fix(inferences): stop showing a healthy scaler as failing

web/src/modules/inferences/lib.test.ts

@@ -191,6 +191,94 @@ describe("installSteps", () => {
   it("calls a deleted ModelRoute bad", () => {
     expect(installSteps(status(), route({ missing: true }) as never, {})[2]!.state).toBe("bad");
   });
+
+  const scaler = (conditions: { type: string; status: string; reason?: string; message?: string }[], cur = 1, want = 1) => ({
+    result: { ref: { apiVersion: "v1", kind: "LLMScaler", name: "r" } } as ObjectResult,
+    status: { currentReplicas: cur, desiredReplicas: want, conditions },
+  });
+  const step = (conditions: { type: string; status: string; reason?: string; message?: string }[], cur = 1, want = 1) =>
+    installSteps(status(), {}, scaler(conditions, cur, want) as never)[3];
+
+  it("reads a healthy scaler as steady, including ScalingLimited=False", () => {
+    expect(step([
+      { type: "ScalingActive", status: "True", reason: "DecisionReceived" },
+      { type: "AbleToScale", status: "True", reason: "Synced" },
+      { type: "ScalingLimited", status: "False", reason: "DesiredWithinRange" },
+    ])).toEqual({ key: "scaler", state: "ok", detail: "steady", params: { n: 1 } });
+  });
+  it("calls AbleToScale=False a failure and shows its message", () => {
+    expect(step([
+      { type: "ScalingActive", status: "True", reason: "DecisionReceived" },
+      { type: "AbleToScale", status: "False", reason: "TargetNotFound", message: "deployment demo is gone" },
+    ])).toEqual({ key: "scaler", state: "bad", detail: "failingMessage", params: { reason: "TargetNotFound", message: "deployment demo is gone" } });
+  });
+  it("calls ScalingActive=False a failure", () => {
+    expect(step([
+      { type: "ScalingActive", status: "False", reason: "DecisionUnavailable" },
+      { type: "AbleToScale", status: "True", reason: "Synced" },
+    ])).toEqual({ key: "scaler", state: "bad", detail: "failing", params: { reason: "DecisionUnavailable" } });
+  });
+  it("prefers AbleToScale when it and ScalingActive are both False", () => {
+    expect(step([
+      { type: "ScalingActive", status: "False", reason: "InvalidSpec", message: "bad query" },
+      { type: "AbleToScale", status: "False", reason: "TargetWriteFailed", message: "apiserver rejected the scale" },
+    ])).toEqual({ key: "scaler", state: "bad", detail: "failingMessage", params: { reason: "TargetWriteFailed", message: "apiserver rejected the scale" } });
+  });
+  it("uses the condition type when a failure gives no reason", () => {
+    expect(step([{ type: "AbleToScale", status: "False" }])).toEqual({ key: "scaler", state: "bad", detail: "failing", params: { reason: "AbleToScale" } });
+  });
+  it("does not treat ScalingLimited as a failure", () => {
+    expect(step([
+      { type: "ScalingLimited", status: "False", reason: "DesiredWithinRange" },
+      { type: "SomeOther", status: "False", reason: "Whatever" },
+    ])).toEqual({ key: "scaler", state: "ok", detail: "steady", params: { n: 1 } });
+    expect(step([
+      { type: "ScalingActive", status: "True", reason: "MetricsAvailable" },
+      { type: "AbleToScale", status: "True", reason: "Synced" },
+      { type: "ScalingLimited", status: "True", reason: "TooManyReplicas" },
+    ])).toEqual({ key: "scaler", state: "ok", detail: "steady", params: { n: 1 } });
+  });
+  it("holds while a rollout or scale-down guard is in effect", () => {
+    for (const reason of ["RolloutInProgress", "ScaleDownSettling", "ScaleDownStabilized"]) {
+      expect(step([
+        { type: "ScalingActive", status: "True", reason: "MetricsAvailable" },
+        { type: "AbleToScale", status: "True", reason },
+      ], 3, 1)).toEqual({ key: "scaler", state: "wait", detail: "deferred", params: { reason } });
+    }
+  });
+  it("treats DeferralTimedOut as a normal scale", () => {
+    expect(step([
+      { type: "ScalingActive", status: "True", reason: "DecisionReceived" },
+      { type: "AbleToScale", status: "True", reason: "DeferralTimedOut" },
+    ], 1, 2)).toEqual({ key: "scaler", state: "wait", detail: "scaling", params: { cur: 1, want: 2 } });
+  });
+  // Operator 0.5.0 sets DecisionAvailable only under the Custom provider, and no condition under Prometheus.
+  it("reads a 0.5.0 scaler with a decision as steady", () => {
+    expect(step([
+      { type: "DecisionAvailable", status: "True", reason: "DecisionReceived", message: "decision server recommends 2 replicas" },
+    ], 2, 2)).toEqual({ key: "scaler", state: "ok", detail: "steady", params: { n: 2 } });
+  });
+  it("calls a 0.5.0 DecisionAvailable=False a failure, with its message", () => {
+    expect(step([
+      { type: "DecisionAvailable", status: "False", reason: "DecisionUnavailable", message: "decision server returned 404" },
+    ])).toEqual({ key: "scaler", state: "bad", detail: "failingMessage", params: { reason: "DecisionUnavailable", message: "decision server returned 404" } });
+  });
+  it("reads a 0.5.0 Prometheus scaler with no conditions from its replicas", () => {
+    expect(step([], 1, 3)).toEqual({ key: "scaler", state: "wait", detail: "scaling", params: { cur: 1, want: 3 } });
+    expect(step([], 3, 3)).toEqual({ key: "scaler", state: "ok", detail: "steady", params: { n: 3 } });
+  });
+  it("fails on AbleToScale=False with its message when ScalingActive is missing", () => {
+    expect(step([
+      { type: "AbleToScale", status: "False", reason: "TargetUnreadable", message: "cannot read deployment demo" },
+    ])).toEqual({ key: "scaler", state: "bad", detail: "failingMessage", params: { reason: "TargetUnreadable", message: "cannot read deployment demo" } });
+  });
+  it("prefers ScalingActive over DecisionAvailable", () => {
+    expect(step([
+      { type: "ScalingActive", status: "True", reason: "MetricsAvailable" },
+      { type: "DecisionAvailable", status: "False", reason: "DecisionUnavailable" },
+      { type: "AbleToScale", status: "True", reason: "Synced" },
+    ])).toEqual({ key: "scaler", state: "ok", detail: "steady", params: { n: 1 } });
+  });
 });
 
