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>

backend/CLAUDE.md

@@ -112,7 +112,7 @@ CI runs these regression tests for every pull request via [.github/workflows/bac
 The backend is split into two layers with a strict dependency direction:
 
 - **Harness** (`packages/harness/deerflow/`): Publishable agent framework package (`deerflow-harness`). Import prefix: `deerflow.*`. Contains agent orchestration, tools, sandbox, models, MCP, skills, config — everything needed to build and run agents.
-- **App** (`app/`): Unpublished application code. Import prefix: `app.*`. Contains the FastAPI Gateway API and IM channel integrations (Feishu, Slack, Telegram).
+- **App** (`app/`): Unpublished application code. Import prefix: `app.*`. Contains the FastAPI Gateway API and IM channel integrations (Feishu, Slack, Telegram, DingTalk).
 
 **Dependency rule**: App imports deerflow, but deerflow never imports app. This boundary is enforced by `tests/test_harness_boundary.py` which runs in CI.
 
@@ -312,7 +312,8 @@ Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` →
 
 ### IM Channels System (`app/channels/`)
 
-Bridges external messaging platforms (Feishu, Slack, Telegram) to the DeerFlow agent via Gateway's LangGraph-compatible API.
+Bridges external messaging platforms (Feishu, Slack, Telegram, DingTalk) to the DeerFlow agent via the LangGraph Server.
+
 
 **Architecture**: Channels communicate with Gateway through the `langgraph-sdk` HTTP client (same as the frontend), ensuring threads are created and managed server-side. The internal SDK client injects process-local internal auth plus a matching CSRF cookie/header pair so Gateway accepts state-changing thread/run requests from channel workers without relying on browser session cookies.
 
@@ -322,7 +323,7 @@ Bridges external messaging platforms (Feishu, Slack, Telegram) to the DeerFlow a
 - `manager.py` - Core dispatcher: creates threads via `client.threads.create()`, routes commands, keeps Slack/Telegram on `client.runs.wait()`, and uses `client.runs.stream(["messages-tuple", "values"])` for Feishu incremental outbound updates
 - `base.py` - Abstract `Channel` base class (start/stop/send lifecycle)
 - `service.py` - Manages lifecycle of all configured channels from `config.yaml`
-- `slack.py` / `feishu.py` / `telegram.py` - Platform-specific implementations (`feishu.py` tracks the running card `message_id` in memory and patches the same card in place)
+- `slack.py` / `feishu.py` / `telegram.py` / `dingtalk.py` - Platform-specific implementations (`feishu.py` tracks the running card `message_id` in memory and patches the same card in place; `dingtalk.py` optionally uses AI Card streaming for in-place updates when `card_template_id` is configured)
 
 **Message Flow**:
 1. External platform -> Channel impl -> `MessageBus.publish_inbound()`
@@ -331,14 +332,16 @@ Bridges external messaging platforms (Feishu, Slack, Telegram) to the DeerFlow a
 4. Feishu chat: `runs.stream()` → accumulate AI text → publish multiple outbound updates (`is_final=False`) → publish final outbound (`is_final=True`)
 5. Slack/Telegram chat: `runs.wait()` → extract final response → publish outbound
 6. Feishu channel sends one running reply card up front, then patches the same card for each outbound update (card JSON sets `config.update_multi=true` for Feishu's patch API requirement)
-7. For commands (`/new`, `/status`, `/models`, `/memory`, `/help`): handle locally or query Gateway API
-8. Outbound → channel callbacks → platform reply
+7. DingTalk AI Card mode (when `card_template_id` configured): `runs.stream()` → create card with initial text → stream updates via `PUT /v1.0/card/streaming` → finalize on `is_final=True`. Falls back to `sampleMarkdown` if card creation or streaming fails
+8. For commands (`/new`, `/status`, `/models`, `/memory`, `/help`): handle locally or query Gateway API
+9. Outbound → channel callbacks → platform reply
 
 **Configuration** (`config.yaml` -> `channels`):
 - `langgraph_url` - LangGraph-compatible Gateway API base URL (default: `http://localhost:8001/api`)
 - `gateway_url` - Gateway API URL for auxiliary commands (default: `http://localhost:8001`)
 - In Docker Compose, IM channels run inside the `gateway` container, so `localhost` points back to that container. Use `http://gateway:8001/api` for `langgraph_url` and `http://gateway:8001` for `gateway_url`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` / `DEER_FLOW_CHANNELS_GATEWAY_URL`.
-- Per-channel configs: `feishu` (app_id, app_secret), `slack` (bot_token, app_token), `telegram` (bot_token)
+- Per-channel configs: `feishu` (app_id, app_secret), `slack` (bot_token, app_token), `telegram` (bot_token), `dingtalk` (client_id, client_secret, optional `card_template_id` for AI Card streaming)
+
 
 ### Memory System (`packages/harness/deerflow/agents/memory/`)