Point all four READMEs at the new 1:52 intro video rendered from
misc/intro-video, and update the captions: it has no narration and
uses English on-screen text.
* docs(readme): name skills, sandbox, browser and MCP in the overview
The overview only mentioned the built-in MCP Server; the agent's own
tools (skill sandboxes, the local browser, external MCP services) first
appeared far down in What's New and the feature tables.
Add an "Agent tools and execution" bullet to all four READMEs, and
update the Agent capability card (README artwork and the homepage it is
copied from) to mention the local browser, with concrete tags instead
of "tool calling / skills".
* docs(readme): condense the English feature and client tables
The four feature tables had 42 rows, many written as release notes
(removed backends, deprecated packages) or UI details, and repeated
what the overview, product tour and What's New already cover.
Replace them with a seven-row feature table linked to the docs and a
supported-backends table that keeps every compatibility list. Drop the
MCP Server subsection and the three client detail blocks, which repeat
the clients table, and shorten the v0.7.x entries in earlier releases.
* docs(readme): drop the v0.8.2 screenshot row
The three screenshots rendered at a third of the column width, too
small to read, and the local browser shot already appears in the
product tour.
* docs(readme): move the agent toolbox out of "beyond the three modes"
Skills, sandboxes, the local browser and MCP tools are part of the
agent mode, not something beside it. Describe them in a short paragraph
right under the capability cards and keep the list for platform
capabilities.
* docs(readme): condense the CN, JA and KO feature and client tables
Bring the translated READMEs to the same structure as the English one:
a seven-row feature table linked to the docs, a supported-backends table
with every compatibility list, no MCP Server subsection or client detail
blocks, and one-line v0.7.x entries.
* docs(readme): match the product website's look and drop slogan copy
Add hero and capability-card artwork (English and Chinese, light and dark)
drawn in the website's palette, type and line icons, plus small gold table
icons; docs/images/readme/src/generate.py rebuilds them. The copy in the
artwork is the homepage's own.
Replace per-bullet emoji and slogan-style lead-ins with plain labels, drop
emoji from headings and captions, add the homepage's three ways to get
started and the v0.8.2 product shots, restyle the badges in the brand
colors, and give the client table real logos or consistent line icons.
* docs(readme): bring JA/KO in line and add feature spotlights
Rebuild README_JA.md and README_KO.md on the same structure as the English
and Chinese READMEs, keeping their existing translations. Add what they
were missing: CLI and Mini Program entries, the contribution validation
steps, knowledge graph, access control and security rows, Zhipu
embeddings and Tencent Cloud COS. README_KO keeps its usage scenarios.
Generate Japanese and Korean hero and capability artwork with
language-specific CJK fonts, so Japanese kanji do not fall back to
Chinese glyph forms and Hangul wraps at spaces.
Replace the flat screenshot grid with four spotlights (local browser,
skills and sandbox, automatic wiki, observability), each pairing two
real screenshots in window frames; the remaining shots move to a
two-column "more screenshots" grid. docs/images/readme/src/spotlights.py
rebuilds the spotlight images.
* docs(readme): keep the browser task preview visible in its spotlight
The browser-connection window sat in the bottom-right corner, right over
the in-chat task preview that the main screenshot is meant to show. Let
each spotlight pick the corner for its side window and put the browser
one bottom-left, over the session list instead.
* docs(readme): make spotlight images clickable and sharp when opened
GitHub links a bare <img> to the full image but leaves <picture> inert,
so the spotlights could not be opened. Wrap each one in a link to its
image, and write the spotlights at 3200x1800 so the screenshots are
readable at full size and crisp on high-density displays.
* docs(readme): add Q&A and toolbox spotlights, drop the leftover screenshots
Add two spotlights: quick Q&A beside smart reasoning, and the toolbox's
MCP service tools beside its skill catalog. They cover the Q&A and skill
catalog shots from the screenshot grid, so the grid and its remaining
chunk editing, folder tree and wiki revision shots go.
