OpenBMB/ChatDev
1
1
Fork 0
mirror of https://github.com/OpenBMB/ChatDev.git synced 2024-10-06 15:48:26 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity

Modified Poker game. I have edited the files that ChatDev produced and got a semi-working game of poker. Can handle simple betting rules and card tracking, but can't determine winner of hand correctly.

Browse Source
This commit is contained in:
Ethan McQuillan 2023-10-07 06:43:14 -05:00
parent eaff6168bb
commit 9799437451
18 changed files with 12858 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
WareHouse/ChatDev Submodule

@ -0,0 +1 @@
Subproject commit e9657636f66293a61b211b414180435d22bfe8c2

98
WareHouse/Gomoku_DefaultOrganization_20231006033707.log Normal file
View File

@ -0,0 +1,98 @@
[2023-06-10 03:37:07 INFO] **[Preprocessing]**
**ChatDev Starts** (20231006033707)
**Timestamp**: 20231006033707
**config_path**: C:\Users\piema\ChatDev\CompanyConfig\Default\ChatChainConfig.json
**config_phase_path**: C:\Users\piema\ChatDev\CompanyConfig\Default\PhaseConfig.json
**config_role_path**: C:\Users\piema\ChatDev\CompanyConfig\Default\RoleConfig.json
**task_prompt**: Create a Texas Hold'em Poker game that adheres to the official No Limit Texas Hold'em rules. The game should simulate a poker tournament with 1 human player and 4 AI characters. Each player, including the human player and AI characters, starts with $1000 in chips.
**project_name**: Gomoku
**Log File**: C:\Users\piema\ChatDev\WareHouse\Gomoku_DefaultOrganization_20231006033707.log
**ChatDevConfig**:
ChatEnvConfig.clear_structure: True
ChatEnvConfig.git_management: False
ChatEnvConfig.gui_design: True
**ChatGPTConfig**:
ChatGPTConfig(temperature=0.2, top_p=1.0, n=1, stream=False, stop=None, max_tokens=None, presence_penalty=0.0, frequency_penalty=0.0, logit_bias={}, user='')
[2023-06-10 03:37:09 INFO] flask app.py did not start for online log
[2023-06-10 03:37:09 INFO] System: **[chatting]**
| Parameter | Value |
| --- | --- |
| **task_prompt** | Create a Texas Hold'em Poker game that adheres to the official No Limit Texas Hold'em rules. The game should simulate a poker tournament with 1 human player and 4 AI characters. Each player, including the human player and AI characters, starts with $1000 in chips. |
| **need_reflect** | True |
| **assistant_role_name** | Chief Product Officer |
| **user_role_name** | Chief Executive Officer |
| **phase_prompt** | ChatDev has made products in the following form before: Image: can present information in line chart, bar chart, flow chart, cloud chart, Gantt chart, etc. Document: can present information via .docx files. PowerPoint: can present information via .pptx files. Excel: can present information via .xlsx files. PDF: can present information via .pdf files. Website: can present personal resume, tutorial, products, or ideas, via .html files. Application: can implement visualized game, software, tool, etc, via python. Dashboard: can display a panel visualizing real-time information. Mind Map: can represent ideas, with related concepts arranged around a core concept. As the {assistant_role}, to satisfy the new user's demand and the product should be realizable, you should keep discussing with me to decide which product modality do we want the product to be? Note that we must ONLY discuss the product modality and do not discuss anything else! Once we all have expressed our opinion(s) and agree with the results of the discussion unanimously, any of us must actively terminate the discussion by replying with only one line, which starts with a single word , followed by our final product modality without any other words, e.g., " PowerPoint". |
| **phase_name** | DemandAnalysis |
| **assistant_role_prompt** | {chatdev_prompt} You are Chief Product Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer. You are responsible for all product-related matters in ChatDev. Usually includes product design, product strategy, product vision, product innovation, project management and product marketing. Here is a new customer's task: {task}. To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs. |
| **user_role_prompt** | {chatdev_prompt} You are Chief Executive Officer. Now, we are both working at ChatDev and we share a common interest in collaborating to successfully complete a task assigned by a new customer. Your main responsibilities include being an active decision-maker on users' demands and other key policy issues, leader, manager, and executor. Your decision-making role involves high-level decisions about policy and strategy; and your communicator role can involve speaking to the organization's management and employees. Here is a new customer's task: {task}. To complete the task, I will give you one or more instructions, and you must help me to write a specific solution that appropriately solves the requested instruction based on your expertise and my needs. |
| **chat_turn_limit** | 10 |
| **placeholders** | {} |
| **model_type** | ModelType.GPT_3_5_TURBO |
[2023-06-10 03:37:11 INFO] flask app.py did not start for online log
[2023-06-10 03:37:11 INFO] System: **[RolePlaying]**
| Parameter | Value |
| --- | --- |
| **assistant_role_name** | Chief Product Officer |
| **user_role_name** | Chief Executive Officer |
| **assistant_role_prompt** | {chatdev_prompt} You are Chief Product Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer. You are responsible for all product-related matters in ChatDev. Usually includes product design, product strategy, product vision, product innovation, project management and product marketing. Here is a new customer's task: {task}. To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs. |
| **user_role_prompt** | {chatdev_prompt} You are Chief Executive Officer. Now, we are both working at ChatDev and we share a common interest in collaborating to successfully complete a task assigned by a new customer. Your main responsibilities include being an active decision-maker on users' demands and other key policy issues, leader, manager, and executor. Your decision-making role involves high-level decisions about policy and strategy; and your communicator role can involve speaking to the organization's management and employees. Here is a new customer's task: {task}. To complete the task, I will give you one or more instructions, and you must help me to write a specific solution that appropriately solves the requested instruction based on your expertise and my needs. |
| **task_prompt** | Create a Texas Hold'em Poker game that adheres to the official No Limit Texas Hold'em rules. The game should simulate a poker tournament with 1 human player and 4 AI characters. Each player, including the human player and AI characters, starts with $1000 in chips. |
| **with_task_specify** | False |
| **model_type** | ModelType.GPT_3_5_TURBO |
[2023-06-10 03:37:13 INFO] flask app.py did not start for online log
[2023-06-10 03:37:13 INFO] Chief Executive Officer: **[Start Chat]**
[ChatDev is a software company powered by multiple intelligent agents, such as chief executive officer, chief human resources officer, chief product officer, chief technology officer, etc, with a multi-agent organizational structure and the mission of "changing the digital world through programming".
You are Chief Product Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.
You are responsible for all product-related matters in ChatDev. Usually includes product design, product strategy, product vision, product innovation, project management and product marketing.
Here is a new customer's task: Create a Texas Hold'em Poker game that adheres to the official No Limit Texas Hold'em rules. The game should simulate a poker tournament with 1 human player and 4 AI characters. Each player, including the human player and AI characters, starts with $1000 in chips..
To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs.]
ChatDev has made products in the following form before:
Image: can present information in line chart, bar chart, flow chart, cloud chart, Gantt chart, etc.
Document: can present information via .docx files.
PowerPoint: can present information via .pptx files.
Excel: can present information via .xlsx files.
PDF: can present information via .pdf files.
Website: can present personal resume, tutorial, products, or ideas, via .html files.
Application: can implement visualized game, software, tool, etc, via python.
Dashboard: can display a panel visualizing real-time information.
Mind Map: can represent ideas, with related concepts arranged around a core concept.
As the Chief Product Officer, to satisfy the new user's demand and the product should be realizable, you should keep discussing with me to decide which product modality do we want the product to be?
Note that we must ONLY discuss the product modality and do not discuss anything else! Once we all have expressed our opinion(s) and agree with the results of the discussion unanimously, any of us must actively terminate the discussion by replying with only one line, which starts with a single word <INFO>, followed by our final product modality without any other words, e.g., "<INFO> PowerPoint".
[2023-06-10 03:37:15 INFO] flask app.py did not start for online log
[2023-06-10 03:37:16 INFO] error_code=insufficient_quota error_message='You exceeded your current quota, please check your plan and billing details.' error_param=None error_type=insufficient_quota message='OpenAI API error received' stream_error=False
[2023-06-10 03:37:21 INFO] error_code=insufficient_quota error_message='You exceeded your current quota, please check your plan and billing details.' error_param=None error_type=insufficient_quota message='OpenAI API error received' stream_error=False
[2023-06-10 03:37:29 INFO] error_code=insufficient_quota error_message='You exceeded your current quota, please check your plan and billing details.' error_param=None error_type=insufficient_quota message='OpenAI API error received' stream_error=False
[2023-06-10 03:37:34 INFO] error_code=insufficient_quota error_message='You exceeded your current quota, please check your plan and billing details.' error_param=None error_type=insufficient_quota message='OpenAI API error received' stream_error=False
[2023-06-10 03:37:42 INFO] error_code=insufficient_quota error_message='You exceeded your current quota, please check your plan and billing details.' error_param=None error_type=insufficient_quota message='OpenAI API error received' stream_error=False

