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/chat.ts

@@ -0,0 +1,52 @@
+import { http } from "@/http"
+
+export interface ToolCall {
+  id: string
+  name: string
+  arguments: Record<string, unknown>
+}
+
+export interface ChatMessage {
+  id: number
+  role: "user" | "assistant" | "tool"
+  /** user: {text}；assistant: {text, tool_calls, stopped?, error?}；tool: {tool_call_id, name, result} */
+  content: Record<string, any>
+  provider_id: number | null
+  usage: { input_tokens?: number, output_tokens?: number } | null
+  created_at: string
+}
+
+export interface ChatSession {
+  id: number
+  created_at: string
+  messages: ChatMessage[]
+  estimated_tokens: number
+  generating: boolean
+}
+
+export interface ChatContext {
+  id: number | null
+  content: string
+  source: "user" | "chat" | "reset" | null
+  created_at: string | null
+}
+
+export function getChatSession(): Promise<ChatSession> {
+  return http.get("/chat/session")
+}
+
+export function resetChat(clearContext: boolean): Promise<void> {
+  return http.post("/chat/reset", { clear_context: clearContext })
+}
+
+export function getChatContext(): Promise<ChatContext> {
+  return http.get("/chat/context")
+}
+
+export function saveChatContext(content: string): Promise<ChatContext> {
+  return http.put("/chat/context", { content })
+}
+
+export function listChatContextVersions(): Promise<ChatContext[]> {
+  return http.get("/chat/context/versions")
+}