perf(tests): trim sweep, copilot, and timer-bound suites; run three CI shards

.github/workflows/test-build.yml

@@ -182,17 +182,17 @@ jobs:
       # without `--coverage`. See the Codecov note below.
       #
       # apps/sim runs only its first shard here; `test-shard` below runs the
-      # other. That suite is bound by the single Vite server thread that feeds
+      # others. That suite is bound by the single Vite server thread that feeds
       # every worker — wall time is flat from 4 to 13 workers — so a bigger
-      # runner buys nothing and a second runner halves it.
+      # runner buys nothing and each extra runner takes a proportional slice.
       - name: Run tests
         env:
           NODE_OPTIONS: '--no-warnings --max-old-space-size=8192'
           NEXT_PUBLIC_APP_URL: 'https://www.sim.ai'
           DATABASE_URL: 'postgresql://postgres:postgres@localhost:5432/simstudio'
           ENCRYPTION_KEY: '0000000000000000000000000000000000000000000000000000000000000000' # dummy key for CI only
           TURBO_CACHE_DIR: .turbo
-          SIM_TEST_SHARD: 1/2
+          SIM_TEST_SHARD: 1/3
         run: bun run test
 
       - name: Check schema and migrations are in sync
@@ -208,15 +208,20 @@ jobs:
           fi
           echo "✅ Schema and migrations are in sync"
 
-  # The second half of apps/sim's Vitest suite. Everything else — lint, the
-  # audits, type-check, the other workspaces' suites — lives in `test-build`
-  # with shard 1; this job exists only because that suite cannot go faster on
-  # one machine (see the "Run tests" note there). The Turbo cache disk gets
-  # its own key so the two shards' entries do not evict each other.
+  # The remaining shards of apps/sim's Vitest suite. Everything else — lint,
+  # the audits, type-check, the other workspaces' suites — lives in
+  # `test-build` with shard 1; these jobs exist only because that suite cannot
+  # go faster on one machine (see the "Run tests" note there). Three shards
+  # put each runner at roughly the fixed cost of checkout + install. The Turbo
+  # cache disk gets its own key so the shards' entries do not evict each other.
   test-shard:
-    name: Test (shard 2)
+    name: Test (shard ${{ matrix.shard }})
     runs-on: ${{ (vars.CI_PROVIDER == '' || vars.CI_PROVIDER == 'blacksmith') && 'blacksmith-8vcpu-ubuntu-2404' || 'ubuntu-latest' }}
     timeout-minutes: 15
+    strategy:
+      fail-fast: false
+      matrix:
+        shard: [2, 3]
 
     steps:
       - name: Checkout code
@@ -250,7 +255,7 @@ jobs:
         uses: ./.github/actions/cache-mount
         with:
           provider: ${{ vars.CI_PROVIDER }}
-          key: ${{ github.repository }}-turbo-cache-shard-${{ github.event_name }}${{ github.event.pull_request.head.repo.fork && '-fork' || '' }}
+          key: ${{ github.repository }}-turbo-cache-shard-${{ matrix.shard }}-${{ github.event_name }}${{ github.event.pull_request.head.repo.fork && '-fork' || '' }}
           path: ./.turbo
 
       - name: Install dependencies
@@ -259,14 +264,14 @@ jobs:
       - name: Install ripgrep
         run: command -v rg || (sudo apt-get update && sudo apt-get install -y ripgrep)
 
-      - name: Run tests (apps/sim shard 2/2)
+      - name: Run tests (apps/sim shard ${{ matrix.shard }}/3)
         env:
           NODE_OPTIONS: '--no-warnings --max-old-space-size=8192'
           NEXT_PUBLIC_APP_URL: 'https://www.sim.ai'
           DATABASE_URL: 'postgresql://postgres:postgres@localhost:5432/simstudio'
           ENCRYPTION_KEY: '0000000000000000000000000000000000000000000000000000000000000000' # dummy key for CI only
           TURBO_CACHE_DIR: .turbo
-          SIM_TEST_SHARD: 2/2
+          SIM_TEST_SHARD: ${{ matrix.shard }}/3
         run: bunx turbo run test --filter=@sim/app
 
