* fix(hybrid-search): normalize MatchCount once instead of at the truncation site
An omitted match_count deserializes to Go's zero value, which reached the
truncation step in HybridSearch and sliced the deduplicated chunk list to
[:0] — a successful retrieval returned an empty result set. A negative
value panicked on that same slice bound and surfaced as a 500.
Resolve the value once at the top of HybridSearch via normalizedMatchCount
so all three consumers agree, rather than patching the truncation site
alone: the over-retrieval floor, the FAQ iterative-retrieval trigger
(which never fired on this path because len(chunks) < 0 is false), and the
truncation itself.
Bound the FAQ iterative path while here, since normalization is what makes
it reachable with a large MatchCount: its TopK seeds from MatchCount*3 and
doubles five times, previously without limit. It now stops at the pool cap
instead of re-issuing an identical query.
Co-authored-by: Cursor <cursoragent@cursor.com>
* refactor(retrieval): share the default retrieval depth as one constant
The value 50 was written three times — the over-retrieval floor in
HybridSearch, the MatchCount fallback added alongside it, and
RetrievalConfig.GetEffectiveEmbeddingTopK — with nothing recording that the
three are meant to agree. Anyone tuning one would silently desync the
others.
Promote it to types.DefaultRetrievalTopK. No behavior change.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: drakezhang <drakezhang@tencent.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
AppendWithOverlap deduplicates chunker-prepended table headers by
matching a suffix of acc against a head window of next. When chunks are
strictly contiguous (positionOverlap == 0) there is no overlap to
deduplicate, but the loop still ran. If a sentence at the tail of acc
reappeared as real content inside next's head window (same sentence
written multiple times in the document), the head of next was mistaken
for a prepended header and deleted — silently losing up to hundreds of
bytes from the merged result.
This affects three callers:
- chat_pipeline.mergeOverlappingChunks: RAG search results returned
to the LLM with truncated content
- wiki_ingest.reconstructContent: distillation text fed to the LLM
is truncated, so wiki search returns 0 hits for present content
- frontend doc-content.vue port: the "merged" document view drops
the same segment
Fix: skip text matching when positionOverlap <= 0 and concatenate
verbatim. The chunker's prepended-header case only occurs inside the
overlap region (positionOverlap > 0), which still runs the loop.
Add a regression test covering a compliance-doc scenario where a
logging-requirement sentence recurs in a later Compliance section.
* test(datasource): cover scoped sync deletions
- deleted connector items remove the matching KB knowledge, scoped per data
source via metadata datasource_id + external_id
- SyncDeletions=false neither deletes nor counts
- stream handler classifies deleted/failed items like the batch loop
* fix(datasource): perform real sync deletions scoped per data source
- applyFetchedItem now performs the KB deletion instead of only counting
- lookup is scoped to datasource_id + external_id so identical external IDs
from two data sources cannot collide or overwrite each other
- ingestItem update-path lookup uses the same scoped query
* fix(datasource): note failed deletions retry only on full sync
- SyncResult.DeletionFailed tracks deletion failures (subset of Failed)
- streaming partial message warns that failed deletions only retry on a full
sync, since the connector cursor is checkpointed past the deleted item
* fix(datasource): humanize deletion errors, keep raw detail in logs
- raw lookup/delete errors go to server logs only, with full context
- UI samples carry a humanized "see server logs" fallback
- add datasource.syncError.* i18n keys
Note: ko-KR / ru-RU syncError translations were generated without a
native-speaker review.
* fix(datasource): hard-delete synced rows and tighten deletion scoping
Sync-internal deletions now call HardDeleteKnowledge after the soft-delete
cascade so tombstones cannot block re-sync; subtree sweeps and URL metadata
attach failures are handled with datasource scoping and explicit errors.
* chore: add git hooks aligned with CI and PR checks
Install via scripts/install-git-hooks.sh (sets core.hooksPath). Pre-commit
runs whitespace/gofmt/golangci-lint on staged files; pre-push mirrors
app/frontend/cli workflows on the diff since origin/main.
