Merge pull request #2719 from 6vision/feat/deepseek-bot

feat: add independent DeepSeek bot module with dedicated config
2026-04-06 20:38:17 +08:00 · 2026-03-23 22:42:58 +08:00
parent 3ca52b118d cffa20d37e
commit 0974c940a8
11 changed files with 305 additions and 39 deletions
--- a/README.md
+++ b/README.md
@@ -155,6 +155,8 @@ pip3 install -r requirements-optional.txt
  "claude_api_base": "https://api.anthropic.com/v1",          # Claude API 地址，修改可接入三方代理平台
  "gemini_api_key": "",                                       # Gemini API Key
  "gemini_api_base": "https://generativelanguage.googleapis.com", # Gemini API地址
+  "deepseek_api_key": "",                                      # DeepSeek API Key
+  "deepseek_api_base": "https://api.deepseek.com/v1",         # DeepSeek API 地址，可修改为第三方代理
  "open_ai_api_key": "",                                      # OpenAI API Key
  "open_ai_api_base": "https://api.openai.com/v1",            # OpenAI API 地址
  "linkai_api_key": "",                                       # LinkAI API Key
@@ -472,21 +474,31 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)

 2. 填写配置

+方式一：官方接入（推荐）：
+
 ```json
 {
    "model": "deepseek-chat",
-    "open_ai_api_key": "sk-xxxxxxxxxxx",
-    "open_ai_api_base": "https://api.deepseek.com/v1",
-    "bot_type": "openai"
-
+    "deepseek_api_key": "sk-xxxxxxxxxxx"
 }
 ```

- - `bot_type`: OpenAI兼容方式
 - `model`: 可填 `deepseek-chat、deepseek-reasoner`，分别对应的是 DeepSeek-V3 和 DeepSeek-R1 模型
- - `open_ai_api_key`: DeepSeek平台的 API Key
- - `open_ai_api_base`: DeepSeek平台 BASE URL
-</details>
+ - `deepseek_api_key`: DeepSeek平台的 API Key
+ - `deepseek_api_base`: 可选，默认为 `https://api.deepseek.com/v1`，可修改为第三方代理地址
+
+方式二：OpenAI兼容方式接入：
+
+```json
+{
+    "model": "deepseek-chat",
+    "bot_type": "openai",
+    "open_ai_api_key": "sk-xxxxxxxxxxx",
+    "open_ai_api_base": "https://api.deepseek.com/v1"
+}
+```
+
+ </details>

 <details>
 <summary>Azure</summary>
--- a/bridge/agent_bridge.py
+++ b/bridge/agent_bridge.py
@@ -74,7 +74,7 @@ class AgentLLMModel(LLMModel):
        ("qwen", const.QWEN_DASHSCOPE), ("qwq", const.QWEN_DASHSCOPE), ("qvq", const.QWEN_DASHSCOPE),
        ("gemini", const.GEMINI), ("glm", const.ZHIPU_AI), ("claude", const.CLAUDEAPI),
        ("moonshot", const.MOONSHOT), ("kimi", const.MOONSHOT),
-        ("doubao", const.DOUBAO),
+        ("doubao", const.DOUBAO), ("deepseek", const.DEEPSEEK),
    ]

    def __init__(self, bridge: Bridge, bot_type: str = "chat"):
@@ -115,8 +115,6 @@ class AgentLLMModel(LLMModel):
            return const.QWEN_DASHSCOPE
        if model_name in [const.MOONSHOT, "moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]:
            return const.MOONSHOT
-        if model_name in [const.DEEPSEEK_CHAT, const.DEEPSEEK_REASONER]:
-            return const.OPENAI
        for prefix, btype in self._MODEL_PREFIX_MAP:
            if model_name.startswith(prefix):
                return btype
--- a/bridge/bridge.py
+++ b/bridge/bridge.py
@@ -61,6 +61,9 @@ class Bridge(object):
            if model_type and model_type.startswith("doubao"):
                self.btype["chat"] = const.DOUBAO

+            if model_type and model_type.startswith("deepseek"):
+                self.btype["chat"] = const.DEEPSEEK
+
            if model_type in [const.MODELSCOPE]:
                self.btype["chat"] = const.MODELSCOPE
            
