ai_sealed keeps a private task's prompt text and picture file names behind tokens ([P1], [img1], task["sealed"]): mcp_server puts the texts back into a call's arguments for the tool only, and ai_privacy.guard has every result masked on its way out (a node's STRING inputs by ComfyUI's node list, prompt fields, picture names, any sealed text, also in the text content). The user's own canvas changes are told sealed. A "prompts" panel block is the user's prompt box (ui_ai_prompt_box.js): prompts, a negative one and reference pictures from the gallery or dropped in, answered only from Anomalous, the AI getting tokens; above it the prompt_pose skill's words for the canvas's model. A new private-only skill, privacy, tells the AI how to work, and begin_task points a private task at it. Tests plant canary prompts and picture names in every tool's result and check none gets out. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Architecture Topic Guide
Start with the repository-root ARCHITECTURE.md, then
open only the topic needed for the current task.
ui-flows.md: the UI map's hand-written part, in Chinese: what each part of a page is for, what a click does and why, and one name per thing (a glossary the structure check enforces). Where a word on screen is drawn and what it calls comes from the code:node tools/ui_map.mjs find <words>(tools/ui_map.mjs, its indextools/ui_map_scan.mjs;buildwrites the whole map to the untrackeddocs/ui-map.md).backend.md: Python routes, filesystem safety, persistence, scan state, model sidecars, and backend performance.frontend.md: extension bootstrap, UI ownership, localization, media lifecycle, panel state, and graph mutations.recipes.md: Workflow Recipes, packages, galleries, Parameter Notebooks, prompt roles, and recipe-to-model transitions.material-library.md: saved prompts and node values (material files), keeping an output image, and dragging prompts onto the canvas.recipe-model-lifecycle.md: authoritative model fields, Hash synchronization, local matching, partial append, and note privacy.model-resolution.md: model provenance, Model Check, hash injection, model scanning, and recovery policy.../decisions/README.md: concise records of product and architectural decisions that still explain current behavior.
These documents describe current contracts rather than implementation history.
For exact changes, use Git history. For user-visible releases, use
CHANGELOG.md. For recurring implementation traps, use
lessons.md.