fix(zerogpu): normalize tiny-model script speakers

fix(zerogpu): keep fallback rank items above threshold

feat: ZeroGPU backend for Hugging Face Spaces deployment (#4)

fix: persist stage diagnostics and accurate run status

fix: pass Jina API key to reader requests

fix: use Hugging Face inference on Space

feat: add scheduled job backend and resumable pipeline sync

feat: implement background task worker queue and pollable history view to run pipeline asynchronously

feat: implement automatic CPU fallback for ZeroGPU queue lease execution failures

feat: implement frontend pipeline stage chaining to prevent ZeroGPU request lease timeouts

Implement robust Hugging Face repository bootstrapper in Gradio and update DB schema to support saving repository paths in user preferences. Remove static startup repo warnings.

feat: expose Hugging Face repository configuration fields in Gradio Preferences UI

feat: implement budget-aware resilient queue for ZeroGPU backend

feat: integrate storage backend into app, pipeline, and publish

feat: add auth, schema, and DuckDB storage backend

Apply user's zerogpu.patch

Fix ZeroGPU: Use snapshot_download and lazy loading pattern

Fix ZeroGPU: module-level model loading with bfloat16, drop bitsandbytes

Fix: prevent low-level CUDA init outside of spaces.GPU decorator on ZeroGPU

fix: resolve NVML assertion failure in ZeroGPU backend by loading globally

chore: update tests for app refactor and config changes

Restrict model loading to CUDA-enabled environments on ZeroGPUBackend

Refactor ZeroGPUBackend to use BAML's native render and parse API

Implement switchable LLM backends (BAML & ZeroGPU) for HF Spaces deployment

Refactor stage 4 script generation: implement story deduplication, guide segues with transition instructions, and configure NotebookLM-style long-form prompts with strict turn constraints (#2)

feat: Integrate fresh gr.Workflow feature into UI

feat: Deploy on HF Spaces with Gradio Walkthrough interface

chore: full project audit — delete dead code, fix bugs, add 32 tests

feat: production-ready DenseFeed pipeline with jj workflow docs