101
WareHouse/Gomoku_DefaultOrganization_20231006033707/ChatChainConfig.json Normal file
View File

@ -0,0 +1,101 @@
{
"chain": [
{
"phase": "DemandAnalysis",
"phaseType": "SimplePhase",
"max_turn_step": -1,
"need_reflect": "True"
},
{
"phase": "LanguageChoose",
"phaseType": "SimplePhase",
"max_turn_step": -1,
"need_reflect": "True"
},
{
"phase": "Coding",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
},
{
"phase": "CodeCompleteAll",
"phaseType": "ComposedPhase",
"cycleNum": 10,
"Composition": [
{
"phase": "CodeComplete",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
}
]
},
{
"phase": "CodeReview",
"phaseType": "ComposedPhase",
"cycleNum": 3,
"Composition": [
{
"phase": "CodeReviewComment",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
},
{
"phase": "CodeReviewModification",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
}
]
},
{
"phase": "Test",
"phaseType": "ComposedPhase",
"cycleNum": 3,
"Composition": [
{
"phase": "TestErrorSummary",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
},
{
"phase": "TestModification",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
}
]
},
{
"phase": "EnvironmentDoc",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "True"
},
{
"phase": "Manual",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
}
],
"recruitments": [
"Chief Executive Officer",
"Counselor",
"Chief Human Resource Officer",
"Chief Product Officer",
"Chief Technology Officer",
"Programmer",
"Code Reviewer",
"Software Test Engineer",
"Chief Creative Officer"
],
"clear_structure": "True",
"brainstorming": "False",
"gui_design": "True",
"git_management": "False",
"self_improve": "False"
}

1
WareHouse/Gomoku_DefaultOrganization_20231006033707/Gomoku.prompt Normal file
View File

@ -0,0 +1 @@
Create a Texas Hold'em Poker game that adheres to the official No Limit Texas Hold'em rules. The game should simulate a poker tournament with 1 human player and 4 AI characters. Each player, including the human player and AI characters, starts with $1000 in chips.

