Commit Graph

1383 Commits

Author SHA1 Message Date
wizardchen 1fe1f853d5 fix(chat): keep input visible when conversation overflows viewport
The chat layout is a flex column (.chat) inside .platform-route-outlet,
with .chat_scroll_box {flex:1; overflow-y:auto} above .input-container.
Flex items default to min-height:auto, so when messages outgrew the
viewport the scroll box was stretched by its content instead of
scrolling internally. That pushed the input container out of view and
broke page-level scrolling because the parent clips overflow.

- .chat: add min-height:0 so its flex:1 child can shrink
- .chat_scroll_box: add min-height:0 to enable overflow-y scrolling
- .input-container: add flex-shrink:0 so a tall scroll box cannot
  squeeze it to zero height
2026-04-29 17:34:20 +08:00
wizardchen da90867dd4 feat(ui): refactor IM channels list layout and form\n\n- Change IM channel form from dialog to drawer for better UX\n- Convert channel list from vertical layout to responsive grid cards\n- Move edit/delete actions into a dropdown menu for cleaner card design\n- Replace platform radio group with a select dropdown in the add channel form 2026-04-29 17:34:20 +08:00
wizardchen c62ff4c906 fix(frontend): knowledge document list layout, batch bar, and selection
- Platform route outlet: flex min-height so document area is not collapsed
- Card grid: stable :key=item.id; clamp selection anchor after list reload
- DocumentListView: TDesign checkbox, sticky header, neutral file icons
- DocumentBatchBar: column-footer placement; toned style vs floating pill
- Clear selection i18n: less ambiguous wording (e.g. 取消选择)
- Batch delete: poll list refresh after async queue; getKnowled returns Promise
- files.ts: use file icon for text types; align chat/upload icon usage
2026-04-29 15:20:41 +08:00
nullkey a40f191430 fix(knowledge-base): restore hover feedback on selected list rows
The previous list-view tone refinement set the selected-row hover
background to var(--td-brand-color-light), which is aliased to
var(--td-brand-color-1) — the same value used as the static selected
background. Hovering a selected row produced no visible change, leaving
users without feedback for what was clickable.

Use color-mix() to blend brand-color-1 with a touch of brand-color so
the hover delta is visible in both light and dark themes, without
reverting to the saturated brand-color-2 the original code used.
2026-04-29 14:28:56 +08:00
nullkey 48a764b866 refactor(knowledge-base): address review feedback
Backend
- BatchDeleteKnowledge handler now enqueues an asynq
  TypeKnowledgeListDelete task instead of calling DeleteKnowledgeList
  synchronously, matching the pattern used by ClearKnowledgeBaseContents.
  Avoids long HTTP timeouts on large batches and shares the existing
  async cleanup pipeline.
- Extract a small enqueueKnowledgeListDelete helper on KnowledgeHandler
  so BatchDeleteKnowledge and ClearKnowledgeBaseContents share the
  payload/marshal/enqueue boilerplate.

Frontend (DocumentListView)
- softer outer border and lighter row separators
- header background switched to the page tone with placeholder-color
  text, reducing institutional gray
- selected row uses an inset left accent bar and a quieter brand tint
  instead of a saturated background; hover stays neutral
- consolidate the .row-more-btn { opacity: 1 } rule that was duplicated
  across the hover and selected blocks
2026-04-29 12:01:38 +08:00
nullkey be8e53bf08 feat(knowledge-base): add document batch delete and list view
Add a list-view alongside the existing card grid (issue #957) and
multi-select batch delete (issue #1045) for documents inside a knowledge
base. The two views are toggled from the toolbar and the preference is
persisted in localStorage. Selection state is shared between views with
shift-range support and a sticky batch-action bar.

Backend
- POST /api/v1/knowledge/batch-delete: validates KB scope and editor
  permission, then delegates to the existing DeleteKnowledgeList service
  which already cascades vector/file/graph cleanup. Caps batch size at
  200 and uses a single GetKnowledgeBatch call for membership validation.

Frontend
- DocumentListView: table layout with sticky header, checkbox column
  (with indeterminate select-all), file-type icons, status badges,
  per-row action menu.
- DocumentBatchBar: floating pill bar with selected count and delete
  action; appears when items are selected.
- KnowledgeBase.vue: view-mode toggle, selection state, batch-delete
  confirmation dialog, hover/active checkbox overlay on existing cards.
- Extracted formatFileSize and getFileIcon to utils/files.ts to share
  with the new list view and avoid further drift from the existing
  inline copies.
- i18n keys added for zh-CN, en-US, ko-KR, ru-RU.

