Improved and fixed template for GPT-OSS (again). Includes preserve_thinking and fix for Unsloth-induced bug

Excerpt

I posted an updated GPT-OSS template a couple of months ago , which was based on Unsloth's version . It turns out that both Unsloth's version (and, thus, mine) contain a very serious bug that can degrade the model when chat history is replayed and contains previous reasoning (aka the analysis channel) turns. As far as I can tell, retaining this history is pretty much the default for a lot of tools now and definitely can happen at the API level - tools can consolidate reasoning and answer. Can yo