Add an opt-in human approval gate so Agent runs pause before executing
MCP tools that operators flag as dangerous, surface an approval card in
the chat UI, and only resume after the user approves (optionally with
edited args) or rejects.
Backend
- New mcp_tool_approvals table + repo/service to mark per-tool approval
required (PG migration 000042 + sqlite init).
- approval.Gate coordinates RequestAndWait / Resolve with sync.Once
delivery, configurable timeout, and Redis Pub/Sub fan-out so multi-
replica deployments work without sticky sessions.
- MCPTool.Execute integrates the gate; uses a round-level ApprovalCtx
(without the per-tool 60s timeout) for the wait, and re-derives a
fresh 60s exec ctx after approval so CallTool keeps a full window.
- New SSE response types (tool_approval_required / _resolved) and
EventBus events plumb approval state to AgentStreamDisplay.
- REST: list/set per-tool approval flag, resolve pending approval.
- Configurable via agent.tool_approval_timeout_seconds (yaml) or
WEKNORA_AGENT_TOOL_APPROVAL_TIMEOUT env (accepts seconds or Go
duration).
Frontend
- MCP settings: per-tool "require approval" switch on the test panel.
- Chat: ToolApprovalCard renders the pause point with editable JSON
args, validation feedback, mm:ss countdown that turns warning/danger
near deadline, and a resolved state that retains context.
- i18n strings added for zh-CN / en-US / ko-KR / ru-RU.
Docs
- docs/zh/mcp-approval.md covering behavior, config, API, deployment
considerations (Redis cross-instance, restart limitations).
Fixes O(n²) write amplification during wiki ingest on large KBs. Previously
every ingest/retract op re-wrote the single `slug='log'` row end-to-end and
every batch re-wrote the entire `slug='index'` directory markdown. On a 40k-
doc KB the log row grew to tens of MB and the index row to several MB, so
each batch triggered giant TOAST updates that dominated ingest wall time.
Log: new `wiki_log_entries` event table (`id DESC` indexed per KB) replaces
the single TEXT row. Batch ingest now collects entries and flushes them
once per batch via `AppendBatch`. Each entry stores `pages_affected` as
JSONB `[{slug,title}]` so the UI can render real titles; custom Scan falls
back to legacy `[]string` so older rows still deserialize.
Index: `wiki_pages[slug=index].content` keeps only the LLM-generated intro
(a few KB). The directory is now served by a structured paginated API
(`GetIndexView`) that reads `slug/title/summary` per type with cursor
pagination, so the agent and the frontend only pull the slice they need.
`RebuildIndexPage` degrades to a no-op; agent `wiki_read_page('index')`
synthesizes a small top-K overview and points callers at `wiki_search`.
Ingest resilience: LLM calls wrap with 3-attempt exponential backoff on
transient errors (5xx/408/429, transport resets/timeouts). Summary/extract
failures now bubble up so the batch's failed-op requeue path runs instead
of silently dropping the doc.
Frontend: sidebar Index/Log entries switch to dedicated views. Index view
streams intro → Summary → Entity → Concept → Synthesis → Comparison via
IntersectionObserver (with a nextTick re-check so small KBs still load
every section). Log view uses cursor pagination; pages_affected renders
titles with slug tooltip.
- new migration: migrations/versioned/000040_wiki_log_entries.{up,down}.sql
- tests: log repo pagination + legacy Scan, ListByTypeLight windowing,
renderIndexOverviewForAgent output, isTransientLLMError classifier
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
resolveFileServiceForKnowledge was reading os.Getenv("LOCAL_STORAGE_BASE_DIR")
on every request. This causes a mismatch when the variable is not in the
process environment at request time (e.g. it was set programmatically before
app startup but not exported, or the DI-constructed fileService uses a
different configured path).
Fix: store the value in a new localBaseDir field at NewDataAnalysisTool
construction time — the same moment the DI container assembles the local
FileService — and use t.localBaseDir in resolveFileServiceForKnowledge
instead. This guarantees the data-analysis tool always resolves files
under the same base directory that the local FileService was configured
with, eliminating the "path not found" errors when LOCAL storage is used
for a knowledge base while the global storage backend is minio/oss/cos.
Fixes#1040
The outer if/else in Execute claimed to prefer chatModel (LLM-based
reranking), but both branches called rerankResults which internally
prefers rerankModel first. This made the outer branching dead code
with a misleading comment.
Consolidate into a single branch that delegates entirely to
rerankResults, whose actual priority is: rerankModel → chatModel → none.
