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

# Conflicts:
#	.agents/skills/add-integration/SKILL.md

Author: waleedlatif1

.agents/skills/add-integration/SKILL.md

@@ -80,7 +80,7 @@ service id:
    `server.ts`). Make one cheap, documented read on the tools' own host with the tools' own auth,
    reusing their header and URL builders. `domain` and `workspaceId` normalize to exactly the form
    the tools build URLs from and throw for anything that could steer the host or path
-   (`normalizeHttpBaseUrl`, `allowedDomain`, and a refusal of credentials in the URL); the normalized domain is what
+   (`normalizeHttpBaseUrl`, `allowedDomain`, `refuseUnsafeTypedUrl`); the normalized domain is what
    the credential stores. Set `egress` when the user chooses the host. Add `forbiddenMeansScoped`,
    `rejectsKey`, or `provesKey` only for documented replies (probe a fake key to see how a bad one
    answers), and `errorBodyEchoesToken` when an error body echoes the token.
@@ -359,7 +359,7 @@ export const BLOCK_META_REGISTRY: Record<string, BlockMeta> = {
 
 ### Trigger Registry (`apps/sim/triggers/registry.ts`) - If triggers exist
 
-```typescript illustrative
+```typescript
 // Add import (alphabetically)
 import {
   {service}EventATrigger,
@@ -423,9 +423,7 @@ a resolvable capability must fail validation; an independent service account use
 ## Step 8: Generate and Validate the Catalog
 
 Run `bun run generate:tool-metadata`, `bun run scripts/generate-docs.ts`,
-`bun run generate:deployment-config`, `bun scripts/sync-platform-integration-metadata.ts` (the
-Platform integration catalog; `check:platform-integration-metadata` is in `check:audits`), then
-`bun run check:audits` (see the `validate-integration`
+`bun run generate:deployment-config`, then `bun run check:audits` (see the `validate-integration`
 skill → Regenerate Derived Artifacts for the full list and what each check verifies).
 
 The docs generator creates `apps/docs/content/docs/integrations/{service}.mdx` — one page per service carrying the block's Actions and, if it has one, its Triggers section. Never hand-edit generated pages; the only editable region is the `{/* MANUAL-CONTENT */}` block (see `scripts/README.md`).
@@ -654,7 +652,7 @@ tools: {
 
 #### 3. Define and register the in-process operation
 
-```typescript illustrative
+```typescript
 export const {service}UploadTool: InternalToolConfig<Params, Response> = {
   id: '{service}_upload',
   // ...

apps/docs/content/docs/integrations/mistral_parse.mdx

@@ -10,12 +10,12 @@ import { ReferenceDetails } from "@sim/emcn-docs/reference-details"
 
 
 {/* MANUAL-CONTENT-START:intro */}
-Use [Mistral's OCR API](https://mistral.ai/) to extract text and page structure from a PDF uploaded to Sim or supplied by URL. The current parser returns page Markdown, image metadata, the model, and usage information. **Specific Pages** accepts zero-based indices such as `0,1,2`; leave it empty to process all pages. The block offers Markdown, plain-text, and JSON format values, but its current result uses the structured page output documented below. Turn on **Extract Images** to get the images Mistral finds in the document (figures, logos, photos) as files on the `images` output, up to 100 per parse; each page's image entry carries a `file_name` matching its file. **Max Images** and **Min Image Size** (advanced) narrow what is extracted. **Tables** keeps tables inline in the page Markdown by default, or returns them separately as Markdown or HTML in each page's `tables` list.
+Use [Mistral's OCR API](https://mistral.ai/) to extract text and page structure from a PDF uploaded to Sim or passed in as a file from a previous block. The current parser returns page Markdown, image metadata, the model, and usage information. **Specific Pages** accepts zero-based indices such as `0,1,2`; leave it empty to process all pages. The block offers Markdown, plain-text, and JSON format values, but its current result uses the structured page output documented below. Turn on **Extract Images** to get the images Mistral finds in the document (figures, logos, photos) as files on the `images` output, up to 100 per parse; each page's image entry carries a `file_name` matching its file. **Max Images** and **Min Image Size** (advanced) narrow what is extracted. **Tables** keeps tables inline in the page Markdown by default, or returns them separately as Markdown or HTML in each page's `tables` list.
 {/* MANUAL-CONTENT-END */}
 
 ## Use the block [#usage-instructions]
 
-Extract text, tables, and images from uploaded PDF documents, or from a URL. Images come back as files an agent can pass on.
+Extract text, tables, and images from an uploaded PDF or a file from a previous block. Images come back as files an agent can pass on.
 
