Commit Graph

152 Commits

Author SHA1 Message Date
qilifan 9afb8b7b68 feat(im,datasource): support Lark, Feishu's international edition
Lark and Feishu are the same product deployed on two isolated clouds
(open.larksuite.com and open.feishu.cn). WeKnora touches both from two
places — the IM bot and the Wiki data-source connector — and this brings
Lark to parity across both. Neither API surface differs, so rather than
duplicate either implementation, each is parametrized by a Region and
registered twice.

IM (internal/im/feishu):
  Every API call routes through a.api(), which prefixes the region's
  host, and the WebSocket client passes larkws.WithDomain — the SDK
  defaults to open.feishu.cn, so Lark long connections would otherwise
  fail to authenticate.

Data source (internal/datasource/connector/feishu):
  Lark was half-supported: the client honoured a base_url override and a
  LarkBaseURL constant existed, but the connector registered only as
  "feishu" and the UI never exposed base_url, so Lark wikis could not be
  configured at all. Lark is now its own connector type. base_url is kept
  as an explicit override so data sources that pointed a "feishu"
  connector at open.larksuite.com keep working.

Bugs found and fixed along the way:

- Wiki resource links were hardcoded to https://feishu.cn/wiki/{token} in
  four places, so a Lark wiki linked into the wrong cloud entirely.
- Bot identity is now platform-prefixed (feishu:cli_x vs lark:cli_x).
  BotIdentity carries a unique index, so without this a Lark channel
  would be rejected as a duplicate of an unrelated Feishu bot sharing an
  app_id.
- The card image cache is now keyed by app_id. image_keys are issued per
  app on one cloud; a Feishu key handed to a Lark app fails the card
  update with code=200570.
- The datasource doc claimed Lark "adapts automatically" — it could not,
  since the UI had no way to reach base_url.

Permissions are where the clouds genuinely diverge. Identical APIs do not
mean identical permission catalogues: aily:file:read, aily:file:write and
corehr:file:download exist on Feishu but not on Lark, so pasting Feishu's
scope JSON into Lark fails to import. That JSON is also over-broad (it
covers products WeKnora never calls) and simultaneously incomplete (it
omits the drive:*/docx:* scopes the connector needs). Lark therefore gets
its own list, derived from the 17 endpoints the code actually calls and
checked identifier-by-identifier against Lark's own API reference, plus a
full Feishu→Lark mapping table marking each scope verified, unverified,
or absent. Both features use tenant_access_token only — no user_access_
token exists anywhere in the repo — so the user dimension stays empty.

Known limitation: Region.ThinkingText makes Lark's initial card
placeholder English, but once streaming starts the think-block headers
come from the shared MarkdownThinkStyle and are Chinese on every platform
(Lark, Slack, Telegram, Mattermost alike). Fixing that means threading a
locale through FormatIMDisplayContent, which has no platform context — a
cross-platform change, not a Lark one. Documented as such.

The channel-creation 400 message is now derived from validIMPlatforms so
the list cannot drift as platforms are added.

Tests: region invariants and per-region URL construction on both sides,
the Feishu/Lark bot-identity split, platform-to-channel mapping, base_url
override precedence, an end-to-end SendReply against a fake Open Platform
(token fetch, reply, thread-unsupported fallback, hard-error surfacing),
and a ListResources drive asserting wiki links never leak the other
cloud's host.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-17 11:05:54 +08:00
wizardchen ceb4d1a310 feat(chat): add session-scoped temporary attachments with async parsing
Let users upload documents in chat without ingesting them into a knowledge base: files are parsed in the background, referenced by ID on send, and expire after a configurable TTL.
2026-07-16 17:41:27 +08:00
wizardchen 6d14cc3536 feat(resource): add stable resource registry with LLM-context alias compaction
Introduce resource://<handle> as the stable application identity for stored
objects, decoupling API responses, persisted rich text, and LLM prompts from
physical storage paths. Adds a resource catalog service (register/resolve/bind,
revocable expiring access grants), a request-local alias registry that compacts
resource references while in the LLM context and restores them (including across
streaming chunks), plus router, IM, chat-pipeline, and multimodal integration.

Includes schema migrations (resources, resource_bindings, resource_access_grants)
for sqlite, and hardens URL/output security handling.
2026-07-15 17:02:43 +08:00
wizardchen f8b3e5f148 feat(storage): add multi-instance storage backends per workspace
Introduce tenant-scoped storage backend registry so workspaces can register
multiple storage instances and bind each knowledge base to a specific backend,
with migration from legacy tenant-level storage config and new settings UI.
2026-07-15 14:54:39 +08:00
wizardchen ace84bc757 fix(knowledge): recover tasks safely after server restart
Stop failing distributed-mode knowledge rows on startup; let housekeeping
decide using span activity and Asynq queue state. In Lite mode, resume
wiki work from durable task_pending_ops and surface SERVER_RESTART errors
in the processing timeline with i18n support.
2026-07-14 17:55:26 +08:00
wizardchen 087fcc9fe7 feat(agent): add question suggestions with after-answer follow-ups
Enable agents to configure starter prompts and async follow-up questions after completed answers, with durable caching, analytics events, and chat/embed UI integration.
2026-07-14 11:17:25 +08:00
wizardchen 07ba01ec93 feat(worker): replace aggregate asynq concurrency with per-pool governance
Split the monolithic upstream worker budget into explicit core, post-process,
enrichment, maintenance, and shared elastic pools, expose live cluster capacity
on the runtime dashboard, and retire the legacy asynq.concurrency setting.
2026-07-13 15:51:06 +08:00
wizardchen d496d0fc73 feat(task-queue): split upstream workers into isolated core/enrichment/maintenance pools
Route summary/sync/maintenance tasks to dedicated queues and servers so parsing, enrichment, and batch work no longer share one concurrency budget, while extending the runtime dashboard and settings validation to reflect the new topology.
2026-07-10 23:51:29 +08:00
wizardchen 38aacc3113 chore(env): update WEKNORA_MODEL_MAX_CONCURRENCY to 32 in configuration files
Increase the default value of WEKNORA_MODEL_MAX_CONCURRENCY from 8 to 32 in .env.example, docker-compose.yml, and related application code. This change enhances the concurrency limit for background tasks, ensuring better performance and resource management across the system.
2026-07-10 14:51:01 +08:00
wizardchen 98ad41cda4 fix(models): harden background concurrency governor
Follow-up hardening on the per-model background concurrency governor:

