diff --git a/metagpt/actions/action_node.py b/metagpt/actions/action_node.py
index 07638ce423..ad3f0a1d18 100644
--- a/metagpt/actions/action_node.py
+++ b/metagpt/actions/action_node.py
@@ -237,12 +237,19 @@ def create_model_class(cls, class_name: str, mapping: Dict[str, Tuple[Type, Any]
         """基于pydantic v2的模型动态生成，用来检验结果类型正确性"""
 
         def check_fields(cls, values):
-            required_fields = set(mapping.keys())
+            all_fields = set(mapping.keys())
+            required_fields = set()
+            for k, v in mapping.items():
+                type_v, field_info = v
+                if ActionNode.is_optional_type(type_v):
+                    continue
+                required_fields.add(k)
+
             missing_fields = required_fields - set(values.keys())
             if missing_fields:
                 raise ValueError(f"Missing fields: {missing_fields}")
 
-            unrecognized_fields = set(values.keys()) - required_fields
+            unrecognized_fields = set(values.keys()) - all_fields
             if unrecognized_fields:
                 logger.warning(f"Unrecognized fields: {unrecognized_fields}")
             return values
@@ -717,3 +724,12 @@ def from_pydantic(cls, model: Type[BaseModel], key: str = None):
             root_node.add_child(child_node)
 
         return root_node
+
+    @staticmethod
+    def is_optional_type(tp) -> bool:
+        """Return True if `tp` is `typing.Optional[...]`"""
+        if typing.get_origin(tp) is Union:
+            args = typing.get_args(tp)
+            non_none_types = [arg for arg in args if arg is not type(None)]
+            return len(non_none_types) == 1 and len(args) == 2
+        return False
diff --git a/metagpt/actions/project_management_an.py b/metagpt/actions/project_management_an.py
index 308579cc30..f530624337 100644
--- a/metagpt/actions/project_management_an.py
+++ b/metagpt/actions/project_management_an.py
@@ -12,7 +12,7 @@
 REQUIRED_PACKAGES = ActionNode(
     key="Required packages",
     expected_type=Optional[List[str]],
-    instruction="Provide required packages in requirements.txt format.",
+    instruction="Provide required third-party packages in requirements.txt format.",
     example=["flask==1.1.2", "bcrypt==3.2.0"],
 )
 
diff --git a/metagpt/actions/write_code_an_draft.py b/metagpt/actions/write_code_an_draft.py
index ed6c66cf6b..20ed201a36 100644
--- a/metagpt/actions/write_code_an_draft.py
+++ b/metagpt/actions/write_code_an_draft.py
@@ -139,7 +139,7 @@ class Main {\
     end", "Anything UNCLEAR": "目前项目要求明确，没有不清楚的地方。"}
 
 ## Tasks
-{"Required packages": ["无需Python包"], "Required Other language third-party packages": ["vue.js"], "Logic Analysis": [["index.html", "作为游戏的入口文件和主要的HTML结构"], ["styles.css", "包含所有的CSS样式，确保游戏界面美观"], ["main.js", "包含Main类，负责初始化游戏和绑定事件"], ["game.js", "包含Game类，负责游戏逻辑，如开始游戏、移动方块等"], ["storage.js", "包含Storage类，用于获取和设置玩家的最高分"]], "Task list": ["index.html", "styles.css", "storage.js", "game.js", "main.js"], "Full API spec": "", "Shared Knowledge": "\'game.js\' 包含游戏逻辑相关的函数，被 \'main.js\' 调用。", "Anything UNCLEAR": "目前项目要求明确，没有不清楚的地方。"}
+{"Required packages": ["无需第三方包"], "Required Other language third-party packages": ["vue.js"], "Logic Analysis": [["index.html", "作为游戏的入口文件和主要的HTML结构"], ["styles.css", "包含所有的CSS样式，确保游戏界面美观"], ["main.js", "包含Main类，负责初始化游戏和绑定事件"], ["game.js", "包含Game类，负责游戏逻辑，如开始游戏、移动方块等"], ["storage.js", "包含Storage类，用于获取和设置玩家的最高分"]], "Task list": ["index.html", "styles.css", "storage.js", "game.js", "main.js"], "Full API spec": "", "Shared Knowledge": "\'game.js\' 包含游戏逻辑相关的函数，被 \'main.js\' 调用。", "Anything UNCLEAR": "目前项目要求明确，没有不清楚的地方。"}
 