Dev-mode repro from the issue reporter's logs:
[Tool][DataAnalysis] Failed to create table from Excel: IO Error:
GDAL Error (4): Failed to open file
'local://10000/.../1777030910246871000.xlsx': No such file or directory
The local file service returns a custom 'local://' URL from GetFileURL,
which the duckdb spatial/excel extensions can't resolve (they expect
plain paths or http(s)/s3:// style URIs). Presigned HTTPS URLs from
cloud backends worked by accident; the 'local://' dev path has always
been broken for the Data Analysis tool.
Instead of per-scheme adapters, stream the file through
FileService.GetFile into a temp file and hand DuckDB the resulting
filesystem path. This works uniformly across every backend (local,
OSS, S3, MinIO, COS) and survives future scheme changes without any
changes to the Data Analysis tool.
- Preserve the original file extension on the temp file so DuckDB's
format auto-detection (csv / xlsx / xls) still kicks in.
- Clean up the temp file when LoadFromKnowledge returns, including on
every error branch. Cleanup is idempotent (double-invoke safe).
- New tests stub FileService to lock in that (a) we never leak a
provider:// URL to DuckDB, (b) GetFile errors propagate, (c) the
extension survives case normalization.
Refs: https://github.com/Tencent/WeKnora/issues/1007
Catching up on a real-world check: when a multi-sheet .xlsx fixture is
fed through LoadFromExcel against an in-memory DuckDB with the spatial
and excel extensions, the first iteration's sheet enumeration quietly
fell back because st_read_meta doesn't expose a scalar 'layer_name'
column — it returns a LIST<STRUCT> column called 'layers'. We now
UNNEST(layers).name so enumeration actually works, and assert the full
data path with three DuckDB-backed tests:
- multi-sheet workbook yields the sum of all rows and per-sheet
breakdown via __sheet_name (including schema drift: columns only
present in one sheet are NULL for the other)
- single-sheet workbook still works and tags rows with its sheet name
- sheet name containing a single quote (Q1'24) survives the SQL
literal round-trip
excelize/v2 is added as a test-time helper to build the fixtures
deterministically. If DuckDB's spatial/excel extensions can't be
installed (offline CI), the tests skip rather than fail.
Refs: https://github.com/Tencent/WeKnora/issues/1007
DuckDB's st_read (spatial) only reads the first layer/sheet of a .xlsx
workbook, so every sheet beyond Sheet1 was silently dropped from the
DuckDB table the Data Analysis tool builds. Users trying to analyse
multi-sheet workbooks could only see the first sheet.
Switch to DuckDB's dedicated 'excel' extension (read_xlsx) for the
actual data load, enumerate sheets via the spatial extension's
st_read_meta, and UNION ALL BY NAME the rows of every sheet into one
table. A synthetic __sheet_name column records the source so the LLM
can still filter/aggregate per sheet; schema drift between sheets is
tolerated via UNION BY NAME. If enumeration fails (older DuckDB, local
filesystem errors, …) we fall back to reading the first sheet so the
tool stays usable.
- Install & LOAD the 'excel' extension alongside 'spatial' both at
startup (internal/container) and in the offline prefetch binary
(cmd/download/duckdb).
- Harden sheet/path handling against single quotes.
- Update the tool description so the agent knows about __sheet_name.
- Add unit tests for the CREATE TABLE SQL builder covering 0 / 1 / N
sheets and quote escaping.
Refs: https://github.com/Tencent/WeKnora/issues/1007
The agent loop previously kept running when the LLM emitted final_answer with
malformed JSON arguments: observe.analyzeResponse strictly json.Unmarshal'd the
raw args and returned isDone=false on failure, while act.runToolCall separately
repaired the JSON and executed the tool. The mismatch made final_answer
non-terminal, so the LLM saw its own answer in the next round's tool result
and re-emitted final_answer, surfacing near-identical answers multiple times
to the user (issue #1008).
Fix by unifying parsing in a new tools.ParseFinalAnswerArgs helper with three
fallbacks (strict -> RepairJSON -> regex extraction) and making final_answer
always terminal in analyzeResponse. When no answer can be recovered, emit a
user-visible fallback message and a Done=true event so the UI still resolves.
Also route final_answer.Execute through the same helper so tool execution and
loop termination stay consistent.
Adds regression tests in observe_test.go and final_answer_test.go covering
valid args, RepairJSON recovery, unrecoverable args, and garbage input.
