- Deleted references to WeCom document integration in the data source import module documentation.
- Updated the quick start guide and related sections to reflect the removal of WeCom, enhancing clarity and focus on supported platforms.
- Implemented polling mechanism in DataSourceSettings for real-time updates on data source synchronization status.
- Improved loading state management and user feedback during data source operations.
- Added load more functionality in DataSourceSyncLogs for better log retrieval experience.
- Updated UI elements for consistency, including icon changes and styling adjustments for better visual clarity.
- Added checks to ensure that the tenant ID matches between data sources and knowledge bases during creation and updates.
- Implemented ownership verification for data sources and knowledge bases in the DataSourceHandler, enhancing security and access control.
- Refactored data source retrieval methods to centralize ownership validation, improving code maintainability and clarity.
- Updated error handling to provide more informative responses when access is denied or when knowledge bases are not found.
- Introduced new icons for Feishu, Notion, and Yuque data sources to enhance visual representation.
- Updated localization files to include success and failure messages for data source creation and synchronization.
- Enhanced DataSourceEditorDialog and DataSourceSettings components with improved user feedback during data source operations.
- Added DataSourceTypeIcon component for consistent icon display across data source settings.
- Deleted WeCom document connector and callback handling code to streamline the datasource management.
- Removed associated localization entries and UI elements related to WeCom integration.
- Updated data source management logic to eliminate references to WeCom, enhancing maintainability and clarity.
- Adjusted error handling and logging to reflect the removal of WeCom-specific functionality.
- Improved logging for missing data sources, providing clearer warnings when a data source is not found.
- Updated sync log status to 'canceled' when a data source is deleted, ensuring accurate tracking of sync operations.
- Adjusted error handling to prevent unnecessary error returns, enhancing overall process stability.
- Updated error handling in DataSourceSettings and DataSourceEditorDialog to provide more informative messages.
- Enhanced the UI to display error details more clearly, improving user experience during connection tests and resource loading.
- Adjusted HTTP response status checks in request utility for better accuracy in handling success responses.
- Improved DataSourceSettings component with better loading handling and UI updates for data source cards.
- Refactored layout and styling for data source cards, including enhanced title and status display.
- Updated DataSourceSyncLogs component with improved summary statistics and log display styles.
- Enhanced responsiveness and visual consistency across components with updated padding, margins, and font sizes.
- Added translations for "Refresh logs" in English, Korean, Russian, and Chinese.
- Enhanced the knowledge base editor modal to include a badge for data source count.
- Improved data source settings UI with a confirmation dialog for deletion and a refresh button in sync logs.
- Updated the data source sync logs component to fetch logs on visibility change and added a refresh option in the header.
- Implemented WeCom document connector to sync smart documents and WeDrive files into WeKnora.
- Added detailed documentation for WeCom integration, including setup instructions for callback URL and API access.
- Enhanced frontend localization to support WeCom-specific messages and instructions.
- Updated data source management UI to include WeCom configuration options and callback URL handling.
- Improved error handling and validation for WeCom API interactions.
- Introduced comprehensive documentation for the data source import module, detailing integration with external platforms like Feishu, Notion, and Confluence.
- Included a quick start guide, front-end management instructions, architecture overview, and data model specifications.
- Enhanced user understanding of data source configuration, synchronization processes, and error handling.
- Added a new API for managing data sources, including CRUD operations and connection validation.
- Introduced UI components for data source settings, sync logs, and editor dialog, enhancing user experience in managing external data sources.
- Updated localization files to support new data source features in multiple languages.
- Implemented cron expression humanization for better scheduling visibility.
- Enhanced knowledge base editor to include data source management options.
The file upload pipeline (ProcessDocument) only called ResolveAndStore(),
which handles inline bytes and base64 data URIs but explicitly skips
http/https URLs. This meant markdown files with external image URLs
(e.g. GitHub issue screenshots) were never downloaded, stored, or
processed by VLM multimodal.
Add ResolveRemoteImages() call after ResolveAndStore() in the file
upload path, matching the existing manual processing path behavior.
The S3 storage adapter (s3.go) was added in e309e0b but the provider
scheme integration was incomplete — ParseProviderScheme() and frontend
security.ts were not updated, causing s3:// URLs to fail in the /files
proxy, VLM image processing, and frontend rendering.
Additionally, S3-compatible services (MinIO, Ceph, etc.) require
path-style addressing (endpoint/bucket/key) but the SDK client only
used virtual-hosted style. The deprecated WithEndpointResolver API
is replaced with BaseEndpoint, and path-style is auto-enabled for
non-AWS endpoints (detected by amazonaws.com in the URL).
