Alex-GilbertandClaude Opus 4.6 672bdc3223 fix: batch LLM validation, stream results, improve scoring prompt
- Batch candidates in groups of 50 (was 200) to avoid output token
  truncation that caused all-zero scores
- Stream scored results via SSE as each batch completes instead of
  waiting for all batches to finish
- Include solve_id in done event so validate works when results fit
  in a single page
- Rewrite prompt to judge sentence coherence ("does it make sense")
  rather than word predictability ("is it expected")
- Frontend inserts results in score-sorted order as they arrive

Co-Authored-By: Claude Opus 4.6 <[email protected]>
2026-02-23 21:17:00 -06:00
S
Description
No description provided
MIT
6.9 MiB
0 Stars 1 Watchers 0 Forks
Languages
Python 65.5%
JavaScript 16.7%
Rust 10.6%
CSS 4.2%
HTML 1.8%
Other 1.2%