Merge branch 'dev' of https://github.com/geekan/MetaGPT into geekan/dev

metagpt/actions/action.py

@@ -25,7 +25,7 @@ from metagpt.utils.project_repo import ProjectRepo
 
 
 class Action(SerializationMixin, ContextMixin, BaseModel):
-    model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"])
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     name: str = ""
     i_context: Union[dict, CodingContext, CodeSummarizeContext, TestingContext, RunCodeContext, str, None] = ""

metagpt/config2.py

@@ -18,7 +18,7 @@ from metagpt.configs.redis_config import RedisConfig
 from metagpt.configs.s3_config import S3Config
 from metagpt.configs.search_config import SearchConfig
 from metagpt.configs.workspace_config import WorkspaceConfig
-from metagpt.const import METAGPT_ROOT
+from metagpt.const import CONFIG_ROOT, METAGPT_ROOT
 from metagpt.utils.yaml_model import YamlModel
 
 
@@ -81,6 +81,11 @@ class Config(CLIParams, YamlModel):
     AZURE_TTS_REGION: str = ""
     mermaid_engine: str = "nodejs"
 
+    @classmethod
+    def from_home(cls, path):
+        """Load config from ~/.metagpt/config.yaml"""
+        return Config.model_validate_yaml(CONFIG_ROOT / path)
+
     @classmethod
     def default(cls):
         """Load default config

metagpt/const.py

@@ -47,7 +47,7 @@ def get_metagpt_root():
 
 
 # METAGPT PROJECT ROOT AND VARS
-
+CONFIG_ROOT = Path.home() / ".metagpt"
 METAGPT_ROOT = get_metagpt_root()  # Dependent on METAGPT_PROJECT_ROOT
 DEFAULT_WORKSPACE_ROOT = METAGPT_ROOT / "workspace"
 

metagpt/context_mixin.py

@@ -19,6 +19,11 @@ class ContextMixin(BaseModel):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
+    # Pydantic has bug on _private_attr when using inheritance, so we use private_* instead
+    # - https://github.com/pydantic/pydantic/issues/7142
+    # - https://github.com/pydantic/pydantic/issues/7083
+    # - https://github.com/pydantic/pydantic/issues/7091
+
     # Env/Role/Action will use this context as private context, or use self.context as public context
     private_context: Optional[Context] = Field(default=None, exclude=True)
     # Env/Role/Action will use this config as private config, or use self.context.config as public config
@@ -52,6 +57,8 @@ class ContextMixin(BaseModel):
     def set_config(self, config: Config, override=False):
         """Set config"""
         self.set("private_config", config, override)
+        if config is not None:
+            _ = self.llm  # init llm
 
     def set_llm(self, llm: BaseLLM, override=False):
         """Set llm"""

metagpt/llm.py

@@ -5,13 +5,15 @@
 @Author  : alexanderwu
 @File    : llm.py
 """
+from typing import Optional
 
-
+from metagpt.configs.llm_config import LLMConfig
 from metagpt.context import CONTEXT
 from metagpt.provider.base_llm import BaseLLM
 
 
-def LLM() -> BaseLLM:
+def LLM(llm_config: Optional[LLMConfig] = None) -> BaseLLM:
     """get the default llm provider if name is None"""
-    # context.use_llm(name=name, provider=provider)
+    if llm_config is not None:
+        CONTEXT.llm_with_cost_manager_from_llm_config(llm_config)
     return CONTEXT.llm()

metagpt/provider/__init__.py

@@ -15,6 +15,7 @@ from metagpt.provider.zhipuai_api import ZhiPuAILLM
 from metagpt.provider.azure_openai_api import AzureOpenAILLM
 from metagpt.provider.metagpt_api import MetaGPTLLM
 from metagpt.provider.human_provider import HumanProvider
+from metagpt.provider.spark_api import SparkLLM
 
 __all__ = [
     "FireworksLLM",
@@ -26,4 +27,5 @@ __all__ = [
     "MetaGPTLLM",
     "OllamaLLM",
     "HumanProvider",
+    "SparkLLM",
 ]

metagpt/provider/base_llm.py

@@ -59,7 +59,9 @@ class BaseLLM(ABC):
         if system_msgs:
             message = self._system_msgs(system_msgs)
         else:
-            message = [self._default_system_msg()] if self.use_system_prompt else []
+            message = [self._default_system_msg()]
+        if not self.use_system_prompt:
+            message = []
         if format_msgs:
             message.extend(format_msgs)
         message.append(self._user_msg(msg))

metagpt/provider/openai_api.py

@@ -220,10 +220,12 @@ class OpenAILLM(BaseLLM):
 
     @handle_exception
     def _update_costs(self, usage: CompletionUsage):
-        if self.config.calc_usage and usage:
+        if self.config.calc_usage and usage and self.cost_manager:
             self.cost_manager.update_cost(usage.prompt_tokens, usage.completion_tokens, self.model)
 
     def get_costs(self) -> Costs:
+        if not self.cost_manager:
+            return Costs()
         return self.cost_manager.get_costs()
 
     def _get_max_tokens(self, messages: list[dict]):

metagpt/provider/spark_api.py

@@ -26,14 +26,14 @@ from metagpt.provider.llm_provider_registry import register_provider
 class SparkLLM(BaseLLM):
     def __init__(self, config: LLMConfig):
         self.config = config
-        logger.warning("当前方法无法支持异步运行。当你使用acompletion时，并不能并行访问。")
+        logger.warning("SparkLLM：当前方法无法支持异步运行。当你使用acompletion时，并不能并行访问。")
 
