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.
- Updated logging in the callLLMWithRetry function to summarize message details, limiting the output to the last few messages to avoid repetition.
- Introduced a constant to define the maximum number of detailed messages logged, improving the readability of logs during LLM calls.
- Introduced a new `channel` field in multiple request and message structures to track the source channel (e.g., "web", "api", "im").
- Updated frontend API calls and chat components to include the `channel` parameter, ensuring consistent channel tracking in user messages.
- Enhanced localization files to support channel labels in English, Korean, Russian, and Chinese.
- Added database migration scripts to incorporate the `channel` column in the messages table, facilitating the storage of channel information.
- Refactored related functions and components to accommodate the new channel feature, improving overall message context and tracking.
- Introduced a new ParallelToolCalls field in ChatOptions to control parallel execution of tool calls.
- Updated the BuildChatCompletionRequest method to handle the new ParallelToolCalls option, ensuring it is correctly propagated in requests.
- Enhanced the streamThinkingToEventBus function to utilize the ParallelToolCalls setting.
- Added comprehensive tests to validate the behavior of ParallelToolCalls in various scenarios, ensuring correct propagation and default handling.
- Introduced a new test file for MCPTool, covering various aspects such as name sanitization, name generation based on service and tool names, and description handling.
- Implemented tests to ensure consistent tool name generation across different UUIDs and validate the maximum length constraints for tool names.
- Added tests for tool registration behavior, ensuring that the first registered tool wins in case of name collisions.
- Enhanced parameter handling tests to verify schema retrieval and default behavior when no schema is provided.
- Improved the message consolidation logic to preserve the current turn's user query and all subsequent assistant/tool messages, ensuring better context retention.
- Updated the CompressContext function to reflect the new consolidation strategy, maintaining the system prompt and relevant recent messages.
- Refactored the context manager to support optional message repository for improved context rebuilding from persistent storage.
- Added comprehensive tests to validate the new consolidation behavior and ensure correct message handling across various scenarios.
- Implemented ClearKnowledgeBaseContents function in the Client to asynchronously delete all knowledge entries while preserving the knowledge base.
- Added corresponding ClearKnowledgeBaseContents handler in the KnowledgeHandler to validate access and enqueue deletion tasks.
- Updated router to include a new DELETE endpoint for clearing knowledge base contents.
- Added diagnostics for streaming events in the AgentEngine, including chunk counts and response type distributions.
- Implemented logging for emitted event types during the thinking process to aid in debugging and performance analysis.
- Updated the session handler to provide more informative warnings when fallback answers are emitted due to non-streaming behavior.
- Introduced a dedicated HTTP client for Ollama to improve connection handling and timeout management during streaming calls.
- Updated regex patterns in MarkdownImageUtil to support alt text containing brackets and handle MIME types with hyphens.
- Implemented new functions in ImageResolver for resolving HTML <img> tags with data URIs and bare base64 content, improving image handling in markdown.
- Added comprehensive tests for various image scenarios, ensuring robust handling of data URIs and base64 images.
- Modified the sortedKeys function to sort keys numerically when all keys are numeric strings, ensuring correct order for keys like "2" and "10".
- Updated the NeedsKBRetrieval method to include IntentSummarize as a valid case for knowledge base retrieval.
- Added a new test data file for chat import to support testing of document parsing and processing functionalities.
- Introduced Volcengine as a new provider in the chat provider specifications.
- Refactored the thinking configuration to a more generic format, applicable to both LKEAP and Volcengine.
- Updated request customizers to handle the new thinking configuration structure for both LKEAP and Volcengine providers.
- Introduced support for JSON file types in English, Korean, Russian, and Chinese locale files.
- Updated the file type acceptance criteria in the document upload component to include JSON.
- Enhanced the knowledge base parser settings to recognize JSON as a valid file type.
- Implemented JSON conversion functionality in the document parser, allowing for JSON content to be processed and converted to markdown.
- Added comprehensive tests for JSON to markdown conversion to ensure functionality and reliability.
- Updated regex patterns for table separator and row matching to use [ \t] instead of \s, preventing newline consumption across rows.
- Enhanced comments for clarity on the changes made to the regex expressions.
- Updated the merging process in the chat pipeline to include a new step for re-merging overlapping ranges introduced by context expansion.
- Implemented a new function, removePartialOverlaps, to eliminate chunks that are largely contained within higher-scored chunks, improving deduplication accuracy.
- Enhanced normalization and overlap checking utilities to support the new deduplication logic.
- Simplified model filtering logic by removing the deduplication function and directly filtering models based on type.
- Updated SSRF validation to preserve backend-managed fields when parameters are not provided by the frontend.
- Clarified comments and improved code readability in the ModelEditorDialog and ModelSettings components.
- Updated the page size from 100 to 1000 in the buildTagMap function to enhance performance and efficiency when retrieving tags from the knowledge base.
- Changed the tag retrieval process to support pagination, allowing for more efficient handling of large sets of tags.
- Adjusted the page size to 100 for better performance and reduced memory usage.
- Ensured that the function continues fetching tags until all are retrieved, improving the completeness of the tag map.
- Improved the CreateAgentEngine method by breaking down the process into distinct steps for better readability and maintainability.
- Added a new registerMCPTools method to streamline the registration of MCP tools based on the agent configuration.
- Enhanced error handling and logging for MCP service registration, ensuring clearer feedback during the process.
- Introduced resolveKBAndDocInfos to load knowledge base metadata and selected document information for prompt generation.