* fix: gofmt test file; tighten pre-push to match CI app workflow
Pre-push now gofmts the full PR diff and runs go vet on all app packages
(like app.yml), not only Go files in the latest commit. Previous pushes
skipped checks via --no-verify and because hook-only commits had no .go files.
* fix(hooks): align pre-push diff with GitHub PR base via gh
Use three-dot diff against the open PR baseRefOid (same as CI) instead of
a two-dot merge-base range; run full go vet on every push with Go PR changes.
* style: gofumpt datasource_service_test.go
---------
Co-authored-by: wizardchen <wizardchen@tencent.com>
MinerU keys file_parse results by the uploaded filename stem, so preserving
real basenames requires dynamic response lookup instead of results.document.
Also append FileType when the basename has no extension.
- Updated test files to use types.EmbedChannelContextKey instead of middleware.EmbedChannelContextKey for consistency.
- Introduced context cloning decisions for EmbedChannelContextKey to ensure proper context management during background tasks.
- Added tests to verify the correct behavior of context key declarations and their cloning decisions.
- Added a new configuration option for agents to enable or disable long-term memory.
- Implemented UI elements in the Agent Editor for managing long-term memory settings.
- Updated internationalization files for English, Korean, Russian, and Chinese to include new labels and descriptions related to long-term memory.
- Enhanced backend logic to support memory retrieval and management based on user and agent preferences.
- Introduced a new tool for searching long-term memory, ensuring it respects the agent's memory settings.
- Added tests to verify the functionality of the new memory features and their integration with existing systems.
- Introduced a new method to mark memories as forced consolidated, allowing users to request immediate consolidation.
- Added a new message for users indicating that a tidy-up just ran and to try again shortly.
- Updated internationalization files for English, Korean, Russian, and Chinese to include the new message.
- Enhanced memory repository and service logic to support the new forced consolidation functionality.
- Updated database schema to include a new timestamp for forced consolidation.
- Updated the item listing query to ensure deterministic paging by including the item ID in the order clause.
- Added a new test to verify that models used by memory extraction cannot be deleted, ensuring proper error handling.
- Refactored the model deletion logic to check both embedding and extraction models against tenant memory configurations.
- Introduced a new method to handle tombstone records during memory clearing, ensuring that live memories retain their tombstone status when cleared.
Persist extracted and explicit memories across sessions with topic
resolution, semantic recall, document affinity, consolidation, workspace
settings, and inbox/interests UI.
* 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
* feat(im): support reverse proxy for feishu websocket long connection
Add api_base_url channel config for Feishu/Lark IM adapters so internal
deployments can route Feishu API calls and the WebSocket long connection
through a reverse proxy (nginx). The config overrides both the SDK
bootstrap domain (WithDomain) and the adapter HTTP API origin (api()),
unified into a single field.
- adapter: NewAdapter gains apiBaseURL + SSRF validation (http(s) scheme,
ValidateURLForSSRF), mirroring wecom's validateEndpointURL; api() uses
the override instead of region.OpenBaseURL
- longconn: NewLongConnClient forwards apiBaseURL to larkws.WithDomain
- factory: reads api_base_url once, passes to both adapter and longconn
- frontend: Feishu/Lark channel config gains an API Base URL input
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(ci): restore build-test-images workflow dropped by 00d7090f
00d7090f ("docs: 删除误提交的文件") deleted build-test-images.yml
alongside two obsolete design docs, causing the workflow_dispatch
trigger to disappear from the branch. Restore it so the manual
build-test-images action is available again.
