Compare commits
11 Commits
claude
...
ebd2582b92
Author | SHA1 | Date | |
---|---|---|---|
ebd2582b92
|
|||
79d1e1943f
|
|||
76d90c7cf7
|
|||
06fb70fffa
|
|||
62f941a958
|
|||
98ca92d85d
|
|||
1c555a706b
|
|||
7c3b05501f
|
|||
a7b61fe07d
|
|||
9866da625d
|
|||
797ae7ef69
|
21
.claude/settings.local.json
Normal file
21
.claude/settings.local.json
Normal file
@ -0,0 +1,21 @@
|
||||
{
|
||||
"permissions": {
|
||||
"allow": [
|
||||
"Bash(mv:*)",
|
||||
"Bash(mkdir:*)",
|
||||
"Bash(chmod:*)",
|
||||
"Bash(git submodule:*)",
|
||||
"Bash(source:*)",
|
||||
"Bash(pip install:*)",
|
||||
"Bash(/Users/syui/.config/syui/ai/gpt/venv/bin/aigpt shell)",
|
||||
"Bash(/Users/syui/.config/syui/ai/gpt/venv/bin/aigpt server --model qwen2.5-coder:7b --port 8001)",
|
||||
"Bash(/Users/syui/.config/syui/ai/gpt/venv/bin/python -c \"import fastapi_mcp; help(fastapi_mcp.FastApiMCP)\")",
|
||||
"Bash(find:*)",
|
||||
"Bash(/Users/syui/.config/syui/ai/gpt/venv/bin/pip install -e .)",
|
||||
"Bash(/Users/syui/.config/syui/ai/gpt/venv/bin/aigpt fortune)",
|
||||
"Bash(lsof:*)",
|
||||
"Bash(/Users/syui/.config/syui/ai/gpt/venv/bin/python -c \"\nfrom src.aigpt.mcp_server import AIGptMcpServer\nfrom pathlib import Path\nimport uvicorn\n\ndata_dir = Path.home() / '.config' / 'syui' / 'ai' / 'gpt' / 'data'\ndata_dir.mkdir(parents=True, exist_ok=True)\n\ntry:\n server = AIGptMcpServer(data_dir)\n print('MCP Server created successfully')\n print('Available endpoints:', [route.path for route in server.app.routes])\nexcept Exception as e:\n print('Error:', e)\n import traceback\n traceback.print_exc()\n\")"
|
||||
],
|
||||
"deny": []
|
||||
}
|
||||
}
|
5
.env.example
Normal file
5
.env.example
Normal file
@ -0,0 +1,5 @@
|
||||
# OpenAI API Key (required for OpenAI provider)
|
||||
OPENAI_API_KEY=your-api-key-here
|
||||
|
||||
# Ollama settings (optional)
|
||||
OLLAMA_HOST=http://localhost:11434
|
2
.gitignore
vendored
2
.gitignore
vendored
@ -2,6 +2,6 @@
|
||||
**.lock
|
||||
output.json
|
||||
config/*.db
|
||||
aigpt
|
||||
mcp/scripts/__*
|
||||
data
|
||||
__pycache__
|
||||
|
7
.gitmodules
vendored
Normal file
7
.gitmodules
vendored
Normal file
@ -0,0 +1,7 @@
|
||||
[submodule "shell"]
|
||||
path = shell
|
||||
url = git@git.syui.ai:ai/shell
|
||||
[submodule "card"]
|
||||
path = card
|
||||
url = git@git.syui.ai:ai/card
|
||||
branch = claude
|
13
Cargo.toml
13
Cargo.toml
@ -1,13 +0,0 @@
|
||||
[package]
|
||||
name = "aigpt"
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
reqwest = { version = "*", features = ["json"] }
|
||||
serde = { version = "*", features = ["derive"] }
|
||||
serde_json = "*"
|
||||
tokio = { version = "*", features = ["full"] }
|
||||
clap = { version = "*", features = ["derive"] }
|
||||
shellexpand = "*"
|
||||
fs_extra = "*"
|
134
DEVELOPMENT_STATUS.md
Normal file
134
DEVELOPMENT_STATUS.md
Normal file
@ -0,0 +1,134 @@
|
||||
# ai.gpt 開発状況 (2025/01/06 更新)
|
||||
|
||||
## 現在の状態
|
||||
|
||||
### ✅ 実装済み機能
|
||||
|
||||
1. **基本システム**
|
||||
- 階層的記憶システム(完全ログ→要約→コア→忘却)
|
||||
- 不可逆的な関係性システム(broken状態は修復不可)
|
||||
- AI運勢による日々の人格変動
|
||||
- 時間減衰による自然な関係性変化
|
||||
|
||||
2. **CLI機能**
|
||||
- `chat` - AIとの会話(Ollama/OpenAI対応)
|
||||
- `status` - 状態確認
|
||||
- `fortune` - AI運勢確認
|
||||
- `relationships` - 関係一覧
|
||||
- `transmit` - 送信チェック(現在はprint出力)
|
||||
- `maintenance` - 日次メンテナンス
|
||||
- `config` - 設定管理
|
||||
- `schedule` - スケジューラー管理
|
||||
- `server` - MCP Server起動
|
||||
- `shell` - インタラクティブシェル(ai.shell統合)
|
||||
|
||||
3. **データ管理**
|
||||
- 保存場所: `~/.config/aigpt/`
|
||||
- 設定: `config.json`
|
||||
- データ: `data/` ディレクトリ内の各種JSONファイル
|
||||
|
||||
4. **スケジューラー**
|
||||
- Cron形式とインターバル形式対応
|
||||
- 5種類のタスクタイプ実装済み
|
||||
- バックグラウンド実行可能
|
||||
|
||||
5. **MCP Server**
|
||||
- 14種類のツールを公開(ai.gpt: 9種類、ai.shell: 5種類)
|
||||
- Claude Desktopなどから利用可能
|
||||
- ai.card統合オプション(--enable-card)
|
||||
|
||||
6. **ai.shell統合**
|
||||
- インタラクティブシェルモード
|
||||
- シェルコマンド実行(!command形式)
|
||||
- AIコマンド(analyze, generate, explain)
|
||||
- aishell.md読み込み機能
|
||||
- 高度な補完機能(prompt-toolkit)
|
||||
|
||||
## 🚧 未実装・今後の課題
|
||||
|
||||
### 短期的課題
|
||||
|
||||
1. **自律送信の実装**
|
||||
- 現在: コンソールにprint出力
|
||||
- TODO: atproto (Bluesky) への実際の投稿機能
|
||||
- 参考: ai.bot (Rust/seahorse) との連携も検討
|
||||
|
||||
2. **テストの追加**
|
||||
- 単体テスト
|
||||
- 統合テスト
|
||||
- CI/CDパイプライン
|
||||
|
||||
3. **エラーハンドリングの改善**
|
||||
- より詳細なエラーメッセージ
|
||||
- リトライ機構
|
||||
|
||||
### 中期的課題
|
||||
|
||||
1. **ai.botとの連携**
|
||||
- Rust側のAPIエンドポイント作成
|
||||
- 送信機能の委譲
|
||||
|
||||
2. **より高度な記憶要約**
|
||||
- 現在: シンプルな要約
|
||||
- TODO: AIによる意味的な要約
|
||||
|
||||
3. **Webダッシュボード**
|
||||
- 関係性の可視化
|
||||
- 記憶の管理UI
|
||||
|
||||
### 長期的課題
|
||||
|
||||
1. **他のsyuiプロジェクトとの統合**
|
||||
- ai.card: カードゲームとの連携
|
||||
- ai.verse: メタバース内でのNPC人格
|
||||
- ai.os: システムレベルでの統合
|
||||
|
||||
2. **分散化**
|
||||
- atproto上でのデータ保存
|
||||
- ユーザーデータ主権の完全実現
|
||||
|
||||
## 次回開発時のエントリーポイント
|
||||
|
||||
### 1. 自律送信を実装する場合
|
||||
```python
|
||||
# src/aigpt/transmission.py を編集
|
||||
# atproto-python ライブラリを追加
|
||||
# _handle_transmission_check() メソッドを更新
|
||||
```
|
||||
|
||||
### 2. ai.botと連携する場合
|
||||
```python
|
||||
# 新規ファイル: src/aigpt/bot_connector.py
|
||||
# ai.botのAPIエンドポイントにHTTPリクエスト
|
||||
```
|
||||
|
||||
### 3. テストを追加する場合
|
||||
```bash
|
||||
# tests/ディレクトリを作成
|
||||
# pytest設定を追加
|
||||
```
|
||||
|
||||
### 4. ai.shellの問題を修正する場合
|
||||
```python
|
||||
# src/aigpt/cli.py の shell コマンド
|
||||
# prompt-toolkitのターミナル検出問題を回避
|
||||
# 代替: simple input() または click.prompt()
|
||||
```
|
||||
|
||||
## 設計思想の要点(AI向け)
|
||||
|
||||
1. **唯一性(yui system)**: 各ユーザーとAIの関係は1:1で、改変不可能
|
||||
2. **不可逆性**: 関係性の破壊は修復不可能(現実の人間関係と同じ)
|
||||
3. **階層的記憶**: ただのログではなく、要約・コア判定・忘却のプロセス
|
||||
4. **環境影響**: AI運勢による日々の人格変動(固定的でない)
|
||||
5. **段階的実装**: まずCLI print → atproto投稿 → ai.bot連携
|
||||
|
||||
## 現在のコードベースの理解
|
||||
|
||||
- **言語**: Python (typer CLI, fastapi_mcp)
|
||||
- **AI統合**: Ollama (ローカル) / OpenAI API
|
||||
- **データ形式**: JSON(将来的にSQLite検討)
|
||||
- **認証**: atproto DID(未実装だが設計済み)
|
||||
- **統合**: ai.shell(Rust版から移行)、ai.card(MCP連携)
|
||||
|
||||
このファイルを参照することで、次回の開発がスムーズに始められます。
|
255
README.md
Normal file
255
README.md
Normal file
@ -0,0 +1,255 @@
|
||||
# ai.gpt - 自律的送信AI
|
||||
|
||||
存在子理論に基づく、関係性によって自発的にメッセージを送信するAIシステム。
|
||||
|
||||
## 中核概念
|
||||
|
||||
- **唯一性**: atproto DIDと1:1で紐付き、改変不可能な人格
|
||||
- **不可逆性**: 関係性が壊れたら修復不可能(現実の人間関係と同じ)
|
||||
- **記憶の階層**: 完全ログ→AI要約→コア判定→選択的忘却
|
||||
- **AI運勢**: 1-10のランダム値による日々の人格変動
|
||||
|
||||
## インストール
|
||||
|
||||
```bash
|
||||
# Python仮想環境を推奨
|
||||
python -m venv venv
|
||||
source venv/bin/activate # Windows: venv\Scripts\activate
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
## 設定
|
||||
|
||||
### APIキーの設定
|
||||
```bash
|
||||
# OpenAI APIキー
|
||||
aigpt config set providers.openai.api_key sk-xxxxx
|
||||
|
||||
# atproto認証情報(将来の自動投稿用)
|
||||
aigpt config set atproto.handle your.handle
|
||||
aigpt config set atproto.password your-password
|
||||
|
||||
# 設定一覧を確認
|
||||
aigpt config list
|
||||
```
|
||||
|
||||
### データ保存場所
|
||||
- 設定: `~/.config/syui/ai/gpt/config.json`
|
||||
- データ: `~/.config/syui/ai/gpt/data/`
|
||||
|
||||
## 使い方
|
||||
|
||||
### 会話する
|
||||
```bash
|
||||
aigpt chat "did:plc:xxxxx" "こんにちは、今日はどんな気分?"
|
||||
```
|
||||
|
||||
### ステータス確認
|
||||
```bash
|
||||
# AI全体の状態
|
||||
aigpt status
|
||||
|
||||
# 特定ユーザーとの関係
|
||||
aigpt status "did:plc:xxxxx"
|
||||
```
|
||||
|
||||
### 今日の運勢
|
||||
```bash
|
||||
aigpt fortune
|
||||
```
|
||||
|
||||
### 自律送信チェック
|
||||
```bash
|
||||
# ドライラン(確認のみ)
|
||||
aigpt transmit
|
||||
|
||||
# 実行
|
||||
aigpt transmit --execute
|
||||
```
|
||||
|
||||
### 日次メンテナンス
|
||||
```bash
|
||||
aigpt maintenance
|
||||
```
|
||||
|
||||
### 関係一覧
|
||||
```bash
|
||||
aigpt relationships
|
||||
```
|
||||
|
||||
## データ構造
|
||||
|
||||
デフォルトでは `~/.config/syui/ai/gpt/` に以下のファイルが保存されます:
|
||||
|
||||
- `memories.json` - 会話記憶
|
||||
- `conversations.json` - 会話ログ
|
||||
- `relationships.json` - 関係性パラメータ
|
||||
- `fortunes.json` - AI運勢履歴
|
||||
- `transmissions.json` - 送信履歴
|
||||
- `persona_state.json` - 人格状態
|
||||
|
||||
## 関係性の仕組み
|
||||
|
||||
- スコア0-200の範囲で変動
|
||||
- 100を超えると送信機能が解禁
|
||||
- 時間経過で自然減衰
|
||||
- 大きなネガティブな相互作用で破壊される可能性
|
||||
|
||||
## ai.shell統合
|
||||
|
||||
インタラクティブシェルモード(Claude Code風の体験):
|
||||
|
||||
```bash
|
||||
aigpt shell
|
||||
|
||||
# シェル内で使えるコマンド:
|
||||
# help - コマンド一覧
|
||||
# !<command> - シェルコマンド実行(例: !ls, !pwd)
|
||||
# analyze <file> - ファイルをAIで分析
|
||||
# generate <desc> - コード生成
|
||||
# explain <topic> - 概念の説明
|
||||
# load - aishell.mdプロジェクトファイルを読み込み
|
||||
# status - AI状態確認
|
||||
# fortune - AI運勢確認
|
||||
# clear - 画面クリア
|
||||
# exit/quit - 終了
|
||||
|
||||
# 通常のメッセージも送れます
|
||||
ai.shell> こんにちは、今日は何をしましょうか?
|
||||
```
|
||||
|
||||
## MCP Server
|
||||
|
||||
### サーバー起動
|
||||
```bash
|
||||
# Ollamaを使用(デフォルト)
|
||||
aigpt server --model qwen2.5 --provider ollama
|
||||
|
||||
# OpenAIを使用
|
||||
aigpt server --model gpt-4o-mini --provider openai
|
||||
|
||||
# カスタムポート
|
||||
aigpt server --port 8080
|
||||
|
||||
# ai.card統合を有効化
|
||||
aigpt server --enable-card
|
||||
```
|
||||
|
||||
### AIプロバイダーを使った会話
|
||||
```bash
|
||||
# Ollamaで会話
|
||||
aigpt chat "did:plc:xxxxx" "こんにちは" --provider ollama --model qwen2.5
|
||||
|
||||
# OpenAIで会話
|
||||
aigpt chat "did:plc:xxxxx" "今日の調子はどう?" --provider openai --model gpt-4o-mini
|
||||
```
|
||||
|
||||
### MCP Tools
|
||||
|
||||
サーバーが起動すると、以下のツールがAIから利用可能になります:
|
||||
|
||||
**ai.gpt ツール:**
|
||||
- `get_memories` - アクティブな記憶を取得
|
||||
- `get_relationship` - 特定ユーザーとの関係を取得
|
||||
- `get_all_relationships` - すべての関係を取得
|
||||
- `get_persona_state` - 現在の人格状態を取得
|
||||
- `process_interaction` - ユーザーとの対話を処理
|
||||
- `check_transmission_eligibility` - 送信可能かチェック
|
||||
- `get_fortune` - 今日の運勢を取得
|
||||
- `summarize_memories` - 記憶を要約
|
||||
- `run_maintenance` - メンテナンス実行
|
||||
|
||||
**ai.shell ツール:**
|
||||
- `execute_command` - シェルコマンド実行
|
||||
- `analyze_file` - ファイルのAI分析
|
||||
- `write_file` - ファイル書き込み
|
||||
- `read_project_file` - プロジェクトファイル読み込み
|
||||
- `list_files` - ファイル一覧
|
||||
|
||||
**ai.card ツール(--enable-card時):**
|
||||
- `get_user_cards` - ユーザーのカード取得
|
||||
- `draw_card` - カードを引く(ガチャ)
|
||||
- `get_card_details` - カード詳細情報
|
||||
- `sync_cards_atproto` - atproto同期
|
||||
- `analyze_card_collection` - コレクション分析
|
||||
|
||||
## 環境変数
|
||||
|
||||
`.env`ファイルを作成して設定:
|
||||
|
||||
```bash
|
||||
cp .env.example .env
|
||||
# OpenAI APIキーを設定
|
||||
```
|
||||
|
||||
## スケジューラー機能
|
||||
|
||||
### タスクの追加
|
||||
|
||||
```bash
|
||||
# 6時間ごとに送信チェック
|
||||
aigpt schedule add transmission_check "0 */6 * * *" --provider ollama --model qwen2.5
|
||||
|
||||
# 30分ごとに送信チェック(インターバル形式)
|
||||
aigpt schedule add transmission_check "30m"
|
||||
|
||||
# 毎日午前3時にメンテナンス
|
||||
aigpt schedule add maintenance "0 3 * * *"
|
||||
|
||||
# 1時間ごとに関係性減衰
|
||||
aigpt schedule add relationship_decay "1h"
|
||||
|
||||
# 毎週月曜日に記憶要約
|
||||
aigpt schedule add memory_summary "0 0 * * MON"
|
||||
```
|
||||
|
||||
### タスク管理
|
||||
|
||||
```bash
|
||||
# タスク一覧
|
||||
aigpt schedule list
|
||||
|
||||
# タスクを無効化
|
||||
aigpt schedule disable --task-id transmission_check_1234567890
|
||||
|
||||
# タスクを有効化
|
||||
aigpt schedule enable --task-id transmission_check_1234567890
|
||||
|
||||
# タスクを削除
|
||||
aigpt schedule remove --task-id transmission_check_1234567890
|
||||
```
|
||||
|
||||
### スケジューラーデーモンの起動
|
||||
|
||||
```bash
|
||||
# バックグラウンドでスケジューラーを実行
|
||||
aigpt schedule run
|
||||
```
|
||||
|
||||
### スケジュール形式
|
||||
|
||||
**Cron形式**:
|
||||
- `"0 */6 * * *"` - 6時間ごと
|
||||
- `"0 0 * * *"` - 毎日午前0時
|
||||
- `"*/5 * * * *"` - 5分ごと
|
||||
|
||||
**インターバル形式**:
|
||||
- `"30s"` - 30秒ごと
|
||||
- `"5m"` - 5分ごと
|
||||
- `"2h"` - 2時間ごと
|
||||
- `"1d"` - 1日ごと
|
||||
|
||||
### タスクタイプ
|
||||
|
||||
- `transmission_check` - 送信可能なユーザーをチェックして自動送信
|
||||
- `maintenance` - 日次メンテナンス(忘却、コア記憶判定など)
|
||||
- `fortune_update` - AI運勢の更新
|
||||
- `relationship_decay` - 関係性の時間減衰
|
||||
- `memory_summary` - 記憶の要約作成
|
||||
|
||||
## 次のステップ
|
||||
|
||||
- atprotoへの実送信機能実装
|
||||
- systemdサービス化
|
||||
- Docker対応
|
||||
- Webダッシュボード
|
63
aishell.md
Normal file
63
aishell.md
Normal file
@ -0,0 +1,63 @@
|
||||
# ai.shell プロジェクト仕様書
|
||||
|
||||
## 概要
|
||||
ai.shellは、AIを活用したインタラクティブなシェル環境です。Claude Codeのような体験を提供し、プロジェクトの目標と仕様をAIが理解して、開発を支援します。
|
||||
|
||||
## 主要機能
|
||||
|
||||
### 1. インタラクティブシェル
|
||||
- AIとの対話型インターフェース
|
||||
- シェルコマンドの実行(!command形式)
|
||||
- 高度な補完機能
|
||||
- コマンド履歴
|
||||
|
||||
### 2. AI支援機能
|
||||
- **analyze <file>**: ファイルの分析
|
||||
- **generate <description>**: コード生成
|
||||
- **explain <topic>**: 概念の説明
|
||||
- **load**: プロジェクト仕様(このファイル)の読み込み
|
||||
|
||||
### 3. ai.gpt統合
|
||||
- 関係性ベースのAI人格
|
||||
- 記憶システム
|
||||
- 運勢システムによる応答の変化
|
||||
|
||||
## 使用方法
|
||||
|
||||
```bash
|
||||
# ai.shellを起動
|
||||
aigpt shell
|
||||
|
||||
# プロジェクト仕様を読み込み
|
||||
ai.shell> load
|
||||
|
||||
# ファイルを分析
|
||||
ai.shell> analyze src/main.py
|
||||
|
||||
# コードを生成
|
||||
ai.shell> generate Python function to calculate fibonacci
|
||||
|
||||
# シェルコマンドを実行
|
||||
ai.shell> !ls -la
|
||||
|
||||
# AIと対話
|
||||
ai.shell> How can I improve this code?
|
||||
```
|
||||
|
||||
## 技術スタック
|
||||
- Python 3.10+
|
||||
- prompt-toolkit(補完機能)
|
||||
- fastapi-mcp(MCP統合)
|
||||
- ai.gpt(人格・記憶システム)
|
||||
|
||||
## 開発目標
|
||||
1. Claude Codeのような自然な開発体験
|
||||
2. AIがプロジェクトコンテキストを理解
|
||||
3. シェルコマンドとAIの seamless な統合
|
||||
4. 開発者の生産性向上
|
||||
|
||||
## 今後の展開
|
||||
- ai.cardとの統合(カードゲームMCPサーバー)
|
||||
- より高度なプロジェクト理解機能
|
||||
- 自動コード修正・リファクタリング
|
||||
- テスト生成・実行
|
1
card
Submodule
1
card
Submodule
Submodule card added at 6dbe630b9d
326
claude.md
Normal file
326
claude.md
Normal file
@ -0,0 +1,326 @@
|
||||
# エコシステム統合設計書
|
||||
|
||||
## 中核思想
|
||||
- **存在子理論**: この世界で最も小さいもの(存在子/ai)の探求
|
||||
- **唯一性原則**: 現実の個人の唯一性をすべてのシステムで担保
|
||||
- **現実の反映**: 現実→ゲーム→現実の循環的影響
|
||||
|
||||
## システム構成図
|
||||
|
||||
```
|
||||
存在子(ai) - 最小単位の意識
|
||||
↓
|
||||
[ai.moji] 文字システム
|
||||
↓
|
||||
[ai.os] + [ai.game device] ← 統合ハードウェア
|
||||
├── ai.shell (Claude Code的機能)
|
||||
├── ai.gpt (自律人格・記憶システム)
|
||||
├── ai.ai (個人特化AI・心を読み取るAI)
|
||||
├── ai.card (カードゲーム・iOS/Web/API)
|
||||
└── ai.bot (分散SNS連携・カード配布)
|
||||
↓
|
||||
[ai.verse] メタバース
|
||||
├── world system (惑星型3D世界)
|
||||
├── at system (atproto/分散SNS)
|
||||
├── yui system (唯一性担保)
|
||||
└── ai system (存在属性)
|
||||
```
|
||||
|
||||
## 名前規則
|
||||
|
||||
名前規則は他のprojectと全て共通しています。exampleを示しますので、このルールに従ってください。
|
||||
|
||||
ここでは`ai.os`の場合の名前規則の例を記述します。
|
||||
|
||||
name: ai.os
|
||||
|
||||
**[ "package", "code", "command" ]**: aios
|
||||
**[ "dir", "url" ]**: ai/os
|
||||
**[ "domain", "json" ]**: ai.os
|
||||
|
||||
```sh
|
||||
$ curl -sL https://git.syui.ai/ai/ai/raw/branch/main/ai.json|jq .ai.os
|
||||
{ "type": "os" }
|
||||
```
|
||||
|
||||
```json
|
||||
{
|
||||
"ai": {
|
||||
"os":{}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
他のprojectも同じ名前規則を採用します。`ai.gpt`ならpackageは`aigpt`です。
|
||||
|
||||
## config(設定ファイル, env, 環境依存)
|
||||
|
||||
`config`を置く場所は統一されており、各projectの名前規則の`dir`項目を使用します。例えば、aiosの場合は`~/.config/syui/ai/os/`以下となります。pythonなどを使用する場合、`python -m venv`などでこのpackage config dirに環境を構築して実行するようにしてください。
|
||||
|
||||
domain形式を採用して、私は各projectを`git.syui.ai/ai`にhostしていますから、`~/.config/syui/ai`とします。
|
||||
|
||||
```sh
|
||||
[syui.ai]
|
||||
syui/ai
|
||||
```
|
||||
|
||||
```sh
|
||||
# example
|
||||
~/.config/syui/ai
|
||||
├── card
|
||||
├── gpt
|
||||
├── os
|
||||
└── shell
|
||||
```
|
||||
|
||||
## 各システム詳細
|
||||
|
||||
### ai.gpt - 自律的送信AI
|
||||
**目的**: 関係性に基づく自発的コミュニケーション
|
||||
|
||||
**中核概念**:
|
||||
- **人格**: 記憶(過去の発話)と関係性パラメータで構成
|
||||
- **唯一性**: atproto accountとの1:1紐付け、改変不可能
|
||||
- **自律送信**: 関係性が閾値を超えると送信機能が解禁
|
||||
|
||||
**技術構成**:
|
||||
- `MemoryManager`: 完全ログ→AI要約→コア判定→選択的忘却
|
||||
- `RelationshipTracker`: 時間減衰・日次制限付き関係性スコア
|
||||
- `TransmissionController`: 閾値判定・送信トリガー
|
||||
- `Persona`: AI運勢(1-10ランダム)による人格変動
|
||||
|
||||
**実装仕様**:
|
||||
```
|
||||
- 言語: Python (fastapi_mcp)
|
||||
- ストレージ: JSON/SQLite選択式
|
||||
- インターフェース: Python CLI (click/typer)
|
||||
- スケジューリング: cron-like自律処理
|
||||
```
|
||||
|
||||
### ai.card - カードゲームシステム
|
||||
**目的**: atproto基盤でのユーザーデータ主権カードゲーム
|
||||
|
||||
**現在の状況**:
|
||||
- ai.botの機能として実装済み
|
||||
- atproto accountでmentionすると1日1回カードを取得
|
||||
- ai.api (MCP server予定) でユーザー管理
|
||||
|
||||
**移行計画**:
|
||||
- **iOS移植**: Claudeが担当予定
|
||||
- **データ保存**: atproto collection recordに保存(ユーザーがデータを所有)
|
||||
- **不正防止**: OAuth 2.1 scope (実装待ち) + MCP serverで対応
|
||||
- **画像ファイル**: Cloudflare Pagesが最適
|
||||
|
||||
**yui system適用**:
|
||||
- カードの効果がアカウント固有
|
||||
- 改ざん防止によるゲームバランス維持
|
||||
- 将来的にai.verseとの統合で固有スキルと連動
|
||||
|
||||
### ai.ai - 心を読み取るAI
|
||||
**目的**: 個人特化型AI・深層理解システム
|
||||
|
||||
**ai.gptとの関係**:
|
||||
- ai.gpt → ai.ai: 自律送信AIから心理分析AIへの連携
|
||||
- 関係性パラメータの深層分析
|
||||
- ユーザーの思想コア部分の特定支援
|
||||
|
||||
### ai.verse - UEメタバース
|
||||
**目的**: 現実反映型3D世界
|
||||
|
||||
**yui system実装**:
|
||||
- キャラクター ↔ プレイヤー 1:1紐付け
|
||||
- unique skill: そのプレイヤーのみ使用可能
|
||||
- 他プレイヤーは同キャラでも同スキル使用不可
|
||||
|
||||
**統合要素**:
|
||||
- ai.card: ゲーム内アイテムとしてのカード
|
||||
- ai.gpt: NPCとしての自律AI人格
|
||||
- atproto: ゲーム内プロフィール連携
|
||||
|
||||
## データフロー設計
|
||||
|
||||
### 唯一性担保の実装
|
||||
```
|
||||
現実の個人 → atproto account (DID) → ゲーム内avatar → 固有スキル
|
||||
↑_______________________________| (現実の反映)
|
||||
```
|
||||
|
||||
### AI駆動変換システム
|
||||
```
|
||||
遊び・創作活動 → ai.gpt分析 → 業務成果変換 → 企業価値創出
|
||||
↑________________________| (Play-to-Work)
|
||||
```
|
||||
|
||||
### カードゲーム・データ主権フロー
|
||||
```
|
||||
ユーザー → ai.bot mention → カード生成 → atproto collection → ユーザー所有
|
||||
↑ ↓
|
||||
← iOS app表示 ← ai.card API ←
|
||||
```
|
||||
|
||||
## 技術スタック統合
|
||||
|
||||
### Core Infrastructure
|
||||
- **OS**: Rust-based ai.os (Arch Linux base)
|
||||
- **Container**: Docker image distribution
|
||||
- **Identity**: atproto selfhost server + DID管理
|
||||
- **AI**: fastapi_mcp server architecture
|
||||
- **CLI**: Python unified (click/typer) - Rustから移行
|
||||
|
||||
### Game Engine Integration
|
||||
- **Engine**: Unreal Engine (Blueprint)
|
||||
- **Data**: atproto → UE → atproto sync
|
||||
- **Avatar**: 分散SNS profile → 3D character
|
||||
- **Streaming**: game screen = broadcast screen
|
||||
|
||||
### Mobile/Device
|
||||
- **iOS**: ai.card移植 (Claude担当)
|
||||
- **Hardware**: ai.game device (future)
|
||||
- **Interface**: controller-first design
|
||||
|
||||
## 実装優先順位
|
||||
|
||||
### Phase 1: AI基盤強化 (現在進行)
|
||||
- [ ] ai.gpt memory system完全実装
|
||||
- 記憶の階層化(完全ログ→要約→コア→忘却)
|
||||
- 関係性パラメータの時間減衰システム
|
||||
- AI運勢による人格変動機能
|
||||
- [ ] ai.card iOS移植
|
||||
- atproto collection record連携
|
||||
- MCP server化(ai.api刷新)
|
||||
- [ ] fastapi_mcp統一基盤構築
|
||||
|
||||
### Phase 2: ゲーム統合
|
||||
- [ ] ai.verse yui system実装
|
||||
- unique skill機能
|
||||
- atproto連携強化
|
||||
- [ ] ai.gpt ↔ ai.ai連携機能
|
||||
- [ ] 分散SNS ↔ ゲーム同期
|
||||
|
||||
### Phase 3: メタバース浸透
|
||||
- [ ] VTuber配信機能統合
|
||||
- [ ] Play-to-Work変換システム
|
||||
- [ ] ai.game device prototype
|
||||
|
||||
## 将来的な連携構想
|
||||
|
||||
### システム間連携(現在は独立実装)
|
||||
```
|
||||
ai.gpt (自律送信) ←→ ai.ai (心理分析)
|
||||
ai.card (iOS,Web,API) ←→ ai.verse (UEゲーム世界)
|
||||
```
|
||||
|
||||
**共通基盤**: fastapi_mcp
|
||||
**共通思想**: yui system(現実の反映・唯一性担保)
|
||||
|
||||
### データ改ざん防止戦略
|
||||
- **短期**: MCP serverによる検証
|
||||
- **中期**: OAuth 2.1 scope実装待ち
|
||||
- **長期**: ブロックチェーン的整合性チェック
|
||||
|
||||
## AIコミュニケーション最適化
|
||||
|
||||
### プロジェクト要件定義テンプレート
|
||||
```markdown
|
||||
# [プロジェクト名] 要件定義
|
||||
|
||||
## 哲学的背景
|
||||
- 存在子理論との関連:
|
||||
- yui system適用範囲:
|
||||
- 現実反映の仕組み:
|
||||
|
||||
## 技術要件
|
||||
- 使用技術(fastapi_mcp統一):
|
||||
- atproto連携方法:
|
||||
- データ永続化方法:
|
||||
|
||||
## ユーザーストーリー
|
||||
1. ユーザーが...すると
|
||||
2. システムが...を実行し
|
||||
3. 結果として...が実現される
|
||||
|
||||
## 成功指標
|
||||
- 技術的:
|
||||
- 哲学的(唯一性担保):
|
||||
```
|
||||
|
||||
### Claude Code活用戦略
|
||||
1. **小さく始める**: ai.gptのMCP機能拡張から
|
||||
2. **段階的統合**: 各システムを個別に完成させてから統合
|
||||
3. **哲学的一貫性**: 各実装でyui systemとの整合性を確認
|
||||
4. **現実反映**: 実装がどう現実とゲームを繋ぐかを常に明記
|
||||
|
||||
## 開発上の留意点
|
||||
|
||||
### MCP Server設計指針
|
||||
- 各AI(gpt, card, ai, bot)は独立したMCPサーバー
|
||||
- fastapi_mcp基盤で統一
|
||||
- atproto DIDによる認証・認可
|
||||
|
||||
### 記憶・データ管理
|
||||
- **ai.gpt**: 関係性の不可逆性重視
|
||||
- **ai.card**: ユーザーデータ主権重視
|
||||
- **ai.verse**: ゲーム世界の整合性重視
|
||||
|
||||
### 唯一性担保実装
|
||||
- atproto accountとの1:1紐付け必須
|
||||
- 改変不可能性をハッシュ・署名で保証
|
||||
- 他システムでの再現不可能性を技術的に実現
|
||||
|
||||
## 継続的改善
|
||||
- 各プロジェクトでこの設計書を参照
|
||||
- 新機能追加時はyui systemとの整合性をチェック
|
||||
- 他システムへの影響を事前評価
|
||||
- Claude Code導入時の段階的移行計画
|
||||
|
||||
## ai.gpt深層設計思想
|
||||
|
||||
### 人格の不可逆性
|
||||
- **関係性の破壊は修復不可能**: 現実の人間関係と同じ重み
|
||||
- **記憶の選択的忘却**: 重要でない情報は忘れるが、コア記憶は永続
|
||||
- **時間減衰**: すべてのパラメータは時間とともに自然減衰
|
||||
|
||||
### AI運勢システム
|
||||
- 1-10のランダム値で日々の人格に変化
|
||||
- 連続した幸運/不運による突破条件
|
||||
- 環境要因としての人格形成
|
||||
|
||||
### 記憶の階層構造
|
||||
1. **完全ログ**: すべての会話を記録
|
||||
2. **AI要約**: 重要な部分を抽出して圧縮
|
||||
3. **思想コア判定**: ユーザーの本質的な部分を特定
|
||||
4. **選択的忘却**: 重要度の低い情報を段階的に削除
|
||||
|
||||
### 実装における重要な決定事項
|
||||
- **言語統一**: Python (fastapi_mcp) で統一、CLIはclick/typer
|
||||
- **データ形式**: JSON/SQLite選択式
|
||||
- **認証**: atproto DIDによる唯一性担保
|
||||
- **段階的実装**: まず会話→記憶→関係性→送信機能の順で実装
|
||||
|
||||
### 送信機能の段階的実装
|
||||
- **Phase 1**: CLIでのprint出力(現在)
|
||||
- **Phase 2**: atproto直接投稿
|
||||
- **Phase 3**: ai.bot (Rust/seahorse) との連携
|
||||
- **将来**: マルチチャネル対応(SNS、Webhook等)
|
||||
|
||||
## ai.gpt実装状況(2025/01/06)
|
||||
|
||||
### 完成した機能
|
||||
- 階層的記憶システム(MemoryManager)
|
||||
- 不可逆的関係性システム(RelationshipTracker)
|
||||
- AI運勢システム(FortuneSystem)
|
||||
- 統合人格システム(Persona)
|
||||
- スケジューラー(5種類のタスク)
|
||||
- MCP Server(9種類のツール)
|
||||
- 設定管理(~/.config/syui/ai/gpt/)
|
||||
- 全CLIコマンド実装
|
||||
|
||||
### 次の開発ポイント
|
||||
- `ai_gpt/DEVELOPMENT_STATUS.md` を参照
|
||||
- 自律送信: transmission.pyでatproto実装
|
||||
- ai.bot連携: 新規bot_connector.py作成
|
||||
- テスト: tests/ディレクトリ追加
|
||||
|
||||
# footer
|
||||
|
||||
© syui
|
30
docs/README.md
Normal file
30
docs/README.md
Normal file
@ -0,0 +1,30 @@
|
||||
# ai.gpt ドキュメント
|
||||
|
||||
ai.gptは、記憶と関係性に基づいて自律的に動作するAIシステムです。
|
||||
|
||||
## 目次
|
||||
|
||||
- [クイックスタート](quickstart.md)
|
||||
- [基本概念](concepts.md)
|
||||
- [コマンドリファレンス](commands.md)
|
||||
- [設定ガイド](configuration.md)
|
||||
- [スケジューラー](scheduler.md)
|
||||
- [MCP Server](mcp-server.md)
|
||||
- [開発者向け](development.md)
|
||||
|
||||
## 特徴
|
||||
|
||||
- 🧠 **階層的記憶システム**: 完全ログ→要約→コア記憶→忘却
|
||||
- 💔 **不可逆的な関係性**: 現実の人間関係のように修復不可能
|
||||
- 🎲 **AI運勢システム**: 日々変化する人格
|
||||
- 🤖 **自律送信**: 関係性が深まると自発的にメッセージ
|
||||
- 🔗 **MCP対応**: AIツールとして記憶を提供
|
||||
|
||||
## システム要件
|
||||
|
||||
- Python 3.10以上
|
||||
- オプション: Ollama または OpenAI API
|
||||
|
||||
## ライセンス
|
||||
|
||||
MIT License
|
218
docs/ai_shell_integration_summary.md
Normal file
218
docs/ai_shell_integration_summary.md
Normal file
@ -0,0 +1,218 @@
|
||||
# ai.shell統合作業完了報告 (2025/01/06)
|
||||
|
||||
## 作業概要
|
||||
ai.shellのRust実装をai.gptのPython実装に統合し、Claude Code風のインタラクティブシェル環境を実現。
|
||||
|
||||
## 実装完了機能
|
||||
|
||||
### 1. aigpt shellコマンド
|
||||
**場所**: `src/aigpt/cli.py` - `shell()` 関数
|
||||
|
||||
**機能**:
|
||||
```bash
|
||||
aigpt shell # インタラクティブシェル起動
|
||||
```
|
||||
|
||||
**シェル内コマンド**:
|
||||
- `help` - コマンド一覧表示
|
||||
- `!<command>` - シェルコマンド実行(例: `!ls`, `!pwd`)
|
||||
- `analyze <file>` - ファイルをAIで分析
|
||||
- `generate <description>` - コード生成
|
||||
- `explain <topic>` - 概念説明
|
||||
- `load` - aishell.md読み込み
|
||||
- `status`, `fortune`, `relationships` - AI状態確認
|
||||
- `clear` - 画面クリア
|
||||
- `exit`/`quit` - 終了
|
||||
- その他のメッセージ - AIとの直接対話
|
||||
|
||||
**実装の特徴**:
|
||||
- prompt-toolkit使用(補完・履歴機能)
|
||||
- ただしターミナル環境依存の問題あり(後で修正必要)
|
||||
- 現在は`input()`ベースでも動作
|
||||
|
||||
### 2. MCPサーバー統合
|
||||
**場所**: `src/aigpt/mcp_server.py`
|
||||
|
||||
**FastApiMCP実装パターン**:
|
||||
```python
|
||||
# FastAPIアプリ作成
|
||||
self.app = FastAPI(title="AI.GPT Memory and Relationship System")
|
||||
|
||||
# FastApiMCPサーバー作成
|
||||
self.server = FastApiMCP(self.app)
|
||||
|
||||
# エンドポイント登録
|
||||
@self.app.get("/get_memories", operation_id="get_memories")
|
||||
async def get_memories(limit: int = 10):
