* fix(api): align message search with page size
Pass a positive, capped page size to MeiliSearch and use the same conversation limit so requested message search pages are not silently truncated.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(data-schemas): expand shared-link search results
Request the MeiliSearch result ceiling using only conversationId so cursor pagination is not limited to the default 20 hits or burdened with unused fields.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* ⚡ perf: Append Saved Message Ids Instead of Rebuilding the Conversation Array
Every saveConvo read every message id in the conversation (sorted) and
wrote the array back onto the document — twice per chat turn, O(n) in
conversation length, from a write path. The turn's savers know exactly
which message they just wrote, so they now pass it as
metadata.appendMessageIds and saveConvo $addToSet-s it, skipping the
read and the full-array rewrite. Every save without the option — titles,
archive, fork, import, threads — still rebuilds from the database, which
remains the heal point for the drift that message deletion has always
left behind (deletes never ran saveConvo).
The array's consumers read presence or length, or use it as an
optimistic cache placeholder, so incremental maintenance is
behaviorally identical; on traced turns the array stays exactly equal
to the messages collection.
Per-turn queries: 15 -> 13 (two Message.find gone), and the growing
array payload no longer crosses the wire twice per turn.
* 🎯 fix: Brand the Lineage-Only Resolved Conversation Instead of Guessing by Shape
The resolved-conversation files fast path treated an absent files
property as unresolved so the lineage-only partial from a bound
agent-event continuation could not silently hide a conversation's
uploads. But MongoDB never stores an empty files array, so nearly every
real conversation also lacks the property and the fast path never fired
— a follow-up turn on an upload-free conversation still paid the
getConvoFiles round trip.
The synthesized partial is the one object that cannot speak for the
database, so it now carries an explicit symbol brand
(PARTIAL_RESOLVED_CONVERSATION, non-serializing and invisible to key
iteration), and a stored document without files means what it means:
no files. Traced follow-up turns drop from 14 queries to 13.
* 🧪 test: Expect the Appended Message Id in the Route's saveConvo Metadata
messages-get.spec.js pins the exact metadata POST /api/messages passes to
saveConvo; the route now forwards the saved message's _id as
appendMessageIds, which is the behavior the append path depends on.
* feat: add interface option to hide response feedback buttons
Adds `interface.feedback` to librechat.yaml. When set to false, the
thumbs up/thumbs down buttons are removed from the message action row
and the feedback endpoint rejects writes with 403, so deployments that
do not consume the data can stop collecting it. Defaults to true.
* refactor: hoist the feedback gate out of the message row and into typed middleware
Reading startup config inside HoverButtons put a query observer and two Recoil
subscriptions on every message row, and rows never unmount, so the cost grew
with the conversation. Resolve the flag once per chat in useChatHelpers and
carry it on TMessageChatContext; useMessageActions withholds handleFeedback
when it is off, which the action row already treats as "no feedback controls".
The flag now stays false until the config resolves, so a disabled deployment
never flashes controls whose writes are rejected.
Move the server-side policy into requireFeedbackEnabled under packages/api so
the route keeps no policy of its own.
* test: stub the feedback gate in specs that replace the api package
The messages router now imports requireFeedbackEnabled, and express rejects an
undefined handler at require time, so every spec that mocks @librechat/api
wholesale has to carry the export.
* ⚡ perf: Index the Conversation Fetch and Trim the Client Message Projection
* ⚡ perf: Memoize the Message Tree per Cache Write
* ⚡ perf: Serve Message Reads via the Trimmed Projection and an Ownership Probe
* ⚡ perf: Defer Collapsed Disclosure Bodies Until First Expansion
* ⚡ perf: Progressively Mount Long Threads from the Scroll Anchor
* 🩹 fix: Address Codex Findings on Retention, Anchoring, and Cache Bounds
* 🩹 fix: Poll the Oversized Export Precondition Through the Progressive Mount
* 🩹 fix: Keep Video Results in the Client Message Projection
* style: Unify message row layout and edit surfaces
Route chat, share, and search messages through a shared MessageRow so
user turns render as right-aligned bubbles and assistant turns keep a
visible identity column.
Replace per-part text editors with one edit surface that keeps tools,
errors, and artifacts visible. Preserve non-text fields when saving
content parts, copy the full serialized message, and hide hover actions
that do not apply during streaming or errors.
* style: Align edit footer and lighten editor field in dark mode
Drop the divider above the user edit footer so both edit surfaces share
the same footer treatment.
Move the editor fields to surface-tertiary-alt. Light mode is unchanged
at #fff, while dark mode lifts from #0d0d0d to #2f2f2f so the field sits
above the #212121 panel instead of sinking into near-black.
* style: Drop focus border and ring from message editors
The editor fields changed border color and added a ring on focus. Keep
the border static and rely on the app-level focus handling instead.
* fix: Keep a triggered message action visible when the row is not hovered
Hover actions fade out on non-last rows, and mobile.css only restored
display and visibility for an active button, never opacity. Opening the
fork popover therefore left it anchored to an invisible trigger once the
pointer left the row. Skip the fade entirely while a button is active.
Extract the recipe the three toolbars repeated so the rule has one home.
Rework the streaming guard to the contract the toolbar now implements:
edit and fork are omitted from a streaming response rather than rendered
disabled, and the settled turn above keeps its own actions. It asserted
the removed disabled-and-transparent behaviour and its opacity check only
held because the growing response shifted the row out from under the
pointer.
* style: Trim message edit chrome and stabilize the status row
The edit surface was a titled card sitting inside the conversation: a
bordered panel with an "Edit message" heading wrapping bordered fields,
which read as a settings dialog rather than an inline editor. Drop the
card background, border and heading, and take the footer buttons down to
the small size so the editor reads as a field in the message flow. The
captured row goes from 253px to 187px.
Move "Unsaved changes" into the footer and merge the rerun hint into the
same slot. Both previously added their own row, so typing pushed the rest
of the conversation down. The slot is clamped to two lines, which stays
under the 36px button row, so the footer height holds at 36px regardless
of which message is showing.
* test: Cover message edit layout stability
Add a mock e2e spec that measures the edit footer and section boxes and
asserts they hold steady as the status text appears, for both the
single-part user editor and a multi-part response.
The multi-part case needs an assistant message with two editable parts,
so add an E2E_THINK_REPLY marker to the fake model. Its think tags are
parsed downstream by the agents stream pipeline, which yields a reasoning
part followed by a text part.
* fix: Read the fork popover open state from its store
Fork mirrored the popover state into its own useState and reset it from an
onClose prop. Ariakit 0.4 has no onClose, and React's DOM types accept the
name on any element, so it type-checked, landed on a div and never fired.
Closing by Escape or an outside click therefore left the button reading as
active until the trigger was clicked again.
Read the state from the store instead so every close path clears it.
* fix: Keep the whole toolbar visible while an action is open
Only the triggered button escaped the hover fade, so opening the editor or
the fork popover left the row as a single floating button once the pointer
moved away. Mark the active button and have every action in the toolbar key
off it, so the group stays opaque for as long as a surface is open.
The marker is a dedicated class rather than the existing `active`, which
HoverButtons pins to the edit button of every assistant message and would
hold those toolbars open permanently.
The existing guard pressed Escape to close the editor while focus sat on the
body, so the editor never closed and its assertion only held because the
sibling faded regardless. Close the editor through its own control, and drop
focus before measuring the fade now that Escape returns it to the trigger.
* fix: Withhold copy while a response is still streaming
Text-to-speech, fork and feedback were all withheld from a message that is
still generating, but copy was rendered throughout, so the button offered to
put half a sentence on the clipboard. Gate it on the same condition.
That empties the toolbar for the duration, and SubRow collapses an empty row,
so a streaming response now carries no actions at all until it settles. Both
guards encoded the old contract: the unit test asserted copy was present and
counted a single button, and the browser guard used copy as its proof that the
toolbar had mounted. The settled turn above takes over that role.
