feat: merge geekan:main

README.md

@@ -26,7 +26,9 @@ # MetaGPT: The Multi-Agent Framework
 </p>
 
 ## News
-🚀 Feb. 08, 2024: [v0.7.0](https://github.com/geekan/MetaGPT/releases/tag/v0.7.0) released, supporting assigning different LLMs to different Roles. We also introduced [Interpreter](https://github.com/geekan/MetaGPT/blob/main/examples/mi/README.md), a powerful agent capable of solving a wide range of real-world problems.
+🚀 March. 01, 2024: Our Data Interpreter paper is on arxiv. Find all design and benchmark details [here](https://arxiv.org/abs/2402.18679)!
+
+🚀 Feb. 08, 2024: [v0.7.0](https://github.com/geekan/MetaGPT/releases/tag/v0.7.0) released, supporting assigning different LLMs to different Roles. We also introduced [Data Interpreter](https://github.com/geekan/MetaGPT/blob/main/examples/di/README.md), a powerful agent capable of solving a wide range of real-world problems.
 
 🚀 Jan. 16, 2024: Our paper [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
 ](https://arxiv.org/abs/2308.00352) accepted for oral presentation **(top 1.2%)** at ICLR 2024, **ranking #1** in the LLM-based Agent category.

examples/di/README.md

@@ -0,0 +1,18 @@
+# Data Interpreter (DI)
+
+## What is Data Interpreter
+Data Interpreter is an agent who solves problems through codes. It understands user requirements, makes plans, writes codes for execution, and uses tools if necessary. These capabilities enable it to tackle a wide range of scenarios, please check out the examples below.
+
+## Example List
+- Data visualization
+- Machine learning modeling
+- Image background removal
+- Solve math problems
+- Receipt OCR
+- Tool usage: web page imitation
+- Tool usage: web crawling
+- Tool usage: text2image
+- Tool usage: email summarization and response
+- More on the way!
+
+Please see [here](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/interpreter/intro.html) for detailed explanation.

examples/di/crawl_webpage.py

@@ -5,15 +5,15 @@
 @File    :   crawl_webpage.py
 """
 
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main():
     prompt = """Get data from `paperlist` table in https://papercopilot.com/statistics/iclr-statistics/iclr-2024-statistics/,
     and save it to a csv file. paper title must include `multiagent` or `large language model`. *notice: print key variables*"""
-    mi = Interpreter(use_tools=True)
+    di = DataInterpreter(use_tools=True)
 
-    await mi.run(prompt)
+    await di.run(prompt)
 
 
 if __name__ == "__main__":

examples/di/data_visualization.py

@@ -1,11 +1,11 @@
 import asyncio
 
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main(requirement: str = ""):
-    mi = Interpreter(use_tools=False)
-    await mi.run(requirement)
+    di = DataInterpreter(use_tools=False)
+    await di.run(requirement)
 
 
 if __name__ == "__main__":

examples/di/email_summary.py

@@ -6,7 +6,7 @@
 """
 import os
 
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main():
@@ -22,9 +22,9 @@ async def main():
             Firstly, Please help me fetch the latest 5 senders and full letter contents.
             Then, summarize each of the 5 emails into one sentence (you can do this by yourself, no need to import other models to do this) and output them in a markdown format."""
 
-    mi = Interpreter(use_tools=True)
+    di = DataInterpreter(use_tools=True)
 
-    await mi.run(prompt)
+    await di.run(prompt)
 
 
 if __name__ == "__main__":

examples/di/imitate_webpage.py

@@ -5,7 +5,7 @@
 @Author  : mannaandpoem
 @File    : imitate_webpage.py
 """
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main():
@@ -15,9 +15,9 @@ Firstly, utilize Selenium and WebDriver for rendering.
 Secondly, convert image to a webpage including HTML, CSS and JS in one go. 
 Finally, save webpage in a text file. 
 Note: All required dependencies and environments have been fully installed and configured."""
-    mi = Interpreter(use_tools=True)
+    di = DataInterpreter(use_tools=True)
 
-    await mi.run(prompt)
+    await di.run(prompt)
 
 
 if __name__ == "__main__":

examples/di/machine_learning.py

@@ -1,12 +1,12 @@
 import fire
 
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main(auto_run: bool = True):
     requirement = "Run data analysis on sklearn Wine recognition dataset, include a plot, and train a model to predict wine class (20% as validation), and show validation accuracy."
-    mi = Interpreter(auto_run=auto_run)
-    await mi.run(requirement)
+    di = DataInterpreter(auto_run=auto_run)
+    await di.run(requirement)
 
 
 if __name__ == "__main__":

examples/di/ml_engineer_with_tools.py

@@ -1,6 +1,6 @@
 import asyncio
 
-from metagpt.roles.mi.ml_engineer import MLEngineer
+from metagpt.roles.di.ml_engineer import MLEngineer
 
 
 async def main(requirement: str):

examples/di/ocr_receipt.py

@@ -1,4 +1,4 @@
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main():
@@ -10,9 +10,9 @@ async def main():
     coordinates and confidence levels, then recognize the total amount from ocr text content, and finally save as table. 
     Image path: {image_path}.
     NOTE: The environments for Paddle and PaddleOCR are all ready and has been fully installed."""
-    mi = Interpreter()
+    di = DataInterpreter()
 
-    await mi.run(requirement)
+    await di.run(requirement)
 
 
 if __name__ == "__main__":

examples/di/rm_image_background.py

@@ -1,11 +1,11 @@
 import asyncio
 
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main(requirement: str = ""):
-    mi = Interpreter(use_tools=False)
-    await mi.run(requirement)
+    di = DataInterpreter(use_tools=False)
+    await di.run(requirement)
 
 
 if __name__ == "__main__":

examples/di/sd_tool_usage.py

@@ -4,12 +4,12 @@
 # @Desc    :
 import asyncio
 
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main(requirement: str = ""):
-    mi = Interpreter(use_tools=True, goal=requirement)
-    await mi.run(requirement)
+    di = DataInterpreter(use_tools=True, goal=requirement)
+    await di.run(requirement)
 
 
 if __name__ == "__main__":

examples/di/solve_math_problems.py

@@ -1,11 +1,11 @@
 import asyncio
 
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 async def main(requirement: str = ""):
-    mi = Interpreter(use_tools=False)
-    await mi.run(requirement)
+    di = DataInterpreter(use_tools=False)
+    await di.run(requirement)
 
 
 if __name__ == "__main__":

examples/mi/README.md

@@ -1,18 +0,0 @@
-# MetaGPT Interpreter (MI)
-
-## What is Interpreter
-Interpreter is an agent who solves problems through codes. It understands user requirements, makes plans, writes codes for execution, and uses tools if necessary. These capabilities enable it to tackle a wide range of scenarios, please check out the examples below.
-
-## Example List
-- Data visualization
-- Machine learning modeling
-- Image background removal
-- Solve math problems
-- Receipt OCR
-- Tool usage: web page imitation
-- Tool usage: web crawling
-- Tool usage: text2image
-- Tool usage: email summarization and response
-- More on the way!
-
-Please see [here](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/interpreter/mi_intro.html) for detailed explanation.

metagpt/actions/__init__.py

@@ -22,9 +22,9 @@ from metagpt.actions.write_code_review import WriteCodeReview
 from metagpt.actions.write_prd import WritePRD
 from metagpt.actions.write_prd_review import WritePRDReview
 from metagpt.actions.write_test import WriteTest
-from metagpt.actions.mi.execute_nb_code import ExecuteNbCode
-from metagpt.actions.mi.write_analysis_code import WriteCodeWithoutTools, WriteCodeWithTools
-from metagpt.actions.mi.write_plan import WritePlan
+from metagpt.actions.di.execute_nb_code import ExecuteNbCode
+from metagpt.actions.di.write_analysis_code import WriteCodeWithoutTools, WriteCodeWithTools
+from metagpt.actions.di.write_plan import WritePlan
 
 
 class ActionType(Enum):

metagpt/actions/design_api_an.py

@@ -8,7 +8,6 @@
 from typing import List
 
 from metagpt.actions.action_node import ActionNode
-from metagpt.logs import logger
 from metagpt.utils.mermaid import MMC1, MMC2
 
 IMPLEMENTATION_APPROACH = ActionNode(
@@ -109,14 +108,3 @@ REFINED_NODES = [
 
 DESIGN_API_NODE = ActionNode.from_children("DesignAPI", NODES)
 REFINED_DESIGN_NODE = ActionNode.from_children("RefinedDesignAPI", REFINED_NODES)
-
-
-def main():
-    prompt = DESIGN_API_NODE.compile(context="")
-    logger.info(prompt)
-    prompt = REFINED_DESIGN_NODE.compile(context="")
-    logger.info(prompt)
-
-
-if __name__ == "__main__":
-    main()

metagpt/actions/di/debug_code.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from metagpt.actions.mi.write_analysis_code import BaseWriteAnalysisCode
+from metagpt.actions.di.write_analysis_code import BaseWriteAnalysisCode
 from metagpt.logs import logger
 from metagpt.schema import Message
 from metagpt.utils.common import create_func_call_config

metagpt/actions/di/ml_action.py

@@ -3,14 +3,14 @@ from __future__ import annotations
 from typing import Tuple
 
 from metagpt.actions import Action
-from metagpt.actions.mi.write_analysis_code import WriteCodeWithTools
-from metagpt.prompts.mi.ml_action import (
+from metagpt.actions.di.write_analysis_code import WriteCodeWithTools
+from metagpt.prompts.di.ml_action import (
     ML_GENERATE_CODE_PROMPT,
     ML_TOOL_USAGE_PROMPT,
     PRINT_DATA_COLUMNS,
     UPDATE_DATA_COLUMNS,
 )
-from metagpt.prompts.mi.write_analysis_code import CODE_GENERATOR_WITH_TOOLS
+from metagpt.prompts.di.write_analysis_code import CODE_GENERATOR_WITH_TOOLS
 from metagpt.schema import Message, Plan
 from metagpt.utils.common import create_func_call_config, remove_comments
 

metagpt/actions/di/write_analysis_code.py

@@ -10,7 +10,7 @@ from typing import Tuple
 
 from metagpt.actions import Action
 from metagpt.logs import logger
-from metagpt.prompts.mi.write_analysis_code import (
+from metagpt.prompts.di.write_analysis_code import (
     CODE_GENERATOR_WITH_TOOLS,
     SELECT_FUNCTION_TOOLS,
     TOOL_RECOMMENDATION_PROMPT,

metagpt/actions/di/write_plan.py

@@ -12,7 +12,7 @@ from typing import Tuple
 
 from metagpt.actions import Action
 from metagpt.logs import logger
-from metagpt.prompts.mi.write_analysis_code import (
+from metagpt.prompts.di.write_analysis_code import (
     ASSIGN_TASK_TYPE_CONFIG,
     ASSIGN_TASK_TYPE_PROMPT,
 )

metagpt/actions/project_management_an.py

@@ -8,7 +8,6 @@
 from typing import List
 
 from metagpt.actions.action_node import ActionNode
-from metagpt.logs import logger
 
