Merge remote-tracking branch 'origin/staging' into improvement/enterprise-self-host

Author: icecrasher321

apps/sim/app/api/tools/confluence/selector-spaces/route.ts

@@ -23,6 +23,27 @@ const PAGE_LIMIT = 250
 
 type SpaceStatus = 'current' | 'archived'
 
+/** A row as Confluence returns it. `status` is not marked required in the v2 schema. */
+interface SpaceRow {
+  id: string
+  name: string
+  key: string
+  status?: SpaceStatus
+}
+
+interface SpacesResponse {
+  results?: SpaceRow[]
+  _links?: { next?: string }
+}
+
+/** A row as this selector emits it, with `status` always resolved. */
+interface SelectorSpace {
+  id: string
+  name: string
+  key: string
+  status: SpaceStatus
+}
+
 /**
  * Cursor format: `<status>:<innerCursor>`. Empty inner cursor means "first page
  * of that status". When current is exhausted we hand back `archived:` so the
@@ -45,7 +66,7 @@ export const POST = withRouteHandler(async (request: NextRequest) => {
     const parsed = await parseRequest(confluenceSpacesSelectorContract, request, {})
     if (!parsed.success) return parsed.response
 
-    const { credential, workflowId, domain, cursor } = parsed.data.body
+    const { credential, workflowId, domain, cursor, spaceKey } = parsed.data.body
 
     if (!credential) {
       logger.error('Missing credential in request')
@@ -101,32 +122,73 @@ export const POST = withRouteHandler(async (request: NextRequest) => {
     const baseUrl = `https://api.atlassian.com/ex/confluence/${cloudIdValidation.sanitized}/wiki/api/v2/spaces`
     const { status, inner } = parseCursor(cursor)
 
-    const params = new URLSearchParams({ limit: String(PAGE_LIMIT), status })
-    if (inner) params.set('cursor', inner)
-    const url = `${baseUrl}?${params.toString()}`
+    const requestSpaces = async (
+      search: URLSearchParams
+    ): Promise<{ ok: true; data: SpacesResponse } | { ok: false; response: NextResponse }> => {
+      const response = await fetch(`${baseUrl}?${search.toString()}`, {
+        method: 'GET',
+        headers: { Accept: 'application/json', Authorization: `Bearer ${accessToken}` },
+      })
+
+      if (!response.ok) {
+        const errorText = await response.text()
+        const message = parseAtlassianErrorMessage(response.status, response.statusText, errorText)
+        logger.error('Confluence API error response', { error: message, status: response.status })
+        return { ok: false, response: NextResponse.json({ error: message }, { status: 502 }) }
+      }
 
-    const response = await fetch(url, {
-      method: 'GET',
-      headers: { Accept: 'application/json', Authorization: `Bearer ${accessToken}` },
-    })
+      return { ok: true, data: await response.json() }
+    }
 
-    if (!response.ok) {
-      const errorText = await response.text()
-      const message = parseAtlassianErrorMessage(response.status, response.statusText, errorText)
-      logger.error('Confluence API error response', { error: message, status: response.status })
-      return NextResponse.json({ error: message }, { status: 502 })
+    const toSpaces = (rows: SpaceRow[] | undefined, queried: SpaceStatus): SelectorSpace[] =>
+      (rows ?? []).map((space) => ({
+        id: space.id,
+        name: space.name,
+        key: space.key,
+        // Trust the row's own status; fall back to the status this call asked for.
+        status: space.status ?? queried,
+      }))
+
+    if (spaceKey) {
+      /**
+       * Exact-key lookup, bypassing the paged drain the dropdown otherwise depends
+       * on. Both statuses are queried explicitly rather than omitting `status`: it
+       * takes a single value on this endpoint (unlike `/pages`, where it is an array
+       * with a documented `current,archived` default) and `/spaces` documents no
+       * default, while archived spaces are reachable in the paged path and sync works
+       * against them. Concurrent because the key is user-typed text, so a miss — which
+       * dominates while typing — would otherwise pay two round-trips.
+       */
+      const [current, archived] = await Promise.all([
+        requestSpaces(
+          new URLSearchParams({ keys: spaceKey, limit: String(PAGE_LIMIT), status: 'current' })
+        ),
+        requestSpaces(
+          new URLSearchParams({ keys: spaceKey, limit: String(PAGE_LIMIT), status: 'archived' })
+        ),
+      ])
+      // Only a total failure is fatal: one leg erroring must not discard a match
+      // the other leg found.
+      if (!current.ok && !archived.ok) return current.response
+
+      // A single resolution, never a page in a drained stream, so no cursor.
+      return NextResponse.json({
+        spaces: [
+          ...(current.ok ? toSpaces(current.data.results, 'current') : []),
+          ...(archived.ok ? toSpaces(archived.data.results, 'archived') : []),
+        ],
+        nextCursor: undefined,
+      })
     }
 
