LibreChat/api/server/controllers/assistants/chatV2.js
Marco Beretta e1e1d1b19d 🎒 feat: Carry Project Context Across Conversations (#15684)
* 🎒 feat: Carry Project Context Across Conversations

* fix: fail a project attach whose upload hold cannot be released and keep file deletes independent of project cleanup

- Attaching a project file now fails, with nothing attached, when the file's
  temporary upload hold cannot be released, instead of attaching a file that
  can still expire.
- A failed project cleanup after a file delete is logged rather than failing a
  delete that already happened, and a user-wide delete clears that user's
  project references without reading every file first.
- Both resize handles share the orientation-aware grip, so a primary handle in
  a vertical group renders a rotated grip like the alternate one.

* fix: treat an empty tenant id as no tenant in the project file picker

* fix: attach nothing when a project file is deleted while the attach is in flight

* fix: localize project file association failures instead of showing server text

* test: expect a localized reason for a rejected project file association

* fix: scope project file listing to the caller's tenant and name the file limit when attaching an existing file

- Listing a project's attached files now returns not found when the project
  belongs to another tenant, matching the available-file listing and the
  chat context resolver.
- Choosing an existing file for a full project now names the project file
  limit instead of the generic attach error, like the upload path.

* fix: treat an empty tenant id as no tenant in every project tenant check

A caller whose tenant id is an empty string was refused its own tenantless
project when listing attached or available files, because the handlers
compared '' with null. The project handlers and the chat context resolver now
share one comparison that treats an empty tenant id as no tenant, the rule the
project file queries already follow.

* test: wait for the workspace layout swap and the mobile drawer before acting in the long-metadata spec

The desktop title was measured while the phone layout could still be the one
rendered, and the sidebar row menu was opened before the mobile drawer
committed its open state, which closes a menu opened ahead of it. The spec
now waits for the workspace's phone-only sidebar toggle to leave and for the
drawer to drop inert, the same drawer signal the agents helpers use.

* fix: keep the agent context fingerprint of a turn outside any project unchanged

Every turn now passes a project context key into the agent context
fingerprint, and a turn outside any project passed the no-project sentinel,
which changed the digest of every existing no-project checkpoint. An agent
event conversation written before this change then cold-started and reloaded
its history on its next event. The fingerprint now hashes the no-project key
as absent, so those checkpoints keep matching.

* test: load the long-metadata spec at phone width before driving the mobile drawer

The spec crossed back from desktop to phone width without a reload, which
leaves the drawer on the desktop toggle path whose delayed focus handoff to
the close button dismissed the row menu roughly 200ms after it opened. The
spec now reloads at phone width, as a phone arrives, and waits for the
drawer's own focus handoff before opening the menu.

(cherry picked from commit 4062bc3c00)

Original-PR: https://github.com/LibreChat-AI/LibreChat/pull/15684
2026-10-01 03:46:19 +00:00

