credit")
|
||||
|
||||
def test_a_failure_is_the_same_kind_the_chain_already_catches(self):
|
||||
# worker, the file transcriber and the meeting all keep the raw
|
||||
# transcript when an ApiError comes out of here.
|
||||
self.assertTrue(issubclass(cleanup.CleanupError, api.ApiError))
|
||||
|
||||
def test_a_program_that_is_not_installed_says_so_before_running_anything(self):
|
||||
self.patch_attr(cleanup.shutil, "which", lambda name: "")
|
||||
with self.assertRaises(cleanup.CleanupError) as caught:
|
||||
self.run_cleanup(stdout="Book it.")
|
||||
self.assertIn("claude", str(caught.exception))
|
||||
|
||||
def test_a_run_that_never_ends(self):
|
||||
def run(cmd, **kwargs):
|
||||
raise subprocess.TimeoutExpired(cmd, 180)
|
||||
|
||||
with mock.patch.object(subprocess, "run", side_effect=run):
|
||||
with self.assertRaises(cleanup.CleanupError) as caught:
|
||||
cleanup.run("uh, book it", self.conf, "the rules")
|
||||
self.assertIn("180", str(caught.exception))
|
||||
|
||||
|
||||
class Codex(DikteTest):
|
||||
def setUp(self):
|
||||
super().setUp()
|
||||
self.conf = self.config(cleanup_provider="codex")
|
||||
self.patch_attr(cleanup.shutil, "which", lambda name: f"/usr/bin/{name}")
|
||||
|
||||
def run_cleanup(self, text="uh, book it", **kwargs):
|
||||
patcher, calls = fake_run(**kwargs)
|
||||
with patcher:
|
||||
answer = cleanup.run(text, self.conf, "the rules")
|
||||
return answer, calls[0]
|
||||
|
||||
def test_the_rules_ride_in_front_of_the_transcript(self):
|
||||
answer, cmd = self.run_cleanup(last_message="Book it.\n")
|
||||
self.assertEqual(answer, "Book it.")
|
||||
self.assertEqual(cmd[:2], ["codex", "exec"])
|
||||
self.assertEqual(cmd[-1],
|
||||
"the rules\n\n---\n\n<transcript>\nuh, book it\n</transcript>")
|
||||
|
||||
def test_the_answer_is_read_from_the_file_rather_than_the_noise_on_stdout(self):
|
||||
answer, _ = self.run_cleanup(
|
||||
stdout="workdir: /home\nmodel: gpt-5.4\ntokens used 400\n",
|
||||
last_message="Book it.",
|
||||
)
|
||||
self.assertEqual(answer, "Book it.")
|
||||
|
||||
def test_that_file_does_not_stay_behind(self):
|
||||
_, cmd = self.run_cleanup(last_message="Book it.")
|
||||
self.assertFalse(os.path.exists(cmd[cmd.index("-o") + 1]))
|
||||
|
||||
def test_it_may_read_but_not_write_and_has_nobody_to_ask(self):
|
||||
_, cmd = self.run_cleanup(last_message="Book it.")
|
||||
self.assertEqual(cmd[cmd.index("--sandbox") + 1], "read-only")
|
||||
self.assertIn('approval_policy="never"', cmd)
|
||||
self.assertIn("--ephemeral", cmd)
|
||||
|
||||
def test_the_model_is_left_alone_until_one_is_typed_in(self):
|
||||
_, cmd = self.run_cleanup(last_message="Book it.")
|
||||
self.assertNotIn("-m", cmd)
|
||||
self.conf["cleanup_codex_model"] = "gpt-5.4"
|
||||
_, cmd = self.run_cleanup(last_message="Book it.")
|
||||
self.assertEqual(cmd[cmd.index("-m") + 1], "gpt-5.4")
|
||||
|
||||
def test_the_thinking_setting_lands_on_the_nearest_rung_codex_has(self):
|
||||
self.conf["cleanup_reasoning"] = "xhigh"
|
||||
_, cmd = self.run_cleanup(last_message="Book it.")
|
||||
self.assertIn('model_reasoning_effort="high"', cmd)
|
||||
|
||||
def test_an_answer_of_nothing(self):
|
||||
with self.assertRaises(cleanup.CleanupError):
|
||||
self.run_cleanup(stdout="tokens used 400", last_message="")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user