请详细回答以下问题：解释什么是递归，并举例说明。请展开论述，分点说明，条理清晰。

Method: POST

URL: https://tokease.cn/v1/chat/completions

Headers:
{
  "Authorization": "Bearer sk-oRd5RE9JhT1bDLQ3lOZgdkESeCuowucrcNX16gZEgHecnxmu",
  "Content-Type": "application/json"
}

Body:
{
  "max_tokens": 300,
  "messages": [
    {
      "role": "user",
      "content": "请详细回答以下问题：解释什么是递归，并举例说明。请展开论述，分点说明，条理清晰。"
    }
  ],
  "model": "deepseek-v4-flash/yd"
}

Headers:
{
  "Content-Length": "2006",
  "Content-Type": "application/json",
  "Date": "Fri, 21 Aug 2026 08:24:53 GMT",
  "Req-Arrive-Time": "1787300692944",
  "Req-Cost-Time": "694",
  "Resp-Start-Time": "1787300693638",
  "Server": "nginx",
  "Set-Cookie": "route=b6817f60ab83a9ecf16ead57be0f0f66; Path=/",
  "Vary": "Accept-Encoding",
  "Via": "1.1 Caddy",
  "X-Envoy-Upstream-Service-Time": "686",
  "X-New-Api-Version": "v0.0.0",
  "X-Oneapi-Request-Id": "202608210824529153306388268d9d6YgCWFhtl",
  "X-Request-Id": "7ceabaac-66ad-4624-8d34-4f70581e4def"
}

Body:
{
  "id": "chatcmpl-541ef531-6b53-4466-b984-91053a70473e",
  "object": "chat.completion",
  "created": 1787300693,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "## 什么是递归\n\n递归（Recursion）是一种在数学和计算机科学中广泛使用的编程技术，其核心思想是**函数直接或间接地调用自身**，通过将一个大问题分解为若干个规模更小、结构相似的子问题，逐步求解，最终汇总结果。\n\n递归包含两个核心要素：\n\n1. **基线条件（Base Case）**：递归停止的条件，当问题规模小到可以直接求解时，不再继续调用自身。缺少基线条件会导致无限递归（栈溢出）。\n2. **递归条件（Recursive Case）**：将当前问题转化为一个或多个同类型但规模更小的子问题，并调用自身来解决。\n\n---\n\n## 递归的工作原理\n\n递归的执行过程可以分为两个阶段：\n\n- **递推（递去）**：每次调用自身时，问题规模逐渐缩小，直到触底（达到基线条件）。\n- **回归（归来）**：当基线条件满足后，函数开始逐层返回结果，并将各层结果合并，最终得到原问题的解。\n\n---\n\n## 经典举例\n\n### 例子1：阶乘（Factorial）\n\n阶乘的定义：\n- `n! = n × (n-1) × ... × 1`  \n- 特别地，`0! = 1`\n\n递归实现（Python）：\n```python\ndef factorial(n):\n    # 基线条件\n    if n == 0 or n == 1:\n        return 1\n    #",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "function_call": null,
        "reasoning": null
      },
      "logprobs": null,
      "finish_reason": "length",
      "stop_reason": null,
      "token_ids": null,
      "routed_experts": null
    }
  ],
  "service_tier": null,
  "system_fingerprint": "vllm-0.25.1-dp8-ep-1d021cfb",
  "usage": {
    "prompt_tokens": 30,
    "total_tokens": 330,
    "completion_tokens": 300,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "multimodal_tokens": null
    }
  },
  "prompt_logprobs": null,
  "prompt_token_ids": null,
  "prompt_text": null,
  "kv_transfer_params": null,
  "metrics": null
}

{
  "prompt_tokens": 30,
  "total_tokens": 330,
  "completion_tokens": 300,
  "prompt_tokens_details": {
    "cached_tokens": 0,
    "multimodal_tokens": null
  }
}

Method: POST

URL: /v1/chat/completions

Headers:
{
  "Accept": "*/*",
  "Accept-Encoding": "gzip",
  "Authorization": "Bearer sk_r4gAXloJQt74Cp4prb19OItKzoG77lLhjmWT4ei20Ua",
  "Content-Length": "211",
  "Content-Type": "application/json",
  "User-Agent": "Go-http-client/2.0",
  "Via": "2.0 Caddy",
  "X-Forwarded-For": "13.212.110.206",
  "X-Forwarded-Host": "api.tokendiet.cn",
  "X-Forwarded-Proto": "https"
}

Body:
{
  "model": "deepseek-v4-flash-g1",
  "messages": [
    {
      "role": "user",
      "content": "请详细回答以下问题：解释什么是递归，并举例说明。请展开论述，分点说明，条理清晰。"
    }
  ],
  "max_tokens": 300
}

Body:
{
  "choices": [
    {
      "finish_reason": "length",
      "index": 0,
      "logprobs": null,
      "message": {
        "annotations": null,
        "audio": null,
        "content": "## 什么是递归\n\n递归（Recursion）是一种在数学和计算机科学中广泛使用的编程技术，其核心思想是**函数直接或间接地调用自身**，通过将一个大问题分解为若干个规模更小、结构相似的子问题，逐步求解，最终汇总结果。\n\n递归包含两个核心要素：\n\n1. **基线条件（Base Case）**：递归停止的条件，当问题规模小到可以直接求解时，不再继续调用自身。缺少基线条件会导致无限递归（栈溢出）。\n2. **递归条件（Recursive Case）**：将当前问题转化为一个或多个同类型但规模更小的子问题，并调用自身来解决。\n\n---\n\n## 递归的工作原理\n\n递归的执行过程可以分为两个阶段：\n\n- **递推（递去）**：每次调用自身时，问题规模逐渐缩小，直到触底（达到基线条件）。\n- **回归（归来）**：当基线条件满足后，函数开始逐层返回结果，并将各层结果合并，最终得到原问题的解。\n\n---\n\n## 经典举例\n\n### 例子1：阶乘（Factorial）\n\n阶乘的定义：\n- `n! = n × (n-1) × ... × 1`  \n- 特别地，`0! = 1`\n\n递归实现（Python）：\n```python\ndef factorial(n):\n    # 基线条件\n    if n == 0 or n == 1:\n        return 1\n    #",
        "function_call": null,
        "reasoning": null,
        "refusal": null,
        "role": "assistant"
      },
      "routed_experts": null,
      "stop_reason": null,
      "token_ids": null
    }
  ],
  "created": 1787300693,
  "id": "chatcmpl-gsTs4lxOAlJ7DJSO",
  "kv_transfer_params": null,
  "metrics": null,
  "model": "deepseek-v4-flash-g1",
  "object": "chat.completion",
  "prompt_logprobs": null,
  "prompt_text": null,
  "prompt_token_ids": null,
  "service_tier": null,
  "system_fingerprint": "vllm-0.25.1-dp8-ep-1d021cfb",
  "usage": {
    "completion_tokens": 300,
    "prompt_tokens": 30,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "multimodal_tokens": null
    },
    "total_tokens": 330
  }
}