Changes:
- types/knowledgebase.go: add "s3" to ParseProviderScheme()
- file/s3.go: auto path-style for S3-compatible endpoints + replace
deprecated WithEndpointResolver with BaseEndpoint
- frontend/security.ts: add s3 to 5 provider scheme allowlists
- knowledgebase_test.go: add ParseProviderScheme + InferStorage tests
- s3_test.go: add path-style detection + parseS3FilePath tests
Add session_mode ("user" | "thread") to IM channel config. In thread
mode, each message thread gets its own session, enabling multi-user
collaboration within the same thread context.
Backend:
- Add SessionMode type constants and validation
- Add ThreadID field to IncomingMessage and ChannelSession
- Split resolveSession into resolveUserSession/resolveThreadSession
- Update makeUserKey to include threadID only in thread mode
- Extract ThreadID in Slack, Mattermost, Feishu, Telegram adapters
- Add message_thread_id to Telegram SendReply/StartStream for Forums
- DB migration 000028: session_mode column + thread_id column + index
Frontend:
- Add session_mode radio group to IMChannelPanel dialog
- Auto-reset session_mode when switching to non-thread platform
- Show thread badge on channel card for thread-mode channels
- Add i18n keys for en-US, ko-KR, zh-CN, ru-RU
When ParallelToolCalls is enabled in AgentConfig and the LLM returns
2+ tool calls, execute them concurrently via errgroup. Results are
collected in original order for deterministic observe-phase behavior.
Sequential execution remains the default. Parallel mode is opt-in
per agent configuration to avoid side effects with stateful tools.
Refactors executeToolCalls into composable helpers (runToolCall,
executeSingleToolCall, executeToolCallsParallel) for testability.
Fixes#707
- Remove all backdrop-filter: blur() from 20+ elements (primary perf bottleneck)
- Remove all filter: drop-shadow() from 40 animated SVG elements
- Reduce animated knowledge nodes from 20 to 12 and connection lines from 20 to 12
- Add will-change hints for GPU-composited animation properties
- Add contain: strict on animation container to isolate layout recalc
- Restore background radial-gradient overlay for visual depth
- Replace repeated languageOptions.find() calls with cached computed property
- Consolidate onBeforeUnmount import to top-level
- Add prefers-reduced-motion media query for accessibility
- Maintain visual fidelity with enhanced box-shadow glow on nodes
Made-with: Cursor
- Added new integrations for Telegram, DingTalk, and Mattermost IM channels.
- Introduced a pluggable slash command system and a suggested questions feature for enhanced user interaction.
- Implemented VLM auto-description for images returned by MCP tools.
- Improved stability of MCP tool names and added channel tracking for knowledge entries.
- Fixed multiple bugs including empty responses when no knowledge base is configured and UTF-8 truncation issues.
- Updated documentation to reflect new features and enhancements.
- Bumped project version from 0.1.3 to 0.3.4.
- Updated dependencies: marked to version 17.0.5, dompurify to version 3.3.3, and picomatch to version 4.0.4.
- Removed outdated @types/marked dependency.
- Introduced `escapeLikeKeyword` function to escape SQL LIKE wildcards in search queries, ensuring accurate keyword matching.
- Updated search queries to utilize the new escaping function for filtering by file name and title.
- Added `FindByMetadataKey` method to retrieve knowledge items based on key-value pairs in the metadata JSON column, enhancing search capabilities.
- guard against empty content completion in analyzeResponse/executeLoop
with retry (max 2), nudge message, and fallback response
- propagate actual finish_reason through streaming pipeline instead of
hardcoding "stop" in streamThinkingToEventBus
- add FinishReason field to StreamResponse and streamLLMResult
- add finish marker chunk in processStreamDelta for empty content scenarios
- propagate lastFinishReason through EOF handler in processStream
- strengthen PureAgent system prompt with MCP tool guidelines and
graceful fallback instructions for unanswerable questions
- add unit tests for empty response bug and finish_reason propagation
- Updated context template to include runtime metadata such as current time and week, improving contextual awareness in user queries.
- Enhanced rewrite template with critical instructions for intent classification, ensuring that rewritten questions preserve essential entities and keywords.
- Refined intent classification logic to prioritize user intents more effectively, improving the accuracy of responses based on user queries.
- Added examples to clarify expected input and output formats for intent classification, enhancing usability for developers.
