Commit Graph

1243 Commits

Author SHA1 Message Date
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 76a8092483 refactor(task_queue): enhance claim handling and test coverage
- Renamed TestTaskPendingOps_ClaimBatch_NewSiblingRowNotDoubleClaimed to TestTaskPendingOps_ClaimBatch_LateSiblingBlockedByFreshClaim for clarity on behavior.
- Added new test TestTaskPendingOps_ClaimBatch_LateSiblingClaimableAfterStale to verify claim behavior when a holder crashes.
- Updated ClaimBatch logic to ensure that fresh claims block late siblings entirely, maintaining serialization of same-document operations.
- Improved comments in task_queue.go to clarify the handling of concurrent claims and the implications of the claimed_at field.
- Added crash safety mechanism in ProcessWikiIngest to release claims on abnormal exits, ensuring timely re-claims of pending operations.
2026-07-09 17:41:07 +08:00
wizardchen 60f7f35e40 fix(wiki): recover stranded claims and prevent finalize double-run
- claim/peekPendingList now surface DB errors so a transient load
  failure retries via asynq instead of acking as a false "no pending
  ops" success that strands the queue.
- no_pending_ops now arms a coalesced stale-claim recheck (TaskID
  keyed, delayed past wikiClaimStaleAfter) so rows held by a crashed
  batch's fresh claim are reclaimed automatically instead of sitting
  unclaimable and never re-triggered.
- ProcessWikiFinalize fails CLOSED on a SetNX error (returns an error
  to retry) instead of running unlocked, avoiding two finalize runs
  double-rebuilding the index page.
2026-07-09 17:41:07 +08:00
wizardchen c8a4fd5ba3 fix(wiki): prevent silent work loss and cross-batch doc races
Two correctness fixes on the Phase 3 concurrent claim-based ingest path:

- Slug-lock timeout / reduce failure no longer silently drops work. When a
  per-slug lock can't be acquired within wikiSlugLockWait, or reduce returns
  an error, the page's read-modify-write never lands. Previously the owning
  document was still counted as successful and its pending row was deleted at
  trim time, permanently losing the contribution (finalize only rebuilds the
  index / cross-links, it does not re-run reduce). Such documents are now
  folded into failedOps: their rows stay queued, their finalizing slot is
  held, and requeueFailedOps' fail_count budget retries them (dead-lettering
  a permanently hot/broken slug).

- ClaimBatch now claims by dedup_key affinity so a document is never split
  across concurrent batches. limit counts distinct dedup_keys (documents),
  and ALL eligible rows sharing a key are claimed together. On Postgres the
  per-key anchor row is locked with FOR UPDATE SKIP LOCKED, handing
  concurrent claimers disjoint key sets. This restores in-document ordering
  (e.g. ingest-then-retract collapses correctly) that the per-batch dedup
  could not guarantee once the exclusive per-KB lock was removed, preventing
  a stale ingest from resurrecting a retracted document.

Adds repository tests for same-key affinity and in-flight sibling rows.
2026-07-09 17:41:07 +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
wizardchen 7642117b70 fix(im): harden DingTalk file download with SSRF checks and pictureDownloadCode fallback
Validate temporary download URLs against allowed DingTalk CDN hosts before fetching,
and accept pictureDownloadCode when downloadCode is absent so image messages ingest reliably.
2026-07-09 15:38:13 +08:00
nullkey a6ff0036b5 fix(im): ingest DingTalk file/image messages into knowledge base (#1771)
The DingTalk adapter only ever classified incoming messages as text and
did not implement FileDownloader, so files sent to the bot were never
saved to the channel's configured knowledge base — unlike WeCom, which
worked. Users saw the file received and read, but never stored.

