You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/helm.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -63,7 +63,7 @@ Use `get_helm_release` for detail:
63
63
-`include=notes_diff` returns release notes diff.
64
64
-`include=resource_diff` returns added/removed/unchanged rendered resource identities between revisions.
65
65
66
-
`get_changes`is intentionally Kubernetes-resource timeline data, not Helm release history. For Helm deployments, use the Helm MCP tools above.
66
+
`get_changes`includes the Kubernetes-resource timeline plus recent native Helm release deployment and operation history (`source: helm`). Use it when an agent asks what changed before an incident. For full Helm revision history, operation details, hook diagnostics, values, and diffs, use the Helm MCP tools above.
Copy file name to clipboardExpand all lines: docs/mcp.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -184,8 +184,8 @@ Add to `~/.gemini/settings.json`:
184
184
185
185
| Tool | Description | Parameters |
186
186
|------|-------------|------------|
187
-
|`issues`| "What's broken right now?" — a ranked, curated stream of live operational failures: failing workloads/pods, dangling references, pod-startup blockers (unschedulable / admission-rejected / stuck post-bind), and False CRD conditions. No source filter; each row carries a `source` label sliceable via `filter`. Recovered Helm rollbacks are deploy history, not live issues; use `list_helm_releases` / `get_helm_release` for Helm release history. For static posture use `get_cluster_audit`; for raw events use `get_events`. |`namespace` (optional), `severity` (optional: `critical,warning`), `kind` (optional), `filter` (optional CEL), `limit` (optional, default 200, max 1000) |
188
-
|`diagnose`| Root-cause one workload or GitOps reconciler in a single call. Pod/Deployment/StatefulSet/DaemonSet get minified resource + `resourceContext` + current AND previous container logs across pods + filtered events + `startupBlockers`; Application/Kustomization/HelmRelease get reconciler status + related parsed issues. |`kind` (required: workload or GitOps reconciler), `namespace` (required), `name` (required) |
187
+
|`issues`| "What's broken right now?" — a ranked, curated stream of live operational failures: failing workloads/pods, active native Helm release failures or stuck pending operations (`kind=HelmRelease`, `group=helm.sh`), dangling references, pod-startup blockers (unschedulable / admission-rejected / stuck post-bind), and False CRD conditions. No source filter; each row carries a `source` label sliceable via `filter`. Recovered Helm rollbacks are deploy history, not live issues; use `get_changes` for Helm deployment history and `get_helm_release` for native Helm full revision/history/hook diagnostics. Flux `HelmRelease` rows (`group=helm.toolkit.fluxcd.io`) are GitOps reconcilers and should use `diagnose`. For static posture use `get_cluster_audit`; for raw events use `get_events`. |`namespace` (optional), `severity` (optional: `critical,warning`), `kind` (optional), `filter` (optional CEL), `limit` (optional, default 200, max 1000) |
188
+
|`diagnose`| Root-cause one workload or GitOps reconciler in a single call. Pod/Deployment/StatefulSet/DaemonSet get minified resource + `resourceContext` + current AND previous container logs across pods + filtered events + `startupBlockers`; Application/Kustomization/Flux HelmRelease get reconciler status + related parsed issues. |`kind` (required: workload or GitOps reconciler), `namespace` (required), `name` (required) |
189
189
|`get_dashboard`| Cluster/namespace health overview — resource counts, failing pods, unhealthy workloads, warning events, Helm status. Inventory-style triage before drilling in. |`namespace` (optional) |
190
190
|`top_resources`| Live metrics ranked like `kubectl top | sort`, joined with K8s context (status, restarts, owner, requests/limits). Use for CPU/memory/OOM/load symptoms. |`kind` (optional: `pods` default, `workloads`, `nodes`), `namespace` (optional), `sort` (optional: `cpu` default, `memory`), `limit` (optional, default 20, max 100) |
191
191
|`list_resources`| List resources of a kind with minified summaries + per-row `summaryContext` (managedBy / health / issueCount). |`kind` (required), `group` (optional), `namespace` (optional), `context` (optional: default / `none`) |
@@ -194,7 +194,7 @@ Add to `~/.gemini/settings.json`:
194
194
|`get_topology`| Whole-namespace/cluster topology graph (nodes + edges). Use `summary` format for LLM-friendly text chains. Once you have a suspect root, prefer `get_neighborhood`. |`namespace` (optional), `view` (optional: `traffic` or `resources`), `format` (optional: `graph` or `summary`) |
195
195
|`get_neighborhood`| BFS-expanded topology neighborhood around one known root — cheaper and clearer than `get_topology` for cross-resource failures (routing, selector/endpoint, refs, owner chains). RBAC-filtered. |`kind` (required), `namespace` (optional), `name` (required), `profile` (optional: `auto` default / `all`), `hops` (optional, default 1, max 2) |
196
196
|`get_events`| Recent Kubernetes Warning events, deduplicated and sorted by recency. Filter by resource kind/name to scope. |`namespace` (optional), `limit` (optional, default 20, max 100), `kind` (optional), `name` (optional) |
197
-
|`get_changes`| Recent resource changes (creates, updates, deletes) from the Kubernetes cluster timeline. Use to investigate what changed before an incident. Helm release deployment history is separate; use `list_helm_releases` or `get_helm_release include=history,operations` for failed upgrades and rollbacks. |`namespace` (optional), `kind` (optional), `name` (optional), `since` (optional, e.g. `1h`, `30m`; default `1h`), `limit` (optional, default 20, max 50) |
197
+
|`get_changes`| Recent meaningful changes from the Kubernetes cluster timeline plus native Helm release deployment/operation history (`source: helm`). Use to investigate what changed before an incident, including failed upgrades, rollbacks, and current Helm revisions. If the response includes `sourcesErrored`, treat it as partial data for those sources. Use `get_helm_release include=history,operations` for the full Helm revision trail. |`namespace` (optional), `kind` (optional), `name` (optional), `since` (optional, e.g. `1h`, `30m`; default `1h`), `limit` (optional, default 20, max 50) |
198
198
|`get_pod_logs`| Filtered pod logs prioritizing errors/warnings, with secret redaction. Set `grep` for server-side filtering. |`namespace` (required), `name` (required), `container` (optional), `tail_lines` (optional, default 200), `grep` (optional) |
199
199
|`get_workload_logs`| Aggregated, AI-filtered logs from all pods of a workload (Deployment, StatefulSet, DaemonSet) |`kind` (required), `namespace` (required), `name` (required), `container` (optional), `tail_lines` (optional, default 100 per pod), `grep` (optional) |
200
200
|`get_cluster_audit`| Static config posture — best-practice findings (Security / Reliability / Efficiency) with remediation. INDEPENDENT of operational health; for "what's broken right now?" use `issues`. |`namespace` (optional), `category` (optional), `severity` (optional) |
{"flux chart not ready is render", classifyInput{Source: SourceProblem, Kind: "HelmRelease", APIGroup: "helm.toolkit.fluxcd.io", Reason: "ChartNotReady"}, issuesapi.CategoryGitOpsRenderFailed},
64
67
{"flux-looking kustomization group is not gitops", classifyInput{Source: SourceProblem, Kind: "Kustomization", APIGroup: "custom-fluxcd.io", Reason: "ReconciliationFailed"}, issuesapi.CategoryUnknown},
return"Open the Helm release details, check whether the operation is still running, then inspect hooks, Jobs, Pods, events, logs, and owned resources."
93
+
}
94
+
return"Open the Helm release history and hook diagnostics, then inspect the failed revision, values, hooks, and owned resources."
0 commit comments