feat(background): subfolder support, per-file context selection, and multimodal image improvements #20

Closed

casper-stevens wants to merge 0 commits from development_bg_panel_improvements into development

pull from: development_bg_panel_improvements

merge into: lhumina_code:development

lhumina_code:development

lhumina_code:development_casper

lhumina_code:development_default_scan_directory

lhumina_code:main

Conversation 0 Commits - Files changed - +1132 -229

casper-stevens commented 2026-04-15 07:32:08 +00:00

Member

Copy link

Summary

• Recursive subfolder support in the background panel (create nested folders, drag files between any depth)
• Top upload button always targets root
• Drag files back to root by dropping on the root section
• Per-file context selection in the create-slide modal and instruct panel (expand any folder to pick individual files)
• Select-all / deselect-all checkbox in both context sections
• Background context section now appears when only root files exist (no folders needed)
• Multimodal image generation: smarter directive tells the model to reproduce images verbatim when the slide calls for it, extract data when asked, or use as style reference otherwise
• All images normalised to PNG before sending to AI (fixes JPEG handling)

Related Issue

Closes #7

Changes

• discovery.rs: recursive find_background_folders, per-folder file filtering in collect_selected_background_images and read_background_content
• generator.rs: three-rule image directive replacing the blanket style-reference framing
• deck_module.rs: slide_create_content and slide_instruct_content accept bg_root_files_csv, bg_folder_files_json
• generate_job.rs / rpc.rs: new params wired through both create and instruct pipelines
• dashboard.js: nested tree rendering, subfolder creation, drag-to-root, per-folder file checkboxes in modal and instruct panel, select-all checkbox
• index.html: select-all checkbox added to both context sections

## Summary - Recursive subfolder support in the background panel (create nested folders, drag files between any depth) - Top upload button always targets root - Drag files back to root by dropping on the root section - Per-file context selection in the create-slide modal and instruct panel (expand any folder to pick individual files) - Select-all / deselect-all checkbox in both context sections - Background context section now appears when only root files exist (no folders needed) - Multimodal image generation: smarter directive tells the model to reproduce images verbatim when the slide calls for it, extract data when asked, or use as style reference otherwise - All images normalised to PNG before sending to AI (fixes JPEG handling) ## Related Issue Closes https://forge.ourworld.tf/lhumina_code/hero_slides/issues/7 ## Changes - `discovery.rs`: recursive `find_background_folders`, per-folder file filtering in `collect_selected_background_images` and `read_background_content` - `generator.rs`: three-rule image directive replacing the blanket style-reference framing - `deck_module.rs`: `slide_create_content` and `slide_instruct_content` accept `bg_root_files_csv`, `bg_folder_files_json` - `generate_job.rs` / `rpc.rs`: new params wired through both create and instruct pipelines - `dashboard.js`: nested tree rendering, subfolder creation, drag-to-root, per-folder file checkboxes in modal and instruct panel, select-all checkbox - `index.html`: select-all checkbox added to both context sections

casper-stevens added 1 commit 2026-04-15 07:32:08 +00:00

feat(background): improve panel UX, image upload, root file support, and multimodal AI ... 121e9120bf

- Allow PNG/JPG/JPEG/WEBP/GIF uploads to background panel (was text-only)
- Collapse background panel by default; auto-open when content exists
- Support files directly at content/background/ root (no subfolder needed)
- Include root text files and images in AI generation context
- Pass background images as multimodal input to AI content and image generation
- Add framing prompt so background images inform style/mood, not literal output
- Normalize all images to PNG before passing to AI (fixes JPEG handling)
- Add per-root-file selection checkboxes in create-slide modal
- Fix root file selection key bug in background tree UI

#7

casper-stevens referenced this pull request 2026-04-15 07:32:13 +00:00

Improve background panel: collapse behavior, image upload, and single-file support #7

casper-stevens added 1 commit 2026-04-15 08:27:01 +00:00

fix(generator): remove framing note that blocked literal image reproduction ... b64a60677f

The framing prompt told the model never to reproduce background images
literally. This broke the core use case of getting an exact image on a
slide. Per-file selection checkboxes already let users exclude unwanted
images, so the restriction is no longer needed.

#7

casper-stevens added 1 commit 2026-04-15 08:56:32 +00:00

feat(background): subfolder support, per-file selection, and instruct context control ... bcf0bba61c

Background panel:
- Recursive folder discovery — subfolders like "company/team" now visible
- Nested tree rendering with indentation and per-folder expand/collapse
- "Add subfolder" button on every folder node
- Top upload button always targets root (was incorrectly targeting first folder)
- Drag files to root by dropping on the root files section
- Drag files between any folder depth (fixed lastIndexOf parsing for nested paths)
- Context menu "Move to Root" option added

Create-slide modal:
- Per-folder file checkboxes — expand any folder to pick individual files
- Root files still selectable individually as before
- Only selected files passed to AI generation

Instruct panel (slide editor):
- Background context section now shows root files + folders + per-file selection
- Root files individually selectable with checkboxes
- Each folder expandable to pick specific files
- Selected background_root_files and background_folder_files passed through
  the full job pipeline (RPC → generate_job → rhai → deck_module)
- JPEG/WebP images normalized to PNG before passing to AI (consistent with create flow)

#7

casper-stevens added 1 commit 2026-04-15 09:03:36 +00:00

fix(background): show context selection when only root files exist ... ef02d5ca6e

handle_deck_get was only checking find_background_folders (directories)
to set has_background. If a deck had files directly at content/background/
but no subfolders, has_background was false and the context section never
appeared in the create-slide modal or instruct panel.

casper-stevens added 1 commit 2026-04-15 09:06:36 +00:00

feat(background): add select all / deselect all toggle to context sections ... 8c068d7443

Adds an 'All'/'None' toggle button to both the create-slide modal and the
instruct panel background context sections. Button label reflects current
state: shows 'None' when everything is selected, 'All' when deselected.

casper-stevens added 1 commit 2026-04-15 09:09:04 +00:00

feat(background): add checkmark icon to select-all toggle button 8cf5b3cbaf

casper-stevens added 1 commit 2026-04-15 09:31:21 +00:00

fix(background): replace toggle button with actual checkbox for select-all c4b7439262

casper-stevens added 1 commit 2026-04-15 09:56:00 +00:00

fix(generator): smarter image directive for multimodal slide generation ... 6a40512172

Replaces the blanket "style-reference only" framing with a three-rule
directive that tells the model to read the slide content first and decide:
1. reproduce the image verbatim if the slide calls for it
2. extract information from it if the slide asks for data/text
3. use it as style reference only if the slide doesn't reference it

Also includes discovery and CSS tweaks from the parallel work session.

#7

casper-stevens changed title from feat(background): improve panel UX, image upload, root file support, and multimodal AI to feat(background): subfolder support, per-file context selection, and multimodal image improvements 2026-04-15 09:56:23 +00:00

casper-stevens closed this pull request 2026-04-16 08:52:21 +00:00

casper-stevens referenced this pull request 2026-04-16 08:53:06 +00:00

feat(background+pdf): subfolder context, per-file selection, PDF extraction, and multimodal improvements #21

Some checks failed

Hide all checks

Test / test (pull_request) Failing after 1m6s

Details

Test / test (push) Failing after 1m6s

Details

Pull request closed

This pull request cannot be reopened because the branch was deleted.

Sign in to join this conversation.

Reviewers

No reviewers

Labels

Clear labels

No items

No labels

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

1 participant

Notifications

Subscribe

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

lhumina_code/hero_slides!20

No description provided.