- Introduced a configurable LLM call timeout with a default value, allowing for better control over LLM call durations.
- Added logic to retry transient errors (e.g., timeouts, rate limits) up to a specified maximum number of retries, improving robustness in error handling.
- Implemented parameter casting for tool arguments to ensure correct types are used, addressing common LLM quirks.
- Enhanced tool execution error messages with guidance for retrying with different approaches.
- Added validation for configuration values to prevent runtime errors.
Previously, rag_stream relied entirely on the rewrite plugin's
internal loadHistory() to load conversation history. This meant that
when rewrite was disabled (enable_rewrite=false), RAG mode had NO
conversation history at all — multi-turn conversations silently
degraded to single-turn.
Changes:
1. Add LOAD_HISTORY as the first step in rag_stream pipeline,
ensuring history is always available regardless of rewrite config.
2. Make rewrite plugin reuse chatManage.History if already populated
by the upstream LOAD_HISTORY step, avoiding duplicate DB queries.
This brings rag_stream in line with chat_history_stream which already
has LOAD_HISTORY as an independent step.
Two related fixes for thinking mode streaming:
1. chat_completion_stream.go: When the response channel closes
unexpectedly (context cancelled, upstream error) while thinking
is in progress, the <think> tag was left unclosed. This caused
the stored message to have an incomplete tag, making the frontend
show a perpetual "thinking..." state on history reload.
Now we emit a closing </think> tag when the channel ends with
thinkingStarted=true but thinkingEnded=false.
2. remote_api.go: The thinking Done=true event was only sent when
the first answer content chunk arrived. If the model produced
only reasoning with no answer (e.g., finish_reason set with
empty content), the thinking-done signal was never emitted.
Now we also check isDone && state.hasThinking at the end of
processStreamDelta to ensure the done event is always sent.
The assistant message content may contain <think>...</think> tags from
extended thinking mode. Previously this raw thinking content was
indexed into the chat history knowledge base, polluting embeddings
and degrading RAG retrieval quality with intermediate reasoning text.
Now we strip thinking blocks before building the passage for
IndexMessageToKB, consistent with how load_history and rewrite
plugins already strip thinking from conversation history.
Enhanced cleanPassageForRerank() to convert markdown table data rows
(| col1 | col2 |) into plain text ("col1, col2") instead of leaving
them intact. Added filtering to skip empty/whitespace-only passages
before sending to the rerank API, preventing Baidu Qianfan 400 errors
caused by empty document fragments after markdown cleaning.
When an MCP tool returns image content items, the agent engine now
automatically generates text descriptions using the configured VLM
model and appends them to the tool result message. This makes image
content accessible to LLMs that receive tool results as text.
Images are not passed directly to the LLM because Chat Completions API
does not reliably support images in tool role messages across providers
(tested: gpt-5.4 silently ignores them, Qwen3.5 processes them).
Changes:
- Add Images field to ToolResult for preserving base64 data URIs
- Add extractContentAndImages() with MIME whitelist, size/count limits
- Add ImageDescriberFunc injection to AgentEngine (no vlm package dep)
- Add describeImages() with graceful error handling and ctx cancellation
- Add VLM model injection in CreateAgentEngine (same pattern as
SetAppConfig/SetSkillsManager)
- Redact image base64 from Data map to prevent log/SSE exposure
When a tenant setting is updated via PUT /tenants/kv/{key} (e.g.,
retrieval-config, parser-engine-config), the GORM AfterFind-decrypted
plaintext api_key was silently written back to the database because
db.Updates() does not trigger the BeforeSave hook.
Guard the repository's UpdateTenant to skip writing plaintext api_key
back to the database. Pre-encrypted values (enc:v1:… from CreateTenant
/ UpdateAPIKey) are written as-is; AfterFind-decrypted plaintext is
blanked so GORM skips the column entirely.
Closes#798
Aliyun rerank API rejects empty documents with error "document index:X
should not be empty". This fix validates passage content before building
the documents array, skipping empty chunks and logging them for data
quality monitoring.
- Updated DeleteChunks method to split IDs into batches of 5000 to prevent MySQL Error 1390.
- Added unit tests for CalculateFAQContentHash to ensure consistent hashing behavior across various scenarios, including normalization and case sensitivity.
- Enhanced the SummaryGenerationPayload struct to include a Language field for better localization.
- Updated enqueueSummaryGenerationTask and ProcessSummaryGeneration methods to handle language context in summary generation tasks.
- Modified the session title generation template to focus on extracting only the intent of the user's question.
- Enhanced the session service to include language context when generating titles.
- Updated middleware to inject language into the request context.
- Added a new test suite for validating SSRF safety of URLs.
- Added timezone and language settings to the environment configuration.
- Introduced built-in agent configurations with multilingual support for various agents.
- Updated Docker Compose to utilize new environment variables for timezone and language.
- Created new prompt templates for question generation, summary generation, and keywords extraction.
