对话存储

// typescript
const sessionStore = context.store.claudeSessionStore()

// python
session_store = context.store.claude_session_store()

// typescript
const session = context.store.openaiSession(context.conversation_id)

// python
session = context.store.openai_session(context.conversation_id)

// typescript
const checkpointer = context.store.langgraphCheckpointer
const store = context.store.langgraphStore

// python
checkpointer = context.store.langgraph_checkpointer
store = context.store.langgraph_store

// typescript
const checkpointer = context.store.langgraphCheckpointer
const store = context.store.langgraphStore

// python
checkpointer = context.store.langgraph_checkpointer
store = context.store.langgraph_store

const messageId = await context.store.appendMessage({
  conversationId: context.conversation_id,
  role: 'user',
  content: context.request.body.message,
  userId: context.request.body.userId,
  metadata: { source: 'web' },
})

message_id = await context.store.append_message(
    conversation_id=context.conversation_id,
    role="user",
    content=context.request.body["message"],
    user_id=context.request.body.get("user_id"),
    metadata={"source": "web"},
)

const messages = await context.store.getMessages({
  conversationId: context.conversation_id,
  limit: 50,
})
const reply = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: context.store.toOpenAIInput(messages),
})

messages = await context.store.get_messages(
    conversation_id=context.conversation_id,
    limit=50,
)
reply = await openai_client.chat.completions.create(
    model="gpt-4o",
    messages=context.store.to_openai_input(messages),
)

const updated = await context.store.updateMessage({
  conversationId: context.conversation_id,
  messageId: 'msg_abc123',
  content: 'corrected answer',
  metadata: { edited: true },
})

updated = await context.store.update_message(
    conversation_id=context.conversation_id,
    message_id="msg_abc123",
    content="corrected answer",
    metadata={"edited": True},
)

await context.store.deleteMessage({
  conversationId: context.conversation_id,
  messageId: 'msg_abc123',
})

await context.store.delete_message(
    conversation_id=context.conversation_id,
    message_id="msg_abc123",
)

await context.store.clearMessages({ conversationId: context.conversation_id })

await context.store.clear_messages(conversation_id=context.conversation_id)

const meta = await context.store.getConversation({
  conversationId: context.conversation_id,
})
console.log(meta.messageCount, meta.metadata?.title)

meta = await context.store.get_conversation(
    conversation_id=context.conversation_id,
)
print(meta.message_count, (meta.metadata or {}).get("title"))

const { items, nextCursor } = await context.store.listConversations({
  userId: 'u_123',
  limit: 20,
})

result = await context.store.list_conversations(user_id="u_123", limit=20)
items, next_cursor = result.items, result.next_cursor

await context.store.updateConversation({
  conversationId: context.conversation_id,
  metadata: { title: '产品咨询', tag: null },  // 设标题，删 tag
})

await context.store.update_conversation(
    conversation_id=context.conversation_id,
    metadata={"title": "产品咨询", "tag": None},
)

await context.store.deleteConversation({
  conversationId: context.conversation_id,
})

await context.store.delete_conversation(
    conversation_id=context.conversation_id,
)

const history = await context.store.getMessages({
  conversationId: context.conversation_id,
})
const resp = await anthropic.messages.create({
  model: 'claude-sonnet-4',
  max_tokens: 1024,
  messages: context.store.toAnthropicMessages(history),
})

history = await context.store.get_messages(
    conversation_id=context.conversation_id,
)
resp = await anthropic_client.messages.create(
    model="claude-sonnet-4",
    max_tokens=1024,
    messages=context.store.to_anthropic_messages(history),
)

const history = await context.store.getMessages({
  conversationId: context.conversation_id,
})
const resp = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: context.store.toOpenAIInput(history),
})

history = await context.store.get_messages(
    conversation_id=context.conversation_id,
)
resp = await openai_client.chat.completions.create(
    model="gpt-4o",
    messages=context.store.to_openai_input(history),
)

interface Message {
  messageId: string                       // msg_xxx（appendMessage 自动生成）
  role: 'user' | 'assistant' | 'system' | 'tool'
  content: any                            // string / array / object（多模态）
  createdAt: number                       // ms 时间戳
  metadata?: Record<string, any>          // 自定义（token 数、tool_call 等）
  updatedAt?: number                      // 仅 updateMessage 后存在
}

interface ConversationMeta {
  conversationId: string
  createdAt: number                       // ms 时间戳
  lastMessageAt: number                   // ms 时间戳
  messageCount: number
  metadata?: Record<string, any>          // 业务自定义（标题、用户、标签等）
}

interface ListConversationsResult {
  items: ConversationMeta[]
  nextCursor?: string                     // 下一页游标，传给 after 参数
  previousCursor?: string                 // 上一页游标，传给 before 参数
}

async function summarizeWithLLM(previousSummary, newMessages) {
  const transcript = newMessages
    .filter(m => m.role === 'user' || m.role === 'assistant')
    .map(m => `${m.role}: ${
      typeof m.content === 'string' ? m.content : JSON.stringify(m.content)
    }`)
    .join('\n')
  const prompt = previousSummary
    ? `下面是一段对话的【已有摘要】和【新增对话】，请合并成一段新摘要。
要求：
- 保留：关键事实、用户偏好、未完成的任务、重要的上下文设定
- 删除：寒暄、确认收到、重复内容、工具调用细节
- 用与最近对话相同的语言书写
- 控制在 500 字内

【已有摘要】
${previousSummary}

【新增对话】
${transcript}

【新摘要】`
    : `请把下面的对话总结成一段摘要。
要求：
- 保留：关键事实、用户偏好、未完成的任务、重要的上下文设定
- 删除：寒暄、确认收到、重复内容、工具调用细节
- 用与对话相同的语言书写
- 控制在 500 字内

【对话】
${transcript}
【摘要】`
  const { text } = await generateText({
    model: openai('gpt-4o-mini'),
    prompt,
    maxTokens: 800,
  })
  return text.trim()
}