 describe("age", () => {

web/src/modules/inferences/lib.ts

@@ -159,13 +159,31 @@ function routeStep({ result, spec, status }: Picked<ModelRouteSpec, ModelRouteSt
   return status?.ready ? { key, state: "ok", detail: "ready", params } : { key, state: "wait", detail: "notReady", params };
 }
 
+// AbleToScale=True reasons that hold a step. Synced and DeferralTimedOut are a normal scale.
+const SCALE_HOLD_REASONS = new Set(["RolloutInProgress", "ScaleDownSettling", "ScaleDownStabilized"]);
+
 function scalerStep({ result, status }: Picked<LLMScalerSpec, LLMScalerStatus>): Step {
   const key = "scaler";
   if (!result) return { key, state: "off", detail: "none" };
   if (result.error) return { key, state: "wait", detail: "unreadable" };
   if (result.missing) return { key, state: "bad", detail: "deleted" };
-  const failing = status?.conditions?.find((c) => c.status === "False");
-  if (failing) return { key, state: "bad", detail: "failing", params: { reason: failing.reason || failing.type } };
+  // DecisionAvailable is a deprecated mirror of ScalingActive and the only condition operator 0.5.0 writes.
+  const conditions = status?.conditions ?? [];
+  const ofType = (type: string) => conditions.find((c) => c.type === type);
+  const active = ofType("ScalingActive") ?? ofType("DecisionAvailable");
+  const able = ofType("AbleToScale");
+
+  const failing = able?.status === "False" ? able : active?.status === "False" ? active : undefined;
+  if (failing) {
+    const reason = failing.reason || failing.type;
+    if (failing.message) return { key, state: "bad", detail: "failingMessage", params: { reason, message: failing.message } };
+    return { key, state: "bad", detail: "failing", params: { reason } };
+  }
+
+  if (able?.status === "True" && able.reason && SCALE_HOLD_REASONS.has(able.reason)) {
+    return { key, state: "wait", detail: "deferred", params: { reason: able.reason } };
+  }
+
   const cur = status?.currentReplicas;
   const want = status?.desiredReplicas;
   if (cur === undefined) return { key, state: "wait", detail: "noDecision" };

web/src/modules/inferences/locales/en-US.json

@@ -197,6 +197,8 @@
       "unreadable": "Unreadable",
       "deleted": "LLMScaler deleted",
       "failing": "{reason}",
+      "failingMessage": "{reason}: {message}",
+      "deferred": "Holding: {reason}",
       "noDecision": "No decision yet",
       "scaling": "{cur} → {want} replicas",
       "steady": "{n} replicas, steady"

web/src/modules/inferences/locales/zh-CN.json

@@ -186,6 +186,8 @@
       "unreadable": "读取失败",
       "deleted": "LLMScaler 已被删除",
       "failing": "{reason}",
+      "failingMessage": "{reason}：{message}",
+      "deferred": "伸缩暂缓：{reason}",
       "noDecision": "还没有伸缩决策",
       "scaling": "{cur} → {want} 副本",
       "steady": "{n} 副本，稳定"