Tomas Kracmar a255be93fe feat: aggregate large event sets before sending to LLM ...

When a query matches >50 events, the LLM now receives:
- Aggregated counts by service, operation, result, and actor
- A list of failures (up to 10)
- The 50 most recent raw events as samples

This scales to thousands of events without blowing the token budget
or losing signal. The LLM gets a bird's-eye view plus concrete examples.

Also updates the system prompt to handle both individual event lists
and aggregated overviews correctly.

2026-04-20 16:23:55 +02:00

..

ask.py

feat: aggregate large event sets before sending to LLM

2026-04-20 16:23:55 +02:00

config.py

feat: implement Phase 2 stabilization

2026-04-14 12:02:28 +02:00

events.py

style: apply ruff formatting to all backend files

2026-04-16 18:58:41 +02:00

fetch.py

style: apply ruff formatting to all backend files

2026-04-16 18:58:41 +02:00

health.py

style: apply ruff formatting to all backend files

2026-04-16 18:58:41 +02:00

rules.py

feat: implement Phase 4 enhancements

2026-04-14 15:38:39 +02:00

webhooks.py

feat: implement Phase 3 scaling

2026-04-14 14:58:50 +02:00