Commit Graph

664 Commits

Author SHA1 Message Date
wizardchen 635d7c9643 feat(integrations): polish embed/IM channel editors and agent rebind
Align embed channel setup with a step wizard, simplify deploy layout,
and allow changing bound agents on update for embed and IM channels.
2026-06-24 20:09:19 +08:00
wizardchen 7855f36799 fix(model): block deletion when model is referenced by KB or agent
Reject model delete with HTTP 400 when the current tenant still has
knowledge bases or custom agents bound to the model ID.
2026-06-23 20:36:16 +08:00
wizardchen bc9ad3aca0 fix(qa): wire agent thinking toggle and show reasoning in RAG timeline
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.
2026-06-23 20:17:19 +08:00
wizardchen 35f717f7fa fix(datasource): optimize RSS incremental sync and surface partial failures
Skip article-page fetches when feed signals are unchanged, preserve sync
cursor across transient feed outages, and record partial multi-feed syncs.
2026-06-23 17:30:38 +08:00
wizardchen 11d461a4f7 fix(knowledgebase): delete data sources when knowledge base is removed
Stop cron schedules and cancel in-flight sync logs when a KB is deleted,
and skip datasource sync tasks if the target KB no longer exists.
2026-06-23 17:30:38 +08:00
wizardchen 3cb0e906a7 fix(datasource): harden RSS connector and editor UX after review
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.
2026-06-23 17:30:38 +08:00
langcaiye 3eb49da746 feat(retriever): configure Tencent VectorDB replicas via env 2026-06-22 20:21:25 +08:00
wizardchen 7f3f219f58 feat(mcp): add OAuth2 authorization for MCP services
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
2026-06-22 20:19:31 +08:00
wizardchen 5d0d317a36 feat(datasource): reveal pre-existing selections in lazily-loaded picker
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.
2026-06-22 19:24:08 +08:00
wizardchen d8f13ada4a fix(datasource): lazy-load Feishu wiki resources to avoid listing timeout (#1672)
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
2026-06-22 17:53:30 +08:00
wizardchen c3cd629da7 fix(tenant): purge memberships on delete and filter stale switcher rows
Cascade soft-delete tenant_members when a workspace is removed so the
tenant switcher no longer shows ghost entries as "#<id>". Also filter
orphaned memberships in /auth/me and switch to another workspace after
delete when one remains.
2026-06-17 10:31:53 +08:00
“jiangyijun” 6bc8e9ed49 fix(vectordb): 修复 question 数据复制到向量数据库的 ID 映射问题
主要改进:
1. CopyIndices 新增分页查询逻辑(每页500条),避免大批量数据查询失败
2. 修复 ID 字段优先级:优先使用 IndexInfo.ID,兜底使用 ChunkID
3. 新增 translateSourceID 函数,智能处理 question 类型数据的 SourceID 映射:
   - 当 SourceID == ChunkID 时,直接映射为目标 ChunkID
   - 当 SourceID 为 "ChunkID-QuestionID" 格式时,保留 QuestionID 部分
   - 其他情况使用 SHA256 生成稳定的映射 ID