 REQUIRED_PYTHON_PACKAGES = ActionNode(
     key="Required Python packages",
@@ -119,14 +118,3 @@ REFINED_NODES = [
 
 PM_NODE = ActionNode.from_children("PM_NODE", NODES)
 REFINED_PM_NODE = ActionNode.from_children("REFINED_PM_NODE", REFINED_NODES)
-
-
-def main():
-    prompt = PM_NODE.compile(context="")
-    logger.info(prompt)
-    prompt = REFINED_PM_NODE.compile(context="")
-    logger.info(prompt)
-
-
-if __name__ == "__main__":
-    main()

metagpt/actions/write_code_plan_and_change_an.py

@@ -6,30 +6,44 @@
 @File    : write_code_plan_and_change_an.py
 """
 import os
+from typing import List
 
 from pydantic import Field
 
 from metagpt.actions.action import Action
 from metagpt.actions.action_node import ActionNode
+from metagpt.logs import logger
 from metagpt.schema import CodePlanAndChangeContext
 
-CODE_PLAN_AND_CHANGE = ActionNode(
-    key="Code Plan And Change",
-    expected_type=str,
-    instruction="Developing comprehensive and step-by-step incremental development plan, and write Incremental "
-    "Change by making a code draft that how to implement incremental development including detailed steps based on the "
-    "context. Note: Track incremental changes using mark of '+' or '-' for add/modify/delete code, and conforms to the "
-    "output format of git diff",
-    example="""
-1. Plan for calculator.py: Enhance the functionality of `calculator.py` by extending it to incorporate methods for subtraction, multiplication, and division. Additionally, implement robust error handling for the division operation to mitigate potential issues related to division by zero. 
-```python
+DEVELOPMENT_PLAN = ActionNode(
+    key="Development Plan",
+    expected_type=List[str],
+    instruction="Develop a comprehensive and step-by-step incremental development plan, providing the detail "
+    "changes to be implemented at each step based on the order of 'Task List'",
+    example=[
+        "Enhance the functionality of `calculator.py` by extending it to incorporate methods for subtraction, ...",
+        "Update the existing codebase in main.py to incorporate new API endpoints for subtraction, ...",
+    ],
+)
+
+INCREMENTAL_CHANGE = ActionNode(
+    key="Incremental Change",
+    expected_type=List[str],
+    instruction="Write Incremental Change by making a code draft that how to implement incremental development "
+    "including detailed steps based on the context. Note: Track incremental changes using the marks `+` and `-` to "
+    "indicate additions and deletions, and ensure compliance with the output format of `git diff`",
+    example=[
+        '''```diff
+--- Old/calculator.py
++++ New/calculator.py
+
 class Calculator:
          self.result = number1 + number2
          return self.result
 
 -    def sub(self, number1, number2) -> float:
 +    def subtract(self, number1: float, number2: float) -> float:
-+        '''
++        """
 +        Subtracts the second number from the first and returns the result.
 +
 +        Args:
@@ -38,13 +52,13 @@ class Calculator:
 +
 +        Returns:
 +            float: The difference of number1 and number2.
-+        '''
++        """
 +        self.result = number1 - number2
 +        return self.result
 +
     def multiply(self, number1: float, number2: float) -> float:
 -        pass
-+        '''
++        """
 +        Multiplies two numbers and returns the result.
 +
 +        Args:
@@ -53,15 +67,15 @@ class Calculator:
 +
 +        Returns:
 +            float: The product of number1 and number2.
-+        '''
++        """
 +        self.result = number1 * number2
 +        return self.result
 +
     def divide(self, number1: float, number2: float) -> float:
 -        pass
-+        '''
++        """
 +            ValueError: If the second number is zero.
-+        '''
++        """
 +        if number2 == 0:
 +            raise ValueError('Cannot divide by zero')
 +        self.result = number1 / number2
@@ -75,10 +89,11 @@ class Calculator:
 +            print("Result is already zero, no need to clear.")
 +
          self.result = 0.0
-```
+```''',
+        """```diff
+--- Old/main.py
++++ New/main.py
 