   # Next.js production build, in parallel with lint + tests. Sticky disks are

apps/docs/package.json

@@ -42,7 +42,6 @@
   "devDependencies": {
     "@sim/tsconfig": "workspace:*",
     "@tailwindcss/postcss": "^4.0.12",
-    "@types/mdx": "^2.0.13",
     "@types/node": "24.2.1",
     "@types/react": "^19.1.2",
     "@types/react-dom": "^19.0.4",

apps/sim/app/workspace/[workspaceId]/files/components/file-viewer/rich-markdown-editor/code-languages.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  *
  * Guards against drift between the code-block language picker and the Prism grammars actually
  * registered by CodeBlockHighlight: every selectable language must have a registered grammar, or it

apps/sim/app/workspace/[workspaceId]/files/components/file-viewer/rich-markdown-editor/collaboration/apply-streamed-markdown.test.ts

@@ -157,41 +157,6 @@ describe('agent-stream applier', () => {
     expect(freshText).toContain('Gamma paragraph')
   })
 
-  it('preserves a concurrent peer edit to a region the agent snapshot does not include', () => {
-    // This is the core "AI as a CRDT peer" guarantee: the agent relays only its OWN delta (computed
-    // against a private shadow), never a whole-document reconcile that would revert a peer's edit.
-    const { editor, doc } = track(makeCollabEditor())
-
-    const session = beginAgentStream(editor)!
-    applyAgentStreamFrame(editor, session, 'Alpha paragraph.\n\nBeta paragraph.')
-
-    // A peer edits the FIRST paragraph directly on the shared doc — the agent's later snapshot still
-    // carries the ORIGINAL first paragraph (it was built from the base, before this edit).
-    const peer = new Y.Doc()
-    Y.applyUpdate(peer, Y.encodeStateAsUpdate(doc))
-    const peerFrag = peer.getXmlFragment('default')
-    peer.transact(() => {
-      const firstPara = peerFrag.get(0) as Y.XmlElement
-      const textNode = firstPara.get(0) as Y.XmlText
-      textNode.insert(textNode.toString().length, ' EDITED')
-    })
-    Y.applyUpdate(doc, Y.encodeStateAsUpdate(peer, Y.encodeStateVector(doc)))
-    peer.destroy()
-
-    // The agent appends a third paragraph. Its snapshot's first paragraph is the stale original, but the
-    // shadow-relayed delta only inserts the new paragraph — so the peer's " EDITED" must survive.
-    applyAgentStreamFrame(
-      editor,
-      session,
-      'Alpha paragraph.\n\nBeta paragraph.\n\nGamma paragraph.'
-    )
-    endAgentStream(session)
-
-    const live = doc.getXmlFragment('default').toString()
-    expect(live).toContain('EDITED')
-    expect(live).toContain('Gamma paragraph')
-  })
-
   it('reuses cached binding metadata across frames, still emitting minimal per-frame deltas', () => {
     // The binding `meta` is built ONCE (first frame) and reused — `updateYFragment` maintains it in place,
     // so we skip an O(doc) `initProseMirrorDoc` rebuild per frame. This guards that caching preserves the

apps/sim/app/workspace/[workspaceId]/files/components/file-viewer/rich-markdown-editor/image-drag-move.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  *
  * Dragging an image to reposition it inside a document must MOVE it, not import it again.
  *

apps/sim/app/workspace/[workspaceId]/files/components/file-viewer/rich-markdown-editor/image.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  */
 import { describe, expect, it } from 'vitest'
 import {

apps/sim/app/workspace/[workspaceId]/files/components/file-viewer/rich-markdown-editor/markdown-parse.test.ts