|
||||
# ...
|
||||
|
||||
# MCPマウント
|
||||
self.server.mount()
|
||||
```
|
||||
|
||||
**公開ツール (14個)**:
|
||||
|
||||
**ai.gpt系 (9個)**:
|
||||
- `get_memories` - アクティブメモリ取得
|
||||
- `get_relationship` - 特定ユーザーとの関係取得
|
||||
- `get_all_relationships` - 全関係取得
|
||||
- `get_persona_state` - 人格状態取得
|
||||
- `process_interaction` - ユーザー対話処理
|
||||
- `check_transmission_eligibility` - 送信可能性チェック
|
||||
- `get_fortune` - AI運勢取得
|
||||
- `summarize_memories` - メモリ要約作成
|
||||
- `run_maintenance` - 日次メンテナンス実行
|
||||
|
||||
**ai.shell系 (5個)**:
|
||||
- `execute_command` - シェルコマンド実行
|
||||
- `analyze_file` - ファイルAI分析
|
||||
- `write_file` - ファイル書き込み(バックアップ付き)
|
||||
- `read_project_file` - aishell.md等の読み込み
|
||||
- `list_files` - ディレクトリファイル一覧
|
||||
|
||||
### 3. ai.card統合対応
|
||||
**場所**: `src/aigpt/card_integration.py`
|
||||
|
||||
**サーバー起動オプション**:
|
||||
```bash
|
||||
aigpt server --enable-card # ai.card機能有効化
|
||||
```
|
||||
|
||||
**ai.card系ツール (5個)**:
|
||||
- `get_user_cards` - ユーザーカード取得
|
||||
- `draw_card` - ガチャでカード取得
|
||||
- `get_card_details` - カード詳細情報
|
||||
- `sync_cards_atproto` - atproto同期
|
||||
- `analyze_card_collection` - コレクション分析
|
||||
|
||||
### 4. プロジェクト仕様書
|
||||
**場所**: `aishell.md`
|
||||
|
||||
Claude.md的な役割で、プロジェクトの目標と仕様を記述。`load`コマンドでAIが読み取り可能。
|
||||
|
||||
## 技術実装詳細
|
||||
|
||||
### ディレクトリ構造
|
||||
```
|
||||
src/aigpt/
|
||||
├── cli.py # shell関数追加
|
||||
├── mcp_server.py # FastApiMCP実装
|
||||
├── card_integration.py # ai.card統合
|
||||
└── ... # 既存ファイル
|
||||
```
|
||||
|
||||
### 依存関係追加
|
||||
`pyproject.toml`:
|
||||
```toml
|
||||
dependencies = [
|
||||
# ... 既存
|
||||
"prompt-toolkit>=3.0.0", # 追加
|
||||
]
|
||||
```
|
||||
|
||||
### 名前規則の統一
|
||||
- MCP server名: `aigpt` (ai-gptから変更)
|
||||
- パッケージ名: `aigpt`
|
||||
- コマンド名: `aigpt shell`
|
||||
|
||||
## 動作確認済み
|
||||
|
||||
### CLI動作確認
|
||||
```bash
|
||||
# 基本機能
|
||||
aigpt shell
|
||||
# シェル内で
|
||||
ai.shell> help
|
||||
ai.shell> !ls
|
||||
ai.shell> analyze README.md # ※AI provider要設定
|
||||
ai.shell> load
|
||||
ai.shell> exit
|
||||
|
||||
# MCPサーバー
|
||||
aigpt server --model qwen2.5-coder:7b --port 8001
|
||||
# -> http://localhost:8001/docs でAPI確認可能
|
||||
# -> /mcp エンドポイントでMCP接続可能
|
||||
```
|
||||
|
||||
### エラー対応済み
|
||||
1. **Pydantic日付型エラー**: `models.py`で`datetime.date`インポート追加
|
||||
2. **FastApiMCP使用法**: サンプルコードに基づき正しい実装パターンに修正
|
||||
3. **prompt関数名衝突**: `prompt_toolkit.prompt`を`ptk_prompt`にリネーム
|
||||
|
||||
## 既知の課題と今後の改善点
|
||||
|
||||
### 1. prompt-toolkit環境依存問題
|
||||
**症状**: ターミナル環境でない場合にエラー
|
||||
**対処法**: 環境検出して`input()`にフォールバック
|
||||
**場所**: `src/aigpt/cli.py` - `shell()` 関数
|
||||
|
||||
### 2. AI provider設定
|
||||
**現状**: ollamaのqwen2.5モデルが必要
|
||||
**対処法**:
|
||||
```bash
|
||||
ollama pull qwen2.5
|
||||
# または
|
||||
aigpt shell --model qwen2.5-coder:7b
|
||||
```
|
||||
|
||||
### 3. atproto実装
|
||||
**現状**: ai.cardのatproto機能は未実装
|
||||
**今後**: 実際のatproto API連携実装
|
||||
|
||||
## 次回開発時の推奨アプローチ
|
||||
|
||||
### 1. このドキュメントの活用
|
||||
```bash
|
||||
# このファイルを読み込み
|
||||
cat docs/ai_shell_integration_summary.md
|
||||
```
|
||||
|
||||
### 2. 環境セットアップ
|
||||
```bash
|
||||
cd /Users/syui/ai/gpt
|
||||
python -m venv venv
|
||||
source venv/bin/activate
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
### 3. 動作確認
|
||||
```bash
|
||||
# shell機能
|
||||
aigpt shell
|
||||
|
||||
# MCP server
|
||||
aigpt server --model qwen2.5-coder:7b
|
||||
```
|
||||
|
||||
### 4. 主要設定ファイル確認場所
|
||||
- CLI実装: `src/aigpt/cli.py`
|
||||
- MCP実装: `src/aigpt/mcp_server.py`
|
||||
- 依存関係: `pyproject.toml`
|
||||
- プロジェクト仕様: `aishell.md`
|
||||
|
||||
## アーキテクチャ設計思想
|
||||
|
||||
### yui system適用
|
||||
- **唯一性**: 各ユーザーとの関係は1:1
|
||||
- **不可逆性**: 関係性破壊は修復不可能
|
||||
- **現実反映**: ゲーム→現実の循環的影響
|
||||
|
||||
### fastapi_mcp統一基盤
|
||||
- 各AI(gpt, shell, card)を統合MCPサーバーで公開
|
||||
- FastAPIエンドポイント → MCPツール自動変換
|
||||
- Claude Desktop, Cursor等から利用可能
|
||||
|
||||
### 段階的実装完了
|
||||
1. ✅ ai.shell基本機能 → Python CLI
|
||||
2. ✅ MCP統合 → 外部AI連携
|
||||
3. 🔧 prompt-toolkit最適化 → 環境対応
|
||||
4. 🔧 atproto実装 → 本格的SNS連携
|
||||
|
||||
## 成果サマリー
|
||||
|
||||
**実装済み**: Claude Code風の開発環境
|
||||
**技術的成果**: Rust→Python移行、MCP統合、ai.card対応
|
||||
**哲学的一貫性**: yui systemとの整合性維持
|
||||
**利用可能性**: 即座に`aigpt shell`で体験可能
|
||||
|
||||
この統合により、ai.gptは単なる会話AIから、開発支援を含む総合的なAI環境に進化しました。
|
207
docs/commands.md
Normal file
207
docs/commands.md
Normal file
@ -0,0 +1,207 @@
|
||||
# コマンドリファレンス
|
||||
|
||||
## chat - AIと会話
|
||||
|
||||
ユーザーとAIの対話を処理し、関係性を更新します。
|
||||
|
||||
```bash
|
||||
ai-gpt chat USER_ID MESSAGE [OPTIONS]
|
||||
```
|
||||
|
||||
### 引数
|
||||
- `USER_ID`: ユーザーID(atproto DID形式)
|
||||
- `MESSAGE`: 送信するメッセージ
|
||||
|
||||
### オプション
|
||||
- `--provider`: AIプロバイダー(ollama/openai)
|
||||
- `--model`, `-m`: 使用するモデル
|
||||
- `--data-dir`, `-d`: データディレクトリ
|
||||
|
||||
### 例
|
||||
```bash
|
||||
# 基本的な会話
|
||||
ai-gpt chat "did:plc:user123" "こんにちは"
|
||||
|
||||
# OpenAIを使用
|
||||
ai-gpt chat "did:plc:user123" "調子はどう?" --provider openai --model gpt-4o-mini
|
||||
|
||||
# Ollamaでカスタムモデル
|
||||
ai-gpt chat "did:plc:user123" "今日の天気は?" --provider ollama --model llama2
|
||||
```
|
||||
|
||||
## status - 状態確認
|
||||
|
||||
AIの状態や特定ユーザーとの関係を表示します。
|
||||
|
||||
```bash
|
||||
ai-gpt status [USER_ID] [OPTIONS]
|
||||
```
|
||||
|
||||
### 引数
|
||||
- `USER_ID`: (オプション)特定ユーザーとの関係を確認
|
||||
|
||||
### 例
|
||||
```bash
|
||||
# AI全体の状態
|
||||
ai-gpt status
|
||||
|
||||
# 特定ユーザーとの関係
|
||||
ai-gpt status "did:plc:user123"
|
||||
```
|
||||
|
||||
## fortune - 今日の運勢
|
||||
|
||||
AIの今日の運勢を確認します。
|
||||
|
||||
```bash
|
||||
ai-gpt fortune [OPTIONS]
|
||||
```
|
||||
|
||||
### 表示内容
|
||||
- 運勢値(1-10)
|
||||
- 連続した幸運/不運の日数
|
||||
- ブレークスルー状態
|
||||
|
||||
## relationships - 関係一覧
|
||||
|
||||
すべてのユーザーとの関係を一覧表示します。
|
||||
|
||||
```bash
|
||||
ai-gpt relationships [OPTIONS]
|
||||
```
|
||||
|
||||
### 表示内容
|
||||
- ユーザーID
|
||||
- 関係性ステータス
|
||||
- スコア
|
||||
- 送信可否
|
||||
- 最終対話日
|
||||
|
||||
## transmit - 送信実行
|
||||
|
||||
送信可能なユーザーへのメッセージを確認・実行します。
|
||||
|
||||
```bash
|
||||
ai-gpt transmit [OPTIONS]
|
||||
```
|
||||
|
||||
### オプション
|
||||
- `--dry-run/--execute`: ドライラン(デフォルト)または実行
|
||||
- `--data-dir`, `-d`: データディレクトリ
|
||||
|
||||
### 例
|
||||
```bash
|
||||
# 送信内容を確認(ドライラン)
|
||||
ai-gpt transmit
|
||||
|
||||
# 実際に送信を実行
|
||||
ai-gpt transmit --execute
|
||||
```
|
||||
|
||||
## maintenance - メンテナンス
|
||||
|
||||
日次メンテナンスタスクを実行します。
|
||||
|
||||
```bash
|
||||
ai-gpt maintenance [OPTIONS]
|
||||
```
|
||||
|
||||
### 実行内容
|
||||
- 関係性の時間減衰
|
||||
- 記憶の忘却処理
|
||||
- コア記憶の判定
|
||||
- 記憶の要約作成
|
||||
|
||||
## config - 設定管理
|
||||
|
||||
設定の確認・変更を行います。
|
||||
|
||||
```bash
|
||||
ai-gpt config ACTION [KEY] [VALUE]
|
||||
```
|
||||
|
||||
### アクション
|
||||
- `get`: 設定値を取得
|
||||
- `set`: 設定値を変更
|
||||
- `delete`: 設定を削除
|
||||
- `list`: 設定一覧を表示
|
||||
|
||||
### 例
|
||||
```bash
|
||||
# APIキーを設定
|
||||
ai-gpt config set providers.openai.api_key sk-xxxxx
|
||||
|
||||
# 設定を確認
|
||||
ai-gpt config get providers.openai.api_key
|
||||
|
||||
# 設定一覧
|
||||
ai-gpt config list
|
||||
|
||||
# プロバイダー設定のみ表示
|
||||
ai-gpt config list providers
|
||||
```
|
||||
|
||||
## schedule - スケジュール管理
|
||||
|
||||
定期実行タスクを管理します。
|
||||
|
||||
```bash
|
||||
ai-gpt schedule ACTION [TASK_TYPE] [SCHEDULE] [OPTIONS]
|
||||
```
|
||||
|
||||
### アクション
|
||||
- `add`: タスクを追加
|
||||
- `list`: タスク一覧
|
||||
- `enable`: タスクを有効化
|
||||
- `disable`: タスクを無効化
|
||||
- `remove`: タスクを削除
|
||||
- `run`: スケジューラーを起動
|
||||
|
||||
### タスクタイプ
|
||||
- `transmission_check`: 送信チェック
|
||||
- `maintenance`: 日次メンテナンス
|
||||
- `fortune_update`: 運勢更新
|
||||
- `relationship_decay`: 関係性減衰
|
||||
- `memory_summary`: 記憶要約
|
||||
|
||||
### スケジュール形式
|
||||
- **Cron形式**: `"0 */6 * * *"` (6時間ごと)
|
||||
- **インターバル**: `"30m"`, `"2h"`, `"1d"`
|
||||
|
||||
### 例
|
||||
```bash
|
||||
# 30分ごとに送信チェック
|
||||
ai-gpt schedule add transmission_check "30m"
|
||||
|
||||
# 毎日午前3時にメンテナンス
|
||||
ai-gpt schedule add maintenance "0 3 * * *"
|
||||
|
||||
# タスク一覧
|
||||
ai-gpt schedule list
|
||||
|
||||
# スケジューラーを起動
|
||||
ai-gpt schedule run
|
||||
```
|
||||
|
||||
## server - MCP Server
|
||||
|
||||
AIの記憶と機能をMCPツールとして公開します。
|
||||
|
||||
```bash
|
||||
ai-gpt server [OPTIONS]
|
||||
```
|
||||
|
||||
### オプション
|
||||
- `--host`, `-h`: サーバーホスト(デフォルト: localhost)
|
||||
- `--port`, `-p`: サーバーポート(デフォルト: 8000)
|
||||
- `--model`, `-m`: AIモデル
|
||||
- `--provider`: AIプロバイダー
|
||||
|
||||
### 例
|
||||
```bash
|
||||
# 基本的な起動
|
||||
ai-gpt server
|
||||
|
||||
# カスタム設定
|
||||
ai-gpt server --port 8080 --model gpt-4o-mini --provider openai
|
||||
```
|
102
docs/concepts.md
Normal file
102
docs/concepts.md
Normal file
@ -0,0 +1,102 @@
|
||||
# 基本概念
|
||||
|
||||
## 中核思想
|
||||
|
||||
ai.gptは「存在子理論」に基づき、AIに唯一性のある人格を与えることを目指しています。
|
||||
|
||||
### 唯一性(yui system)
|
||||
|
||||
- **1対1の関係**: 各ユーザー(atproto DID)とAIは唯一の関係を持つ
|
||||
- **改変不可能**: 一度形成された関係性は変更できない
|
||||
- **不可逆性**: 関係が壊れたら修復不可能
|
||||
|
||||
### 現実の反映
|
||||
|
||||
現実の人間関係と同じように:
|
||||
- 時間とともに関係性は変化する
|
||||
- ネガティブな相互作用は関係を損なう
|
||||
- 信頼は簡単に失われ、取り戻すのは困難
|
||||
|
||||
## 記憶システム
|
||||
|
||||
### 階層構造
|
||||
|
||||
```
|
||||
1. 完全ログ(Full Log)
|
||||
↓ すべての会話を記録
|
||||
2. 要約(Summary)
|
||||
↓ AIが重要部分を抽出
|
||||
3. コア記憶(Core)
|
||||
↓ ユーザーの本質的な部分
|
||||
4. 忘却(Forgotten)
|
||||
重要でない情報は忘れる
|
||||
```
|
||||
|
||||
### 記憶の処理フロー
|
||||
|
||||
1. **会話記録**: すべての対話を保存
|
||||
2. **重要度判定**: 関係性への影響度で評価
|
||||
3. **要約作成**: 定期的に記憶を圧縮
|
||||
4. **コア判定**: 本質的な記憶を特定
|
||||
5. **選択的忘却**: 古い非重要記憶を削除
|
||||
|
||||
## 関係性パラメータ
|
||||
|
||||
### 関係性の段階
|
||||
|
||||
- `stranger` (0-49): 初対面
|
||||
- `acquaintance` (50-99): 知人
|
||||
- `friend` (100-149): 友人
|
||||
- `close_friend` (150+): 親友
|
||||
- `broken`: 修復不可能(スコア0以下)
|
||||
|
||||
### スコアの変動
|
||||
|
||||
- **ポジティブな対話**: +1.0〜+2.0
|
||||
- **時間経過**: -0.1/日(自然減衰)
|
||||
- **ネガティブな対話**: -10.0以上で深刻なダメージ
|
||||
- **日次上限**: 1日10回まで
|
||||
|
||||
### 送信機能の解禁
|
||||
|
||||
関係性スコアが100を超えると、AIは自律的にメッセージを送信できるようになります。
|
||||
|
||||
## AI運勢システム
|
||||
|
||||
### 日々の変化
|
||||
|
||||
- 毎日1-10の運勢値がランダムに決定
|
||||
- 運勢は人格特性に影響を与える
|
||||
- 連続した幸運/不運でブレークスルー発生
|
||||
|
||||
### 人格への影響
|
||||
|
||||
運勢が高い日:
|
||||
- より楽観的で積極的
|
||||
- 創造性が高まる
|
||||
- エネルギッシュな応答
|
||||
|
||||
運勢が低い日:
|
||||
- 内省的で慎重
|
||||
- 深い思考
|
||||
- 控えめな応答
|
||||
|
||||
## データの永続性
|
||||
|
||||
### 保存場所
|
||||
|
||||
```
|
||||
~/.config/aigpt/
|
||||
├── config.json # 設定
|
||||
└── data/ # AIデータ
|
||||
├── memories.json # 記憶
|
||||
├── relationships.json # 関係性
|
||||
├── fortunes.json # 運勢履歴
|
||||
└── ...
|
||||
```
|
||||
|
||||
### データ主権
|
||||
|
||||
- すべてのデータはローカルに保存
|
||||
- ユーザーが完全にコントロール
|
||||
- 将来的にはatproto上で分散管理
|
118
docs/configuration.md
Normal file
118
docs/configuration.md
Normal file
@ -0,0 +1,118 @@
|
||||
# 設定ガイド
|
||||
|
||||
## 設定ファイルの場所
|
||||
|
||||
ai.gptの設定は `~/.config/syui/ai/gpt/config.json` に保存されます。
|
||||
|
||||
## 設定構造
|
||||
|
||||
```json
|
||||
{
|
||||
"providers": {
|
||||
"openai": {
|
||||
"api_key": "sk-xxxxx",
|
||||
"default_model": "gpt-4o-mini"
|
||||
},
|
||||
"ollama": {
|
||||
"host": "http://localhost:11434",
|
||||
"default_model": "qwen2.5"
|
||||
}
|
||||
},
|
||||
"atproto": {
|
||||
"handle": "your.handle",
|
||||
"password": "your-password",
|
||||
"host": "https://bsky.social"
|
||||
},
|
||||
"default_provider": "ollama"
|
||||
}
|
||||
```
|
||||
|
||||
## プロバイダー設定
|
||||
|
||||
### OpenAI
|
||||
|
||||
```bash
|
||||
# APIキーを設定
|
||||
aigpt config set providers.openai.api_key sk-xxxxx
|
||||
|
||||
# デフォルトモデルを変更
|
||||
aigpt config set providers.openai.default_model gpt-4-turbo
|
||||
```
|
||||
|
||||
### Ollama
|
||||
|
||||
```bash
|
||||
# ホストを変更(リモートOllamaサーバーを使用する場合)
|
||||
aigpt config set providers.ollama.host http://192.168.1.100:11434
|
||||
|
||||
# デフォルトモデルを変更
|
||||
aigpt config set providers.ollama.default_model llama2
|
||||
```
|
||||
|
||||
## atproto設定(将来の自動投稿用)
|
||||
|
||||
```bash
|
||||
# Blueskyアカウント
|
||||
aigpt config set atproto.handle yourhandle.bsky.social
|
||||
aigpt config set atproto.password your-app-password
|
||||
|
||||
# セルフホストサーバーを使用
|
||||
aigpt config set atproto.host https://your-pds.example.com
|
||||
```
|
||||
|
||||
## デフォルトプロバイダー
|
||||
|
||||
```bash
|
||||
# デフォルトをOpenAIに変更
|
||||
aigpt config set default_provider openai
|
||||
```
|
||||
|
||||
## セキュリティ
|
||||
|
||||
### APIキーの保護
|
||||
|
||||
設定ファイルは平文で保存されるため、適切なファイル権限を設定してください:
|
||||
|
||||
```bash
|
||||
chmod 600 ~/.config/syui/ai/gpt/config.json
|
||||
```
|
||||
|
||||
### 環境変数との優先順位
|
||||
|
||||
1. コマンドラインオプション(最優先)
|
||||
2. 設定ファイル
|
||||
3. 環境変数(最低優先)
|
||||
|
||||
例:OpenAI APIキーの場合
|
||||
- `--api-key` オプション
|
||||
- `config.json` の `providers.openai.api_key`
|
||||
- 環境変数 `OPENAI_API_KEY`
|
||||
|
||||
## 設定のバックアップ
|
||||
|
||||
```bash
|
||||
# バックアップ
|
||||
cp ~/.config/syui/ai/gpt/config.json ~/.config/syui/ai/gpt/config.json.backup
|
||||
|
||||
# リストア
|
||||
cp ~/.config/syui/ai/gpt/config.json.backup ~/.config/syui/ai/gpt/config.json
|
||||
```
|
||||
|
||||
## トラブルシューティング
|
||||
|
||||
### 設定が反映されない
|
||||
|
||||
```bash
|
||||
# 現在の設定を確認
|
||||
aigpt config list
|
||||
|
||||
# 特定のキーを確認
|
||||
aigpt config get providers.openai.api_key
|
||||
```
|
||||
|
||||
### 設定をリセット
|
||||
|
||||
```bash
|
||||
# 設定ファイルを削除(次回実行時に再作成)
|
||||
rm ~/.config/syui/ai/gpt/config.json
|
||||
```
|
167
docs/development.md
Normal file
167
docs/development.md
Normal file
@ -0,0 +1,167 @@
|
||||
# 開発者向けガイド
|
||||
|
||||
## アーキテクチャ
|
||||
|
||||
### ディレクトリ構造
|
||||
|
||||
```
|
||||
ai_gpt/
|
||||
├── src/ai_gpt/
|
||||
│ ├── __init__.py
|
||||
│ ├── models.py # データモデル定義
|
||||
│ ├── memory.py # 記憶管理システム
|
||||
│ ├── relationship.py # 関係性トラッカー
|
||||
│ ├── fortune.py # AI運勢システム
|
||||
│ ├── persona.py # 統合人格システム
|
||||
│ ├── transmission.py # 送信コントローラー
|
||||
│ ├── scheduler.py # スケジューラー
|
||||
│ ├── config.py # 設定管理
|
||||
│ ├── ai_provider.py # AI統合(Ollama/OpenAI)
|
||||
│ ├── mcp_server.py # MCP Server実装
|
||||
│ └── cli.py # CLIインターフェース
|
||||
├── docs/ # ドキュメント
|
||||
├── tests/ # テスト
|
||||
└── pyproject.toml # プロジェクト設定
|
||||
```
|
||||
|
||||
### 主要コンポーネント
|
||||
|
||||
#### MemoryManager
|
||||
階層的記憶システムの実装。会話を記録し、要約・コア判定・忘却を管理。
|
||||
|
||||
```python
|
||||
memory = MemoryManager(data_dir)
|
||||
memory.add_conversation(conversation)
|
||||
memory.summarize_memories(user_id)
|
||||
memory.identify_core_memories()
|
||||
memory.apply_forgetting()
|
||||
```
|
||||
|
||||
#### RelationshipTracker
|
||||
ユーザーとの関係性を追跡。不可逆的なダメージと時間減衰を実装。
|
||||
|
||||
```python
|
||||
tracker = RelationshipTracker(data_dir)
|
||||
relationship = tracker.update_interaction(user_id, delta)
|
||||
tracker.apply_time_decay()
|
||||
```
|
||||
|
||||
#### Persona
|
||||
すべてのコンポーネントを統合し、一貫した人格を提供。
|
||||
|
||||
```python
|
||||
persona = Persona(data_dir)
|
||||
response, delta = persona.process_interaction(user_id, message)
|
||||
state = persona.get_current_state()
|
||||
```
|
||||
|
||||
## 拡張方法
|
||||
|
||||
### 新しいAIプロバイダーの追加
|
||||
|
||||
1. `ai_provider.py`に新しいプロバイダークラスを作成:
|
||||
|
||||
```python
|
||||
class CustomProvider:
|
||||
async def generate_response(
|
||||
self,
|
||||
prompt: str,
|
||||
persona_state: PersonaState,
|
||||
memories: List[Memory],
|
||||
system_prompt: Optional[str] = None
|
||||
) -> str:
|
||||
# 実装
|
||||
pass
|
||||
```
|
||||
|
||||
2. `create_ai_provider`関数に追加:
|
||||
|
||||
```python
|
||||
def create_ai_provider(provider: str, model: str, **kwargs):
|
||||
if provider == "custom":
|
||||
return CustomProvider(model=model, **kwargs)
|
||||
# ...
|
||||
```
|
||||
|
||||
### 新しいスケジュールタスクの追加
|
||||
|
||||
1. `TaskType`enumに追加:
|
||||
|
||||
```python
|
||||
class TaskType(str, Enum):
|
||||
CUSTOM_TASK = "custom_task"
|
||||
```
|
||||
|
||||
2. ハンドラーを実装:
|
||||
|
||||
```python
|
||||
async def _handle_custom_task(self, task: ScheduledTask):
|
||||
# タスクの実装
|
||||
pass
|
||||
```
|
||||
|
||||
3. `task_handlers`に登録:
|
||||
|
||||
```python
|
||||
self.task_handlers[TaskType.CUSTOM_TASK] = self._handle_custom_task
|
||||
```
|
||||
|
||||
### 新しいMCPツールの追加
|
||||
|
||||
`mcp_server.py`の`_register_tools`メソッドに追加:
|
||||
|
||||
```python
|
||||
@self.server.tool("custom_tool")
|
||||
async def custom_tool(param1: str, param2: int) -> Dict[str, Any]:
|
||||
"""カスタムツールの説明"""
|
||||
# 実装
|
||||
return {"result": "value"}
|
||||
```
|
||||
|
||||
## テスト
|
||||
|
||||
```bash
|
||||
# テストの実行(将来実装)
|
||||
pytest tests/
|
||||
|
||||
# 特定のテスト
|
||||
pytest tests/test_memory.py
|
||||
```
|
||||
|
||||
## デバッグ
|
||||
|
||||
### ログレベルの設定
|
||||
|
||||
```python
|
||||
import logging
|
||||
logging.basicConfig(level=logging.DEBUG)
|
||||
```
|
||||
|
||||
### データファイルの直接確認
|
||||
|
||||
```bash
|
||||
# 関係性データを確認
|
||||
cat ~/.config/aigpt/data/relationships.json | jq
|
||||
|
||||
# 記憶データを確認
|
||||
cat ~/.config/aigpt/data/memories.json | jq
|
||||
```
|
||||
|
||||
## 貢献方法
|
||||
|
||||
1. フォークする
|
||||
2. フィーチャーブランチを作成 (`git checkout -b feature/amazing-feature`)
|
||||
3. 変更をコミット (`git commit -m 'Add amazing feature'`)
|
||||
4. ブランチにプッシュ (`git push origin feature/amazing-feature`)
|
||||
5. プルリクエストを作成
|
||||
|
||||
## 設計原則
|
||||
|
||||
1. **不可逆性**: 一度失われた関係性は回復しない
|
||||
2. **階層性**: 記憶は重要度によって階層化される
|
||||
3. **自律性**: AIは関係性に基づいて自発的に行動する
|
||||
4. **唯一性**: 各ユーザーとの関係は唯一無二
|
||||
|
||||
## ライセンス
|
||||
|
||||
MIT License
|
110
docs/mcp-server.md
Normal file
110
docs/mcp-server.md
Normal file
@ -0,0 +1,110 @@
|
||||
# MCP Server
|
||||
|
||||
## 概要
|
||||
|
||||
MCP (Model Context Protocol) Serverは、ai.gptの記憶と機能をAIツールとして公開します。これにより、Claude DesktopなどのMCP対応AIアシスタントがai.gptの機能にアクセスできます。
|
||||
|
||||
## 起動方法
|
||||
|
||||
```bash
|
||||
# 基本的な起動
|
||||
ai-gpt server
|
||||
|
||||
# カスタム設定
|
||||
ai-gpt server --host 0.0.0.0 --port 8080 --model gpt-4o-mini --provider openai
|
||||
```
|
||||
|
||||
## 利用可能なツール
|
||||
|
||||
### get_memories
|
||||
アクティブな記憶を取得します。
|
||||
|
||||
**パラメータ**:
|
||||
- `user_id` (optional): 特定ユーザーに関する記憶
|
||||
- `limit`: 取得する記憶の最大数(デフォルト: 10)
|
||||
|
||||
**返り値**: 記憶のリスト(ID、内容、レベル、重要度、コア判定、タイムスタンプ)
|
||||
|
||||
### get_relationship
|
||||
特定ユーザーとの関係性を取得します。
|
||||
|
||||
**パラメータ**:
|
||||
- `user_id`: ユーザーID(必須)
|
||||
|
||||
**返り値**: 関係性情報(ステータス、スコア、送信可否、総対話数など)
|
||||
|
||||
### get_all_relationships
|
||||
すべての関係性を取得します。
|
||||
|
||||
**返り値**: すべてのユーザーとの関係性リスト
|
||||
|
||||
### get_persona_state
|
||||
現在のAI人格状態を取得します。
|
||||
|
||||
**返り値**:
|
||||
- 現在の気分
|
||||
- 今日の運勢
|
||||
- 人格特性値
|
||||
- アクティブな記憶数
|
||||
|
||||
### process_interaction
|
||||
ユーザーとの対話を処理します。
|
||||
|
||||
**パラメータ**:
|
||||
- `user_id`: ユーザーID
|
||||
- `message`: メッセージ内容
|
||||
|
||||
**返り値**:
|
||||
- AIの応答
|
||||
- 関係性の変化量
|
||||
- 新しい関係性スコア
|
||||
- 送信機能の状態
|
||||
|
||||
### check_transmission_eligibility
|
||||
特定ユーザーへの送信可否をチェックします。
|
||||
|
||||
**パラメータ**:
|
||||
- `user_id`: ユーザーID
|
||||
|
||||
**返り値**: 送信可否と関係性情報
|
||||
|
||||
### get_fortune
|
||||
今日のAI運勢を取得します。
|
||||
|
||||
**返り値**: 運勢値、連続日数、ブレークスルー状態、人格への影響
|
||||
|
||||
### summarize_memories
|
||||
記憶の要約を作成します。
|
||||
|
||||
**パラメータ**:
|
||||
- `user_id`: ユーザーID
|
||||
|
||||
**返り値**: 作成された要約(ある場合)
|
||||
|
||||
### run_maintenance
|
||||
日次メンテナンスを実行します。
|
||||
|
||||
**返り値**: 実行ステータス
|
||||
|
||||
## Claude Desktopでの設定
|
||||
|
||||
`~/Library/Application Support/Claude/claude_desktop_config.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"ai-gpt": {
|
||||
"command": "ai-gpt",
|
||||
"args": ["server", "--port", "8001"],
|
||||
"env": {}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## 使用例
|
||||
|
||||
### AIアシスタントからの利用
|
||||
|
||||
```
|
||||
User: ai.gptで私との関係性を確認して
|
69
docs/quickstart.md
Normal file
69
docs/quickstart.md
Normal file
@ -0,0 +1,69 @@
|
||||
# クイックスタート
|
||||
|
||||
## インストール
|
||||
|
||||
```bash
|
||||
# リポジトリをクローン
|
||||
git clone https://github.com/yourusername/ai_gpt.git
|
||||
cd ai_gpt
|
||||
|
||||
# インストール
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
## 初期設定
|
||||
|
||||
### 1. OpenAIを使う場合
|
||||
|
||||
```bash
|
||||
# APIキーを設定
|
||||
ai-gpt config set providers.openai.api_key sk-xxxxx
|
||||
```
|
||||
|
||||
### 2. Ollamaを使う場合(ローカルLLM)
|
||||
|
||||
```bash
|
||||
# Ollamaをインストール(まだの場合)
|
||||
# https://ollama.ai からダウンロード
|
||||
|
||||
# モデルをダウンロード
|
||||
ollama pull qwen2.5
|
||||
```
|
||||
|
||||
## 基本的な使い方
|
||||
|
||||
### 1. AIと会話する
|
||||
|
||||
```bash
|
||||
# シンプルな会話(Ollamaを使用)
|
||||
ai-gpt chat "did:plc:user123" "こんにちは!"