-2. Plan for main.py: Integrate new API endpoints for subtraction, multiplication, and division into the existing codebase of `main.py`. Then, ensure seamless integration with the overall application architecture and maintain consistency with coding standards.
-```python
 def add_numbers():
      result = calculator.add_numbers(num1, num2)
      return jsonify({'result': result}), 200
@@ -106,6 +121,7 @@ def add_numbers():
  if __name__ == '__main__':
      app.run()
 ```""",
+    ],
 )
 
 CODE_PLAN_AND_CHANGE_CONTEXT = """
@@ -172,14 +188,16 @@ Role: You are a professional engineer; The main goal is to complete incremental
 2. COMPLETE CODE: Your code will be part of the entire project, so please implement complete, reliable, reusable code snippets.
 3. Set default value: If there is any setting, ALWAYS SET A DEFAULT VALUE, ALWAYS USE STRONG TYPE AND EXPLICIT VARIABLE. AVOID circular import.
 4. Follow design: YOU MUST FOLLOW "Data structures and interfaces". DONT CHANGE ANY DESIGN. Do not use public member functions that do not exist in your design.
-5. Follow Code Plan And Change: If there is any Incremental Change that is marked by the git diff format using '+' and '-' for add/modify/delete code, or Legacy Code files contain "{filename} to be rewritten", you must merge it into the code file according to the plan. 
+5. Follow Code Plan And Change: If there is any "Incremental Change" that is marked by the git diff format with '+' and '-' symbols, or Legacy Code files contain "{filename} to be rewritten", you must merge it into the code file according to the "Development Plan". 
 6. CAREFULLY CHECK THAT YOU DONT MISS ANY NECESSARY CLASS/FUNCTION IN THIS FILE.
 7. Before using a external variable/module, make sure you import it first.
 8. Write out EVERY CODE DETAIL, DON'T LEAVE TODO.
 9. Attention: Retain details that are not related to incremental development but are important for maintaining the consistency and clarity of the old code.
 """
 
-WRITE_CODE_PLAN_AND_CHANGE_NODE = ActionNode.from_children("WriteCodePlanAndChange", [CODE_PLAN_AND_CHANGE])
+CODE_PLAN_AND_CHANGE = [DEVELOPMENT_PLAN, INCREMENTAL_CHANGE]
+
+WRITE_CODE_PLAN_AND_CHANGE_NODE = ActionNode.from_children("WriteCodePlanAndChange", CODE_PLAN_AND_CHANGE)
 
 
 class WriteCodePlanAndChange(Action):
@@ -192,14 +210,14 @@ class WriteCodePlanAndChange(Action):
         prd_doc = await self.repo.docs.prd.get(filename=self.i_context.prd_filename)
         design_doc = await self.repo.docs.system_design.get(filename=self.i_context.design_filename)
         task_doc = await self.repo.docs.task.get(filename=self.i_context.task_filename)
-        code_text = await self.get_old_codes()
         context = CODE_PLAN_AND_CHANGE_CONTEXT.format(
             requirement=self.i_context.requirement,
             prd=prd_doc.content,
             design=design_doc.content,
             task=task_doc.content,
-            code=code_text,
+            code=await self.get_old_codes(),
         )
+        logger.info("Writing code plan and change..")
         return await WRITE_CODE_PLAN_AND_CHANGE_NODE.fill(context=context, llm=self.llm, schema="json")
 
     async def get_old_codes(self) -> str:

metagpt/actions/write_prd_an.py

@@ -56,7 +56,7 @@ REFINED_PRODUCT_GOALS = ActionNode(
     key="Refined Product Goals",
     expected_type=List[str],
     instruction="Update and expand the original product goals to reflect the evolving needs due to incremental "
-    "development.Ensure that the refined goals align with the current project direction and contribute to its success.",
+    "development. Ensure that the refined goals align with the current project direction and contribute to its success.",
     example=[
         "Enhance user engagement through new features",
         "Optimize performance for scalability",

metagpt/configs/llm_config.py

@@ -16,6 +16,7 @@ from metagpt.utils.yaml_model import YamlModel
 class LLMType(Enum):
     OPENAI = "openai"
     ANTHROPIC = "anthropic"
+    CLAUDE = "claude"  # alias name of anthropic
     SPARK = "spark"
     ZHIPUAI = "zhipuai"
     FIREWORKS = "fireworks"

metagpt/document.py

@@ -11,12 +11,12 @@ from pathlib import Path
 from typing import Optional, Union
 
 import pandas as pd
-from langchain.document_loaders import (
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_community.document_loaders import (
     TextLoader,
     UnstructuredPDFLoader,
     UnstructuredWordDocumentLoader,
 )
-from langchain.text_splitter import CharacterTextSplitter
 from pydantic import BaseModel, ConfigDict, Field
 from tqdm import tqdm
 

metagpt/provider/__init__.py

@@ -16,6 +16,7 @@ from metagpt.provider.human_provider import HumanProvider
 from metagpt.provider.spark_api import SparkLLM
 from metagpt.provider.qianfan_api import QianFanLLM
 from metagpt.provider.dashscope_api import DashScopeLLM
+from metagpt.provider.anthropic_api import AnthropicLLM
 
 __all__ = [
     "GeminiLLM",
@@ -28,4 +29,5 @@ __all__ = [
     "SparkLLM",
     "QianFanLLM",
     "DashScopeLLM",
+    "AnthropicLLM",
 ]

metagpt/provider/anthropic_api.py

@@ -1,37 +1,71 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-"""
-@Time    : 2023/7/21 11:15
-@Author  : Leo Xiao
-@File    : anthropic_api.py
-"""
 
-import anthropic
-from anthropic import Anthropic, AsyncAnthropic
+from anthropic import AsyncAnthropic
+from anthropic.types import Message, Usage
 
-from metagpt.configs.llm_config import LLMConfig
+from metagpt.configs.llm_config import LLMConfig, LLMType
+from metagpt.logs import log_llm_stream
+from metagpt.provider.base_llm import BaseLLM
+from metagpt.provider.llm_provider_registry import register_provider
 
 
-class Claude2:
+@register_provider([LLMType.ANTHROPIC, LLMType.CLAUDE])
+class AnthropicLLM(BaseLLM):
     def __init__(self, config: LLMConfig):
         self.config = config
+        self.__init_anthropic()
 
-    def ask(self, prompt: str) -> str:
-        client = Anthropic(api_key=self.config.api_key)
+    def __init_anthropic(self):
+        self.model = self.config.model
+        self.aclient: AsyncAnthropic = AsyncAnthropic(api_key=self.config.api_key, base_url=self.config.base_url)
 
-        res = client.completions.create(
-            model="claude-2",
-            prompt=f"{anthropic.HUMAN_PROMPT} {prompt} {anthropic.AI_PROMPT}",
-            max_tokens_to_sample=1000,
-        )
-        return res.completion
+    def _const_kwargs(self, messages: list[dict], stream: bool = False) -> dict:
+        kwargs = {
+            "model": self.model,
+            "messages": messages,
+            "max_tokens": self.config.max_token,
+            "stream": stream,
+        }
+        if self.use_system_prompt:
+            # if the model support system prompt, extract and pass it
+            if messages[0]["role"] == "system":
+                kwargs["messages"] = messages[1:]
+                kwargs["system"] = messages[0]["content"]  # set system prompt here
+        return kwargs
 
-    async def aask(self, prompt: str) -> str:
-        aclient = AsyncAnthropic(api_key=self.config.api_key)
+    def _update_costs(self, usage: Usage, model: str = None, local_calc_usage: bool = True):
+        usage = {"prompt_tokens": usage.input_tokens, "completion_tokens": usage.output_tokens}
+        super()._update_costs(usage, model)
 
-        res = await aclient.completions.create(
-            model="claude-2",
-            prompt=f"{anthropic.HUMAN_PROMPT} {prompt} {anthropic.AI_PROMPT}",
-            max_tokens_to_sample=1000,
-        )
-        return res.completion
+    def get_choice_text(self, resp: Message) -> str:
+        return resp.content[0].text
+
+    async def _achat_completion(self, messages: list[dict], timeout: int = 3) -> Message:
+        resp: Message = await self.aclient.messages.create(**self._const_kwargs(messages))
+        self._update_costs(resp.usage, self.model)
+        return resp
+
+    async def acompletion(self, messages: list[dict], timeout: int = 3) -> Message:
+        return await self._achat_completion(messages, timeout=timeout)
+
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
+        stream = await self.aclient.messages.create(**self._const_kwargs(messages, stream=True))
+        collected_content = []
+        usage = Usage(input_tokens=0, output_tokens=0)
+        async for event in stream:
+            event_type = event.type
+            if event_type == "message_start":
+                usage.input_tokens = event.message.usage.input_tokens
+                usage.output_tokens = event.message.usage.output_tokens
+            elif event_type == "content_block_delta":
+                content = event.delta.text
+                log_llm_stream(content)
+                collected_content.append(content)
+            elif event_type == "message_delta":
+                usage.output_tokens = event.usage.output_tokens  # update final output_tokens
+
+        log_llm_stream("\n")
+        self._update_costs(usage)
+        full_content = "".join(collected_content)
+        return full_content

metagpt/provider/base_llm.py

@@ -15,10 +15,18 @@ from typing import Dict, Optional, Union
 from openai import AsyncOpenAI
 from openai.types import CompletionUsage
 from pydantic import BaseModel
+from tenacity import (
+    after_log,
+    retry,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_random_exponential,
+)
 
 from metagpt.configs.llm_config import LLMConfig
 from metagpt.logs import logger
 from metagpt.schema import Message
+from metagpt.utils.common import log_and_reraise
 from metagpt.utils.cost_manager import CostManager, Costs
 from metagpt.utils.exceptions import handle_exception
 
@@ -134,6 +142,10 @@ class BaseLLM(ABC):
         """FIXME: No code segment filtering has been done here, and all results are actually displayed"""
         raise NotImplementedError
 
+    @abstractmethod
+    async def _achat_completion(self, messages: list[dict], timeout=3):
+        """_achat_completion implemented by inherited class"""
+
     @abstractmethod
     async def acompletion(self, messages: list[dict], timeout=3):
         """Asynchronous version of completion
@@ -146,8 +158,22 @@ class BaseLLM(ABC):
         """
 
     @abstractmethod
-    async def acompletion_text(self, messages: list[dict], stream=False, timeout=3) -> str:
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
+        """_achat_completion_stream implemented by inherited class"""
+
+    @retry(
+        stop=stop_after_attempt(3),
+        wait=wait_random_exponential(min=1, max=60),
+        after=after_log(logger, logger.level("WARNING").name),
+        retry=retry_if_exception_type(ConnectionError),
+        retry_error_callback=log_and_reraise,
+    )
+    async def acompletion_text(self, messages: list[dict], stream: bool = False, timeout: int = 3) -> str:
         """Asynchronous version of completion. Return str. Support stream-print"""
+        if stream:
