Files
gods-eye-view/server/providers/gemini/chat.js
T
manjunath22466andDarren Dignam af461febae 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]>
2026-11-02 20:56:39 +05:30

173 lines
5.4 KiB
JavaScript

import { createTextChatHandler } from '../common/textChat.js';
import { invalidCalls } from '../common/textTools.js';
import { textInstructions } from '../common/textInstructions.js';
import { GEV_REALTIME_TOOLS } from '../openai/tools.js';
import { normalizeGeminiModel } from './config.js';
const object = (value) =>
value && typeof value === 'object' && !Array.isArray(value);
const keys = (value, allowed) =>
Object.keys(value).every((key) => allowed.includes(key));
// Only text and function exchanges may cross this route, never media or config.
export function validChatContents(contents, names) {
return (
Array.isArray(contents) &&
contents.length > 0 &&
contents.length <= 96 &&
contents.every(
(content) =>
object(content) &&
keys(content, ['role', 'parts']) &&
['user', 'model'].includes(content.role) &&
Array.isArray(content.parts) &&
content.parts.length > 0 &&
content.parts.length <= 32 &&
content.parts.every((part) => {
if (
!object(part) ||
!keys(part, [
'text',
'functionCall',
'functionResponse',
'thoughtSignature',
])
)
return false;
if (
part.thoughtSignature !== undefined &&
(typeof part.thoughtSignature !== 'string' ||
part.thoughtSignature.length > 32000 ||
content.role !== 'model')
)
return false;
if (Object.hasOwn(part, 'text'))
return (
keys(part, ['text', 'thoughtSignature']) &&
typeof part.text === 'string'
);
const call = part.functionCall ?? part.functionResponse;
if (
!object(call) ||
typeof call.name !== 'string' ||
call.name.length > 128 ||
(names && !names.has(call.name)) ||
(call.id !== undefined &&
(typeof call.id !== 'string' || call.id.length > 1024))
)
return false;
if (part.functionCall)
return (
content.role === 'model' &&
keys(part, ['functionCall', 'thoughtSignature']) &&
keys(call, ['name', 'args', 'id']) &&
(call.args === null || object(call.args ?? {}))
);
return (
content.role === 'user' &&
keys(part, ['functionResponse']) &&
keys(call, ['name', 'response', 'id']) &&
object(call.response)
);
}),
)
);
}
export function createGeminiChatHandler({
annotationGuidance,
tools = GEV_REALTIME_TOOLS,
resolveChatModel = () =>
process.env.GEMINI_CHAT_MODEL || 'gemini-3.5-flash-lite',
resolveApiKey = () => process.env.GEMINI_API_KEY,
...options
} = {}) {
return createTextChatHandler({
...options,
provider: 'gemini',
resolveApiKey,
prepare(input) {
const model = normalizeGeminiModel(resolveChatModel());
if (!model || /live|audio|tts/i.test(model)) return { errorStatus: 503 };
if (
!object(input) ||
!keys(input, ['contents']) ||
!validChatContents(input.contents, null)
)
return null;
if (!pairedContents(input.contents)) return null;
return {
endpoint: `https://generativelanguage.googleapis.com/v1beta/models/${model}:generateContent`,
headers: (key) => ({ 'x-goog-api-key': key }),
body: {
contents: input.contents,
systemInstruction: {
parts: [{ text: textInstructions(annotationGuidance) }],
},
tools: [
{
functionDeclarations: tools.map(
({ name, description, parameters }) => ({
name,
description,
parametersJsonSchema: parameters,
}),
),
},
],
generationConfig: {
responseModalities: ['TEXT'],
maxOutputTokens: 4096,
thinkingConfig: { thinkingLevel: 'LOW' },
},
},
};
},
parse(data) {
const candidate = data?.candidates?.[0];
const content = candidate?.content;
if (
!content ||
!validChatContents([content], null) ||
content.role !== 'model'
)
return null;
const calls = content.parts
.filter((part) => part.functionCall)
.map((part) => part.functionCall);
return {
content,
finishReason: candidate.finishReason,
invalidCalls: invalidCalls(calls, tools),
};
},
});
}
// Never forward an orphan result or an unfinished batch in browser history.
function pairedContents(contents) {
let pending = [];
for (const content of contents) {
const calls = content.parts
.filter((part) => part.functionCall)
.map((part) => part.functionCall);
const results = content.parts
.filter((part) => part.functionResponse)
.map((part) => part.functionResponse);
if (pending.length) {
if (
calls.length ||
results.length !== pending.length ||
results.some(
(result, i) =>
result.name !== pending[i].name || result.id !== pending[i].id,
)
)
return false;
pending = [];
} else if (results.length) return false;
if (calls.length) pending = calls;
}
return !pending.length;
}