chore(search): remove legacy indexed enterprise search (#8528)

* chore(search): remove legacy indexed enterprise search

* fix(search): preserve live onboarding and Slack scope policies

* fix(search): close retired document writes and refresh Search consent

* fix(search): preserve ordinary knowledge base classification

Author: icecrasher321

.github/workflows/ci.yml

@@ -222,7 +222,6 @@ jobs:
           platforms: linux/amd64
           tags: ${{ steps.login-ecr.outputs.registry }}/${{ steps.ecr-repo.outputs.name }}:${{ github.sha }}-dev
           build-args: |
-            SIM_SEARCH_LIVE_DEFAULT=true
             MSHIP_PLAN_MODE_DEFAULT=true
           max-cache-size-mb: ${{ matrix.cache_mb }}
 

.github/workflows/desktop-e2e.yml

@@ -28,7 +28,6 @@ on:
       - 'apps/sim/hooks/queries/personal-search-integrations.ts'
       - 'apps/sim/hooks/use-search-integration-connection.ts'
       - 'apps/sim/hooks/use-github-installation-setup.ts'
-      - 'apps/sim/app/o/**/integrations/indexed/use-member-enrollment.ts'
       - 'apps/sim/lib/api/contracts/desktop-source-connect.ts'
       - 'apps/sim/scripts/fixtures/desktop-source-connect.tsx'
       - 'apps/sim/app/workspace/**/browser-session/**'

apps/docs/content/docs/platform/self-hosting/integrations-oauth.mdx

@@ -207,7 +207,7 @@ The private key must include its PEM header, footer, and contents. Sim accepts a
 
 Keep the private key and client secret in the deployment's server configuration; organization admins select installations in Sim without entering these secrets.
 
-The live Search application needs these five variables. If a worker also indexes ordinary GitHub knowledge bases, or Search has explicitly reverted to `SIM_SEARCH_LIVE=false`, configure the variables in that worker’s matching environment too. Updating the app’s secret store does not update a separately configured worker. Live Search does not schedule a GitHub indexing worker.
+The live Search application needs these five variables. If a worker also indexes ordinary GitHub knowledge bases, configure the variables in that worker’s matching environment too. Updating the app’s secret store does not update a separately configured worker. Live Search does not schedule a GitHub indexing worker.
 
 The **Client ID** is different from the numeric **App ID**. Use credentials from **Developer settings → GitHub Apps**. `GITHUB_CLIENT_ID` and `GITHUB_CLIENT_SECRET` belong to the separate GitHub sign-in integration and remain unchanged. Search does not read `GITHUB_REPO_CLIENT_ID` or `GITHUB_REPO_CLIENT_SECRET`.
 

apps/docs/content/docs/search/index.mdx

@@ -80,6 +80,6 @@ Conversations remain private to their author. Connecting an external account doe
 
 ## Legacy indexing and workspace knowledge bases
 
-Live Search is the default. An operator can explicitly set `SIM_SEARCH_LIVE=false` to restore the legacy indexed Search backend. Its content sync, document processing, and stored permission maintenance are specific to that mode. These guides describe live Search.
+Enterprise Search uses live provider queries. Search sources do not run content indexing or stored permission maintenance; ordinary knowledge-base connectors retain their indexing behavior.
 
 Ordinary workspace [knowledge bases](/knowledgebase) still ingest, chunk, and index documents for their own features. Their connector setup, processing status, and access settings remain separate.

apps/docs/content/docs/search/mcp.mdx

@@ -44,7 +44,7 @@ The connection applies to the organization whose URL you copied. Sim checks curr
 
 `chat` accepts questions up to 8,192 characters. Tool responses are limited to 1 MiB. API rate limits apply; follow any retry delay. Provider failures or incomplete retrieval are reported explicitly, and the tools do not fall back to an old index when a live provider is unavailable.
 
-These are the live-backend schemas. If an operator explicitly selects legacy Search with `SIM_SEARCH_LIVE=false`, the server advertises its indexed search/read schemas instead. Refresh your MCP client's tool discovery after changing backends.
+These are the Search MCP schemas. Refresh tool discovery in clients that previously connected to the retired indexed backend.
 
