mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-06-25 08:56:10 +00:00
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
GitNexus Index / index (push) Waiting to run
GitNexus Index / post-index (push) Blocked by required conditions
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Waiting to run
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Waiting to run
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
Sync Helm Chart Tags / Ignore non-main push (push) Waiting to run
Sync Helm Chart Tags / Sync chart tags (push) Waiting to run
* ⚡ feat: Immediate Conversation Title Generation Generate conversation titles as soon as the request is made (in parallel with the response, from the user's first message) as the new default, fixing the #13318 race where a transient /gen_title 404 left new chats stuck on "New Chat". - Add per-endpoint `titleTiming` ('immediate' | 'final') to baseEndpointSchema; `endpoints.all` acts as the global default, unset = immediate. Resolve via a new `resolveTitleTiming` helper (`all` takes precedence). - Fire title generation in parallel with `sendMessage`; `titleConvo` waits (bounded, abortable) for the agent run and titles from the user input only. Persist after the conversation row exists; defer `disposeClient` until the title settles. - Expose `titleGenerationTiming` via startup config; `useTitleGeneration` fetches eagerly in immediate mode with a bounded 404 retry and never treats a transient 404 as final. Skip title queueing for temporary conversations. - Supersedes #13329 while incorporating its bounded 404-retry. * 🩹 fix: Address Copilot review findings on title timing - Guard against an undefined conversationId in addTitle (skip + warn) so the gen_title cache key can't collide as `userId-undefined` and saveConvo is never called without a conversationId. - Gate the title `useQueries` on `enabled` so no /gen_title request fires while unauthenticated (e.g. after logout) even if the module queue holds IDs. - Drop the stale `conversationId` param from the titleConvo JSDoc. - Add a regression test for the undefined-conversationId guard. * 🧵 fix: Harden immediate-title edge cases from codex review - Cancel in-flight immediate title generation when the request aborts: thread job.abortController.signal through addTitle so pressing Stop on a new chat neither consumes the title model nor surfaces a title for a cancelled turn. - Preserve a locally-applied title when the final SSE event's conversation carries no title yet (built before the title was saved), so long immediate-mode responses no longer revert the chat to "New Chat" until reload. - Guarantee one full post-completion gen_title fetch cycle before giving up, so a `final`-mode title (generated only after the stream ends) is still fetched under a global `immediate` default instead of being stranded. - Add regression tests for the abort propagation and the undefined-conversationId guard. * 🔁 fix: Correct title abort, post-completion refetch, and replacement ordering Follow-up to codex review of the immediate-title fixes: - Use a dedicated title AbortController instead of `job.abortController`. The latter is also aborted by `completeJob` on *successful* completion, which cancelled any title slower than a short response. The title is now cancelled only on a real user Stop or when the stream is replaced; a completed-then- aborted title is discarded (no save, cache cleared) rather than persisted. - Reset (not remove) the post-completion title query: `resetQueries` refetches the mounted observer with a fresh retry budget, whereas `removeQueries` left it stuck in its error state, so the promised post-completion cycle never ran. - Run the job-replacement check before resolving `convoReady`, and on a replaced stream cancel/discard the stale title so a discarded prompt can't persist a title. * 🧷 fix: Tighten title abort ordering and endpoint-level timing resolution Follow-up to codex review: - Abort the title controller before resolving `convoReady` on a stopped turn, so the title task can't resume and persist before the later abort. - Cancel the title and unblock its waits on ANY send failure (not just user aborts): a preflight/quota failure before the run exists otherwise hangs `_waitForRun`, deferring client disposal until the 45s title timeout. - Resolve `titleTiming` for custom endpoints via `getCustomEndpointConfig` (their config lives under `endpoints.custom[]`, not `endpoints[endpoint]`). - Derive the startup `titleGenerationTiming` via `resolveTitleTiming` for the agents endpoint so an endpoint-level `final` (without `endpoints.all`) is honored client-side instead of defaulting to immediate and burning eager gen_title polls. * 🪢 fix: Per-agent title timing and safer abort/replacement handling Follow-up to codex review: - Resolve `titleTiming` from the agent's actual endpoint after initialization, so a per-endpoint `final` override on a custom/provider endpoint backing an (ephemeral) agent is honored instead of always using the `agents` endpoint's value. - Don't preserve a locally-fetched title on a stopped (unfinished) turn: the server cancels and discards that title, so keeping it client-side would diverge from server state and leave the stopped chat titled until reload. - On abort/replacement, only delete the cached title if it still holds THIS task's value — a replacement stream shares the `userId-conversationId` key and may have already cached its own valid title that must not be removed. * 🪞 fix: Mirror AgentClient title-config resolution for titleTiming Per maintainer guidance, keep titleTiming resolution identical to how `AgentClient#titleConvo` already resolves the endpoint config — `endpoints.all` is the intended global override and the agent's actual provider endpoint is used: - Resolve via `endpoints.all ?? endpoints[endpoint] ?? getProviderConfig(endpoint) .customEndpointConfig` (was using `getCustomEndpointConfig` directly). Going through `getProviderConfig` picks up its case-insensitive fallback for normalized provider names (e.g. `openrouter` → `OpenRouter`), so a custom endpoint's `titleTiming` is honored like its other title settings. - Add `titleTiming` to the Azure endpoint schema `.pick()` so `endpoints.azureOpenAI.titleTiming` is no longer silently stripped by Zod. Note: per-endpoint title settings being skipped when `endpoints.all` is present is the existing, intended global-override behavior — not changed here. * 🧪 test: Cover useTitleGeneration effect logic (integration) Adds a deterministic white-box integration test that drives the real hook's React effects with a controllable react-query surface, locking down the stateful decisions that previously had no coverage: - immediate mode fetches a queued conversation while its stream is still active - final mode gates until the stream completes, then becomes eligible - success applies the fetched title to the conversation caches - a 404 while active defers (removeQueries) instead of giving up - a 404 after completion forces a fresh fetch via resetQueries (post-completion remount) * feat: Stream immediate title events * style: Format title SSE handler * test: Preserve data-provider exports in OAuth mock * test: Isolate OAuth route API mock * test: Keep OAuth callback factory capture * fix: Replay streamed title events on resume * fix: Honor agents title timing precedence * style: Format title timing fixes
163 lines
5.4 KiB
JavaScript
163 lines
5.4 KiB
JavaScript
const { isEnabled } = require('@librechat/api');
|
|
const { logger } = require('@librechat/data-schemas');
|
|
const { CacheKeys } = require('librechat-data-provider');
|
|
const getLogStores = require('~/cache/getLogStores');
|
|
const { saveConvo } = require('~/models');
|
|
|
|
/**
|
|
* Add title to conversation in a way that avoids memory retention.
|
|
*
|
|
* @param {ServerRequest} req
|
|
* @param {Object} params
|
|
* @param {string} params.text - The user's first message.
|
|
* @param {TMessage} [params.response] - The assistant response (legacy/`final` timing only).
|
|
* @param {AgentClient} params.client
|
|
* @param {string} [params.conversationId] - Required for `immediate` timing, where
|
|
* `response` is not yet available; falls back to `response.conversationId`.
|
|
* @param {boolean} [params.immediate] - When true, the title is generated in parallel
|
|
* with the response (from the user's first message) and persisted to the conversation
|
|
* only after `convoReady` resolves (the conversation row must exist for `noUpsert`).
|
|
* @param {Promise<void>} [params.convoReady] - Resolves once the conversation has been
|
|
* persisted; awaited before saving the title in `immediate` mode.
|
|
* @param {AbortSignal} [params.signal] - When aborted (e.g. the user stops an
|
|
* immediate-mode generation), cancels the in-flight title model call so a
|
|
* cancelled turn neither consumes the title model nor surfaces a title.
|
|
* @param {(params: { conversationId: string, title: string }) => Promise<void>|void} [params.onTitleGenerated]
|
|
* Called after the title is cached and before persistence waits for the
|
|
* conversation row. Used by live streams to push the title immediately.
