* feat: support multi-tag for document knowledge
- Add knowledge_tag_relations join table for many-to-many tag-knowledge mapping
- Migrate existing single tag_id data to the new table
- Update Knowledge struct, filter, payload types (TagID -> Tags/TagIDs)
- Rewrite repository layer: SetKnowledgeTags, GetKnowledgeTags, ListIDsByTagIDs
- Update tag count references to query knowledge_tag_relations
- Update service/handler layers for multi-tag create/list/batch-update
- Frontend: multi-select tag sidebar, multi-tag chip display, tag toggle in popup
- FAQ tags remain single-tag model (unchanged)
* feat(knowledge): tag edit dialog with dynamic overflow and inline creation
- Add TagEditDialog component with search, multi-select, and confirm
- Replace inline t-popup tag selector with dialog-based editing
- Tags overflow with +N badge, visible count adapts to container width via ResizeObserver
- Date/card layout: fixed date width, tags flex to fill remaining space
- Add persistent new-tag input bar in dialog (Enter to create, auto-select)
- Tag creation emits callback to refresh parent tag list immediately
- Apply same overflow + dialog trigger to both card view and list view
- Add i18n keys: tagEditDialogTitle, tagEditSearch, tagSelectedCount, tagOverflowTip, tagNewPlaceholder
* fix: exclude soft-deleted knowledge from tag reference counts
CountReferences, BatchCountReferences, and DeleteUnusedTags now
JOIN with knowledges table to filter out soft-deleted records
when counting knowledge_tag_relations. Previously they queried
knowledge_tag_relations directly without the deleted_at check,
causing stale tag counts after knowledge deletion.
* fix: refresh tag counts after async knowledge deletion completes
Add a second delayed tag list refresh (2.5s) after tag deletion to capture
updated reference counts for remaining tags. The original immediate refresh
handles removing the deleted tag from the list, while this delayed refresh
ensures other tags' counts are correct after the async deletion finishes.
---------
Co-authored-by: lyingbug <xiayula2014@gmail.com>
Optimistically mark submitted documents as pending and poll until the worker
updates the backend, preventing a stale completed state after list reload.
Move batch reparse work to an asynq task to avoid HTTP timeouts, add i18n
for all locales, guard in-flight documents, and prevent concurrent delete/reparse.
This commit introduces the Batch Reparse feature for the Knowledge Base.
Users can now select multiple documents and trigger a re-parsing pipeline in batches, streamlining the recovery from parse failures.
Tighten shared-agent readiness checks, surface not-ready toasts in the
selector, validate chat-model overrides in resolveChatModelID, and
improve configure deep-links for shared agents.
Block chat when agents lack an explicit chat or rerank model, guide users
through the selector and editor with field highlight, and align session QA
checks with the same readiness rules on backend and frontend.
Let admins send real requests against configured chat, embedding, rerank,
VLM, and ASR models from settings, with thinking controls shown only when
the model supports them.
Add recent=true to knowledge search so the mention picker can list recent
files without a keyword, and consolidate KB/FAQ/file chip styling across
chat input and message history.
Add compact agent filter beside channel list titles with selected name
display, fix embed localStorage agentId read on rebind, add IM agent
rebind tests, and deep-link agent editor counts to the matching tab.
Map legacy section=integrations to tab=im instead of an invalid tab value,
and mount only the active IntegrationsModal tab to avoid duplicate API calls.
Move IM and web embed channel management into a dedicated sidebar entry,
remove the user-menu IM overview submenu, and show a lightweight publish
channel status row in the agent editor basic settings instead of full panels.
WPS embeds images in cells using =DISPIMG("ID",mode) which may appear as plain text prefixed with "_xlfn." when processed by openpyxl. These function strings pollute the RAG-indexed document content, causing incorrect AI recall.
Add a regex filter (_is_image_function) that detects _xlfn.DISPIMG(...) and _xlfn.IMAGE(...) patterns and excludes them during row processing in ExcelParser.parse_into_text().
Refs: https://github.com/Tencent/WeKnora/issues/1779
Return provider-specific diagnostics when connectivity tests return zero
results, including SearXNG unresponsive_engines details instead of a
misleading API key hint.
