chore: README

AGENTS.md

@@ -0,0 +1,26 @@
+# Transui design
+
+- Linux is a GTK3 desktop recorder. It supports hosted transcription with an optional local fallback and can type at the cursor or copy to the clipboard.
+- Android is remote-only. It provides an Android `RecognitionService`, a voice-only input method, and a floating recognition activity. Do not add a local llama.cpp path to Android.
+- Both clients call OpenAI-compatible `/v1/audio/transcriptions` endpoints and clean only the Qwen3-ASR `language …<astext>` or `language …<asr_text>` prefix.
+- The Android voice UI is an opaque, compact system surface. Teal is the recording signal. `PushToTalkButton` draws the Apps and Stop Circle glyphs with Canvas because the target device drops `ImageButton` image layers. Keep the glyphs drawn above the button background.
+
+## llama.cpp local endpoint
+
+The Linux local fallback begins with this multipart request. `response_format=json`
+is required; `prompt` is optional and may request transcription or translation.
+
+```sh
+curl -s -X POST -F response_format=json http://localhost:8080/v1/audio/transcriptions \
+  -F file="@test.mp3" \
+  -F 'prompt=Transcribe the following speech segment in English, and translate them into chinese.'
+```
+
+llama.cpp may return an event envelope instead of a bare OpenAI response:
+
+```json
+{"type":"transcript.text.done","text":"这是个测试。你能听到什么？我希望这很好。","usage":{"type":"tokens","input_tokens":241,"output_tokens":516,"total_tokens":757,"input_tokens_details":{"cached_tokens":0}}}
+```
+
+Use `text` as the transcript. Accept `transcript.text.done`; do not require a
+bare `{ "text": "…" }` response.