Merge branch 'main' of https://gitlab.deepwisdomai.com/pub/MetaGPT into mgx_intent

.github/ISSUE_TEMPLATE/show_me_the_bug.md

@@ -19,6 +19,7 @@
 - LLM type and model name:
 - System version:
 - Python version:
+- MetaGPT version or branch:
 
 <!-- Dependent packagess：the packages version cause the bug(like `pydantic 1.10.8`), installation method（like `pip install metagpt` or `pip install from source` or `run in docker`） -->
 

.github/workflows/build-package.yaml

@@ -1,8 +1,9 @@
 name: Build and upload python package
 
 on:
+  workflow_dispatch:
   release:
-    types: [created]
+    types: [created, published]
 
 jobs:
   deploy:

.gitignore

@@ -1,7 +1,7 @@
 ### Python template
 
 # Byte-compiled / optimized / DLL files
-__pycache__/
+__pycache__
 *.py[cod]
 *$py.class
 

MANIFEST.in

@@ -0,0 +1,3 @@
+recursive-include metagpt/ext/stanford_town/prompts *.txt
+recursive-include metagpt/ext/stanford_town/static_dirs *.csv
+recursive-include metagpt/ext/stanford_town/static_dirs *.json

README.md

@@ -26,7 +26,7 @@ # MetaGPT: The Multi-Agent Framework
 </p>
 
 ## News
-🚀 Mar. 14, 2024: Our Data Interpreter paper is on [arxiv](https://arxiv.org/abs/2402.18679). Check the [example](https://docs.deepwisdom.ai/main/en/DataInterpreter/) and [code](https://github.com/geekan/MetaGPT/tree/main/examples/di)!
+🚀 Mar. 14, 2024: Our **Data Interpreter** paper is on [arxiv](https://arxiv.org/abs/2402.18679). Check the [example](https://docs.deepwisdom.ai/main/en/DataInterpreter/) and [code](https://github.com/geekan/MetaGPT/tree/main/examples/di)!
 
 🚀 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.
 
@@ -55,9 +55,9 @@ ## Software Company as Multi-Agent System
 
 <p align="center">Software Company Multi-Agent Schematic (Gradually Implementing)</p>
 
-## Install
+## Get Started
 
-### Pip installation
+### Installation
 
 > Ensure that Python 3.9+ is installed on your system. You can check this by using: `python --version`.  
 > You can use conda like this: `conda create -n metagpt python=3.9 && conda activate metagpt`
@@ -68,6 +68,9 @@ # or `pip install --upgrade git+https://github.com/geekan/MetaGPT.git`
 # or `git clone https://github.com/geekan/MetaGPT && cd MetaGPT && pip install --upgrade -e .`
 ```
 
+For detailed installation guidance, please refer to [cli_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-stable-version)
+ or [docker_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-with-docker)
+
 ### Configuration
 
 You can init the config of MetaGPT by running the following command, or manually create `~/.metagpt/config2.yaml` file:
@@ -88,13 +91,13 @@ # Check https://docs.deepwisdom.ai/main/en/guide/get_started/configuration.html
 
 ### Usage
 
-After installation, you can use it as CLI
+After installation, you can use MetaGPT at CLI
 
 ```bash
 metagpt "Create a 2048 game"  # this will create a repo in ./workspace
 ```
 
-or you can use it as library
+or use it as library
 
 ```python
 from metagpt.software_company import generate_repo, ProjectRepo
@@ -102,47 +105,19 @@ ### Usage
 print(repo)  # it will print the repo structure with files
 ```
 
-detail installation please refer to [cli_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-stable-version)
- or [docker_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-with-docker)
+You can also use its [Data Interpreter](https://github.com/geekan/MetaGPT/tree/main/examples/di)
 
-### Docker installation
-<details><summary><strong>⏬ Step 1: Download metagpt image and prepare config2.yaml </strong><i>:: click to expand ::</i></summary>
-<div>
+```python
+import asyncio
+from metagpt.roles.di.data_interpreter import DataInterpreter
 
-```bash
-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
+async def main():
+    di = DataInterpreter()
+    await di.run("Run data analysis on sklearn Iris dataset, include a plot")
+
+asyncio.run(main())  # or await main() in a jupyter notebook setting
 ```
 
-</div>
-</details>
-
-<details><summary><strong>⏬ Step 2: Run metagpt container </strong><i>:: click to expand ::</i></summary>
-<div>
-
-```bash
-docker run --name metagpt -d \
-    --privileged \
-    -v /opt/metagpt/config/config2.yaml:/app/metagpt/config/config2.yaml \
-    -v /opt/metagpt/workspace:/app/metagpt/workspace \
-    metagpt/metagpt:latest
-```
-
-</div>
-</details>
-
-<details><summary><strong>⏬ Step 3: Use metagpt </strong><i>:: click to expand ::</i></summary>
-<div>
-
-```bash
-docker exec -it metagpt /bin/bash
-$ metagpt "Create a 2048 game"  # this will create a repo in ./workspace
-```
-
-</div>
-</details>
 
 ### QuickStart & Demo Video
 - Try it on [MetaGPT Huggingface Space](https://huggingface.co/spaces/deepwisdom/MetaGPT)
@@ -162,6 +137,7 @@ ## Tutorial
 - 🧑‍💻 Contribution
   - [Develop Roadmap](docs/ROADMAP.md)
 - 🔖 Use Cases
+  - [Data Interpreter](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/interpreter/intro.html)
   - [Debate](https://docs.deepwisdom.ai/main/en/guide/use_cases/multi_agent/debate.html)
   - [Researcher](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/researcher.html)
   - [Recepit Assistant](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/receipt_assistant.html)

config/config2.example.yaml

@@ -4,6 +4,7 @@ llm:
   api_key: "YOUR_API_KEY"
   model: "gpt-4-turbo-preview"  # or gpt-3.5-turbo-1106 / gpt-4-1106-preview
   proxy: "YOUR_PROXY"  # for LLM API requests
+  # timeout: 600 # Optional. If set to 0, default value is 300.
   pricing_plan: "" # Optional. If invalid, it will be automatically filled in with the value of the `model`.
   # Azure-exclusive pricing plan mappings：
   # - gpt-3.5-turbo 4k: "gpt-3.5-turbo-1106"

examples/di/arxiv_reader.py

@@ -1,10 +1,5 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-"""
-@Time    : 2024/01/15
-@Author  : mannaandpoem
-@File    : imitate_webpage.py
-"""
 from metagpt.roles.di.data_interpreter import DataInterpreter
 
 

examples/di/custom_tool.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+@Time    : 2024/3/22 10:54
+@Author  : alexanderwu
+@File    : custom_tool.py
+"""
+
+from metagpt.roles.di.data_interpreter import DataInterpreter
+from metagpt.tools.tool_registry import register_tool
+
+
+@register_tool()
+def magic_function(arg1: str, arg2: int) -> dict:
+    """
+    The magic function that does something.
+
+    Args:
+        arg1 (str): ...
+        arg2 (int): ...
+
+    Returns:
+        dict: ...
+    """
+    return {"arg1": arg1 * 3, "arg2": arg2 * 5}
+
+
+async def main():
+    di = DataInterpreter(tools=["magic_function"])
+    await di.run("Just call the magic function with arg1 'A' and arg2 2. Tell me the result.")
+
+
+if __name__ == "__main__":
+    import asyncio
+
+    asyncio.run(main())

examples/di/data_visualization.py

@@ -1,14 +1,17 @@
 import asyncio
 
+from metagpt.logs import logger
 from metagpt.roles.di.data_interpreter import DataInterpreter
+from metagpt.utils.recovery_util import save_history
 
 
 async def main(requirement: str = ""):
     di = DataInterpreter()
-    await di.run(requirement)
+    rsp = await di.run(requirement)
+    logger.info(rsp)
+    save_history(role=di)
 
 
 if __name__ == "__main__":
     requirement = "Run data analysis on sklearn Iris dataset, include a plot"
-
     asyncio.run(main(requirement))

examples/rag_pipeline.py

@@ -11,9 +11,13 @@ from metagpt.rag.schema import (
     BM25RetrieverConfig,
     ChromaIndexConfig,
     ChromaRetrieverConfig,
+    ElasticsearchIndexConfig,
+    ElasticsearchRetrieverConfig,
+    ElasticsearchStoreConfig,
     FAISSRetrieverConfig,
     LLMRankerConfig,
 )
+from metagpt.utils.exceptions import handle_exception
 
 DOC_PATH = EXAMPLE_DATA_PATH / "rag/writer.txt"
 QUESTION = "What are key qualities to be a good writer?"
@@ -39,12 +43,22 @@ class Player(BaseModel):
 class RAGExample:
     """Show how to use RAG."""
 
-    def __init__(self):
-        self.engine = SimpleEngine.from_docs(
-            input_files=[DOC_PATH],
-            retriever_configs=[FAISSRetrieverConfig(), BM25RetrieverConfig()],
-            ranker_configs=[LLMRankerConfig()],
-        )
+    def __init__(self, engine: SimpleEngine = None):
+        self._engine = engine
+
+    @property
+    def engine(self):
+        if not self._engine:
+            self._engine = SimpleEngine.from_docs(
+                input_files=[DOC_PATH],
+                retriever_configs=[FAISSRetrieverConfig(), BM25RetrieverConfig()],
+                ranker_configs=[LLMRankerConfig()],
+            )
+        return self._engine
+
+    @engine.setter
+    def engine(self, value: SimpleEngine):
+        self._engine = value
 
     async def run_pipeline(self, question=QUESTION, print_title=True):
         """This example run rag pipeline, use faiss&bm25 retriever and llm ranker, will print something like:
@@ -97,6 +111,7 @@ class RAGExample:
         self.engine.add_docs([travel_filepath])
         await self.run_pipeline(question=travel_question, print_title=False)
 
+    @handle_exception
     async def add_objects(self, print_title=True):
         """This example show how to add objects.
 