影响范围:
- 修改文件:internal/application/repository/retriever/tencentvectordb/repository.go
- 新增函数:copySourceQueryParams、remapCopiedEmbeddings、translateSourceID
2026-06-17 05:08:50 +08:00
wizardchen 16363623ab feat(wiki): enhance anchored form popups and internationalization updates
Add new styles for anchored form popups in the wiki browser, improving the user interface for folder actions and confirmations. Update internationalization strings for move confirmation titles in English, Korean, Russian, and Chinese locales to enhance user experience across multiple languages. Refactor existing components to integrate the new popup styles and ensure consistent behavior.
2026-06-17 00:28:30 +08:00
wizardchen e76738d054 feat(wiki): implement folder management features in wiki API
Add new API functions for managing wiki folders, including creating, updating, deleting, and listing folders. Introduce a new WikiFolder interface to represent folder structure and enhance the WikiBrowser component with folder actions. Update internationalization strings for folder-related actions in English, Korean, Russian, and Chinese locales. Refactor existing code to accommodate folder hierarchy and improve user experience in the wiki browser.
2026-06-16 23:51:29 +08:00
wizardchen 83eeec0ddf feat(i18n): add optional embedding model descriptions for multiple locales
Enhance the internationalization support by adding optional descriptions for the embedding model in English, Korean, Russian, and Chinese. Update the UI to reflect these changes, ensuring users are informed about the optional nature of the embedding model when configuring knowledge base settings.
2026-06-16 23:51:29 +08:00
wizardchen 588f00b18a refactor(wiki): enhance taxonomy planning and streamline category handling
Revamp the wiki taxonomy planning process to assign coherent directory paths to entity/concept pages in a single pass, ensuring consistent reuse of existing folders. This change eliminates the need for per-page category assignments during the reduce phase, preserving user-curated categories.

Consolidate category path parsing and deduplication into a shared utility, improving consistency across the service and repository layers. Update related functions and tests to reflect these changes, ensuring efficient handling of category paths in the wiki ingestion process.
2026-06-16 20:26:06 +08:00
wizardchen 88c10da0b0 refactor(wiki): unify category cleaning and push directory listing to SQL
Centralize the wiki category-path normalization (separator/quote cleanup,
type-label stripping, dedup, depth cap) into a single types helper shared by
the service, repository, and taxonomy layers so stored and queried paths are
always cleaned identically and cannot drift.

Flatten category_path into fixed category_l1/l2/l3 columns (kept in sync on
write) and rewrite ListDistinctCategoryPathsByType to group, count, and
paginate directly in cross-dialect SQL, returning the page of child folders
plus the total distinct count. This removes the prior full-column scan and
in-memory pagination (whose maxPaths cap was effectively dead) and makes Total
and later pages correct.

Add the level columns + composite index to the wiki migrations and the repo
test schema, and cover the SQL grouping/counting/pagination with a new test.
2026-06-16 20:26:06 +08:00
wizardchen fe33db9493 feat(wiki): add page hierarchy/category metadata and retrieval APIs
Persist category and hierarchy metadata on wiki pages (new migration), expose
category-path retrieval and related repository/service/handler/router APIs, and
update wiki ingestion (batch, cite, taxonomy) plus agent wiki prompts to build
and consume the taxonomy. Regenerate swagger docs for the new endpoints.
2026-06-16 20:26:06 +08:00
langcaiye 0c3d45d3cd fix: mark knowledge delete failures after retry exhaustion 2026-06-16 16:47:46 +08:00
FFFFFFpy e21a5da422 feat: add EPUB and MHTML document support 2026-06-16 11:25:27 +08:00
wizardchen efe8b6f41d feat(agent): add tool result persistence trimming for large outputs
Introduce display_type-based output stripping for SSE/DB storage and
add knowledge_chunks_list display type for list_knowledge_chunks.
2026-06-16 01:09:23 +08:00
wizardchen de525a4f02 feat(observability): enhance Langfuse retrieve and rerank tracing
Add shared retrieval observation helpers, expand rerank generation output
with previews and score stats, and enrich retrieve/rerank pipeline spans.
2026-06-16 01:09:23 +08:00
wizardchen 9e916839ef feat(backend): add RAG pipeline progress events
Emit query-understanding and knowledge-search progress over SSE, emit
references before stream completion, and wire progress into session QA.
2026-06-16 01:09:07 +08:00
wizardchen 2906c6656e feat(backend): improve parent-child chunk merge and imageinfo matching
Scope image info to matched text children during parent resolution and
add range/URL filtering utilities with unit tests.
2026-06-16 01:09:07 +08:00
FFFFFFpy a997441392 fix(wiki): mask image URLs before LLM to prevent UUID/path corruption
Wiki summary/entity/concept/page-modify prompts instructed the LLM to
reproduce ![caption](url) verbatim, so high-entropy image URLs passed
through generation and got corrupted (dropped UUID segments, duplicated
or mangled path prefixes, even CJK chars inserted into the bucket name),
producing object keys that don't exist -> 404.

