🔥 feat: deepseek-reasoner Thought Streaming (#5379)

* 🔧 refactor: Remove unused penalties and enhance reasoning token handling in OpenAIClient

* 🔧 refactor: `addInstructions` default to adding instructions at index 0, flag for legacy behavior

* chore: remove long placeholder

* chore: update localization strings across multiple languages

* ci: adjust tests for new `addInstructions` behavior

api/app/clients/BaseClient.js

@@ -264,17 +264,24 @@ class BaseClient {
   /**
    * Adds instructions to the messages array. If the instructions object is empty or undefined,
    * the original messages array is returned. Otherwise, the instructions are added to the messages
-   * array, preserving the last message at the end.
+   * array either at the beginning (default) or preserving the last message at the end.
    *
    * @param {Array} messages - An array of messages.
    * @param {Object} instructions - An object containing instructions to be added to the messages.
+   * @param {boolean} [beforeLast=false] - If true, adds instructions before the last message; if false, adds at the beginning.
    * @returns {Array} An array containing messages and instructions, or the original messages if instructions are empty.
    */
-  addInstructions(messages, instructions) {
-    const payload = [];
+  addInstructions(messages, instructions, beforeLast = false) {
     if (!instructions || Object.keys(instructions).length === 0) {
       return messages;
     }
+
+    if (!beforeLast) {
+      return [instructions, ...messages];
+    }
+
+    // Legacy behavior: add instructions before the last message
+    const payload = [];
     if (messages.length > 1) {
       payload.push(...messages.slice(0, -1));
     }

api/app/clients/OpenAIClient.js

@@ -614,8 +614,6 @@ class OpenAIClient extends BaseClient {
     model = 'gpt-4o-mini',
     modelName,
     temperature = 0.2,
-    presence_penalty = 0,
-    frequency_penalty = 0,
     max_tokens,
     streaming,
     context,
@@ -626,8 +624,6 @@ class OpenAIClient extends BaseClient {
     const modelOptions = {
       modelName: modelName ?? model,
       temperature,
-      presence_penalty,
-      frequency_penalty,
       user: this.user,
     };
 
@@ -1065,6 +1061,7 @@ ${convo}
     let error = null;
     const errorCallback = (err) => (error = err);
     const intermediateReply = [];
+    const reasoningTokens = [];
     try {
       if (!abortController) {
         abortController = new AbortController();
@@ -1292,8 +1289,23 @@ ${convo}
             }
           });
 
+        let reasoningCompleted = false;
         for await (const chunk of stream) {
+          if (chunk?.choices?.[0]?.delta?.reasoning_content) {
+            const reasoning_content = chunk?.choices?.[0]?.delta?.reasoning_content || '';
+            intermediateReply.push(reasoning_content);
+            reasoningTokens.push(reasoning_content);
+            onProgress(reasoning_content);
+          }
+
           const token = chunk?.choices?.[0]?.delta?.content || '';
+          if (!reasoningCompleted && reasoningTokens.length > 0 && token) {
+            reasoningCompleted = true;
+            const separatorTokens = '\n\n---\n';
+            reasoningTokens.push(separatorTokens);
+            onProgress(separatorTokens);
+          }
+
           intermediateReply.push(token);
           onProgress(token);
           if (abortController.signal.aborted) {
@@ -1360,6 +1372,10 @@ ${convo}
         return reply;
       }
 
+      if (reasoningTokens.length > 0) {
+        return reasoningTokens.join('') + message.content;
+      }
+
       return message.content;
     } catch (err) {
       if (

api/app/clients/specs/BaseClient.test.js

@@ -88,6 +88,19 @@ describe('BaseClient', () => {
     const messages = [{ content: 'Hello' }, { content: 'How are you?' }, { content: 'Goodbye' }];
     const instructions = { content: 'Please respond to the question.' };
     const result = TestClient.addInstructions(messages, instructions);
+    const expected = [
+      { content: 'Please respond to the question.' },
+      { content: 'Hello' },
+      { content: 'How are you?' },
+      { content: 'Goodbye' },
+    ];
+    expect(result).toEqual(expected);
+  });
+
+  test('returns the input messages with instructions properly added when addInstructions() with legacy flag', () => {
+    const messages = [{ content: 'Hello' }, { content: 'How are you?' }, { content: 'Goodbye' }];
+    const instructions = { content: 'Please respond to the question.' };
+    const result = TestClient.addInstructions(messages, instructions, true);
     const expected = [
       { content: 'Hello' },
       { content: 'How are you?' },