Merge pull request #900 from garylin2099/ci_dev

Unified naming

README.md

@@ -26,6 +26,8 @@ # 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.
+
 🚀 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.
 
@@ -60,7 +62,27 @@ ### Pip installation
 
 ```bash
 pip install metagpt
-metagpt --init-config  # create ~/.metagpt/config2.yaml, modify it to your own config
+# https://docs.deepwisdom.ai/main/en/guide/get_started/configuration.html
+metagpt --init-config  # it will create ~/.metagpt/config2.yaml, just modify it to your needs
+```
+
+### Configuration
+
+You can configure `~/.metagpt/config2.yaml` according to the [example](https://github.com/geekan/MetaGPT/blob/main/config/config2.example.yaml) and [doc](https://docs.deepwisdom.ai/main/en/guide/get_started/configuration.html):
+
+```yaml
+llm:
+  api_type: "openai"  # or azure / ollama / open_llm etc. Check LLMType for more options
+  model: "gpt-4-turbo-preview"  # or gpt-3.5-turbo-1106 / gpt-4-1106-preview
+  base_url: "https://api.openai.com/v1"  # or forward url / other llm url
+  api_key: "YOUR_API_KEY"
+```
+
+### Usage
+
+After installation, you can use it as CLI
+
+```bash
 metagpt "Create a 2048 game"  # this will create a repo in ./workspace
 ```
 
@@ -73,27 +95,7 @@ ### Pip installation
 ```
 
 detail installation please refer to [cli_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-stable-version)
-
-### Docker installation
-> Note: In the Windows, you need to replace "/opt/metagpt" with a directory that Docker has permission to create, such as "D:\Users\x\metagpt"
-
-```bash
-# Step 1: Download metagpt official image and prepare config2.yaml
-docker pull metagpt/metagpt:latest
-mkdir -p /opt/metagpt/{config,workspace}
-docker run --rm metagpt/metagpt:latest cat /app/metagpt/config/config2.yaml > /opt/metagpt/config/config2.yaml
-vim /opt/metagpt/config/config2.yaml # Change the config
-
-# Step 2: Run metagpt demo with container
-docker run --rm \
-    --privileged \
-    -v /opt/metagpt/config/config2.yaml:/app/metagpt/config/config2.yaml \
-    -v /opt/metagpt/workspace:/app/metagpt/workspace \
-    metagpt/metagpt:latest \
-    metagpt "Create a 2048 game"
-```
-
-detail installation please refer to [docker_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-with-docker)
+ or [docker_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-with-docker)
 
 ### QuickStart & Demo Video
 - Try it on [MetaGPT Huggingface Space](https://huggingface.co/spaces/deepwisdom/MetaGPT)

config/config2.example.yaml

@@ -1,10 +1,12 @@
 llm:
-  api_type: "openai"  # or azure / ollama etc.
+  api_type: "openai"  # or azure / ollama / open_llm etc. Check LLMType for more options
   base_url: "YOUR_BASE_URL"
   api_key: "YOUR_API_KEY"
   model: "gpt-4-turbo-preview"  # or gpt-3.5-turbo-1106 / gpt-4-1106-preview
+  repair_llm_output: true  # when the output is not a valid json, try to repair it
+  proxy: "YOUR_PROXY"  # for LLM API requests
 
-proxy: "YOUR_PROXY"
+proxy: "YOUR_PROXY"  # for tools like requests, playwright, selenium, etc.
