Install Steam
login
|
language
简体中文 (Simplified Chinese)
繁體中文 (Traditional Chinese)
日本語 (Japanese)
한국어 (Korean)
ไทย (Thai)
Български (Bulgarian)
Čeština (Czech)
Dansk (Danish)
Deutsch (German)
Español - España (Spanish - Spain)
Español - Latinoamérica (Spanish - Latin America)
Ελληνικά (Greek)
Français (French)
Italiano (Italian)
Bahasa Indonesia (Indonesian)
Magyar (Hungarian)
Nederlands (Dutch)
Norsk (Norwegian)
Polski (Polish)
Português (Portuguese - Portugal)
Português - Brasil (Portuguese - Brazil)
Română (Romanian)
Русский (Russian)
Suomi (Finnish)
Svenska (Swedish)
Türkçe (Turkish)
Tiếng Việt (Vietnamese)
Українська (Ukrainian)
Report a translation problem
something like this should have a "downside". What if you keep some of the errors (basically, fix any that cause issues such as lag, incompatibility, ect), but leave some errors (or, even add your own, such as some incorrectly made XMLs. Or code that mimics an error, like if you can output an "error" to the log that is red...(
If you use code to make fake errors in the log, maybe some of the reports from this mod will be put in the log along with actual errors... (wether or not it gets saved in the file and/ or uploaded by HugsLib is up to you)
However, when I check my OpenRouter API KEY activity monitoring, it shows no API usage
CopyOpenRimWorldAI (AI Chat request failed: )
UnityEngine.StackTraceUtility:ExtractStackTrace ()
Verse.Log:Message (string)
OpenRimWorldAI.Log:Message (string)
OpenRimWorldAI.AI/<>c__DisplayClass14_1:<AIChatAsync>b__0 (UnityEngine.AsyncOperation)
UnityEngine.AsyncOperation:InvokeCompletionEvent ()
OpenRimWorldAI (Response Code: 200)
UnityEngine.StackTraceUtility:ExtractStackTrace ()
Verse.Log:Message (string)
OpenRimWorldAI.Log:Message (string)
OpenRimWorldAI.AI/<>c__DisplayClass14_1:<AIChatAsync>b__0 (UnityEngine.AsyncOperation)
UnityEngine.AsyncOperation:InvokeCompletionEvent ()
Does this error indicate that the mod is not working properly?
Large improvements compared to the prior version with some additional feature being added (See AI Settings to enable them)
You can use flash thinking, however it'll be contained within the response and currently it's not being filtered out. I can experiment with this, but I want to get the basic functionality working (e,g: The room perimeters need to be correctly defined by the AI)
Wouldnt 2.0 flash thinking be the best? It can 'think' about what its doing
Do you use the tools function built into the gemini api (if you can)
Are you uploading all the data need to a file then sending that file or putting it all in text?
I added new settings, "Create New Buildings" will be off by default until I can debug it further, but you should be able to turn it on and see some better results.