Commit Graph

191 Commits (014f95f1394a7bfd1c7bbbdcdc19057a80dcaca5)

Author SHA1 Message Date
lyingbug 76a19f14c4
feat(mcp): add built-in MCP server with per-workspace endpoints (#3371)
* feat(mcp): add built-in MCP server with per-workspace endpoints

WeKnora previously exposed itself to MCP clients only through the Python
package under mcp-server/, which binds one process to one API key and
therefore to one workspace, and mirrors the REST API tool-for-tool.

This adds a native MCP server surface to the Go backend:

- New mcp_endpoints table (PostgreSQL 000100, SQLite 000020). A workspace
  can publish any number of endpoints, each with its own bearer token
  (SHA-256 stored, rotatable, shown once), knowledge-base allowlist, tool
  allowlist, default agent and per-minute rate limit.
- Management API under /api/v1/mcp-endpoints (Viewer reads, Admin writes,
  API keys need manage_channels) plus a tool catalog endpoint.
- internal/mcpserver hosts one mcp-go Streamable HTTP server in stateless
  mode at /mcp/:endpoint_id. tools/list is filtered per endpoint and
  tools/call re-checks the allowlist, applies rate limiting and touches
  last_used_at. MCPEndpointAuth resolves the token and injects the
  workspace, an mcp_endpoint principal and an API-key style scope derived
  from the endpoint, so existing knowledge-base and capability checks
  apply unchanged.
- Redesigned tool set (12 tools in four groups): retrieval and reading
  reuse the agent's native tools; ask runs the default or a named agent
  synchronously and returns a cited answer with a session_id for
  follow-ups; wiki tools cover search, read and index; write tools are
  off by default. Knowledge bases accept ids or names.
- Frontend: new "MCP Server" integrations tab (tab id mcpserver, to
  avoid clashing with the existing MCP-client settings section) with
  endpoint cards, a create/edit drawer, a one-time token dialog and
  ready-to-paste snippets for Cursor/VS Code/Claude Desktop, Claude Code
  and mcp-remote. Locales updated in all five languages.
- Deployment capability integrations.mcpserver wired on both sides.
- Docs: website-docs MCP page now leads with the built-in server; the
  Python mcp-server README carries a deprecation notice.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* fix(mcp): wire the MCP server into DI/router and tighten authorization

The previous commit lost eight staged files to the repo pre-commit hook,
which resolves ROOT to the main checkout and re-adds the main-checkout
copies of tracked files into the worktree index. This commit restores them
(container providers, RouterParams and route registration, context key,
principal, clone table entry, deployment capability key, SQLite parity
test) and addresses the review findings:

- Knowledge-base scope is authorized, not trusted: endpoint allowlists and
  every tool call resolve each knowledge base through access.ResolveKB for
  the calling principal (ownership or organization share). Foreign IDs are
  rejected on create/update and dropped at call time.
- Write tools mint explicit editor grants via access.KBAccess.WithGrant
  before calling the knowledge service, so add/update/delete go through the
  same RequireKBWrite path as the REST API. add_document also checks the
  grant itself.
- ask no longer accepts agent_id. It runs only the endpoint's configured
  agent; tenant-owned agents and user-facing builtins qualify, internal
  builtins (wiki fixer, skill installer) are refused both on save and at
  call time. Web search is forced off for MCP calls.
- Tool annotations match behaviour: ask is not read-only, add_document is
  a mutation.
- CORS allows MCP-Protocol-Version / Mcp-Session-Id / Last-Event-ID and
  exposes Mcp-Session-Id for browser-based MCP clients.
- Rate limiter runs its local cleanup goroutine; SQLite migration gains the
  deleted_at index for parity with PostgreSQL; non-ASCII endpoint names get
  unique mcpServers keys derived from the endpoint id.
- Swagger annotations on the management handler.
- Tests: KB isolation (service and server), write grants, endpoint-agent
  restriction, tool annotations, and a router test that mounts the public
  /mcp/:endpoint_id surface and checks the deployment capability.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* chore(mcp): renumber migrations after rebase onto main

main took 000100 / 000020 for chunks_index_diet, so the mcp_endpoints
migrations move to 000101 (PostgreSQL) and 000021 (SQLite); the SQLite
parity test and docs follow.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* fix(mcp): run document tools under the knowledge base owner tenant

Shared knowledge bases resolved through access.ResolveKB were only half
usable: documents of an organization-shared knowledge base are stored under
the owner tenant, so the document-level tools that queried by the calling
tenant found nothing, and add_document would have created rows under the
caller's tenant inside someone else's knowledge base.

- knowledgeInScope loads documents tenant-agnostically and then requires
  the document to belong to an allowed knowledge base and to that base's
  tenant.
- scopedKBContext replaces grantContext: it resolves the grant, switches
  the execution tenant to the knowledge base owner (KBAccess.Context) and
  swaps TenantInfo to the owner so storage/model settings resolve there.
  list_documents, read_document and every write tool run under it.
- Locale text and docs no longer claim clients can pass agent_id.
- Go SDK gains MCP endpoint methods (client/mcp_endpoint.go) with docs, and
  the Swagger artifacts are regenerated.
- Tests: shared knowledge base read/write under the owner tenant, spoofed
  document tenant rejected, viewer share cannot write.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* chore(mcp): renumber migrations after rebase onto main

main now carries 000101 / 000021 (knowledge_profiles), so the
mcp_endpoints migrations move to 000102 (PostgreSQL) and 000022 (SQLite);
the SQLite parity test expects version 22 and the docs follow.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* fix(mcp): guard last_used touch without a repository and wrap SDK line

The transport tests build the server without a repository; the background
last_used_at write then dereferenced a nil interface and, on the slower CI
runner, took the test binary down. touchLastUsed now returns early when no
repository is wired, and the tests inject a recording repository and assert
the touch instead. Also wraps a 123-column SDK signature for the client
module's lll check.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-17 22:40:05 +08:00
lyingbug 5574ebc011
feat(knowledge): derive knowledge base descriptions from document profiles (#3370)
* feat(knowledge): derive knowledge base descriptions from document profiles

Knowledge bases only had a hand-written description, which most users
leave empty, so agents bound to several knowledge bases had nothing to
route on and searched all of them. This adds a generated description
that is derived from per-document data instead of maintained by a model.

Document profile: the summary call now returns JSON with a 2-3 sentence
summary plus a gist, 3-5 topic keywords, a document type and one
typical question (knowledges.profile). Input is capped at 8k chars and
output at 1024 tokens; plain-text replies from custom templates still
work and simply carry no profile. The summary chunk embeds the gist and
short summary.

Knowledge base aggregate: a database-only fold over those rows (counts
per file type, tag, normalized topic and doc type; stratified samples of
titles and questions; a hash of the inputs). Deleting, moving or
re-parsing a document changes nothing but the rows, so the next rebuild
is exact without any model judgement.

Description text: one small model call over the aggregate yields a
gist, merged topics and typical questions (knowledge_bases.
generated_profile). The call is skipped when the aggregate hash is
unchanged; failures keep the previous text and record the error; an
empty knowledge base clears it. The manual description is never
touched, and the agent runtime context renders both so the model can
pass knowledge_base_ids instead of fanning out.

Refreshes are requested from summary task exit, post-process completion,
deletion, cross-KB moves and enabling the option, debounced per
knowledge base in 30 s windows via kb:profile on the summary queue.
POST /knowledge-bases/:id/profile/generate regenerates synchronously.
profile_config (enabled, model_id, custom_instructions) opts a document
knowledge base in; the settings dialog shows the generated card with
regenerate and adopt-as-description actions in five locales. Search
results now log hits per chunk type so the value of indexing summary
chunks can be measured.

Migrations 000101 (PostgreSQL) and 000021 (SQLite) add the columns; the
SQLite schema test expects the new version and columns.

* fix(knowledge): keep generated descriptions out of duplicates and refresh clones

DuplicateKnowledgeBase copies the source row through JSON, which carried
generated_profile onto a knowledge base that has no documents yet, so
an empty duplicate advertised the source's topics. The duplicate now
starts without a generated description and keeps profile_config so it
derives its own once documents arrive.

CopyKnowledgeBase builds the target field by field and skipped
profile_config, and the clone task never asked for a description after
copying the documents, so a clone stayed undescribed until its next
upload. The target now carries a copy of profile_config and both clone
paths request a refresh on completion.

