The previous version bump commit (bb4376c) only updated the root
package.json but did not run `npm run release:version` to propagate
the version and sandboxImageUri to all workspace packages.
This caused Docker sandbox integration tests to fail in CI with
"manifest unknown" because build_sandbox.js built image 0.14.1
(from packages/cli/package.json) while sandboxConfig.ts expected
image 0.14.2 (from root package.json).
Fixes: https://github.com/QwenLM/qwen-code/actions/runs/24135197272/job/70424966323
- Update all packages from 0.13.x to 0.14.0
- Update sandbox image URI to 0.14.0
This prepares the 0.14.0 release with updated version numbers
across all workspace packages.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- fix: sanitize remote filenames with basename() and isolate uploads
in UUID subdirs to prevent path traversal and collision (#2-4, #27)
- fix: use crypto.randomInt() for pairing codes instead of Math.random() (#5)
- fix: pass config.sessionScope instead of hardcoded 'user' (#6);
add per-channel scope overrides via setChannelScope() for startAll (#7)
- fix: removeSession now returns removed session IDs and persists
when chatId is provided (#8)
- fix: /clear only removes the cleared session from instructedSessions,
not all sessions (#9)
- fix: DingTalk @mention stripping now removes only the first mention
instead of all mentions (#10)
- fix: remove dead TELEGRAF_COMMANDS Set and its guard (#13)
- fix: WeChat cursor saved after message processing, not before (#14)
- fix: crash recovery uses time-window counting instead of resettable
counter to prevent infinite restart loops (#17)
- fix: call channel.disconnect() before exit on crash exhaustion (#18)
Add three dispatch modes for handling concurrent messages:
- steer (default): cancel current prompt and start new one
- collect: buffer messages and coalesce into follow-up prompt
- followup: queue messages for sequential processing
Introduce onPromptStart/onPromptEnd lifecycle hooks for working
indicators. These fire only when a prompt actually begins processing,
not for buffered (collect mode) or gated/blocked messages.
Refactor Telegram, WeChat, and DingTalk adapters to use the new hooks
instead of overriding handleInbound, simplifying the working indicator
pattern and ensuring correct behavior with dispatch modes.
This enables better UX for async workflows and prevents indicator
leaks when messages are buffered or cancelled.
- Add Attachment interface with type, data, filePath, mimeType, fileName
- Resolve attachments in ChannelBase before prompting bridge
- Update DingTalk, Telegram, Weixin adapters to use structured attachments
- Clean up placeholder text when files are received
- Export Attachment type from base package index
This enables proper handling of images and files across all channels,
separating attachment metadata from message text.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Update package.json exports to point to dist directory
- Add TypeScript build scripts to each channel adapter
- Include channel adapters in build order
This enables proper TypeScript compilation and distribution of channel
adapter packages.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Bump channel package versions to 0.13.0
- Add publish steps for @qwen-code/channel-base and @qwen-code/channel-plugin-example
- Update version script to convert file: references to semver for published packages
This enables proper npm publishing of channel packages during the release process.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Refactor channel system to use a formal plugin interface:
- Add ChannelPlugin interface to @qwen-code/channel-base (channelType,
displayName, requiredConfigFields, createChannel factory)
- Each built-in adapter (Telegram, WeChat, DingTalk) exports a plugin object
- Replace hardcoded if/else factory with a Map-based channel registry
- Config validation now uses plugin's requiredConfigFields dynamically
- ChannelType changed from fixed union to string for extensibility
- Multi-channel mode now picks model from first channel config
This is the foundation for external plugin support — built-in channels
go through the exact same code path that third-party plugins will use.
- Add interfaces for DingTalkRepliedMsg and DingTalkRichTextPart types
- Support both newer text.repliedMsg and legacy quoteMessage formats
- Extract quoted message context with isReplyToBot detection
- Summarize replied content (text, richText, media placeholders)
This enables the bot to understand when users are replying to specific
messages and provides context about what message is being referenced.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Handle richText, picture, file, audio, video message types
- Download media via DingTalk API two-step flow
- Attach images as base64, save other files to temp dir
- Add DingTalkMessageData interface for richer payloads
This enables the DingTalk channel to process media attachments
in incoming messages.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Convert tables to pipe-separated plain text (DingTalk doesn't render tables)
- Split long messages into chunks respecting ~3800 char limit
- Handle code fences across chunk boundaries
- Extract title from first markdown line for webhook payload
This ensures markdown content renders correctly in DingTalk's limited renderer.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Cache sessionWebhook by conversationId for reliable message routing
- Show 👀 reaction while processing messages, then recall it
- Use conversationId as chatId instead of webhook URL
- Fix rawData parsing for already-parsed message data
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add @qwen-code/channel-dingtalk package with stream-based bot integration
- Support clientId/clientSecret authentication for DingTalk
- Add message deduplication and group chat mention handling
- Update ChannelConfig type to include dingtalk channel type
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