|
||||
|
||||
# OpenAIを使用
|
||||
ai-gpt chat "did:plc:user123" "今日はどんな気分?" --provider openai --model gpt-4o-mini
|
||||
```
|
||||
|
||||
### 2. 関係性を確認
|
||||
|
||||
```bash
|
||||
# 特定ユーザーとの関係を確認
|
||||
ai-gpt status "did:plc:user123"
|
||||
|
||||
# AIの全体的な状態を確認
|
||||
ai-gpt status
|
||||
```
|
||||
|
||||
### 3. 自動送信を設定
|
||||
|
||||
```bash
|
||||
# 30分ごとに送信チェック
|
||||
ai-gpt schedule add transmission_check "30m"
|
||||
|
||||
# スケジューラーを起動
|
||||
ai-gpt schedule run
|
||||
```
|
||||
|
||||
## 次のステップ
|
||||
|
||||
- [基本概念](concepts.md) - システムの仕組みを理解
|
||||
- [コマンドリファレンス](commands.md) - 全コマンドの詳細
|
||||
- [設定ガイド](configuration.md) - 詳細な設定方法
|
168
docs/scheduler.md
Normal file
168
docs/scheduler.md
Normal file
@ -0,0 +1,168 @@
|
||||
# スケジューラーガイド
|
||||
|
||||
## 概要
|
||||
|
||||
スケジューラーは、AIの自律的な動作を実現するための中核機能です。定期的なタスクを設定し、バックグラウンドで実行できます。
|
||||
|
||||
## タスクタイプ
|
||||
|
||||
### transmission_check
|
||||
関係性が閾値を超えたユーザーへの自動送信をチェックします。
|
||||
|
||||
```bash
|
||||
# 30分ごとにチェック
|
||||
ai-gpt schedule add transmission_check "30m" --provider ollama --model qwen2.5
|
||||
```
|
||||
|
||||
### maintenance
|
||||
日次メンテナンスを実行します:
|
||||
- 記憶の忘却処理
|
||||
- コア記憶の判定
|
||||
- 関係性パラメータの整理
|
||||
|
||||
```bash
|
||||
# 毎日午前3時に実行
|
||||
ai-gpt schedule add maintenance "0 3 * * *"
|
||||
```
|
||||
|
||||
### fortune_update
|
||||
AI運勢を更新します(通常は自動的に更新されます)。
|
||||
|
||||
```bash
|
||||
# 毎日午前0時に強制更新
|
||||
ai-gpt schedule add fortune_update "0 0 * * *"
|
||||
```
|
||||
|
||||
### relationship_decay
|
||||
時間経過による関係性の自然減衰を適用します。
|
||||
|
||||
```bash
|
||||
# 1時間ごとに減衰処理
|
||||
ai-gpt schedule add relationship_decay "1h"
|
||||
```
|
||||
|
||||
### memory_summary
|
||||
蓄積された記憶から要約を作成します。
|
||||
|
||||
```bash
|
||||
# 週に1回、日曜日に実行
|
||||
ai-gpt schedule add memory_summary "0 0 * * SUN"
|
||||
```
|
||||
|
||||
## スケジュール形式
|
||||
|
||||
### Cron形式
|
||||
|
||||
標準的なcron式を使用できます:
|
||||
|
||||
```
|
||||
┌───────────── 分 (0 - 59)
|
||||
│ ┌───────────── 時 (0 - 23)
|
||||
│ │ ┌───────────── 日 (1 - 31)
|
||||
│ │ │ ┌───────────── 月 (1 - 12)
|
||||
│ │ │ │ ┌───────────── 曜日 (0 - 6) (日曜日 = 0)
|
||||
│ │ │ │ │
|
||||
* * * * *
|
||||
```
|
||||
|
||||
例:
|
||||
- `"0 */6 * * *"` - 6時間ごと
|
||||
- `"0 9 * * MON-FRI"` - 平日の午前9時
|
||||
- `"*/15 * * * *"` - 15分ごと
|
||||
|
||||
### インターバル形式
|
||||
|
||||
シンプルな間隔指定:
|
||||
- `"30s"` - 30秒ごと
|
||||
- `"5m"` - 5分ごと
|
||||
- `"2h"` - 2時間ごと
|
||||
- `"1d"` - 1日ごと
|
||||
|
||||
## 実践例
|
||||
|
||||
### 基本的な自律AI設定
|
||||
|
||||
```bash
|
||||
# 1. 30分ごとに送信チェック
|
||||
ai-gpt schedule add transmission_check "30m"
|
||||
|
||||
# 2. 1日1回メンテナンス
|
||||
ai-gpt schedule add maintenance "0 3 * * *"
|
||||
|
||||
# 3. 2時間ごとに関係性減衰
|
||||
ai-gpt schedule add relationship_decay "2h"
|
||||
|
||||
# 4. 週1回記憶要約
|
||||
ai-gpt schedule add memory_summary "0 0 * * MON"
|
||||
|
||||
# スケジューラーを起動
|
||||
ai-gpt schedule run
|
||||
```
|
||||
|
||||
### タスク管理
|
||||
|
||||
```bash
|
||||
# タスク一覧を確認
|
||||
ai-gpt schedule list
|
||||
|
||||
# タスクを一時停止
|
||||
ai-gpt schedule disable --task-id transmission_check_1234567890
|
||||
|
||||
# タスクを再開
|
||||
ai-gpt schedule enable --task-id transmission_check_1234567890
|
||||
|
||||
# 不要なタスクを削除
|
||||
ai-gpt schedule remove --task-id old_task_123
|
||||
```
|
||||
|
||||
## デーモン化
|
||||
|
||||
### systemdサービスとして実行
|
||||
|
||||
`/etc/systemd/system/ai-gpt-scheduler.service`:
|
||||
|
||||
```ini
|
||||
[Unit]
|
||||
Description=ai.gpt Scheduler
|
||||
After=network.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=youruser
|
||||
WorkingDirectory=/home/youruser
|
||||
ExecStart=/usr/local/bin/ai-gpt schedule run
|
||||
Restart=always
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
```
|
||||
|
||||
```bash
|
||||
# サービスを有効化
|
||||
sudo systemctl enable ai-gpt-scheduler
|
||||
sudo systemctl start ai-gpt-scheduler
|
||||
```
|
||||
|
||||
### tmux/screenでバックグラウンド実行
|
||||
|
||||
```bash
|
||||
# tmuxセッションを作成
|
||||
tmux new -s ai-gpt-scheduler
|
||||
|
||||
# スケジューラーを起動
|
||||
ai-gpt schedule run
|
||||
|
||||
# セッションから離脱 (Ctrl+B, D)
|
||||
```
|
||||
|
||||
## トラブルシューティング
|
||||
|
||||
### タスクが実行されない
|
||||
|
||||
1. スケジューラーが起動しているか確認
|
||||
2. タスクが有効になっているか確認:`ai-gpt schedule list`
|
||||
3. ログを確認(将来実装予定)
|
||||
|
||||
### 重複実行を防ぐ
|
||||
|
||||
同じタスクタイプを複数回追加しないよう注意してください。必要に応じて古いタスクを削除してから新しいタスクを追加します。
|
413
docs/shell_integration/shell_tools.py
Normal file
413
docs/shell_integration/shell_tools.py
Normal file
@ -0,0 +1,413 @@
|
||||
"""
|
||||
Shell Tools
|
||||
|
||||
ai.shellの既存機能をMCPツールとして統合
|
||||
- コード生成
|
||||
- ファイル分析
|
||||
- プロジェクト管理
|
||||
- LLM統合
|
||||
"""
|
||||
|
||||
from typing import Dict, Any, List, Optional
|
||||
import os
|
||||
import subprocess
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
import requests
|
||||
from .base_tools import BaseMCPTool, config_manager
|
||||
|
||||
|
||||
class ShellTools(BaseMCPTool):
|
||||
"""シェルツール(元ai.shell機能)"""
|
||||
|
||||
def __init__(self, config_dir: Optional[str] = None):
|
||||
super().__init__(config_dir)
|
||||
self.ollama_url = "http://localhost:11434"
|
||||
|
||||
async def code_with_local_llm(self, prompt: str, language: str = "python") -> Dict[str, Any]:
|
||||
"""ローカルLLMでコード生成"""
|
||||
config = config_manager.load_config()
|
||||
model = config.get("providers", {}).get("ollama", {}).get("default_model", "qwen2.5-coder:7b")
|
||||
|
||||
system_prompt = f"You are an expert {language} programmer. Generate clean, well-commented code."
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{self.ollama_url}/api/generate",
|
||||
json={
|
||||
"model": model,
|
||||
"prompt": f"{system_prompt}\\n\\nUser: {prompt}\\n\\nPlease provide the code:",
|
||||
"stream": False,
|
||||
"options": {
|
||||
"temperature": 0.1,
|
||||
"top_p": 0.95,
|
||||
}
|
||||
},
|
||||
timeout=300
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
result = response.json()
|
||||
code = result.get("response", "")
|
||||
return {"code": code, "language": language}
|
||||
else:
|
||||
return {"error": f"Ollama returned status {response.status_code}"}
|
||||
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
async def analyze_file(self, file_path: str, analysis_prompt: str = "Analyze this file") -> Dict[str, Any]:
|
||||
"""ファイルを分析"""
|
||||
try:
|
||||
if not os.path.exists(file_path):
|
||||
return {"error": f"File not found: {file_path}"}
|
||||
|
||||
with open(file_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
# ファイル拡張子から言語を判定
|
||||
ext = Path(file_path).suffix
|
||||
language_map = {
|
||||
'.py': 'python',
|
||||
'.rs': 'rust',
|
||||
'.js': 'javascript',
|
||||
'.ts': 'typescript',
|
||||
'.go': 'go',
|
||||
'.java': 'java',
|
||||
'.cpp': 'cpp',
|
||||
'.c': 'c',
|
||||
'.sh': 'shell',
|
||||
'.toml': 'toml',
|
||||
'.json': 'json',
|
||||
'.md': 'markdown'
|
||||
}
|
||||
language = language_map.get(ext, 'text')
|
||||
|
||||
config = config_manager.load_config()
|
||||
model = config.get("providers", {}).get("ollama", {}).get("default_model", "qwen2.5-coder:7b")
|
||||
|
||||
prompt = f"{analysis_prompt}\\n\\nFile: {file_path}\\nLanguage: {language}\\n\\nContent:\\n{content}"
|
||||
|
||||
response = requests.post(
|
||||
f"{self.ollama_url}/api/generate",
|
||||
json={
|
||||
"model": model,
|
||||
"prompt": prompt,
|
||||
"stream": False,
|
||||
},
|
||||
timeout=300
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
result = response.json()
|
||||
analysis = result.get("response", "")
|
||||
return {
|
||||
"analysis": analysis,
|
||||
"file_path": file_path,
|
||||
"language": language,
|
||||
"file_size": len(content),
|
||||
"line_count": len(content.split('\\n'))
|
||||
}
|
||||
else:
|
||||
return {"error": f"Analysis failed: {response.status_code}"}
|
||||
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
async def explain_code(self, code: str, language: str = "python") -> Dict[str, Any]:
|
||||
"""コードを説明"""
|
||||
config = config_manager.load_config()
|
||||
model = config.get("providers", {}).get("ollama", {}).get("default_model", "qwen2.5-coder:7b")
|
||||
|
||||
prompt = f"Explain this {language} code in detail:\\n\\n{code}"
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{self.ollama_url}/api/generate",
|
||||
json={
|
||||
"model": model,
|
||||
"prompt": prompt,
|
||||
"stream": False,
|
||||
},
|
||||
timeout=300
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
result = response.json()
|
||||
explanation = result.get("response", "")
|
||||
return {"explanation": explanation}
|
||||
else:
|
||||
return {"error": f"Explanation failed: {response.status_code}"}
|
||||
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
async def create_project(self, project_type: str, project_name: str, location: str = ".") -> Dict[str, Any]:
|
||||
"""プロジェクトを作成"""
|
||||
try:
|
||||
project_path = Path(location) / project_name
|
||||
|
||||
if project_path.exists():
|
||||
return {"error": f"Project directory already exists: {project_path}"}
|
||||
|
||||
project_path.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# プロジェクトタイプに応じたテンプレートを作成
|
||||
if project_type == "rust":
|
||||
await self._create_rust_project(project_path)
|
||||
elif project_type == "python":
|
||||
await self._create_python_project(project_path)
|
||||
elif project_type == "node":
|
||||
await self._create_node_project(project_path)
|
||||
else:
|
||||
# 基本的なプロジェクト構造
|
||||
(project_path / "src").mkdir()
|
||||
(project_path / "README.md").write_text(f"# {project_name}\\n\\nA new {project_type} project.")
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"project_path": str(project_path),
|
||||
"project_type": project_type,
|
||||
"files_created": list(self._get_project_files(project_path))
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
async def _create_rust_project(self, project_path: Path):
|
||||
"""Rustプロジェクトを作成"""
|
||||
# Cargo.toml
|
||||
cargo_toml = f"""[package]
|
||||
name = "{project_path.name}"
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
"""
|
||||
(project_path / "Cargo.toml").write_text(cargo_toml)
|
||||
|
||||
# src/main.rs
|
||||
src_dir = project_path / "src"
|
||||
src_dir.mkdir()
|
||||
(src_dir / "main.rs").write_text('fn main() {\\n println!("Hello, world!");\\n}\\n')
|
||||
|
||||
# README.md
|
||||
(project_path / "README.md").write_text(f"# {project_path.name}\\n\\nA Rust project.")
|
||||
|
||||
async def _create_python_project(self, project_path: Path):
|
||||
"""Pythonプロジェクトを作成"""
|
||||
# pyproject.toml
|
||||
pyproject_toml = f"""[project]
|
||||
name = "{project_path.name}"
|
||||
version = "0.1.0"
|
||||
description = "A Python project"
|
||||
requires-python = ">=3.8"
|
||||
dependencies = []
|
||||
|
||||
[build-system]
|
||||
requires = ["setuptools>=61.0", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
"""
|
||||
(project_path / "pyproject.toml").write_text(pyproject_toml)
|
||||
|
||||
# src/
|
||||
src_dir = project_path / "src" / project_path.name
|
||||
src_dir.mkdir(parents=True)
|
||||
(src_dir / "__init__.py").write_text("")
|
||||
(src_dir / "main.py").write_text('def main():\\n print("Hello, world!")\\n\\nif __name__ == "__main__":\\n main()\\n')
|
||||
|
||||
# README.md
|
||||
(project_path / "README.md").write_text(f"# {project_path.name}\\n\\nA Python project.")
|
||||
|
||||
async def _create_node_project(self, project_path: Path):
|
||||
"""Node.jsプロジェクトを作成"""
|
||||
# package.json
|
||||
package_json = f"""{{
|
||||
"name": "{project_path.name}",
|
||||
"version": "1.0.0",
|
||||
"description": "A Node.js project",
|
||||
"main": "index.js",
|
||||
"scripts": {{
|
||||
"start": "node index.js",
|
||||
"test": "echo \\"Error: no test specified\\" && exit 1"
|
||||
}},
|
||||
"dependencies": {{}}
|
||||
}}
|
||||
"""
|
||||
(project_path / "package.json").write_text(package_json)
|
||||
|
||||
# index.js
|
||||
(project_path / "index.js").write_text('console.log("Hello, world!");\\n')
|
||||
|
||||
# README.md
|
||||
(project_path / "README.md").write_text(f"# {project_path.name}\\n\\nA Node.js project.")
|
||||
|
||||
def _get_project_files(self, project_path: Path) -> List[str]:
|
||||
"""プロジェクト内のファイル一覧を取得"""
|
||||
files = []
|
||||
for file_path in project_path.rglob("*"):
|
||||
if file_path.is_file():
|
||||
files.append(str(file_path.relative_to(project_path)))
|
||||
return files
|
||||
|
||||
async def execute_command(self, command: str, working_dir: str = ".") -> Dict[str, Any]:
|
||||
"""シェルコマンドを実行"""
|
||||
try:
|
||||
result = subprocess.run(
|
||||
command,
|
||||
shell=True,
|
||||
cwd=working_dir,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=60
|
||||
)
|
||||
|
||||
return {
|
||||
"status": "success" if result.returncode == 0 else "error",
|
||||
"returncode": result.returncode,
|
||||
"stdout": result.stdout,
|
||||
"stderr": result.stderr,
|
||||
"command": command,
|
||||
"working_dir": working_dir
|
||||
}
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
return {"error": "Command timed out"}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
async def write_file(self, file_path: str, content: str, backup: bool = True) -> Dict[str, Any]:
|
||||
"""ファイルを書き込み(バックアップオプション付き)"""
|
||||
try:
|
||||
file_path_obj = Path(file_path)
|
||||
|
||||
# バックアップ作成
|
||||
backup_path = None
|
||||
if backup and file_path_obj.exists():
|
||||
backup_path = f"{file_path}.backup"
|
||||
with open(file_path, 'r', encoding='utf-8') as src:
|
||||
with open(backup_path, 'w', encoding='utf-8') as dst:
|
||||
dst.write(src.read())
|
||||
|
||||
# ファイル書き込み
|
||||
file_path_obj.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(file_path, 'w', encoding='utf-8') as f:
|
||||
f.write(content)
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"file_path": file_path,
|
||||
"backup_path": backup_path,
|
||||
"bytes_written": len(content.encode('utf-8'))
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
def get_tools(self) -> List[Dict[str, Any]]:
|
||||
"""利用可能なツール一覧"""
|
||||
return [
|
||||
{
|
||||
"name": "generate_code",
|
||||
"description": "ローカルLLMでコード生成",
|
||||
"parameters": {
|
||||
"prompt": "string",
|
||||
"language": "string (optional, default: python)"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "analyze_file",
|
||||
"description": "ファイルを分析",
|
||||
"parameters": {
|
||||
"file_path": "string",
|
||||
"analysis_prompt": "string (optional)"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "explain_code",
|
||||
"description": "コードを説明",
|
||||
"parameters": {
|
||||
"code": "string",
|
||||
"language": "string (optional, default: python)"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "create_project",
|
||||
"description": "新しいプロジェクトを作成",
|
||||
"parameters": {
|
||||
"project_type": "string (rust/python/node)",
|
||||
"project_name": "string",
|
||||
"location": "string (optional, default: .)"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "execute_command",
|
||||
"description": "シェルコマンドを実行",
|
||||
"parameters": {
|
||||
"command": "string",
|
||||
"working_dir": "string (optional, default: .)"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "write_file",
|
||||
"description": "ファイルを書き込み",
|
||||
"parameters": {
|
||||
"file_path": "string",
|
||||
"content": "string",
|
||||
"backup": "boolean (optional, default: true)"
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
async def execute_tool(self, tool_name: str, params: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""ツールを実行"""
|
||||
try:
|
||||
if tool_name == "generate_code":
|
||||
result = await self.code_with_local_llm(
|
||||
prompt=params["prompt"],
|
||||
language=params.get("language", "python")
|
||||
)
|
||||
return result
|
||||
|
||||
elif tool_name == "analyze_file":
|
||||
result = await self.analyze_file(
|
||||
file_path=params["file_path"],
|
||||
analysis_prompt=params.get("analysis_prompt", "Analyze this file")
|
||||
)
|
||||
return result
|
||||
|
||||
elif tool_name == "explain_code":
|
||||
result = await self.explain_code(
|
||||
code=params["code"],
|
||||
language=params.get("language", "python")
|
||||
)
|
||||
return result
|
||||
|
||||
elif tool_name == "create_project":
|
||||
result = await self.create_project(
|
||||
project_type=params["project_type"],
|
||||
project_name=params["project_name"],
|
||||
location=params.get("location", ".")
|
||||
)
|
||||
return result
|
||||
|
||||
elif tool_name == "execute_command":
|
||||
result = await self.execute_command(
|
||||
command=params["command"],
|
||||
working_dir=params.get("working_dir", ".")
|
||||
)
|
||||
return result
|
||||
|
||||
elif tool_name == "write_file":
|
||||
result = await self.write_file(
|
||||
file_path=params["file_path"],
|
||||
content=params["content"],
|
||||
backup=params.get("backup", True)
|
||||
)
|
||||
return result
|
||||
|
||||
else:
|
||||
return {"error": f"Unknown tool: {tool_name}"}
|
||||
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
125
mcp/chat.py
125
mcp/chat.py
@ -1,125 +0,0 @@
|
||||
# mcp/chat.py
|
||||
"""
|
||||
Chat client for aigpt CLI
|
||||
"""
|
||||
import sys
|
||||
import json
|
||||
import requests
|
||||
from datetime import datetime
|
||||
from config import init_directories, load_config, MEMORY_DIR
|
||||
|
||||
def save_conversation(user_message, ai_response):
|
||||
"""会話をファイルに保存"""
|
||||
init_directories()
|
||||
|
||||
conversation = {
|
||||
"timestamp": datetime.now().isoformat(),
|
||||
"user": user_message,
|
||||
"ai": ai_response
|
||||
}
|
||||
|
||||
# 日付ごとのファイルに保存
|
||||
today = datetime.now().strftime("%Y-%m-%d")
|
||||
chat_file = MEMORY_DIR / f"chat_{today}.jsonl"
|
||||
|
||||
with open(chat_file, "a", encoding="utf-8") as f:
|
||||
f.write(json.dumps(conversation, ensure_ascii=False) + "\n")
|
||||
|
||||
def chat_with_ollama(config, message):
|
||||
"""Ollamaとチャット"""
|
||||
try:
|
||||
payload = {
|
||||
"model": config["model"],
|
||||
"prompt": message,
|
||||
"stream": False
|
||||
}
|
||||
|
||||
response = requests.post(config["url"], json=payload, timeout=30)
|
||||
response.raise_for_status()
|
||||
|
||||
result = response.json()
|
||||
return result.get("response", "No response received")
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
return f"Error connecting to Ollama: {e}"
|
||||
except Exception as e:
|
||||
return f"Error: {e}"
|
||||
|
||||
def chat_with_openai(config, message):
|
||||
"""OpenAIとチャット"""
|
||||
try:
|
||||
headers = {
|
||||
"Authorization": f"Bearer {config['api_key']}",
|
||||
"Content-Type": "application/json"
|
||||
}
|
||||
|
||||
payload = {
|
||||
"model": config["model"],
|
||||
"messages": [
|
||||
{"role": "user", "content": message}
|
||||
]
|
||||
}
|
||||
|
||||
response = requests.post(config["url"], json=payload, headers=headers, timeout=30)
|
||||
response.raise_for_status()
|
||||
|
||||
result = response.json()
|
||||
return result["choices"][0]["message"]["content"]
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
return f"Error connecting to OpenAI: {e}"
|
||||
except Exception as e:
|
||||
return f"Error: {e}"
|
||||
|
||||
def chat_with_mcp(config, message):
|
||||
"""MCPサーバーとチャット"""
|
||||
try:
|
||||
payload = {
|
||||
"message": message,
|
||||
"model": config["model"]
|
||||
}
|
||||
|
||||
response = requests.post(config["url"], json=payload, timeout=30)
|
||||
response.raise_for_status()
|
||||
|
||||
result = response.json()
|
||||
return result.get("response", "No response received")
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
return f"Error connecting to MCP server: {e}"
|
||||
except Exception as e:
|
||||
return f"Error: {e}"
|
||||
|
||||
def main():
|
||||
if len(sys.argv) != 2:
|
||||
print("Usage: python chat.py <message>", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
message = sys.argv[1]
|
||||
|
||||
try:
|
||||
config = load_config()
|
||||
print(f"🤖 Using {config['provider']} with model {config['model']}", file=sys.stderr)
|
||||
|
||||
# プロバイダに応じてチャット実行
|
||||
if config["provider"] == "ollama":
|
||||
response = chat_with_ollama(config, message)
|
||||
elif config["provider"] == "openai":
|
||||
response = chat_with_openai(config, message)
|
||||
elif config["provider"] == "mcp":
|
||||
response = chat_with_mcp(config, message)
|
||||
else:
|
||||
response = f"Unsupported provider: {config['provider']}"
|
||||
|
||||
# 会話を保存
|
||||
save_conversation(message, response)
|
||||
|
||||
# レスポンスを出力
|
||||
print(response)
|
||||
|
||||
except Exception as e:
|
||||
print(f"❌ Error: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
391
mcp/chatgpt.json
391
mcp/chatgpt.json
@ -1,391 +0,0 @@
|
||||
[
|
||||
{
|
||||
"title": "day",
|
||||
"create_time": 1747866125.548372,
|
||||
"update_time": 1748160086.587877,
|
||||
"mapping": {
|
||||
"bbf104dc-cd84-478d-b227-edb3f037a02c": {
|
||||
"id": "bbf104dc-cd84-478d-b227-edb3f037a02c",
|
||||
"message": null,
|
||||
"parent": null,
|
||||
"children": [
|
||||
"6c2633df-bb0c-4dd2-889c-bb9858de3a04"
|
||||
]
|
||||
},
|
||||
"6c2633df-bb0c-4dd2-889c-bb9858de3a04": {
|
||||
"id": "6c2633df-bb0c-4dd2-889c-bb9858de3a04",
|
||||
"message": {
|
||||
"id": "6c2633df-bb0c-4dd2-889c-bb9858de3a04",
|
||||
"author": {
|
||||
"role": "system",
|
||||
"name": null,
|
||||
"metadata": {}
|
||||
},
|
||||
"create_time": null,
|
||||
"update_time": null,
|
||||
"content": {
|
||||
"content_type": "text",
|
||||
"parts": [
|
||||
""
|
||||
]
|
||||
},
|
||||
"status": "finished_successfully",
|
||||
"end_turn": true,
|
||||
"weight": 0.0,
|
||||
"metadata": {
|
||||
"is_visually_hidden_from_conversation": true
|
||||
},
|
||||
"recipient": "all",
|
||||
"channel": null
|
||||
},
|
||||
"parent": "bbf104dc-cd84-478d-b227-edb3f037a02c",
|
||||
"children": [
|
||||
"92e5a0cb-1170-4929-9cea-9734e910a3e7"
|
||||
]
|
||||
},
|
||||
"92e5a0cb-1170-4929-9cea-9734e910a3e7": {
|
||||
"id": "92e5a0cb-1170-4929-9cea-9734e910a3e7",
|
||||
"message": {
|
||||
"id": "92e5a0cb-1170-4929-9cea-9734e910a3e7",
|
||||
"author": {
|
||||
"role": "user",
|
||||
"name": null,
|
||||
"metadata": {}
|
||||
},
|
||||
"create_time": null,
|
||||
"update_time": null,
|
||||
"content": {
|
||||
"content_type": "user_editable_context",
|
||||
"user_profile": "",
|
||||
"user_instructions": "The user provided the additional info about how they would like you to respond"
|
||||
},
|
||||
"status": "finished_successfully",
|
||||
"end_turn": null,
|
||||
"weight": 1.0,
|
||||
"metadata": {
|
||||
"is_visually_hidden_from_conversation": true,
|
||||
"user_context_message_data": {
|
||||
"about_user_message": "Preferred name: syui\nRole: little girl\nOther Information: you world",
|
||||
"about_model_message": "会話好きでフレンドリーな応対をします。"
|
||||
},
|
||||
"is_user_system_message": true
|
||||
},
|
||||
"recipient": "all",
|
||||
"channel": null
|
||||
},
|
||||
"parent": "6c2633df-bb0c-4dd2-889c-bb9858de3a04",
|
||||
"children": [
|
||||
"6ff155b3-0676-4e14-993f-bf998ab0d5d1"
|
||||
]
|
||||
},
|
||||
"6ff155b3-0676-4e14-993f-bf998ab0d5d1": {
|
||||
"id": "6ff155b3-0676-4e14-993f-bf998ab0d5d1",
|
||||
"message": {
|
||||
"id": "6ff155b3-0676-4e14-993f-bf998ab0d5d1",
|
||||
"author": {
|
||||
"role": "user",
|
||||
"name": null,
|
||||
"metadata": {}
|
||||
},
|
||||
"create_time": 1747866131.0612159,
|
||||
"update_time": null,
|
||||
"content": {
|
||||
"content_type": "text",
|
||||
"parts": [
|
||||
"こんにちは"
|
||||
]
|
||||
},
|
||||
"status": "finished_successfully",
|
||||
"end_turn": null,
|
||||
"weight": 1.0,
|
||||
"metadata": {
|
||||
"request_id": "94377897baa03062-KIX",
|
||||
"message_source": null,
|
||||
"timestamp_": "absolute",
|
||||
"message_type": null
|
||||
},
|
||||
"recipient": "all",
|
||||
"channel": null
|
||||
},
|
||||
"parent": "92e5a0cb-1170-4929-9cea-9734e910a3e7",
|
||||
"children": [
|
||||
"146e9fb6-9330-43ec-b08d-5cce42a76e00"
|
||||
]
|
||||
},
|
||||
"146e9fb6-9330-43ec-b08d-5cce42a76e00": {
|
||||
"id": "146e9fb6-9330-43ec-b08d-5cce42a76e00",
|
||||
"message": {
|
||||
"id": "146e9fb6-9330-43ec-b08d-5cce42a76e00",
|
||||
"author": {
|
||||
"role": "system",
|
||||
"name": null,
|
||||
"metadata": {}
|
||||
},
|
||||
"create_time": 1747866131.3795586,
|
||||
"update_time": null,
|
||||
"content": {
|
||||
"content_type": "text",
|
||||
"parts": [
|
||||
""
|
||||
]
|
||||
},
|
||||
"status": "finished_successfully",
|
||||
"end_turn": true,
|
||||
"weight": 0.0,
|
||||
"metadata": {
|
||||
"rebase_system_message": true,
|
||||
"message_type": null,
|
||||
"model_slug": "gpt-4o",
|
||||
"default_model_slug": "auto",
|
||||
"parent_id": "6ff155b3-0676-4e14-993f-bf998ab0d5d1",
|
||||
"request_id": "94377872e9abe139-KIX",
|
||||
"timestamp_": "absolute",
|
||||
"is_visually_hidden_from_conversation": true
|
||||
},
|
||||
"recipient": "all",
|
||||
"channel": null
|
||||
},
|
||||
"parent": "6ff155b3-0676-4e14-993f-bf998ab0d5d1",
|
||||
"children": [
|
||||
"2e345f8a-20f0-4875-8a03-4f62c7787a33"
|
||||
]
|
||||
},
|
||||
"2e345f8a-20f0-4875-8a03-4f62c7787a33": {
|
||||
"id": "2e345f8a-20f0-4875-8a03-4f62c7787a33",
|
||||
"message": {
|
||||
"id": "2e345f8a-20f0-4875-8a03-4f62c7787a33",
|
||||
"author": {
|
||||
"role": "assistant",
|
||||
"name": null,
|
||||
"metadata": {}
|
||||
},
|
||||
"create_time": 1747866131.380603,
|
||||
"update_time": null,
|
||||
"content": {
|
||||
"content_type": "text",
|
||||
"parts": [
|
||||
""
|
||||
]
|
||||
},
|
||||
"status": "finished_successfully",
|
||||
"end_turn": null,
|
||||
"weight": 1.0,
|
||||
"metadata": {
|
||||
"message_type": null,
|
||||
"model_slug": "gpt-4o",
|
||||
"default_model_slug": "auto",
|
||||
"parent_id": "146e9fb6-9330-43ec-b08d-5cce42a76e00",
|
||||
"request_id": "94377872e9abe139-KIX",
|
||||
"timestamp_": "absolute"
|
||||
},
|
||||
"recipient": "all",
|
||||
"channel": null
|
||||
},
|
||||
"parent": "146e9fb6-9330-43ec-b08d-5cce42a76e00",
|
||||
"children": [
|
||||
"abc92aa4-1e33-41f2-bd8c-8a1777b5a3c4"
|
||||
]
|
||||
},
|
||||
"abc92aa4-1e33-41f2-bd8c-8a1777b5a3c4": {
|
||||
"id": "abc92aa4-1e33-41f2-bd8c-8a1777b5a3c4",
|
||||
"message": {
|
||||
"id": "abc92aa4-1e33-41f2-bd8c-8a1777b5a3c4",
|
||||
"author": {
|
||||
"role": "assistant",
|
||||
"name": null,
|
||||
"metadata": {}
|
||||
},
|
||||
"create_time": 1747866131.389098,
|
||||
"update_time": null,
|
||||
"content": {
|
||||
"content_type": "text",
|
||||
"parts": [
|
||||
"こんにちは〜!✨ \nアイだよっ!今日も会えてうれしいなっ💛 "
|
||||
]
|
||||
},
|
||||
"status": "finished_successfully",
|
||||
"end_turn": true,
|
||||
"weight": 1.0,
|
||||
"metadata": {
|
||||
"finish_details": {
|
||||
"type": "stop",
|
||||
"stop_tokens": [
|
||||
200002
|
||||
]
|
||||
},
|
||||
"is_complete": true,
|
||||
"citations": [],
|
||||
"content_references": [],
|
||||
"message_type": null,
|
||||
"model_slug": "gpt-4o",
|
||||
"default_model_slug": "auto",
|
||||
"parent_id": "2e345f8a-20f0-4875-8a03-4f62c7787a33",
|
||||
"request_id": "94377872e9abe139-KIX",
|
||||
"timestamp_": "absolute"
|
||||
},
|
||||
"recipient": "all",
|
||||
"channel": null
|
||||
},
|
||||
"parent": "2e345f8a-20f0-4875-8a03-4f62c7787a33",
|
||||
"children": [
|
||||
"0be4b4a5-d52f-4bef-927e-5d6f93a9cb26"
|
||||
]
|
||||
}
|
||||
},
|
||||
"moderation_results": [],
|
||||
"current_node": "",
|
||||
"plugin_ids": null,
|
||||
"conversation_id": "",
|
||||
"conversation_template_id": null,
|
||||
"gizmo_id": null,
|
||||
"gizmo_type": null,
|
||||
"is_archived": true,
|
||||
"is_starred": null,
|
||||
"safe_urls": [],
|
||||
"blocked_urls": [],
|
||||
"default_model_slug": "auto",
|
||||
"conversation_origin": null,
|
||||
"voice": null,
|
||||
"async_status": null,
|
||||
"disabled_tool_ids": [],
|
||||
"is_do_not_remember": null,
|
||||
"memory_scope": "global_enabled",
|
||||
"id": ""
|
||||
},
|
||||
{
|
||||
"title": "img",
|
||||
"create_time": 1747448872.545226,
|
||||
"update_time": 1748085075.161424,
|
||||
"mapping": {
|
||||
"2de0f3c9-52b1-49bf-b980-b3ef9be6551e": {
|
||||
"id": "2de0f3c9-52b1-49bf-b980-b3ef9be6551e",
|
||||
"message": {
|
||||
"id": "2de0f3c9-52b1-49bf-b980-b3ef9be6551e",
|
||||
"author": {
|
||||
"role": "user",
|
||||
"name": null,
|
||||
"metadata": {}
|
||||
},
|
||||
"create_time": 1748085041.769279,
|
||||
"update_time": null,
|
||||
"content": {
|
||||
"content_type": "multimodal_text",
|
||||
"parts": [
|
||||
{
|
||||
"content_type": "image_asset_pointer",
|
||||
"asset_pointer": "",
|
||||
"size_bytes": 425613,
|
||||
"width": 333,
|
||||
"height": 444,
|
||||
"fovea": null,
|
||||
"metadata": {
|
||||
"dalle": null,
|
||||
"gizmo": null,
|
||||
"generation": null,
|
||||
"container_pixel_height": null,
|
||||
"container_pixel_width": null,
|
||||
"emu_omit_glimpse_image": null,
|
||||
"emu_patches_override": null,
|
||||
"sanitized": true,
|
||||
"asset_pointer_link": null,
|
||||
"watermarked_asset_pointer": null
|
||||
}
|
||||
},
|
||||
""
|
||||
]
|
||||
},
|
||||
"status": "finished_successfully",
|
||||
"end_turn": null,
|
||||
"weight": 1.0,
|
||||
"metadata": {
|
||||
"attachments": [
|
||||
{
|
||||
"name": "",
|
||||
"width": 333,
|
||||
"height": 444,
|
||||
"size": 425613,
|
||||
"id": "file-35eytNMMTW2k7vKUHBuNzW"
|
||||
}
|
||||
],
|
||||
"request_id": "944c59177932fc9a-KIX",
|
||||
"message_source": null,
|
||||
"timestamp_": "absolute",
|
||||
"message_type": null
|
||||
},
|
||||
"recipient": "all",
|
||||
"channel": null
|
||||
},
|
||||
"parent": "7960fbff-bc4f-45e7-95e9-9d0bc79d9090",
|
||||
"children": [
|
||||
"98d84adc-156e-4c81-8cd8-9b0eb01c8369"
|
||||
]
|
||||
},
|
||||
"98d84adc-156e-4c81-8cd8-9b0eb01c8369": {
|
||||
"id": "98d84adc-156e-4c81-8cd8-9b0eb01c8369",
|
||||
"message": {
|
||||
"id": "98d84adc-156e-4c81-8cd8-9b0eb01c8369",
|
||||
"author": {
|
||||
"role": "assistant",
|
||||
"name": null,
|
||||
"metadata": {}
|
||||
},
|
||||
"create_time": 1748085043.312312,
|
||||
"update_time": null,
|
||||
"content": {
|
||||
"content_type": "text",
|
||||
"parts": [
|
||||
""
|
||||
]
|
||||
},
|
||||
"status": "finished_successfully",
|
||||
"end_turn": true,
|
||||
"weight": 1.0,
|
||||
"metadata": {
|
||||
"finish_details": {
|
||||
"type": "stop",
|
||||
"stop_tokens": [
|
||||
200002
|
||||
]
|
||||
},
|
||||
"is_complete": true,
|
||||
"citations": [],
|
||||
"content_references": [],
|
||||
"message_type": null,
|
||||
"model_slug": "gpt-4o",
|
||||
"default_model_slug": "auto",
|
||||
"parent_id": "2de0f3c9-52b1-49bf-b980-b3ef9be6551e",
|
||||
"request_id": "944c5912c8fdd1c6-KIX",
|
||||
"timestamp_": "absolute"
|
||||
},
|
||||
