feat: Add new files for i18n, libs, and project structure

libs/external/chat-vault/src/parsers/__init__.py

@@ -0,0 +1,7 @@
+from .codex import CodexParser
+from .gemini import GeminiParser
+from .claude import ClaudeParser
+from .kiro import KiroParser
+from .base import SessionData
+
+__all__ = ["CodexParser", "GeminiParser", "ClaudeParser", "KiroParser", "SessionData"]

libs/external/chat-vault/src/parsers/base.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
+from typing import List, Dict
+
+@dataclass
+class SessionData:
+    """会话数据"""
+    session_id: str
+    source: str
+    file_path: str
+    file_mtime: float = 0
+    cwd: str = None
+    messages: List[Dict] = field(default_factory=list)  # [{"time", "role", "content"}]
+
+class BaseParser(ABC):
+    @abstractmethod
+    def find_files(self, paths: list) -> list:
+        pass
+    
+    @abstractmethod
+    def parse_file(self, filepath: str) -> SessionData:
+        pass

libs/external/chat-vault/src/parsers/claude.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+import os
+import json
+import hashlib
+from datetime import datetime
+from collections import defaultdict
+from .base import BaseParser, SessionData
+
+class ClaudeParser(BaseParser):
+    def find_files(self, paths: list) -> list:
+        files = []
+        for base in paths:
+            history = os.path.join(base, "history.jsonl")
+            if os.path.exists(history):
+                files.append(history)
+        return files
+    
+    def parse_file(self, filepath: str) -> list:
+        """返回多个 SessionData（按 project 分组）"""
+        projects = defaultdict(list)
+        file_mtime = os.path.getmtime(filepath)
+        
+        with open(filepath, 'r', encoding='utf-8') as f:
+            for line in f:
+                line = line.strip()
+                if not line:
+                    continue
+                data = json.loads(line)
+                content = data.get('display', '')
+                if not content:
+                    continue
+                
+                project = data.get('project', 'unknown')
+                ts_ms = data.get('timestamp', 0)
+                ts = datetime.fromtimestamp(ts_ms / 1000).isoformat() if ts_ms else ''
+                
+                projects[project].append({
+                    'time': ts,
+                    'role': 'user',
+                    'content': content
+                })
+        
+        return [
+            SessionData(
+                session_id='claude-' + hashlib.md5(proj.encode()).hexdigest()[:12],
+                source='claude',
+                file_path=filepath,
+                file_mtime=file_mtime,
+                cwd=proj,
+                messages=msgs
+            )
+            for proj, msgs in projects.items()
+        ]

libs/external/chat-vault/src/parsers/codex.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+import os
+import json
+import re
+from .base import BaseParser, SessionData
+
+class CodexParser(BaseParser):
+    def __init__(self, source: str = 'codex'):
+        self.source = source
+    
+    def find_files(self, paths: list) -> list:
+        files = []
+        for base in paths:
+            if not os.path.exists(base):
+                continue
+            for root, _, names in os.walk(base):
+                for f in names:
+                    if f.endswith('.jsonl') and f != 'history.jsonl':
+                        files.append(os.path.join(root, f))
+        return files
+    
+    def _extract_id(self, filepath: str) -> str:
+        match = re.search(r'([0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})', 
+                          os.path.basename(filepath))
+        return match.group(1) if match else os.path.basename(filepath).replace('.jsonl', '')
+    
+    def parse_file(self, filepath: str) -> SessionData:
+        s = SessionData(
+            session_id=self._extract_id(filepath),
+            source=self.source,
+            file_path=filepath,
+            file_mtime=os.path.getmtime(filepath)
+        )
+        
+        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+            for line in f:
+                line = line.strip()
+                if not line or line[0] != '{':
+                    continue
+                try:
+                    data = json.loads(line)
+                except json.JSONDecodeError:
+                    continue
+                
+                if data.get('type') == 'session_meta':
+                    p = data.get('payload', {})
+                    s.cwd = p.get('cwd')
+                    s.session_id = p.get('id', s.session_id)
+                    continue
+                
+                if data.get('type') != 'response_item':
+                    continue
+                payload = data.get('payload', {})
+                if payload.get('type') != 'message':
+                    continue
+                role = payload.get('role')
+                if role not in ('user', 'assistant'):
+                    continue
+                
+                parts = [item.get('text', '') for item in payload.get('content', [])
+                         if isinstance(item, dict) and item.get('type') in ('input_text', 'output_text', 'text')]
+                if parts:
+                    s.messages.append({
+                        'time': data.get('timestamp', ''),
+                        'role': 'user' if role == 'user' else 'ai',
+                        'content': ' '.join(parts)
+                    })
+        
+        return s

