Merge pull request #10 from yusufipk/worktree-claude-openai-support

Clean the transcript up on the subscription you already have

README.md

@@ -1,7 +1,7 @@
 # Dikte
 
 Press `Ctrl+Space`, talk, press again. The recording goes to OpenAI or OpenRouter
-for transcription, a model on OpenRouter cleans it up (dropping the *uh*s, the
+for transcription, a model cleans it up (dropping the *uh*s, the
 restarts, the missing punctuation), and the result lands in your clipboard and
 is pasted into whatever window you were typing in.
 
@@ -43,8 +43,8 @@ again and leaves your settings and dictations alone unless you pass `--purge`.
 
 Three keys go in the settings window: **OpenAI**, **Groq** and **OpenRouter**.
 Speech to text runs on any of them (`gpt-4o-transcribe` by default), cleanup
-always on OpenRouter (`google/gemini-3.5-flash-lite`), so a single OpenRouter key
+on OpenRouter (`google/gemini-3.5-flash-lite`) or, when either is installed, on
-can cover both. They fall back to `OPENAI_API_KEY`, `GROQ_API_KEY` and
+Claude Code or Codex instead, so a single OpenRouter key can cover both. They fall back to `OPENAI_API_KEY`, `GROQ_API_KEY` and
 `OPENROUTER_API_KEY`, and are
 stored in `~/.config/dikte/config.json`, mode 600. Cleanup can be switched off,
 in which case the raw transcript is pasted, and a thinking model's effort can be
@@ -148,6 +148,7 @@ audio.py          PCM capture: pw-record for dictation, ffmpeg for a meeting
 meeting.py        channel split, speaker labelling, cleanup, minutes
 assistant.py      running a dictation through Claude Code, Codex or OpenRouter
 api.py            transcription on either provider, OpenRouter cleanup (stdlib only)
+cleanup.py        who rewrites the transcript: OpenRouter, Claude Code or Codex
 worker.py         transcribe → clean up → clipboard → paste
 vad.py            deciding whether a recording holds speech at all
 filetranscribe.py file transcription: ffmpeg, chunking, timestamps

README.tr.md

@@ -1,7 +1,7 @@
 # Dikte
 
 `Ctrl+Space`'e bas, konuş, tekrar bas. Ses OpenAI'ye ya da OpenRouter'a gidip
-yazıya çevrilir, OpenRouter'daki bir model transkripti temizler (ıı'lar,
+yazıya çevrilir, bir model transkripti temizler (ıı'lar,
 tekrarlar, eksik noktalama), sonuç panoya kopyalanır ve o an yazdığın pencereye
 yapıştırılır.
 
@@ -44,8 +44,8 @@ diktelerine dokunmaz.
 
 Ayarlar penceresinde üç anahtar istenir: **OpenAI**, **Groq** ve **OpenRouter**.
 Sesi yazıya çevirme üçünden birinde çalışır (varsayılan `gpt-4o-transcribe`),
-temizleme her zaman OpenRouter'da (`google/gemini-3.5-flash-lite`), yani tek bir
+temizleme OpenRouter'da (`google/gemini-3.5-flash-lite`) ya da kuruluysa Claude
-OpenRouter anahtarı ikisine de yeter. Boş bırakırsan `OPENAI_API_KEY`,
+Code veya Codex'te, yani tek bir OpenRouter anahtarı ikisine de yeter. Boş bırakırsan `OPENAI_API_KEY`,
 `GROQ_API_KEY` ve `OPENROUTER_API_KEY` kullanılır;
 anahtarlar `~/.config/dikte/config.json`
 içinde, izinler 600. Temizlemeyi tamamen kapatabilirsin, o zaman ham transkript
@@ -147,6 +147,7 @@ audio.py          PCM kaydı: diktede pw-record, toplantıda ffmpeg
 meeting.py        kanal ayırma, konuşmacı etiketi, temizleme, tutanak
 assistant.py      dikteyi Claude Code, Codex ya da OpenRouter'dan geçirme
 api.py            iki sağlayıcıda transkript + OpenRouter temizleme (yalnız stdlib)
+cleanup.py        transkripti kim temizler: OpenRouter, Claude Code ya da Codex
 worker.py         transkript → temizleme → pano → yapıştırma
 vad.py            kayıtta gerçekten konuşma var mı kararı
 filetranscribe.py dosyadan transkript: ffmpeg, parçalama, zaman damgaları

