Conversational fallback with memory; reject zero-amount expenses

Dashboard chat routes through the feature registry - log expenses from the web too

Document why ssr_mode=False is required

Disable Gradio SSR on Spaces - the SSR frontend 404s under a custom launch

Let Gradio own its port on Spaces so frontend assets load

Add torchvision (Qwen2.5-VL needs it); stop leaking internals to users

Warn loudly when a dataset repo is set without a token

v0.1.1 - rebuild to pick up Space secrets

Stop logging the bot token; redact Telegram errors

Extract dashboard auth boundary; docs

Username access, web dashboard and coach chat

Document the ZeroGPU/local-model architecture

Let Gradio own the server so ZeroGPU can instrument it

Run a local model on ZeroGPU instead of paid inference

Declare a @spaces.GPU probe for ZeroGPU

Declare a @spaces.GPU probe for ZeroGPU

Bind 7860; 7861 is held by the platform

Bind GRADIO_SERVER_PORT, not the proxy PORT

Switch to Gradio SDK for free ZeroGPU tier

Deploy coco-finbot

initial commit