+            return await self._achat_completion_stream(messages, timeout=timeout)
+        resp = await self._achat_completion(messages, timeout=timeout)
+        return self.get_choice_text(resp)
 
     def get_choice_text(self, rsp: dict) -> str:
         """Required to provide the first text of choice"""

metagpt/provider/dashscope_api.py

@@ -24,18 +24,10 @@ from dashscope.common.error import (
     ModelRequired,
     UnsupportedApiProtocol,
 )
-from tenacity import (
-    after_log,
-    retry,
-    retry_if_exception_type,
-    stop_after_attempt,
-    wait_random_exponential,
-)
 
-from metagpt.logs import log_llm_stream, logger
+from metagpt.logs import log_llm_stream
 from metagpt.provider.base_llm import BaseLLM, LLMConfig
 from metagpt.provider.llm_provider_registry import LLMType, register_provider
-from metagpt.provider.openai_api import log_and_reraise
 from metagpt.utils.cost_manager import CostManager
 from metagpt.utils.token_counter import DASHSCOPE_TOKEN_COSTS
 
@@ -210,16 +202,16 @@ class DashScopeLLM(BaseLLM):
         self._update_costs(dict(resp.usage))
         return resp.output
 
-    async def _achat_completion(self, messages: list[dict]) -> GenerationOutput:
+    async def _achat_completion(self, messages: list[dict], timeout: int = 3) -> GenerationOutput:
         resp: GenerationResponse = await self.aclient.acall(**self._const_kwargs(messages, stream=False))
         self._check_response(resp)
         self._update_costs(dict(resp.usage))
         return resp.output
 
     async def acompletion(self, messages: list[dict], timeout=3) -> GenerationOutput:
-        return await self._achat_completion(messages)
+        return await self._achat_completion(messages, timeout=timeout)
 
-    async def _achat_completion_stream(self, messages: list[dict]) -> str:
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
         resp = await self.aclient.acall(**self._const_kwargs(messages, stream=True))
         collected_content = []
         usage = {}
@@ -233,16 +225,3 @@ class DashScopeLLM(BaseLLM):
         self._update_costs(usage)
         full_content = "".join(collected_content)
         return full_content
-
-    @retry(
-        stop=stop_after_attempt(3),
-        wait=wait_random_exponential(min=1, max=60),
-        after=after_log(logger, logger.level("WARNING").name),
-        retry=retry_if_exception_type(ConnectionError),
-        retry_error_callback=log_and_reraise,
-    )
-    async def acompletion_text(self, messages: list[dict], stream=False, timeout: int = 3) -> str:
-        if stream:
-            return await self._achat_completion_stream(messages)
-        resp = await self._achat_completion(messages)
-        return self.get_choice_text(resp)

metagpt/provider/google_gemini_api.py

@@ -13,19 +13,11 @@ from google.generativeai.types.generation_types import (
     GenerateContentResponse,
     GenerationConfig,
 )
-from tenacity import (
-    after_log,
-    retry,
-    retry_if_exception_type,
-    stop_after_attempt,
-    wait_random_exponential,
-)
 
 from metagpt.configs.llm_config import LLMConfig, LLMType
-from metagpt.logs import log_llm_stream, logger
+from metagpt.logs import log_llm_stream
 from metagpt.provider.base_llm import BaseLLM
 from metagpt.provider.llm_provider_registry import register_provider
-from metagpt.provider.openai_api import log_and_reraise
 
 
 class GeminiGenerativeModel(GenerativeModel):
@@ -96,16 +88,16 @@ class GeminiLLM(BaseLLM):
         self._update_costs(usage)
         return resp
 
-    async def _achat_completion(self, messages: list[dict]) -> "AsyncGenerateContentResponse":
+    async def _achat_completion(self, messages: list[dict], timeout: int = 3) -> "AsyncGenerateContentResponse":
         resp: AsyncGenerateContentResponse = await self.llm.generate_content_async(**self._const_kwargs(messages))
         usage = await self.aget_usage(messages, resp.text)
         self._update_costs(usage)
         return resp
 
     async def acompletion(self, messages: list[dict], timeout=3) -> dict:
-        return await self._achat_completion(messages)
+        return await self._achat_completion(messages, timeout=timeout)
 
-    async def _achat_completion_stream(self, messages: list[dict]) -> str:
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
         resp: AsyncGenerateContentResponse = await self.llm.generate_content_async(
             **self._const_kwargs(messages, stream=True)
         )
@@ -120,17 +112,3 @@ class GeminiLLM(BaseLLM):
         usage = await self.aget_usage(messages, full_content)
         self._update_costs(usage)
         return full_content
-
-    @retry(
-        stop=stop_after_attempt(3),
-        wait=wait_random_exponential(min=1, max=60),
-        after=after_log(logger, logger.level("WARNING").name),
-        retry=retry_if_exception_type(ConnectionError),
-        retry_error_callback=log_and_reraise,
-    )
-    async def acompletion_text(self, messages: list[dict], stream=False, timeout: int = 3) -> str:
-        """response in async with stream or non-stream mode"""
-        if stream:
-            return await self._achat_completion_stream(messages)
-        resp = await self._achat_completion(messages)
-        return self.get_choice_text(resp)

metagpt/provider/human_provider.py

@@ -35,10 +35,16 @@ class HumanProvider(BaseLLM):
     ) -> str:
         return self.ask(msg, timeout=timeout)
 
+    async def _achat_completion(self, messages: list[dict], timeout=3):
+        pass
+
     async def acompletion(self, messages: list[dict], timeout=3):
         """dummy implementation of abstract method in base"""
         return []
 
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
+        pass
+
     async def acompletion_text(self, messages: list[dict], stream=False, timeout=3) -> str:
         """dummy implementation of abstract method in base"""
         return ""

metagpt/provider/ollama_api.py

@@ -4,22 +4,12 @@
 
 import json
 
-from requests import ConnectionError
-from tenacity import (
-    after_log,
-    retry,
-    retry_if_exception_type,
-    stop_after_attempt,
-    wait_random_exponential,
-)
-
 from metagpt.configs.llm_config import LLMConfig, LLMType
 from metagpt.const import LLM_API_TIMEOUT
-from metagpt.logs import log_llm_stream, logger
+from metagpt.logs import log_llm_stream
 from metagpt.provider.base_llm import BaseLLM
 from metagpt.provider.general_api_requestor import GeneralAPIRequestor
 from metagpt.provider.llm_provider_registry import register_provider
-from metagpt.provider.openai_api import log_and_reraise
 from metagpt.utils.cost_manager import TokenCostManager
 
 
@@ -60,7 +50,7 @@ class OllamaLLM(BaseLLM):
         chunk = chunk.decode(encoding)
         return json.loads(chunk)
 
-    async def _achat_completion(self, messages: list[dict]) -> dict:
+    async def _achat_completion(self, messages: list[dict], timeout: int = 3) -> dict:
         resp, _, _ = await self.client.arequest(
             method=self.http_method,
             url=self.suffix_url,
@@ -73,9 +63,9 @@ class OllamaLLM(BaseLLM):
         return resp
 
     async def acompletion(self, messages: list[dict], timeout=3) -> dict:
-        return await self._achat_completion(messages)
+        return await self._achat_completion(messages, timeout=timeout)
 
-    async def _achat_completion_stream(self, messages: list[dict]) -> str:
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
         stream_resp, _, _ = await self.client.arequest(
             method=self.http_method,
             url=self.suffix_url,
@@ -101,17 +91,3 @@ class OllamaLLM(BaseLLM):
         self._update_costs(usage)
         full_content = "".join(collected_content)
         return full_content
-
-    @retry(
-        stop=stop_after_attempt(3),
-        wait=wait_random_exponential(min=1, max=60),
-        after=after_log(logger, logger.level("WARNING").name),
-        retry=retry_if_exception_type(ConnectionError),
-        retry_error_callback=log_and_reraise,
-    )
-    async def acompletion_text(self, messages: list[dict], stream=False, timeout: int = 3) -> str:
-        """response in async with stream or non-stream mode"""
-        if stream:
-            return await self._achat_completion_stream(messages)
-        resp = await self._achat_completion(messages)
-        return self.get_choice_text(resp)

metagpt/provider/openai_api.py

@@ -30,7 +30,7 @@ from metagpt.provider.base_llm import BaseLLM
 from metagpt.provider.constant import GENERAL_FUNCTION_SCHEMA
 from metagpt.provider.llm_provider_registry import register_provider
 from metagpt.schema import Message
-from metagpt.utils.common import CodeParser, decode_image
+from metagpt.utils.common import CodeParser, decode_image, log_and_reraise
 from metagpt.utils.cost_manager import CostManager
 from metagpt.utils.exceptions import handle_exception
 from metagpt.utils.token_counter import (
@@ -40,17 +40,6 @@ from metagpt.utils.token_counter import (
 )
 
 
-def log_and_reraise(retry_state):
-    logger.error(f"Retry attempts exhausted. Last exception: {retry_state.outcome.exception()}")
-    logger.warning(
-        """
-Recommend going to https://deepwisdom.feishu.cn/wiki/MsGnwQBjiif9c3koSJNcYaoSnu4#part-XdatdVlhEojeAfxaaEZcMV3ZniQ
-See FAQ 5.8
-"""
-    )
-    raise retry_state.outcome.exception()
-
-
 @register_provider([LLMType.OPENAI, LLMType.FIREWORKS, LLMType.OPEN_LLM, LLMType.MOONSHOT, LLMType.MISTRAL])
 class OpenAILLM(BaseLLM):
     """Check https://platform.openai.com/examples for examples"""

metagpt/provider/qianfan_api.py

@@ -7,19 +7,11 @@ import os
 import qianfan
 from qianfan import ChatCompletion
 from qianfan.resources.typing import JsonBody
-from tenacity import (
-    after_log,
-    retry,
-    retry_if_exception_type,
-    stop_after_attempt,
-    wait_random_exponential,
-)
 
 from metagpt.configs.llm_config import LLMConfig, LLMType
-from metagpt.logs import log_llm_stream, logger
+from metagpt.logs import log_llm_stream
 from metagpt.provider.base_llm import BaseLLM
 from metagpt.provider.llm_provider_registry import register_provider
-from metagpt.provider.openai_api import log_and_reraise
 from metagpt.utils.cost_manager import CostManager
 from metagpt.utils.token_counter import (
     QIANFAN_ENDPOINT_TOKEN_COSTS,
@@ -115,15 +107,15 @@ class QianFanLLM(BaseLLM):
         self._update_costs(resp.body.get("usage", {}))
         return resp.body
 
-    async def _achat_completion(self, messages: list[dict]) -> JsonBody:
+    async def _achat_completion(self, messages: list[dict], timeout: int = 3) -> JsonBody:
         resp = await self.aclient.ado(**self._const_kwargs(messages=messages, stream=False))
         self._update_costs(resp.body.get("usage", {}))
         return resp.body
 
-    async def acompletion(self, messages: list[dict], timeout=3) -> JsonBody:
-        return await self._achat_completion(messages)
+    async def acompletion(self, messages: list[dict], timeout: int = 3) -> JsonBody:
