Let the command go to Codex or OpenRouter, not only Claude Code

Everything the last commit built assumed one agent was installed, which is a
poor assumption to bake into a dictation tool. So the provider is a setting, and
what it selects is one of three quite different things.

Claude Code and Codex are the same shape: a CLI, streaming JSONL, a session id
to resume, tools that reach the machine and whatever is connected to it. They
share the runner. What differs is spelled out where it differs, which is more
than the flag names: Codex has no system prompt to append, so the instruction
rides in front of the command with a rule between them; it confines its commands
in a sandbox rather than asking about them, so the permission setting is a
sandbox mode; and `-s` is not accepted by `exec resume`, so both settings go
through `-c` overrides, which are.

OpenRouter is the odd one and is meant to be. No tools, no files, no calendar:
it can say what the capital of Peru is and not what is in your diary, and the
settings box says so rather than letting it be discovered. It also has no
session to resume, so the conversation is kept here and resent, capped at 24
messages.

A stored conversation names the provider that made it, and is ignored by any
other: none of them can pick up another's thread, and a stale id would otherwise
fail every command until the timeout cleared it.

The interface calls the thing by its name, which in Turkish means the suffix has
to agree with it: Claude'a but Codex'e, Claude'u but Codex'i. A name dropped
into a sentence through t() cannot be inflected by that sentence, so it arrives
inflected, from a small table in i18n. English takes the name as it is and keeps
the preposition in the sentence.
This commit is contained in:
yusufipk
2026-07-28 17:08:14 +07:00
parent 0206303751
commit 01eea7a363
9 changed files with 527 additions and 179 deletions
+6 -4
View File
@@ -87,9 +87,11 @@ elapsed time, then the stage it is on. It never takes focus. Pressing
what comes of it: the answer, or a sentence saying what was done. It is the
session you would have opened yourself, so your skills and connected services
are there, which is what makes "put that in my calendar on Thursday at three"
a thing you can say to a window that is not Claude. Model, permissions and
working directory are under Settings → Claude, and commands close together
stay in one conversation.
a thing you can say to a window that is not Claude. Codex (`codex exec`) runs
the same way, and OpenRouter is there as a plain question-and-answer fallback
for a machine with neither CLI on it. Provider, model, permissions and working
directory are under Settings → Claude, and commands close together stay in one
conversation.
- **Meetings** are recorded from the microphone and the speaker output at the
same time, which settles who said what by the channel a voice arrived on
instead of guessing at it. The two sides are transcribed separately and
@@ -121,7 +123,7 @@ needs your user in the `input` group: `sudo usermod -aG input $USER`.
dikte.py entry point, tray icon, state machine, IPC
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 and reading it back
assistant.py running a dictation through Claude Code, Codex or OpenRouter
api.py transcription on either provider, OpenRouter cleanup (stdlib only)
worker.py transcribe → clean up → clipboard → paste
vad.py deciding whether a recording holds speech at all