 
 search:
   api_type: "google"
@@ -41,5 +43,3 @@ iflytek_api_key: "YOUR_API_KEY"
 iflytek_api_secret: "YOUR_API_SECRET"
 
 metagpt_tti_url: "YOUR_MODEL_URL"
-
-repair_llm_output: true

config/config2.yaml

@@ -1,3 +1,7 @@
+# Full Example: https://github.com/geekan/MetaGPT/blob/main/config/config2.example.yaml
+# Reflected Code: https://github.com/geekan/MetaGPT/blob/main/metagpt/config2.py
 llm:
-  api_key: "YOUR_API_KEY"
-  model: "gpt-4-turbo-preview"  # or gpt-3.5-turbo-1106 / gpt-4-1106-preview
+  api_type: "openai"  # or azure / ollama / open_llm etc. Check LLMType for more options
+  model: "gpt-4-turbo-preview"  # or gpt-3.5-turbo-1106 / gpt-4-1106-preview
+  base_url: "https://api.openai.com/v1"  # or forward url / other llm url
+  api_key: "YOUR_API_KEY"

docs/ROADMAP.md

@@ -35,14 +35,14 @@ ### Tasks
 3. Strategies
    1. Support ReAct strategy (experimentation done with game agents)
    2. Support CoT strategy (experimentation done with game agents)
-   3. Support ToT strategy
+   3. ~~Support ToT strategy~~ (v0.6.0)
    4. Support Reflection strategy (experimentation done with game agents)
-   5. Support planning
+   5. ~~Support planning~~ (v0.7.0)
 4. Actions
    1. ~~Implementation: Search~~ (v0.2.1)
    2. Implementation: Knowledge search, supporting 10+ data formats
-   3. Implementation: Data EDA (expected v0.7.0)
-   4. Implementation: Review & Revise (expected v0.7.0)
+   3. ~~Implementation: Data EDA~~ (v0.7.0)
+   4. ~~Implementation: Review & Revise~~ (v0.7.0)
    5. ~~Implementation: Add Document~~ (v0.5.0)
    6. ~~Implementation: Delete Document~~ (v0.5.0)
    7. Implementation: Self-training
@@ -50,7 +50,7 @@ ### Tasks
    9. Implementation: Generate reliable unit tests based on YAPI
    10. Implementation: Self-evaluation
    11. Implementation: AI Invocation
-   12. Implementation: Learning and using third-party standard libraries
+   12. ~~Implementation: Learning and using third-party standard libraries~~ (v0.7.0)
    13. Implementation: Data collection
    14. Implementation: AI training
    15. ~~Implementation: Run code~~ (v0.2.1)
@@ -63,14 +63,14 @@ ### Tasks
 7. Roles
    1. Perfect the action pool/skill pool for each role
    2. E-commerce seller
-   3. Data analyst (expected v0.7.0)
+   3. ~~Data analyst~~ (v0.7.0)
    4. News observer
    5. ~~Institutional researcher~~ (v0.2.1)
 8. Evaluation
    1. Support an evaluation on a game dataset (experimentation done with game agents)
    2. Reproduce papers, implement full skill acquisition for a single game role, achieving SOTA results (experimentation done with game agents)
-   3. Support an evaluation on a math dataset (expected v0.7.0)
-   4. Reproduce papers, achieving SOTA results for current mathematical problem solving process
+   3. Support an evaluation on a math dataset (expected v0.8.0)
+   4. Reproduce papers, achieving SOTA results for current mathematical problem solving process (expected v0.8.0)
 9. LLM
    1. Support Claude underlying API
    2. ~~Support Azure asynchronous API~~

docs/scripts/coverage.sh

@@ -1 +1 @@
-coverage run --source ./metagpt -m pytest --durations=0 --timeout=100 && coverage report -m && coverage html && open htmlcov/index.html
+coverage run --source ./metagpt -m pytest -n 8 --durations=0 --timeout=100 && coverage report -m && coverage html && open htmlcov/index.html

examples/ci/README.md

@@ -1,18 +0,0 @@
-# Code Interpreter (CI)
-
-## What is CodeInterpreter
-CodeInterpreter 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/code_interpreter/ci_intro.html) for detailed explanation.

examples/mi/README.md

@@ -0,0 +1,18 @@
+# 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.

examples/mi/crawl_webpage.py

@@ -5,15 +5,15 @@
 @File    :   crawl_webpage.py
 """
 
-from metagpt.roles.ci.code_interpreter import CodeInterpreter
+from metagpt.roles.mi.interpreter import Interpreter
 
 
 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*"""
-    ci = CodeInterpreter(goal=prompt, use_tools=True)
+    mi = Interpreter(use_tools=True)
 
-    await ci.run(prompt)
+    await mi.run(prompt)
 
 
 if __name__ == "__main__":

examples/mi/data_visualization.py

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

examples/mi/email_summary.py

@@ -6,7 +6,7 @@
 """
 import os
 
-from metagpt.roles.ci.code_interpreter import CodeInterpreter
+from metagpt.roles.mi.interpreter import Interpreter
 
 
 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."""
