Commit Graph

955 Commits

Author SHA1 Message Date
wizardchen 39816f2756 feat(security): add validation for file path to prevent path traversal attacks
- Implemented a check to reject file paths containing "..", enhancing security against path traversal vulnerabilities in the file serving functionality.
2026-03-25 22:08:29 +08:00
wizardchen b2c009e61c feat(security): implement SSRF and path traversal protections in image handling and file downloads
- Added SSRF protection by stripping client-supplied URL and Caption fields from image attachments in the QA request handler.
- Introduced a validation function to ensure Feishu API path parameters contain only safe characters, preventing path traversal attacks.
- Enhanced the WeCom webhook adapter to reject internal/private URLs unless they are on an allowlist, improving security during file downloads.
- Implemented a mechanism to bypass SSRF checks for trusted IM platform API hosts.
2026-03-25 22:08:29 +08:00
wizardchen 052be53c42 feat(prompts): update assistant descriptions and add intent-specific templates
- 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.
2026-03-25 22:08:29 +08:00
wizardchen 109393dd16 fix(server): reduce kill delay and implement port retry mechanism
- Changed the kill delay from 30 seconds to 2 seconds in the configuration.
- Refactored the server startup process to include a retry mechanism for binding to the port, addressing potential issues during hot-reload scenarios.
- Added a new function, listenWithRetry, to handle port binding with exponential backoff, improving server reliability during restarts.
2026-03-25 22:08:29 +08:00
wizardchen 0bb1a581de feat(agent): enhance token management and context handling in AgentEngine
- 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.
2026-03-25 22:08:29 +08:00
wizardchen 0d4ceb6c96 feat(image): enhance image resolution handling for data URIs and remote images
- Added functionality to resolve embedded data:image;base64 images in markdown, storing them and replacing references with stable URLs.
- Updated the knowledge service to process data URIs before handling remote images, ensuring all images are resolved consistently.
- Improved logging for resolved images, providing better insights during manual processing.
- Added unit tests to validate the new data URI resolution functionality and ensure reliability.
2026-03-25 22:08:29 +08:00
wizardchen 9650188a35 feat(chunk): add FindFAQChunkWithDuplicateQuestion method for enhanced duplicate question checking
- 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.
2026-03-25 22:08:29 +08:00
wizardchen 3a8bd36d8a feat(env): add SSRF whitelist configuration to .env.example and docker-compose.yml 2026-03-25 22:08:29 +08:00
wizardchen d7fd3b5eee feat(types): add language field to QuestionGenerationPayload for locale support 2026-03-25 22:08:29 +08:00
wizardchen 59d2f6b54c feat(graph): enhance graph extraction prompt rendering and language context handling
- Added a new method to render graph extraction prompts with shared placeholders for language.
- Updated entity and relationship extraction methods to utilize the new rendering function, improving prompt customization.
- Enhanced question generation task to include language context, ensuring prompts are generated in the correct language.
- Improved error handling for empty prompt configurations in question generation, enhancing robustness.
2026-03-25 22:08:29 +08:00
wizardchen 08ac3937ac fix(agent): update tool hint comment for clarity in UI progress display 2026-03-25 22:08:29 +08:00
wizardchen a167886aac chore(docker): update PostgreSQL image version to v0.22.2-pg17 in development and production configurations 2026-03-25 22:08:29 +08:00
wizardchen e138e0c81a refactor(agent): remove query display from DatabaseQuery component and update tool result structure
- Removed the query display section from the DatabaseQuery component to streamline the UI.
- Updated the DatabaseQueryData interface to eliminate the query field, reflecting changes in tool result handling.
- Enhanced the DatabaseQuery tool execution to focus on returning structured results without exposing raw SQL queries.
- Added a new utility to strip <think> blocks from LLM outputs, improving content clarity and user experience.
2026-03-25 22:08:29 +08:00
wizardchen 637376428e feat(agent): implement core agent functionalities and context management
- Introduced the AgentEngine with methods for executing tool calls, managing context windows, and handling final answer generation.
- Added functionality to stream LLM responses and tool results through the EventBus, enhancing real-time interaction.
- Implemented context management to consolidate messages and prevent exceeding token limits, ensuring efficient use of context.
- Enhanced error handling and logging for tool execution and response analysis, improving robustness and traceability.
- Added unit tests to validate the new functionalities and ensure reliability in agent operations.
2026-03-25 22:08:29 +08:00
wizardchen 2f7e3a8ac1 feat(agent): enhance tool execution and message sanitization
- Introduced a default timeout for tool execution to prevent indefinite hangs during long-running tasks.
- Implemented context cancellation handling in the execution loop to gracefully manage timeouts and user cancellations.
- Added a JSON repair utility to fix common malformations in tool arguments, improving robustness in argument parsing.
- Enhanced message sanitization to merge consecutive user messages and handle orphaned tool results, ensuring compatibility with LLM providers.
- Added unit tests for the new JSON repair and message sanitization functionalities to validate their effectiveness.
2026-03-25 22:08:29 +08:00
wizardchen 0851d6d656 feat(agent): implement memory consolidation and context management
- 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.
2026-03-25 22:08:29 +08:00
wizardchen 9f4fb39e10 feat(chat): introduce provider-specific request customizers and specs
- Added a new `ProviderSpec` struct to define provider-specific behaviors for chat completions.
- Implemented request and endpoint customizers for various providers including Qwen3, LKEAP, DeepSeek, and Generic.
- Refactored the `NewRemoteChat` function to utilize the new provider specs for customizing requests based on the provider and model name.
- Removed legacy chat implementations for LKEAP, NVIDIA, DeepSeek, and Qwen, consolidating their logic into the new structure.
2026-03-25 22:08:29 +08:00
wizardchen e936e0b347 feat(agent): implement LLM call timeout and transient error handling
- 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.
2026-03-25 22:08:29 +08:00
lyingbug 00ac14aabb fix: add LOAD_HISTORY to rag_stream pipeline for independent history
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.
2026-03-25 22:08:29 +08:00
lyingbug 03fda55261 fix(frontend): replace v-html with text interpolation in deepThink
Replace v-html + DOMPurify sanitization with plain Vue text
interpolation ({{ }}) and CSS white-space: pre-wrap for the
thinking content display.