assistant.py

@@ -75,7 +75,10 @@ CODEX_ITEMS = {
 CLAUDE_EFFORT = {"none": "low", "minimal": "low", "low": "low",
                  "medium": "medium", "high": "high", "xhigh": "xhigh",
                  "max": "max"}
-CODEX_EFFORT = {"none": "minimal", "minimal": "minimal", "low": "low",
+# "minimal" was Codex's bottom rung until the newer models replaced it with
+# "none", and each of them rejects the other's word for it with a 400. "low" is
+# the one every model has, so the two lowest rungs land there instead.
+CODEX_EFFORT = {"none": "low", "minimal": "low", "low": "low",
                 "medium": "medium", "high": "high", "xhigh": "high",
                 "max": "high"}
 
@@ -421,7 +424,7 @@ def _conclude(found, code, stderr, session, service):
     if code != 0 and not found["answer"]:
         if session and _session_missing(stderr):
             raise _SessionGone()
-        raise AssistantError(_last_line(stderr) or found["failure"] or t(
+        raise AssistantError(last_line(stderr) or found["failure"] or t(
             "{service} exited with code {code}.", service=service, code=code))
     if found["failure"] and not found["answer"]:
         raise AssistantError(found["failure"])
@@ -480,6 +483,11 @@ def _finish(proc):
     return stderr
 
 
-def _last_line(text):
+def last_line(text):
+    """The line worth showing out of a CLI's stderr: the last one it wrote.
+
+    Shared with cleanup, which runs the same two programs for a different job
+    and fails the same way when they are unhappy.
+    """
     lines = [line for line in (text or "").splitlines() if line.strip()]
     return lines[-1].strip() if lines else ""

