Commit Graph

1356 Commits

Author SHA1 Message Date
wizardchen 84f65a809f fix(agent): ensure wiki summary slugs are preserved during citation compaction
This update addresses the issue where wiki summary-page slugs (summary/<knowledgeID>) were being mangled during the citation compaction process, leading to dead links. The changes include:

- Reordering the message encoding process to ensure resource references are aliased before source references, preventing the UUID from being replaced in the summary slug.
- Implementing a new function to selectively replace document IDs while preserving the integrity of summary slugs.
- Adding unit tests to verify that summary slugs remain intact and are not altered during compaction.

This fix enhances the reliability of cross-links in the wiki system and prevents potential dead links from being generated.
2026-07-24 15:57:08 +08:00
wizardchen 5d0326f987 fix(wiki): harden slug integrity across ingest and agent write paths
Weak LLMs routinely mangle high-entropy wiki slugs (especially UUID-based
summary/<id> slugs), producing dead cross-links and cross-item dedup
hallucinations. This tightens integrity end to end:

- Ingest dedup now groups each new item with only its own trigram
  candidates and validates merges against that per-item scope, rejecting
  cross-item mispairings; candidate top-K narrowed 20 -> 5.
- Editor path aliases out-link slugs behind low-entropy ref-N tokens and
  translates them back after generation, removing the chance to mangle.
- Agent write tool normalizes/validates slugs, blocks manual creation of
  system-owned summary pages, and auto-repairs dead [[slug]] links
  (rewrite-only, never strips) via bigram/display-text resolution.
- llmresource registry aliases summary/<uuid> slugs the same way as
  storage handles so they round-trip safely through chat.

Adds unit tests for slug validation, aliasing round-trip, dead-link
repair, and dedup rejection rules.
2026-07-24 15:57:08 +08:00
wizardchen d283fabc99 fix(doris): harden Stream Load HTTP with SSRF-safe client
Doris Stream Load previously used a plain http.Client, leaving FE→BE
redirects and stored FE URLs without outbound SSRF checks. Use the shared
SSRFSafeHTTPClient, validate URLs at send time, and only forward Basic
credentials to whitelisted BE hosts after FE 307 redirects.
2026-07-24 15:10:44 +08:00
wizardchen 50eb48c344 fix(org): disambiguate shared-space terms and tighten invite search
Search tenants for invite by workspace name only (a user may belong to
multiple workspaces, so username/email matching was ambiguous). Align
organization i18n to distinguish shared spaces from workspaces, fix the
duplicate zh-CN members key, and wrap invite-code generation response in
data so the frontend and Go SDK can read it.
2026-07-24 11:42:27 +08:00
Jack Wang 43839f7830 fix(agent): honor suggested-questions limit parameter
Treat limit as the authoritative upper bound instead of clamping it down
to the agent's Starters.Count, so ?limit=N no longer always returns 6.

