Skip to content

perf: reduce repeated chat lookups and restore regressions#300

Open
FRBIE wants to merge 3 commits intodecolua:masterfrom
FRBIE:perf/chat-request-cache
Open

perf: reduce repeated chat lookups and restore regressions#300
FRBIE wants to merge 3 commits intodecolua:masterfrom
FRBIE:perf/chat-request-cache

Conversation

@FRBIE
Copy link

@FRBIE FRBIE commented Mar 13, 2026

Summary

  • cache repeated local DB reads within a single chat request so combo resolution, provider lookup, and settings reuse the same request context
  • restore OpenAI request normalization for text-only Claude payloads and raw NDJSON stream parsing so translator behavior matches existing expectations
  • fix Cursor auto-import platform handling and fallback errors, then bring the Vitest suite back to green

Testing

  • bash -lc ./node_modules/.bin/vitest run --reporter=verbose --config ./vitest.config.js

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant