Wire the human-facing surface for the tenant-RBAC system that PR 1
introduced and PR 2 enforced: REST endpoints + UI for managing tenant
members, plus the long-pending invite_only registration gate.
Backend
- internal/handler/auth.go: Register now rejects with 403 when
auth.registration_mode=invite_only. PR 1 already exposes the mode via
/auth/config so the frontend hides the sign-up link; this is the
server-side enforcement for direct API calls.
- internal/handler/tenant_member.go: new TenantMemberHandler with
ListMembers / AddMember / UpdateMemberRole / RemoveMember. Maps
service-layer sentinels onto HTTP semantics (ErrLastOwner -> 409,
ErrMembershipAlreadyExists -> 409, ErrUserNotFound on AddMember -> 404,
ErrInvalidTenantRole -> 400). AddMember requires the invitee to
already have an account; SMTP-driven email invites are deferred.
- internal/types/tenant_member.go: new TenantMemberResponse projection
carrying the fields the management UI renders (email, username,
avatar, role, joined_at).
- internal/router/router.go: four routes under /tenants/:id/members
gated per the matrix (Viewer+ for list, Owner+ for every mutation).
- internal/container/container.go: dig provider for the new handler.
Tests
- handler/tenant_member_test.go: 12 table-driven cases covering happy
path, dangling-user tolerance, ErrLastOwner -> 409, ErrMembershipNotFound
-> 404, ErrMembershipAlreadyExists -> 409, unknown email -> 404,
invalid role rejected before user lookup, bad tenant id -> 400.
- handler/auth_register_invite_only_test.go: invite_only -> 403,
self_serve -> 201, nil Auth config falls through.
Frontend
- src/api/tenant/members.ts: typed client (TenantRole/TenantMember/...)
for the four endpoints.
- src/views/settings/TenantMembers.vue: members table with add dialog,
inline role select, confirm-remove modal. All mutation widgets gated
behind currentTenantRole === 'owner'; server still enforces.
- src/views/settings/Settings.vue: register the Members tab; show only
when currentTenantRole is loaded (avoids tab flash on cold nav).
- i18n in en-US/zh-CN/ko-KR/ru-RU: new tenantMember namespace covering
all UI strings and structured error messages (lastOwner / userNotFound
/ alreadyMember / invalidRole etc).
This completes the #1303 RBAC rollout. With cfg.Tenant.EnableRBAC=true
operators now have a full management surface; with EnableRBAC=false
the routes still exist but mutations log-and-pass per PR 2 contract.
Lay the foundation for tenant-level RBAC without enforcing it yet.
Schema, types, middleware lookup, and login-flow shape changes ship now;
RequireRole/route annotations and member-management endpoints follow in
PR 2 and PR 3.
Highlights:
- New tenant_members table (Postgres + SQLite) with (user_id, tenant_id)
unique key and (owner|admin|contributor|viewer) role values. Migration
000043 backfills one row per existing user, marking the earliest-created
active user in each tenant as Owner and the rest as Contributor.
- KnowledgeBase.creator_id and CustomAgent.runnable_by_viewer added so
PR 2 can wire ownership-based and Viewer-runtime checks.
- Auth middleware loads the active TenantMember row, sets a new
TenantRoleContextKey, and falls back via three escape hatches:
cross-tenant superusers (CanAccessAllTenants) get Admin in the target
tenant; orphan tenants (zero members) auto-promote the first authenticating
human to Owner; and when tenant.enable_rbac is false (the v1 default)
unmatched lookups fail open with Admin to preserve current behaviour.
- Register / OIDC provisioning now insert an Owner membership for the
registrant via TenantMemberService.EnsureOwner.
- LoginResponse renamed tenant -> active_tenant and gained a memberships
array. POST /auth/switch-tenant issues a fresh token pair scoped to a
target membership; GET /auth/config exposes auth.registration_mode for
the frontend register-tab gating.
- New config keys: auth.registration_mode (self_serve | invite_only,
defaults to self_serve) and tenant.enable_rbac (defaults to false).
Both have WEKNORA_* env overrides.
- Frontend store persists memberships and exposes currentTenantRole;
Login.vue calls /auth/config and hides the Register tab in invite_only
mode. Go SDK types updated to match the new LoginResponse shape.