@@ -2,7 +2,7 @@
  * @vitest-environment jsdom
  */
 import { Editor } from '@tiptap/core'
-import { afterEach, describe, expect, it } from 'vitest'
+import { afterAll, describe, expect, it } from 'vitest'
 import { createMarkdownContentExtensions } from './extensions'
 import { parseMarkdownToDoc, serializeMarkdownBody, splitMarkdownBlocks } from './markdown-parse'
 import { isRoundTripSafe } from './round-trip-safety'
@@ -12,19 +12,20 @@ const isEmptyPara = (n: { type?: string; content?: unknown[] }): boolean =>
   n.type === 'paragraph' && !n.content?.length
 
 let editor: Editor | null = null
-afterEach(() => {
+afterAll(() => {
   editor?.destroy()
   editor = null
 })
 
-/** The current whole-document path: parse markdown in one shot, serialize back. */
+/**
+ * The current whole-document path: parse markdown in one shot, serialize back. One editor serves
+ * every call — `setContent` replaces the document wholesale, so a fresh instance per call only adds
+ * the cost of building the view, which the property tests below paid hundreds of times over.
+ */
 function oneShot(body: string): string {
-  editor = new Editor({ extensions: createMarkdownContentExtensions() })
+  editor ??= new Editor({ extensions: createMarkdownContentExtensions() })
   editor.commands.setContent(body, { contentType: 'markdown' })
-  const out = editor.getMarkdown()
-  editor.destroy()
-  editor = null
-  return out
+  return editor.getMarkdown()
 }
 
 /**

apps/sim/app/workspace/[workspaceId]/home/components/mothership-view/components/resource-content/components/terminal-session/terminal-session.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  */
 
 import { resolveDesktopZoom } from '@sim/desktop-bridge'

apps/sim/app/workspace/[workspaceId]/logs/utils.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  */
 import { describe, expect, it } from 'vitest'
 import { resolveLogWorkflowId, workflowEditorPath } from './utils'

apps/sim/app/workspace/[workspaceId]/w/[workflowId]/utils/workflow-attachment-upload.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  */
 import { beforeEach, describe, expect, it, vi } from 'vitest'
 

apps/sim/blocks/blocks/mothership.ts

@@ -1,4 +1,4 @@
-import { Blimp } from '@sim/emcn'
+import { Blimp } from '@sim/emcn/icons'
 import type { BlockConfig } from '@/blocks/types'
 import type { ToolResponse } from '@/tools/types'
 

apps/sim/executor/utils/block-data.test.ts

@@ -8,9 +8,14 @@ import type { SerializedBlock } from '@/serializer/types'
 
 /**
  * These assertions are about what the real block registry publishes, so the global stub — which
- * returns one mock block with no outputs — would make every case here pass vacuously.
+ * returns one mock block with no outputs — would make every case here pass vacuously. Only the
+ * generic webhook block is read, so only it is registered.
  */
 vi.unmock('@/blocks/registry')
+vi.mock('@/blocks/registry-maps', async () => {
+  const { partialBlockRegistry } = await import('@sim/testing/mocks/block-registry.mock')
+  return partialBlockRegistry(await import('@/blocks/blocks/generic_webhook'))
+})
 
 function triggerBlock(type: string, params: Record<string, unknown> = {}): SerializedBlock {
   return {

apps/sim/hooks/queries/environment.ts

@@ -2,11 +2,11 @@ import { createLogger } from '@sim/logger'
 import { useMutation, useQuery, useQueryClient } from '@tanstack/react-query'
 import { requestJson } from '@/lib/api/client/request'
 import {
-  type ContractBodyInput,
   removeWorkspaceEnvironmentContract,
   savePersonalEnvironmentContract,
   upsertWorkspaceEnvironmentContract,
-} from '@/lib/api/contracts'
+} from '@/lib/api/contracts/environment'
+import type { ContractBodyInput } from '@/lib/api/contracts/types'
 import type { WorkspaceEnvironmentData } from '@/lib/environment/api'
 import { fetchPersonalEnvironment, fetchWorkspaceEnvironment } from '@/lib/environment/api'
 import { invalidateSelectorQueries } from '@/hooks/queries/utils/selector-keys'