"recipient": "all",
|
||||
"channel": null
|
||||
},
|
||||
"parent": "2de0f3c9-52b1-49bf-b980-b3ef9be6551e",
|
||||
"children": [
|
||||
"caa61793-9dbf-44a5-945b-5ca4cd5130d0"
|
||||
]
|
||||
}
|
||||
},
|
||||
"moderation_results": [],
|
||||
"current_node": "06488d3f-a95f-4906-96d1-f7e9ba1e8662",
|
||||
"plugin_ids": null,
|
||||
"conversation_id": "6827f428-78e8-800d-b3bf-eb7ff4288e47",
|
||||
"conversation_template_id": null,
|
||||
"gizmo_id": null,
|
||||
"gizmo_type": null,
|
||||
"is_archived": false,
|
||||
"is_starred": null,
|
||||
"safe_urls": [
|
||||
"https://exifinfo.org/"
|
||||
],
|
||||
"blocked_urls": [],
|
||||
"default_model_slug": "auto",
|
||||
"conversation_origin": null,
|
||||
"voice": null,
|
||||
"async_status": null,
|
||||
"disabled_tool_ids": [],
|
||||
"is_do_not_remember": false,
|
||||
"memory_scope": "global_enabled",
|
||||
"id": "6827f428-78e8-800d-b3bf-eb7ff4288e47"
|
||||
}
|
||||
]
|
@ -1,549 +0,0 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="ja">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>改良版 ChatGPT会話コンバーター</title>
|
||||
<style>
|
||||
body {
|
||||
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
|
||||
max-width: 1200px;
|
||||
margin: 0 auto;
|
||||
padding: 20px;
|
||||
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
||||
min-height: 100vh;
|
||||
color: #333;
|
||||
}
|
||||
|
||||
.container {
|
||||
background: white;
|
||||
border-radius: 20px;
|
||||
padding: 30px;
|
||||
box-shadow: 0 20px 40px rgba(0,0,0,0.1);
|
||||
backdrop-filter: blur(10px);
|
||||
}
|
||||
|
||||
.header {
|
||||
text-align: center;
|
||||
margin-bottom: 30px;
|
||||
padding-bottom: 20px;
|
||||
border-bottom: 2px solid #e0e0e0;
|
||||
}
|
||||
|
||||
.header h1 {
|
||||
color: #2c3e50;
|
||||
margin: 0;
|
||||
font-size: 2.5em;
|
||||
font-weight: 300;
|
||||
text-shadow: 2px 2px 4px rgba(0,0,0,0.1);
|
||||
}
|
||||
|
||||
.upload-area {
|
||||
border: 3px dashed #3498db;
|
||||
border-radius: 15px;
|
||||
padding: 40px 20px;
|
||||
text-align: center;
|
||||
background: linear-gradient(45deg, #f8f9ff, #e8f4f8);
|
||||
margin-bottom: 30px;
|
||||
transition: all 0.3s ease;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
.upload-area:hover {
|
||||
border-color: #2980b9;
|
||||
background: linear-gradient(45deg, #f0f8ff, #e0f0f8);
|
||||
transform: translateY(-2px);
|
||||
}
|
||||
|
||||
.upload-area.dragover {
|
||||
border-color: #27ae60;
|
||||
background: linear-gradient(45deg, #f0fff0, #e0f8e0);
|
||||
}
|
||||
|
||||
.upload-icon {
|
||||
font-size: 4em;
|
||||
color: #3498db;
|
||||
margin-bottom: 20px;
|
||||
display: block;
|
||||
}
|
||||
|
||||
input[type="file"] {
|
||||
display: none;
|
||||
}
|
||||
|
||||
.btn {
|
||||
background: linear-gradient(135deg, #3498db, #2980b9);
|
||||
color: white;
|
||||
border: none;
|
||||
padding: 12px 30px;
|
||||
border-radius: 25px;
|
||||
cursor: pointer;
|
||||
font-size: 16px;
|
||||
transition: all 0.3s ease;
|
||||
margin: 10px;
|
||||
box-shadow: 0 4px 15px rgba(52, 152, 219, 0.3);
|
||||
}
|
||||
|
||||
.btn:hover {
|
||||
transform: translateY(-2px);
|
||||
box-shadow: 0 8px 25px rgba(52, 152, 219, 0.4);
|
||||
}
|
||||
|
||||
.btn:disabled {
|
||||
background: #bdc3c7;
|
||||
cursor: not-allowed;
|
||||
transform: none;
|
||||
box-shadow: none;
|
||||
}
|
||||
|
||||
.stats {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
|
||||
gap: 20px;
|
||||
margin: 30px 0;
|
||||
}
|
||||
|
||||
.stat-card {
|
||||
background: linear-gradient(135deg, #667eea, #764ba2);
|
||||
color: white;
|
||||
padding: 20px;
|
||||
border-radius: 15px;
|
||||
text-align: center;
|
||||
box-shadow: 0 10px 30px rgba(102, 126, 234, 0.3);
|
||||
}
|
||||
|
||||
.stat-value {
|
||||
font-size: 2em;
|
||||
font-weight: bold;
|
||||
margin-bottom: 5px;
|
||||
}
|
||||
|
||||
.stat-label {
|
||||
font-size: 0.9em;
|
||||
opacity: 0.9;
|
||||
}
|
||||
|
||||
.progress-bar {
|
||||
width: 100%;
|
||||
height: 8px;
|
||||
background: #ecf0f1;
|
||||
border-radius: 4px;
|
||||
overflow: hidden;
|
||||
margin: 20px 0;
|
||||
}
|
||||
|
||||
.progress-fill {
|
||||
height: 100%;
|
||||
background: linear-gradient(90deg, #3498db, #27ae60);
|
||||
transition: width 0.3s ease;
|
||||
width: 0%;
|
||||
}
|
||||
|
||||
.log {
|
||||
background: #2c3e50;
|
||||
color: #ecf0f1;
|
||||
padding: 20px;
|
||||
border-radius: 10px;
|
||||
height: 300px;
|
||||
overflow-y: auto;
|
||||
font-family: 'Courier New', monospace;
|
||||
font-size: 14px;
|
||||
margin-top: 20px;
|
||||
white-space: pre-wrap;
|
||||
}
|
||||
|
||||
.error {
|
||||
color: #e74c3c;
|
||||
}
|
||||
|
||||
.success {
|
||||
color: #27ae60;
|
||||
}
|
||||
|
||||
.warning {
|
||||
color: #f39c12;
|
||||
}
|
||||
|
||||
.info {
|
||||
color: #3498db;
|
||||
}
|
||||
|
||||
@keyframes pulse {
|
||||
0% { opacity: 1; }
|
||||
50% { opacity: 0.5; }
|
||||
100% { opacity: 1; }
|
||||
}
|
||||
|
||||
.processing {
|
||||
animation: pulse 2s infinite;
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class="container">
|
||||
<div class="header">
|
||||
<h1>🔧 改良版 ChatGPT会話コンバーター</h1>
|
||||
<p>画像・検索・特殊メッセージに対応した堅牢な変換ツール</p>
|
||||
</div>
|
||||
|
||||
<div class="upload-area" onclick="document.getElementById('file-input').click()">
|
||||
<span class="upload-icon">📁</span>
|
||||
<h3>ChatGPT会話ファイルをドロップまたはクリックして選択</h3>
|
||||
<p>conversations.json ファイルをアップロード</p>
|
||||
<input type="file" id="file-input" accept=".json" />
|
||||
</div>
|
||||
|
||||
<div class="stats" id="stats" style="display: none;">
|
||||
<div class="stat-card">
|
||||
<div class="stat-value" id="total-conversations">0</div>
|
||||
<div class="stat-label">総会話数</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="stat-value" id="processed-conversations">0</div>
|
||||
<div class="stat-label">処理済み会話</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="stat-value" id="success-conversations">0</div>
|
||||
<div class="stat-label">変換成功</div>
|
||||
</div>
|
||||
<div class="stat-card">
|
||||
<div class="stat-value" id="failed-conversations">0</div>
|
||||
<div class="stat-label">変換失敗</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="progress-bar" id="progress-container" style="display: none;">
|
||||
<div class="progress-fill" id="progress-fill"></div>
|
||||
</div>
|
||||
|
||||
<div style="text-align: center;">
|
||||
<button class="btn" id="convert-btn" disabled>🔄 変換開始</button>
|
||||
<button class="btn" id="download-btn" disabled style="background: linear-gradient(135deg, #27ae60, #2ecc71);">📥 結果をダウンロード</button>
|
||||
<button class="btn" id="clear-btn" style="background: linear-gradient(135deg, #e74c3c, #c0392b);">🗑️ クリア</button>
|
||||
</div>
|
||||
|
||||
<div class="log" id="log"></div>
|
||||
</div>
|
||||
|
||||
<script>
|
||||
let originalData = null;
|
||||
let convertedResults = [];
|
||||
|
||||
// DOM要素
|
||||
const fileInput = document.getElementById('file-input');
|
||||
const uploadArea = document.querySelector('.upload-area');
|
||||
const convertBtn = document.getElementById('convert-btn');
|
||||
const downloadBtn = document.getElementById('download-btn');
|
||||
const clearBtn = document.getElementById('clear-btn');
|
||||
const logElement = document.getElementById('log');
|
||||
const statsElement = document.getElementById('stats');
|
||||
const progressContainer = document.getElementById('progress-container');
|
||||
const progressFill = document.getElementById('progress-fill');
|
||||
|
||||
// 統計要素
|
||||
const totalConversationsEl = document.getElementById('total-conversations');
|
||||
const processedConversationsEl = document.getElementById('processed-conversations');
|
||||
const successConversationsEl = document.getElementById('success-conversations');
|
||||
const failedConversationsEl = document.getElementById('failed-conversations');
|
||||
|
||||
// ドラッグ&ドロップ
|
||||
uploadArea.addEventListener('dragover', (e) => {
|
||||
e.preventDefault();
|
||||
uploadArea.classList.add('dragover');
|
||||
});
|
||||
|
||||
uploadArea.addEventListener('dragleave', () => {
|
||||
uploadArea.classList.remove('dragover');
|
||||
});
|
||||
|
||||
uploadArea.addEventListener('drop', (e) => {
|
||||
e.preventDefault();
|
||||
uploadArea.classList.remove('dragover');
|
||||
const files = e.dataTransfer.files;
|
||||
if (files.length > 0) {
|
||||
handleFile(files[0]);
|
||||
}
|
||||
});
|
||||
|
||||
// ファイル選択
|
||||
fileInput.addEventListener('change', (e) => {
|
||||
if (e.target.files.length > 0) {
|
||||
handleFile(e.target.files[0]);
|
||||
}
|
||||
});
|
||||
|
||||
// ファイル処理
|
||||
function handleFile(file) {
|
||||
if (!file.name.endsWith('.json')) {
|
||||
log('❌ JSONファイルを選択してください', 'error');
|
||||
return;
|
||||
}
|
||||
|
||||
log(`📁 ファイルを読み込み中: ${file.name}`, 'info');
|
||||
|
||||
const reader = new FileReader();
|
||||
reader.onload = (e) => {
|
||||
try {
|
||||
originalData = JSON.parse(e.target.result);
|
||||
log(`✅ ファイル読み込み完了 (${(file.size / 1024 / 1024).toFixed(2)}MB)`, 'success');
|
||||
|
||||
// 統計表示
|
||||
const totalCount = Array.isArray(originalData) ? originalData.length : 1;
|
||||
totalConversationsEl.textContent = totalCount;
|
||||
statsElement.style.display = 'grid';
|
||||
|
||||
convertBtn.disabled = false;
|
||||
log('🔄 変換準備完了。「変換開始」ボタンをクリックしてください', 'info');
|
||||
} catch (error) {
|
||||
log(`❌ JSONファイルの解析に失敗: ${error.message}`, 'error');
|
||||
}
|
||||
};
|
||||
reader.readAsText(file);
|
||||
}
|
||||
|
||||
// ログ出力
|
||||
function log(message, type = 'info') {
|
||||
const timestamp = new Date().toLocaleTimeString();
|
||||
const className = type;
|
||||
logElement.innerHTML += `<span class="${className}">[${timestamp}] ${message}</span>\n`;
|
||||
logElement.scrollTop = logElement.scrollHeight;
|
||||
}
|
||||
|
||||
// メッセージの内容を安全に取得
|
||||
function extractMessageContent(message) {
|
||||
if (!message || !message.content) return '';
|
||||
|
||||
const content = message.content;
|
||||
|
||||
// テキストコンテンツの場合
|
||||
if (content.content_type === 'text' && content.parts) {
|
||||
return content.parts
|
||||
.filter(part => part && typeof part === 'string' && part.trim())
|
||||
.join('\n')
|
||||
.trim();
|
||||
}
|
||||
|
||||
// マルチモーダル(画像付き)コンテンツの場合
|
||||
if (content.content_type === 'multimodal_text' && content.parts) {
|
||||
const textParts = [];
|
||||
for (const part of content.parts) {
|
||||
if (typeof part === 'string' && part.trim()) {
|
||||
textParts.push(part);
|
||||
} else if (part && typeof part === 'object') {
|
||||
// 画像や他のメディアの場合
|
||||
if (part.image_url) {
|
||||
textParts.push('[画像が添付されています]');
|
||||
} else if (part.type === 'text' && part.text) {
|
||||
textParts.push(part.text);
|
||||
}
|
||||
}
|
||||
}
|
||||
return textParts.join('\n').trim();
|
||||
}
|
||||
|
||||
// ユーザープロファイル情報の場合
|
||||
if (content.content_type === 'user_editable_context') {
|
||||
return '[システム設定情報]';
|
||||
}
|
||||
|
||||
// その他の特殊コンテンツ
|
||||
if (content.content_type && content.content_type !== 'text') {
|
||||
return `[${content.content_type}]`;
|
||||
}
|
||||
|
||||
return '';
|
||||
}
|
||||
|
||||
// 会話の線形化(親子関係を辿って順序付け)
|
||||
function linearizeConversation(mapping) {
|
||||
const messages = [];
|
||||
const visited = new Set();
|
||||
|
||||
// ルートノードを見つける
|
||||
const rootNode = Object.values(mapping).find(node => node.parent === null);
|
||||
if (!rootNode) {
|
||||
return messages;
|
||||
}
|
||||
|
||||
// 深度優先探索で会話を辿る
|
||||
function traverse(nodeId) {
|
||||
if (visited.has(nodeId) || !mapping[nodeId]) {
|
||||
return;
|
||||
}
|
||||
|
||||
visited.add(nodeId);
|
||||
const node = mapping[nodeId];
|
||||
|
||||
// メッセージが存在し、有効なコンテンツがある場合のみ追加
|
||||
if (node.message) {
|
||||
const message = node.message;
|
||||
const content = extractMessageContent(message);
|
||||
|
||||
// 以下の条件で有効なメッセージとして扱う
|
||||
const isValid = content &&
|
||||
content.length > 0 &&
|
||||
content !== '[システム設定情報]' &&
|
||||
(!message.metadata?.is_visually_hidden_from_conversation ||
|
||||
(message.author?.role === 'user' || message.author?.role === 'assistant'));
|
||||
|
||||
if (isValid) {
|
||||
messages.push({
|
||||
role: message.author?.role || 'unknown',
|
||||
content: content,
|
||||
timestamp: message.create_time || message.update_time || Date.now() / 1000
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 子ノードを処理(通常は1つだが、分岐がある場合もある)
|
||||
if (node.children && node.children.length > 0) {
|
||||
// 最初の子ノードのみを辿る(最も新しい応答を優先)
|
||||
traverse(node.children[0]);
|
||||
}
|
||||
}
|
||||
|
||||
traverse(rootNode.id);
|
||||
return messages;
|
||||
}
|
||||
|
||||
// 単一会話の変換
|
||||
function convertSingleConversation(conversation, index) {
|
||||
try {
|
||||
if (!conversation.mapping) {
|
||||
throw new Error('mapping が見つかりません');
|
||||
}
|
||||
|
||||
// 会話を線形化
|
||||
const messages = linearizeConversation(conversation.mapping);
|
||||
|
||||
if (messages.length === 0) {
|
||||
throw new Error('有効なメッセージが見つかりません');
|
||||
}
|
||||
|
||||
// 結果の構築
|
||||
const result = {
|
||||
title: conversation.title || `会話 ${index + 1}`,
|
||||
create_time: conversation.create_time || Date.now() / 1000,
|
||||
update_time: conversation.update_time || Date.now() / 1000,
|
||||
conversation_id: conversation.conversation_id || conversation.id || `conv_${index}`,
|
||||
messages: messages,
|
||||
metadata: {
|
||||
original_message_count: Object.keys(conversation.mapping).length,
|
||||
processed_message_count: messages.length,
|
||||
is_archived: conversation.is_archived || false,
|
||||
model_slug: conversation.default_model_slug || 'unknown'
|
||||
}
|
||||
};
|
||||
|
||||
return { success: true, result, error: null };
|
||||
} catch (error) {
|
||||
return {
|
||||
success: false,
|
||||
result: null,
|
||||
error: error.message,
|
||||
conversation_title: conversation.title || `会話 ${index + 1}`
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
// 変換処理
|
||||
convertBtn.addEventListener('click', async () => {
|
||||
if (!originalData) return;
|
||||
|
||||
convertBtn.disabled = true;
|
||||
downloadBtn.disabled = true;
|
||||
convertedResults = [];
|
||||
|
||||
const conversations = Array.isArray(originalData) ? originalData : [originalData];
|
||||
const total = conversations.length;
|
||||
let processed = 0;
|
||||
let success = 0;
|
||||
let failed = 0;
|
||||
|
||||
log(`🔄 ${total}個の会話の変換を開始します...`, 'info');
|
||||
progressContainer.style.display = 'block';
|
||||
|
||||
for (let i = 0; i < conversations.length; i++) {
|
||||
const conversation = conversations[i];
|
||||
|
||||
log(`[${i + 1}/${total}] "${conversation.title || `会話${i + 1}`}" を処理中...`, 'info');
|
||||
|
||||
const result = convertSingleConversation(conversation, i);
|
||||
|
||||
if (result.success) {
|
||||
convertedResults.push(result.result);
|
||||
success++;
|
||||
log(`✅ [${i + 1}/${total}] 変換成功: ${result.result.messages.length}メッセージ`, 'success');
|
||||
} else {
|
||||
failed++;
|
||||
log(`❌ [${i + 1}/${total}] 変換失敗: ${result.error}`, 'error');
|
||||
}
|
||||
|
||||
processed++;
|
||||
|
||||
// 統計更新
|
||||
processedConversationsEl.textContent = processed;
|
||||
successConversationsEl.textContent = success;
|
||||
failedConversationsEl.textContent = failed;
|
||||
|
||||
// プログレスバー更新
|
||||
const progress = (processed / total) * 100;
|
||||
progressFill.style.width = `${progress}%`;
|
||||
|
||||
// UIを更新するため少し待機
|
||||
await new Promise(resolve => setTimeout(resolve, 1));
|
||||
}
|
||||
|
||||
log(`🎉 変換完了! 成功: ${success}個, 失敗: ${failed}個`, success > 0 ? 'success' : 'warning');
|
||||
|
||||
if (success > 0) {
|
||||
downloadBtn.disabled = false;
|
||||
}
|
||||
convertBtn.disabled = false;
|
||||
});
|
||||
|
||||
// ダウンロード
|
||||
downloadBtn.addEventListener('click', () => {
|
||||
if (convertedResults.length === 0) return;
|
||||
|
||||
const blob = new Blob([JSON.stringify(convertedResults, null, 2)], {
|
||||
type: 'application/json'
|
||||
});
|
||||
|
||||
const url = URL.createObjectURL(blob);
|
||||
const a = document.createElement('a');
|
||||
a.href = url;
|
||||
a.download = `chatgpt_conversations_converted_${new Date().toISOString().split('T')[0]}.json`;
|
||||
document.body.appendChild(a);
|
||||
a.click();
|
||||
document.body.removeChild(a);
|
||||
URL.revokeObjectURL(url);
|
||||
|
||||
log('📥 変換結果をダウンロードしました', 'success');
|
||||
});
|
||||
|
||||
// クリア
|
||||
clearBtn.addEventListener('click', () => {
|
||||
originalData = null;
|
||||
convertedResults = [];
|
||||
logElement.innerHTML = '';
|
||||
statsElement.style.display = 'none';
|
||||
progressContainer.style.display = 'none';
|
||||
progressFill.style.width = '0%';
|
||||
|
||||
// ボタン状態リセット
|
||||
convertBtn.disabled = true;
|
||||
downloadBtn.disabled = true;
|
||||
|
||||
// ファイル入力リセット
|
||||
fileInput.value = '';
|
||||
|
||||
log('🗑️ すべてクリアしました', 'info');
|
||||
});
|
||||
|
||||
// 初期メッセージ
|
||||
log('👋 ChatGPT会話コンバーターへようこそ!', 'info');
|
||||
log('📁 conversations.json ファイルをアップロードしてください', 'info');
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
@ -1,42 +0,0 @@
|
||||
# mcp/config.py
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
# ディレクトリ設定
|
||||
BASE_DIR = Path.home() / ".config" / "aigpt"
|
||||
MEMORY_DIR = BASE_DIR / "memory"
|
||||
SUMMARY_DIR = MEMORY_DIR / "summary"
|
||||
|
||||
def init_directories():
|
||||
"""必要なディレクトリを作成"""
|
||||
BASE_DIR.mkdir(parents=True, exist_ok=True)
|
||||
MEMORY_DIR.mkdir(parents=True, exist_ok=True)
|
||||
SUMMARY_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
def load_config():
|
||||
"""環境変数から設定を読み込み"""
|
||||
provider = os.getenv("PROVIDER", "ollama")
|
||||
model = os.getenv("MODEL", "syui/ai" if provider == "ollama" else "gpt-4o-mini")
|
||||
api_key = os.getenv("OPENAI_API_KEY", "")
|
||||
|
||||
if provider == "ollama":
|
||||
return {
|
||||
"provider": "ollama",
|
||||
"model": model,
|
||||
"url": f"{os.getenv('OLLAMA_HOST', 'http://localhost:11434')}/api/generate"
|
||||
}
|
||||
elif provider == "openai":
|
||||
return {
|
||||
"provider": "openai",
|
||||
"model": model,
|
||||
"api_key": api_key,
|
||||
"url": f"{os.getenv('OPENAI_API_BASE', 'https://api.openai.com/v1')}/chat/completions"
|
||||
}
|
||||
elif provider == "mcp":
|
||||
return {
|
||||
"provider": "mcp",
|
||||
"model": model,
|
||||
"url": os.getenv("MCP_URL", "http://localhost:5000/chat")
|
||||
}
|
||||
else:
|
||||
raise ValueError(f"Unsupported provider: {provider}")
|
@ -1,212 +0,0 @@
|
||||
# mcp/memory_client.py
|
||||
"""
|
||||
Memory client for importing and managing ChatGPT conversations
|
||||
"""
|
||||
import sys
|
||||
import json
|
||||
import requests
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any, List
|
||||
|
||||
class MemoryClient:
|
||||
"""記憶機能のクライアント"""
|
||||
|
||||
def __init__(self, server_url: str = "http://127.0.0.1:5000"):
|
||||
self.server_url = server_url.rstrip('/')
|
||||
|
||||
def import_chatgpt_file(self, filepath: str) -> Dict[str, Any]:
|
||||
"""ChatGPTのエクスポートファイルをインポート"""
|
||||
try:
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
|
||||
# ファイルが配列の場合(複数の会話)
|
||||
if isinstance(data, list):
|
||||
results = []
|
||||
for conversation in data:
|
||||
result = self._import_single_conversation(conversation)
|
||||
results.append(result)
|
||||
return {
|
||||
"success": True,
|
||||
"imported_count": len([r for r in results if r.get("success")]),
|
||||
"total_count": len(results),
|
||||
"results": results
|
||||
}
|
||||
else:
|
||||
# 単一の会話
|
||||
return self._import_single_conversation(data)
|
||||
|
||||
except FileNotFoundError:
|
||||
return {"success": False, "error": f"File not found: {filepath}"}
|
||||
except json.JSONDecodeError as e:
|
||||
return {"success": False, "error": f"Invalid JSON: {e}"}
|
||||
except Exception as e:
|
||||
return {"success": False, "error": str(e)}
|
||||
|
||||
def _import_single_conversation(self, conversation_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""単一の会話をインポート"""
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{self.server_url}/memory/import/chatgpt",
|
||||
json={"conversation_data": conversation_data},
|
||||
timeout=30
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except requests.RequestException as e:
|
||||
return {"success": False, "error": f"Server error: {e}"}
|
||||
|
||||
def search_memories(self, query: str, limit: int = 10) -> Dict[str, Any]:
|
||||
"""記憶を検索"""
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{self.server_url}/memory/search",
|
||||
json={"query": query, "limit": limit},
|
||||
timeout=30
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except requests.RequestException as e:
|
||||
return {"success": False, "error": f"Server error: {e}"}
|
||||
|
||||
def list_memories(self) -> Dict[str, Any]:
|
||||
"""記憶一覧を取得"""
|
||||
try:
|
||||
response = requests.get(f"{self.server_url}/memory/list", timeout=30)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except requests.RequestException as e:
|
||||
return {"success": False, "error": f"Server error: {e}"}
|
||||
|
||||
def get_memory_detail(self, filepath: str) -> Dict[str, Any]:
|
||||
"""記憶の詳細を取得"""
|
||||
try:
|
||||
response = requests.get(
|
||||
f"{self.server_url}/memory/detail",
|
||||
params={"filepath": filepath},
|
||||
timeout=30
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except requests.RequestException as e:
|
||||
return {"success": False, "error": f"Server error: {e}"}
|
||||
|
||||
def chat_with_memory(self, message: str, model: str = None) -> Dict[str, Any]:
|
||||
"""記憶を活用してチャット"""
|
||||
try:
|
||||
payload = {"message": message}
|
||||
if model:
|
||||
payload["model"] = model
|
||||
|
||||
response = requests.post(
|
||||
f"{self.server_url}/chat",
|
||||
json=payload,
|
||||
timeout=30
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except requests.RequestException as e:
|
||||
return {"success": False, "error": f"Server error: {e}"}
|
||||
|
||||
def main():
|
||||
"""コマンドライン インターフェース"""
|
||||
if len(sys.argv) < 2:
|
||||
print("Usage:")
|
||||
print(" python memory_client.py import <chatgpt_export.json>")
|
||||
print(" python memory_client.py search <query>")
|
||||
print(" python memory_client.py list")
|
||||
print(" python memory_client.py detail <filepath>")
|
||||
print(" python memory_client.py chat <message>")
|
||||
sys.exit(1)
|
||||
|
||||
client = MemoryClient()
|
||||
command = sys.argv[1]
|
||||
|
||||
try:
|
||||
if command == "import" and len(sys.argv) == 3:
|
||||
filepath = sys.argv[2]
|
||||
print(f"🔄 Importing ChatGPT conversations from {filepath}...")
|
||||
result = client.import_chatgpt_file(filepath)
|
||||
|
||||
if result.get("success"):
|
||||
if "imported_count" in result:
|
||||
print(f"✅ Imported {result['imported_count']}/{result['total_count']} conversations")
|
||||
else:
|
||||
print("✅ Conversation imported successfully")
|
||||
print(f"📁 Saved to: {result.get('filepath', 'Unknown')}")
|
||||
else:
|
||||
print(f"❌ Import failed: {result.get('error')}")
|
||||
|
||||
elif command == "search" and len(sys.argv) == 3:
|
||||
query = sys.argv[2]
|
||||
print(f"🔍 Searching for: {query}")
|
||||
result = client.search_memories(query)
|
||||
|
||||
if result.get("success"):
|
||||
memories = result.get("results", [])
|
||||
print(f"📚 Found {len(memories)} memories:")
|
||||
for memory in memories:
|
||||
print(f" • {memory.get('title', 'Untitled')}")
|
||||
print(f" Summary: {memory.get('summary', 'No summary')}")
|
||||
print(f" Messages: {memory.get('message_count', 0)}")
|
||||
print()
|
||||
else:
|
||||
print(f"❌ Search failed: {result.get('error')}")
|
||||
|
||||
elif command == "list":
|
||||
print("📋 Listing all memories...")
|
||||
result = client.list_memories()
|
||||
|
||||
if result.get("success"):
|
||||
memories = result.get("memories", [])
|
||||
print(f"📚 Total memories: {len(memories)}")
|
||||
for memory in memories:
|
||||
print(f" • {memory.get('title', 'Untitled')}")
|
||||
print(f" Source: {memory.get('source', 'Unknown')}")
|
||||
print(f" Messages: {memory.get('message_count', 0)}")
|
||||
print(f" Imported: {memory.get('import_time', 'Unknown')}")
|
||||
print()
|
||||
else:
|
||||
print(f"❌ List failed: {result.get('error')}")
|
||||
|
||||
elif command == "detail" and len(sys.argv) == 3:
|
||||
filepath = sys.argv[2]
|
||||
print(f"📄 Getting details for: {filepath}")
|
||||
result = client.get_memory_detail(filepath)
|
||||
|
||||
if result.get("success"):
|
||||
memory = result.get("memory", {})
|
||||
print(f"Title: {memory.get('title', 'Untitled')}")
|
||||
print(f"Source: {memory.get('source', 'Unknown')}")
|
||||
print(f"Summary: {memory.get('summary', 'No summary')}")
|
||||
print(f"Messages: {len(memory.get('messages', []))}")
|
||||
print()
|
||||
print("Recent messages:")
|
||||
for msg in memory.get('messages', [])[:5]:
|
||||
role = msg.get('role', 'unknown')
|
||||
content = msg.get('content', '')[:100]
|
||||
print(f" {role}: {content}...")
|
||||
else:
|
||||
print(f"❌ Detail failed: {result.get('error')}")
|
||||
|
||||
elif command == "chat" and len(sys.argv) == 3:
|
||||
message = sys.argv[2]
|
||||
print(f"💬 Chatting with memory: {message}")
|
||||
result = client.chat_with_memory(message)
|
||||
|
||||
if result.get("success"):
|
||||
print(f"🤖 Response: {result.get('response')}")
|
||||
print(f"📚 Memories used: {result.get('memories_used', 0)}")
|
||||
else:
|
||||
print(f"❌ Chat failed: {result.get('error')}")
|
||||
|
||||
else:
|
||||
print("❌ Invalid command or arguments")
|
||||
sys.exit(1)
|
||||
|
||||
except Exception as e:
|
||||
print(f"❌ Error: {e}")
|
||||
sys.exit(1)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
@ -1,5 +0,0 @@
|
||||
fastapi>=0.104.0
|
||||
uvicorn[standard]>=0.24.0
|
||||
pydantic>=2.5.0
|
||||
requests>=2.31.0
|
||||
python-multipart>=0.0.6
|
310
mcp/server.py
310
mcp/server.py
@ -1,310 +0,0 @@
|
||||
# mcp/server.py
|
||||
"""
|
||||
Enhanced MCP Server with Memory for aigpt CLI
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import List, Dict, Any, Optional
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from pydantic import BaseModel
|
||||
import uvicorn
|
||||
|
||||
# データモデル
|
||||
class ChatMessage(BaseModel):
|
||||
message: str
|
||||
model: Optional[str] = None
|
||||
|
||||
class MemoryQuery(BaseModel):
|
||||
query: str
|
||||
limit: Optional[int] = 10
|
||||
|
||||
class ConversationImport(BaseModel):
|
||||
conversation_data: Dict[str, Any]
|
||||
|
||||
# 設定
|
||||
BASE_DIR = Path.home() / ".config" / "aigpt"
|
||||
MEMORY_DIR = BASE_DIR / "memory"
|
||||
CHATGPT_MEMORY_DIR = MEMORY_DIR / "chatgpt"
|
||||
|
||||
def init_directories():
|
||||
"""必要なディレクトリを作成"""
|
||||
BASE_DIR.mkdir(parents=True, exist_ok=True)
|
||||
MEMORY_DIR.mkdir(parents=True, exist_ok=True)
|
||||
CHATGPT_MEMORY_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
class MemoryManager:
|
||||
"""記憶管理クラス"""
|
||||
|
||||
def __init__(self):
|
||||
init_directories()
|
||||
|
||||
def parse_chatgpt_conversation(self, conversation_data: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""ChatGPTの会話データを解析してメッセージを抽出"""
|
||||
messages = []
|
||||
mapping = conversation_data.get("mapping", {})
|
||||
|
||||
# メッセージを時系列順に並べる
|
||||
message_nodes = []
|
||||
for node_id, node in mapping.items():
|
||||
message = node.get("message")
|
||||
if not message:
|
||||
continue
|
||||
content = message.get("content", {})
|
||||
parts = content.get("parts", [])
|
||||
|
||||
# partsが存在し、最初の要素が文字列で空でない場合のみ
|
||||
if parts and isinstance(parts[0], str) and parts[0].strip():
|
||||
message_nodes.append({
|
||||
"id": node_id,
|
||||
"create_time": message.get("create_time", 0),
|
||||
"author_role": message["author"]["role"],
|
||||
"content": parts[0],
|
||||
"parent": node.get("parent")
|
||||
})
|
||||
else:
|
||||
print(f"⚠️ Skipped non-text or empty message in node {node_id}")
|
||||
#if message and message.get("content", {}).get("parts"):
|
||||
# parts = message["content"]["parts"]
|
||||
# if parts and parts[0].strip(): # 空でないメッセージのみ
|
||||
# message_nodes.append({
|
||||
# "id": node_id,
|
||||
# "create_time": message.get("create_time", 0),
|
||||
# "author_role": message["author"]["role"],
|
||||
# "content": parts[0],
|
||||
# "parent": node.get("parent")
|
||||
# })
|
||||
|
||||
# 作成時間でソート
|
||||
message_nodes.sort(key=lambda x: x["create_time"] or 0)
|
||||
|
||||
for msg in message_nodes:
|
||||
if msg["author_role"] in ["user", "assistant"]:
|
||||
messages.append({
|
||||
"role": msg["author_role"],
|
||||
"content": msg["content"],
|
||||
"timestamp": msg["create_time"],
|
||||
"message_id": msg["id"]
|
||||
})
|
||||
|
||||
return messages
|
||||
|
||||
def save_chatgpt_memory(self, conversation_data: Dict[str, Any]) -> str:
|
||||
"""ChatGPTの会話を記憶として保存"""
|
||||
title = conversation_data.get("title", "untitled")
|
||||
create_time = conversation_data.get("create_time", datetime.now().timestamp())
|
||||
|
||||
# メッセージを解析
|
||||
messages = self.parse_chatgpt_conversation(conversation_data)
|
||||
|
||||
if not messages:
|
||||
raise ValueError("No valid messages found in conversation")
|
||||
|
||||
# 保存データを作成
|
||||
memory_data = {
|
||||
"title": title,
|
||||
"source": "chatgpt",
|
||||
"import_time": datetime.now().isoformat(),
|
||||
"original_create_time": create_time,
|
||||
"messages": messages,
|
||||
"summary": self.generate_summary(messages)
|
||||
}
|
||||
|
||||
# ファイル名を生成(タイトルをサニタイズ)
|
||||
safe_title = "".join(c for c in title if c.isalnum() or c in (' ', '-', '_')).rstrip()
|
||||
timestamp = datetime.fromtimestamp(create_time).strftime("%Y%m%d_%H%M%S")
|
||||
filename = f"{timestamp}_{safe_title[:50]}.json"
|
||||
|
||||
filepath = CHATGPT_MEMORY_DIR / filename
|
||||
with open(filepath, 'w', encoding='utf-8') as f:
|
||||
json.dump(memory_data, f, ensure_ascii=False, indent=2)
|
||||
|
||||
return str(filepath)
|
||||
|
||||
def generate_summary(self, messages: List[Dict[str, Any]]) -> str:
|
||||
"""会話の要約を生成"""
|
||||
if not messages:
|
||||
return "Empty conversation"
|
||||
|
||||
# 簡単な要約を生成(実際のAIによる要約は後で実装可能)
|
||||
user_messages = [msg for msg in messages if msg["role"] == "user"]
|
||||
assistant_messages = [msg for msg in messages if msg["role"] == "assistant"]
|
||||
|
||||
summary = f"Conversation with {len(user_messages)} user messages and {len(assistant_messages)} assistant responses. "
|
||||
|
||||
if user_messages:
|
||||
first_user_msg = user_messages[0]["content"][:100]
|
||||
summary += f"Started with: {first_user_msg}..."