Parse file/picture msgtypes in both the webhook and stream paths (set
MessageTypeFile/Image, FileName, FileKey=downloadCode, robot_code), and
implement DownloadFile: exchange the downloadCode for a temporary URL via
robot/messageFiles/download, then fetch it. robotCode comes from the
callback (webhook) or the app client ID (stream). Pictures get a
MsgID-derived name, mirroring the WeCom adapter.
2026-07-09 15:28:57 +08:00
wizardchen b6d3420a5d fix: harden document pipeline concurrency and diagnostics
- docreader: serialize all pdfium access behind a global lock. pypdfium2
  is process-global and not thread-safe, so concurrent PDF uploads could
  corrupt its shared state and deadlock the whole process (requests stuck
  in "Parsing document" forever). Non-PDF parsers still run concurrently.
- logger: strip ANSI color escapes from file logs so on-disk logs stay
  plain text while stdout keeps terminal colors.
- storage: log baseDir/resolvedPath on file-open failure and when the
  multimodal service resolves a file service, so a LOCAL_STORAGE_BASE_DIR
  mismatch between writer and reader is immediately visible.
- docker: set TZ (default Asia/Shanghai) for the docreader container.
2026-07-09 13:26:40 +08:00
wizardchen 6ac1703198 Simplify KB duplicate API and improve naming/docs coverage.
Drop client-supplied target_id, generate IDs server-side, localize duplicate
names from request language, document the endpoint, and expand handler/client tests.
2026-07-08 20:55:54 +08:00
wizardchen 58b79876ae Add knowledge base duplicate flow 2026-07-08 20:55:54 +08:00
wizardchen a1b49e2664 fix(faq): guard against division by zero in import timing logs
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-08 15:27:51 +08:00
wizardchen d9bb7aa8f2 fix(search): harden tag scope resolution after #1907
Default missing KB metadata to document tag relation lookup, propagate tag resolution failures instead of returning empty results, and reject ambiguous bare tag_ids when multiple knowledge bases are in scope.
2026-07-08 10:55:42 +08:00
wizardchen 3209ed77fd feat(quick-qa): add references drawer and polish retrieval source UI
Add a side panel for web and knowledge-base citations with citation-badge
highlighting, refine collapsed RAG pipeline summary layout, and emit
knowledge_base_id from agent knowledge_search results.
2026-07-08 00:26:34 +08:00
wizardchen 45eab4a95f fix(quick-qa): distinguish web and knowledge base retrieval in pipeline UI
Emit search_source metadata from RAG progress events so quick-answer steps,
summaries, and IM labels no longer mislabel web-only results as knowledge base search.
2026-07-08 00:26:34 +08:00
wizardchen 77cf6a5789 fix(web-search): polish Keenable provider integration after #1946
Expose optional API key in settings UI, map longer API snippets into Content
for RAG, align maxResults fallback with other providers, sync Swagger enum,
and add follow-up unit tests.
2026-07-07 17:14:39 +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 974231190c Add API key member and space capabilities 2026-07-07 12:00:13 +08:00
wizardchen d60614475e test(api-keys): add unit tests for tenant API key validation
Introduce unit tests for the tenant API key validation logic, ensuring that scoped keys require capabilities, while full-access keys are validated without them. The tests cover various scenarios, reinforcing the expected behavior of the API key validation function.
2026-07-07 12:00:13 +08:00
wizardchen 2c6f082062 Refine scoped API key capabilities 2026-07-07 12:00:13 +08:00
wizardchen b5cc7d2a28 feat(api-keys): implement throttled last_used_at updates for API key authentication
Enhance the tenant API key service by introducing asynchronous throttling for the last_used_at updates during API key authentication. This change reduces database write frequency under high request rates, improving performance. Additionally, update tests to validate the throttling behavior, ensuring that last_used_at is only updated once per key within the defined interval. This implementation aligns with the goal of optimizing API key management and maintaining system efficiency.
2026-07-07 12:00:13 +08:00
wizardchen 97c36f634a refactor(api-keys): remove API key reset endpoint and update documentation
Eliminate the POST /tenants/{id}/api-key endpoint for resetting tenant API keys, transitioning to a more granular API key management approach. Update related documentation and API specifications to reflect the new structure, including changes to the tenant API key management paths. Adjust frontend code and internationalization files to remove references to the deprecated API key reset functionality, enhancing clarity and consistency across the application.
2026-07-07 12:00:13 +08:00
wizardchen 1d1e1e3d25 refactor(api-keys): update role handling and enhance API key restrictions
Change the default role for tenant API keys from 'admin' to 'owner' to align with the new authorization model. Update related tests to reflect this change, ensuring that API keys with the owner role are correctly denied access to management paths and system-admin routes. Introduce new tests to validate that API keys are properly restricted from accessing sensitive endpoints, reinforcing the security measures in place.
2026-07-07 12:00:13 +08:00
wizardchen a6759d61b5 feat(api-keys): implement DenyAPIKeyPrincipal middleware and related tests
Add DenyAPIKeyPrincipal middleware to explicitly block API-key principals from accessing certain routes, ensuring security for endpoints outside the /api/v1 group. Introduce tests to validate that API keys are correctly denied access while allowing JWT sessions to pass through. This enhances the overall authorization model by reinforcing the default-deny approach for API keys.
2026-07-07 12:00:13 +08:00
wizardchen d2ffc1b973 refactor(api-keys): simplify authorization to a single-role gate
Redesign tenant API key authorization around one dimension (role) plus a
central default-deny gate, replacing the previous role + KB-scoped flag model.

