Topaz Photo AI

Build me a focused AI photo enhancement workflow for the personal core of Topaz Photo AI. Requirements:

- Use exactly this stack: Tauri 2 + React + TypeScript + Canvas API. Model source assets, editable projects, operations, and exported versions; keep stable source IDs and timestamps.
- Paid product context: Desktop denoising, sharpening, recovery, and image upscaling. Build only this DIY scope: Build a focused local AI photo enhancement editor with import, a small set of transformations, undo, and standards-based export.
- For AI photo enhancement, import user-owned assets and save editable operations separately from originals.
- Apply the supported template or canvas transformation with undo and a versioned preview.
- Export a PNG, SVG, or PDF appropriate to the requested workflow.
- Use a desktop window with source import, a work list, and result export. Required input or access: sample user-owned assets.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: Undo must restore the previous visual state; export dimensions and asset hash must match the saved project.
- Out of scope: cloud collaboration and mobile apps; high-fidelity color, format, and export handling. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for Topaz Photo AI

## Project scope
Build a focused local AI photo enhancement editor with import, a small set of transformations, undo, and standards-based export.

Catalogue verdict: no. Do not mistake the interface for the product. Topaz Photo AI's durable value is editor polish, assets, algorithms, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- desktop development machine
- Node.js 22 and Rust toolchain
- sample user-owned assets
- Explicit README warning that this is a consolation build, not a production replacement

## Stack and architecture
- Use exactly this stack: Tauri 2 + React + TypeScript + Canvas API.
- Model source assets, editable projects, operations, and exported versions; keep stable source IDs and timestamps.
- Interface for this AI photo enhancement workflow: a desktop window with source import, a work list, and result export.

## Security and data integrity
- Undo must restore the previous visual state; export dimensions and asset hash must match the saved project.
- Validate imported records and file paths; keep user data within the storage location named in the prompt.
- State the practical limit: cloud collaboration and mobile apps.

## Agent implementation rules
- Project rule, data: Model source assets, editable projects, operations, and exported versions; keep stable source IDs and timestamps.
- Project rule, behavior: For AI photo enhancement, import user-owned assets and save editable operations separately from originals.
- Project rule, recovery: Undo must restore the previous visual state; export dimensions and asset hash must match the saved project.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this AI photo enhancement operation with sample or user-owned data: For AI photo enhancement, import user-owned assets and save editable operations separately from originals.
- Show a concrete result or export: Export a PNG, SVG, or PDF appropriate to the requested workflow.
- State the practical limit: cloud collaboration and mobile apps.

## Engineering roadmap
1. Phase 1, architecture and data: Use exactly this stack: Tauri 2 + React + TypeScript + Canvas API. Model source assets, editable projects, operations, and exported versions; keep stable source IDs and timestamps.
2. Phase 2, implement: For AI photo enhancement, import user-owned assets and save editable operations separately from originals.
3. Phase 3, implement: Apply the supported template or canvas transformation with undo and a versioned preview.
4. Phase 4, review and output: Export a PNG, SVG, or PDF appropriate to the requested workflow.
5. Phase 5, recovery and acceptance: Verify this invariant with a saved fixture: Undo must restore the previous visual state; export dimensions and asset hash must match the saved project. State the practical limit: cloud collaboration and mobile apps.

## Paid-product capabilities outside this build
- cloud collaboration and mobile apps
- high-fidelity color, format, and export handling
- pixel-perfect professional tooling
- large template and asset libraries
- color-management edge cases

## Implementation prompt
Build me a focused AI photo enhancement workflow for the personal core of Topaz Photo AI. Requirements:

- Use exactly this stack: Tauri 2 + React + TypeScript + Canvas API. Model source assets, editable projects, operations, and exported versions; keep stable source IDs and timestamps.
- Paid product context: Desktop denoising, sharpening, recovery, and image upscaling. Build only this DIY scope: Build a focused local AI photo enhancement editor with import, a small set of transformations, undo, and standards-based export.
- For AI photo enhancement, import user-owned assets and save editable operations separately from originals.
- Apply the supported template or canvas transformation with undo and a versioned preview.
- Export a PNG, SVG, or PDF appropriate to the requested workflow.
- Use a desktop window with source import, a work list, and result export. Required input or access: sample user-owned assets.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: Undo must restore the previous visual state; export dimensions and asset hash must match the saved project.
- Out of scope: cloud collaboration and mobile apps; high-fidelity color, format, and export handling. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.