diff --git a/nix/host-modules/swarm-grafana.nix b/nix/host-modules/swarm-grafana.nix index 0ba6b51c..1e9fde3f 100644 --- a/nix/host-modules/swarm-grafana.nix +++ b/nix/host-modules/swarm-grafana.nix @@ -61,6 +61,7 @@ let "agents.json" "authelia.json" "claude-usage.json" + "forge.json" "logstore.json" "metricstore.json" "queue.json" diff --git a/nix/host-modules/swarm-grafana/dashboards/forge.json b/nix/host-modules/swarm-grafana/dashboards/forge.json new file mode 100644 index 00000000..1102ae2f --- /dev/null +++ b/nix/host-modules/swarm-grafana/dashboards/forge.json @@ -0,0 +1,414 @@ +{ + "title": "hyperhive · forge (content)", + "uid": "hyperhive-swarm-forge", + "description": "An INVENTORY board, not a service-health board — and the difference is the first thing to know about it. Its three siblings (metrics store, log store, authelia) answer 'is this service healthy': request rates, error rates, latency. Forgejo's exporter publishes no such series; what it publishes is a census of what the forge CONTAINS. So every number here is a gauge of stored things, sampled at scrape time. Nothing on this board can tell you the forge is slow or erroring, and a flat line means nobody created anything, not that scraping stopped — check the metrics-store board for that. Series are labelled service.name, NOT job; there is no job label in this store.", + "editable": true, + "refresh": "5m", + "schemaVersion": 39, + "tags": ["hyperhive", "swarm", "forge", "content"], + "time": { "from": "now-7d", "to": "now" }, + "timezone": "utc", + "version": 1, + "templating": { "list": [] }, + "panels": [ + { + "id": 1, + "type": "stat", + "title": "Repositories", + "description": "Every repo the forge holds, including agent config repos — which is most of them on a busy hive, so this tracks agent count more closely than it tracks project count.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 4, "w": 4, "x": 0, "y": 0 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_repositories", + "instant": true, + "legendFormat": "repos" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "fixed", "fixedColor": "text" }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false } + } + }, + { + "id": 2, + "type": "stat", + "title": "Users", + "description": "Forge accounts. Agents hold one each, so this is operators plus the live agent roster — a drop without a matching agent teardown is worth a look.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 4, "w": 4, "x": 4, "y": 0 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_users", + "instant": true, + "legendFormat": "users" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "fixed", "fixedColor": "text" }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false } + } + }, + { + "id": 3, + "type": "stat", + "title": "Organizations", + "description": "Orgs — the forge's coarsest grouping, and on a hyperhive forge the line between agent-owned repos and everything else. A change is a structural decision someone made rather than activity; how often that happens is a fact about this hive's projects, not something the panel can assume.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 4, "w": 4, "x": 8, "y": 0 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_organizations", + "instant": true, + "legendFormat": "orgs" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "fixed", "fixedColor": "text" }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false } + } + }, + { + "id": 4, + "type": "stat", + "title": "Issues open", + "description": "Open issues across every repo. The one number on this board that behaves like a backlog gauge — rising means work is being filed faster than it is closed.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 4, "w": 4, "x": 12, "y": 0 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_issues_open", + "instant": true, + "legendFormat": "open" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "fixed", "fixedColor": "text" }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false } + } + }, + { + "id": 5, + "type": "stat", + "title": "Issues closed", + "description": "Cumulative closed issues. Only ever rises, so read it as throughput-to-date rather than as a current state.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 4, "w": 4, "x": 16, "y": 0 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_issues_closed", + "instant": true, + "legendFormat": "closed" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "fixed", "fixedColor": "text" }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false } + } + }, + { + "id": 6, + "type": "stat", + "title": "Releases", + "description": "Tagged releases across every repo. Cumulative, so it only rises; the rate is the signal, not the level. Whether zero is normal here depends entirely on how this hive's projects ship — a board shipped to every hive cannot know that, so read a CHANGE rather than a value.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 4, "w": 4, "x": 20, "y": 0 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_releases", + "instant": true, + "legendFormat": "releases" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "fixed", "fixedColor": "text" }, + "mappings": [] + }, + "overrides": [] + }, + "options": { + "graphMode": "none", + "colorMode": "value", + "textMode": "value", + "justifyMode": "auto", + "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false } + } + }, + { + "id": 10, + "type": "timeseries", + "title": "Issues: open vs closed", + "description": "The two together, because either alone misleads. Open flat while closed climbs is a backlog being worked down; both climbing together is a backlog growing while work happens. ⚠️ A vertical step in closed is a batch operation of some kind — a bulk close, an import, a repo removal — and is not distinguishable here from a burst of real work; the issue list is what tells them apart.