--- a/channel/web/web_channel.py
+++ b/channel/web/web_channel.py
@@ -563,9 +563,9 @@ class ConfigHandler:
        }),
        ("deepseek", {
            "label": "DeepSeek",
-            "api_key_field": "open_ai_api_key",
-            "api_base_key": None,
-            "api_base_default": None,
+            "api_key_field": "deepseek_api_key",
+            "api_base_key": "deepseek_api_base",
+            "api_base_default": "https://api.deepseek.com/v1",
            "models": [const.DEEPSEEK_CHAT, const.DEEPSEEK_REASONER],
        }),
        ("linkai", {
@@ -579,9 +579,9 @@ class ConfigHandler:

    EDITABLE_KEYS = {
        "model", "bot_type", "use_linkai",
-        "open_ai_api_base", "claude_api_base", "gemini_api_base",
+        "open_ai_api_base", "deepseek_api_base", "claude_api_base", "gemini_api_base",
        "zhipu_ai_api_base", "moonshot_base_url", "ark_base_url",
-        "open_ai_api_key", "claude_api_key", "gemini_api_key",
+        "open_ai_api_key", "deepseek_api_key", "claude_api_key", "gemini_api_key",
        "zhipu_ai_api_key", "dashscope_api_key", "moonshot_api_key",
        "ark_api_key", "minimax_api_key", "linkai_api_key",
        "agent_max_context_tokens", "agent_max_context_turns", "agent_max_steps",
--- a/docs/en/models/deepseek.mdx
+++ b/docs/en/models/deepseek.mdx
@@ -3,7 +3,22 @@ title: DeepSeek
 description: DeepSeek model configuration
 ---

-Use OpenAI-compatible configuration:
+Option 1: Native integration (recommended):
+
+```json
+{
+  "model": "deepseek-chat",
+  "deepseek_api_key": "YOUR_API_KEY"
+}
+```
+
+| Parameter | Description |
+| --- | --- |
+| `model` | `deepseek-chat` (DeepSeek-V3), `deepseek-reasoner` (DeepSeek-R1) |
+| `deepseek_api_key` | Create at [DeepSeek Platform](https://platform.deepseek.com/api_keys) |
+| `deepseek_api_base` | Optional, defaults to `https://api.deepseek.com/v1`. Can be changed to a third-party proxy |
+
+Option 2: OpenAI-compatible configuration:

 ```json
 {
@@ -14,9 +29,6 @@ Use OpenAI-compatible configuration:
 }
 ```

-| Parameter | Description |
-| --- | --- |
-| `model` | `deepseek-chat` (DeepSeek-V3), `deepseek-reasoner` (DeepSeek-R1) |
-| `bot_type` | Must be `openai` (OpenAI-compatible mode) |
-| `open_ai_api_key` | Create at [DeepSeek Platform](https://platform.deepseek.com/api_keys) |
-| `open_ai_api_base` | DeepSeek platform BASE URL |
+<Note>
+  Existing users who configured DeepSeek via `open_ai_api_key` / `open_ai_api_base` do not need to change anything — the program will automatically fall back to those fields. New users are recommended to use Option 1 to avoid config conflicts with OpenAI.
+</Note>
--- a/docs/ja/models/deepseek.mdx
+++ b/docs/ja/models/deepseek.mdx
@@ -3,7 +3,22 @@ title: DeepSeek
 description: DeepSeekモデルの設定
 ---