* docs(readme): redraw the architecture diagram and widen the hero highlights
Replace docs/images/architecture.png with a generated diagram in the
same visual language as the rest of the README (per language, light and
dark), drawn from website-docs/02-architecture: clients and channels
feed the Go app, where RAG Q&A, agent reasoning and auto wiki share one
knowledge pipeline over workspaces, the model catalog, the task queue
and tracing; the app calls docreader, sandboxes, model providers, web
search, external MCP services and data sources, and stores data in
PostgreSQL (ParadeDB), Redis and the optional vector, object, Neo4j and
Langfuse stores. The old PNG was only referenced by the READMEs.
The hero listed only the three core modes; show eight highlights
instead (adding the local browser, skills and sandbox, MCP Server,
long-term memory, and data sources and IM) so the first screen reflects
the product's range. The capability cards below still explain the three
core modes.
Move Quick Start up to the second screen, split the one-paragraph overview
into three core-capability cards plus themed highlights, and group v0.8.2 /
v0.8.0 notes by topic with links into the release notes; earlier releases
move into a collapsible block unchanged.
Merge the seven scattered client and ecosystem sections into one table,
keeping CLI and MCP Server expanded and the rest in collapsible blocks.
Feature tables keep every row and gain per-group links to the docs site.
Point documentation links at the public site weknora.weixin.qq.com/docs,
fix the broken top-nav anchors, add an "other ways to deploy" table
(Helm, Lite, desktop), and realign the two languages (CLI section in
Chinese, knowledge graph and Tencent COS in English, current docs-site
preview command).
Move the CHANGELOG and release-notes date to 2026-09-24. In all four
READMEs, add the v0.8.2 entry to Latest Updates and bring the overview
and feature tables up to date: local browser, built-in MCP Server,
conversation control, artifacts library, sandbox terminal and desktop,
Lite host sandbox, model catalog, Confluence, Bocha / Serply, UI
languages and whitelist-only outbound. The MCP Server section now points
to the built-in server and marks the Python one deprecated.
* docs(ollama): document embedding model config and RAM guidance (#3480)
Local embedding and generation share the Ollama process at OLLAMA_BASE_URL.
The embedding model name is the local Embedding model's name; EMBEDDING_MODEL_NAME
is read only when builtin_models.yaml references it. The published 8 GB
starting point does not include Ollama weights or optional Neo4j.
Fixes#3480
* docs(ollama): shrink README/docs scope per maintainer review (#3480)
* feat(website): add product homepage and unified docs deployment
* fix(website): build the unified site in a multi-stage Docker image
* fix(website): reveal and highlight the active documentation sidebar item
* docs: add English and bilingual product tours to READMEs
* docs: center product tour cover buttons and language labels
* docs: highlight skills memory and integrations on tour covers
* docs: stabilize product screenshots in narrated tours
* docs: host HD product tours as GitHub attachments
* docs: embed product tours inline and simplify captions
* feat(dsh-weknora): DeepSeek Harness plugin exposing WeKnora retrieval tools
dsh ships no retrieval, embedding or knowledge-base capability of its own:
its search tools read the workspace and web_search reads the internet. This
plugin fills that gap with the user's own documents, registering four
read-only tools against a WeKnora deployment — knowledge base listing,
hybrid retrieval, full document reading, and WeKnora's own composed answer
with citations.
The package declares no runtime dependency on any harness package. It
mirrors the slice of the tool-definition contract it uses as structural
types and hands ctx.tools.register() a plain object, so a harness release
that adds optional fields cannot break an installed copy. Configuration is
validated at plugin load, so a typo fails the load with every violation
named rather than failing inside the first tool call.
* test(dsh-weknora): unit, API contract and in-harness end-to-end coverage
Three layers, each catching a different class of break.