Replaced the WeCom SVG icon with a new design and updated the associated styles in the IMChannelPanel and SessionSourceFilter components to reflect the new color scheme. Adjusted layout properties for better responsiveness and visual consistency across the application.
Add agent complete wait timeout and answer fallbacks for cancel paths,
restore Telegram Markdown on finalize with plain-text retry, and show
answer-only final IM frames instead of the collapsed think summary.
Wait for agent complete without a short timeout, unify Telegram stream
parse mode, remove obsolete FinalAnswer handling, isolate per-section
newline tracking, add lifecycle tests, and update IM streaming docs.
Mirror Web AgentStreamDisplay/RagPipelineProgress in IM text streams:
retract live answers into 思考过程, show Web-aligned tool titles with
query/summary from structured data, and collapse thinking on finalize
instead of dropping it entirely.
Added a new SessionSourceFilter component to allow users to filter session lists by source, enhancing the user experience. The component integrates with existing session management features and includes logic for displaying web and channel sources. Additionally, utility functions for managing session source options and visibility conditions have been introduced, along with corresponding unit tests to ensure functionality.
Channel folder headers and nested session rows now share 13px type,
consistent icon sizing, and aligned indentation so the menu no longer
mixes oversized session titles with undersized folder labels.
Default unset agent thinking to explicit false so thinking_type models
receive disabled/enabled wire params. Render reasoning inside the quick-answer
pipeline timeline only when thinking events arrive, avoiding a flash of the
thinking step when thinking mode is off.
The runnable_by_viewer field was never populated for built-in agents,
so TenantRoleViewer users always hit 403 on agent-chat. Drop the field
and RBAC check so agent-chat matches knowledge-chat access for viewers.
Scope auth headers to feed fetches, use feed-scoped external IDs and
content-based incremental fingerprints, tolerate partial feed failures,
store feed URLs in settings, and fix credential configured detection.
Introduce a new feature allowing users to add custom HTTP headers for MCP requests. This includes:
- A user interface for adding and managing custom headers within the MCP service dialog.
- Localization support for custom headers in English, Korean, Russian, and Chinese.
- Updates to the form submission process to include custom headers, ensuring they are serialized correctly.
- Removal of warnings for ignored headers, as all headers are now captured in the custom headers editor.
This enhancement improves the flexibility and usability of the MCP service configuration.
Implement a new feature that allows users to import MCP service configurations via a standard JSON format. This includes:
- A toggle for importing from code with a user-friendly hint and placeholder.
- Error handling for various scenarios such as empty input, invalid JSON, and missing URLs.
- Toast notifications for successful imports and warnings about ignored headers.
- Updates to the MCP service dialog to support this new functionality, ensuring a seamless user experience during service creation and editing.
Support connecting to MCP servers that require OAuth2, with a Cursor-like
zero-config flow: the user provides only a URL and the system performs
metadata discovery, dynamic client registration (DCR), and the
authorization code flow with PKCE on first connect.
- Persist per-user access/refresh tokens and per-service DCR client
credentials, encrypted at rest (AES-256-GCM)
- Store the PKCE verifier/state during the flow via Redis with an
in-memory fallback for Lite mode
- Cache MCP clients per (service, user) so tokens stay user-isolated
- Add endpoints for authorize-url, callback, status, and token revoke;
the callback is allowlisted for unauthenticated access
- Surface a structured "authorization required" hint when a tool call
hits an unauthorized MCP service
- Frontend: add an auth-type selector with OAuth config, inline
authorization status/actions, and render the connection test result
inline in the editor drawer instead of a stacked centered dialog
Reset organizationsLoadedAt to 0 after orgStore.create() succeeds,
so that the subsequent fetchOrganizations() call from
handleSettingsSaved is not blocked by the 60-second TTL cache.
This ensures resource_counts and other aggregated fields are
refreshed immediately after creating a shared space.
When editing a data source whose tree loads one level at a time (Feishu
wiki), a saved deep-node selection was invisible: only top-level spaces
were listed, so the selected node could not be seen and its ancestor
space rendered as unchecked.
- Add Connector.ResolveResourceAncestors: given selected resource IDs,
return the ancestor IDs that must be expanded to reveal them. Feishu
walks up via GetWikiNode (O(depth) per selection, no full-tree walk);
Notion/Yuque return empty.