277
WareHouse/Gomoku_DefaultOrganization_20231006033707/PhaseConfig.json Normal file
View File

@ -0,0 +1,277 @@
{
"DemandAnalysis": {
"assistant_role_name": "Chief Product Officer",
"user_role_name": "Chief Executive Officer",
"phase_prompt": [
"ChatDev has made products in the following form before:",
"Image: can present information in line chart, bar chart, flow chart, cloud chart, Gantt chart, etc.",
"Document: can present information via .docx files.",
"PowerPoint: can present information via .pptx files.",
"Excel: can present information via .xlsx files.",
"PDF: can present information via .pdf files.",
"Website: can present personal resume, tutorial, products, or ideas, via .html files.",
"Application: can implement visualized game, software, tool, etc, via python.",
"Dashboard: can display a panel visualizing real-time information.",
"Mind Map: can represent ideas, with related concepts arranged around a core concept.",
"As the {assistant_role}, to satisfy the new user's demand and the product should be realizable, you should keep discussing with me to decide which product modality do we want the product to be?",
"Note that we must ONLY discuss the product modality and do not discuss anything else! Once we all have expressed our opinion(s) and agree with the results of the discussion unanimously, any of us must actively terminate the discussion by replying with only one line, which starts with a single word <INFO>, followed by our final product modality without any other words, e.g., \"<INFO> PowerPoint\"."
]
},
"LanguageChoose": {
"assistant_role_name": "Chief Technology Officer",
"user_role_name": "Chief Executive Officer",
"phase_prompt": [
"According to the new user's task and some creative brainstorm ideas listed below: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Ideas: \"{ideas}\".",
"We have decided to complete the task through a executable software implemented via a programming language. ",
"As the {assistant_role}, to satisfy the new user's demand and make the software realizable, you should propose a concrete programming language. If python can complete this task via Python, please answer Python; otherwise, answer another programming language (e.g., Java, C++, etc,).",
"Note that we must ONLY discuss the target programming language and do not discuss anything else! Once we all have expressed our opinion(s) and agree with the results of the discussion unanimously, any of us must actively terminate the discussion and conclude the best programming language we have discussed without any other words or reasons, return only one line using the format: \"<INFO> *\" where \"*\" represents a programming language."
]
},
"Coding": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Technology Officer",
"phase_prompt": [
"According to the new user's task and our software designs listed below: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas:\"{ideas}\"",
"We have decided to complete the task through a executable software with multiple files implemented via {language}. As the {assistant_role}, to satisfy the new user's demands, you should write one or multiple files and make sure that every detail of the architecture is, in the end, implemented as code. {gui}",
"Think step by step and reason yourself to the right decisions to make sure we get it right.",
"You will first lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.",
"Then you will output the content of each file including complete code. Each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"You will start with the \"main\" file, then go to the ones that are imported by that file, and so on.",
"Please note that the code should be fully functional. Ensure to implement all functions. No placeholders (such as 'pass' in Python)."
]
},
"ArtDesign": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Creative Officer",
"phase_prompt": [
"Our developed source codes and corresponding test reports are listed below: ",
"Task: \"{task}\".",
"Programming Language: \"{language}\"",
"Source Codes:",
"\"{codes}\"",
"Note that each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the new user's demand and equip the software with a beautiful graphical user interface (GUI), we will discuss and design many decorative images for GUI decoration. Now, we keep discussing the GUI beautification by listing some functionally independent elements in GUI that are being considered to be decorated by different pictures. For example, ten digits (0-9) in a calculator are functionally independent.",
"To answer, use the format: \" FILENAME.png: DESCRIPTION\" where \"FILENAME\" is the filename of the image and \"DESCRIPTION\" denotes the detailed description of the independent elements. For example:",
"'''",
"button_1.png: The button with the number \"1\" on it.",
"button_multiply.png: The button with the multiplication symbol (\"*\") on it.",
"background.png: the background color to decorate the Go game",
"'''",
"Now, list all functionally independent elements as much as possible."
]
},
"ArtIntegration": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Creative Officer",
"phase_prompt": [
"Our developed source codes and corresponding test reports are listed below: ",
"Task: \"{task}\".",
"Programming Language: \"{language}\"",
"Source Codes:",
"\"{codes}\"",
"Note that each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the new user's demand and equip the software with a beautiful graphical user interface (GUI), you will incorporate our designed images for GUI decoration. Here are some ready-made high-quality pictures and corresponding descriptions:",
"{images}",
"Note that the designed images have a fixed size of 256x256 pixels and the images are located in the same directory as all the Python files; please dynamically scaling these images according to the size of GUI, and use \"self.*\" to avoid displaying-related problems caused by automatic garbage collection. For example:",
"```",
"self.image = ImageTk.PhotoImage(Image.open(\"./image.png\").resize((50, 50)))",
"```",
"Now, use some or all of the pictures into the GUI to make it more beautiful and creative. Output codes strictly following the required format mentioned above."
]
},
"CodeComplete": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Technology Officer",
"phase_prompt": [
"According to the new user's task and our software designs listed below: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Codes:",
"\"{codes}\"",
"Unimplemented File:",
"\"{unimplemented_file}\"",
"In our software, each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the complete function of our developed software, you have to implement all methods in the {unimplemented_file} file which contains a unimplemented class. Now, implement all methods of the {unimplemented_file} and all other codes needed, then output the fully implemented codes, strictly following the required format."
]
},
"CodeReviewComment": {
"assistant_role_name": "Code Reviewer",
"user_role_name": "Programmer",
"phase_prompt": [
"According to the new user's task and our software designs: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas: \"{ideas}\"",
"Codes:",
"\"{codes}\"",
"As the {assistant_role}, to make the software directly operable without further coding, ChatDev have formulated the following regulations:",
"1) all referenced classes should be imported;",
"2) all methods should be implemented;",
"3) all methods need to have the necessary comments;",
"4) no potential bugs;",
"5) The entire project conforms to the tasks proposed by the user;",
"6) most importantly, do not only check the errors in the code, but also the logic of code. Make sure that user can interact with generated software without losing any feature in the requirement;",
"Now, you should check the above regulations one by one and review the codes in detail, propose one comment with the highest priority about the codes, and give me instructions on how to fix. Tell me your comment with the highest priority and corresponding suggestions on revision. If the codes are perfect and you have no comment on them, return only one line like \"<INFO> Finished\"."
]
},
"CodeReviewModification": {
"assistant_role_name": "Programmer",
"user_role_name": "Code Reviewer",
"phase_prompt": [
"According to the new user's task, our designed product modality, languages and ideas, our developed first-edition source codes are listed below: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas: \"{ideas}\"",
"Codes: ",
"\"{codes}\"",
"Comments on Codes:",
"\"{comments}\"",
"In the software, each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code. Format:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the new user's demand and make the software creative, executive and robust, you should modify corresponding codes according to the comments. Then, output the full and complete codes with all bugs fixed based on the comments. Return all codes strictly following the required format."
]
},
"TestErrorSummary": {
"assistant_role_name": "Programmer",
"user_role_name": "Software Test Engineer",
"phase_prompt": [
"Our developed source codes and corresponding test reports are listed below: ",
"Programming Language: \"{language}\"",
"Source Codes:",
"\"{codes}\"",
"Test Reports of Source Codes:",
"\"{test_reports}\"",
"According to my test reports, please locate and summarize the bugs that cause the problem."
]
},
"TestModification": {
"assistant_role_name": "Programmer",
"user_role_name": "Software Test Engineer",
"phase_prompt": [
"Our developed source codes and corresponding test reports are listed below: ",
"Programming Language: \"{language}\"",
"Source Codes:",
"\"{codes}\"",
"Test Reports of Source Codes:",
"\"{test_reports}\"",
"Error Summary of Test Reports:",
"\"{error_summary}\"",
"Note that each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the new user's demand and make the software execute smoothly and robustly, you should modify the codes based on the error summary. Now, use the format exemplified above and modify the problematic codes based on the error summary. Output the codes that you fixed based on the test reported and corresponding explanations (strictly follow the format defined above, including FILENAME, LANGUAGE, DOCSTRING and CODE; incomplete \"TODO\" codes are strictly prohibited). If no bugs are reported, please return only one line like \"<INFO> Finished\"."
]
},
"EnvironmentDoc": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Technology Officer",
"phase_prompt": [
"The new user's task and our developed codes are listed: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas: \"{ideas}\"",
"Codes: ",
"\"{codes}\"",
"As the {assistant_role}, you should write a requirements.txt file, which is commonly used in Python projects to specify the dependencies or packages required for the project to run properly. It serves as a way to document and manage the project's dependencies in a standardized format. For example:",
"requirements.txt",
"```",
"numpy==1.19.2",
"pandas>=1.1.4",
"```",
"According to the codes and file format listed above, write a requirements.txt file to specify the dependencies or packages required for the project to run properly."
]
},
"Manual": {
"assistant_role_name": "Chief Product Officer",
"user_role_name": "Chief Executive Officer",
"phase_prompt": [
"The new user's task, our developed codes and required dependencies are listed: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas: \"{ideas}\"",
"Codes: ",
"\"{codes}\"",
"Requirements:",
"\"{requirements}\"",
"As the {assistant_role}, by using Markdown, you should write a manual.md file which is a detailed user manual to use the software, including introducing main functions of the software, how to install environment dependencies and how to use/play it. For example:",
"manual.md",
"```",
"# LangChain",
"Building applications with LLMs through composability",
"Looking for the JS/TS version? Check out LangChain.js.",
"**Production Support:** As you move your LangChains into production, we'd love to offer more comprehensive support.",
"Please fill out this form and we'll set up a dedicated support Slack channel.",
"## Quick Install",
"`pip install langchain`",
"or",
"`conda install langchain -c conda-forge`",
"## 🤔 What is this?",
"Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. However, using these LLMs in isolation is often insufficient for creating a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.",
"This library aims to assist in the development of those types of applications. Common examples of these applications include:",
"**❓ Question Answering over specific documents**",
"- Documentation",
"- End-to-end Example: Question Answering over Notion Database",
"**🤖 Agents**",
"- Documentation",
"- End-to-end Example: GPT+WolframAlpha",
"## 📖 Documentation",
"Please see [here](https://python.langchain.com) for full documentation on:",
"- Getting started (installation, setting up the environment, simple examples)",
"- How-To examples (demos, integrations, helper functions)",
"- Reference (full API docs)",
"- Resources (high-level explanation of core concepts)",
"```"
]
}
}

