Introduce platform API keys with capability-based access to tenant management,
system settings, runtime queues, and audit logs, plus admin UI for key lifecycle
and system audit log viewing.
Large Feishu wikis stopped syncing after the first batch (Tencent/WeKnora#2136:
5000+ docs, only ~150 ingested; #1262: a child-list failure aborted the run).
Three compounding causes, fixed in layers:
1. Rate-limit / transient failures had no retry. Feishu's wiki/drive/export
APIs are aggressively rate limited; a thousand-doc sync issues tens of
thousands of calls, and a single 429/5xx burst failed whole swathes of docs.
Add exponential backoff honouring Retry-After to doRequest (JSON) and
downloadRawBytes (files): 429 up to 3x, 5xx once, transport errors back off.
2. The batch path fetched the entire tree into memory before ingesting, so a
sync that hit the 2h task timeout lost all progress and restarted from
scratch, and a transient per-document export failure advanced the cursor and
skipped that doc permanently. Add an optional StreamingConnector interface,
implemented for Feishu: FetchStream interleaves fetch -> ingest -> checkpoint,
bounding memory to one item and persisting a per-node edit-time cursor at
page boundaries. The service dispatches to it via type assertion; connectors
without it fall back to FetchAll / FetchIncremental unchanged (non-breaking).
A resumed/incremental run skips nodes already recorded at their current edit
time (converges), a failed fetch does not advance the cursor (retried next
run instead of dropped), and partial listing failures emit error items and
carry prior edit times forward instead of aborting the sync.
3. Failures and skips were invisible. Unsupported node types (mindnote/slides/…)
were skipped with no item, error or log ("13 docs synced only 3"). FetchAll
now tallies discovered/fetched/failed/skipped per resource with a per-type
skip breakdown and a progress line every 100 nodes. The backend already
persisted per-item errors in SyncLog.result.errors but the frontend type
omitted the field; declare `result` on SyncLog and render up to 50 failed
documents in the sync-log drawer (#1262). i18n for zh-CN/en-US/ko-KR/ru-RU.
result.errors is a jsonb column shipped in every list response, so it is
capped at 100 samples server-side (recordSyncError); the exact failure total
comes from the bounded items_failed counter, which the drawer uses for its
count and "N more" line so a sync that fails thousands of docs stays bounded.
Each sample is a structured, localisable SyncItemError instead of a raw
"title: ...api error: status=500 body={json}" dump that repeated the title
and leaked status/body/log_id. The connector (feishuFailure) classifies the
error into a stable i18n code (+ the feishu code as a param); the service
builds {title, code, params, message}; the drawer localises via vue-i18n to
the viewer's language (zh/en/ko/ru), falling back to message. A custom
UnmarshalJSON keeps old string-form logs readable. The banner is localised
from items_failed too. Raw errors stay in the server logs. Follows the
two-tier norm of Airbyte/Fivetran/Onyx: human, actionable, localised
summaries in the UI; raw detail in logs. Transient errors say "will retry"
(the cursor is retained); auth/permission errors point at the fix instead.
Tests: client_retry_test (backoff), tally_test (accounting), connector_stream /
datasource_stream (streaming dispatch + checkpoint), connector_convergence
(timeout + transient-failure resume converges to full coverage; proven to catch
#2136 via bug injection), datasource_result_cap (error-sample cap + structured
localisable SyncItemError, no raw body), connector_error_reason (error→i18n-code
classification), sync_item_error (legacy-string + structured back-compat) — all
in the normal suite. connector_realapi / connector_seed are an opt-in real-Feishu
harness gated by the feishu_integration build tag AND env vars, never run in CI.
Stop hardcoding DOCREADER_PDF_RENDER_PARALLELISM=4 in compose so low-core
containers use min(4,cpu). Clarify WEKNORA_LANGUAGE precedence and align
docreader JPEG quality docs with the 85 default.
* feat(compose): align env vars in docker-compose and .env.example with code
docker-compose.yml / docker-compose.dev.yml
- app.environment: remove deprecated vars Go app no longer reads
(CRYPTO_MASTER_KEY, CRYPTO_SALT, TENANT_AES_KEY, ENABLE_GRAPH_RAG);
add missing vars the code actually consumes (OSS/S3/TOS/COS completion,
OpenSearch, Tencent VectorDB, Milvus credentials, Redis TLS/namespace,
OIDC, audit/invitation/quota, LLM tuning, doc timeouts, etc.)