     def get_choice_text(self, rsp: dict) -> str:
         return rsp["payload"]["choices"]["text"][-1]["content"]
 
     async def acompletion_text(self, messages: list[dict], stream=False, timeout: int = 3) -> str:
         # 不支持
-        logger.warning("当前方法无法支持异步运行。当你使用acompletion时，并不能并行访问。")
+        # logger.warning("当前方法无法支持异步运行。当你使用acompletion时，并不能并行访问。")
         w = GetMessageFromWeb(messages, self.config)
         return w.run()
 

metagpt/roles/engineer.py

@@ -104,7 +104,7 @@ class Engineer(Role):
             # Code review
             if review:
                 action = WriteCodeReview(i_context=coding_context, context=self.context, llm=self.llm)
-                self._init_action_system_message(action)
+                self._init_action(action)
                 coding_context = await action.run()
             await self.project_repo.srcs.save(
                 filename=coding_context.filename,

metagpt/roles/role.py

@@ -132,6 +132,13 @@ class Role(SerializationMixin, ContextMixin, BaseModel):
 
     role_id: str = ""
     states: list[str] = []
+
+    # scenarios to set action system_prompt:
+    #   1. `__init__` while using Role(actions=[...])
+    #   2. add action to role while using `role.set_action(action)`
+    #   3. set_todo while using `role.set_todo(action)`
+    #   4. when role.system_prompt is being updated (e.g. by `role.system_prompt = "..."`)
+    # Additional, if llm is not set, we will use role's llm
     actions: list[SerializeAsAny[Action]] = Field(default=[], validate_default=True)
     rc: RoleContext = Field(default_factory=RoleContext)
     addresses: set[str] = set()
@@ -146,6 +153,10 @@ class Role(SerializationMixin, ContextMixin, BaseModel):
         self.pydantic_rebuild_model()
         super().__init__(**data)
 
+        if self.is_human:
+            self.llm = HumanProvider(None)
+
+        self._check_actions()
         self.llm.system_prompt = self._get_prefix()
         self._watch(data.get("watch") or [UserRequirement])
 
@@ -225,7 +236,16 @@ class Role(SerializationMixin, ContextMixin, BaseModel):
     def _setting(self):
         return f"{self.name}({self.profile})"
 
-    def _init_action_system_message(self, action: Action):
+    def _check_actions(self):
+        """Check actions and set llm and prefix for each action."""
+        self.set_actions(self.actions)
+        return self
+
+    def _init_action(self, action: Action):
+        if not action.private_config:
+            action.set_llm(self.llm, override=True)
+        else:
+            action.set_llm(self.llm, override=False)
         action.set_prefix(self._get_prefix())
 
     def set_action(self, action: Action):
@@ -241,7 +261,7 @@ class Role(SerializationMixin, ContextMixin, BaseModel):
         self._reset()
         for action in actions:
             if not isinstance(action, Action):
-                i = action(name="", llm=self.llm)
+                i = action()
             else:
                 if self.is_human and not isinstance(action.llm, HumanProvider):
                     logger.warning(
@@ -250,7 +270,7 @@ class Role(SerializationMixin, ContextMixin, BaseModel):
                         f"try passing in Action classes instead of initialized instances"
                     )
                 i = action
-            self._init_action_system_message(i)
+            self._init_action(i)
             self.actions.append(i)
             self.states.append(f"{len(self.actions)}. {action}")
 
@@ -308,6 +328,7 @@ class Role(SerializationMixin, ContextMixin, BaseModel):
         if env:
             env.set_addresses(self, self.addresses)
             self.llm.system_prompt = self._get_prefix()
+            self.set_actions(self.actions)  # reset actions to update llm and prefix
 
     def _get_prefix(self):
         """Get the role prefix"""
@@ -320,7 +341,8 @@ class Role(SerializationMixin, ContextMixin, BaseModel):
             prefix += CONSTRAINT_TEMPLATE.format(**{"constraints": self.constraints})
 
         if self.rc.env and self.rc.env.desc:
-            other_role_names = ", ".join(self.rc.env.role_names())
+            all_roles = self.rc.env.role_names()
+            other_role_names = ", ".join([r for r in all_roles if r != self.name])
             env_desc = f"You are in {self.rc.env.desc} with roles({other_role_names})."
             prefix += env_desc
         return prefix
@@ -480,7 +502,6 @@ class Role(SerializationMixin, ContextMixin, BaseModel):
             if not msg.cause_by:
                 msg.cause_by = UserRequirement
             self.put_message(msg)
-
         if not await self._observe():
             # If there is no new information, suspend and wait
             logger.debug(f"{self._setting}: no news. waiting.")

metagpt/startup.py

@@ -7,7 +7,7 @@ from pathlib import Path
 import typer
 
 from metagpt.config2 import config
-from metagpt.const import METAGPT_ROOT
+from metagpt.const import CONFIG_ROOT, METAGPT_ROOT
 
 app = typer.Typer(add_completion=False, pretty_exceptions_show_locals=False)
 
@@ -118,7 +118,7 @@ def startup(
 
 def copy_config_to(config_path=METAGPT_ROOT / "config" / "config2.yaml"):
     """Initialize the configuration file for MetaGPT."""
-    target_path = Path.home() / ".metagpt" / "config2.yaml"
+    target_path = CONFIG_ROOT / "config2.yaml"
 
     # 创建目标目录（如果不存在）
     target_path.parent.mkdir(parents=True, exist_ok=True)