Merge remote-tracking branch 'origin/staging' into wip/platform-org-wiring

Author: waleedlatif1

apps/sim/lib/compare/data/sim.ts

@@ -134,14 +134,19 @@ export const simProfile: CompetitorProfile = {
   facts: {
     platform: {
       builderType: {
-        value: 'Visual drag-and-drop canvas, natural-language (Chat), or code (API/SDK)',
+        value: 'Visual drag-and-drop canvas, natural-language (Chat), or code (REST API and CLI)',
         shortValue: 'Visual canvas, chat, or code',
         confidence: 'verified',
         sources: [
           {
             url: 'https://docs.sim.ai/introduction',
-            label: 'Sim Docs: Introduction (visual, natural-language, and API/SDK building)',
-            asOf: '2026-07-08',
+            label: 'Sim Docs: Introduction (visual, natural-language, and API building)',
+            asOf: '2026-11-10',
+          },
+          {
+            url: 'https://docs.sim.ai/cli',
+            label: 'Sim Docs: CLI',
+            asOf: '2026-11-10',
           },
         ],
       },
@@ -155,8 +160,8 @@ export const simProfile: CompetitorProfile = {
         sources: [
           {
             url: 'https://docs.sim.ai/introduction',
-            label: 'Sim Docs: Introduction (visual, natural-language, and API/SDK building)',
-            asOf: '2026-07-08',
+            label: 'Sim Docs: Introduction (visual, natural-language, and API building)',
+            asOf: '2026-11-10',
           },
         ],
       },

apps/sim/lib/credentials/databricks-service-account.server.test.ts

@@ -48,6 +48,20 @@ describe('saving a Databricks connection', () => {
     )
   })
 
+  it('refuses an identity reply over the size cap instead of saving the host as the identity', async () => {
+    fetch.mockResolvedValue(
+      jsonResponse({ userName: 'me@example.com', groups: 'g'.repeat(1024 * 1024) })
+    )
+
+    await expect(
+      verifyAndEncryptDatabricksCredential(
+        patConfig('dbc-1234abcd-5678.cloud.databricks.com'),
+        owner
+      )
+    ).rejects.toThrow(/Could not verify/)
+    expect(encryptionMockFns.mockEncryptSecret).not.toHaveBeenCalled()
+  })
+
   it.each([
     'attacker.example.com',
     'https://attacker.example.com',
@@ -175,6 +189,32 @@ describe('getting a Databricks token for a run', () => {
     })
   })
 
+  it('reports a token reply over the size cap as oversized, not as a refused request', async () => {
+    fetch.mockResolvedValue(jsonResponse({ access_token: 't'.repeat(1024 * 1024) }, 200))
+
+    await expect(resolveDatabricksCredentialToken('cred-1')).rejects.toMatchObject({
+      code: 'provider_unavailable',
+      logDetail: { reason: 'Databricks token response exceeded the size limit' },
+    })
+  })
+
+  it('reports a token reply cut off mid-body as the provider being unavailable, not a bad credential', async () => {
+    const body = new ReadableStream<Uint8Array>({
+      start(controller) {
+        controller.enqueue(new TextEncoder().encode('{"error":"invalid_cl'))
+        controller.error(new Error('socket hang up'))
+      },
+    })
+    fetch.mockResolvedValue(
+      new Response(body, { status: 401, headers: { 'Content-Type': 'application/json' } })
+    )
+
+    await expect(resolveDatabricksCredentialToken('cred-1')).rejects.toMatchObject({
+      code: 'provider_unavailable',
+      logDetail: { reason: 'Databricks token response could not be read' },
+    })
+  })
+
   it('reports a token reply without a token as the provider misbehaving, not a bad credential', async () => {
     fetch.mockResolvedValue(jsonResponse({}, 200))
 

apps/sim/lib/credentials/databricks-service-account.server.ts

@@ -5,6 +5,7 @@ import { eq } from 'drizzle-orm'
 import { z } from 'zod'
 import { decryptSecret, encryptSecret } from '@/lib/core/security/encryption'
 import { validateDatabricksWorkspaceHost } from '@/lib/core/security/input-validation'
+import { isPayloadSizeLimitError, readResponseJsonWithLimit } from '@/lib/core/utils/stream-limits'
 import { parseServiceAccountConfig } from '@/lib/credentials/service-account-config'
 import {
   providerFailureCode,
@@ -42,6 +43,8 @@ const DATABRICKS_CREDENTIAL_SECRET_TYPE = 'databricks_credential_v1' as const
 const DATABRICKS_WORKLOAD_IDENTITY_AUDIENCE = WORKLOAD_IDENTITY_AUDIENCES.databricks
 
 const REQUEST_TIMEOUT_MS = 15_000
+/** Token and identity responses are small; the cap keeps a misbehaving host from exhausting memory. */
+const MAX_RESPONSE_BYTES = 1024 * 1024
 const CLIENT_ID_PATTERN = /^[A-Za-z0-9-]{8,128}$/
 
