Add AI chat with skills management and model provider settings

- Model providers for OpenAI and Anthropic message formats (e.g. via
  Sub2API), with API keys encrypted at rest and never returned
- Skills tree with markdown editing, priorities, drafts, publishing and
  rollback; only published skills enter the chat prompt
- Chat page with tool calls over collected news and Binance USD-M
  klines, a persisted CONTEXT.md, reset, and stop-generation support
- Chat may only create skill drafts and update CONTEXT.md; publishing,
  deleting, moving and priority changes stay with the user

web/src/apis/settings.ts

@@ -0,0 +1,58 @@
+import { http } from "@/http"
+
+export type Protocol = "openai" | "anthropic"
+
+export interface Provider {
+  id: number
+  name: string
+  protocol: Protocol
+  base_url: string
+  api_key_hint: string
+  model: string
+  max_tokens: number
+  context_window: number
+  temperature: number | null
+  is_default: boolean
+  updated_at: string
+}
+
+export interface ProviderForm {
+  name: string
+  protocol: Protocol
+  base_url: string
+  /** 编辑时为空表示不修改 */
+  api_key: string
+  model: string
+  max_tokens: number
+  context_window: number
+  temperature: number | null
+  is_default: boolean
+}
+
+export interface TestResult {
+  ok: boolean
+  elapsed_ms: number
+  reply: string | null
+  error: string | null
+}
+
+export function listProviders(): Promise<Provider[]> {
+  return http.get("/settings/providers")
+}
+
+export function createProvider(body: ProviderForm): Promise<Provider> {
+  return http.post("/settings/providers", body)
+}
+
+export function patchProvider(id: number, body: Partial<ProviderForm>): Promise<Provider> {
+  return http.patch(`/settings/providers/${id}`, body)
+}
+
+export function deleteProvider(id: number): Promise<void> {
+  return http.delete(`/settings/providers/${id}`)
+}
+
+export function testProvider(id: number): Promise<TestResult> {
+  // 模型接口超时 120s 且 SDK 会重试，前端放宽等待时间
+  return http.post(`/settings/providers/${id}/test`, null, { timeout: 400000 })
+}