feat(voice): add typed AI chat beside voice

Chat sits next to the mic in the command dock. Replies are silent and never
request the microphone; the first message connects with the selected provider
and runs the same map actions as voice through each provider's text API
(OpenAI OPENAI_CHAT_MODEL, Gemini GEMINI_CHAT_MODEL via generateContent, which
never starts Live). Only one mode runs at a time.

- Chat panel rendered by the voice control presenter: conversation, recent and
  quick-command suggestions, Up/Down history, attachments (map-layer
  references or small UTF-8 text files, sent only with the message)
- Chat and voice panels sit above the dock or dock into the right rail's
  column; minimized bars sit centred above the dock, and height animates on
  swaps
- A centred panel steps down to its bar for the Location and Visual Presets
  trays without moving focus, rests above an open tray, and docks right while
  expanded over one; it returns to the centre once the trays close
- Minimized voice previews the last sentence from each side; the empty Voice
  Preview suggests things to say
- Settings opened from chat keep chat's frame and show the shared AI provider
  and quick commands; voice Settings show Back to voice
- Closing chat ends a typed session; the voice panel's close turns voice off
- The dock widens its voice control for the chat button and restyles its
  wings, which show icons only at 900px and below; assistant panels share the
  left panels' glass, and Cyber keeps its own surfaces
- Server text-chat handlers with body, time and per-IP limits
  (GEV_RATELIMIT_*_CHAT_PER_MIN), documented in SECURITY.md; tests and all
  eleven locales

Co-authored-by: Darren Dignam <[email protected]>
This commit is contained in:
manjunath22466andDarren Dignam committed 2026-11-02 20:56:39 +05:30
1 parent 720260af58
commit af461febae
57 files changed
+6500 -63

No files matched your search

+68
View File
@@ -0,0 +1,68 @@
import { getLocale } from '../i18n/index.js';
const segmenters = new Map();
const segmenter = (locale) => {
if (!segmenters.has(locale))
segmenters.set(
locale,
new Intl.Segmenter(locale, { granularity: 'sentence' }),
);
return segmenters.get(locale);
};
/** The final sentence of a transcript, split by the active locale's rules. */
export function lastSentence(text, locale = getLocale()) {
const clean = String(text ?? '')
.replace(/\s+/g, ' ')
.trim();
if (!clean) return '';
let parts;
try {
parts = [...segmenter(locale).segment(clean)].map((part) =>
part.segment.trim(),
);
} catch {
parts = clean.split(/(?<=[.!?。!?])\s+/);
}
return parts.filter(Boolean).at(-1) ?? clean;
}
/**
* Keep the minimized voice bar's preview: the last spoken sentence from the
* user and from the assistant. Typed chat turns belong to the chat panel.
* Once either side has spoken, the root marks the exchange so the empty
* preview's "Try saying" hints step aside until the next session.
*/
export function bindVoiceMiniPreview({ ui, session }) {
let assistant = '';
let response = null;
const sentences = { user: '', assistant: '' };
const show = (role, text) => {
sentences[role] = lastSentence(text);
ui.update('mini', { [role]: sentences[role] });
const spoken = Boolean(sentences.user || sentences.assistant);
if (ui.state.root.voiceExchange !== spoken)
ui.update('root', { voiceExchange: spoken });
};
const clear = () => {
assistant = '';
response = null;
show('user', '');
show('assistant', '');
};
clear();
return session.subscribe((event) => {
if (session.adapter?.getStartOptions?.().textOnly) return;
if (event.type === 'state' && event.state === 'connecting') clear();
if (event.type !== 'transcript' || !event.text) return;
if (event.role === 'user') show('user', event.text);
if (event.role !== 'assistant') return;
const id = event.responseId || null;
// Deltas accumulate per response; a final transcript replaces them.
assistant = event.final
? event.text
: `${id === response ? assistant : ''}${event.text}`;
response = id;
show('assistant', assistant);
});
}