Fixes #2238
2026-07-24 10:46:53 +08:00
wizardchen 8cb43473e6 fix(knowledge): restrict source file download to Editor and above
Downloading exposes the original source file, which is more sensitive than viewing parsed content or previews. Align backend route guards, handler checks, and frontend UI so tenant Viewers and org-shared read-only access cannot download.
2026-07-23 22:19:39 +08:00
wizardchen c28cd05c0c fix(models): align model debug upload limit with global MAX_FILE_SIZE
Use the deploy-time file size configuration for model debugger uploads
instead of a hardcoded 20 MB cap, and validate file size on the frontend
before sending the request.
2026-07-23 19:43:06 +08:00
wizardchen 6fb858105a feat(llm): add prompt-cache observability and wiki cache-friendly prompts
Normalize provider-specific cache counters into TokenUsage, propagate call
purpose and prefix fingerprints through context for logging and Langfuse,
and restructure wiki page-modify prompts with warmup/singleflight to improve
prefix cache hit rates during reduce batches.
2026-07-23 19:17:30 +08:00
wizardchen 6c794f64cf feat(runtime): add bulk purge for archived queue tasks and chat_attachment i18n
Operators can clear all finally-failed tasks in one queue from the runtime
drawer, with audit logging and scoped API access. Also localize the
chat_attachment queue label in the runtime queue details table.
2026-07-23 16:52:35 +08:00
ttommybot a287808597 fix: prevent API keys from assigning owner role 2026-07-23 16:04:42 +08:00
wizardchen 8ae82573ab fix(mcp): coordinate OAuth token refresh and authorization polling
Prevent concurrent refresh-token rotation across instances, distinguish
expired-but-refreshable tokens from active authorization, and bind OAuth
popup polling to a per-attempt ID so stale tokens cannot satisfy new consent.
2026-07-23 15:35:24 +08:00
lhy c74b0caa35 fix(task-inspector): handle lazy queue not found errors 2026-07-23 14:24:21 +08:00
wizardchen 0869f3e829 fix(im): harden Yunzhijia image download and prune dead validation
- Follow a single download redirect while re-validating the target stays
  within the allowed host suffix; never forward the bearer token across it.
  The shared http client disables auto-redirects for SSRF safety, so a 302
  from downloadfileOpen previously failed the download outright.
- Cap in-memory download size at 32 MiB via a limited read-closer that
  errors instead of silently truncating, avoiding OOM on large responses.
- Remove dead frontend host-suffix validation branch (normalize always
  fills the default) and drop the now-unused i18n keys
  yunzhijiaAllowedHostSuffixRequired / yunzhijiaRequiredCredentials.
- Add tests for redirect follow/reject and the size limit.
2026-07-23 12:41:19 +08:00
jacentsao 85c9b61ad0 feat(im): support Yunzhijia image messages 2026-07-23 12:25:51 +08:00
wizardchen 986a6f3699 fix(tasks): detach KB deletion queue cleanup from request ctx
Run the synchronous best-effort queue scrub in DeleteKnowledgeBase with
context.WithoutCancel and kbTaskCleanupTimeout so client disconnects
cannot truncate cancellation mid-scan, matching ProcessKBDelete cleanup
semantics.
2026-07-23 12:20:03 +08:00
zhangzherui 37de0afad0 fix(tasks): dequeue work for deleted knowledge bases 2026-07-23 12:17:14 +08:00
zhangzherui 7fde37eeeb fix(search): validate hybrid search query text 2026-07-23 12:05:57 +08:00
wizardchen 146e341748 refactor(http): share SSRF-safe transport across model clients
Extract NewSSRFSafeTransport and NewSSRFSafeHTTPClientWithTransport so
embedding and rerank can reuse one connection pool without allocating a
throwaway transport per client. SSRF dial and redirect policies are
unchanged; each client still keeps its own timeout.
2026-07-23 12:00:05 +08:00
zhangzherui ccf02e1a2a fix(embedding): reuse SSRF-safe HTTP transport 2026-07-23 11:51:54 +08:00
wizardchen 8ca9c117bb feat(knowledge): enhance FAQ entry filtering and tagging
- Updated the listFAQEntries function to support multiple tag IDs for filtering.
- Modified the frontend components to accommodate the new tag_ids parameter.
- Enhanced the KbTagManageDrawer and FAQEntryManager components to reflect changes in tag handling.
- Improved API documentation to clarify the new tag filtering capabilities.

This commit enhances the flexibility of FAQ entry retrieval, allowing users to filter by multiple tags for more precise results.
2026-07-23 10:50:32 +08:00
wizardchen b6a3b347da feat(knowledge): enhance FAQ export functionality
- Updated the exportFAQEntries function to support exporting FAQ entries in both CSV and JSON formats.
- Modified the frontend to include options for selecting the export format.
- Enhanced localization files to reflect the new export options in English, Russian, and Chinese.
- Implemented new tests to validate the export functionality for both formats.

This commit improves the flexibility of FAQ exports, allowing users to choose their preferred format for better integration with other tools.
2026-07-23 10:50:32 +08:00
wizardchen 135033e6df feat(knowledge): enhance FAQ import result tracking and UI
- Added new fields for tracking added, merged, and partially failed entries during FAQ imports.
- Updated the import result statistics to include detailed counts for added and merged entries.
- Enhanced the UI to display progress hints and improved import result summaries.
- Implemented a new method for saving chunks in a single transaction to improve performance.

This commit improves the visibility and accuracy of FAQ import results, providing better user feedback and tracking capabilities.
2026-07-23 10:50:32 +08:00
wizardchen 5af8eae81d feat(knowledge): enhance activity logging for FAQ imports
- Added new actions for FAQ import lifecycle: `faq.import_started`, `faq.import_completed`, and `faq.import_failed`.
- Updated activity details to include success, failure, and skipped counts for FAQ imports.
- Enhanced UI to display additional activity information, including filtering options and clearer summaries.
- Implemented tests to validate the new FAQ import outcomes and activity details.