Wires KnowledgeBase.VectorStoreID and the ownership-aware retrieve factory
into the user-facing knowledge-base lifecycle:
- POST /knowledge-bases validates the requested vector_store_id against
the caller's tenant scope and the engine registry. New error codes
ErrVectorStoreBindingInvalid (2200) and ErrVectorStoreUnavailable (2201)
distinguish the typed branches without echoing UUIDs to the client.
- GET / POST / PUT / PUT-pin responses embed the bound store's display
metadata (name, source, engine_type, status) without exposing any
connection credentials. Cross-tenant shared KBs receive a suppressed
payload (vector_store_id stripped, source="shared") so operator-chosen
store names cannot be enumerated across tenants.
- POST /knowledge-bases/copy synchronously rejects clones whose target
has a different embedding model or vector store, before the async
clone task is enqueued. The async clone worker re-applies the same
checks for defense in depth.
- DELETE /vector-stores/:id refuses to remove a store with bound KBs,
inside a transaction that row-locks the store on PostgreSQL and
serializes via WAL on SQLite. unregister-from-registry is wrapped in
defer/recover so a panic surfaces as a structured warning instead of
silently leaking a stale engine.
- vector_store_id is immutable after creation. The GORM <-:create tag
blocks every ORM update path; the service-layer DTO omits the field
entirely; a reflection-based regression test catches any future
maintainer who adds it back to either layer.
- Empty-string vector_store_id is normalized to nil at both the create
path and inside SharesStoreWith, so rows persisted by callers that
did not run Normalize first cannot trip false same-store comparisons.
Part of #993. Depends on #994 and #1310.
Replace the legacy "redacted placeholder + Clear* boolean" pattern with
dedicated per-resource credential subresources across MCP services,
Models, Web search providers, and Data sources.
Why
---
The previous design had three problems:
1. Main PUT body carried secret fields. The frontend echoed back a
redacted "***" placeholder, and a fragile MergeUpdate / IsRedactedOrEmpty
defense in the service layer tried to detect "user did not change this"
vs "user wants to clear this". A regression in that defense (or a new
frontend forgetting it) silently overwrites the stored secret with the
placeholder.
2. The "remove this credential" UX was a red checkbox under a pre-filled
password input. Three intents (preserve / replace / clear) collapsed
onto one field, and credential changes were bundled with unrelated
config edits in the same submit. Users wiped working keys by mistake.
3. Secret presence was inferred from "did the response come back with a
'***' placeholder", which couples the contract to a magic string.
Design
------
Each of the four resources now exposes:
PUT /{resource}/{id}/credentials # write one or more fields
DELETE /{resource}/{id}/credentials/{field} # clear a single field
"Is this configured?" metadata travels on the main resource response as
a typed map (dto.MCPServiceResponse.Credentials etc.) — no separate GET
endpoint. The frontend reads the configured boolean from the main GET
and never sees secret values at all.
Main PUT endpoints now ignore any secret fields in the request body and
log a deprecation warning if they appear, so legacy clients fail loudly
rather than overwriting silently.
Frontend
--------
- New reusable <CredentialResource> component renders a three-state card
(unconfigured / configured / editing) and drives the dedicated
endpoints. Used by MCP, Model, Web search; DataSource has a bespoke
card with the same behaviour because its credentials are a single
atomic per-connector map.
- Cancel from edit mode now restores state synchronously from the meta
prop. The previous async refresh() was a no-op while state was still
'editing', leaving the input frozen open.
- Remove is single-click + toast. The danger-themed button is the
deterrent; a modal confirm adds friction without adding safety (the
plaintext is irrecoverable client-side either way — recovery means
re-typing).
DTOs (internal/handler/dto/) are deliberately separate from the GORM
models so "no secret in response" is a compile-time invariant: a future
contributor cannot leak a secret without explicitly adding the field to
the DTO, which is review-able in a single diff.
Storage is unchanged — credentials still live in the existing jsonb /
parameters columns. No schema migration.
Cleanup
-------
- types.MCPService / types.Model / types.WebSearchProviderEntity /
types.DataSourceConfig: drop ClearAPIKey / ClearToken / ClearAppSecret
/ ClearCredentials boolean fields, MergeUpdate(), RedactSensitiveData().
- utils/types/secret.go: drop PreserveIfRedacted / IsRedactedOrEmpty.
RedactedSecretPlaceholder constant is retained because VectorStore
still uses the old pattern and is out of scope here.
- Frontend hasExistingApiKey / clearApiKey / convertToLegacyFormat
redaction handling removed; i18n keys renamed secret -> credential.
Extracts the 25 repeated NewCompositeRetrieveEngine call sites across
seven services into two factory functions with tenant-ownership
verification: CreateRetrieveEngineForKB (synchronous) and
CreateRetrieveEngineFromPayload (async task handlers). Promotes
GetByStoreID from concrete-only to interfaces.RetrieveEngineRegistry.
Extends KBDeletePayload / IndexDeletePayload with an omitempty
VectorStoreID snapshot.
Design highlights
- Factory verifies tenant ownership of the resolved store
(defense-in-depth) so a gap in PR3 validation or a tampered Asynq
payload cannot cross tenants. Cross-tenant attempts return
ErrVectorStoreForbidden with a structured log entry.
- Sentinel errors (ErrTenantInfoMissing, ErrVectorStoreNotFound,
ErrVectorStoreForbidden) let async handlers classify non-retryable
failures as asynq.SkipRetry.
- nil and empty-string pointers for vectorStoreID normalize to
"unbound" so callers never send an empty UUID to GetByStoreID.
- resolveBoundEngine constructs engineInfos directly (with
slices.Clone of Support()) instead of going through
NewCompositeRetrieveEngine. The latter only reads from the
byEngineType map and cannot reach DB stores in byStoreID -- multiple
stores can share the same engine type. Unbound fallbacks still reuse
NewCompositeRetrieveEngine so the tenant effective-engines path is
byte-for-byte unchanged.
- DeleteKnowledgeBase now reads the KB before soft-delete so the
enqueued KBDeletePayload carries a VectorStoreID snapshot; once the
row is soft-deleted GORM's default scope hides it. Cost: +1 SELECT
per KB-delete request (a rare admin operation).
- enqueueIndexDeleteTask gains a vectorStoreID *string parameter that
the single caller (tag.go) populates from the owning KB. The worker
(ProcessIndexDelete) validates ownership via the factory.
- cleanupKnowledgeResources loads the KB so bound-store cleanup routes
correctly. If the load fails it warns and falls back to tenant
effective engines; orphan vectors become observable in logs instead
of disappearing silently.
- DeleteKnowledges (batch) stays on the tenant effective-engines path
-- batches can span stores and multi-store fan-out is PR4 scope.
Noted inline.
Merge safety
All knowledge bases have VectorStoreID = NULL at merge time (introduced
nullable in PR1, Tencent/WeKnora#994). Every factory call falls back to
NewCompositeRetrieveEngine(registry, tenantInfo.GetEffectiveEngines()),
which is the existing code path for these KBs. Async payloads from
before this change decode to VectorStoreID = nil (omitempty) and take
the same fallback.
Testing
- go build ./...
- go vet ./...
- go test -race -count=1 ./internal/application/service/retriever/...
covers unbound (nil/empty), bound, cross-tenant, unregistered store,
ownership infra error, legacy payload shapes (missing field/null/
empty string/nil), tampered payload, and parallel invocation.
- grep -r NewCompositeRetrieveEngine internal/application/service
returns zero results outside factory.go/composite.go.
Refs: Part of Tencent/WeKnora#993. Depends on Tencent/WeKnora#994.
The Agent ran a parallel context cache (Redis/in-memory) on top of the
messages table to feed multi-turn history into the LLM. That dual-write
caused subtle drift (e.g. compression diverging from DB, system-prompt
swaps lost on restart) and required a separate ClearContext path on
session/IM clear.
Make the messages table the single source of truth:
- Add service.LoadAgentHistory: rebuilds chat.Message history per turn
from the persisted messages, expanding AgentSteps into proper OpenAI
assistant_with_tool_calls + tool messages and replaying the canonical
final answer (with <think> blocks stripped). final_answer tool calls
are filtered to avoid duplicating the trailing answer.