libs/external/chat-vault/src/parsers/gemini.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+import os
+import glob
+import json
+from .base import BaseParser, SessionData
+
+class GeminiParser(BaseParser):
+    def find_files(self, paths: list) -> list:
+        files = []
+        for base in paths:
+            if os.path.exists(base):
+                files.extend(glob.glob(os.path.join(base, "*", "chats", "*.json")))
+        return files
+    
+    def parse_file(self, filepath: str) -> SessionData:
+        s = SessionData(
+            session_id=os.path.basename(filepath).replace('.json', ''),
+            source='gemini',
+            file_path=filepath,
+            file_mtime=os.path.getmtime(filepath)
+        )
+        
+        with open(filepath, 'r', encoding='utf-8') as f:
+            data = json.load(f)
+        
+        s.session_id = data.get('sessionId', s.session_id)
+        
+        for msg in data.get('messages', []):
+            if msg.get('type') not in ('user', 'gemini'):
+                continue
+            content = msg.get('content', '')
+            if content:
+                s.messages.append({
+                    'time': msg.get('timestamp', ''),
+                    'role': 'user' if msg.get('type') == 'user' else 'ai',
+                    'content': content
+                })
+        
+        return s

libs/external/chat-vault/src/parsers/kiro.py

@@ -0,0 +1,75 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Kiro CLI 解析器 - 从 SQLite 数据库读取"""
+import os
+import json
+import sqlite3
+import hashlib
+from datetime import datetime
+from .base import BaseParser, SessionData
+
+KIRO_DB = os.path.expanduser("~/.local/share/kiro-cli/data.sqlite3")
+
+class KiroParser(BaseParser):
+    def find_files(self, paths: list) -> list:
+        """返回数据库路径（如果存在）"""
+        if os.path.exists(KIRO_DB):
+            return [KIRO_DB]
+        return []
+    
+    def parse_file(self, filepath: str) -> list:
+        """解析 Kiro SQLite 数据库，返回多个 SessionData"""
+        sessions = []
+        file_mtime = os.path.getmtime(filepath)
+        
+        conn = sqlite3.connect(filepath)
+        for row in conn.execute('SELECT key, value FROM conversations'):
+            cwd, value = row
+            try:
+                data = json.loads(value)
+            except json.JSONDecodeError:
+                continue
+            
+            conv_id = data.get('conversation_id', hashlib.md5(cwd.encode()).hexdigest()[:12])
+            history = data.get('history', [])
+            
+            messages = []
+            for item in history:
+                # 用户消息
+                if 'user' in item:
+                    user = item['user']
+                    content = user.get('content', {})
+                    if isinstance(content, dict) and 'Prompt' in content:
+                        prompt = content['Prompt'].get('prompt', '')
+                        if prompt:
+                            messages.append({
+                                'time': '',
+                                'role': 'user',
+                                'content': prompt
+                            })
+                
+                # AI 回复
+                if 'assistant' in item:
+                    assistant = item['assistant']
+                    content = assistant.get('content', {})
+                    if isinstance(content, dict) and 'Message' in content:
+                        msg = content['Message'].get('message', '')
+                        if msg:
+                            messages.append({
+                                'time': '',
+                                'role': 'ai',
+                                'content': msg
+                            })
+            
+            if messages:
+                sessions.append(SessionData(
+                    session_id=f'kiro-{conv_id[:12]}',
+                    source='kiro',
+                    file_path=f'kiro:{conv_id}',
+                    file_mtime=file_mtime,
+                    cwd=cwd,
+                    messages=messages
+                ))
+        
+        conn.close()
+        return sessions