@@ -154,20 +169,41 @@ class RAGExample:
         """
         self._print_title("Init And Query ChromaDB")
 
-        # save index
+        # 1. save index
         output_dir = DATA_PATH / "rag"
         SimpleEngine.from_docs(
             input_files=[TRAVEL_DOC_PATH],
             retriever_configs=[ChromaRetrieverConfig(persist_path=output_dir)],
         )
 
-        # load index
-        engine = SimpleEngine.from_index(
-            index_config=ChromaIndexConfig(persist_path=output_dir),
+        # 2. load index
+        engine = SimpleEngine.from_index(index_config=ChromaIndexConfig(persist_path=output_dir))
+
+        # 3. query
+        answer = await engine.aquery(TRAVEL_QUESTION)
+        self._print_query_result(answer)
+
+    @handle_exception
+    async def init_and_query_es(self):
+        """This example show how to use es. how to save and load index. will print something like:
+
+        Query Result:
+        Bob likes traveling.
+        """
+        self._print_title("Init And Query Elasticsearch")
+
+        # 1. create es index and save docs
+        store_config = ElasticsearchStoreConfig(index_name="travel", es_url="http://127.0.0.1:9200")
+        engine = SimpleEngine.from_docs(
+            input_files=[TRAVEL_DOC_PATH],
+            retriever_configs=[ElasticsearchRetrieverConfig(store_config=store_config)],
         )
 
-        # query
-        answer = engine.query(TRAVEL_QUESTION)
+        # 2. load index
+        engine = SimpleEngine.from_index(index_config=ElasticsearchIndexConfig(store_config=store_config))
+
+        # 3. query
+        answer = await engine.aquery(TRAVEL_QUESTION)
         self._print_query_result(answer)
 
     @staticmethod
@@ -205,6 +241,7 @@ async def main():
     await e.add_objects()
     await e.init_objects()
     await e.init_and_query_chromadb()
+    await e.init_and_query_es()
 
 
 if __name__ == "__main__":

examples/search_with_specific_engine.py

@@ -13,7 +13,7 @@ async def main():
     question = "What are the most interesting human facts?"
 
     search = Config.default().search
-    kwargs = {"api_key": search.api_key, "cse_id": search.cse_id, "proxy": None}
+    kwargs = search.model_dump()
     await Searcher(search_engine=SearchEngine(engine=search.api_type, **kwargs)).run(question)
 
 

examples/stanford_town/run_st_game.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   : entry of Stanford Town(ST/st) game
+
+import asyncio
+from typing import Optional
+
+import fire
+
+from metagpt.ext.stanford_town.roles.st_role import STRole
+from metagpt.ext.stanford_town.stanford_town import StanfordTown
+from metagpt.ext.stanford_town.utils.const import STORAGE_PATH
+from metagpt.ext.stanford_town.utils.mg_ga_transform import (
+    get_reverie_meta,
+    write_curr_sim_code,
+    write_curr_step,
+)
+from metagpt.ext.stanford_town.utils.utils import copy_folder
+from metagpt.logs import logger
+
+
+async def startup(
+    idea: str, fork_sim_code: str, sim_code: str, temp_storage_path: str, investment: float = 30.0, n_round: int = 500
+):
+    town = StanfordTown()
+    logger.info("StanfordTown init environment")
+
+    # copy `storage/{fork_sim_code}` to `storage/{sim_code}`
+    copy_folder(str(STORAGE_PATH.joinpath(fork_sim_code)), str(STORAGE_PATH.joinpath(sim_code)))
+
+    # get role names from `storage/{simulation_name}/reverie/meta.json` and then init roles
+    reverie_meta = get_reverie_meta(fork_sim_code)
+    roles = []
+    sim_path = STORAGE_PATH.joinpath(sim_code)
+    sim_path.mkdir(exist_ok=True)
+    for idx, role_name in enumerate(reverie_meta["persona_names"]):
+        has_inner_voice = True if idx == 0 else False
+        role = STRole(
+            name=role_name,
+            profile=role_name,
+            sim_code=sim_code,
+            step=reverie_meta.get("step", 0),
+            start_time=reverie_meta.get("start_date"),
+            curr_time=reverie_meta.get("curr_time"),
+            sec_per_step=reverie_meta.get("sec_per_step"),
+            has_inner_voice=has_inner_voice,
+        )
+        roles.append(role)
+
+    # init temp_storage
+    write_curr_sim_code({"sim_code": sim_code}, temp_storage_path)
+    write_curr_step({"step": reverie_meta.get("step", 0)}, temp_storage_path)
+
+    await town.hire(roles)
+
+    town.invest(investment)
+    town.run_project(idea)
+
+    await town.run(n_round)
+
+
+def main(
+    idea: str,
+    fork_sim_code: str,
+    sim_code: str,
+    temp_storage_path: Optional[str] = None,
+    investment: float = 30.0,
+    n_round: int = 500,
+):
+    """
+    Args:
+        idea: idea works as an `inner voice` to the first agent.
+        fork_sim_code: old simulation name to start with, choose one inside `generative_agents/environment/frontend_server/storage/`
+        sim_code: new simulation name to save simulation result
+        temp_storage_path: generative_agents temp_storage path inside `environment/frontend_server` to interact.
+        investment: the investment of running agents
+        n_round: rounds to run agents
+    """
+
+    asyncio.run(
+        startup(
+            idea=idea,
+            fork_sim_code=fork_sim_code,
+            sim_code=sim_code,
+            temp_storage_path=temp_storage_path,
+            investment=investment,
+            n_round=n_round,
+        )
+    )
+
+
+if __name__ == "__main__":
+    fire.Fire(main)

examples/stanford_town/storage/.gitignore

@@ -0,0 +1,4 @@
+# path to store simulation data
+test_*
+unittest*
+July*

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/environment/0.json

@@ -0,0 +1,26 @@
+{
+  "Isabella Rodriguez": {
+    "maze": "the_ville",
+    "x": 72,
+    "y": 14
+  },
+  "Klaus Mueller": {
+    "maze": "the_ville",
+    "x": 126,
+    "y": 46
+  },
+  "Maria Lopez": {
+    "maze": "the_ville",
+    "x": 123,
+    "y": 57
+  }
+}
+
+
+
+
+
+
+
+
+

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Isabella Rodriguez/bootstrap_memory/associative_memory/embeddings.json

@@ -0,0 +1 @@
+{}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Isabella Rodriguez/bootstrap_memory/associative_memory/kw_strength.json

@@ -0,0 +1,2 @@
+{"kw_strength_event": {},
+ "kw_strength_thought": {}}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Isabella Rodriguez/bootstrap_memory/associative_memory/nodes.json

@@ -0,0 +1 @@
+{}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Isabella Rodriguez/bootstrap_memory/scratch.json

@@ -0,0 +1,51 @@
+{
+  "vision_r": 8, 
+  "att_bandwidth": 8, 
+  "retention": 8, 
+  "curr_time": null, 
+  "curr_tile": null, 
+  "daily_plan_req": "Isabella Rodriguez opens Hobbs Cafe at 8am everyday, and works at the counter until 8pm, at which point she closes the cafe.", 
+  "name": "Isabella Rodriguez", 
+  "first_name": "Isabella", 
+  "last_name": "Rodriguez", 
+  "age": 34, 
+  "innate": "friendly, outgoing, hospitable", 
+  "learned": "Isabella Rodriguez is a cafe owner of Hobbs Cafe who loves to make people feel welcome. She is always looking for ways to make the cafe a place where people can come to relax and enjoy themselves.", 
+  "currently": "Isabella Rodriguez is planning on having a Valentine's Day party at Hobbs Cafe with her customers on February 14th, 2023 at 5pm. She is gathering party material, and is telling everyone to join the party at Hobbs Cafe on February 14th, 2023, from 5pm to 7pm.", 
+  "lifestyle": "Isabella Rodriguez goes to bed around 11pm, awakes up around 6am.", 
+  "living_area": "the Ville:Isabella Rodriguez's apartment:main room",
+  "concept_forget": 100,
+  "daily_reflection_time": 180,
+  "daily_reflection_size": 5,
+  "overlap_reflect_th": 4,
+  "kw_strg_event_reflect_th": 10, 
+  "kw_strg_thought_reflect_th": 9, 
+
+  "recency_w": 1,
+  "relevance_w": 1,
+  "importance_w": 1,
+  "recency_decay": 0.995,
+  "importance_trigger_max": 150,
+  "importance_trigger_curr": 150,
+  "importance_ele_n": 0, 
+  "thought_count": 5, 
+
+  "daily_req": [], 
+  "f_daily_schedule": [],
+  "f_daily_schedule_hourly_org": [],
+  "act_address": null, 
+  "act_start_time": null, 
+  "act_duration": null, 
+  "act_description": null, 
+  "act_pronunciatio": null, 
+  "act_event": ["Isabella Rodriguez", null, null], 
+  "act_obj_description": null, 
+  "act_obj_pronunciatio": null, 
+  "act_obj_event": [null, null, null], 
+  "chatting_with": null, 
+  "chat": null,
+  "chatting_with_buffer": {}, 
+  "chatting_end_time": null,
+  "act_path_set": false, 
+  "planned_path": []
+}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Isabella Rodriguez/bootstrap_memory/spatial_memory.json