* fix(knowledge): refresh the loaded clone target and carry document profiles

ProcessKBClone requested the description refresh with the reservation
stub it builds before CopyKnowledgeBase runs. For the main create path
that stub has neither a type nor profile_config, so the refresh helper
rejected it and nothing was enqueued. The refresh now uses the loaded
target returned by CopyKnowledgeBase.

cloneKnowledge copied the summary text but not the structured profile,
so even a scheduled refresh would have aggregated titles without topics
until every clone was re-summarized. Cloned documents now carry an
independent copy of the profile.
2026-09-17 22:21:55 +08:00
nullptr-error 42e6163981
feat(session): fork conversations from a historical user message (#3304)
* feat(session): add fork schema and history queries

为会话分叉增加数据模型与迁移,并提供截至分叉点的消息查询以及会话内的 request_id 配对。

* feat(sandbox): add git, fork snapshots, and bootstrap hook

沙箱镜像安装 git,Docker 快照使用独立的 fork 命名空间,并在首次创建会话沙箱时接入可选 bootstrap。

* feat(session): checkpoint workspace at the end of each turn

每轮结束后对沙箱 /workspace 打 git checkpoint,并避免 fork 后因 mtime 刷新重复挂上产物、以及附件仍绑在父会话而无法还原。

* feat(session): fork conversations and reap orphan snapshots

支持从历史 user 消息分叉会话、首次打开时从快照 bootstrap,并在失败或删除未打开的分叉时回收孤儿快照。

* feat(chat): add session fork entry, prefill, and badges

在用户消息上提供分叉入口,进入新会话时预填原问题,并展示降级提示与来源角标。

* style: add missing newline so session_fork_delete_test.go is gofmt-clean

* fix(session): prune later git history when rolling a fork workspace back

reset --hard 只还原工作区,分叉点之后的 commit 仍可被 checkout。校验 SHA 后丢掉其他 ref 并 gc,避免错误基线。

* style(session): clear golangci-lint findings on the session-fork diff

Pre-push lints the whole PR against main; wrap long lines, check c.Error,
and fix gofumpt/revive/staticcheck so the merge can be pushed.

* fix(chat): show the fork button on hover without shifting the thread

Overlay the action so revealing it no longer expands the user bubble and janks the messages below.

* fix(chat): drop the fork landing banners

Keep the original question prefilled; do not explain sandbox snapshot vs checkpoint on the new thread.

* fix(agent): dedupe artifacts by content hash, not size

Same-path same-size rewrites were skipped as restores. Keep path+mtime as the cheap skip, hash bytes when mtime moves, and stamp the restored mtime onto this session only.

* feat(session): allow forking from an assistant answer

User forks still copy history before the question and prefill it. Assistant forks copy through that reply and reuse its checkpoint, with a degrade tooltip when none exists.

* fix(session): resolve parent attachments from a forked chat

Fork copies attachment IDs onto the new messages but leaves temporary_documents on the parent. Preview and Get now look up those IDs on the fork's copied history instead of a scoped miss.

* fix(agent): rewrite sandbox refs after a content-hash skip

Fork restores change mtime on unchanged files, so Collect returns empty
and named citations were left as sandbox: paths. Resolve those names
against session artifacts, notify only real uploads, and stamp restored
mtime only on the matching content hash.

* fix(session): drop a dead fork snapshot and retry checkpoint rewrite

Create from a missing template now abandons bootstrap so the next
Resolve uses a normal sandbox. A failed checkpoint rewrite no longer
marks the bootstrap consumed, which previously made nested forks
SANDBOX_REPLACED.

* fix(session): load forked parent attachments into the prompt

ResolveForPrompt used session-scoped lookup, so copied parent attachment
IDs passed Get but never reached the model. Use the same resolveInSession
path as preview.

* fix(chat): keep the user-message fork button visible

The control was hover-only, which hid it on touch. Always show it, and
drop the unused degrade tooltip.

---------

Co-authored-by: hailongzhao <hailongzhao@tencent.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-09-17 14:20:18 +08:00
serply e80f5dfbc7 feat(web-search): add Serply provider
Serply returns Google results through a keyed JSON API, which fills the
gap between Google Custom Search (needs an engine ID and a restricted
scope) and the scrapers. The adapter follows brave.go: hardcoded
endpoint, redirects refused so the key never leaves the official host,
4MB response cap, and per-call country and freshness filters. country
maps to Google's gl parameter and pd/pw/pm/py map to tbs qdr:d/w/m/y.
Serply has no date-range filter, so that form returns an error instead
of being silently dropped. num is clamped to 10 because the API serves
one results page per call.

Wiring matches the Bocha provider: type constant and metadata, registry
factory, service validation, frontend union, swagger enum entries (edited
by hand; a full swag regen drags in unrelated drift), and the web search
docs table.
2026-09-17 12:25:09 +08:00
jacentsao 01f0700b35
feat(datasource): add Confluence sync (#3287)
* feat(datasource): add Confluence sync

* fix(confluence): resume full sync and list Server pages without CQL

CQL search silently truncates large spaces and can delete pages that
dropped out of the index. Full-sync checkpoints now keep a deletion
baseline so Asynq retries continue instead of restarting.

* fix(confluence): satisfy package lint for pre-push against main

* fix(confluence): parse Server page lists and keep version expand

The default Server/DC edition unmarshaled /content/page as a nested
envelope, so sync imported zero pages. Pagination next links also drop
expand=version,space, which made later pages versionless and hid edits.

* fix(confluence): classify errors and fail closed on empty listings

Raw Confluence error bodies were copied into sync-log UI, and pagination
next links could leave the configured context path via `..`. Empty
listings against a non-empty baseline now abort instead of deleting.

---------

Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-09-16 14:38:16 +08:00
nullptr-error 6ccc5cedf1
feat(sandbox): add a graphical desktop to session sandboxes (#3245) 2026-09-14 20:37:37 +08:00
DEMO 5d3114fc9e
feat(datasource): add DingTalk Docs integration with safe sync and localization (#2313)
* feat(datasource): add DingTalk Docs integration

* fix(datasource): harden DingTalk sync and complete translations

* fix(datasource): close DingTalk review gaps in sync and rendering

Prefer millisecond node timestamps, keep full-sync deletion reconciliation, and stop dropping official block payloads so incremental updates and Markdown import stay complete.

---------

Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-09-14 19:53:29 +08:00
lyingbug 7e53c31671
feat(browser): connect local Chrome with task controls and display modes (#3180)
* feat(browser): integrate BrowserSkill local task tabs and account pairing

* feat(browser): refine task routing, lifecycle, and display modes

* fix(browser): reclaim temporary task tabs and groups

* test(database): cover browser authorization migration schema
2026-09-11 17:59:27 +08:00
lyingbug 72581cb462 Revert "feat(sandbox): add safe live file management to session sandboxes (#3…"
This reverts commit 01205b3d56.
2026-09-11 17:42:08 +08:00
DEMO 01205b3d56
feat(sandbox): add safe live file management to session sandboxes (#3181)
* feat(sandbox): add safe live file management to session sandboxes

* fix(sandbox): keep live files from waking paused sandboxes

Serialize directory entries as "directory", refuse Files-tab Connect on paused runtimes, and cap list/delete trees so oversized workspaces fail closed.

---------

Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-09-11 17:31:53 +08:00
nullptr-error 277d6ee851
feat(sandbox): add an interactive terminal and files tab beside chat (#3110)
* feat(sandbox): stream interactive PTYs from Cube and E2B

Give session sandboxes a provider-neutral terminal capability so a later
WebSocket layer can attach without knowing Cube vs E2B. Long-lived
streams use a timeout-free client; idle terminals keep the sandbox alive
by refreshing TTL, and a workspace can set how long to wait before
disconnect.

* feat(session): bridge browser terminals to the session sandbox

Mint a short-lived ticket over a normal authenticated POST so the browser
WebSocket never puts the access JWT in the query string. After upgrade,
recheck the bound token, membership, and session ownership so logout or
revocation tears the PTY down. Provisioning stays opt-in: a GET
handshake only creates a sandbox when the client sends provision=1.

* feat(chat): add a sandbox terminal panel beside the conversation

Open a side panel with an xterm attached to the session sandbox. Starting
the terminal is an explicit click so merely opening the panel does not
create or resume a microVM; reconnects stay lookup-only until the user
confirms create-and-start. Persist the remote shell PID in
sessionStorage so a refresh reattaches instead of spawning an orphan.

* feat(sandbox): let workspaces set terminal idle disconnect

Expose the idle-disconnect duration in the sandbox config editor so an
operator can close unused terminals and let the provider TTL pause the
sandbox, instead of leaving PTYs open for the built-in 15 minutes.

* feat(chat): show generated files in the sandbox side panel

Move the per-message artifact list into the first tab of the right-hand panel so generated files stay in view with the terminal. Keep the old drawer only for embedded chat.

