mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-17 08:50:15 +01:00
* refactor: pass model in message edit payload, use encoder in standalone util function * feat: add summaryBuffer helper * refactor(api/messages): use new countTokens helper and add auth middleware at top * wip: ConversationSummaryBufferMemory * refactor: move pre-generation helpers to prompts dir * chore: remove console log * chore: remove test as payload will no longer carry tokenCount * chore: update getMessagesWithinTokenLimit JSDoc * refactor: optimize getMessagesForConversation and also break on summary, feat(ci): getMessagesForConversation tests * refactor(getMessagesForConvo): count '00000000-0000-0000-0000-000000000000' as root message * chore: add newer model to token map * fix: condition was point to prop of array instead of message prop * refactor(BaseClient): use object for refineMessages param, rename 'summary' to 'summaryMessage', add previous_summary refactor(getMessagesWithinTokenLimit): replace text and tokenCount if should summarize, summary, and summaryTokenCount are present fix/refactor(handleContextStrategy): use the right comparison length for context diff, and replace payload first message when a summary is present * chore: log previous_summary if debugging * refactor(formatMessage): assume if role is defined that it's a valid value * refactor(getMessagesWithinTokenLimit): remove summary logic refactor(handleContextStrategy): add usePrevSummary logic in case only summary was pruned refactor(loadHistory): initial message query will return all ordered messages but keep track of the latest summary refactor(getMessagesForConversation): use object for single param, edit jsdoc, edit all files using the method refactor(ChatGPTClient): order messages before buildPrompt is called, TODO: add convoSumBuffMemory logic * fix: undefined handling and summarizing only when shouldRefineContext is true * chore(BaseClient): fix test results omitting system role for summaries and test edge case * chore: export summaryBuffer from index file * refactor(OpenAIClient/BaseClient): move refineMessages to subclass, implement LLM initialization for summaryBuffer * feat: add OPENAI_SUMMARIZE to enable summarizing, refactor: rename client prop 'shouldRefineContext' to 'shouldSummarize', change contextStrategy value to 'summarize' from 'refine' * refactor: rename refineMessages method to summarizeMessages for clarity * chore: clarify summary future intent in .env.example * refactor(initializeLLM): handle case for either 'model' or 'modelName' being passed * feat(gptPlugins): enable summarization for plugins * refactor(gptPlugins): utilize new initializeLLM method and formatting methods for messages, use payload array for currentMessages and assign pastMessages sooner * refactor(agents): use ConversationSummaryBufferMemory for both agent types * refactor(formatMessage): optimize original method for langchain, add helper function for langchain messages, add JSDocs and tests * refactor(summaryBuffer): add helper to createSummaryBufferMemory, and use new formatting helpers * fix: forgot to spread formatMessages also took opportunity to pluralize filename * refactor: pass memory to tools, namely openapi specs. not used and may never be used by new method but added for testing * ci(formatMessages): add more exhaustive checks for langchain messages * feat: add debug env var for OpenAI * chore: delete unnecessary comments * chore: add extra note about summary feature * fix: remove tokenCount from payload instructions * fix: test fail * fix: only pass instructions to payload when defined or not empty object * refactor: fromPromptMessages is deprecated, use renamed method fromMessages * refactor: use 'includes' instead of 'startsWith' for extended OpenRouter compatibility * fix(PluginsClient.buildPromptBody): handle undefined message strings * chore: log langchain titling error * feat: getModelMaxTokens helper * feat: tokenSplit helper * feat: summary prompts updated * fix: optimize _CUT_OFF_SUMMARIZER prompt * refactor(summaryBuffer): use custom summary prompt, allow prompt to be passed, pass humanPrefix and aiPrefix to memory, along with any future variables, rename messagesToRefine to context * fix(summaryBuffer): handle edge case where messagesToRefine exceeds summary context, refactor(BaseClient): allow custom maxContextTokens to be passed to getMessagesWithinTokenLimit, add defined check before unshifting summaryMessage, update shouldSummarize based on this refactor(OpenAIClient): use getModelMaxTokens, use cut-off message method for summary if no messages were left after pruning * fix(handleContextStrategy): handle case where incoming prompt is bigger than model context * chore: rename refinedContent to splitText * chore: remove unnecessary debug log