Refs: Tencent/WeKnora#1008
- Introduced a unified capability requirements system for agent tools, ensuring consistent filtering of knowledge bases based on their capabilities.
- Implemented derived `kb_filter` logic to streamline compatibility checks between agent tools and knowledge bases, reducing redundancy in configuration.
- Updated frontend components to reflect new filtering logic, including improved handling of empty states and user feedback when no compatible knowledge bases are available.
- Enhanced internationalization support by adding relevant messages for tool compatibility issues across multiple languages.
- Changed `kb_selection_mode` in agent type presets from "selected" to "all" to allow agents to access all knowledge bases by default.
- Revised prompt templates to clarify the handling of bound knowledge bases, replacing the `{{knowledge_bases}}` placeholder with a reference to the `<bound_knowledge_bases>` block in the user message's `<runtime_context>`.
- Enhanced internal logic to ensure that only searchable knowledge bases are considered during retrieval, improving the efficiency of knowledge searches.
- Added new functions for better formatting and handling of knowledge base metadata in the runtime context.
- Updated documentation and comments for clarity on the changes made to knowledge base interactions.
- Updated the agent system prompt to emphasize the use of regex for chunk searches, improving retrieval accuracy and efficiency.
- Introduced a new `Capabilities` field in the `KnowledgeBaseInfo` struct to define the retrieval surfaces available for each knowledge base, guiding the agent's strategy selection.
- Enhanced the `grep_chunks` tool to support regex queries, allowing for more flexible and powerful text pattern matching in knowledge base chunks.
- Improved JSON handling in the `RepairJSON` function to address invalid escape sequences, particularly for regex patterns, ensuring robust parsing and error handling.
- Updated documentation and comments across various files to clarify usage and expectations for regex and knowledge base capabilities.
These changes significantly enhance the agent's ability to retrieve relevant information while ensuring the integrity of input data handling.
- Improved the `getKbIdForWiki` function to better handle multiple knowledge bases associated with a single slug, ensuring the most recent tool call's mapping is prioritized.
- Updated the `buildRuntimeContextBlock` function to include active knowledge bases and pinned documents, providing a clearer context for multi-turn interactions and preventing prompt injection.
- Added `registerLinkedSlugs` function to track outbound and inbound links for wiki pages, facilitating better resolution of slugs in the frontend without additional requests.
These enhancements significantly improve the accuracy and safety of knowledge base retrieval and context management in the agent system.
- Added the `isStructuralPage` function to identify wiki-level structural/meta pages (index, log) that should not be filtered by knowledge IDs.
- Updated the `pageIntersectsKnowledgeIDs` function to incorporate logic for structural pages, ensuring they are always accessible regardless of filtering.
- Enhanced the handling of pages with no SourceRefs to allow them through the filter, improving the accuracy of content retrieval.
These changes enhance the filtering logic for wiki pages, ensuring that essential structural pages remain accessible while refining the overall content management process.
- Added the WikiScope struct to define the retrieval scope for wiki knowledge bases, allowing for optional filtering by specific document IDs.
- Implemented NewWikiScopesFromKBIDs constructor for easier creation of WikiScope instances.
- Enhanced the wikiReadPageTool and wikiSearchTool to utilize WikiScope, improving the handling of knowledge base IDs and document filtering during page retrieval.
- Updated the agent service to carry document whitelists into the wiki scopes, ensuring that only relevant pages are surfaced based on user mentions.
These changes significantly improve the flexibility and accuracy of wiki page retrieval, enhancing the overall user experience when interacting with wiki content.
- Modified the XML output structure in the wikiReadPageTool to replace title and slug elements with a unified link format, enhancing clarity and consistency in the representation of wiki pages.
- Adjusted the wikiSearchTool to align with the new output format, ensuring that search results maintain the same structure for better integration and usability.
These changes streamline the output format for wiki pages, contributing to a more coherent and user-friendly experience when accessing wiki content.
- Updated the chat component to include a new class for handling sidebar collapse, improving layout responsiveness.
- Enhanced the wiki page retrieval logic to support multiple knowledge bases for the same slug, allowing for more comprehensive results.
- Introduced a mechanism to track ambiguous slugs across knowledge bases, improving clarity in search results.
These changes significantly improve the user experience in the chat interface and enhance the functionality of the wiki page retrieval system.
- Updated the agent system prompt to require wiki-links in citations, improving user navigation to source pages.