-    const data = await response.json()
-    const spaces = (data.results || []).map((space: { id: string; name: string; key: string }) => ({
-      id: space.id,
-      name: space.name,
-      key: space.key,
-      status,
-    }))
+    const params = new URLSearchParams({ limit: String(PAGE_LIMIT), status })
+    if (inner) params.set('cursor', inner)
+    const result = await requestSpaces(params)
+    if (!result.ok) return result.response
+    const data = result.data
 
     let nextInner: string | undefined
-    const nextLink = data._links?.next as string | undefined
+    const nextLink = data._links?.next
     if (nextLink) {
       try {
         nextInner = new URL(nextLink, 'https://placeholder').searchParams.get('cursor') || undefined
@@ -142,7 +204,7 @@ export const POST = withRouteHandler(async (request: NextRequest) => {
       nextCursor = 'archived:'
     }
 
-    return NextResponse.json({ spaces, nextCursor })
+    return NextResponse.json({ spaces: toSpaces(data.results, status), nextCursor })
   } catch (error) {
     logger.error('Error listing Confluence spaces:', error)
     return NextResponse.json(

apps/sim/app/workspace/[workspaceId]/knowledge/[id]/components/connector-selector-field/connector-selector-field.tsx

@@ -1,16 +1,23 @@
 'use client'
 
-import { useMemo } from 'react'
+import { useMemo, useState } from 'react'
 import { ChipCombobox, type ComboboxOption, Loader } from '@sim/emcn'
+import { SEARCH_DEBOUNCE_MS } from '@/lib/url-state'
 import { SELECTOR_CONTEXT_FIELDS } from '@/lib/workflows/subblocks/context'
 import type {
   ConfigFieldMap,
   ConfigFieldValue,
 } from '@/app/workspace/[workspaceId]/knowledge/[id]/hooks/use-connector-config-fields'
 import { getDependsOnFields } from '@/blocks/utils'
 import type { ConnectorConfigField } from '@/connectors/types'
+import { getSelectorDefinition } from '@/hooks/selectors/registry'
 import type { SelectorContext, SelectorKey } from '@/hooks/selectors/types'
-import { useSelectorOptions } from '@/hooks/selectors/use-selector-query'
+import {
+  useSelectorOptionDetail,
+  useSelectorOptionDetails,
+  useSelectorOptions,
+} from '@/hooks/selectors/use-selector-query'
+import { useDebounce } from '@/hooks/use-debounce'
 
 interface ConnectorSelectorFieldProps {
   field: ConnectorConfigField & { selectorKey: SelectorKey }
@@ -34,6 +41,7 @@ export function ConnectorSelectorField({
   disabled,
 }: ConnectorSelectorFieldProps) {
   const isMulti = Boolean(field.multi)
+  const [searchTerm, setSearchTerm] = useState('')
 
   const context = useMemo<SelectorContext>(() => {
     const ctx: SelectorContext = {}
@@ -62,15 +70,68 @@ export function ConnectorSelectorField({
   }, [field.dependsOn, sourceConfig, configFields, canonicalModes])
 
   const isEnabled = !disabled && !!credentialId && depsResolved
-  const { data: options = [], isLoading } = useSelectorOptions(field.selectorKey, {
+  const {
+    data: options = [],
+    isLoading,
+    hasMore,
+    isFetchingMore,
+    truncated,
+    error,
+  } = useSelectorOptions(field.selectorKey, {
     context,
     enabled: isEnabled,
   })
 