147 lines
4.4 KiB
JavaScript
147 lines
4.4 KiB
JavaScript
const { HumanChatMessage, AIChatMessage } = require('langchain/schema');
|
|
const PluginsClient = require('../PluginsClient');
|
|
const crypto = require('crypto');
|
|
|
|
jest.mock('../../../lib/db/connectDb');
|
|
jest.mock('../../../models/Conversation', () => {
|
|
return function () {
|
|
return {
|
|
save: jest.fn(),
|
|
deleteConvos: jest.fn(),
|
|
};
|
|
};
|
|
});
|
|
|
|
describe('PluginsClient', () => {
|
|
let TestAgent;
|
|
let options = {
|
|
tools: [],
|
|
modelOptions: {
|
|
model: 'gpt-3.5-turbo',
|
|
temperature: 0,
|
|
max_tokens: 2,
|
|
},
|
|
agentOptions: {
|
|
model: 'gpt-3.5-turbo',
|
|
},
|
|
};
|
|
let parentMessageId;
|
|
let conversationId;
|
|
const fakeMessages = [];
|
|
const userMessage = 'Hello, ChatGPT!';
|
|
const apiKey = 'fake-api-key';
|
|
|
|
beforeEach(() => {
|
|
TestAgent = new PluginsClient(apiKey, options);
|
|
TestAgent.loadHistory = jest
|
|
.fn()
|
|
.mockImplementation((conversationId, parentMessageId = null) => {
|
|
if (!conversationId) {
|
|
TestAgent.currentMessages = [];
|
|
return Promise.resolve([]);
|
|
}
|
|
|
|
const orderedMessages = TestAgent.constructor.getMessagesForConversation({
|
|
messages: fakeMessages,
|
|
parentMessageId,
|
|
});
|
|
|
|
const chatMessages = orderedMessages.map((msg) =>
|
|
msg?.isCreatedByUser || msg?.role?.toLowerCase() === 'user'
|
|
? new HumanChatMessage(msg.text)
|
|
: new AIChatMessage(msg.text),
|
|
);
|
|
|
|
TestAgent.currentMessages = orderedMessages;
|
|
return Promise.resolve(chatMessages);
|
|
});
|
|
TestAgent.sendMessage = jest.fn().mockImplementation(async (message, opts = {}) => {
|
|
if (opts && typeof opts === 'object') {
|
|
TestAgent.setOptions(opts);
|
|
}
|
|
const conversationId = opts.conversationId || crypto.randomUUID();
|
|
const parentMessageId = opts.parentMessageId || '00000000-0000-0000-0000-000000000000';
|
|
const userMessageId = opts.overrideParentMessageId || crypto.randomUUID();
|
|
this.pastMessages = await TestAgent.loadHistory(
|
|
conversationId,
|
|
TestAgent.options?.parentMessageId,
|
|
);
|
|
|
|
const userMessage = {
|
|
text: message,
|
|
sender: 'ChatGPT',
|
|
isCreatedByUser: true,
|
|
messageId: userMessageId,
|
|
parentMessageId,
|
|
conversationId,
|
|
};
|
|
|
|
const response = {
|
|
sender: 'ChatGPT',
|
|
text: 'Hello, User!',
|
|
isCreatedByUser: false,
|
|
messageId: crypto.randomUUID(),
|
|
parentMessageId: userMessage.messageId,
|
|
conversationId,
|
|
};
|
|
|
|
fakeMessages.push(userMessage);
|
|
fakeMessages.push(response);
|
|
return response;
|
|
});
|
|
});
|
|
|
|
test('initializes PluginsClient without crashing', () => {
|
|
expect(TestAgent).toBeInstanceOf(PluginsClient);
|
|
});
|
|
|
|
test('check setOptions function', () => {
|
|
expect(TestAgent.agentIsGpt3).toBe(true);
|
|
});
|
|
|
|
describe('sendMessage', () => {
|
|
test('sendMessage should return a response message', async () => {
|
|
const expectedResult = expect.objectContaining({
|
|
sender: 'ChatGPT',
|
|
text: expect.any(String),
|
|
isCreatedByUser: false,
|
|
messageId: expect.any(String),
|
|
parentMessageId: expect.any(String),
|
|
conversationId: expect.any(String),
|
|
});
|
|
|
|
const response = await TestAgent.sendMessage(userMessage);
|
|
parentMessageId = response.messageId;
|
|
conversationId = response.conversationId;
|
|
expect(response).toEqual(expectedResult);
|
|
});
|
|
|
|
test('sendMessage should work with provided conversationId and parentMessageId', async () => {
|
|
const userMessage = 'Second message in the conversation';
|
|
const opts = {
|
|
conversationId,
|
|
parentMessageId,
|
|
};
|
|
|
|
const expectedResult = expect.objectContaining({
|
|
sender: 'ChatGPT',
|
|
text: expect.any(String),
|
|
isCreatedByUser: false,
|
|
messageId: expect.any(String),
|
|
parentMessageId: expect.any(String),
|
|
conversationId: opts.conversationId,
|
|
});
|
|
|
|
const response = await TestAgent.sendMessage(userMessage, opts);
|
|
parentMessageId = response.messageId;
|
|
expect(response.conversationId).toEqual(conversationId);
|
|
expect(response).toEqual(expectedResult);
|
|
});
|
|
|
|
test('should return chat history', async () => {
|
|
const chatMessages = await TestAgent.loadHistory(conversationId, parentMessageId);
|
|
expect(TestAgent.currentMessages).toHaveLength(4);
|
|
expect(chatMessages[0].text).toEqual(userMessage);
|
|
});
|
|
});
|
|
});
|