Closes #1045
Closes #957
2026-04-29 12:01:38 +08:00
wolfkill abd188d344 fix(miniprogram): improve knowledge base selection 2026-04-29 12:00:02 +08:00
wolfkill d06111e5f7 feat(miniprogram): add WeChat mini program plugin 2026-04-29 12:00:02 +08:00
wizardchen d55b52652c fix(docparser): preserve standalone image uploads from icon filter
When the uploaded file is itself an image, the image reference now carries
an IsOriginal flag so ResolveAndStore skips the small-icon size filter.
Otherwise small standalone images (e.g. avatars below 64x64) were silently
dropped before reaching multimodal OCR/caption processing.
2026-04-29 11:58:02 +08:00
hjz 535aec87e3 feat: data_analysis sql validation & type processing 2026-04-28 23:47:34 +08:00
wizardchen d812770806 fix: inject KB document listing on fallback for broad queries (#959)
When users ask broad queries like "请整理知识库中的数据" in RAG mode,
vector/keyword search returns nothing because the query has no specific
content to match. The user needs to see what documents exist, not search
results.

- Add buildKBDocumentListing() to fetch document titles/filenames from
  the knowledge base and inject them into the fallback prompt via
  {{kb_documents}} placeholder
- Update fallback prompt templates (model_fallback, default_fallback_prompt)
  to include document listing context so the LLM can guide users
- Improve rewrite prompt: tighten summarize vs kb_search classification,
  expand kb_search to cover browse/organize/list operations, add examples

Closes #959
2026-04-28 23:31:04 +08:00
wizardchen d5f6c7ba21 fix(docreader): remove default 100-page limit for DOCX parsing
The default DOCREADER_DOCX_MAX_PAGES=100 silently truncates large
documents, causing users to see at most ~1000 chunks regardless of
document length. Change the default to 0 (no limit) so all pages are
processed. Operators who need a cap can still set the env var.

Fixes #719
2026-04-28 21:50:15 +08:00
wizardchen 80a007cc06 fix(im): remove pipeline-level timeout that kills multi-round agent reasoning
The IM service applied a hard 120s deadline (`qaTimeout`) to the entire
QA pipeline context. Multi-round ReAct agents easily exceed this — when
the deadline fires mid-stream the LLM provider returns "context deadline
exceeded" which leaks into the user-visible answer (fixes #1000).

Changes:
- Replace `context.WithTimeout(ctx, qaTimeout)` with `context.WithCancel(ctx)`
  in both `handleMessageStream` and `runQA`, matching the web handler's
  approach. Each agent round still has its own per-call LLMCallTimeout
  (default 120s) which is sufficient.
- Filter `ResponseTypeError` stream chunks in `streamLLMToEventBus` so
  error messages (e.g. "context deadline exceeded") are never appended
  to the LLM content. Instead they are captured in `StreamError` and
  surfaced as a Go error when no usable content was produced.
- Bump Redis inflight mapping TTL from qaTimeout+30s to 10 minutes to
  accommodate longer agent runs.
- Remove the now-unused `qaTimeout` constant.
2026-04-28 21:17:56 +08:00
wizardchen c578fdbad6 fix(im): isolate IM sessions per agent and recover from deleted sessions
Three bugs fixed:

1. Session cross-contamination (#1066): resolveUserSession and
   resolveThreadSession looked up ChannelSession by (platform, user_id,
   chat_id, tenant_id) without agent_id. When the same user talked to
   two bots bound to different agents under the same tenant, they shared
   a session — mixing knowledge base context. Add agent_id to all four
   WHERE clauses and update the DB unique indexes to match.

2. Swapped parameters in resolveThreadSession: the SQL expected
   (chat_id, thread_id) but Go args passed (threadID, msg.ChatID).

3. Orphaned ChannelSession crash (#1046): deleting a session from the
   WeKnora UI soft-deletes it (GORM), but the ChannelSession row
   survives because soft-delete doesn't trigger SQL ON DELETE CASCADE.
   Subsequent IM messages hit "record not found" on GetSession and the
   bot becomes permanently unresponsive. Now detect this case, recycle
   the stale mapping, and transparently create a fresh session.
2026-04-28 20:53:06 +08:00
wizardchen a4c0832007 fix(search): align rerank priority between Execute and rerankResults
The outer if/else in Execute claimed to prefer chatModel (LLM-based
reranking), but both branches called rerankResults which internally
prefers rerankModel first. This made the outer branching dead code
with a misleading comment.