* fix(sandbox-terminal): keep tickets out of logs and live PTYs across refresh

Gin was copying the handshake JWT into response_body logs, silent access-token
rotation dropped open terminals as AUTH_REVOKED, and first-use provisioning
missed shared agents. Local echo now skips password prompts.

---------

Co-authored-by: hailongzhao <hailongzhao@tencent.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-09-08 17:43:15 +08:00
lyingbug 647848f395
fix(agent): improve web search and persistent page reading (#3086)
* 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.
2026-09-07 23:09:27 +08:00
Fei.Chen 15727591a7
feat(web-search): add Bocha AI Search provider (#3036)
* feat(web-search): add Bocha AI Search provider

Add a Bocha (bochaai.com) web search provider following the Metaso
adapter pattern: hardcoded official endpoint (SSRF-safe), Bearer auth,
4MB response cap, error-detail extraction, and RFC3339 date parsing
(datePublished preferred, dateLastCrawled fallback).

Tenant-facing config fields:
- freshness: noLimit/oneDay/oneWeek/oneMonth/oneYear (default noLimit)
- summary: request long text summaries, preferred as snippets (default on)

Wiring: registry factory in container, provider type enum + /types
metadata (dynamic form fields), frontend provider union type, and
swagger docs enum entries.

* fix(web-search): match Bocha's real wire format for codes and error messages

Live endpoint probing showed errors return {"message": .., "code": "401"}
(string code, message field) instead of the documented {msg, code:int}.
Parse the code tolerantly (string or number) and extract the detail from
message/msg so auth and rate-limit failures surface their reason.

* fix(web-search): allow Bocha in provider CRUD validation

In-service integration testing caught a fourth wiring point the adapter,
registry, /types metadata and frontend covered but CRUD did not: the
service-layer whitelist (isValidProviderType) and parameter validation
switches rejected provider type 'bocha', so providers could be tested
via POST /web-search-providers/test but never created or updated.

Add Bocha to both switches (delegating to ValidateBochaParameters like
Metaso/Zhipu) with service-level test coverage.

* fix(web-search): correct Bocha legacy timestamp timezone

---------

Co-authored-by: vicfei <vicfei@users.noreply.github.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-09-07 20:06:26 +08:00
lyingbug d5cb842580
feat(agent): unify sandbox tools and drop host preloaded skills (#3033)
* 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.
2026-09-05 16:45:59 +08:00
wizardchen cd3f8b4a9a feat(skills): store skills in a tenant catalog and install per sandbox
A skill is a workspace definition, not a sandbox setting. Keep one catalog
row and run a full image install for each backend, so agents only enable
skills that are already ready on the sandbox they use.
2026-08-28 15:17:37 +08:00
hailongzhao 188200e3b1 feat(sandbox): inject per-user and workspace skill env vars at execution
Skills declare the environment variables they read at run time, so a
credential no longer has to be an admin-set value shared by everyone
using the same skill image.

The installer agent writes a declaration the server validates against the
bundle. Admins fill workspace-wide values from the skill drawer, members
fill their own under Settings, and a successful shell_exec captures the
declared names a run already used for the current speaker. Resolution is
keyed by Principal so IM callers do not collapse onto one synthetic
account, and values are injected only into the process of that one run.

Values are AES-GCM encrypted at rest and never returned by any endpoint.
2026-08-27 14:32:00 +08:00
wizardchen 7fda02637c feat(sandbox): remove the Local host-process backend
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.
2026-08-26 17:48:21 +08:00
nullptr-error 18d22b014b
feat(sandbox): expose tenant skill management over HTTP and in the console (#2789)
* feat(sandbox): enhance skill management in sandbox configurations

Updated the skill management system to allow listing, installing, and removing skills within sandbox configurations. The ListSkills function now accepts a sandboxConfigID to filter skills based on the selected configuration. Introduced a new SandboxSkillsDrawer component for managing skills through the UI, along with necessary updates to the API and localization files to support these features.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix: keep skill maintenance sessions out of the console session list

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat: store and expose the installer transcript locators

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat: record the skill installer agent's conversation

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat: stream and persist the installer transcript during a skill install

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat: expose install transcript locators on the skill type

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat: add the floating skill install transcript window

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat: open the install transcript from the sandbox skills drawer

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat(sandbox): 重构技能安装体验,支持内联时间线、编辑第4步及保留镜像指针

- 替换右下角浮窗为内联安装时间线 (SkillInstallTimeline.vue)
  - 新增 GET /api/v1/sandbox-configs/:id/skills/:skillId/transcript 接口,支持回放与追尾
  - 移除 /sessions/continue-stream 依赖,避免 404 问题
  - 事件日志以 install_prompt 开头,不再将工具调用 preamble 拼入最终答案
  - 删除 SkillInstallTranscript.vue,技能条目下可展开/折叠时间线

- 编辑向导新增第 4 步「管理技能」
  - Cube/E2B 环境:连接 → 模板 → 运行配置 → 技能(第4步)
  - Docker/Local 环境:无第4步(无快照镜像)
  - 首次创建必须按 1→2→3 顺序,第3步保存成功后自动进入第4步
  - 已有配置支持步骤条数字跳转,可直接访问任意步骤
  - 卡片菜单「管理技能」打开同一抽屉并定位至第4步
  - SandboxSkillsDrawer.vue 重命名为 SandboxSkillsPanel.vue,去除独立抽屉壳

- 修复保存运行配置时冲掉 skill_image 的问题
  - 顶部展示信息(基础模板/快照ID/版本/构建时间)读取 config.skill_image
  - 编辑器保存 payload 不再包含 skill_image,合并时保留已有 SkillImage 和 VolumeMount
  - MergeSandboxConfigForUpdate 增加对 SkillImage 和 VolumeMount 的保护
  - 已冲掉的配置需重新安装技能才能恢复镜像指针

- 「查看安装过程」在安装开始时即显示
  - 技能列表中出现「正在安装」状态即展示按钮
  - 若记录尚未写入,展示等待提示并自动重试,避免误报「没有留下记录」

* 沙盒内技能目录从 UUID 改成 SKILL.md 的 name。

* fix(sandbox): heal stuck skill rows and block planted maintenance sessions

The reaper left a mid-upgrade install spinning forever when the old snapshot was still live, and restored removals to ready after the pointer had already moved. Client session create/update can no longer hide chats behind the skill_maintenance: prefix.

* style: gofumpt the skill reaper test stubs

* style: satisfy golangci on the tenant skill admin API

* feat(sandbox): rebuild skill images at turn boundaries, not mid-exec

Hold a session turn lease through AgentQA so an install cannot tear down
the live sandbox between tool calls; the next turn's first resolve picks
up the new image. Configs can instead keep existing sandboxes and boot
the new snapshot only for new sessions.

* fix(sandbox): judge stuck skill runs from the snapshot chain

InstalledSnapshotID only records the generation that installed a skill; later
installs of other skills advance the live pointer without rewriting older rows.
Comparing those IDs made the reaper fail healthy installs and delete live
skills whose removal had stalled.

---------

Co-authored-by: hailongzhao <hailongzhao@tencent.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-08-25 11:28:12 +08:00
hailongzhao 67cdf26216 feat(sandbox): add tenant skill install and remove service layer
Introduce the hidden skill-installer agent and TenantSkillService so a
sandbox config can install or remove skills into snapshot images under a
per-config lock, without yet exposing HTTP or UI entry points.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-24 17:51:13 +08:00
hailongzhao 00fe035668 feat(sandbox): add tenant skill snapshot infrastructure
Give Cube/E2B a shared snapshot API and persist skill image pointers so later session sandboxes can inherit installed skills from a config snapshot instead of the base template.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-24 16:00:23 +08:00
wizardchen ffcb10f953 feat(memory): add cross-session long-term memory
Persist extracted and explicit memories across sessions with topic
resolution, semantic recall, document affinity, consolidation, workspace
settings, and inbox/interests UI.
2026-08-13 18:00:02 +08:00
Numblgw d3524d8d04
feat(datasource): 支持 GitLab 数据源文档同步 (#2656)
* 支持gitlab数据源

* 添加单元测试 && 修复gitlab数据源配置多个的UI展示问题

* 补充韩语、俄语文案

* gitlab数据源同步:新增文件类型过滤 && 改为streaming实现

* fix: remove duplicate RSS locale keys

---------

Co-authored-by: liguowei <liguowei@xinye.com>
2026-08-12 16:09:55 +08:00
joeyczheng 664d193ca7 feat(datasource): add Tencent IMA datasource
Signed-off-by: joeyczheng <joeyczheng@tencent.com>
2026-08-12 14:56:25 +08:00
Syt3s 5eaabf6bbb
feat: add Exa WebSearch (#2617)
* feat: add Exa WebSearch