This commit improves the tracking and visibility of FAQ import activities within the knowledge base, ensuring better audit trails and user feedback.
2026-07-23 10:50:32 +08:00
wizardchen a3a0308b62 feat(knowledge): add scoped activity audit trail 2026-07-23 10:50:32 +08:00
wolfkill f195e0494c fix(wiki): support orphan count on sqlite 2026-07-23 10:44:08 +08:00
Changjin Li 8248752e62 修复共享知识库文档预览路径 2026-07-23 10:43:31 +08:00
wizardchen 4c3ae69b49 feat(wiki): prune empty folders after document retract
Automatically remove wiki folders that become empty when knowledge is
retracted, using the durable finalize lane so pruning waits until ingest
drains. Repository DeleteFolder now atomically checks emptiness to avoid
races with concurrent page or child-folder writes.
2026-07-22 19:27:22 +08:00
unknown ab0b1d65b5 fix: correct graph and multimodal processing traces 2026-07-22 17:38:28 +08:00
wizardchen b9b81a6c3c fix(knowledge): stop async delete from leaving visible/zombie rows (#2192)
Two backend fixes for the v0.7.0 regression where a deleted document keeps
showing in the list ('delete success' toast) and a follow-up reparse then
reports the file is missing:

1. List filtering: applyKnowledgeListFilter now hides rows in the transient
   'deleting' state from the default document list. The async delete pipeline
   marks a row 'deleting' before tearing down its resources, so without this
   the entry lingers as a normal doc until it is physically gone. Rows whose
   delete task exhausts retries are flipped to 'failed' by the dead-letter
   callback and stay visible so the failure remains actionable; an explicit
   parse_status=deleting filter can still surface in-flight rows.

2. Delete ordering: DeleteKnowledge / DeleteKnowledgeList now delete the DB
   row FIRST and defer physical file (+ extracted image) cleanup until after
   the row is gone. Previously file removal ran concurrently with the
   index/chunk/graph cleanup; when one of those failed the row was kept but
   the file could already be deleted, producing a 'file missing but row
   present' zombie that could neither be reparsed nor cleanly re-deleted.
   Orphaning a file after the row is gone is the tolerable failure mode.

Adds a repository regression test covering the default/explicit deleting
visibility rules.
2026-07-22 17:30:14 +08:00
wizardchen 0f2c6cee11 fix: normalize API key expiry timestamps to UTC (#2137)
Store authorization timestamps as timestamptz and normalize Unix expiry
inputs to UTC so tenant/platform API keys expire at the intended instant
even when the app process timezone differs from the PostgreSQL session.
2026-07-22 17:09:55 +08:00
wizardchen 554d273cf5 fix(knowledge): copy embedded chunk images into exports namespace
Cloned images were unreachable via GET /knowledge-bases/:id/files:
copyOwnedObject used CopyFile, which writes to the knowledge-scoped upload
layout ({tenant}/{knowledgeID}/...), but the KB proxy only serves objects
under {tenant}/exports/ (ValidateKBScopedStoragePath). Read the source
bytes and re-save via SaveBytes instead, mirroring how images are
persisted during ingestion, so copies land in the servable exports
namespace and remain independent of the source object.
2026-07-22 15:27:11 +08:00
wangke.2002 2e540654f1 feat: 修复IM问答无法读取session的问题 2026-07-22 14:25:55 +08:00
wizardchen 1d37b90a17 fix(knowledge): rewrite parent text chunk image URLs via global pass
For document knowledge, extracted images live in independent image_ocr/
image_caption child chunks that carry image_info, while the parent text
chunk embeds the ![](url) reference with an empty image_info. Rewriting
content per-chunk therefore missed the parent text chunk, leaving it
pointing at soon-to-be-deleted source storage.