Mask all image URLs to opaque placeholders at the generateWithTemplate
chokepoint and deterministically rehydrate after generation; drop
corrupted/hallucinated placeholders so broken links never reach storage.
2026-06-15 17:27:56 +08:00
wizardchen ed9802ff2b feat(embed): add backend embed channels with auth and rate limiting (#1657)
Introduce embed_channels storage, publish-token and session-token auth,
origin allowlist enforcement, shared Redis rate limiter, public embed API
routes, webhooks with SSRF validation, and session listing by embed source.
2026-06-12 23:10:39 +08:00
langcaiye a0786b6fe7 fix(wiki): clear stale citation chunks on deletion 2026-06-12 23:08:20 +08:00
langcaiye 903b014992 fix(tcvdb): keep default replica number at one 2026-06-12 22:54:44 +08:00
langcaiye d07a62af06 fix(tcvdb): improve collection compatibility 2026-06-12 22:54:44 +08:00
nullkey 5851c64ba1 feat(im): IM session improvements — titles, in-flight recovery, classification
Three related improvements to the IM-session experience:

- Auto-generated titles: a new IM session starts untitled and gets a
  content-based title from its first message via the same GenerateTitleAsync
  flow web sessions use, instead of an identity title like "user · dm". Falls
  back to the identity title when the first message has no text. All platforms.

- In-flight reply recovery (web chat): opening a session whose reply is still
  being generated on an IM channel made the web client attach via
  continue-stream and fail (the IM answer never streams through this server),
  flashing a "stream failed" toast and forcing a manual refresh. Treat a failed
  attach to an IM reply (channel === 'im') as recoverable — poll until it
  completes, then reload the thread; on timeout surface the standard error.
  Web/api replies keep the original behaviour, untouched.

