chore: merge master into feat/issue-646-policy-guardrail-visibility (base sync)

webui/app.py

@@ -47,6 +47,12 @@ from webui.runtime_health import load_runtime_snapshot, snapshot_to_dict as runt
 from webui.runtime_views import render_runtime_page
 from webui.policy_inventory import load_policy_inventory, snapshot_to_dict as policy_snapshot_to_dict
 from webui.policy_views import render_policy_page
+from webui.system_health import (
+    API_PATH as SYSTEM_HEALTH_API_PATH,
+    load_system_health,
+    process_uptime,
+    snapshot_to_dict as system_health_to_dict,
+)
 
 _READ_ONLY_METHODS = frozenset({"GET", "HEAD", "OPTIONS"})
 _AUDIT_MUTATION_PATHS = frozenset({"/audit", "/api/audit"})
@@ -81,16 +87,43 @@ async def home(_request: Request) -> HTMLResponse:
 
 
 async def health(_request: Request) -> JSONResponse:
+    """Liveness only — deliberately cheap, runs no dependency probe (#634).
+
+    Every MVP key is retained so existing pollers keep working; the additions
+    are a pointer to the structured API and the in-memory process uptime.
+    Readiness lives at that API because answering it costs real probes.
+    """
     bind_host = _request.app.state.webui_bind_host
+    started_at, uptime_seconds = process_uptime()
     return JSONResponse({
         "status": "ok",
         "service": "mcp-control-plane-webui",
         "mode": "read-only-mvp",
         "timestamp": datetime.now(timezone.utc).isoformat(),
         "deployment": deployment_snapshot(bind_host=bind_host),
+        "started_at": started_at,
+        "uptime_seconds": uptime_seconds,
+        "system_health_api": SYSTEM_HEALTH_API_PATH,
     })
 
 
+def _truthy_flag(value: str | None) -> bool:
+    return (value or "").strip().lower() in {"1", "true", "yes", "on"}
+
+
+async def api_system_health(request: Request) -> JSONResponse:
+    """Structured read-only system health (#634).
+
+    `?deep=1` opts into the expensive network probe. The response status code
+    reflects readiness so automated checks can branch on it without parsing the
+    body: 200 when ready, 503 when a required dependency failed or never ran.
+    """
+    deep = _truthy_flag(request.query_params.get("deep"))
+    snapshot = load_system_health(deep=deep)
+    payload = system_health_to_dict(snapshot)
+    return JSONResponse(payload, status_code=200 if snapshot.ready else 503)
+
+
 async def queue(_request: Request) -> HTMLResponse:
     snapshot = load_queue_snapshot()
     return HTMLResponse(render_page(title="Queue", body_html=render_queue_page(snapshot)))
@@ -413,6 +446,7 @@ def create_app(*, bind_host: str | None = None) -> Starlette:
         routes=[
             Route("/", home, methods=["GET"]),
             Route("/health", health, methods=["GET"]),
+            Route(SYSTEM_HEALTH_API_PATH, api_system_health, methods=["GET"]),
             Route("/queue", queue, methods=["GET"]),
             Route("/api/queue", api_queue, methods=["GET"]),
             Route("/projects", projects, methods=["GET"]),