Move content URL rewriting to a final pass over all cloned chunks, run
once urlCache holds the complete old->new mapping. FAQ chunks are
self-contained, so they are rewritten inline from the same cache.
2026-07-22 14:22:58 +08:00
wizardchen ac321a3e81 fix(knowledge): rewrite chunk content image URLs on clone
When cloning knowledge chunks, image_info was deep-copied to new storage
objects but Content still embedded the source markdown image URLs. After
the source knowledge is deleted, those in-content references break while
image_info points at the new copies. Rewrite Content alongside image_info
so both stay consistent.
2026-07-22 12:06:31 +08:00
jacentsao 7e7083ce17 feat(im): default markdown format for yunzhijia replies
SendReply now sets param.formatType=markdown by default since WeKnora
replies are authored in Markdown. Callers can override via
reply.Extra["yunzhijia_format_type"] (empty string disables the param).
2026-07-22 11:01:49 +08:00
wizardchen 0d545c8c6a feat(knowledge): implement AminusB function for multiset comparison of knowledge bases
- Added AminusB method to the knowledgeRepository, which returns IDs of knowledge in A that have no counterpart in B, comparing by file_hash as a multiset.
- This implementation addresses issues with handling duplicate entries and NULL file_hash values, ensuring accurate synchronization between knowledge bases.
- Updated the KnowledgeRepository interface to reflect the new functionality and improved documentation for clarity.
2026-07-21 17:44:51 +08:00
wizardchen 23db592c4a feat(api-keys): add platform-scoped API keys for control-plane automation
Introduce platform API keys with capability-based access to tenant management,
system settings, runtime queues, and audit logs, plus admin UI for key lifecycle
and system audit log viewing.
2026-07-21 17:21:35 +08:00
nullkey c695125dce fix(feishu): resilient large-wiki sync — retry, streaming resume, failure visibility
Large Feishu wikis stopped syncing after the first batch (Tencent/WeKnora#2136:
5000+ docs, only ~150 ingested; #1262: a child-list failure aborted the run).
Three compounding causes, fixed in layers:

1. Rate-limit / transient failures had no retry. Feishu's wiki/drive/export
   APIs are aggressively rate limited; a thousand-doc sync issues tens of
   thousands of calls, and a single 429/5xx burst failed whole swathes of docs.
   Add exponential backoff honouring Retry-After to doRequest (JSON) and
   downloadRawBytes (files): 429 up to 3x, 5xx once, transport errors back off.

2. The batch path fetched the entire tree into memory before ingesting, so a
   sync that hit the 2h task timeout lost all progress and restarted from
   scratch, and a transient per-document export failure advanced the cursor and
   skipped that doc permanently. Add an optional StreamingConnector interface,
   implemented for Feishu: FetchStream interleaves fetch -> ingest -> checkpoint,
   bounding memory to one item and persisting a per-node edit-time cursor at
   page boundaries. The service dispatches to it via type assertion; connectors
   without it fall back to FetchAll / FetchIncremental unchanged (non-breaking).
   A resumed/incremental run skips nodes already recorded at their current edit
   time (converges), a failed fetch does not advance the cursor (retried next
   run instead of dropped), and partial listing failures emit error items and
   carry prior edit times forward instead of aborting the sync.

3. Failures and skips were invisible. Unsupported node types (mindnote/slides/…)
   were skipped with no item, error or log ("13 docs synced only 3"). FetchAll
   now tallies discovered/fetched/failed/skipped per resource with a per-type
   skip breakdown and a progress line every 100 nodes. The backend already
   persisted per-item errors in SyncLog.result.errors but the frontend type
   omitted the field; declare `result` on SyncLog and render up to 50 failed
   documents in the sync-log drawer (#1262). i18n for zh-CN/en-US/ko-KR/ru-RU.
   result.errors is a jsonb column shipped in every list response, so it is
   capped at 100 samples server-side (recordSyncError); the exact failure total
   comes from the bounded items_failed counter, which the drawer uses for its
   count and "N more" line so a sync that fails thousands of docs stays bounded.
   Each sample is a structured, localisable SyncItemError instead of a raw
   "title: ...api error: status=500 body={json}" dump that repeated the title
   and leaked status/body/log_id. The connector (feishuFailure) classifies the
   error into a stable i18n code (+ the feishu code as a param); the service
   builds {title, code, params, message}; the drawer localises via vue-i18n to
   the viewer's language (zh/en/ko/ru), falling back to message. A custom
   UnmarshalJSON keeps old string-form logs readable. The banner is localised
   from items_failed too. Raw errors stay in the server logs. Follows the
   two-tier norm of Airbyte/Fivetran/Onyx: human, actionable, localised
   summaries in the UI; raw detail in logs. Transient errors say "will retry"
   (the cursor is retained); auth/permission errors point at the fix instead.