-  const comboboxOptions = useMemo<ComboboxOption[]>(
-    () => options.map((opt) => ({ label: opt.label, value: opt.id })),
-    [options]
+  /**
+   * Label every selected value, including values restored from saved config that no
+   * in-session search would have resolved. Queries are keyed on `context`, so a label
+   * can never outlive the context that produced it, and they share keys with the
+   * speculative lookup below so an already-resolved id costs no extra request.
+   */
+  const singleValue = Array.isArray(value) ? value[0] : value
+  const selectedIds = useMemo(
+    () => (Array.isArray(value) ? value : value ? [value] : []).filter(Boolean),
+    [value]
   )
+  const selectedOptions = useSelectorOptionDetails(field.selectorKey, {
+    context,
+    detailIds: isEnabled ? selectedIds : [],
+  })
+
+  /**
+   * The option list fills by draining pages in the background and the combobox filters
+   * it client-side, so an option is only findable once its page has arrived. Where the
+   * selector's `fetchById` tolerates an unknown id, whatever the user typed is resolved
+   * directly so an exact key is selectable immediately. Gated on that flag because most
+   * implementations resolve a record by id, where a partial keystroke is a guaranteed
+   * failed upstream request rather than an empty result.
+   */
+  const resolvesUnknownIds = Boolean(getSelectorDefinition(field.selectorKey).resolvesUnknownIds)
+  const debouncedSearch = useDebounce(searchTerm.trim(), SEARCH_DEBOUNCE_MS)
+  const { data: searchedOption } = useSelectorOptionDetail(field.selectorKey, {
+    context,
+    detailId:
+      resolvesUnknownIds && isEnabled && debouncedSearch.length > 0 ? debouncedSearch : undefined,
+  })
+
+  const emptyMessage = getEmptyMessage(field.title.toLowerCase(), {
+    error,
+    hasMore,
+    isFetchingMore,
+    truncated,
+  })
+
+  const comboboxOptions = useMemo<ComboboxOption[]>(() => {
+    const base = options.map((opt) => ({ label: opt.label, value: opt.id }))
+    const seen = new Set(base.map((opt) => opt.value))
+    const extras: ComboboxOption[] = []
+    for (const option of searchedOption ? [...selectedOptions, searchedOption] : selectedOptions) {
+      if (seen.has(option.id)) continue
+      seen.add(option.id)
+      extras.push({ label: option.label, value: option.id })
+    }
+    return extras.length > 0 ? [...extras, ...base] : base
+  }, [options, selectedOptions, searchedOption])
 
   if (isLoading && isEnabled) {
     return (
@@ -88,8 +149,9 @@ export function ConnectorSelectorField({
         multiSelect
         options={comboboxOptions}
         multiSelectValues={multiValues}
-        onMultiSelectChange={(values) => onChange(values)}
+        onMultiSelectChange={onChange}
         searchable
+        onSearchChange={setSearchTerm}
         searchPlaceholder={`Search ${field.title.toLowerCase()}...`}
         placeholder={
           !credentialId
@@ -99,18 +161,18 @@ export function ConnectorSelectorField({
               : field.placeholder || `Select ${field.title.toLowerCase()}`
         }
         disabled={disabled || !credentialId || !depsResolved}
-        emptyMessage={`No ${field.title.toLowerCase()} found`}
+        emptyMessage={emptyMessage}
       />
     )
   }
 
-  const singleValue = Array.isArray(value) ? value[0] : value
   return (
     <ChipCombobox
       options={comboboxOptions}
       value={singleValue || undefined}
-      onChange={(next) => onChange(next)}
+      onChange={onChange}
       searchable
+      onSearchChange={setSearchTerm}
       searchPlaceholder={`Search ${field.title.toLowerCase()}...`}
       placeholder={
         !credentialId
@@ -120,11 +182,36 @@ export function ConnectorSelectorField({
             : field.placeholder || `Select ${field.title.toLowerCase()}`
       }
       disabled={disabled || !credentialId || !depsResolved}
-      emptyMessage={`No ${field.title.toLowerCase()} found`}
+      emptyMessage={emptyMessage}
     />
   )
 }
 