 
-    ci = CodeInterpreter(use_tools=True)
+    mi = Interpreter(use_tools=True)
 
-    await ci.run(prompt)
+    await mi.run(prompt)
 
 
 if __name__ == "__main__":

examples/mi/imitate_webpage.py

@@ -5,7 +5,7 @@
 @Author  : mannaandpoem
 @File    : imitate_webpage.py
 """
-from metagpt.roles.ci.code_interpreter import CodeInterpreter
+from metagpt.roles.mi.interpreter import Interpreter
 
 
 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."""
-    ci = CodeInterpreter(use_tools=True)
+    mi = Interpreter(use_tools=True)
 
-    await ci.run(prompt)
+    await mi.run(prompt)
 
 
 if __name__ == "__main__":

examples/mi/machine_learning.py

@@ -1,11 +1,11 @@
 import asyncio
 
-from metagpt.roles.ci.code_interpreter import CodeInterpreter
+from metagpt.roles.mi.interpreter import Interpreter
 
 
 async def main(requirement: str):
-    role = CodeInterpreter(auto_run=True, use_tools=False)
-    await role.run(requirement)
+    mi = Interpreter(auto_run=True, use_tools=False)
+    await mi.run(requirement)
 
 
 if __name__ == "__main__":

examples/mi/ml_engineer_with_tools.py

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

examples/mi/ocr_receipt.py

@@ -1,16 +1,16 @@
-from metagpt.roles.ci.code_interpreter import CodeInterpreter
+from metagpt.roles.mi.interpreter import Interpreter
 
 
 async def main():
     # Notice: pip install metagpt[ocr] before using this example
     image_path = "image.jpg"
     language = "English"
-    requirement = f"""This is a {language} invoice image.
+    requirement = f"""This is a {language} receipt image.
     Your goal is to perform OCR on images using PaddleOCR, then extract the total amount from ocr text results, and finally save as table. Image path: {image_path}. 
     NOTE: The environments for Paddle and PaddleOCR are all ready and has been fully installed."""
-    ci = CodeInterpreter()
+    mi = Interpreter()
 
-    await ci.run(requirement)
+    await mi.run(requirement)
 
 
 if __name__ == "__main__":

examples/mi/rm_image_background.py

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

examples/mi/sd_tool_usage.py

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

examples/mi/solve_math_problems.py

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

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.ci.execute_nb_code import ExecuteNbCode
-from metagpt.actions.ci.write_analysis_code import WriteCodeWithoutTools, WriteCodeWithTools
-from metagpt.actions.ci.write_plan import WritePlan
+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
 
 
 class ActionType(Enum):

metagpt/actions/mi/debug_code.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from metagpt.actions.ci.write_analysis_code import BaseWriteAnalysisCode
+from metagpt.actions.mi.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/mi/ml_action.py

@@ -3,14 +3,14 @@ from __future__ import annotations
 from typing import Tuple
 
 from metagpt.actions import Action
-from metagpt.actions.ci.write_analysis_code import WriteCodeWithTools
-from metagpt.prompts.ci.ml_action import (
+from metagpt.actions.mi.write_analysis_code import WriteCodeWithTools
+from metagpt.prompts.mi.ml_action import (
     ML_GENERATE_CODE_PROMPT,
     ML_TOOL_USAGE_PROMPT,
     PRINT_DATA_COLUMNS,
     UPDATE_DATA_COLUMNS,
 )
-from metagpt.prompts.ci.write_analysis_code import CODE_GENERATOR_WITH_TOOLS
+from metagpt.prompts.mi.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/mi/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.ci.write_analysis_code import (
+from metagpt.prompts.mi.write_analysis_code import (
     CODE_GENERATOR_WITH_TOOLS,
     SELECT_FUNCTION_TOOLS,
     TOOL_RECOMMENDATION_PROMPT,

metagpt/actions/mi/write_plan.py

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

metagpt/roles/mi/interpreter.py

