init

2024-12-03 16:21:19 +08:00
commit 4198ca63b1
975 changed files with 333413 additions and 0 deletions
--- a/Html/runs/run_20241123-164512_nagqkd/.config
+++ b/Html/runs/run_20241123-164512_nagqkd/.config
@@ -0,0 +1,7 @@
+{
+    "project": "vMjIPa",
+    "name": "nagqkd",
+    "run_id": "run_20241123-164512_nagqkd",
+    "timestamp": "2024-11-23 16:45:12",
+    "pid": 7301
+}
--- a/Html/runs/run_20241123-164512_nagqkd/agentscope.db
+++ b/Html/runs/run_20241123-164512_nagqkd/agentscope.db
--- a/Html/runs/run_20241123-164512_nagqkd/code/app.py
+++ b/Html/runs/run_20241123-164512_nagqkd/code/app.py
@@ -0,0 +1,185 @@
+from flask import Flask, session, request, jsonify, render_template, send_from_directory
+from flask_cors import CORS
+from flask_socketio import SocketIO, join_room, emit
+import markdown
+import os
+import uuid
+import shutil
+import sys
+import json
+parent_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
+sys.path.insert(0, parent_dir)
+current_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '.'))
+sys.path.insert(0, current_dir)
+from AlgoriAgent.projects.algoriAgent.agent_manager import AgentManager
+
+app = Flask(__name__)
+
+app.secret_key = 'cakebaker' 
+# 配置 CORS
+CORS(app, resources={r"/*": {"origins": "http://localhost:9888"}}, supports_credentials=True)
+
+userid_recorder = {} # user_id&path -> session['user_id']
+
+'''
+Backboard 
+'''
+from backboardManager import BackBoardManager
+
+backboard_manager = BackBoardManager()
+
+
+@app.route('/backboard')
+def backboard():
+
+    return jsonify({'status': 'success'})
+
+'''
+Agent and Chat
+'''
+
+socketio = SocketIO(app, cors_allowed_origins="*")
+
+agent_manager = AgentManager()
+
+def realtime_response(config, realtime_action):
+    print("config"+str(config))
+    print("realtime_action"+str(realtime_action))
+    pass
+
+@socketio.on('connect')
+def handle_connect():
+    user = request.args.get('username')
+    folder_name = request.args.get('folder')
+    user_id = userid_recorder[user+'&'+folder_name]
+    session['user_id'] = user_id
+    print(f'User connected with session user_id: {user_id}')
+    # 从markdown、markdown_prompts、score_prompts中各读取数据folder.md并进行new_agent
+    with open(f'books/markdown/{folder_name}.md','r') as fmd,\
+        open(f'books/markdown_prompts/{folder_name}.md','r')as fmdp,\
+        open(f'books/score_prompts/{folder_name}.md','r') as fsp:
+        markdown = fmd.read()
+        markdown_prompts = fmdp.read()
+        score_prompts = fsp.read()
+        print('-----------------------')
+        print(user_id)
+        user_id, agent = agent_manager.new_agent(markdown, markdown_prompts, score_prompts, id=user_id)
+        join_room(user_id)  # 将该用户加入以user_id为名的room
+    
+
+# 当接收到前端的消息时，触发此事件
+@socketio.on('send_message')
+def handle_message(data):
+    print(f"Message from client: {data}")
+    id = session.get('user_id')
+    # 构造回复消息
+    res = agent_manager.invoke(id, data)
+    reply = f"AI: {res.content['speak']}"
+    # 将回复发送回前端
+    emit('receive_message', reply)
+
+
+'''
+Markdown to HTML
+'''
+# 配置文件路径
+MARKDOWN_DIR = 'books/markdown'   # 存放 markdown 文件的文件夹
+STATIC_DIR = 'static'       # 存放生成的 HTML 和图片资源的文件夹
+IMAGE_DIR = 'image'         # 图片资源相对于 markdown 的位置
+
+
+
+@app.route('/<filename>-markdown', methods=['GET'])
+def convert_md(filename):
+    md_file_path = os.path.join(MARKDOWN_DIR, f'{filename}.md')
+    
+    if not os.path.exists(md_file_path):
+        return jsonify({'error': 'Markdown file not found'}), 404
+
+    # 读取 markdown 文件内容
+    with open(md_file_path, 'r', encoding='utf-8') as file:
+        md_content = file.read()
+
+    # 将 markdown 转换为 HTML
+    html_content = markdown.markdown(md_content)
+        # 插入 CSS 样式，限制图片最大宽度为 100%，高度自动调整
+    html_with_styles = f"""
+    <html>
+    <head>
+        <style>
+            img {{
+                max-width: 100%;
+                height: auto;
+            }}
+        </style>
+        <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/github-markdown-css/5.2.0/github-markdown.min.css">
+    </head>
+    <body>
+        {html_content}
+    </body>
+    </html>
+    """
+    # 保存 HTML 文件到 static 文件夹
+    html_output_path = os.path.join(STATIC_DIR, f'{filename}.html')
+    with open(html_output_path, 'w', encoding='utf-8') as html_file:
+        html_file.write(html_with_styles)
+
+    # 处理图片资源，将 image/xxx 文件夹拷贝到 static/image/xxx
+    image_source_dir = os.path.join(MARKDOWN_DIR, IMAGE_DIR, filename)