The thinking content is raw model output that should never be
interpreted as HTML. Using v-html here created an unnecessary XSS
attack surface — even with DOMPurify, the \n→<br/> replacement
happened before sanitization, and future changes to sanitizer config
could introduce vulnerabilities.

Plain text rendering with pre-wrap:
- Eliminates XSS risk entirely (no HTML parsing)
- Preserves line breaks natively via CSS
- Removes the sanitizeHTML import and safeProcessThinkContent function
- Simpler code with identical visual output
2026-03-25 22:08:29 +08:00
lyingbug 34d711d15f fix(frontend): unify think tag parsing between stream and history
Two consistency fixes for <think> tag parsing in index.vue:

1. Streaming path (line 579): Changed indexOf to lastIndexOf when
   splitting thinking content from answer, matching the history
   loading path. Prevents incorrect splitting if </think> appears
   multiple times (e.g., model discusses think tags in answer).

2. History loading path (line 274-281): Removed redundant split()
   call, now uses only lastIndexOf consistently. The split was
   creating an unnecessary intermediate array that could produce
   wrong results with multiple </think> occurrences.

Both paths now use identical logic: lastIndexOf('</think>') to find
the boundary, substring(0, index) for thinkContent, substring(index+8)
for answer content.
2026-03-25 22:08:29 +08:00
lyingbug e5c46642e9 fix: handle thinking stream edge cases (unclosed tags + missing done)
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.
2026-03-25 22:08:29 +08:00
lyingbug 1c5013e559 fix: strip thinking content before indexing to chat history KB
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.
2026-03-25 22:08:29 +08:00
lyingbug cbee01f5e9 fix: improve markdown table cleaning and filter empty passages in rerank (#752)
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.
2026-03-25 22:08:29 +08:00
ochan.kwon b291381cc2 feat: auto-describe MCP tool result images via VLM
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
2026-03-25 21:38:15 +08:00
Manx98 9d2228a826 fix: upgrade marked dependency to version 17.0.5 to fix code block rendering 2026-03-25 21:25:54 +08:00
ochan.kwon 8d8cc051be fix(tenant): prevent api_key encryption loss on tenant settings update
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
2026-03-25 21:25:21 +08:00
Andy Yang be6e289bc9 fix: add missing common.saveSuccess and common.saveFailed i18n keys 2026-03-25 21:21:09 +08:00
Dounx 8df12aeee2 fix: make Milvus vector metric type configurable via MILVUS_METRIC_TYPE 2026-03-25 21:20:49 +08:00
ochan.kwon 5af8e4e9f8 feat(i18n): add missing locale keys and extract hardcoded Chinese strings
- Add 26 missing i18n keys to ko-KR and ru-RU for image upload,
  storage, VLM model, and multimodal features
- Add 7 new tool name keys (queryKnowledgeGraph, finalAnswer,
  readSkill, executeSkillScript, dataAnalysis, dataSchema,
  databaseQuery) to all 4 locales (zh-CN, en-US, ko-KR, ru-RU)
- Replace hardcoded Chinese tool name map (TOOL_NAME_DISPLAY) in
  AgentStreamDisplay with i18n key references via i18n.global.t(),
  merged into existing TOOL_NAME_KEYS
- Fix hardcoded Chinese error message in KnowledgeBase.vue to use
  existing i18n key knowledgeBase.fileExists
2026-03-25 21:20:05 +08:00
ChenRussell bfa78cc933 fix(rerank): filter empty passages to prevent Aliyun API error
