Backport tag-leak fix to codette_orchestrator.py

Backport tag-leak fix to codette_tools.py

Trim persona tail welded onto finished answers

Fix runaway generation + rewrite front door (hf_orchestrator.py)

Fix runaway generation + rewrite front door (app.py)

Fix ZeroGPU illegal duration: 150 -> 60 (reserved 225s > 120s cap)

Upload 7 files

wire Codette's cocoon memory from CodetteBrain bucket (read-only /data)

wire Codette's cocoon memory from CodetteBrain bucket (read-only /data)

fix rambling: stop at <|eot_id|> (Llama-3.1 turn end) + cap tokens + anti-loop

swap to BEHAVIORAL adapters (locks-trained, production's preferred set)

Upgrade to REAL orchestrated Codette on ZeroGPU (transformers backend for the llama.cpp pipeline)

fix generate(): apply_chat_template return_dict=True + **inputs (transformers 5 BatchEncoding)

gradio 6: drop removed ChatInterface(type=) arg

fix ZeroGPU: load adapters on CPU (peft infer_device saw hijacked cuda) before intercepted .to(cuda)

vendor 8 perspective adapters into the Space + load from local paths (token-free, no gated fetch)

fix deps: transformers>=5.3 to match hub 1.x on the Space image

Codette multi-perspective demo: 8 perspective LoRAs on Llama-3.1-8B (ZeroGPU)

initial commit