- limiter: heartbeat now refreshes the ZSET key's PEXPIRE alongside the
  lease score, so a semaphore that stays saturated with no slot turnover
  can't let the whole key expire (which would drop every lease and admit
  over the limit); reuse one poll timer instead of allocating time.After
  each iteration under contention.
- governor: extract the process-wide governor + Gate helper into the
  limiter package so chat and vlm share one limiter/limit without
  importing each other; add an in-process localLimiter for Lite mode.
- vlm: gate background multimodal (VLM) calls through the same governor;
  previously only chat was throttled.
- chat: ChatStream releases its slot when the consumer abandons the
  stream and cancels ctx (select on ctx.Done, drain inner), fixing a
  slot/goroutine leak.
- container/sync_task: install the local governor in Lite mode and tag
  SyncTaskExecutor runs as background; honour model.max_concurrency=0 as
  an explicit disable instead of falling back to the default.
- tests: cover the governor gating, local limiter, and stream release.
2026-07-09 20:40:51 +08:00
wizardchen 63198c5d9f feat(models): cap background LLM concurrency per model
Background ingestion/enrichment stages (summary, question, graph,
multimodal) all target the same chat model, and asynq queue weights are
scheduling priority rather than throttling. A large upload could therefore
burst up to the entire worker pool of concurrent chat calls against a
single provider, unbounded across replicas, with no model-side rate limit.

Govern concurrency at the chat-client layer (the one place that sees every
task type), keyed by model ID:

- internal/models/limiter: Redis ZSET + Lua distributed semaphore with a
  lease heartbeat, expired-lease reclaim for crashed holders, and fail-open
  on any backend error or context cancellation.
- chat: concurrencyChat decorator (outermost in NewChat) acquires a
  per-model slot only for background tasks; interactive chat is never gated.
- router/task: asynq middleware tags every worker execution as background.
- container: wire the Redis limiter with WEKNORA_MODEL_MAX_CONCURRENCY
  (model.max_concurrency), default 8; enabled only when Redis is present.

Tested with miniredis: concurrency cap, expired-lease reclaim, per-key
isolation, and all fail-open paths (nil client, backend down, cancelled ctx).
2026-07-09 20:40:51 +08:00
wizardchen 70e2e85fa6 feat(wiki): dedicated worker pool with concurrent claim-based batching
Isolate the wiki generation pipeline from the document parse pipeline so
the two can no longer starve each other during concurrent uploads.

- Dedicated asynq worker pool for QueueWiki (NewWikiAsynqServer) with its
  own concurrency budget (WEKNORA_WIKI_ASYNQ_CONCURRENCY / asynq.wiki_
  concurrency, default 16), split from the parse pool (NewParseAsynqServer).
  Both run the same mux over disjoint queue sets. Replaces the old
  weighted-lottery approach where wiki sat on the low queue (weight 1).
- Task queue: add ClaimBatch (SELECT ... FOR UPDATE SKIP LOCKED + claimed_at)
  and ReleaseByIDs so multiple concurrent consumers pull disjoint rows
  without an external per-KB lock; PeekBatch retained for Lite mode.
- New TypeWikiFinalize debounced KB-global finalize task (index rebuild /
  dead-link cleanup / cross-linking), registered on both Redis and Lite paths.
- Two-level wiki ingest concurrency: IngestMaxInflight caps concurrent
  batches per KB; Map/Reduce fan-out sized within a batch. New config knob
  + system setting + swagger docs.
2026-07-09 17:41:07 +08:00
Ilya Bogin 8cf9f1c882 feat: add Keenable as a configurable web search provider
Add Keenable Search alongside the existing DuckDuckGo / Bing / Google /
Tavily / Ollama / Baidu / SearXNG providers.