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.
2026-03-25 21:19:40 +08:00
nullkey 804a17d58c docs(im): add Telegram and DingTalk platform documentation
- add setup guides for both WebSocket and Webhook modes
- document streaming reply mechanisms (editMessage / AI card)
- update architecture diagrams, data model, and config reference
2026-03-24 22:12:08 +08:00
nullkey 1bf6603271 feat(im): add AI card streaming for DingTalk and improve IM platform robustness
- 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
2026-03-24 22:12:08 +08:00
nullkey a1a384ec67 feat(im): add DingTalk platform integration
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.
2026-03-24 22:12:08 +08:00
nullkey aea0a97be3 feat(im): add Telegram platform integration
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.
2026-03-24 22:12:08 +08:00
Alex-wuhu f0c6d0752a feat(provider): add Novita AI as LLM provider
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
2026-03-24 22:10:42 +08:00
Andy Yang 62e6ae960f fix(chat): support reasoning content in streaming responses for vLLM models
- 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
2026-03-24 11:56:55 +08:00
ChenRussell 5b43d04d6b fix(frontend): reset page counter when reloading knowledge files
Reset the global page variable to 1 when reloading the file list after operations like tagging, uploading, moving, editing, or deleting documents. This fixes a pagination bug where scrolling would skip pages after performing these operations.
2026-03-24 11:52:39 +08:00
joeyczheng 4b0f2d4cc6 chore(client): remove redeclared UserInfo in client package
Signed-off-by: joeyczheng <joeyczheng@tencent.com>
2026-03-24 11:52:15 +08:00
qunbo.guo 4a39081d53 fix(chat): preserve image markdown during sanitize
Made-with: Cursor
2026-03-24 10:44:14 +08:00
lyingbug 28b3f1b9dd feat: friendly display for MCP tool names in frontend (#715)
- Format MCP tool names from "mcp_my_server_search_docs" to
  "My Server Search Docs" in the agent stream UI
- Apply same formatting in sanitizeForDisplay for inline text
- Update tool-icons.ts getToolDisplayName with MCP support
2026-03-21 10:22:05 +08:00
lyingbug da9f7b43b6 fix: use service name for MCP tool naming with collision protection (#715)
- 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).
2026-03-21 10:22:05 +08:00
lyingbug e3ab971430 fix: use service name instead of UUID for MCP tool naming (#715)
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.
2026-03-21 10:22:05 +08:00
lyingbug db16de084d fix: respect global default storage engine when creating knowledge base (#772)
Change default storageProvider in initFormData() from hardcoded 'local'
to empty string so KBStorageSettings.vue can apply the global config.
2026-03-21 10:21:49 +08:00
Dounx e11bd8c57d fix: use milvus result set length for empty search results 2026-03-20 18:22:40 +08:00
Andy Yang 5c31a9123f fix: Adjust temperature validation to allow zero as a valid setting and default only for negative values. 2026-03-20 18:21:39 +08:00
Dounx a4d3d69843 feat: expose builtin parser engine in settings 2026-03-20 15:52:33 +08:00
Dounx a9c2d61695 fix: add OpenRouter embedding provider support 2026-03-20 15:50:42 +08:00
Dounx cf9b935144 fix(dev): add milvus env and versioned docreader image 2026-03-20 15:50:16 +08:00
Dounx fc5c405639 feat(dev): add milvus service and db host config 2026-03-20 15:50:16 +08:00