No description
Find a file
jtricerolph 50ef00c336 Fix AI insight output truncation — bump token cap, enforce bullet brevity
Live-tested on the dev stack: with the more verbose Sonnet model, the old
550-token cap cut the last bullet off mid-sentence. Bumped to 800 and told
the model to keep each bullet to 1-2 sentences so it isn't relying on the
cap alone to stay in bounds.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-24 19:39:26 +00:00
backend Fix AI insight output truncation — bump token cap, enforce bullet brevity 2026-07-24 19:39:26 +00:00
db Forecasting app: hybrid port to HNF stack 2026-07-04 18:49:34 +00:00
frontend Expand AI insight: fix broken competitor query, add continuity, 30-day horizon, holidays 2026-07-24 18:03:31 +00:00
.gitignore Forecasting app: hybrid port to HNF stack 2026-07-04 18:49:34 +00:00
docker-compose.yml NewBook credentials from central Settings service 2026-07-04 19:36:41 +00:00
seed-app.js Forecasting app: hybrid port to HNF stack 2026-07-04 18:49:34 +00:00