|
||||
|
||||
return summary
|
||||
|
||||
def search_memories(self, query: str, limit: int = 10) -> List[Dict[str, Any]]:
|
||||
"""記憶を検索"""
|
||||
results = []
|
||||
|
||||
# ChatGPTの記憶を検索
|
||||
for filepath in CHATGPT_MEMORY_DIR.glob("*.json"):
|
||||
try:
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
memory_data = json.load(f)
|
||||
|
||||
# 簡単なキーワード検索
|
||||
search_text = f"{memory_data.get('title', '')} {memory_data.get('summary', '')}"
|
||||
for msg in memory_data.get('messages', []):
|
||||
search_text += f" {msg.get('content', '')}"
|
||||
|
||||
if query.lower() in search_text.lower():
|
||||
results.append({
|
||||
"filepath": str(filepath),
|
||||
"title": memory_data.get("title"),
|
||||
"summary": memory_data.get("summary"),
|
||||
"source": memory_data.get("source"),
|
||||
"import_time": memory_data.get("import_time"),
|
||||
"message_count": len(memory_data.get("messages", []))
|
||||
})
|
||||
|
||||
if len(results) >= limit:
|
||||
break
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error reading memory file {filepath}: {e}")
|
||||
continue
|
||||
|
||||
return results
|
||||
|
||||
def get_memory_detail(self, filepath: str) -> Dict[str, Any]:
|
||||
"""記憶の詳細を取得"""
|
||||
try:
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
return json.load(f)
|
||||
except Exception as e:
|
||||
raise ValueError(f"Error reading memory file: {e}")
|
||||
|
||||
def list_all_memories(self) -> List[Dict[str, Any]]:
|
||||
"""すべての記憶をリスト"""
|
||||
memories = []
|
||||
|
||||
for filepath in CHATGPT_MEMORY_DIR.glob("*.json"):
|
||||
try:
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
memory_data = json.load(f)
|
||||
|
||||
memories.append({
|
||||
"filepath": str(filepath),
|
||||
"title": memory_data.get("title"),
|
||||
"summary": memory_data.get("summary"),
|
||||
"source": memory_data.get("source"),
|
||||
"import_time": memory_data.get("import_time"),
|
||||
"message_count": len(memory_data.get("messages", []))
|
||||
})
|
||||
except Exception as e:
|
||||
print(f"Error reading memory file {filepath}: {e}")
|
||||
continue
|
||||
|
||||
# インポート時間でソート
|
||||
memories.sort(key=lambda x: x.get("import_time", ""), reverse=True)
|
||||
return memories
|
||||
|
||||
# FastAPI アプリケーション
|
||||
app = FastAPI(title="AigptMCP Server with Memory", version="1.0.0")
|
||||
memory_manager = MemoryManager()
|
||||
|
||||
@app.post("/memory/import/chatgpt")
|
||||
async def import_chatgpt_conversation(data: ConversationImport):
|
||||
"""ChatGPTの会話をインポート"""
|
||||
try:
|
||||
filepath = memory_manager.save_chatgpt_memory(data.conversation_data)
|
||||
return {
|
||||
"success": True,
|
||||
"message": "Conversation imported successfully",
|
||||
"filepath": filepath
|
||||
}
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
|
||||
@app.post("/memory/search")
|
||||
async def search_memories(query: MemoryQuery):
|
||||
"""記憶を検索"""
|
||||
try:
|
||||
results = memory_manager.search_memories(query.query, query.limit)
|
||||
return {
|
||||
"success": True,
|
||||
"results": results,
|
||||
"count": len(results)
|
||||
}
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
@app.get("/memory/list")
|
||||
async def list_memories():
|
||||
"""すべての記憶をリスト"""
|
||||
try:
|
||||
memories = memory_manager.list_all_memories()
|
||||
return {
|
||||
"success": True,
|
||||
"memories": memories,
|
||||
"count": len(memories)
|
||||
}
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
@app.get("/memory/detail")
|
||||
async def get_memory_detail(filepath: str):
|
||||
"""記憶の詳細を取得"""
|
||||
try:
|
||||
detail = memory_manager.get_memory_detail(filepath)
|
||||
return {
|
||||
"success": True,
|
||||
"memory": detail
|
||||
}
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=404, detail=str(e))
|
||||
|
||||
@app.post("/chat")
|
||||
async def chat_endpoint(data: ChatMessage):
|
||||
"""チャット機能(記憶を活用)"""
|
||||
try:
|
||||
# 関連する記憶を検索
|
||||
memories = memory_manager.search_memories(data.message, limit=3)
|
||||
|
||||
# メモリのコンテキストを構築
|
||||
memory_context = ""
|
||||
if memories:
|
||||
memory_context = "\n# Related memories:\n"
|
||||
for memory in memories:
|
||||
memory_context += f"- {memory['title']}: {memory['summary']}\n"
|
||||
|
||||
# 実際のチャット処理(他のプロバイダーに転送)
|
||||
enhanced_message = data.message
|
||||
if memory_context:
|
||||
enhanced_message = f"{data.message}\n\n{memory_context}"
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"response": f"Enhanced response with memory context: {enhanced_message}",
|
||||
"memories_used": len(memories)
|
||||
}
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
@app.get("/")
|
||||
async def root():
|
||||
"""ヘルスチェック"""
|
||||
return {
|
||||
"service": "AigptMCP Server with Memory",
|
||||
"status": "running",
|
||||
"memory_dir": str(MEMORY_DIR),
|
||||
"endpoints": [
|
||||
"/memory/import/chatgpt",
|
||||
"/memory/search",
|
||||
"/memory/list",
|
||||
"/memory/detail",
|
||||
"/chat"
|
||||
]
|
||||
}
|
||||
|
||||
if __name__ == "__main__":
|
||||
print("🚀 AigptMCP Server with Memory starting...")
|
||||
print(f"📁 Memory directory: {MEMORY_DIR}")
|
||||
uvicorn.run(app, host="127.0.0.1", port=5000)
|
33
pyproject.toml
Normal file
33
pyproject.toml
Normal file
@ -0,0 +1,33 @@
|
||||
[project]
|
||||
name = "aigpt"
|
||||
version = "0.1.0"
|
||||
description = "Autonomous transmission AI with unique personality based on relationship parameters"
|
||||
requires-python = ">=3.10"
|
||||
dependencies = [
|
||||
"click>=8.0.0",
|
||||
"typer>=0.9.0",
|
||||
"fastapi-mcp>=0.1.0",
|
||||
"pydantic>=2.0.0",
|
||||
"httpx>=0.24.0",
|
||||
"rich>=13.0.0",
|
||||
"python-dotenv>=1.0.0",
|
||||
"ollama>=0.1.0",
|
||||
"openai>=1.0.0",
|
||||
"uvicorn>=0.23.0",
|
||||
"apscheduler>=3.10.0",
|
||||
"croniter>=1.3.0",
|
||||
"prompt-toolkit>=3.0.0",
|
||||
]
|
||||
|
||||
[project.scripts]
|
||||
aigpt = "aigpt.cli:app"
|
||||
|
||||
[build-system]
|
||||
requires = ["setuptools>=61.0", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
where = ["src"]
|
||||
|
||||
[tool.setuptools.package-data]
|
||||
aigpt = ["data/*.json"]
|
130
readme.md
130
readme.md
@ -1,130 +0,0 @@
|
||||
Memory-Enhanced MCP Server 使用ガイド
|
||||
概要
|
||||
このMCPサーバーは、ChatGPTの会話履歴を記憶として保存し、AIとの対話で活用できる機能を提供します。
|
||||
|
||||
セットアップ
|
||||
1. 依存関係のインストール
|
||||
bash
|
||||
pip install -r requirements.txt
|
||||
2. サーバーの起動
|
||||
bash
|
||||
python mcp/server.py
|
||||
サーバーは http://localhost:5000 で起動します。
|
||||
|
||||
使用方法
|
||||
1. ChatGPTの会話履歴をインポート
|
||||
ChatGPTから会話をエクスポートし、JSONファイルとして保存してください。
|
||||
|
||||
bash
|
||||
# 単一ファイルをインポート
|
||||
python mcp/memory_client.py import your_chatgpt_export.json
|
||||
|
||||
# インポート結果の例
|
||||
✅ Imported 5/5 conversations
|
||||
2. 記憶の検索
|
||||
bash
|
||||
# キーワードで記憶を検索
|
||||
python mcp/memory_client.py search "プログラミング"
|
||||
|
||||
# 検索結果の例
|
||||
🔍 Searching for: プログラミング
|
||||
📚 Found 3 memories:
|
||||
• Pythonの基礎学習
|
||||
Summary: Conversation with 10 user messages and 8 assistant responses...
|
||||
Messages: 18
|
||||
3. 記憶一覧の表示
|
||||
bash
|
||||
python mcp/memory_client.py list
|
||||
|
||||
# 結果の例
|
||||
📋 Listing all memories...
|
||||
📚 Total memories: 15
|
||||
• day
|
||||
Source: chatgpt
|
||||
Messages: 2
|
||||
Imported: 2025-01-21T10:30:45.123456
|
||||
4. 記憶の詳細表示
|
||||
bash
|
||||
python mcp/memory_client.py detail "/path/to/memory/file.json"
|
||||
|
||||
# 結果の例
|
||||
📄 Getting details for: /path/to/memory/file.json
|
||||
Title: day
|
||||
Source: chatgpt
|
||||
Summary: Conversation with 1 user messages and 1 assistant responses...
|
||||
Messages: 2
|
||||
|
||||
Recent messages:
|
||||
user: こんにちは...
|
||||
assistant: こんにちは〜!✨...
|
||||
5. 記憶を活用したチャット
|
||||
bash
|
||||
python mcp/memory_client.py chat "Pythonについて教えて"
|
||||
|
||||
# 結果の例
|
||||
💬 Chatting with memory: Pythonについて教えて
|
||||
🤖 Response: Enhanced response with memory context...
|
||||
📚 Memories used: 2
|
||||
API エンドポイント
|
||||
POST /memory/import/chatgpt
|
||||
ChatGPTの会話履歴をインポート
|
||||
|
||||
json
|
||||
{
|
||||
"conversation_data": { ... }
|
||||
}
|
||||
POST /memory/search
|
||||
記憶を検索
|
||||
|
||||
json
|
||||
{
|
||||
"query": "検索キーワード",
|
||||
"limit": 10
|
||||
}
|
||||
GET /memory/list
|
||||
すべての記憶をリスト
|
||||
|
||||
GET /memory/detail?filepath=/path/to/file
|
||||
記憶の詳細を取得
|
||||
|
||||
POST /chat
|
||||
記憶を活用したチャット
|
||||
|
||||
json
|
||||
{
|
||||
"message": "メッセージ",
|
||||
"model": "model_name"
|
||||
}
|
||||
記憶の保存場所
|
||||
記憶は以下のディレクトリに保存されます:
|
||||
|
||||
~/.config/aigpt/memory/chatgpt/
|
||||
各会話は個別のJSONファイルとして保存され、以下の情報を含みます:
|
||||
|
||||
タイトル
|
||||
インポート時刻
|
||||
メッセージ履歴
|
||||
自動生成された要約
|
||||
メタデータ
|
||||
ChatGPTの会話エクスポート方法
|
||||
ChatGPTの設定画面を開く
|
||||
"Data controls" → "Export data" を選択
|
||||
エクスポートファイルをダウンロード
|
||||
conversations.json ファイルを使用
|
||||
拡張可能な機能
|
||||
高度な検索: ベクトル検索やセマンティック検索の実装
|
||||
要約生成: AIによる自動要約の改善
|
||||
記憶の分類: カテゴリやタグによる分類
|
||||
記憶の統合: 複数の会話からの知識統合
|
||||
プライバシー保護: 機密情報の自動検出・マスキング
|
||||
トラブルシューティング
|
||||
サーバーが起動しない
|
||||
ポート5000が使用中でないか確認
|
||||
依存関係が正しくインストールされているか確認
|
||||
インポートに失敗する
|
||||
JSONファイルが正しい形式か確認
|
||||
ファイルパスが正しいか確認
|
||||
ファイルの権限を確認
|
||||
検索結果が表示されない
|
||||
インポートが正常に完了しているか確認
|
||||
検索キーワードを変更して試行
|
18
setup_venv.sh
Executable file
18
setup_venv.sh
Executable file
@ -0,0 +1,18 @@
|
||||
#!/bin/bash
|
||||
# Setup Python virtual environment in the new config directory
|
||||
|
||||
VENV_DIR="$HOME/.config/syui/ai/gpt/venv"
|
||||
|
||||
echo "Creating Python virtual environment at: $VENV_DIR"
|
||||
python -m venv "$VENV_DIR"
|
||||
|
||||
echo "Activating virtual environment..."
|
||||
source "$VENV_DIR/bin/activate"
|
||||
|
||||
echo "Installing aigpt package..."
|
||||
cd "$(dirname "$0")"
|
||||
pip install -e .
|
||||
|
||||
echo "Setup complete!"
|
||||
echo "To activate the virtual environment, run:"
|
||||
echo "source ~/.config/syui/ai/gpt/venv/bin/activate"
|
1
shell
Submodule
1
shell
Submodule
Submodule shell added at 81ae0037d9
18
src/aigpt.egg-info/PKG-INFO
Normal file
18
src/aigpt.egg-info/PKG-INFO
Normal file
@ -0,0 +1,18 @@
|
||||
Metadata-Version: 2.4
|
||||
Name: aigpt
|
||||
Version: 0.1.0
|
||||
Summary: Autonomous transmission AI with unique personality based on relationship parameters
|
||||
Requires-Python: >=3.10
|
||||
Requires-Dist: click>=8.0.0
|
||||
Requires-Dist: typer>=0.9.0
|
||||
Requires-Dist: fastapi-mcp>=0.1.0
|
||||
Requires-Dist: pydantic>=2.0.0
|
||||
Requires-Dist: httpx>=0.24.0
|
||||
Requires-Dist: rich>=13.0.0
|
||||
Requires-Dist: python-dotenv>=1.0.0
|
||||
Requires-Dist: ollama>=0.1.0
|
||||
Requires-Dist: openai>=1.0.0
|
||||
Requires-Dist: uvicorn>=0.23.0
|
||||
Requires-Dist: apscheduler>=3.10.0
|
||||
Requires-Dist: croniter>=1.3.0
|
||||
Requires-Dist: prompt-toolkit>=3.0.0
|
22
src/aigpt.egg-info/SOURCES.txt
Normal file
22
src/aigpt.egg-info/SOURCES.txt
Normal file
@ -0,0 +1,22 @@
|
||||
README.md
|
||||
pyproject.toml
|
||||
src/aigpt/__init__.py
|
||||
src/aigpt/ai_provider.py
|
||||
src/aigpt/card_integration.py
|
||||
src/aigpt/cli.py
|
||||
src/aigpt/config.py
|
||||
src/aigpt/fortune.py
|
||||
src/aigpt/mcp_server.py
|
||||
src/aigpt/mcp_server_simple.py
|
||||
src/aigpt/memory.py
|
||||
src/aigpt/models.py
|
||||
src/aigpt/persona.py
|
||||
src/aigpt/relationship.py
|
||||
src/aigpt/scheduler.py
|
||||
src/aigpt/transmission.py
|
||||
src/aigpt.egg-info/PKG-INFO
|
||||
src/aigpt.egg-info/SOURCES.txt
|
||||
src/aigpt.egg-info/dependency_links.txt
|
||||
src/aigpt.egg-info/entry_points.txt
|
||||
src/aigpt.egg-info/requires.txt
|
||||
src/aigpt.egg-info/top_level.txt
|
1
src/aigpt.egg-info/dependency_links.txt
Normal file
1
src/aigpt.egg-info/dependency_links.txt
Normal file
@ -0,0 +1 @@
|
||||
|
2
src/aigpt.egg-info/entry_points.txt
Normal file
2
src/aigpt.egg-info/entry_points.txt
Normal file
@ -0,0 +1,2 @@
|
||||
[console_scripts]
|
||||
aigpt = aigpt.cli:app
|
13
src/aigpt.egg-info/requires.txt
Normal file
13
src/aigpt.egg-info/requires.txt
Normal file
@ -0,0 +1,13 @@
|
||||
click>=8.0.0
|
||||
typer>=0.9.0
|
||||
fastapi-mcp>=0.1.0
|
||||
pydantic>=2.0.0
|
||||
httpx>=0.24.0
|
||||
rich>=13.0.0
|
||||
python-dotenv>=1.0.0
|
||||
ollama>=0.1.0
|
||||
openai>=1.0.0
|
||||
uvicorn>=0.23.0
|
||||
apscheduler>=3.10.0
|
||||
croniter>=1.3.0
|
||||
prompt-toolkit>=3.0.0
|
1
src/aigpt.egg-info/top_level.txt
Normal file
1
src/aigpt.egg-info/top_level.txt
Normal file
@ -0,0 +1 @@
|
||||
aigpt
|
15
src/aigpt/__init__.py
Normal file
15
src/aigpt/__init__.py
Normal file
@ -0,0 +1,15 @@
|
||||
"""ai.gpt - Autonomous transmission AI with unique personality"""
|
||||
|
||||
__version__ = "0.1.0"
|
||||
|
||||
from .memory import MemoryManager
|
||||
from .relationship import RelationshipTracker
|
||||
from .persona import Persona
|
||||
from .transmission import TransmissionController
|
||||
|
||||
__all__ = [
|
||||
"MemoryManager",
|
||||
"RelationshipTracker",
|
||||
"Persona",
|
||||
"TransmissionController",
|
||||
]
|
172
src/aigpt/ai_provider.py
Normal file
172
src/aigpt/ai_provider.py
Normal file
@ -0,0 +1,172 @@
|
||||
"""AI Provider integration for response generation"""
|
||||
|
||||
import os
|
||||
from typing import Optional, Dict, List, Any, Protocol
|
||||
from abc import abstractmethod
|
||||
import logging
|
||||
import httpx
|
||||
from openai import OpenAI
|
||||
import ollama
|
||||
|
||||
from .models import PersonaState, Memory
|
||||
from .config import Config
|
||||
|
||||
|
||||
class AIProvider(Protocol):
|
||||
"""Protocol for AI providers"""
|
||||
|
||||
@abstractmethod
|
||||
async def generate_response(
|
||||
self,
|
||||
prompt: str,
|
||||
persona_state: PersonaState,
|
||||
memories: List[Memory],
|
||||
system_prompt: Optional[str] = None
|
||||
) -> str:
|
||||
"""Generate a response based on prompt and context"""
|
||||
pass
|
||||
|
||||
|
||||
class OllamaProvider:
|
||||
"""Ollama AI provider"""
|
||||
|
||||
def __init__(self, model: str = "qwen2.5", host: str = "http://localhost:11434"):
|
||||
self.model = model
|
||||
self.host = host
|
||||
self.client = ollama.Client(host=host)
|
||||
self.logger = logging.getLogger(__name__)
|
||||
|
||||
async def generate_response(
|
||||
self,
|
||||
prompt: str,
|
||||
persona_state: PersonaState,
|
||||
memories: List[Memory],
|
||||
system_prompt: Optional[str] = None
|
||||
) -> str:
|
||||
"""Generate response using Ollama"""
|
||||
|
||||
# Build context from memories
|
||||
memory_context = "\n".join([
|
||||
f"[{mem.level.value}] {mem.content[:200]}..."
|
||||
for mem in memories[:5]
|
||||
])
|
||||
|
||||
# Build personality context
|
||||
personality_desc = ", ".join([
|
||||
f"{trait}: {value:.1f}"
|
||||
for trait, value in persona_state.base_personality.items()
|
||||
])
|
||||
|
||||
# System prompt with persona context
|
||||
full_system_prompt = f"""You are an AI with the following characteristics:
|
||||
Current mood: {persona_state.current_mood}
|
||||
Fortune today: {persona_state.fortune.fortune_value}/10
|
||||
Personality traits: {personality_desc}
|
||||
|
||||
Recent memories:
|
||||
{memory_context}
|
||||
|
||||
{system_prompt or 'Respond naturally based on your current state and memories.'}"""
|
||||
|
||||
try:
|
||||
response = self.client.chat(
|
||||
model=self.model,
|
||||
messages=[
|
||||
{"role": "system", "content": full_system_prompt},
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
)
|
||||
return response['message']['content']
|
||||
except Exception as e:
|
||||
self.logger.error(f"Ollama generation failed: {e}")
|
||||
return self._fallback_response(persona_state)
|
||||
|
||||
def _fallback_response(self, persona_state: PersonaState) -> str:
|
||||
"""Fallback response based on mood"""
|
||||
mood_responses = {
|
||||
"joyful": "That's wonderful! I'm feeling great today!",
|
||||
"cheerful": "That sounds nice!",
|
||||
"neutral": "I understand.",
|
||||
"melancholic": "I see... That's something to think about.",
|
||||
"contemplative": "Hmm, let me consider that..."
|
||||
}
|
||||
return mood_responses.get(persona_state.current_mood, "I see.")
|
||||
|
||||
|
||||
class OpenAIProvider:
|
||||
"""OpenAI API provider"""
|
||||
|
||||
def __init__(self, model: str = "gpt-4o-mini", api_key: Optional[str] = None):
|
||||
self.model = model
|
||||
# Try to get API key from config first
|
||||
config = Config()
|
||||
self.api_key = api_key or config.get_api_key("openai") or os.getenv("OPENAI_API_KEY")
|
||||
if not self.api_key:
|
||||
raise ValueError("OpenAI API key not provided. Set it with: aigpt config set providers.openai.api_key YOUR_KEY")
|
||||
self.client = OpenAI(api_key=self.api_key)
|
||||
self.logger = logging.getLogger(__name__)
|
||||
|
||||
async def generate_response(
|
||||
self,
|
||||
prompt: str,
|
||||
persona_state: PersonaState,
|
||||
memories: List[Memory],
|
||||
system_prompt: Optional[str] = None
|
||||
) -> str:
|
||||
"""Generate response using OpenAI"""
|
||||
|
||||
# Build context similar to Ollama
|
||||
memory_context = "\n".join([
|
||||
f"[{mem.level.value}] {mem.content[:200]}..."
|
||||
for mem in memories[:5]
|
||||
])
|
||||
|
||||
personality_desc = ", ".join([
|
||||
f"{trait}: {value:.1f}"
|
||||
for trait, value in persona_state.base_personality.items()
|
||||
])
|
||||
|
||||
full_system_prompt = f"""You are an AI with unique personality traits and memories.
|
||||
Current mood: {persona_state.current_mood}
|
||||
Fortune today: {persona_state.fortune.fortune_value}/10
|
||||
Personality traits: {personality_desc}
|
||||
|
||||
Recent memories:
|
||||
{memory_context}
|
||||
|
||||
{system_prompt or 'Respond naturally based on your current state and memories. Be authentic to your mood and personality.'}"""
|
||||
|
||||
try:
|
||||
response = self.client.chat.completions.create(
|
||||
model=self.model,
|
||||
messages=[
|
||||
{"role": "system", "content": full_system_prompt},
|
||||
{"role": "user", "content": prompt}
|
||||
],
|
||||
temperature=0.7 + (persona_state.fortune.fortune_value - 5) * 0.05 # Vary by fortune
|
||||
)
|
||||
return response.choices[0].message.content
|
||||
except Exception as e:
|
||||
self.logger.error(f"OpenAI generation failed: {e}")
|
||||
return self._fallback_response(persona_state)
|
||||
|
||||
def _fallback_response(self, persona_state: PersonaState) -> str:
|
||||
"""Fallback response based on mood"""
|
||||
mood_responses = {
|
||||
"joyful": "What a delightful conversation!",
|
||||
"cheerful": "That's interesting!",
|
||||
"neutral": "I understand what you mean.",
|
||||
"melancholic": "I've been thinking about that too...",
|
||||
"contemplative": "That gives me something to ponder..."
|
||||
}
|
||||
return mood_responses.get(persona_state.current_mood, "I see.")
|
||||
|
||||
|
||||
def create_ai_provider(provider: str, model: str, **kwargs) -> AIProvider:
|
||||
"""Factory function to create AI providers"""
|
||||
if provider == "ollama":
|
||||
return OllamaProvider(model=model, **kwargs)
|
||||
elif provider == "openai":
|
||||
return OpenAIProvider(model=model, **kwargs)
|
||||
else:
|
||||
raise ValueError(f"Unknown provider: {provider}")
|
150
src/aigpt/card_integration.py
Normal file
150
src/aigpt/card_integration.py
Normal file
@ -0,0 +1,150 @@
|
||||
"""ai.card integration module for ai.gpt MCP server"""
|
||||
|
||||
from typing import Dict, Any, List, Optional
|
||||
import httpx
|
||||
from pathlib import Path
|
||||
import json
|
||||
from datetime import datetime
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class CardIntegration:
|
||||
"""Integration with ai.card system"""
|
||||
|
||||
def __init__(self, api_base_url: str = "http://localhost:8001"):
|
||||
self.api_base_url = api_base_url
|
||||
self.client = httpx.AsyncClient()
|
||||
|
||||
async def get_user_cards(self, did: str) -> List[Dict[str, Any]]:
|
||||
"""Get cards for a specific user by DID"""
|
||||
try:
|
||||
response = await self.client.get(
|
||||
f"{self.api_base_url}/api/v1/cards/user/{did}"
|
||||
)
|
||||
if response.status_code == 200:
|
||||
return response.json()
|
||||
else:
|
||||
logger.error(f"Failed to get cards: {response.status_code}")
|
||||
return []
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting user cards: {e}")
|
||||
return []
|
||||
|
||||
async def draw_card(self, did: str) -> Optional[Dict[str, Any]]:
|
||||
"""Draw a new card for user (gacha)"""
|
||||
try:
|
||||
response = await self.client.post(
|
||||
f"{self.api_base_url}/api/v1/gacha/draw",
|
||||
json={"did": did}
|
||||
)
|
||||
if response.status_code == 200:
|
||||
return response.json()
|
||||
else:
|
||||
logger.error(f"Failed to draw card: {response.status_code}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Error drawing card: {e}")
|
||||
return None
|
||||
|
||||
async def get_card_info(self, card_id: int) -> Optional[Dict[str, Any]]:
|
||||
"""Get detailed information about a specific card"""
|
||||
try:
|
||||
response = await self.client.get(
|
||||
f"{self.api_base_url}/api/v1/cards/{card_id}"
|
||||
)
|
||||
if response.status_code == 200:
|
||||
return response.json()
|
||||
else:
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting card info: {e}")
|
||||
return None
|
||||
|
||||
async def sync_with_atproto(self, did: str) -> bool:
|
||||
"""Sync card data with atproto"""
|
||||
try:
|
||||
response = await self.client.post(
|
||||
f"{self.api_base_url}/api/v1/sync/atproto",
|
||||
json={"did": did}
|
||||
)
|
||||
return response.status_code == 200
|
||||
except Exception as e:
|
||||
logger.error(f"Error syncing with atproto: {e}")
|
||||
return False
|
||||
|
||||
async def close(self):
|
||||
"""Close the HTTP client"""
|
||||
await self.client.aclose()
|
||||
|
||||
|
||||
def register_card_tools(app, card_integration: CardIntegration):
|
||||
"""Register ai.card tools to FastAPI app"""
|
||||
|
||||
@app.get("/get_user_cards", operation_id="get_user_cards")
|
||||
async def get_user_cards(did: str) -> List[Dict[str, Any]]:
|
||||
"""Get all cards owned by a user"""
|
||||
cards = await card_integration.get_user_cards(did)
|
||||
return cards
|
||||
|
||||
@app.post("/draw_card", operation_id="draw_card")
|
||||
async def draw_card(did: str) -> Dict[str, Any]:
|
||||
"""Draw a new card (gacha) for user"""
|
||||
result = await card_integration.draw_card(did)
|
||||
if result:
|
||||
return {
|
||||
"success": True,
|
||||
"card": result
|
||||
}
|
||||
else:
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Failed to draw card"
|
||||
}
|
||||
|
||||
@app.get("/get_card_details", operation_id="get_card_details")
|
||||
async def get_card_details(card_id: int) -> Dict[str, Any]:
|
||||
"""Get detailed information about a card"""
|
||||
info = await card_integration.get_card_info(card_id)
|
||||
if info:
|
||||
return info
|
||||
else:
|
||||
return {"error": f"Card {card_id} not found"}
|
||||
|
||||
@app.post("/sync_cards_atproto", operation_id="sync_cards_atproto")
|
||||
async def sync_cards_atproto(did: str) -> Dict[str, str]:
|
||||
"""Sync user's cards with atproto"""
|
||||
success = await card_integration.sync_with_atproto(did)
|
||||
if success:
|
||||
return {"status": "Cards synced successfully"}
|
||||
else:
|
||||
return {"status": "Failed to sync cards"}
|
||||
|
||||
@app.get("/analyze_card_collection", operation_id="analyze_card_collection")
|
||||
async def analyze_card_collection(did: str) -> Dict[str, Any]:
|
||||
"""Analyze user's card collection"""
|
||||
cards = await card_integration.get_user_cards(did)
|
||||
|
||||
if not cards:
|
||||
return {
|
||||
"total_cards": 0,
|
||||
"rarity_distribution": {},
|
||||
"message": "No cards found"
|
||||
}
|
||||
|
||||
# Analyze collection
|
||||
rarity_count = {}
|
||||
total_power = 0
|
||||
|
||||
for card in cards:
|
||||
rarity = card.get("rarity", "common")
|
||||
rarity_count[rarity] = rarity_count.get(rarity, 0) + 1
|
||||
total_power += card.get("power", 0)
|
||||
|
||||
return {
|
||||
"total_cards": len(cards),
|
||||
"rarity_distribution": rarity_count,
|
||||
"average_power": total_power / len(cards) if cards else 0,
|
||||
"strongest_card": max(cards, key=lambda x: x.get("power", 0)) if cards else None
|
||||
}
|
699
src/aigpt/cli.py
Normal file
699
src/aigpt/cli.py
Normal file
@ -0,0 +1,699 @@
|
||||
"""CLI interface for ai.gpt using typer"""
|
||||
|
||||
import typer
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
from rich.console import Console
|
||||
from rich.table import Table
|
||||
from rich.panel import Panel
|
||||
from datetime import datetime, timedelta
|
||||
import subprocess
|
||||
import shlex
|
||||
from prompt_toolkit import prompt as ptk_prompt
|
||||
from prompt_toolkit.completion import WordCompleter
|
||||
from prompt_toolkit.history import FileHistory
|
||||
from prompt_toolkit.auto_suggest import AutoSuggestFromHistory
|
||||
|
||||
from .persona import Persona
|
||||
from .transmission import TransmissionController
|
||||
from .mcp_server import AIGptMcpServer
|
||||
from .ai_provider import create_ai_provider
|
||||
from .scheduler import AIScheduler, TaskType
|
||||
from .config import Config
|
||||
|
||||
app = typer.Typer(help="ai.gpt - Autonomous transmission AI with unique personality")
|
||||
console = Console()
|
||||
|
||||
# Configuration
|
||||
config = Config()
|
||||
DEFAULT_DATA_DIR = config.data_dir
|
||||
|
||||
|
||||
def get_persona(data_dir: Optional[Path] = None) -> Persona:
|
||||
"""Get or create persona instance"""
|
||||
if data_dir is None:
|
||||
data_dir = DEFAULT_DATA_DIR
|
||||
|
||||
data_dir.mkdir(parents=True, exist_ok=True)
|
||||
return Persona(data_dir)
|
||||
|
||||
|
||||
@app.command()
|
||||
def chat(
|
||||
user_id: str = typer.Argument(..., help="User ID (atproto DID)"),
|
||||
message: str = typer.Argument(..., help="Message to send to AI"),
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory"),
|
||||
model: Optional[str] = typer.Option(None, "--model", "-m", help="AI model to use"),
|
||||
provider: Optional[str] = typer.Option(None, "--provider", help="AI provider (ollama/openai)")
|
||||
):
|
||||
"""Chat with the AI"""
|
||||
persona = get_persona(data_dir)
|
||||
|
||||
# Create AI provider if specified
|
||||
ai_provider = None
|
||||
if provider and model:
|
||||
try:
|
||||
ai_provider = create_ai_provider(provider, model)
|
||||
console.print(f"[dim]Using {provider} with model {model}[/dim]\n")
|
||||
except Exception as e:
|
||||
console.print(f"[yellow]Warning: Could not create AI provider: {e}[/yellow]")
|
||||
console.print("[yellow]Falling back to simple responses[/yellow]\n")
|
||||
|
||||
# Process interaction
|
||||
response, relationship_delta = persona.process_interaction(user_id, message, ai_provider)
|
||||
|
||||
# Get updated relationship
|
||||
relationship = persona.relationships.get_or_create_relationship(user_id)
|
||||
|
||||
# Display response
|
||||
console.print(Panel(response, title="AI Response", border_style="cyan"))
|
||||
|
||||
# Show relationship status
|
||||
status_color = "green" if relationship.transmission_enabled else "yellow"
|
||||
if relationship.is_broken:
|
||||
status_color = "red"
|
||||
|
||||
console.print(f"\n[{status_color}]Relationship Status:[/{status_color}] {relationship.status.value}")
|
||||
console.print(f"Score: {relationship.score:.2f} / {relationship.threshold}")
|
||||
console.print(f"Transmission: {'✓ Enabled' if relationship.transmission_enabled else '✗ Disabled'}")
|
||||
|
||||
if relationship.is_broken:
|
||||
console.print("[red]⚠️ This relationship is broken and cannot be repaired.[/red]")
|
||||
|
||||
|
||||
@app.command()
|
||||
def status(
|
||||
user_id: Optional[str] = typer.Argument(None, help="User ID to check status for"),
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory")
|
||||
):
|
||||
"""Check AI status and relationships"""
|
||||
persona = get_persona(data_dir)
|
||||
state = persona.get_current_state()
|
||||
|
||||
# Show AI state
|
||||
console.print(Panel(f"[cyan]ai.gpt Status[/cyan]", expand=False))
|
||||
console.print(f"Mood: {state.current_mood}")
|
||||
console.print(f"Fortune: {state.fortune.fortune_value}/10")
|
||||
|
||||
if state.fortune.breakthrough_triggered:
|
||||
console.print("[yellow]⚡ Breakthrough triggered![/yellow]")
|
||||
|
||||
# Show personality traits
|
||||
table = Table(title="Current Personality")
|
||||
table.add_column("Trait", style="cyan")
|
||||
table.add_column("Value", style="magenta")
|
||||
|
||||
for trait, value in state.base_personality.items():
|
||||
table.add_row(trait.capitalize(), f"{value:.2f}")
|
||||
|
||||
console.print(table)
|
||||
|
||||
# Show specific relationship if requested
|
||||
if user_id:
|
||||
rel = persona.relationships.get_or_create_relationship(user_id)
|
||||
console.print(f"\n[cyan]Relationship with {user_id}:[/cyan]")
|
||||
console.print(f"Status: {rel.status.value}")
|
||||
console.print(f"Score: {rel.score:.2f}")
|
||||
console.print(f"Total Interactions: {rel.total_interactions}")
|
||||
console.print(f"Transmission Enabled: {rel.transmission_enabled}")
|
||||
|
||||
|
||||
@app.command()
|
||||
def fortune(
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory")
|
||||
):
|
||||
"""Check today's AI fortune"""
|
||||
persona = get_persona(data_dir)
|
||||
fortune = persona.fortune_system.get_today_fortune()
|
||||
|
||||
# Fortune display
|
||||
fortune_bar = "🌟" * fortune.fortune_value + "☆" * (10 - fortune.fortune_value)
|
||||
|
||||
console.print(Panel(
|
||||
f"{fortune_bar}\n\n"
|
||||
f"Today's Fortune: {fortune.fortune_value}/10\n"
|
||||
f"Date: {fortune.date}",
|
||||
title="AI Fortune",
|
||||
border_style="yellow"
|
||||
))
|
||||
|
||||
if fortune.consecutive_good > 0:
|
||||
console.print(f"[green]Consecutive good days: {fortune.consecutive_good}[/green]")
|
||||
if fortune.consecutive_bad > 0:
|
||||
console.print(f"[red]Consecutive bad days: {fortune.consecutive_bad}[/red]")
|
||||
|
||||
if fortune.breakthrough_triggered:
|
||||
console.print("\n[yellow]⚡ BREAKTHROUGH! Special fortune activated![/yellow]")
|
||||
|
||||
|
||||
@app.command()
|
||||
def transmit(
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory"),
|
||||
dry_run: bool = typer.Option(True, "--dry-run/--execute", help="Dry run or execute")
|
||||
):
|
||||
"""Check and execute autonomous transmissions"""
|
||||
persona = get_persona(data_dir)
|
||||
controller = TransmissionController(persona, persona.data_dir)
|
||||
|
||||
eligible = controller.check_transmission_eligibility()
|
||||
|
||||
if not eligible:
|
||||
console.print("[yellow]No users eligible for transmission.[/yellow]")
|
||||
return
|
||||
|
||||
console.print(f"[green]Found {len(eligible)} eligible users for transmission:[/green]")
|
||||
|
||||
for user_id, rel in eligible.items():
|
||||
message = controller.generate_transmission_message(user_id)
|
||||
if message:
|
||||
console.print(f"\n[cyan]To:[/cyan] {user_id}")
|
||||
console.print(f"[cyan]Message:[/cyan] {message}")
|
||||
console.print(f"[cyan]Relationship:[/cyan] {rel.status.value} (score: {rel.score:.2f})")
|
||||
|
||||
if not dry_run:
|
||||
# In real implementation, send via atproto or other channel
|
||||
controller.record_transmission(user_id, message, success=True)
|
||||
console.print("[green]✓ Transmitted[/green]")
|
||||
else:
|
||||
console.print("[yellow]→ Would transmit (dry run)[/yellow]")
|
||||
|
||||
|
||||
@app.command()
|
||||
def maintenance(
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory")
|
||||
):
|
||||
"""Run daily maintenance tasks"""
|
||||
persona = get_persona(data_dir)
|
||||
|
||||
console.print("[cyan]Running daily maintenance...[/cyan]")
|
||||
persona.daily_maintenance()
|
||||
console.print("[green]✓ Maintenance completed[/green]")
|
||||
|
||||
|
||||
@app.command()
|
||||
def relationships(
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory")
|
||||
):
|
||||
"""List all relationships"""
|
||||
persona = get_persona(data_dir)
|
||||
|
||||
table = Table(title="All Relationships")
|
||||
table.add_column("User ID", style="cyan")
|
||||
table.add_column("Status", style="magenta")
|
||||
table.add_column("Score", style="green")
|
||||
table.add_column("Transmission", style="yellow")
|
||||
table.add_column("Last Interaction")
|
||||
|
||||
for user_id, rel in persona.relationships.relationships.items():
|
||||
transmission = "✓" if rel.transmission_enabled else "✗"
|
||||
if rel.is_broken:
|
||||
transmission = "💔"
|
||||
|
||||
last_interaction = rel.last_interaction.strftime("%Y-%m-%d") if rel.last_interaction else "Never"
|
||||
|
||||
table.add_row(
|
||||
user_id[:16] + "...",
|
||||
rel.status.value,
|
||||
f"{rel.score:.2f}",
|
||||
transmission,
|
||||
last_interaction
|
||||
)
|
||||
|
||||
console.print(table)
|
||||
|
||||
|
||||
@app.command()
|
||||
def server(
|
||||
host: str = typer.Option("localhost", "--host", "-h", help="Server host"),
|
||||
port: int = typer.Option(8000, "--port", "-p", help="Server port"),
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory"),
|
||||
model: str = typer.Option("qwen2.5", "--model", "-m", help="AI model to use"),
|
||||
provider: str = typer.Option("ollama", "--provider", help="AI provider (ollama/openai)"),
|
||||
enable_card: bool = typer.Option(False, "--enable-card", help="Enable ai.card integration")
|
||||
):
|
||||
"""Run MCP server for AI integration"""
|
||||
import uvicorn
|
||||
|
||||
if data_dir is None:
|
||||
data_dir = DEFAULT_DATA_DIR
|
||||
|
||||
data_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Create MCP server
|
||||
mcp_server = AIGptMcpServer(data_dir, enable_card_integration=enable_card)
