Commit Graph

1188 Commits

Author SHA1 Message Date
wizardchen 8d40959f88 fix lint and test failures 2026-07-01 17:31:42 +08:00
wizardchen 4c962a9403 feat(agent): add configurable MCP OAuth wait timeout per agent
Allow agents to set how long in-conversation OAuth prompts wait before
auto-skipping, with UI in the agent editor and bounded gate behavior.
2026-07-01 14:37:37 +08:00
lawrence fdfc7297de fix(vlm): allow configurable temperature for VLM models
Some VLM models (e.g. certain vision models) only accept temperature=1.
Previously temperature was hardcoded to 0.1. Now reads from model's
ExtraConfig["temperature"] with fallback to default 0.1.

Usage: set ExtraConfig.temperature=1 in the VLM model configuration.
2026-07-01 12:20:09 +08:00
wizardchen ee1014f87c feat(frontend): add API integration playground 2026-07-01 11:14:51 +08:00
wizardchen 5074344c16 feat(embed): scope OAuth and sessions per visitor principal
Add embed visitor principals (X-Embed-Visitor), widen sessions.user_id,
embed MCP OAuth/approval routes, OAuth callback context detachment, and
CloneContext principal preservation for async QA streams.
2026-06-30 20:01:05 +08:00
wizardchen 97bca74a31 fix: harden API principal config after review
Add require_direct_header toggle, external user ID validation, JWT TTL
limits, SaveToken error handling, ru-RU i18n, API docs, and Go SDK methods.
2026-06-30 20:01:05 +08:00
wizardchen cb99736d72 feat: scope API MCP OAuth by principal 2026-06-30 20:01:05 +08:00
wizardchen b5a1c88f75 fix(mcp): add OAuth skip endpoint and streamline in-chat interaction cards
Add a dedicated cancel route so users can skip mid-conversation OAuth without
token verification, and restyle OAuth/approval cards to match AgentStreamDisplay
with compact inline actions.
2026-06-29 23:22:28 +08:00
wizardchen 505195865a fix(mcp): trigger OAuth prompt during tool registration and dedupe helpers
OAuth authorization was only handled in MCPTool.Execute, so unauthenticated
services failed silently during RegisterMCPTools before any tool reached the
agent. Wire EventBus/session metadata into registration and reuse the same
getOrCreateMCPClientWithOAuthRetry path used at execution time.

Extract MCP OAuth session/wait/connect logic into mcp_oauth.go and remove the
duplicate waitForOAuthAndRetry + RegisterMCPContext layering in mcp_tool.go.
2026-06-29 23:22:28 +08:00
wizardchen 9fd7a7f522 feat(mcp): prompt and resume OAuth authorization mid-conversation
When an agent invokes an OAuth-enabled MCP service that the current user has
not authorized yet, the tool call now pauses and surfaces an "Authorize" card
in the chat instead of failing with an opaque error. After the user completes
the per-user OAuth popup, the backend verifies a token exists and resumes the
paused tool call automatically.

Backend:
- Add mcp_oauth_required / mcp_oauth_resolved events and response types.
- Add OAuthPendingRequest + Gate.RequestOAuthAndWait, reusing the existing
  approval waiter, Resolve, Redis cross-instance fan-out and timeout.
- MCPTool.Execute pauses on an authorization-required error for OAuth services
  and retries once (with a fresh ctx and recycled connection) after the user
  authorizes.
- Forward the new events to the SSE stream.
- Add ResolveMCPOAuth handler + route; it verifies authorization before
  unblocking so a premature resolve cannot resume into another failure.

Frontend:
- Add McpOAuthCard with an Authorize button reusing the popup + status-poll
  flow, then resolve the paused run.
- Handle the new stream events (dedup multiple pending cards per service).
- Add resolveMCPOAuth API client and i18n keys (zh/en/ko/ru).
2026-06-29 23:22:28 +08:00
wizardchen f2686e9e39 feat(mcp): drive auth by AuthType and auto-detect OAuth on test
Select the auth header for the configured strategy only, instead of
emitting both X-API-Key and Authorization whenever the fields happened
to be set (which double-authed after switching strategies). AuthType=""
keeps the legacy infer-from-fields behavior for pre-existing rows.