- Source-filter classification: the sidebar filter treats "web" as sessions
  with no IM mapping, but the list join excluded soft-deleted mappings, so
  /clear'd IM sessions leaked into the user's own web chats. Include soft-deleted
  mappings so a session ever bound to an IM channel stays under its platform.
  Adds a repository regression test.
2026-06-12 17:01:28 +08:00
Yeongpil Yoon c6fc315042 fix(chat): preserve provider tool-call metadata 2026-06-09 20:55:20 +08:00
wizardchen 2aadd61fcc feat: implement reparse functionality with process configuration support
- Enhanced the `reparseKnowledge` function to accept optional process configuration overrides, allowing users to adjust parsing settings during reparse operations.
- Updated the frontend components to integrate reparse capabilities, including the `UploadConfirmDialog` and `KnowledgeBase` views, providing a user-friendly interface for confirming reparse actions.
- Added new localization strings for reparse confirmation and process configuration details in multiple languages.
- Modified the backend API to handle reparse requests with optional configuration, ensuring proper validation and persistence of overrides.
- Introduced new types and interfaces to manage reparse-specific data structures in the store, improving type safety and clarity in the codebase.
2026-06-09 20:38:24 +08:00
wizardchen d8a26f7c23 refactor: remove enable_multimodal and adjust parent-child configuration
- Removed the `enable_multimodal` field from the `ChunkingConfigOverride` interface and related components to streamline configuration.
- Updated the logic in `UploadConfirmDialog.vue` to default `enableParentChild` to false when initializing from knowledge base info.
- Modified the `mergeChunkingConfig` function to ensure that `EnableParentChild` is authoritative, allowing explicit control over its state.
- Added a new test case in `knowledge_process_config_test.go` to verify the behavior of parent-child toggles in process configuration resolution.
2026-06-09 20:38:24 +08:00
wizardchen 76dc23226d fix: correct graph_enabled logic in process configuration
- Updated the logic for `graph_enabled` in `UploadConfirmDialog.vue` to require both `nodeExtractConfig.enabled` and `graphEnabled` to be true.
- Added a new test case in `knowledge_process_config_test.go` to ensure that `GraphEnabled` is false when `ExtractConfig.Enabled` is false.
- Adjusted the `ResolveProcessConfig` function to reflect the updated dependency between graph and extract configurations, ensuring proper behavior in the process configuration resolution.
2026-06-09 20:38:24 +08:00
wizardchen ed9e780c8c feat(client): enhance knowledge file upload with process configuration support
- Updated the `CreateKnowledgeFromFile` function to accept an optional `processConfig` parameter for per-upload parse configuration overrides.
- Introduced the `KnowledgeProcessOverrides` type to define various parsing settings, including parser engine rules and chunking configurations.
- Modified the API client and related components to handle the new process configuration, improving flexibility in knowledge file uploads.
- Updated documentation and API specifications to reflect the new `process_config` parameter in the upload process.
- Added a new `UploadConfirmHost` component to facilitate user confirmation for uploads, integrating with the updated upload logic.
- Enhanced user experience by providing detailed configuration options during the upload process.
2026-06-09 20:38:24 +08:00
wizardchen 1778c5ac7b refactor(tracing): remove Jaeger integration and related components
This commit removes Jaeger tracing support from the project, including the associated Docker configurations, Go modules, and middleware. The changes simplify the codebase by eliminating unused tracing functionality, which was previously integrated for observability. Documentation and scripts have also been updated to reflect the removal of Jaeger references.
2026-06-08 21:01:04 +08:00
langcaiye 9e898ae72c fix(schema): expand knowledge source length 2026-06-05 15:12:25 +08:00
ochan.kwon db7baad84c fix: reject cross-store reuse_vectors knowledge move
Moving knowledge with mode=reuse_vectors copies vector index entries
directly between knowledge bases, which only works when both KBs are
bound to the same vector store (CopyIndices is routed through the source
store). Nothing rejected a cross-store reuse_vectors move, so it would
copy target-KB rows into the source store and then delete the source
indices — corrupting vector data. The move endpoint validated only the
embedding model, and ListMoveTargets surfaces same-model KBs regardless
of their store binding, so a cross-store target is reachable.

Reject reuse_vectors moves whose source and target KBs are bound to
different vector stores:

- MoveKnowledge handler: synchronous 400 before enqueueing, with a
  message pointing the caller at reparse mode.
- moveOneKnowledge: re-check before marking the knowledge as processing,
  so a rejected move leaves it untouched rather than stranded.
- moveKnowledgeReuseVectors: a top-of-function guard as defense in depth
  for any directly enqueued task, satisfying the pre-existing contract
  noted in the comment ("callers must reject cross-store moves").