632 lines
17 KiB
JavaScript

const { v4 } = require('uuid');
const { sleep } = require('@librechat/agents');
const { logger } = require('@librechat/data-schemas');
const {
sendEvent,
countTokens,
checkBalance,
createBalanceReservations,
getBalanceConfig,
getTransactionsConfig,
getModelMaxTokens,
ATTACHMENT_ONLY_TEXT,
isContentFilterError,
hasActiveFilePolicy,
preflightAssistantRunContent,
reportLocatorTraversalFailure,
preflightAssistantUserMessageContent,
settleAssistantFinal,
resolveAssistantProjectTurn,
joinChatProjectInstructions,
} = require('@librechat/api');
const {
Time,
Constants,
RunStatus,
CacheKeys,
ContentTypes,
ToolCallTypes,
EModelEndpoint,
retrievalMimeTypes,
AssistantStreamEvents,
} = require('librechat-data-provider');
const {
initThread,
recordUsage,
saveUserMessage,
addThreadMetadata,
saveAssistantMessage,
} = require('~/server/services/Threads');
const { runAssistant, createOnTextProgress } = require('~/server/services/AssistantService');
const { createErrorHandler } = require('~/server/controllers/assistants/errors');
const validateAuthor = require('~/server/middleware/assistants/validateAuthor');
const { createRun, StreamRunManager } = require('~/server/services/Runs');
const { addTitle } = require('~/server/services/Endpoints/assistants');
const { createRunBody } = require('~/server/services/createRunBody');
const setHeaders = require('~/server/middleware/setHeaders');
const {
getConvo,
getMultiplier,
getTransactions,
reserveBalance,
renewBalanceReservation,
releaseBalanceReservation,
getChatProject,
getProjectFiles,
getFiles,
} = require('~/models');
const { logViolation, getLogStores } = require('~/cache');
const { getOpenAIClient } = require('./helpers');
/**
* @route POST /
* @desc Chat with an assistant
* @access Public
* @param {ServerRequest} req - The request object, containing the request data.
* @param {Express.Response} res - The response object, used to send back a response.
* @returns {void}
*/
const chatV2 = async (req, res) => {
const appConfig = req.config;
/** @type {{files: MongoFile[]}} */
const {
text,
model,
endpoint,
files = [],
promptPrefix,
assistant_id,
instructions,
endpointOption,
thread_id: _thread_id,
messageId: _messageId,
conversationId: convoId,
parentMessageId: _parentId = Constants.NO_PARENT,
clientTimestamp,
} = req.body;
logger.debug('[/assistants/chat/] request', {
endpoint,
conversationId: convoId,
assistantId: assistant_id,
hasText: typeof text === 'string' && text.length > 0,
fileCount: Array.isArray(files) ? files.length : 0,
});
/** @type {OpenAI} */
let openai;
/** @type {string|undefined} - the current thread id */
let thread_id = _thread_id;
/** @type {string|undefined} - the current run id */
let run_id;
/** @type {string|undefined} - the parent messageId */
let parentMessageId = _parentId;
/** @type {TMessage[]} */
let previousMessages = [];
/** @type {import('librechat-data-provider').TConversation | null} */
let conversation = null;
/** @type {string[]} */
let file_ids = [];
/** @type {Set<string>} */
let attachedFileIds = new Set();
/** @type {TMessage | null} */
let requestMessage = null;
const userMessageId = v4();
const responseMessageId = v4();
/** @type {string} - The conversation UUID - created if undefined */
const conversationId = convoId ?? v4();
const cache = getLogStores(CacheKeys.ABORT_KEYS);
const cacheKey = `${req.user.id}:${conversationId}`;
/** @type {Run | undefined} - The completed run, undefined if incomplete */
let completedRun;
let contentRejected = false;
const balanceReservations = createBalanceReservations();
const getContext = () => ({
openai,
run_id,
endpoint,
cacheKey,
thread_id,
completedRun,
assistant_id,
conversationId,
parentMessageId,
responseMessageId,
});
const handleError = createErrorHandler({ req, res, getContext });
try {
res.on('close', async () => {
if (!completedRun && !contentRejected) {
await handleError(new Error('Request closed'));
}
});
const projectTurn = await resolveAssistantProjectTurn(
{
userId: req.user.id,
tenantId: req.user.tenantId,
conversationId: convoId,
requestedProjectId: endpointOption?.chatProjectId ?? req.body?.chatProjectId,
resolvedConversation: req.resolvedConversation,
filters: req.config?.filters,
},
{ getConvo, getChatProject, getProjectFiles },
);
if (projectTurn.rejection) {
contentRejected = true;
return res.status(projectTurn.rejection.status).json(projectTurn.rejection.body);
}
const existingConversation = projectTurn.conversation;
const projectInstructions = projectTurn.instructions;
req.resolvedConversation = existingConversation;
req.chatProjectContext = projectTurn.context;
if (convoId && !_thread_id) {
completedRun = true;
throw new Error('Missing thread_id for existing conversation');
}
if (!assistant_id) {
completedRun = true;
throw new Error('Missing assistant_id');
}
