6 Commits

Author	SHA1	Message	Date
emily	6b3724b765	edited the way api keys are handled. ... Since API keys are now loaded from the auth server, this means that there is a delay between starting the software, loading the keys, and loading all the module files. Due to nodejs running Async, the modules are being loaded BEFORE the api keys have been returned from the auth server. So now the api keys are being set inside the module every time the module is being called. This has absolutely no impact on performance, or security, plus, this was the easiest solution, especially as it required no big changes to the rest of the code	2026-01-14 03:01:30 +01:00
emily	562debd883	added test for qwen3 model and added a console log for debugging purposes to the gemini test because that shit model keeps being dogshit and throwing errors about being overloaded because the dogshit company called google cant fucking manage to set up a model that doesnt shit itself the moment more than 3 people send a query at the same time, god i fucking hate google and LLMs, it is truly an insult that we have to write this dogshit software	2025-12-16 18:27:43 +01:00
MikeHughes-BIN	04b2457ca3	Changes to the LLMs to return a Promise (outp path) and main now calls the export process	2025-12-15 17:58:03 +01:00
MikeHughes-BIN	ec57411992	Refactor document generation to output HTML format and update system instructions for clarity	2025-12-15 13:53:14 +01:00
MikeHughes-BIN	1e38cc79f4	Extended the Role description	2025-12-14 16:53:35 +01:00
MikeHughes-BIN	746fec05d4	Changed model from llama to quen3 because llama was timing out due to token limit	2025-12-14 16:28:48 +01:00