fix(traefik): a router's 5xx share is judged only over enough requests, like its 4xx share (#5859)

Two 500s of about sixteen requests graded roundtable@swarm critical at
9.1%. The Settings → Thresholds minimum of requests in 15 minutes (30 by
default) now guards both shares; the 5xx share still keeps its fixed
cutoff whatever the router's history.

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

plugins/traefik/mcp_tools.py

@@ -4,7 +4,7 @@ Registered through register_mcp_tools() in __init__.py, so they exist only
 while the plugin is enabled. Routers are graded exactly as the Traefik page
 grades them (routes.py): over the last 15 minutes, the 5xx share against its
 fixed cutoff, the 4xx share and p95 against the router's own normal where it
-has one.
+has one; neither share over fewer requests than Settings → Thresholds asks.
 """
 from __future__ import annotations
 

plugins/traefik/routes.py

@@ -61,14 +61,15 @@ def error_cutoffs(thresholds: dict) -> tuple[float, float]:
 # that is its normal, not a problem. Departing by less than the floor
 # (Settings → Thresholds, norms.floor.router_*) is never news. A share over
 # fewer than min_requests() in the window is not graded: one 404 of three
-# requests is 33%. The 5xx share is a failure and keeps its fixed cutoff
-# whatever the history or traffic (the operator's ruling).
+# requests is 33%, two 500s of sixteen 12%. The 5xx share is a failure and
+# keeps its fixed cutoff whatever the history; it shares the 4xx share's
+# minimum of traffic (the operator, #5859).
 NORMED = ("error_rate_4xx_pct", "latency_p95_ms")
 
 
 def min_requests(thresholds: dict) -> float:
-    """Fewest requests over the STATE_WINDOW for a 4xx share to be graded
-    (Settings → Thresholds, traefik.threshold.min_requests)."""
+    """Fewest requests over the STATE_WINDOW for a 4xx or 5xx share to be
+    graded (Settings → Thresholds, traefik.threshold.min_requests)."""
     return float(thresholds.get("router_requests", {}).get("warn", 30))
 
 
@@ -78,10 +79,13 @@ def router_state(reading, thresholds: dict, over: str = "", norms: dict | None =
     critical cutoff or a 4xx share past its cutoff (all Settings → Thresholds),
     otherwise ok. `norms` ({metric: Norm}) are the router's normals for this
     hour: a p95 or 4xx share past its cutoff but within its normal is ok, and
-    `why` then says it is usual. `over` names the span the reading covers."""
+    `why` then says it is usual. `over` names the span the reading covers.
+    Neither share is graded over fewer than min_requests() requests."""
     norms = norms or {}
     error_5xx, error_4xx = error_cutoffs(thresholds)
-    if (reading.error_rate_5xx_pct or 0) > error_5xx:
+    requests = getattr(reading, "requests", None)
+    enough = requests is None or requests >= min_requests(thresholds)
+    if enough and (reading.error_rate_5xx_pct or 0) > error_5xx:
         return "crit", f"{reading.error_rate_5xx_pct:.1f}% of responses are 5xx{over}"
     usual = []
     p95 = reading.latency_p95_ms
@@ -91,9 +95,8 @@ def router_state(reading, thresholds: dict, over: str = "", norms: dict | None =
         if out:
             return "warn", f"p95 latency is {p95:.0f} ms{over}" + (f", {said}" if said else "")
         usual.append(f"p95 {p95:.0f} ms is {said}")
-    requests = getattr(reading, "requests", None)
     e4 = reading.error_rate_4xx_pct or 0
-    if e4 > error_4xx and (requests is None or requests >= min_requests(thresholds)):
+    if enough and e4 > error_4xx:
         out, said = anom.against(e4, norms.get("error_rate_4xx_pct"),
                                   floor_of(thresholds, "router_4xx_pct"), "%")
         if out: