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
Description
Self-hosted multi-user AI agent platform — web dashboard, TUI, remote control, shared memory, mission orchestration
16 MiB
2026-04-08 00:42:54 +00:00
Languages
TypeScript 74.5%
Shell 19.7%
PowerShell 3%
JavaScript 1.4%
Python 1%
Other 0.4%