-OpenAI互換の設定を使用します:
+方法1：公式接続（推奨）：
+
+```json
+{
+  "model": "deepseek-chat",
+  "deepseek_api_key": "YOUR_API_KEY"
+}
+```
+
+| パラメータ | 説明 |
+| --- | --- |
+| `model` | `deepseek-chat` (DeepSeek-V3)、`deepseek-reasoner` (DeepSeek-R1) |
+| `deepseek_api_key` | [DeepSeek Platform](https://platform.deepseek.com/api_keys)で作成 |
+| `deepseek_api_base` | オプション、デフォルトは `https://api.deepseek.com/v1`。サードパーティプロキシに変更可能 |
+
+方法2：OpenAI互換方式：

 ```json
 {
@@ -13,10 +28,3 @@ OpenAI互換の設定を使用します:
  "open_ai_api_base": "https://api.deepseek.com/v1"
 }
 ```
-
-| パラメータ | 説明 |
-| --- | --- |
-| `model` | `deepseek-chat` (DeepSeek-V3)、`deepseek-reasoner` (DeepSeek-R1) |
-| `bot_type` | `openai`を指定（OpenAI互換モード） |
-| `open_ai_api_key` | [DeepSeek Platform](https://platform.deepseek.com/api_keys)で作成 |
-| `open_ai_api_base` | DeepSeekプラットフォームのBASE URL |
--- a/docs/models/deepseek.mdx
+++ b/docs/models/deepseek.mdx
@@ -3,20 +3,32 @@ title: DeepSeek
 description: DeepSeek 模型配置
 ---

-通过 OpenAI 兼容方式接入：
+方式一：官方接入（推荐）：

 ```json
 {
  "model": "deepseek-chat",
-  "open_ai_api_key": "YOUR_API_KEY",
-  "open_ai_api_base": "https://api.deepseek.com/v1",
-  "bot_type": "openai"
+  "deepseek_api_key": "YOUR_API_KEY"
 }
 ```

 | 参数 | 说明 |
 | --- | --- |
 | `model` | `deepseek-chat`（DeepSeek-V3）、`deepseek-reasoner`（DeepSeek-R1） |
-| `bot_type` | 固定为 `openai`（OpenAI 兼容方式） |
-| `open_ai_api_key` | 在 [DeepSeek 平台](https://platform.deepseek.com/api_keys) 创建 |
-| `open_ai_api_base` | DeepSeek 平台 BASE URL |
+| `deepseek_api_key` | 在 [DeepSeek 平台](https://platform.deepseek.com/api_keys) 创建 |
+| `deepseek_api_base` | 可选，默认为 `https://api.deepseek.com/v1`，可修改为第三方代理地址 |
+
+方式二：OpenAI 兼容方式接入：
+
+```json
+{
+  "model": "deepseek-chat",
+  "bot_type": "openai",
+  "open_ai_api_key": "YOUR_API_KEY",
+  "open_ai_api_base": "https://api.deepseek.com/v1"
+}
+```
+
+<Note>
+  已有用户如果之前通过 `open_ai_api_key` / `open_ai_api_base` 配置 DeepSeek，无需修改，程序会自动兼容。推荐新用户使用方式一的独立配置，避免与 OpenAI 配置冲突。
+</Note>
--- a/models/bot_factory.py
+++ b/models/bot_factory.py
@@ -17,7 +17,11 @@ def create_bot(bot_type):
        from models.baidu.baidu_wenxin import BaiduWenxinBot
        return BaiduWenxinBot()

-    elif bot_type in (const.OPENAI, const.CHATGPT, const.DEEPSEEK):  # OpenAI-compatible API
+    elif bot_type == const.DEEPSEEK:
+        from models.deepseek.deepseek_bot import DeepSeekBot
+        return DeepSeekBot()
+
+    elif bot_type in (const.OPENAI, const.CHATGPT):  # OpenAI-compatible API
        from models.chatgpt.chat_gpt_bot import ChatGPTBot
        return ChatGPTBot()

