backend/app/api/__init__.py

@@ -38,6 +38,7 @@ def all_blueprints() -> list[Blueprint]:
     from .suggestions import suggestions_bp
     from .system_activity import system_activity_bp
     from .system_backup import system_backup_bp
+    from .system_health import system_health_bp
     from .tags import tags_bp
     from .thumbnails import thumbnails_bp
     return [
@@ -51,6 +52,7 @@ def all_blueprints() -> list[Blueprint]:
         showcase_bp,
         settings_bp,
         system_activity_bp,
+        system_health_bp,
         system_backup_bp,
         admin_bp,
         cleanup_bp,

backend/app/api/system_health.py

@@ -0,0 +1,192 @@
+"""Is every part of FabledCurator running? One verdict, one endpoint.
+
+Milestone 365. The nav indicator and the System page both read this and
+nothing else — composing a verdict is this module's job, not the UI's.
+
+## Two kinds of part, answered two different ways
+
+**Learned** — celery roles and the GPU agent, from `service_seen`. The
+question is "how long since it checked in", and these are the parts that can
+be ABSENT, which is the whole point: `celery inspect` alone reports presence,
+so a dead worker is a shorter list rather than a red light.
+
+**Probed live** — Postgres and Redis. Always expected, never learned, and a
+last-seen for them would be actively misleading: that Redis answered thirty
+seconds ago says nothing about now.
+
+## This endpoint must never fail because something it checks has failed
+
+The inversion is easy to write by accident and it destroys the feature exactly
+when it is needed — a 500 when Redis is down, instead of `redis: down`. Every
+probe is wrapped, every wait has a deadline (rule 156), and the roster refresh
+swallows its own errors. The worst case is a part reported `unknown`, which is
+a true statement.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+import time
+from datetime import UTC, datetime
+
+from quart import Blueprint, jsonify
+from sqlalchemy import select, text
+
+from ..config import get_config
+from ..extensions import get_session
+from ..models import ServiceSeen
+from ..services.service_roster import refresh_if_stale
+
+log = logging.getLogger(__name__)
+
+system_health_bp = Blueprint("system_health", __name__, url_prefix="/api/system")
+
+# How long a learned part may go quiet before it is doubted, then disbelieved.
+#
+# These are deliberately generous, and the reason is a deploy rather than a
+# worker: `docker compose up -d` rolls start-first, so a role is briefly served
+# by two containers and then by neither while the old one drains. Thresholds
+# tight enough to catch a crash in seconds would paint the page red every time
+# the stack is updated, and an alarm that cries wolf on every deploy is one
+# nobody reads. Tune down only after watching a real deploy pass through.
+STALE_AFTER_SECONDS = 90
+DOWN_AFTER_SECONDS = 300
+
+# Probes cross a process boundary, so they carry deadlines. A hung Postgres
+# must make this endpoint say "postgres: down", not hang alongside it.
+PROBE_TIMEOUT_SECONDS = 2.0
+
+_OK, _STALE, _DOWN, _UNKNOWN = "ok", "stale", "down", "unknown"
+
+# Worst-first, so an overall verdict is just the max.
+_SEVERITY = {_OK: 0, _UNKNOWN: 1, _STALE: 2, _DOWN: 3}
+
+
+def _age_state(age_seconds: float) -> str:
+    if age_seconds >= DOWN_AFTER_SECONDS:
+        return _DOWN
+    if age_seconds >= STALE_AFTER_SECONDS:
+        return _STALE
+    return _OK
+
+
+def _describe_learned(name: str, state: str, age: float, details: dict) -> str:
+    """Say what the state MEANS. A red chip tells an operator less than a
+    sentence does at the moment they are deciding whether to go and look."""
+    if state == _OK:
+        replicas = details.get("replicas")
+        if replicas and replicas > 1:
+            return f"{name} is running ({replicas} replicas)"
+        return f"{name} is running"
+    mins = int(age // 60)
+    ago = f"{mins} min" if mins else f"{int(age)}s"
+    if state == _STALE:
+        return f"{name} has not checked in for {ago}"
+    return f"{name} has not checked in for {ago} — treat it as stopped"
+
+