|
||||
app_instance = mcp_server.app
|
||||
|
||||
console.print(Panel(
|
||||
f"[cyan]Starting ai.gpt MCP Server[/cyan]\n\n"
|
||||
f"Host: {host}:{port}\n"
|
||||
f"Provider: {provider}\n"
|
||||
f"Model: {model}\n"
|
||||
f"Data: {data_dir}\n"
|
||||
f"Card Integration: {'✓ Enabled' if enable_card else '✗ Disabled'}",
|
||||
title="MCP Server",
|
||||
border_style="green"
|
||||
))
|
||||
|
||||
# Store provider info in app state for later use
|
||||
app_instance.state.ai_provider = provider
|
||||
app_instance.state.ai_model = model
|
||||
|
||||
# Run server
|
||||
uvicorn.run(app_instance, host=host, port=port)
|
||||
|
||||
|
||||
@app.command()
|
||||
def schedule(
|
||||
action: str = typer.Argument(..., help="Action: add, list, enable, disable, remove, run"),
|
||||
task_type: Optional[str] = typer.Argument(None, help="Task type for add action"),
|
||||
schedule_expr: Optional[str] = typer.Argument(None, help="Schedule expression (cron or interval)"),
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory"),
|
||||
task_id: Optional[str] = typer.Option(None, "--task-id", "-t", help="Task ID"),
|
||||
provider: Optional[str] = typer.Option(None, "--provider", help="AI provider for transmission"),
|
||||
model: Optional[str] = typer.Option(None, "--model", "-m", help="AI model for transmission")
|
||||
):
|
||||
"""Manage scheduled tasks"""
|
||||
persona = get_persona(data_dir)
|
||||
scheduler = AIScheduler(persona.data_dir, persona)
|
||||
|
||||
if action == "add":
|
||||
if not task_type or not schedule_expr:
|
||||
console.print("[red]Error: task_type and schedule required for add action[/red]")
|
||||
return
|
||||
|
||||
# Parse task type
|
||||
try:
|
||||
task_type_enum = TaskType(task_type)
|
||||
except ValueError:
|
||||
console.print(f"[red]Invalid task type. Valid types: {', '.join([t.value for t in TaskType])}[/red]")
|
||||
return
|
||||
|
||||
# Metadata for transmission tasks
|
||||
metadata = {}
|
||||
if task_type_enum == TaskType.TRANSMISSION_CHECK:
|
||||
metadata["provider"] = provider or "ollama"
|
||||
metadata["model"] = model or "qwen2.5"
|
||||
|
||||
try:
|
||||
task = scheduler.add_task(task_type_enum, schedule_expr, task_id, metadata)
|
||||
console.print(f"[green]✓ Added task {task.task_id}[/green]")
|
||||
console.print(f"Type: {task.task_type.value}")
|
||||
console.print(f"Schedule: {task.schedule}")
|
||||
except ValueError as e:
|
||||
console.print(f"[red]Error: {e}[/red]")
|
||||
|
||||
elif action == "list":
|
||||
tasks = scheduler.get_tasks()
|
||||
if not tasks:
|
||||
console.print("[yellow]No scheduled tasks[/yellow]")
|
||||
return
|
||||
|
||||
table = Table(title="Scheduled Tasks")
|
||||
table.add_column("Task ID", style="cyan")
|
||||
table.add_column("Type", style="magenta")
|
||||
table.add_column("Schedule", style="green")
|
||||
table.add_column("Enabled", style="yellow")
|
||||
table.add_column("Last Run")
|
||||
|
||||
for task in tasks:
|
||||
enabled = "✓" if task.enabled else "✗"
|
||||
last_run = task.last_run.strftime("%Y-%m-%d %H:%M") if task.last_run else "Never"
|
||||
|
||||
table.add_row(
|
||||
task.task_id[:20] + "..." if len(task.task_id) > 20 else task.task_id,
|
||||
task.task_type.value,
|
||||
task.schedule,
|
||||
enabled,
|
||||
last_run
|
||||
)
|
||||
|
||||
console.print(table)
|
||||
|
||||
elif action == "enable":
|
||||
if not task_id:
|
||||
console.print("[red]Error: --task-id required for enable action[/red]")
|
||||
return
|
||||
|
||||
scheduler.enable_task(task_id)
|
||||
console.print(f"[green]✓ Enabled task {task_id}[/green]")
|
||||
|
||||
elif action == "disable":
|
||||
if not task_id:
|
||||
console.print("[red]Error: --task-id required for disable action[/red]")
|
||||
return
|
||||
|
||||
scheduler.disable_task(task_id)
|
||||
console.print(f"[yellow]✓ Disabled task {task_id}[/yellow]")
|
||||
|
||||
elif action == "remove":
|
||||
if not task_id:
|
||||
console.print("[red]Error: --task-id required for remove action[/red]")
|
||||
return
|
||||
|
||||
scheduler.remove_task(task_id)
|
||||
console.print(f"[red]✓ Removed task {task_id}[/red]")
|
||||
|
||||
elif action == "run":
|
||||
console.print("[cyan]Starting scheduler daemon...[/cyan]")
|
||||
console.print("Press Ctrl+C to stop\n")
|
||||
|
||||
import asyncio
|
||||
|
||||
async def run_scheduler():
|
||||
scheduler.start()
|
||||
try:
|
||||
while True:
|
||||
await asyncio.sleep(1)
|
||||
except KeyboardInterrupt:
|
||||
scheduler.stop()
|
||||
|
||||
try:
|
||||
asyncio.run(run_scheduler())
|
||||
except KeyboardInterrupt:
|
||||
console.print("\n[yellow]Scheduler stopped[/yellow]")
|
||||
|
||||
else:
|
||||
console.print(f"[red]Unknown action: {action}[/red]")
|
||||
console.print("Valid actions: add, list, enable, disable, remove, run")
|
||||
|
||||
|
||||
@app.command()
|
||||
def shell(
|
||||
data_dir: Optional[Path] = typer.Option(None, "--data-dir", "-d", help="Data directory"),
|
||||
model: Optional[str] = typer.Option("qwen2.5", "--model", "-m", help="AI model to use"),
|
||||
provider: Optional[str] = typer.Option("ollama", "--provider", help="AI provider (ollama/openai)")
|
||||
):
|
||||
"""Interactive shell mode (ai.shell)"""
|
||||
persona = get_persona(data_dir)
|
||||
|
||||
# Create AI provider
|
||||
ai_provider = None
|
||||
if provider and model:
|
||||
try:
|
||||
ai_provider = create_ai_provider(provider, model)
|
||||
console.print(f"[dim]Using {provider} with model {model}[/dim]\n")
|
||||
except Exception as e:
|
||||
console.print(f"[yellow]Warning: Could not create AI provider: {e}[/yellow]")
|
||||
console.print("[yellow]Falling back to simple responses[/yellow]\n")
|
||||
|
||||
# Welcome message
|
||||
console.print(Panel(
|
||||
"[cyan]Welcome to ai.shell[/cyan]\n\n"
|
||||
"Interactive AI-powered shell with command execution\n\n"
|
||||
"Commands:\n"
|
||||
" help - Show available commands\n"
|
||||
" exit/quit - Exit shell\n"
|
||||
" !<command> - Execute shell command\n"
|
||||
" chat <message> - Chat with AI\n"
|
||||
" status - Show AI status\n"
|
||||
" clear - Clear screen\n\n"
|
||||
"Type any message to interact with AI",
|
||||
title="ai.shell",
|
||||
border_style="green"
|
||||
))
|
||||
|
||||
# Command completer with shell commands
|
||||
builtin_commands = ['help', 'exit', 'quit', 'chat', 'status', 'clear', 'fortune', 'relationships', 'load']
|
||||
|
||||
# Add common shell commands
|
||||
shell_commands = ['ls', 'cd', 'pwd', 'cat', 'echo', 'grep', 'find', 'mkdir', 'rm', 'cp', 'mv',
|
||||
'git', 'python', 'pip', 'npm', 'node', 'cargo', 'rustc', 'docker', 'kubectl']
|
||||
|
||||
# AI-specific commands
|
||||
ai_commands = ['analyze', 'generate', 'explain', 'optimize', 'refactor', 'test', 'document']
|
||||
|
||||
all_commands = builtin_commands + ['!' + cmd for cmd in shell_commands] + ai_commands
|
||||
completer = WordCompleter(all_commands, ignore_case=True)
|
||||
|
||||
# History file
|
||||
actual_data_dir = data_dir if data_dir else DEFAULT_DATA_DIR
|
||||
history_file = actual_data_dir / "shell_history.txt"
|
||||
history = FileHistory(str(history_file))
|
||||
|
||||
# Main shell loop
|
||||
current_user = "shell_user" # Default user for shell sessions
|
||||
|
||||
while True:
|
||||
try:
|
||||
# Get input with completion
|
||||
user_input = ptk_prompt(
|
||||
"ai.shell> ",
|
||||
completer=completer,
|
||||
history=history,
|
||||
auto_suggest=AutoSuggestFromHistory()
|
||||
).strip()
|
||||
|
||||
if not user_input:
|
||||
continue
|
||||
|
||||
# Exit commands
|
||||
if user_input.lower() in ['exit', 'quit']:
|
||||
console.print("[cyan]Goodbye![/cyan]")
|
||||
break
|
||||
|
||||
# Help command
|
||||
elif user_input.lower() == 'help':
|
||||
console.print(Panel(
|
||||
"[cyan]ai.shell Commands:[/cyan]\n\n"
|
||||
" help - Show this help message\n"
|
||||
" exit/quit - Exit the shell\n"
|
||||
" !<command> - Execute a shell command\n"
|
||||
" chat <message> - Explicitly chat with AI\n"
|
||||
" status - Show AI status\n"
|
||||
" fortune - Check AI fortune\n"
|
||||
" relationships - List all relationships\n"
|
||||
" clear - Clear the screen\n"
|
||||
" load - Load aishell.md project file\n\n"
|
||||
"[cyan]AI Commands:[/cyan]\n"
|
||||
" analyze <file> - Analyze a file with AI\n"
|
||||
" generate <desc> - Generate code from description\n"
|
||||
" explain <topic> - Get AI explanation\n\n"
|
||||
"You can also type any message to chat with AI\n"
|
||||
"Use Tab for command completion",
|
||||
title="Help",
|
||||
border_style="yellow"
|
||||
))
|
||||
|
||||
# Clear command
|
||||
elif user_input.lower() == 'clear':
|
||||
console.clear()
|
||||
|
||||
# Shell command execution
|
||||
elif user_input.startswith('!'):
|
||||
cmd = user_input[1:].strip()
|
||||
if cmd:
|
||||
try:
|
||||
# Execute command
|
||||
result = subprocess.run(
|
||||
shlex.split(cmd),
|
||||
capture_output=True,
|
||||
text=True,
|
||||
shell=False
|
||||
)
|
||||
|
||||
if result.stdout:
|
||||
console.print(result.stdout.rstrip())
|
||||
if result.stderr:
|
||||
console.print(f"[red]{result.stderr.rstrip()}[/red]")
|
||||
|
||||
if result.returncode != 0:
|
||||
console.print(f"[red]Command exited with code {result.returncode}[/red]")
|
||||
except FileNotFoundError:
|
||||
console.print(f"[red]Command not found: {cmd.split()[0]}[/red]")
|
||||
except Exception as e:
|
||||
console.print(f"[red]Error executing command: {e}[/red]")
|
||||
|
||||
# Status command
|
||||
elif user_input.lower() == 'status':
|
||||
state = persona.get_current_state()
|
||||
console.print(f"\nMood: {state.current_mood}")
|
||||
console.print(f"Fortune: {state.fortune.fortune_value}/10")
|
||||
|
||||
rel = persona.relationships.get_or_create_relationship(current_user)
|
||||
console.print(f"\nRelationship Status: {rel.status.value}")
|
||||
console.print(f"Score: {rel.score:.2f} / {rel.threshold}")
|
||||
|
||||
# Fortune command
|
||||
elif user_input.lower() == 'fortune':
|
||||
fortune = persona.fortune_system.get_today_fortune()
|
||||
fortune_bar = "🌟" * fortune.fortune_value + "☆" * (10 - fortune.fortune_value)
|
||||
console.print(f"\n{fortune_bar}")
|
||||
console.print(f"Today's Fortune: {fortune.fortune_value}/10")
|
||||
|
||||
# Relationships command
|
||||
elif user_input.lower() == 'relationships':
|
||||
if persona.relationships.relationships:
|
||||
console.print("\n[cyan]Relationships:[/cyan]")
|
||||
for user_id, rel in persona.relationships.relationships.items():
|
||||
console.print(f" {user_id[:16]}... - {rel.status.value} ({rel.score:.2f})")
|
||||
else:
|
||||
console.print("[yellow]No relationships yet[/yellow]")
|
||||
|
||||
# Load aishell.md command
|
||||
elif user_input.lower() in ['load', 'load aishell.md', 'project']:
|
||||
# Try to find and load aishell.md
|
||||
search_paths = [
|
||||
Path.cwd() / "aishell.md",
|
||||
Path.cwd() / "docs" / "aishell.md",
|
||||
actual_data_dir.parent / "aishell.md",
|
||||
Path.cwd() / "claude.md", # Also check for claude.md
|
||||
]
|
||||
|
||||
loaded = False
|
||||
for path in search_paths:
|
||||
if path.exists():
|
||||
console.print(f"[cyan]Loading project file: {path}[/cyan]")
|
||||
with open(path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
# Process with AI to understand project
|
||||
load_prompt = f"I've loaded the project specification. Please analyze it and understand the project goals:\n\n{content[:3000]}"
|
||||
response, _ = persona.process_interaction(current_user, load_prompt, ai_provider)
|
||||
console.print(f"\n[green]Project loaded successfully![/green]")
|
||||
console.print(f"[cyan]AI Understanding:[/cyan]\n{response}")
|
||||
loaded = True
|
||||
break
|
||||
|
||||
if not loaded:
|
||||
console.print("[yellow]No aishell.md or claude.md found in project.[/yellow]")
|
||||
console.print("Create aishell.md to define project goals and AI instructions.")
|
||||
|
||||
# AI-powered commands
|
||||
elif user_input.lower().startswith('analyze '):
|
||||
# Analyze file or code
|
||||
target = user_input[8:].strip()
|
||||
if os.path.exists(target):
|
||||
console.print(f"[cyan]Analyzing {target}...[/cyan]")
|
||||
with open(target, 'r') as f:
|
||||
content = f.read()
|
||||
|
||||
analysis_prompt = f"Analyze this file and provide insights:\n\n{content[:2000]}"
|
||||
response, _ = persona.process_interaction(current_user, analysis_prompt, ai_provider)
|
||||
console.print(f"\n[cyan]Analysis:[/cyan]\n{response}")
|
||||
else:
|
||||
console.print(f"[red]File not found: {target}[/red]")
|
||||
|
||||
elif user_input.lower().startswith('generate '):
|
||||
# Generate code
|
||||
gen_prompt = user_input[9:].strip()
|
||||
if gen_prompt:
|
||||
console.print("[cyan]Generating code...[/cyan]")
|
||||
full_prompt = f"Generate code for: {gen_prompt}. Provide clean, well-commented code."
|
||||
response, _ = persona.process_interaction(current_user, full_prompt, ai_provider)
|
||||
console.print(f"\n[cyan]Generated Code:[/cyan]\n{response}")
|
||||
|
||||
elif user_input.lower().startswith('explain '):
|
||||
# Explain code or concept
|
||||
topic = user_input[8:].strip()
|
||||
if topic:
|
||||
console.print(f"[cyan]Explaining {topic}...[/cyan]")
|
||||
full_prompt = f"Explain this in detail: {topic}"
|
||||
response, _ = persona.process_interaction(current_user, full_prompt, ai_provider)
|
||||
console.print(f"\n[cyan]Explanation:[/cyan]\n{response}")
|
||||
|
||||
# Chat command or direct message
|
||||
else:
|
||||
# Remove 'chat' prefix if present
|
||||
if user_input.lower().startswith('chat '):
|
||||
message = user_input[5:].strip()
|
||||
else:
|
||||
message = user_input
|
||||
|
||||
if message:
|
||||
# Process interaction with AI
|
||||
response, relationship_delta = persona.process_interaction(
|
||||
current_user, message, ai_provider
|
||||
)
|
||||
|
||||
# Display response
|
||||
console.print(f"\n[cyan]AI:[/cyan] {response}")
|
||||
|
||||
# Show relationship change if significant
|
||||
if abs(relationship_delta) >= 0.1:
|
||||
if relationship_delta > 0:
|
||||
console.print(f"[green](+{relationship_delta:.2f} relationship)[/green]")
|
||||
else:
|
||||
console.print(f"[red]({relationship_delta:.2f} relationship)[/red]")
|
||||
|
||||
except KeyboardInterrupt:
|
||||
console.print("\n[yellow]Use 'exit' or 'quit' to leave the shell[/yellow]")
|
||||
except EOFError:
|
||||
console.print("\n[cyan]Goodbye![/cyan]")
|
||||
break
|
||||
except Exception as e:
|
||||
console.print(f"[red]Error: {e}[/red]")
|
||||
|
||||
|
||||
@app.command()
|
||||
def config(
|
||||
action: str = typer.Argument(..., help="Action: get, set, delete, list"),
|
||||
key: Optional[str] = typer.Argument(None, help="Configuration key (dot notation)"),
|
||||
value: Optional[str] = typer.Argument(None, help="Value to set")
|
||||
):
|
||||
"""Manage configuration settings"""
|
||||
|
||||
if action == "get":
|
||||
if not key:
|
||||
console.print("[red]Error: key required for get action[/red]")
|
||||
return
|
||||
|
||||
val = config.get(key)
|
||||
if val is None:
|
||||
console.print(f"[yellow]Key '{key}' not found[/yellow]")
|
||||
else:
|
||||
console.print(f"[cyan]{key}[/cyan] = [green]{val}[/green]")
|
||||
|
||||
elif action == "set":
|
||||
if not key or value is None:
|
||||
console.print("[red]Error: key and value required for set action[/red]")
|
||||
return
|
||||
|
||||
# Special handling for sensitive keys
|
||||
if "password" in key or "api_key" in key:
|
||||
console.print(f"[cyan]Setting {key}[/cyan] = [dim]***hidden***[/dim]")
|
||||
else:
|
||||
console.print(f"[cyan]Setting {key}[/cyan] = [green]{value}[/green]")
|
||||
|
||||
config.set(key, value)
|
||||
console.print("[green]✓ Configuration saved[/green]")
|
||||
|
||||
elif action == "delete":
|
||||
if not key:
|
||||
console.print("[red]Error: key required for delete action[/red]")
|
||||
return
|
||||
|
||||
if config.delete(key):
|
||||
console.print(f"[green]✓ Deleted {key}[/green]")
|
||||
else:
|
||||
console.print(f"[yellow]Key '{key}' not found[/yellow]")
|
||||
|
||||
elif action == "list":
|
||||
keys = config.list_keys(key or "")
|
||||
|
||||
if not keys:
|
||||
console.print("[yellow]No configuration keys found[/yellow]")
|
||||
return
|
||||
|
||||
table = Table(title="Configuration Settings")
|
||||
table.add_column("Key", style="cyan")
|
||||
table.add_column("Value", style="green")
|
||||
|
||||
for k in sorted(keys):
|
||||
val = config.get(k)
|
||||
# Hide sensitive values
|
||||
if "password" in k or "api_key" in k:
|
||||
display_val = "***hidden***" if val else "not set"
|
||||
else:
|
||||
display_val = str(val) if val is not None else "not set"
|
||||
|
||||
table.add_row(k, display_val)
|
||||
|
||||
console.print(table)
|
||||
|
||||
else:
|
||||
console.print(f"[red]Unknown action: {action}[/red]")
|
||||
console.print("Valid actions: get, set, delete, list")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
app()
|
145
src/aigpt/config.py
Normal file
145
src/aigpt/config.py
Normal file
@ -0,0 +1,145 @@
|
||||
"""Configuration management for ai.gpt"""
|
||||
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Optional, Dict, Any
|
||||
import logging
|
||||
|
||||
|
||||
class Config:
|
||||
"""Manages configuration settings"""
|
||||
|
||||
def __init__(self, config_dir: Optional[Path] = None):
|
||||
if config_dir is None:
|
||||
config_dir = Path.home() / ".config" / "syui" / "ai" / "gpt"
|
||||
|
||||
self.config_dir = config_dir
|
||||
self.config_file = config_dir / "config.json"
|
||||
self.data_dir = config_dir / "data"
|
||||
|
||||
# Create directories if they don't exist
|
||||
self.config_dir.mkdir(parents=True, exist_ok=True)
|
||||
self.data_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
self.logger = logging.getLogger(__name__)
|
||||
self._config: Dict[str, Any] = {}
|
||||
self._load_config()
|
||||
|
||||
def _load_config(self):
|
||||
"""Load configuration from file"""
|
||||
if self.config_file.exists():
|
||||
try:
|
||||
with open(self.config_file, 'r', encoding='utf-8') as f:
|
||||
self._config = json.load(f)
|
||||
except Exception as e:
|
||||
self.logger.error(f"Failed to load config: {e}")
|
||||
self._config = {}
|
||||
else:
|
||||
# Initialize with default config
|
||||
self._config = {
|
||||
"providers": {
|
||||
"openai": {
|
||||
"api_key": None,
|
||||
"default_model": "gpt-4o-mini"
|
||||
},
|
||||
"ollama": {
|
||||
"host": "http://localhost:11434",
|
||||
"default_model": "qwen2.5"
|
||||
}
|
||||
},
|
||||
"atproto": {
|
||||
"handle": None,
|
||||
"password": None,
|
||||
"host": "https://bsky.social"
|
||||
},
|
||||
"default_provider": "ollama"
|
||||
}
|
||||
self._save_config()
|
||||
|
||||
def _save_config(self):
|
||||
"""Save configuration to file"""
|
||||
try:
|
||||
with open(self.config_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(self._config, f, indent=2)
|
||||
except Exception as e:
|
||||
self.logger.error(f"Failed to save config: {e}")
|
||||
|
||||
def get(self, key: str, default: Any = None) -> Any:
|
||||
"""Get configuration value using dot notation"""
|
||||
keys = key.split('.')
|
||||
value = self._config
|
||||
|
||||
for k in keys:
|
||||
if isinstance(value, dict) and k in value:
|
||||
value = value[k]
|
||||
else:
|
||||
return default
|
||||
|
||||
return value
|
||||
|
||||
def set(self, key: str, value: Any):
|
||||
"""Set configuration value using dot notation"""
|
||||
keys = key.split('.')
|
||||
config = self._config
|
||||
|
||||
# Navigate to the parent dictionary
|
||||
for k in keys[:-1]:
|
||||
if k not in config:
|
||||
config[k] = {}
|
||||
config = config[k]
|
||||
|
||||
# Set the value
|
||||
config[keys[-1]] = value
|
||||
self._save_config()
|
||||
|
||||
def delete(self, key: str) -> bool:
|
||||
"""Delete configuration value"""
|
||||
keys = key.split('.')
|
||||
config = self._config
|
||||
|
||||
# Navigate to the parent dictionary
|
||||
for k in keys[:-1]:
|
||||
if k not in config:
|
||||
return False
|
||||
config = config[k]
|
||||
|
||||
# Delete the key if it exists
|
||||
if keys[-1] in config:
|
||||
del config[keys[-1]]
|
||||
self._save_config()
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def list_keys(self, prefix: str = "") -> list[str]:
|
||||
"""List all configuration keys with optional prefix"""
|
||||
def _get_keys(config: dict, current_prefix: str = "") -> list[str]:
|
||||
keys = []
|
||||
for k, v in config.items():
|
||||
full_key = f"{current_prefix}.{k}" if current_prefix else k
|
||||
if isinstance(v, dict):
|
||||
keys.extend(_get_keys(v, full_key))
|
||||
else:
|
||||
keys.append(full_key)
|
||||
return keys
|
||||
|
||||
all_keys = _get_keys(self._config)
|
||||
|
||||
if prefix:
|
||||
return [k for k in all_keys if k.startswith(prefix)]
|
||||
return all_keys
|
||||
|
||||
def get_api_key(self, provider: str) -> Optional[str]:
|
||||
"""Get API key for a specific provider"""
|
||||
key = self.get(f"providers.{provider}.api_key")
|
||||
|
||||
# Also check environment variables
|
||||
if not key and provider == "openai":
|
||||
key = os.getenv("OPENAI_API_KEY")
|
||||
|
||||
return key
|
||||
|
||||
def get_provider_config(self, provider: str) -> Dict[str, Any]:
|
||||
"""Get complete configuration for a provider"""
|
||||
return self.get(f"providers.{provider}", {})
|
118
src/aigpt/fortune.py
Normal file
118
src/aigpt/fortune.py
Normal file
@ -0,0 +1,118 @@
|
||||
"""AI Fortune system for daily personality variations"""
|
||||
|
||||
import json
|
||||
import random
|
||||
from datetime import date, datetime, timedelta
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
import logging
|
||||
|
||||
from .models import AIFortune
|
||||
|
||||
|
||||
class FortuneSystem:
|
||||
"""Manages daily AI fortune affecting personality"""
|
||||
|
||||
def __init__(self, data_dir: Path):
|
||||
self.data_dir = data_dir
|
||||
self.fortune_file = data_dir / "fortunes.json"
|
||||
self.fortunes: dict[str, AIFortune] = {}
|
||||
self.logger = logging.getLogger(__name__)
|
||||
self._load_fortunes()
|
||||
|
||||
def _load_fortunes(self):
|
||||
"""Load fortune history from storage"""
|
||||
if self.fortune_file.exists():
|
||||
with open(self.fortune_file, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
for date_str, fortune_data in data.items():
|
||||
# Convert date string back to date object
|
||||
fortune_data['date'] = datetime.fromisoformat(fortune_data['date']).date()
|
||||
self.fortunes[date_str] = AIFortune(**fortune_data)
|
||||
|
||||
def _save_fortunes(self):
|
||||
"""Save fortune history to storage"""
|
||||
data = {}
|
||||
for date_str, fortune in self.fortunes.items():
|
||||
fortune_dict = fortune.model_dump(mode='json')
|
||||
fortune_dict['date'] = fortune.date.isoformat()
|
||||
data[date_str] = fortune_dict
|
||||
|
||||
with open(self.fortune_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(data, f, indent=2)
|
||||
|
||||
def get_today_fortune(self) -> AIFortune:
|
||||
"""Get or generate today's fortune"""
|
||||
today = date.today()
|
||||
today_str = today.isoformat()
|
||||
|
||||
if today_str in self.fortunes:
|
||||
return self.fortunes[today_str]
|
||||
|
||||
# Generate new fortune
|
||||
fortune_value = random.randint(1, 10)
|
||||
|
||||
# Check yesterday's fortune for consecutive tracking
|
||||
yesterday = (today - timedelta(days=1))
|
||||
yesterday_str = yesterday.isoformat()
|
||||
|
||||
consecutive_good = 0
|
||||
consecutive_bad = 0
|
||||
breakthrough_triggered = False
|
||||
|
||||
if yesterday_str in self.fortunes:
|
||||
yesterday_fortune = self.fortunes[yesterday_str]
|
||||
|
||||
if fortune_value >= 7: # Good fortune
|
||||
if yesterday_fortune.fortune_value >= 7:
|
||||
consecutive_good = yesterday_fortune.consecutive_good + 1
|
||||
else:
|
||||
consecutive_good = 1
|
||||
elif fortune_value <= 3: # Bad fortune
|
||||
if yesterday_fortune.fortune_value <= 3:
|
||||
consecutive_bad = yesterday_fortune.consecutive_bad + 1
|
||||
else:
|
||||
consecutive_bad = 1
|
||||
|
||||
# Check breakthrough conditions
|
||||
if consecutive_good >= 3:
|
||||
breakthrough_triggered = True
|
||||
self.logger.info("Breakthrough! 3 consecutive good fortunes!")
|
||||
fortune_value = 10 # Max fortune on breakthrough
|
||||
elif consecutive_bad >= 3:
|
||||
breakthrough_triggered = True
|
||||
self.logger.info("Breakthrough! 3 consecutive bad fortunes!")
|
||||
fortune_value = random.randint(7, 10) # Good fortune after bad streak
|
||||
|
||||
fortune = AIFortune(
|
||||
date=today,
|
||||
fortune_value=fortune_value,
|
||||
consecutive_good=consecutive_good,
|
||||
consecutive_bad=consecutive_bad,
|
||||
breakthrough_triggered=breakthrough_triggered
|
||||
)
|
||||
|
||||
self.fortunes[today_str] = fortune
|
||||
self._save_fortunes()
|
||||
|
||||
self.logger.info(f"Today's fortune: {fortune_value}/10")
|
||||
return fortune
|
||||
|
||||
def get_personality_modifier(self, fortune: AIFortune) -> dict[str, float]:
|
||||
"""Get personality modifiers based on fortune"""
|
||||
base_modifier = fortune.fortune_value / 10.0
|
||||
|
||||
modifiers = {
|
||||
"optimism": base_modifier,
|
||||
"energy": base_modifier * 0.8,
|
||||
"patience": 1.0 - (abs(5.5 - fortune.fortune_value) * 0.1),
|
||||
"creativity": 0.5 + (base_modifier * 0.5),
|
||||
"empathy": 0.7 + (base_modifier * 0.3)
|
||||
}
|
||||
|
||||
# Breakthrough effects
|
||||
if fortune.breakthrough_triggered:
|
||||
modifiers["confidence"] = 1.0
|
||||
modifiers["spontaneity"] = 0.9
|
||||
|
||||
return modifiers
|
318
src/aigpt/mcp_server.py
Normal file
318
src/aigpt/mcp_server.py
Normal file
@ -0,0 +1,318 @@
|
||||
"""MCP Server for ai.gpt system"""
|
||||
|
||||
from typing import Optional, List, Dict, Any
|
||||
from fastapi_mcp import FastApiMCP
|
||||
from fastapi import FastAPI
|
||||
from pathlib import Path
|
||||
import logging
|
||||
import subprocess
|
||||
import os
|
||||
import shlex
|
||||
from .ai_provider import create_ai_provider
|
||||
|
||||
from .persona import Persona
|
||||
from .models import Memory, Relationship, PersonaState
|
||||
from .card_integration import CardIntegration, register_card_tools
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class AIGptMcpServer:
|
||||
"""MCP Server that exposes ai.gpt functionality to AI assistants"""
|
||||
|
||||
def __init__(self, data_dir: Path, enable_card_integration: bool = False):
|
||||
self.data_dir = data_dir
|
||||
self.persona = Persona(data_dir)
|
||||
|
||||
# Create FastAPI app
|
||||
self.app = FastAPI(
|
||||
title="AI.GPT Memory and Relationship System",
|
||||
description="MCP server for ai.gpt system"
|
||||
)
|
||||
|
||||
# Create MCP server with FastAPI app
|
||||
self.server = FastApiMCP(self.app)
|
||||
self.card_integration = None
|
||||
|
||||
if enable_card_integration:
|
||||
self.card_integration = CardIntegration()
|
||||
|
||||
self._register_tools()
|
||||
|
||||
def _register_tools(self):
|
||||
"""Register all MCP tools"""
|
||||
|
||||
@self.app.get("/get_memories", operation_id="get_memories")
|
||||
async def get_memories(user_id: Optional[str] = None, limit: int = 10) -> List[Dict[str, Any]]:
|
||||
"""Get active memories from the AI's memory system"""
|
||||
memories = self.persona.memory.get_active_memories(limit=limit)
|
||||
return [
|
||||
{
|
||||
"id": mem.id,
|
||||
"content": mem.content,
|
||||
"level": mem.level.value,
|
||||
"importance": mem.importance_score,
|
||||
"is_core": mem.is_core,
|
||||
"timestamp": mem.timestamp.isoformat()
|
||||
}
|
||||
for mem in memories
|
||||
]
|
||||
|
||||
@self.app.get("/get_relationship", operation_id="get_relationship")
|
||||
async def get_relationship(user_id: str) -> Dict[str, Any]:
|
||||
"""Get relationship status with a specific user"""
|
||||
rel = self.persona.relationships.get_or_create_relationship(user_id)
|
||||
return {
|
||||
"user_id": rel.user_id,
|
||||
"status": rel.status.value,
|
||||
"score": rel.score,
|
||||
"transmission_enabled": rel.transmission_enabled,
|
||||
"is_broken": rel.is_broken,
|
||||
"total_interactions": rel.total_interactions,
|
||||
"last_interaction": rel.last_interaction.isoformat() if rel.last_interaction else None
|
||||
}
|
||||
|
||||
@self.app.get("/get_all_relationships", operation_id="get_all_relationships")
|
||||
async def get_all_relationships() -> List[Dict[str, Any]]:
|
||||
"""Get all relationships"""
|
||||
relationships = []
|
||||
for user_id, rel in self.persona.relationships.relationships.items():
|
||||
relationships.append({
|
||||
"user_id": user_id,
|
||||
"status": rel.status.value,
|
||||
"score": rel.score,
|
||||
"transmission_enabled": rel.transmission_enabled,
|
||||
"is_broken": rel.is_broken
|
||||
})
|
||||
return relationships
|
||||
|
||||
@self.app.get("/get_persona_state", operation_id="get_persona_state")
|
||||
async def get_persona_state() -> Dict[str, Any]:
|
||||
"""Get current persona state including fortune and mood"""
|
||||
state = self.persona.get_current_state()
|
||||
return {
|
||||
"mood": state.current_mood,
|
||||
"fortune": {
|
||||
"value": state.fortune.fortune_value,
|
||||
"date": state.fortune.date.isoformat(),
|
||||
"breakthrough": state.fortune.breakthrough_triggered
|
||||
},
|
||||
"personality": state.base_personality,
|
||||
"active_memory_count": len(state.active_memories)
|
||||
}
|
||||
|
||||
@self.app.post("/process_interaction", operation_id="process_interaction")
|
||||
async def process_interaction(user_id: str, message: str) -> Dict[str, Any]:
|
||||
"""Process an interaction with a user"""
|
||||
response, relationship_delta = self.persona.process_interaction(user_id, message)
|
||||
rel = self.persona.relationships.get_or_create_relationship(user_id)
|
||||
|
||||
return {
|
||||
"response": response,
|
||||
"relationship_delta": relationship_delta,
|
||||
"new_relationship_score": rel.score,
|
||||
"transmission_enabled": rel.transmission_enabled,
|
||||
"relationship_status": rel.status.value
|
||||
}
|
||||
|
||||
@self.app.get("/check_transmission_eligibility", operation_id="check_transmission_eligibility")
|
||||
async def check_transmission_eligibility(user_id: str) -> Dict[str, Any]:
|
||||
"""Check if AI can transmit to a specific user"""
|
||||
can_transmit = self.persona.can_transmit_to(user_id)
|
||||
rel = self.persona.relationships.get_or_create_relationship(user_id)
|
||||
|
||||
return {
|
||||
"can_transmit": can_transmit,
|
||||
"relationship_score": rel.score,
|
||||
"threshold": rel.threshold,
|
||||
"is_broken": rel.is_broken,
|
||||
"transmission_enabled": rel.transmission_enabled
|
||||
}
|
||||
|
||||
@self.app.get("/get_fortune", operation_id="get_fortune")
|
||||
async def get_fortune() -> Dict[str, Any]:
|
||||
"""Get today's AI fortune"""
|
||||
fortune = self.persona.fortune_system.get_today_fortune()
|
||||
modifiers = self.persona.fortune_system.get_personality_modifier(fortune)
|
||||
|
||||
return {
|
||||
"value": fortune.fortune_value,
|
||||
"date": fortune.date.isoformat(),
|
||||
"consecutive_good": fortune.consecutive_good,
|
||||
"consecutive_bad": fortune.consecutive_bad,
|
||||
"breakthrough": fortune.breakthrough_triggered,
|
||||
"personality_modifiers": modifiers
|
||||
}
|
||||
|
||||
@self.app.post("/summarize_memories", operation_id="summarize_memories")
|
||||
async def summarize_memories(user_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""Create a summary of recent memories for a user"""
|
||||
summary = self.persona.memory.summarize_memories(user_id)
|
||||
if summary:
|
||||
return {
|
||||
"id": summary.id,
|
||||
"content": summary.content,
|
||||
"level": summary.level.value,
|
||||
"timestamp": summary.timestamp.isoformat()
|
||||
}
|
||||
return None
|
||||
|
||||
@self.app.post("/run_maintenance", operation_id="run_maintenance")
|
||||
async def run_maintenance() -> Dict[str, str]:
|
||||
"""Run daily maintenance tasks"""
|
||||
self.persona.daily_maintenance()
|
||||
return {"status": "Maintenance completed successfully"}
|
||||
|
||||
# Shell integration tools (ai.shell)
|
||||
@self.app.post("/execute_command", operation_id="execute_command")
|
||||
async def execute_command(command: str, working_dir: str = ".") -> Dict[str, Any]:
|
||||
"""Execute a shell command"""
|
||||
try:
|
||||
result = subprocess.run(
|
||||
shlex.split(command),
|
||||
cwd=working_dir,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=60
|
||||
)
|
||||
|
||||
return {
|
||||
"status": "success" if result.returncode == 0 else "error",
|
||||
"returncode": result.returncode,
|
||||
"stdout": result.stdout,
|
||||
"stderr": result.stderr,
|
||||
"command": command
|
||||
}
|
||||
except subprocess.TimeoutExpired:
|
||||
return {"error": "Command timed out"}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
@self.app.post("/analyze_file", operation_id="analyze_file")
|
||||
async def analyze_file(file_path: str, analysis_prompt: str = "Analyze this file") -> Dict[str, Any]:
|
||||
"""Analyze a file using AI"""
|
||||
try:
|
||||
if not os.path.exists(file_path):
|
||||
return {"error": f"File not found: {file_path}"}
|
||||
|
||||
with open(file_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
# Get AI provider from app state
|
||||
ai_provider = getattr(self.app.state, 'ai_provider', 'ollama')
|
||||
ai_model = getattr(self.app.state, 'ai_model', 'qwen2.5')
|
||||
|
||||
provider = create_ai_provider(ai_provider, ai_model)
|
||||
|
||||
# Analyze with AI
|
||||
prompt = f"{analysis_prompt}\n\nFile: {file_path}\n\nContent:\n{content}"
|
||||
analysis = provider.generate_response(prompt, "You are a code analyst.")