Consolidate into a single branch that delegates entirely to
rerankResults, whose actual priority is: rerankModel → chatModel → none.
2026-04-28 20:23:57 +08:00
goodnight ca1c8074bc fix(container): aggregate registration errors in connector registry initialization 2026-04-28 20:02:13 +08:00
wizardchen 4b87239929 fix: LaTeX formulas flash and disappear during streaming response (#1056)
Replace token-by-token rendering (marked.lexer + v-for + marked.parser)
with single-pass marked.parse() in botmsg.vue and AgentStreamDisplay.vue.
This prevents Vue's v-for keyed diffing from destroying KaTeX DOM nodes
on each streaming update.

Also adds a dev-only markdown test page (/platform/dev/markdown) with
LaTeX, code, tables, Mermaid, and streaming simulation for visual
regression testing.
2026-04-28 19:34:33 +08:00
wizardchen 1f03741462 fix(wiki): Lite ingest lock, failed-op requeue, sync task retry parity
- Add per-KB sync.Map lock in Lite mode to mirror Redis SetNX concurrency.
- Requeue failed wiki ops in Lite by enqueueing asynq tasks with delay/tracing.
- Teach SyncTaskExecutor to honor ProcessIn delay and MaxRetry like Redis asynq.
2026-04-28 18:27:00 +08:00
wizardchen 48c032ccbe chore(i18n): align en-US/ko-KR/ru-RU locales with zh-CN
Sync key structure of non-Chinese locale files with zh-CN.ts as the
source of truth: add missing keys (translated into the target language)
and remove keys that no longer exist in zh-CN.

- en-US: +1 (knowledgeEditor.wikiBrowser.aliases)
- ko-KR: +110 / -9 (drop confluence/github/web_crawler entries that
  don't exist in zh-CN; add chat.wiki*, auth.oidc*, agent.editor.web*,
  knowledgeEditor.indexing.*, agentEditor.{im.wechat*,desc.web*,
  llmCallTimeout.*}, datasource.* prereq/scheduleHuman/resourceType/
  relative-time keys, etc.)
- ru-RU: +108 / -9 (same shape as ko-KR, minus auth.oidc which already
  existed)
2026-04-28 18:01:22 +08:00
wizardchen dd524ffb1c feat: enhance Scan method in RetrieverEngines to support legacy and current formats
- Update Scan method to handle both legacy bare-array format (e.g. [{...}, {...}]) and current object-wrapped format (e.g. {"engines": [{...}, {...}]}).
- Improve error handling for unmarshalling failures, providing clearer feedback on format issues.

This change ensures backward compatibility while allowing for the new data structure.
2026-04-28 17:21:56 +08:00
wizardchen c34f7b6254 Enhance wiki ingest process to handle failed operations
- Introduced a mechanism to track and requeue failed operations during the wiki ingest process.
- Added a new `requeueFailedOps` function to append failed operations back to the Redis pending list for retry in subsequent batches.
- Updated the `ProcessWikiIngest` method to collect failed operations and ensure they are retried after trimming the pending list.

This change improves the robustness of the ingest process by preventing data loss from transient failures.
2026-04-28 17:21:42 +08:00
wizardchen 13260b831c Fix wiki ingest silent data loss from malformed JSON in Redis queue
Two critical fixes to the peekPendingList function:

1. Add error logging for JSON unmarshal failures (line 303)
   - Previously: Malformed JSON items were silently skipped with no indication
   - Now: Each failure is logged with the error and raw item content (first 100 chars)
   - This makes data loss visible and debuggable

2. Fix trim count mismatch (line 325)
   - Previously: Returned len(result) - the count of raw Redis items peeked
   - Now: Returns len(ops) - the count of successfully parsed items
   - Impact: Malformed items now stay in Redis for retry instead of being discarded
   - This prevents silent data loss when JSON encoding issues occur

Root cause of the reported issue:
- When 8 files are uploaded in a batch, if one has encoding issues that cause
  JSON.Unmarshal to fail, it was silently dropped from processing
- The file was trimmed from Redis without being processed
- Result: Only 7 of 8 files appeared in the Wiki

