LibreChat/client/src/components/Nav/SettingsTabs/Speech/Speech.tsx
Marco Beretta 650e9b4f6c
📜 refactor: Optimize Conversation History Nav with Cursor Pagination (#5785)
*  feat: improve Nav/Conversations/Convo/NewChat component performance

*  feat: implement cursor-based pagination for conversations API

* 🔧 refactor: remove createdAt from conversation selection in API and type definitions

* 🔧 refactor: include createdAt in conversation selection and update related types

*  fix: search functionality and bugs with loadMoreConversations

* feat: move ArchivedChats to cursor and DataTable standard

* 🔧 refactor: add InfiniteQueryObserverResult type import in Nav component

* feat: enhance conversation listing with pagination, sorting, and search capabilities

* 🔧 refactor: remove unnecessary comment regarding lodash/debounce in ArchivedChatsTable

* 🔧 refactor: remove unused translation keys for archived chats and search results

* 🔧 fix: Archived Chats, Delete Convo, Duplicate Convo

* 🔧 refactor: improve conversation components with layout adjustments and new translations

* 🔧 refactor: simplify archive conversation mutation and improve unarchive handling; fix: update fork mutation

* 🔧 refactor: decode search query parameter in conversation route; improve error handling in unarchive mutation; clean up DataTable component styles

* 🔧 refactor: remove unused translation key for empty archived chats

* 🚀 fix: `archivedConversation` query key not updated correctly while archiving

* 🧠 feat: Bedrock Anthropic Reasoning & Update Endpoint Handling (#6163)

* feat: Add thinking and thinkingBudget parameters for Bedrock Anthropic models

* chore: Update @librechat/agents to version 2.1.8

* refactor: change region order in params

* refactor: Add maxTokens parameter to conversation preset schema

* refactor: Update agent client to use bedrockInputSchema and improve error handling for model parameters

* refactor: streamline/optimize llmConfig initialization and saving for bedrock

* fix: ensure config titleModel is used for all endpoints

* refactor: enhance OpenAIClient and agent initialization to support endpoint checks for OpenRouter

* chore: bump @google/generative-ai

*  feat: improve Nav/Conversations/Convo/NewChat component performance

* 🔧 refactor: remove unnecessary comment regarding lodash/debounce in ArchivedChatsTable

* 🔧 refactor: update translation keys for clarity; simplify conversation query parameters and improve sorting functionality in SharedLinks component

* 🔧 refactor: optimize conversation loading logic and improve search handling in Nav component

* fix: package-lock

* fix: package-lock 2

* fix: package lock 3

* refactor: remove unused utility files and exports to clean up the codebase

* refactor: remove i18n and useAuthRedirect modules to streamline codebase

* refactor: optimize Conversations component and remove unused ToggleContext

* refactor(Convo): add RenameForm and ConvoLink components; enhance Conversations component with responsive design

* fix: add missing @azure/storage-blob dependency in package.json

* refactor(Search): add error handling with toast notification for search errors

* refactor: make createdAt and updatedAt fields of tConvoUpdateSchema less restrictive if timestamps are missing

* chore: update @azure/storage-blob dependency to version 12.27.0, ensure package-lock is correct

* refactor(Search): improve conversation handling server side

* fix: eslint warning and errors

* refactor(Search): improved search loading state and overall UX

* Refactors conversation cache management

Centralizes conversation mutation logic into dedicated utility functions for adding, updating, and removing conversations from query caches.

Improves reliability and maintainability by:
- Consolidating duplicate cache manipulation code
- Adding type safety for infinite query data structures
- Implementing consistent cache update patterns across all conversation operations
- Removing obsolete conversation helper functions in favor of standardized utilities

* fix: conversation handling and SSE event processing

- Optimizes conversation state management with useMemo and proper hook ordering
- Improves SSE event handler documentation and error handling
- Adds reset guard flag for conversation changes
- Removes redundant navigation call
- Cleans up cursor handling logic and document structure

Improves code maintainability and prevents potential race conditions in conversation state updates

* refactor: add type for SearchBar `onChange`

* fix: type tags

* style: rounded to xl all Header buttons

* fix: activeConvo in Convo not working

* style(Bookmarks): improved UI

* a11y(AccountSettings): fixed hover style not visible when using light theme

* style(SettingsTabs): improved tab switchers and dropdowns

* feat: add translations keys for Speech

* chore: fix package-lock

* fix(mutations): legacy import after rebase

* feat: refactor conversation navigation for accessibility

* fix(search): convo and message create/update date not returned

* fix(search): show correct iconURL and endpoint for searched messages

* fix: small UI improvements

* chore: console.log cleanup

* chore: fix tests

* fix(ChatForm): improve conversation ID handling and clean up useMemo dependencies