apps/sim/lib/auth/sso-trust.test.ts

@@ -8,12 +8,7 @@
  * domain-verification proof entirely.
  */
 import { resetEnvFlagsMock, setEnvFlags } from '@sim/testing'
-import { afterAll, expect, it, vi } from 'vitest'
-
-// Structurally slow — it imports the entire Better Auth module graph — so under a fully-parallel local run this file
-// blows the default timeout while passing in isolation and on CI. Give it a
-// real budget instead of letting machine load decide the verdict.
-vi.setConfig({ testTimeout: 30_000 })
+import { afterAll, beforeAll, expect, it, vi } from 'vitest'
 
 const { ssoOptions } = vi.hoisted(() => ({
   ssoOptions: { current: undefined as Record<string, unknown> | undefined },
@@ -28,24 +23,30 @@ vi.mock('@better-auth/sso', () => ({
 
 setEnvFlags({ isSsoEnabled: true })
 
-afterAll(resetEnvFlagsMock)
-
-it('never trusts the IdP-supplied email_verified claim for SSO linking', async () => {
+/**
+ * Structurally slow — it imports the entire Better Auth module graph — so under
+ * a fully-parallel local run this import blows the default budget while passing
+ * in isolation and on CI. The plugin options are captured once at module
+ * evaluation, so every assertion reads the same object: import once, outside
+ * any per-test budget, with a real budget of its own instead of letting machine
+ * load decide the verdict.
+ */
+beforeAll(async () => {
   await import('@/lib/auth/auth')
+}, 30_000)
 
+afterAll(resetEnvFlagsMock)
+
+it('never trusts the IdP-supplied email_verified claim for SSO linking', () => {
   expect(ssoOptions.current).toBeDefined()
   expect(ssoOptions.current?.trustEmailVerified).toBe(false)
 })
 
-it('keeps domain verification as the sole SSO linking trust source', async () => {
-  await import('@/lib/auth/auth')
-
+it('keeps domain verification as the sole SSO linking trust source', () => {
   expect(ssoOptions.current?.domainVerification).toEqual({ enabled: true })
 })
 
-it('disables Better Auth membership writes so Sim owns JIT admission', async () => {
-  await import('@/lib/auth/auth')
-
+it('disables Better Auth membership writes so Sim owns JIT admission', () => {
   expect(ssoOptions.current?.organizationProvisioning).toEqual({
     disabled: true,
     defaultRole: 'member',

apps/sim/lib/collab-doc/merge.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  */
 import { FILE_DOC_SEED } from '@sim/realtime-protocol/file-doc'
 import { describe, expect, it } from 'vitest'

apps/sim/lib/collab-doc/persist.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  */
 import { beforeEach, describe, expect, it, vi } from 'vitest'
 import * as Y from 'yjs'

apps/sim/lib/collab-doc/seed.test.ts

@@ -1,5 +1,5 @@
 /**
- * @vitest-environment jsdom
+ * @vitest-environment node
  */
 import { FILE_DOC_SEED } from '@sim/realtime-protocol/file-doc'
 import { getSchema } from '@tiptap/core'

apps/sim/lib/copilot/chat/payload.test.ts

@@ -59,6 +59,9 @@ vi.mock('@/tools/registry', () => ({
   },
 }))
 
+/** Denied-operation projection walks the block map only for blocks the mocked tool list never names. */
+vi.mock('@/blocks/registry-maps', () => ({ BLOCK_REGISTRY: {}, BLOCK_META_REGISTRY: {} }))
+
 vi.mock('@/tools/utils', () => ({
   getLatestVersionTools: vi.fn((input) => input),
   stripVersionSuffix: vi.fn((toolId: string) => toolId),

apps/sim/lib/copilot/chat/process-contents-log-projection.test.ts

@@ -21,12 +21,16 @@ import {
   permissionGroupScopeMockFns,
   resetPermissionGroupScopeMock,
   workflowAuthzMockFns,
+  workflowsUtilsMock,
 } from '@sim/testing'
 import { beforeEach, describe, expect, it, vi } from 'vitest'
 import type { ChatContext } from '@/stores/panel'
 
 vi.mock('@/lib/permission-groups/config-scope.server', () => permissionGroupScopeMock)
 
