Jinja templates that fix issues with some models

For llama.cpp

• full context reprocess when thinking is toggled on/off mid-conversation

• might potentially change outputs when reasoning is disabled (I haven't noticed so it's rather theoretical)

• Qwen 3.6 35B A3B
• Qwen 3.6 27B
• Bonsai 27B (binary/ternary)
• possibly other Qwen 3.6 variants or finetunes

• full response reprocess in case the model emitted a non-standard new line at the end of the thinking block

• extra white spaces are no longer trimmed; if the model goes crazy and starts multiplying them, there's no stopping it
• if you don't use preserve-thinking, you've not encountered the issue so you don't need this
• can be used with KAT-Coder-V2.5-Dev too, but this model seems to be more disciplined with new lines, so it doesn't need it

• thinking block correctly rendered/parsed in llama.cpp

• thinking toggle doesn't work (never did); use the instruct variant if you don't want it to think, I suppose

• not a fix, but disables thinking completely
• model doesn't respect thinking toggle, and its reasoning is garbage anyway, so no big loss

• reasoning now works

• just an unchanged template from Ling Mini 2.0 - seems to work fine