* Fix test for Exa config options validation

* feat: add exa connection test
2026-08-11 17:05:52 +08:00
wizardchen 738fe1ec53 feat(sandbox): 沙箱后端改为按空间配置,并补齐 E2B 模板与检测诊断
沙箱的后端类型、凭据、模板、超时和私网访问策略此前分散在部署级
WEKNORA_SANDBOX_* 环境变量里,一个实例只能有一套,租户之间无法各用
自己的 E2B 账号或自建 Cube 集群。现在这些配置全部落到空间维度的具名
沙箱配置上:部署环境不再提供覆盖项,未选择配置的智能体直接不启用脚本
执行,而不是静默回落到某个部署默认值——后者会让「这个智能体到底跑在
哪」无从判断。

同时把连接检测从「能不能连上控制面」扩展成可解释的诊断:
- E2B 标准模板显式带上 default 标签构建。创建沙箱时裸模板名/ID 只解析
  default 标签,构建带了别的标签就永远拿不到,表现为一个与「模板不存在」
  无法区分的 404。
- 模板状态不再从历史构建或 spawn 次数反推就绪,只认当前构建;构建完成
  却没有 default 标签的模板单独报成 untagged,因为它在列表里和「仍在构建」
  长得一样,但等待永远不会有结果。
- 创建失败带上 HTTP 状态,404 走模板解释路径,给出具体到「重建模板」还是
  「Key 属于其他团队」的结论。
- 探针脚本改在进程工作目录下暂存。系统临时目录在 macOS 上位于
  /var/folders,Docker 虚拟机并不共享,挂载进容器后是空目录,真实技能执行
  (脚本在 skills/ 下)却不会踩到,检测因此报假失败。
- 检测失败不再只说「命令输出与预期不符」,带上退出码与 stderr 首行。

前端把沙箱设置页与配置抽屉重做:凭据按「是否已配置」展示而非回显掩码,
删除与停用改为就地确认,占用情况走右侧抽屉,列表卡片展示模板状态、凭据、
超时等可判断健康度的事实。
2026-08-11 15:42:02 +08:00
nullptr-error 5df788dc77
feat(sandbox) (#2301)
* cubesandbox support

* feat(agent): add sandbox shell execution, file management tools, and Artifacts collection/download system

- Add three sandbox agent tools: shell_exec / sandbox_ls / sandbox_read
  - shell_exec: safely execute shell commands in session sandbox with timeout & output truncation
  - sandbox_ls: enumerate files under sandbox artifact output directory with recursive listing & pagination
  - sandbox_read: read sandbox file content with offset-based chunked reading
- Add Artifacts system:
  - ArtifactCollector: real-time collection of sandbox tool output files, attached to messages
  - /api/artifacts/{session_id}/{message_id}/{filename}: download endpoint for frontend
  - ChatArtifactsDrawer.vue: frontend artifacts sidebar UI
  - DB migration 000066_message_artifacts: add artifacts column to messages table
- Attachment sandbox staging: upload user attachments to session sandbox on QA request for skill tool access
- Update Agent Prompts: add shell/sandbox tool usage constraints and safety rules
- Extend Agent Observe: include agent steps in Langfuse observability tracing
- Refactor Sandbox SessionManager: support session-scoped file listing, reading, and status queries
- Frontend: render artifact events in AgentStreamDisplay, i18n updates for 4 locales
- Add comprehensive tests: shell_exec_test, sandbox_read_test, artifact_collector_test, etc.

* feat(agent):add remote sandbox client abstract  & client errors

* feat(sandbox): implement Redis binding store with distributed lifecycle lock;

* feat(sandbox): add remote session lifecycle with ownership context

Implement remoteSessionLifecycle to coordinate persistent remote sandboxes
across multi-instance deployments. Supports Resolve (lazy provision,
recovery, race-safe create) and Destroy with compare-delete semantics.
Add ownership context isolation to decouple remote resource cleanup from
request cancellation.

* feat(sandbox): add CubeRemoteClient adapter for RemoteSandboxClient

Implement CubeRemoteClient as a provider-neutral RemoteSandboxClient
implementation. Error normalization, timeout mapping, and metadata
support are fully integrated. SDK details remain private to the
adapter.

* refactor(sandbox): decouple SessionBoundManager from Cube

Remove internal/sandbox/cube.go (CubeSandbox, sync.Map reaper). Add
RemoteSandbox as provider-neutral Sandbox interface implementation.
Rewrite SessionBoundManager to depend on RemoteSandboxClient +
SessionSandboxBindingStore + SessionExistenceChecker, with all
lifecycle ops delegated to remoteSessionLifecycle (Redis + distributed
lock). Application-layer interfaces migrated to RemoteDirEntry/StatEntry
with time.Time ModTime. Cleanup delegated to provider idle-timeout.

* refactor(agent): enhance session capability handling in sandbox manager

- Introduced sessionFileStore and sessionShellExecutor functions to centralize capability checks for session-scoped file and shell execution.
- Updated agent service to register tools based on the presence of session filesystem capabilities, improving compatibility with various sandbox backends.
- Refactored tests to validate behavior when session capabilities are absent, ensuring robust handling of different sandbox types.
- Removed Cube-specific checks, promoting a more provider-neutral approach to session management.

* refactor(sandbox): add E2B backend, modernize Cube adapter, and enable multi-instance Redis binding

- Add e2b_remote_client.go (~850 lines) — full RemoteSandboxClient implementation
  covering lifecycle, execution, and filesystem ops (ListDir/Stat/MakeDir/Remove)
- Wire E2B into NewManagerFromType and container/bootstrap path (buildE2BManager)
- Dependency: matiasinsaurralde/go-e2b v0.1.0

- Cut ~1500 lines of legacy SDK wrapper (cube_client.go, cube_envd.go,
  cube_defaults.go) and replace with direct *cubesandbox.Client usage
- Parse CubeProxy URL directly in adapter (parseProxyURL), removing the
  old hand-rolled envd transport layer
- Pass lifecycle extra fields (onTimeout, autoResume) via SDK CreateOptions.Extra
- Target Cube deployment v0.5.1

- Add RemoteNetworkPolicy to RemoteCreateRequest with AllowInternetAccess,
  AllowPublicTraffic, AllowOut/DenyOut — shared by Cube and E2B adapters
- Both adapters default to permissive (internet+public on) for backwards compat

- Add selectSessionBindingStore() — Redis-backed or in-memory, controlled by
  WEKNORA_SANDBOX_REDIS_NAMESPACE / WEKNORA_REDIS_NAMESPACE
- Add repositorySessionExistenceChecker — checks session existence via DB
  (gorm.ErrRecordNotFound → not exists, transient errors → preserve binding)
- newSandboxManager() now accepts redisClient + sessionRepo; deprecated
  hardcoded NewMemorySessionSandboxBindingStore() in production path

- buildSessionCreateRequest default timeout action: Kill → Pause+AutoResume
  (Cube and E2B). Sessions survive brief idle periods; providers still
  handle TTL-based reaping.

- buildSessionCreateRequest() and effectiveHTTPTimeout() parameterized
  by RemoteProvider (was hardcoded to Cube Config fields)
- NewSessionBoundManager validates provider and delegates defaults to
  per-provider apply*Defaults helpers

- Legacy SDK wrapper: cube_client.go, cube_envd.go, cube_defaults.go,
  cube_envd_test.go, cube_net_diag_test.go, cube_test.go (~2500 lines)
- Unused helpers: DefaultManager.validateExecution, IsRemoteTerminal,
  IsRemoteUnsupported, IsRemoteTransient, ShouldPreserveRemoteBinding
- Dead Config fields: CubeEnvdPort, CubeIdleTTL, AllowedCmds
- Dead ExecuteResult method: GetOutput
- Unused test: session_artifacts_integration_test.go
- Preloaded skill: sandbox-test-python

- Extract shared httpErrorKind() from per-adapter normalize functions
- Add SupportsFilesystemEnumeration capability flag — gates SessionFileStore
  advertisement (E2B returns true post-reconnect, Cube always true)
- Fix stale comments: Cube-only → remote backends, remove "tomorrow"/"future"
- Bump session sandbox TTL defaults: 604800s → 300s (.env.example)
- Update docs/agent-skills.md: full multi-instance deployment guide

Total: 29 files, +1188 / -3721

* feat(agent): bind collected skill artifacts to owning message in resource registry

When ArtifactCollector persists a skill-generated file it now registers a
resource:// binding (owner_type=message, owner_id=assistantMessageID,
relation=artifact) in addition to the messages.artifacts JSONB record. This
mirrors how knowledge uploads and chat attachments bind their resources, so
artifacts can be enumerated and garbage-collected through the resource
registry instead of only via the message JSONB column.