- docreader.environment: complete PDF tuning knobs, SSRF/LOG_LEVEL/gRPC
params, GRPC_MTLS_REQUIRE_CLIENT_CERT; fix DOCREADER_PDF_JPEG_QUALITY
default 90 -> 85 to match code (config.py)
- mcp.environment: add MCP_SERVER_AUTH_TOKEN (required by HTTP transport),
WEKNORA_CHAT_TIMEOUT, WEKNORA_VERIFY_SSL, MCP_ALLOWED_UPLOAD_DIRS
- dev compose docreader.environment kept symmetric with prod
.env.example
- reorganize into A-J sections (deploy / data / retrieval / models /
parsing / auth / agent / integrations / observability / security)
- remove the four deprecated vars, document why
- add missing vars, fix NEO4J_URI to bolt:// (matches compose + single-node),
fix DORIS_COMPAT_MODE typo, complete docreader PDF tuning defaults
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(helm): inject NEO4J_ENABLE and drop deprecated TENANT_AES_KEY
helm graph bug fix
- NEO4J_ENABLE is the sole graph switch the Go app reads (since v0.1.6,
ENABLE_GRAPH_RAG is no longer read). helm never injected NEO4J_ENABLE,
so GraphRAG was silently broken: setting neo4j.enabled=true gave the
app NEO4J_URI/USERNAME/PASSWORD but not the switch, and the UI rejected
Node Extractor config with "请正确配置环境变量NEO4J_ENABLE".
- app.yaml: inject NEO4J_ENABLE=true inside the neo4j.enabled block;
remove the dead ENABLE_GRAPH_RAG injection
- NOTES.txt: update GraphRAG instructions (just enable neo4j, no need
to set the deprecated ENABLE_GRAPH_RAG)
- values.yaml: drop ENABLE_GRAPH_RAG, fix neo4j section comment
TENANT_AES_KEY cleanup (deprecated since v0.4.0, encryption now uses
SYSTEM_AES_KEY exclusively; Go app no longer reads it)
- secrets.yaml: stop generating/looking-up/writing TENANT_AES_KEY,
fix stale comment about tenants.api_key rotation
- app.yaml: remove TENANT_AES_KEY secretKeyRef
- values.yaml: drop tenantAesKey, fix existingSecret key list + comments
- cloud-image/firstboot.sh: stop generating/writing/printing TENANT_AES
- cloud-image/README.md: drop TENANT_AES_KEY from credential list
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
The generic OpenAI-compatible reranker hardcoded `truncate_prompt_tokens:
511` on every /rerank request. Providers that honor this vLLM-specific
field (e.g. SiliconFlow serving Qwen3-Reranker) keep only the last 511
tokens of the templated rerank prompt, cutting the instruction and query
off any document longer than ~511 tokens. Every relevance score then
collapses to near zero (~0.0067 instead of ~0.998), falls below the score
threshold, and knowledge-base search returns empty results. A direct curl
without the field returns the correct scores.
WeKnora already removed this exact hardcoded parameter from the embedding
path in #960; the rerank path was never fixed.
- Add `omitempty` to `truncate_prompt_tokens` and `additional_data` so
empty optional fields are not sent.
- Make truncation opt-in via `extra_config.truncate_prompt_tokens`
(validated > 0 at construction), preserving an escape hatch for
self-hosted vLLM deployments with small-context rerankers.
- Add regression tests reproducing the collapsed-score symptom and the
opt-in path.
Fixes#2143
Multiple GORM tag options must be separated by ';', not ','. The comma was
parsed as part of the type value, producing malformed DDL that causes
AutoMigrate(&Message{}) to fail on SQLite with a syntax error.
Restrict channel-managed sessions (API keys, IM, embed) to tenant admin
in the Web console for list/read paths, hide channel sidebar buckets from
non-admins, and add CountSessionsBySource for aggregate stats without
exposing session rows to viewers.
Split oversized candidate sets into concurrent batches instead of failing when retrieval exceeds the VikingDB rerank per-request cap, and align ko/ru locale hints with zh-CN.