* chore: improve typing

* chore: improve typing

* fix(useSSE): clear conversation ID on submission to prevent draft restoration

* refactor(OpenAIClient): clean up abort handler

* refactor(abortMiddleware): change handleAbort to use function expression

* feat: add PENDING_CONVO constant and update conversation ID checks

* fix: final event handling on abort

* fix: improve title sync and query cache sync on final event

* fix: prevent overwriting cached conversation data if it already exists

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-04-15 04:04:00 -04:00

235 lines
8.6 KiB
TypeScript

import { useRecoilState } from 'recoil';
import * as Tabs from '@radix-ui/react-tabs';
import { Lightbulb, Cog } from 'lucide-react';
import React, { useState, useRef, useEffect, useCallback } from 'react';
import { useGetCustomConfigSpeechQuery } from 'librechat-data-provider/react-query';
import {
CloudBrowserVoicesSwitch,
AutomaticPlaybackSwitch,
TextToSpeechSwitch,
EngineTTSDropdown,
CacheTTSSwitch,
VoiceDropdown,
PlaybackRate,
} from './TTS';
import {
AutoTranscribeAudioSwitch,
LanguageSTTDropdown,
SpeechToTextSwitch,
AutoSendTextSelector,
EngineSTTDropdown,
DecibelSelector,
} from './STT';
import { useOnClickOutside, useMediaQuery, useLocalize } from '~/hooks';
import ConversationModeSwitch from './ConversationModeSwitch';
import { cn, logger } from '~/utils';
import store from '~/store';
function Speech() {
const localize = useLocalize();
const [confirmClear, setConfirmClear] = useState(false);
const { data } = useGetCustomConfigSpeechQuery();
const isSmallScreen = useMediaQuery('(max-width: 767px)');
const [sttExternal, setSttExternal] = useState(false);
const [ttsExternal, setTtsExternal] = useState(false);
const [advancedMode, setAdvancedMode] = useRecoilState(store.advancedMode);
const [autoTranscribeAudio, setAutoTranscribeAudio] = useRecoilState(store.autoTranscribeAudio);
const [conversationMode, setConversationMode] = useRecoilState(store.conversationMode);
const [speechToText, setSpeechToText] = useRecoilState(store.speechToText);
const [textToSpeech, setTextToSpeech] = useRecoilState(store.textToSpeech);
const [cacheTTS, setCacheTTS] = useRecoilState(store.cacheTTS);
const [engineSTT, setEngineSTT] = useRecoilState<string>(store.engineSTT);
const [languageSTT, setLanguageSTT] = useRecoilState<string>(store.languageSTT);
const [decibelValue, setDecibelValue] = useRecoilState(store.decibelValue);
const [autoSendText, setAutoSendText] = useRecoilState(store.autoSendText);
const [engineTTS, setEngineTTS] = useRecoilState<string>(store.engineTTS);
const [voice, setVoice] = useRecoilState(store.voice);
const [cloudBrowserVoices, setCloudBrowserVoices] = useRecoilState<boolean>(
store.cloudBrowserVoices,
);
const [languageTTS, setLanguageTTS] = useRecoilState<string>(store.languageTTS);
const [automaticPlayback, setAutomaticPlayback] = useRecoilState(store.automaticPlayback);
const [playbackRate, setPlaybackRate] = useRecoilState(store.playbackRate);
const updateSetting = useCallback(
(key: string, newValue: string | number) => {
const settings = {
sttExternal: { value: sttExternal, setFunc: setSttExternal },
ttsExternal: { value: ttsExternal, setFunc: setTtsExternal },
conversationMode: { value: conversationMode, setFunc: setConversationMode },
advancedMode: { value: advancedMode, setFunc: setAdvancedMode },
speechToText: { value: speechToText, setFunc: setSpeechToText },
textToSpeech: { value: textToSpeech, setFunc: setTextToSpeech },
cacheTTS: { value: cacheTTS, setFunc: setCacheTTS },
engineSTT: { value: engineSTT, setFunc: setEngineSTT },
languageSTT: { value: languageSTT, setFunc: setLanguageSTT },
autoTranscribeAudio: { value: autoTranscribeAudio, setFunc: setAutoTranscribeAudio },
decibelValue: { value: decibelValue, setFunc: setDecibelValue },
autoSendText: { value: autoSendText, setFunc: setAutoSendText },
engineTTS: { value: engineTTS, setFunc: setEngineTTS },
