Select llama.cpp GGUF on CPU Basic Spaces

Improve lab knowledge graph from common labs PDF

Expand lab knowledge graph markers and videos

Add field guide and few-shot examples to extraction prompt.

Default extraction to the fine-tuned MiniCPM-V Hub checkpoint.

Remove dead chat code and obsolete planning docs.

Expand lab knowledge graph to 107 markers with curated YouTube videos.

Lock trace steps until extraction completes and simplify step headers.

Polish trace steps and add marker video embeds to reports.

Make agent pipeline steps easier to understand in plain language.

Polish section 3 trace panel and Space startup reliability.

Add agent trace panel, vision extraction, and local Transformers backend.

Route ZeroGPU auto backend to Transformers

Fall back from Transformers to llama.cpp

Select extraction backend by CUDA availability

Switch extraction to PDF text only

Stabilize llama.cpp multimodal decoding

Increase llama.cpp ZeroGPU duration

Drop unsupported llama.cpp reasoning flag

Expose llama.cpp worker errors

feat: surface cross-marker patterns in the report UI

feat: interpretation render layer (markdown + HTML cards) for the UI

Fix llama.cpp JSON extraction path

Make llama.cpp ZeroGPU backend default

Wire llama.cpp ZeroGPU badge path

feat: robust marker-name matching + cleaned real training labels

feat: gentler fine-tune + diversified synth data + interpretation engine + before/after eval

feat: working Modal LoRA fine-tune + llama.cpp-on-ZeroGPU backend

Switch Space deployment to ZeroGPU

Add knowledge graph health report pipeline

Add local model bundle and report UI refinements

feat(extraction): offline llama-server backend + tolerant JSON parsing

feat(markers): resolve verbose real-report marker names

Merge remote-tracking branch 'origin/main' into feat/offline-minicpmv-extraction-finetune

feat(eval): field-level extraction eval harness + tests

feat(markers): canonical 31-marker reference

feat(extraction): GBNF grammar + local MiniCPM-V (llama.cpp) backend + factory

Restore automatic PDF page extraction

Add OpenBMB lab extraction app