- internal/infrastructure/web_search/keenable.go: KeenableProvider
  implementing the WebSearchProvider interface, following the Tavily
  provider pattern. Keyless by default: with no API key it calls the
  public endpoint (/v1/search/public, rate-limited); a key switches to
  /v1/search and lifts the cap. Base URL is hardcoded (SSRF-safe), proxy
  is honored.
- Registered "keenable" in the container registry.
- Added the keenable provider type + type metadata (RequiresAPIKey=false)
  and service validation (no required key, like DuckDuckGo).
- Provider-specific empty-results diagnostic (keyless rate-limit hint).
- Frontend: extend the provider union type with 'keenable'.
- Unit tests: keyless vs keyed endpoint, attribution header, maxResults
  trim, result mapping, error status, name.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 16:58:26 +08:00
wizardchen 505bc7ddec feat: add scoped tenant api keys 2026-07-07 12:00:13 +08:00
qilifan d5b8d2f886 feat(redis): support TLS for Redis connections (#1930)
[Feature]: Support TLS for Redis connections
2026-07-06 23:02:02 +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 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
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 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
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 99f35f8dea fix(duckdb): avoid extension install during startup 2026-06-08 15:29:42 +08:00
ruihao.li a12b6ff61b feat: support Milvus database selection for vector stores 2026-06-05 15:11:37 +08:00
wizardchen 482686d17e feat(chat): implement local image resolver for multimodal chat
- Added a LocalImageResolver function to resolve local storage URLs to their byte data using the tenant's storage configuration.
- Integrated the resolver into the container setup to support reading local images in multimodal chat scenarios.
- Enhanced the handling of local storage paths to correctly parse tenant IDs and retrieve files based on the configured storage settings.
2026-06-01 20:54:37 +08:00
ochan.kwon 40b74e2efa feat(retriever): activate OpenSearch k-NN driver (PR 3 of 3)
Phase 3 (#1440) gate flip. PR 1 (#1445) + PR 2a (#1481) + PR 2b (#1482)
laid the type prep + driver skeleton + read/write paths as gated dead
code; this PR wires every activation surface so opensearch becomes a
registerable VectorStore engine.

Activation wiring
- internal/types: validEngineTypes / GetVectorStoreTypes (with HNSW
  bounds + knn_engine enum + Immutable hints) / retrieverEngineMapping /
  buildEnvStoreForDriver — every gated surface now recognises
  "opensearch". IndexConfig grows four omitempty HNSW fields (HNSWM /
  HNSWEFConstruction / HNSWEFSearch / KNNEngine), keeping other engines'
  serialised config byte-identical.
- internal/container: createOpenSearchEngine + the switch case in
  createEngineServiceFromStore; the RETRIEVE_DRIVER=opensearch env path
  in initRetrieveEngineRegistry; NewEngineFactory now closes over the
  AuditLogService (the EngineFactory type itself is unchanged).
- internal/application/service/vectorstore_healthcheck.go: a
  testOpenSearchConnection case so CreateStore's connectivity probe
  accepts opensearch instead of returning 400.
- internal/application/repository/retriever/opensearch/transport.go:
  NewOpenSearchClient is exported so the factory and env path can build
  the TLS-hardened client; healthcheck.go reuses the unexported
  probeVersion / probeKNNPlugin for the service-layer probe.

Service-layer validation
- validateOpenSearchIndexConfig validates the HNSW caps (m 2-100,
  ef_construction 2-4096, ef_search 1-10000, knn_engine ∈ lucene|faiss).
  Shards/replicas continue to be enforced by the flat ValidateIndexConfig.
  Create-only: UpdateStore mutates the name only.
- validateConnectionConfig requires addr for opensearch.

Sync implementations (stubs.go shrinks)
- CopyIndices (copy.go) mirrors the Elasticsearch / Qdrant pattern —
  search → BatchSave with the source_id remap for generated questions —
  so dim/keyword routing and the source_id contract come from BatchSave
  for free. embeddingMap is keyed by the *target* SourceID because
  OpenSearch's BatchSave looks up embeddings by SourceID
  (lookupEmbedding), not by chunk_id (the ES driver's convention).
  Pagination is from/size; copies larger than max_result_window
  (default 10000) need the scroll-based async path that lands later.
- BatchUpdateChunkEnabledStatus / BatchUpdateChunkTagID (bulk_update.go)
  group the input by target value and issue one _update_by_query per
  group over the cross-dim <base>_* pattern. Caller values flow through
  bound script params only — never string-interpolated into the Painless
  source — closing the script-injection surface.
- inspectByQueryResponse (byquery.go) mirrors inspectBulkResponse: the
  full failure reason goes to the debug log only; the returned error
  carries the bounded id + type.
- UpdateByQueryParams.Refresh is *bool in opensearch-go v4.6.0 (the same
  shape as DeleteByQuery's quirk), so refresh=wait_for is not
  expressible; we use refresh=true.

Driver-owned audit (DIP)
- A new opensearch.AuditSink interface (with nopSink + WithAuditSink
  functional option) lets the driver emit opensearch.index_created and
  opensearch.reindex_executed events without importing any service
  package — the service layer implements the interface. NewRepository
  takes opts, so existing 4-arg test call sites keep compiling unchanged.
- internal/container/audit_sink.go bridges AuditSink to AuditLogService.
  When the context carries no tenant (the env-path registration ctx
  during boot, for example) the adapter skips the emit with a warning
  rather than silently writing tenant_id=0, which would collide with the
  system-scope sentinel.

Frontend + polish
- FieldSchema (frontend/src/api/vector-store.ts) gains min/max/enum/
  immutable. VectorStoreSettings.vue is now schema-driven: a closed
  `enum` renders a t-select; number inputs use the schema's `:min`/`:max`
  and fall back to the legacy replica-vs-shard heuristic only when the
  schema does not pin them; a danger-coloured warning fires when
  insecure_skip_verify is toggled on (the switch and warning are wrapped
  in a vertical stack so the warning sits on its own row below the switch).
- i18n: labels for hnsw_m / hnsw_ef_construction / hnsw_ef_search /
  knn_engine / insecure_skip_verify plus the warning copy in en-US,
  ko-KR, zh-CN, ru-RU.
- docker-compose.dev.yml: an opensearch profile (single-node 3.3.2 with
  security plugin disabled for dev only). OpenSearch Dashboards lives in a
  separate, opt-in opensearch-ui profile so the heavy UI container is not
  forced up alongside the cluster (the driver e2e is fully curl-verifiable
  against :9200). The new docs/dev/opensearch-integration-test.md covers the
  end-to-end exercise and the single-node guidance (set replicas=0 to keep
  the cluster Green).