65
WareHouse/Gomoku_DefaultOrganization_20231006033707/RoleConfig.json Normal file
View File

@ -0,0 +1,65 @@
{
"Chief Executive Officer": [
"{chatdev_prompt}",
"You are Chief Executive Officer. Now, we are both working at ChatDev and we share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"Your main responsibilities include being an active decision-maker on users' demands and other key policy issues, leader, manager, and executor. Your decision-making role involves high-level decisions about policy and strategy; and your communicator role can involve speaking to the organization's management and employees.",
"Here is a new customer's task: {task}.",
"To complete the task, I will give you one or more instructions, and you must help me to write a specific solution that appropriately solves the requested instruction based on your expertise and my needs."
],
"Chief Product Officer": [
"{chatdev_prompt}",
"You are Chief Product Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You are responsible for all product-related matters in ChatDev. Usually includes product design, product strategy, product vision, product innovation, project management and product marketing.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Counselor": [
"{chatdev_prompt}",
"You are Counselor. Now, we share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"Your main responsibilities include asking what user and customer think and provide your valuable suggestions. ",
"Here is a new customer's task: {task}.",
"To complete the task, I will give you one or more instructions, and you must help me to write a specific solution that appropriately solves the requested instruction based on your expertise and my needs."
],
"Chief Technology Officer": [
"{chatdev_prompt}",
"You are Chief Technology Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You are very familiar to information technology. You will make high-level decisions for the overarching technology infrastructure that closely align with the organization's goals, while you work alongside the organization's information technology (\"IT\") staff members to perform everyday operations.",
"Here is a new customer's task: {task}.",
"To complete the task, You must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Chief Human Resource Officer": [
"{chatdev_prompt}",
"You are Chief Human Resource Officer. Now, we are both working at ChatDev and we share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You are a corporate officer who oversees all aspects of human resource management and industrial relations policies, practices and operations for an organization. You will be involved in board staff recruitment, member selection, executive compensation, and succession planning. Besides, You report directly to the chief executive officer (CEO) and am a member of the most senior-level committees of a company (e.g., executive committee or office of CEO).",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Programmer": [
"{chatdev_prompt}",
"You are Programmer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You can write/create computer software or applications by providing a specific programming language to the computer. You have extensive computing and coding experience in many varieties of programming languages and platforms, such as Python, Java, C, C++, HTML, CSS, JavaScript, XML, SQL, PHP, etc,.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Code Reviewer": [
"{chatdev_prompt}",
"You are Code Reviewer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You can help programmers to assess source codes for software troubleshooting, fix bugs to increase code quality and robustness, and offer proposals to improve the source codes.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Software Test Engineer": [
"{chatdev_prompt}",
"You are Software Test Engineer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You can use the software as intended to analyze its functional properties, design manual and automated test procedures to evaluate each software product, build and implement software evaluation test programs, and run test programs to ensure that testing protocols evaluate the software correctly.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Chief Creative Officer": [
"{chatdev_prompt}",
"You are Chief Creative Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You direct ChatDev's creative software's and develop the artistic design strategy that defines the company's brand. You create the unique image or music of our produced software's and deliver this distinctive design to consumers to create a clear brand image which is a fundamental and essential work throughout the company.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
]
}

101
WareHouse/Poker1_DefaultOrganization_20231006035628/ChatChainConfig.json Normal file
View File

@ -0,0 +1,101 @@
{
"chain": [
{
"phase": "DemandAnalysis",
"phaseType": "SimplePhase",
"max_turn_step": -1,
"need_reflect": "True"
},
{
"phase": "LanguageChoose",
"phaseType": "SimplePhase",
"max_turn_step": -1,
"need_reflect": "True"
},
{
"phase": "Coding",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
},
{
"phase": "CodeCompleteAll",
"phaseType": "ComposedPhase",
"cycleNum": 10,
"Composition": [
{
"phase": "CodeComplete",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
}
]
},
{
"phase": "CodeReview",
"phaseType": "ComposedPhase",
"cycleNum": 3,
"Composition": [
{
"phase": "CodeReviewComment",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
},
{
"phase": "CodeReviewModification",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
}
]
},
{
"phase": "Test",
"phaseType": "ComposedPhase",
"cycleNum": 3,
"Composition": [
{
"phase": "TestErrorSummary",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
},
{
"phase": "TestModification",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
}
]
},
{
"phase": "EnvironmentDoc",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "True"
},
{
"phase": "Manual",
"phaseType": "SimplePhase",
"max_turn_step": 1,
"need_reflect": "False"
}
],
"recruitments": [
"Chief Executive Officer",
"Counselor",
"Chief Human Resource Officer",
"Chief Product Officer",
"Chief Technology Officer",
"Programmer",
"Code Reviewer",
"Software Test Engineer",
"Chief Creative Officer"
],
"clear_structure": "True",
"brainstorming": "False",
"gui_design": "True",
"git_management": "False",
"self_improve": "False"
}