@@ -0,0 +1,66 @@
+{
+  "the Ville": {
+    "Hobbs Cafe": {
+      "cafe": [
+        "refrigerator",
+        "cafe customer seating",
+        "cooking area",
+        "kitchen sink",
+        "behind the cafe counter",
+        "piano"
+      ]
+    },
+    "Isabella Rodriguez's apartment": {
+      "main room": [
+        "bed",
+        "desk",
+        "refrigerator",
+        "closet",
+        "shelf"
+      ]
+    },
+    "The Rose and Crown Pub": {
+      "pub": [
+        "shelf",
+        "refrigerator",
+        "bar customer seating",
+        "behind the bar counter",
+        "kitchen sink",
+        "cooking area",
+        "microphone"
+      ]
+    },
+    "Harvey Oak Supply Store": {
+      "supply store": [
+        "supply store product shelf",
+        "behind the supply store counter",
+        "supply store counter"
+      ]
+    },
+    "The Willows Market and Pharmacy": {
+      "store": [
+        "behind the pharmacy counter",
+        "pharmacy store shelf",
+        "pharmacy store counter",
+        "grocery store shelf",
+        "behind the grocery counter",
+        "grocery store counter"
+      ]
+    },
+    "Dorm for Oak Hill College": {
+      "garden": [
+        "dorm garden"
+      ],
+      "common room": [
+        "common room sofa",
+        "pool table",
+        "common room table"
+      ]
+    },
+    "Johnson Park": {
+      "park": [
+        "park garden"
+      ]
+    }
+  }
+}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Klaus Mueller/bootstrap_memory/associative_memory/embeddings.json

@@ -0,0 +1 @@
+{}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Klaus Mueller/bootstrap_memory/associative_memory/kw_strength.json

@@ -0,0 +1,2 @@
+{"kw_strength_event": {},
+ "kw_strength_thought": {}}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Klaus Mueller/bootstrap_memory/associative_memory/nodes.json

@@ -0,0 +1 @@
+{}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Klaus Mueller/bootstrap_memory/scratch.json

@@ -0,0 +1,51 @@
+{
+  "vision_r": 8, 
+  "att_bandwidth": 8, 
+  "retention": 8, 
+  "curr_time": null, 
+  "curr_tile": null, 
+  "daily_plan_req": "Klaus Mueller goes to the library at Oak Hill College early in the morning, spends his days writing, and eats at Hobbs Cafe.", 
+  "name": "Klaus Mueller", 
+  "first_name": "Klaus", 
+  "last_name": "Mueller", 
+  "age": 20,
+  "innate": "kind, inquisitive, passionate", 
+  "learned": "Klaus Mueller is a student at Oak Hill College studying sociology. He is passionate about social justice and loves to explore different perspectives.", 
+  "currently": "Klaus Mueller is writing a research paper on the effects of gentrification in low-income communities.", 
+  "lifestyle": "Klaus Mueller goes to bed around 11pm, awakes up around 7am, eats dinner around 5pm.", 
+  "living_area": "the Ville:Dorm for Oak Hill College:Klaus Mueller's room",
+  "concept_forget": 100,
+  "daily_reflection_time": 180,
+  "daily_reflection_size": 5,
+  "overlap_reflect_th": 4,
+  "kw_strg_event_reflect_th": 10, 
+  "kw_strg_thought_reflect_th": 9, 
+
+  "recency_w": 1,
+  "relevance_w": 1,
+  "importance_w": 1,
+  "recency_decay": 0.99,
+  "importance_trigger_max": 150,
+  "importance_trigger_curr": 150,
+  "importance_ele_n": 0, 
+  "thought_count": 5, 
+  
+  "daily_req": [], 
+  "f_daily_schedule": [],
+  "f_daily_schedule_hourly_org": [],
+  "act_address": null, 
+  "act_start_time": null, 
+  "act_duration": null, 
+  "act_description": null, 
+  "act_pronunciatio": null, 
+  "act_event": ["Klaus Mueller", null, null], 
+  "act_obj_description": null, 
+  "act_obj_pronunciatio": null, 
+  "act_obj_event": [null, null, null], 
+  "chatting_with": null, 
+  "chat": null,
+  "chatting_with_buffer": {}, 
+  "chatting_end_time": null,
+  "act_path_set": false, 
+  "planned_path": []
+}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Klaus Mueller/bootstrap_memory/spatial_memory.json

@@ -0,0 +1,86 @@
+{
+  "the Ville": {
+    "Oak Hill College": {
+      "hallway": [],
+      "library": [
+        "library sofa",
+        "library table",
+        "bookshelf"
+      ],
+      "classroom": [
+        "blackboard",
+        "classroom podium",
+        "classroom student seating"
+      ]
+    },
+    "Dorm for Oak Hill College": {
+      "garden": [
+        "dorm garden"
+      ],
+      "Klaus Mueller's room": [
+        "bed",
+        "game console",
+        "closet",
+        "desk"
+      ],
+      "woman's bathroom": [
+        "toilet",
+        "shower",
+        "bathroom sink"
+      ],
+      "common room": [
+        "common room sofa",
+        "pool table",
+        "common room table"
+      ],
+      "man's bathroom": [
+        "shower",
+        "bathroom sink",
+        "toilet"
+      ]
+    },
+    "The Willows Market and Pharmacy": {
+      "store": [
+        "grocery store shelf",
+        "behind the grocery counter",
+        "grocery store counter",
+        "pharmacy store shelf",
+        "pharmacy store counter",
+        "behind the pharmacy counter"
+      ]
+    },
+    "Harvey Oak Supply Store": {
+      "supply store": [
+        "supply store product shelf",
+        "behind the supply store counter",
+        "supply store counter"
+      ]
+    },
+    "Johnson Park": {
+      "park": [
+        "park garden"
+      ]
+    },
+    "The Rose and Crown Pub": {
+      "pub": [
+        "shelf",
+        "refrigerator",
+        "bar customer seating",
+        "behind the bar counter",
+        "kitchen sink",
+        "cooking area",
+        "microphone"
+      ]
+    },
+    "Hobbs Cafe": {
+      "cafe": [
+        "refrigerator",
+        "cafe customer seating",
+        "cooking area",
+        "kitchen sink",
+        "behind the cafe counter",
+        "piano"
+      ]
+    }
+  }
+}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Maria Lopez/bootstrap_memory/associative_memory/embeddings.json

@@ -0,0 +1 @@
+{}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Maria Lopez/bootstrap_memory/associative_memory/kw_strength.json

@@ -0,0 +1,2 @@
+{"kw_strength_event": {},
+ "kw_strength_thought": {}}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Maria Lopez/bootstrap_memory/associative_memory/nodes.json

@@ -0,0 +1 @@
+{}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Maria Lopez/bootstrap_memory/scratch.json

@@ -0,0 +1,51 @@
+{
+  "vision_r": 8, 
+  "att_bandwidth": 8, 
+  "retention": 8, 
+  "curr_time": null, 
+  "curr_tile": null, 
+  "daily_plan_req": "Maria Lopez spends at least 3 hours a day Twitch streaming or gaming.", 
+  "name": "Maria Lopez", 
+  "first_name": "Maria", 
+  "last_name": "Lopez", 
+  "age": 21,
+  "innate": "energetic, enthusiastic, inquisitive", 
+  "learned": "Maria Lopez is a student at Oak Hill College studying physics and a part time Twitch game streamer who loves to connect with people and explore new ideas.", 
+  "currently": "Maria Lopez is working on her physics degree and streaming games on Twitch to make some extra money. She visits Hobbs Cafe for studying and eating just about everyday.", 
+  "lifestyle": "Maria Lopez goes to bed around 2am, awakes up around 9am, eats dinner around 6pm. She likes to hang out at Hobbs Cafe if it's before 6pm.", 
+  "living_area": "the Ville:Dorm for Oak Hill College:Maria Lopez's room",
+  "concept_forget": 100,
+  "daily_reflection_time": 180,
+  "daily_reflection_size": 5,
+  "overlap_reflect_th": 4,
+  "kw_strg_event_reflect_th": 10, 
+  "kw_strg_thought_reflect_th": 9, 
+
+  "recency_w": 1,
+  "relevance_w": 1,
+  "importance_w": 1,
+  "recency_decay": 0.99,
+  "importance_trigger_max": 150,
+  "importance_trigger_curr": 150,
+  "importance_ele_n": 0, 
+  "thought_count": 5, 
+  
+  "daily_req": [], 
+  "f_daily_schedule": [],
+  "f_daily_schedule_hourly_org": [],
+  "act_address": null, 
+  "act_start_time": null, 
+  "act_duration": null, 
+  "act_description": null, 
+  "act_pronunciatio": null, 
+  "act_event": ["Maria Lopez", null, null], 
+  "act_obj_description": null, 
+  "act_obj_pronunciatio": null, 
+  "act_obj_event": [null, null, null], 
+  "chatting_with": null, 
+  "chat": null,
+  "chatting_with_buffer": {}, 
+  "chatting_end_time": null,
+  "act_path_set": false, 
+  "planned_path": []
+}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/personas/Maria Lopez/bootstrap_memory/spatial_memory.json