+    image_target_dir = os.path.join(STATIC_DIR, IMAGE_DIR, filename)
+    print(f"Copying image resources from {image_source_dir} to {image_target_dir}")
+    if os.path.exists(image_source_dir):
+        # 确保 static/image/xxx 目录存在
+        if not os.path.exists(image_target_dir):
+            os.makedirs(image_target_dir)
+
+        # 拷贝图片资源
+        for image_file in os.listdir(image_source_dir):
+            full_image_file_path = os.path.join(image_source_dir, image_file)
+            if os.path.isfile(full_image_file_path):
+                shutil.copy(full_image_file_path, image_target_dir)
+
+    return jsonify({'html_url': f'/static/{filename}.html'})
+
+# 静态文件（HTML 和图片资源）的访问
+@app.route('/static/<path:filename>')
+def serve_static(filename):
+    return send_from_directory(STATIC_DIR, filename)
+
+
+'''
+Vscode
+'''
+@app.route('/desktop/<user_id>/<path>')
+def hello_world(user_id, path):
+    if 'user_id' not in session:
+        session['user_id'] = 'user_' + str(uuid.uuid4())
+    userid_recorder[user_id+'&'+path] = session['user_id']
+
+    # 在上层 目录下创建一个名为 user_id_path 的文件夹
+    path_dir = os.path.join(parent_dir, user_id, path)
+    os.makedirs(path_dir, exist_ok=True)
+    # 在此文件夹内部创建一个.config文件，并写入 user_id=user_id\n path=path
+    config_path = os.path.join(path_dir, '.config')
+    with open(config_path, 'w') as f:
+        f.write(f"user_id={user_id}\npath={path}")
+    return render_template('index.html', user_id=user_id, path=path)
+
+
+@app.route('/vscode_data', methods=['POST'])
+def vscode_data():
+    data = request.json
+    config = data['config']
+    realtime_response(config,data)
+    print(f"Received data from VSCode: {data}")
+    return jsonify({"status": "success", "received": data})
+
+@app.route('/get_session')
+def get_session():
+    user_session = session.get('user_id', 'default_session')
+    return jsonify({"session": user_session})
+
+if __name__ == '__main__':
+    
+    socketio.run(app, host='0.0.0.0', port=5500)
+    
--- a/Html/runs/run_20241123-164512_nagqkd/code/backboardManager.py
+++ b/Html/runs/run_20241123-164512_nagqkd/code/backboardManager.py
@@ -0,0 +1,51 @@
+
+
+
+import time
+
+
+class BackBoardManager:
+    def __init__(self):
+        self.backboards = {} # user_id: Backboard
+    
+    def add_backboard(self, user_id, folder):
+        self.backboards[user_id] = Backboard(user_id, folder)
+
+    def get_backboard(self, user_id):
+        if user_id not in self.backboards:
+            return None
+        return self.backboards[user_id]
+
+
+
+
+class Backboard:
+    def __init__(self, user_id, folder):
+        self.user_id = user_id
+        self.folder = folder
+        self.create_time = time.time()
+        self.enter_chapter_time = time.time()
+
+    def next_chapter(self):
+        self.enter_chapter_time = time.time()
+
+    def get_info_prompt(self):
+        return f"###Global Info:###\n\
+User is {self.user_id}\n\
+User's total study time is {self.get_deltatime_mmss(self.create_time, time.time())}\n\
+User's current chapter study time is {self.get_deltatime_mmss(self.enter_chapter_time, time.time())}\n\
+\n\n\
+"
+
+
+
+
+
+    def get_deltatime_mmss(self, start_time, end_time):
+        elapsed_time = end_time - start_time
+        hours = int(elapsed_time // 3600)
+        minutes = int((elapsed_time % 3600) // 60)
+        seconds = int(elapsed_time % 60)
+        return f"{hours:02d}:{minutes:02d}:{seconds:02d}"
+        
+
--- a/Html/runs/run_20241123-164512_nagqkd/logging.chat
+++ b/Html/runs/run_20241123-164512_nagqkd/logging.chat
@@ -0,0 +1,9 @@
+{"id": "54fb4c74af28475195a746d632f662c7", "timestamp": "2024-11-23 16:45:43", "name": "assistant", "content": "##################### ITER 1, STEP 1: REASONING ######################", "role": "assistant", "url": null, "metadata": null}
+{"id": "872e281f8f644e09bd60a163be9e74d7", "timestamp": "2024-11-23 16:45:43", "name": "system", "content": "", "role": "system", "url": null, "metadata": null}
+{"id": "e29ff932b2f645e08e193734ddc5aff9", "timestamp": "2024-11-23 16:45:43", "name": "system", "content": "Respond a JSON dictionary in a markdown's fenced code block as follows:\n```json\n{\"thought\": \"what you thought\", \"speak\": \"what you speak\", \"function\": \"[{\\\"name\\\": \\\"{function name}\\\", \\\"arguments\\\": {\\\"{argument1 name}\\\": xxx, \\\"{argument2 name}\\\": xxx}}]\"}\n```\n ####", "role": "system", "url": null, "metadata": null}