Fix approach:
- Make unmarshal failures visible in logs
- Retry malformed items in the next batch instead of discarding them
- Admin can see the errors and take corrective action

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-28 17:21:42 +08:00
wizardchen b1fc0e18d9 feat: Add LLM call timeout configuration to agent frontend
- Add llm_call_timeout field to CustomAgentConfig TypeScript interface
- Add thinking field to CustomAgentConfig (for extended thinking support)
- Add UI control (number input) in AgentEditorModal for timeout configuration
  - Range: 0-600 seconds (0 = use global default)
  - Supports 60-600 seconds recommended range
- Add i18n translations in Chinese (zh-CN) and English (en-US)
  - Label: "LLM 调用超时" / "LLM Call Timeout"
  - Description with explanation of timeout behavior
  - Hint about default and unlimited wait implications
  - Placeholder with recommended range
- Initialize llm_call_timeout: 0 in formData (uses global default)

This completes the frontend support for per-agent LLM timeout configuration that was previously missing. The setting integrates with the existing three-tier configuration hierarchy:
1. Per-agent config (llm_call_timeout in custom_agents table)
2. Global config (agent.llm_call_timeout in config.yaml)
3. Hardcoded default (120 seconds)
2026-04-28 17:21:17 +08:00
wizardchen 29a65cc250 docs(readme): update tracing references from Jaeger to Langfuse across multiple languages 2026-04-27 15:35:15 +08:00
wizardchen 9fa60c7e7d docs(readme): enhance layout for Agent Mode and Observability sections across multiple languages 2026-04-27 15:27:24 +08:00
wizardchen 99c17a0548 docs(readme): adjust layout for Agent Mode and Knowledge Base Management sections 2026-04-27 13:39:08 +08:00
wizardchen a888bc2dfe docs(images): update agent-qa.png to improve visual content 2026-04-27 13:39:08 +08:00
wizardchen ddd4234e64 docs(readme): move Interface Showcase up and rebalance layout
- Promote Interface Showcase to right after Latest Updates / before
  Architecture so users see the product UI early.
- Rebalance grid: hero Q&A (full width) -> Wiki Browser + Wiki Graph
  (50/50) -> Agent Mode (full width) -> KB Management + Settings
  (50/50). Forces equal-width columns via width=50% so screenshots
  no longer look uneven.
- Add small emoji prefixes to subsection labels for visual rhythm.
2026-04-27 13:39:08 +08:00
hjz efae3d466f feat: correct data analysis errors using fileService. 2026-04-27 13:18:08 +08:00
wizardchen e7cdd787f0 docs(readme): refresh title and overview to reflect RAG + Agent + Auto-Wiki 2026-04-27 13:15:48 +08:00
wizardchen 09d5508351 fix(docs): standardize feature headings in README 2026-04-27 12:23:02 +08:00
wizardchen 8ad5361cac chore(docs): update README files for localization and formatting
Removed unnecessary details sections and adjusted formatting for consistency across English, Chinese, Japanese, and Korean README files. Updated headings for features to enhance clarity and readability.
2026-04-27 12:23:02 +08:00
wizardchen b587844d06 chore(release): v0.5.0
Bump version to v0.5.0 across VERSION, frontend/package.json,
frontend/package-lock.json and helm/Chart.yaml.

Highlights:
- Wiki Mode: agent-driven Wiki knowledge system that distills raw
  documents into interlinked markdown pages, with a dedicated
  WikiBrowser and an interactive knowledge graph visualizing page
  references and relationships.
- Observability: Langfuse tracing across the agent ReAct loop, LLM
  token usage, tool calls and the asynq async pipeline.
- Customizable indexing strategy: per-knowledge-base toggles for
  vector / keyword / Wiki / knowledge-graph indexing.
- Vector Store UI & per-KB binding.
- Yuque connector with full / incremental sync.
- Agent enhancements: json_repair tool, OpenMAIC Classroom skill,
  multi-sheet DuckDB Excel analysis.
- Docs: refreshed READMEs (EN/CN/JA/KO), CHANGELOG, QA, regenerated
  Swagger and updated architecture diagram with new Wiki/Langfuse
  components.
2026-04-27 12:23:02 +08:00
jw_mac 4050060850 change the hardcode into the * comparison to ensure compatibile for new linux version 2026-04-24 22:42:17 +08:00
jw_mac faaf6124b2 add output that if install package of offline protoc exitst 2026-04-24 22:42:17 +08:00
jw_mac 6128c7a30e fix(docreader): whitelist offline protoc zip packages in dockerignore 2026-04-24 22:42:17 +08:00
goodnight a4fe86f828 fix(agent): improve tenant context handling and error reporting 2026-04-24 22:40:57 +08:00
wizardchen c12296aa88 feat(observability): instrument agent ReAct loop and tool calls in Langfuse
The existing Langfuse integration covered Chat / Embedding / Rerank / VLM /
ASR generations plus the HTTP + asynq spans, but the agent's own execution
tree was invisible: tool calls never appeared, multi-round ReAct iterations
were flat under the HTTP trace, and there was no single node representing
"one agent run".