The unit tests drive the tools against a mock WeKnora and assert what the
model actually sees. The contract layer pins every WeKnora call the plugin
makes in a fixture, then asserts it from both sides: contract.test.mjs
checks the plugin still emits exactly those calls, and contract_test.go
checks WeKnora's real Go request and response types still accept and serve
them — so a rename on either side fails CI instead of a user's agent.
The end-to-end check installs the package into a throwaway dsh profile with
`dsh plugin add`, boots the headless profile against a deterministic
OpenAI-compatible model and a mock backend, and asserts the harness agent
loop really called the tools and answered from what they returned. It runs
both documented paths: the shipped bundle configured only by environment
variables, and a profile patch that overrides the row and renames the tool
prefix.
* docs(dsh-weknora): document the plugin and wire up its CI
The package READMEs cover installation, the configuration reference, the
permission and data-flow story, and the compatibility note naming the dsh
release the plugin is verified against. The four root READMEs gain a short
paragraph pointing at it.
CI runs the tests and a packaging check on every touch, and the end-to-end
check against a pinned harness release so a plugin change is the only thing
that can turn it red. A weekly advisory job runs the same check against
dsh@latest to notice a harness breaking change early, since dsh is in
developer preview and states that breaking changes will happen. Publishing
is gated on a tag that names the packaged version, skips a version already
on npm, and goes out with provenance.
* fix(dsh-weknora): demand the retrieval scope WeKnora actually requires
WeKnora rejects a knowledge-search that names no knowledge base,
document or tag. The search tool told the model the opposite — that the
deployment would decide the scope when a call named none — so on a
deployment with no configured default, which is what the quickstart's
optional WEKNORA_KNOWLEDGE_BASE_IDS leaves behind, the model's first
search failed with an opaque HTTP 400.
The mock backend answered unscoped retrievals where the real handler
refuses them, which is why no test caught this. Align the mock with the
handler, state the requirement in the description, and reject the call
inside the plugin so the model gets a message naming the argument to
supply instead of a transport error. Scenario C covers the resulting
discovery path end to end inside dsh.
* feat(dsh-weknora): make search resolve its own scope and match names
Two gaps made the tool set awkward to use against a real deployment.
Scope: WeKnora refuses an unscoped retrieval, so the model had to pick a
knowledge base before it could search. On a real workspace that choice is
not makeable — 25 bases named "多福多寿", "撒打算", "test 副本 2". Since
knowledge bases sharing a vector store retrieve through a single fan-out
group, searching all of them costs about what searching one costs, so an
unconfigured deployment now resolves the visible set once and searches it.
Names: read_document needs a knowledge_id that only a passage hit could
supply, so "read the X handbook" had no path at all. Search now also
matches document names through /knowledge/search, which spans every base
and needs no scope, and reports the matches it finds inside the caller's
scope. A question-shaped query matches no name and costs nothing.
Also: page 1 of a document now leads with its title and WeKnora's
generated summary, so a long document can be judged without paging; ask
is described as the broad-synthesis tool it is rather than a peer of
search; and a wide scope renders as a count instead of spelling out
every id on every result.
* feat(dsh-weknora): enhance CI workflow and documentation for WeKnora plugin
Updated the GitHub Actions workflow to include Go contract tests, ensuring compatibility with WeKnora's Go types. Enhanced README files to clarify the plugin's functionality and usage. Added error handling for incomplete responses in the client, ensuring that truncated streams are properly managed. Improved test coverage for the ask tool to validate scope resolution and agent behavior.
* Fix README formatting and update text
* Fix image alt text formatting in README_CN.md
* Fix badge alt text in README_JA.md
* Fix badge alt text formatting in README_KO.md
* Update README.md
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.
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.
Users downloading a release and running `docker compose up -d` may get
cached old images because Docker doesn't pull by default. This caused
confusion when the UI displayed an older version than the release.
