🏄‍♂️ refactor: Optimize Reasoning UI & Token Streaming (#5546)

*  feat: Implement Show Thinking feature; refactor: testing thinking render optimizations

*  feat: Refactor Thinking component styles and enhance Markdown rendering

* chore: add back removed code, revert type changes

* chore: Add back resetCounter effect to Markdown component for improved code block indexing

* chore: bump @librechat/agents and google langchain packages

* WIP: reasoning type updates

* WIP: first pass, reasoning content blocks

* chore: revert code

* chore: bump @librechat/agents

* refactor: optimize reasoning tag handling

* style: ul indent padding

* feat: add Reasoning component to handle reasoning display

* feat: first pass, content reasoning part styling

* refactor: add content placeholder for endpoints using new stream handler

* refactor: only cache messages when requesting stream audio

* fix: circular dep.

* fix: add default param

* refactor: tts, only request after message stream, fix chrome autoplay

* style: update label for submitting state and add localization for 'Thinking...'

* fix: improve global audio pause logic and reset active run ID

* fix: handle artifact edge cases

* fix: remove unnecessary console log from artifact update test

* feat: add support for continued message handling with new streaming method

---------

Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
This commit is contained in:
Danny Avila 2025-01-29 19:46:58 -05:00 committed by GitHub
parent d60a149ad9
commit 591a019766
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
48 changed files with 1791 additions and 726 deletions

View file

@ -7,15 +7,12 @@ const {
EModelEndpoint,
ErrorTypes,
Constants,
CacheKeys,
Time,
} = require('librechat-data-provider');
const { getMessages, saveMessage, updateMessage, saveConvo } = require('~/models');
const { addSpaceIfNeeded, isEnabled } = require('~/server/utils');
const { truncateToolCallOutputs } = require('./prompts');
const checkBalance = require('~/models/checkBalance');
const { getFiles } = require('~/models/File');
const { getLogStores } = require('~/cache');
const TextStream = require('./TextStream');
const { logger } = require('~/config');
@ -54,6 +51,12 @@ class BaseClient {
this.outputTokensKey = 'completion_tokens';
/** @type {Set<string>} */
this.savedMessageIds = new Set();
/**
* Flag to determine if the client re-submitted the latest assistant message.
* @type {boolean | undefined} */
this.continued;
/** @type {TMessage[]} */
this.currentMessages = [];
}
setOptions() {
@ -589,6 +592,7 @@ class BaseClient {
} else {
latestMessage.text = generation;
}
this.continued = true;
} else {
this.currentMessages.push(userMessage);
}
@ -720,17 +724,6 @@ class BaseClient {
this.responsePromise = this.saveMessageToDatabase(responseMessage, saveOptions, user);
this.savedMessageIds.add(responseMessage.messageId);
if (responseMessage.text) {
const messageCache = getLogStores(CacheKeys.MESSAGES);
messageCache.set(
responseMessageId,
{
text: responseMessage.text,
complete: true,
},
Time.FIVE_MINUTES,
);
}
delete responseMessage.tokenCount;
return responseMessage;
}