When LLM summary generation fails, the fallback logic truncates
the first chunk content to 500 characters. Previously used byte-based
slicing (summary[:500]) which could cut multi-byte UTF-8 characters
in half, causing PostgreSQL to reject invalid byte sequences.
Changed to rune-based truncation to ensure valid UTF-8 after truncation.
Fixes: Documents stuck in "Generating summary" status when containing
Chinese/emoji characters and summary generation fails.
Update MiniMax provider description and model references from the legacy
MiniMax-M2.1/M2.1-lightning to the latest MiniMax-M2.7/M2.7-highspeed
models. Also update Novita AI's MiniMax model reference from M2.5 to M2.7.
Changes:
- Update MiniMax provider description in minimax.go
- Update Novita provider MiniMax model reference in novita.go
- Update all i18n locale files (en-US, zh-CN, ko-KR, ru-RU)
- Add MiniMax provider validation tests
- Replaced the default DialContext with SSRFSafeDialContext in the raw HTTP client to improve security against DNS rebinding attacks.
- Added SSRF validation for BaseURL and endpoint in NewRemoteAPIChat and chat methods, ensuring safer URL handling.
- Updated security utility functions to provide consistent SSRF checks across the application.
- Added github.com/tiktoken-go/tokenizer v0.7.0 to the required dependencies for improved tokenization support.
- Included golang.org/x/sys v0.40.0 to enhance system call functionalities.
- Removed indirect references to these packages to streamline the dependency management.
- Implemented a new API method to fetch suggested questions based on an agent's knowledge bases, enhancing user interaction in the chat interface.
- Introduced data structures for request and response handling, including options for limiting results and specifying knowledge base IDs.
- Enhanced query construction to support flexible filtering of suggested questions, improving the overall chat experience.
- Introduced a new task enqueuer in the ImageMultimodalService to handle question generation for image knowledge.
- Implemented logic to enqueue question generation tasks when valid captions or OCR content are available, enhancing the knowledge base's interactivity.
- Updated image reference handling to ensure markdown URLs are correctly formatted, accommodating filenames with spaces.
- Enhanced regex pattern in image resolver to support filenames with spaces, improving image processing accuracy.
- Added a new API endpoint to fetch suggested questions based on the agent's associated knowledge bases.
- Implemented frontend components to display suggested questions in both chat and create chat views, enhancing user interaction.
- Updated localization files to include translations for suggested questions in English, Korean, Russian, and Chinese.
- Introduced debounce logic for fetching suggestions to optimize performance during knowledge base changes.
- Enhanced backend services to support fetching and returning suggested questions, improving the overall chat experience.
- Removed redundant instructions from the context template to simplify user guidance.
- Added context retrieval information to the system prompt, ensuring consistency in how context is presented across templates.
- Enhanced parameter casting to allow single strings to be treated as string arrays, improving flexibility in parameter handling.
- Adjusted minimum thought requirements in sequential thinking to allow for more varied input scenarios.
- Updated search queries to filter by both file name and title when a keyword is provided, improving search accuracy.
- Added support for filtering by URL and HTML file types in search queries, enhancing the flexibility of the search functionality.
- Refactored query construction for file types to streamline the inclusion of additional conditions, ensuring robust handling of various file types.
- Updated the searchChunks method to calculate and include the total chunk count for each knowledge ID in the results.
- Introduced logic to fetch chunk counts based on unique knowledge IDs, improving the efficiency of data retrieval.
- Enhanced error handling for chunk count fetching, ensuring robust logging in case of failures.
- Updated Elasticsearch repository methods to use ID fields without the ".keyword" suffix, aligning with the new index mapping requirements.
- Enhanced documentation for the VectorEmbedding struct to clarify expected index mapping and usage guidelines for ID fields.
- Ensured consistency across all repository methods that interact with ID fields, improving query performance and maintainability.
- Updated the CreateKnowledgeFromFile function to include a new optional `channel` parameter, allowing for better tracking of knowledge entry sources.
- Enhanced documentation to reflect the addition of the channel parameter, improving clarity for future developers.
- Introduced a new `channel` field in the Knowledge struct and associated request types to track the source channel (e.g., "web", "api", "browser_extension").
- Updated various frontend components to display channel information and enhance user experience with channel labels.
- Enhanced localization files to support channel labels in English and Chinese.
- Modified backend services and database migrations to accommodate the new channel feature, ensuring consistent tracking across knowledge entries.
- Refactored related functions to integrate channel handling, improving overall knowledge management and context.