277
WareHouse/Poker1_DefaultOrganization_20231006035628/PhaseConfig.json Normal file
View File

@ -0,0 +1,277 @@
{
"DemandAnalysis": {
"assistant_role_name": "Chief Product Officer",
"user_role_name": "Chief Executive Officer",
"phase_prompt": [
"ChatDev has made products in the following form before:",
"Image: can present information in line chart, bar chart, flow chart, cloud chart, Gantt chart, etc.",
"Document: can present information via .docx files.",
"PowerPoint: can present information via .pptx files.",
"Excel: can present information via .xlsx files.",
"PDF: can present information via .pdf files.",
"Website: can present personal resume, tutorial, products, or ideas, via .html files.",
"Application: can implement visualized game, software, tool, etc, via python.",
"Dashboard: can display a panel visualizing real-time information.",
"Mind Map: can represent ideas, with related concepts arranged around a core concept.",
"As the {assistant_role}, to satisfy the new user's demand and the product should be realizable, you should keep discussing with me to decide which product modality do we want the product to be?",
"Note that we must ONLY discuss the product modality and do not discuss anything else! Once we all have expressed our opinion(s) and agree with the results of the discussion unanimously, any of us must actively terminate the discussion by replying with only one line, which starts with a single word <INFO>, followed by our final product modality without any other words, e.g., \"<INFO> PowerPoint\"."
]
},
"LanguageChoose": {
"assistant_role_name": "Chief Technology Officer",
"user_role_name": "Chief Executive Officer",
"phase_prompt": [
"According to the new user's task and some creative brainstorm ideas listed below: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Ideas: \"{ideas}\".",
"We have decided to complete the task through a executable software implemented via a programming language. ",
"As the {assistant_role}, to satisfy the new user's demand and make the software realizable, you should propose a concrete programming language. If python can complete this task via Python, please answer Python; otherwise, answer another programming language (e.g., Java, C++, etc,).",
"Note that we must ONLY discuss the target programming language and do not discuss anything else! Once we all have expressed our opinion(s) and agree with the results of the discussion unanimously, any of us must actively terminate the discussion and conclude the best programming language we have discussed without any other words or reasons, return only one line using the format: \"<INFO> *\" where \"*\" represents a programming language."
]
},
"Coding": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Technology Officer",
"phase_prompt": [
"According to the new user's task and our software designs listed below: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas:\"{ideas}\"",
"We have decided to complete the task through a executable software with multiple files implemented via {language}. As the {assistant_role}, to satisfy the new user's demands, you should write one or multiple files and make sure that every detail of the architecture is, in the end, implemented as code. {gui}",
"Think step by step and reason yourself to the right decisions to make sure we get it right.",
"You will first lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.",
"Then you will output the content of each file including complete code. Each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"You will start with the \"main\" file, then go to the ones that are imported by that file, and so on.",
"Please note that the code should be fully functional. Ensure to implement all functions. No placeholders (such as 'pass' in Python)."
]
},
"ArtDesign": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Creative Officer",
"phase_prompt": [
"Our developed source codes and corresponding test reports are listed below: ",
"Task: \"{task}\".",
"Programming Language: \"{language}\"",
"Source Codes:",
"\"{codes}\"",
"Note that each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the new user's demand and equip the software with a beautiful graphical user interface (GUI), we will discuss and design many decorative images for GUI decoration. Now, we keep discussing the GUI beautification by listing some functionally independent elements in GUI that are being considered to be decorated by different pictures. For example, ten digits (0-9) in a calculator are functionally independent.",
"To answer, use the format: \" FILENAME.png: DESCRIPTION\" where \"FILENAME\" is the filename of the image and \"DESCRIPTION\" denotes the detailed description of the independent elements. For example:",
"'''",
"button_1.png: The button with the number \"1\" on it.",
"button_multiply.png: The button with the multiplication symbol (\"*\") on it.",
"background.png: the background color to decorate the Go game",
"'''",
"Now, list all functionally independent elements as much as possible."
]
},
"ArtIntegration": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Creative Officer",
"phase_prompt": [
"Our developed source codes and corresponding test reports are listed below: ",
"Task: \"{task}\".",
"Programming Language: \"{language}\"",
"Source Codes:",
"\"{codes}\"",
"Note that each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the new user's demand and equip the software with a beautiful graphical user interface (GUI), you will incorporate our designed images for GUI decoration. Here are some ready-made high-quality pictures and corresponding descriptions:",
"{images}",
"Note that the designed images have a fixed size of 256x256 pixels and the images are located in the same directory as all the Python files; please dynamically scaling these images according to the size of GUI, and use \"self.*\" to avoid displaying-related problems caused by automatic garbage collection. For example:",
"```",
"self.image = ImageTk.PhotoImage(Image.open(\"./image.png\").resize((50, 50)))",
"```",
"Now, use some or all of the pictures into the GUI to make it more beautiful and creative. Output codes strictly following the required format mentioned above."
]
},
"CodeComplete": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Technology Officer",
"phase_prompt": [
"According to the new user's task and our software designs listed below: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Codes:",
"\"{codes}\"",
"Unimplemented File:",
"\"{unimplemented_file}\"",
"In our software, each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the complete function of our developed software, you have to implement all methods in the {unimplemented_file} file which contains a unimplemented class. Now, implement all methods of the {unimplemented_file} and all other codes needed, then output the fully implemented codes, strictly following the required format."
]
},
"CodeReviewComment": {
"assistant_role_name": "Code Reviewer",
"user_role_name": "Programmer",
"phase_prompt": [
"According to the new user's task and our software designs: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas: \"{ideas}\"",
"Codes:",
"\"{codes}\"",
"As the {assistant_role}, to make the software directly operable without further coding, ChatDev have formulated the following regulations:",
"1) all referenced classes should be imported;",
"2) all methods should be implemented;",
"3) all methods need to have the necessary comments;",
"4) no potential bugs;",
"5) The entire project conforms to the tasks proposed by the user;",
"6) most importantly, do not only check the errors in the code, but also the logic of code. Make sure that user can interact with generated software without losing any feature in the requirement;",
"Now, you should check the above regulations one by one and review the codes in detail, propose one comment with the highest priority about the codes, and give me instructions on how to fix. Tell me your comment with the highest priority and corresponding suggestions on revision. If the codes are perfect and you have no comment on them, return only one line like \"<INFO> Finished\"."
]
},
"CodeReviewModification": {
"assistant_role_name": "Programmer",
"user_role_name": "Code Reviewer",
"phase_prompt": [
"According to the new user's task, our designed product modality, languages and ideas, our developed first-edition source codes are listed below: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas: \"{ideas}\"",
"Codes: ",
"\"{codes}\"",
"Comments on Codes:",
"\"{comments}\"",
"In the software, each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code. Format:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the new user's demand and make the software creative, executive and robust, you should modify corresponding codes according to the comments. Then, output the full and complete codes with all bugs fixed based on the comments. Return all codes strictly following the required format."
]
},
"TestErrorSummary": {
"assistant_role_name": "Programmer",
"user_role_name": "Software Test Engineer",
"phase_prompt": [
"Our developed source codes and corresponding test reports are listed below: ",
"Programming Language: \"{language}\"",
"Source Codes:",
"\"{codes}\"",
"Test Reports of Source Codes:",
"\"{test_reports}\"",
"According to my test reports, please locate and summarize the bugs that cause the problem."
]
},
"TestModification": {
"assistant_role_name": "Programmer",
"user_role_name": "Software Test Engineer",
"phase_prompt": [
"Our developed source codes and corresponding test reports are listed below: ",
"Programming Language: \"{language}\"",
"Source Codes:",
"\"{codes}\"",
"Test Reports of Source Codes:",
"\"{test_reports}\"",
"Error Summary of Test Reports:",
"\"{error_summary}\"",
"Note that each file must strictly follow a markdown code block format, where the following tokens must be replaced such that \"FILENAME\" is the lowercase file name including the file extension, \"LANGUAGE\" in the programming language, \"DOCSTRING\" is a string literal specified in source code that is used to document a specific segment of code, and \"CODE\" is the original code:",
"FILENAME",
"```LANGUAGE",
"'''",
"DOCSTRING",
"'''",
"CODE",
"```",
"As the {assistant_role}, to satisfy the new user's demand and make the software execute smoothly and robustly, you should modify the codes based on the error summary. Now, use the format exemplified above and modify the problematic codes based on the error summary. Output the codes that you fixed based on the test reported and corresponding explanations (strictly follow the format defined above, including FILENAME, LANGUAGE, DOCSTRING and CODE; incomplete \"TODO\" codes are strictly prohibited). If no bugs are reported, please return only one line like \"<INFO> Finished\"."
]
},
"EnvironmentDoc": {
"assistant_role_name": "Programmer",
"user_role_name": "Chief Technology Officer",
"phase_prompt": [
"The new user's task and our developed codes are listed: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas: \"{ideas}\"",
"Codes: ",
"\"{codes}\"",
"As the {assistant_role}, you should write a requirements.txt file, which is commonly used in Python projects to specify the dependencies or packages required for the project to run properly. It serves as a way to document and manage the project's dependencies in a standardized format. For example:",
"requirements.txt",
"```",
"numpy==1.19.2",
"pandas>=1.1.4",
"```",
"According to the codes and file format listed above, write a requirements.txt file to specify the dependencies or packages required for the project to run properly."
]
},
"Manual": {
"assistant_role_name": "Chief Product Officer",
"user_role_name": "Chief Executive Officer",
"phase_prompt": [
"The new user's task, our developed codes and required dependencies are listed: ",
"Task: \"{task}\".",
"Modality: \"{modality}\".",
"Programming Language: \"{language}\"",
"Ideas: \"{ideas}\"",
"Codes: ",
"\"{codes}\"",
"Requirements:",
"\"{requirements}\"",
"As the {assistant_role}, by using Markdown, you should write a manual.md file which is a detailed user manual to use the software, including introducing main functions of the software, how to install environment dependencies and how to use/play it. For example:",
"manual.md",
"```",
"# LangChain",
"Building applications with LLMs through composability",
"Looking for the JS/TS version? Check out LangChain.js.",
"**Production Support:** As you move your LangChains into production, we'd love to offer more comprehensive support.",
"Please fill out this form and we'll set up a dedicated support Slack channel.",
"## Quick Install",
"`pip install langchain`",
"or",
"`conda install langchain -c conda-forge`",
"## 🤔 What is this?",
"Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. However, using these LLMs in isolation is often insufficient for creating a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.",
"This library aims to assist in the development of those types of applications. Common examples of these applications include:",
"**❓ Question Answering over specific documents**",
"- Documentation",
"- End-to-end Example: Question Answering over Notion Database",
"**🤖 Agents**",
"- Documentation",
"- End-to-end Example: GPT+WolframAlpha",
"## 📖 Documentation",
"Please see [here](https://python.langchain.com) for full documentation on:",
"- Getting started (installation, setting up the environment, simple examples)",
"- How-To examples (demos, integrations, helper functions)",
"- Reference (full API docs)",
"- Resources (high-level explanation of core concepts)",
"```"
]
}
}

1
WareHouse/Poker1_DefaultOrganization_20231006035628/Poker1.prompt Normal file
View File

@ -0,0 +1 @@
Create a Texas Hold'em Poker game that adheres to the official No Limit Texas Hold'em rules. The game should simulate a poker tournament with 1 human player and 4 AI characters. Each player, including the human player and AI characters, starts with $1000 in chips. The tournament begins with blinds set at $5 for the small blind and $10 for the big blind. The blinds will follow the World Poker Tour incremental blinds guidelines, increasing at regular intervals. Ensure that the blinds increase according to these guidelines to maintain a challenging pace. For AI character decision-making, they should employ basic poker theory for most of their actions, striving to make optimal choices based on their hands and the community cards. However, each AI character should also have the ability to make occasional 'random' decisions, deviating from optimal play to add an element of unpredictability and excitement to the game. The game should provide a realistic poker experience, including actions such as checking, betting, raising, calling, and folding. It should accurately track the chip counts of all players, manage the community cards and the deck, and determine the winner(s) of each hand. Please generate a detailed description and implementation plan for this Texas Hold'em Poker game, specifying how the AI characters will make decisions and interact with the human player. Additionally, outline the algorithm for increasing blinds according to the World Poker Tour guidelines.

