fixing some issues including browse section disappear and whenever the image is replaced or cleared the vlm_usage_state because that usage belongs to the previous image and VLM caption. When the replacement image gets its new caption, vlm_usage_state will be populated with the new API call’s usage.

Require VLM feedback before submission, localize feedback validation, and track OpenAI token usage in dataset JSON

Merge branch 'main' of hf.co:spaces/team-wonders/ema-dev

Fix VLM caption generation variable, remove high-quality wording from examples, and enforce instant scroll-to-top on step transitions

Fix VLM caption generation variable, remove high-quality wording from examples, and enforce instant scroll-to-top on step transitions

Ensure step navigation smoothly scrolls up to the top of the page

Fix VLM prompt version and model assignment recording & clean up word cap post-processing

Fix duplicate box borders by resetting nested step-description-box styles

Wrap step descriptions in styled box containers

Support versioned overrides (v0, v1, v2) for localized prompts

Support random selection of active prompt versions and save chosen version

Rename default, default_step3, and default_step3_detailed to v0, v1, and v2

Increase word count limits for step 3 prompts to 80-100 words

Add default_step3 and default_step3_detailed templates to vlm_prompts.yaml

Update instructions.

Add is_positive field to USA and Spain examples JSON files

Fallback to default VLM model if loaded model is obsolete or empty

Remove Image and Description tip cards from examples modal

Move locale selection to first page and position dropdowns next to each other

Replacing the image in a loaded sample now triggers a fresh VLM caption without clearing the existing annotation fields.

several fixes - see slack

fixing categorical value choices

solving merging conflicts

scroll to top after next

Fix examples image load

Fix load image

Upload example1.png

Add files for per country examples, update Spanish example and fix vlm voting language

Add draft of negative example

add black forest cake example

Multilingual table headers

Multilingual stats tables on user page

Add multilingual step instructions

Multilingual user page and other language fixes

Spanish translations

Enhance input validations, add step 3 image preview, and style user back button

Update AI Description layout, instructions, and translation values

Configure back buttons layout, colors and update metadata tab translations

Update guidelines layout, metadata translation structure, and USA English guidelines

More minor formatting

Minor formatting

Soften wording for steps 1&3

metadata fix

More instruction changes

Updated instructions

fix: replace component instantiation with gr.update() in all event handlers

generate captions automatically and country/language selection skip

Update data/guidelines/USA/English/intro.md

Update data/guidelines/USA/English/intro.md

Update with new intructions