|
|
*/
|
|
const addTitle = async (
|
|
req,
|
|
{
|
|
text,
|
|
response,
|
|
client,
|
|
conversationId,
|
|
immediate = false,
|
|
convoReady,
|
|
signal,
|
|
onTitleGenerated,
|
|
},
|
|
) => {
|
|
const { TITLE_CONVO = true } = process.env ?? {};
|
|
if (!isEnabled(TITLE_CONVO)) {
|
|
return;
|
|
}
|
|
|
|
if (client.options.titleConvo === false) {
|
|
return;
|
|
}
|
|
|
|
// Skip title generation for temporary conversations
|
|
if (req?.body?.isTemporary) {
|
|
return;
|
|
}
|
|
|
|
const convoId = conversationId ?? response?.conversationId;
|
|
if (!convoId) {
|
|
logger.warn('[addTitle] Missing conversationId; skipping title generation');
|
|
return;
|
|
}
|
|
|
|
const titleCache = getLogStores(CacheKeys.GEN_TITLE);
|
|
const key = `${req.user.id}-${convoId}`;
|
|
/** @type {NodeJS.Timeout} */
|
|
let timeoutId;
|
|
try {
|
|
const timeoutPromise = new Promise((_, reject) => {
|
|
timeoutId = setTimeout(() => reject(new Error('Title generation timeout')), 45000);
|
|
}).catch((error) => {
|
|
logger.error('Title error:', error);
|
|
});
|
|
|
|
let titlePromise;
|
|
let abortController = new AbortController();
|
|
/** Propagate a request abort (Stop) to the title generation so a cancelled
|
|
* turn does not consume the title model or surface a title. */
|
|
if (signal) {
|
|
if (signal.aborted) {
|
|
abortController.abort();
|
|
} else {
|
|
signal.addEventListener('abort', () => abortController.abort(), { once: true });
|
|
}
|
|
}
|
|
if (client && typeof client.titleConvo === 'function') {
|
|
titlePromise = Promise.race([
|
|
client
|
|
.titleConvo({
|
|
text,
|
|
abortController,
|
|
immediate,
|
|
})
|
|
.catch((error) => {
|
|
logger.error('Client title error:', error);
|
|
}),
|
|
timeoutPromise,
|
|
]);
|
|
} else {
|
|
return;
|
|
}
|
|
|
|
const title = await titlePromise;
|
|
if (!abortController.signal.aborted) {
|
|
abortController.abort();
|
|
}
|
|
if (timeoutId) {
|
|
clearTimeout(timeoutId);
|
|
}
|
|
|
|
if (!title) {
|
|
logger.debug(`[${key}] No title generated`);
|
|
return;
|
|
}
|
|
|
|
await titleCache.set(key, title, 120000);
|
|
|
|
if (!signal?.aborted && typeof onTitleGenerated === 'function') {
|
|
try {
|
|
await onTitleGenerated({ conversationId: convoId, title });
|
|
} catch (error) {
|
|
logger.error('Error emitting generated title:', error);
|
|
}
|
|
}
|
|
|
|
/** In immediate mode the title is generated in parallel with the response,
|
|
* so the conversation row may not exist yet. `saveConvo` with `noUpsert`
|
|
* is a silent no-op when the row is missing, which would drop the title
|
|
* from the database (the cache above still serves the live UI). Wait for
|
|
* the controller to signal the conversation has been persisted. */
|
|
if (convoReady) {
|
|
await convoReady;
|
|
}
|
|
|
|
if (signal?.aborted) {
|
|
// The turn was stopped, or this stream was replaced, after the title had
|
|
// already been generated — discard it instead of persisting a title for a
|
|
// cancelled/discarded response. Only clear the cache if it still holds THIS
|
|
// task's title: a replacement stream shares the `userId-conversationId` key
|
|
// and may have already cached its own (valid) title that we must not remove.
|
|
const cached = await titleCache.get(key);
|
|
if (cached === title) {
|
|
await titleCache.delete(key);
|
|
}
|
|
return;
|
|
}
|
|
|
|
await saveConvo(
|
|
{
|
|
userId: req?.user?.id,
|
|
isTemporary: req?.body?.isTemporary,
|
|
interfaceConfig: req?.config?.interfaceConfig,
|
|
},
|
|
{
|
|
conversationId: convoId,
|
|
title,
|
|
},
|
|
{ context: 'api/server/services/Endpoints/agents/title.js', noUpsert: true },
|
|
);
|
|
} catch (error) {
|
|
logger.error('Error generating title:', error);
|
|
}
|
|
};
|
|
|
|
module.exports = addTitle;
|