* fix: Move retry navigation to the outer edge of a user turn
A user turn is right-aligned, but its sibling navigation rendered ahead of the
actions, so the retry counter sat inboard of the icons instead of under the
edge of the bubble it belongs to. Order it last on user turns.
* fix: Ride the stream instead of chasing it
Following a generating answer went through a helper throttled at 145ms, so the
thread caught up in visible jerks rather than flowing. It now writes the scroll
position directly on each frame, which is what an answer arriving a few pixels
at a time actually needs, and glides only for the one long trip a turn makes,
when sending has to travel from wherever the reader was down to the newest
word.
Whether to follow at all is now answered by where the reader is and which way
they were going, rather than by the abort flag. `useMessageProcess` raises that
flag on any wheel at all, downward ones included, through a throttle whose
trailing call lands after the gesture has ended, so nothing timed to the
gesture could outlive it. Scrolling down to the newest word could therefore
never resume the ride, while the scroll-to-bottom button, which touches no
wheel, always could.
Arrival is judged on the scroll it produces rather than the wheel tick that
started it, because wheel scrolling is animated and at tick time the thread is
still far short of where the tick is taking it. Arriving also counts from
further out than leaving does: while an answer streams the end recedes between
the last tick and the frame that measures it, so judging arrival as tightly as
departure leaves a reader unable to catch it at all.
* fix: Reveal retry navigation on hover while an answer generates
Copy, edit, fork and read-aloud are all withheld from a response that is still
generating, which left the retry counter as the only thing rendering under a
half-written answer. It now reveals on hover there, like the actions it sits
with, and stays put on a settled turn.
* fix: Keep a refused rerun from discarding the edit
While a response is streaming, the edit action stays available on every earlier
row, and those editors see a per-message submitting flag that is false, so
Update and rerun is enabled. The send itself is still refused: ask() returns
false for the duration of the active submission. Both editors ignored that and
closed anyway, so the draft went with them and no rerun ever started.
Both rerun paths now check the result and leave the editor untouched when the
send is refused, so the work survives until the thread is free.
* fix: Let an upward gesture beat the pending send glide
Sending arms a smooth glide down to the newest word, and the landing re-pins the
thread to the bottom. The landing was scheduled two ways, on scrollend and on a
700ms fallback, and neither was ever cancelled. A reader who changed their mind
and headed up mid-flight was pinned again regardless, then dragged back by the
next streaming resize. The fallback fires for the whole window, so this held even
after the glide had visibly settled.
The gesture now marks the glide interrupted, wherever it lets go of the bottom,
and the landing stands down when it sees that. A glide the reader leaves alone
still re-affirms the ride.
* fix: Fade retry navigation on every streaming response format
Every other action is withheld from the row that is still generating, so the
retry counter is the only thing left under a half-written answer. The plain text
row already faded it to hover-only there; the structured rows did not, and left
it sitting on its own.
Both structured paths now apply the same condition, and the class string the
three of them share moves next to the hover action styles it belongs with.
* i18n: Correct the copy the edit surface rewrite left behind
The multi-part hint told the reader to save first and then rerun, but a save
closes the editor and reopening seeds the drafts from what was just saved, so
there is nothing left to rerun and the button stays disabled. Rerunning carries a
single edited section by design, so the hint now states that limit rather than
pointing at a step that is not there.
Drop com_ui_save_submit as well: the per-part editor that used it is gone.
* test: Make the message visual baselines opt-in
The suite asserts sixteen screenshots and the repository tracks none, so
Playwright's default treats every one as a miss and the mock e2e job fails on
Linux. Baselines only compare cleanly against the machine that produced them, and
nothing here can generate ones that match the runner image.
The flows keep running and asserting their structure, which is where their value
was; only the pixel comparison is now gated behind E2E_VISUAL_SNAPSHOTS.
* style: Restore import order in the reworked message files
The repository sorter and CI disagreed with what these files were left holding
after the edit surface rework. No behavior change.
* test: Follow the reworded rerun hint in the edit layout spec
The multi-part hint was restated in the previous commit; this assertion still
expected the old wording and would have failed the mock e2e suite.
* fix: Leave the send glide alone while the answer streams in
Every delta of an answer reruns the scroll effect, and the plain follow writes
scrollTop outright, which cancels an animation on its first frame. So the glide a
send starts was killed by the first token to arrive and the reader was snapped
down instead of carried.
The follow now stands down while a glide is travelling, which is what the hook
already documented but only enforced on the resize path.
* fix: Write a saved edit onto the thread as it stands
An earlier turn stays editable while the newest answer streams, and the save
captured the thread before the request but wrote it back after. Every delta that
landed during the round trip was overwritten. Most of the time the next delta
re-merged and the damage showed as a one-frame truncation, but a save that
resolved after the stream's final write left the cache wrong for the rest of the
session.
The thread is now read once the request has resolved, which is what the content
part editor already did.
The editor actions in this file also wrap again rather than hold one unbreakable
row, for the reason given in the following commit.
* fix: Let the editor actions wrap on a narrow row
At 320px an assistant turn gives the editor about 252px once page padding, the
identity column and the row gap are taken out, and Cancel, Save and Update &
rerun need more than that in English alone. The group was pinned with shrink-0,
so it ran past the edge of the row instead of wrapping. A longer translated label
makes it worse, and the user turn had no margin left either.
Both editors wrap again, which is what the footer did before the status row was
folded into it.
* fix: Catch up to the new bottom when the glide lands
Following stands down for the length of the glide, so an answer that arrives
while it travels moves the bottom past the target the glide aimed at. A short
response that finished before the glide reported landing left the thread a few
lines short of its own end, with nothing left to correct it.
Landing now closes whatever gap opened, unless the reader took over on the way.
* test: Follow the renamed rerun button in the edit flow specs
The button became 'Update & rerun' when the edit surfaces were unified, but two
edit-flow specs still located 'Save & Submit' and would have waited for it until
they timed out. A type comment named the old button too.
* fix: Judge the first thread scroll against a real position
The direction check seeded its last-position ref at 0, so the first scroll
event on an opened thread, which arrives carrying a large positive
scrollTop, read as a jump downward. Near the end that cleared the abort
flag and re-pinned a reader to the stream they were scrolling away from.
Take the first event as a baseline and judge direction from the next.
* fix: Hold the content part editor to what it replaced
EditContentParts took over from EditTextPart and left two of its behaviors
behind.
An emptied box now blocks Save and rerun instead of persisting a blank
part. EditTextPart refused the same edit through its form's required rule
and the sibling EditMessage still does, so both editors hold one line. The
keyboard shortcuts reach the save paths directly, so they are guarded
there too, and the footer says why the buttons are down.
The editor also follows the chat direction again, taking dir and text
alignment from the same setting EditMessage reads.
* fix: Hold the footer height while a response streams
Every action is withheld from the row that is still generating, and a lone
sibling counter renders nothing, so the footer measured zero until the answer
landed and then sprang to the height of the buttons. The transcript stepped
upward under the reader at the moment a response completed.
The placeholder that used to reserve this space went when the footer became
unconditional, so hold the height on the row itself instead.
* fix: Remember where the thread was put before judging a gesture
Direction is judged against the last sample, and the thread is placed at its
end without the reader touching it. With no record of where it was put, their
first gesture was spent taking the baseline instead of being obeyed: a single
PageUp cleared no flag of its own, so the next streamed resize rode the reader
straight back to the end they were leaving.
Every programmatic move now records the position it left the thread at, so the
sentinel stands only until something has actually placed it.
* fix: Spend the start of a turn only once it can be honored
A reader who scrolls away during one answer leaves the abort flag raised, and
nothing lowers it until the next connection opens, which is after this effect
has already seen the send. Marking the turn as started on that first pass spent
it against a closed gate: by the time the flag cleared there was no start left
to honor, the reader was still detached, and the answer they had just asked for
streamed on offscreen.
Record the turn as started only on the pass that acts on it.
* fix: Show the part edits that survived a refused save
The editor saves every changed part through one button, but the endpoint
takes a single part per call and nothing rolls a write back. A part the
server refused therefore left the earlier ones stored while the editor
reported that the message could not be saved, so cancelling from there
walked away from edits that were already live.