- ArtifactCollector: inject ResourceCatalog, add messageID to Collect/
  maybePersist, and add best-effort bindArtifactResource (binding failures are
  logged, never drop the artifact; only resource:// refs are bound).
- agent_stream_handler: pass assistantMessageID into Collect.
- Renumber message_artifacts migration 000066 -> 000077 to resolve the
  version collision with existing migrations (upstream now uses 000075/000076).
- Tests: update collector signatures and add coverage for the binding path
  and for graceful degradation when Bind fails.

Note: binding applies to newly generated artifacts only; existing rows are
not backfilled.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(sandbox): harden remote sandbox security and artifact collection

Disable Cube local fallback so skill scripts never run on the host when
the remote provider is unavailable. Require Redis for cube/e2b binding
unless WEKNORA_SANDBOX_ALLOW_MEMORY_BINDING=true for single-node dev.

Collect artifacts with WithoutCancel so user stop does not drop files,
reject shell_exec work_dir outside /workspace, and refuse session-scoped
Execute when a local fallback would be engaged.

* fix(ci): gofmt sandbox files and resolve artifact drawer type error

Apply gofmt to PR-touched Go files and narrow ChatArtifactsDrawer
props in AgentStreamDisplay so session-id is always a string.

* fix(sandbox): adapt to upstream main after rebase

Renumber the message_artifacts migration 000077 -> 000079: upstream now
uses 000077_remove_wiki_log and 000078_chunk_editing_and_custom_metadata.

Declare empty model-handle policies for shell_exec / list_sandbox_files /
read_sandbox_file. Upstream added a coverage test requiring every
UI-exposed tool to declare one; sandbox output is arbitrary skill-authored
content, so it gets the same treatment as execute_skill_script.

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat(sandbox): replace single tenant sandbox config column with a configs table to support multi-sandbox config per tenant.

* feat(sandbox): add sandbox config entity, cordon lease and session pin field

* feat(sandbox): add sandbox config repository with tenant scoping and cordon lease

* feat(sandbox): stamp sandbox config ID onto sandbox metadata

* feat(sandbox): scope sandbox listing, release and reaping to a single config

* feat(sandbox): resolve managers per config and refuse cordoned or missing configs

* feat(sandbox): implement session pinning and config identity change detection

- Add SessionSandboxPinner with read/pin/clear to bind session to config
- Refactor four entry points (execute/attachment/artifact/destroy) to use pinned config
- Add config_identity.go to detect identity changes by effective values (APIURL/APIKey/Domain/ProxyURL)
- Add SandboxIdentityChanged with key-masked comparison to prevent false 409 conflicts
- Fix artifact collection for default backend and destroy for legacy empty-pin sessions

* feat(sandbox): add multi-tenant sandbox config management and HTTP APIs

Service layer:
- Add sandbox config business service supporting CRUD and inventory listing
- For non-identity changes (e.g., template, TTL), save directly without locking or remote interactions
- For identity changes (e.g., API key, endpoint), reject save if there are still live sandboxes under this config on the remote side,
  and return structured inventory details (sandbox count, affected sessions, related agents) for frontend prompting
- Before deleting a config, check remote live sandboxes; if occupied, reject and prompt user to end sessions or create a new config
- Identity comparison based on effective values to avoid normal saves being misidentified as credential rotation

HTTP interfaces and routing:
- Add REST endpoints for sandbox config (List/Create/Get/Update/Delete/Inventory)
- Mask sensitive credentials (API key, etc.) in all read responses
- Return 409 with structured inventory details on rejection scenarios
- sandbox-check probing supports specifying an existing config_id directly
- Remove old handler file, consolidate validation logic into service layer
- DI wiring and route registration for all six endpoints

* feat(sandbox): add sandbox_config_id field to allow agent referencing named sandbox config

- Add SandboxConfigID field to CustomAgentConfig with omitempty; empty value falls back to global defaults
- Validate config existence on create/update; return 400 if not found
- Inject sandboxConfigService into CustomAgentHandler
- Add unit tests covering field serialization and validation logic

* feat(sandbox, agent): Migrate sandbox config to multi-config CRUD, support named backend selection and workspace scripts policy

Migrate frontend API from legacy KV single-config to /sandbox-configs REST interface, supplement type definitions, detection methods and policy fields; refactor sandbox settings page to multi-config card grid, manage configs with cube/e2b tabs, add editor drawer for create/edit/delete, connection testing and occupancy hints, and add workspace scripts policy toggle; add sandbox config dropdown in Agent editor skill section, integrate config caching, and support selecting named config or falling back to deployment default.

* feat(sandbox): Unify sandbox disable semantics and add tenant-level policy master switch

- Backend: Unify interception in resolveTenantSandboxForConfig with priority: global disable > tenant disable > default fallback > named config; add deploymentSandboxDisabled() using env var to avoid mis‑impacting named E2B; update WorkspaceSandboxPolicy comment as master switch for entire workspace; add unit tests for various scenarios.
- Frontend: Sync i18n copy: button text changed to "Disable/Enable sandbox execution"; confirmation dialog clarifies impact scope; success/failure messages aligned.
- Semantic layering: WEKNORA_SANDBOX_MODE=disabled disables globally; tenant‑level "Disable sandbox execution" only disables for the current workspace.

* feat(sandbox): Add SSRF protection, Agent binding to named configs, and reference query capabilities

- Add outbound URL security guard to validate Cube/E2B API/Proxy addresses against SSRF (including cloud metadata), support allowing private endpoints via env var, link-local always blocked
- Add named backend type validation, only cube/e2b can be stored as workspace named config
- Add sandbox config ID field to Agent at runtime, resolve sandbox for attachments and execution based on Agent's selected named config instead of always global default
- Add query to list Agents referencing a sandbox config ID, useful for deletion/changes to show dependents
- Adapt artifact collector and other callers to fill missing resolve signature parameter

* fix(sandbox): fix session teardown and config-update, add HTTP pool sharing for Cube

Session teardown & deletion ordering
- Move sandbox destroy (and pin `Clear`) before soft‑delete operations (`DeleteSession`/`BatchDeleteSessions`/`DeleteAllSessions`) to prevent remote sandbox leaks and stale pins.
- Pass deployment‑wide `SessionBoundManager` as fallback into `resolveTenantSandboxForConfig` for sentinel pins (`"-"`) to support deployment‑default sessions.

## Config update edge cases
- When identity fields change but old credentials cannot build a client or list config sandboxes, log a warning and proceed with the update instead of returning `sandbox_inventory_unverifiable`; live sandboxes still return 409.
- UI: move `sandboxes_still_live` / `unverifiable` alerts to the top of the sandbox config drawer and auto‑scroll on save refusal and connectivity check results.

Artifact collection for Cube skills
- Pre‑create `/workspace/output` via envd with correct ownership/permissions for `DefaultSandboxExecUser` to ensure Cube skill artifacts are collected properly by `ArtifactCollector`.

HTTP pool sharing for named Cube configs
- Named sandbox configs rebuilt a client on every `Resolve`, causing fresh TCP connections to CubeAPI and the envd proxy on each request.
- Add `CubeTransportPool` and `cubeSplitTransport`:
  - Control plane traffic reuses the same `SharedTransport` as E2B.
  - Data plane traffic uses a guarded transport cached per proxy host:port, preserving the sandbox `Host` header.
- Wire the pool through the tenant resolver `buildClient`; keep SDK defaults for the deployment‑default manager and connectivity probes.

* feat(sandbox): sandbox execution DefaultUser change from root to user

* fix(multi-sandbox-config-per-tenant): align deployment config with tenant resolver and centralize defaults

- Merge form overrides onto DeploymentConfig() via WEKNORA_SANDBOX_* env vars
  instead of DefaultConfig() hardcoded values, allowing empty fields to inherit
  from .env rather than Go constants
- Centralize deployment baseline parsing in sandbox/defaults.go with
  DeploymentConfig, CubeConfigFromEnv, E2BConfigFromEnv
- Delegate container startup to shared helpers to avoid drift
- Propagate tenant env_vars through ResolveEffectiveConfig into
  buildSessionCreateRequest for both Cube and E2B session sandboxes

* fix(multi-sandbox-config-per-tenant): fix some bugs frontend.

* fix(sandbox): guard check-path dials, fix staging gate and shared-agent binding tenant

Three defects found while reviewing the remote sandbox work:

- The Cube connectivity probe and the deployment-default Cube/E2B managers
  built clients without a guarded transport, so an admin-supplied api_url or
  proxy_url could reach link-local addresses via DNS rebinding even though
  save-time validation passed. All three now dial through the same outbound
  guard the per-tenant resolver enforces.