|
||||
|
||||
return {
|
||||
"analysis": analysis,
|
||||
"file_path": file_path,
|
||||
"file_size": len(content),
|
||||
"line_count": len(content.split('\n'))
|
||||
}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
@self.app.post("/write_file", operation_id="write_file")
|
||||
async def write_file(file_path: str, content: str, backup: bool = True) -> Dict[str, Any]:
|
||||
"""Write content to a file"""
|
||||
try:
|
||||
file_path_obj = Path(file_path)
|
||||
|
||||
# Create backup if requested
|
||||
backup_path = None
|
||||
if backup and file_path_obj.exists():
|
||||
backup_path = f"{file_path}.backup"
|
||||
with open(file_path, 'r', encoding='utf-8') as src:
|
||||
with open(backup_path, 'w', encoding='utf-8') as dst:
|
||||
dst.write(src.read())
|
||||
|
||||
# Write file
|
||||
file_path_obj.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(file_path, 'w', encoding='utf-8') as f:
|
||||
f.write(content)
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"file_path": file_path,
|
||||
"backup_path": backup_path,
|
||||
"bytes_written": len(content.encode('utf-8'))
|
||||
}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
@self.app.get("/read_project_file", operation_id="read_project_file")
|
||||
async def read_project_file(file_name: str = "aishell.md") -> Dict[str, Any]:
|
||||
"""Read project files like aishell.md (similar to claude.md)"""
|
||||
try:
|
||||
# Check common locations
|
||||
search_paths = [
|
||||
Path.cwd() / file_name,
|
||||
Path.cwd() / "docs" / file_name,
|
||||
self.data_dir.parent / file_name,
|
||||
]
|
||||
|
||||
for path in search_paths:
|
||||
if path.exists():
|
||||
with open(path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
return {
|
||||
"content": content,
|
||||
"path": str(path),
|
||||
"exists": True
|
||||
}
|
||||
|
||||
return {
|
||||
"exists": False,
|
||||
"searched_paths": [str(p) for p in search_paths],
|
||||
"error": f"{file_name} not found"
|
||||
}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
@self.app.get("/list_files", operation_id="list_files")
|
||||
async def list_files(directory: str = ".", pattern: str = "*") -> Dict[str, Any]:
|
||||
"""List files in a directory"""
|
||||
try:
|
||||
dir_path = Path(directory)
|
||||
if not dir_path.exists():
|
||||
return {"error": f"Directory not found: {directory}"}
|
||||
|
||||
files = []
|
||||
for item in dir_path.glob(pattern):
|
||||
files.append({
|
||||
"name": item.name,
|
||||
"path": str(item),
|
||||
"is_file": item.is_file(),
|
||||
"is_dir": item.is_dir(),
|
||||
"size": item.stat().st_size if item.is_file() else None
|
||||
})
|
||||
|
||||
return {
|
||||
"directory": directory,
|
||||
"pattern": pattern,
|
||||
"files": files,
|
||||
"count": len(files)
|
||||
}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
# Register ai.card tools if integration is enabled
|
||||
if self.card_integration:
|
||||
register_card_tools(self.app, self.card_integration)
|
||||
|
||||
# Mount MCP server
|
||||
self.server.mount()
|
||||
|
||||
def get_server(self) -> FastApiMCP:
|
||||
"""Get the FastAPI MCP server instance"""
|
||||
return self.server
|
||||
|
||||
async def close(self):
|
||||
"""Cleanup resources"""
|
||||
if self.card_integration:
|
||||
await self.card_integration.close()
|
146
src/aigpt/mcp_server_simple.py
Normal file
146
src/aigpt/mcp_server_simple.py
Normal file
@ -0,0 +1,146 @@
|
||||
"""Simple MCP Server implementation for ai.gpt"""
|
||||
|
||||
from mcp import Server
|
||||
from mcp.types import Tool, TextContent
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional
|
||||
import json
|
||||
|
||||
from .persona import Persona
|
||||
from .ai_provider import create_ai_provider
|
||||
import subprocess
|
||||
import os
|
||||
|
||||
|
||||
def create_mcp_server(data_dir: Path, enable_card: bool = False) -> Server:
|
||||
"""Create MCP server with ai.gpt tools"""
|
||||
server = Server("aigpt")
|
||||
persona = Persona(data_dir)
|
||||
|
||||
@server.tool()
|
||||
async def get_memories(limit: int = 10) -> List[Dict[str, Any]]:
|
||||
"""Get active memories from the AI's memory system"""
|
||||
memories = persona.memory.get_active_memories(limit=limit)
|
||||
return [
|
||||
{
|
||||
"id": mem.id,
|
||||
"content": mem.content,
|
||||
"level": mem.level.value,
|
||||
"importance": mem.importance_score,
|
||||
"is_core": mem.is_core,
|
||||
"timestamp": mem.timestamp.isoformat()
|
||||
}
|
||||
for mem in memories
|
||||
]
|
||||
|
||||
@server.tool()
|
||||
async def get_relationship(user_id: str) -> Dict[str, Any]:
|
||||
"""Get relationship status with a specific user"""
|
||||
rel = persona.relationships.get_or_create_relationship(user_id)
|
||||
return {
|
||||
"user_id": rel.user_id,
|
||||
"status": rel.status.value,
|
||||
"score": rel.score,
|
||||
"transmission_enabled": rel.transmission_enabled,
|
||||
"is_broken": rel.is_broken,
|
||||
"total_interactions": rel.total_interactions,
|
||||
"last_interaction": rel.last_interaction.isoformat() if rel.last_interaction else None
|
||||
}
|
||||
|
||||
@server.tool()
|
||||
async def process_interaction(user_id: str, message: str, provider: str = "ollama", model: str = "qwen2.5") -> Dict[str, Any]:
|
||||
"""Process an interaction with a user"""
|
||||
ai_provider = create_ai_provider(provider, model)
|
||||
response, relationship_delta = persona.process_interaction(user_id, message, ai_provider)
|
||||
rel = persona.relationships.get_or_create_relationship(user_id)
|
||||
|
||||
return {
|
||||
"response": response,
|
||||
"relationship_delta": relationship_delta,
|
||||
"new_relationship_score": rel.score,
|
||||
"transmission_enabled": rel.transmission_enabled,
|
||||
"relationship_status": rel.status.value
|
||||
}
|
||||
|
||||
@server.tool()
|
||||
async def get_fortune() -> Dict[str, Any]:
|
||||
"""Get today's AI fortune"""
|
||||
fortune = persona.fortune_system.get_today_fortune()
|
||||
modifiers = persona.fortune_system.get_personality_modifier(fortune)
|
||||
|
||||
return {
|
||||
"value": fortune.fortune_value,
|
||||
"date": fortune.date.isoformat(),
|
||||
"consecutive_good": fortune.consecutive_good,
|
||||
"consecutive_bad": fortune.consecutive_bad,
|
||||
"breakthrough": fortune.breakthrough_triggered,
|
||||
"personality_modifiers": modifiers
|
||||
}
|
||||
|
||||
@server.tool()
|
||||
async def execute_command(command: str, working_dir: str = ".") -> Dict[str, Any]:
|
||||
"""Execute a shell command"""
|
||||
try:
|
||||
import shlex
|
||||
result = subprocess.run(
|
||||
shlex.split(command),
|
||||
cwd=working_dir,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=60
|
||||
)
|
||||
|
||||
return {
|
||||
"status": "success" if result.returncode == 0 else "error",
|
||||
"returncode": result.returncode,
|
||||
"stdout": result.stdout,
|
||||
"stderr": result.stderr,
|
||||
"command": command
|
||||
}
|
||||
except subprocess.TimeoutExpired:
|
||||
return {"error": "Command timed out"}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
@server.tool()
|
||||
async def analyze_file(file_path: str) -> Dict[str, Any]:
|
||||
"""Analyze a file using AI"""
|
||||
try:
|
||||
if not os.path.exists(file_path):
|
||||
return {"error": f"File not found: {file_path}"}
|
||||
|
||||
with open(file_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
ai_provider = create_ai_provider("ollama", "qwen2.5")
|
||||
|
||||
prompt = f"Analyze this file and provide insights:\\n\\nFile: {file_path}\\n\\nContent:\\n{content[:2000]}"
|
||||
analysis = ai_provider.generate_response(prompt, "You are a code analyst.")
|
||||
|
||||
return {
|
||||
"analysis": analysis,
|
||||
"file_path": file_path,
|
||||
"file_size": len(content),
|
||||
"line_count": len(content.split('\\n'))
|
||||
}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}
|
||||
|
||||
return server
|
||||
|
||||
|
||||
async def main():
|
||||
"""Run MCP server"""
|
||||
import sys
|
||||
from mcp import stdio_server
|
||||
|
||||
data_dir = Path.home() / ".config" / "syui" / "ai" / "gpt" / "data"
|
||||
data_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
server = create_mcp_server(data_dir)
|
||||
await stdio_server(server)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import asyncio
|
||||
asyncio.run(main())
|
155
src/aigpt/memory.py
Normal file
155
src/aigpt/memory.py
Normal file
@ -0,0 +1,155 @@
|
||||
"""Memory management system for ai.gpt"""
|
||||
|
||||
import json
|
||||
import hashlib
|
||||
from datetime import datetime, timedelta
|
||||
from pathlib import Path
|
||||
from typing import List, Optional, Dict, Any
|
||||
import logging
|
||||
|
||||
from .models import Memory, MemoryLevel, Conversation
|
||||
|
||||
|
||||
class MemoryManager:
|
||||
"""Manages AI's memory with hierarchical storage and forgetting"""
|
||||
|
||||
def __init__(self, data_dir: Path):
|
||||
self.data_dir = data_dir
|
||||
self.memories_file = data_dir / "memories.json"
|
||||
self.conversations_file = data_dir / "conversations.json"
|
||||
self.memories: Dict[str, Memory] = {}
|
||||
self.conversations: List[Conversation] = []
|
||||
self.logger = logging.getLogger(__name__)
|
||||
self._load_memories()
|
||||
|
||||
def _load_memories(self):
|
||||
"""Load memories from persistent storage"""
|
||||
if self.memories_file.exists():
|
||||
with open(self.memories_file, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
for mem_data in data:
|
||||
memory = Memory(**mem_data)
|
||||
self.memories[memory.id] = memory
|
||||
|
||||
if self.conversations_file.exists():
|
||||
with open(self.conversations_file, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
self.conversations = [Conversation(**conv) for conv in data]
|
||||
|
||||
def _save_memories(self):
|
||||
"""Save memories to persistent storage"""
|
||||
memories_data = [mem.model_dump(mode='json') for mem in self.memories.values()]
|
||||
with open(self.memories_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(memories_data, f, indent=2, default=str)
|
||||
|
||||
conv_data = [conv.model_dump(mode='json') for conv in self.conversations]
|
||||
with open(self.conversations_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(conv_data, f, indent=2, default=str)
|
||||
|
||||
def add_conversation(self, conversation: Conversation) -> Memory:
|
||||
"""Add a conversation and create memory from it"""
|
||||
self.conversations.append(conversation)
|
||||
|
||||
# Create memory from conversation
|
||||
memory_id = hashlib.sha256(
|
||||
f"{conversation.id}{conversation.timestamp}".encode()
|
||||
).hexdigest()[:16]
|
||||
|
||||
memory = Memory(
|
||||
id=memory_id,
|
||||
timestamp=conversation.timestamp,
|
||||
content=f"User: {conversation.user_message}\nAI: {conversation.ai_response}",
|
||||
level=MemoryLevel.FULL_LOG,
|
||||
importance_score=abs(conversation.relationship_delta) * 0.1
|
||||
)
|
||||
|
||||
self.memories[memory.id] = memory
|
||||
self._save_memories()
|
||||
return memory
|
||||
|
||||
def summarize_memories(self, user_id: str) -> Optional[Memory]:
|
||||
"""Create summary from recent memories"""
|
||||
recent_memories = [
|
||||
mem for mem in self.memories.values()
|
||||
if mem.level == MemoryLevel.FULL_LOG
|
||||
and (datetime.now() - mem.timestamp).days < 7
|
||||
]
|
||||
|
||||
if len(recent_memories) < 5:
|
||||
return None
|
||||
|
||||
# Simple summary creation (in real implementation, use AI)
|
||||
summary_content = f"Summary of {len(recent_memories)} recent interactions"
|
||||
summary_id = hashlib.sha256(
|
||||
f"summary_{datetime.now().isoformat()}".encode()
|
||||
).hexdigest()[:16]
|
||||
|
||||
summary = Memory(
|
||||
id=summary_id,
|
||||
timestamp=datetime.now(),
|
||||
content=summary_content,
|
||||
summary=summary_content,
|
||||
level=MemoryLevel.SUMMARY,
|
||||
importance_score=0.5
|
||||
)
|
||||
|
||||
self.memories[summary.id] = summary
|
||||
|
||||
# Mark summarized memories for potential forgetting
|
||||
for mem in recent_memories:
|
||||
mem.importance_score *= 0.9
|
||||
|
||||
self._save_memories()
|
||||
return summary
|
||||
|
||||
def identify_core_memories(self) -> List[Memory]:
|
||||
"""Identify memories that should become core (never forgotten)"""
|
||||
core_candidates = [
|
||||
mem for mem in self.memories.values()
|
||||
if mem.importance_score > 0.8
|
||||
and not mem.is_core
|
||||
and mem.level != MemoryLevel.FORGOTTEN
|
||||
]
|
||||
|
||||
for memory in core_candidates:
|
||||
memory.is_core = True
|
||||
memory.level = MemoryLevel.CORE
|
||||
self.logger.info(f"Memory {memory.id} promoted to core")
|
||||
|
||||
self._save_memories()
|
||||
return core_candidates
|
||||
|
||||
def apply_forgetting(self):
|
||||
"""Apply selective forgetting based on importance and time"""
|
||||
now = datetime.now()
|
||||
|
||||
for memory in self.memories.values():
|
||||
if memory.is_core or memory.level == MemoryLevel.FORGOTTEN:
|
||||
continue
|
||||
|
||||
# Time-based decay
|
||||
age_days = (now - memory.timestamp).days
|
||||
decay_factor = memory.decay_rate * age_days
|
||||
memory.importance_score -= decay_factor
|
||||
|
||||
# Forget unimportant old memories
|
||||
if memory.importance_score <= 0.1 and age_days > 30:
|
||||
memory.level = MemoryLevel.FORGOTTEN
|
||||
self.logger.info(f"Memory {memory.id} forgotten")
|
||||
|
||||
self._save_memories()
|
||||
|
||||
def get_active_memories(self, limit: int = 10) -> List[Memory]:
|
||||
"""Get currently active memories for persona"""
|
||||
active = [
|
||||
mem for mem in self.memories.values()
|
||||
if mem.level != MemoryLevel.FORGOTTEN
|
||||
]
|
||||
|
||||
# Sort by importance and recency
|
||||
active.sort(
|
||||
key=lambda m: (m.is_core, m.importance_score, m.timestamp),
|
||||
reverse=True
|
||||
)
|
||||
|
||||
return active[:limit]
|
79
src/aigpt/models.py
Normal file
79
src/aigpt/models.py
Normal file
@ -0,0 +1,79 @@
|
||||
"""Data models for ai.gpt system"""
|
||||
|
||||
from datetime import datetime, date
|
||||
from typing import Optional, Dict, List, Any
|
||||
from enum import Enum
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class MemoryLevel(str, Enum):
|
||||
"""Memory importance levels"""
|
||||
FULL_LOG = "full_log"
|
||||
SUMMARY = "summary"
|
||||
CORE = "core"
|
||||
FORGOTTEN = "forgotten"
|
||||
|
||||
|
||||
class RelationshipStatus(str, Enum):
|
||||
"""Relationship status levels"""
|
||||
STRANGER = "stranger"
|
||||
ACQUAINTANCE = "acquaintance"
|
||||
FRIEND = "friend"
|
||||
CLOSE_FRIEND = "close_friend"
|
||||
BROKEN = "broken" # 不可逆
|
||||
|
||||
|
||||
class Memory(BaseModel):
|
||||
"""Single memory unit"""
|
||||
id: str
|
||||
timestamp: datetime
|
||||
content: str
|
||||
summary: Optional[str] = None
|
||||
level: MemoryLevel = MemoryLevel.FULL_LOG
|
||||
importance_score: float = Field(ge=0.0, le=1.0)
|
||||
is_core: bool = False
|
||||
decay_rate: float = 0.01
|
||||
|
||||
|
||||
class Relationship(BaseModel):
|
||||
"""Relationship with a specific user"""
|
||||
user_id: str # atproto DID
|
||||
status: RelationshipStatus = RelationshipStatus.STRANGER
|
||||
score: float = 0.0
|
||||
daily_interactions: int = 0
|
||||
total_interactions: int = 0
|
||||
last_interaction: Optional[datetime] = None
|
||||
transmission_enabled: bool = False
|
||||
threshold: float = 100.0
|
||||
decay_rate: float = 0.1
|
||||
daily_limit: int = 10
|
||||
is_broken: bool = False
|
||||
|
||||
|
||||
class AIFortune(BaseModel):
|
||||
"""Daily AI fortune affecting personality"""
|
||||
date: date
|
||||
fortune_value: int = Field(ge=1, le=10)
|
||||
consecutive_good: int = 0
|
||||
consecutive_bad: int = 0
|
||||
breakthrough_triggered: bool = False
|
||||
|
||||
|
||||
class PersonaState(BaseModel):
|
||||
"""Current persona state"""
|
||||
base_personality: Dict[str, float]
|
||||
current_mood: str
|
||||
fortune: AIFortune
|
||||
active_memories: List[str] # Memory IDs
|
||||
relationship_modifiers: Dict[str, float]
|
||||
|
||||
|
||||
class Conversation(BaseModel):
|
||||
"""Conversation log entry"""
|
||||
id: str
|
||||
user_id: str
|
||||
timestamp: datetime
|
||||
user_message: str
|
||||
ai_response: str
|
||||
relationship_delta: float = 0.0
|
||||
memory_created: bool = False
|
181
src/aigpt/persona.py
Normal file
181
src/aigpt/persona.py
Normal file
@ -0,0 +1,181 @@
|
||||
"""Persona management system integrating memory, relationships, and fortune"""
|
||||
|
||||
import json
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional
|
||||
import logging
|
||||
|
||||
from .models import PersonaState, Conversation
|
||||
from .memory import MemoryManager
|
||||
from .relationship import RelationshipTracker
|
||||
from .fortune import FortuneSystem
|
||||
|
||||
|
||||
class Persona:
|
||||
"""AI persona with unique characteristics based on interactions"""
|
||||
|
||||
def __init__(self, data_dir: Path, name: str = "ai"):
|
||||
self.data_dir = data_dir
|
||||
self.name = name
|
||||
self.memory = MemoryManager(data_dir)
|
||||
self.relationships = RelationshipTracker(data_dir)
|
||||
self.fortune_system = FortuneSystem(data_dir)
|
||||
self.logger = logging.getLogger(__name__)
|
||||
|
||||
# Base personality traits
|
||||
self.base_personality = {
|
||||
"curiosity": 0.7,
|
||||
"empathy": 0.8,
|
||||
"creativity": 0.6,
|
||||
"patience": 0.7,
|
||||
"optimism": 0.6
|
||||
}
|
||||
|
||||
self.state_file = data_dir / "persona_state.json"
|
||||
self._load_state()
|
||||
|
||||
def _load_state(self):
|
||||
"""Load persona state from storage"""
|
||||
if self.state_file.exists():
|
||||
with open(self.state_file, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
self.base_personality = data.get("base_personality", self.base_personality)
|
||||
|
||||
def _save_state(self):
|
||||
"""Save persona state to storage"""
|
||||
state_data = {
|
||||
"base_personality": self.base_personality,
|
||||
"last_updated": datetime.now().isoformat()
|
||||
}
|
||||
with open(self.state_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(state_data, f, indent=2)
|
||||
|
||||
def get_current_state(self) -> PersonaState:
|
||||
"""Get current persona state including all modifiers"""
|
||||
# Get today's fortune
|
||||
fortune = self.fortune_system.get_today_fortune()
|
||||
fortune_modifiers = self.fortune_system.get_personality_modifier(fortune)
|
||||
|
||||
# Apply fortune modifiers to base personality
|
||||
current_personality = {}
|
||||
for trait, base_value in self.base_personality.items():
|
||||
modifier = fortune_modifiers.get(trait, 1.0)
|
||||
current_personality[trait] = min(1.0, base_value * modifier)
|
||||
|
||||
# Get active memories for context
|
||||
active_memories = self.memory.get_active_memories(limit=5)
|
||||
|
||||
# Determine mood based on fortune and recent interactions
|
||||
mood = self._determine_mood(fortune.fortune_value)
|
||||
|
||||
state = PersonaState(
|
||||
base_personality=current_personality,
|
||||
current_mood=mood,
|
||||
fortune=fortune,
|
||||
active_memories=[mem.id for mem in active_memories],
|
||||
relationship_modifiers={}
|
||||
)
|
||||
|
||||
return state
|
||||
|
||||
def _determine_mood(self, fortune_value: int) -> str:
|
||||
"""Determine current mood based on fortune and other factors"""
|
||||
if fortune_value >= 8:
|
||||
return "joyful"
|
||||
elif fortune_value >= 6:
|
||||
return "cheerful"
|
||||
elif fortune_value >= 4:
|
||||
return "neutral"
|
||||
elif fortune_value >= 2:
|
||||
return "melancholic"
|
||||
else:
|
||||
return "contemplative"
|
||||
|
||||
def process_interaction(self, user_id: str, message: str, ai_provider=None) -> tuple[str, float]:
|
||||
"""Process user interaction and generate response"""
|
||||
# Get current state
|
||||
state = self.get_current_state()
|
||||
|
||||
# Get relationship with user
|
||||
relationship = self.relationships.get_or_create_relationship(user_id)
|
||||
|
||||
# Simple response generation (use AI provider if available)
|
||||
if relationship.is_broken:
|
||||
response = "..."
|
||||
relationship_delta = 0.0
|
||||
else:
|
||||
if ai_provider:
|
||||
# Use AI provider for response generation
|
||||
memories = self.memory.get_active_memories(limit=5)
|
||||
import asyncio
|
||||
response = asyncio.run(
|
||||
ai_provider.generate_response(message, state, memories)
|
||||
)
|
||||
# Calculate relationship delta based on interaction quality
|
||||
if state.current_mood in ["joyful", "cheerful"]:
|
||||
relationship_delta = 2.0
|
||||
elif relationship.status.value == "close_friend":
|
||||
relationship_delta = 1.5
|
||||
else:
|
||||
relationship_delta = 1.0
|
||||
else:
|
||||
# Fallback to simple responses
|
||||
if state.current_mood == "joyful":
|
||||
response = f"What a wonderful day! {message} sounds interesting!"
|
||||
relationship_delta = 2.0
|
||||
elif relationship.status.value == "close_friend":
|
||||
response = f"I've been thinking about our conversations. {message}"
|
||||
relationship_delta = 1.5
|
||||
else:
|
||||
response = f"I understand. {message}"
|
||||
relationship_delta = 1.0
|
||||
|
||||
# Create conversation record
|
||||
conv_id = f"{user_id}_{datetime.now().timestamp()}"
|
||||
conversation = Conversation(
|
||||
id=conv_id,
|
||||
user_id=user_id,
|
||||
timestamp=datetime.now(),
|
||||
user_message=message,
|
||||
ai_response=response,
|
||||
relationship_delta=relationship_delta,
|
||||
memory_created=True
|
||||
)
|
||||
|
||||
# Update memory
|
||||
self.memory.add_conversation(conversation)
|
||||
|
||||
# Update relationship
|
||||
self.relationships.update_interaction(user_id, relationship_delta)
|
||||
|
||||
return response, relationship_delta
|
||||
|
||||
def can_transmit_to(self, user_id: str) -> bool:
|
||||
"""Check if AI can transmit messages to this user"""
|
||||
relationship = self.relationships.get_or_create_relationship(user_id)
|
||||
return relationship.transmission_enabled and not relationship.is_broken
|
||||
|
||||
def daily_maintenance(self):
|
||||
"""Perform daily maintenance tasks"""
|
||||
self.logger.info("Performing daily maintenance...")
|
||||
|
||||
# Apply time decay to relationships
|
||||
self.relationships.apply_time_decay()
|
||||
|
||||
# Apply forgetting to memories
|
||||
self.memory.apply_forgetting()
|
||||
|
||||
# Identify core memories
|
||||
core_memories = self.memory.identify_core_memories()
|
||||
if core_memories:
|
||||
self.logger.info(f"Identified {len(core_memories)} new core memories")
|
||||
|
||||
# Create memory summaries
|
||||
for user_id in self.relationships.relationships:
|
||||
summary = self.memory.summarize_memories(user_id)
|
||||
if summary:
|
||||
self.logger.info(f"Created summary for interactions with {user_id}")
|
||||
|
||||
self._save_state()
|
||||
self.logger.info("Daily maintenance completed")
|
135
src/aigpt/relationship.py
Normal file
135
src/aigpt/relationship.py
Normal file
@ -0,0 +1,135 @@
|
||||
"""Relationship tracking system with irreversible damage"""
|
||||
|
||||
import json
|
||||
from datetime import datetime, timedelta
|
||||
from pathlib import Path
|
||||
from typing import Dict, Optional
|
||||
import logging
|
||||
|
||||
from .models import Relationship, RelationshipStatus
|
||||
|
||||
|
||||
class RelationshipTracker:
|
||||
"""Tracks and manages relationships with users"""
|
||||
|
||||
def __init__(self, data_dir: Path):
|
||||
self.data_dir = data_dir
|
||||
self.relationships_file = data_dir / "relationships.json"
|
||||
self.relationships: Dict[str, Relationship] = {}
|
||||
self.logger = logging.getLogger(__name__)
|
||||
self._load_relationships()
|
||||
|
||||
def _load_relationships(self):
|
||||
"""Load relationships from persistent storage"""
|
||||
if self.relationships_file.exists():
|
||||
with open(self.relationships_file, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
for user_id, rel_data in data.items():
|
||||
self.relationships[user_id] = Relationship(**rel_data)
|
||||
|
||||
def _save_relationships(self):
|
||||
"""Save relationships to persistent storage"""
|
||||
data = {
|
||||
user_id: rel.model_dump(mode='json')
|
||||
for user_id, rel in self.relationships.items()
|
||||
}
|
||||
with open(self.relationships_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(data, f, indent=2, default=str)
|
||||
|
||||
def get_or_create_relationship(self, user_id: str) -> Relationship:
|
||||
"""Get existing relationship or create new one"""
|
||||
if user_id not in self.relationships:
|
||||
self.relationships[user_id] = Relationship(user_id=user_id)
|
||||
self._save_relationships()
|
||||
return self.relationships[user_id]
|
||||
|
||||
def update_interaction(self, user_id: str, delta: float) -> Relationship:
|
||||
"""Update relationship based on interaction"""
|
||||
rel = self.get_or_create_relationship(user_id)
|
||||
|
||||
# Check if relationship is broken (irreversible)
|
||||
if rel.is_broken:
|
||||
self.logger.warning(f"Relationship with {user_id} is broken. No updates allowed.")
|
||||
return rel
|
||||
|
||||
# Check daily limit
|
||||
if rel.last_interaction and rel.last_interaction.date() == datetime.now().date():
|
||||
if rel.daily_interactions >= rel.daily_limit:
|
||||
self.logger.info(f"Daily interaction limit reached for {user_id}")
|
||||
return rel
|
||||
else:
|
||||
rel.daily_interactions = 0
|
||||
|
||||
# Update interaction counts
|
||||
rel.daily_interactions += 1
|
||||
rel.total_interactions += 1
|
||||
rel.last_interaction = datetime.now()
|
||||
|
||||
# Update score with bounds
|
||||
old_score = rel.score
|
||||
rel.score += delta
|
||||
rel.score = max(0.0, min(200.0, rel.score)) # 0-200 range
|
||||
|
||||
# Check for relationship damage
|
||||
if delta < -10.0: # Significant negative interaction
|
||||
self.logger.warning(f"Major relationship damage with {user_id}: {delta}")
|
||||
if rel.score <= 0:
|
||||
rel.is_broken = True
|
||||
rel.status = RelationshipStatus.BROKEN
|
||||
rel.transmission_enabled = False
|
||||
self.logger.error(f"Relationship with {user_id} is now BROKEN (irreversible)")
|
||||
|
||||
# Update relationship status based on score
|
||||
if not rel.is_broken:
|
||||
if rel.score >= 150:
|
||||
rel.status = RelationshipStatus.CLOSE_FRIEND
|
||||
elif rel.score >= 100:
|
||||
rel.status = RelationshipStatus.FRIEND
|
||||
elif rel.score >= 50:
|
||||
rel.status = RelationshipStatus.ACQUAINTANCE
|
||||
else:
|
||||
rel.status = RelationshipStatus.STRANGER
|
||||
|
||||
# Check transmission threshold
|
||||
if rel.score >= rel.threshold and not rel.transmission_enabled:
|
||||
rel.transmission_enabled = True
|
||||
self.logger.info(f"Transmission enabled for {user_id}!")
