feat: add Anthropic API provider support and missing env vars

- Add LLM_PROVIDER env var (openai/anthropic) to switch cloud backend
- Use ChatAnthropic for anthropic provider with custom base_url
- Add CONTEXT_MAX_TOKENS, CONTEXT_KEEP_RECENT, SESSIONS_DIR,
  HISTORY_MAX_SNAPSHOTS to .env and .env.example
- Add langchain-anthropic dependency to requirements.txt

Note: E2E testing blocked — the configured MiniMax API key
(sk-cp-...) returns 401 across all endpoints (Anthropic and OpenAI).
The API key may be expired or lack text-generation model access.

backend/llm.py

@@ -1,4 +1,4 @@
-"""大语言模型工厂：支持 OpenAI 兼容的云端 API 和本地 Ollama。"""
+"""大语言模型工厂：支持 OpenAI 兼容的云端 API、Anthropic 兼容 API 和本地 Ollama。"""
 
 import os
 from dotenv import load_dotenv
@@ -13,6 +13,17 @@ def get_llm():
 
         model = os.getenv("LOCAL_LLM_MODEL", "qwen2.5-coder:7b")
         return ChatOllama(model=model, temperature=0.1)
+
+    provider = os.getenv("LLM_PROVIDER", "openai")
+    if provider == "anthropic":
+        from langchain_anthropic import ChatAnthropic
+
+        return ChatAnthropic(
+            model=os.getenv("LLM_MODEL", "claude-sonnet-4-6"),
+            api_key=os.getenv("OPENAI_API_KEY"),
+            base_url=os.getenv("OPENAI_BASE_URL", "https://api.anthropic.com"),
+            temperature=0.1,
+        )
     else:
         from langchain_openai import ChatOpenAI