 ## Actions
 

apps/sim/blocks/blocks/mistral_parse.ts

@@ -12,6 +12,7 @@ import {
   normalizeFileInput,
   parseOptionalNumberInput,
 } from '@/blocks/utils'
+import { MAX_OCR_EXTRACTED_IMAGES } from '@/tools/mistral/types'
 
 export const MistralParseBlock: BlockConfig = {
   type: 'mistral_parse',
@@ -310,7 +311,7 @@ export const MistralParseV3Block: BlockConfig = {
   name: 'Mistral Parser',
   description: 'Extract text, tables, and images from PDF documents',
   longDescription:
-    'Extract text, tables, and images from uploaded PDF documents, or from a URL. Images come back as files an agent can pass on.',
+    'Extract text, tables, and images from an uploaded PDF or a file from a previous block. Images come back as files an agent can pass on.',
   hideFromToolbar: false,
   /* v3 renamed the canonical pair's advanced member `filePath` -> `fileReference`,
      so the inherited sentence would reference a subblock this block lacks. */
@@ -464,6 +465,7 @@ export const MistralParseV3Block: BlockConfig = {
           parameters.imageLimit = parseOptionalNumberInput(params.imageLimit, 'Max Images', {
             integer: true,
             min: 0,
+            max: MAX_OCR_EXTRACTED_IMAGES,
           })
           parameters.imageMinSize = parseOptionalNumberInput(
             params.imageMinSize,

apps/sim/lib/internal/mistral/images.test.ts

@@ -1,5 +1,6 @@
 import { describe, expect, it } from 'vitest'
-import { extractOcrImageFiles, MAX_OCR_EXTRACTED_IMAGES } from '@/lib/internal/mistral/images'
+import { extractOcrImageFiles } from '@/lib/internal/mistral/images'
+import { MAX_OCR_EXTRACTED_IMAGES } from '@/tools/mistral/types'
 
 const JPEG = Buffer.concat([Buffer.from([0xff, 0xd8, 0xff]), Buffer.from('synthetic jpeg body')])
 const dataUri = (bytes: Buffer) => `data:image/jpeg;base64,${bytes.toString('base64')}`

apps/sim/lib/internal/mistral/images.ts

@@ -5,9 +5,7 @@ import type { InternalToolFile } from '@/lib/internal/tool-operations/file-resul
 import { MAX_BUFFERED_TRANSFER_BYTES } from '@/lib/uploads/shared/types'
 import { resolveEffectiveMimeType } from '@/lib/uploads/utils/file'
 import { resolveStoredFileMetadata } from '@/lib/uploads/utils/stored-file-metadata'
-
-/** Most images one parse stores; Mistral's `image_limit` is clamped to it. */
-export const MAX_OCR_EXTRACTED_IMAGES = 100
+import { MAX_OCR_EXTRACTED_IMAGES } from '@/tools/mistral/types'
 
 /** Largest single image kept; a bigger one is a page scan, not a figure. */
 const MAX_OCR_IMAGE_BYTES = 20 * 1024 * 1024

apps/sim/lib/internal/mistral/operations.ts

@@ -7,7 +7,7 @@ import { decodeDataUriWithinLimit } from '@/lib/file-parsers/data-uri'
 import { isFileParserError } from '@/lib/file-parsers/errors'
 import { submitMistralOcr } from '@/lib/internal/mistral/client'
 import { MistralOperationError } from '@/lib/internal/mistral/errors'
-import { extractOcrImageFiles, MAX_OCR_EXTRACTED_IMAGES } from '@/lib/internal/mistral/images'
+import { extractOcrImageFiles } from '@/lib/internal/mistral/images'
 import type { MistralParseInput } from '@/lib/internal/mistral/input'
 import { countMistralPdfPages } from '@/lib/internal/mistral/page-count'
 import {
@@ -31,6 +31,7 @@ import {
   type ServableFile,
 } from '@/lib/uploads/utils/file.server'
 import { assertToolFileAccess } from '@/app/api/files/authorization'
+import { MAX_OCR_EXTRACTED_IMAGES } from '@/tools/mistral/types'
 
 const logger = createLogger('MistralOperations')
 const IMAGE_EXTENSIONS = ['.png', '.jpg', '.jpeg', '.gif', '.webp', '.avif'] as const

apps/sim/tools/mistral/types.ts

@@ -2,6 +2,12 @@ import type { RawFileInput } from '@/lib/uploads/utils/file'
 import type { UserFile } from '@/executor/types'
 import type { OutputProperty, ToolResponse } from '@/tools/types'
 
+/**
+ * Most images one Mistral Parser run extracts. Bounds the block's Max Images field, the
+ * server's `image_limit` clamp, and the extraction loop.
+ */
+export const MAX_OCR_EXTRACTED_IMAGES = 100
+
 /**
  * Shared output property definitions for Mistral OCR API responses.
  * Based on Mistral API documentation: https://docs.mistral.ai/api/endpoint/ocr

packages/deployment-config/src/integrations.json

@@ -1,5 +1,5 @@
 {
-  "updatedAt": "2026-11-10",
+  "updatedAt": "2026-11-11",
   "integrations": [
     {
       "type": "onepassword",
@@ -18362,7 +18362,7 @@
       "slug": "mistral-parser",
       "name": "Mistral Parser",
       "description": "Extract text, tables, and images from PDF documents",
-      "longDescription": "Extract text, tables, and images from uploaded PDF documents, or from a URL. Images come back as files an agent can pass on.",
+      "longDescription": "Extract text, tables, and images from an uploaded PDF or a file from a previous block. Images come back as files an agent can pass on.",
       "bgColor": "#000000",
       "iconName": "MistralIcon",
       "docsUrl": "https://docs.sim.ai/integrations/mistral_parse",
@@ -18379,7 +18379,7 @@
       "category": "tools",
       "integrationType": "ai",
       "tags": ["document-processing", "ocr"],
-      "updatedAt": "2026-11-10"
+      "updatedAt": "2026-11-11"
     },
     {
       "type": "modal",