- Implemented logic in AgentStreamDisplay to handle wiki link clicks and keyboard interactions, facilitating seamless navigation to knowledge base wiki pages.
- Enhanced WikiBrowser to auto-select pages based on query parameters, improving user experience when accessing specific wiki content.
- Added localization support for new error messages related to knowledge base identification, ensuring clarity in user interactions.
These changes significantly improve the usability and functionality of the wiki navigation system, providing users with a more intuitive experience when accessing and citing wiki content.
- Introduced `enrichChunkImageInfo` function to populate image information for text chunks by retrieving data from child chunks, ensuring that image-related content is not lost during processing.
- Updated `reconstructContent` to `reconstructEnrichedContent`, allowing for the inclusion of OCR text and captions from images, improving the quality of content sent to the LLM.
- Added `writeDedupItemXML` and `xmlEscape` functions to format entity and concept entries as structured XML, enhancing clarity and preventing nonsensical merges in deduplication prompts.
- Refined the `deduplicateExtractedBatch` method to utilize the new XML formatting for better output consistency.
These changes significantly improve the handling of image data and the overall clarity of deduplication prompts, contributing to a more effective wiki content management system.
- Added new tools for wiki page editing, including writing, replacing text, renaming, and deleting pages, with corresponding data structures for each action.
- Enhanced the frontend with a new `WikiEditResult` component to display results of wiki edits, supporting multiple languages for improved accessibility.
- Updated localization files for English and Chinese to include new strings related to wiki actions.
- Modified existing tools to return structured data for wiki actions, improving the clarity and usability of the output messages.
These changes significantly enhance the wiki editing capabilities, providing users with a more robust and user-friendly experience when managing wiki content.
- Updated the agent system prompt to refine the workflow for fixing issues, emphasizing the need to verify if issues still exist before making edits.
- Introduced a new `embeddedMode` prop in the frontend components to manage UI behavior based on the context of use.
- Simplified issue fix prompts in multiple languages for clarity, ensuring users receive concise instructions for resolving issues.
- Enhanced the WikiBrowser component to improve the display of issues and actions, including updated icons and streamlined interaction elements.
These changes significantly improve the user experience and functionality of the Wiki Fixer agent, fostering more efficient issue resolution and content management.
- Added a new built-in agent, "Wiki Fixer," designed to repair and optimize Wiki pages based on linter issues, with multilingual support for enhanced accessibility.
- Implemented a corresponding system prompt detailing the agent's role, mission, and workflow for effective issue resolution.
- Introduced new API functions for listing and updating wiki issues, allowing for better management of content conflicts and errors.
- Enhanced the frontend with new UI elements to display pending issues and facilitate auto-fixing, improving user interaction with the Wiki content.
These changes significantly enhance the agent's capabilities for maintaining the accuracy and quality of Wiki pages, fostering a more reliable knowledge base.
- Added a new tool, `wiki_flag_issue`, enabling users to report factual errors, mixed entities, or outdated information on wiki pages.
- Updated the agent system prompt and tool definitions to include the new tool, enhancing the agent's capabilities for maintaining wiki accuracy.
- Implemented backend functionality for creating, listing, and updating the status of flagged issues, ensuring effective tracking and resolution.
These changes significantly improve the agent's ability to manage and report issues within the wiki, fostering a more reliable knowledge base.
- Added a new tool, `wiki_read_source_doc`, allowing agents to access specific source documents for detailed information retrieval when wiki page content is insufficient.
- Updated the agent system prompt and tool definitions to incorporate the new tool, enhancing the agent's capabilities for in-depth knowledge extraction.
- Modified existing tools to support the new functionality, ensuring seamless integration within the agent's workflow.
These changes significantly improve the agent's ability to provide accurate and detailed responses by leveraging source documents alongside wiki content.
- Updated the agent system prompt to clarify the workflow for knowledge retrieval, emphasizing the use of `wiki_search` and `wiki_read_page` tools for specific queries and general overviews.
- Modified the `wikiReadPageTool` to support reading multiple wiki pages simultaneously, improving efficiency in fetching content.
- Enhanced the `wikiSearchTool` to utilize PostgreSQL POSIX regular expressions for more effective search queries, allowing for complex pattern matching.
- Adjusted the `wikiPageRepository` to replace `ILIKE` with regex matching for search queries, increasing the precision of search results.
These changes significantly improve the agent's ability to retrieve and synthesize information from the wiki, enhancing user interactions and response accuracy.