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

metagpt/roles/mi/ml_engineer.py

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

metagpt/strategy/planner.py

@@ -4,8 +4,8 @@ import json
 
 from pydantic import BaseModel, Field
 
-from metagpt.actions.ci.ask_review import AskReview, ReviewConst
-from metagpt.actions.ci.write_plan import (
+from metagpt.actions.mi.ask_review import AskReview, ReviewConst
+from metagpt.actions.mi.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 CodeInterpreterSolver(BaseSolver):
-    """CodeInterpreterSolver: Write&Run code in the graph"""
+class InterpreterSolver(BaseSolver):
+    """InterpreterSolver: Write&Run code in the graph"""
 
     async def solve(self):
         raise NotImplementedError

tests/conftest.py

@@ -14,6 +14,7 @@ import re
 import uuid
 from typing import Callable
 
+import aiohttp.web
 import pytest
 
 from metagpt.const import DEFAULT_WORKSPACE_ROOT, TEST_DATA_PATH
@@ -171,9 +172,8 @@ def new_filename(mocker):
     yield mocker
 
 
-@pytest.fixture(scope="session")
-def search_rsp_cache():
-    rsp_cache_file_path = TEST_DATA_PATH / "search_rsp_cache.json"  # read repo-provided
+def _rsp_cache(name):
+    rsp_cache_file_path = TEST_DATA_PATH / f"{name}.json"  # read repo-provided
     if os.path.exists(rsp_cache_file_path):
         with open(rsp_cache_file_path, "r") as f1:
             rsp_cache_json = json.load(f1)
@@ -184,6 +184,16 @@ def search_rsp_cache():
         json.dump(rsp_cache_json, f2, indent=4, ensure_ascii=False)
 
 
+@pytest.fixture(scope="session")
+def search_rsp_cache():
+    yield from _rsp_cache("search_rsp_cache")
+
+
+@pytest.fixture(scope="session")
+def mermaid_rsp_cache():
+    yield from _rsp_cache("mermaid_rsp_cache")
+
+
 @pytest.fixture
 def aiohttp_mocker(mocker):
     MockResponse = type("MockResponse", (MockAioResponse,), {})
@@ -231,3 +241,32 @@ def search_engine_mocker(aiohttp_mocker, curl_cffi_mocker, httplib2_mocker, sear
     aiohttp_mocker.rsp_cache = httplib2_mocker.rsp_cache = curl_cffi_mocker.rsp_cache = search_rsp_cache
     aiohttp_mocker.check_funcs = httplib2_mocker.check_funcs = curl_cffi_mocker.check_funcs = check_funcs
     yield check_funcs
+
+
+@pytest.fixture
+def http_server():
+    async def handler(request):
+        return aiohttp.web.Response(
+            text="""<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8">
+            <title>MetaGPT</title></head><body><h1>MetaGPT</h1></body></html>""",
+            content_type="text/html",
+        )
+
+    async def start():
+        server = aiohttp.web.Server(handler)
+        runner = aiohttp.web.ServerRunner(server)
+        await runner.setup()
+        site = aiohttp.web.TCPSite(runner, "localhost", 0)
+        await site.start()
+        host, port = site._server.sockets[0].getsockname()
+        return site, f"http://{host}:{port}"
+
+    return start
+
+
+@pytest.fixture
+def mermaid_mocker(aiohttp_mocker, mermaid_rsp_cache):
+    check_funcs: dict[tuple[str, str], Callable[[dict], str]] = {}
+    aiohttp_mocker.rsp_cache = mermaid_rsp_cache
+    aiohttp_mocker.check_funcs = check_funcs
+    yield check_funcs

tests/metagpt/actions/mi/test_ask_review.py

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

tests/metagpt/actions/mi/test_debug_code.py

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

tests/metagpt/actions/mi/test_execute_nb_code.py

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

tests/metagpt/actions/mi/test_ml_action.py

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

tests/metagpt/actions/mi/test_write_analysis_code.py

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

tests/metagpt/actions/mi/test_write_plan.py

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