Table-driven tests for sanitizeManualDownloadFilename covering normal titles,
each dangerous character replacement (/ \ " \n \r), blank/whitespace-only
titles falling back to "untitled.md", and safe passthrough of = ; characters.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Use mime.FormatMediaType for both attachment and inline Content-Disposition
headers in DownloadKnowledgeFile and the preview handler, preventing header
injection via a user-controlled knowledge title (e.g. containing ';' or '=')
- Extract inline sanitize logic into sanitizeManualDownloadFilename helper and
add a blank/whitespace-only title fallback to "untitled" so the download
never produces a degenerate ".md" filename
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add an early-return branch that streams manual knowledge content
(stored as Markdown in Metadata.content) directly as a .md file,
avoiding the runtime error that occurred when FilePath is empty.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Removed outdated instructions regarding the `skip_kb_search` field in the conversation configuration.
- Clarified requirements for `image_description` to ensure it is non-empty when images are present.
- Adjusted the handling of message parts in the chat pipeline to improve image processing.
- Deleted unused migration files related to image handling in the database schema.
These changes enhance the clarity and functionality of the conversation and image processing logic.
- Added blur handling for the textarea in the Input-field component to prevent errors when navigating away from the component.
- Improved the sanitization process in the AgentStreamDisplay component to preserve specific tags during markdown processing, ensuring accurate content display.
- Introduced new methods for handling FAQ-specific post-processing in the knowledge base service, optimizing retrieval and filtering of search results.
These changes enhance user experience by improving input handling and content rendering in the chat interface.
- Introduced a new `QARequest` type to streamline parameters for KnowledgeQA and AgentQA service calls, replacing multiple parameters with a single structured request.
- Updated the `KnowledgeQA` and `AgentQA` methods in the session service interface to accept the new `QARequest` type, enhancing clarity and maintainability.
- Refactored the request parsing logic to utilize the new `buildQARequest` method, improving code organization and reducing redundancy.
- Implemented a new `resolveAgent` method to simplify custom agent resolution logic, enhancing readability and maintainability.
These changes improve the overall structure and usability of the QA request handling, facilitating easier updates and better code organization.
- Introduced a new parameter `webSearchEnabled` to the `AgentQA` method, allowing for conditional web search capabilities.
- Updated the session service interface and handler to accommodate the new parameter, enhancing the flexibility of the AgentQA process.
- Adjusted the configuration to ensure that web search functionality can be toggled based on the provided input.
These changes improve the AgentQA feature by enabling users to control web search integration, enhancing the overall user experience.
- Introduced a new method to resolve embedding model IDs to their actual identity keys (name + endpoint), enabling optimal grouping of knowledge bases across different tenants.
- Updated the concurrent search functionality to utilize the resolved model keys, improving the efficiency of query embedding computations.
- Refactored search target grouping to reduce redundant API calls and enhance performance during hybrid searches.
These changes significantly improve the knowledge search process by ensuring that embeddings are computed efficiently and reused across multiple knowledge bases sharing the same underlying model.
- Enhanced the concurrent search functionality to group search targets by their embedding model, allowing for a single computation of query embeddings per model.
- Implemented batch fetching of knowledge base records to improve efficiency and reduce redundant API calls.
- Updated the HybridSearch method to support multiple knowledge base IDs, enabling combined retrieval for full-KB targets and improving overall search performance.
- Added a new GetQueryEmbedding method to compute embeddings for queries, facilitating reuse across multiple knowledge bases sharing the same model.
These changes significantly enhance the performance and efficiency of the knowledge search process, reducing API calls and improving response times.
- Implemented a new API endpoint to clear all messages in a session, enhancing session management capabilities.
- Updated the frontend to include a clear messages option in the session menu, allowing users to easily remove chat history.
- Added localization support for the new feature in English, Korean, Russian, and Chinese, improving accessibility for a broader audience.
- Enhanced the chat view to handle session message clearing events, ensuring a responsive user experience.
These changes significantly improve the user experience by providing a straightforward method to manage session messages effectively.
- Refactored the chat model ID selection process to prioritize the request's summaryModelID, followed by the custom agent's ModelID, and finally a fallback to the default model selection.
- Improved logging to provide clearer insights into which model ID is being used during the selection process.
- Removed the deprecated selectChatModelIDWithOverride function to streamline the codebase and enhance maintainability.
These changes improve the flexibility and clarity of chat model selection, ensuring a more robust session management experience.
- Added support for updating the description field in knowledge records, improving the detail and context of knowledge entries.
- Refactored knowledge base update logic to ensure configuration updates are only applied when provided, enhancing robustness and preventing unnecessary overwrites.
- Modified the request structure to make the configuration field optional, allowing for more flexible updates.
These changes improve the knowledge management system by allowing for more comprehensive updates and better handling of configuration data.
- Updated configuration to support three tasks in the assistant's prompt: rewriting questions, classifying intent for knowledge base retrieval, and analyzing attached images.
- Implemented backend functionality to update image descriptions in user messages, ensuring that image context is preserved across conversation history.
- Modified session handling to return complete session data after updates, improving the accuracy of session information provided to users.