voice: { value: voice, setFunc: setVoice },
cloudBrowserVoices: { value: cloudBrowserVoices, setFunc: setCloudBrowserVoices },
languageTTS: { value: languageTTS, setFunc: setLanguageTTS },
automaticPlayback: { value: automaticPlayback, setFunc: setAutomaticPlayback },
playbackRate: { value: playbackRate, setFunc: setPlaybackRate },
};
if (
(settings[key].value !== newValue || settings[key].value === newValue || !settings[key]) &&
settings[key].value === 'sttExternal' &&
settings[key].value === 'ttsExternal'
) {
return;
}
const setting = settings[key];
setting.setFunc(newValue);
},
[
sttExternal,
ttsExternal,
conversationMode,
advancedMode,
speechToText,
textToSpeech,
cacheTTS,
engineSTT,
languageSTT,
autoTranscribeAudio,
decibelValue,
autoSendText,
engineTTS,
voice,
cloudBrowserVoices,
languageTTS,
automaticPlayback,
playbackRate,
setSttExternal,
setTtsExternal,
setConversationMode,
setAdvancedMode,
setSpeechToText,
setTextToSpeech,
setCacheTTS,
setEngineSTT,
setLanguageSTT,
setAutoTranscribeAudio,
setDecibelValue,
setAutoSendText,
setEngineTTS,
setVoice,
setCloudBrowserVoices,
setLanguageTTS,
setAutomaticPlayback,
setPlaybackRate,
],
);
useEffect(() => {
if (data && data.message !== 'not_found') {
Object.entries(data).forEach(([key, value]) => {
updateSetting(key, value);
});
}
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [data]);
logger.log({ sttExternal, ttsExternal });
const contentRef = useRef(null);
useOnClickOutside(contentRef, () => confirmClear && setConfirmClear(false), []);
return (
<Tabs.Root
defaultValue={'simple'}
orientation="horizontal"
value={advancedMode ? 'advanced' : 'simple'}
>
<div className="sticky -top-1 z-50 mb-4 bg-white dark:bg-gray-700">
<Tabs.List className="flex justify-center bg-background">
<Tabs.Trigger
onClick={() => setAdvancedMode(false)}
className={cn(
'group m-1 flex items-center justify-center gap-2 bg-transparent px-4 py-2 text-sm text-text-secondary transition-all duration-200 ease-in-out radix-state-active:bg-secondary radix-state-active:text-foreground radix-state-active:shadow-lg',
isSmallScreen ? 'flex-row rounded-lg' : 'rounded-xl',
'w-full',
)}
value="simple"
style={{ userSelect: 'none' }}
>
<Lightbulb />
{localize('com_ui_simple')}
</Tabs.Trigger>
<Tabs.Trigger
onClick={() => setAdvancedMode(true)}
className={cn(
'group m-1 flex items-center justify-center gap-2 bg-transparent px-4 py-2 text-sm text-text-secondary transition-all duration-200 ease-in-out radix-state-active:bg-secondary radix-state-active:text-foreground radix-state-active:shadow-lg',
isSmallScreen ? 'flex-row rounded-lg' : 'rounded-xl',
'w-full',
)}
value="advanced"
style={{ userSelect: 'none' }}
>
<Cog />
{localize('com_ui_advanced')}
</Tabs.Trigger>
</Tabs.List>
</div>
<Tabs.Content value={'simple'}>
<div className="flex flex-col gap-3 text-sm text-text-primary">
<SpeechToTextSwitch />
<EngineSTTDropdown external={sttExternal} />
<LanguageSTTDropdown />
<div className="h-px bg-border-medium" role="none" />
<TextToSpeechSwitch />
<EngineTTSDropdown external={ttsExternal} />
<VoiceDropdown />
</div>
</Tabs.Content>
<Tabs.Content value={'advanced'}>
<div className="flex flex-col gap-3 text-sm text-text-primary">
<ConversationModeSwitch />
<div className="mt-2 h-px bg-border-medium" role="none" />
<SpeechToTextSwitch />
<EngineSTTDropdown external={sttExternal} />
<LanguageSTTDropdown />
<div className="pb-2">
<AutoTranscribeAudioSwitch />
</div>
{autoTranscribeAudio && (
<div className="pb-2">
<DecibelSelector />
</div>
)}
<div className="pb-2">
<AutoSendTextSelector />
</div>
<div className="h-px bg-border-medium" role="none" />
<div className="pb-3">
<TextToSpeechSwitch />
</div>
<AutomaticPlaybackSwitch />
<EngineTTSDropdown external={ttsExternal} />
<VoiceDropdown />
{engineTTS === 'browser' && (
<div className="pb-2">
<CloudBrowserVoicesSwitch />
</div>
)}
<div className="pb-2">
<PlaybackRate />
</div>
<CacheTTSSwitch />
</div>
</Tabs.Content>
</Tabs.Root>
);
}
export default React.memo(Speech);