const checkBalanceBeforeRun = async () => {
const balanceConfig = getBalanceConfig(appConfig);
if (!balanceConfig?.enabled) {
return;
}
const transactions =
(await getTransactions({
user: req.user.id,
context: 'message',
conversationId,
})) ?? [];
const totalPreviousTokens = Math.abs(
transactions.reduce((acc, curr) => acc + curr.rawAmount, 0),
);
// TODO: make promptBuffer a config option; buffer for title generation.
const promptBuffer = parentMessageId === Constants.NO_PARENT && !_thread_id ? 200 : 0;
// 5 is added for labels
const promptText = joinChatProjectInstructions(
`${text ?? ''}${promptPrefix ?? ''}`,
projectInstructions,
);
let promptTokens = totalPreviousTokens + (await countTokens(promptText)) + 5 + promptBuffer;
// Count tokens up to the current context window
promptTokens = Math.min(promptTokens, getModelMaxTokens(model));
return await checkBalance(
{
req,
res,
txData: {
model,
user: req.user.id,
tokenType: 'prompt',
amount: promptTokens,
},
},
{
getMultiplier,
reserveBalance,
renewBalanceReservation,
releaseBalanceReservation,
logViolation,
balanceConfig,
},
);
};
const { openai: _openai } = await getOpenAIClient({
req,
res,
endpointOption,
});
openai = _openai;
await validateAuthor({ req, openai });
try {
await preflightAssistantRunContent({
onTraversalFailure: reportLocatorTraversalFailure,
config: req.config,
openai,
user: req.user,
assistantId: assistant_id,
threadId: _thread_id,
getFiles,
});
} catch (error) {
if (!isContentFilterError(error)) {
throw error;
}
contentRejected = true;
return res.status(error.statusCode).json(error.body);
}
if (previousMessages.length) {
parentMessageId = previousMessages[previousMessages.length - 1].messageId;
}
/**
* Threads rejects an empty message body, so an attachment-only turn sends
* a minimal note instead. The persisted message keeps its empty text.
*/
const isAttachmentOnly = !text?.trim() && files.length > 0;
let userMessage = {
role: 'user',
content: [
{
type: ContentTypes.TEXT,
text: isAttachmentOnly ? ATTACHMENT_ONLY_TEXT : text,
},
],
metadata: {
messageId: userMessageId,
},
};
/** @type {CreateRunBody | undefined} */
const body = createRunBody({
assistant_id,
model,
promptPrefix,
instructions,
endpointOption,
clientTimestamp,
});
if (projectInstructions) {
body.additional_instructions = joinChatProjectInstructions(
body.additional_instructions,
projectInstructions,
);
}
const getRequestFileIds = async () => {
let thread_file_ids = [];
if (convoId) {
const convo = existingConversation;
if (convo && convo.file_ids) {
thread_file_ids = convo.file_ids;
}
}
if (files.length || thread_file_ids.length) {
attachedFileIds = new Set([...file_ids, ...thread_file_ids]);
let attachmentIndex = 0;
for (const file of files) {
file_ids.push(file.file_id);
if (file.type.startsWith('image')) {
userMessage.content.push({
type: ContentTypes.IMAGE_FILE,
[ContentTypes.IMAGE_FILE]: { file_id: file.file_id },
});
}
if (!userMessage.attachments) {
userMessage.attachments = [];
}
userMessage.attachments.push({
file_id: file.file_id,
tools: [{ type: ToolCallTypes.CODE_INTERPRETER }],
});
if (file.type.startsWith('image')) {
continue;
}
const mimeType = file.type;
const isSupportedByRetrieval = retrievalMimeTypes.some((regex) => regex.test(mimeType));
if (isSupportedByRetrieval) {
userMessage.attachments[attachmentIndex].tools.push({
type: ToolCallTypes.FILE_SEARCH,
});
}
attachmentIndex++;
}
}
};
/** @type {Promise<Run>|undefined} */
let userMessagePromise;
const inspectFinalMessageFiles = hasActiveFilePolicy(req.config?.filters);
const initializeThread = async () => {
if (!inspectFinalMessageFiles) {
await getRequestFileIds();
}
// TODO: may allow multiple messages to be created beforehand in a future update
const initThreadBody = {
messages: [userMessage],
metadata: {
user: req.user.id,
conversationId,
},
};
const result = await initThread({ openai, body: initThreadBody, thread_id });
thread_id = result.thread_id;
createOnTextProgress({
openai,
conversationId,
userMessageId,
messageId: responseMessageId,
thread_id,
});
requestMessage = {
user: req.user.id,
text,
messageId: userMessageId,
parentMessageId,
// TODO: make sure client sends correct format for `files`, use zod
files,
file_ids,
conversationId,
isCreatedByUser: true,
assistant_id,
thread_id,
model: assistant_id,
endpoint,
};
previousMessages.push(requestMessage);
/* asynchronous */
userMessagePromise = saveUserMessage(req, { ...requestMessage, model });
const conversationProjectId = projectTurn.membershipProjectId;
conversation = {
conversationId,
endpoint,
promptPrefix: promptPrefix,
instructions: instructions,
assistant_id,
// model,
...(conversationProjectId !== undefined ? { chatProjectId: conversationProjectId } : {}),
};
if (file_ids.length) {
conversation.file_ids = file_ids;
}
};
if (inspectFinalMessageFiles) {
await getRequestFileIds();
try {
