Jason Woltje 1d4916fe97 feat(P4-004): summarization pipeline — LLM + cron scheduling ...

Add SummarizationService that reads hot agent logs (>24h), groups by
session, calls a cheap LLM (gpt-4o-mini default, configurable via
SUMMARIZATION_MODEL) to extract key insights, stores them with
embeddings in the insights table, and transitions processed logs to
warm tier. Add CronService with node-cron for scheduled execution
(summarization every 6h, tier management daily at 3am). Tier
management promotes warm→cold (30d) and purges cold logs (90d).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-13 08:52:52 -05:00

332 KiB

Raw Blame History

View Raw