 /** Workspace origin with Databricks' own host allowlist as the SSRF guard. */
@@ -143,7 +146,21 @@ async function requestWorkspaceToken(
     redirect: 'error',
     signal: signal ? AbortSignal.any([signal, timeout]) : timeout,
   })
-  const payload = (await response.json().catch(() => ({}))) as {
+  const payload = (await readResponseJsonWithLimit(response, {
+    maxBytes: MAX_RESPONSE_BYTES,
+    label: 'Databricks token response',
+  }).catch((error: unknown) => {
+    if (error instanceof SyntaxError) return {}
+    signal?.throwIfAborted()
+    if (isPayloadSizeLimitError(error)) {
+      throw new DatabricksCredentialError(
+        'Databricks token response exceeded the size limit',
+        response.status
+      )
+    }
+    // An interrupted body says nothing about the credential, whatever the status line was.
+    throw new DatabricksCredentialError('Databricks token response could not be read', 502)
+  })) as {
     access_token?: unknown
     error_description?: unknown
     error?: unknown
@@ -240,7 +257,15 @@ async function verifyWorkspaceIdentity(
       signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS),
     })
     if (!response.ok) throw new Error(`workspace returned HTTP ${response.status}`)
-    const me = (await response.json().catch(() => ({}))) as {
+    // A malformed body only loses the display name; an oversized one must fail
+    // verification rather than save the host as the identity.
+    const me = (await readResponseJsonWithLimit(response, {
+      maxBytes: MAX_RESPONSE_BYTES,
+      label: 'Databricks identity response',
+    }).catch((error: unknown) => {
+      if (error instanceof SyntaxError) return {}
+      throw error
+    })) as {
       userName?: unknown
       displayName?: unknown
     }

apps/sim/lib/credentials/service-account-secret.ts

@@ -393,7 +393,9 @@ async function buildTokenServiceAccountSecret(
     providerId,
     apiToken,
     ...(requiresDomain ? { domain: validation.normalizedDomain ?? domain } : {}),
-    ...(requiresWorkspace ? { providerWorkspaceId } : {}),
+    ...(requiresWorkspace
+      ? { providerWorkspaceId: validation.normalizedWorkspaceId ?? providerWorkspaceId }
+      : {}),
     metadata: { ...validation.storedMetadata, ...principalMetadata },
   }
   const { encrypted } = await encryptSecret(JSON.stringify(blob))

apps/sim/lib/credentials/token-service-accounts/server.ts

@@ -270,6 +270,8 @@ export interface TokenServiceAccountValidationResult {
   storedMetadata?: Record<string, string>
   /** Normalized domain to persist instead of the raw user input (when collected). */
   normalizedDomain?: string
+  /** Normalized account id to persist instead of the raw user input (when collected). */
+  normalizedWorkspaceId?: string
 }
 
 export type TokenServiceAccountValidator = (

apps/sim/lib/credentials/token-service-accounts/validators/gitlab.test.ts

@@ -15,10 +15,16 @@ import { validateGitLabServiceAccount } from '@/lib/credentials/token-service-ac
 const activeToken = { name: 'sim-workflows', active: true, revoked: false, scopes: ['api'] }
 
 describe('GitLab saved token verification', () => {
-  const fetch = inputValidationMockFns.mockSecureFetchWithValidation
+  const fetch = inputValidationMockFns.mockSecureFetchWithPinnedIP
+  const validateUrl = inputValidationMockFns.mockValidateUrlWithDNS
 
   beforeEach(() => {
     fetch.mockReset()
+    validateUrl.mockReset().mockResolvedValue({
+      isValid: true,
+      resolvedIP: '203.0.113.7',
+      originalHostname: 'gitlab.example.com',
+    })
   })
 