cleanup.py

@@ -0,0 +1,181 @@
+"""Who rewrites the transcript once it has been heard.
+
+Normally a small model on OpenRouter: one request, a second, a few tenths of a
+cent. A machine with Claude Code or Codex on it is already paying for a model
+though, and the subscription that answers "put that in my calendar on Thursday"
+can just as well take the "eee"s out of a sentence. No second key, no second
+bill. It costs seconds rather than one, because a CLI opens a whole session to
+do it, which is the trade.
+
+Whoever does it, the job is the same one: no tools, no files, no memory of the
+last dictation. There is nothing here to look up and nothing to carry over, and
+a transcript is text from a microphone rather than an instruction, so the less
+the agent can reach while it reads one, the better.
+"""
+
+import os
+import shutil
+import subprocess
+import tempfile
+
+import api
+import assistant
+from i18n import t
+
+PROVIDERS = ("openrouter", "claude", "codex")
+
+
+class CleanupError(api.ApiError):
+    """What a CLI could not do.
+
+    An ApiError because to the chain a cleanup that failed is a cleanup that
+    failed, whichever way it was run, and every caller already catches one and
+    keeps the raw transcript.
+    """
+
+
+def provider(conf):
+    chosen = conf["cleanup_provider"]
+    return chosen if chosen in PROVIDERS else "openrouter"
+
+
+def executable(name):
+    """The CLI a provider runs, or "" when it needs none."""
+    return {"claude": "claude", "codex": "codex"}.get(name, "")
+
+
+def model(conf):
+    """Which model does the cleaning, for the history and the settings window."""
+    name = provider(conf)
+    if name == "claude":
+        return conf["cleanup_claude_model"].strip() or "haiku"
+    if name == "codex":
+        # Codex is left on whatever it is set to unless a model is typed in, so
+        # here there is only the name of the thing that did it.
+        return conf["cleanup_codex_model"].strip() or "codex"
+    return conf["cleanup_model"]
+
+
+def run(text, conf, system_prompt, timeout=180):
+    """Hand the transcript to whoever is set to clean it up."""
+    name = provider(conf)
+    if name == "openrouter":
+        return api.cleanup(
+            text, conf.openrouter_key(), conf["cleanup_model"], system_prompt,
+            reasoning=conf["cleanup_reasoning"],
+            base_url=conf["openrouter_base_url"], timeout=timeout,
+        )
+    runner = _claude if name == "claude" else _codex
+    return runner(text, conf, system_prompt, timeout)
+
+
+def _wrap(text):
+    """The same fence the OpenRouter call puts around it: this is the material,
+    not the instruction, however much of it reads like one."""
+    return f"<transcript>\n{text}\n</transcript>"
+
+
+# --- Claude Code ----------------------------------------------------------
+
+def _claude(text, conf, system_prompt, timeout):
+    cmd = [
+        "claude", "-p", _wrap(text),
+        # --system-prompt rather than --append-system-prompt: the cleanup rules
+        # are the whole job, and Claude Code's own instructions are about
+        # working on a codebase.
+        "--system-prompt", system_prompt,
+        "--model", model(conf),
+        "--output-format", "text",
+        "--tools", "",                                    # nothing to run
+        "--strict-mcp-config", "--mcp-config", '{"mcpServers":{}}',
+        "--no-session-persistence",                       # nothing to resume
+    ]
+    effort = assistant.CLAUDE_EFFORT.get(conf["cleanup_reasoning"], "")
+    if effort:
+        cmd += ["--effort", effort]
+
+    answer = _output(cmd, timeout, "Claude")
+    if not answer:
+        raise CleanupError(t("{service} answered with nothing.", service="Claude"))
+    return answer
+
+
+# --- Codex ----------------------------------------------------------------
+
+def _codex(text, conf, system_prompt, timeout):
+    # Codex takes no system prompt of its own, so the rules ride in front of the
+    # transcript, kept apart from it so the two are not read as one.
+    body = f"{system_prompt}\n\n---\n\n{_wrap(text)}"
+    cmd = [
+        "codex", "exec",
+        "--sandbox", "read-only",          # it has no reason to touch the disk
+        "--skip-git-repo-check",
+        "--ephemeral",                     # nothing to resume
+        "--color", "never",
+        "-c", 'approval_policy="never"',   # there is nobody here to approve
+    ]
+    if conf["cleanup_codex_model"].strip():
+        cmd += ["-m", conf["cleanup_codex_model"].strip()]
+    effort = assistant.CODEX_EFFORT.get(conf["cleanup_reasoning"], "")
+    if effort:
+        cmd += ["-c", f'model_reasoning_effort="{effort}"']
+
+    # `codex exec` prints a header, its thinking and a token count around the
+    # answer; the file it writes on the way out is the answer on its own.
+    handle, last_message = tempfile.mkstemp(prefix="dikte-cleanup-", suffix=".txt")
+    os.close(handle)
+    cmd += ["-o", last_message, body]
+    try:
+        _output(cmd, timeout, "Codex")
+        answer = _read(last_message)
+    finally:
+        try:
+            os.unlink(last_message)
+        except OSError:
+            pass
+
+    if not answer:
+        raise CleanupError(t("{service} answered with nothing.", service="Codex"))
+    return answer
+
+
+def _read(path):
+    try:
+        with open(path, encoding="utf-8", errors="replace") as fh:
+            return fh.read().strip()
+    except OSError:
+        return ""
+
+
+# --- running a CLI --------------------------------------------------------
+
+def _output(cmd, timeout, service):
+    """Run cmd to the end and return what it printed.
+
+    It runs in the home directory rather than wherever the agent is pointed: a
+    project's instructions have opinions about how text should be written, and
+    none of them are about this transcript.
+    """
+    binary = cmd[0]
+    if not shutil.which(binary):
+        raise CleanupError(t(
+            "{binary} not found. Install it, or have OpenRouter clean up "
+            "instead, under Settings → API and models.", binary=binary,
+        ))
+    try:
+        done = subprocess.run(
+            cmd, cwd=os.path.expanduser("~"), stdin=subprocess.DEVNULL,
+            capture_output=True, text=True, encoding="utf-8", errors="replace",
+            timeout=timeout,
+        )
+    except subprocess.TimeoutExpired:
+        raise CleanupError(t("{service} did not finish within {seconds} seconds.",
+                             service=service, seconds=timeout)) from None
+    except OSError as exc:
+        raise CleanupError(t("Could not run {binary}: {error}",
+                             binary=binary, error=exc)) from exc
+    if done.returncode != 0:
+        raise CleanupError(assistant.last_line(done.stderr) or t(
+            "{service} exited with code {code}.",
+            service=service, code=done.returncode))
+    return (done.stdout or "").strip()