Let tenant-wide retrieve keys serve tenant-bounded /files paths while
denying KB-restricted keys, declare knowledge batch write routes for
ingest-capable keys, and short-circuit ownership checks for API-key
principals already authorized by the gate and KB allow-list.
The floating `nginx:stable-alpine` tag drifts with every stable release.
A newer Alpine base (3.24+) fails to start on old hosts such as CentOS 7
(kernel 3.10 + old libseccomp), which broke v0.7.0. Pin to nginx 1.30.3 /
Alpine 3.23.5 by digest, the same base as the working v0.6.3 image.
Add GetOwnedSession method to enforce strict ownership checks for session mutations, ensuring tenant admins can read but not modify API-key sessions. Update relevant handlers to utilize this method for operations that alter session data, maintaining security and integrity of API-key sessions.
Let tenant admins list and open API-key sessions from the Web console while
keeping per-key isolation for everyone else. Pin the session source filter so
it no longer jumps when switching buckets, and resolve session origin on read
so deep links stay in sync with the active folder after refresh.
Use bounded detached contexts for wiki ingest tail cleanup so pending row
settlement, span closure, finalize enqueueing, and follow-up scheduling can
finish even after the asynq task context is cancelled.
Return settlement errors from pending row trimming and failed-op requeueing,
and only mark claims settled after rows are deleted, released, or
dead-lettered successfully. Requeue documents whose reduce updates were not
applied after context cancellation to avoid silently dropping wiki work.
Add unit coverage for detached cleanup contexts and settlement error handling.
Add a new 'is-docked' class to the ChatHeader component for improved styling when the references panel is visible. Introduce a 'hasReferencesPanel' prop to manage this state, enhancing the layout and responsiveness of the chat header on wider screens.
Finish-time metadata was discarded and implicit root traces opened by
StartSpan/StartGeneration were never ended, leaving orphaned parents in
Langfuse. Also stop mutating the global OTel text-map propagator.
Migrate WeKnora's Langfuse tracing from the legacy /api/public/ingestion
batch API to the OpenTelemetry Go SDK emitting OTLP/HTTP to
/api/public/otel/v1/traces — the Langfuse v3+ standard ingestion protocol.
Why: Langfuse v3 deprecated the legacy ingestion API in favor of OTLP, and
OTel-only backends (e.g. the LiteFuse Doris fork) dropped it entirely, so the
legacy client was incompatible. Migrating to the OTel SDK also adds W3C
traceparent cross-service propagation: an upstream caller's trace id is
inherited so its run and the WeKnora call land under one trace in the UI.
What:
- Manager owns an OTel TracerProvider backed by an otlptracehttp exporter
(Basic auth + the x-langfuse-ingestion-version gate header). Spans are
buffered by BatchSpanProcessor and exported complete on End, so a long
trace no longer fragments across flush batches.
- *Trace/*Span/*Generation wrap OTel spans; the public API (StartTrace/
Span/Generation, handles, InjectTracing, asynq/gin middleware, Config,
TokenUsage) is unchanged, so callers (agent/chat/handler/scheduler/asynqdl)
need no edits.
- W3C traceparent: GinMiddleware extracts traceparent from incoming requests;
AsynqMiddleware + InjectTracing propagate it across the asynq payload.
types.TracingContext gains a LangfuseTraceparent field.
- logger.CloneContext preserves the active OTel span across context rebuilds
so child spans (agent engine, summary generation) stitch to the HTTP trace
instead of orphaning into separate traces.
- StartSpan/StartGeneration re-establish the parent from the *Trace handle
when the ctx lost the active OTel span, covering background/derived contexts.
Compatibility: works with Langfuse v3+ (cloud / self-hosted / the bundled
docker-compose profile) and LiteFuse. Drops Langfuse v2 (legacy-only) support.
Uses the OTel Go SDK already (indirectly) in go.mod, promoting
otlptracehttp to direct; no third-party langfuse-go library.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Give chat a left-aligned header for rename/pin/copy/clear/delete, share session mutations across sidebar and chat view, and support copying the full conversation as Markdown.
Publish scoped API keys, worker-pool governance, multi-instance storage,
and the rest of the v0.7.0 feature set across CHANGELOG, READMEs, QA,
Swagger, and version pins.
