Files
dc-recorder/src
MythEclipseandClaude Opus 4.7 81bb9cc6ab perf: maximize AI batches by token budget
Batch AI moderation by estimated token budget instead of fixed message count. Send as many messages as fit within an 80k token request budget while keeping one concurrent API request. Include message metadata and chronological conversation context so the model can judge provocation and replies from surrounding discussion.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 04:42:28 +07:00
..
2026-05-13 15:28:25 +07:00
2026-05-13 15:28:25 +07:00
2026-05-13 15:28:25 +07:00
2026-05-13 15:54:54 +07:00