+        return await self._achat_completion(messages, timeout=timeout)
 
-    async def _achat_completion_stream(self, messages: list[dict]) -> str:
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
         resp = await self.aclient.ado(**self._const_kwargs(messages=messages, stream=True))
         collected_content = []
         usage = {}
@@ -137,16 +129,3 @@ class QianFanLLM(BaseLLM):
         self._update_costs(usage)
         full_content = "".join(collected_content)
         return full_content
-
-    @retry(
-        stop=stop_after_attempt(3),
-        wait=wait_random_exponential(min=1, max=60),
-        after=after_log(logger, logger.level("WARNING").name),
-        retry=retry_if_exception_type(ConnectionError),
-        retry_error_callback=log_and_reraise,
-    )
-    async def acompletion_text(self, messages: list[dict], stream=False, timeout: int = 3) -> str:
-        if stream:
-            return await self._achat_completion_stream(messages)
-        resp = await self._achat_completion(messages)
-        return self.get_choice_text(resp)

metagpt/provider/spark_api.py

@@ -31,12 +31,18 @@ class SparkLLM(BaseLLM):
     def get_choice_text(self, rsp: dict) -> str:
         return rsp["payload"]["choices"]["text"][-1]["content"]
 
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
+        pass
+
     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。")
         w = GetMessageFromWeb(messages, self.config)
         return w.run()
 
+    async def _achat_completion(self, messages: list[dict], timeout=3):
+        pass
+
     async def acompletion(self, messages: list[dict], timeout=3):
         # 不支持异步
         w = GetMessageFromWeb(messages, self.config)

metagpt/provider/zhipuai_api.py

@@ -5,21 +5,12 @@
 from enum import Enum
 from typing import Optional
 
-from requests import ConnectionError
-from tenacity import (
-    after_log,
-    retry,
-    retry_if_exception_type,
-    stop_after_attempt,
-    wait_random_exponential,
-)
 from zhipuai.types.chat.chat_completion import Completion
 
 from metagpt.configs.llm_config import LLMConfig, LLMType
-from metagpt.logs import log_llm_stream, logger
+from metagpt.logs import log_llm_stream
 from metagpt.provider.base_llm import BaseLLM
 from metagpt.provider.llm_provider_registry import register_provider
-from metagpt.provider.openai_api import log_and_reraise
 from metagpt.provider.zhipuai.zhipu_model_api import ZhiPuModelAPI
 from metagpt.utils.cost_manager import CostManager
 
@@ -87,17 +78,3 @@ class ZhiPuAILLM(BaseLLM):
         self._update_costs(usage)
         full_content = "".join(collected_content)
         return full_content
-
-    @retry(
-        stop=stop_after_attempt(3),
-        wait=wait_random_exponential(min=1, max=60),
-        after=after_log(logger, logger.level("WARNING").name),
-        retry=retry_if_exception_type(ConnectionError),
-        retry_error_callback=log_and_reraise,
-    )
-    async def acompletion_text(self, messages: list[dict], stream=False, timeout=3) -> str:
-        """response in async with stream or non-stream mode"""
-        if stream:
-            return await self._achat_completion_stream(messages)
-        resp = await self._achat_completion(messages)
-        return self.get_choice_text(resp)

metagpt/roles/di/data_interpreter.py

@@ -2,9 +2,9 @@ from __future__ import annotations
 
 from pydantic import Field
 
-from metagpt.actions.mi.ask_review import ReviewConst
-from metagpt.actions.mi.execute_nb_code import ExecuteNbCode
-from metagpt.actions.mi.write_analysis_code import (
+from metagpt.actions.di.ask_review import ReviewConst
+from metagpt.actions.di.execute_nb_code import ExecuteNbCode
+from metagpt.actions.di.write_analysis_code import (
     WriteCodeWithoutTools,
     WriteCodeWithTools,
 )
@@ -13,9 +13,9 @@ from metagpt.roles import Role
 from metagpt.schema import Message, Task, TaskResult
 
 
-class Interpreter(Role):
-    name: str = "Ivy"
-    profile: str = "Interpreter"
+class DataInterpreter(Role):
+    name: str = "David"
+    profile: str = "DataInterpreter"
     auto_run: bool = True
     use_tools: bool = False
     execute_code: ExecuteNbCode = Field(default_factory=ExecuteNbCode, exclude=True)

metagpt/roles/di/ml_engineer.py

@@ -1,13 +1,13 @@
-from metagpt.actions.mi.debug_code import DebugCode
-from metagpt.actions.mi.execute_nb_code import ExecuteNbCode
-from metagpt.actions.mi.ml_action import UpdateDataColumns, WriteCodeWithToolsML
+from metagpt.actions.di.debug_code import DebugCode
+from metagpt.actions.di.execute_nb_code import ExecuteNbCode
+from metagpt.actions.di.ml_action import UpdateDataColumns, WriteCodeWithToolsML
 from metagpt.logs import logger
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 from metagpt.tools.tool_type import ToolType
 from metagpt.utils.common import any_to_str
 
 
-class MLEngineer(Interpreter):
+class MLEngineer(DataInterpreter):
     name: str = "Mark"
     profile: str = "MLEngineer"
     debug_context: list = []

metagpt/roles/engineer.py

@@ -204,7 +204,6 @@ class Engineer(Role):
 
     async def _act_code_plan_and_change(self):
         """Write code plan and change that guides subsequent WriteCode and WriteCodeReview"""
-        logger.info("Writing code plan and change..")
         node = await self.rc.todo.run()
         code_plan_and_change = node.instruct_content.model_dump_json()
         dependencies = {

metagpt/strategy/planner.py

@@ -4,8 +4,8 @@ import json
 
 from pydantic import BaseModel, Field
 
-from metagpt.actions.mi.ask_review import AskReview, ReviewConst
-from metagpt.actions.mi.write_plan import (
+from metagpt.actions.di.ask_review import AskReview, ReviewConst
+from metagpt.actions.di.write_plan import (
     WritePlan,
     precheck_update_plan_from_rsp,
     update_plan_from_rsp,

metagpt/strategy/solver.py

@@ -49,8 +49,8 @@ class TOTSolver(BaseSolver):
         raise NotImplementedError
 
 
-class InterpreterSolver(BaseSolver):
-    """InterpreterSolver: Write&Run code in the graph"""
+class DataInterpreterSolver(BaseSolver):
+    """DataInterpreterSolver: Write&Run code in the graph"""
 
     async def solve(self):
         raise NotImplementedError

metagpt/utils/common.py

@@ -810,3 +810,14 @@ def decode_image(img_url_or_b64: str) -> Image:
         img_data = BytesIO(base64.b64decode(b64_data))
         img = Image.open(img_data)
     return img
+
+
+def log_and_reraise(retry_state: RetryCallState):
+    logger.error(f"Retry attempts exhausted. Last exception: {retry_state.outcome.exception()}")
+    logger.warning(
+        """
+Recommend going to https://deepwisdom.feishu.cn/wiki/MsGnwQBjiif9c3koSJNcYaoSnu4#part-XdatdVlhEojeAfxaaEZcMV3ZniQ
+See FAQ 5.8
+"""
+    )
+    raise retry_state.outcome.exception()

metagpt/utils/project_repo.py

@@ -136,6 +136,7 @@ class ProjectRepo(FileRepository):
         code_files = self.with_src_path(path=git_workdir / git_workdir.name).srcs.all_files
         if not code_files:
             return False
+        return bool(code_files)
 
     def with_src_path(self, path: str | Path) -> ProjectRepo:
         try:

metagpt/utils/token_counter.py

@@ -43,6 +43,11 @@ TOKEN_COSTS = {
     "mistral-small-latest": {"prompt": 0.002, "completion": 0.006},
     "mistral-medium-latest": {"prompt": 0.0027, "completion": 0.0081},
     "mistral-large-latest": {"prompt": 0.008, "completion": 0.024},
+    "claude-instant-1.2": {"prompt": 0.0008, "completion": 0.0024},
+    "claude-2.0": {"prompt": 0.008, "completion": 0.024},
+    "claude-2.1": {"prompt": 0.008, "completion": 0.024},
+    "claude-3-sonnet-20240229": {"prompt": 0.003, "completion": 0.015},
+    "claude-3-opus-20240229": {"prompt": 0.015, "completion": 0.075},
 }
 
 
@@ -166,6 +171,11 @@ TOKEN_MAX = {
     "mistral-small-latest": 32768,
     "mistral-medium-latest": 32768,
     "mistral-large-latest": 32768,
+    "claude-instant-1.2": 100000,
+    "claude-2.0": 100000,
+    "claude-2.1": 200000,
+    "claude-3-sonnet-20240229": 200000,
+    "claude-3-opus-20240229": 200000,
 }
 
 

requirements.txt

@@ -12,6 +12,7 @@ typer==0.9.0
 # google_api_python_client==2.93.0  # Used by search_engine.py
 lancedb==0.4.0
 langchain==0.1.8
+sqlalchemy==2.0.0  # along with langchain
 loguru==0.6.0
 meilisearch==0.21.0
 numpy>=1.24.3,<1.25.0
@@ -33,7 +34,7 @@ tqdm==4.65.0
 #unstructured[local-inference]
 # selenium>4
 # webdriver_manager<3.9
-anthropic==0.8.1
+anthropic==0.18.1
 typing-inspect==0.8.0
 libcst==1.0.1
 qdrant-client==1.7.0

setup.py

@@ -57,7 +57,7 @@ extras_require["dev"] = (["pylint~=3.0.3", "black~=23.3.0", "isort~=5.12.0", "pr
 
 setup(
     name="metagpt",
-    version="0.7.2",
+    version="0.7.4",
     description="The Multi-Agent Framework",
     long_description=long_description,
     long_description_content_type="text/markdown",

tests/conftest.py

@@ -12,6 +12,7 @@ import logging
 import os
 import re
 import uuid
+from pathlib import Path
 from typing import Callable
 
 import aiohttp.web
@@ -270,3 +271,11 @@ def mermaid_mocker(aiohttp_mocker, mermaid_rsp_cache):
     aiohttp_mocker.rsp_cache = mermaid_rsp_cache
     aiohttp_mocker.check_funcs = check_funcs
     yield check_funcs
+
+
+@pytest.fixture
+def git_dir():
+    """Fixture to get the unittest directory."""
+    git_dir = Path(__file__).parent / f"unittest/{uuid.uuid4().hex}"
+    git_dir.mkdir(parents=True, exist_ok=True)
+    return git_dir

tests/data/incremental_dev_project/mock.py

@@ -149,7 +149,7 @@ sequenceDiagram
 
 The requirement analysis suggests the need for a clean and intuitive interface. Since we are using a command-line interface, we need to ensure that the text-based UI is as user-friendly as possible. Further clarification on whether a graphical user interface (GUI) is expected in the future would be helpful for planning the extendability of the game."""
 
-TASKS_SAMPLE = """
+TASK_SAMPLE = """
 ## Required Python packages
 
 - random==2.2.1
@@ -345,7 +345,7 @@ REFINED_DESIGN_JSON = {
     "Anything UNCLEAR": "",
 }
 
-REFINED_TASKS_JSON = {
+REFINED_TASK_JSON = {
     "Required Python packages": ["random==2.2.1", "Tkinter==8.6"],
     "Required Other language third-party packages": ["No third-party dependencies required"],
     "Refined Logic Analysis": [
@@ -373,7 +373,14 @@ REFINED_TASKS_JSON = {
 }
 
 CODE_PLAN_AND_CHANGE_SAMPLE = {