+/**
+ * Only visible once the first page has landed (`isLoading` renders a spinner
+ * before that), so "no match" here means no match among the options drained
+ * *so far* — a flat "none found" would wrongly read as "does not exist".
+ *
+ * `error` is checked before `hasMore`: a failed page halts the drain but leaves
+ * `hasMore` set, which would otherwise claim to be loading forever.
+ */
+function getEmptyMessage(
+  noun: string,
+  state: {
+    error: Error | null
+    hasMore: boolean
+    isFetchingMore: boolean
+    truncated: boolean
+  }
+): string {
+  if (state.error) return 'No match — the list failed to load. Try reopening'
+  if (state.hasMore || state.isFetchingMore) return 'No match yet — still loading…'
+  if (state.truncated) return 'No match — too many to list. Try a more exact term'
+  // `noun` is singular on some connectors ("Base") and plural on others ("Spaces"),
+  // so only this settled message puts it behind a quantifier.
+  return `No ${noun} found`
+}
+
 function resolveDepValue(
   depFieldId: string,
   configFields: ConnectorConfigField[],

apps/sim/hooks/selectors/providers/confluence/selectors.ts

@@ -49,11 +49,12 @@ export const confluenceSelectors = {
         nextCursor: data.nextCursor,
       }
     },
+    /** The server filters by key and returns nothing for a key that does not exist. */
+    resolvesUnknownIds: true,
     /**
-     * Resolves a single space label. Hits only the first page — the dropdown's
-     * `fetchPage` stream populates the options cache for spaces beyond page 1,
-     * and `useSelectorOptionMap` merges them in. Walking all pages here would
-     * double API load since the stream is already running in parallel.
+     * Resolves a single space by key via the server's exact-key lookup, independent
+     * of how far the page drain has run — a space sorting beyond page 1 would
+     * otherwise never resolve, which on a large site is most of them.
      */
     fetchById: async ({ context, detailId, signal }: SelectorQueryArgs) => {
       if (!detailId) return null
@@ -64,6 +65,7 @@ export const confluenceSelectors = {
           credential: credentialId,
           workflowId: context.workflowId,
           domain,
+          spaceKey: detailId,
         },
         signal,
       })
@@ -87,6 +89,16 @@ export const confluenceSelectors = {
       search ?? '',
     ],
     enabled: ({ context }) => Boolean(context.oauthCredential && context.domain),
+    /**
+     * Deliberately a single request, not a drain. `/pages` is cursor-paginated and
+     * this list is therefore capped at `limit`, which is a real gap — but draining it
+     * is worse: with no search term `title` is unset, so the drain would walk the
+     * entire site (up to `MAX_AUTO_DRAIN_PAGES` requests) every time the dropdown
+     * opens, and the route does not forward an abort signal upstream, so superseded
+     * drains still bill the tenant's rate limit. Fixing this properly needs
+     * server-side search whose `title` semantics have been confirmed against a live
+     * instance, not brute-force loading.
+     */
     fetchList: async ({ context, search, signal }: SelectorQueryArgs) => {
       const credentialId = ensureCredential(context, 'confluence.pages')
       const domain = ensureDomain(context, 'confluence.pages')

apps/sim/hooks/selectors/types.ts

@@ -136,6 +136,13 @@ export interface SelectorDefinition {
    */
   fetchPage?: (args: SelectorPageArgs) => Promise<SelectorPage>
   fetchById?: (args: SelectorQueryArgs) => Promise<SelectorOption | null>
+  /**
+   * Set when `fetchById` tolerates an id that may not exist, returning `null` rather
+   * than erroring. Only then is it safe to speculatively resolve whatever a user has
+   * typed — most implementations resolve a record by id and would turn every partial
+   * keystroke into a failed upstream request.
+   */
+  resolvesUnknownIds?: boolean
   enabled?: (args: SelectorQueryArgs) => boolean
   staleTime?: number
 }