Record the writes that landed and reconcile the transcript with them
whichever way the save ended. The refused parts are the only ones left
holding a draft, so a retry no longer rewrites what already arrived.
* fix: Stop a shared transcript from calling the sharer the reader
The share row reused the chat view's user label, which reads "You". It is
the screen-reader heading for the user turn, so anyone opening a share
link heard every prompt the sharer wrote credited to themselves.
Use the neutral "User" label on this surface. It keeps the localization
the row gained, unlike the untranslated string it replaced.
* fix: Let go of the stream when an interaction settles over several resizes
Expanding a tool result mid-answer renders the container first and fills it
once its contents arrive, so one gesture produces more than one resize. Only
the first was credited to the interaction. The second read the reader as still
riding the stream and put them back on the bottom they had just left.
The suppressed resize now settles the ride as well as the near-bottom measure,
using the position the interaction actually left the reader at, so an
interaction that kept them on the end still streams.
* fix: Edit inside a structured text part instead of flattening it
A text content part holds either a string or a { value, annotations } object.
The Assistants thread sync persists the structured form with its file
citations intact, and the editor reads the part through the same union, so
saving an edit wrote a bare string over the whole object and took every
citation with it.
The same object was handed to the tokenizer, which measures length, so a part
that had been edited this way also stored a NaN token count. Write the edit
into value, keep the rest of the part, and count the text itself.
* fix: Keep a saved part's citations in the transcript it is written back to
A text or think part holds either a bare string or a { value, annotations }
object, and the editor already read both through getPartText. Writing the
draft back into the local message cache put the string over the whole value,
so a response carrying file citations lost them the moment it was edited and
did not get them back until a refetch.
Reading and writing now go through the same accessor, so an edit lands in the
shape it was read from and the rest of the part survives.
* fix: Let the message editor follow the chosen font size
Editing a message dropped the draft to a fixed 14px regardless of the
Font Size setting. On dev the textarea carried the markdown class, so it
read --markdown-font-size like the rendered message does; restyling it
into a bordered box replaced that with text-sm, and the new per-part
editor was written the same way. Anyone on Extra Small, Large or Extra
Large saw the text jump the moment they entered edit mode.
Share the .message-content typography with the editors through a
message-editor-text class so a draft is sized like the message it
replaces and keeps tracking the setting.
The message-edit route recomputed a user message's tokenCount from the edited
`text` alone, ignoring its persisted `quotes`. But the send path re-prepends
those quotes into the prompt on every turn (mergeQuotedText), so after editing a
quoted message the stored tokenCount under-reported by the whole quote block,
skewing the context gauge and any other tokenCount consumer.
The full-recount path now fetches the message's quotes and counts the merged
text+quotes via a new `mergeQuotedTextForCount` helper in packages/api (mirrors
the send path), so the stored count stays authoritative. The incremental
content-part path is left as-is: it deltas only the edited part and preserves the
rest of the count (incl. the quote contribution), and applies to content-array
messages rather than text+quotes user turns.
Deferred follow-up from #13953.
* feat: surface message feedback (thumbs up/down) as Langfuse scores
When Langfuse tracing is enabled, the message feedback endpoint now posts a
boolean `user-feedback` score (1/0 + tag/comment) to Langfuse for the
assistant message's trace; clearing feedback deletes the score. Fire-and-
forget, so the feedback UX never blocks on Langfuse.
Linking is lookup-free: the run opts into deterministic Langfuse trace ids
(`langfuse.deterministicTraceId`, passed to the agents Run), so the trace id
is sha256(messageId)[:32]. The feedback route recomputes the same id and
scores by it.
- api/server/services/Langfuse.js: POST/DELETE /api/public/scores (env-gated)
- api/server/utils/langfuseTrace.js: traceIdForMessage(messageId)
- api/server/routes/messages.js: fire feedback score after the Mongo write
- packages/api: pass langfuse.deterministicTraceId to the run
- bump @librechat/agents to ^3.2.21 (adds LangfuseConfig.deterministicTraceId)
Closes#13537
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: match Langfuse trace environment for feedback scores
@librechat/agents passes no environment to its Langfuse tracer, so
@langfuse/otel falls back to LANGFUSE_TRACING_ENVIRONMENT and otherwise to
Langfuse's "default". The score helper instead fell back to NODE_ENV, so a
deployment with only NODE_ENV=production filed scores under "production" while
the trace stayed on "default" — the score never landed on the trace.
Use LANGFUSE_TRACING_ENVIRONMENT only, and omit `environment` when unset so
Langfuse defaults both score and trace to "default".
Addresses Codex review on #13544.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: don't require LANGFUSE_BASE_URL to post feedback scores
The agent tracer emits traces with just the public/secret keys (defaulting to
Langfuse Cloud, or via the legacy LANGFUSE_BASEURL alias), but the score helper
disabled itself unless LANGFUSE_BASE_URL was set — so an otherwise-traced
deployment silently posted no scores. Resolve the base URL the same way the
tracer does (LANGFUSE_BASE_URL -> LANGFUSE_BASEURL -> Cloud) and gate enablement
on the credentials only.
Addresses Codex review on #13544.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: only post feedback scores for agent-endpoint messages
The feedback route is shared by all message types, but deterministic Langfuse
trace IDs are only enabled for agent runs. Rating a message from a non-agent
endpoint (with Langfuse configured) posted a user-feedback score for
sha256(messageId) that no trace will ever match, leaving orphan scores.
Gate scoring on isAgentsEndpoint(message.endpoint); `updateMessage` now returns
`endpoint` so the route can check it.
Addresses Codex review on #13544.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: gate feedback scoring by !isAssistantsEndpoint, not isAgentsEndpoint
The previous gate used isAgentsEndpoint, which only matches the literal
`agents` endpoint. But provider endpoints (anthropic, openai, custom, …) run
through the agents runtime as ephemeral agents and DO emit deterministic
AgentRun traces, so isAgentsEndpoint('anthropic') === false suppressed scoring
for the common case. Only the OpenAI/Azure Assistants endpoints use a separate
runtime with no agent trace, so gate on !isAssistantsEndpoint instead.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* style: sort message method imports
* fix: honor Langfuse tracing gates for feedback scores
* refactor: move Langfuse feedback logic to api package
* fix: support Langfuse host for feedback scores
* test: type Langfuse feedback fetch mock
* chore: compact Langfuse feedback comment
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* chore: move database model methods to /packages/data-schemas
* chore: add TypeScript ESLint rule to warn on unused variables
* refactor: model imports to streamline access
- Consolidated model imports across various files to improve code organization and reduce redundancy.
- Updated imports for models such as Assistant, Message, Conversation, and others to a unified import path.
- Adjusted middleware and service files to reflect the new import structure, ensuring functionality remains intact.
- Enhanced test files to align with the new import paths, maintaining test coverage and integrity.
* chore: migrate database models to packages/data-schemas and refactor all direct Mongoose Model usage outside of data-schemas
* test: update agent model mocks in unit tests
- Added `getAgent` mock to `client.test.js` to enhance test coverage for agent-related functionality.
- Removed redundant `getAgent` and `getAgents` mocks from `openai.spec.js` and `responses.unit.spec.js` to streamline test setup and reduce duplication.
- Ensured consistency in agent mock implementations across test files.
* fix: update types in data-schemas
* refactor: enhance type definitions in transaction and spending methods
- Updated type definitions in `checkBalance.ts` to use specific request and response types.
- Refined `spendTokens.ts` to utilize a new `SpendTxData` interface for better clarity and type safety.
- Improved transaction handling in `transaction.ts` by introducing `TransactionResult` and `TxData` interfaces, ensuring consistent data structures across methods.
- Adjusted unit tests in `transaction.spec.ts` to accommodate new type definitions and enhance robustness.
* refactor: streamline model imports and enhance code organization
- Consolidated model imports across various controllers and services to a unified import path, improving code clarity and reducing redundancy.