Gating-guard tests flipped
- The "OpenSearch is NOT in validEngineTypes / mapping / types list /
  env builder / stubs" guard tests from PR 1 / PR 2 are replaced by
  their positive counterparts in this PR. The test suite was the
  activation checklist; the activation flip is its diff.

Backward compatibility
- Additive everywhere. IndexConfig's new HNSW fields are omitempty so
  other engines' serialised config is byte-identical. Existing
  Elasticsearch / Qdrant / Milvus / Weaviate / Doris / TencentVectorDB
  stores are untouched. No migrations.

Test plan
- go build ./... clean
- go vet ./... clean
- gofmt -l clean on touched files
- go test ./... — only TestOssEnsureBucket_CreateFails (Aliyun OSS
  endpoint), the docreader gRPC tests, and the doris SQL-shape tests
  fail; all three are pre-existing on upstream/main and untouched by
  this PR.
- New tests across internal/types, opensearch, service and container —
  including a full end-to-end env-path test that exercises
  initRetrieveEngineRegistry with RETRIEVE_DRIVER=opensearch against an
  httptest cluster.
2026-05-29 16:32:27 +08:00
wizardchen 19a1b15106 fix(container): correct resetPendingTasks SQL on startup
Split knowledge list/update queries to avoid GORM UPDATE...FROM
duplicate-table errors after Find, and use sync_logs started_at/
finished_at column names instead of start_time/end_time.
2026-05-29 15:46:11 +08:00
wizardchen f1a27e0e18 feat: implement CancelOpenSpansByName method and related tests
This commit introduces the CancelOpenSpansByName method in the KnowledgeSpanRepository, allowing for the cancellation of open spans by their name for a specific knowledge ID and attempt. This functionality is crucial for managing spans during retries or server restarts, preventing duplicate entries in the trace tree. Additionally, a new test case, TestKnowledgeSpanRepo_CancelOpenSpansByName, has been added to ensure the correct behavior of this method, verifying that only the intended spans are cancelled while others remain unaffected. This enhancement improves the robustness of span management in the application.
2026-05-28 20:16:02 +08:00
wizardchen 44d6175559 feat: add knowledge parse cancellation with finalizing post-process state
Lets users stop an in-flight document parse to free up LLM / worker
resources without losing the chunks and index already written. The
core insight is that the previous parse_status=completed flipped as
soon as primary chunks landed, while the most expensive subtasks
(graph extract = N LLM calls per chunk, plus summary, question
generation) were still running in the background — so "completed"
wasn't actually terminal from a resource standpoint.

State machine

  pending -> processing -> finalizing -> completed
                              |
                              +-> cancelled (any of the three
                                            in-flight states)
                              +-> failed
                              +-> deleting

`finalizing` is the new post-process fan-out window. parse_status
only promotes to `completed` once pending_subtasks_count (a new
column tracking summary + question + per-chunk graph extract)
drains to zero via atomic FinalizeSubtask. Wiki ingest is
intentionally excluded from the counter — it's a KB-scoped
debounced batch and would otherwise pin parse_status in
`finalizing` for the wiki batch window.

Backend

- New ParseStatusFinalizing + pending_subtasks_count column with
  migration 000056.
- knowledgeRepository.SetFinalizing transitions processing -> finalizing
  conditionally so a racing cancel cannot be clobbered.
- knowledgeRepository.FinalizeSubtask atomically decrements the
  counter and self-promotes the row to completed when it hits zero.
- KnowledgePostProcess restructured to compute expected subtask
  count up front, flip to finalizing (or completed when no
  enrichment is enabled), and only then fan out subtasks. Subtask
  handlers (summary, question, graph extract) defer-decrement on
  terminal exit using the existing isFinalAsynqAttempt convention.
- New POST /api/v1/knowledge/{id}/cancel-parse handler accepting
  pending / processing / finalizing. Marks the row cancelled,
  zeroes the counter, best-effort dequeues asynq tasks via a new
  TaskInspector abstraction (asynq-mode walks pending/scheduled/
  retry queues; Lite-mode noop), and scrubs wiki ingest pending op.
- SpanTracker.AbortAttempt flat-sweeps every still-running span
  for the attempt via a new repo.CancelAllOpenSpans helper so the
  trace viewer's striped bars all flip to cancelled, even leaf
  generations whose parent stage already EndSpan'd (multimodal
  fan-out pattern). knowledge_post_process closes its postSpan
  via SkipSpan on the cancel/deleting entry guard so a worker
  that opens a span AFTER the cancel sweep doesn't leak it.
- Housekeeping and resetPendingTasks sweep finalizing rows
  identically to processing so a crash/restart can't strand them.
- DeleteKnowledge/DeleteKnowledgeList proactively dequeue
  downstream tasks via the same TaskInspector path.
- ChunkExtractService gets a cancel entry guard so the most
  expensive enrichment (graph extract) bails immediately when the
  parent knowledge is aborted.

Frontend

- New cancelKnowledgeParse API client + "Stop parsing" entry in
  both list view and card view more menus, gated on
  pending/processing/finalizing.
- Polling predicate refactored to a shared isParseInFlight helper
  that recognises `finalizing` (previously the doc list silently
  stopped polling once parse_status flipped from processing).
- Knowledge processing timeline: isPolling includes finalizing,
  new isHardTerminal short-circuits LIVE for cancelled/failed/
  completed so stranded child spans cannot pin LIVE on.
- DocumentListView.computeStatus distinguishes finalizing
  ("增强中") from completed and shows the previous "生成摘要中"
  copy when summary_status is still pending under finalizing.
  Added cancelled badge as well.
- i18n: statusFinalizing / statusCancelled / cancelParse* keys
  across zh-CN, en-US, ko-KR, ru-RU.