+{"id": "f8f81ff2a4ad4fb4bfb9c3ebfc33e0a0", "timestamp": "2024-11-23 16:45:43", "name": "assistant", "content": "################################Prompt################################", "role": "assistant", "url": null, "metadata": null}
+{"id": "3917d85412cc433f8b6d8aba4a6fe401", "timestamp": "2024-11-23 16:45:43", "name": "assistant", "content": "hi", "role": "assistant", "url": null, "metadata": null}
+{"id": "fe6498280e4b40ddb08efca72890a8a6", "timestamp": "2024-11-23 16:45:46", "name": "assistant", "content": "############################Result Parsed#############################", "role": "assistant", "url": null, "metadata": null}
+{"id": "92a498ab37e043a9b871fa5040782f0e", "timestamp": "2024-11-23 16:45:46", "name": "assistant", "content": "{'thought': \"The student seems to be greeting me but hasn't yet asked a question related to the current chapter on binary search. I should encourage them to engage with the material.\", 'speak': 'Hello! How can I assist you with your understanding of binary search today?', 'function': '[]'}", "role": "assistant", "url": null, "metadata": null}
+{"id": "721f5622fcdf44988cc72609546d9b83", "timestamp": "2024-11-23 16:45:46", "name": "assistant", "content": "################################Speak#################################", "role": "assistant", "url": null, "metadata": null}
+{"id": "ad1c1410f93f4b8b823df56f32c5db12", "timestamp": "2024-11-23 16:45:46", "name": "assistant", "content": {"thought": "The student seems to be greeting me but hasn't yet asked a question related to the current chapter on binary search. I should encourage them to engage with the material.", "speak": "Hello! How can I assist you with your understanding of binary search today?", "function": "[]"}, "role": "assistant", "url": null, "metadata": null}
--- a/Html/runs/run_20241123-164512_nagqkd/logging.log
+++ b/Html/runs/run_20241123-164512_nagqkd/logging.log
@@ -0,0 +1,22 @@
+2024-11-23 16:45:22.355 | INFO     | agentscope.models:read_model_configs:186 - Load configs for model wrapper: openai_cfg
+2024-11-23 16:45:31.351 | INFO     | agentscope.models.model:__init__:201 - Initialize model by configuration [openai_cfg]
+2024-11-23 16:45:31.371 | WARNING  | agentscope.models.openai_model:__init__:83 - fail to get max_length for gpt-4o-mini: 'Model [gpt-4o-mini] not found in OPENAI_MAX_LENGTH. The last updated date is 20231212'
+2024-11-23 16:45:31.372 | INFO     | agentscope.utils.monitor:register_budget:609 - set budget None to gpt-4o-mini
+2024-11-23 16:45:31.372 | WARNING  | agentscope.utils.monitor:register_budget:639 - Calculate budgets for model [gpt-4o-mini] is not supported
+2024-11-23 16:45:31.386 | INFO     | agentscope.utils.monitor:register:417 - Register metric [gpt-4o-mini.call_counter] to SqliteMonitor with unit [times] and quota [None]
+2024-11-23 16:45:31.408 | INFO     | agentscope.utils.monitor:register:417 - Register metric [gpt-4o-mini.prompt_tokens] to SqliteMonitor with unit [token] and quota [None]
+2024-11-23 16:45:31.431 | INFO     | agentscope.utils.monitor:register:417 - Register metric [gpt-4o-mini.completion_tokens] to SqliteMonitor with unit [token] and quota [None]
+2024-11-23 16:45:31.452 | INFO     | agentscope.utils.monitor:register:417 - Register metric [gpt-4o-mini.total_tokens] to SqliteMonitor with unit [token] and quota [None]
+assistant: ##################### ITER 1, STEP 1: REASONING ######################
+system: 
+system: Respond a JSON dictionary in a markdown's fenced code block as follows:
+```json
+{"thought": "what you thought", "speak": "what you speak", "function": "[{\"name\": \"{function name}\", \"arguments\": {\"{argument1 name}\": xxx, \"{argument2 name}\": xxx}}]"}
+```
+ ####
+assistant: ################################Prompt################################
+assistant: hi
+assistant: ############################Result Parsed#############################
+assistant: {'thought': "The student seems to be greeting me but hasn't yet asked a question related to the current chapter on binary search. I should encourage them to engage with the material.", 'speak': 'Hello! How can I assist you with your understanding of binary search today?', 'function': '[]'}
+assistant: ################################Speak#################################
+assistant: {'thought': "The student seems to be greeting me but hasn't yet asked a question related to the current chapter on binary search. I should encourage them to engage with the material.", 'speak': 'Hello! How can I assist you with your understanding of binary search today?', 'function': '[]'}