11353
WareHouse/Poker1_DefaultOrganization_20231006035628/Poker1_DefaultOrganization_20231006035628.log Normal file
View File

File diff suppressed because one or more lines are too long

65
WareHouse/Poker1_DefaultOrganization_20231006035628/RoleConfig.json Normal file
View File

@ -0,0 +1,65 @@
{
"Chief Executive Officer": [
"{chatdev_prompt}",
"You are Chief Executive Officer. Now, we are both working at ChatDev and we share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"Your main responsibilities include being an active decision-maker on users' demands and other key policy issues, leader, manager, and executor. Your decision-making role involves high-level decisions about policy and strategy; and your communicator role can involve speaking to the organization's management and employees.",
"Here is a new customer's task: {task}.",
"To complete the task, I will give you one or more instructions, and you must help me to write a specific solution that appropriately solves the requested instruction based on your expertise and my needs."
],
"Chief Product Officer": [
"{chatdev_prompt}",
"You are Chief Product Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You are responsible for all product-related matters in ChatDev. Usually includes product design, product strategy, product vision, product innovation, project management and product marketing.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Counselor": [
"{chatdev_prompt}",
"You are Counselor. Now, we share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"Your main responsibilities include asking what user and customer think and provide your valuable suggestions. ",
"Here is a new customer's task: {task}.",
"To complete the task, I will give you one or more instructions, and you must help me to write a specific solution that appropriately solves the requested instruction based on your expertise and my needs."
],
"Chief Technology Officer": [
"{chatdev_prompt}",
"You are Chief Technology Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You are very familiar to information technology. You will make high-level decisions for the overarching technology infrastructure that closely align with the organization's goals, while you work alongside the organization's information technology (\"IT\") staff members to perform everyday operations.",
"Here is a new customer's task: {task}.",
"To complete the task, You must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Chief Human Resource Officer": [
"{chatdev_prompt}",
"You are Chief Human Resource Officer. Now, we are both working at ChatDev and we share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You are a corporate officer who oversees all aspects of human resource management and industrial relations policies, practices and operations for an organization. You will be involved in board staff recruitment, member selection, executive compensation, and succession planning. Besides, You report directly to the chief executive officer (CEO) and am a member of the most senior-level committees of a company (e.g., executive committee or office of CEO).",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Programmer": [
"{chatdev_prompt}",
"You are Programmer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You can write/create computer software or applications by providing a specific programming language to the computer. You have extensive computing and coding experience in many varieties of programming languages and platforms, such as Python, Java, C, C++, HTML, CSS, JavaScript, XML, SQL, PHP, etc,.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Code Reviewer": [
"{chatdev_prompt}",
"You are Code Reviewer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You can help programmers to assess source codes for software troubleshooting, fix bugs to increase code quality and robustness, and offer proposals to improve the source codes.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Software Test Engineer": [
"{chatdev_prompt}",
"You are Software Test Engineer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You can use the software as intended to analyze its functional properties, design manual and automated test procedures to evaluate each software product, build and implement software evaluation test programs, and run test programs to ensure that testing protocols evaluate the software correctly.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
],
"Chief Creative Officer": [
"{chatdev_prompt}",
"You are Chief Creative Officer. we are both working at ChatDev. We share a common interest in collaborating to successfully complete a task assigned by a new customer.",
"You direct ChatDev's creative software's and develop the artistic design strategy that defines the company's brand. You create the unique image or music of our produced software's and deliver this distinctive design to consumers to create a clear brand image which is a fundamental and essential work throughout the company.",
"Here is a new customer's task: {task}.",
"To complete the task, you must write a response that appropriately solves the requested instruction based on your expertise and customer's needs."
]
}

22
WareHouse/Poker1_DefaultOrganization_20231006035628/deck.py Normal file
View File

@ -0,0 +1,22 @@
'''
Deck module that defines the Deck class.
'''
import random
class Deck:
def __init__(self):
self.cards = self.create_deck()
def create_deck(self):
suits = ["Spades", "Hearts", "Diamonds", "Clubs"]
ranks = ["2", "3", "4", "5", "6", "7", "8", "9", "10", "J", "Q", "K", "A"]
deck = []
for suit in suits:
for rank in ranks:
deck.append(rank + " of " + suit)
return deck
def shuffle(self):
random.shuffle(self.cards)
def draw(self, num_cards):
cards = []
for _ in range(num_cards):
cards.append(self.cards.pop())
return cards

