fix some issuen, added cache and added a test for the config

README.md

@@ -0,0 +1,86 @@
+# k3s Health Dashboard
+
+A Streamlit dashboard for monitoring a k3s (or any Kubernetes) cluster — nodes, pods, deployments, and metrics in one place.
+
+## Architecture
+
+```
+app/
+  main.py          FastAPI backend (REST API)
+  cache.py         Streamlit cache wrappers (TTL-based)
+  k8s_client.py    Kubernetes API client & data helpers
+  config.py        Config loaded from environment variables
+  routers/         FastAPI route handlers
+app.py             Streamlit frontend entry point
+k3s-dashboard.yaml Kubernetes deployment manifest
+```
+
+## Prerequisites
+
+- Python 3.10+
+- A running Kubernetes cluster with a valid kubeconfig at `~/.kube/config`
+- (Optional) `metrics-server` installed on the cluster for CPU/memory usage
+
+## Local setup
+
+```bash
+python -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+```
+
+Copy the example environment file and edit as needed:
+
+```bash
+cp .env .env.local
+```
+
+Key environment variables:
+
+| Variable          | Default               | Description                          |
+|-------------------|-----------------------|--------------------------------------|
+| `KUBECONFIG`      | `~/.kube/config`      | Path to kubeconfig                   |
+| `IN_CLUSTER`      | (unset)               | Set to `true` when running as a pod  |
+| `CACHE_TTL`       | `15`                  | Seconds between Kubernetes API calls |
+| `METRICS_ENABLED` | `true`                | Set `false` if metrics-server absent |
+
+## Running locally
+
+**Streamlit dashboard:**
+
+```bash
+streamlit run app.py
+```
+
+Opens at `http://localhost:8501`.
+
+**FastAPI backend only:**
+
+```bash
+uvicorn app.main:app --reload
+```
+
+API docs at `http://localhost:8000/docs`.
+
+## Running tests
+
+```bash
+pytest
+```
+
+## Deploying to Kubernetes
+
+1. Build and push the Docker image:
+
+```bash
+docker build -t your-registry/k3s-dashboard:latest .
+docker push your-registry/k3s-dashboard:latest
+```
+
+2. Update the image name in `k3s-dashboard.yaml`, then apply:
+
+```bash
+kubectl apply -f k3s-dashboard.yaml
+```
+
+The manifest creates a `ServiceAccount` with read-only `ClusterRole` access to nodes, pods, namespaces, and metrics.

app.py

@@ -0,0 +1,99 @@
+import time
+import streamlit as st
+from app import cfg
+from app.cache import (
+    clients,
+    cached_nodes,
+    cached_pods,
+    cached_deployments,
+    cached_namespaces,
+    cached_node_metrics,
+    clear,
+)
+
+st.set_page_config(page_title=cfg.page_title, page_icon=cfg.page_icon, layout="wide")
+
+clients()
+
+with st.sidebar:
+    st.title("☸️ k3s Dashboard")
+
+    auto_refresh = st.toggle("Auto-refresh (15s)", value=False)
+
+    if st.button("🔄 Refresh now"):
+        clear()
+        st.rerun()
+
+    namespaces = ["all"] + cached_namespaces()
+    sel_ns = st.selectbox("Namespace", namespaces)
+
+    view = st.radio("View", ["Overview", "Nodes", "Pods", "Deployments"])
+
+
+# Auto-refresh: sleep only the time remaining since the last refresh,
+# not the full TTL on every rerun (which would freeze the UI on sidebar clicks).
+if auto_refresh:
+    now = time.time()
+    if "last_refresh" not in st.session_state:
+        st.session_state.last_refresh = now
+    elapsed = now - st.session_state.last_refresh
+    remaining = cfg.cache_ttl - elapsed
+    if remaining <= 0:
+        clear()
+        st.session_state.last_refresh = time.time()
+        st.rerun()
+    else:
+        time.sleep(remaining)
+        st.rerun()
+
+
+# ── Views ──────────────────────────────────────────────────────────────────────
+
+if view == "Overview":
+    nodes       = cached_nodes()
+    pods        = cached_pods(sel_ns)
+    deployments = cached_deployments(sel_ns)
+    metrics     = cached_node_metrics()
+
+    ready_nodes = sum(1 for n in nodes if n["ready"])
+    ready_pods  = sum(1 for p in pods if p["ready"])
+    ready_deps  = sum(1 for d in deployments if d["available"] >= d["desired"] > 0)
+
+    c1, c2, c3 = st.columns(3)
+    c1.metric("Nodes",       f"{ready_nodes}/{len(nodes)} ready")
+    c2.metric("Pods",        f"{ready_pods}/{len(pods)} ready")
+    c3.metric("Deployments", f"{ready_deps}/{len(deployments)} ready")
+
+    st.divider()
+    st.subheader("Nodes")
+    st.dataframe(nodes, use_container_width=True)
+
+    st.subheader("Pods")
+    st.dataframe(pods, use_container_width=True)
+
+elif view == "Nodes":
+    nodes   = cached_nodes()
+    metrics = cached_node_metrics()
+
+    st.subheader("Nodes")
+    for node in nodes:
+        m = metrics.get(node["name"], {})
+        with st.expander(f"{'✅' if node['ready'] else '❌'} {node['name']}  —  {node['roles']}"):
+            col1, col2, col3 = st.columns(3)
+            col1.metric("CPU capacity",    f"{node['cpu_cap']} cores")
+            col2.metric("Memory capacity", f"{node['mem_cap_mi']:.0f} Mi")
+            col3.metric("Age",             node["age"])
+            if m:
+                col1.metric("CPU usage",    m["cpu_usage"])
+                col2.metric("Memory usage", m["memory_usage"])
+            st.caption(f"OS: {node['os']}   Kubelet: {node['kubelet_version']}")
+
+elif view == "Pods":
+    pods = cached_pods(sel_ns)
+    st.subheader(f"Pods — {sel_ns}")
+    st.dataframe(pods, use_container_width=True)
+
+elif view == "Deployments":
+    deployments = cached_deployments(sel_ns)
+    st.subheader(f"Deployments — {sel_ns}")
+    st.dataframe(deployments, use_container_width=True)