- Make AgentEngine stateless across turns: drop ContextManager / sessionID
cache plumbing from the engine, agent service, and CreateAgentEngine
signature. The engine only uses sessionID for logging/event emission.
- Wire AgentQA to load history from DB on demand using HistoryTurns
(default 5) when MultiTurnEnabled, otherwise run with empty history.
- Delete the llmcontext package (ContextManager interface, Redis/memory
storage, factory) and the SessionService.ClearContext API path; IM
/clear and session message clear no longer need to invalidate cache.
Behavior preserved: KnowledgeQA-mode replay is unchanged (turns with
empty AgentSteps just produce the single canonical assistant message),
and Agent-mode turns now consistently see prior tool calls and results.
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).
The wiki ingest post-process pipeline OOM'd and ran for hours on KBs
with ~40k documents. The dominant tail was a per-batch ListAllPages
that pulled every page (multi-MB content blobs) into Go memory, plus a
24h-TTL Redis pending list whose data could be evicted before a long
serialized backlog drained. dedup did O(P × N) Jaccard scoring in Go
on every batch. Lint loaded the full graph. The index page kept the
entire wiki directory in its content column and rewrote the TOAST
chunk on every ingest. None of these survive at 4w docs.
This change reworks the write path end to end and pulls the durable-
queue + dead-letter primitives out of wiki and into shared
infrastructure that every asynq task type now benefits from.
- migration 000041: task_pending_ops + task_dead_letters tables, plus
three GIN indexes on wiki_pages (source_refs jsonb_path_ops,
source_refs text fallback, lower(title) trgm).
- TaskPendingOpsRepository + TaskDeadLetterRepository in
internal/application/repository/task_queue.go: cursor-paginated
list, atomic IncrFailCount via UPDATE…RETURNING, dedup-key scoped
delete that refuses empty keys so a buggy caller can't wipe a KB's
queue.
- internal/middleware/asynqdl: writes a task_dead_letters row when an
asynq task exhausts its retry budget. Payload-agnostic — a small
probe struct extracts TenantID + scope hints across every existing
payload type, so summary:generation / image:multimodal /
faq_import / kb:clone / etc. all dead-letter without per-handler
code. Best-effort: an insert failure never masks the underlying
task error. Installed in router/task.go before the langfuse mw so
it sees raw errors.
- Pending queue moved Redis → PG (no TTL, restart-durable). Redis
keeps just the active-batch lock and the delete tombstone.
- In-batch retry budget (wikiMaxFailRetries=5) tracked via
pendingRepo.IncrFailCount; over the cap the row is moved to
task_dead_letters with task_type=wiki:ingest, related_id=knowledge
id. Asynq retries (10) are handled by the new middleware.
- Removed the per-batch ListAllPages. WikiBatchContext now carries
lazy fetcher closures (SlugTitleMany, SummaryByKnowledgeID) with
mutex-protected caches; reduce reaches for titles / summaries on
demand instead of pre-loading the whole KB.
- getExistingPageSlugsForKnowledge now uses ListSlugsBySourceRef,
which the new GIN index on source_refs serves as a Bitmap Index
Scan instead of a sequential text LIKE.
- Dedup pre-filter uses pg_trgm via FindSimilarPages
(idx_wiki_pages_title_trgm). For each new entity/concept (and each
of its aliases) we ask the DB for the top-K trigram-similar
existing pages and union the results — bounded prompt size, no Go-
side O(P × M) loop. Small KBs (≤25 entities) bypass the pre-filter.
- cleanDeadLinks / injectCrossLinks are scoped to the batch's
affected slugs (a few dozen) instead of every page in the KB. Both
use the new lite ListBySlugs / ExistsSlugs repo methods so they
pull only slug + title + outlinks, not full content.
- Slug fuzzy resolve (slug_fuzzy.go): when the LLM emits
[[bad-slug|display]] the cleanup path now tries display-text
reverse lookup → hyphen/case normalized equality → char-bigram
Jaccard ≥ 0.8 before stripping. Recovers the common pinyin-word-
break drift case ("shang-hai-tower" vs "shanghai-tower") in place
instead of replacing the link with plain text.