   it('verifies the token at the host it was typed with and stores that host', async () => {
@@ -33,6 +39,7 @@ describe('GitLab saved token verification', () => {
     })
     expect(fetch).toHaveBeenCalledWith(
       'https://gitlab.example.com/api/v4/personal_access_tokens/self',
+      '203.0.113.7',
       expect.objectContaining({ maxRedirects: 0, profile: 'configuredEndpoint' })
     )
   })
@@ -67,11 +74,11 @@ describe('GitLab saved token verification', () => {
   })
 
   it('reports a host that does not exist as not found, so the user fixes it instead of retrying', async () => {
-    fetch.mockRejectedValue(
-      new Error('url hostname could not be resolved', {
-        cause: Object.assign(new Error('getaddrinfo ENOTFOUND'), { code: 'ENOTFOUND' }),
-      })
-    )
+    validateUrl.mockResolvedValue({
+      isValid: false,
+      error: 'url hostname could not be resolved',
+      cause: Object.assign(new Error('getaddrinfo ENOTFOUND'), { code: 'ENOTFOUND' }),
+    })
 
     await expect(
       validateGitLabServiceAccount({ apiToken: 'glpat-x', domain: 'gitlab.exmaple.com' })

apps/sim/lib/credentials/token-service-accounts/validators/http.test.ts

@@ -129,7 +129,8 @@ describe('tokenCheckValidator', () => {
 })
 
 describe('tokenCheckValidator with a typed host', () => {
-  const secureFetch = inputValidationMockFns.mockSecureFetchWithValidation
+  const validateUrl = inputValidationMockFns.mockValidateUrlWithDNS
+  const pinnedFetch = inputValidationMockFns.mockSecureFetchWithPinnedIP
   const validateHost = tokenCheckValidator({
     serviceLabel: 'Example',
     domain: ({ domain }) => {
@@ -145,17 +146,30 @@ describe('tokenCheckValidator with a typed host', () => {
   })
 
   beforeEach(() => {
-    secureFetch.mockReset()
+    validateUrl.mockReset()
+    validateUrl.mockResolvedValue({
+      isValid: true,
+      resolvedIP: '203.0.113.7',
+      originalHostname: 'tools.example.com',
+    })
+    pinnedFetch.mockReset()
   })
 
   it('verifies at the normalized host through the guarded egress and stores that host', async () => {
-    secureFetch.mockResolvedValue(jsonResponse({ ok: true }))
+    pinnedFetch.mockResolvedValue(jsonResponse({ ok: true }))
 
     await expect(
       validateHost({ apiToken: 'good', domain: ' Tools.Example.com ' })
     ).resolves.toMatchObject({ normalizedDomain: 'tools.example.com' })
-    expect(secureFetch).toHaveBeenCalledWith(
+    expect(validateUrl).toHaveBeenCalledWith(
+      'https://tools.example.com/api/me',
+      'url',
+      'configuredEndpoint',
+      expect.anything()
+    )
+    expect(pinnedFetch).toHaveBeenCalledWith(
       'https://tools.example.com/api/me',
+      '203.0.113.7',
       expect.objectContaining({ profile: 'configuredEndpoint', maxRedirects: 0 })
     )
   })
@@ -174,22 +188,41 @@ describe('tokenCheckValidator with a typed host', () => {
     await expect(
       validateHost({ apiToken: 'good', domain: 'evil.example.com@tools.example.com' })
     ).rejects.toMatchObject({ code: 'invalid_credentials' })
-    expect(secureFetch).not.toHaveBeenCalled()
+    expect(validateUrl).not.toHaveBeenCalled()
+    expect(pinnedFetch).not.toHaveBeenCalled()
+  })
+
+  it('reports a host the egress policy refuses as the user input, not a retryable outage', async () => {
+    validateUrl.mockResolvedValue({ isValid: false, error: 'url resolves to a private address' })
+
+    await expect(
+      validateHost({ apiToken: 'good', domain: 'grafana.internal' })
+    ).rejects.toMatchObject({ code: 'invalid_credentials', status: 400 })
+    expect(pinnedFetch).not.toHaveBeenCalled()
+  })
+
+  it('reports a host that cannot be reached as the provider being unavailable', async () => {
+    pinnedFetch.mockRejectedValue(new Error('connect ECONNREFUSED'))
+
+    await expect(
+      validateHost({ apiToken: 'good', domain: 'tools.example.com' })
+    ).rejects.toMatchObject({ code: 'provider_unavailable', status: 502 })
   })
 