- Updated multiple files to reflect the new import structure, ensuring all functionalities remain intact.
- Enhanced overall code organization by removing duplicate import statements and optimizing the usage of model methods.
* feat: implement loadAddedAgent and refactor agent loading logic
- Introduced `loadAddedAgent` function to handle loading agents from added conversations, supporting multi-convo parallel execution.
- Created a new `load.ts` file to encapsulate agent loading functionalities, including `loadEphemeralAgent` and `loadAgent`.
- Updated the `index.ts` file to export the new `load` module instead of the deprecated `loadAgent`.
- Enhanced type definitions and improved error handling in the agent loading process.
- Adjusted unit tests to reflect changes in the agent loading structure and ensure comprehensive coverage.
* refactor: enhance balance handling with new update interface
- Introduced `IBalanceUpdate` interface to streamline balance update operations across the codebase.
- Updated `upsertBalanceFields` method signatures in `balance.ts`, `transaction.ts`, and related tests to utilize the new interface for improved type safety.
- Adjusted type imports in `balance.spec.ts` to include `IBalanceUpdate`, ensuring consistency in balance management functionalities.
- Enhanced overall code clarity and maintainability by refining type definitions related to balance operations.
* feat: add unit tests for loadAgent functionality and enhance agent loading logic
- Introduced comprehensive unit tests for the `loadAgent` function, covering various scenarios including null and empty agent IDs, loading of ephemeral agents, and permission checks.
- Enhanced the `initializeClient` function by moving `getConvoFiles` to the correct position in the database method exports, ensuring proper functionality.
- Improved test coverage for agent loading, including handling of non-existent agents and user permissions.
* chore: reorder memory method exports for consistency
- Moved `deleteAllUserMemories` to the correct position in the exported memory methods, ensuring a consistent and logical order of method exports in `memory.ts`.
* fix: add user filter to message deletion to prevent IDOR
* refactor: streamline DELETE request syntax in messages-delete test
- Simplified the DELETE request syntax in the messages-delete.spec.js test file by combining multiple lines into a single line for improved readability. This change enhances the clarity of the test code without altering its functionality.
* fix: address review findings for message deletion IDOR fix
* fix: add user filter to message deletion in conversation tests
- Included a user filter in the message deletion test to ensure proper handling of user-specific deletions, enhancing the accuracy of the test case and preventing potential IDOR vulnerabilities.
* chore: lint
- Changed default sorting from 'createdAt' to 'updatedAt' in both Conversation and Message routes.
- Updated pagination logic to ensure the cursor is created from the last returned item instead of the popped item, preventing skipped items at page boundaries.
- Added comprehensive tests for pagination behavior, ensuring no messages or conversations are skipped and that sorting works as expected.
* 🌊 feat: Implement multi-conversation feature with added conversation context and payload adjustments
* refactor: Replace isSubmittingFamily with isSubmitting across message components for consistency
* feat: Add loadAddedAgent and processAddedConvo for multi-conversation agent execution
* refactor: Update ContentRender usage to conditionally render PlaceholderRow based on isLast and isSubmitting
* WIP: first pass, sibling index
* feat: Enhance multi-conversation support with agent tracking and display improvements
* refactor: Introduce isEphemeralAgentId utility and update related logic for agent handling
* refactor: Implement createDualMessageContent utility for sibling message display and enhance useStepHandler for added conversations
* refactor: duplicate tools for added agent if ephemeral and primary agent is also ephemeral
* chore: remove deprecated multimessage rendering
* refactor: enhance dual message content creation and agent handling for parallel rendering
* refactor: streamline message rendering and submission handling by removing unused state and optimizing conditional logic
* refactor: adjust content handling in parallel mode to utilize existing content for improved agent display
* refactor: update @librechat/agents dependency to version 3.0.53
* refactor: update @langchain/core and @librechat/agents dependencies to latest versions
* refactor: remove deprecated @langchain/core dependency from package.json
* chore: remove unused SearchToolConfig and GetSourcesParams types from web.ts
* refactor: remove unused message properties from Message component
* refactor: enhance parallel content handling with groupId support in ContentParts and useStepHandler
* refactor: implement parallel content styling in Message, MessageRender, and ContentRender components. use explicit model name
* refactor: improve agent ID handling in createDualMessageContent for dual message display
* refactor: simplify title generation in AddedConvo by removing unused sender and preset logic
* refactor: replace string interpolation with cn utility for className in HoverButtons component
* refactor: enhance agent ID handling by adding suffix management for parallel agents and updating related components
* refactor: enhance column ordering in ContentParts by sorting agents with suffix management
* refactor: update @librechat/agents dependency to version 3.0.55
* feat: implement parallel content rendering with metadata support
- Added `ParallelContentRenderer` and `ParallelColumns` components for rendering messages in parallel based on groupId and agentId.
- Introduced `contentMetadataMap` to store metadata for each content part, allowing efficient parallel content detection.
- Updated `Message` and `ContentRender` components to utilize the new metadata structure for rendering.
- Modified `useStepHandler` to manage content indices and metadata during message processing.
- Enhanced `IJobStore` interface and its implementations to support storing and retrieving content metadata.
- Updated data schemas to include `contentMetadataMap` for messages, enabling multi-agent and parallel execution scenarios.
* refactor: update @librechat/agents dependency to version 3.0.56
* refactor: remove unused EPHEMERAL_AGENT_ID constant and simplify agent ID check
* refactor: enhance multi-agent message processing and primary agent determination
* refactor: implement branch message functionality for parallel responses
* refactor: integrate added conversation retrieval into message editing and regeneration processes
* refactor: remove unused isCard and isMultiMessage props from MessageRender and ContentRender components
* refactor: update @librechat/agents dependency to version 3.0.60
* refactor: replace usage of EPHEMERAL_AGENT_ID constant with isEphemeralAgentId function for improved clarity and consistency
* refactor: standardize agent ID format in tests for consistency
* chore: move addedConvo property to the correct position in payload construction
* refactor: rename agent_id values in loadAgent tests for clarity
* chore: reorder props in ContentParts component for improved readability
* refactor: rename variable 'content' to 'result' for clarity in RedisJobStore tests
* refactor: streamline useMessageActions by removing duplicate handleFeedback assignment
* chore: revert placeholder rendering logic MessageRender and ContentRender components to original
* refactor: implement useContentMetadata hook for optimized content metadata handling
* refactor: remove contentMetadataMap and related logic from the codebase and revert back to agentId/groupId in content parts
- Eliminated contentMetadataMap from various components and services, simplifying the handling of message content.
- Updated functions to directly access agentId and groupId from content parts instead of relying on a separate metadata map.
- Adjusted related hooks and components to reflect the removal of contentMetadataMap, ensuring consistent handling of message content.
- Updated tests and documentation to align with the new structure of message content handling.
* refactor: remove logging from groupParallelContent function to clean up output
* refactor: remove model parameter from TBranchMessageRequest type for simplification
* refactor: enhance branch message creation by stripping metadata for standalone content
* chore: streamline branch message creation by simplifying content filtering and removing unnecessary metadata checks
* refactor: include attachments in branch message creation for improved content handling
* refactor: streamline agent content processing by consolidating primary agent identification and filtering logic
* refactor: simplify multi-agent message processing by creating a dedicated mapping method and enhancing content filtering
* refactor: remove unused parameter from loadEphemeralAgent function for cleaner code
* refactor: update groupId handling in metadata to only set when provided by the server
* 🗑️ chore: Remove unused Legacy Provider clients and related helpers
* Deleted OpenAIClient and GoogleClient files along with their associated tests.
* Removed references to these clients in the clients index file.
* Cleaned up typedefs by removing the OpenAISpecClient export.
* Updated chat controllers to use the OpenAI SDK directly instead of the removed client classes.
* chore/remove-openapi-specs
* 🗑️ chore: Remove unused mergeSort and misc utility functions
* Deleted mergeSort.js and misc.js files as they are no longer needed.
* Removed references to cleanUpPrimaryKeyValue in messages.js and adjusted related logic.