- Attachment staging was gated on the process-wide manager, so a workspace
  pointing an agent at a named Cube/E2B config while the deployment default
  stayed docker/local would run its tools remotely against an empty
  /workspace/input. The gate now resolves the manager the session actually
  runs on.

- Session to sandbox bindings were keyed by the tenant in context, which a
  shared agent deliberately swaps for the agent owner's so models, KBs and
  named configs resolve in the sharing workspace. Session deletion only ever
  knows the session's own tenant, so teardown looked up a key nobody wrote
  and abandoned a paused MicroVM that keeps billing. The binding tenant is
  now carried separately and survives CloneContext.

* chore(sandbox): renumber migrations above upstream and de-collide test stub

Upstream main took 000079 (knowledge_folder_path) and 000080
(knowledge_base_auto_tag_config) while this branch was open, so the three
sandbox migrations move to 000081-000083. golang-migrate requires unique,
ordered versions, and the RAISE NOTICE labels move with the file names.

Main also added a handler test declaring stubSessionService in the same
package; the artifact download test's configurable variant is renamed rather
than merged, since the two stubs answer GetSession differently.

---------

Co-authored-by: hailongzhao <hailongzhao@tencent.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-08-10 21:28:20 +08:00
Binks Riverton 355d161d64 feat: add Metaso web search provider 2026-08-10 13:33:55 +08:00
lyingbug 1030832c4b
fix(security): harden outbound URL SSRF protection (#2626)
* fix(security): harden outbound URL SSRF protection

* test(security): add SSRF validation tests for outbound URL caching

Introduce tests for outbound SSRF validation cache to ensure proper handling of URL validation, including cache reuse for the same origin, cache invalidation on whitelist changes, and expiration of cached entries. This enhances the robustness of SSRF protection mechanisms in the application.

* refactor: clean up whitespace in engine_factory.go and ssrf_outbound_cache.go

Removed unnecessary blank lines in engine_factory.go and adjusted variable declarations for consistency in ssrf_outbound_cache.go. This improves code readability without altering functionality.
2026-08-10 13:24:14 +08:00
lkx 9426ee1470 feat: 增加自动添加标签的功能 2026-08-07 15:01:01 +08:00
Greenplumwine 439af21f9b
feat(feishu-driver): 新增飞书云盘数据源 (#2466)
* feat(datasource): add Feishu/Lark Drive (云盘) connector

Add a new Drive (云盘) data source alongside the existing Feishu wiki
connector, letting users sync documents/files under a user-supplied Drive
folder_token. Shares the feishu connector package (Client/Config/Region/
export/download/error-handling) with the wiki connector; only resource
enumeration and fetch dispatch differ.

Backend:
- types/datasource.go: ConnectorTypeFeishuDrive / ConnectorTypeLarkDrive
- region.go: RegionFeishuDrive / RegionLarkDrive + driveFolderURL
- types.go: driveFile / driveFileListResponse / partialDriveFileListError
  / feishuDriveCursor
- client.go: ListDriveFiles / ListDriveFilesRecursiveFrom (shortcut
  expansion via shortcut_info, visited cycle guard, root-folder rejection)
- drive_connector.go: DriveConnector implementing StreamingConnector
  (FetchStream) + FetchAll + FetchIncremental fallback paths, mirroring
  the wiki connector's three cursor semantics (resume fast-path,
  failure-does-not-advance-cursor, toSyncCursor snapshot), plus
  ListResources / ResolveResourceAncestors (top-down shared traversal,
  best-effort) / fetchDriveFileContent / parseDriveResourceID
- container.go + connector.go: register two Drive instances + metadata

Incremental detection uses modified_time returned directly by the list
API (verified) - no batch_query/metas call needed. Shortcuts are expanded
at list-parse time via shortcut_info; target_type is never "folder".

Frontend:
- DataSourceEditorDialog.vue: connectorDefs for feishu_drive/lark_drive,
  Drive root folder_token input + load button before the lazy-load tree,
  edit-mode prefill from resource_ids
- datasourceIcons.ts: reuse feishu/lark icons
- i18n (zh-CN/en-US/ko-KR/ru-RU): connector labels, descriptions, drive
  input group

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(datasource): refine Feishu Drive connector UI, channel and root folder

A batch of fixes from end-to-end verification of the Feishu/Lark Drive
connector, all aimed at matching the wiki connector's behavior:

Channel (knowledge "source" label):
- Add ChannelFeishuDrive / ChannelLarkDrive constants so Drive docs show
  "飞书云盘" / "Lark 云盘" instead of "unknown", distinct from the wiki
  connector's "飞书" (ChannelFeishu).
- fetchDriveFileContent / appendDriveFileListFailureItems select the
  channel by region via a new driveChannel() helper.
- ingestItem now prefers metadata["channel"] over ds.Type so the
  connector-supplied channel value reaches the knowledge base.
- doc-content.vue channelLabelMap maps feishu_drive/lark_drive.

Frontend Drive picker UX:
- loadDriveRoot persists the new folder_token in edit mode too (previously
  skipped updates in edit mode, so listResources read the old token).
- The folder_token input is now always visible alongside the tree (not a
  switch); the tree area shows a "load a folder first" placeholder until
  the first successful load.
- extractDriveFolderToken accepts a bare token or a Feishu Drive folder
  URL (https://xxx.feishu.cn/drive/folder/<token>) and extracts the token.
- Edit mode auto-loads when a saved folder_token exists, and reveals
  pre-existing selections via revealExistingSelections.
- Classify Drive list errors (403/forbidden, 401/auth, not-found) into
  actionable i18n hints.

Root folder name & selection:
- Add GetDriveFolderMeta (GET /drive/explorer/v2/folder/:folderToken/meta)
  to resolve the root folder's human-readable name; the list API only
  returns children. Best-effort, falls back to the token.
- Fix root folder ExternalID to be the bare rootFolderToken (no ":token"
  suffix) so it matches the saved resource_id form and the direct
  children's ParentID, which previously broke selection matching on edit.

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(datasource): sync a single selected Drive file without folder error

When a user selects a single file (not a folder) in the Drive picker, the
resourceID is "rootFolderToken:fileToken". FetchStream/FetchAll/
FetchIncremental previously passed fileToken straight to
ListDriveFilesRecursiveFrom, which expects a folder token - the Feishu
list API returns 1061002 (params error) for a file token, failing the
whole sync with "all fetched items failed".

The wiki connector resolves a single selected node via GetWikiNode; Drive
has no single-file meta API (folder meta only works on folders, and
metas/batch_query requires doc_type as input - a chicken-and-egg).
Instead, listDriveFilesForResource walks the root folder subtree (the
file's parent) and filters to the selected fileToken, yielding the full
driveFile (type/name/modified_time) needed for fetchDriveFileContent.

A sub-folder selection (fileToken is itself a folder) still walks that
sub-folder directly - ListDriveFilesRecursiveFrom accepts a folder token,
so no filtering is needed there.

Co-Authored-By: Claude <noreply@anthropic.com>

* ci: add build-test-images workflow for tar.gz artifact export

Manual-only workflow_dispatch that builds linux/amd64 Docker images for
the current branch and exports them as .tar.gz artifacts downloadable
from the Actions run page. No Docker Hub push, no secrets required.

- build-ui: builds frontend dist, builds weknora-ui image, exports tar.gz
- build-app: builds weknora-app image (CGO + duckdb), exports tar.gz
- Input choice: build both / app only / ui only
- Artifacts retained 7 days

Co-Authored-By: Claude <noreply@anthropic.com>

* ci: add build-test-images workflow for tar.gz artifact export

Manual-only workflow_dispatch that builds linux/amd64 Docker images for a
selected branch and exports them as .tar.gz artifacts downloadable from the
Actions run page. No Docker Hub push, no secrets required.

- build-ui: builds frontend dist, builds weknora-ui image, exports tar.gz
- build-app: builds weknora-app image (CGO + duckdb), exports tar.gz
- Input choice: build both / app only / ui only
- Artifacts retained 7 days

Placed on the default branch so the workflow appears in the Actions list;
trigger it with the branch you want to build (e.g. feat/datasource-feishu-drive).