+/** Folder listing is untouched by `@log` mentions; the real module drags in the block and trigger registries. */
+vi.mock('@/lib/workflows/utils', () => workflowsUtilsMock)
+
 import { processContextsServer } from '@/lib/copilot/chat/process-contents'
 import { DEFAULT_PERMISSION_GROUP_CONFIG } from '@/lib/permission-groups/fields'
 

apps/sim/lib/copilot/request/go/stream.test.ts

@@ -11,6 +11,12 @@ import {
   MothershipStreamV1ToolPhase,
 } from '@/lib/copilot/generated/mothership-stream-v1'
 
+/** Table side effects are not exercised here, and the real module loads the table application layer. */
+vi.mock('@/lib/copilot/request/tools/tables', () => ({
+  maybeWriteOutputToTable: vi.fn(async (_toolName, _params, result) => result),
+  maybeWriteReadCsvToTable: vi.fn(async (_toolName, _params, result) => result),
+}))
+
 vi.mock('@/lib/copilot/request/session', async () => {
   const actual = await vi.importActual<typeof import('@/lib/copilot/request/session')>(
     '@/lib/copilot/request/session'

apps/sim/lib/copilot/request/handlers/handlers.test.ts

@@ -65,6 +65,12 @@ vi.mock('@/lib/copilot/async-runs/repository', () => ({
   claimWorkflowToolExecution,
 }))
 
+/** Table side effects are not exercised here, and the real module loads the table application layer. */
+vi.mock('@/lib/copilot/request/tools/tables', () => ({
+  maybeWriteOutputToTable: vi.fn(async (_toolName, _params, result) => result),
+  maybeWriteReadCsvToTable: vi.fn(async (_toolName, _params, result) => result),
+}))
+
 vi.mock('@/lib/copilot/request/tools/client', () => ({
   waitForClientToolCompletion,
   waitForToolCompletion,

apps/sim/lib/copilot/request/lifecycle/resume-leg-context.test.ts

@@ -1,6 +1,13 @@
-import { describe, expect, it } from 'vitest'
+import { describe, expect, it, vi } from 'vitest'
 import { MothershipStreamV1CompletionStatus } from '@/lib/copilot/generated/mothership-stream-v1'
 import { createStreamingContext } from '@/lib/copilot/request/context/request-context'
+
+/** Table side effects are not exercised here, and the real module loads the table application layer. */
+vi.mock('@/lib/copilot/request/tools/tables', () => ({
+  maybeWriteOutputToTable: vi.fn(async (_toolName, _params, result) => result),
+  maybeWriteReadCsvToTable: vi.fn(async (_toolName, _params, result) => result),
+}))
+
 import { makeResumeLegContext, mergeResumeLegOutputs } from '@/lib/copilot/request/lifecycle/run'
 
 // Guards the makeResumeLegContext / mergeResumeLegOutputs contract: the two MUST

apps/sim/lib/copilot/server/agent-url.test.ts

@@ -16,7 +16,7 @@ const { envMock } = vi.hoisted(() => ({
   },
 }))
 
-vi.mock('@/lib/api/contracts', () => ({
+vi.mock('@/lib/api/contracts/user', () => ({
   mothershipEnvironmentSchema: {
     safeParse: (value: unknown) =>
       ['default', 'dev', 'staging', 'prod'].includes(String(value))

apps/sim/lib/copilot/server/agent-url.ts

@@ -1,7 +1,7 @@
 import { db } from '@sim/db'
 import { settings, user } from '@sim/db/schema'
 import { eq } from 'drizzle-orm'
-import { type MothershipEnvironment, mothershipEnvironmentSchema } from '@/lib/api/contracts'
+import { type MothershipEnvironment, mothershipEnvironmentSchema } from '@/lib/api/contracts/user'
 import { SIM_AGENT_API_URL, SIM_AGENT_API_URL_DEFAULT } from '@/lib/copilot/constants'
 import { env } from '@/lib/core/config/env'