-    "Code Plan And Change": '\n1. Plan for gui.py: Develop the GUI using Tkinter to replace the command-line interface. Start by setting up the main window and event handling. Then, add widgets for displaying the game status, results, and feedback. Implement interactive elements for difficulty selection and visualize the guess history. Finally, create animations for guess feedback and ensure responsiveness across different screen sizes.\n```python\nclass GUI:\n-    pass\n+    def __init__(self):\n+        self.setup_window()\n+\n+    def setup_window(self):\n+        # Initialize the main window using Tkinter\n+        pass\n+\n+    def bind_events(self):\n+        # Bind button clicks and other events\n+        pass\n+\n+    def update_feedback(self, message: str):\n+        # Update the feedback label with the given message\n+        pass\n+\n+    def update_attempts(self, attempts: int):\n+        # Update the attempts label with the number of attempts\n+        pass\n+\n+    def update_history(self, history: list):\n+        # Update the history view with the list of past guesses\n+        pass\n+\n+    def show_difficulty_selector(self):\n+        # Show buttons or a dropdown for difficulty selection\n+        pass\n+\n+    def animate_guess_result(self, correct: bool):\n+        # Trigger an animation for correct or incorrect guesses\n+        pass\n```\n\n2. Plan for main.py: Modify the main.py to initialize the GUI and start the event-driven game loop. Ensure that the GUI is the primary interface for user interaction.\n```python\nclass Main:\n     def main(self):\n-        user_interface = UI()\n-        user_interface.start()\n+        graphical_user_interface = GUI()\n+        graphical_user_interface.setup_window()\n+        graphical_user_interface.bind_events()\n+        # Start the Tkinter main loop\n+        pass\n\n if __name__ == "__main__":\n     main_instance = Main()\n     main_instance.main()\n```\n\n3. Plan for ui.py: Refactor ui.py to work with the new GUI class. Remove command-line interactions and delegate display and input tasks to the GUI.\n```python\nclass UI:\n-    def display_message(self, message: str):\n-        print(message)\n+\n+    def display_message(self, message: str):\n+        # This method will now pass the message to the GUI to display\n+        pass\n\n-    def get_user_input(self, prompt: str) -> str:\n-        return input(prompt)\n+\n+    def get_user_input(self, prompt: str) -> str:\n+        # This method will now trigger the GUI to get user input\n+        pass\n\n-    def show_attempts(self, attempts: int):\n-        print(f"Number of attempts: {attempts}")\n+\n+    def show_attempts(self, attempts: int):\n+        # This method will now update the GUI with the number of attempts\n+        pass\n\n-    def show_history(self, history: list):\n-        print("Guess history:")\n-        for guess in history:\n-            print(guess)\n+\n+    def show_history(self, history: list):\n+        # This method will now update the GUI with the guess history\n+        pass\n```\n\n4. Plan for game.py: Ensure game.py remains mostly unchanged as it contains the core game logic. However, make minor adjustments if necessary to integrate with the new GUI.\n```python\nclass Game:\n     # No changes required for now\n```\n'
+    "Development Plan": [
+        "Develop the GUI using Tkinter to replace the command-line interface. Start by setting up the main window and event handling. Then, add widgets for displaying the game status, results, and feedback. Implement interactive elements for difficulty selection and visualize the guess history. Finally, create animations for guess feedback and ensure responsiveness across different screen sizes.",
+        "Modify the main.py to initialize the GUI and start the event-driven game loop. Ensure that the GUI is the primary interface for user interaction.",
+    ],
+    "Incremental Change": [
+        """```diff\nclass GUI:\n-    pass\n+    def __init__(self):\n+        self.setup_window()\n+\n+    def setup_window(self):\n+        # Initialize the main window using Tkinter\n+        pass\n+\n+    def bind_events(self):\n+        # Bind button clicks and other events\n+        pass\n+\n+    def update_feedback(self, message: str):\n+        # Update the feedback label with the given message\n+        pass\n+\n+    def update_attempts(self, attempts: int):\n+        # Update the attempts label with the number of attempts\n+        pass\n+\n+    def update_history(self, history: list):\n+        # Update the history view with the list of past guesses\n+        pass\n+\n+    def show_difficulty_selector(self):\n+        # Show buttons or a dropdown for difficulty selection\n+        pass\n+\n+    def animate_guess_result(self, correct: bool):\n+        # Trigger an animation for correct or incorrect guesses\n+        pass\n```""",
+        """```diff\nclass Main:\n     def main(self):\n-        user_interface = UI()\n-        user_interface.start()\n+        graphical_user_interface = GUI()\n+        graphical_user_interface.setup_window()\n+        graphical_user_interface.bind_events()\n+        # Start the Tkinter main loop\n+        pass\n\n if __name__ == "__main__":\n     main_instance = Main()\n     main_instance.main()\n```\n\n3. Plan for ui.py: Refactor ui.py to work with the new GUI class. Remove command-line interactions and delegate display and input tasks to the GUI.\n```python\nclass UI:\n-    def display_message(self, message: str):\n-        print(message)\n+\n+    def display_message(self, message: str):\n+        # This method will now pass the message to the GUI to display\n+        pass\n\n-    def get_user_input(self, prompt: str) -> str:\n-        return input(prompt)\n+\n+    def get_user_input(self, prompt: str) -> str:\n+        # This method will now trigger the GUI to get user input\n+        pass\n\n-    def show_attempts(self, attempts: int):\n-        print(f"Number of attempts: {attempts}")\n+\n+    def show_attempts(self, attempts: int):\n+        # This method will now update the GUI with the number of attempts\n+        pass\n\n-    def show_history(self, history: list):\n-        print("Guess history:")\n-        for guess in history:\n-            print(guess)\n+\n+    def show_history(self, history: list):\n+        # This method will now update the GUI with the guess history\n+        pass\n```\n\n4. Plan for game.py: Ensure game.py remains mostly unchanged as it contains the core game logic. However, make minor adjustments if necessary to integrate with the new GUI.\n```python\nclass Game:\n     # No changes required for now\n```\n""",
+    ],
 }
 
 REFINED_CODE_INPUT_SAMPLE = """

tests/metagpt/actions/di/test_ask_review.py

@@ -1,6 +1,6 @@
 import pytest
 
-from metagpt.actions.mi.ask_review import AskReview
+from metagpt.actions.di.ask_review import AskReview
 
 
 @pytest.mark.asyncio

tests/metagpt/actions/di/test_debug_code.py

@@ -5,7 +5,7 @@
 
 import pytest
 
-from metagpt.actions.mi.debug_code import DebugCode
+from metagpt.actions.di.debug_code import DebugCode
 from metagpt.schema import Message
 
 ErrorStr = """Tested passed:

tests/metagpt/actions/di/test_execute_nb_code.py

@@ -1,6 +1,6 @@
 import pytest
 
-from metagpt.actions.mi.execute_nb_code import ExecuteNbCode, truncate
+from metagpt.actions.di.execute_nb_code import ExecuteNbCode, truncate
 
 
 @pytest.mark.asyncio

tests/metagpt/actions/di/test_ml_action.py

@@ -1,6 +1,6 @@
 import pytest
 
-from metagpt.actions.mi.ml_action import WriteCodeWithToolsML
+from metagpt.actions.di.ml_action import WriteCodeWithToolsML
 from metagpt.schema import Plan, Task
 
 

tests/metagpt/actions/di/test_write_analysis_code.py

@@ -2,8 +2,8 @@ import asyncio
 
 import pytest
 
-from metagpt.actions.mi.execute_nb_code import ExecuteNbCode
-from metagpt.actions.mi.write_analysis_code import (
+from metagpt.actions.di.execute_nb_code import ExecuteNbCode
+from metagpt.actions.di.write_analysis_code import (
     WriteCodeWithoutTools,
     WriteCodeWithTools,
 )

tests/metagpt/actions/di/test_write_plan.py

@@ -1,6 +1,6 @@
 import pytest
 
-from metagpt.actions.mi.write_plan import (
+from metagpt.actions.di.write_plan import (
     Plan,
     Task,
     WritePlan,

tests/metagpt/actions/mock_json.py

@@ -37,7 +37,7 @@ DESIGN = {
 }
 
 
-TASKS = {
+TASK = {
     "Required Python packages": ["pygame==2.0.1"],
     "Required Other language third-party packages": ["No third-party dependencies required"],
     "Logic Analysis": [

tests/metagpt/actions/test_design_api.py

@@ -9,8 +9,10 @@
 import pytest
 
 from metagpt.actions.design_api import WriteDesign
+from metagpt.llm import LLM
 from metagpt.logs import logger
 from metagpt.schema import Message
+from tests.data.incremental_dev_project.mock import DESIGN_SAMPLE, REFINED_PRD_JSON
 
 
 @pytest.mark.asyncio
@@ -25,3 +27,16 @@ async def test_design_api(context):
         logger.info(result)
 
         assert result
+
+
+@pytest.mark.asyncio
+async def test_refined_design_api(context):
+    await context.repo.docs.prd.save(filename="1.txt", content=str(REFINED_PRD_JSON))
+    await context.repo.docs.system_design.save(filename="1.txt", content=DESIGN_SAMPLE)
+
+    design_api = WriteDesign(context=context, llm=LLM())
+
+    result = await design_api.run(Message(content="", instruct_content=None))
+    logger.info(result)
+
+    assert result

tests/metagpt/actions/test_project_management.py

@@ -9,13 +9,19 @@
 import pytest
 
 from metagpt.actions.project_management import WriteTasks
+from metagpt.llm import LLM
 from metagpt.logs import logger
 from metagpt.schema import Message
+from tests.data.incremental_dev_project.mock import (
+    REFINED_DESIGN_JSON,
+    REFINED_PRD_JSON,
+    TASK_SAMPLE,
+)
 from tests.metagpt.actions.mock_json import DESIGN, PRD
 
 
 @pytest.mark.asyncio
-async def test_design_api(context):
+async def test_task(context):
     await context.repo.docs.prd.save("1.txt", content=str(PRD))
     await context.repo.docs.system_design.save("1.txt", content=str(DESIGN))
     logger.info(context.git_repo)
@@ -26,3 +32,19 @@ async def test_design_api(context):
     logger.info(result)
 
     assert result
+
+
+@pytest.mark.asyncio
+async def test_refined_task(context):
+    await context.repo.docs.prd.save("2.txt", content=str(REFINED_PRD_JSON))
+    await context.repo.docs.system_design.save("2.txt", content=str(REFINED_DESIGN_JSON))
+    await context.repo.docs.task.save("2.txt", content=TASK_SAMPLE)
+
+    logger.info(context.git_repo)
+
+    action = WriteTasks(context=context, llm=LLM())
+
+    result = await action.run(Message(content="", instruct_content=None))
+    logger.info(result)
+
+    assert result

tests/metagpt/actions/test_project_management_an.py

@@ -10,13 +10,14 @@ from openai._models import BaseModel
 
 from metagpt.actions.action_node import ActionNode, dict_to_markdown
 from metagpt.actions.project_management import NEW_REQ_TEMPLATE
-from metagpt.actions.project_management_an import REFINED_PM_NODE
+from metagpt.actions.project_management_an import PM_NODE, REFINED_PM_NODE
 from metagpt.llm import LLM
 from tests.data.incremental_dev_project.mock import (
     REFINED_DESIGN_JSON,
-    REFINED_TASKS_JSON,
-    TASKS_SAMPLE,
+    REFINED_TASK_JSON,
+    TASK_SAMPLE,
 )
+from tests.metagpt.actions.mock_json import TASK
 
 
 @pytest.fixture()
@@ -24,20 +25,40 @@ def llm():
     return LLM()
 
 
-def mock_refined_tasks_json():
-    return REFINED_TASKS_JSON
+def mock_refined_task_json():
+    return REFINED_TASK_JSON
+
+
+def mock_task_json():
