- 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.
- Add DingTalk AI Card streaming support with create/deliver/update via OpenAPI
- Extract shared think-block rendering into reusable im.TransformThinkBlocks
- Add stream orphan reaper and edit throttling for DingTalk and Telegram
- Apply think-block transform on all reply paths (DingTalk, Telegram, Feishu)
- Add Card Template ID config to frontend IM channel panel with i18n
Add DingTalk bot adapter supporting both webhook (HmacSHA256 signature
verification) and Stream mode (via official dingtalk-stream-sdk-go),
with sessionWebhook/OpenAPI reply fallback and AccessToken caching.
Add Telegram Bot API adapter supporting both webhook and long-polling
modes with streaming replies via editMessageText, file download via
getFile API, and timing-safe secret token verification.
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
- Parse reasoning field together with standard stream response using local struct
- Unify reasoning content extraction from standard and vLLM response paths
- Adapt processStreamDelta to accept reasoning content as a separate parameter
- Send reasoning content as thinking response in the stream when available
- Ensure compatibility with existing SDK logic by constructing standard choice object
- 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).
When an MCP server re-registers after long idle, a new UUID is generated,
causing tool names to change and agent tool calls to fail. Switch from
t.service.ID to t.service.Name so tool names remain stable across
re-registrations.
- Wire slash-command registry into Service and HandleMessage dispatch
- Add bounded QA worker pool (qaQueue) with per-user backpressure
- Add sliding-window rate limiter to prevent message abuse
- Support /stop cancellation for queued and in-flight QA requests
- Fix WeCom group chat replies via appchat API with user fallback
- Fix WeCom longconn nil map panic and stream buffer memory leak
- Add Feishu stream reaper to clean orphaned streams (memory leak fix)
- Show "正在思考..." placeholder during Feishu streaming
- Handle empty-stream fallback when no visible content is produced
- Derive WebSearchEnabled from agent config for IM channels
Introduce a pluggable command framework for IM channels. Includes
Command interface, CommandRegistry for registration and dispatch,
and five built-in commands: /help (list commands), /info (inspect
knowledge bases), /search (search knowledge), /stop (cancel running
QA), and /clear (reset conversation context).
- Updated the AgentEngine to emit final answer events even when the LLM stops without calling the final_answer tool, ensuring the frontend can render responses correctly.
- Added fallback logic in the AgentStreamHandler to emit final answers as fallback events when no answer events are streamed, improving robustness in edge cases.
- 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.
- Removed the validation for a maximum of 10 knowledge IDs in GetDocumentInfoTool to allow more flexibility.
- Adjusted pagination settings in chunk retrieval to limit results to 1 per request for more granular control.
- Updated the searchChunks method to use case-insensitive matching based on the database type, improving compatibility across different systems.
- Enhanced query structure for better readability and maintainability.
- Updated the message streaming logic to handle <think> blocks more effectively, ensuring proper formatting for Feishu.
- Introduced a new transformThinkBlocks function to convert <think> content into Feishu-compatible markdown blockquotes.
- Improved the handling of tool call events to prevent duplicate processing and ensure correct message formatting.
- Enhanced documentation for permission configuration in the IM channel setup.
- Updated formatToolCallStart and formatToolCallResult functions to return plain-text lines instead of Markdown snippets for better integration within <think> blocks.
- Introduced briefToolSummary function to extract concise summaries from tool output.
- Enhanced handleMessageStream to manage <think> blocks more effectively during agent interactions.
- Added handling for server-side events in WeCom long connection management to improve reconnection logic.
- 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 critical language rules to fallback response templates to ensure consistent language usage in responses.
- Updated logger context to include language and session-related keys for improved context management.
- 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.
Add specific error handling for 'Endpoint url cannot have fully qualified paths'
to guide users to remove http:// or https:// prefix from endpoint URL."
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>
- Introduced MessageContentPart and ImageURL types to allow for multi-content messages that can include both text and images.
- Updated the Message struct to include a MultiContent field for handling multiple message parts.
- Modified the ConvertMessages function to prioritize processing of multi-content messages, improving the handling of user messages with images.
These changes enhance the flexibility and functionality of chat messages, enabling richer content delivery.
- 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.
- Introduced a new IMChannelPanel component for managing WeCom and Feishu channels.
- Added CRUD operations for IM channels, including create, update, delete, and list functionalities.
- Enhanced the backend with new API endpoints for IM channel management.
- Updated documentation to reflect changes in IM integration and channel management.
- Improved localization support for new IM-related UI elements across multiple languages.