@@ -0,0 +1,87 @@
+{
+  "the Ville": {
+    "Oak Hill College": {
+      "hallway": [],
+      "library": [
+        "library sofa",
+        "library table",
+        "bookshelf"
+      ],
+      "classroom": [
+        "blackboard",
+        "classroom podium",
+        "classroom student seating"
+      ]
+    },
+    "Dorm for Oak Hill College": {
+      "garden": [
+        "dorm garden"
+      ],
+      "Maria Lopez's room": [
+        "closet",
+        "desk",
+        "bed",
+        "computer",
+        "blackboard"
+      ],
+      "woman's bathroom": [
+        "toilet",
+        "shower",
+        "bathroom sink"
+      ],
+      "common room": [
+        "common room sofa",
+        "pool table",
+        "common room table"
+      ],
+      "man's bathroom": [
+        "shower",
+        "bathroom sink",
+        "toilet"
+      ]
+    },
+    "The Willows Market and Pharmacy": {
+      "store": [
+        "grocery store shelf",
+        "behind the grocery counter",
+        "grocery store counter",
+        "pharmacy store shelf",
+        "pharmacy store counter",
+        "behind the pharmacy counter"
+      ]
+    },
+    "Harvey Oak Supply Store": {
+      "supply store": [
+        "supply store product shelf",
+        "behind the supply store counter",
+        "supply store counter"
+      ]
+    },
+    "Johnson Park": {
+      "park": [
+        "park garden"
+      ]
+    },
+    "The Rose and Crown Pub": {
+      "pub": [
+        "shelf",
+        "refrigerator",
+        "bar customer seating",
+        "behind the bar counter",
+        "kitchen sink",
+        "cooking area",
+        "microphone"
+      ]
+    },
+    "Hobbs Cafe": {
+      "cafe": [
+        "refrigerator",
+        "cafe customer seating",
+        "cooking area",
+        "kitchen sink",
+        "behind the cafe counter",
+        "piano"
+      ]
+    }
+  }
+}

examples/stanford_town/storage/base_the_ville_isabella_maria_klaus/reverie/meta.json

@@ -0,0 +1,13 @@
+{
+  "fork_sim_code": "base_the_ville_isabella_maria_klaus",
+  "start_date": "February 13, 2023",
+  "curr_time": "February 13, 2023, 00:00:00",
+  "sec_per_step": 10,
+  "maze_name": "the_ville",
+  "persona_names": [
+    "Isabella Rodriguez", 
+    "Maria Lopez",
+    "Klaus Mueller"    
+  ],
+  "step": 0
+}

metagpt/actions/action_node.py

@@ -17,6 +17,7 @@ from pydantic import BaseModel, Field, create_model, model_validator
 from tenacity import retry, stop_after_attempt, wait_random_exponential
 
 from metagpt.actions.action_outcls_registry import register_action_outcls
+from metagpt.const import USE_CONFIG_TIMEOUT
 from metagpt.llm import BaseLLM
 from metagpt.logs import logger
 from metagpt.provider.postprocess.llm_output_postprocess import llm_output_postprocess
@@ -330,7 +331,7 @@ class ActionNode:
 
     def compile_to(self, i: Dict, schema, kv_sep) -> str:
         if schema == "json":
-            return json.dumps(i, indent=4)
+            return json.dumps(i, indent=4, ensure_ascii=False)
         elif schema == "markdown":
             return dict_to_markdown(i, kv_sep=kv_sep)
         else:
@@ -339,10 +340,7 @@ class ActionNode:
     def tagging(self, text, schema, tag="") -> str:
         if not tag:
             return text
-        if schema == "json":
-            return f"[{tag}]\n" + text + f"\n[/{tag}]"
-        else:  # markdown
-            return f"[{tag}]\n" + text + f"\n[/{tag}]"
+        return f"[{tag}]\n{text}\n[/{tag}]"
 
     def _compile_f(self, schema, mode, tag, format_func, kv_sep, exclude=None) -> str:
         nodes = self.to_dict(format_func=format_func, mode=mode, exclude=exclude)
@@ -374,7 +372,7 @@ class ActionNode:
             schema="markdown": 编译context, example(markdown), instruction(markdown), constraint, action
         """
         if schema == "raw":
-            return context + "\n\n## Actions\n" + LANGUAGE_CONSTRAINT + "\n" + self.instruction
+            return f"{context}\n\n## Actions\n{LANGUAGE_CONSTRAINT}\n{self.instruction}"
 
         ### 直接使用 pydantic BaseModel 生成 instruction 与 example，仅限 JSON
         # child_class = self._create_children_class()
@@ -416,7 +414,7 @@ class ActionNode:
         images: Optional[Union[str, list[str]]] = None,
         system_msgs: Optional[list[str]] = None,
         schema="markdown",  # compatible to original format
-        timeout=3,
+        timeout=USE_CONFIG_TIMEOUT,
     ) -> (str, BaseModel):
         """Use ActionOutput to wrap the output of aask"""
         content = await self.llm.aask(prompt, system_msgs, images=images, timeout=timeout)
@@ -448,7 +446,9 @@ class ActionNode:
     def set_context(self, context):
         self.set_recursive("context", context)
 
-    async def simple_fill(self, schema, mode, images: Optional[Union[str, list[str]]] = None, timeout=3, exclude=None):
+    async def simple_fill(
+        self, schema, mode, images: Optional[Union[str, list[str]]] = None, timeout=USE_CONFIG_TIMEOUT, exclude=None
+    ):
         prompt = self.compile(context=self.context, schema=schema, mode=mode, exclude=exclude)
 
         if schema != "raw":
@@ -473,7 +473,7 @@ class ActionNode:
         mode="auto",
         strgy="simple",
         images: Optional[Union[str, list[str]]] = None,
-        timeout=3,
+        timeout=USE_CONFIG_TIMEOUT,
         exclude=[],
     ):
         """Fill the node(s) with mode.

metagpt/actions/di/write_analysis_code.py

@@ -18,7 +18,7 @@ from metagpt.prompts.di.write_analysis_code import (
     STRUCTUAL_PROMPT,
 )
 from metagpt.schema import Message, Plan
-from metagpt.utils.common import CodeParser, process_message, remove_comments
+from metagpt.utils.common import CodeParser, remove_comments
 
 
 class WriteAnalysisCode(Action):
@@ -50,7 +50,7 @@ class WriteAnalysisCode(Action):
         )
 
         working_memory = working_memory or []
-        context = process_message([Message(content=structual_prompt, role="user")] + working_memory)
+        context = self.llm.format_msg([Message(content=structual_prompt, role="user")] + working_memory)
 
         # LLM call
         if use_reflection:

metagpt/configs/llm_config.py

@@ -10,6 +10,7 @@ from typing import Optional
 
 from pydantic import field_validator
 
+from metagpt.const import LLM_API_TIMEOUT
 from metagpt.utils.yaml_model import YamlModel
 
 
@@ -74,7 +75,7 @@ class LLMConfig(YamlModel):
     stream: bool = False
     logprobs: Optional[bool] = None  # https://cookbook.openai.com/examples/using_logprobs
     top_logprobs: Optional[int] = None
-    timeout: int = 60
+    timeout: int = 600
 
     # For Network
     proxy: Optional[str] = None
@@ -88,3 +89,8 @@ class LLMConfig(YamlModel):
         if v in ["", None, "YOUR_API_KEY"]:
             raise ValueError("Please set your API key in config2.yaml")
         return v
+
+    @field_validator("timeout")
+    @classmethod
+    def check_timeout(cls, v):
+        return v or LLM_API_TIMEOUT

metagpt/configs/search_config.py

@@ -7,6 +7,8 @@
 """
 from typing import Callable, Optional
 
+from pydantic import Field
+
 from metagpt.tools import SearchEngineType
 from metagpt.utils.yaml_model import YamlModel
 
@@ -18,3 +20,11 @@ class SearchConfig(YamlModel):
     api_key: str = ""
     cse_id: str = ""  # for google
     search_func: Optional[Callable] = None
+    params: dict = Field(
+        default_factory=lambda: {
+            "engine": "google",
+            "google_domain": "google.com",
+            "gl": "us",
+            "hl": "en",
+        }
+    )

metagpt/const.py

@@ -123,7 +123,6 @@ BASE64_FORMAT = "base64"
 
 # REDIS
 REDIS_KEY = "REDIS_KEY"
-LLM_API_TIMEOUT = 300
 
 # Message id
 IGNORED_MESSAGE_ID = "0"
@@ -132,3 +131,7 @@ IGNORED_MESSAGE_ID = "0"
 GENERALIZATION = "Generalize"
 COMPOSITION = "Composite"
 AGGREGATION = "Aggregate"
+
+# Timeout
+USE_CONFIG_TIMEOUT = 0  # Using llm.timeout configuration.
+LLM_API_TIMEOUT = 300

metagpt/environment/README.md

@@ -21,7 +21,7 @@ ## Usage
 from metagpt.environment.api.env_api import EnvAPIAbstract
 