--- a/models/deepseek/init.py
+++ b/models/deepseek/init.py
--- a/models/deepseek/deepseek_bot.py
+++ b/models/deepseek/deepseek_bot.py
@@ -0,0 +1,160 @@
+# encoding:utf-8
+
+"""
+DeepSeek Bot — fully OpenAI-compatible, uses its own API key / base config.
+"""
+
+import time
+
+import requests
+from models.bot import Bot
+from models.openai_compatible_bot import OpenAICompatibleBot
+from models.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common import const
+from common.log import logger
+from config import conf, load_config
+from .deepseek_session import DeepSeekSession
+
+DEFAULT_API_BASE = "https://api.deepseek.com/v1"
+
+
+class DeepSeekBot(Bot, OpenAICompatibleBot):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(
+            DeepSeekSession,
+            model=conf().get("model") or const.DEEPSEEK_CHAT,
+        )
+        conf_model = conf().get("model") or const.DEEPSEEK_CHAT
+        self.args = {
+            "model": conf_model,
+            "temperature": conf().get("temperature", 0.7),
+            "top_p": conf().get("top_p", 1.0),
+            "frequency_penalty": conf().get("frequency_penalty", 0.0),
+            "presence_penalty": conf().get("presence_penalty", 0.0),
+        }
+
+    # ---------- config helpers ----------
+
+    @property
+    def api_key(self):
+        return conf().get("deepseek_api_key") or conf().get("open_ai_api_key")
+
+    @property
+    def api_base(self):
+        url = (
+            conf().get("deepseek_api_base")
+            or conf().get("open_ai_api_base")
+            or DEFAULT_API_BASE
+        )
+        return url.rstrip("/")
+
+    def get_api_config(self):
+        """OpenAICompatibleBot interface — used by call_with_tools()."""
+        return {
+            "api_key": self.api_key,
+            "api_base": self.api_base,
+            "model": conf().get("model", const.DEEPSEEK_CHAT),
+            "default_temperature": conf().get("temperature", 0.7),
+            "default_top_p": conf().get("top_p", 1.0),
+            "default_frequency_penalty": conf().get("frequency_penalty", 0.0),
+            "default_presence_penalty": conf().get("presence_penalty", 0.0),
+        }
+
+    # ---------- simple chat (non-agent mode) ----------
+
+    def reply(self, query, context=None):
+        if context.type == ContextType.TEXT:
+            logger.info("[DEEPSEEK] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[DEEPSEEK] session query={}".format(session.messages))
+
+            new_args = self.args.copy()
+            reply_content = self.reply_text(session, args=new_args)
+            logger.debug(
+                "[DEEPSEEK] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages, session_id,
+                    reply_content["content"], reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(
+                    reply_content["content"], session_id, reply_content["total_tokens"],
+                )
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[DEEPSEEK] reply {} used 0 tokens.".format(reply_content))
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session, args=None, retry_count: int = 0) -> dict:
+        try:
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": "Bearer " + self.api_key,
+            }
+            body = args.copy()
+            body["messages"] = session.messages
+
+            res = requests.post(
+                f"{self.api_base}/chat/completions",
+                headers=headers,
+                json=body,
+                timeout=180,
+            )
+            if res.status_code == 200:
+                response = res.json()
+                return {
+                    "total_tokens": response["usage"]["total_tokens"],
+                    "completion_tokens": response["usage"]["completion_tokens"],
+                    "content": response["choices"][0]["message"]["content"],
+                }
+            else:
+                response = res.json()
+                error = response.get("error", {})
+                logger.error(
+                    f"[DEEPSEEK] chat failed, status_code={res.status_code}, "
+                    f"msg={error.get('message')}, type={error.get('type')}"
+                )
+                result = {"completion_tokens": 0, "content": "提问太快啦，请休息一下再问我吧"}
+                need_retry = False
+                if res.status_code >= 500:
+                    need_retry = retry_count < 2
+                elif res.status_code == 401:
+                    result["content"] = "授权失败，请检查API Key是否正确"
+                elif res.status_code == 429:
+                    result["content"] = "请求过于频繁，请稍后再试"
+                    need_retry = retry_count < 2
+
+                if need_retry:
+                    time.sleep(3)
+                    return self.reply_text(session, args, retry_count + 1)
+                return result
+        except Exception as e:
+            logger.exception(e)
+            if retry_count < 2:
+                return self.reply_text(session, args, retry_count + 1)
+            return {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
--- a/models/deepseek/deepseek_session.py
+++ b/models/deepseek/deepseek_session.py
@@ -0,0 +1,57 @@
+from models.session_manager import Session
+from common.log import logger
+
+
+class DeepSeekSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="deepseek-chat"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(
+                    max_tokens, cur_tokens, len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages, self.model)
+
+
+def num_tokens_from_messages(messages, model):
+    tokens = 0
+    for msg in messages:
+        content = msg.get("content", "")
+        if isinstance(content, str):
+            tokens += len(content)
+        elif isinstance(content, list):
+            for block in content:
+                if isinstance(block, dict):
+                    tokens += len(block.get("text", ""))
+    return tokens