* Updated mongoMeili.ts to eliminate local implementations of removed functions.
* chore: remove legacy endpoints
* chore: remove all plugins endpoint related code
* chore: remove unused prompt handling code and clean up imports
* Deleted handleInputs.js and instructions.js files as they are no longer needed.
* Removed references to these files in the prompts index.js.
* Updated docker-compose.yml to simplify reverse proxy configuration.
* chore: remove unused LightningIcon import from Icons.tsx
* chore: clean up translation.json by removing deprecated and unused keys
* chore: update Jest configuration and remove unused mock file
* Simplified the setupFiles array in jest.config.js by removing the fetchEventSource mock.
* Deleted the fetchEventSource.js mock file as it is no longer needed.
* fix: simplify endpoint type check in Landing and ConversationStarters components
* Updated the endpoint type check to use strict equality for better clarity and performance.
* Ensured consistency in the handling of the azureOpenAI endpoint across both components.
* chore: remove unused dependencies from package.json and package-lock.json
* chore: remove legacy EditController, associated routes and imports
* chore: update banResponse logic to refine request handling for banned users
* chore: remove unused validateEndpoint middleware and its references
* chore: remove unused 'res' parameter from initializeClient in multiple endpoint files
* chore: remove unused 'isSmallScreen' prop from BookmarkNav and NewChat components; clean up imports in ArchivedChatsTable and useSetIndexOptions hooks; enhance localization in PromptVersions
* chore: remove unused import of Constants and TMessage from MobileNav; retain only necessary QueryKeys import
* chore: remove unused TResPlugin type and related references; clean up imports in types and schemas
* refactor: Token Limit Processing with Enhanced Efficiency
- Added a new test suite for `processTextWithTokenLimit`, ensuring comprehensive coverage of various scenarios including under, at, and exceeding token limits.
- Refactored the `processTextWithTokenLimit` function to utilize a ratio-based estimation method, significantly reducing the number of token counting function calls compared to the previous binary search approach.
- Improved handling of edge cases and variable token density, ensuring accurate truncation and performance across diverse text inputs.
- Included direct comparisons with the old implementation to validate correctness and efficiency improvements.
* refactor: Remove Tokenizer Route and Related References
- Deleted the tokenizer route from the server and removed its references from the routes index and server files, streamlining the API structure.
- This change simplifies the routing configuration by eliminating unused endpoints.
* refactor: Migrate countTokens Utility to API Module
- Removed the local countTokens utility and integrated it into the @librechat/api module for centralized access.
- Updated various files to reference the new countTokens import from the API module, ensuring consistent usage across the application.
- Cleaned up unused references and imports related to the previous countTokens implementation.
* refactor: Centralize escapeRegExp Utility in API Module
- Moved the escapeRegExp function from local utility files to the @librechat/api module for consistent usage across the application.
- Updated imports in various files to reference the new centralized escapeRegExp function, ensuring cleaner code and reducing redundancy.
- Removed duplicate implementations of escapeRegExp from multiple files, streamlining the codebase.
* refactor: Enhance Token Counting Flexibility in Text Processing
- Updated the `processTextWithTokenLimit` function to accept both synchronous and asynchronous token counting functions, improving its versatility.
- Introduced a new `TokenCountFn` type to define the token counting function signature.
- Added comprehensive tests to validate the behavior of `processTextWithTokenLimit` with both sync and async token counting functions, ensuring consistent results.
- Implemented a wrapper to track call counts for the `countTokens` function, optimizing performance and reducing unnecessary calls.
- Enhanced existing tests to compare the performance of the new implementation against the old one, demonstrating significant improvements in efficiency.
* chore: documentation for Truncation Safety Buffer in Token Processing
- Added a safety buffer multiplier to the character position estimates during text truncation to prevent overshooting token limits.
- Updated the `processTextWithTokenLimit` function to utilize the new `TRUNCATION_SAFETY_BUFFER` constant, enhancing the accuracy of token limit processing.
- Improved documentation to clarify the rationale behind the buffer and its impact on performance and efficiency in token counting.
* 🕵️ feat: Enhance Index Sync and MeiliSearch filtering for User Field
- Implemented `ensureFilterableAttributes` function to configure MeiliSearch indexes for messages and conversations to filter by user.
- Updated sync logic to trigger a full re-sync if the user field is missing or index settings are modified.
- Adjusted search queries in Conversation and Message models to include user filtering.
- Ensured 'user' field is marked as filterable in MongoDB schema for both messages and conversations.
This update improves data integrity and search capabilities by ensuring user-related data is properly indexed and retrievable.
* fix: message processing in Search component to use linear list and not tree
* feat: Implement user filtering in MeiliSearch for shared links
* refactor: Optimize message search retrieval by batching database calls
* chore: Update MeiliSearch parameters type to use SearchParams for improved type safety
* 🐛 fix: Enhance provider validation and error handling in getProviderConfig function
* WIP: edit text part
* refactor: Allow updating of both TEXT and THINK content types in message updates
* WIP: first pass, save & submit
* chore: remove legacy generation user message field
* feat: merge edited content
* fix: update placeholder and description for bedrock setting
* fix: remove unsupported warning message for AI resubmission
* refactor: move model definitions and database-related methods to packages/data-schemas
* ci: update tests due to new DB structure
fix: disable mocking `librechat-data-provider`
feat: Add schema exports to data-schemas package
- Introduced a new schema module that exports various schemas including action, agent, and user schemas.
- Updated index.ts to include the new schema exports for better modularity and organization.
ci: fix appleStrategy tests
fix: Agent.spec.js
ci: refactor handleTools tests to use MongoMemoryServer for in-memory database
fix: getLogStores imports
ci: update banViolation tests to use MongoMemoryServer and improve session mocking
test: refactor samlStrategy tests to improve mock configurations and user handling
ci: fix crypto mock in handleText tests for improved accuracy
ci: refactor spendTokens tests to improve model imports and setup
ci: refactor Message model tests to use MongoMemoryServer and improve database interactions
* refactor: streamline IMessage interface and move feedback properties to types/message.ts
* refactor: use exported initializeRoles from `data-schemas`, remove api workspace version (this serves as an example of future migrations that still need to happen)
* refactor: update model imports to use destructuring from `~/db/models` for consistency and clarity
* refactor: remove unused mongoose imports from model files for cleaner code
* refactor: remove unused mongoose imports from Share, Prompt, and Transaction model files for cleaner code
* refactor: remove unused import in Transaction model for cleaner code
* ci: update deploy workflow to reference new Docker Dev Branch Images Build and add new workflow for building Docker images on dev branch
* chore: cleanup imports
* feat: working started for feedback implementation.
TODO:
- needs some refactoring.
- needs some UI animations.
* feat: working rate functionality
* feat: works now as well to reader the already rated responses from the server.
* feat: added the option to give feedback in text (optional)
* feat: added Dismiss option `x` to the `FeedbackTagOptions`
* ✨ feat: Add rating and ratingContent fields to message schema
* 🔧 chore: Bump version to 0.0.3 in package.json
* ✨ feat: Enhance feedback localization and update UI elements
* 🚀 feat: Implement feedback tagging system with thumbs up/down options
* 🚀 feat: Add data-provider package to unused i18n keys detection
* 🎨 style: update HoverButtons' style
* 🎨 style: Update HoverButtons and Fork components for improved styling and visibility
* 🔧 feat: Implement feedback system with rating and content options
* 🔧 feat: Enhance feedback handling with improved rating toggle and tag options
* 🔧 feat: Integrate toast notifications for feedback submission and clean up unused state
* 🔧 feat: Remove unused feedback tag options from translation file
* ✨ refactor: clean up Feedback component and improve HoverButtons structure
* ✨ refactor: remove unused settings switches for auto scroll, hide side panel, and user message markdown
* refactor: reorganize import order
* ✨ refactor: enhance HoverButtons and Fork components with improved styles and animations
* ✨ refactor: update feedback response phrases for improved user engagement
* ✨ refactor: add CheckboxOption component and streamline fork options rendering
* Refactor feedback components and logic
- Consolidated feedback handling into a single Feedback component, removing FeedbackButtons and FeedbackTagOptions.