Chat attachment parser rules belong on agents; drop the duplicate workspace settings section while preserving legacy tenant rules when engine config is updated without that field.
Decouple the references SSE event from the per-agent citation output toggle
so the retrieval-results drawer still works, and align follow-up suggestion
card layout with the chat column.
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>
Improve reference list readability by resolving URL-like titles to domains,
stripping markdown noise from snippets, and aligning suggestion chip hover
styles across chat and embed surfaces.
Update the SuggestedQuestionsRequest to include TagScopes for better filtering of knowledge items based on their parent knowledge bases. Modify related API documentation and frontend interfaces to accommodate the new structure. Ensure backend services handle the new tag scope logic correctly, including tests for the updated functionality.
Add a test to verify that selecting an agent defaults web search to off until the user enables it. Update the agent selection logic to ensure that the web search capability is controlled by user action rather than agent configuration. Modify comments in the Input-field component to reflect this change in behavior.
Implement improvements to the chat references drawer, including a new event for handling panel entry to ensure smooth scrolling to highlighted citations. Update the logic for retrieving references from agent events, allowing for better integration of citation data. Additionally, enhance tests to cover new functionality and ensure correct behavior of the references drawer during interactions.
Implement a mechanism to ensure follow-up suggestions are only displayed after the answer is fully rendered. Introduce an event for rendering completion and update related components to handle this new logic. Update tests to verify the correct behavior of follow-up suggestions based on rendering state.
Move citation protocol injection to the system layer so custom prompts no
longer own citation syntax. Agents can disable inline citations while source
aliases still encode and decode tool arguments correctly.
Replace raw chunk/document/KB IDs in LLM context with short cN/dN/bN/wN
aliases, decode tool arguments on the way in, and expand compact <ref/>
citations to the public <kb>/<web> format before user-facing output.
Preserve selected MCP IDs in the agent editor when services are disabled or
missing, display them as disabled options with clear labels, and tighten
setting-row layout so long multi-select tags do not overflow.
Shorten follow-up and refresh labels across locales, and replace flashy
suggestion card hovers with the same border, neutral background, and
shadow treatment used elsewhere in the chat page.
Keep the agent timeline placeholder visible between tool rounds when
nothing is pending, remove redundant thinking dot loaders, and replace
embed bouncing dots with a lightweight native spinner.
Remove redundant bounce-dot indicators from agent/RAG timelines and non-agent
answers; use existing pending step cards before activity and a compact spinner
for global wait states so streaming feedback stays aligned with the timeline.
Implement a maximum limit of 5 for the total number of images and attachments that can be uploaded in a chat session. Introduce a warning message for users when the limit is exceeded. Additionally, add functionality to clear pending uploads when switching sessions to prevent errors related to stale document IDs. Update localization files to include new warning messages in English, Korean, Russian, and Chinese.
Add functionality to normalize temporary attachment IDs, ensuring deduplication and enforcing a maximum limit of 5 attachments per message. Update related handlers and tests to support this new behavior, enhancing the robustness of attachment management in chat sessions.
Persist resolved temporary-attachment content onto the stored user message
so later turns can replay it in history. Close the retrieval progress spinner
on early pipeline exits, and reshape model-fallback messages with a proper
system role plus trailing user question.
Update the classification logic for follow-up questions to include reasoning about previously described images or documents. Ensure that follow-up queries referencing earlier attachments are correctly identified and processed without triggering unnecessary knowledge base searches. This change improves the model's ability to maintain context and respond accurately to user inquiries related to past interactions.
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.
Tighten model prompt so retrieval questions stay topic-bound and self-contained,
reserve knowledge slots in hybrid mode, and carry suggestion KB IDs into the next send.
When retrieved context or tool results contain Markdown images, dynamically
append output requirements to system prompts and final-answer instructions.
Also normalize fullwidth image parentheses in the frontend renderer so
localized model output still renders correctly.
Chat and agent tool context now emits answer-ready Markdown images instead
of internal <image> XML so copied content renders safely. The frontend also
normalizes legacy XML blocks in persisted conversations during streaming.
Improve follow-up question quality by feeding the model structured context
(evidence, capabilities, complete turns) instead of raw RAG content, and
rank knowledge candidates by current-topic relevance.