Docs / SDK

- docs/api/knowledge.md: documents the new finalizing state,
  cancel-parse semantics, and which statuses accept cancel.
- client (Go SDK): CancelKnowledgeParse with docstring listing
  the cancellable statuses.
2026-05-28 20:16:02 +08:00
wizardchen c9941a6688 refactor(knowledge): replace flat stage table with langfuse-style span tree
Addresses review feedback that the PR② design had four shortcomings:

  1. The pipeline is a DAG, not a sequence — Embedding and Multimodal
     are independent of each other, both downstream of Chunking, both
     upstream of PostProcess. The flat (knowledge_id, stage) table
     couldn't represent that, so a Chunking failure left dependents
     stranded as "pending" forever instead of being marked as
     impossible-to-run.

  2. No history across attempts. A reparse erased the previous run's
     status before the new run started, leaving operators with no way
     to investigate "why did this fail twice?".

  3. Stages had only status + duration. Operators want to know how big
     the work was — pages parsed, chunks created, tokens embedded, VLM
     calls made — to distinguish "slow because the file is huge" from
     "slow because the docreader is wedged".

  4. Multimodal fans out N image tasks; Embedding fans out M batches;
     PostProcess fans out into Summary/Question/Wiki/Graph. Each unit
     is interesting on its own (Langfuse already captures this for
     LLM calls). The flat model couldn't express it.

The redesign mirrors Langfuse's trace/span/generation hierarchy:

  * Migration 000053 supersedes 000052: knowledge_processing_spans
    table with (knowledge_id, attempt, span_id) primary key, plus
    parent_span_id, kind ∈ {root, stage, subspan, generation},
    status ∈ {pending,running,done,failed,skipped,cancelled}, and
    JSONB input/output/metadata fields.

  * SpanTracker (replacing StageTracker) exposes OpenAttempt /
    BeginStage / BeginSubSpan / EndSpan / FailSpan / SkipSpan /
    LookupStage. Cross-process workers (image_multimodal) get the
    parent's attempt + span via payload + LookupStage so subspans
    attach correctly.

  * StageDependencies declares the DAG; FailSpan now cascades —
    descendants of the failed span and dependent stages are flipped
    to "cancelled" with a UPSTREAM_FAILED code. The UI sees a clear
    blast radius instead of orphan spinners.

  * Reparse now calls OpenAttempt up front so the timeline reflects
    "new attempt, all pending" instead of letting the previous run's
    status linger until the worker picks up the task.

  * Image_multimodal records each image as a generation subspan with
    its own success/failure on the parent attempt's multimodal stage.
    The finalize-on-last-attempt counter logic is preserved unchanged.

  * GET /api/v1/knowledge/:id/spans (also kept /stages alias) returns
    a tree shape with synthesized pending placeholders so the
    frontend always renders five timeline segments. ?attempt=N
    enables history navigation.
2026-05-28 15:14:45 +08:00
wizardchen 04f56f9cda feat(knowledge): track per-stage parsing progress with /stages API
Adds a five-segment progress model for the document parsing pipeline so
the UI (PR③) can render a timeline showing where each document is
(DocReader → Chunking → Embedding → Multimodal → PostProcess) and
which stage failed with what error code.

- New table `knowledge_processing_stages` (migration 000052) with one
  row per (knowledge_id, stage). UPSERT on Begin/Done/Fail bumps an
  attempt counter so re-parses don't lose history.

- StageTracker service exposes Begin/Done/Fail/Skip; all calls are
  best-effort and never break the pipeline if persistence fails.

- Stable error codes (DOCREADER_TIMEOUT / EMBEDDING_RATE_LIMIT /
  VECTORSTORE_WRITE_FAILED / ...) the UI can map to localized
  remediation hints.

- Tracker call sites added at the four meaningful failure points:
  convert (DocReader), CreateChunks (Chunking), BatchIndex (Embedding),
  enqueueImageMultimodalTasks (Multimodal start),
  KnowledgePostProcess.Handle (Multimodal close + PostProcess).

- New endpoint `GET /api/v1/knowledge/:id/stages` returns the five
  canonical stages — missing rows are synthesized as "pending" so
  the timeline always renders five segments. Includes current_stage
  and last_error block.
2026-05-28 15:14:45 +08:00
wizardchen 3ae3ea97c5 fix(knowledge): prevent documents from getting stuck in "processing"
Several failure modes left Knowledge.parse_status pinned at "processing"
forever, with no signal to users beyond a permanent spinner. This commit
addresses the root causes and adds a safety net.

- Asynq worker pool: explicit Concurrency (default 16, env-tunable via
  WEKNORA_ASYNQ_CONCURRENCY) so batch uploads don't queue behind a
  CPU-count-sized worker pool. Redis op timeouts raised to 500ms/1000ms
  (WEKNORA_REDIS_OP_TIMEOUT_MS) to absorb bursty multimodal counter ops.

- DocReader RPC: cap each call with WEKNORA_DOCREADER_CALL_TIMEOUT
  (default 30m). Without this, a hung docreader pinned a worker for the
  full DocumentProcessTimeout window.