 # get screenshot from ExtEnv
-screenshot_path: Path = env.observe(
+screenshot_path: Path = await env.observe(
             EnvAPIAbstract(
                 api_name="get_screenshot", kwargs={"ss_name": f"{round_count}_before", "local_save_dir": task_dir}
             )
@@ -34,5 +34,5 @@ # do a `tap` action on the screen
 ## TODO
 - add android app operation assistant under `examples/android_assistant`
 - migrate roles/actions of werewolf game from old version into current version
-- migrate roles/actions of mincraft game from old version into current version
+- migrate roles/actions of minecraft game from old version into current version
 - migrate roles/actions of stanford_town game from old version into current version

metagpt/environment/__init__.py

@@ -3,11 +3,10 @@
 # @Desc   :
 
 from metagpt.environment.base_env import Environment
-from metagpt.environment.android_env.android_env import AndroidEnv
-from metagpt.environment.mincraft_env.mincraft_env import MincraftExtEnv
-from metagpt.environment.werewolf_env.werewolf_env import WerewolfEnv
-from metagpt.environment.stanford_town_env.stanford_town_env import StanfordTownEnv
-from metagpt.environment.software_env.software_env import SoftwareEnv
+from metagpt.environment.android.android_env import AndroidEnv
+from metagpt.environment.werewolf.werewolf_env import WerewolfEnv
+from metagpt.environment.stanford_town.stanford_town_env import StanfordTownEnv
+from metagpt.environment.software.software_env import SoftwareEnv
 
 
-__all__ = ["AndroidEnv", "MincraftExtEnv", "WerewolfEnv", "StanfordTownEnv", "SoftwareEnv", "Environment"]
+__all__ = ["AndroidEnv", "WerewolfEnv", "StanfordTownEnv", "SoftwareEnv", "Environment"]

metagpt/environment/android/android_env.py

@@ -4,7 +4,7 @@
 
 from pydantic import Field
 
-from metagpt.environment.android_env.android_ext_env import AndroidExtEnv
+from metagpt.environment.android.android_ext_env import AndroidExtEnv
 from metagpt.environment.base_env import Environment
 
 

metagpt/environment/android/android_ext_env.py

@@ -8,8 +8,9 @@ from typing import Any, Optional
 
 from pydantic import Field
 
-from metagpt.environment.android_env.const import ADB_EXEC_FAIL
+from metagpt.environment.android.const import ADB_EXEC_FAIL
 from metagpt.environment.base_env import ExtEnv, mark_as_readable, mark_as_writeable
+from metagpt.environment.base_env_space import BaseEnvAction, BaseEnvObsParams
 
 
 class AndroidExtEnv(ExtEnv):
@@ -19,6 +20,20 @@ class AndroidExtEnv(ExtEnv):
     width: int = Field(default=720, description="device screen width")
     height: int = Field(default=1080, description="device screen height")
 
+    def reset(
+        self,
+        *,
+        seed: Optional[int] = None,
+        options: Optional[dict[str, Any]] = None,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        pass
+
+    def observe(self, obs_params: Optional[BaseEnvObsParams] = None) -> Any:
+        pass
+
+    def step(self, action: BaseEnvAction) -> tuple[dict[str, Any], float, bool, bool, dict[str, Any]]:
+        pass
+
     def __init__(self, **data: Any):
         super().__init__(**data)
         if data.get("device_id"):

metagpt/environment/base_env.py

@@ -3,9 +3,12 @@
 # @Desc   : base env of executing environment
 
 import asyncio
+from abc import abstractmethod
 from enum import Enum
 from typing import TYPE_CHECKING, Any, Dict, Iterable, Optional, Set, Union
 
+from gymnasium import spaces
+from gymnasium.core import ActType, ObsType
 from pydantic import BaseModel, ConfigDict, Field, SerializeAsAny, model_validator
 
 from metagpt.context import Context
@@ -14,6 +17,7 @@ from metagpt.environment.api.env_api import (
     ReadAPIRegistry,
     WriteAPIRegistry,
 )
+from metagpt.environment.base_env_space import BaseEnvAction, BaseEnvObsParams
 from metagpt.logs import logger
 from metagpt.schema import Message
 from metagpt.utils.common import get_function_schema, is_coroutine_func, is_send_to
@@ -26,7 +30,7 @@ class EnvType(Enum):
     ANDROID = "Android"
     GYM = "Gym"
     WEREWOLF = "Werewolf"
-    MINCRAFT = "Mincraft"
+    MINECRAFT = "Minecraft"
     STANFORDTOWN = "StanfordTown"
 
 
@@ -49,6 +53,11 @@ def mark_as_writeable(func):
 class ExtEnv(BaseModel):
     """External Env to integrate actual game environment"""
 
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    action_space: spaces.Space[ActType] = Field(default_factory=spaces.Space, exclude=True)
+    observation_space: spaces.Space[ObsType] = Field(default_factory=spaces.Space, exclude=True)
+
     def _check_api_exist(self, rw_api: Optional[str] = None):
         if not rw_api:
             raise ValueError(f"{rw_api} not exists")
@@ -61,39 +70,56 @@ class ExtEnv(BaseModel):
         else:
             return env_write_api_registry.get_apis()
 
-    async def observe(self, env_action: Union[str, EnvAPIAbstract]):
+    async def read_from_api(self, env_action: Union[str, EnvAPIAbstract]):
         """get observation from particular api of ExtEnv"""
         if isinstance(env_action, str):
-            read_api = env_read_api_registry.get(api_name=env_action)["func"]
-            self._check_api_exist(read_api)
-            if is_coroutine_func(read_api):
-                res = await read_api(self)
+            env_read_api = env_read_api_registry.get(api_name=env_action)["func"]
+            self._check_api_exist(env_read_api)
+            if is_coroutine_func(env_read_api):
+                res = await env_read_api(self)
             else:
-                res = read_api(self)
+                res = env_read_api(self)
         elif isinstance(env_action, EnvAPIAbstract):
-            read_api = env_read_api_registry.get(api_name=env_action.api_name)["func"]
-            self._check_api_exist(read_api)
-            if is_coroutine_func(read_api):
-                res = await read_api(self, *env_action.args, **env_action.kwargs)
+            env_read_api = env_read_api_registry.get(api_name=env_action.api_name)["func"]
+            self._check_api_exist(env_read_api)
+            if is_coroutine_func(env_read_api):
+                res = await env_read_api(self, *env_action.args, **env_action.kwargs)
             else:
-                res = read_api(self, *env_action.args, **env_action.kwargs)
+                res = env_read_api(self, *env_action.args, **env_action.kwargs)
         return res
 
-    async def step(self, env_action: Union[str, Message, EnvAPIAbstract, list[EnvAPIAbstract]]):
+    async def write_thru_api(self, env_action: Union[str, Message, EnvAPIAbstract, list[EnvAPIAbstract]]):
         """execute through particular api of ExtEnv"""
         res = None
         if isinstance(env_action, Message):
             self.publish_message(env_action)
         elif isinstance(env_action, EnvAPIAbstract):
-            write_api = env_write_api_registry.get(env_action.api_name)["func"]
-            self._check_api_exist(write_api)
-            if is_coroutine_func(write_api):
-                res = await write_api(self, *env_action.args, **env_action.kwargs)
+            env_write_api = env_write_api_registry.get(env_action.api_name)["func"]
+            self._check_api_exist(env_write_api)
+            if is_coroutine_func(env_write_api):
+                res = await env_write_api(self, *env_action.args, **env_action.kwargs)
             else:
-                res = write_api(self, *env_action.args, **env_action.kwargs)
+                res = env_write_api(self, *env_action.args, **env_action.kwargs)
 
         return res
 
+    @abstractmethod
+    def reset(
+        self,
+        *,
+        seed: Optional[int] = None,
+        options: Optional[dict[str, Any]] = None,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        """Implement this to get init observation"""
+
+    @abstractmethod
+    def observe(self, obs_params: Optional[BaseEnvObsParams] = None) -> Any:
+        """Implement this if you want to get partial observation from the env"""
+
+    @abstractmethod
+    def step(self, action: BaseEnvAction) -> tuple[dict[str, Any], float, bool, bool, dict[str, Any]]:
+        """Implement this to feed a action and then get new observation from the env"""
+
 
 class Environment(ExtEnv):
     """环境，承载一批角色，角色可以向环境发布消息，可以被其他角色观察到
@@ -108,6 +134,20 @@ class Environment(ExtEnv):
     history: str = ""  # For debug
     context: Context = Field(default_factory=Context, exclude=True)
 
+    def reset(
+        self,
+        *,
+        seed: Optional[int] = None,
+        options: Optional[dict[str, Any]] = None,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        pass
+
+    def observe(self, obs_params: Optional[BaseEnvObsParams] = None) -> Any:
+        pass
+
+    def step(self, action: BaseEnvAction) -> tuple[dict[str, Any], float, bool, bool, dict[str, Any]]:
+        pass
+
     @model_validator(mode="after")
     def init_roles(self):
         self.add_roles(self.roles.values())

metagpt/environment/base_env_space.py

@@ -0,0 +1,33 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   :
+
+from enum import IntEnum
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class BaseEnvActionType(IntEnum):
+    # # NONE = 0  # no action to run, just get observation
+    pass
+
+
+class BaseEnvAction(BaseModel):
+    """env action type and its related params of action functions/apis"""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    action_type: int = Field(default=0, description="action type")
+
+
+class BaseEnvObsType(IntEnum):
+    # # NONE = 0                     # get whole observation from env
+    pass
+
+
+class BaseEnvObsParams(BaseModel):
+    """observation params for different EnvObsType to get its observe result"""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    obs_type: int = Field(default=0, description="observation type")

metagpt/environment/minecraft/const.py

@@ -4,8 +4,8 @@
 
 from metagpt.const import METAGPT_ROOT
 
-# For Mincraft Game Agent
-MC_CKPT_DIR = METAGPT_ROOT / "data/mincraft/ckpt"
+# For Minecraft Game Agent
+MC_CKPT_DIR = METAGPT_ROOT / "data/minecraft/ckpt"
 MC_LOG_DIR = METAGPT_ROOT / "logs"
 MC_DEFAULT_WARMUP = {
     "context": 15,

metagpt/environment/minecraft/minecraft_env.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-# @Desc   : MG Mincraft Env
+# @Desc   : MG Minecraft Env
 #           refs to `voyager voyager.py`
 
 import json
@@ -8,19 +8,19 @@ import re
 import time
 from typing import Any, Iterable
 
