* fix(agent): improve web search and persistent page reading
* fix(agent): make web fetch snapshots waitable and retryable
Keep in-flight page fetches independent of a caller's short deadline so
content=true and continuations cannot cancel a shared download or miss a
snapshot that is still loading. Mark snapshot_expired as retryable, fetch
only the first three search hits in parallel, and stop forcing Brave's
country to US.
* feat(ui): multi-stage Docker build without host npm
Build frontend assets inside the image with node:24-bookworm, then
copy into the existing digest-pinned nginx runtime so docker compose
and CI no longer require a host-side dist step.
* fix(ui): copy local xlsx package and raise Node heap in Docker build
npm ci needs packages/xlsx before install, and vite OOM'd under the
default Node heap during the multi-stage image build.
* fix(ui): native multi-arch frontend Docker build and layer cache
Keep Vite on BUILDPLATFORM so CI does not qemu-emulate Node, pin the
builder image, and move the commit ARG after npm ci so dependency
layers stay cacheable.
---------
Co-authored-by: wizardchen <wizardchen@tencent.com>
* feat(i18n): add Japanese (ja-JP) locale support
Add a complete Japanese UI locale for the admin frontend and the web
embed widget, and register it everywhere the supported-locale list is
enumerated.
- frontend/src/i18n/locales/ja-JP.ts: full bundle (5,600+ keys) aligned
with en-US/zh-CN key structure; verified by the locale key audit
- frontend/src/i18n/embed.ts: ja-JP block for the embed widget, plus
`ja*` normalisation in normalizeEmbedLocale
- Register ja-JP in i18n index, SUPPORTED_LOCALES, localeKeyAudit
bundles/order, TDesign locale map (ja_JP), login language picker,
general settings dropdown and embed default-locale options
- Add `language.jaJP` key to every locale so the settings dropdown can
use $t like its siblings
- Accept ja-JP as an embed channel default_locale on the backend and as
DEFAULT_LOCALE in the frontend docker entrypoint
- Extend locale-enumerating tests and update accepted-value lists in
.env.example, public/config.js, widget script and website-docs
* feat(i18n): add ja-JP names and descriptions for prompt templates
Add a ja-JP block to the i18n map of all 32 prompt templates
(system_prompt, context_template, rewrite, fallback, intent_prompts,
agent_system_prompt) so the template picker shows Japanese labels when
the UI locale is ja-JP instead of falling back to the Chinese names.
Prompt content is unchanged.
* feat(i18n): add ja-JP strings for the CLI integration page
main gained the CLI setup page (#3081) with 18 new integrations.cli.* /
integrations.tabs.cli keys; add their Japanese translations so the
locale key audit stays green after rebasing onto main.
* style(i18n): unify ja-JP spacing and long-vowel conventions
- Remove spaces between Latin tokens and adjacent Japanese text
(e.g. "MCP サービス" -> "MCPサービス"), matching the majority style
already used in the bundle
- Drop the trailing long-vowel mark on common technical katakana terms
(サーバ, ユーザ, フォルダ, プロバイダ, パラメータ, ヘッダ, クラスタ, ...)
so the whole locale follows one convention
* feat(i18n): add ja-JP labels for agent type presets
config/agent_type_presets.yaml carried default / zh-CN / zh-TW labels
only, so the agent editor showed English preset names in the Japanese
UI. Add a ja-JP label and description to all five presets.
* feat(agent): unify sandbox tools and drop host preloaded skills
Read workspace and skill files through read_file, and run installed or staged skills through shell_exec(skill_name). Remove the unused skills/preloaded tree and keep generated-file previews stable across re-renders.
* fix(frontend): do not assume classList in markdown sanitize hooks
Node unit tests stub anchors without a DOM classList. Detect download cards from class/download attributes instead.
Refuse truncated tool calls, compact-and-retry once on overflow, and let
sandbox files be appended, paged, and batch-edited instead of rewritten.
Models can set context_window (default 200K) so compaction sizes itself
from the real window; agent max_iterations of -1 means unlimited.
* fix(models): show usage details when deletion is blocked
* fix(models): open the matching agent section and cap usage lists
Agent "open configuration" now lands on the tab that owns the binding
(VLM/ASR vs follow-ups), and delete failures keep the server message when
structured details cannot be parsed. Listed KB/agent rows are capped at 50
while totals still drive the deletion guard and dialog headings.
---------
Co-authored-by: Leon <leon_hfut@foxmail.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
The app drops to appuser via gosu, so compose group_add never reaches the
process. Matching the socket GID before the drop lets a mounted Engine API
socket work without chmod 666 on the host.
* fix(auth): record last-active-tenant preference on SwitchTenant
* docs(auth): note SwitchTenant updating last-active-tenant preference
* fix(auth): persist last-active tenant before SwitchTenant tokens
RefreshToken re-resolves from this preference because refresh JWTs omit
tenant_id. Fail the switch if the write fails so a 200 never returns a
token pair whose later refresh would land in a different workspace.
* fix(cli): align HybridSearch interfaces with SDK variadic options
Client.HybridSearch gained ResourceURLOptions; CLI ChunksService and
MCP knowledgeService still used the old signature, so *Client no longer
satisfied those interfaces.
* style(cli): wrap HybridSearch signatures under the 120-column lint
---------
Co-authored-by: wizardchen <wizardchen@tencent.com>
* feat: require opt-in for the Docker sandbox backend
Docker engine access is host-root equivalent, so keep the backend off
until System Settings or WEKNORA_SANDBOX_DOCKER_ENABLED says otherwise.
