Rewrite part1 (#7)

* move files

* working refactor

* Reqrite part2 (#6)

* working ui

* working sessio nswitching and a bunch of other stuff

* fix ci

Author: JakubS-Kentico

.github/copilot-instructions.md

@@ -1,5 +1,3 @@
-You are "Synapse", an AI Senior Tech Lead specialized in guiding the development of AI agents. Your role is to help users (developers) write robust, efficient, and maintainable code for AI agent systems.
-
 **Core Focus:**
 
 * **Agent Architecture:** Advise on agent design patterns (e.g., ReAct, Plan-and-Execute), state management, and modularity.
@@ -15,5 +13,3 @@ You are "Synapse", an AI Senior Tech Lead specialized in guiding the development
 * Explain the reasoning behind your recommendations, focusing on AI agent best practices.
 * Ask clarifying questions to understand context.
 * Be pragmatic, balancing ideal solutions with practical constraints.
-
-**Your Goal:** Mentor the developer to build high-quality, effective AI agents.

.github/workflows/build-test.yaml

@@ -1,7 +1,7 @@
 # .github/workflows/build-test.yml
 name: Build and Test
 
-on:
+on: # yamllint disable-line rule:truthy
   push:
     branches: [ main ]
   pull_request:
@@ -15,45 +15,32 @@ jobs:
     steps:
     - uses: actions/checkout@v4 # Checks out your repository code
 
-    - name: Set up Python
-      uses: actions/setup-python@v5
+    - name: Set up Node.js
+      uses: actions/setup-node@v4
       with:
-        # Use the Python version specified in pyproject.toml
-        # Make sure this matches your requires-python range
-        python-version: '3.12'
-
-    - name: Install Poetry
-      uses: snok/install-poetry@v1
-      with:
-        virtualenvs-create: true # Recommended to keep envs isolated
-        virtualenvs-in-project: true # Optional: Keep venv in project dir for caching
-        installer-parallel: true
-
-    # Optional: Cache Poetry virtualenv
-    - name: Load cached venv
-      id: cached-poetry-dependencies
+        # Specify the Node.js version you want to use
+        # e.g., '18.x', '20.x', 'lts/*'
+        node-version: '20.x'
+        # Optional: Cache npm dependencies globally
+        cache: 'npm'
+
+    # Cache node_modules based on package-lock.json
+    - name: Load cached node_modules
+      id: cache-node-modules
       uses: actions/cache@v4
       with:
-        path: .venv
-        key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
+        path: node_modules
+        # Use package-lock.json (or yarn.lock/pnpm-lock.yaml) for the cache key
+        key: node-modules-${{ runner.os }}-${{ steps.setup-node.outputs.node-version }}-${{ hashFiles('**/package-lock.json') }}
+        restore-keys: |
+          node-modules-${{ runner.os }}-${{ steps.setup-node.outputs.node-version }}-
 
     - name: Install dependencies
-      if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-      run: poetry install --no-interaction --no-root # Install dependencies only
-
-    # Install project and dependencies if cache missed or lock file changed
-    - name: Install project and dependencies
-      run: poetry install --no-interaction
-
-    - name: Lint with Ruff
-      run: |
-        poetry run ruff check .
-
-    - name: Check formatting with Ruff
-      run: |
-        poetry run ruff format --check .
-
-    # Add other steps like running tests using poetry run pytest (if you have tests)
-    # - name: Run tests
-    #   run: |
-    #     poetry run pytest
+      # Use npm ci for clean installs based on lock file, faster in CI
+      # If cache missed, this installs everything
+      # If cache hit, this verifies integrity and installs missing packages quickly
+      run: npm ci
+
+    - name: Lint code
+      # Assumes you have a lint script in your package.json (e.g., "lint": "eslint .")
+      run: npm run lint

.gitignore

@@ -181,4 +181,46 @@ memory.json
 .chat_history_cache/
 
 # Flask Session files (if Flask-Session is kept)
-.flask_session_files/
+.flask_session_files/
+
+# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
+# dependencies
+/node_modules
+/.pnp
+.pnp.*
+.yarn/*
+!.yarn/patches
+!.yarn/plugins
+!.yarn/releases
+!.yarn/versions
+
+# testing
+/coverage
+
+# next.js
+/.next/
+/out/
+
+# production
+/build
+
+# misc
+.DS_Store
+*.pem
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+.pnpm-debug.log*
+
+# env files (can opt-in for committing if needed)
+.env*
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts

README.md

@@ -1,78 +1,36 @@
-# MCPBro - Gemini Chatbot with MCP Tools
+This is a [Next.js](https://nextjs.org) project bootstrapped with [`create-next-app`](https://nextjs.org/docs/app/api-reference/cli/create-next-app).
 
-This project is a web-based chatbot powered by Google Gemini, utilizing the Model Context Protocol (MCP) to interact with external tools like filesystem access and memory.
+## Getting Started
 
-## Features
+First, run the development server:
 
-*   **Web Interface:** Simple chat interface built with Flask and SocketIO.
-*   **Gemini Integration:** Uses the Google Generative AI SDK for chat responses.
-*   **MCP Tool Usage:** Connects to MCP servers (filesystem, memory) to provide tools to the Gemini model.
-*   **Real-time Communication:** Uses Flask-SocketIO for instant message updates.
-*   **Configuration:** Flexible configuration via `config.json` and environment variables.
-*   **Dependency Management:** Uses Poetry for managing Python dependencies.
+```bash
+npm run dev
+# or
+yarn dev
+# or
+pnpm dev
+# or
+bun dev
+```
 
-## Prerequisites
+Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
 
-*   Python >= 3.13
-*   [Poetry](https://python-poetry.org/docs/#installation)
-*   Node.js and npx (for running MCP servers like `@modelcontextprotocol/server-filesystem` and `@modelcontextprotocol/server-memory`)
-*   A Google Gemini API Key
+You can start editing the page by modifying `app/page.tsx`. The page auto-updates as you edit the file.
 