Co-Authored-By: Claude <noreply@anthropic.com>
* feat(im): support reverse proxy for feishu websocket long connection
飞书 SDK 的 WebSocket 长连接分两阶段:bootstrap HTTP 拿 ws 地址 + ws dial
直连飞书下发的地址。WithDomain 只控制 bootstrap 请求目标,ws dial 的地址
由飞书服务端下发(host 为 msg-frontier.feishu.cn),SDK 不支持改写。
内网部署无法直连飞书 wss,因此新增 api_base_url 字段:让 bootstrap 和
HTTP API 走反代,并通过 nginx sub_filter 改写飞书下发的 wss 地址为明文
ws,使 ws dial 也经反代回连 nginx。
Co-Authored-By: Claude <noreply@anthropic.com>
* feat(frontend): add api_base_url config for feishu IM channel
新增 api_base_url 配置入口与 i18n 文案,用于内网反代部署。
Co-Authored-By: Claude <noreply@anthropic.com>
* docs(im): document feishu api_base_url reverse proxy usage
补充 nginx 反代配置说明:三个 location(bootstrap/open.feishu.cn +
sub_filter、ws dial/msg-frontier.feishu.cn、OpenAPI/open.feishu.cn),
以及 sub_filter 改写 wss 地址、rewrite 前缀剥离、SSRF 白名单等要点。
Co-Authored-By: Claude <noreply@anthropic.com>
* feat(ci): add manual docker build workflow
Add a workflow_dispatch-only workflow to build ui/app/docreader/sandbox
images on demand. No auto-trigger on push/tag. Each package is gated by
a boolean input (build_all + per-package), and the branch is picked via
the native workflow_dispatch ref selector. Builds are load-only (push
false) to verify Dockerfiles without needing any registry secret.
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(ci): sync manual docker build workflow from main (add tar export + unified package job)
* Delete .github/workflows/docker-build.yml
* Delete .github/workflows/build-test-images.yml
---------
Co-authored-by: Claude <noreply@anthropic.com>
Notes (media_type=11) were skipped as "unsupported by wiki OpenAPI". The wiki
namespace indeed never exposes a note body, but IMA reads it from a second
namespace: get_media_info reports a notebook_id, which
/openapi/note/v1/get_doc_content turns into the note text. The connector
already parsed that notebook_id into item metadata and then dropped the
record, so this wires up the one call that was missing.
Note bodies arrive as plain text and are ingested as Markdown, since IMA notes
are authored as rich text and the export keeps its heading and list markers.
An unreadable note now takes the same retry path as a failed download instead
of being recorded as synced; empty notes are skipped.
AI sessions (12) and video parses (16) stay skipped, as those genuinely have
no read endpoint, and the connector description now names them specifically
rather than implying notes are unsupported.
Also accept the {retcode, errmsg} spelling of the response envelope alongside
{code, msg}. The reference MCP implementation confirms {code, msg} is correct,
but several published IMA references disagree, and under the wrong spelling
the status code would decode as 0 and turn every API error into a silent
success.
The sync cursor was built from the raw IMA listing before any content was
fetched, so an item whose get_media_info or download failed was still recorded
as "seen with this media_id". Every later incremental sync then skipped it as
unchanged and the document was silently missing from the knowledge base for
good. Track the listed keys and the successfully synced keys separately: the
cursor now only remembers what was actually resolved, while delete detection
keeps using the full listing so a failed download is never mistaken for a
document that vanished. Deterministic skips (unsupported media types, items
with no URL) are still recorded so they are not re-probed every cycle.
Alongside that:
- Drop media_type from logicalKey. get_knowledge_list omits the field, so
folding it in meant every external_id would shift the day IMA starts
populating it, which reads downstream as "every document deleted".
- Download URL-backed media that carry auth headers rather than handing the
bare URL to the ingest layer, which cannot replay those headers.
- Derive image extensions from the response Content-Type; IMA reports every
image as media_type=9, so a JPEG was being written as .png.
- Stop logging API response bodies, which carry pre-signed storage URLs and
per-request auth headers.
- Validate media URLs against the SSRF policy before the first connection.
- Stop writing the redundant kb_media map into the persisted cursor.
- Say in the connector description that notes and AI sessions are skipped.
Combined wiki extraction can require well over 8k completion tokens.
When MaxTokens is unset, OpenAI-compatible clients omit max_tokens and
providers such as DeepSeek default to 8192, truncating mid-JSON and
failing postprocess.wiki.extract with unexpected end of JSON input.
Set a 32768 completion budget for all generateWithTemplate calls so
large extracts can finish while short replies still stop early.