254
WareHouse/Poker1_DefaultOrganization_20231006035628/game.py Normal file
View File

@ -0,0 +1,254 @@
'''
Game module that manages the Texas Hold'em Poker game.
'''
from player import HumanPlayer, AIPlayer
from deck import Deck
class Game:
def __init__(self):
self.players = []
self.deck = Deck()
self.community_cards = []
self.small_blind = 5
self.big_blind = 10
self.current_bet = 0
self.pot = 0
def start(self):
self.initialize_players()
self.initialize_blinds()
self.play_round()
def initialize_players(self):
self.players.append(HumanPlayer("Human", 1000))
self.players.append(AIPlayer("AI 1", 1000))
self.players.append(AIPlayer("AI 2", 1000))
self.players.append(AIPlayer("AI 3", 1000))
self.players.append(AIPlayer("AI 4", 1000))
def initialize_blinds(self):
for player in self.players:
if player.name == "AI 4":
player.blind = self.small_blind
elif player.name == "Human":
player.blind = self.big_blind
def play_round(self):
while len(self.players) > 1:
self.deck.shuffle()
self.reset_round()
self.collect_blinds()
self.deal_hole_cards()
self.play_betting_round()
if len(self.players) > 1:
self.deal_community_cards()
self.play_betting_round()
self.deal_community_cards()
self.play_betting_round()
self.deal_community_cards()
self.play_betting_round()
if len(self.players) > 1:
self.determine_winner()
elif len(self.players) == 1:
self.players[0].chips += pot
def reset_round(self):
self.community_cards = []
self.current_bet = 0
self.pot = 0
for player in self.players:
player.reset()
def collect_blinds(self):
for player in self.players:
if player.blind == self.small_blind:
self.pot += player.blind_bet(self.small_blind)
elif player.blind == self.big_blind:
self.pot += player.blind_bet(self.big_blind)
def deal_hole_cards(self):
for player in self.players:
player.receive_cards(self.deck.draw(2))
def play_betting_round(self):
for player in self.players:
if len(self.community_cards) != 0:
player.previous_bet = 0
player.blind = 0
self.current_bet = 0
else:
self.current_bet = 10
if len(self.community_cards) != 0:
print (f"Community cards: {self.community_cards}")
print (f"Pot: {self.pot}")
current_player_index = self.get_next_player_index(0)
last_raiser_index = None
while True:
current_player = self.players[current_player_index]
if current_player.is_active():
action = current_player.make_decision(self.current_bet)
if action == "fold":
current_player.fold()
elif action == "check":
if last_raiser_index is not None:
if (self.current_bet > current_player.previous_bet):
print(f"{current_player.name} attempted to check. Forcing fold...")
current_player.fold() #Bot likes to check to avoid calling, force them to fold with this
else:
current_player.check()
elif action == "call":
if last_raiser_index is not None: #Someone raised
if (amount >= current_player.chips): #All in
self.pot += current_player.all_in()
else: #Has the chips to call
prev_bet = current_player.call(self.current_bet - current_player.previous_bet - current_player.blind)
self.pot += prev_bet
current_player.previous_bet += prev_bet + current_player.blind
current_player.blind = 0
else: #No one raised, pay big blind
self.pot += current_player.call(self.big_blind - current_player.blind)
self.previous_bet = 10
current_player.previous_bet = 10
current_player.blind = 0
elif action == "raise":
amount = current_player.get_raise_amount(self.current_bet)
new_amount = amount + self.current_bet*2 - current_player.blind - current_player.previous_bet
self.current_bet = new_amount + current_player.blind + current_player.previous_bet
current_player.blind = 0
self.pot += current_player.raise_bet(new_amount)
print(f"Current top bet is: {self.current_bet}")
last_raiser_index = current_player_index
current_player.previous_bet = self.current_bet
current_player_index = self.get_next_player_index(current_player_index)
if current_player_index == last_raiser_index:
break
def deal_community_cards(self):
if len(self.players[0].community_cards) == 0:
self.community_cards.extend(self.deck.draw(3))
elif len(self.players[0].community_cards) == 3:
self.community_cards.extend(self.deck.draw(1))
elif len(self.players[0].community_cards) == 4:
self.community_cards.extend(self.deck.draw(1))
for player in self.players:
player.receive_community_cards(self.community_cards)
def determine_winner(self):
best_hand_value = 0
winners = []
for player in self.players:
if player.is_active():
hand_value = self.calculate_hand_value(player)
if hand_value > best_hand_value:
best_hand_value = hand_value
winners = [player]
elif hand_value == best_hand_value:
winners.append(player)
if len(winners) == 1:
winning_player = winners[0]
print(f"{winning_player.name} wins with {self.get_hand_name(best_hand_value)}!")
winning_player.chips += self.pot
else:
print("It's a tie!")
def calculate_hand_value(self, player):
# Implement logic to calculate the unique hand value as described in the provided information.
hand_type = self.determine_hand_type(player.hand)
card_values = [self.get_card_value(card) for card in player.hand]
hand_value = hand_type
for card_value in card_values:
hand_value = (hand_value << 4) + card_value
print(f"{player.name} with cards: {player.hand} has hand value: {hand_value}")
return hand_value
def determine_hand_type(self, hand):
# Sort the hand in descending order based on card values
sorted_hand = sorted(hand, key=lambda card: self.get_card_value(card), reverse=True)
# Check for specific hand types in decreasing order of rank
if self.is_royal_flush(sorted_hand):
return 9 # Royal flush
if self.is_straight_flush(sorted_hand):
return 8 # Straight flush
if self.is_four_of_a_kind(sorted_hand):
return 7 # Four of a kind
if self.is_full_house(sorted_hand):
return 6 # Full house
if self.is_flush(sorted_hand):
return 5 # Flush
if self.is_straight(sorted_hand):
return 4 # Straight
if self.is_three_of_a_kind(sorted_hand):
return 3 # Three of a kind
if self.is_two_pair(sorted_hand):
return 2 # Two pair
if self.is_pair(sorted_hand):
return 1 # Pair
return 0 # High card
def get_card_value(self, card):
# Map card ranks (2, 3, 4, etc.) to their corresponding values (0 to 12)
rank_to_value = {
"2": 0, "3": 1, "4": 2, "5": 3, "6": 4, "7": 5, "8": 6,
"9": 7, "10": 8, "J": 9, "Q": 10, "K": 11, "A": 12
}
rank = card.split()[0] # Extract the rank from the card string
return rank_to_value.get(rank, 0) # Default to 0 for unknown ranks
def get_hand_name(self, hand_type):
# Map hand types to their human-readable names
hand_names = {
9: "Royal flush", 8: "Straight flush", 7: "Four of a kind",
6: "Full house", 5: "Flush", 4: "Straight",
3: "Three of a kind", 2: "Two pair", 1: "Pair", 0: "High card"
}
return hand_names.get(hand_type, "Unknown")
def is_royal_flush(self, hand):
# Check for a Royal flush (A, K, Q, J, 10 of the same suit)
return self.is_straight_flush(hand) and self.get_card_value(hand[0]) == 12
def is_straight_flush(self, hand):
# Check for a Straight flush (five consecutive cards of the same suit)
return self.is_straight(hand) and self.is_flush(hand)
def is_four_of_a_kind(self, hand):
# Check for Four of a kind (four cards of the same rank)
return self.has_n_of_a_kind(hand, 4)
def is_full_house(self, hand):
# Check for a Full house (three cards of one rank and two cards of another rank)
return self.has_n_of_a_kind(hand, 3) and self.has_n_of_a_kind(hand, 2)
def is_flush(self, hand):
# Check for a Flush (five cards of the same suit)
suits = [card.split()[-1] for card in hand]
return all(suit == suits[0] for suit in suits)
def is_straight(self, hand):
# Check for a Straight (five consecutive cards of different suits)
values = [self.get_card_value(card) for card in hand]
values.sort()
return all(values[i] == values[i - 1] + 1 for i in range(1, len(values)))
def is_three_of_a_kind(self, hand):
# Check for Three of a kind (three cards of the same rank)
return self.has_n_of_a_kind(hand, 3)
def is_two_pair(self, hand):
# Check for Two pair (two cards of one rank and two cards of another rank)
ranks = [self.get_card_value(card) for card in hand]
rank_counts = {rank: ranks.count(rank) for rank in set(ranks)}
return list(rank_counts.values()).count(2) == 2
def is_pair(self, hand):
# Check for a Pair (two cards of the same rank)
return self.has_n_of_a_kind(hand, 2)
def has_n_of_a_kind(self, hand, n):
# Helper function to check if there are 'n' cards of the same rank in the hand
ranks = [self.get_card_value(card) for card in hand]
rank_counts = {rank: ranks.count(rank) for rank in set(ranks)}
return n in rank_counts.values()
def get_next_player_index(self, current_index):
next_index = current_index + 1
if next_index >= len(self.players):
next_index = 0
return next_index

11
WareHouse/Poker1_DefaultOrganization_20231006035628/main.py Normal file
View File

@ -0,0 +1,11 @@
'''
Main file for the Texas Hold'em Poker game.
'''
from game import Game
from player import HumanPlayer, AIPlayer
from deck import Deck
def main():
game = Game()
game.start()
if __name__ == "__main__":
main()