 ## Reconnect or revoke access
 

apps/sim/app/api/knowledge/connectors/directory-sync/route.test.ts

@@ -4,7 +4,6 @@ import {
   hasMockCondition,
   resetEnvFlagsMock,
   schemaMock,
-  setEnvFlags,
 } from '@sim/testing'
 import { authInternalMock, authInternalMockFns } from '@sim/testing/mocks/auth-internal.mock'
 import { dbChainMockFns } from '@sim/testing/mocks/database.mock'
@@ -108,24 +107,6 @@ describe('connector directory sync scheduler', () => {
     await expect(run()).resolves.toMatchObject({ dispatched: 1, failed: 1 })
   })
 
-  it.each([true, false])(
-    'excludes Search directories from scheduled pages only when live Search is %s',
-    async (liveSearch) => {
-      setEnvFlags({ isLiveEnterpriseSearchEnabled: liveSearch })
-      mockConnectorRows.mockResolvedValue([])
-      await run()
-      expect(
-        hasMockCondition(
-          mockWhere.mock.calls[0][0],
-          (node) =>
-            node.type === 'eq' &&
-            node.left === schemaMock.knowledgeBase.isSearchIndex &&
-            node.right === false
-        )
-      ).toBe(liveSearch)
-    }
-  )
-
   it('does not enqueue a connector another scheduler claimed or paused', async () => {
     mockConnectorRows.mockResolvedValue([connector()])
     mockClaim.mockResolvedValueOnce([])

apps/sim/app/api/knowledge/search/route.ts

@@ -6,68 +6,9 @@ import {
 } from '@/lib/api/server/routes'
 import { internalKnowledgeErrorPolicies } from '@/lib/knowledge/api/route-policies'
 import { knowledgeOperations } from '@/lib/knowledge/application/operations'
-import { DEFAULT_RERANKER_MODEL } from '@/lib/knowledge/reranker-models'
-import { sourceAuthor } from '@/lib/knowledge/search/author'
-import { searchScopedKnowledge } from '@/lib/sim-search/indexed'
-import { isIndexedOrgSearchEnabled } from '@/lib/sim-search/indexed/gate'
 import { searchLiveKnowledge } from '@/lib/sim-search/live/application'
 
-const DIRECT_SEARCH_VECTOR_BUDGET_MS = 3000
-
-const indexedSearchRoute = defineInternalJsonRoute({
-  contract: searchWorkspaceKnowledgeContract,
-  auth: internalSessionAuth,
-  operation: knowledgeOperations.search,
-  rateLimit: internalRateLimits.none({
-    reason:
-      'A person typing queries; the embedding call is metered against the canonical search owner',
-  }),
-  errorPolicy: internalKnowledgeErrorPolicies.search,
-  mapInput: ({ body }, { request }) => ({
-    workspaceId: body.workspaceId,
-    organizationId: body.organizationId,
-    filters: body.filters,
-    query: body.query,
-    topK: body.topK,
-    allowPartialResults: true,
-    vectorBudgetMs: DIRECT_SEARCH_VECTOR_BUDGET_MS,
-    /**
-     * A person's search is reranked by a cross-encoder whenever the workspace or the platform
-     * holds a key for one; the use case checks that before spending a call, and reranking stays
-     * best-effort, so a provider outage leaves the fused order in place.
-     */
-    rerankerEnabled: true,
-    rerankerModel: DEFAULT_RERANKER_MODEL,
-    surface: 'dashboard' as const,
-    signal: request.signal,
-  }),
-  useCase: searchScopedKnowledge,
-  present: ({ results, knowledgeBases, retrieval }, { input }) => {
-    const knowledgeBaseNames = new Map(knowledgeBases.map((kb) => [kb.id, kb.name]))
-    return {
-      success: true as const,
-      data: {
-        query: input.query ?? '',
-        retrieval,
-        results: results.map((result) => ({
-          documentId: result.documentId,
-          knowledgeBaseId: result.knowledgeBaseId,
-          knowledgeBaseName: knowledgeBaseNames.get(result.knowledgeBaseId) ?? '',
-          documentName: result.documentName,
-          sourceUrl: result.sourceUrl,
-          connectorType: result.connectorType,
-          sourceModifiedAt: result.sourceModifiedAt?.toISOString() ?? null,
-          author: sourceAuthor(result.metadata),
-          content: result.content,
-          chunkIndex: result.chunkIndex,
-          similarity: result.similarity,
-        })),
-      },
-    }
-  },
-})
-
-const liveSearchRoute = defineInternalJsonRoute({
+export const POST = defineInternalJsonRoute({
   contract: searchWorkspaceKnowledgeContract,
   auth: internalSessionAuth,
   operation: knowledgeOperations.search,
@@ -80,6 +21,3 @@ const liveSearchRoute = defineInternalJsonRoute({
   useCase: searchLiveKnowledge,
   present: (data) => ({ success: true as const, data }),
 })
-
-/** Indexed organization search is dormant unless its gate is on; Live Search serves otherwise. */
-export const POST = isIndexedOrgSearchEnabled() ? indexedSearchRoute : liveSearchRoute