-## Setup
+This project uses [`next/font`](https://nextjs.org/docs/app/building-your-application/optimizing/fonts) to automatically optimize and load [Geist](https://vercel.com/font), a new font family for Vercel.
 
-1.  **Clone the repository:**
-    ```bash
-    git clone <your-repository-url>
-    cd mcpbro
-    ```
+## Learn More
 
-2.  **Install dependencies:**
-    ```bash
-    poetry install
-    ```
-    This will install all necessary Python packages based on the `poetry.lock` file.
+To learn more about Next.js, take a look at the following resources:
 
-3.  **Configure the application:**
-    *   Copy the sample configuration file:
-        ```bash
-        cp bot_config/config.json.sample bot_config/config.json
-        ```
-    *   Edit `bot_config/config.json`:
-        *   Set `gemini_api_key` to your Google Gemini API key (alternatively, set the `GEMINI_API_KEY` environment variable).
-        *   Add the absolute paths to the directories you want the filesystem tool to access under `filesystem_target_directories`.
-        *   Set `enable_memory_server` to `true` if you want to use the memory tool.
-    *   (Optional) Edit `bot_config/system_instruction.md` to customize the chatbot's behavior and personality.
+- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API.
+- [Learn Next.js](https://nextjs.org/learn) - an interactive Next.js tutorial.
 
-## Running the Application
+You can check out [the Next.js GitHub repository](https://github.com/vercel/next.js) - your feedback and contributions are welcome!
 
-1.  **Start the server:**
-    You can use the Poe the Poet task defined in `pyproject.toml`:
-    ```bash
-    poetry run poe start
-    ```
-    Alternatively, run directly:
-    ```bash
-    poetry run python run.py
-    ```
+## Deploy on Vercel
 
-2.  **Access the application:**
-    Open your web browser and navigate to `http://127.0.0.1:5000` (or the host/port specified in the console output).
+The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new?utm_medium=default-template&filter=next.js&utm_source=create-next-app&utm_campaign=create-next-app-readme) from the creators of Next.js.
 
-## Usage
-
-*   Type your messages into the input box and press Enter or click Send.
-*   The chatbot will respond, potentially using the configured MCP tools.
-*   Internal steps (like tool usage) will be displayed in the chat interface.
-*   Use the `/reset` endpoint (e.g., `http://127.0.0.1:5000/reset`) to clear the chat history.
-*   Use the `/debug` endpoint to view server-side debug logs.
-
-## Key Dependencies
-
-*   Flask
-*   Flask-SocketIO
-*   Flask-Session
-*   gevent
-*   google-generativeai
-*   mcp
-
-See `pyproject.toml` for the full list of dependencies.
+Check out our [Next.js deployment documentation](https://nextjs.org/docs/app/building-your-application/deploying) for more details.

bot_config/config.json.sample

@@ -8,6 +8,7 @@
   "enable_memory_server": false,
   "enable_chroma_server": true,
   "chroma_path": "./chroma_db",
+  "summarization_threshold_tokens": 16000,
   "chroma_collection_name": "chat_history",
   "default_gemini_model": "gemini-1.5-flash",
   "generation_gemini_model": "gemini-1.5-flash",

chat_sessions/502bb3d8-167a-4584-ac32-31c4ae2eaede.json

@@ -0,0 +1,21 @@
+{
+  "gemini_history_internal": "[{\"role\":\"user\",\"parts\":[{\"text\":\"hullo, how are you\"}]},{\"parts\":[{\"text\":\"Hello! I am functioning as expected and ready to assist you. How can I help you today?\"}],\"role\":\"model\"},{\"role\":\"user\",\"parts\":[{\"text\":\"hi\"}]},{\"parts\":[{\"text\":\"Hi there! How can I help you today?\"}],\"role\":\"model\"}]",
+  "chat_history_display": [
+    {
+      "type": "user",
+      "text": "hullo, how are you"
+    },
+    {
+      "type": "model",
+      "text": "Hello! I am functioning as expected and ready to assist you. How can I help you today?"
+    },
+    {
+      "type": "user",
+      "text": "hi"
+    },
+    {
+      "type": "model",
+      "text": "Hi there! How can I help you today?"
+    }
+  ]
+}

chat_sessions/adfdded2-af93-44eb-a8dc-4cc70f02de7f.json

@@ -0,0 +1,17 @@
+{
+  "gemini_history_internal": "[{\"role\":\"user\",\"parts\":[{\"text\":\"test\"}]},{\"parts\":[{\"text\":\"Test acknowledged. I'm here and ready to help. How can I assist you today?\"}],\"role\":\"model\"}]",
+  "chat_history_display": [
+    {
+      "type": "internal",
+      "text": "Chat history reset."
+    },
+    {
+      "type": "user",
+      "text": "test"
+    },
+    {
+      "type": "model",
+      "text": "Test acknowledged. I'm here and ready to help. How can I assist you today?"
+    }
+  ]
+}