Fixes#2604
- Added detailed logging for sandbox creation and execution failures in `sandbox_check.go` and `cube_remote_client.go`.
- Introduced `logCubeSandboxCreated` and `logCubeDataPlaneExec` functions to capture relevant context during sandbox operations.
- Improved `RemoteErrorDiagnostics` to format error messages with additional context, including operation type and HTTP status.
- Updated tests to validate new error diagnostics functionality.
* feat(sandbox): unify remote sandbox on E2B protocol with self-hosted support
- Add e2b.proxy_url gateway config and generic gateway transport layer
- Add envd compat layer for Basic auth and multipart /files uploads
- Support Dockerfile.sandbox runtime and e2b-backend build targets in CI
- Rename sandbox image non-root user to align with E2B template convention
- Add sandbox-protocol.md and extend cluster deployment / local repro docs
Enables connecting to any E2B-compatible control plane (E2B Cloud,
CubeSandbox, Agent-Sandbox, etc.) without per-backend client code.
* style(sandbox): gofmt tenant_resolver struct alignment
Reject out-of-range and duplicate response indexes before mapping them to batch inputs. Return an error when a requested input has no response item instead of silently passing an incomplete batch downstream.
Add focused coverage for malformed responses and valid out-of-order results.
Signed-off-by: PP1 <74917296+pengpengyi92@users.noreply.github.com>
New endpoint GET /api/v1/auth/oidc/start — unlike /auth/oidc/url which
returns JSON and requires frontend JS to navigate, this endpoint directly
returns a 302 redirect to the OIDC Provider's authorization page. This
enables external platforms (enterprise portals, Nexus, etc.) to give a
single clickable link that triggers the full OIDC authorization code
flow and, when the IdP has an active SSO session, achieves passwordless
login without any frontend involvement.
- backend derives the callback URL from the request origin automatically
(no caller-supplied redirect_uri needed)
- OIDC nonce cookie is bound identically to /auth/oidc/url (CSRF/replay
protection)
- registered in the auth middleware public-path whitelist (otherwise
the global auth middleware returns 401 before routing reaches the
handler)
- refactored shared nonce-cookie helper out of GetOIDCAuthorizationURL
for reuse by OIDCStart
* 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>
Deduplicate the two inline SearchResult rebuilds (SSE references and
agent-stream references) into one searchResultFromMap helper.
Add a JSON round-trip test pinning all fields.
- Reconcile stale pending invites after auto-accept AddMember
- Adopt invited workspace as home tenant when invitee is tenantless
- Await refreshFromAuthMe on SPA boot; sync auto_accept in hydrateSessionFromToken
- Document capabilities.auto_accept_invitation; extend client SDK and OpenAPI
Add a global tenant switch (tenant.auto_accept_invitation /
WEKNORA_TENANT_AUTO_ACCEPT_INVITATION, default false). When enabled,
inviting an already-registered user adds them to the tenant as an
active member immediately, instead of creating a pending invitation
the invitee must accept from their inbox.
Backend:
- CreateInvitation reads the switch and, when on, calls the new shared
addMemberAndRespond helper (extracted from TenantMemberHandler.AddMember)
to persist the member and write the HTTP response. Both call sites
share it so the sentinel->status mapping can't drift apart.
- Register the setting in the system_setting registry (bool, default
false).
- Expose the switch as capabilities.auto_accept_invitation on
GET /auth/me, so the SPA can adapt the invite popup without calling
the super-admin settings API.
- Cover enabled/disabled, already-a-member, unknown email, owner role
rejection, and nil member service with unit tests.
Frontend:
- The invite popup adapts to the mode. With auto-accept, the form
submits directly (button reads "Send", no "confirm invitation" step)
and refreshes the member roster silently (no toast; the new row is
the feedback). The classic two-step flow is unchanged when off.
- Fix capabilities hydration: refreshFromAuthMe (the only reader of
/auth/me capabilities) was invoked solely from the invitation-token
flow, so on page reload can_create_tenant and auto_accept_invitation
stayed at their initial false. Trigger it from initFromStorage once a
token is restored so deployment switches are reconciled with the live
server.