Add Start/End index inputs under Advanced in the dataset card,
allowing users to slice a dataset by row range before training.
Wired end-to-end: frontend store, API payload, backend Pydantic
model, and trainer dataset loading (inclusive on both ends).
Remove os.chdir(save_directory) from export.py which was causing all of
unsloth-zoo's relative-path internals (check_llama_cpp, use_local_gguf,
_download_convert_hf_to_gguf) to resolve against the export directory
instead of the repo root. This caused llama.cpp to be cloned inside each
export dir and destroyed the repo root's llama-server build on cleanup.
Now passes absolute paths to save_pretrained_gguf so unsloth resolves
llama.cpp from the repo root where setup.sh already built it.
Also builds llama-quantize in setup.sh (needed by unsloth-zoo's export
pipeline) and symlinks it to llama.cpp root for check_llama_cpp().
Fixes two bugs:
1. Chat template tags (<|im_start|>, <|im_end|>) leaking into output
because /v1/completions treated them as literal text
2. Image hallucination because image_b64 was never passed to llama-server
Now llama-server handles chat templates natively and receives images
as OpenAI-format multimodal content parts for vision models.
Replace Python-side GGUF download with llama-server's native -hf flag for
HuggingFace repos. Add frontend variant picker so users can choose
quantization (Q4_K_M, Q8_0, BF16, etc.) with file sizes. Fix vision
detection via mmproj files instead of hardcoding is_vision=False.
- Changed default eval_steps from 0.01 to 0.0 across backend and frontend
- Fixed UI to allow eval_steps=0 (removed min=0.001 constraint)
- Added conditional eval logic with helpful console messages
- Updated tooltip to explain how to disable evaluation
- Tested: confirmed eval disabled by default with eval_steps=0.0
- Added `log_lines` field to track and display runtime logs for executions.
- Enhanced progress tracking with terminal-like log outputs and live log scrolling.
- Introduced detailed "model usage" and "dropped columns" analysis in `ExecutionsView`.
- Optimized UI components for displaying dataset metrics, including input/output token averages.
- Added logic to calculate and manage column-level progress for job executions.
- Introduced `progress_columns_total` and `_column_done` fields for more granular progress updates.
- Improved overall progress computation by considering total columns and individual progress per column.
- Extracted shared execution utilities into `execution-helpers.ts` for reusability across features.
- Replaced deprecated `/preview` endpoint and its logic with unified job execution handling.
- Consolidated job execution flows ("Preview" and "Full Run") into shared `runJobExecution` logic.
- Enhanced execution progress tracking with support for column-level progress reporting.
- Added support for handling execution job events and improved error reporting from the backend.
- Updated backend to better manage dataset access errors and provide more informative error messages.
- Cleaned up redundant code in `use-recipe-studio-actions` and streamlined execution APIs.
- Introduced backend changes to handle dataset pagination with limit, offset, and total row support.
- Updated frontend execution view with dataset pagination controls, including "Next" and "Prev" buttons.
- Extended recipe execution logic to manage dataset pagination details like page number, page size, and total records.
- Introduced "Full Run" support in execution logic, including progress tracking, cancellation, and job status updates.
- Extended backend to manage full execution jobs, handle dataset previews, and return detailed analysis and artifacts.
- Updated frontend components to support full runs, with execution sorting, live updates, and detailed execution views.
- Enhanced `ExecutionsView` with progress indicators, status filtering, and dataset preview capabilities.
- Added IndexedDB schema migration to track additional execution metadata.
- Added `ExecutionsView` with execution history tracking, live updates, and detailed data analysis.
- Implemented IndexedDB support via Dexie to persist execution records locally.
- Enhanced backend preview logic to return execution analysis and artifacts.
- Updated studio header with view toggling between "Editor" and "Executions."