await preflightAssistantUserMessageContent({
onTraversalFailure: reportLocatorTraversalFailure,
config: req.config,
user: req.user,
message: userMessage,
fileIds: [...attachedFileIds, ...file_ids],
getFiles,
});
} catch (error) {
if (!isContentFilterError(error)) {
throw error;
}
contentRejected = true;
return res.status(error.statusCode).json(error.body);
}
}
const promises = [initializeThread(), balanceReservations.track(checkBalanceBeforeRun())];
await Promise.all(promises);
const sendInitialResponse = () => {
sendEvent(res, {
sync: true,
conversationId,
// messages: previousMessages,
requestMessage,
responseMessage: {
user: req.user.id,
messageId: openai.responseMessage.messageId,
parentMessageId: userMessageId,
conversationId,
assistant_id,
thread_id,
model: assistant_id,
},
});
};
/** @type {RunResponse | typeof StreamRunManager | undefined} */
let response;
const processRun = async (retry = false) => {
if (endpoint === EModelEndpoint.azureAssistants) {
body.model = openai._options.model;
openai.attachedFileIds = attachedFileIds;
if (retry) {
response = await runAssistant({
openai,
thread_id,
run_id,
in_progress: openai.in_progress,
});
return;
}
/* NOTE:
* By default, a Run will use the model and tools configuration specified in Assistant object,
* but you can override most of these when creating the Run for added flexibility:
*/
const run = await createRun({
openai,
thread_id,
body,
});
run_id = run.id;
await cache.set(cacheKey, `${thread_id}:${run_id}`, Time.TEN_MINUTES);
sendInitialResponse();
// todo: retry logic
response = await runAssistant({ openai, thread_id, run_id });
return;
}
/** @type {{[AssistantStreamEvents.ThreadRunCreated]: (event: ThreadRunCreated) => Promise<void>}} */
const handlers = {
[AssistantStreamEvents.ThreadRunCreated]: async (event) => {
await cache.set(cacheKey, `${thread_id}:${event.data.id}`, Time.TEN_MINUTES);
run_id = event.data.id;
sendInitialResponse();
},
};
/** @type {undefined | TAssistantEndpoint} */
const config = appConfig.endpoints?.[endpoint] ?? {};
/** @type {undefined | TBaseEndpoint} */
const allConfig = appConfig.endpoints?.all;
const streamRunManager = new StreamRunManager({
req,
res,
openai,
handlers,
thread_id,
attachedFileIds,
parentMessageId: userMessageId,
responseMessage: openai.responseMessage,
streamRate: allConfig?.streamRate ?? config.streamRate,
// streamOptions: {
// },
});
await streamRunManager.runAssistant({
thread_id,
body,
});
response = streamRunManager;
response.text = streamRunManager.intermediateText;
};
try {
await preflightAssistantRunContent({
onTraversalFailure: reportLocatorTraversalFailure,
config: req.config,
openai,
user: req.user,
assistantId: assistant_id,
threadId: thread_id,
getFiles,
});
} catch (error) {
if (!isContentFilterError(error)) {
throw error;
}
contentRejected = true;
return res.status(error.statusCode).json(error.body);
}
setHeaders(req, res, () => {});
await processRun();
logger.debug('[/assistants/chat/] response', {
run: response.run,
steps: response.steps,
});
if (response.run.status === RunStatus.CANCELLED) {
logger.debug('[/assistants/chat/] Run cancelled, handled by `abortRun`');
return res.end();
}
if (response.run.status === RunStatus.IN_PROGRESS) {
balanceReservations.holdUntil(processRun(true));
}
completedRun = response.run;
/** @type {ResponseMessage} */
const responseMessage = {
...(response.responseMessage ?? response.finalMessage),
text: response.text,
parentMessageId: userMessageId,
conversationId,
user: req.user.id,
assistant_id,
thread_id,
model: assistant_id,
endpoint,
spec: endpointOption.spec,
iconURL: endpointOption.iconURL,
};
if (userMessagePromise) {
await userMessagePromise;
}
const settledConversation = await settleAssistantFinal(() =>
saveAssistantMessage(req, { ...responseMessage, model }),
);
sendEvent(res, {
final: true,
conversation: { ...conversation, ...settledConversation },
requestMessage: {
parentMessageId,
thread_id,
},
});
res.end();
if (parentMessageId === Constants.NO_PARENT && !_thread_id) {
addTitle(req, {
text,
responseText: response.text,
conversationId,
});
}
await addThreadMetadata({
openai,
thread_id,
messageId: responseMessage.messageId,
messages: response.messages,
});
if (!response.run.usage) {
await sleep(3000);
completedRun = await openai.beta.threads.runs.retrieve(response.run.id, { thread_id });
if (completedRun.usage) {
await recordUsage({
...completedRun.usage,
user: req.user.id,
model: completedRun.model ?? model,
conversationId,
transactions: getTransactionsConfig(req.config),
});
}
} else {
await recordUsage({
...response.run.usage,
user: req.user.id,
model: response.run.model ?? model,
conversationId,
transactions: getTransactionsConfig(req.config),
});
}
} catch (error) {
await handleError(error);
} finally {
await balanceReservations.release();
}
};
module.exports = chatV2;