- Introduced new feedback tagging system with detailed tags for both thumbs up and thumbs down ratings.
- Updated feedback schema to include new tags and improved type definitions.
- Enhanced user interface for feedback collection, including a dialog for additional comments.
- Removed obsolete files and adjusted imports accordingly.
- Updated translations for new feedback tags and placeholders.
* ✨ refactor: update feedback handling by replacing rating fields with feedback in message updates
* fix: add missing validateMessageReq middleware to feedback route and refactor feedback system
* 🗑️ chore: Remove redundant fork option explanations from translation file
* 🔧 refactor: Remove unused dependency from feedback callback
* 🔧 refactor: Simplify message update response structure and improve error logging
* Chore: removed unused tests.
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* ✨ 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>
* refactor(EditMessage): avoid manipulation of native paste handling, leverage react-hook-form for textarea changes
* style: apply better theming for MinimalIcon
* fix(useVoicesQuery/useCustomConfigSpeechQuery): make sure to only try request once per render
* feat: edit message content parts
* fix(useCopyToClipboard): handle both assistants and agents content blocks
* refactor: remove save & submit and update text content correctly
* chore(.env.example/config): exclude unsupported bedrock models
* feat: artifacts for aws bedrock
* fix: export options for bedrock conversations
* fix: edge case with debugTraverse function in parsers.js
* chore: Update error message in audio stream processing
* refactor: Add ONE_MINUTE and THIRTY_SECONDS options to Time enum
* fix: logging
* fix: do not throw errors for invalid convo id, simply return undefined
* feat: Add error handling and logging to message route definitions
* feat: Refactor Message.js to improve code organization and readability
* fix: Return undefined instead of throwing error for invalid conversation ID in Message.spec.js
* chore: remove unused code
* refactor: Update NewChatButtonIcon component to use JSX syntax
The NewChatButtonIcon component in the Nav folder has been updated to use JSX syntax instead of calling the Icon function directly. This change improves code readability and maintainability.
* remove use memo
* refactor: allow passing `select` to messages db query
* fix: initial fix for non-recursive messages
* ci: first pass, importers test rewrite
* fix(groupConversationsByDate): handle edge case of conversation.updatedAt being null
* fix: correctly handle non-recursive uploads
* feat: imports non-recursive conversations with branches correctly
* feat: support retaining original options on import
* refactor: Allow `messageTree` field for Import of non-recursive conversations
* 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
* feat: add global teardown to remove test data and add registration/log-out to auth flow
* refactor(models/Conversation): index user field and add JSDoc to deleteConvos
* refactor: add user index to message schema and ensure user is saved to each Message
* refactor: add user to each saveMessage call
* fix: handle case where title is null in zod schema
* feat(e2e): ensure messages are deleted on cleanUp
* fix: set last convo for all endpoints on conversation update
* fix: enable registration for CI env
* refactor: replace lodash import with specific function import
fix(api): esm imports to cjs
* refactor(Messages.tsx): convert to TS, out-source scrollToDiv logic to a custom hook
fix(ScreenshotContext.tsx): change Ref to RefObject in ScreenshotContextType
feat(useScrollToRef.ts): add useScrollToRef hook for scrolling to a ref with throttle
fix(Chat.tsx): update import path for Messages component
fix(Search.tsx): update import path for Messages component
* chore(types.ts): add TAskProps and TOptions types
refactor(useMessageHandler.ts): use TAskFunction type for ask function signature
* refactor(Message/Content): convert to TS, move Plugin component to Content dir
* feat(MessageContent.tsx): add MessageContent component for displaying and editing message content
feat(index.ts): export MessageContent component from Messages/Content directory
* wip(Message.jsx): conversion and use of new component in progress
* refactor: convert Message.jsx to TS and fix typing/imports based on changes
* refactor: add typed props and refactor MultiMessage to TS, fix typing issues resulting from the conversion
* edit message in progress
* feat: complete edit AI message logic, refactor continue logic
* feat(middleware): add validateMessageReq middleware
feat(routes): add validation for message requests using validateMessageReq middleware
feat(routes): add create, read, update, and delete routes for messages
* feat: complete frontend logic for editing messages in place
feat(messages.js): update route for updating a specific message
- Change the route for updating a message to include the messageId in the URL
- Update the request handler to use the messageId from the request parameters and the text from the request body
- Call the updateMessage function with the updated parameters
feat(MessageContent.tsx): add functionality to update a message
- Import the useUpdateMessageMutation hook from the data provider
- Destructure the conversationId, parentMessageId, and messageId from the message object
- Create a mutation function using the useUpdateMessageMutation hook
- Implement the updateMessage function to call the mutation function with the updated message parameters
- Update the messages state to reflect the updated message text
feat(api-endpoints.ts): update messages endpoint to include messageId
- Update the messages endpoint to include the messageId as an optional parameter
feat(data-service.ts): add updateMessage function
- Implement the updateMessage function to make a PUT request to
* fix(messages.js): make updateMessage function asynchronous and await its execution
* style(EditIcon): make icon active for AI message
* feat(gptPlugins/anthropic): add edit support
* fix(validateMessageReq.js): handle case when conversationId is 'new' and return empty array
feat(Message.tsx): pass message prop to SiblingSwitch component
refactor(SiblingSwitch.tsx): convert to TS
* fix(useMessageHandler.ts): remove message from currentMessages if isContinued is true
feat(useMessageHandler.ts): add support for submission messages in setMessages
fix(useServerStream.ts): remove unnecessary conditional in setMessages
fix(useServerStream.ts): remove isContinued variable from submission
* fix(continue): switch to continued message generation when continuing an earlier branch in conversation
* fix(abortMiddleware.js): fix condition to check partialText length
chore(abortMiddleware.js): add error logging when abortMessage fails
* refactor(MessageHeader.tsx): convert to TS
fix(Plugin.tsx): add default value for className prop in Plugin component
* refactor(MultiMessage.tsx): remove commented out code
docs(MultiMessage.tsx): update comment to clarify when siblingIdx is reset
* fix(GenerationButtons): optimistic state for continue button
* fix(MessageContent.tsx): add data-testid attribute to message text editor
fix(messages.spec.ts): update waitForServerStream function to include edit endpoint check
feat(messages.spec.ts): add test case for editing messages
* fix(HoverButtons & Message & useGenerations): Refactor edit functionality and related conditions
- Update enterEdit function signature and prop
- Create and utilize hideEditButton variable
- Enhance conditions for edit button visibility and active state
- Update button event handlers
- Introduce isEditableEndpoint in useGenerations and refine continueSupported condition.
* fix(useGenerations.ts): fix condition for hideEditButton to include error and searchResult
chore(data-provider): bump version to 0.1.6
fix(types.ts): add status property to TError type
* chore: bump @dqbd/tiktoken to 1.0.7
* fix(abortMiddleware.js): add required isCreatedByUser property to the error response object
* refactor(Message.tsx): remove unnecessary props from SiblingSwitch component, as setLatestMessage is firing on every switch already
refactor(SiblingSwitch.tsx): remove unused imports and code
* chore(BaseClient.js): move console.debug statements back inside if block
* feat(useMessageHandler.js/ts): Refactor and add features to handle user messages, support multiple endpoints/models, generate placeholder responses, regeneration, and stopGeneration function
fix(conversation.ts, buildTree.ts): Import TMessage type, handle null parentMessageId
feat(schemas.ts): Update and add schemas for various AI services, add default values, optional fields, and endpoint-to-schema mapping, create parseConvo function
chore(useMessageHandler.js, schemas.ts): Remove unused imports, variables, and chatGPT enum
* wip: add generation buttons
* refactor(cleanupPreset.ts): simplify cleanupPreset function
refactor(getDefaultConversation.js): remove unused code and simplify getDefaultConversation function
feat(utils): add getDefaultConversation function
This commit adds a new utility function called `getDefaultConversation` to the `client/src/utils/getDefaultConversation.ts` file. This function is responsible for generating a default conversation object based on the provided parameters.