+from llama_index.vector_stores.chroma import ChromaVectorStore
 from pydantic import ConfigDict, Field
 
 from metagpt.config2 import config as CONFIG
 from metagpt.environment.base_env import Environment
-from metagpt.environment.mincraft_env.const import MC_CKPT_DIR
-from metagpt.environment.mincraft_env.mincraft_ext_env import MincraftExtEnv
+from metagpt.environment.minecraft.const import MC_CKPT_DIR
+from metagpt.environment.minecraft.minecraft_ext_env import MinecraftExtEnv
 from metagpt.logs import logger
-from metagpt.rag.vector_stores.chroma import ChromaVectorStore
 from metagpt.utils.common import load_mc_skills_code, read_json_file, write_json_file
 
 
-class MincraftEnv(Environment, MincraftExtEnv):
-    """MincraftEnv, including shared memory of cache and information between roles"""
+class MinecraftEnv(Environment, MinecraftExtEnv):
+    """MinecraftEnv, including shared memory of cache and information between roles"""
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
@@ -282,7 +282,7 @@ class MincraftEnv(Environment, MincraftExtEnv):
                     position = event["status"]["position"]
                     blocks.append(block)
                     positions.append(position)
-            new_events = self.step(
+            new_events = self._step(
                 f"await givePlacedItemBack(bot, {json.dumps(blocks)}, {json.dumps(positions)})",
                 programs=self.programs,
             )
@@ -323,7 +323,7 @@ class MincraftEnv(Environment, MincraftExtEnv):
                 Exception: If there is an issue retrieving events.
         """
         try:
-            self.reset(
+            self._reset(
                 options={
                     "mode": "soft",
                     "wait_ticks": 20,
@@ -332,13 +332,13 @@ class MincraftEnv(Environment, MincraftExtEnv):
             # difficulty = "easy" if len(self.completed_tasks) > 15 else "peaceful"
             difficulty = "peaceful"
 
-            events = self.step("bot.chat(`/time set ${getNextTime()}`);\n" + f"bot.chat('/difficulty {difficulty}');")
+            events = self._step("bot.chat(`/time set ${getNextTime()}`);\n" + f"bot.chat('/difficulty {difficulty}');")
             self.update_event(events)
             return events
         except Exception as e:
             time.sleep(3)  # wait for mineflayer to exit
             # reset bot status here
-            events = self.reset(
+            events = self._reset(
                 options={
                     "mode": "hard",
                     "wait_ticks": 20,
@@ -365,7 +365,7 @@ class MincraftEnv(Environment, MincraftExtEnv):
                 Exception: If there is an issue retrieving events.
         """
         try:
-            events = self.step(
+            events = self._step(
                 code=self.code,
                 programs=self.programs,
             )
@@ -374,7 +374,7 @@ class MincraftEnv(Environment, MincraftExtEnv):
         except Exception as e:
             time.sleep(3)  # wait for mineflayer to exit
             # reset bot status here
-            events = self.reset(
+            events = self._reset(
                 options={
                     "mode": "hard",
                     "wait_ticks": 20,

metagpt/environment/minecraft/minecraft_ext_env.py

@@ -1,28 +1,29 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-# @Desc   : The Mincraft external environment to integrate with Mincraft game
+# @Desc   : The Minecraft external environment to integrate with Minecraft game
 #           refs to `voyager bridge.py`
 
 import json
 import time
-from typing import Optional
+from typing import Any, Optional
 
 import requests
 from pydantic import ConfigDict, Field, model_validator
 
 from metagpt.environment.base_env import ExtEnv, mark_as_writeable
-from metagpt.environment.mincraft_env.const import (
+from metagpt.environment.base_env_space import BaseEnvAction, BaseEnvObsParams
+from metagpt.environment.minecraft.const import (
     MC_CKPT_DIR,
     MC_CORE_INVENTORY_ITEMS,
     MC_CURRICULUM_OB,
     MC_DEFAULT_WARMUP,
     METAGPT_ROOT,
 )
-from metagpt.environment.mincraft_env.process_monitor import SubprocessMonitor
+from metagpt.environment.minecraft.process_monitor import SubprocessMonitor
 from metagpt.logs import logger
 
 
-class MincraftExtEnv(ExtEnv):
+class MinecraftExtEnv(ExtEnv):
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
     mc_port: Optional[int] = Field(default=None)
@@ -38,6 +39,20 @@ class MincraftExtEnv(ExtEnv):
     server_paused: bool = Field(default=False)
     warm_up: dict = Field(default=dict())
 
+    def reset(
+        self,
+        *,
+        seed: Optional[int] = None,
+        options: Optional[dict[str, Any]] = None,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        pass
+
+    def observe(self, obs_params: Optional[BaseEnvObsParams] = None) -> Any:
+        pass
+
+    def step(self, action: BaseEnvAction) -> tuple[dict[str, Any], float, bool, bool, dict[str, Any]]:
+        pass
+
     @property
     def server(self) -> str:
         return f"{self.server_host}:{self.server_port}"
@@ -48,7 +63,7 @@ class MincraftExtEnv(ExtEnv):
             self.mineflayer = SubprocessMonitor(
                 commands=[
                     "node",
-                    METAGPT_ROOT.joinpath("metagpt", "environment", "mincraft_env", "mineflayer", "index.js"),
+                    METAGPT_ROOT.joinpath("metagpt", "environment", "minecraft", "mineflayer", "index.js"),
                     str(self.server_port),
                 ],
                 name="mineflayer",
@@ -115,7 +130,7 @@ class MincraftExtEnv(ExtEnv):
             return res.json()
 
     @mark_as_writeable
-    def reset(self, *, seed=None, options=None) -> dict:
+    def _reset(self, *, seed=None, options=None) -> dict:
         if options is None:
             options = {}
         if options.get("inventory", {}) and options.get("mode", "hard") != "hard":
@@ -145,7 +160,7 @@ class MincraftExtEnv(ExtEnv):
         return json.loads(returned_data)
 
     @mark_as_writeable
-    def step(self, code: str, programs: str = "") -> dict:
+    def _step(self, code: str, programs: str = "") -> dict:
         if not self.has_reset:
             raise RuntimeError("Environment has not been reset yet")
         self.check_process()

metagpt/environment/stanford_town/env_space.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   :
+
+from typing import Any, Optional, Union
+
+import numpy as np
+import numpy.typing as npt
+from gymnasium import spaces
+from pydantic import ConfigDict, Field, field_validator
+
+from metagpt.environment.base_env_space import (
+    BaseEnvAction,
+    BaseEnvActionType,
+    BaseEnvObsParams,
+    BaseEnvObsType,
+)
+
+
+class EnvActionType(BaseEnvActionType):
+    NONE = 0  # no action to run, just get observation
+
+    ADD_TILE_EVENT = 1  # Add an event triple to a tile
+    RM_TILE_EVENT = 2  # Remove an event triple from a tile
+    TURN_TILE_EVENT_IDLE = 3  # Turn an event triple from a tile into idle
+    RM_TITLE_SUB_EVENT = 4  # Remove an event triple that has the input subject from a tile
+
+
+class EnvAction(BaseEnvAction):
+    """env action type and its related params of action functions/apis"""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    action_type: int = Field(default=EnvActionType.NONE, description="action type")
+    coord: npt.NDArray[np.int64] = Field(
+        default_factory=lambda: np.zeros(2, dtype=np.int64), description="tile coordinate"
+    )
+    subject: str = Field(default="", description="subject name of first element in event")
+    event: tuple[str, Optional[str], Optional[str], Optional[str]] = Field(
+        default=["", None, None, None], description="tile event"
+    )
+
+    @field_validator("coord", mode="before")
+    @classmethod
+    def check_coord(cls, coord) -> npt.NDArray[np.int64]:
+        if not isinstance(coord, np.ndarray):
+            return np.array(coord)
+
+
+class EnvObsType(BaseEnvObsType):
+    """get part observation with specific params"""
+
+    NONE = 0  # get whole observation from env
+
+    GET_TITLE = 1  # get the tile detail dictionary with given tile coord
+    TILE_PATH = 2  # get the tile address with given tile coord
+    TILE_NBR = 3  # get the neighbors of given tile coord and its vision radius
+
+
+class EnvObsParams(BaseEnvObsParams):
+    """observation params for different EnvObsType"""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    obs_type: int = Field(default=EnvObsType.NONE, description="observation type")
+    coord: npt.NDArray[np.int64] = Field(
+        default_factory=lambda: np.zeros(2, dtype=np.int64), description="tile coordinate"
+    )
+    level: str = Field(default="", description="different level of title")
+    vision_radius: int = Field(default=0, description="the vision radius of current tile")
+
+    @field_validator("coord", mode="before")
+    @classmethod
+    def check_coord(cls, coord) -> npt.NDArray[np.int64]:
+        if not isinstance(coord, np.ndarray):
+            return np.array(coord)
+
+
+EnvObsValType = Union[list[list[str]], dict[str, set[tuple[int, int]]], list[list[dict[str, Any]]]]
+
+
+def get_observation_space() -> spaces.Dict:
+    # it's a
+    space = spaces.Dict(
+        {"collision_maze": spaces.Discrete(2), "tiles": spaces.Discrete(2), "address_tiles": spaces.Discrete(2)}
+    )
+
+    return space
+
+
+def get_action_space(maze_shape: tuple[int, int]) -> spaces.Dict:
+    """The fields defined by the space correspond to the input parameters of the action except `action_type`"""
+    space = spaces.Dict(
+        {
+            "action_type": spaces.Discrete(len(EnvActionType)),
+            "coord": spaces.Box(
+                np.array([0, 0], dtype=np.int64), np.array([maze_shape[0], maze_shape[1]], dtype=np.int64)
+            ),  # coord of the tile
+            "subject": spaces.Text(256),  # the first element of an tile event
+            "event": spaces.Tuple(
+                (spaces.Text(256), spaces.Text(256), spaces.Text(256), spaces.Text(256))
+            ),  # event is a tuple of four str
+        }
+    )
+    return space