This change adds three levels of agent-side spans:

  - agent.execute       — wraps AgentEngine.Execute, records query preview,
                           knowledge bases, allowed tools, final-answer length
                           and totals on finish.
  - agent.round.<N>     — wraps each ReAct iteration; records finish_reason,
                           tool-call count, token usage and duration.
  - agent.tool.<name>   — wraps each tool invocation; records arguments,
                           success, duration, output preview (rune-safe, 4KB
                           cap), error, data keys and image count.

To keep the loop's many exit paths (natural stop, stuck loop, empty-content
retry, final_answer, context cancellation) span-safe, the iteration body was
extracted into runReActIteration with a single defer span.Finish() and an
iterOutcome sentinel driving the outer loop. database_query arguments are
redacted (keys only) to avoid leaking raw SQL into the observability
backend, mirroring the existing UI hint policy.

Adds unit tests for the new helpers (truncateForLangfuse, argKeys, dataKeys,
finishToolSpan nil-safety, iterOutcome.String).
2026-04-24 19:58:08 +08:00
wizardchen 8103398fcf fix(agent): materialize knowledge files to temp path for DuckDB (#1007)
Dev-mode repro from the issue reporter's logs:

  [Tool][DataAnalysis] Failed to create table from Excel: IO Error:
  GDAL Error (4): Failed to open file
  'local://10000/.../1777030910246871000.xlsx': No such file or directory

The local file service returns a custom 'local://' URL from GetFileURL,
which the duckdb spatial/excel extensions can't resolve (they expect
plain paths or http(s)/s3:// style URIs). Presigned HTTPS URLs from
cloud backends worked by accident; the 'local://' dev path has always
been broken for the Data Analysis tool.

Instead of per-scheme adapters, stream the file through
FileService.GetFile into a temp file and hand DuckDB the resulting
filesystem path. This works uniformly across every backend (local,
OSS, S3, MinIO, COS) and survives future scheme changes without any
changes to the Data Analysis tool.

- Preserve the original file extension on the temp file so DuckDB's
  format auto-detection (csv / xlsx / xls) still kicks in.
- Clean up the temp file when LoadFromKnowledge returns, including on
  every error branch. Cleanup is idempotent (double-invoke safe).
- New tests stub FileService to lock in that (a) we never leak a
  provider:// URL to DuckDB, (b) GetFile errors propagate, (c) the
  extension survives case normalization.

Refs: https://github.com/Tencent/WeKnora/issues/1007
2026-04-24 19:57:56 +08:00
wizardchen 002d98a640 test(agent): add end-to-end DuckDB excel tests and fix sheet enumeration (#1007)
Catching up on a real-world check: when a multi-sheet .xlsx fixture is
fed through LoadFromExcel against an in-memory DuckDB with the spatial
and excel extensions, the first iteration's sheet enumeration quietly
fell back because st_read_meta doesn't expose a scalar 'layer_name'
column — it returns a LIST<STRUCT> column called 'layers'. We now
UNNEST(layers).name so enumeration actually works, and assert the full
data path with three DuckDB-backed tests:

  - multi-sheet workbook yields the sum of all rows and per-sheet
    breakdown via __sheet_name (including schema drift: columns only
    present in one sheet are NULL for the other)
  - single-sheet workbook still works and tags rows with its sheet name
  - sheet name containing a single quote (Q1'24) survives the SQL
    literal round-trip

excelize/v2 is added as a test-time helper to build the fixtures
deterministically. If DuckDB's spatial/excel extensions can't be
installed (offline CI), the tests skip rather than fail.