The `getDefaultConversation` function takes in an object with the following properties:
- `conversation`: The conversation object to be used as a base.
- `endpointsConfig`: The configuration object containing information about the available endpoints.
- `preset`: An optional preset object that can be used to override the default behavior.
The function first tries to determine the target endpoint based on the preset object. If a valid endpoint is found, it is used as the target endpoint. If not, the function tries to retrieve the last conversation setup from the local storage and uses its endpoint if it is valid. If neither the preset nor the local storage contains a valid endpoint, the function falls back to a default endpoint.
Once the target endpoint is determined,
* fix(utils): remove console.error statement in buildDefaultConversation function
fix(schemas): add default values for catch blocks in openAISchema, googleSchema, bingAISchema, anthropicSchema, chatGPTBrowserSchema, and gptPluginsSchema
* fix: endpoint not changing on change of preset from other endpoint, wip: refactor
* refactor: preset items to TSX
* refactor: convert resetConvo to TS
* refactor(getDefaultConversation.ts): move defaultEndpoints array to the top of the file for better readability
refactor(getDefaultConversation.ts): extract getDefaultEndpoint function for better code organization and reusability
* feat(svg): add ContinueIcon component
feat(svg): add RegenerateIcon component
feat(svg): add ContinueIcon and RegenerateIcon components to index.ts
* feat(Button.tsx): add onClick and className props to Button component
feat(GenerationButtons.tsx): add logic to display Regenerate or StopGenerating button based on isSubmitting and messages
feat(Regenerate.tsx): create Regenerate component with RegenerateIcon and handleRegenerate function
feat(StopGenerating.tsx): create StopGenerating component with StopGeneratingIcon and handleStopGenerating function
* fix(TextChat.jsx): reorder imports and variables for better readability
fix(TextChat.jsx): fix typo in condition for isNotAppendable variable
fix(TextChat.jsx): remove unused handleStopGenerating function
fix(ContinueIcon.tsx): remove unnecessary closing tags for polygon elements
fix(useMessageHandler.ts): add missing type annotations for handleStopGenerating and handleRegenerate functions
fix(useMessageHandler.ts): remove unused variables in return statement
* fix(getDefaultConversation.ts): refactor code to use getLocalStorageItems function
feat(getLocalStorageItems.ts): add utility function to retrieve items from local storage
* fix(OpenAIClient.js): add support for streaming result in sendCompletion method
feat(OpenAIClient.js): add finish_reason metadata to opts in sendCompletion method
feat(Message.js): add finish_reason field to Message model
feat(messageSchema.js): add finish_reason field to messageSchema
feat(openAI.js): parse chatGptLabel and promptPrefix from req.body and pass rest of the modelOptions to endpointOption
feat(openAI.js): add addMetadata function to store metadata in ask function
feat(openAI.js): add metadata to response if available
feat(schemas.ts): add finish_reason field to tMessageSchema
* feat(types.ts): add TOnClick and TGenButtonProps types for button components
feat(Continue.tsx): create Continue component for generating button
feat(GenerationButtons.tsx): update GenerationButtons component to use Continue component
feat(Regenerate.tsx): create Regenerate component for regenerating button
feat(Stop.tsx): create Stop component for stop generating button
* feat(MessageHandler.jsx): add MessageHandler component to handle messages and conversations
fix(Root.jsx): fix import paths for Nav and MessageHandler components
* feat(useMessageHandler.ts): add support for generation parameter in ask function
feat(useMessageHandler.ts): add support for isEdited parameter in ask function
feat(useMessageHandler.ts): add support for continueGeneration function
fix(createPayload.ts): replace endpoint URL when isEdited parameter is true
* chore(client): set skipLibCheck to true in tsconfig.json
* fix(useMessageHandler.ts): remove unused clientId variable
fix(schemas.ts): make clientId field in tMessageSchema nullable and optional
* wip: edit route for continue generation
* refactor(api): move handlers to root of routes dir
* fix(useMessageHandler.ts): initialize currentMessages to an empty array if messages is null
fix(useMessageHandler.ts): update initialResponse text to use responseText variable
fix(useMessageHandler.ts): update setMessages logic for isRegenerate case
fix(MessageHandler.jsx): update setMessages logic for cancelHandler, createdHandler, and finalHandler
* fix(schemas.ts): make createdAt and updatedAt fields optional and set default values using new Date().toISOString()
fix(schemas.ts): change type annotation of TMessage from infer to input
* refactor(useMessageHandler.ts): rename AskProps type to TAskProps
refactor(useMessageHandler.ts): remove generation property from ask function arguments
refactor(useMessageHandler.ts): use nullish coalescing operator (??) instead of logical OR (||)
refactor(useMessageHandler.ts): pass the responseMessageId to message prop of submission
* fix(BaseClient.js): use nullish coalescing operator (??) instead of logical OR (||) for default values
* fix(BaseClient.js): fix responseMessageId assignment in handleStartMethods method
feat(BaseClient.js): add support for isEdited flag in sendMessage method
feat(BaseClient.js): add generation to responseMessage text in sendMessage method
* fix(openAI.js): remove unused imports and commented out code
feat(openAI.js): add support for generation parameter in request body
fix(openAI.js): remove console.log statement
fix(openAI.js): remove unused variables and parameters
fix(openAI.js): update response text in case of error
fix(openAI.js): handle error and abort message in case of error
fix(handlers.js): add generation parameter to createOnProgress function
fix(useMessageHandler.ts): update responseText variable to use generation parameter
* refactor(api/middleware): move inside server dir
* refactor: add endpoint specific, modular functions to build options and initialize clients, create server/utils, move middleware, separate utils into api general utils and server specific utils
* fix(abortMiddleware.js): import getConvo and getConvoTitle functions from models
feat(abortMiddleware.js): add abortAsk function to abortController to handle aborting of requests
fix(openAI.js): import buildOptions and initializeClient functions from endpoints/openAI
refactor(openAI.js): use getAbortData function to get data for abortAsk function
* refactor: move endpoint specific logic to an endpoints dir
* refactor(PluginService.js): fix import path for encrypt and decrypt functions in PluginService.js
* feat(openAI): add new endpoint for adding a title to a conversation
- Added a new file `addTitle.js` in the `api/server/routes/endpoints/openAI` directory.
- The `addTitle.js` file exports a function `addTitle` that takes in request parameters and performs the following actions:
- If the `parentMessageId` is `'00000000-0000-0000-0000-000000000000'` and `newConvo` is true, it proceeds with the following steps:
- Calls the `titleConvo` function from the `titleConvo` module, passing in the necessary parameters.
- Calls the `saveConvo` function from the `saveConvo` module, passing in the user ID and conversation details.
- Updated the `index.js` file in the `api/server/routes/endpoints/openAI` directory to export the `addTitle` function.
- This change adds
* fix(abortMiddleware.js): remove console.log statement
refactor(gptPlugins.js): update imports and function parameters
feat(gptPlugins.js): add support for abortController and getAbortData
refactor(openAI.js): update imports and function parameters
feat(openAI.js): add support for abortController and getAbortData
fix(openAI.js): refactor code to use modularized functions and middleware
fix(buildOptions.js): refactor code to use destructuring and update variable names
* refactor(askChatGPTBrowser.js, bingAI.js, google.js): remove duplicate code for setting response headers
feat(askChatGPTBrowser.js, bingAI.js, google.js): add setHeaders middleware to set response headers
* feat(middleware): validateEndpoint, refactor buildOption to only be concerned of endpointOption
* fix(abortMiddleware.js): add 'finish_reason' property with value 'incomplete' to responseMessage object
fix(abortMessage.js): remove console.log statement for aborted message
fix(handlers.js): modify tokens assignment to handle empty generation string and trailing space
* fix(BaseClient.js): import addSpaceIfNeeded function from server/utils
fix(BaseClient.js): add space before generation in text property
fix(index.js): remove getCitations and citeText exports
feat(buildEndpointOption.js): add buildEndpointOption middleware
fix(index.js): import buildEndpointOption middleware
fix(anthropic.js): remove buildOptions function and use endpointOption from req.body
fix(gptPlugins.js): remove buildOptions function and use endpointOption from req.body
fix(openAI.js): remove buildOptions function and use endpointOption from req.body
feat(utils): add citations.js and handleText.js modules
fix(utils): fix import statements in index.js module
* refactor(gptPlugins.js): use getResponseSender function from librechat-data-provider
* feat(gptPlugins): complete 'continue generating'
* wip: anthropic continue regen
* feat(middleware): add validateRegistration middleware
A new middleware function called `validateRegistration` has been added to the list of exported middleware functions in `index.js`. This middleware is responsible for validating registration data before allowing the registration process to proceed.