- rebuildIndexPage uses ListByTypeRecent(200) for the first-time
intro and drops the full DocumentSummaries blob from the
incremental update prompt, so its context stays bounded regardless
of KB size.
- Concurrency tunables surfaced in WikiConfig: IngestBatchSize /
IngestMapParallel / IngestReduceParallel, with sensible defaults
via OrDefault helpers. scheduleFollowUp drops to ProcessIn(0) so
follow-ups don't waste asynq retry slots bouncing on the active
lock.
- RunLint walks pages via the new ListPagesCursor in 200-page
windows and computes the live-slug set with a one-column
ListAllSlugs Pluck instead of a Limit:0 GetGraph that materialized
every node + edge. Memory is now bounded; 40k pages walks in
constant ~4MB.
- 14 GORM tests for both repos against an in-memory SQLite mirror of
the production DDL (task_queue_test.go).
- 6 tests for the dead-letter middleware covering retry budget
detection, payload-agnostic scope inference, error truncation, and
repo-failure isolation.
- 7 tests for the slug fuzzy resolve helper covering the three
resolution stages, display-text priority over normalized equality,
bigram fallback acceptance, and rejection of unrelated slugs.
- Existing wiki_ingest / wiki_lint / wiki_page tests updated to the
new fetcher / cursor APIs.
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>
IM platforms (Feishu, Slack, Telegram, DingTalk, Mattermost, WeCom) cannot
render provider:// URLs (local://, minio://, s3://, etc.) that appear in
LLM answers containing knowledge base images. The web frontend handles
these via the authenticated /files endpoint, but IM clients need publicly
resolvable HTTP URLs.
Changes:
- Add HMAC-SHA256 presigned URL utility (internal/utils/presign.go) for
generating time-limited, signature-verified file access URLs
- Add GET /api/v1/files/presigned endpoint that serves files without
session auth, verified by HMAC signature and expiry
- Update localFileService.GetFileURL() to return presigned HTTP URLs
when APP_EXTERNAL_URL is configured (cloud backends already return
presigned URLs via their SDKs)
- Add IM content rewriting pipeline: strip <image> XML tags, strip
citation tags, rewrite storage URLs to HTTP — applied at all IM
output points (streaming flush, non-streaming reply, fallback)
- Add holdback buffer in streaming flush to prevent URL/tag splitting
across chunk boundaries
Closes#1058
registerIMAdapterFactories in internal/container/container.go had grown
to ~290 lines of platform-specific config parsing and runtime start/stop
logic across 7 IM platforms, plus three private credential helpers. The
container package is meant to wire dependencies, not own each platform's
credentials schema and websocket lifecycle.
Extract each platform's factory into its own subpackage file and expose
the credential helpers on the im package:
- New im.ParseCredentials / im.GetString / im.GetBool (formerly the
unexported parseCredentials / getString / credentialBool in container).
- New im.ResolveMode helper collapses the six identical "default to
websocket when Mode is empty" blocks.
- New {wecom,feishu,slack,telegram,dingtalk,mattermost,wechat}.NewFactory
returns an im.AdapterFactory; container.go now calls each one in a
single line.
Behavior is preserved: adapter construction, goroutine start/stop,
log messages, default modes (mattermost still defaults to "webhook";
others to "websocket"), and error strings are unchanged. The WeCom
corp_agent_id float64/int switch and the WeChat long-poll-only path
are preserved as-is.
Net: container.go drops ~320 lines and no longer needs to be touched
when adding or tuning an IM platform.
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
Closes#620#497. Add opt-in Langfuse observability covering all five
model types (chat, embedding, rerank, VLM, ASR) with HTTP-request-scoped
traces and Docker Compose support (both cloud and self-hosted).