metagpt/environment/stanford_town/stanford_town_env.py

@@ -0,0 +1,10 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   : MG StanfordTown Env
+
+from metagpt.environment.base_env import Environment
+from metagpt.environment.stanford_town.stanford_town_ext_env import StanfordTownExtEnv
+
+
+class StanfordTownEnv(StanfordTownExtEnv, Environment):
+    pass

metagpt/environment/stanford_town/stanford_town_ext_env.py

@@ -5,11 +5,20 @@
 
 import math
 from pathlib import Path
-from typing import Optional, Tuple
+from typing import Any, Optional
 
 from pydantic import ConfigDict, Field, model_validator
 
 from metagpt.environment.base_env import ExtEnv, mark_as_readable, mark_as_writeable
+from metagpt.environment.stanford_town.env_space import (
+    EnvAction,
+    EnvActionType,
+    EnvObsParams,
+    EnvObsType,
+    EnvObsValType,
+    get_action_space,
+    get_observation_space,
+)
 from metagpt.utils.common import read_csv_to_list, read_json_file
 
 
@@ -197,15 +206,82 @@ class StanfordTownExtEnv(ExtEnv):
                     else:
                         address_tiles[add] = set([(j, i)])
         values["address_tiles"] = address_tiles
+
+        values["action_space"] = get_action_space((maze_width, maze_height))
+        values["observation_space"] = get_observation_space()
         return values
 
+    def reset(
+        self,
+        *,
+        seed: Optional[int] = None,
+        options: Optional[dict[str, Any]] = None,
+    ) -> tuple[dict[str, EnvObsValType], dict[str, Any]]:
+        """reset env and get the init observation
+        Return results corresponding to `observation, info`
+        """
+        super().reset(seed=seed, options=options)
+
+        obs = self._get_obs()
+
+        return obs, {}
+
+    def _get_obs(self) -> dict[str, EnvObsValType]:
+        """Get observation"""
+        return {
+            "collision_maze": self.get_collision_maze(),
+            "tiles": self.tiles,
+            "address_tiles": self.get_address_tiles(),
+        }
+
+    def observe(self, obs_params: Optional[EnvObsParams] = None) -> Any:
+        """Get partial or full observation from the env"""
+        obs_type = obs_params.obs_type if obs_params else EnvObsType.NONE
+        if obs_type == EnvObsType.NONE:
+            obs = self._get_obs()
+        elif obs_type == EnvObsType.GET_TITLE:
+            obs = self.access_tile(tile=obs_params.coord)
+        elif obs_type == EnvObsType.TILE_PATH:
+            obs = self.get_tile_path(tile=obs_params.coord, level=obs_params.level)
+        elif obs_type == EnvObsType.TILE_NBR:
+            obs = self.get_nearby_tiles(tile=obs_params.coord, vision_r=obs_params.vision_radius)
+        return obs
+
+    def step(self, action: EnvAction) -> tuple[dict[str, EnvObsValType], float, bool, bool, dict[str, Any]]:
+        """Execute action and then return observation
+        Return results corresponding to `observation, reward, terminated, truncated, info`
+        """
+        terminated = False
+        try:
+            self._execute_env_action(action)
+        except Exception:
+            terminated = True
+
+        obs = self._get_obs()
+
+        ret = (obs, 1.0, terminated, False, {})
+        return ret
+
+    def _execute_env_action(self, action: EnvAction):
+        action_type = action.action_type
+        if action_type == EnvActionType.NONE:
+            pass
+        elif action_type == EnvActionType.ADD_TILE_EVENT:
+            self.add_event_from_tile(curr_event=action.event, tile=action.coord)
+        elif action_type == EnvActionType.RM_TILE_EVENT:
+            self.remove_event_from_tile(curr_event=action.event, tile=action.coord)
+        elif action_type == EnvActionType.TURN_TILE_EVENT_IDLE:
+            self.turn_event_from_tile_idle(curr_event=action.event, tile=action.coord)
+        elif action_type == EnvActionType.RM_TITLE_SUB_EVENT:
+            self.remove_subject_events_from_tile(subject=action.subject, tile=action.coord)
+
     def turn_coordinate_to_tile(self, px_coordinate: tuple[int, int]) -> tuple[int, int]:
         """
         Turns a pixel coordinate to a tile coordinate.
         """
         x = math.ceil(px_coordinate[0] / self.sq_tile_size)
         y = math.ceil(px_coordinate[1] / self.sq_tile_size)
-        return (x, y)
+        return x, y
 
     @mark_as_readable
     def get_collision_maze(self) -> list:
@@ -316,10 +392,6 @@ class StanfordTownExtEnv(ExtEnv):
                 nearby_tiles += [(i, j)]
         return nearby_tiles
 
-    @mark_as_writeable
-    def add_tiles_event(self, pt_y: int, pt_x: int, event: Tuple[str, str, str, str]):
-        self.tiles[pt_y][pt_x]["events"].add(event)
-
     @mark_as_writeable
     def add_event_from_tile(self, curr_event: tuple[str], tile: tuple[int, int]) -> None:
         """

metagpt/environment/stanford_town_env/stanford_town_env.py

@@ -1,12 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-# @Desc   : MG StanfordTown Env
-
-from metagpt.environment.base_env import Environment
-from metagpt.environment.stanford_town_env.stanford_town_ext_env import (
-    StanfordTownExtEnv,
-)
-
-
-class StanfordTownEnv(Environment, StanfordTownExtEnv):
-    pass

metagpt/environment/werewolf/werewolf_env.py

@@ -5,7 +5,7 @@
 from pydantic import Field
 
 from metagpt.environment.base_env import Environment
-from metagpt.environment.werewolf_env.werewolf_ext_env import WerewolfExtEnv
+from metagpt.environment.werewolf.werewolf_ext_env import WerewolfExtEnv
 from metagpt.logs import logger
 from metagpt.schema import Message
 

metagpt/environment/werewolf/werewolf_ext_env.py

@@ -5,11 +5,12 @@
 import random
 from collections import Counter
 from enum import Enum
-from typing import Callable, Optional
+from typing import Any, Callable, Optional
 
 from pydantic import ConfigDict, Field
 
 from metagpt.environment.base_env import ExtEnv, mark_as_readable, mark_as_writeable
+from metagpt.environment.base_env_space import BaseEnvAction, BaseEnvObsParams
 from metagpt.logs import logger
 
 
@@ -128,6 +129,20 @@ class WerewolfExtEnv(ExtEnv):
     player_poisoned: Optional[str] = Field(default=None)
     player_current_dead: list[str] = Field(default=[])
 