cli.py

@@ -25,6 +25,7 @@ from PyQt6.QtCore import QCoreApplication, QTimer
 import api
 import assistant
 import audio
+import cleanup
 import config as cfg
 import filetranscribe
 import hotkey
@@ -764,16 +765,18 @@ def cmd_status(opts):
 def cmd_doctor(opts):
     """What the settings window checks behind its buttons, in one pass."""
     conf = cfg.Config()
-    programs = {name: shutil.which(name) or ""
+    wanted = ["pw-record", "wl-copy", "ydotool", "ffmpeg", "pactl", "kwriteconfig6",
-                for name in ("pw-record", "wl-copy", "ydotool", "ffmpeg",
+              assistant.executable(assistant.provider(conf)) or "claude",
-                             "pactl", "kwriteconfig6",
+              cleanup.executable(cleanup.provider(conf))]
-                             assistant.executable(assistant.provider(conf)) or "claude")}
+    programs = {name: shutil.which(name) or "" for name in wanted if name}
     target = conf.transcribe_target()
+    cleaner = cleanup.provider(conf)
     checks = {
         "programs": programs,
         "transcription": {"provider": target.provider, "model": target.model,
                           "key": bool(target.api_key)},
-        "cleanup": {"enabled": conf["cleanup_enabled"], "model": conf["cleanup_model"],
+        "cleanup": {"enabled": conf["cleanup_enabled"], "provider": cleaner,
+                    "model": cleanup.model(conf),
                     "key": bool(conf.openrouter_key())},
         "agent": {"provider": assistant.provider(conf),
                   "directory": assistant.working_dir(conf)},
@@ -784,8 +787,11 @@ def cmd_doctor(opts):
     lines += [
         f"{'✓' if target.api_key else '✗'} {target.service} key, transcribing on "
         f"{target.model}",
-        f"{'✓' if conf.openrouter_key() else '✗'} OpenRouter key, cleaning up on "
+        # Cleanup on a CLI needs no key, so what is checked is the program.
-        f"{conf['cleanup_model']}",
+        (f"{'✓' if conf.openrouter_key() else '✗'} OpenRouter key, cleaning up on "
+         f"{conf['cleanup_model']}") if cleaner == "openrouter" else
+        (f"{'✓' if programs[cleanup.executable(cleaner)] else '✗'} "
+         f"{cleanup.executable(cleaner)}, cleaning up on {cleanup.model(conf)}"),
         f"{'✓' if checks['running'] else '·'} application "
         + ("running" if checks["running"] else "not running"),
     ]

config.py

@@ -375,7 +375,10 @@ DEFAULTS = {
     "language": "tr",
     "transcribe_prompt": "",
     "cleanup_enabled": True,
+    "cleanup_provider": "openrouter",  # openrouter | claude | codex
     "cleanup_model": "google/gemini-3.5-flash-lite",
+    "cleanup_claude_model": "haiku",   # Claude Code: an alias, or a full model id
+    "cleanup_codex_model": "",         # empty -> whatever Codex is set to
     "cleanup_reasoning": "",        # empty -> whatever the model does by default
     "cleanup_prompt": "",           # empty -> language-specific default
     "auto_paste": True,