Core package internal/tracing/langfuse:
- HTTP client with batched async ingestion (non-blocking in request path)
- Sampling, environment / release tagging, and graceful fallback when
LANGFUSE_* env vars are absent (wrappers become no-ops)
- Gin middleware opens one trace per traced request and finishes it after
the handler chain returns, attaching method / path / user / session
- Trace context is stored under a typed key exported from internal/types
so logger.CloneContext can preserve it across handler / goroutine
boundaries (otherwise each LLM call auto-created an orphan trace,
fragmenting one request into many)
Per-model generation wrappers (opt-in via NewChat/NewEmbedder/...):
- chat: captures prompt, streaming output, token usage + TTFT
- embedding: approximates tokens when the provider omits usage
- rerank: previews query/docs, summarizes results to keep payload small
- vlm: records image count and total bytes, never uploads raw pixels
- asr: records file size and audio duration, never uploads audio bytes
Async title generation (GenerateTitleAsync) now forwards the trace key
into the goroutine so title calls appear under the parent chat trace.
Docker Compose:
- LANGFUSE_* env passthrough on the `app` service for cloud deployments
- Optional `langfuse` profile spins up a self-hosted Langfuse stack that
reuses WeKnora's existing PostgreSQL (separate database via an idempotent
init container that fixes ICU collation drift) and Redis (separate DB
number), adding only ClickHouse, MinIO, web and worker containers
- web/worker entrypoints URL-encode DB_PASSWORD / REDIS_PASSWORD at start
to avoid Prisma P1013 when passwords contain @ / # / etc.
Docs: docs/Langfuse集成.md covers cloud vs self-hosted, per-model usage
strategy, code map, and resource footprint.
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>
Syncs personal and team Yuque knowledge bases into WeKnora as Markdown,
with full and incremental sync + deletion detection. Mirrors the Feishu
connector pattern; fetches V2Doc.body directly (no async export step).
Config: api_token (required) + base_url (optional, defaults to public cloud).
401/403 wraps ErrInvalidCredentials; 429 honors Retry-After; filters to
status=1 Doc-type at list stage to conserve API quota. Body is trusted as
Markdown for format=markdown|lake — empirically verified against the v2
API: Lake XML lives separately in body_lake, body itself is the Markdown
view. Other formats (e.g. html) are skipped with a placeholder item so
they surface in sync logs instead of silently feeding HTML to the parser.
v2Doc.status accepts both int and string shapes — Yuque's OpenAPI spec
declares string but the live API returns int. sanitizeFileName truncates
at a UTF-8 rune boundary so multi-byte titles don't emit invalid UTF-8
that downstream filename validation rejects.
Also adds logger.SetOutput test hook, used by the token-redaction test.
- Extend RetrieveEngineRegistry with byStoreID map for DB store engines
- Add StoreRegistry interface and EngineFactory function type
- Create engine factory with per-driver SDK client construction
- Load VectorStore records from DB into registry at startup
- Wire Create/Delete to dynamically register/unregister engines
- Add comprehensive unit tests for registry and service
- Added a new logger for LLM calls, enabling detailed logging of model interactions, including request and response data.
- Introduced configuration options for enabling and specifying the log directory for LLM debug logs.
- Implemented cleanup for old log files to manage disk space effectively.
- Wrapped existing chat implementations to log calls when debug logging is enabled, enhancing traceability for model interactions.
Introduce KnowledgePostProcess task to decouple image multimodal
processing from downstream operations like summary, question
generation, and knowledge graph extraction.
This allows unifying the processing logic across documents and
images and ensures all text content, including from images,
is properly extracted before post-processing.
- Removed support for video file uploads across the application, including updates to the knowledge base and document processing services.
- Updated internationalization files to reflect the removal of video-related terminology, changing labels and descriptions to focus solely on audio processing.
- Adjusted file type handling to exclude video formats, ensuring users receive accurate feedback regarding supported file types.
- Enhanced error handling to provide clear messages when users attempt to upload unsupported video files.
This update streamlines the application by focusing on audio processing capabilities and improving user experience through clearer messaging.
Wire VectorStoreService to HTTP with 8 endpoints: types metadata, CRUD
(create/list/get/update/delete), and connection testing (raw + by ID).
Register routes, DI container bindings, and add API documentation.
Allow configuring custom WebSocket and API base URLs for WeCom
via optional credentials fields (ws_endpoint, api_base_url), enabling
integration with privately deployed WeCom instances.