Co-Authored-By: Claude <noreply@anthropic.com>

* docs(datasource): add feishu shared-blocks extraction design spec

Co-Authored-By: Claude <noreply@anthropic.com>

* docs(datasource): add feishu shared-blocks implementation plan

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(datasource): sync feishu drive docx via blocks API with export fallback

- Extract wiki/drive shared helpers from connector.go into shared.go
- Make fetchDocxWithBlocks a package-level function taking docxFetchInput
- Drive docx now renders via blocks API (Markdown + attachment/image
  sub-items), falling back to the export API on blocks errors or empty
  renders, mirroring the wiki connector
- fetchDriveFileContent returns item slices and takes multimodalEnabled

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(frontend): label feishu drive knowledge as 飞书云盘 in list

The knowledge list source column (DocumentListView.getSourceInfo) only
whitelisted feishu/notion/yuque/etc., so feishu_drive/lark_drive docs
fell through to the default "上传" label while the wiki connector's
"feishu" showed "飞书". Map feishu_drive → 飞书云盘 and lark_drive →
Lark 云盘 (i18n keys already existed), and add feishu_drive to the
source filter options in KnowledgeBase.vue.

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(frontend): polish feishu drive resource-step UI in datasource editor

- Replace the two stacked t-alert banners under the folder_token input:
  shareHint becomes an always-visible form-desc line, rootNotSupportedHint
  moves into a help-circle tooltip next to the label.
- folder_token is now required: red asterisk on the label, inline error
  status + tips on the input (replacing the global MessagePlugin) when
  empty on 加载/下一步, cleared on input.
- Step 2 选择范围 no longer scrolls as a whole: the token input stays
  fixed and the resource region (placeholder / loading / empty / tree)
  fills the remaining drawer height, with the tree scrolling internally.

Co-Authored-By: Claude <noreply@anthropic.com>

* docs(datasource): add feishu drive datasource integration guide

User-facing setup guide for feishu_drive/lark_drive: app creation,
required scopes (drive:drive:readonly / drive:export:readonly /
docx:document:readonly), sharing the folder to the app's group, the
four-step wizard, supported file types, sync semantics and FAQ.
Also clarify in extractDriveFolderToken's comment that pasted folder
URLs are matched by path and work for Lark links too.

Co-Authored-By: Claude <noreply@anthropic.com>

* refactor(datasource): unify feishu wiki/drive sync into a single generic streaming engine

Extract a single generic streaming sync engine (engine.go) shared by the wiki Connector and the Drive DriveConnector. Per-connector differences (node type, listing API, edit-time field, cursor wire format, fetch dispatch, log tag) are isolated behind the NodeOps[N] adapter; FetchAll/FetchIncremental become thin shells over the same engine.

Deliberate behaviour changes (design §2.4): the #2136 failure-doesn't-advance-cursor fix now applies to FetchIncremental too (previously it advanced the cursor before fetching, permanently skipping a node on a transient export failure); logs use 'stream progress/summary' uniformly and the FetchIncremental path gains per-100 progress + tally summary logs.

Structural prep for package split (design §3.1): anonymous Data structs in types.go/blocks.go are named so tests can construct wire types across packages.

Co-Authored-By: Claude <noreply@anthropic.com>

* refactor(datasource): split feishu connector into core/wiki/drive packages

Move shared code (Client, blocks, markdown, types, region, engine, shared helpers) into feishu/core; wiki and drive connectors into their own packages. Export core symbols (capitalize) so wiki/drive can reference them; wiki/drive import core and prefix cross-package references.

container.go registration updated to import core/wiki/drive (NewConnector from wiki, NewDriveConnector from drive, Region* from core).

Tests are NOT migrated yet (left in feishu/ root, package feishu) and will fail to compile until moved + adapted in a follow-up commit. Source builds clean (go build ./...feishu/... passes).

Co-Authored-By: Claude <noreply@anthropic.com>

* test(datasource): migrate feishu tests to core/wiki/drive packages

Move 14 test files to their subpackages per design §4. Adapt package declarations, imports, and capitalized core symbol references. Add TestMain (SSRF whitelist) to core and drive. Add local helpers (writeJSON, makeConfig, txt, blk constructors, recordingHandler) where cross-package sharing was not possible. Fix engine.go log wording (summary) clobbered by the capitalization script.

All tests pass: core 4s, wiki 13s, drive 3s.

Co-Authored-By: Claude <noreply@anthropic.com>

* refactor(datasource): reduce feishu core export surface; add drive cursor round-trip test

Lower-case 87 core symbols that are not referenced cross-package back to unexported (BlocksToMarkdown, CellToString, response types, BlockType constants, etc.), shrinking core's API surface to only what wiki/drive actually use. Restore NodeOps.Fetch capitalization (interface method must match wikiOps/driveOps implementations).

Add TestDriveCursorRoundTrip (design §3.2): driveOps.EncodeCursor/DecodeCursorTimes were new code with no direct test.

All tests pass: core 3.5s, wiki 13s, drive 3s.

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(datasource): repair feishu cleanup fallout

Restore core.RegionLarkDrive (cleanup lower-cased it; only container.go references it, outside wiki/drive scan). Restore wiki/connector_realapi_test.go local collectHandler type (cleanup wrongly prefixed core.). Apply gofumpt to helpers_test.go. Add open.feishu.cn/open.larksuite.com to test SSRF whitelist: BaseURL-default tests call ParseFeishuConfig which SSRF-validates the resolved hostname; under a proxy open.feishu.cn resolves to 198.18.0.0/15 restricted range.

All tests pass: core 3.2s, wiki 13s, drive 2.6s. make build-lite passes.

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(frontend): feishu drive data source UI and i18n

Add Drive folder/token picker strings and data source editor entries for the feishu_drive/lark_drive connectors across en-US/zh-CN/ko-KR/ru-RU.

Co-Authored-By: Claude <noreply@anthropic.com>

* chore: add trellis journal merge=union rule

Append-only developer journals merge cleanly across parallel sessions; task state lives in task.json, not the journal.

Co-Authored-By: Claude <noreply@anthropic.com>

* refactor(datasource): rename feishu/drive drive_connector.go to connector.go

Aligns naming with feishu/wiki subpackage (connector.go).

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(frontend): allow data:image base64 URIs in sanitized markdown

DOMPurify's ALLOWED_URI_REGEXP rejected data: URIs, so <img src="data:image/...">
in uploaded markdown files had their src stripped during sanitizeHTML — the file
preview showed broken images while the chunk view (minio:// via
hydrateProtectedFileImages) worked. Add data:image/ to the allowed URI scheme so
base64 images render in preview and in LLM answers that embed base64 images.

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(datasource): add FEISHU_DOCX_PARSE_MODE for feishu docx parse path

The blocks API path renders image blocks as empty ![图片]() placeholders and
fans images into separate knowledge items, breaking image↔document association
across retrieval/wiki/agent. FEISHU_DOCX_PARSE_MODE=export forces the async
export API (.docx binary -> docreader), so images are parsed inline and bound to
the parent document via parent_chunk_id (same as a regular docx upload). Default
(unset / "blocks") keeps the existing blocks-first behaviour. Affects both wiki
and drive connectors since they share FetchDocxWithBlocks.

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(datasource): default FEISHU_DOCX_PARSE_MODE to export

Switch the feishu docx parse default from blocks to export so embedded
images are parsed inline and bound to the parent document via
parent_chunk_id (retrieval / wiki / agent all associate images). Operators
who need the blocks behaviour (faster, keeps docx attachments, no
docreader round-trip) set FEISHU_DOCX_PARSE_MODE=blocks.

- shared.go: default unset -> export; update comment to match
- .env.example / docker-compose.yml: default export
- tests: pin FEISHU_DOCX_PARSE_MODE=blocks on blocks-behaviour tests so
  they don't break under the new default

Co-Authored-By: Claude <noreply@anthropic.com>

* docs(datasource): document FEISHU_DOCX_PARSE_MODE and refresh feishu source layout

- 飞书云盘接入说明: add section on docx parse mode (export default vs
  blocks), permission differences, export tradeoffs
- 数据源导入开发: add env var + mode comparison
- 数据源导入开发文档: rewrite content fetch flow (blocks/export paths),
  add pros/cons table, fix source-file table to core/wiki/drive layout

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: 修复合并main后丢失新增的国际化问题

* fix(i18n): 修复误删的国际化内容

* docs: 删除误提交的文件

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-08-05 19:39:49 +08:00
qilifan 3507156929
feat(storage): support AWS S3 NoAk default credentials (#2008)
* feat(storage): support AWS S3 default credentials

* fix(storage): allow clearing S3 credentials

* fix static checks and trim locale diff

---------

Co-authored-by: qilifan <4359902+qilifan@users.noreply.github.com>
2026-08-05 11:59:02 +08:00
wizardchen 350d9e4eca perf(container): batch legacy storage alias lookup at startup
The startup migration probed every workspace/provider pair with First(),
so each miss emitted a GORM "record not found" log line and a separate
round trip. Load all aliases once and index them in memory instead.
2026-08-04 22:48:54 +08:00
ochan.kwon c15c3e972f fix(retriever): rebuild a missing vector store engine on demand
The engine registry is per-process, so a store's engine is missing
whenever this process did not create it. That happens three ways:

  - Startup skips a store whose engine fails to construct and never
    retries it, so that instance cannot serve the store again -- not
    even after a restart, if the backend is slow to come up.
  - A store registered on one instance is absent on every other until
    they restart, because registration is not broadcast.
  - Registration can fail on the instance handling the create, leaving
    the store missing even there.

