fix(web): keep consultation conclusions across turns and surface cache hits (BUG-555, BUG-556)

Session history was silently clipped to the first 4000 characters of the last 12 messages, so follow-ups could not see timing or audit tables. Keep an append-only tail plus a checkpoint summary, retry overflow in the same request, and expose cache hit rate in admin usage.

Co-authored-by: Cursor <cursoragent@cursor.com>

frontend/src/components/admin/billing-operations-resources.tsx

@@ -415,6 +415,7 @@ type Usage = {
   outputTokens: number;
   costMicrousd: number;
   durationMs: number | null;
+  cacheReadTokens: number | null;
   createdAt: string;
 };
 
@@ -452,6 +453,11 @@ export function UsageResource() {
       render: (_, item) =>
         `${item.inputTokens.toLocaleString()} / ${item.outputTokens.toLocaleString()}`,
     },
+    {
+      title: "缓存读 tokens",
+      dataIndex: "cacheReadTokens",
+      render: (value: number | null) => value == null ? "—" : value.toLocaleString(),
+    },
     {
       title: "成本",
       dataIndex: "costMicrousd",

frontend/src/components/admin/pricing-simulator.tsx

@@ -27,7 +27,19 @@ const BANDS: DistributionBand[] = [
 type ModelRow = ModelPrice & { modelId: string; status: string; enabled: boolean };
 type PricingRow = { featureKey: string; modelTier: string; creditCost: number; status: string; enabled: boolean };
 type Product = { code: string; priceCents: number; enabled: boolean; status: string; entitlements: Array<{ featureKey: string; metadata?: { minuteLimit?: number | null; dayLimit?: number | null; billingLimit?: number | null } }> };
-type UsagePayload = { data: Array<{ featureKey: string; hasData: boolean; metrics: { costMicrousd: Metric; inputTokens: Metric; outputTokens: Metric; durationMs: Metric } }> };
+type CacheModelRow = {
+  actualModelId: string | null;
+  runsWithCache: number;
+  hitRate: number | null;
+  readTokens: number;
+  writeTokens: number;
+  noCacheTokens: number;
+  cacheShare: number | null;
+};
+type UsagePayload = {
+  data: Array<{ featureKey: string; hasData: boolean; metrics: { costMicrousd: Metric; inputTokens: Metric; outputTokens: Metric; durationMs: Metric } }>;
+  cache?: { days7: CacheModelRow[]; days30: CacheModelRow[] };
+};
 
 type LoadState = { models?: ModelRow[]; pricing?: PricingRow[]; products?: Product[]; usage?: UsagePayload; errors: string[] };
 
@@ -48,6 +60,10 @@ function errorText(error: unknown, fallback: string) {
   return error instanceof Error ? error.message : fallback;
 }
 
+function formatPercent(value: number | null) {
+  return value === null || !Number.isFinite(value) ? "—" : `${(value * 100).toFixed(1)}%`;
+}
+
 export function PricingSimulator() {
   const [state, setState] = useState<LoadState>({ errors: [] });
   const [usdToCny, setUsdToCny] = useState<number | null>(null);
@@ -158,6 +174,36 @@ export function PricingSimulator() {
           <Col xs={24} md={8}><Statistic title="画像下可承载会员数" value={capacity ?? "—"} /></Col>
         </Row>
       </Card>
+
+      <Card title="缓存命中">
+        <Typography.Paragraph type="secondary">
+          只统计 `usage_ledger.metadata.cache` 有数据的运行。命中 = 缓存读 tokens &gt; 0。两个窗口互不混算。
+        </Typography.Paragraph>
+        {([
+          ["近 7 天", state.usage?.cache?.days7 ?? []],
+          ["近 30 天", state.usage?.cache?.days30 ?? []],
+        ] as const).map(([title, rows]) => (
+          <div key={title} style={{ marginBottom: 16 }}>
+            <Typography.Text strong>{title}</Typography.Text>
+            <Table<CacheModelRow>
+              size="small"
+              pagination={false}
+              rowKey={(row, index) => `${title}-${row.actualModelId ?? "none"}-${index}`}
+              dataSource={rows}
+              locale={{ emptyText: "暂无缓存数据" }}
+              columns={[
+                { title: "模型", dataIndex: "actualModelId", render: (value) => value ?? "—" },
+                { title: "运行数", dataIndex: "runsWithCache" },
+                { title: "命中率", dataIndex: "hitRate", render: formatPercent },
+                { title: "缓存占比", dataIndex: "cacheShare", render: formatPercent },
+                { title: "读", dataIndex: "readTokens", render: (value: number) => value.toLocaleString() },
+                { title: "写", dataIndex: "writeTokens", render: (value: number) => value.toLocaleString() },
+                { title: "未命中", dataIndex: "noCacheTokens", render: (value: number) => value.toLocaleString() },
+              ]}
+            />
+          </div>
+        ))}
+      </Card>
     </Space>
   );
 }