Changes:
- LongConnClient and WebhookAdapter accept custom endpoint URLs
- Endpoint URLs validated at construction (scheme + SSRF check)
- Private deployment hostnames added to file download SSRF allowlist
- Frontend forms added for both WebSocket and Webhook modes
- i18n support for zh-CN, en-US, ru-RU, ko-KR
Uses default public cloud endpoints when not specified.
- Remove infrastructure/crypto package (CryptoService, config, PBKDF2-based encryption)
- Replace with lightweight utils.GetAESKey/EncryptAESGCM/DecryptAESGCM helpers
- Remove cryptoSvc dependency from modelService, tenantService, weKnoraCloudService
- Remove crypto state persistence logic from container initialization
- Add TruncatePromptTokens field to WeKnoraCloud embed request
- Update frontend hint text for WeKnoraCloud credential errors
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Extended the IMChannel interface to include WeChat as a platform, supporting long-polling mode and full output mode.
- Implemented WeChat QR code login functionality, allowing users to authenticate via a QR code.
- Added new API endpoints for generating and polling the status of WeChat QR codes.
- Updated the frontend to handle WeChat-specific UI elements and interactions, including dynamic form adjustments based on the selected platform.
- Enhanced localization files to include WeChat-related translations.
- Introduced a WeChat adapter for message handling and file downloading via the iLink Bot API.
Go 1.24 has an internal compiler race condition on Windows that causes
'package without types' errors during parallel compilation. Setting
GOFLAGS="-p=1" serializes the build and avoids triggering the bug.
- Implement Validate, ListResources, FetchAll, FetchIncremental
- Per-record database sync with individual knowledge items
- Incremental sync with record-level change detection for databases
- Tree-structured resource listing with parent-child relationships
- Markdown renderer for all Notion block types including nested content
- Register NotionConnector in DI container
- Add unit tests for connector and markdown
WeCom AI Bot does not strip @mention from text.content in group chats,
causing all slash commands (/stop, /clear, /help) to fail — the content
arrives as "@BotName /stop" instead of "/stop".
- Add stripAtMentionBasic (stateless) and stripAtMention (with bot name
caching) to handle multi-word bot display names
- Support bot_name in channel credentials for immediate precision
- Apply stripping in both WebSocket and webhook adapters, text and mixed
- Add mention_test.go with 21 test cases
- 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.
- Deleted WeCom document connector and callback handling code to streamline the datasource management.
- Removed associated localization entries and UI elements related to WeCom integration.
- Updated data source management logic to eliminate references to WeCom, enhancing maintainability and clarity.
- Adjusted error handling and logging to reflect the removal of WeCom-specific functionality.
- Implemented WeCom document connector to sync smart documents and WeDrive files into WeKnora.
- Added detailed documentation for WeCom integration, including setup instructions for callback URL and API access.
- Enhanced frontend localization to support WeCom-specific messages and instructions.
- Updated data source management UI to include WeCom configuration options and callback URL handling.
- Improved error handling and validation for WeCom API interactions.
- Added a new API for managing data sources, including CRUD operations and connection validation.
- Introduced UI components for data source settings, sync logs, and editor dialog, enhancing user experience in managing external data sources.
- Updated localization files to support new data source features in multiple languages.
- Implemented cron expression humanization for better scheduling visibility.
- Enhanced knowledge base editor to include data source management options.
- Updated the assistant descriptions in various prompt templates to specify that they are developed by Tencent.
- Added new intent-specific system prompt templates for greeting, chitchat, follow-up, image analysis, summarization, and web search unavailability scenarios.
- Enhanced citation rules in the system prompts to ensure proper inline citation formatting.
- Refactored the rewrite prompt to classify user intent more accurately and output structured JSON responses.
- Add DingTalk AI Card streaming support with create/deliver/update via OpenAPI
- Extract shared think-block rendering into reusable im.TransformThinkBlocks
- Add stream orphan reaper and edit throttling for DingTalk and Telegram
- Apply think-block transform on all reply paths (DingTalk, Telegram, Feishu)
- Add Card Template ID config to frontend IM channel panel with i18n
Add DingTalk bot adapter supporting both webhook (HmacSHA256 signature
verification) and Stream mode (via official dingtalk-stream-sdk-go),
with sessionWebhook/OpenAPI reply fallback and AccessToken caching.
wizardchen