+    return TASK
 
 
 @pytest.mark.asyncio
 async def test_project_management_an(mocker):
+    root = ActionNode.from_children(
+        "ProjectManagement", [ActionNode(key="", expected_type=str, instruction="", example="")]
+    )
+    root.instruct_content = BaseModel()
+    root.instruct_content.model_dump = mock_task_json
+    mocker.patch("metagpt.actions.project_management_an.PM_NODE.fill", return_value=root)
+
+    node = await PM_NODE.fill(dict_to_markdown(REFINED_DESIGN_JSON), llm)
+
+    assert "Logic Analysis" in node.instruct_content.model_dump()
+    assert "Task list" in node.instruct_content.model_dump()
+    assert "Shared Knowledge" in node.instruct_content.model_dump()
+
+
+@pytest.mark.asyncio
+async def test_project_management_an_inc(mocker):
     root = ActionNode.from_children(
         "RefinedProjectManagement", [ActionNode(key="", expected_type=str, instruction="", example="")]
     )
     root.instruct_content = BaseModel()
-    root.instruct_content.model_dump = mock_refined_tasks_json
+    root.instruct_content.model_dump = mock_refined_task_json
     mocker.patch("metagpt.actions.project_management_an.REFINED_PM_NODE.fill", return_value=root)
 
-    prompt = NEW_REQ_TEMPLATE.format(old_task=TASKS_SAMPLE, context=dict_to_markdown(REFINED_DESIGN_JSON))
+    prompt = NEW_REQ_TEMPLATE.format(old_task=TASK_SAMPLE, context=dict_to_markdown(REFINED_DESIGN_JSON))
     node = await REFINED_PM_NODE.fill(prompt, llm)
 
     assert "Refined Logic Analysis" in node.instruct_content.model_dump()

tests/metagpt/actions/test_write_code.py

@@ -6,7 +6,7 @@
 @File    : test_write_code.py
 @Modifiled By: mashenquan, 2023-12-6. According to RFC 135
 """
-
+import json
 from pathlib import Path
 
 import pytest
@@ -14,10 +14,27 @@ import pytest
 from metagpt.actions.write_code import WriteCode
 from metagpt.logs import logger
 from metagpt.schema import CodingContext, Document
-from metagpt.utils.common import aread
+from metagpt.utils.common import CodeParser, aread
+from tests.data.incremental_dev_project.mock import (
+    CODE_PLAN_AND_CHANGE_SAMPLE,
+    REFINED_CODE_INPUT_SAMPLE,
+    REFINED_DESIGN_JSON,
+    REFINED_TASK_JSON,
+)
 from tests.metagpt.actions.mock_markdown import TASKS_2, WRITE_CODE_PROMPT_SAMPLE
 
 
+def setup_inc_workdir(context, inc: bool = False):
+    """setup incremental workdir for testing"""
+    context.src_workspace = context.git_repo.workdir / "src"
+    if inc:
+        context.config.inc = inc
+        context.repo.old_workspace = context.repo.git_repo.workdir / "old"
+        context.config.project_path = "old"
+
+    return context
+
+
 @pytest.mark.asyncio
 async def test_write_code(context):
     # Prerequisites
@@ -81,5 +98,66 @@ async def test_write_code_deps(context):
     assert rsp.code_doc.content
 
 
+@pytest.mark.asyncio
+async def test_write_refined_code(context, git_dir):
+    # Prerequisites
+    context = setup_inc_workdir(context, inc=True)
+    await context.repo.docs.system_design.save(filename="1.json", content=json.dumps(REFINED_DESIGN_JSON))
+    await context.repo.docs.task.save(filename="1.json", content=json.dumps(REFINED_TASK_JSON))
+    await context.repo.docs.code_plan_and_change.save(
+        filename="1.json", content=json.dumps(CODE_PLAN_AND_CHANGE_SAMPLE)
+    )
+
+    # old_workspace contains the legacy code
+    await context.repo.with_src_path(context.repo.old_workspace).srcs.save(
+        filename="game.py", content=CodeParser.parse_code(block="", text=REFINED_CODE_INPUT_SAMPLE)
+    )
+
+    ccontext = CodingContext(
+        filename="game.py",
+        design_doc=await context.repo.docs.system_design.get(filename="1.json"),
+        task_doc=await context.repo.docs.task.get(filename="1.json"),
+        code_plan_and_change_doc=await context.repo.docs.code_plan_and_change.get(filename="1.json"),
+        code_doc=Document(filename="game.py", content="", root_path="src"),
+    )
+    coding_doc = Document(root_path="src", filename="game.py", content=ccontext.json())
+
+    action = WriteCode(i_context=coding_doc, context=context)
+    rsp = await action.run()
+    assert rsp
+    assert rsp.code_doc.content
+
+
+@pytest.mark.asyncio
+async def test_get_codes(context):
+    # Prerequisites
+    context = setup_inc_workdir(context, inc=True)
+    for filename in ["game.py", "ui.py"]:
+        await context.repo.with_src_path(context.src_workspace).srcs.save(
+            filename=filename, content=f"# {filename}\nnew code ..."
+        )
+        await context.repo.with_src_path(context.repo.old_workspace).srcs.save(
+            filename=filename, content=f"# {filename}\nlegacy code ..."
+        )
+
+    await context.repo.with_src_path(context.repo.old_workspace).srcs.save(
+        filename="gui.py", content="# gui.py\nlegacy code ..."
+    )
+    await context.repo.with_src_path(context.repo.old_workspace).srcs.save(
+        filename="main.py", content='# main.py\nif __name__ == "__main__":\n    main()'
+    )
+    task_doc = Document(filename="1.json", content=json.dumps(REFINED_TASK_JSON))
+
+    context.repo = context.repo.with_src_path(context.src_workspace)
+    # Ready to write gui.py
+    codes = await WriteCode.get_codes(task_doc=task_doc, exclude="gui.py", project_repo=context.repo)
+    codes_inc = await WriteCode.get_codes(task_doc=task_doc, exclude="gui.py", project_repo=context.repo, use_inc=True)
+
+    logger.info(codes)
+    logger.info(codes_inc)
+    assert codes
+    assert codes_inc
+
+
 if __name__ == "__main__":
     pytest.main([__file__, "-s"])

tests/metagpt/actions/test_write_code_plan_and_change_an.py

@@ -5,6 +5,8 @@
 @Author  : mannaandpoem
 @File    : test_write_code_plan_and_change_an.py
 """
+import json
+
 import pytest
 from openai._models import BaseModel
 
@@ -14,15 +16,21 @@ from metagpt.actions.write_code_plan_and_change_an import (
     REFINED_TEMPLATE,
     WriteCodePlanAndChange,
 )
+from metagpt.logs import logger
 from metagpt.schema import CodePlanAndChangeContext
+from metagpt.utils.common import CodeParser
 from tests.data.incremental_dev_project.mock import (
     CODE_PLAN_AND_CHANGE_SAMPLE,
     DESIGN_SAMPLE,
     NEW_REQUIREMENT_SAMPLE,
     REFINED_CODE_INPUT_SAMPLE,
     REFINED_CODE_SAMPLE,
-    TASKS_SAMPLE,
+    REFINED_DESIGN_JSON,
+    REFINED_PRD_JSON,
+    REFINED_TASK_JSON,
+    TASK_SAMPLE,
 )
+from tests.metagpt.actions.test_write_code import setup_inc_workdir
 
 
 def mock_code_plan_and_change():
@@ -30,27 +38,35 @@ def mock_code_plan_and_change():
 
 
 @pytest.mark.asyncio
-async def test_write_code_plan_and_change_an(mocker):
+async def test_write_code_plan_and_change_an(mocker, context, git_dir):
+    context = setup_inc_workdir(context, inc=True)
+    await context.repo.docs.prd.save(filename="2.json", content=json.dumps(REFINED_PRD_JSON))
+    await context.repo.docs.system_design.save(filename="2.json", content=json.dumps(REFINED_DESIGN_JSON))
+    await context.repo.docs.task.save(filename="2.json", content=json.dumps(REFINED_TASK_JSON))
+
+    await context.repo.with_src_path(context.repo.old_workspace).srcs.save(
+        filename="game.py", content=CodeParser.parse_code(block="", text=REFINED_CODE_INPUT_SAMPLE)
+    )
+
     root = ActionNode.from_children(
         "WriteCodePlanAndChange", [ActionNode(key="", expected_type=str, instruction="", example="")]
     )
     root.instruct_content = BaseModel()
     root.instruct_content.model_dump = mock_code_plan_and_change
-    mocker.patch("metagpt.actions.write_code_plan_and_change_an.WriteCodePlanAndChange.run", return_value=root)
-
-    requirement = "New requirement"
-    prd_filename = "prd.md"
-    design_filename = "design.md"
-    task_filename = "task.md"
-    code_plan_and_change_context = CodePlanAndChangeContext(
-        requirement=requirement,
-        prd_filename=prd_filename,
-        design_filename=design_filename,
-        task_filename=task_filename,
+    mocker.patch(
+        "metagpt.actions.write_code_plan_and_change_an.WRITE_CODE_PLAN_AND_CHANGE_NODE.fill", return_value=root
     )
-    node = await WriteCodePlanAndChange(i_context=code_plan_and_change_context).run()
 
-    assert "Code Plan And Change" in node.instruct_content.model_dump()
+    code_plan_and_change_context = CodePlanAndChangeContext(
+        requirement="New requirement",
+        prd_filename="2.json",
+        design_filename="2.json",
+        task_filename="2.json",
+    )
+    node = await WriteCodePlanAndChange(i_context=code_plan_and_change_context, context=context).run()
+
+    assert "Development Plan" in node.instruct_content.model_dump()
+    assert "Incremental Change" in node.instruct_content.model_dump()
 
 
 @pytest.mark.asyncio
@@ -60,7 +76,7 @@ async def test_refine_code(mocker):
         user_requirement=NEW_REQUIREMENT_SAMPLE,
         code_plan_and_change=CODE_PLAN_AND_CHANGE_SAMPLE,
         design=DESIGN_SAMPLE,
-        task=TASKS_SAMPLE,
+        task=TASK_SAMPLE,
         code=REFINED_CODE_INPUT_SAMPLE,
         logs="",
         feedback="",
@@ -69,3 +85,25 @@ async def test_refine_code(mocker):
     )
     code = await WriteCode().write_code(prompt=prompt)
     assert "def" in code
+
+
+@pytest.mark.asyncio
+async def test_get_old_code(context, git_dir):
+    context = setup_inc_workdir(context, inc=True)
+    await context.repo.with_src_path(context.repo.old_workspace).srcs.save(
+        filename="game.py", content=REFINED_CODE_INPUT_SAMPLE
+    )
+
+    code_plan_and_change_context = CodePlanAndChangeContext(
+        requirement="New requirement",
+        prd_filename="1.json",
+        design_filename="1.json",
+        task_filename="1.json",
+    )
+    action = WriteCodePlanAndChange(context=context, i_context=code_plan_and_change_context)
+
+    old_codes = await action.get_old_codes()
+    logger.info(old_codes)
+
+    assert "def" in old_codes
+    assert "class" in old_codes

tests/metagpt/actions/test_write_code_review.py

@@ -32,5 +32,28 @@ def add(a, b):
     print(f"输出内容: {captured.out}")
 
 
+@pytest.mark.asyncio
+async def test_write_code_review_inc(capfd, context):
+    context.src_workspace = context.repo.workdir / "srcs"
+    context.config.inc = True
+    code = """
+    def add(a, b):
+        return a + 
+    """
+    code_plan_and_change = """
+    def add(a, b):
+-        return a + 
++        return a + b
+    """
+    coding_context = CodingContext(
+        filename="math.py",
+        design_doc=Document(content="编写一个从a加b的函数，返回a+b"),
+        code_doc=Document(content=code),
+        code_plan_and_change_doc=Document(content=code_plan_and_change),
+    )
+
+    await WriteCodeReview(i_context=coding_context, context=context).run()
+
+
 if __name__ == "__main__":
     pytest.main([__file__, "-s"])

tests/metagpt/actions/test_write_prd.py

@@ -6,6 +6,7 @@
 @File    : test_write_prd.py
 @Modified By: mashenquan, 2023-11-1. According to Chapter 2.2.1 and 2.2.2 of RFC 116, replace `handle` with `run`.
 """
+
 import pytest
 