filetranscribe.py

@@ -17,6 +17,7 @@ import wave
 from PyQt6.QtCore import QObject, pyqtSignal
 
 import api
+import cleanup
 from i18n import t
 
 CHUNK_SECONDS = 600          # 10 min ≈ 19 MB at 16 kHz mono s16
@@ -130,14 +131,7 @@ class FileTranscriber(QObject):
         out = []
         for block in split_text(text, timestamps):
             self._check()
-            out.append(api.cleanup(
+            out.append(cleanup.run(block, conf, prompt))
-                block,
-                conf.openrouter_key(),
-                conf["cleanup_model"],
-                prompt,
-                reasoning=conf["cleanup_reasoning"],
-                base_url=conf["openrouter_base_url"],
-            ))
         return ("\n" if timestamps else "\n\n").join(out)
 
 

i18n.py

@@ -186,6 +186,18 @@ TR = {
     "Connection works. {count} audio models visible.":
         "Bağlantı tamam. {count} ses modeli görünüyor.",
     "Clean the transcript with a model": "Transkripti bir modelle temizle",
+    "OpenRouter is the quickest and the only one that needs nothing installed. "
+    "Claude Code and Codex clean up on the subscription you already have, "
+    "without a second key, and take a few seconds longer because each one opens "
+    "a session to do it.":
+        "En hızlısı OpenRouter'dır ve kurulu bir program istemeyen tek seçenektir. "
+        "Claude Code ile Codex, temizliği hâlihazırda ödediğin abonelik üzerinden "
+        "yapar, ikinci bir anahtar istemez; her biri bunun için bir oturum açtığından "
+        "birkaç saniye daha uzun sürer.",
+    "{binary} is not on your PATH, so cleanup would fail and the raw transcript "
+    "would be pasted. Install it, or pick another one above.":
+        "{binary} PATH'te değil; temizleme başarısız olur ve ham transkript "
+        "yapıştırılır. Kur ya da yukarıdan başka birini seç.",
     "Thinking": "Düşünme",
     "Model's own default": "Modelin kendi varsayılanı",
     "Off": "Kapalı",
@@ -380,6 +392,14 @@ TR = {
     "It was not allowed to use: {tools}": "Şunları kullanmasına izin yoktu: {tools}",
     "The model returned an empty reply.": "Model boş cevap döndürdü.",
 
+    # --- cleanup, when a CLI does it ----------------------------------------
+    "{binary} not found. Install it, or have OpenRouter clean up instead, "
+    "under Settings → API and models.":
+        "{binary} bulunamadı. Kur ya da Ayarlar → API ve modeller sekmesinden "
+        "temizliği OpenRouter'a bırak.",
+    "{service} did not finish within {seconds} seconds.":
+        "{service} {seconds} saniye içinde bitmedi.",
+
     # --- settings: the agent ------------------------------------------------
     "Agent": "Ajan",
     "This shortcut records the same way dictation does, but the transcript is "

meeting.py

@@ -25,6 +25,7 @@ import wave
 from PyQt6.QtCore import QObject, pyqtSignal
 
 import api
+import cleanup
 import config as cfg
 import filetranscribe
 import vad
@@ -208,14 +209,7 @@ class MeetingPipeline(QObject):
             if len(blocks) > 1:
                 self._say(t("Cleaning up {index}/{count}…",
                             index=index, count=len(blocks)))
-            out.append(api.cleanup(
+            out.append(cleanup.run(block, conf, prompt, timeout=600))
-                block,
-                conf.openrouter_key(),
-                conf["cleanup_model"],
-                prompt,
-                reasoning=conf["cleanup_reasoning"],
-                base_url=conf["openrouter_base_url"],
-            ))
         return "\n".join(out)
 
     def _write(self, doc_path, minutes, transcript, entry):