* feat(Anthropic): complete continue regen
* chore: add librechat-data-provider to api/package.json
* fix(ci): backend-review will mock meilisearch, also installs data-provider as now needed
* chore(ci): remove unneeded SEARCH env var
* style(GenerationButtons): make text shorter for sake of space economy, even though this diverges from chat.openai.com
* style(GenerationButtons/ScrollToBottom): adjust visibility/position based on screen size
* chore(client): 'Editting' typo
* feat(GenerationButtons.tsx): add support for endpoint prop in GenerationButtons component
feat(OptionsBar.tsx): pass endpoint prop to GenerationButtons component
feat(useGenerations.ts): create useGenerations hook to handle generation logic
fix(schemas.ts): add searchResult field to tMessageSchema
* refactor(HoverButtons): convert to TSX and utilize new useGenerations hook
* fix(abortMiddleware): handle error with res headers set, or abortController not found, to ensure proper API error is sent to the client, chore(BaseClient): remove console log for onStart message meant for debugging
* refactor(api): remove librechat-data-provider dep for now as it complicates deployed docker build stage, re-use code in CJS, located in server/endpoints/schemas
* chore: remove console.logs from test files
* ci: add backend tests for AnthropicClient, focusing on new buildMessages logic
* refactor(FakeClient): use actual BaseClient sendMessage method for testing
* test(BaseClient.test.js): add test for loading chat history
test(BaseClient.test.js): add test for sendMessage logic with isEdited flag
* fix(buildEndpointOption.js): add support for azureOpenAI in buildFunction object
wip(endpoints.js): fetch Azure models from Azure OpenAI API if opts.azure is true
* fix(Button.tsx): add data-testid attribute to button component
fix(SelectDropDown.tsx): add data-testid attribute to Listbox.Button component
fix(messages.spec.ts): add waitForServerStream function to consolidate logic for awaiting the server response
feat(messages.spec.ts): add test for stopping and continuing message and improve browser/page context order and closing
* refactor(onProgress): speed up time to save initial message for editable routes
* chore: disable AI message editing (for now), was accidentally allowed
* refactor: ensure continue is only supported for latest message style: improve styling in dark mode and across all hover buttons/icons, including making edit icon for AI invisible (for now)
* fix: add test id to generation buttons so they never resolve to 2+ items
* chore(package.json): add 'packages/' to the list of ignored directories
chore(data-provider/package.json): bump version to 0.1.5
* server-side JWT auth implementation
* move oauth routes and strategies, fix bugs
* backend modifications for wiring up the frontend login and reg forms
* Add frontend data services for login and registration
* Add login and registration forms
* Implment auth context, functional client side auth
* protect routes with jwt auth
* finish local strategy (using local storage)
* Start setting up google auth
* disable token refresh, remove old auth middleware
* refactor client, add ApiErrorBoundary context
* disable google and facebook strategies
* fix: fix presets not displaying specific to user
* fix: fix issue with browser refresh
* fix: casing issue with User.js (#11)
* delete user.js to be renamed
* fix: fix casing issue with User.js
* comment out api error watcher temporarily
* fix: issue with api error watcher (#12)
* delete user.js to be renamed
* fix: fix casing issue with User.js
* comment out api error watcher temporarily
* feat: add google auth social login
* fix: make google login url dynamic based on dev/prod
* fix: bug where UI is briefly displayed before redirecting to login
* fix: fix cookie expires value for local auth
* Update README.md
* Update LOCAL_INSTALL structure
* Add local testing instructions
* Only load google strategy if client id and secret are provided
* Update .env.example files with new params
* fix issue with not redirecting to register form
* only show google login button if value is set in .env
* cleanup log messages
* Add label to button for google login on login form
* doc: fix client/server url values in .env.example
* feat: add error message details to registration failure
* Restore preventing paste on confirm password
* auto-login user after registering
* feat: forgot password (#24)
* make login/reg pages look like openai's
* add password reset data services
* new form designs similar to openai, add password reset pages
* add api's for password reset
* email utils for password reset
* remove bcrypt salt rounds from process.env
* refactor: restructure api auth code, consolidate routes (#25)
* add api's for password reset
* remove bcrypt salt rounds from process.env
* refactor: consolidate auth routes, use controller pattern
* refactor: code cleanup
* feat: migrate data to first user (#26)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes after refactor (#27)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: issue with auto-login when logging out then logging in with new browser window (#28)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: fix issue with auto-login in new tab
* doc: Update README and .env.example files with user system information (#29)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: fix issue with auto-login in new tab
* doc: update README and .env.example files
* Fixup: LOCAL_INSTALL.md PS instructions (#200) (#30)
Co-authored-by: alfredo-f <alfredo.fomitchenko@mail.polimi.it>
* feat: send user with completion to protect against abuse (#31)
* Fixup: LOCAL_INSTALL.md PS instructions (#200)
* server-side JWT auth implementation
* move oauth routes and strategies, fix bugs
* backend modifications for wiring up the frontend login and reg forms
* Add frontend data services for login and registration
* Add login and registration forms
* Implment auth context, functional client side auth
* protect routes with jwt auth
* finish local strategy (using local storage)
* Start setting up google auth
* disable token refresh, remove old auth middleware
* refactor client, add ApiErrorBoundary context
* disable google and facebook strategies
* fix: fix presets not displaying specific to user
* fix: fix issue with browser refresh
* fix: casing issue with User.js (#11)
* delete user.js to be renamed
* fix: fix casing issue with User.js
* comment out api error watcher temporarily
* feat: add google auth social login
* fix: make google login url dynamic based on dev/prod
* fix: bug where UI is briefly displayed before redirecting to login
* fix: fix cookie expires value for local auth
* Only load google strategy if client id and secret are provided
* Update .env.example files with new params
* fix issue with not redirecting to register form
* only show google login button if value is set in .env
* cleanup log messages
* Add label to button for google login on login form
* doc: fix client/server url values in .env.example
* feat: add error message details to registration failure
* Restore preventing paste on confirm password
* auto-login user after registering
* feat: forgot password (#24)
* make login/reg pages look like openai's
* add password reset data services
* new form designs similar to openai, add password reset pages
* add api's for password reset
* email utils for password reset
* remove bcrypt salt rounds from process.env
* refactor: restructure api auth code, consolidate routes (#25)
* add api's for password reset
* remove bcrypt salt rounds from process.env
* refactor: consolidate auth routes, use controller pattern
* refactor: code cleanup
* feat: migrate data to first user (#26)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes after refactor (#27)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: issue with auto-login when logging out then logging in with new browser window (#28)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: fix issue with auto-login in new tab
* doc: Update README and .env.example files with user system information (#29)
* refactor: use /api for auth routes
* fix: use user id instead of username
* feat: migrate data to first user on register
* fix: fix social login routes
* fix: fix issue with auto-login in new tab
* doc: update README and .env.example files
* Send user id to openai to protect against abuse
* add meilisearch to gitignore
* Remove webpack
---------
Co-authored-by: alfredo-f <alfredo.fomitchenko@mail.polimi.it>
---------
Co-authored-by: Danny Avila <110412045+danny-avila@users.noreply.github.com>
Co-authored-by: Alfredo Fomitchenko <alfredo.fomitchenko@mail.polimi.it>