- Add APIKeyGate as the single authority for API-key authorization: routes
  declare one policy (MinRole) via apiKeyGroup/apiKeyRoute helpers; undeclared
  routes are denied by default. JWT principals short-circuit the gate and the
  JWT-centric RBAC guards short-circuit for API-key principals.
- Roles: viewer/contributor/admin are knowledge-base data-plane only (KB scope
  is a pure downstream data filter); owner is a full-access tenant tier that
  unlocks tenant-level infrastructure routes and is required for every method.
- Drop the KBScoped policy flag and the KB-restricted-vs-tenant branching.
- Security hardening: never disclose HMAC secret (return presence only), abort
  writes on API-key encryption failure, deny KB-restricted keys on /files, and
  backfill legacy key hashes at startup instead of O(N) plaintext scans.
- Frontend: two-level create dialog (access type -> permission level), rename
  role labels to reflect actual scope, sync en/zh/ko/ru locales.
- Fix startup self-check false-positive on trailing-slash routes and normalize
  gin paths before comparison; add regression tests.
2026-07-07 12:00:13 +08:00
wizardchen fedb6c3f7e test(api-keys): add tests for tenant API key management path rejection
Introduce tests to validate that tenant API keys are correctly restricted from accessing management paths. Implemented new test cases for both allowed and forbidden paths, ensuring proper enforcement of API key scopes. Additionally, refactored existing tests to utilize the new rejection logic.
2026-07-07 12:00:13 +08:00
wizardchen 9a76a24ce6 refactor(api-keys): use role field and route-level API key guards
Replace scopes JSON with a viewer/contributor/admin role column, move
unsafe-method authorization from path-prefix middleware to declarative
APIKey* guards on routes, and close remaining KB-scope gaps in handlers.
2026-07-07 12:00:13 +08:00
wizardchen c65ffa3d9c fix(api-keys): enforce scope from request context after attach
Use c.Request.Context() in authenticateAPIKeyRequest so scoped keys are
actually restricted, update dto tests for removed tenant.api_key, and add
a regression test for the attach-context contract.
2026-07-07 12:00:13 +08:00
wizardchen 94d18ea15a fix(api-keys): close KB scope gaps in handlers and CloneContext
Enforce per-key knowledge base restrictions on batch/search read paths,
centralize scope checks in shared KB access validators, and propagate
TenantAPIKeyScope through logger.CloneContext so async QA cannot bypass it.
2026-07-07 12:00:13 +08:00
wizardchen 3f516d7f31 fix(api-keys): harden scoped key auth after code review
Revoke existing keys on reset, unify scope enforcement, default empty
scopes to read-only, map API key scopes to tenant roles, and remove dead
key-generation helpers left over from the tenant api_key column removal.
2026-07-07 12:00:13 +08:00
wizardchen 505bc7ddec feat: add scoped tenant api keys 2026-07-07 12:00:13 +08:00
langcaiye 1708d6895a fix(search): apply tag filters to knowledge search 2026-07-06 23:30:33 +08:00
cao_j b16cb0bb56 fix(agent): treat end_turn as natural stop 2026-07-06 23:16:18 +08:00
养乐多 baada32cb6 fix(im/feishu): actually close WebSocket long connection when channel is stopped
Deleting or disabling a Feishu channel left its WebSocket long connection
alive: the Lark SDK's Start blocks on a bare select{} and never observes
ctx, and v3.6.1 exposed no public Close(), so the wsCancel() cleanup was a
no-op. The socket stayed open, the SDK kept auto-reconnecting, and Feishu
kept pushing messages — causing cross-environment message duplication when
the same bot was bound elsewhere.

Fix in three layers:

1. Connection teardown
   - Upgrade oapi-sdk-go v3.6.1 -> v3.9.7 (adds Client.Close()).
   - Add LongConnClient.Close() wrapping wsClient.Close(); factory's cleanup
     now calls Close() first, then wsCancel() as a belt-and-braces fallback.

2. Multi-instance coordination
   - wsLeaderRetryLoop: after acquiring leadership, re-check the DB before
     starting; abort if the channel was deleted/disabled while waiting.
   - wsLeaderRenewLoop: on each renewal, re-check the DB; step down if the
     channel was deleted/disabled on another instance (HTTP request may have
     been served elsewhere), so the leader doesn't keep the connection open
     until process restart.