settings_ui.py

@@ -16,6 +16,7 @@ from PyQt6.QtWidgets import (
 import api
 import assistant
 import audio
+import cleanup
 import config as cfg
 import filetranscribe
 import hotkey
@@ -49,6 +50,15 @@ CLEANUP_MODELS = [
     "google/gemini-2.5-flash-lite", "anthropic/claude-haiku-4.5",
     "openai/gpt-5-mini", "meta-llama/llama-3.3-70b-instruct",
 ]
+# The same two CLIs the agent can run on, doing the smaller job instead. They
+# are offered second: a request to OpenRouter is over in a second, and a CLI
+# opens a session first.
+CLEANUP_PROVIDERS = [
+    ("OpenRouter", "openrouter"), ("Claude Code", "claude"), ("Codex", "codex"),
+]
+# Cleaning up a sentence is the lightest thing either of them will ever be
+# asked, so the small model comes first.
+CLEANUP_CLAUDE_MODELS = ["haiku", "sonnet", "opus", "fable"]
 # Minutes are a harder job than cleanup: an hour of talk has to be read whole
 # and turned into decisions, so the starting points are the larger models.
 MEETING_MODELS = [
@@ -282,16 +292,42 @@ class SettingsWindow(QDialog):
         outer.addWidget(stt)
 
         orr = QGroupBox(t("Transcript cleanup"))
-        orr_form = QFormLayout(orr)
+        orr_form = self.cleanup_form = QFormLayout(orr)
         self.cleanup_enabled = QCheckBox(t("Clean the transcript with a model"))
         orr_form.addRow("", self.cleanup_enabled)
 
+        self.cleanup_provider = QComboBox()
+        for label, value in CLEANUP_PROVIDERS:
+            self.cleanup_provider.addItem(t(label), value)
+        self.cleanup_provider.setToolTip(t(
+            "OpenRouter is the quickest and the only one that needs nothing "
+            "installed. Claude Code and Codex clean up on the subscription you "
+            "already have, without a second key, and take a few seconds longer "
+            "because each one opens a session to do it."
+        ))
+        self.cleanup_provider.currentIndexChanged.connect(self._cleanup_provider_changed)
+        orr_form.addRow(t("Runs on"), self.cleanup_provider)
+
         self.cleanup_model = QComboBox()
         self.cleanup_model.setEditable(True)
         self.cleanup_model.addItems(CLEANUP_MODELS)
         self.refresh_models = QPushButton(t("Fetch model list"))
         self.refresh_models.clicked.connect(self._load_models)
-        orr_form.addRow(t("Model"), self._row(self.cleanup_model, self.refresh_models))
+        self.cleanup_model_row = self._row(self.cleanup_model, self.refresh_models)
+        orr_form.addRow(t("Model"), self.cleanup_model_row)
+
+        # One row per provider rather than one box that means a different thing
+        # in each: an OpenRouter id and a Claude alias do not belong in the same
+        # field, and only the row of whoever is chosen is on screen.
+        self.cleanup_claude_model = QComboBox()
+        self.cleanup_claude_model.setEditable(True)
+        self.cleanup_claude_model.addItems(CLEANUP_CLAUDE_MODELS)
+        orr_form.addRow(t("Model"), self.cleanup_claude_model)
+
+        self.cleanup_codex_model = QComboBox()
+        self.cleanup_codex_model.setEditable(True)
+        self.cleanup_codex_model.addItems([t("Codex's own default")] + CODEX_MODELS)
+        orr_form.addRow(t("Model"), self.cleanup_codex_model)
 