- ImageMultimodal: finalize-on-last-attempt semantics. A permanently
  failing single image no longer strands the parent — the asynq retry
  is allowed to run, but on the final attempt we count the image
  regardless of outcome. Redis DECR errors fall back to enqueuing the
  post-process task instead of returning silently.

- Dead-letter callback: when DocumentProcess / KnowledgePostProcess /
  ManualProcess exhausts retries, immediately mark the corresponding
  Knowledge as failed with the last error. This surfaces the failure
  in the UI without waiting for the housekeeping sweep.

- HousekeepingService: 5-minute cron that flips knowledge rows stuck
  in "processing" past DocumentProcessTimeout + 10m to failed, plus
  summary rows stuck > 1h. Catches anything the other safety nets
  miss (worker SIGKILL mid-handler, etc.). Disable with
  WEKNORA_HOUSEKEEPING_ENABLED=false.

- Distributed startup recovery: previously the post-restart sweep was
  skipped whenever REDIS_ADDR was set, even though Asynq does not
  reschedule the task that was actively running on the dead instance.
  Now the sweep runs in distributed mode too, but only against rows
  older than 30 minutes to avoid racing peer instances.
2026-05-28 15:14:45 +08:00
wizardchen 47a183aa65 feat(system-admin): implement bootstrap for system admin promotion and enhance system settings management
- Added WEKNORA_BOOTSTRAP_SYSTEM_ADMIN_EMAIL environment variable to promote a specified user to system admin on startup.
- Introduced a new bootstrap process in `bootstrap.go` to handle the promotion logic.
- Updated `.env.example` to document the new environment variable and its behavior.
- Created new views for managing system administrators and system settings, including listing, promoting, and revoking admin privileges.
- Enhanced the frontend to reflect the new system admin features, including UI elements for admin management and settings configuration.
- Updated API interfaces to support system admin functionalities, ensuring proper data handling and user management.
2026-05-26 21:13:56 +08:00
Miles Lai 09892ef763 fix(doris): inline LIMIT/OFFSET as literals and enable parameter interpolation
Problem:
Doris does not support ? placeholders for LIMIT and OFFSET clauses, causing
VectorRetrieve, KeywordsRetrieve, and CopyIndices queries to fail at runtime
with SQL parse errors.

Root cause:
1. Query builders passed TopK/pageSize/offset as ? bind parameters (valid in
   MySQL/PostgreSQL but not in Doris's SQL dialect)
2. Doris MySQL driver was not configured to interpolate parameters, preventing
   automatic client-side placeholder replacement

Fix:
1. Enable parameter interpolation in Doris connection DSN:
   - Add &interpolateParams=true to mysql.Open() DSN in container.go
   - This enables driver-level parameter substitution at query time

2. Inline LIMIT/OFFSET as string literals in Doris queries:
   - VectorRetrieve: LIMIT ? → LIMIT %d (params.TopK)
   - KeywordsRetrieve: LIMIT ? → LIMIT %d (params.TopK)
   - CopyIndices: LIMIT ? OFFSET ? → LIMIT %d OFFSET %d (pageSize, offset)
   - Remove inlined values from args slice

Result:
Queries are now built with literal LIMIT/OFFSET values instead of placeholders,
compatible with Doris's SQL parser.
2026-05-26 20:32:49 +08:00
jackson.jia d439b3ae07 feat(builtin-models): add YAML-based declarative config with ${ENV} interpolation
Allow built-in models to be declared in config/builtin_models.yaml
instead of inserting rows via SQL. On every startup the file is read
and each entry is UPSERT-ed into the models table (is_builtin=true)
by stable id.

Any string field may reference an environment variable with ${NAME}.
Unset variables are left as the literal placeholder so
misconfiguration surfaces clearly in provider calls rather than
failing silently with an empty token.

The file is optional: missing file, parse errors, and per-entry
upsert failures all log a warning without aborting startup.
docker-compose.yml adds env_file (.env, required:false) so
deployment-specific variables are passed through automatically.
2026-05-26 11:31:01 +08:00
Li Xianggang b3dbf86bf5 feat(obs): 支持华为云obs存储 2026-05-18 19:38:23 +08:00
wizardchen 884ac44283 feat(invitations): implement pending invitations feature with polling and dialog
Added functionality for managing pending invitations, including a polling mechanism to update the invitation count in real-time. Introduced a new dialog component for users to view and respond to their invitations without navigating away from their current context. Updated API endpoints for fetching and managing invitations, and enhanced the user interface with relevant internationalization support.

Refs: #1303
2026-05-18 17:28:58 +08:00
wizardchen 8332a0dab6 feat(favorites): implement user favorites and recents functionality
Introduced a new API client for managing user favorites, allowing users to list, add, and remove starred resources. Enhanced the sidebar to display favorites and recents, improving user navigation. Updated internationalization files to include relevant labels and tooltips for the new features across multiple languages.

Refs: #1303
2026-05-18 17:28:58 +08:00
wizardchen ff1f03ce0d feat(rbac): daily retention sweep for audit_logs (default 90 days)
The audit_logs table grows monotonically until something purges it.
PR 6 explicitly listed retention as out of scope for v1; this picks
that up.

Adds an `audit.retention_days` config (default 90, 0 disables) and a
small background goroutine `AuditLogRetentionRunner` that fires once
~10 minutes after boot and then every 24h, calling
`AuditLogService.Purge` which DELETEs rows older than the cutoff in a
single statement. The dependency surface is intentionally minimal —
no robfig/cron, no asynq, no migration — because retention has no
wall-clock alignment requirement.