Each one surfaces as "vector store is currently unavailable" and is
cleared today only by restarting the process.

Add GetOrLoadByStoreID, which falls back to building the engine from the
store row when the lookup misses, and route the two bound-store lookups
through it. The method goes on RetrieveEngineRegistry rather than
StoreRegistry because that is the interface the factory functions
receive; the two declare GetByStoreID separately and neither embeds the
other.

Concurrent callers collapse onto one build. That build runs on a context
detached from the caller that started it: callers share the result, so
letting the first one's cancellation abort it would fail everyone else
waiting. A panic inside the build is contained, because singleflight
re-raises it on a goroutine the HTTP recovery middleware cannot reach
and the build calls third-party client constructors.

Publishing is guarded by a per-store generation sampled before the
build, so an engine that finishes after the entry was registered or
removed by someone else does not overwrite it and leave that engine
orphaned with its connections open. A failed build starts a cooldown:
collapsing only helps concurrent callers, so without it a backend that
stays down would cost a full build timeout on every sequential request.

Separate "the store is gone" from "its engine cannot be built right
now". Async delete handlers answer ErrVectorStoreNotFound with
asynq.SkipRetry, so reporting a database blip or a backend outage that
way would permanently discard knowledge-base and index delete tasks and
orphan the vector data they exist to remove. ErrVectorStoreUnavailable
covers the retryable cases; the repository already distinguishes them,
returning (nil, nil) for a missing row and an error for a failure.

For the same reason a caller's own cancellation is never folded into a
store sentinel. The ownership check runs first and queries the database
with that context, so on a shutdown it is usually where cancellation is
noticed.

A search resolves one engine per distinct store, sequentially, and this
server sets no HTTP read or write timeout, so the resolution loop gets a
budget above a single build. An exhausted budget still leaves the
engines warming, since the build is detached, and is reported as an
unavailable store because retrying is likely to succeed.

Build failures are logged where they happen, with the panic stack. The
cause cannot travel back to the caller -- factory errors embed endpoints
and credentials -- so without this the one thing an operator needs when
self-healing fails to heal would be discarded with the error.

Note a deliberate contract change: an ownership lookup failure used to
be reported as not-found, and a test asserted that on purpose. A
database failure says nothing about whether the store exists, and
treating it as permanent is what discards the task, so that assertion is
inverted rather than preserved.
2026-07-29 12:25:18 +08:00
wizardchen e88564a7db Remove redundant Wiki operation log 2026-07-28 11:18:33 +08:00
wizardchen 53ddad57c0 fix(im): harden connection lifecycle across replicas 2026-07-27 20:39:12 +08:00
zhangzherui 37de0afad0 fix(tasks): dequeue work for deleted knowledge bases 2026-07-23 12:17:14 +08:00
jacentsao 150c07368b feat(im): add Yunzhijia integration 2026-07-21 12:24:33 +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
qilifan 9afb8b7b68 feat(im,datasource): support Lark, Feishu's international edition
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>
2026-07-17 11:05:54 +08:00
wizardchen ceb4d1a310 feat(chat): add session-scoped temporary attachments with async parsing
Let users upload documents in chat without ingesting them into a knowledge base: files are parsed in the background, referenced by ID on send, and expire after a configurable TTL.
2026-07-16 17:41:27 +08:00
wizardchen 6d14cc3536 feat(resource): add stable resource registry with LLM-context alias compaction
Introduce resource://<handle> as the stable application identity for stored
objects, decoupling API responses, persisted rich text, and LLM prompts from
physical storage paths. Adds a resource catalog service (register/resolve/bind,
revocable expiring access grants), a request-local alias registry that compacts
resource references while in the LLM context and restores them (including across
streaming chunks), plus router, IM, chat-pipeline, and multimodal integration.

Includes schema migrations (resources, resource_bindings, resource_access_grants)
for sqlite, and hardens URL/output security handling.
2026-07-15 17:02:43 +08:00
wizardchen f8b3e5f148 feat(storage): add multi-instance storage backends per workspace
Introduce tenant-scoped storage backend registry so workspaces can register
multiple storage instances and bind each knowledge base to a specific backend,
with migration from legacy tenant-level storage config and new settings UI.
2026-07-15 14:54:39 +08:00
wizardchen ace84bc757 fix(knowledge): recover tasks safely after server restart
Stop failing distributed-mode knowledge rows on startup; let housekeeping
decide using span activity and Asynq queue state. In Lite mode, resume
wiki work from durable task_pending_ops and surface SERVER_RESTART errors
in the processing timeline with i18n support.
2026-07-14 17:55:26 +08:00
wizardchen 087fcc9fe7 feat(agent): add question suggestions with after-answer follow-ups
Enable agents to configure starter prompts and async follow-up questions after completed answers, with durable caching, analytics events, and chat/embed UI integration.
2026-07-14 11:17:25 +08:00
wizardchen 07ba01ec93 feat(worker): replace aggregate asynq concurrency with per-pool governance
Split the monolithic upstream worker budget into explicit core, post-process,
enrichment, maintenance, and shared elastic pools, expose live cluster capacity
on the runtime dashboard, and retire the legacy asynq.concurrency setting.
2026-07-13 15:51:06 +08:00
wizardchen d496d0fc73 feat(task-queue): split upstream workers into isolated core/enrichment/maintenance pools
Route summary/sync/maintenance tasks to dedicated queues and servers so parsing, enrichment, and batch work no longer share one concurrency budget, while extending the runtime dashboard and settings validation to reflect the new topology.
2026-07-10 23:51:29 +08:00
wizardchen 38aacc3113 chore(env): update WEKNORA_MODEL_MAX_CONCURRENCY to 32 in configuration files
Increase the default value of WEKNORA_MODEL_MAX_CONCURRENCY from 8 to 32 in .env.example, docker-compose.yml, and related application code. This change enhances the concurrency limit for background tasks, ensuring better performance and resource management across the system.
2026-07-10 14:51:01 +08:00
wizardchen 98ad41cda4 fix(models): harden background concurrency governor
Follow-up hardening on the per-model background concurrency governor:

- limiter: heartbeat now refreshes the ZSET key's PEXPIRE alongside the
  lease score, so a semaphore that stays saturated with no slot turnover
  can't let the whole key expire (which would drop every lease and admit
  over the limit); reuse one poll timer instead of allocating time.After
  each iteration under contention.
- governor: extract the process-wide governor + Gate helper into the
  limiter package so chat and vlm share one limiter/limit without
  importing each other; add an in-process localLimiter for Lite mode.
- vlm: gate background multimodal (VLM) calls through the same governor;
  previously only chat was throttled.
- chat: ChatStream releases its slot when the consumer abandons the
  stream and cancels ctx (select on ctx.Done, drain inner), fixing a
  slot/goroutine leak.
- container/sync_task: install the local governor in Lite mode and tag
  SyncTaskExecutor runs as background; honour model.max_concurrency=0 as
  an explicit disable instead of falling back to the default.
- tests: cover the governor gating, local limiter, and stream release.
2026-07-09 20:40:51 +08:00
wizardchen 63198c5d9f feat(models): cap background LLM concurrency per model
Background ingestion/enrichment stages (summary, question, graph,
multimodal) all target the same chat model, and asynq queue weights are
scheduling priority rather than throttling. A large upload could therefore
burst up to the entire worker pool of concurrent chat calls against a
single provider, unbounded across replicas, with no model-side rate limit.

Govern concurrency at the chat-client layer (the one place that sees every
task type), keyed by model ID:

- internal/models/limiter: Redis ZSET + Lua distributed semaphore with a
  lease heartbeat, expired-lease reclaim for crashed holders, and fail-open
  on any backend error or context cancellation.
- chat: concurrencyChat decorator (outermost in NewChat) acquires a
  per-model slot only for background tasks; interactive chat is never gated.
- router/task: asynq middleware tags every worker execution as background.
- container: wire the Redis limiter with WEKNORA_MODEL_MAX_CONCURRENCY
  (model.max_concurrency), default 8; enabled only when Redis is present.

Tested with miniredis: concurrency cap, expired-lease reclaim, per-key
isolation, and all fail-open paths (nil client, backend down, cancelled ctx).
2026-07-09 20:40:51 +08:00