Refs: https://github.com/Tencent/WeKnora/issues/1007
2026-04-24 19:57:56 +08:00
wizardchen 11811f9bf8 fix(agent): load all sheets from Excel files in data analysis (#1007)
DuckDB's st_read (spatial) only reads the first layer/sheet of a .xlsx
workbook, so every sheet beyond Sheet1 was silently dropped from the
DuckDB table the Data Analysis tool builds. Users trying to analyse
multi-sheet workbooks could only see the first sheet.

Switch to DuckDB's dedicated 'excel' extension (read_xlsx) for the
actual data load, enumerate sheets via the spatial extension's
st_read_meta, and UNION ALL BY NAME the rows of every sheet into one
table. A synthetic __sheet_name column records the source so the LLM
can still filter/aggregate per sheet; schema drift between sheets is
tolerated via UNION BY NAME. If enumeration fails (older DuckDB, local
filesystem errors, …) we fall back to reading the first sheet so the
tool stays usable.

- Install & LOAD the 'excel' extension alongside 'spatial' both at
  startup (internal/container) and in the offline prefetch binary
  (cmd/download/duckdb).
- Harden sheet/path handling against single quotes.
- Update the tool description so the agent knows about __sheet_name.
- Add unit tests for the CREATE TABLE SQL builder covering 0 / 1 / N
  sheets and quote escaping.

Refs: https://github.com/Tencent/WeKnora/issues/1007
2026-04-24 19:57:56 +08:00
wizardchen beca2b89a3 feat(observability): extend Langfuse tracing across asynq pipeline
Previously the Langfuse integration only traced in-process HTTP requests
(chat / search / eval), so file uploads and every downstream asynq task
(document parse, chunk embedding, OCR/VLM, summary / question gen, wiki
ingest, datasource sync, etc.) produced either disconnected shallow
traces or no observation at all.

This change threads one trace end-to-end:

- tracer: add SPAN observation type and StartSpan; add ResumeTrace so a
  worker can attach to an upstream trace without emitting a duplicate
  trace-create; StartGeneration now auto-picks parentObservationId from
  ctx so nested trace -> span -> generation trees render correctly.
- types.TracingContext + LangfuseTracingCarrier: embed on all 17 asynq
  payloads so trace_id / parent_obs_id / user_id / session_id serialise
  into every job.
- langfuse.InjectTracing: injected at 28 enqueue sites before json.Marshal
  so the HTTP-layer trace survives the Redis hop.
- langfuse.AsynqMiddleware: mux.Use hook that peeks the payload, either
  resumes the upstream trace or opens a standalone asynq.<type> trace
  for scheduled jobs, and wraps the handler in a SPAN with task metadata
  (id / queue / retry / payload_bytes) plus ERROR level on failure.
- GinMiddleware.shouldTrace: whitelist ingestion / knowledge-mutation /
  FAQ / wiki / datasource endpoints so the root trace actually starts.
- Tests: tracer_test.go covers span nesting, error status, and
  ResumeTrace no-trace-create guarantee; asynq_test.go covers
  InjectTracing round-trip, middleware resume path, and standalone
  trace fallback.
- Docs: docs/Langfuse\u96c6\u6210.md now lists the covered task types
  and documents the cross-process propagation model.

No behavioural change when Langfuse is disabled (all new code paths are
no-ops and carriers serialise to empty strings with omitempty).
2026-04-24 13:16:47 +08:00
wizardchen 59fbf77524 refactor(agent_system_prompt): update synthesis and issue flagging instructions
Revised the agent system prompt to clarify the synthesis process and the handling of factual errors. The instructions now emphasize the mandatory use of the `final_answer` tool for submitting responses and the need to flag issues before calling `final_answer`. This enhances the clarity and consistency of the agent's operational guidelines.
2026-04-24 13:16:47 +08:00
wizardchen 492e92580b feat(observability): integrate Langfuse for LLM token tracking and tracing
Closes #620 #497. Add opt-in Langfuse observability covering all five
model types (chat, embedding, rerank, VLM, ASR) with HTTP-request-scoped
traces and Docker Compose support (both cloud and self-hosted).