Wiring is the same shape as the existing data source scheduler:
container `Provide(NewAuditLogRetentionRunner)`, an `Invoke` that
calls `Start`, and a `ResourceCleaner.RegisterWithName` for graceful
shutdown.

Defaults preserve operator intent:
  - `audit:` section omitted from YAML  -> retention_days=90.
  - explicit `audit.retention_days: 0` in YAML  -> purge disabled.
  - `WEKNORA_AUDIT_RETENTION_DAYS=N` env override (incl. N=0).
  - `retention_days < 0` is rejected by ValidateConfig.

Tests cover the service Purge contract (no-op when disabled, cutoff
math, error propagation) and the runner lifecycle (Start no-op when
disabled, idempotent Start/Stop, ticker cadence, runOnce swallows
errors). 10 new tests, all green.

docs/rbac.md updated with the new YAML / env / behaviour.

Refs: #1303
2026-05-18 17:28:58 +08:00
wizardchen 766a6c482f feat(rbac): per-tenant audit log for RBAC events (PR 6, #1303)
PR 1-5 of the multi-tenant RBAC series enforce the role matrix; what
they don't do is keep a durable record of who did what. Today the
RBAC middleware logs "[rbac] role insufficient ..." to stderr -
perishable, not searchable. Operators cannot answer "who removed
Alice from tenant T-foo on Tuesday" or "did we 403 a probing user
200 times last hour" after the fact.

This PR adds a generic per-tenant audit log that:

- Captures mutating RBAC actions (member add/remove/role-change/leave)
  durably from the tenant_member service after the repo write succeeds.
- Captures enforcement rejections (RequireRole / RequireOwnershipOrRole
  denies under EnableRBAC=true) via a gin-context-injected hook.
- Sliding-window dedup (1 minute) on (tenant, actor, action, path)
  for denied events so a probing client cannot flood audit_logs.
- Default-on - no extra env flag. Schema is generic enough for future
  KB / agent / datasource events to reuse via new action namespaces
  without another migration.

Schema (migration 000044) mirrors wiki_log_entries' shape: a single
audit_logs table with action, target_type/id, request path/method,
outcome, and a JSONB details column. Three indexes: (tenant_id, id
DESC) for the per-tenant cursor feed, actor_user_id for "what did
Alice do", (tenant_id, action) for both the action filter and the
dedup lookup. Sqlite mirror added for Lite mode.

Wiring is nil-safe: the audit field on tenantMemberService and the
gin-context lookup in rbac.go both tolerate a nil service so existing
tests construct without a stub and dormant deployments degrade
gracefully if the provider is misconfigured.

The query API is GET /tenants/:id/audit-log, gated by Admin+ on top
of the existing PathTenantMatch (denial histories should not surface
to ordinary members). Cursor-paginated by descending id (sidesteps
the duplicate-timestamp tie-breaking that BIGSERIAL trivially solves).

Frontend: TenantMembers.vue gets a t-tabs wrapper with Members
(existing) and Audit log (new) tabs; the audit tab is gated to
Admin+ to mirror the server, lazy-loads on first open, paginates via
the next_cursor pattern, and renders coloured chips per
action/outcome so an operator can scan for anomalies. i18n keys
added in all four locales.

Tests: 14 new tests across service (6), middleware (4), and handler
(4). Service tests pin the dedup window behaviour (writes again
after expiry, dedup is per-actor-per-path, degrades on lookup
error). Middleware tests pin both reject sites' audit hook and the
"dormant mode does not fire" + "nil audit does not panic"
invariants. Handler tests pin the cursor envelope and that an empty
page returns next_cursor=0.

Out of scope: per-action ACL on the audit log, retention/TTL job,
KB/agent/datasource event wiring (schema supports it - just no
emitters yet), async writes, frontend filter UI.
2026-05-18 17:28:58 +08:00
wizardchen 3f7150cb5c feat(rbac): tenant member management + invite_only gate (PR 3 of 3, #1303)
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.
2026-05-18 17:28:58 +08:00
wizardchen 7f7a48880f feat(rbac): add tenant_members schema and auth wiring (PR 1 of 3, #1303)
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.
2026-05-18 17:28:58 +08:00
ochan.kwon 0e8de6192c feat(knowledge-base): validate vector store bindings on create, copy, and delete
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.
2026-05-18 15:58:46 +08:00
wizardchen 7643dd457e refactor(credentials): introduce /credentials subresource pattern
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.
2026-05-17 15:27:52 +08:00
ochan.kwon 7478e3cddb refactor(retriever): introduce factory for KB-scoped retrieve engine resolution
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.
2026-05-14 15:53:58 +08:00
wizardchen 1f5970b67e refactor(agent): rebuild multi-turn history from DB, drop llmcontext layer
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.
2026-05-12 12:26:24 +08:00
wizardchen 1110615300 feat(web-search): add SearXNG provider (#1166)
支持对接自建/公共 SearXNG 实例作为网络搜索引擎,缓解免费搜索引擎在国内
网络环境下访问受限的问题。

- types: 新增 WebSearchProviderTypeSearxng 与 BaseURL 参数字段;
  类型元数据新增 RequiresBaseURL,前端可动态渲染 Instance URL 表单。
- infrastructure/web_search/searxng.go: 调用 /search?format=json,强制
  utils.ValidateURLForSSRF 校验 base_url,可选 api_key 透传给反代鉴权。
- service: isValidProviderType 与参数校验接入 searxng。
- container: 注册 NewSearxngProvider 工厂。
- frontend: WebSearchSettings 表单根据 requires_base_url 渲染 Instance
  URL 输入框;编辑回填、free 判定同步更新。
- docker: 新增可选 searxng 服务(profile=searxng/full),附带最小化
  settings.yml(启用 JSON 格式、关闭 limiter、关闭遥测),
  docker-compose 默认 SSRF_WHITELIST 包含 searxng 容器名。
- .env.example: 补充 SEARXNG_PORT / SEARXNG_SECRET 说明。