- Enhanced the chat pipeline to include detailed image descriptions and manage image captions effectively, enriching user interactions with visual content.
These improvements significantly enhance the application's multimodal capabilities, providing a more robust and user-friendly experience when handling image-based queries.
- Updated configuration to improve handling of multimodal queries, including clearer guidelines for when to use [NO_SEARCH] in responses.
- Enhanced the user interface to include dedicated sections for multimodal configuration, allowing users to manage image uploads and related settings more effectively.
- Added localization support for new multimodal features in both English and Chinese, improving accessibility for a broader audience.
- Implemented backend changes to support image analysis and extraction of OCR text, enriching the interaction experience for users.
These enhancements significantly improve the application's capability to process and respond to multimodal queries, fostering a more interactive and user-friendly environment.
- Added functionality for image uploads in chat, allowing users to attach images for multimodal Q&A.
- Enhanced the input field to handle image selection via drag-and-drop and paste, with validation for file types and sizes.
- Updated the backend to process images alongside text queries, including support for image analysis.
- Introduced new UI components for image previews and management, improving user interaction with uploaded content.
- Added localization strings for image upload features and error messages, enhancing accessibility for users in multiple languages.
These changes significantly improve the chat experience by enabling users to incorporate images into their queries, facilitating richer interactions and responses.
- Updated the summary length requirement for document summarization to 100-300 words.
- Added new localization strings for missing storage engine notifications in English, Korean, Russian, and Chinese.
- Implemented UI warnings for users regarding storage engine configuration when files exist, including confirmation dialogs for storage engine changes.
- Enhanced backend validation to ensure a storage engine is configured before allowing content uploads.
These changes improve user experience by providing clearer guidance on storage engine requirements and enhancing the overall functionality of the knowledge base management system.
- Added API endpoints for moving knowledge items between knowledge bases, including validation for source and target compatibility.
- Implemented asynchronous task handling for knowledge moves, tracking progress and status updates.
- Introduced new localization strings for move-related UI elements in English, Korean, Russian, and Chinese.
- Enhanced the frontend to support knowledge move operations, including target selection and progress monitoring.
These changes significantly improve the application's capabilities for managing knowledge across different bases, providing users with a seamless experience in organizing their knowledge assets.
- Revised the storage size calculation logic for Milvus, Qdrant, and Weaviate repositories to provide more accurate estimates based on the actual data structure and indexing methods.
- Updated comments to clarify the relationship between vector dimensions and index storage requirements, enhancing code readability and maintainability.
- Added new API endpoints for managing chat history configuration and retrieval settings, allowing tenants to enable message indexing and configure search parameters.
- Introduced new Vue components for ChatHistorySettings and RetrievalSettings, providing a user-friendly interface for managing these configurations.
- Updated localization files to include new settings descriptions and labels in multiple languages.
- Enhanced the KnowledgeSearch view to support searching across both knowledge bases and chat history, improving the overall search functionality.
These changes significantly enhance the application's capabilities in managing and retrieving chat history, contributing to a more robust user experience.
- Introduced the final_answer tool to ensure agents submit their complete responses as the last action, improving response accuracy and consistency.
- Updated the agent engine to log detailed information about tool calls and responses, including the total duration of agent execution.
- Enhanced the chat message model to include agent_duration_ms, tracking the total execution time from query start to answer delivery.
- Implemented JSON field extraction for streaming responses, allowing for more efficient handling of tool call outputs.
These changes significantly improve the agent's response handling and ensure that final answers are consistently delivered, enhancing overall user experience.
- Add crypto utility (internal/utils/crypto.go) with AES-256-GCM encrypt/decrypt
using SYSTEM_AES_KEY env var, with "enc:v1:" prefix for versioned ciphertext
- Encrypt tenant API key via GORM BeforeSave/AfterFind hooks and manual
encryption in CreateTenant/UpdateAPIKey (db.Updates bypasses hooks)
- Encrypt model API key in ModelParameters Value/Scan (driver.Valuer)
- Widen api_key column from varchar(64) to varchar(256) across all DB dialects
(MySQL, ParadeDB, SQLite) and add versioned migration 000018
- Propagate SYSTEM_AES_KEY through docker-compose, Helm secrets and values
- Fix migration 000017 PL/pgSQL dollar-quoting syntax ($ -> $$)
Convert all LLM-facing prompts, templates, and tool output labels to
language-neutral English so the model responds in the user's input
language. Update frontend relevance/match-type mappings to match.
Output language strategy:
- User-facing: reply in user's input language
- Vector-indexed: match source document language
- LLM-internal: fixed English
- Implemented ListChunksByParentIDs in chunkRepository to retrieve chunks based on multiple parent IDs, improving data retrieval efficiency.
- Enhanced the chunk merging logic in PluginMerge to better handle overlapping chunks and collect merged ImageInfo for parent chunks.
- Updated the ChunkRepository interface to include the new ListChunksByParentIDs method, ensuring consistency across the application.
These changes optimize chunk management and improve the handling of image information during merges, enhancing overall application functionality.
wizardchen