tests/metagpt/roles/mi/test_interpreter.py

@@ -1,23 +1,23 @@
 import pytest
 
 from metagpt.logs import logger
-from metagpt.roles.ci.code_interpreter import CodeInterpreter
+from metagpt.roles.mi.interpreter import Interpreter
 
 
 @pytest.mark.asyncio
 @pytest.mark.parametrize("auto_run", [(True), (False)])
-async def test_code_interpreter(mocker, auto_run):
-    mocker.patch("metagpt.actions.ci.execute_nb_code.ExecuteNbCode.run", return_value=("a successful run", True))
+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("builtins.input", return_value="confirm")
 
     requirement = "Run data analysis on sklearn Iris dataset, include a plot"
     tools = []
 
-    ci = CodeInterpreter(auto_run=auto_run, use_tools=True, tools=tools)
-    rsp = await ci.run(requirement)
+    mi = Interpreter(auto_run=auto_run, use_tools=True, tools=tools)
+    rsp = await mi.run(requirement)
     logger.info(rsp)
     assert len(rsp.content) > 0
 
-    finished_tasks = ci.planner.plan.get_finished_tasks()
+    finished_tasks = mi.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/mi/test_ml_engineer.py

@@ -1,16 +1,16 @@
 import pytest
 
-from metagpt.actions.ci.execute_nb_code import ExecuteNbCode
+from metagpt.actions.mi.execute_nb_code import ExecuteNbCode
 from metagpt.logs import logger
-from metagpt.roles.ci.ml_engineer import MLEngineer
+from metagpt.roles.mi.ml_engineer import MLEngineer
 from metagpt.schema import Message, Plan, Task
 from metagpt.tools.tool_type import ToolType
-from tests.metagpt.actions.ci.test_debug_code import CODE, DebugContext, ErrorStr
+from tests.metagpt.actions.mi.test_debug_code import CODE, DebugContext, ErrorStr
 
 
 def test_mle_init():
-    ci = MLEngineer(goal="test", auto_run=True, use_tools=True, tools=["tool1", "tool2"])
-    assert ci.tools == []
+    mle = MLEngineer(goal="test", auto_run=True, use_tools=True, tools=["tool1", "tool2"])
+    assert mle.tools == []
 
 
 MockPlan = Plan(

tests/metagpt/utils/test_mermaid.py

@@ -14,7 +14,7 @@ from metagpt.utils.mermaid import MMC1, mermaid_to_file
 
 @pytest.mark.asyncio
 @pytest.mark.parametrize("engine", ["nodejs", "ink"])  # TODO: playwright and pyppeteer
-async def test_mermaid(engine, context):
+async def test_mermaid(engine, context, mermaid_mocker):
     # nodejs prerequisites: npm install -g @mermaid-js/mermaid-cli
     # ink prerequisites: connected to internet
     # playwright prerequisites: playwright install --with-deps chromium

tests/metagpt/utils/test_save_code.py

@@ -6,7 +6,7 @@
 import nbformat
 import pytest
 
-from metagpt.actions.ci.execute_nb_code import ExecuteNbCode
+from metagpt.actions.mi.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_aiohttp.py

@@ -10,6 +10,7 @@ class MockAioResponse:
     check_funcs: dict[tuple[str, str], Callable[[dict], str]] = {}
     rsp_cache: dict[str, str] = {}
     name = "aiohttp"
+    status = 200
 
     def __init__(self, session, method, url, **kwargs) -> None:
         fn = self.check_funcs.get((method, url))
@@ -22,6 +23,7 @@ class MockAioResponse:
     async def __aenter__(self):
         if self.response:
             await self.response.__aenter__()
+            self.status = self.response.status
         elif self.mng:
             self.response = await self.mng.__aenter__()
         return self
@@ -41,6 +43,17 @@ class MockAioResponse:
         self.rsp_cache[self.key] = data
         return data
 
+    @property
+    def content(self):
+        return self
+
+    async def read(self):
+        if self.key in self.rsp_cache:
+            return eval(self.rsp_cache[self.key])
+        data = await self.response.content.read()
+        self.rsp_cache[self.key] = str(data)
+        return data
+
     def raise_for_status(self):
         if self.response:
             self.response.raise_for_status()