rcourtman 9c58bfa127 perf: reduce MetricSamples from 100 to 24 points ...

100 samples was causing 326k+ input tokens which is expensive.
24 samples (hourly resolution) still provides good pattern visibility
while significantly reducing token cost.

Estimated reduction: ~75% fewer metric tokens.

2025-12-21 22:56:19 +00:00

..

builder_test.go

fix: Allow Host Agent thresholds to be set to 0 to disable alerting. Related to #864

2025-12-20 20:25:20 +00:00

builder.go

perf: reduce MetricSamples from 100 to 24 points

2025-12-21 22:56:19 +00:00

formatter_test.go

feat(ai): pass raw metric samples to LLM for pattern interpretation

2025-12-21 21:09:24 +00:00

formatter.go

fix: use 24h window for MetricSamples (matches in-memory retention)

2025-12-21 22:19:40 +00:00

trends_test.go

fix: Allow Host Agent thresholds to be set to 0 to disable alerting. Related to #864

2025-12-20 20:25:20 +00:00

trends.go

feat(thresholds): add collapsible accordion sections and UX improvements

2025-12-18 15:47:44 +00:00

types.go

feat(ai): pass raw metric samples to LLM for pattern interpretation

2025-12-21 21:09:24 +00:00