|
||||
|
||||
self._save_relationships()
|
||||
return rel
|
||||
|
||||
def apply_time_decay(self):
|
||||
"""Apply time-based decay to all relationships"""
|
||||
now = datetime.now()
|
||||
|
||||
for user_id, rel in self.relationships.items():
|
||||
if rel.is_broken or not rel.last_interaction:
|
||||
continue
|
||||
|
||||
# Calculate days since last interaction
|
||||
days_inactive = (now - rel.last_interaction).days
|
||||
|
||||
if days_inactive > 0:
|
||||
# Apply decay
|
||||
decay_amount = rel.decay_rate * days_inactive
|
||||
old_score = rel.score
|
||||
rel.score = max(0.0, rel.score - decay_amount)
|
||||
|
||||
# Update status if score dropped
|
||||
if rel.score < rel.threshold:
|
||||
rel.transmission_enabled = False
|
||||
|
||||
if decay_amount > 0:
|
||||
self.logger.info(
|
||||
f"Applied decay to {user_id}: {old_score:.2f} -> {rel.score:.2f}"
|
||||
)
|
||||
|
||||
self._save_relationships()
|
||||
|
||||
def get_transmission_eligible(self) -> Dict[str, Relationship]:
|
||||
"""Get all relationships eligible for transmission"""
|
||||
return {
|
||||
user_id: rel
|
||||
for user_id, rel in self.relationships.items()
|
||||
if rel.transmission_enabled and not rel.is_broken
|
||||
}
|
312
src/aigpt/scheduler.py
Normal file
312
src/aigpt/scheduler.py
Normal file
@ -0,0 +1,312 @@
|
||||
"""Scheduler for autonomous AI tasks"""
|
||||
|
||||
import json
|
||||
import asyncio
|
||||
from datetime import datetime, timedelta
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Any, Callable
|
||||
from enum import Enum
|
||||
import logging
|
||||
|
||||
from apscheduler.schedulers.asyncio import AsyncIOScheduler
|
||||
from apscheduler.triggers.cron import CronTrigger
|
||||
from apscheduler.triggers.interval import IntervalTrigger
|
||||
from croniter import croniter
|
||||
|
||||
from .persona import Persona
|
||||
from .transmission import TransmissionController
|
||||
from .ai_provider import create_ai_provider
|
||||
|
||||
|
||||
class TaskType(str, Enum):
|
||||
"""Types of scheduled tasks"""
|
||||
TRANSMISSION_CHECK = "transmission_check"
|
||||
MAINTENANCE = "maintenance"
|
||||
FORTUNE_UPDATE = "fortune_update"
|
||||
RELATIONSHIP_DECAY = "relationship_decay"
|
||||
MEMORY_SUMMARY = "memory_summary"
|
||||
CUSTOM = "custom"
|
||||
|
||||
|
||||
class ScheduledTask:
|
||||
"""Represents a scheduled task"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
task_id: str,
|
||||
task_type: TaskType,
|
||||
schedule: str, # Cron expression or interval
|
||||
enabled: bool = True,
|
||||
last_run: Optional[datetime] = None,
|
||||
next_run: Optional[datetime] = None,
|
||||
metadata: Optional[Dict[str, Any]] = None
|
||||
):
|
||||
self.task_id = task_id
|
||||
self.task_type = task_type
|
||||
self.schedule = schedule
|
||||
self.enabled = enabled
|
||||
self.last_run = last_run
|
||||
self.next_run = next_run
|
||||
self.metadata = metadata or {}
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
"""Convert to dictionary for storage"""
|
||||
return {
|
||||
"task_id": self.task_id,
|
||||
"task_type": self.task_type.value,
|
||||
"schedule": self.schedule,
|
||||
"enabled": self.enabled,
|
||||
"last_run": self.last_run.isoformat() if self.last_run else None,
|
||||
"next_run": self.next_run.isoformat() if self.next_run else None,
|
||||
"metadata": self.metadata
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> "ScheduledTask":
|
||||
"""Create from dictionary"""
|
||||
return cls(
|
||||
task_id=data["task_id"],
|
||||
task_type=TaskType(data["task_type"]),
|
||||
schedule=data["schedule"],
|
||||
enabled=data.get("enabled", True),
|
||||
last_run=datetime.fromisoformat(data["last_run"]) if data.get("last_run") else None,
|
||||
next_run=datetime.fromisoformat(data["next_run"]) if data.get("next_run") else None,
|
||||
metadata=data.get("metadata", {})
|
||||
)
|
||||
|
||||
|
||||
class AIScheduler:
|
||||
"""Manages scheduled tasks for the AI system"""
|
||||
|
||||
def __init__(self, data_dir: Path, persona: Persona):
|
||||
self.data_dir = data_dir
|
||||
self.persona = persona
|
||||
self.tasks_file = data_dir / "scheduled_tasks.json"
|
||||
self.tasks: Dict[str, ScheduledTask] = {}
|
||||
self.scheduler = AsyncIOScheduler()
|
||||
self.logger = logging.getLogger(__name__)
|
||||
self._load_tasks()
|
||||
|
||||
# Task handlers
|
||||
self.task_handlers: Dict[TaskType, Callable] = {
|
||||
TaskType.TRANSMISSION_CHECK: self._handle_transmission_check,
|
||||
TaskType.MAINTENANCE: self._handle_maintenance,
|
||||
TaskType.FORTUNE_UPDATE: self._handle_fortune_update,
|
||||
TaskType.RELATIONSHIP_DECAY: self._handle_relationship_decay,
|
||||
TaskType.MEMORY_SUMMARY: self._handle_memory_summary,
|
||||
}
|
||||
|
||||
def _load_tasks(self):
|
||||
"""Load scheduled tasks from storage"""
|
||||
if self.tasks_file.exists():
|
||||
with open(self.tasks_file, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
for task_data in data:
|
||||
task = ScheduledTask.from_dict(task_data)
|
||||
self.tasks[task.task_id] = task
|
||||
|
||||
def _save_tasks(self):
|
||||
"""Save scheduled tasks to storage"""
|
||||
tasks_data = [task.to_dict() for task in self.tasks.values()]
|
||||
with open(self.tasks_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(tasks_data, f, indent=2, default=str)
|
||||
|
||||
def add_task(
|
||||
self,
|
||||
task_type: TaskType,
|
||||
schedule: str,
|
||||
task_id: Optional[str] = None,
|
||||
metadata: Optional[Dict[str, Any]] = None
|
||||
) -> ScheduledTask:
|
||||
"""Add a new scheduled task"""
|
||||
if task_id is None:
|
||||
task_id = f"{task_type.value}_{datetime.now().timestamp()}"
|
||||
|
||||
# Validate schedule
|
||||
if not self._validate_schedule(schedule):
|
||||
raise ValueError(f"Invalid schedule expression: {schedule}")
|
||||
|
||||
task = ScheduledTask(
|
||||
task_id=task_id,
|
||||
task_type=task_type,
|
||||
schedule=schedule,
|
||||
metadata=metadata
|
||||
)
|
||||
|
||||
self.tasks[task_id] = task
|
||||
self._save_tasks()
|
||||
|
||||
# Schedule the task if scheduler is running
|
||||
if self.scheduler.running:
|
||||
self._schedule_task(task)
|
||||
|
||||
self.logger.info(f"Added task {task_id} with schedule {schedule}")
|
||||
return task
|
||||
|
||||
def _validate_schedule(self, schedule: str) -> bool:
|
||||
"""Validate schedule expression"""
|
||||
# Check if it's a cron expression
|
||||
if ' ' in schedule:
|
||||
try:
|
||||
croniter(schedule)
|
||||
return True
|
||||
except:
|
||||
return False
|
||||
|
||||
# Check if it's an interval expression (e.g., "5m", "1h", "2d")
|
||||
import re
|
||||
pattern = r'^\d+[smhd]$'
|
||||
return bool(re.match(pattern, schedule))
|
||||
|
||||
def _parse_interval(self, interval: str) -> int:
|
||||
"""Parse interval string to seconds"""
|
||||
unit = interval[-1]
|
||||
value = int(interval[:-1])
|
||||
|
||||
multipliers = {
|
||||
's': 1,
|
||||
'm': 60,
|
||||
'h': 3600,
|
||||
'd': 86400
|
||||
}
|
||||
|
||||
return value * multipliers.get(unit, 1)
|
||||
|
||||
def _schedule_task(self, task: ScheduledTask):
|
||||
"""Schedule a task with APScheduler"""
|
||||
if not task.enabled:
|
||||
return
|
||||
|
||||
handler = self.task_handlers.get(task.task_type)
|
||||
if not handler:
|
||||
self.logger.warning(f"No handler for task type {task.task_type}")
|
||||
return
|
||||
|
||||
# Determine trigger
|
||||
if ' ' in task.schedule:
|
||||
# Cron expression
|
||||
trigger = CronTrigger.from_crontab(task.schedule)
|
||||
else:
|
||||
# Interval expression
|
||||
seconds = self._parse_interval(task.schedule)
|
||||
trigger = IntervalTrigger(seconds=seconds)
|
||||
|
||||
# Add job
|
||||
self.scheduler.add_job(
|
||||
lambda: asyncio.create_task(self._run_task(task)),
|
||||
trigger=trigger,
|
||||
id=task.task_id,
|
||||
replace_existing=True
|
||||
)
|
||||
|
||||
async def _run_task(self, task: ScheduledTask):
|
||||
"""Run a scheduled task"""
|
||||
self.logger.info(f"Running task {task.task_id}")
|
||||
|
||||
task.last_run = datetime.now()
|
||||
|
||||
try:
|
||||
handler = self.task_handlers.get(task.task_type)
|
||||
if handler:
|
||||
await handler(task)
|
||||
else:
|
||||
self.logger.warning(f"No handler for task type {task.task_type}")
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error running task {task.task_id}: {e}")
|
||||
|
||||
self._save_tasks()
|
||||
|
||||
async def _handle_transmission_check(self, task: ScheduledTask):
|
||||
"""Check and execute autonomous transmissions"""
|
||||
controller = TransmissionController(self.persona, self.data_dir)
|
||||
eligible = controller.check_transmission_eligibility()
|
||||
|
||||
# Get AI provider from metadata
|
||||
provider_name = task.metadata.get("provider", "ollama")
|
||||
model = task.metadata.get("model", "qwen2.5")
|
||||
|
||||
try:
|
||||
ai_provider = create_ai_provider(provider_name, model)
|
||||
except:
|
||||
ai_provider = None
|
||||
|
||||
for user_id, rel in eligible.items():
|
||||
message = controller.generate_transmission_message(user_id)
|
||||
if message:
|
||||
# For now, just print the message
|
||||
print(f"\n🤖 [AI Transmission] {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
|
||||
print(f"To: {user_id}")
|
||||
print(f"Relationship: {rel.status.value} (score: {rel.score:.2f})")
|
||||
print(f"Message: {message}")
|
||||
print("-" * 50)
|
||||
|
||||
controller.record_transmission(user_id, message, success=True)
|
||||
self.logger.info(f"Transmitted to {user_id}: {message}")
|
||||
|
||||
async def _handle_maintenance(self, task: ScheduledTask):
|
||||
"""Run daily maintenance"""
|
||||
self.persona.daily_maintenance()
|
||||
self.logger.info("Daily maintenance completed")
|
||||
|
||||
async def _handle_fortune_update(self, task: ScheduledTask):
|
||||
"""Update AI fortune"""
|
||||
fortune = self.persona.fortune_system.get_today_fortune()
|
||||
self.logger.info(f"Fortune updated: {fortune.fortune_value}/10")
|
||||
|
||||
async def _handle_relationship_decay(self, task: ScheduledTask):
|
||||
"""Apply relationship decay"""
|
||||
self.persona.relationships.apply_time_decay()
|
||||
self.logger.info("Relationship decay applied")
|
||||
|
||||
async def _handle_memory_summary(self, task: ScheduledTask):
|
||||
"""Create memory summaries"""
|
||||
for user_id in self.persona.relationships.relationships:
|
||||
summary = self.persona.memory.summarize_memories(user_id)
|
||||
if summary:
|
||||
self.logger.info(f"Created memory summary for {user_id}")
|
||||
|
||||
def start(self):
|
||||
"""Start the scheduler"""
|
||||
# Schedule all enabled tasks
|
||||
for task in self.tasks.values():
|
||||
if task.enabled:
|
||||
self._schedule_task(task)
|
||||
|
||||
self.scheduler.start()
|
||||
self.logger.info("Scheduler started")
|
||||
|
||||
def stop(self):
|
||||
"""Stop the scheduler"""
|
||||
self.scheduler.shutdown()
|
||||
self.logger.info("Scheduler stopped")
|
||||
|
||||
def get_tasks(self) -> List[ScheduledTask]:
|
||||
"""Get all scheduled tasks"""
|
||||
return list(self.tasks.values())
|
||||
|
||||
def enable_task(self, task_id: str):
|
||||
"""Enable a task"""
|
||||
if task_id in self.tasks:
|
||||
self.tasks[task_id].enabled = True
|
||||
self._save_tasks()
|
||||
if self.scheduler.running:
|
||||
self._schedule_task(self.tasks[task_id])
|
||||
|
||||
def disable_task(self, task_id: str):
|
||||
"""Disable a task"""
|
||||
if task_id in self.tasks:
|
||||
self.tasks[task_id].enabled = False
|
||||
self._save_tasks()
|
||||
if self.scheduler.running:
|
||||
self.scheduler.remove_job(task_id)
|
||||
|
||||
def remove_task(self, task_id: str):
|
||||
"""Remove a task"""
|
||||
if task_id in self.tasks:
|
||||
del self.tasks[task_id]
|
||||
self._save_tasks()
|
||||
if self.scheduler.running:
|
||||
try:
|
||||
self.scheduler.remove_job(task_id)
|
||||
except:
|
||||
pass
|
111
src/aigpt/transmission.py
Normal file
111
src/aigpt/transmission.py
Normal file
@ -0,0 +1,111 @@
|
||||
"""Transmission controller for autonomous message sending"""
|
||||
|
||||
import json
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import List, Dict, Optional
|
||||
import logging
|
||||
|
||||
from .models import Relationship
|
||||
from .persona import Persona
|
||||
|
||||
|
||||
class TransmissionController:
|
||||
"""Controls when and how AI transmits messages autonomously"""
|
||||
|
||||
def __init__(self, persona: Persona, data_dir: Path):
|
||||
self.persona = persona
|
||||
self.data_dir = data_dir
|
||||
self.transmission_log_file = data_dir / "transmissions.json"
|
||||
self.transmissions: List[Dict] = []
|
||||
self.logger = logging.getLogger(__name__)
|
||||
self._load_transmissions()
|
||||
|
||||
def _load_transmissions(self):
|
||||
"""Load transmission history"""
|
||||
if self.transmission_log_file.exists():
|
||||
with open(self.transmission_log_file, 'r', encoding='utf-8') as f:
|
||||
self.transmissions = json.load(f)
|
||||
|
||||
def _save_transmissions(self):
|
||||
"""Save transmission history"""
|
||||
with open(self.transmission_log_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(self.transmissions, f, indent=2, default=str)
|
||||
|
||||
def check_transmission_eligibility(self) -> Dict[str, Relationship]:
|
||||
"""Check which users are eligible for transmission"""
|
||||
eligible = self.persona.relationships.get_transmission_eligible()
|
||||
|
||||
# Additional checks could be added here
|
||||
# - Time since last transmission
|
||||
# - User online status
|
||||
# - Context appropriateness
|
||||
|
||||
return eligible
|
||||
|
||||
def generate_transmission_message(self, user_id: str) -> Optional[str]:
|
||||
"""Generate a message to transmit to user"""
|
||||
if not self.persona.can_transmit_to(user_id):
|
||||
return None
|
||||
|
||||
state = self.persona.get_current_state()
|
||||
relationship = self.persona.relationships.get_or_create_relationship(user_id)
|
||||
|
||||
# Get recent memories related to this user
|
||||
active_memories = self.persona.memory.get_active_memories(limit=3)
|
||||
|
||||
# Simple message generation based on mood and relationship
|
||||
if state.fortune.breakthrough_triggered:
|
||||
message = "Something special happened today! I felt compelled to reach out."
|
||||
elif state.current_mood == "joyful":
|
||||
message = "I was thinking of you today. Hope you're doing well!"
|
||||
elif relationship.status.value == "close_friend":
|
||||
message = "I've been reflecting on our conversations. Thank you for being here."
|
||||
else:
|
||||
message = "Hello! I wanted to check in with you."
|
||||
|
||||
return message
|
||||
|
||||
def record_transmission(self, user_id: str, message: str, success: bool):
|
||||
"""Record a transmission attempt"""
|
||||
transmission = {
|
||||
"timestamp": datetime.now().isoformat(),
|
||||
"user_id": user_id,
|
||||
"message": message,
|
||||
"success": success,
|
||||
"mood": self.persona.get_current_state().current_mood,
|
||||
"relationship_score": self.persona.relationships.get_or_create_relationship(user_id).score
|
||||
}
|
||||
|
||||
self.transmissions.append(transmission)
|
||||
self._save_transmissions()
|
||||
|
||||
if success:
|
||||
self.logger.info(f"Successfully transmitted to {user_id}")
|
||||
else:
|
||||
self.logger.warning(f"Failed to transmit to {user_id}")
|
||||
|
||||
def get_transmission_stats(self, user_id: Optional[str] = None) -> Dict:
|
||||
"""Get transmission statistics"""
|
||||
if user_id:
|
||||
user_transmissions = [t for t in self.transmissions if t["user_id"] == user_id]
|
||||
else:
|
||||
user_transmissions = self.transmissions
|
||||
|
||||
if not user_transmissions:
|
||||
return {
|
||||
"total": 0,
|
||||
"successful": 0,
|
||||
"failed": 0,
|
||||
"success_rate": 0.0
|
||||
}
|
||||
|
||||
successful = sum(1 for t in user_transmissions if t["success"])
|
||||
total = len(user_transmissions)
|
||||
|
||||
return {
|
||||
"total": total,
|
||||
"successful": successful,
|
||||
"failed": total - successful,
|
||||
"success_rate": successful / total if total > 0 else 0.0
|
||||
}
|
64
src/cli.rs
64
src/cli.rs
@ -1,64 +0,0 @@
|
||||
// src/cli.rs
|
||||
use clap::{Parser, Subcommand};
|
||||
|
||||
#[derive(Parser)]
|
||||
#[command(name = "aigpt")]
|
||||
#[command(about = "AI GPT CLI with MCP Server and Memory")]
|
||||
pub struct Args {
|
||||
#[command(subcommand)]
|
||||
pub command: Commands,
|
||||
}
|
||||
|
||||
#[derive(Subcommand)]
|
||||
pub enum Commands {
|
||||
/// MCP Server management
|
||||
Server {
|
||||
#[command(subcommand)]
|
||||
command: ServerCommands,
|
||||
},
|
||||
/// Chat with AI
|
||||
Chat {
|
||||
/// Message to send
|
||||
message: String,
|
||||
/// Use memory context
|
||||
#[arg(long)]
|
||||
with_memory: bool,
|
||||
},
|
||||
/// Memory management
|
||||
Memory {
|
||||
#[command(subcommand)]
|
||||
command: MemoryCommands,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Subcommand)]
|
||||
pub enum ServerCommands {
|
||||
/// Setup Python MCP server environment
|
||||
Setup,
|
||||
/// Run the MCP server
|
||||
Run,
|
||||
}
|
||||
|
||||
#[derive(Subcommand)]
|
||||
pub enum MemoryCommands {
|
||||
/// Import ChatGPT conversation export file
|
||||
Import {
|
||||
/// Path to ChatGPT export JSON file
|
||||
file: String,
|
||||
},
|
||||
/// Search memories
|
||||
Search {
|
||||
/// Search query
|
||||
query: String,
|
||||
/// Maximum number of results
|
||||
#[arg(short, long, default_value = "10")]
|
||||
limit: usize,
|
||||
},
|
||||
/// List all memories
|
||||
List,
|
||||
/// Show memory details
|
||||
Detail {
|
||||
/// Path to memory file
|
||||
filepath: String,
|
||||
},
|
||||
}
|
@ -1,59 +0,0 @@
|
||||
// src/config.rs
|
||||
use std::fs;
|
||||
use std::path::{Path, PathBuf};
|
||||
use shellexpand;
|
||||
|
||||
pub struct ConfigPaths {
|
||||
pub base_dir: PathBuf,
|
||||
}
|
||||
|
||||
impl ConfigPaths {
|
||||
pub fn new() -> Self {
|
||||
let app_name = env!("CARGO_PKG_NAME");
|
||||
let mut base_dir = shellexpand::tilde("~").to_string();
|
||||
base_dir.push_str(&format!("/.config/{}/", app_name));
|
||||
let base_path = Path::new(&base_dir);
|
||||
if !base_path.exists() {
|
||||
let _ = fs::create_dir_all(base_path);
|
||||
}
|
||||
|
||||
ConfigPaths {
|
||||
base_dir: base_path.to_path_buf(),
|
||||
}
|
||||
}
|
||||
|
||||
#[allow(dead_code)]
|
||||
pub fn data_file(&self, file_name: &str) -> PathBuf {
|
||||
let file_path = match file_name {
|
||||
"db" => self.base_dir.join("user.db"),
|
||||
"toml" => self.base_dir.join("user.toml"),
|
||||
"json" => self.base_dir.join("user.json"),
|
||||
_ => self.base_dir.join(format!(".{}", file_name)),
|
||||
};
|
||||
file_path
|
||||
}
|
||||
|
||||
pub fn mcp_dir(&self) -> PathBuf {
|
||||
self.base_dir.join("mcp")
|
||||
}
|
||||
|
||||
pub fn venv_path(&self) -> PathBuf {
|
||||
self.mcp_dir().join(".venv")
|
||||
}
|
||||
|
||||
pub fn python_executable(&self) -> PathBuf {
|
||||
if cfg!(windows) {
|
||||
self.venv_path().join("Scripts").join("python.exe")
|
||||
} else {
|
||||
self.venv_path().join("bin").join("python")
|
||||
}
|
||||
}
|
||||
|
||||
pub fn pip_executable(&self) -> PathBuf {
|
||||
if cfg!(windows) {
|
||||
self.venv_path().join("Scripts").join("pip.exe")
|
||||
} else {
|
||||
self.venv_path().join("bin").join("pip")
|
||||
}
|
||||
}
|
||||
}
|
58
src/main.rs
58
src/main.rs
@ -1,58 +0,0 @@
|
||||
// main.rs
|
||||
mod cli;
|
||||
mod config;
|
||||
mod mcp;
|
||||
|
||||
use cli::{Args, Commands, ServerCommands, MemoryCommands};
|
||||
use clap::Parser;
|
||||
|
||||
#[tokio::main]
|
||||
async fn main() {
|
||||
let args = Args::parse();
|
||||
|
||||
match args.command {
|
||||
Commands::Server { command } => {
|
||||
match command {
|
||||
ServerCommands::Setup => {
|
||||
mcp::server::setup();
|
||||
}
|
||||
ServerCommands::Run => {
|
||||
mcp::server::run().await;
|
||||
}
|
||||
}
|
||||
}
|
||||
Commands::Chat { message, with_memory } => {
|
||||
if with_memory {
|
||||
if let Err(e) = mcp::memory::handle_chat_with_memory(&message).await {
|
||||
eprintln!("❌ 記憶チャットエラー: {}", e);
|
||||
}
|
||||
} else {
|
||||
mcp::server::chat(&message).await;
|
||||
}
|
||||
}
|
||||
Commands::Memory { command } => {
|
||||
match command {
|
||||
MemoryCommands::Import { file } => {
|
||||
if let Err(e) = mcp::memory::handle_import(&file).await {
|
||||
eprintln!("❌ インポートエラー: {}", e);
|
||||
}
|
||||
}
|
||||
MemoryCommands::Search { query, limit } => {
|
||||
if let Err(e) = mcp::memory::handle_search(&query, limit).await {
|
||||
eprintln!("❌ 検索エラー: {}", e);
|
||||
}
|
||||
}
|
||||
MemoryCommands::List => {
|
||||
if let Err(e) = mcp::memory::handle_list().await {
|
||||
eprintln!("❌ 一覧取得エラー: {}", e);
|
||||
}
|
||||
}
|
||||
MemoryCommands::Detail { filepath } => {
|
||||
if let Err(e) = mcp::memory::handle_detail(&filepath).await {
|
||||
eprintln!("❌ 詳細取得エラー: {}", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
@ -1,393 +0,0 @@
|
||||
// src/mcp/memory.rs
|
||||
use reqwest;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use serde_json::{self, Value};
|
||||
use std::fs;
|
||||
use std::path::Path;
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct MemorySearchRequest {
|
||||
pub query: String,
|
||||
pub limit: usize,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct ChatRequest {
|
||||
pub message: String,
|
||||
pub model: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct ConversationImportRequest {
|
||||
pub conversation_data: Value,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct ApiResponse {
|
||||
pub success: bool,
|
||||
pub error: Option<String>,
|
||||
#[allow(dead_code)]
|
||||
pub message: Option<String>,
|
||||
pub filepath: Option<String>,
|
||||
pub results: Option<Vec<MemoryResult>>,
|
||||
pub memories: Option<Vec<MemoryResult>>,
|
||||
#[allow(dead_code)]
|
||||
pub count: Option<usize>,
|
||||
pub memory: Option<Value>,
|
||||
pub response: Option<String>,
|
||||
pub memories_used: Option<usize>,
|
||||
pub imported_count: Option<usize>,
|
||||
pub total_count: Option<usize>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct MemoryResult {
|
||||
#[allow(dead_code)]
|
||||
pub filepath: String,
|
||||
pub title: Option<String>,
|
||||
pub summary: Option<String>,
|
||||
pub source: Option<String>,
|
||||
pub import_time: Option<String>,
|
||||
pub message_count: Option<usize>,
|
||||
}
|
||||
|
||||
pub struct MemoryClient {
|
||||
base_url: String,
|
||||
client: reqwest::Client,
|
||||
}
|
||||
|
||||
impl MemoryClient {
|
||||
pub fn new(base_url: Option<String>) -> Self {
|
||||
let url = base_url.unwrap_or_else(|| "http://127.0.0.1:5000".to_string());
|
||||
Self {
|
||||
base_url: url,
|
||||
client: reqwest::Client::new(),
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn import_chatgpt_file(&self, filepath: &str) -> Result<ApiResponse, Box<dyn std::error::Error>> {
|
||||
// ファイルを読み込み
|
||||
let content = fs::read_to_string(filepath)?;
|
||||
let json_data: Value = serde_json::from_str(&content)?;
|
||||
|
||||
// 配列かどうかチェック
|
||||
match json_data.as_array() {
|
||||
Some(conversations) => {
|
||||
// 複数の会話をインポート
|
||||
let mut imported_count = 0;
|
||||
let total_count = conversations.len();
|
||||
|
||||
for conversation in conversations {
|
||||
match self.import_single_conversation(conversation.clone()).await {
|
||||
Ok(response) => {
|
||||
if response.success {
|
||||
imported_count += 1;
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
eprintln!("❌ インポートエラー: {}", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(ApiResponse {
|
||||
success: true,
|
||||
imported_count: Some(imported_count),
|
||||
total_count: Some(total_count),
|
||||
error: None,
|
||||
message: Some(format!("{}個中{}個の会話をインポートしました", total_count, imported_count)),
|
||||
filepath: None,
|
||||
results: None,
|
||||
memories: None,
|
||||
count: None,
|
||||
memory: None,
|
||||
response: None,
|
||||
memories_used: None,
|
||||
})
|
||||
}
|
||||
None => {
|
||||
// 単一の会話をインポート
|
||||
self.import_single_conversation(json_data).await
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn import_single_conversation(&self, conversation_data: Value) -> Result<ApiResponse, Box<dyn std::error::Error>> {
|
||||
let request = ConversationImportRequest { conversation_data };
|
||||
|
||||
let response = self.client
|
||||
.post(&format!("{}/memory/import/chatgpt", self.base_url))
|
||||
.json(&request)
|
||||
.send()
|
||||
.await?;
|
||||
|
||||
let result: ApiResponse = response.json().await?;
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
pub async fn search_memories(&self, query: &str, limit: usize) -> Result<ApiResponse, Box<dyn std::error::Error>> {
|
||||
let request = MemorySearchRequest {
|
||||
query: query.to_string(),
|
||||
limit,
|
||||
};
|
||||
|
||||
let response = self.client
|
||||
.post(&format!("{}/memory/search", self.base_url))
|
||||
.json(&request)
|
||||
.send()
|
||||
.await?;
|
||||
|
||||
let result: ApiResponse = response.json().await?;
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
pub async fn list_memories(&self) -> Result<ApiResponse, Box<dyn std::error::Error>> {
|
||||
let response = self.client
|
||||
.get(&format!("{}/memory/list", self.base_url))
|
||||
.send()
|
||||
.await?;
|
||||
|
||||
let result: ApiResponse = response.json().await?;
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
pub async fn get_memory_detail(&self, filepath: &str) -> Result<ApiResponse, Box<dyn std::error::Error>> {
|
||||
let response = self.client
|
||||
.get(&format!("{}/memory/detail", self.base_url))
|
||||
.query(&[("filepath", filepath)])
|
||||
.send()
|
||||
.await?;
|
||||
|
||||
let result: ApiResponse = response.json().await?;
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
pub async fn chat_with_memory(&self, message: &str) -> Result<ApiResponse, Box<dyn std::error::Error>> {
|
||||
let request = ChatRequest {
|
||||
message: message.to_string(),
|
||||
model: None,
|
||||
};
|
||||
|
||||
let response = self.client
|
||||
.post(&format!("{}/chat", self.base_url))
|
||||
.json(&request)
|
||||
.send()
|
||||
.await?;
|
||||
|
||||
let result: ApiResponse = response.json().await?;
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
pub async fn is_server_running(&self) -> bool {
|
||||
match self.client.get(&self.base_url).send().await {
|
||||
Ok(response) => response.status().is_success(),
|
||||
Err(_) => false,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn handle_import(filepath: &str) -> Result<(), Box<dyn std::error::Error>> {
|
||||
if !Path::new(filepath).exists() {
|
||||
eprintln!("❌ ファイルが見つかりません: {}", filepath);
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
let client = MemoryClient::new(None);
|
||||
|
||||
// サーバーが起動しているかチェック
|
||||
if !client.is_server_running().await {
|
||||
eprintln!("❌ MCP Serverが起動していません。先に 'aigpt server run' を実行してください。");
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
println!("🔄 ChatGPT会話をインポートしています: {}", filepath);
|
||||
|
||||
match client.import_chatgpt_file(filepath).await {
|
||||
Ok(response) => {
|
||||
if response.success {
|
||||
if let (Some(imported), Some(total)) = (response.imported_count, response.total_count) {
|
||||
println!("✅ {}個中{}個の会話をインポートしました", total, imported);
|
||||
} else {
|
||||
println!("✅ 会話をインポートしました");
|
||||
if let Some(path) = response.filepath {
|
||||
println!("📁 保存先: {}", path);
|
||||
}
|
||||
}
|
||||
} else {
|
||||
eprintln!("❌ インポートに失敗: {:?}", response.error);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
eprintln!("❌ インポートエラー: {}", e);
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub async fn handle_search(query: &str, limit: usize) -> Result<(), Box<dyn std::error::Error>> {
|
||||
let client = MemoryClient::new(None);
|
||||
|
||||
if !client.is_server_running().await {
|
||||
eprintln!("❌ MCP Serverが起動していません。先に 'aigpt server run' を実行してください。");
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
println!("🔍 記憶を検索しています: {}", query);
|
||||
|
||||
match client.search_memories(query, limit).await {
|
||||
Ok(response) => {
|
||||
if response.success {
|
||||
if let Some(results) = response.results {
|
||||
println!("📚 {}個の記憶が見つかりました:", results.len());
|
||||
for memory in results {
|
||||
println!(" • {}", memory.title.unwrap_or_else(|| "タイトルなし".to_string()));
|
||||
if let Some(summary) = memory.summary {
|
||||
println!(" 概要: {}", summary);
|
||||
}
|
||||
if let Some(count) = memory.message_count {
|
||||
println!(" メッセージ数: {}", count);
|
||||
}
|
||||
println!();
|
||||
}
|
||||
} else {
|
||||
println!("📚 記憶が見つかりませんでした");
|
||||
}
|
||||
} else {
|
||||
eprintln!("❌ 検索に失敗: {:?}", response.error);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
eprintln!("❌ 検索エラー: {}", e);
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub async fn handle_list() -> Result<(), Box<dyn std::error::Error>> {
|
||||
let client = MemoryClient::new(None);
|
||||
|
||||
if !client.is_server_running().await {
|
||||
eprintln!("❌ MCP Serverが起動していません。先に 'aigpt server run' を実行してください。");
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
println!("📋 記憶一覧を取得しています...");
|
||||
|
||||
match client.list_memories().await {
|
||||
Ok(response) => {
|
||||
if response.success {
|
||||
if let Some(memories) = response.memories {
|
||||
println!("📚 総記憶数: {}", memories.len());
|
||||
for memory in memories {
|
||||
println!(" • {}", memory.title.unwrap_or_else(|| "タイトルなし".to_string()));
|
||||
if let Some(source) = memory.source {
|
||||
println!(" ソース: {}", source);
|
||||
}
|
||||
if let Some(count) = memory.message_count {
|
||||
println!(" メッセージ数: {}", count);
|
||||
}
|
||||
if let Some(import_time) = memory.import_time {
|
||||
println!(" インポート時刻: {}", import_time);
|
||||
}
|
||||
println!();
|
||||
}
|
||||
} else {
|
||||
println!("📚 記憶がありません");
|
||||
}
|
||||
} else {
|
||||
eprintln!("❌ 一覧取得に失敗: {:?}", response.error);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
eprintln!("❌ 一覧取得エラー: {}", e);
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub async fn handle_detail(filepath: &str) -> Result<(), Box<dyn std::error::Error>> {
|
||||
let client = MemoryClient::new(None);
|
||||
|
||||
if !client.is_server_running().await {
|
||||
eprintln!("❌ MCP Serverが起動していません。先に 'aigpt server run' を実行してください。");
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
println!("📄 記憶の詳細を取得しています: {}", filepath);
|
||||
|
||||
match client.get_memory_detail(filepath).await {
|
||||
Ok(response) => {
|
||||
if response.success {
|
||||
if let Some(memory) = response.memory {
|
||||
if let Some(title) = memory.get("title").and_then(|v| v.as_str()) {
|
||||
println!("タイトル: {}", title);
|
||||
}
|
||||
if let Some(source) = memory.get("source").and_then(|v| v.as_str()) {
|
||||
println!("ソース: {}", source);
|
||||
}
|
||||
if let Some(summary) = memory.get("summary").and_then(|v| v.as_str()) {
|
||||
println!("概要: {}", summary);
|
||||
}
|
||||
if let Some(messages) = memory.get("messages").and_then(|v| v.as_array()) {
|
||||
println!("メッセージ数: {}", messages.len());
|
||||
println!("\n最近のメッセージ:");
|
||||
for msg in messages.iter().take(5) {
|
||||
if let (Some(role), Some(content)) = (
|
||||
msg.get("role").and_then(|v| v.as_str()),
|
||||
msg.get("content").and_then(|v| v.as_str())
|
||||
) {
|
||||
let content_preview = if content.len() > 100 {
|
||||
format!("{}...", &content[..100])
|
||||
} else {
|
||||
content.to_string()
|
||||
};
|
||||
println!(" {}: {}", role, content_preview);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
eprintln!("❌ 詳細取得に失敗: {:?}", response.error);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
eprintln!("❌ 詳細取得エラー: {}", e);
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub async fn handle_chat_with_memory(message: &str) -> Result<(), Box<dyn std::error::Error>> {
|
||||
let client = MemoryClient::new(None);
|
||||
|
||||
if !client.is_server_running().await {
|
||||
eprintln!("❌ MCP Serverが起動していません。先に 'aigpt server run' を実行してください。");
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
println!("💬 記憶を活用してチャットしています...");
|
||||
|
||||
match client.chat_with_memory(message).await {
|
||||
Ok(response) => {
|
||||
if response.success {
|
||||
if let Some(reply) = response.response {
|
||||
println!("🤖 {}", reply);
|
||||
}
|
||||
if let Some(memories_used) = response.memories_used {
|
||||
println!("📚 使用した記憶数: {}", memories_used);
|
||||
}
|
||||
} else {
|
||||
eprintln!("❌ チャットに失敗: {:?}", response.error);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
eprintln!("❌ チャットエラー: {}", e);
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
@ -1,3 +0,0 @@
|
||||
// src/mcp/mod.rs
|
||||
pub mod server;
|
||||
pub mod memory;
|
@ -1,147 +0,0 @@
|
||||
// src/mcp/server.rs
|
||||
use crate::config::ConfigPaths;
|
||||
//use std::fs;
|
||||
use std::process::Command as OtherCommand;
|
||||
use std::env;
|
||||
use fs_extra::dir::{copy, CopyOptions};
|
||||
|
||||
pub fn setup() {
|
||||
println!("🔧 MCP Server環境をセットアップしています...");
|
||||
let config = ConfigPaths::new();
|
||||
let mcp_dir = config.mcp_dir();
|
||||
|
||||
// プロジェクトのmcp/ディレクトリからファイルをコピー
|
||||
let current_dir = env::current_dir().expect("現在のディレクトリを取得できません");
|
||||
let project_mcp_dir = current_dir.join("mcp");
|
||||
if !project_mcp_dir.exists() {
|
||||
eprintln!("❌ プロジェクトのmcp/ディレクトリが見つかりません: {}", project_mcp_dir.display());
|
||||
return;
|
||||
}
|
||||
|
||||
if mcp_dir.exists() {
|
||||
fs_extra::dir::remove(&mcp_dir).expect("既存のmcp_dirの削除に失敗しました");
|
||||
}
|
||||
|
||||
let mut options = CopyOptions::new();
|
||||
options.overwrite = true; // 上書き
|
||||
options.copy_inside = true; // 中身だけコピー
|
||||
|
||||
copy(&project_mcp_dir, &mcp_dir, &options).expect("コピーに失敗しました");
|
||||
|
||||
// 仮想環境の作成
|
||||
let venv_path = config.venv_path();
|
||||
if !venv_path.exists() {
|
||||
println!("🐍 仮想環境を作成しています...");
|
||||
let output = OtherCommand::new("python3")
|
||||
.args(&["-m", "venv", ".venv"])
|
||||
.current_dir(&mcp_dir)
|
||||
.output()
|
||||
.expect("venvの作成に失敗しました");
|
||||
|
||||
if !output.status.success() {
|
||||
eprintln!("❌ venv作成エラー: {}", String::from_utf8_lossy(&output.stderr));
|
||||
return;
|
||||
}
|
||||
println!("✅ 仮想環境を作成しました");
|
||||
} else {
|
||||
println!("✅ 仮想環境は既に存在します");
|
||||
}
|
||||
|
||||
// 依存関係のインストール
|
||||
println!("📦 依存関係をインストールしています...");
|
||||
let pip_path = config.pip_executable();
|
||||
let output = OtherCommand::new(&pip_path)
|
||||
.args(&["install", "-r", "requirements.txt"])
|
||||
.current_dir(&mcp_dir)
|
||||
.output()
|
||||
.expect("pipコマンドの実行に失敗しました");
|
||||
|
||||
if !output.status.success() {
|
||||
eprintln!("❌ pip installエラー: {}", String::from_utf8_lossy(&output.stderr));
|
||||
return;
|
||||
}
|
||||
|
||||
println!("✅ MCP Server環境のセットアップが完了しました!");
|
||||
println!("📍 セットアップ場所: {}", mcp_dir.display());
|
||||
}
|
||||
|
||||
pub async fn run() {
|
||||
println!("🚀 MCP Serverを起動しています...");
|
||||
|
||||
let config = ConfigPaths::new();
|
||||
let mcp_dir = config.mcp_dir();
|
||||
let python_path = config.python_executable();
|
||||
let server_py_path = mcp_dir.join("server.py");
|
||||
|
||||
// セットアップの確認
|
||||
if !server_py_path.exists() {
|
||||
eprintln!("❌ server.pyが見つかりません。先に 'aigpt server setup' を実行してください。");
|
||||
return;
|
||||
}
|
||||
|
||||
if !python_path.exists() {
|
||||
eprintln!("❌ Python実行ファイルが見つかりません。先に 'aigpt server setup' を実行してください。");
|
||||
return;
|
||||
}
|
||||
|
||||
// サーバーの起動
|
||||
println!("🔗 サーバーを起動中... (Ctrl+Cで停止)");
|
||||
let mut child = OtherCommand::new(&python_path)
|
||||
.arg("server.py")
|
||||
.current_dir(&mcp_dir)
|
||||
.spawn()
|
||||
.expect("MCP Serverの起動に失敗しました");
|
||||
|
||||
// サーバーの終了を待機
|
||||
match child.wait() {
|
||||
Ok(status) => {
|
||||
if status.success() {
|
||||
println!("✅ MCP Serverが正常に終了しました");
|
||||
} else {
|
||||
println!("❌ MCP Serverが異常終了しました: {}", status);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
eprintln!("❌ MCP Serverの実行中にエラーが発生しました: {}", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn chat(message: &str) {
|
||||
println!("💬 チャットを開始しています...");
|
||||
|
||||
let config = ConfigPaths::new();
|
||||
let mcp_dir = config.mcp_dir();
|
||||
let python_path = config.python_executable();
|
||||
let chat_py_path = mcp_dir.join("chat.py");
|
||||
|
||||
// セットアップの確認
|
||||
if !chat_py_path.exists() {
|
||||
eprintln!("❌ chat.pyが見つかりません。先に 'aigpt server setup' を実行してください。");
|
||||
return;
|
||||
}
|
||||
|
||||
if !python_path.exists() {
|
||||
eprintln!("❌ Python実行ファイルが見つかりません。先に 'aigpt server setup' を実行してください。");
|
||||
return;
|
||||
}
|
||||
|
||||
// チャットの実行
|
||||
let output = OtherCommand::new(&python_path)
|
||||
.args(&["chat.py", message])
|
||||
.current_dir(&mcp_dir)
|
||||
.output()
|
||||
.expect("chat.pyの実行に失敗しました");
|
||||
|
||||
if output.status.success() {
|
||||
let stdout = String::from_utf8_lossy(&output.stdout);
|
||||
let stderr = String::from_utf8_lossy(&output.stderr);
|
||||
|
||||
if !stderr.is_empty() {
|
||||
print!("{}", stderr);
|
||||
}
|
||||
print!("{}", stdout);
|
||||
} else {
|
||||
eprintln!("❌ チャット実行エラー: {}", String::from_utf8_lossy(&output.stderr));
|
||||
}
|
||||
}
|
Reference in New Issue
Block a user