🚀 refactor: Enhance Custom Endpoints, Message Logic, and Payload Handling (#2895)

* chore: use node-fetch for OpenAIClient fetch key for non-crashing usage of AbortController in Bun runtime

* chore: variable order

* fix(useSSE): prevent finalHandler call in abortConversation to update messages/conversation after user navigated away

* chore: params order

* refactor: organize intermediate message logic and ensure correct variables are passed

* fix: Add stt and tts routes before upload limiters, prevent bans

* fix(abortRun): temp fix to delete unfinished messages to avoid message thread parent relationship issues

* refactor: Update AnthropicClient to use node-fetch for fetch key and add proxy support

* fix(gptPlugins): ensure parentMessageId/messageId relationship is maintained

* feat(BaseClient): custom fetch function to analyze/edit payloads just before sending (also prevents abortController crash on Bun runtime)

* feat: `directEndpoint` and `titleMessageRole` custom endpoint options

* chore: Bump version to 0.6.6 in data-provider package.json

api/server/controllers/assistants/chatV2.js

@@ -496,7 +496,7 @@ const chatV2 = async (req, res) => {
         handlers,
         thread_id,
         attachedFileIds,
-        parentMessageId,
+        parentMessageId: userMessageId,
         responseMessage: openai.responseMessage,
         // streamOptions: {