Core package internal/tracing/langfuse:
- HTTP client with batched async ingestion (non-blocking in request path)
- Sampling, environment / release tagging, and graceful fallback when
  LANGFUSE_* env vars are absent (wrappers become no-ops)
- Gin middleware opens one trace per traced request and finishes it after
  the handler chain returns, attaching method / path / user / session
- Trace context is stored under a typed key exported from internal/types
  so logger.CloneContext can preserve it across handler / goroutine
  boundaries (otherwise each LLM call auto-created an orphan trace,
  fragmenting one request into many)

Per-model generation wrappers (opt-in via NewChat/NewEmbedder/...):
- chat: captures prompt, streaming output, token usage + TTFT
- embedding: approximates tokens when the provider omits usage
- rerank: previews query/docs, summarizes results to keep payload small
- vlm: records image count and total bytes, never uploads raw pixels
- asr: records file size and audio duration, never uploads audio bytes

Async title generation (GenerateTitleAsync) now forwards the trace key
into the goroutine so title calls appear under the parent chat trace.

Docker Compose:
- LANGFUSE_* env passthrough on the `app` service for cloud deployments
- Optional `langfuse` profile spins up a self-hosted Langfuse stack that
  reuses WeKnora's existing PostgreSQL (separate database via an idempotent
  init container that fixes ICU collation drift) and Redis (separate DB
  number), adding only ClickHouse, MinIO, web and worker containers
- web/worker entrypoints URL-encode DB_PASSWORD / REDIS_PASSWORD at start
  to avoid Prisma P1013 when passwords contain @ / # / etc.

Docs: docs/Langfuse集成.md covers cloud vs self-hosted, per-model usage
strategy, code map, and resource footprint.
2026-04-24 10:29:19 +08:00
wizardchen b8c45b173e fix(agent-share): don't require rerank model for wiki-only agents
The share-time validation forced every agent bound to a knowledge base to
have a rerank model configured, which blocked Wiki-type agents
(`wiki_search` / `wiki_read_page` / …) from being shared even though they
never invoke the reranker at runtime.

Align the check with the runtime logic in `session_agent_qa.go`: only
require a rerank model when the agent's allowed_tools include
`knowledge_search` (or rely on the default tool set, which contains it).
Wiki-only agents can now be shared without a rerank model; hybrid / RAG
agents still enforce the requirement.

Also update the handler error message to reflect the new rule.
2026-04-24 10:21:05 +08:00
wizardchen 220404348e feat(frontend): add copy action for model cards in settings
Allow users to duplicate non-builtin models (chat / embedding / rerank /
VLLM / ASR) from the model card dropdown. The copied model inherits all
parameters (base_url, api_key, provider, embedding params, custom
headers, vision flag, etc.) and gets a non-conflicting name with a
localized suffix, so users can quickly fork and tweak an existing
configuration without re-entering every field.

Adds matching i18n entries (copySuffix / toasts.copied /
toasts.copyFailed / toasts.builtinCannotCopy) for zh-CN, en-US, ko-KR
and ru-RU.
2026-04-24 00:17:12 +08:00
wizardchen fd3e2992b1 feat(models): support custom HTTP headers across all remote model calls
Introduce per-model `custom_headers` config (similar to OpenAI Python SDK's
`extra_headers`) so users can inject gateway auth tokens, trace IDs, etc.
into every outbound API request for chat / embedding / rerank / VLLM / ASR
models. Reserved headers like Authorization / Content-Type are always
preserved to avoid breaking auth or signing flows.

Along the way, unify production and "test connection" paths onto a single
`ConfigFromModel(*types.Model, appID, appSecret)` constructor in each
model package. Both `service.modelService.GetXxxModel` and the four
`handler.initialization.Check*Model` / `TestEmbeddingModel` endpoints now
go through the same field mapping, so new parameters only need to be
added in one place.

Backend:
- Add `CustomHeaders map[string]string` to `types.ModelParameters` with
  JSON/YAML `omitempty` tags for forward compatibility.
- New `internal/utils/extraheaders.go` providing `ApplyCustomHeaders`
  (for hand-rolled HTTP paths) and `WrapHTTPClientWithHeaders` /
  `CustomHeadersRoundTripper` (for SDK paths like go-openai). Reserved
  headers (Authorization, api-key, Content-Type, Accept, Host,
  Content-Length, User-Agent) are filtered out.
- Inject headers in every remote model path: chat (SDK + raw HTTP),
  embedding (openai/aliyun/jina/volcengine/nvidia/azure_openai), rerank
  (remote_api/aliyun/jina/nvidia/zhipu — via shared `customHeaderSetter`
  interface), VLM and ASR (via http.Client wrapping).
- Add `ConfigFromModel` to each of chat/embedding/rerank/vlm/asr,
  consolidating field mapping (ExtraConfig, CustomHeaders, InterfaceType
  defaulting, WeKnoraCloud credentials, etc.) and cover it with
  dedicated unit tests per package.
- Refactor `service/model.go`: replace ~100 lines of hand-written Config
  literals with one-line `ConfigFromModel` calls; drop the now-unused
  `stringMapToAnyMap` helper.
- Refactor `handler/initialization.go` test-connection endpoints: merge
  four ad-hoc request structs into one `ModelTestRequest`, extract
  `buildTestModel` and `resolveTenantWeKnoraCloudCreds` helpers, and
  route all four endpoints through `ConfigFromModel` + `NewXxx` so the
  test path is now behaviorally identical to production.