   it.each([
     [
       'Node (code on cause)',
-      new Error('fetch failed', {
+      new Error('lookup failed', {
         cause: Object.assign(new Error('getaddrinfo ENOTFOUND'), { code: 'ENOTFOUND' }),
       }),
     ],
-    [
-      'Bun (code on the error)',
-      Object.assign(new TypeError('fetch failed'), { code: 'ENOTFOUND' }),
-    ],
-  ])('reports a host that does not exist as not found under %s', async (_runtime, error) => {
-    secureFetch.mockRejectedValue(error)
+    ['Bun (code on the error)', Object.assign(new Error('lookup failed'), { code: 'ENOTFOUND' })],
+  ])('reports a host that does not exist as not found under %s', async (_runtime, cause) => {
+    validateUrl.mockResolvedValue({
+      isValid: false,
+      error: 'url hostname could not be resolved',
+      cause,
+    })
 
     await expect(
       validateHost({ apiToken: 'good', domain: 'tools.exmaple.com' })

apps/sim/lib/credentials/token-service-accounts/validators/http.ts

@@ -1,6 +1,9 @@
 import { truncate } from '@sim/utils/string'
 import type { EgressProfile } from '@/lib/core/security/egress/profiles'
-import { secureFetchWithValidation } from '@/lib/core/security/input-validation.server'
+import {
+  secureFetchWithPinnedIP,
+  validateUrlWithDNS,
+} from '@/lib/core/security/input-validation.server'
 import { readResponseJsonWithLimit } from '@/lib/core/utils/stream-limits'
 import {
   fetchProvider,
@@ -154,13 +157,34 @@ function normalizedField(
   }
 }
 
-/** Sends a check through the guarded egress profile, mapping a host that doesn't exist to `site_not_found`. */
+/**
+ * Sends a check through the guarded egress profile. A host the policy refuses
+ * (a private address, or plain http where https is required) is the user's
+ * input, so it fails as `invalid_credentials` rather than `provider_unavailable`,
+ * which renders as a retryable 503. A host that doesn't exist is `site_not_found`.
+ */
 async function sendThroughEgress(
   profile: NonNullable<TokenCheck['egress']>,
   { url, method = 'GET', headers, body }: TokenCheckRequest
 ): Promise<ProviderResponse> {
+  const validation = await validateUrlWithDNS(url, 'url', profile, { logDetails: false })
+  if (!validation.isValid) {
+    // Only a failed DNS lookup carries a cause; without one the policy refused the host.
+    if (validation.cause === undefined) {
+      throw new TokenServiceAccountValidationError('invalid_credentials', 400, {
+        step: 'verify',
+        reason: 'host not allowed',
+      })
+    }
+    const notFound = isHostNotFound(validation.cause)
+    throw new TokenServiceAccountValidationError(
+      notFound ? 'site_not_found' : 'provider_unavailable',
+      notFound ? 400 : 502,
+      { step: 'verify', reason: notFound ? 'host does not resolve' : 'host lookup failed' }
+    )
+  }
   try {
-    return await secureFetchWithValidation(url, {
+    return await secureFetchWithPinnedIP(url, validation.resolvedIP, {
       profile,
       method,
       headers,
@@ -170,13 +194,11 @@ async function sendThroughEgress(
       maxResponseBytes: MAX_EGRESS_RESPONSE_BYTES,
       logUrlValidationDetails: false,
     })
-  } catch (error) {
-    const notFound = isHostNotFound(error)
-    throw new TokenServiceAccountValidationError(
-      notFound ? 'site_not_found' : 'provider_unavailable',
-      notFound ? 400 : 502,
-      { step: 'verify', reason: notFound ? 'host does not resolve' : 'host unreachable' }
-    )
+  } catch {
+    throw new TokenServiceAccountValidationError('provider_unavailable', 502, {
+      step: 'verify',
+      reason: 'host unreachable',
+    })
   }
 }
 
@@ -204,6 +226,7 @@ export function tokenCheckValidator(check: TokenCheck): TokenServiceAccountValid
         ...(workspaceId === undefined ? {} : { accountId: workspaceId }),
       },
       ...(domain === undefined ? {} : { normalizedDomain: domain }),
+      ...(workspaceId === undefined ? {} : { normalizedWorkspaceId: workspaceId }),
     }
     const request = check.request(fields)
     const response: ProviderResponse = check.egress