- Add `docker compose pull` before `up -d` in both README and README_CN
- Enable WEKNORA_VERSION in .env.example so users can pin a release tag
Closes#2560
Bump version to 0.7.1 across VERSION, frontend package manifests, and the
Helm chart appVersion. Add the 0.7.1 CHANGELOG entry and refresh all README
locales (badge, latest-updates, IM channel list with Yunzhijia).
Regenerate Swagger/OpenAPI docs, refresh the architecture diagram (IM Bots
9 channels), and extend docs/QA.md with entries for the Yunzhijia IM
integration, Volcengine rerank / Zhipu web search providers, and the Neo4j
conversation-memory removal.
Publish scoped API keys, worker-pool governance, multi-instance storage,
and the rest of the v0.7.0 feature set across CHANGELOG, READMEs, QA,
Swagger, and version pins.
Lark and Feishu are the same product deployed on two isolated clouds
(open.larksuite.com and open.feishu.cn). WeKnora touches both from two
places — the IM bot and the Wiki data-source connector — and this brings
Lark to parity across both. Neither API surface differs, so rather than
duplicate either implementation, each is parametrized by a Region and
registered twice.
IM (internal/im/feishu):
Every API call routes through a.api(), which prefixes the region's
host, and the WebSocket client passes larkws.WithDomain — the SDK
defaults to open.feishu.cn, so Lark long connections would otherwise
fail to authenticate.
Data source (internal/datasource/connector/feishu):
Lark was half-supported: the client honoured a base_url override and a
LarkBaseURL constant existed, but the connector registered only as
"feishu" and the UI never exposed base_url, so Lark wikis could not be
configured at all. Lark is now its own connector type. base_url is kept
as an explicit override so data sources that pointed a "feishu"
connector at open.larksuite.com keep working.
Bugs found and fixed along the way:
- Wiki resource links were hardcoded to https://feishu.cn/wiki/{token} in
four places, so a Lark wiki linked into the wrong cloud entirely.
- Bot identity is now platform-prefixed (feishu:cli_x vs lark:cli_x).
BotIdentity carries a unique index, so without this a Lark channel
would be rejected as a duplicate of an unrelated Feishu bot sharing an
app_id.
- The card image cache is now keyed by app_id. image_keys are issued per
app on one cloud; a Feishu key handed to a Lark app fails the card
update with code=200570.
- The datasource doc claimed Lark "adapts automatically" — it could not,
since the UI had no way to reach base_url.
Permissions are where the clouds genuinely diverge. Identical APIs do not
mean identical permission catalogues: aily:file:read, aily:file:write and
corehr:file:download exist on Feishu but not on Lark, so pasting Feishu's
scope JSON into Lark fails to import. That JSON is also over-broad (it
covers products WeKnora never calls) and simultaneously incomplete (it
omits the drive:*/docx:* scopes the connector needs). Lark therefore gets
its own list, derived from the 17 endpoints the code actually calls and
checked identifier-by-identifier against Lark's own API reference, plus a
full Feishu→Lark mapping table marking each scope verified, unverified,
or absent. Both features use tenant_access_token only — no user_access_
token exists anywhere in the repo — so the user dimension stays empty.
Known limitation: Region.ThinkingText makes Lark's initial card
placeholder English, but once streaming starts the think-block headers
come from the shared MarkdownThinkStyle and are Chinese on every platform
(Lark, Slack, Telegram, Mattermost alike). Fixing that means threading a
locale through FormatIMDisplayContent, which has no platform context — a
cross-platform change, not a Lark one. Documented as such.
The channel-creation 400 message is now derived from validIMPlatforms so
the list cannot drift as platforms are added.
Tests: region invariants and per-region URL construction on both sides,
the Feishu/Lark bot-identity split, platform-to-channel mapping, base_url
override precedence, an end-to-end SendReply against a fake Open Platform
(token fetch, reply, thread-unsupported fallback, hard-error surfacing),
and a ListResources drive asserting wiki links never leak the other
cloud's host.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Align product copy, API docs, Swagger descriptions, and i18n strings
with workspace terminology while keeping internal tenant identifiers
and headers unchanged for API compatibility.