Add a configurable api_key_header (non-secret, defaults to X-API-Key) so
services expecting the key in a different header work without plaintext
custom headers.

On connection test, upgrade a bare 401 that advertises RFC 9728
protected-resource metadata into an explicit OAuthRequired signal so the
UI can guide the user to switch to OAuth 2.0. Surface the server's
description from the initialize handshake in the test result.
2026-06-29 22:37:52 +08:00
wizardchen c29761331c fix(agent): enforce tag scopes across knowledge tools 2026-06-29 19:17:42 +08:00
wizardchen 17ffd902ac fix(agent): avoid expanding tag scopes for grep chunks 2026-06-29 19:17:42 +08:00
wizardchen d3071fbe03 test(agent): add unit tests for buildMustUseBlock functionality
- Introduced tests for buildMustUseBlock to validate multi-word service prefix handling and name sanitization.
- Ensured that service names are correctly sanitized to prevent newline injection in must_use blocks.
- Verified that the generated block includes the correct tool name prefixes and does not contain unwanted characters.
2026-06-29 18:09:44 +08:00
wizardchen 6ad75d19fd test(knowledge): unbreak service test package after tag-loading change
Fixing the knowledge_create_test compile error in this branch let the
internal/application/service test package run for the first time, which
exposed two latent failures introduced when GetKnowledgeByID started
eagerly loading tags:

- GetOwningKBCreatorID went through the service-level GetKnowledgeByID
  (which now calls repo.GetKnowledgeTags); ownership resolution only
  needs the knowledge -> kb_id link, so resolve via repo.GetKnowledgeByID
  directly (tenant-scoped) and drop the extra tag query.
- createKnowledgeFileRepoStub lacked GetKnowledgeTags, which the create
  path always invokes via setAndAttachKnowledgeTags; add the stub method.
2026-06-29 18:09:44 +08:00
wizardchen d24e830c85 refactor(agent): fix grep scope loss and consolidate per-turn @mention scoping
- Fix grep_chunks dropping the full-KB scope when a turn mixes @KB with
  @tag/@file: extract scopeClause and OR knowledge-ID and (kb,tenant)
  predicates together, matching knowledge_search's fan-out.
- Consolidate the three scattered per-request @Skill/@MCP scope blocks in
  buildAgentConfig into applyPerRequestSkillScope / applyPerRequestMCPScope,
  each narrowing the whitelist and computing the must_use pin in one place.
- Dedupe the two identical selection-mode normalizers in Input-field.vue.
- Fix knowledge_create_test passing "" for the tagIDs []string parameter,
  which made the whole service test package fail to compile.
- Add unit tests for scopeClause and the per-request scope helpers.
2026-06-29 18:09:44 +08:00
wizardchen b86efe3f92 fix(agent): harden @mention scope and simplify must_use hints
Tighten per-turn @MCP/@Skill/@tag handling after review: enforce agent
MCP/Skill whitelist, ignore mentions when selection mode is none, tag-scope
grep_chunks, and simplified English must_use lines without tool dumps.
Skip persisting scope envelopes to history rendered_content.
2026-06-29 18:09:44 +08:00
wizardchen 049f85139d feat(chat): add @Skill/@MCP mentions with scoped agent runtime
Wire per-turn @mentions for skills, MCP services, tags, and files through
QA handlers into agent config, runtime_context/must_use user blocks, and
tool registration. Fix tag-only scopes dropping KB tools, refresh suggested
questions on mention changes, and strengthen MCP must_use so @selected
services are invoked before local KB search.
2026-06-29 18:09:44 +08:00
wizardchen 40f217c228 test: fix stale Doris SQL-shape and flaky OSS bucket assertions
Two pre-existing test failures on main, unrelated to any feature change:

- Doris VectorRetrieve/KeywordsRetrieve inline LIMIT as a literal (Doris
  does not support placeholders for LIMIT/OFFSET), but the SQL-shape tests
  still expected `LIMIT ?` with TopK as a bound arg. Match the literal
  LIMIT and drop the extra argument.
- TestOssEnsureBucket_CreateFails used the bucket name "test-bucket",
  which already exists globally on OSS, so IsBucketExist short-circuited
  and the create path never ran. Use a non-existent bucket name so the
  create-with-invalid-credentials path is actually exercised.
2026-06-29 17:44:56 +08:00
wizardchen 6b60d292f8 fix(embedding): add SSRF validation and safe HTTP client for embedders
Align embedding outbound requests with chat module defenses by validating
base URLs at construction time and using SSRFSafeDialContext with redirect checks.
2026-06-26 22:41:04 +08:00
YS-zdck b8ce6a699c feat(im): 新增QQBot即时通讯平台集成支持
完整实现QQBot的IM适配器功能,包括客户端封装、WebSocket长连接管理、消息收发与事件解析;更新后端合法平台校验列表与适配器注册配置;补充前端平台选型选项、logo资源、多语言文案以及渠道配置表单,同时添加对应的单元测试。
2026-06-26 16:53:00 +08:00
wizardchen 6932c3a85d feat(embed): always show channel key via detail API
Fetch publish tokens when opening an embed channel drawer so deploy snippets
stay available after browser restarts, while list endpoints still omit secrets.
2026-06-26 14:55:39 +08:00
wizardchen ecaedf1196 feat(frontend): unify document tag filter, manage drawer, and detail UX
Split tag filtering from CRUD management on the knowledge base document
page, align copy to "tags" across locales, and polish hover/detail surfaces
with setting-drawer section styling. Return tags from GetKnowledge for the
detail drawer.
2026-06-26 12:26:29 +08:00
wizardchen 2f29054110 fix(knowledge): harden multi-tag data integrity and UX follow-ups
Clear tag relations on move/delete, validate tags on create, batch-load tags,
restore KB-scoped reference counts, dedupe SetKnowledgeTags, fix filter
double-fetch and ResizeObserver leaks, and regenerate Swagger for tag_ids.
2026-06-26 10:52:52 +08:00
Anky c007a897cf feat: support multi-tag for document knowledge (#1790)
* 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>
2026-06-26 00:18:48 +08:00
wizardchen 97b7bb9890 fix(knowledge): harden batch reparse UX and async processing
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.
2026-06-25 23:57:54 +08:00
jw_mac a14c1d87aa feat(knowledge): add batch reparse capability
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.
2026-06-25 23:43:27 +08:00
wizardchen 47478491c9 fix(agent): address readiness review findings
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.
2026-06-25 23:33:39 +08:00
wizardchen 9ca4e1f23a feat(agent): enforce model readiness and polish selector UX
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.
2026-06-25 23:33:39 +08:00
杨聪聪 917feceb59 feat(docreader): support forcing PDF scanned-page OCR parsing 2026-06-25 17:30:22 +08:00
wizardchen 2c44a41f2a feat(models): add model test debugger for saved model configs
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.
2026-06-25 17:05:33 +08:00
wizardchen 122408b283 feat(chat): unify resource chips and browse recent files in @ mention
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.
2026-06-24 20:58:16 +08:00
wizardchen babe3f2315 fix(integrations): polish agent filter UX and embed session rebind
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.
2026-06-24 20:09:19 +08:00
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 fa8e2bb087 fix(web-search): improve SearXNG test connection error messages
Return provider-specific diagnostics when connectivity tests return zero
results, including SearXNG unresponsive_engines details instead of a
misleading API key hint.
2026-06-24 14:28:49 +08:00
wizardchen 7c8b15f022 fix(im): harden stream finalize and drop collapsed think header
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.
2026-06-24 10:33:55 +08:00
wizardchen e6b3ef4f73 fix(im): unblock agent stream wait when QA fails before complete event
Close completeDone on pipeline errors and AgentQA early failures so
handleMessageStream and runQA do not hang waiting for EventAgentComplete.
2026-06-24 10:33:55 +08:00
wizardchen da3d65c6f2 fix(im): address stream display review feedback
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.
2026-06-24 10:33:55 +08:00
wizardchen c3b036cb00 feat(im): align agent stream display with web thinking and tool progress
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.
2026-06-24 10:33:55 +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 be26563f86 fix(agent): remove unused RunnableByViewer gate blocking viewer chat
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.
2026-06-23 18:21:23 +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
wizardchen e40ad802d7 feat(datasource): add RSS feed connector with full-text ingestion
Enable private RSS feeds as a knowledge base data source with custom
headers, article body fetching, and Markdown output for incremental sync.
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