mirror of
https://github.com/FoundationAgents/MetaGPT.git
synced 2026-04-26 01:06:27 +02:00
1. SummarizeCode动作:用于基于代码进行总结,思考bug、逻辑、todo
2. CodeReview动作优化:目前强制要求回答问题,有更高的成功率了
1. 增加了LGTM/LBTM的回答,在LGTM时会及时停止,不重写代码
2. 目前增加了设置中的参数code_review_k_times,与reflexion类似,设置为2
3. 仍然有概率发生指令不遵循,尤其是会有比较高的概率发生同时review多个代码文件,还没想好怎么解决 #FIXME
3. 增加了env到Action结构中,现在可以直接调用环境接口了
4. WriteDesign:去除了对project_name的纠正代码,现在引导下可以一次生成对
1. 修改了提示词中的##格式,改为了JSON格式
2. 数据结构
1. Document的标准化:Env->Repo->Document,其中Document/Asset/Code都是Document
1. 原用于检索的Document改为IndexableDocument
2. Repo结构引入:用于Document装载与元数据装载
3. RepoParser引入:写了一个简单的AST parser(后续可能要换tree-sitter),给出了整库symbol
4. Env中增加了set/get/set_doc/get_doc接口,用于set/get单个变量或者一个Document。这个逻辑后续或许会进一步简化
3. 配置优化
1. 默认更换为gpt-4-1106-preview,以获得最好的效果与成本
2. 提供~/.metagpt作为配置最高优先级目录,从中读取config.yaml
3. workspace可以灵活指定了,在config中配置
4. project_name可以由命令行指定,并且改为由ProductManager生成
4. metagpt作为默认命令行,而非python startup.py
metagpt --help
metagpt --project-name game_2048 "make a 2048 game"
metagpt "make a 2048 game"
metagpt --project-name game_2048 --inc "将2048改为4096"
metagpt --project-name game_2048 --auto-inc "make a 2048 game"
1. 使用新的METAGPT_ROOT生成方式,而非寻找git,以便cli安装
2. 命令行由fire换为了typer,它会带来相对更好的体验
3. project_name可以灵活指定了,在metagpt命令行输入中配置
5. 其他
1. 现在支持多国语言了,中文已测试
2. BossRequirement -> UserRequirement
3. 大量错误文本的修正,增加了可读性
4. 中量提示词优化,稍微提升了一些准确率
5. 暂时屏蔽了LongtermMemory相关逻辑,这个逻辑底层调用了langchain的FAISS,会带来~5秒加载耗时
6. 修复了安装包中的部分描述错误
7. 去除了config中在openai_proxy设定时对base的重复修改,这个修改应该在openai初始化时发生
8. 修复了JSON在中文存储时的特定问题,ensure_ascii=False
111 lines
3.4 KiB
Python
111 lines
3.4 KiB
Python
#!/usr/bin/env python
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
@Time : 2023/5/11 22:12
|
|
@Author : alexanderwu
|
|
@File : environment.py
|
|
"""
|
|
import asyncio
|
|
from typing import Iterable
|
|
from pathlib import Path
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
# from metagpt.document import Document
|
|
from metagpt.logs import logger
|
|
from metagpt.document import Repo
|
|
from metagpt.memory import Memory
|
|
from metagpt.roles import Role
|
|
from metagpt.schema import Message
|
|
|
|
|
|
class Environment(BaseModel):
|
|
"""
|
|
Environment, hosting a batch of roles, roles can publish messages to the environment, and can be observed by other roles
|
|
"""
|
|
|
|
roles: dict[str, Role] = Field(default_factory=dict)
|
|
memory: Memory = Field(default_factory=Memory)
|
|
history: str = Field(default='')
|
|
repo: Repo = Field(default_factory=Repo)
|
|
kv: dict = Field(default_factory=dict)
|
|
|
|
class Config:
|
|
arbitrary_types_allowed = True
|
|
|
|
def add_role(self, role: Role):
|
|
"""增加一个在当前环境的角色
|
|
Add a role in the current environment
|
|
"""
|
|
role.set_env(self)
|
|
self.roles[role.profile] = role
|
|
|
|
def add_roles(self, roles: Iterable[Role]):
|
|
"""增加一批在当前环境的角色
|
|
Add a batch of characters in the current environment
|
|
"""
|
|
for role in roles:
|
|
self.add_role(role)
|
|
|
|
def publish_message(self, message: Message):
|
|
"""向当前环境发布信息
|
|
Post information to the current environment
|
|
"""
|
|
# self.message_queue.put(message)
|
|
self.memory.add(message)
|
|
self.history += f"\n{message}"
|
|
|
|
def set_doc(self, content: str, filename: str):
|
|
"""向当前环境发布文档(包括代码)"""
|
|
return self.repo.set(content, filename)
|
|
|
|
def get_doc(self, filename: str):
|
|
return self.repo.get(filename)
|
|
|
|
def set(self, k: str, v: str):
|
|
self.kv[k] = v
|
|
|
|
def get(self, k: str):
|
|
return self.kv.get(k, None)
|
|
|
|
def load_existing_repo(self, path: Path, inc: bool):
|
|
self.repo = Repo.from_path(path)
|
|
logger.info(self.repo.eda())
|
|
|
|
# Incremental mode: publish all docs to messages. Then roles can read the docs.
|
|
if inc:
|
|
docs = self.repo.get_text_documents()
|
|
for doc in docs:
|
|
msg = Message(content=doc.content)
|
|
self.publish_message(msg)
|
|
logger.info(f"Message from existing doc {doc.path}: {msg}")
|
|
logger.info(f"Load {len(docs)} docs from existing repo.")
|
|
raise NotImplementedError
|
|
|
|
async def run(self, k=1):
|
|
"""处理一次所有信息的运行
|
|
Process all Role runs at once
|
|
"""
|
|
# while not self.message_queue.empty():
|
|
# message = self.message_queue.get()
|
|
# rsp = await self.manager.handle(message, self)
|
|
# self.message_queue.put(rsp)
|
|
for _ in range(k):
|
|
futures = []
|
|
for role in self.roles.values():
|
|
future = role.run()
|
|
futures.append(future)
|
|
|
|
await asyncio.gather(*futures)
|
|
|
|
def get_roles(self) -> dict[str, Role]:
|
|
"""获得环境内的所有角色
|
|
Process all Role runs at once
|
|
"""
|
|
return self.roles
|
|
|
|
def get_role(self, name: str) -> Role:
|
|
"""获得环境内的指定角色
|
|
get all the environment roles
|
|
"""
|
|
return self.roles.get(name, None)
|