Extend the AI Chat widget with three ways to ground a conversation:
- Images: attach images to a message, sent inline as OpenAI multimodal
content parts for vision-capable models. A hint warns when the selected
model likely has no vision support.
- Knowledge bases: pick RAG collections exposed by /api/v1/knowledge/.
- Web pages: ingest a URL via /api/v1/retrieval/process/web.
Open WebUI does not run RAG from the chat-completions `files` parameter,
so attached collections (web pages and knowledge bases) are grounded by
retrieving the most relevant chunks at send time
(/api/v1/retrieval/query/collection) and injecting them as system context.
Also add a Retry action to re-run the last turn after a model failure, and
handle the paginated `{ items, total }` shape of the knowledge endpoint on
newer Open WebUI versions.
Adds a new "openWebUi" integration kind (under a new "ai" category) and an
AI Chat widget for chatting with models served by Open WebUI.
- Integration: Bearer API key auth, model list, native chat history CRUD, and
token-by-token streaming chat completions (SSE).
- Widget: in-input model picker, streaming responses, and an in-widget history
panel. Reconstructs conversations from Open WebUI's message tree with a flat
fallback.
- Streaming is delivered over the WebSocket subscription link.
- Adds integration and widget documentation.
Beszel only stores stats at 1m, 10m, 20m, 120m, 480m intervals.
The 1440m type doesn't exist, so queries for 1w/30d returned empty
results. Use 480m (8h) with appropriate perPage (21 for 1w, 90 for 30d).
* fix(beszel): harden cache layer and prevent blank widgets
- Add debug logging across Beszel integration, request handler, and tRPC
router (auth, fetch, SSE, per-procedure entry/exit) gated behind
LOG_LEVEL=debug
- cached-request-handler: retry with backoff, isValid predicate to skip
caching invalid data, in-flight dedup (single-flight per channel) to
avoid thundering herd after cache invalidation
- redis channel: set-then-publish so storage is always consistent even
when pubsub publish fails
- Beszel handlers: opt into fallbackToStaleOnError and retry so brief
upstream hiccups don't throw away good cached data
- beszel-system-stats: add refetchInterval matching each time period's
cache TTL so historical charts refresh in the background
- tRPC router: switch Promise.all -> Promise.allSettled for getSystems
and getAlerts; getSystemStats returns an error object instead of
throwing. Each result carries an optional error field so one failed
integration no longer nukes the whole widget
- Widgets: add explicit isPending loader, empty state for grid and
stats, and a shared per-integration error indicator (tooltip with
failed integration names). Alerts and table now only show their
empty state after loading completes
- Translation: add empty.noSystems key to beszelSystemGrid and
beszelSystemStats
Addresses #6030
* style: auto-fix lint and format
---------
Co-authored-by: ajnart <ajnart@users.noreply.github.com>
Replace all ternary operators with if/else, &&/||, or early returns.
Remove unused noAnimation constant that caused lint error.
Fix variable shadowing in tooltip deduplication loop.
- Add subscribeSystemStats tRPC subscription bridging PocketBase SSE
- Add subscribeRealtimeMetrics to BeszelIntegration with SSE parsing
- Add error handling: try/catch in subscription, response check in topic POST
- Add cacheDurationForInput to request handler for per-period cache TTL
- Add mock subscribeRealtimeMetrics with 1s interval for dev testing
* fix(deps): update dependency zod to ^4.3.5
* fix: omit can not be used with refine
* fix: convert intersection to object due to trpc-openapi issue
* fix: remove omit after refine
---------
Co-authored-by: homarr-renovate[bot] <158783068+homarr-renovate[bot]@users.noreply.github.com>
Co-authored-by: Meier Lukas <meierschlumpf@gmail.com>
When Docker API returns `null` for container ports (instead of `[]`),
the Docker management page crashes. Added optional chaining on
`ports?.length` to handle this case.
Fixes#5311
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>