reparse mode is unaffected: it re-indexes into the target store from
scratch and is the supported way to move across stores.
2026-06-05 15:00:41 +08:00
wizardchen 063809896a refactor(chat): improve handling of <think> tags in chat messages
- Updated logic to manage <think> and </think> tags in chat message content, ensuring accurate representation of thinking states.
- Introduced a new function to handle the closing of thinking events, enhancing clarity and reducing redundancy in event emissions.
- Adjusted event handling for reasoning content to support historical message reconstruction, improving user experience during chat interactions.
2026-06-05 14:56:48 +08:00
langcaiye ba8c96d83a fix(datasource): fail sync when all fetched items fail 2026-06-04 17:39:55 +08:00
lyingbug 4369d156e1 Revert "fix: preserve agent system prompt for greetings"
This reverts commit b22303cec8.
2026-06-04 17:39:38 +08:00
wolfkill b22303cec8 fix: preserve agent system prompt for greetings 2026-06-04 17:39:01 +08:00
wizardchen 035093dc35 feat(configuration): update asynq concurrency settings and enhance FAQ handling
- Increased the default worker pool size for the asynq server from 16 to 32 to improve performance during concurrent uploads.
- Updated the .env.example and docker-compose.yml files to reflect the new default concurrency setting.
- Enhanced the handling of FAQ entries in the tool results, ensuring distinct identification through standard questions, improving user experience and clarity in the output.
- Refactored related components to utilize the new FAQ attributes, ensuring consistent display and interaction across the application.
2026-06-04 15:48:04 +08:00
wizardchen d38a6efd87 refactor(agent): remove final_answer tool references and update related logic
- Eliminated all instances of the final_answer tool from the agent's configuration and logic, transitioning to a model where the agent concludes responses with plain text instead.
- Updated event handling and response analysis to reflect this change, ensuring that the agent's output is now directly delivered as text without relying on a dedicated final answer tool.
- Adjusted localization strings across multiple languages to remove references to final_answer, enhancing clarity and consistency in user-facing messages.
- Improved the overall structure of the agent's response handling to streamline the process and reduce potential confusion regarding tool usage.

refactor(agent): streamline answer handling and preamble logic

- Updated the agent's response handling to treat any text streamed before a tool call as a preamble, ensuring it is not included in the final answer.
- Removed the superseded marker logic from the event emission process, simplifying the flow of answer content and enhancing clarity in the UI.
- Adjusted the event handling to ensure that preamble segments are correctly retracted and relocated into the steps tree, improving the overall user experience.
- Enhanced the agent's internal logic to better manage answer segments and their states during streaming, leading to a more coherent response structure.
2026-06-04 15:48:04 +08:00
wizardchen 0c45cc07df feat(knowledge): refactor retrieval parameters for multi-KB search
- Updated the `resolveStoreGroups` and `buildRetrievalParams` functions to handle multiple knowledge bases more effectively.
- Changed the structure of `buckets` to store pointers to `KnowledgeBase` objects instead of just IDs, allowing for richer data handling.
- Enhanced the retrieval parameter construction to differentiate between FAQ and document-type knowledge bases, ensuring correct routing for vector and keyword retrieval.
- Improved comments for clarity on the logic behind retrieval parameter construction based on knowledge base types.
2026-06-04 15:48:04 +08:00
wizardchen b6337cd970 fix(session): handle user-requested stop events gracefully in QA execution
- Updated the QA execution logic to differentiate between user-requested cancellations and actual errors, preventing unnecessary error events from being emitted when a stop is requested.
- Enhanced logging to provide clear feedback when a QA session is cancelled by the user, improving the user experience and reducing confusion.
- Added context cancellation checks to ensure proper handling of stopped generation scenarios, maintaining the integrity of the session flow.
2026-06-04 15:48:04 +08:00
ochan.kwon 7b2bc8a6b8 fix: validate vector store connection addresses against SSRF policy
Vector store create and raw connection-test accepted user-supplied
connection addresses without SSRF validation, while every other
admin-entered endpoint (e.g. model BaseURL) already runs
ValidateURLForSSRF. An admin could point an engine address at an
internal host and use the connection probe as an SSRF oracle.

Add validateConnectionAddrSSRF, applied at the two user-input
boundaries only:

- CreateStore: validated before any network dial.
- TestStoreRaw: a new TestRawConnection wrapper runs an engine-type
  allowlist, required-field validation, and SSRF validation before
  delegating to TestConnection. TestConnection stays validation-free
  for trusted callers (env stores, stored configs already validated
  at create time).

