feat: issue 305: add streamed response performance benchmarks#378
Merged
imDarshanGK merged 6 commits intoJun 12, 2026
Conversation
|
@SagarSawlani is attempting to deploy a commit to the Darshan's projects Team on Vercel. A member of the Team first needs to authorize it. |
Owner
|
@SagarSawlani resolve conflicts |
…-benchmarks-for-streamed-responses
Contributor
Author
|
@imDarshanGK Done. Can you just verify once |
Owner
|
@SagarSawlani resolve conflict |
…-benchmarks-for-streamed-responses
Contributor
Author
|
Hi @imDarshanGK I've just resolved the merge conflicts in api.js. Could you please take a look when you have a moment? Since api.js gets updated frequently, merging this soon would help prevent another round of conflicts. Thank you! |
Owner
|
@SagarSawlani issue number |
Contributor
Author
|
imDarshanGK
added
SSoC26
imDarshanGK
approved these changes
Jun 12, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Backend Tracking: Computes Time to First Token (TTFT), Total Duration, Token Count, and System RAM Usage (using psutil) for each stream request.
Database Schema Migration: Updates the SQLite messages table schema with a benchmarks column to persist these metrics.
Frontend Stats Popover: Adds a performance icon button (zigzag chart) below assistant responses. Hovering over the button displays a statistics card directly to its right, cleanly aligned with the button to prevent layout shifting, scrolling, or flickering.
RAM Explanation Tooltip: Includes a small circled ⓘ info icon next to the RAM metric. Hovering over it explains: "Total system memory in use across all processes, not just the LLM."
Replaced the single-message export button under assistant responses with a modern Copy button.
Clicking it copies the raw assistant message content to the clipboard and shows a green checkmark feedback icon temporarily.
Re-added the plus circle button (+) next to the chat text area.
Clicking the plus button opens a dropdown to trigger the Use Prompt Template modal.
Includes support for selecting a template chip and updates the send button states so that users can submit template-based requests.