         self.cleanup_reasoning = QComboBox()
         for label, value in REASONING_LEVELS:
@@ -951,6 +987,12 @@ class SettingsWindow(QDialog):
         self._provider_changed()  # selecting index 0 fires no signal
         self.cleanup_enabled.setChecked(conf["cleanup_enabled"])
         self.cleanup_model.setCurrentText(conf["cleanup_model"])
+        self.cleanup_claude_model.setCurrentText(conf["cleanup_claude_model"])
+        self.cleanup_codex_model.setCurrentText(
+            conf["cleanup_codex_model"] or t("Codex's own default")
+        )
+        self._select_data(self.cleanup_provider, conf["cleanup_provider"])
+        self._cleanup_provider_changed()  # selecting index 0 fires no signal
         self._select_data(self.cleanup_reasoning, conf["cleanup_reasoning"])
         self.cleanup_prompt.setPlainText(conf["cleanup_prompt"] or cfg.default_cleanup_prompt())
         self.file_cleanup_prompt.setPlainText(
@@ -1029,7 +1071,14 @@ class SettingsWindow(QDialog):
             conf[who.model] = self._models[name].strip() or cfg.DEFAULTS[who.model]
 
         conf["cleanup_enabled"] = self.cleanup_enabled.isChecked()
+        conf["cleanup_provider"] = self.cleanup_provider.currentData() or "openrouter"
         conf["cleanup_model"] = self.cleanup_model.currentText().strip()
+        conf["cleanup_claude_model"] = (self.cleanup_claude_model.currentText().strip()
+                                        or cfg.DEFAULTS["cleanup_claude_model"])
+        codex_cleanup_model = self.cleanup_codex_model.currentText().strip()
+        conf["cleanup_codex_model"] = (
+            "" if codex_cleanup_model == t("Codex's own default") else codex_cleanup_model
+        )
         conf["cleanup_reasoning"] = self.cleanup_reasoning.currentData() or ""
 
         # Store an empty prompt when it matches the default, so switching the
@@ -1347,6 +1396,27 @@ class SettingsWindow(QDialog):
             else missing
         )
 
+    def _cleanup_provider_changed(self):
+        provider = self.cleanup_provider.currentData() or "openrouter"
+        self.cleanup_form.setRowVisible(self.cleanup_model_row,
+                                        provider == "openrouter")
+        self.cleanup_form.setRowVisible(self.cleanup_claude_model,
+                                        provider == "claude")
+        self.cleanup_form.setRowVisible(self.cleanup_codex_model,
+                                        provider == "codex")
+        binary = cleanup.executable(provider)
+        found = shutil.which(binary) if binary else ""
+        if not binary:
+            self.models_label.setText(t("Runs on OpenRouter."))
+        elif found:
+            self.models_label.setText(t("Found: {path}", path=found))
+        else:
+            self.models_label.setText(t(
+                "{binary} is not on your PATH, so cleanup would fail and the raw "
+                "transcript would be pasted. Install it, or pick another one "
+                "above.", binary=binary,
+            ))
+
     def _assistant_provider_changed(self):
         provider = self.assistant_provider.currentData() or "claude"
         self.claude_box.setVisible(provider == "claude")

tests/test_assistant.py

@@ -79,9 +79,12 @@ class Effort(unittest.TestCase):
         self.assertEqual(assistant.CODEX_EFFORT["xhigh"], "high")
         self.assertEqual(assistant.CODEX_EFFORT["max"], "high")
 
-    def test_claude_has_no_rung_below_low(self):
+    def test_neither_one_asks_for_a_rung_below_low(self):
-        self.assertEqual(assistant.CLAUDE_EFFORT["none"], "low")
+        # Claude has none; Codex has one, but calls it "minimal" on the older
-        self.assertEqual(assistant.CLAUDE_EFFORT["minimal"], "low")
+        # models and "none" on the newer ones, and refuses the wrong word.
+        for scale in (assistant.CLAUDE_EFFORT, assistant.CODEX_EFFORT):
+            self.assertEqual(scale["none"], "low")
+            self.assertEqual(scale["minimal"], "low")
 
     def test_an_empty_setting_asks_for_nothing(self):
         self.assertEqual(assistant.CLAUDE_EFFORT.get("", ""), "")
@@ -232,10 +235,10 @@ class SessionMissing(unittest.TestCase):
                 self.assertFalse(assistant._session_missing(text))
 