 from metagpt.actions import UserRequirement, WritePRD
@@ -15,6 +16,8 @@ from metagpt.roles.product_manager import ProductManager
 from metagpt.roles.role import RoleReactMode
 from metagpt.schema import Message
 from metagpt.utils.common import any_to_str
+from tests.data.incremental_dev_project.mock import NEW_REQUIREMENT_SAMPLE, PRD_SAMPLE
+from tests.metagpt.actions.test_write_code import setup_inc_workdir
 
 
 @pytest.mark.asyncio
@@ -34,5 +37,41 @@ async def test_write_prd(new_filename, context):
     assert product_manager.context.repo.docs.prd.changed_files
 
 
+@pytest.mark.asyncio
+async def test_write_prd_inc(new_filename, context, git_dir):
+    context = setup_inc_workdir(context, inc=True)
+    await context.repo.docs.prd.save("1.txt", PRD_SAMPLE)
+    await context.repo.docs.save(filename=REQUIREMENT_FILENAME, content=NEW_REQUIREMENT_SAMPLE)
+
+    action = WritePRD(context=context)
+    prd = await action.run(Message(content=NEW_REQUIREMENT_SAMPLE, instruct_content=None))
+    logger.info(NEW_REQUIREMENT_SAMPLE)
+    logger.info(prd)
+
+    # Assert the prd is not None or empty
+    assert prd is not None
+    assert prd.content != ""
+    assert "Refined Requirements" in prd.content
+
+
+@pytest.mark.asyncio
+async def test_fix_debug(new_filename, context, git_dir):
+    context.src_workspace = context.git_repo.workdir / context.git_repo.workdir.name
+
+    await context.repo.with_src_path(context.src_workspace).srcs.save(
+        filename="main.py", content='if __name__ == "__main__":\nmain()'
+    )
+    requirements = "Please fix the bug in the code."
+    await context.repo.docs.save(filename=REQUIREMENT_FILENAME, content=requirements)
+    action = WritePRD(context=context)
+
+    prd = await action.run(Message(content=requirements, instruct_content=None))
+    logger.info(prd)
+
+    # Assert the prd is not None or empty
+    assert prd is not None
+    assert prd.content != ""
+
+
 if __name__ == "__main__":
     pytest.main([__file__, "-s"])

tests/metagpt/provider/mock_llm_config.py

@@ -56,3 +56,7 @@ mock_llm_config_spark = LLMConfig(
 mock_llm_config_qianfan = LLMConfig(api_type="qianfan", access_key="xxx", secret_key="xxx", model="ERNIE-Bot-turbo")
 
 mock_llm_config_dashscope = LLMConfig(api_type="dashscope", api_key="xxx", model="qwen-max")
+
+mock_llm_config_anthropic = LLMConfig(
+    api_type="anthropic", api_key="xxx", base_url="https://api.anthropic.com", model="claude-3-opus-20240229"
+)

tests/metagpt/provider/req_resp_const.py

@@ -3,6 +3,14 @@
 # @Desc   : default request & response data for provider unittest
 
 
+from anthropic.types import (
+    ContentBlock,
+    ContentBlockDeltaEvent,
+    Message,
+    MessageStartEvent,
+    TextDelta,
+)
+from anthropic.types import Usage as AnthropicUsage
 from dashscope.api_entities.dashscope_response import (
     DashScopeAPIResponse,
     GenerationOutput,
@@ -130,6 +138,38 @@ def get_dashscope_response(name: str) -> GenerationResponse:
     )
 
 
+# For Anthropic
+def get_anthropic_response(name: str, stream: bool = False) -> Message:
+    if stream:
+        return [
+            MessageStartEvent(
+                message=Message(
+                    id="xxx",
+                    model=name,
+                    role="assistant",
+                    type="message",
+                    content=[ContentBlock(text="", type="text")],
+                    usage=AnthropicUsage(input_tokens=10, output_tokens=10),
+                ),
+                type="message_start",
+            ),
+            ContentBlockDeltaEvent(
+                index=0,
+                delta=TextDelta(text=resp_cont_tmpl.format(name=name), type="text_delta"),
+                type="content_block_delta",
+            ),
+        ]
+    else:
+        return Message(
+            id="xxx",
+            model=name,
+            role="assistant",
+            type="message",
+            content=[ContentBlock(text=resp_cont_tmpl.format(name=name), type="text")],
+            usage=AnthropicUsage(input_tokens=10, output_tokens=10),
+        )
+
+
 # For llm general chat functions call
 async def llm_general_chat_funcs_test(llm: BaseLLM, prompt: str, messages: list[dict], resp_cont: str):
     resp = await llm.aask(prompt, stream=False)

tests/metagpt/provider/test_anthropic_api.py

@@ -2,31 +2,45 @@
 # -*- coding: utf-8 -*-
 # @Desc   : the unittest of Claude2
 
-
 import pytest
 from anthropic.resources.completions import Completion
 
-from metagpt.provider.anthropic_api import Claude2
-from tests.metagpt.provider.mock_llm_config import mock_llm_config
-from tests.metagpt.provider.req_resp_const import prompt, resp_cont_tmpl
+from metagpt.provider.anthropic_api import AnthropicLLM
+from tests.metagpt.provider.mock_llm_config import mock_llm_config_anthropic
+from tests.metagpt.provider.req_resp_const import (
+    get_anthropic_response,
+    llm_general_chat_funcs_test,
+    messages,
+    prompt,
+    resp_cont_tmpl,
+)
 
-resp_cont = resp_cont_tmpl.format(name="Claude")
+name = "claude-3-opus-20240229"
+resp_cont = resp_cont_tmpl.format(name=name)
 
 
-def mock_anthropic_completions_create(self, model: str, prompt: str, max_tokens_to_sample: int) -> Completion:
-    return Completion(id="xx", completion=resp_cont, model="claude-2", stop_reason="stop_sequence", type="completion")
+async def mock_anthropic_messages_create(
+    self, messages: list[dict], model: str, stream: bool = True, max_tokens: int = None, system: str = None
+) -> Completion:
+    if stream:
 
+        async def aresp_iterator():
+            resps = get_anthropic_response(name, stream=True)
+            for resp in resps:
+                yield resp
 
-async def mock_anthropic_acompletions_create(self, model: str, prompt: str, max_tokens_to_sample: int) -> Completion:
-    return Completion(id="xx", completion=resp_cont, model="claude-2", stop_reason="stop_sequence", type="completion")
-
-
-def test_claude2_ask(mocker):
-    mocker.patch("anthropic.resources.completions.Completions.create", mock_anthropic_completions_create)
-    assert resp_cont == Claude2(mock_llm_config).ask(prompt)
+        return aresp_iterator()
+    else:
+        return get_anthropic_response(name)
 
 
 @pytest.mark.asyncio
-async def test_claude2_aask(mocker):
-    mocker.patch("anthropic.resources.completions.AsyncCompletions.create", mock_anthropic_acompletions_create)
-    assert resp_cont == await Claude2(mock_llm_config).aask(prompt)
+async def test_anthropic_acompletion(mocker):
+    mocker.patch("anthropic.resources.messages.AsyncMessages.create", mock_anthropic_messages_create)
+
+    anthropic_llm = AnthropicLLM(mock_llm_config_anthropic)
+
+    resp = await anthropic_llm.acompletion(messages)
+    assert resp.content[0].text == resp_cont
+
+    await llm_general_chat_funcs_test(anthropic_llm, prompt, messages, resp_cont)

tests/metagpt/provider/test_base_llm.py

@@ -27,9 +27,15 @@ class MockBaseLLM(BaseLLM):
     def completion(self, messages: list[dict], timeout=3):
         return get_part_chat_completion(name)
 
+    async def _achat_completion(self, messages: list[dict], timeout=3):
+        pass
+
     async def acompletion(self, messages: list[dict], timeout=3):
         return get_part_chat_completion(name)
 
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = 3) -> str:
+        pass
+
     async def acompletion_text(self, messages: list[dict], stream=False, timeout=3) -> str:
         return default_resp_cont
 

tests/metagpt/roles/di/test_data_interpreter.py

@@ -1,23 +1,23 @@
 import pytest
 
 from metagpt.logs import logger
-from metagpt.roles.mi.interpreter import Interpreter
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
 
 @pytest.mark.asyncio
 @pytest.mark.parametrize("auto_run", [(True), (False)])
 async def test_interpreter(mocker, auto_run):
-    mocker.patch("metagpt.actions.mi.execute_nb_code.ExecuteNbCode.run", return_value=("a successful run", True))
+    mocker.patch("metagpt.actions.di.execute_nb_code.ExecuteNbCode.run", return_value=("a successful run", True))
     mocker.patch("builtins.input", return_value="confirm")
 
     requirement = "Run data analysis on sklearn Iris dataset, include a plot"
     tools = []
 
-    mi = Interpreter(auto_run=auto_run, use_tools=True, tools=tools)
-    rsp = await mi.run(requirement)
+    di = DataInterpreter(auto_run=auto_run, use_tools=True, tools=tools)
+    rsp = await di.run(requirement)
     logger.info(rsp)
     assert len(rsp.content) > 0
 
-    finished_tasks = mi.planner.plan.get_finished_tasks()
+    finished_tasks = di.planner.plan.get_finished_tasks()
     assert len(finished_tasks) > 0
     assert len(finished_tasks[0].code) > 0  # check one task to see if code is recorded

tests/metagpt/roles/di/test_ml_engineer.py

@@ -1,11 +1,11 @@
 import pytest
 
-from metagpt.actions.mi.execute_nb_code import ExecuteNbCode
+from metagpt.actions.di.execute_nb_code import ExecuteNbCode
 from metagpt.logs import logger
-from metagpt.roles.mi.ml_engineer import MLEngineer
+from metagpt.roles.di.ml_engineer import MLEngineer
 from metagpt.schema import Message, Plan, Task
 from metagpt.tools.tool_type import ToolType
-from tests.metagpt.actions.mi.test_debug_code import CODE, DebugContext, ErrorStr
+from tests.metagpt.actions.di.test_debug_code import CODE, DebugContext, ErrorStr
 
 
 def test_mle_init():

tests/metagpt/utils/test_save_code.py

@@ -6,7 +6,7 @@
 import nbformat
 import pytest
 
-from metagpt.actions.mi.execute_nb_code import ExecuteNbCode
+from metagpt.actions.di.execute_nb_code import ExecuteNbCode
 from metagpt.utils.common import read_json_file
 from metagpt.utils.save_code import DATA_PATH, save_code_file
 

tests/mock/mock_llm.py

@@ -3,7 +3,7 @@ from typing import Optional, Union
 
 from metagpt.config2 import config
 from metagpt.configs.llm_config import LLMType
-from metagpt.logs import log_llm_stream, logger
+from metagpt.logs import logger
 from metagpt.provider.azure_openai_api import AzureOpenAILLM
 from metagpt.provider.openai_api import OpenAILLM
 from metagpt.schema import Message
@@ -24,17 +24,8 @@ class MockLLM(OriginalLLM):
     async def acompletion_text(self, messages: list[dict], stream=False, timeout=3) -> str:
         """Overwrite original acompletion_text to cancel retry"""
         if stream:
-            resp = self._achat_completion_stream(messages, timeout=timeout)
-
-            collected_messages = []
-            async for i in resp:
-                log_llm_stream(i)
-                collected_messages.append(i)
-
-            full_reply_content = "".join(collected_messages)
-            usage = self._calc_usage(messages, full_reply_content)
-            self._update_costs(usage)
-            return full_reply_content
+            resp = await self._achat_completion_stream(messages, timeout=timeout)
+            return resp
 
         rsp = await self._achat_completion(messages, timeout=timeout)
         return self.get_choice_text(rsp)