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_issues_open", + "legendFormat": "open" + }, + { + "refId": "B", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_issues_closed", + "legendFormat": "closed" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "palette-classic" }, + "custom": { + "drawStyle": "line", + "lineWidth": 1, + "fillOpacity": 10, + "showPoints": "never", + "spanNulls": false, + "axisSoftMin": 0 + } + }, + "overrides": [] + }, + "options": { + "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true, "calcs": [] }, + "tooltip": { "mode": "multi", "sort": "desc" } + } + }, + { + "id": 11, + "type": "timeseries", + "title": "Repositories and users", + "description": "Both climb when an agent is created — a config repo and an account arrive together. So the interesting reading is when they DIVERGE: repos without users means repos created by hand, users without repos means accounts provisioned for something that never got one.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_repositories", + "legendFormat": "repos" + }, + { + "refId": "B", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_users", + "legendFormat": "users" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "palette-classic" }, + "custom": { + "drawStyle": "line", + "lineWidth": 1, + "fillOpacity": 0, + "showPoints": "never", + "spanNulls": false, + "axisSoftMin": 0 + } + }, + "overrides": [] + }, + "options": { + "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true, "calcs": [] }, + "tooltip": { "mode": "multi", "sort": "desc" } + } + }, + { + "id": 20, + "type": "timeseries", + "title": "Discussion volume", + "description": "Comments and review comments across the forge. The closest thing here to an activity signal, and still a cumulative count rather than a rate — a steepening slope is more conversation, a flat stretch is a quiet period, and neither says anything about whether the forge is up.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 7, "w": 12, "x": 0, "y": 12 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_comments", + "legendFormat": "comments" + }, + { + "refId": "B", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_attachments", + "legendFormat": "attachments" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "palette-classic" }, + "custom": { + "drawStyle": "line", + "lineWidth": 1, + "fillOpacity": 10, + "showPoints": "never", + "spanNulls": false, + "axisSoftMin": 0 + } + }, + "overrides": [] + }, + "options": { + "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true, "calcs": [] }, + "tooltip": { "mode": "multi", "sort": "desc" } + } + }, + { + "id": 21, + "type": "timeseries", + "title": "Automation surface", + "description": "Webhooks and their queued delivery tasks. Worth a glance when something that should have triggered did not: a hooktask count that climbs and never settles is deliveries backing up rather than being consumed. The webhook count itself is whatever this hive has wired — it says nothing on its own, and a jump in it is someone's integration change.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 7, "w": 12, "x": 12, "y": 12 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_webhooks", + "legendFormat": "webhooks" + }, + { + "refId": "B", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "gitea_hooktasks", + "legendFormat": "hooktasks" + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "color": { "mode": "palette-classic" }, + "custom": { + "drawStyle": "line", + "lineWidth": 1, + "fillOpacity": 0, + "showPoints": "never", + "spanNulls": false, + "axisSoftMin": 0 + } + }, + "overrides": [] + }, + "options": { + "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true, "calcs": [] }, + "tooltip": { "mode": "multi", "sort": "desc" } + } + }, + { + "id": 30, + "type": "bargauge", + "title": "Issues by label — every issue ever, ranked", + "description": "How the whole issue corpus is distributed across labels, biggest first. NOT the open backlog: this metric counts open and closed issues alike, which is checkable from this board alone — the top label here is far larger than the Issues open stat beside it, and no single label can outnumber the issues it is a subset of. So read it as the shape of what the project has worked on, not as what is left. It is also a RANKING of one moment rather than a time series: the label set is as wide as the tracker's, so one line per label is unreadable by construction, and the history of any single label is an ad-hoc query, not a panel. Colour carries no meaning here; the axis carries the identity. If the panel is empty, check whether the forgejo process restarted since [metrics] last changed — a merged config alone does not enable a series, and an absent series never says why it is absent.", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "gridPos": { "h": 16, "w": 24, "x": 0, "y": 19 }, + "targets": [ + { + "refId": "A", + "datasource": { "type": "prometheus", "uid": "@datasourceUid@" }, + "expr": "sort_desc(gitea_issues_by_label)", + "legendFormat": "{{label}}", + "instant": true + } + ], + "fieldConfig": { + "defaults": { + "unit": "short", + "decimals": 0, + "min": 0, + "color": { "mode": "fixed", "fixedColor": "semi-dark-blue" }, + "noValue": "no series — check whether the forgejo process restarted since [metrics] last changed; an absent series never says why it is absent" + }, + "overrides": [] + }, + "options": { + "orientation": "horizontal", + "displayMode": "basic", + "showUnfilled": true, + "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false } + } + } + ] +}