app/cache.py

@@ -0,0 +1,71 @@
+import streamlit as st
+from app import cfg
+from app.k8s_client import get_core, get_custom_client, fetch_nodes, fetch_pods
+
+
+@st.cache_resource
+def clients():
+    get_core()
+    get_custom_client()
+
+
+@st.cache_data(ttl=cfg.cache_ttl)
+def cached_nodes():
+    return fetch_nodes()
+
+
+@st.cache_data(ttl=cfg.cache_ttl)
+def cached_pods(namespace="all"):
+    return fetch_pods(namespace=namespace)
+
+
+@st.cache_data(ttl=cfg.cache_ttl)
+def cached_deployments(namespace="all"):
+    from kubernetes import client as _k8s
+    get_core()  # ensures kubeconfig is loaded before AppsV1Api is created
+    apps_v1 = _k8s.AppsV1Api()
+    if namespace == "all":
+        items = apps_v1.list_deployment_for_all_namespaces().items
+    else:
+        items = apps_v1.list_namespaced_deployment(namespace=namespace).items
+    return [
+        {
+            "namespace": d.metadata.namespace,
+            "name": d.metadata.name,
+            "ready": f"{d.status.ready_replicas or 0}/{d.spec.replicas or 0}",
+            "available": d.status.available_replicas or 0,
+            "desired": d.spec.replicas or 0,
+        }
+        for d in items
+    ]
+
+
+@st.cache_data(ttl=cfg.cache_ttl)
+def cached_namespaces():
+    return [ns.metadata.name for ns in get_core().list_namespace().items]
+
+
+@st.cache_data(ttl=cfg.cache_ttl)
+def cached_node_metrics():
+    try:
+        api = get_custom_client()
+        data = api.list_cluster_custom_object(
+            group="metrics.k8s.io", version="v1beta1", plural="nodes"
+        )
+        return {
+            item["metadata"]["name"]: {
+                "cpu_usage": item["usage"]["cpu"],
+                "memory_usage": item["usage"]["memory"],
+            }
+            for item in data["items"]
+        }
+    except Exception:
+        return {}
+
+
+def clear():
+    cached_nodes.clear()
+    cached_pods.clear()
+    cached_deployments.clear()
+    cached_namespaces.clear()
+    cached_node_metrics.clear()

app/routers/metrics.py

@@ -1,5 +1,5 @@
 from fastapi import APIRouter
-from k8s_client import get_custom_client
+from app.k8s_client import get_custom_client
 
 router = APIRouter(prefix="/metrics", tags=["metrics"])
 

requirements.txt

@@ -3,3 +3,5 @@ uvicorn
 kubernetes
 python-dotenv
 httpx
+streamlit
+pytest

tests/conftest.py

@@ -0,0 +1,3 @@
+import sys, pathlib
+
+sys.path.insert(0, str(pathlib.Path(__file__).resolve().parent.parent))