📑 feat: Anthropic Direct Provider Upload (#9072)

* feat: implement Anthropic native PDF support with document preservation

- Add comprehensive debug logging throughout PDF processing pipeline
- Refactor attachment processing to separate image and document handling
- Create distinct addImageURLs(), addDocuments(), and processAttachments() methods
- Fix critical bugs in stream handling and parameter passing
- Add streamToBuffer utility for proper stream-to-buffer conversion
- Remove api/agents submodule from repository

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* chore: remove out of scope formatting changes

* fix: stop duplication of file in chat on end of response stream

* chore: bring back file search and ocr options

* chore: localize upload to provider string in file menu

* refactor: change createMenuItems args to fit new pattern introduced by anthropic-native-pdf-support

* feat: add cache point for pdfs processed by anthropic endpoint since they are unlikely to change and should benefit from caching

* feat: combine Upload Image into Upload to Provider since they both perform direct upload and change provider upload icon to reflect multimodal upload

* feat: add citations support according to docs

* refactor: remove redundant 'document' check since documents are handled properly by formatMessage in the agents repo now

* refactor: change upload logic so anthropic endpoint isn't exempted from normal upload path using Agents for consistency with the rest of the upload logic

* fix: include width and height in return from uploadLocalFile so images are correctly identified when going through an AgentUpload in addImageURLs

* chore: remove client specific handling since the direct provider stuff is handled by the agent client

* feat: handle documents in AgentClient so no need for change to agents repo

* chore: removed unused changes

* chore: remove auto generated comments from OG commit

* feat: add logic for agents to use direct to provider uploads if supported (currently just anthropic)

* fix: reintroduce role check to fix render error because of undefined value for Content Part

* fix: actually fix render bug by using proper isCreatedByUser check and making sure our mutation of formattedMessage.content is consistent

---------

Co-authored-by: Andres Restrepo <andres@thelinuxkid.com>
Co-authored-by: Claude <noreply@anthropic.com>

api/server/controllers/agents/client.js

@@ -222,6 +222,42 @@ class AgentClient extends BaseClient {
     return files;
   }
 
+  async addDocuments(message, attachments) {
+    const documentResult =
+      await require('~/server/services/Files/documents').encodeAndFormatDocuments(
+        this.options.req,
+        attachments,
+        this.options.agent.provider,
+      );
+    message.documents =
+      documentResult.documents && documentResult.documents.length
+        ? documentResult.documents
+        : undefined;
+    return documentResult.files;
+  }
+
+  async processAttachments(message, attachments) {
+    const [imageFiles, documentFiles] = await Promise.all([
+      this.addImageURLs(message, attachments),
+      this.addDocuments(message, attachments),
+    ]);
+
+    const allFiles = [...imageFiles, ...documentFiles];
+    const seenFileIds = new Set();
+    const uniqueFiles = [];
+
+    for (const file of allFiles) {
+      if (file.file_id && !seenFileIds.has(file.file_id)) {
+        seenFileIds.add(file.file_id);
+        uniqueFiles.push(file);
+      } else if (!file.file_id) {
+        uniqueFiles.push(file);
+      }
+    }
+
+    return uniqueFiles;
+  }
+
   async buildMessages(
     messages,
     parentMessageId,
@@ -255,7 +291,7 @@ class AgentClient extends BaseClient {
         };
       }
 
-      const files = await this.addImageURLs(
+      const files = await this.processAttachments(
         orderedMessages[orderedMessages.length - 1],
         attachments,
       );
@@ -278,6 +314,27 @@ class AgentClient extends BaseClient {
         assistantName: this.options?.modelLabel,
       });
 
+      if (
+        message.documents &&
+        message.documents.length > 0 &&
+        message.isCreatedByUser &&
+        this.options.agent.provider === EModelEndpoint.anthropic
+      ) {
+        const contentParts = [];
+        contentParts.push(...message.documents);
+        if (message.image_urls && message.image_urls.length > 0) {
+          contentParts.push(...message.image_urls);
+        }
+
+        if (typeof formattedMessage.content === 'string') {
+          contentParts.push({ type: 'text', text: formattedMessage.content });
+        } else {
+          const textPart = formattedMessage.content.find((part) => part.type === 'text');
+          contentParts.push(textPart);
+        }
+        formattedMessage.content = contentParts;
+      }
+
       if (message.ocr && i !== orderedMessages.length - 1) {
         if (typeof formattedMessage.content === 'string') {
           formattedMessage.content = message.ocr + '\n' + formattedMessage.content;
@@ -793,6 +850,7 @@ class AgentClient extends BaseClient {
       };
 
       const toolSet = new Set((this.options.agent.tools ?? []).map((tool) => tool && tool.name));
+
       let { messages: initialMessages, indexTokenCountMap } = formatAgentMessages(
         payload,
         this.indexTokenCountMap,