fix(voice): address review of typed AI chat

Typed chat sessions no longer end on the voice inactivity timeout, and a
failed or stopped reply keeps the conversation: Stop cancels only the
reply in progress, and map actions that already ran stay in the model's
context. Each upstream request and map action gets its own deadline, old
tool results shrink instead of the history overflowing, and step limits,
a missing or rejected key, the OAuth lock and throttling each get their
own message.

- Server: OpenAI chat is off under GEV_PREFER_CODEX_OAUTH; chat throttles
  default to the provider's throttle; replies carry API_KEY_MISSING,
  API_KEY_REJECTED, CODEX_OAUTH_REQUIRED and RATE_LIMITED codes; upstream
  Retry-After passes through, and a rejected key (Gemini's invalid-key 400
  included) cools down for a minute
- Pinokio forwards the chat throttle settings
- UI: the reply reveal publishes only the message list; the border orbit
  runs only while busy; layers attach with a button or Enter; the log is
  aria-busy while a reply types out; auto-scroll respects a reader who
  scrolled up; Escape closes the attach menu; the chat gear says Settings;
  a note says chat bills the OpenAI key when voice uses ChatGPT sign-in
- Layout does less work while panel height animates; unused blurs removed
- Gemini voice start ends chat; the voice preview clears on every new
  session
- Tests for the route gates, client limits, attachments and the fixes
This commit is contained in:
manjunath22466 committed 2026-11-03 22:01:08 +05:30
1 parent 11cd0142ac
commit da8b0dd8cd
49 files changed
+2121 -160

No files matched your search

+90
View File
@@ -2,9 +2,13 @@ import assert from 'node:assert/strict';
import test from 'node:test';
import path from 'node:path';
import { fileURLToPath } from 'node:url';
import { readFileSync } from 'node:fs';
import { EventEmitter } from 'node:events';
import { Readable } from 'node:stream';
import { readPinokioEnvironment } from '../scripts/pinokio-environment.mjs';
import { openAiRealtimeProxy } from 'gods-eye-view/server/providers/openai';
import { geminiLiveProxy } from '../server/providers/gemini.js';
import { GEMINI_DEFAULT_PER_MIN } from '../server/providers/gemini/chat.js';
import {
makeCostRateLimiter,
resolvePerMinuteCap,
@@ -168,6 +172,92 @@ test('the realtime token route throttles by default, and says so in a 429', asyn
);
});
function chatRequest(handler, input) {
const req = Readable.from([Buffer.from(JSON.stringify(input))]);
Object.assign(req, {
method: 'POST',
url: '/',
headers: {
host: 'localhost:4173',
origin: 'http://localhost:4173',
'content-type': 'application/json',
},
socket: { remoteAddress: '127.0.0.1' },
});
const headers = {};
const res = Object.assign(new EventEmitter(), {
statusCode: 200,
setHeader(name, value) {
headers[name.toLowerCase()] = value;
},
});
return new Promise((resolve, reject) => {
res.end = (body = '') => {
res.writableEnded = true;
resolve({ status: res.statusCode, headers, body: String(body) });
};
Promise.resolve(handler(req, res)).catch(reject);
});
}
test('typed chat follows each provider throttle by default, before upstream', async (t) => {
for (const name of [
'GEV_RATELIMIT_OPENAI_CHAT_PER_MIN',
'GEV_RATELIMIT_OPENAI_PER_MIN',
'GEV_RATELIMIT_GEMINI_CHAT_PER_MIN',
'GEV_RATELIMIT_GEMINI_PER_MIN',
'GEV_PREFER_CODEX_OAUTH',
])
env(t, name, undefined);
env(t, 'OPENAI_API_KEY', 'fixture-upstream-secret');
env(t, 'GEMINI_API_KEY', 'fixture-upstream-secret');
let upstreamCalls = 0;
t.mock.method(globalThis, 'fetch', async (url) => {
upstreamCalls += 1;
return Response.json(
String(url).includes('openai')
? { choices: [{ message: { role: 'assistant', content: 'Hi' } }] }
: {
candidates: [
{ content: { role: 'model', parts: [{ text: 'Hi' }] } },
],
},
);
});
// The chat fallback must track the Gemini token route's own default.
const tokenDefault = readFileSync(
new URL('../server/providers/gemini/realtime.js', import.meta.url),
'utf8',
).match(/GEV_RATELIMIT_GEMINI_PER_MIN \?\? '(\d+)'/)?.[1];
assert.equal(Number(tokenDefault), GEMINI_DEFAULT_PER_MIN);
for (const [route, handler, cap, input] of [
[
'/api/openai/chat',
install(openAiRealtimeProxy({})).get('/api/openai/chat'),
OPENAI_DEFAULT_PER_MIN,
{ messages: [{ role: 'user', content: 'Hello' }] },
],
[
'/api/gemini/chat',
install(geminiLiveProxy({})).get('/api/gemini/chat'),
GEMINI_DEFAULT_PER_MIN,
{ contents: [{ role: 'user', parts: [{ text: 'Hello' }] }] },
],
]) {
upstreamCalls = 0;
const statuses = [];
for (let i = 0; i < cap; i += 1)
statuses.push((await chatRequest(handler, input)).status);
assert.deepEqual(statuses, Array(cap).fill(200), route);
const overLimit = await chatRequest(handler, input);
assert.equal(overLimit.status, 429, route);
assert.equal(overLimit.headers['retry-after'], '60');
assert.equal(overLimit.body.includes('fixture-upstream-secret'), false);
assert.equal(upstreamCalls, cap, `${route} refuses before upstream`);
}
});
test('the HUD summary route throttles the paid path, never the free one', async (t) => {
env(t, 'OPENAI_API_KEY', 'fixture-upstream-secret');
let upstreamCalls = 0;