release-tag / Resolve release metadata (push) Successful in 30s
release-tag / Build knowledge (push) Failing after 4m51s
release-tag / Build control (push) Failing after 5m0s
release-tag / Build agent (push) Failing after 5m0s
release-tag / Build agent-data-init (push) Failing after 5m5s
release-tag / Build neuroforge-worker (push) Failing after 5m7s
release-tag / Build neuroforge (push) Failing after 5m9s
34 lines
1.3 KiB
YAML
34 lines
1.3 KiB
YAML
groups:
|
|
- name: neuroforge
|
|
rules:
|
|
- alert: NeuroForgeDown
|
|
expr: up{job="neuroforge"} == 0
|
|
for: 2m
|
|
labels: {severity: critical}
|
|
annotations:
|
|
summary: "NeuroForge is unavailable"
|
|
- alert: NeuroForgeHTTP5xx
|
|
expr: sum(rate(neuroforge_http_requests_total{code=~"5.."}[5m])) > 0.1
|
|
for: 5m
|
|
labels: {severity: warning}
|
|
annotations:
|
|
summary: "NeuroForge is returning 5xx responses"
|
|
- alert: NeuroForgeClusterCommitLag
|
|
expr: neuroforge_cluster_log_index - neuroforge_cluster_commit_index > 100
|
|
for: 5m
|
|
labels: {severity: warning}
|
|
annotations:
|
|
summary: "NeuroForge cluster commit lag is growing"
|
|
- alert: NeuroForgePageCacheThrash
|
|
expr: rate(neuroforge_page_cache_evictions_total[10m]) > 10
|
|
for: 10m
|
|
labels: {severity: warning}
|
|
annotations:
|
|
summary: "NeuroForge page cache is evicting aggressively"
|
|
- alert: NeuroForgeDailyBudget80Percent
|
|
expr: neuroforge_openai_cost_usd{period="day"} / clamp_min(neuroforge_openai_budget_usd{period="day"}, 0.000001) > 0.8
|
|
for: 5m
|
|
labels: {severity: warning}
|
|
annotations:
|
|
summary: "NeuroForge OpenAI daily budget is above 80%"
|