Feishu Chat History

Feishu Chat History

Fetch message history from a Feishu group chat and summarize or present it to the user.

When to Use

• User asks what was discussed in a group
• User wants a summary or review of recent messages
• User provides a chat_id or is in a group and asks about its history

How to Fetch Messages

Use the Feishu IM API directly via Python. See references/api.md for full details.

Quick summary: 1. Read credentials from config → channels.feishu.appId / appSecret 2. Get tenant_access_token via POST /auth/v3/tenant_access_token/internal 3. Fetch messages via GET /im/v1/messages?container_id_type=chat&container_id={chat_id}&page_size=50

Identifying the chat_id

• If the user is asking about the current group chat, use the chat_id from the inbound metadata (chat:oc_xxxxx → strip the chat: prefix to get the raw ID)
• If the user provides a different group, ask for the chat_id

Presenting Results

Parse each message and present a clean summary:

• Filter out msg_type=system (join/leave events) unless relevant
• For msg_type=text: extract .body.content as JSON, get the text field
• For msg_type=interactive: extract text nodes from the elements array
• For msg_type=image: note as [图片]
• Include sender name (from mentions or known bot app_ids), timestamp, and content
• Group by thread if root_id is present
• End with a human-readable summary of topics discussed

Pagination

If has_more=true, fetch more pages using page_token. Default: fetch 1 page (50 messages). Ask user if they want more.

feishu-chat-history

获取并总结飞书群聊消息记录，快速了解群里聊了什么。

能力

• 拉取指定飞书群的最近消息（默认 50 条/页）
• 自动解析 text / interactive / image 等消息类型
• 按话题分组、生成人类可读的讨论摘要
• 支持分页加载更多历史消息

触发场景

• "看群聊记录"、"群里聊了啥"
• "帮我看看这个群"、"群消息历史"
• "chat history"、"what did the group discuss"

工作原理

1. 从配置读取飞书应用凭据（appId / appSecret） 2. 获取 tenant_access_token 3. 调用 GET /im/v1/messages 拉取群消息 4. 解析各类型消息内容，过滤系统消息 5. 生成讨论话题摘要

消息解析

配置

需要飞书应用凭据，通过 channels.feishu.appId / appSecret 配置。

License

MIT

Feishu IM API Reference

Auth

POST https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal
Content-Type: application/json

{"app_id": "...", "app_secret": "..."}

Response: {"tenant_access_token": "...", "expire": 7200}

Fetch Chat Messages

GET https://open.feishu.cn/open-apis/im/v1/messages
  ?container_id_type=chat
  &container_id={chat_id}
  &page_size=50
  [&page_token={token}]      # pagination
  [&start_time={unix_ms}]    # filter by time range
  [&end_time={unix_ms}]
Authorization: Bearer {tenant_access_token}

Response fields:

• data.items[]: message list (newest first by default)
• data.has_more: bool
• data.page_token: use for next page

Message Object Fields

Parsing msg_type

text

{"text": "hello world @_user_1"}

Replace @_user_X keys with the corresponding mentions[].name.

interactive (card)

{"title": null, "elements": [[{"tag": "text", "text": "..."}, ...]]}

Walk elements and concatenate all tag=text nodes.

post

{"title": "", "content": [[{"tag": "text", "text": "...", "style": []}]]}

Walk content rows and concatenate text nodes.

image

{"image_key": "img_v3_..."}

Render as [图片].

system

Template messages like join/leave events. Usually skip unless relevant.

Python Snippet

import json, os, urllib.request

config_path = os.path.expanduser('~/.openclaw-autoclaw/openclaw.json')
with open(config_path) as f:
    cfg = json.load(f)['channels']['feishu']

# Auth
req = urllib.request.Request(
    'https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal',
    data=json.dumps({'app_id': cfg['appId'], 'app_secret': cfg['appSecret']}).encode(),
    headers={'Content-Type': 'application/json'}
)
token = json.loads(urllib.request.urlopen(req).read())['tenant_access_token']

# Fetch messages
chat_id = 'oc_xxxxxx'
url = f'https://open.feishu.cn/open-apis/im/v1/messages?container_id_type=chat&container_id={chat_id}&page_size=50'
req2 = urllib.request.Request(url, headers={'Authorization': f'Bearer {token}'})
data = json.loads(urllib.request.urlopen(req2).read())
messages = data['data']['items']
has_more = data['data'].get('has_more', False)
page_token = data['data'].get('page_token')