Add radar/precipitation freshness context to AI summaries #18

Closed
opened 2026-06-23 23:15:27 +00:00 by rbrooks · 1 comment
Owner

Target release: v1.3.0

Add radar/media freshness or coarse precipitation context to AI summaries when useful.

Source: docs/ROADMAP.md → Local LLM Alert Summarization → "Post-Phase 3 candidates".

**Target release:** v1.3.0 Add radar/media freshness or coarse precipitation context to AI summaries when useful. Source: `docs/ROADMAP.md` → Local LLM Alert Summarization → "Post-Phase 3 candidates".
Contributor

Done in #104 (merged). A small factual radar-freshness field is added to the AI context — radar_station, local last-updated time, age_minutes, and a human "radar imagery last updated N minutes ago" description (with an ok/stale status vs the 2h media threshold) — derived from the media: freshness rows for the location's nearest radar. DB-only (no network, no imagery), so it's ungated. Local providers only (cloud whitelist), consistent with the other context fields.

Done in #104 (merged). A small factual radar-freshness field is added to the AI context — `radar_station`, local last-updated time, `age_minutes`, and a human "radar imagery last updated N minutes ago" description (with an ok/stale status vs the 2h media threshold) — derived from the `media:` freshness rows for the location's nearest radar. DB-only (no network, no imagery), so it's ungated. Local providers only (cloud whitelist), consistent with the other context fields.
Sign in to join this conversation.
No project
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
rbrooks/WeatherBot#18
No description provided.