3. Robustness
   - DB checks distinguish gorm.ErrRecordNotFound (channel truly gone ->
     stop/abort) from transient DB errors (skip this round, retry next tick)
     so a DB hiccup can't cause a spurious stop or permanent leader-abort.
   - startChannelInternal now stops any existing channelState for the same
     ID before overwriting, making it idempotent against concurrent start
     paths and preventing adapter/long-connection leaks.

No interface changes; webhook and long-poll modes unaffected.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-06 23:10:45 +08:00
wizardchen 4f2dca0b63 fix(redis): harden TLS tests and surface TLS config at startup
Isolate Redis TLS unit tests from parent-process env vars and log
REDIS_USE_TLS settings at boot so misconfiguration is easier to spot.
2026-07-06 23:04:52 +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
nullkey 445a4330fa fix(server): case-insensitive doc keyword search + not-found classification
Make document keyword search case-insensitive (LOWER(...) LIKE LOWER(?)) in the
list filter and SearchKnowledge / SearchKnowledgeInScopes paths so a query and
its differently-cased variant return the same results.

Classify not-found consistently as HTTP 404 (not 500) so clients read a
permanent resource.not_found instead of a retryable 5xx: map the document /
chunk not-found sentinels in the KB-access middleware (typed ErrChunkNotFound
via errors.Is), and return 404 for a missing message on the continue-stream and
message-delete endpoints.
2026-07-06 22:53:01 +08:00
wizardchen 1b0502e562 fix(feishu): upload card markdown images 2026-07-06 14:52:29 +08:00
wizardchen 1661827d6e fix(security): harden model client redirects 2026-07-02 19:15:46 +08:00
wizardchen 663d13eb58 fix(security): harden outbound requests and file previews 2026-07-02 19:15:46 +08:00
wizardchen 7099a7e181 fix(security): redact IM list credentials and harden MinerU SSRF
Stop returning bot credentials from Viewer-accessible IM channel list
endpoints and validate self-hosted MinerU URLs at config save and fetch time.
2026-07-02 17:58:20 +08:00
wizardchen 235e86b876 fix(security): harden refresh token validation and add auth tests
Reject refresh attempts when the DB token type is not refresh_token,
and add service-layer tests for bearer refresh rejection, logout
revocation, and expired-token logout handling.
2026-07-02 17:08:17 +08:00
wizardchen 040504447e fix(security): block refresh tokens as bearer and sandbox MCP uploads
Reject refresh JWTs in ValidateToken, revoke all user sessions on logout,
and restrict create_knowledge_from_file to allowed directories on network MCP transports.
2026-07-02 17:08:17 +08:00
wizardchen cd65665894 fix(security): close remaining GHSA gaps from security triage
Block scheme-prefixed loopback storage checks, validate Notion attachment
URLs, sanitize wiki markdown HTML, and require MCP_SERVER_AUTH_TOKEN for
network MCP transports.
2026-07-02 15:03:53 +08:00
wizardchen f23c674bad fix(security): close six open GHSA findings from security triage
Harden share-link listing, password rotation, OIDC callback binding,
org invite search, knowledge batch mutations, and connector redirects.
2026-07-02 15:03:53 +08:00
wizardchen fc64751f4e fix(security): close init config and parser-check redaction gaps
Strip model base URLs from viewer-accessible initialization config
responses and merge redacted parser secrets before engine check overrides
so admin test flows keep working after masked GET responses.
2026-07-02 14:41:42 +08:00
wizardchen 1a264e09c1 fix(security): harden secret redaction follow-ups for PR #1884
Restore PreserveIfRedacted merge on tenant KV PUT so Admin settings saves
no longer overwrite stored secrets with placeholder values. Redact cross-
tenant tenant listings, tighten Viewer MCP/model responses, and align init
config frontend types with credentials metadata.
2026-07-02 14:41:42 +08:00
wizardchen 512d2e5c25 fix(security): redact secrets in login and tenant KV update responses
Apply the same tenant/integration secret policy to auth login, OIDC
callback, switch-tenant, and invite-register payloads, and return masked
config objects from Admin-only tenant KV PUT handlers.
2026-07-02 14:41:42 +08:00
wizardchen 0b73080bb8 fix(security): redact integration secrets from viewer-accessible endpoints
Prevent low-privileged tenant members from reading raw API keys and
infrastructure credentials via tenant profile, KV config, model/MCP/web
search listings, and KB initialization config responses.
2026-07-02 14:41:42 +08:00
wizardchen 8325dac738 fix(security): harden web_fetch and datasource connector SSRF paths
Use SSRF-safe HTTP clients in chat pipeline web_fetch and Feishu/Yuque/Notion
connectors, validating tenant-supplied base_url values before outbound requests.
2026-07-02 12:27:48 +08:00