Introduce the VectorStore domain model as a foundation for multi-store
vector DB architecture (Phase 1, PR 1/4).
- VectorStore entity with ConnectionConfig (AES-GCM encrypted) and IndexConfig
- VectorStoreRepository interface and GORM implementation (CRUD + duplicate check)
- PostgreSQL migration (000031) and SQLite migration (000001)
- Unit tests for types, encryption, validation, and helpers
- Define notionPage, notionBlock, notionParent, notionFile and cursor types
- Implement rate-limited HTTP client with context-aware retry and backoff
- Support search, page/block retrieval, database queries, and file downloads
- Add HasChildren field to Resource type, NotionChannel to knowledge types
- Add unit tests for types and client
- Added ASR configuration options to the knowledge base and model settings.
- Implemented ASR model selection and transcription capabilities in the knowledge processing pipeline.
- Enhanced file upload support to include audio formats for ASR processing.
- Updated localization files to include ASR-related labels and descriptions.
- Refactored model handling to accommodate ASR as a new model type.
Previously, only the original uploaded file was deleted via knowledge.FilePath.
Images extracted by the builtin parser (stored as individual S3/MinIO/local files
via ImageResolver) were never cleaned up, causing orphan files to accumulate.
- Add ListImageInfoByKnowledgeIDs repository method (no chunk_type filter)
- Add collectImageURLs utility with URL deduplication and JSON parse logging
- Add deleteExtractedImages helper (standalone, best-effort with error logging)
- Fix DeleteKnowledge: collect image URLs before errgroup, delete in file goroutine
- Fix DeleteKnowledgeList: bulk collect with KB-level fileSvc mapping
- Fix cleanupKnowledgeResources: collect before chunk deletion, delete after
- Fix ProcessKBDelete: collect before chunk deletion for KB-wide cleanup
- Add DefaultLanguage() that reads WEKNORA_LANGUAGE env with zh-CN fallback
- Replace hardcoded zh-CN in LanguageNameFromContext with DefaultLanguage()
- Unify middleware/language.go to use types.DefaultLanguage()
- Add Language field to DocumentProcessPayload (8 enqueue sites + worker restore)
- Add Language field to ImageMultimodalPayload (enqueue + worker restore)
- Propagate language from ImageMultimodalPayload to QuestionGenerationPayload
- Updated UpdateKnowledgeTagBatch method to include an authorizedKBID parameter for restricting updates to specific knowledge items.
- Implemented validation to ensure that all requested knowledge IDs belong to the authorized knowledge base.
- Enhanced GetKnowledgeBatch and UpdateKnowledgeTagBatch methods to incorporate agent-specific knowledge base access restrictions.
- Added utility functions to resolve allowed knowledge base IDs for agents based on their configuration.
- Updated relevant files to include provider registration, implementation, and metadata.
- Enhanced frontend components to support provider management and configuration.
- Added localization for new provider settings and messages.
- Implemented backend repository methods for CRUD operations on web search providers.
- 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.
- 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 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
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
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- Updated the page size from 100 to 1000 in the buildTagMap function to enhance performance and efficiency when retrieving tags from the knowledge base.
- Added support for SO_REUSEPORT in the listenWithRetry function to improve port binding during hot-reloads.
- Implemented graceful shutdown by closing the listener immediately upon receiving a shutdown signal, allowing for quicker port release.
- Updated logging to provide clearer feedback during server shutdown and error handling.
- Updated the assistant descriptions in various prompt templates to specify that they are developed by Tencent.
- Added new intent-specific system prompt templates for greeting, chitchat, follow-up, image analysis, summarization, and web search unavailability scenarios.
- Enhanced citation rules in the system prompts to ensure proper inline citation formatting.
- Refactored the rewrite prompt to classify user intent more accurately and output structured JSON responses.
- Added token usage tracking to the AgentEngine, allowing for better estimation of current context token counts.
- Implemented a new method to estimate current tokens based on previous usage and newly appended messages, improving context management.
- Updated context window management to utilize estimated token counts for more efficient message consolidation.
- Enhanced streaming methods to include token usage information, providing better insights into LLM interactions.
- Refactored the token estimator to support BPE tokenization, ensuring accurate token counts for messages.
- Added unit tests to validate new token estimation and context management functionalities.
- Implemented a new method in the chunk repository to find FAQ chunks with overlapping standard or similar questions.
- Updated the knowledge service to utilize this method for checking duplicates during FAQ question creation.
- Improved error handling for duplicate questions, providing clearer feedback on conflicts.
- Introduced a memory consolidator to summarize older messages when the context window exceeds a specified limit, preserving key facts and tool results.
- Enhanced the AgentEngine to utilize the new token estimator and memory consolidator for improved context window management.
- Implemented logic to compress message history when approaching token limits, ensuring efficient use of context.
- Added unit tests for the memory consolidator and token estimator to validate functionality and performance.
- Updated tool execution to validate parameters against JSON schema before execution, improving error handling and robustness.
- 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.
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
Add Novita AI as a new model provider supporting chat, embedding,
and VLLM model types via OpenAI-compatible API endpoint.
- Add NovitaProvider implementation with OpenAI-compatible API
- Register ProviderNovita in provider registry
- Add ModelSourceNovita constant
- Add Novita to frontend fallback provider options
- Add i18n translations for en-US, zh-CN, ru-RU, ko-KR
- Use service.Name instead of service.ID (UUID) for stable tool names
across MCP server reconnections
- Add (tenant_id, name) unique index on MCPService to prevent name
collisions at the DB level
- Add collision detection logging in RegisterMCPTools for defense-in-depth
- Improve truncation logic to prioritize keeping the tool name intact
Security: first-wins policy in ToolRegistry + unique name constraint
prevents tool hijacking (GHSA-67q9-58vj-32qx).
- 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.
- 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.
liweixin