Frontend:
- Add `custom_headers` to the `ModelConfig` API type.
- `ModelEditorDialog.vue`: new Key-Value header editor (add/remove rows),
  auto-converts map <-> array when loading/saving, and passes the
  current header set to the `Test Connection` button so the preview
  reflects exactly what production will send.
- `ModelSettings.vue`: serialize the header array back into a map for
  the backend (drops empty rows).
- i18n: add custom-header labels / descriptions / placeholders to
  zh-CN, en-US, ru-RU, ko-KR.

Tests:
- `internal/utils/extraheaders_test.go` covers reserved-header filtering
  and round-tripper wrapping (including nil-client fallback).
- New `config_from_model_test.go` in chat / embedding / rerank / vlm /
  asr verifies all fields (CustomHeaders, ExtraConfig, InterfaceType
  defaulting, AppID/AppSecret) are propagated end-to-end.
2026-04-23 23:36:40 +08:00
wizardchen a6d4266c93 fix(agent): terminate ReAct loop on final_answer regardless of arg parse success
The agent loop previously kept running when the LLM emitted final_answer with
malformed JSON arguments: observe.analyzeResponse strictly json.Unmarshal'd the
raw args and returned isDone=false on failure, while act.runToolCall separately
repaired the JSON and executed the tool. The mismatch made final_answer
non-terminal, so the LLM saw its own answer in the next round's tool result
and re-emitted final_answer, surfacing near-identical answers multiple times
to the user (issue #1008).

Fix by unifying parsing in a new tools.ParseFinalAnswerArgs helper with three
fallbacks (strict -> RepairJSON -> regex extraction) and making final_answer
always terminal in analyzeResponse. When no answer can be recovered, emit a
user-visible fallback message and a Done=true event so the UI still resolves.

Also route final_answer.Execute through the same helper so tool execution and
loop termination stay consistent.

Adds regression tests in observe_test.go and final_answer_test.go covering
valid args, RepairJSON recovery, unrecoverable args, and garbage input.

Refs: Tencent/WeKnora#1008
2026-04-23 19:36:28 +08:00
wizardchen 3231ae30a4 fix(frontend): bundle tdesign-icons sprite locally for offline deploys
The <t-icon> component from tdesign-vue-next lazily loads its SVG sprite
from https://tdesign.gtimg.com/icon/<ver>/fonts/index.js at runtime. In
air-gapped or intranet deployments this request fails and the whole UI
loses its icons (agent cards, knowledge-base breadcrumbs/cards, upload
buttons, etc.).

Ship the sprite (tdesign-icons-vue-next@0.4.1) as a static asset under
frontend/public/tdesign-icons/0.4.1/fonts/index.js and preload it from
index.html so every <t-icon name="..."> resolves against local symbols.
An offline guard injects stub <script>/<link> nodes that match tdesign's
dedup selectors, so checkScriptAndLoad / checkLinkAndLoad short-circuit
without ever hitting the CDN (covers both the 0.4.0 and 0.4.1 hardcoded
URLs for forward-compat).

Closes #867
Closes #897
2026-04-23 18:21:49 +08:00
wizardchen 1ec43b328d refactor: Simplify WeKnoraCloud request customization and message conversion
- Removed redundant struct definitions for WeKnoraCloud requests and messages, streamlining the customization process.
- Updated the weKnoraCloudRequestCustomizer function to directly modify the request object, enhancing clarity and reducing complexity.
- Improved the convertToWeKnoraCloudMessagesFromOpenAI function to maintain the original message structure while ensuring compatibility with WeKnoraCloud requirements.
2026-04-23 17:52:43 +08:00