- Fix wikiNode.ParentNodeID JSON tag: the Feishu API field is
parent_node_token, not parent_node_id, so GetWikiNode can return the
parent and the ancestor walk works in production.
- Expose POST /datasource/{id}/resource-ancestors (service + handler +
route) and a matching frontend API client.
- Edit-mode picker reveals hidden selections by expanding and lazily
loading each ancestor level, so selections are visible and checked.
- Gate child fetching on treeFullyLoaded instead of a partial-children
heuristic, avoiding a redundant request for full-tree connectors.
Listing resources for a Feishu data source eagerly walked the entire wiki
tree (one API call per node across every space), which exceeded the request
timeout for large knowledge bases. ListResources now takes a parentID and
returns a single level at a time: empty lists the wiki spaces, a space/node
ID lists only its direct children. The frontend fetches children on demand
when a node is expanded. Notion (full tree in one call) and Yuque (flat)
keep their existing behavior by ignoring non-empty parentID.
Refs: https://github.com/Tencent/WeKnora/issues/1672
PaddleOCR-VL renders tables as HTML with per-cell text-align styles.
These waste tokens on layout markup and bypass the chunker's
table-protection logic (which only recognizes Markdown pipe tables),
causing large tables to be split mid-row.
Convert inline HTML <table> blocks to GFM Markdown tables when possible,
and strip presentational attributes (style/class/align/...) for tables
using rowspan/colspan that Markdown cannot express.
Refs: https://github.com/Tencent/WeKnora/issues/1725
GET with a JSON body was non-standard and confused integrators. Register
POST as the preferred method and keep GET for existing clients; update SDK,
MCP server, and API docs accordingly.
Refs: https://github.com/Tencent/WeKnora/issues/1727
- Add IM service dependency to CustomAgentHandler for managing agent-related IM channels.
- Implement DeleteChannelsByAgent method to stop and soft-delete IM channels associated with a custom agent upon its removal.
- Update ListChannelsByTenant to exclude soft-deleted custom agents, ensuring consistent overview lists after agent removal.
The angle-bracket image target parser declared a local variable named
`close`, which shadows Go's built-in `close` function and is flagged by
revive's redefines-builtin-id rule, breaking `make lint`. Rename it to
`closeIdx`.
- Introduce detailed descriptions for authentication, SSRF protection, tenant management, and async task worker settings in English, Korean, Russian, and Chinese localization files.
- Enhance user understanding of configuration options by providing context-sensitive help directly within the settings interface.
- Update the Settings and SystemSettings components to utilize these new descriptions for improved user experience.
DingTalk websocket (Stream) channels stopped delivering @-mentions after
a day or two and only recovered when the IM channel was toggled off/on.
The factory fired the SDK's Start once and relied entirely on the SDK's
internal auto-reconnect, with no liveness supervision on WeKnora's side.
On long-running connections the SDK can enter a zombie state where the
connection object stays alive but no longer receives messages, leaving no
way to recover automatically. The cancel func was also ineffective because
the SDK ignores the context after the initial dial, so stopping a channel
leaked the old connection.
Add a reusable RunSupervised helper that keeps a long connection alive and
proactively recycles it every 6h on top of the SDK's own reconnect, which
bounds the worst-case outage and clears stuck connections. Wire DingTalk to
it, add LongConnClient.Close (disables AutoReconnect before closing so the
SDK does not resurrect the connection), and make the cancel func actually
tear the connection down. Drop the now-unused stream client reference from
the adapter, which only sends replies via sessionWebhook or OpenAPI.
- Add dedicated MCP service configuration section in AgentEditorModal (agent mode only)
- Unify sidebar nav hover/active states across settings and editor modals
- Refine tool card and tag chip colors to use design tokens and color-mix
- Tighten suggested questions button padding and border-radius
- Update regex patterns to account for opening delimiters preceded by letters/numbers and followed by punctuation, ensuring proper rendering of emphasis in markdown.
- Add tests to validate new behavior for various edge cases, including punctuation-adjacent emphasis and exponent markers.
- Improve overall markdown rendering consistency in chat components.
Anky