A skill for checking production from Loki and Tempo

.claude/skills/ipx-prod-check: what production's JSON log and traces
carry, the queries that find trouble (warnings grouped, failing feeds and
downloads, 5xx and slow routes, whether the worker keeps up, slow and
failed traces), how to tell a publisher's dead feed from an ipx bug, and
filing what is found as issues per CLAUDE.md. query.py beside it runs the
LogQL and TraceQL through a throwaway container on the monitoring
network, since Loki and Tempo publish no query port.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

.claude/skills/ipx-prod-check/query.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+"""Ask production's Loki or Tempo a question, from anywhere that can run docker on Tower.
+
+    query.py logs    '<LogQL log query>'    [since]   lines, newest first
+    query.py metric  '<LogQL metric query>' [since]   one value per series; $range is `since`
+    query.py traces  '<TraceQL query>'      [since]   matching traces, slowest first
+    query.py trace   <trace id>                       one trace's spans, as a tree
+
+`since` is 1h, 24h, 7d and the like (default 24h). Loki and Tempo publish no query port on the
+host, so each call runs a throwaway alpine container on the monitoring project's network.
+"""
+import json, subprocess, sys, time, urllib.parse
+
+NET = "monitoring_default"
+
+
+def fetch(url):
+    out = subprocess.run(["docker", "run", "--rm", "--network", NET, "alpine", "wget", "-qO-", url],
+                         capture_output=True, text=True, timeout=120)
+    if out.returncode:
+        sys.exit(f"query failed: {out.stderr.strip() or out.stdout.strip()}\n{url}")
+    return json.loads(out.stdout)
+
+
+def seconds(since):
+    return int(since[:-1]) * {"m": 60, "h": 3600, "d": 86400}[since[-1]]
+
+
+def main():
+    if len(sys.argv) < 3:
+        sys.exit(__doc__)
+    kind, q = sys.argv[1], sys.argv[2]
+    since = sys.argv[3] if len(sys.argv) > 3 else "24h"
+    now = time.time()
+    start = now - seconds(since)
+    enc = urllib.parse.quote
+    if kind == "logs":
+        r = fetch(f"http://loki:3100/loki/api/v1/query_range?query={enc(q)}&limit=500"
+                  f"&start={int(start * 1e9)}&end={int(now * 1e9)}&direction=backward")
+        lines = [(ts, line) for s in r["data"]["result"] for ts, line in s["values"]]
+        for ts, line in sorted(lines, reverse=True):
+            print(line)
+        print(f"-- {len(lines)} line(s){' (limit reached)' if len(lines) >= 500 else ''}", file=sys.stderr)
+    elif kind == "metric":
+        r = fetch(f"http://loki:3100/loki/api/v1/query?query={enc(q.replace('$range', since))}&time={int(now * 1e9)}")
+        rows = sorted(r["data"]["result"], key=lambda s: -float(s["value"][1]))
+        for s in rows:
+            labels = {k: v for k, v in s["metric"].items() if k not in ("container", "compose_project", "service_name")}
+            print(f"{s['value'][1]:>12}  {json.dumps(labels) if labels else ''}")
+        print(f"-- {len(rows)} series", file=sys.stderr)
+    elif kind == "traces":
+        r = fetch(f"http://tempo:3200/api/search?q={enc(q)}&start={int(start)}&end={int(now)}&limit=100")
+        traces = sorted(r.get("traces", []), key=lambda t: -t.get("durationMs", 0))
+        for t in traces:
+            when = time.strftime("%m-%d %H:%M:%S", time.gmtime(int(t["startTimeUnixNano"]) / 1e9))
+            print(f"{t.get('durationMs', 0):>8}ms  {when}Z  {t['traceID']}  {t.get('rootTraceName', '')}")
+        print(f"-- {len(traces)} trace(s)", file=sys.stderr)
+    elif kind == "trace":
+        r = fetch(f"http://tempo:3200/api/traces/{q}")
+        spans = [sp for b in r.get("batches", r.get("resourceSpans", []))
+                 for ss in b.get("scopeSpans", b.get("instrumentationLibrarySpans", [])) for sp in ss["spans"]]
+        kids = {}
+        for sp in spans:
+            kids.setdefault(sp.get("parentSpanId", ""), []).append(sp)
+
+        def show(sp, depth):
+            ms = (int(sp["endTimeUnixNano"]) - int(sp["startTimeUnixNano"])) / 1e6
+            attrs = {a["key"]: next(iter(a["value"].values()), None) for a in sp.get("attributes", [])
+                     if not a["key"].startswith(("code.", "thread.")) and a["key"] not in ("busy_ns", "idle_ns", "target")}
+            err = " ERROR" if sp.get("status", {}).get("code") in (2, "STATUS_CODE_ERROR") else ""
+            print(f"{'  ' * depth}{sp['name']}  {ms:.0f}ms{err}  {json.dumps(attrs) if attrs else ''}")
+            for e in sp.get("events", []):
+                msg = next((a["value"].get("stringValue") for a in e.get("attributes", []) if a["key"] == "message"), e.get("name"))
+                # A scan logs a skip for every feed not due; they bury what happened.
+                if '"ev":"feed_skip"' in (msg or ""):
+                    continue
+                print(f"{'  ' * depth}  - {msg}")
+            for k in sorted(kids.get(sp["spanId"], []), key=lambda s: int(s["startTimeUnixNano"])):
+                show(k, depth + 1)
+
+        ids = {sp["spanId"] for sp in spans}
+        for root in [sp for sp in spans if sp.get("parentSpanId", "") not in ids]:
+            show(root, 0)
+    else:
+        sys.exit(__doc__)
+
+
+if __name__ == "__main__":
+    main()