+    def reset(
+        self,
+        *,
+        seed: Optional[int] = None,
+        options: Optional[dict[str, Any]] = None,
+    ) -> tuple[dict[str, Any], dict[str, Any]]:
+        pass
+
+    def observe(self, obs_params: Optional[BaseEnvObsParams] = None) -> Any:
+        pass
+
+    def step(self, action: BaseEnvAction) -> tuple[dict[str, Any], float, bool, bool, dict[str, Any]]:
+        pass
+
     @property
     def living_players(self) -> list[str]:
         player_names = []

metagpt/ext/__init__.py

@@ -0,0 +1,3 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   :

metagpt/ext/stanford_town/README.md

@@ -0,0 +1,36 @@
+## Stanford Town Game
+
+### Pre-Description
+In order to facilitate GA( [generative_agents](https://github.com/joonspk-research/generative_agents) )'s frontend docking data (to avoid changing its code), you can set the value `temp_storage_path` to `temp_storage` of `generative_agents` when start `run_st_game.py`. like
+
+`python3 run_st_game.py --temp_storage_path path/to/ga/temp_storage xxx`  
+
+Or change the path under `const.py` like beflow  
+
+```
+STORAGE_PATH = EXAMPLE_PATH.joinpath("storage")
+TEMP_STORAGE_PATH = EXAMPLE_PATH.joinpath("temp_storage")
+# updated
+STORAGE_PATH = Path("{path/to/ga/storage}")
+TEMP_STORAGE_PATH = Path("{path/to/ga/temp_storage}")
+```
+
+This can be used to achieve docking of simulation data without changing the GA code. Otherwise, the GA code must be modified to adapt to the MG output path.  
+
+If you don't want to start from 0, copy other simulation directories under `generative_agents/environment/frontend_server/storage/` to `examples/stanford_town/storage`, and select a directory named `fork_sim_code`.  
+
+### Backend service startup
+The execution entry is `python3 run_st_game.py "Host a open lunch party at 13:00 pm" "base_the_ville_isabella_maria_klaus" "test_sim" 10`  
+or   
+`python3 run_st_game.py "Host a open lunch party at 13:00 pm" "base_the_ville_isabella_maria_klaus" "test_sim" 10 --temp_storage_path path/to/ga/temp_storage`  
+
+`idea` is the user's voice to the first Agent, and it is disseminated through this voice to see whether the final multi-agents achieve the goal of hosting or participating in the event.  
+
+### Frontend service startup
+Enter project folder `generative_agents`  
+
+Enter `environment/frontend_server` and use `python3 manage.py runserver` to start the front-end service.  
+Visit `http://localhost:8000/simulator_home` to enter the current simulation interface.  
+
+## Appreciation
+The reproduction work has referred the `https://github.com/joonspk-research/generative_agents`, let's make a general statement here.  

metagpt/ext/stanford_town/README_CN.md

@@ -0,0 +1,35 @@
+## Stanford Town Game
+
+### 前置
+为了方便GA（ [generative_agents](https://github.com/joonspk-research/generative_agents) ）的前端对接数据（避免改动它那块的代码），可在启动`run_st_game.py`加上`temp_storage_path`指向`generative_agents`对应的`temp_storage`路径。比如
+
+`python3 run_st_game.py --temp_storage_path path/to/ga/temp_storage xxx`   
+
+或将`const.py`下的
+
+```
+STORAGE_PATH = EXAMPLE_PATH.joinpath("storage")
+TEMP_STORAGE_PATH = EXAMPLE_PATH.joinpath("temp_storage")
+# 更新为
+STORAGE_PATH = Path("{path/to/ga/storage}")
+TEMP_STORAGE_PATH = Path("{path/to/ga/temp_storage}")
+```
+这样可用实现不改变GA代码情况下，实现仿真数据的对接。不然得修改GA的代码来适配MG的输出路径。  
+
+如果你不想从0开始启动，拷贝`generative_agents/environment/frontend_server/storage/`下的其他仿真目录到`examples/stanford_town/storage`，并选择一个目录名作为`fork_sim_code`。  
+
+### 后端服务启动
+执行入口为：`python3 run_st_game.py "Host a open lunch party at 13:00 pm" "base_the_ville_isabella_maria_klaus" "test_sim" 10`  
+或者  
+`python3 run_st_game.py "Host a open lunch party at 13:00 pm" "base_the_ville_isabella_maria_klaus" "test_sim" 10 --temp_storage_path path/to/ga/temp_storage`
+
+`idea`为用户给第一个Agent的用户心声，并通过这个心声进行传播，看最后多智能体是否达到举办、参加活动的目标。  
+
+### 前端服务启动
+进入`generative_agents`项目目录
+
+进入`environment/frontend_server`，使用`python3 manage.py runserver`启动前端服务。  
+访问`http://localhost:8000/simulator_home` 进入当前的仿真界面。  
+
+## Appreciation
+The reproduction work has referred the `https://github.com/joonspk-research/generative_agents`, let's make a general statement here.

metagpt/ext/stanford_town/__init__.py

@@ -0,0 +1,3 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   : stanford town implement

metagpt/ext/stanford_town/actions/__init__.py

@@ -0,0 +1,3 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   :

metagpt/ext/stanford_town/actions/agent_chat_sum_rel.py

@@ -0,0 +1,39 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   : summarize relationship in a agent chat
+
+from metagpt.ext.stanford_town.actions.st_action import STAction
+from metagpt.logs import logger
+
+
+class AgentChatSumRel(STAction):
+    name: str = "AgentChatSumRel"
+
+    def _func_validate(self, llm_resp: str, prompt: str) -> bool:
+        resp = False
+        try:
+            _ = llm_resp.split('"')[0].strip()
+            resp = True
+        except Exception:
+            pass
+        return resp
+
+    def _func_cleanup(self, llm_resp: str, prompt: str) -> str:
+        return llm_resp.split('"')[0].strip()
+
+    def _func_fail_default_resp(self) -> str:
+        pass
+
+    async def run(self, init_role: "STRole", target_role: "STRole", statements: str) -> str:
+        def create_prompt_input(init_role: "STRole", target_role: "STRole", statements: str) -> str:
+            prompt_input = [statements, init_role.name, target_role.name]
+            return prompt_input
+
+        prompt_input = create_prompt_input(init_role, target_role, statements)
+        prompt = self.generate_prompt_with_tmpl_filename(prompt_input, "summarize_chat_relationship_v2.txt")
+
+        example_output = "Jane Doe is working on a project"
+        special_instruction = "The output should be a string that responds to the question."
+        output = await self._run_gpt35(prompt, example_output, special_instruction)
+        logger.info(f"Role: {init_role.name} Action: {self.cls_name} output: {output}")
+        return output

metagpt/ext/stanford_town/actions/decide_to_talk.py

@@ -0,0 +1,97 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Desc   : device to talk to another role, return yes or no
+
+from metagpt.ext.stanford_town.actions.st_action import STAction
+from metagpt.logs import logger
+
+
+class DecideToTalk(STAction):
+    name: str = "DecideToTalk"
+
+    def _func_validate(self, llm_resp: str, prompt: str) -> bool:
+        resp = False
+        try:
+            if llm_resp.split("Answer in yes or no:")[-1].strip().lower() in ["yes", "no"]:
+                resp = True
+        except ValueError:
+            pass
+        return resp
+
+    def _func_cleanup(self, llm_resp: str, prompt: str) -> str:
+        return llm_resp.split("Answer in yes or no:")[-1].strip().lower()
+
+    def _func_fail_default_resp(self) -> str:
+        return "yes"
+
+    async def run(self, init_role: "STRole", target_role: "STRole", retrieved: dict, *args, **kwargs) -> bool:
+        """Run action"""
+
+        def create_prompt_input(init_role: "STRole", target_role: "STRole", retrieved: dict) -> str:
+            scratch = init_role.rc.scratch
+            target_scratch = target_role.rc.scratch
+            last_chat = init_role.rc.memory.get_last_chat(target_role.name)
+            last_chatted_time = ""
+            last_chat_about = ""
+            if last_chat:
+                last_chatted_time = last_chat.created.strftime("%B %d, %Y, %H:%M:%S")
+                last_chat_about = last_chat.description
+
+            context = ""
+            for c_node in retrieved["events"]:
+                curr_desc = c_node.description.split(" ")
+                curr_desc[2:3] = ["was"]
+                curr_desc = " ".join(curr_desc)
+                context += f"{curr_desc}. "
+            context += "\n"
+            for c_node in retrieved["thoughts"]:
+                context += f"{c_node.description}. "
+
+            curr_time = scratch.curr_time.strftime("%B %d, %Y, %H:%M:%S %p")
+            init_act_desc = scratch.act_description
+            if "(" in init_act_desc:
+                init_act_desc = init_act_desc.split("(")[-1][:-1]
+
+            if len(scratch.planned_path) == 0 and "waiting" not in init_act_desc:
+                init_p_desc = f"{init_role.name} is already {init_act_desc}"
+            elif "waiting" in init_act_desc:
+                init_p_desc = f"{init_role.name} is {init_act_desc}"
+            else:
+                init_p_desc = f"{init_role.name} is on the way to {init_act_desc}"
+
+            target_act_desc = scratch.act_description
+            if "(" in target_act_desc:
+                target_act_desc = target_act_desc.split("(")[-1][:-1]
+
+            if len(target_scratch.planned_path) == 0 and "waiting" not in init_act_desc:
+                target_p_desc = f"{target_role.name} is already {target_act_desc}"
+            elif "waiting" in init_act_desc:
+                target_p_desc = f"{init_role.name} is {init_act_desc}"
+            else:
+                target_p_desc = f"{target_role.name} is on the way to {target_act_desc}"
+
+            prompt_input = []
+            prompt_input += [context]
+
+            prompt_input += [curr_time]
+
+            prompt_input += [init_role.name]
+            prompt_input += [target_role.name]
+            prompt_input += [last_chatted_time]
+            prompt_input += [last_chat_about]
+
+            prompt_input += [init_p_desc]
+            prompt_input += [target_p_desc]
+            prompt_input += [init_role.name]
+            prompt_input += [target_role.name]
+            return prompt_input
+
+        prompt_input = create_prompt_input(init_role, target_role, retrieved)
+        prompt = self.generate_prompt_with_tmpl_filename(
+            prompt_input=prompt_input, tmpl_filename="decide_to_talk_v2.txt"
+        )
+        self.fail_default_resp = self._func_fail_default_resp()
+        output = await self._run_gpt35_max_tokens(prompt, max_tokens=20)  # yes or no
+        result = True if output == "yes" else False
+        logger.info(f"Role: {init_role.name} Action: {self.cls_name} output: {result}")
+        return result