 ## Code Files
 ----- index.html
diff --git a/metagpt/utils/token_counter.py b/metagpt/utils/token_counter.py
index 8e674f5751..a7df27258a 100644
--- a/metagpt/utils/token_counter.py
+++ b/metagpt/utils/token_counter.py
@@ -40,6 +40,7 @@
     "gpt-4-vision-preview": {"prompt": 0.01, "completion": 0.03},  # TODO add extra image price calculator
     "gpt-4-1106-vision-preview": {"prompt": 0.01, "completion": 0.03},
     "gpt-4o": {"prompt": 0.005, "completion": 0.015},
+    "gpt-4o-mini": {"prompt": 0.00015, "completion": 0.0006},
     "gpt-4o-2024-05-13": {"prompt": 0.005, "completion": 0.015},
     "text-embedding-ada-002": {"prompt": 0.0004, "completion": 0.0},
     "glm-3-turbo": {"prompt": 0.0007, "completion": 0.0007},  # 128k version, prompt + completion tokens=0.005￥/k-tokens
@@ -210,6 +211,7 @@
     "gpt-4-0613": 8192,
     "gpt-4-32k": 32768,
     "gpt-4-32k-0613": 32768,
+    "gpt-4o-mini": 128000,
     "gpt-3.5-turbo-0125": 16385,
     "gpt-3.5-turbo": 16385,
     "gpt-3.5-turbo-1106": 16385,
@@ -355,8 +357,9 @@ def count_input_tokens(messages, model="gpt-3.5-turbo-0125"):
         "gpt-4-turbo",
         "gpt-4-vision-preview",
         "gpt-4-1106-vision-preview",
-        "gpt-4o-2024-05-13",
         "gpt-4o",
+        "gpt-4o-2024-05-13",
+        "gpt-4o-mini",
     }:
         tokens_per_message = 3  # # every reply is primed with <|start|>assistant<|message|>
         tokens_per_name = 1
diff --git a/requirements.txt b/requirements.txt
index e74cfef6bb..db0204862e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -73,6 +73,8 @@ dashscope~=1.19.3
 rank-bm25==0.2.2  # for tool recommendation
 jieba==0.42.1  # for tool recommendation
 volcengine-python-sdk[ark]~=1.0.94
+# llama-index-vector-stores-elasticsearch~=0.2.5 # Used by `metagpt/memory/longterm_memory.py`
+# llama-index-vector-stores-chroma~=0.1.10 # Used by `metagpt/memory/longterm_memory.py`
 gymnasium==0.29.1
 boto3~=1.34.69
 spark_ai_python~=0.3.30
diff --git a/tests/metagpt/actions/test_action_node.py b/tests/metagpt/actions/test_action_node.py
index 989e2249cb..58a6dd5179 100644
--- a/tests/metagpt/actions/test_action_node.py
+++ b/tests/metagpt/actions/test_action_node.py
@@ -6,7 +6,7 @@
 @File    : test_action_node.py
 """
 from pathlib import Path
-from typing import List, Tuple
+from typing import List, Optional, Tuple
 
 import pytest
 from pydantic import BaseModel, Field, ValidationError
@@ -302,6 +302,19 @@ def test_action_node_from_pydantic_and_print_everything():
     assert "tasks" in code, "tasks should be in code"
 
 
+def test_optional():
+    mapping = {
+        "Logic Analysis": (Optional[List[Tuple[str, str]]], Field(default=None)),
+        "Task list": (Optional[List[str]], None),
+        "Plan": (Optional[str], ""),
+        "Anything UNCLEAR": (Optional[str], None),
+    }
+    m = {"Anything UNCLEAR": "a"}
+    t = ActionNode.create_model_class("test_class_1", mapping)
+
+    t1 = t(**m)
+    assert t1
+
+
 if __name__ == "__main__":
-    test_create_model_class()
-    test_create_model_class_with_mapping()
+    pytest.main([__file__, "-s"])
diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py
index 7ce5765cff..797daf5dc4 100644
--- a/tests/metagpt/test_config.py
+++ b/tests/metagpt/test_config.py
@@ -14,8 +14,8 @@
 def test_config_1():
     cfg = Config.default()
     llm = cfg.get_openai_llm()
-    assert llm is not None
-    assert llm.api_type == LLMType.OPENAI
+    if cfg.llm.api_type == LLMType.OPENAI:
+        assert llm is not None
 
 
 def test_config_from_dict():
diff --git a/tests/metagpt/test_context.py b/tests/metagpt/test_context.py
index f8218c44dd..a6daf95cd2 100644
--- a/tests/metagpt/test_context.py
+++ b/tests/metagpt/test_context.py
@@ -53,8 +53,8 @@ def test_context_1():
 def test_context_2():
     ctx = Context()
     llm = ctx.config.get_openai_llm()
-    assert llm is not None
-    assert llm.api_type == LLMType.OPENAI
+    if ctx.config.llm.api_type == LLMType.OPENAI:
+        assert llm is not None
 
     kwargs = ctx.kwargs
     assert kwargs is not None