Tests: client_retry_test (backoff), tally_test (accounting), connector_stream /
datasource_stream (streaming dispatch + checkpoint), connector_convergence
(timeout + transient-failure resume converges to full coverage; proven to catch
#2136 via bug injection), datasource_result_cap (error-sample cap + structured
localisable SyncItemError, no raw body), connector_error_reason (error→i18n-code
classification), sync_item_error (legacy-string + structured back-compat) — all
in the normal suite. connector_realapi / connector_seed are an opt-in real-Feishu
harness gated by the feishu_integration build tag AND env vars, never run in CI.
2026-07-21 16:14:22 +08:00
jacentsao 150c07368b feat(im): add Yunzhijia integration 2026-07-21 12:24:33 +08:00
Martín Alcalá Rubí 83da0903b6 fix(rerank): stop sending vLLM truncate_prompt_tokens by default
The generic OpenAI-compatible reranker hardcoded `truncate_prompt_tokens:
511` on every /rerank request. Providers that honor this vLLM-specific
field (e.g. SiliconFlow serving Qwen3-Reranker) keep only the last 511
tokens of the templated rerank prompt, cutting the instruction and query
off any document longer than ~511 tokens. Every relevance score then
collapses to near zero (~0.0067 instead of ~0.998), falls below the score
threshold, and knowledge-base search returns empty results. A direct curl
without the field returns the correct scores.

WeKnora already removed this exact hardcoded parameter from the embedding
path in #960; the rerank path was never fixed.

- Add `omitempty` to `truncate_prompt_tokens` and `additional_data` so
  empty optional fields are not sent.
- Make truncation opt-in via `extra_config.truncate_prompt_tokens`
  (validated > 0 at construction), preserving an escape hatch for
  self-hosted vLLM deployments with small-context rerankers.
- Add regression tests reproducing the collapsed-score symptom and the
  opt-in path.

Fixes #2143
2026-07-21 12:12:56 +08:00
myheart99@126.com e289595054 fix(types): use correct GORM tag separator in Message.KnowledgeReferences
Multiple GORM tag options must be separated by ';', not ','. The comma was
parsed as part of the type value, producing malformed DDL that causes
AutoMigrate(&Message{}) to fail on SQLite with a syntax error.
2026-07-21 12:06:48 +08:00
wizardchen 25ef7b6c68 feat(session): gate IM/embed/API channel sessions behind admin
Restrict channel-managed sessions (API keys, IM, embed) to tenant admin
in the Web console for list/read paths, hide channel sidebar buckets from
non-admins, and add CountSessionsBySource for aggregate stats without
exposing session rows to viewers.
2026-07-20 20:31:54 +08:00
wizardchen b1b42abe23 fix(rerank): batch Volcengine rerank requests over API document limit
Split oversized candidate sets into concurrent batches instead of failing when retrieval exceeds the VikingDB rerank per-request cap, and align ko/ru locale hints with zh-CN.
2026-07-20 20:07:21 +08:00
KKtwo 3011f132e9 feat: support Volcengine rerank 2026-07-20 19:58:48 +08:00
wizardchen d1cab68e3d fix(api-keys): allow scoped file serve and ingest batch routes
Let tenant-wide retrieve keys serve tenant-bounded /files paths while
denying KB-restricted keys, declare knowledge batch write routes for
ingest-capable keys, and short-circuit ownership checks for API-key
principals already authorized by the gate and KB allow-list.
2026-07-20 19:52:13 +08:00
wizardchen 29bec6c613 feat(session): implement strict owner scope for API-key sessions
Add GetOwnedSession method to enforce strict ownership checks for session mutations, ensuring tenant admins can read but not modify API-key sessions. Update relevant handlers to utilize this method for operations that alter session data, maintaining security and integrity of API-key sessions.
2026-07-20 19:31:02 +08:00
wizardchen 76a4ffe525 feat(session): add admin API session bucket and stabilize sidebar filter
Let tenant admins list and open API-key sessions from the Web console while
keeping per-key isolation for everyone else. Pin the session source filter so
it no longer jumps when switching buckets, and resolve session origin on read
so deep links stay in sync with the active folder after refresh.
2026-07-20 19:31:02 +08:00
wizardchen eab91d2f7f feat(web-search): add Zhipu AI web search provider support
Integrate Zhipu's standalone Web Search API with configurable search
engine and content size options, plus settings UI, docs, and tests.
2026-07-20 12:15:35 +08:00
wizardchen 380e371c2e refactor: remove Neo4j-based conversation memory feature
Drop the memory pipeline, API fields, settings UI, and embed toggles so chat no longer depends on Neo4j graph storage for episodic recall.
2026-07-18 23:41:48 +08:00
zhangshuai 7807dee42a fix: stabilize top-k retrieval ordering 2026-07-17 18:42:45 +08:00