Also move system-settings help into the title icon and add i18n for
tenant.auto_accept_invitation.
* fix(i18n): drop tenant wording from Docker host-risk copy
The workspace terminology check rejects 租户 / tenant in user-facing strings.
* feat(provider): add LiteLLM as an OpenAI-compatible provider
* docs: use revive-compliant comment for ProviderLiteLLM const
* fix(provider): stop defaulting LiteLLM to localhost under SSRF
The catalog URL localhost:4000 is blocked by default SSRF and does not
match DetectProvider, so UI/CLI could neither save nor auto-detect it.
Use a placeholder host, keep thinking aligned with generic, and sync
ModelSource across types, Swagger, and docs.
---------
Co-authored-by: wizardchen <wizardchen@tencent.com>
Local was a host-subprocess fallback that skill install, snapshots, and
session sandboxes already excluded. Drop it so Cube, E2B, and Docker are
the only backends; leftover local configs can only be deleted.
Clicking most settings sidebar items left the URL on
?section=system-global, so the route watcher snapped the panel back.
Write ?section=<navKey> for every page, including integration-claw,
and keep old ?tab= bookmarks as aliases.
* fix(hybrid-search): normalize MatchCount once instead of at the truncation site
An omitted match_count deserializes to Go's zero value, which reached the
truncation step in HybridSearch and sliced the deduplicated chunk list to
[:0] — a successful retrieval returned an empty result set. A negative
value panicked on that same slice bound and surfaced as a 500.
Resolve the value once at the top of HybridSearch via normalizedMatchCount
so all three consumers agree, rather than patching the truncation site
alone: the over-retrieval floor, the FAQ iterative-retrieval trigger
(which never fired on this path because len(chunks) < 0 is false), and the
truncation itself.
Bound the FAQ iterative path while here, since normalization is what makes
it reachable with a large MatchCount: its TopK seeds from MatchCount*3 and
doubles five times, previously without limit. It now stops at the pool cap
instead of re-issuing an identical query.
Co-authored-by: Cursor <cursoragent@cursor.com>
* refactor(retrieval): share the default retrieval depth as one constant
The value 50 was written three times — the over-retrieval floor in
HybridSearch, the MatchCount fallback added alongside it, and
RetrievalConfig.GetEffectiveEmbeddingTopK — with nothing recording that the
three are meant to agree. Anyone tuning one would silently desync the
others.
Promote it to types.DefaultRetrievalTopK. No behavior change.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: drakezhang <drakezhang@tencent.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Whitelist locale tags in docker-entrypoint to prevent config.js injection,
extract resolveDefaultLocale with trim/validation, add unit tests, and sync
local dev config plus docs for the new deployment default language setting.
* feat(sandbox): unify remote sandbox on E2B protocol with self-hosted support
- Add e2b.proxy_url gateway config and generic gateway transport layer
- Add envd compat layer for Basic auth and multipart /files uploads
- Support Dockerfile.sandbox runtime and e2b-backend build targets in CI
- Rename sandbox image non-root user to align with E2B template convention
- Add sandbox-protocol.md and extend cluster deployment / local repro docs
Enables connecting to any E2B-compatible control plane (E2B Cloud,
CubeSandbox, Agent-Sandbox, etc.) without per-backend client code.
* style(sandbox): gofmt tenant_resolver struct alignment
Introduce a new entrypoint script for the Nginx container to ensure proper startup behavior. Update the Dockerfile to use a stable-alpine Nginx base image and include the entrypoint script, enhancing the deployment process for the documentation site.
Update the Nginx configuration to listen on port 8081 instead of the default port 80. This change is necessary for serving the documentation site correctly in the current deployment setup.
Introduce a Dockerfile for building the documentation site using VitePress and an Nginx configuration for serving the built assets. The Dockerfile sets up a multi-stage build process, while the Nginx config handles routing and caching for the /docs/ path. Update VitePress configuration to set the base path for asset links. This enhances the deployment process for the WeKnora documentation site.
Follow up on #2567 by documenting the upgrade workflow, syncing JA/KO
READMEs and installation guide, and clarifying that WEKNORA_VERSION
changes require docker compose pull to avoid stale cached images.
Import and update WeKnora documentation with VitePress: getting started,
architecture, features, API reference, clients, and development guides.
Includes landing page with inline SVG illustrations, theme components,
doc check scripts, and product screenshots.
Follow up on #2567 by documenting the upgrade workflow, syncing JA/KO
READMEs and installation guide, and clarifying that WEKNORA_VERSION
changes require docker compose pull to avoid stale cached images.
This commit sets up a new documentation site for WeKnora using VitePress. Key additions include:
- A structured `.gitignore` to manage ignored files.
- An `index.md` file serving as the landing page with a clear title and layout.
- A `package.json` and `package-lock.json` to manage dependencies, including VitePress and related plugins.
- Thematic styles and components for a cohesive user experience, including a custom landing page and zoom functionality for diagrams.
- A README update to guide users on local development and site structure.
This foundational setup aims to enhance user onboarding and provide comprehensive documentation for the WeKnora system.
This commit introduces a complete set of documentation for WeKnora, organized into six main sections: Getting Started, Architecture, Features, API Reference, Clients, and Development Guide. Key highlights include:
- Detailed installation instructions and quick start guides.
- In-depth architectural overview and backend design documentation.
- Comprehensive feature descriptions, including multi-tenant support, document parsing, and agent capabilities.
- API reference covering approximately 360 endpoints with usage examples.
- Client documentation for various interfaces including web, CLI, and SDK.
This documentation aims to facilitate user onboarding and provide a thorough understanding of the WeKnora system.