Condense v0.6.0 highlights into one line and remove the collapsible
<details> wrapper so the full release history is visible by default
across all four READMEs (EN/CN/JA/KO).
Tenant RBAC headline release: 4-tier role matrix (Owner/Admin/
Contributor/Viewer), per-KB resource ownership, per-tenant audit
log, tenant member management, self-service workspaces.
Also: CLI v0.3/v0.4 GA, KB retrieval fan-out across vector stores,
AES-256-GCM credential at-rest, docreader gRPC TLS+Token, Zhipu
embedding, Huawei OBS, vLLM URL for MinerU, Apache Doris compat
modes, server-side user preferences, Go 1.26.0.
See CHANGELOG.md for the full list.
docs(rbac): wire RBAC screenshots into READMEs and RBAC guide
- README.md / README_CN.md / README_JA.md / README_KO.md: replace the
single member-management thumbnail under the v0.6.0 RBAC highlight
with a 2×2 showcase (member management, workspace switcher,
self-service workspace creation, pending invitations).
- docs/RBAC说明.md: add the member-management screenshot to the
existing 前端实际界面 showcase so the guide is self-contained
and no longer cross-references README for it.
feat(rbac-ui): link tenant member page to RBAC guide
Add an inline doc-link in the Tenant Members settings page that
opens docs/RBAC说明.md on GitHub in a new tab, complementing the
existing in-app role-matrix popover. New i18n key
tenantMember.learnRbacGuide covered for zh-CN / en-US / ko-KR /
ru-RU.
Bump version to v0.5.2 across VERSION, Helm chart, frontend package
files, and cloud-image script comment. Update CHANGELOG and all four
language READMEs with v0.5.2 highlights (Wiki Mode at scale, MCP
human-in-the-loop approval, new LLM/vector/storage/search backends,
adaptive 3-tier chunking, global command palette, CLI preview, etc.).
Discoverability gaps surfaced by the pre-PR review:
- New cli/README.md: install (build-from-source / pre-built once shipped)
+ 5-minute quickstart (auth login → kb list → link → doc upload →
chat) + multi-context walkthrough + JSON envelope shape + agent /
scripting integration overview + dev workflow. Points readers at
cli/AGENTS.md for the full operational contract.
- Top-level README.md: new "⌨️ Command-Line Interface" section between
Key Features and Getting Started, with a one-paragraph pitch + four
representative commands and links to cli/README.md and cli/AGENTS.md.
English README only this round; CN / JA / KO translations to follow
in v0.3 to match the existing four-language pattern.
- CHANGELOG.md [Unreleased] gets a "weknora CLI v0.2" bullet listing
the headline capabilities (10-command surface, project-link,
envelope, agent affordance, multi-context auth, doctor) and pointing
at cli/README.md.
- cli/AGENTS.md gains an "Architecture decisions" section documenting
ADR-3 (gh as primary mainstream north star + the four documented
deviations: link, chat/search, context use, doctor) and ADR-4
(Factory closures + narrow Service interfaces). The in-source
references (`(v0.2 ADR-3)`, `(per ADR-4)`) now point at committed
prose rather than dangling.
Bump version to 0.5.1 across VERSION, frontend package files, and
Helm chart, and refresh CHANGELOG plus the four-language README
"Latest Updates" section to merge v0.5.1 highlights with the v0.5.0
core feature set.
- 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.
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.
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.
- Revised the changelog to reflect the new features in version 0.4.0, including the introduction of the Cloud Knowledge Assistant and updates to WeKnora Cloud integration.
- Enhanced descriptions for ClawHub Skill and data source import capabilities, clarifying functionality and usage.
- Updated README files in multiple languages to ensure consistency and accuracy in feature descriptions and links.
This update improves the clarity and accessibility of the project's documentation, ensuring users are well-informed about the latest features and integrations.