feat(channels): add DingTalk channel integration (#2628)

* feat(channels): add DingTalk channel integration

Add a new DingTalk messaging channel using the dingtalk-stream SDK
with Stream Push (WebSocket), requiring no public IP. Supports both
plain sampleMarkdown replies and optional AI Card streaming for a
typewriter effect when card_template_id is configured.

- Add DingTalkChannel implementation with token management, message
  routing, allowed_users filtering, and markdown adaptation
- Register dingtalk in channel service registry and capability map
- Propagate inbound metadata to outbound messages in ChannelManager
  for DingTalk sender context (sender_staff_id, conversation_type)
- Add dingtalk-stream dependency to pyproject.toml
- Add configuration examples in config.example.yaml and .env.example
- Update all README translations with setup instructions
- Add comprehensive test suite (test_dingtalk_channel.py) and
  metadata propagation test in test_channels.py
- Update backend CLAUDE.md to document DingTalk channel

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(channels): address PR review feedback for DingTalk integration

- Replace runtime mutation of CHANNEL_CAPABILITIES with a
  `supports_streaming` property on the Channel base class, overridden
  by DingTalkChannel, FeishuChannel, and WeComChannel
- Store stream client reference and attempt graceful disconnect in
  stop(); guard _on_chatbot_message with _running check to prevent
  post-stop message processing
- Use msg.chat_id as the primary routing key in send/send_file via
  a shared _resolve_routing helper, with metadata as fallback
- Fix process() return type annotation from tuple[str, str] to
  tuple[int, str] to match AckMessage.STATUS_OK
- Protect _incoming_messages with threading.Lock for cross-thread
  safety between the Stream Push thread and the asyncio loop
- Re-add Docker Compose URL guidance removed during DingTalk setup
  docs addition in README.md
- Fix incomplete sentence in README_zh.md (missing verb "启用")

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(docs): restore plain paragraph format for Docker Compose note

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(channels): fix isinstance TypeError and add file size guard in DingTalk channel

Use tuple syntax for isinstance() type check to avoid runtime TypeError
with PEP 604 union types. Add upload size limit (20MB) before reading
files into memory. Narrow exception handlers to specific types.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(channels): propagate markdown fallback errors and validate access token response

- Re-raise exceptions in _send_markdown_fallback to prevent partial
  deliveries (files sent without accompanying text)
- Validate _get_access_token response: reject non-dict bodies, empty
  tokens, and coerce invalid expireIn to a safe default
- Add tests for both fixes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(channels): validate upload response and broaden send_file exception handling

- Validate _upload_media JSON response: handle JSONDecodeError and
  non-dict payloads gracefully by returning None
- Broaden send_file exception tuple to include TypeError and
  AttributeError for unexpected JSON shapes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(channels): fix streaming race on channel registration and slim outbound metadata

- Register channel in service before calling start() to avoid race
  where background receiver publishes inbound before registration,
  causing manager to fall back to static CHANNEL_CAPABILITIES
- Strip known-large metadata keys (raw_message, ref_msg) from outbound
  messages to prevent memory bloat from propagated inbound payloads

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Update service.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update CLAUDE.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
He Wang
2026-04-30 11:25:33 +08:00
committed by GitHub
parent 0691c4dda3
commit 08afdcb907
18 changed files with 2544 additions and 7 deletions
+20
View File
@@ -345,6 +345,7 @@ DeerFlow supports receiving tasks from messaging apps. Channels auto-start when
| Feishu / Lark | WebSocket | Moderate |
| WeChat | Tencent iLink (long-polling) | Moderate |
| WeCom | WebSocket | Moderate |
| DingTalk | Stream Push (WebSocket) | Moderate |
**Configuration in `config.yaml`:**
@@ -414,6 +415,13 @@ channels:
context:
thinking_enabled: true
subagent_enabled: true
dingtalk:
enabled: true
client_id: $DINGTALK_CLIENT_ID # Client ID of your DingTalk application
client_secret: $DINGTALK_CLIENT_SECRET # Client Secret of your DingTalk application
allowed_users: [] # empty = allow all
card_template_id: "" # Optional: AI Card template ID for streaming typewriter effect
```
Notes:
@@ -442,6 +450,10 @@ WECHAT_ILINK_BOT_ID=your_ilink_bot_id
# WeCom
WECOM_BOT_ID=your_bot_id
WECOM_BOT_SECRET=your_bot_secret
# DingTalk
DINGTALK_CLIENT_ID=your_client_id
DINGTALK_CLIENT_SECRET=your_client_secret
```
**Telegram Setup**
@@ -480,6 +492,14 @@ WECOM_BOT_SECRET=your_bot_secret
4. Make sure backend dependencies include `wecom-aibot-python-sdk`. The channel uses a WebSocket long connection and does not require a public callback URL.
5. The current integration supports inbound text, image, and file messages. Final images/files generated by the agent are also sent back to the WeCom conversation.
**DingTalk Setup**
1. Create a DingTalk application in the [DingTalk Developer Console](https://open.dingtalk.com/) and enable **Robot** capability.
2. Set the message receiving mode to **Stream Mode** in the robot configuration page.
3. Copy the `Client ID` and `Client Secret`, set `DINGTALK_CLIENT_ID` and `DINGTALK_CLIENT_SECRET` in `.env`, and enable the channel in `config.yaml`.
4. *(Optional)* To enable streaming AI Card replies (typewriter effect), create an **AI Card** template on the [DingTalk Card Platform](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card), then set `card_template_id` in `config.yaml` to the template ID. You also need to apply for the `Card.Streaming.Write` and `Card.Instance.Write` permissions.
When DeerFlow runs in Docker Compose, IM channels execute inside the `gateway` container. In that case, do not point `channels.langgraph_url` or `channels.gateway_url` at `localhost`; use container service names such as `http://gateway:8001/api` and `http://gateway:8001`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` and `DEER_FLOW_CHANNELS_GATEWAY_URL`.
**Commands**