Finish repo-first implementation of Agent System UI pipeline

Co-authored-by: Junie <junie@jetbrains.com>

services/agent-system/README.md

@@ -0,0 +1,37 @@
+### Agent System
+Central runtime materializer and Operator Control Plane UI.
+
+#### Components
+- **Redis**: Central state store (on PIHA).
+- **Runtime Materializer**: Converts Redis state to JSON files in `/opt/homelab/world`.
+- **Web UI**: Exposes API endpoints and serving the Operator UI.
+
+#### Deployment (on PIHA)
+```bash
+cd services/agent-system
+./deploy.sh
+```
+
+#### Deployment (on CHELSTY)
+```bash
+cd services/stability-agent
+docker compose up -d --build
+```
+
+#### Verification
+The `deploy.sh` script automatically verifies the local endpoints.
+You can also manually check:
+```bash
+# Check runtime summary
+curl http://localhost:18180/summary
+
+# Check discovered nodes
+curl http://localhost:18180/nodes
+
+# Check discovered services
+curl http://localhost:18180/services
+```
+
+#### Directory Structure
+- `/opt/homelab/world`: Contains materialized JSON state.
+- `/opt/homelab/state`: Contains operator configuration and local heartbeats.

services/agent-system/deploy.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+set -e
+
+echo ">>> Validating docker-compose configuration..."
+docker compose config
+
+echo ">>> Building and starting Agent System services..."
+docker compose up -d --build
+
+echo ">>> Services status:"
+docker ps --filter "name=agent-system"
+
+echo ">>> Verifying API endpoints..."
+sleep 5 # Give it a moment to start
+
+endpoints=("summary" "nodes" "services")
+for ep in "${endpoints[@]}"; do
+  echo "Checking /$ep..."
+  curl -s -f http://localhost:18180/$ep > /dev/null && echo "  OK" || echo "  FAILED"
+done
+
+echo ">>> Deployment complete."

services/agent-system/runtime-materializer/materializer.py

@@ -30,6 +30,17 @@ def safe_json_loads(data, default=None):
     except (json.JSONDecodeError, TypeError):
         return data
 
+def normalize_health(health):
+    """Normalizes health values for the UI."""
+    if not health:
+        return "nominal"
+    h = str(health).lower()
+    if h in ["healthy", "ok", "running", "nominal"]:
+        return "nominal"
+    if h in ["degraded", "warning"]:
+        return "degraded"
+    return "error"
+
 def materialize():
     """Reads state from Redis and writes JSON files to the world directory."""
     print(f"[{datetime.now().isoformat()}] Materializing world state...")
@@ -42,6 +53,9 @@ def materialize():
         for key in node_keys:
             node_data = r.hgetall(key)
             if node_data:
+                # Normalize health
+                if "health" in node_data:
+                    node_data["health"] = normalize_health(node_data["health"])
                 # Parse JSON fields if they exist
                 if "capabilities" in node_data:
                     node_data["capabilities"] = safe_json_loads(node_data["capabilities"], [])
@@ -55,6 +69,9 @@ def materialize():
         for key in service_keys:
             svc_data = r.hgetall(key)
             if svc_data:
+                # Normalize health
+                if "health" in svc_data:
+                    svc_data["health"] = normalize_health(svc_data["health"])
                 if "dependencies" in svc_data:
                     svc_data["dependencies"] = safe_json_loads(svc_data["dependencies"], [])
                 if "recommendations" in svc_data:
@@ -82,6 +99,9 @@ def materialize():
         for key in incident_keys:
             incident_data = r.hgetall(key)
             if incident_data:
+                # Normalize health if present
+                if "health" in incident_data:
+                    incident_data["health"] = normalize_health(incident_data["health"])
                 incidents.append(incident_data)
 
         # 5. Deployments (Hash)
@@ -101,13 +121,26 @@ def materialize():
                 recommendations.append(rec_data)
 
         # 7. Runtime Summary
+        unhealthy_services = [s for s in services if s.get("health") != "nominal"]
+        active_incidents = [i for i in incidents if i.get("status") not in ["resolved", "closed"]]
+
+        status = "nominal"
+        if len(active_incidents) > 0 or len(unhealthy_services) > 5:
+            status = "error"
+        elif len(unhealthy_services) > 0:
+            status = "degraded"
+
         summary = {
+            "status": status,
             "timestamp": datetime.utcnow().isoformat() + "Z",
+            "last_update": int(time.time()),
             "node_count": len(nodes),
             "service_count": len(services),
-            "unhealthy_services_count": len([s for s in services if s.get("health") != "healthy"]),
+            "active_incidents_count": len(active_incidents),
+            "unhealthy_services_count": len(unhealthy_services),
             "incident_count": len(incidents),
-            "recent_events_count": len(events)
+            "recent_events_count": len(events),
+            "stale": False
         }
 
         # Ensure directory exists

services/agent-system/webui/web.py

@@ -47,45 +47,37 @@ def save_config(config):
 
 
 def current_nodes():
-    return read_json_file(STATE_DIR / "nodes.json")
+    return read_json_file(WORLD_DIR / "nodes.json")
 
 
 def current_services():
-    return read_json_file(STATE_DIR / "services.json")
+    return read_json_file(WORLD_DIR / "services.json")
 
 
 def current_deployments():
-    return read_json_file(STATE_DIR / "deployments.json")
+    return read_json_file(WORLD_DIR / "deployments.json")
 
 
 def current_incidents():
-    return read_json_file(STATE_DIR / "incidents.json")
+    return read_json_file(WORLD_DIR / "incidents.json")
 
 
 def current_recommendations():
-    return read_json_file(STATE_DIR / "recommendations.json")
+    return read_json_file(WORLD_DIR / "recommendations.json")
 
 
 def current_summary():
-    summary = read_json_file(STATE_DIR / "runtime-summary.json", default={})
+    summary = read_json_file(WORLD_DIR / "runtime-summary.json", default={})
     if summary:
         # Check for staleness
-        mtime = os.path.getmtime(STATE_DIR / "runtime-summary.json")
+        mtime = os.path.getmtime(WORLD_DIR / "runtime-summary.json")
         summary["last_update"] = mtime
         summary["stale"] = (time.time() - mtime) > 60  # Stale if older than 60s
     return summary
 
 
 def current_events():
-    events = []
+    return read_json_file(WORLD_DIR / "events.json", default=[])
-    if EVENTS_DIR.exists():
-        for f in EVENTS_DIR.glob("*.json"):
-            data = read_json_file(f)
-            if data:
-                # Add source file for traceability
-                data["_source"] = f.name
-                events.append(data)
-    return sorted(events, key=lambda x: x.get("timestamp", 0), reverse=True)
 
 
 def current_actions():

services/stability-agent/src/stability_agent.py

@@ -293,7 +293,7 @@ def main():
                     
                     redis_client.hset(f"homelab:nodes:{NODE_NAME}", {
                         "id": NODE_NAME,
-                        "hostname": socket.gethostname(),
+                        "hostname": NODE_NAME,
                         "health": node_health,
                         "status": "online",
                         "last_seen": status["timestamp"],