diff --git a/deploy/monitoring/llmgw-rules.yml b/deploy/monitoring/llmgw-rules.yml index 67cacd67..3940ecb9 100644 --- a/deploy/monitoring/llmgw-rules.yml +++ b/deploy/monitoring/llmgw-rules.yml @@ -156,6 +156,18 @@ groups: llmgw-backup.service` on the control plane says why the last one failed; docs/install.md, "Backing up", says how to set it up. + - alert: ModelUpdateAvailable + expr: llmgw_model_update_available == 1 + for: 1h + labels: { severity: info } + annotations: + summary: "{{ $labels.repo }} has new weights for {{ $labels.model }}" + description: >- + The registry repository the model was served from has published + different files under the same names. `llmgw ctl model updates` + lists what changed; `llmgw ctl model update {{ $labels.model }}` + moves it to them, and `llmgw ctl model rollback` goes back. + - alert: PoolSaturated expr: llmgw_pool_saturation > 1 for: 5m diff --git a/internal/cli/server.go b/internal/cli/server.go index d820e0b9..2a79d450 100644 --- a/internal/cli/server.go +++ b/internal/cli/server.go @@ -184,8 +184,8 @@ func newServerCmd() *cobra.Command { if err := rt.RegisterMetrics(fleetmetrics.New(ctl)); err != nil { return err } - // Whether models' repositories have new weights; filled in - // once the mirror is set up, below. + // Whether models' repositories have new weights; given its + // source once the mirror is set up, below. if err := rt.RegisterMetrics(updateMetrics); err != nil { return err }