+async def _probe_postgres(session) -> dict:
+    started = time.monotonic()
+    try:
+        await asyncio.wait_for(
+            session.execute(text("SELECT 1")), timeout=PROBE_TIMEOUT_SECONDS
+        )
+    except Exception as exc:  # noqa: BLE001 — a probe reports, it never raises
+        return {
+            "key": "postgres", "kind": "datastore", "name": "PostgreSQL",
+            "state": _DOWN, "detail": f"not answering: {type(exc).__name__}",
+        }
+    return {
+        "key": "postgres", "kind": "datastore", "name": "PostgreSQL", "state": _OK,
+        "detail": "answering", "latency_ms": round((time.monotonic() - started) * 1000, 1),
+    }
+
+
+def _ping_redis_sync() -> None:
+    import redis  # local import; mirrors system_activity's pattern
+
+    client = redis.Redis.from_url(
+        get_config().celery_broker_url,
+        socket_connect_timeout=PROBE_TIMEOUT_SECONDS,
+        socket_timeout=PROBE_TIMEOUT_SECONDS,
+    )
+    client.ping()
+
+
+async def _probe_redis() -> dict:
+    started = time.monotonic()
+    try:
+        await asyncio.wait_for(
+            asyncio.to_thread(_ping_redis_sync), timeout=PROBE_TIMEOUT_SECONDS * 2
+        )
+    except Exception as exc:  # noqa: BLE001
+        return {
+            "key": "redis", "kind": "datastore", "name": "Redis",
+            "state": _DOWN,
+            "detail": f"not answering: {type(exc).__name__} — queues and workers "
+                      f"cannot be reached either",
+        }
+    return {
+        "key": "redis", "kind": "datastore", "name": "Redis", "state": _OK,
+        "detail": "answering", "latency_ms": round((time.monotonic() - started) * 1000, 1),
+    }
+
+
+@system_health_bp.route("/health", methods=["GET"])
+async def system_health():
+    """Every part, its state, and one overall verdict.
+
+    Response: {overall, parts: [{key, kind, name, state, detail, last_seen_at,
+    …}], checked_at}
+    """
+    parts: list[dict] = []
+    now = datetime.now(UTC)
+
+    async with get_session() as session:
+        # Postgres first, and if it is unreachable nothing else can be read —
+        # say so rather than failing, because "the database is down" is the
+        # single most useful thing this endpoint can ever report.
+        pg = await _probe_postgres(session)
+        parts.append(pg)
+
+        if pg["state"] == _OK:
+            # Rate-limited inside; see service_roster on why the web process
+            # is the right observer.
+            try:
+                await refresh_if_stale(session)
+                await session.commit()
+            except Exception:  # noqa: BLE001
+                log.warning("system health: roster refresh failed", exc_info=True)
+
+            rows = (
+                await session.execute(select(ServiceSeen).order_by(ServiceSeen.display_name))
+            ).scalars().all()
+            for row in rows:
+                age = (now - row.last_seen_at).total_seconds()
+                state = _age_state(age)
+                parts.append({
+                    "key": row.key,
+                    "kind": row.kind,
+                    "name": row.display_name,
+                    "state": state,
+                    "detail": _describe_learned(row.display_name, state, age, row.details or {}),
+                    "last_seen_at": row.last_seen_at.isoformat(),
+                    "first_seen_at": row.first_seen_at.isoformat(),
+                    **{k: v for k, v in (row.details or {}).items() if k != "agent_id"},
+                })
+
+    parts.append(await _probe_redis())
+
+    overall = max((p["state"] for p in parts), key=lambda s: _SEVERITY[s], default=_UNKNOWN)
+    return jsonify({
+        "overall": overall,
+        "parts": sorted(parts, key=lambda p: (-_SEVERITY[p["state"]], p["name"])),
+        "checked_at": now.isoformat(),
+        # So the UI can explain a `stale` without hard-coding the same numbers
+        # in a second place.
+        "thresholds": {
+            "stale_after_seconds": STALE_AFTER_SECONDS,
+            "down_after_seconds": DOWN_AFTER_SECONDS,
+        },
+    })