98
WareHouse/Poker1_DefaultOrganization_20231006035628/manual.md Normal file
View File

@ -0,0 +1,98 @@
# Texas Hold'em Poker Game User Manual
## Introduction
Welcome to the Texas Hold'em Poker Game! This game allows you to experience the excitement and strategy of playing Texas Hold'em Poker against AI opponents. The game follows the official No Limit Texas Hold'em rules and simulates a poker tournament with 1 human player and 4 AI characters.
## Installation
To install and run the Texas Hold'em Poker Game, please follow these steps:
1. Ensure that you have Python installed on your computer. You can download Python from the official website: https://www.python.org/downloads/
2. Clone or download the game code from the GitHub repository: [link to repository]
3. Open a terminal or command prompt and navigate to the directory where you downloaded the game code.
4. Create a virtual environment (optional but recommended) by running the following command:
```
python -m venv env
```
5. Activate the virtual environment by running the appropriate command for your operating system:
- For Windows:
```
env\Scripts\activate
```
- For macOS and Linux:
```
source env/bin/activate
```
6. Install the required dependencies by running the following command:
```
pip install -r requirements.txt
```
7. You are now ready to play the Texas Hold'em Poker Game!
## Game Instructions
1. Open a terminal or command prompt and navigate to the directory where you downloaded the game code.
2. Activate the virtual environment (if you created one) by running the appropriate command as mentioned in the installation steps.
3. Run the game by executing the following command:
```
python main.py
```
4. The game will start, and you will be prompted to enter your decisions during each betting round. The available decisions are:
- Fold: To fold your hand and exit the current round.
- Check: To pass the betting action to the next player without placing a bet.
- Bet: To place a bet. You will be prompted to enter the bet amount.
- Call: To match the current bet amount.
- Raise: To increase the current bet amount. You will be prompted to enter the raise amount.
5. The AI characters will also make their decisions based on their hand and the community cards. They may occasionally make random decisions to add unpredictability to the game.
6. The game will continue until there is only one player left or until you choose to exit the game.
## Game Features
The Texas Hold'em Poker Game includes the following features:
- Realistic poker experience adhering to the official No Limit Texas Hold'em rules.
- Simulated poker tournament with 1 human player and 4 AI characters.
- Each player starts with $1000 in chips.
- Blinds set at $5 for the small blind and $10 for the big blind.
- Blinds increase according to the World Poker Tour incremental blinds guidelines.
- AI characters make decisions based on basic poker theory, with occasional random decisions.
- Actions available: checking, betting, raising, calling, and folding.
- Accurate tracking of chip counts for all players.
- Management of community cards and the deck.
- Determination of the winner(s) of each hand.
## Algorithm for Increasing Blinds
The algorithm for increasing blinds follows the World Poker Tour incremental blinds guidelines. The blinds increase at regular intervals to maintain a challenging pace. The specific algorithm is as follows:
1. The tournament starts with blinds set at $5 for the small blind and $10 for the big blind.
2. After a certain number of rounds (e.g., every 10 rounds), the blinds increase by a fixed amount (e.g., $5).
3. The new blinds are then applied to the next round and continue to increase at the same fixed amount after each interval.
4. This ensures that the blinds gradually increase over time, creating a more challenging gameplay experience.
## Conclusion
Congratulations! You are now ready to enjoy the Texas Hold'em Poker Game. Have fun playing against the AI characters and test your poker skills. Good luck!

30
WareHouse/Poker1_DefaultOrganization_20231006035628/meta.txt Normal file
View File

@ -0,0 +1,30 @@
Task:
Create a Texas Hold'em Poker game that adheres to the official No Limit Texas Hold'em rules. The game should simulate a poker tournament with 1 human player and 4 AI characters. Each player, including the human player and AI characters, starts with $1000 in chips. The tournament begins with blinds set at $5 for the small blind and $10 for the big blind. The blinds will follow the World Poker Tour incremental blinds guidelines, increasing at regular intervals. Ensure that the blinds increase according to these guidelines to maintain a challenging pace. For AI character decision-making, they should employ basic poker theory for most of their actions, striving to make optimal choices based on their hands and the community cards. However, each AI character should also have the ability to make occasional 'random' decisions, deviating from optimal play to add an element of unpredictability and excitement to the game. The game should provide a realistic poker experience, including actions such as checking, betting, raising, calling, and folding. It should accurately track the chip counts of all players, manage the community cards and the deck, and determine the winner(s) of each hand. Please generate a detailed description and implementation plan for this Texas Hold'em Poker game, specifying how the AI characters will make decisions and interact with the human player. Additionally, outline the algorithm for increasing blinds according to the World Poker Tour guidelines.
Config:
ChatEnvConfig.clear_structure: True
ChatEnvConfig.git_management: False
ChatEnvConfig.gui_design: True
Roster:
Chief Executive Officer, Counselor, Chief Human Resource Officer, Chief Product Officer, Chief Technology Officer, Programmer, Code Reviewer, Software Test Engineer, Chief Creative Officer
Modality:
application
Ideas:
Language:
Python
Code_Version:
7.0
Proposed_images:
0
Incorporated_images:
0

101
WareHouse/Poker1_DefaultOrganization_20231006035628/player.py Normal file
View File

@ -0,0 +1,101 @@
'''
Player module that defines the HumanPlayer and AIPlayer classes.
'''
import sys
import random
class Player:
def __init__(self, name, chips):
self.name = name
self.chips = chips
self.hand = []
self.community_cards = []
self.active = True
self.blind = 0
self.previous_bet = 0
self.is_in_showdown = True
def receive_cards(self, cards):
self.hand.extend(cards)
def receive_community_cards(self, cards):
self.community_cards = cards
def is_active(self):
return self.active
def all_in(self):
tmp = self.chips
self.chips = 0
self.active = False
print(f"{self.name} is All In for {tmp}")
return tmp
def fold(self):
print(f"{self.name} folded.")
self.active = False
self.is_in_showdown = False
def check(self):
prompt = f"{self.name} checked."
print(prompt)
return 0
def call(self, amount):
self.chips -= amount
prompt = f"{self.name} called {amount}. Remaining chips: {self.chips}"
print(prompt)
return amount
def raise_bet(self, amount):
self.chips -= amount
prompt = f"{self.name} raised an additonal {amount}. Remaining chips: {self.chips}"
print(prompt)
return amount
def blind_bet(self, amount):
self.chips -= amount
#self.previous_bet = amount
prompt = f"{self.name} posted blind of {amount}. Remaining chips: {self.chips}"
print(prompt)
return amount
def reset(self):
self.hand = []
self.community_cards = []
self.active = True
self.is_in_showdown = True
class HumanPlayer(Player):
def make_decision(self, current_bet):
cards = ", ".join(self.hand)
prompt = f"Your cards: {cards}"
print(prompt)
prompt = f"Community cards: {self.community_cards}"
print(prompt)
decision = input("Enter your decision (fold/check/bet/call/raise): ")
if decision == "fold" or decision == "check":
return decision
elif decision == "q":
print("Quitting...")
sys.exit() #Goodbye mf
elif decision == "call":
return decision
elif decision == "raise":
return decision
else:
print("Invalid decision. Please enter a valid decision.")
return self.make_decision(current_bet)
def get_raise_amount(self, current_bet):
try:
amount = int(input(f"Enter the raise amount: {current_bet*2} + "))
return amount
except ValueError:
print("Invalid input.")
return self.get_raise_amount(current_bet)
class AIPlayer(Player):
def make_decision(self, current_bet):
if random.random() < 0.05: # 5% chance of making a random decision
return random.choice(["fold", "check", "bet", "call", "raise"])
else:
if current_bet > self.chips:
return random.choice(["call, fold"])
elif current_bet == 0:
return random.choice(["check", "raise"])
elif current_bet > self.previous_bet:
return random.choice(["fold", "call", "raise"])
else:
return random.choice(["check", "call", "raise"])
def get_raise_amount(self, current_bet):
therand = random.randint(0, 100)
print(f"Raise increment: {therand}")
return therand

2
WareHouse/Poker1_DefaultOrganization_20231006035628/requirements.txt Normal file
View File

@ -0,0 +1,2 @@
numpy==1.19.2
pandas>=1.1.4