OMate 1.9.2 B213: Bug Fixes

Too many changes, let’s just release a minor version

https://download.omate.net/omate-pro-1.9.2-b213.apk

  • Added a terminate request menu on the chat page, allowing manual termination after a request is sent
  • Fixed an issue on some devices where legacy data tables caused permanent memory failure when using fts5
  • Added batch delete and modify category functions to the notepad category management
  • Added quick input of existing categories to the category input box on the new and edit prompt pages
  • Added an option to use memory as a reference in the rewrite function
  • Removed the forced auto-scroll to the bottom feature during streaming output
  • Addressed an issue where the background_fetch module failed to load on some models, causing continuous errors
  • Error prompts now close upon clicking and a copy button has been added
  • Fixed a full-text search error caused by empty queries
  • Fixed lag issues with permanent memory during streaming output
  • Fixed a failure issue caused by incorrect data format in role extraction inference logs
  • Added an input box focus option, allowing users to choose whether to automatically return the cursor to the input box after sending a message
  • Added scroll controllers and auto-scroll features to the role, mask, and API selection areas

- I checked the new version log and found the correct format; it turns out it still needs to be written as a JSON array. The format is as follows: [{\n"name": “Conversion Project”,\n"upserted_info": “Test dialogue text 33121233”\n}]

- In the new version, is RoleNotebook now required to read characterDataJson and recent_chat_history mandatorily, without relying on variables?

The template for characterInfoExtractorPrompt customization - Character Information Extraction.

The default prompt for characterInfoExtractorPrompt has been customized by me, and the variables {{characterData}} and {{recent_chat_history}} have been completely removed. However, the inference log still fully reads all the contents of the character notebook and the recent chat history.

Can read, but will not enter the context.

Understood, it indeed won’t affect it.

I found that the reasoning log stores historical reasoning logs, and after multiple conversations, I have to scroll down for a long time. It seems like there’s no limit; I’ve already stored over two hundred entries :joy:

You can clear it in the upper right corner. Also, I remember that exiting the app or conversation and re-entering should make it disappear.

There is a copy log in the upper right corner. However, it disappears when the application is reopened.

Simply switching conversations does not open a new reasoning log; it still displays the log from the previous conversation. When a new message is sent in a new conversation, the reasoning log for the new conversation will appear at the bottom, while the historical log at the top remains the reasoning log from the previous conversation.

Teacher, could we add a “scroll to bottom” button in the chat interface? Sometimes I scroll up to check the conversation details and then have to scroll down for a long time~ Having this button would be a bit more convenient :sparkling_heart:

The new feature of long-term memory, “Save memory to knowledge base,” is very hands-free, but the maximum number of long-term memories is 100~5000. This means that if long-term memories are not manually deleted, there will be at least 100 overlaps between the knowledge base and long-term memories. Can the minimum value of the maximum number of long-term memories be set to 1?

No, when you enable [Save Memory to Knowledge Base], it shouldn’t store content in long-term memory.

I’ll add it in the next version. The main issue is the positioning.

Ah, it really is… I remembered it wrong :joy:

Teacher Fangtang, version 213 will force the addition of a chat rewrite prompt when re-rolling.

In the PC version 209, leaving it blank will not send the rewrite prompt:

QQ图片20251211191119

After updating the mobile version to 213, even if left blank, this prompt will be output:

QQ图片20251211191131

Can it be changed back so that leaving it blank does not send the prompt? T T

Hmm, I’ll fix this in the next version.

Is it possible to make the selection area box smaller? It’s hard to scroll down with such a large area.

I’m not quite sure what you’re talking about.

The “Notepad Auto Load Prompt” in prompt customization does not support the {{char}} variable.

Let me add it, I originally thought it wasn’t needed here. Not all prompt templates support {{char}}, they only support variables present in the original prompt.

Occasionally, an error occurs: Application error: Null check operator used on a null value

I don’t know the reason, maybe it’s because I directly deleted the applied knowledge base txt? Directly deleting the applied knowledge base txt in the role settings will leave an error in the inference log, just like before, it does not affect normal use.