fix(llm): switch models and add monitor auto-reset - #28
Merged
Merged
Conversation
- Replace unreliable nvidia model with xiaomi/mimo-v2-flash:free as primary
- Use mistralai/devstral-2512:free as single fallback tier
- Remove fallback2 (3-tier reduced to 2-tier) for simpler retry logic
- Add resetMonitorCheckpoint() function to supabase.ts
- Add auto-reset in sui-monitor when gap exceeds 50k checkpoints
- Add POST /api/admin/reset-checkpoint endpoint for manual recovery
- Export LIVE_BOOTSTRAP_OFFSET constant for reuse
The nvidia model was returning HTTP 200 with invalid JSON (empty {}),
causing parse failures that didn't trigger fallback. Monitor checkpoints
were stuck 3.5M behind due to old database values from prior deploys.
- Move search bar next to Start Analysis button for better UX - Add sort dropdown (newest, oldest, highest/lowest risk) - Remove unused Card import - Clean up search result display styling - Reduce file size by 120 lines through layout consolidation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Changes
Backend (LLM Fix)
nvidia/nemotron-3-nano-30b-a3b:freewithxiaomi/mimo-v2-flash:freeas primarymistralai/devstral-2512:freeas single fallback (simplified from 3-tier to 2-tier)getSecondFallbackConfigand simplify retry logicBackend (Monitor Reset)
resetMonitorCheckpoint()function to supabase.tsPOST /api/admin/reset-checkpointendpoint for manual recoveryLIVE_BOOTSTRAP_OFFSETconstant for reuseFrontend
Test plan