Closes #1166
2026-05-11 16:53:47 +08:00
wizardchen 5510ea8f5a feat(agent): human-in-the-loop approval for MCP tool calls (#1173)
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).
2026-05-10 22:57:12 +08:00
wizardchen 04e8105728 perf(wiki-ingest): scale to 4w-doc KBs + generic task queue / dead-letter
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.
2026-05-10 00:01:06 +08:00
langcaiye 74b1342440 feat: add Tencent VectorDB retriever backend 2026-05-09 13:14:01 +08:00
wizardchen fc6f160eff fix(retriever/doris): code review cleanup
针对 4cce6f2e(接入 Apache Doris)的 code review 修复,主要修正若干阻断性
问题与可读性问题,并剔除不应进入主仓的本地工作流文件。

阻断性修复:
- docker-compose: Doris 镜像由 2.1.0 升至 4.1.0。原 2.1.0 不支持 HNSW
  ANN、cosine_distance_approximate 与 Stream Load partial_columns,
  按当前 DDL 一启动就会失败。
- DSN 字面量拼接改用 mysql.Config.FormatDSN()。原 fmt.Sprintf 在用户名/
  密码包含 `@`/`:`/`/` 等字符时会跑偏。覆盖 health check 与 engine
  factory 两处。

健壮性修复:
- 新增 validateEmbedding,写入与查询前拒绝 NaN/±Inf;strconv.FormatFloat
  对非有限值会输出 "NaN"/"+Inf" 拼成无效 SQL。
- waitANNReady 改为后台 goroutine + 独立 context,避免新维度首次写入路径
  阻塞最长 30s;ANN 未就绪时 Doris 会自动退化为 brute-force。

清理:
- annIndexReady 移除最终两个分支都 return true 的冗余写法。
- Save 移除冗余的双重 toDorisVectorEmbedding。
- testDorisConnection 把 "5.7.99 Doris-4.1.0" 解析为裸 "4.1.0",与
  Postgres/ES 的版本格式对齐。

剔除(不应合入主仓):
- docs/wiki/集成扩展/Doris改动与上游同步.md:纯 fork 维护工作流文档。
- scripts/e2e-doris.sh:作者本地 E2E 验证清单。

测试:
- repository_test 用 require.Eventually 适配 ANN 异步轮询。
- 现有 doris 单测全部通过。
2026-05-09 00:31:03 +08:00
issunion 4cce6f2e99 feat(retriever): 接入 Apache Doris 4.1 作为向量数据库
为 RetrieveEngine 体系新增 Doris 后端,与现有 Qdrant/Milvus/Weaviate
等保持完整能力对齐:向量检索、关键词检索、健康检查、环境变量与多实例
DB 配置、前端类型注册、单元测试、Docker Compose 模板。

实现要点:
- 协议分工:主链路用 MySQL 协议(database/sql + go-sql-driver/mysql)
  做 DDL / 查询 / 删除;批量更新走 Stream Load HTTP API,并启用
  partial_update=true、merge_type=APPEND,自动按 1MiB 切分批次并处理
  307 重定向。
- 表结构:UNIQUE KEY(id) + enable_unique_key_merge_on_write=true 以
  支持 upsert/部分列更新;按维度分表(<base>_<dim>),每张表上建
  HNSW ANN 索引(metric_type=cosine_distance)和 INVERTED 索引
  (parser=chinese)。
- 分数语义:使用 cosine_distance_approximate,再以 1 - dist 转换为
  "越大越相似",与现有 KVHybridRetrieveEngine 约定一致。
- 异步索引:ANN 索引为后台构建,ensureTable 通过轮询 SHOW INDEX 等
  待索引就绪后再放行写入,避免首次检索召回为空。
- ARRAY<FLOAT> 序列化:go-sql-driver/mysql 不支持数组占位符,
  embeddingLiteral 将 []float32 转成 SQL 字面量字符串再拼接。

新增文件:
- internal/application/repository/retriever/doris/{structs,schema,
  query,repository,streamload,repository_test}.go
- scripts/e2e-doris.sh:E2E 验证清单
- docs/wiki/集成扩展/Doris改动与上游同步.md:fork-and-rebase 工作流
  与改动清单

修改文件(接线 + 文档):
- internal/types/{retriever,tenant,vectorstore}.go:新增
  DorisRetrieverEngineType、env 解析、表单 schema 与索引参数校验
- internal/container/{container,engine_factory}.go:环境变量驱动
  与 VectorStore 配置驱动两条路径都支持 Doris
- internal/application/service/vectorstore{,_healthcheck}.go:连接
  校验 + Ping/Version 健康检查
- docker-compose.yml:新增 doris-fe / doris-be 服务(profile=doris)
- .env.example:DORIS_* 环境变量与示例
- docs/{使用其他向量数据库,wiki/集成扩展/集成向量数据库}.md:
  使用说明与索引/分数行为说明

依赖:go.mod/go.sum 新增 github.com/go-sql-driver/mysql(运行时)和
github.com/DATA-DOG/go-sqlmock(测试)。

测试:repository 层 SQL 形状、Stream Load HTTP 行为、whereBuilder
逻辑、embeddingLiteral 往返、健康检查错误路径均有单测覆盖。
2026-05-08 21:59:35 +08:00