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/onboard.ts

@@ -0,0 +1,31 @@
+import {
+  createModelCatalogPresetAppliers,
+  type OpenClawConfig,
+} from "openclaw/plugin-sdk/provider-onboard";
+import {
+  buildVeniceModelDefinition,
+  VENICE_BASE_URL,
+  VENICE_DEFAULT_MODEL_REF,
+  VENICE_MODEL_CATALOG,
+} from "./api.js";
+
+export { VENICE_DEFAULT_MODEL_REF };
+
+const venicePresetAppliers = createModelCatalogPresetAppliers({
+  primaryModelRef: VENICE_DEFAULT_MODEL_REF,
+  resolveParams: (_cfg: OpenClawConfig) => ({
+    providerId: "venice",
+    api: "openai-completions",
+    baseUrl: VENICE_BASE_URL,
+    catalogModels: VENICE_MODEL_CATALOG.map(buildVeniceModelDefinition),
+    aliases: [{ modelRef: VENICE_DEFAULT_MODEL_REF, alias: "Kimi K2.5" }],
+  }),
+});
+
+export function applyVeniceProviderConfig(cfg: OpenClawConfig): OpenClawConfig {
+  return venicePresetAppliers.applyProviderConfig(cfg);
+}
+
+export function applyVeniceConfig(cfg: OpenClawConfig): OpenClawConfig {
+  return venicePresetAppliers.applyConfig(cfg);
+}