Validation covers every address-bearing field a driver dials
(Addr, qdrant Host+Port, weaviate Host and GrpcAddress) and
fails closed for unmapped engine types. The Elasticsearch probe no
longer follows redirects, closing a 302-to-internal bypass.

docker-compose whitelists the bundled vector-store service hostnames
(qdrant, milvus, weaviate, doris-fe) via SSRF_WHITELIST_EXTRA so the
out-of-box experience is preserved; postgres is intentionally not
whitelisted. .env.example and the OpenSearch dev guide document how
to whitelist external or local-dev addresses.
2026-06-04 15:26:56 +08:00
ochan.kwon e9980c6011 fix: deep-copy stored files and images when cloning a knowledge base
Cloning a knowledge base previously copied only the storage path strings
(knowledge.FilePath and chunk.ImageInfo.URL), so the source and the clone
shared the same physical objects in the storage backend. Once the original
file and extracted images are deleted on source removal, the clone is left
with dangling references and its document and images become unreadable —
data loss that occurs even for same-store clones.

Add a CopyFile primitive to the FileService interface and implement it in
every backend: server-side CopyObject on the object stores
(s3/obs/cos/oss/tos/ks3/minio), io.Copy on local, and a no-op on dummy.
Destinations use the knowledge-owned layout and reuse the existing
path/object-key guards; a sentinel ErrCrossBackendCopy is returned when the
source scheme does not match the backend.

Use CopyFile to deep-copy the document file in cloneKnowledge and the
extracted images in CloneChunk and cloneFAQKnowledgeBase via a shared
cloneChunkImageInfo helper that deduplicates identical image URLs per clone
and rewrites them to the new objects. Copied objects are cleaned up
best-effort if a clone fails partway through. A clone-time preflight rejects
cloning into a target bound to a different storage backend when the tenant
pins providers via StorageEngineConfig.

Adds unit tests for local CopyFile (independent copy survives source
deletion, traversal rejection, cross-backend rejection), cloneChunkImageInfo
(empty/multi/dedup/parse-failure/OriginalURL handling), and the storage
provider preflight.
2026-06-03 14:45:59 +08:00
wizardchen ef1047bf67 feat(parser): add OpenDataLoader, PaddleOCR-VL engines, and parser improvements
Introduce opendataloader and PaddleOCR-VL parser engines with tenant-level
settings UI, replace liteparse, and harden Excel/PPT/Markdown parsing.
Optional odl-hybrid sidecar stays local-build only and is excluded from
default dev-start and full profiles.
2026-06-03 12:29:13 +08:00
wizardchen 7b1bb1054f feat(docreader): speed up scanned-PDF parsing, stream image results, isolate heavy async queues
Large scanned PDFs (hundreds of pages) were slow and fragile end-to-end.
This change addresses the parse, transport, and task-scheduling layers:

docreader (parse + transport):
- Parallelize per-page scanned rendering across processes (forkserver/fork),
  with serial fallback. ~4-7x faster on large scanned PDFs; pdfium is not
  thread-safe so we fan out across processes. Configurable via
  DOCREADER_PDF_RENDER_PARALLELISM.
- Add server-streaming ReadStream RPC: emit one meta frame then one frame per
  image, so documents with many page images are no longer capped by the unary
  gRPC message-size limit (a 874-page PDF produced ~193MiB of images, far over
  the 50MB cap) and memory is bounded on both ends. Unary Read is kept for
  backward compatibility; the Go production reader switches to ReadStream.

VLM:
- Make the VLM HTTP timeout configurable (VLM_HTTP_TIMEOUT_SECONDS) and raise
  the default 90s -> 180s so dense scanned-page OCR does not time out with
  "context deadline exceeded".

Async task queues:
- Isolate high-volume, model-heavy fan-out tasks into dedicated asynq queues so
  a single large document cannot saturate the shared worker pool and block
  user-facing document parsing:
    image:multimodal  -> "multimodal"
    chunk:extract     -> "graph"
    question:generation -> "question"
- Register the new queues in the server weight map and the cancel inspector's
  scanned-queue set (so cancelling a knowledge still purges its pending tasks).
2026-06-03 12:29:13 +08:00