- Introduced a new built-in agent, "Wiki Researcher," designed for navigating and answering questions based on Wiki knowledge bases, complete with multilingual support.
- Added a corresponding system prompt that outlines the agent's role, mission, and workflow for effective knowledge graph traversal.
- Updated the agent configuration to include specific tools and parameters tailored for the Wiki Researcher, enhancing its functionality and user interaction.
- Removed deprecated wiki tools from the agent service to streamline the toolset and improve performance.
These changes significantly enhance the capabilities of the agent system, providing users with a specialized tool for in-depth research and information retrieval from Wiki sources.
This commit introduces the complete wiki feature for WeKnora, enabling AI-powered wiki page generation and management. The implementation includes:
**Backend Changes:**
- Wiki data model: WikiPage type with support for multiple page types (Summary, Entity, Concept, Index, Log)
- Database schema: wiki_pages table with full migration support
- WikiPageService: CRUD operations and page management
- WikiPageRepository: GORM-based persistence layer
- Wiki ingest pipeline: Automated generation of wiki pages from knowledge documents
* Summary page generation using LLM
* Entity and concept extraction in a single LLM call
* Synthesis opportunity detection
* Index page rebuilding
* Log page maintenance
- Wiki boost feature: Enhance chat retrieval with wiki context
- Wiki linting: Maintenance and validation utilities
- Agent wiki tools: Enable agents to query and interact with wiki pages
- Wiki prompts: Comprehensive LLM prompt templates for all wiki generation tasks
- Language support: Reuse existing middleware language infrastructure for LLM prompts
**Frontend Changes:**
- Wiki browser UI: View all wiki pages with filtering and search
- Wiki API client: Knowledge base wiki management endpoints
- Knowledge base editor: Configure wiki settings (language, auto-ingest, synthesis model)
- i18n updates: Support for English, Korean, Russian, and Chinese interfaces
**Configuration:**
- Container DI: Wire up all wiki services
- Router: Register wiki API endpoints
- Task handling: Support async wiki ingest tasks
**Testing:**
- Unit tests for wiki page types
- Service layer tests
- Endpoint tests for wiki operations
- Integration tests with LLM mocking
**Documentation:**
- Language refactoring analysis and guides
- Implementation completion reports
- Quick reference guides for developers
**Key Features:**
✅ LLM-powered wiki page generation from documents
✅ Multi-language support (9+ languages)
✅ Automatic extraction of entities and concepts
✅ Synthesis opportunity detection
✅ Index and log page maintenance
✅ Progressive wiki building across multiple documents
✅ Agent-based wiki interaction
✅ Chat retrieval enhancement with wiki context
✅ Full frontend UI for wiki browsing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
limit and offset are optional parameters with default values (limit=20,
offset=0). Marking them as required in the JSON Schema forces LLM clients
to always supply them, breaking calls that rely on the defaults.
Fixes#1003
- Updated the formatKnowledgeBaseList function to return knowledge base information as XML, improving data structure for integration.
- Modified the formatOutput function in GrepChunksTool to format search results as XML, enhancing readability and consistency.
- Adjusted the formatOutput method in KnowledgeSearchTool to output search results in XML format, providing a structured response.
- Refactored the buildOutput function in ListKnowledgeChunksTool to generate XML output, improving the clarity of chunk information.
These changes standardize output formats across multiple tools, facilitating better data handling and integration.
- Keep strict mode blocking all direct IPs (IPv4 and IPv6 uniformly)
- Unify all SSRF call sites to use ValidateURLForSSRF (whitelist-aware)
- Add Teredo (2001:0000::/32) and 6to4 (2002::/16) tunnel detection
- Make redirect handler and DNS pinning respect SSRF_WHITELIST
- Unexport isSSRFSafeURL to prevent future callers bypassing whitelist
- Add scheme validation for whitelisted redirect targets
- Document IPv6 whitelist syntax in .env.example
- Add comprehensive IPv6 test coverage
- 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.
- Added a reconnection retry mechanism for MCP tool calls and tool listing operations to handle stale connections.
- Enhanced error logging to provide clearer feedback during reconnection attempts.
- Updated comments for clarity on the retry behavior and connection management.
- Updated DatabaseQueryTool to accept search targets during initialization.
- Implemented search scope filtering in SQL validation to restrict queries to specified knowledge bases and documents.
- Enhanced the SQL validation process to include new filtering options for improved security and query accuracy.
- 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 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.
- 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.
- 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.
- 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.
- 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.
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
- 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.
- 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.
- 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.
wizardchen