重构主控编排与运行时预热链路，统一工作区提示词/专家调度协议并补齐 wiki 记忆注入与写回闭环。

同时收敛启动与运维脚本默认行为（含 wiki worker）、更新 Admin 可观测性与相关测试，降低首轮时延并提高运行稳定性。

Made-with: Cursor

openclaw/extensions/venice/index.ts

@@ -0,0 +1,48 @@
+import { defineSingleProviderPluginEntry } from "openclaw/plugin-sdk/provider-entry";
+import { applyXaiModelCompat } from "openclaw/plugin-sdk/provider-tools";
+import { normalizeLowercaseStringOrEmpty } from "openclaw/plugin-sdk/text-runtime";
+import { applyVeniceConfig, VENICE_DEFAULT_MODEL_REF } from "./onboard.js";
+import { buildVeniceProvider } from "./provider-catalog.js";
+
+const PROVIDER_ID = "venice";
+
+function isXaiBackedVeniceModel(modelId: string): boolean {
+  return normalizeLowercaseStringOrEmpty(modelId).includes("grok");
+}
+
+export default defineSingleProviderPluginEntry({
+  id: PROVIDER_ID,
+  name: "Venice Provider",
+  description: "Bundled Venice provider plugin",
+  provider: {
+    label: "Venice",
+    docsPath: "/providers/venice",
+    auth: [
+      {
+        methodId: "api-key",
+        label: "Venice AI API key",
+        hint: "Privacy-focused (uncensored models)",
+        optionKey: "veniceApiKey",
+        flagName: "--venice-api-key",
+        envVar: "VENICE_API_KEY",
+        promptMessage: "Enter Venice AI API key",
+        defaultModel: VENICE_DEFAULT_MODEL_REF,
+        applyConfig: (cfg) => applyVeniceConfig(cfg),
+        noteMessage: [
+          "Venice AI provides privacy-focused inference with uncensored models.",
+          "Get your API key at: https://venice.ai/settings/api",
+          "Supports 'private' (fully private) and 'anonymized' (proxy) modes.",
+        ].join("\n"),
+        noteTitle: "Venice AI",
+        wizard: {
+          groupLabel: "Venice AI",
+        },
+      },
+    ],
+    catalog: {
+      buildProvider: buildVeniceProvider,
+    },
+    normalizeResolvedModel: ({ modelId, model }) =>
+      isXaiBackedVeniceModel(modelId) ? applyXaiModelCompat(model) : undefined,
+  },
+});