     def test_the_last_line_is_the_one_worth_showing(self):
-        self.assertEqual(assistant._last_line("warning\n\nreal error\n"),
+        self.assertEqual(assistant.last_line("warning\n\nreal error\n"),
                          "real error")
-        self.assertEqual(assistant._last_line(""), "")
+        self.assertEqual(assistant.last_line(""), "")
-        self.assertEqual(assistant._last_line(None), "")
+        self.assertEqual(assistant.last_line(None), "")
 
 
 class Conclude(DikteTest):

tests/test_cleanup.py

@@ -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()

tests/test_cli.py

@@ -366,6 +366,34 @@ class Providers(DikteTest):
         self.assertIn("Groq", out)
 
 
+class Doctor(DikteTest):
+    """One pass over everything the settings window checks behind its buttons."""
+
+    def run_doctor(self, as_json=True, **settings):
+        self.write_config(settings)
+        with mock.patch.object(ipc, "send", return_value=None), \
+                captured() as (out, _err):
+            cli.cmd_doctor(Options(json=as_json))
+        return json.loads(out.getvalue()) if as_json else out.getvalue()
+
+    def test_cleanup_on_openrouter_is_a_question_about_the_key(self):
+        reply = self.run_doctor(cleanup_model="some/model")
+        self.assertEqual(reply["cleanup"]["provider"], "openrouter")
+        self.assertEqual(reply["cleanup"]["model"], "some/model")
+        self.assertIn("OpenRouter key, cleaning up on some/model",
+                      self.run_doctor(as_json=False, cleanup_model="some/model"))
+
+    def test_cleanup_on_a_cli_is_a_question_about_the_program(self):
+        reply = self.run_doctor(cleanup_provider="codex",
+                                cleanup_codex_model="gpt-5.4")
+        self.assertEqual(reply["cleanup"]["provider"], "codex")
+        self.assertEqual(reply["cleanup"]["model"], "gpt-5.4")
+        self.assertIn("codex", reply["programs"])
+        self.assertIn("codex, cleaning up on gpt-5.4",
+                      self.run_doctor(as_json=False, cleanup_provider="codex",
+                                      cleanup_codex_model="gpt-5.4"))
+
+
 class Finding(DikteTest):
     def test_no_history_at_all(self):
         self.assertIsNone(cli._find_history("last"))

tests/test_ui.py

@@ -44,7 +44,10 @@ CHANGED = {
     "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.",
@@ -128,6 +131,20 @@ class Settings(DikteTest):
             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,

worker.py

@@ -18,6 +18,7 @@ from PyQt6.QtCore import QObject, pyqtSignal
 import api
 import assistant
 import audio
+import cleanup
 import config as cfg
 import i18n
 import paste
@@ -112,14 +113,7 @@ class Pipeline(QObject):
             if (conf["assistant_cleanup"] if ask else conf["cleanup_enabled"]):
                 self.stage.emit(t("Cleaning up…"))
                 try:
-                    text = api.cleanup(
+                    text = cleanup.run(raw, conf, conf.cleanup_prompt())
-                        raw,
-                        conf.openrouter_key(),
-                        conf["cleanup_model"],
-                        conf.cleanup_prompt(),
-                        reasoning=conf["cleanup_reasoning"],
-                        base_url=conf["openrouter_base_url"],
-                    )
                 except api.ApiError as exc:
                     # Keep the transcript, but never let the failure pass unseen:
                     # a rejected key would otherwise look like working dictation.
@@ -159,7 +153,7 @@ class Pipeline(QObject):
                 "duration": round(duration, 1),
                 "elapsed": round(time.monotonic() - started, 1),
                 "model": target.model,
-                "cleanup_model": conf["cleanup_model"] if conf["cleanup_enabled"] else "",
+                "cleanup_model": cleanup.model(conf) if conf["cleanup_enabled"] else "",
                 "cleanup_error": warning,
                 "mode": "ask" if ask else "",
                 "question": question,