NightCafe

Build me a focused AI art generation workflow for the personal core of NightCafe. Requirements:

- Use exactly this stack: Python 3.12 + FastAPI + ComfyUI API + React. Model prompts, model settings, generation jobs, source assets, and exported images; keep stable source IDs and timestamps.
- Paid product context: Community AI art generation using multiple models and credit plans. Build only this DIY scope: Build the closest honest personal AI art generation console around a locally available image model, with prompt history and file export.
- For AI art generation, accept a prompt, selected model, seed, and output dimensions; validate the model path or declared provider credential.
- Run one generation job and persist model parameters, status, and the produced file path.
- Preview the image, allow a prompt revision, and export the image with a JSON sidecar recording generation settings.
- Use a local web page with input, progress, review, and export views. Required input or access: GPU-capable machine or user-provided inference API; model weights obtained under their own licence.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A failed or cancelled model job retains its prompt and source assets; an exported image must reopen at the recorded dimensions.
- Out of scope: licensed training data and style tuning; fast elastic inference. 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 NightCafe

## Project scope
Build the closest honest personal AI art generation console around a locally available image model, with prompt history and file export.

Catalogue verdict: no. Do not mistake the interface for the product. NightCafe's durable value is proprietary model, inference, 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
- GPU-capable machine or user-provided inference API
- Python 3.12
- model weights obtained under their own licence
- Explicit README warning that this is a consolation build, not a production replacement

## Stack and architecture
- Use exactly this stack: Python 3.12 + FastAPI + ComfyUI API + React.
- Model prompts, model settings, generation jobs, source assets, and exported images; keep stable source IDs and timestamps.
- Interface for this AI art generation workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- A failed or cancelled model job retains its prompt and source assets; an exported image must reopen at the recorded dimensions.
- Validate imported records and file paths; keep user data within the storage location named in the prompt.
- State the practical limit: licensed training data and style tuning.

## Agent implementation rules
- Project rule, data: Model prompts, model settings, generation jobs, source assets, and exported images; keep stable source IDs and timestamps.
- Project rule, behavior: For AI art generation, accept a prompt, selected model, seed, and output dimensions; validate the model path or declared provider credential.
- Project rule, recovery: A failed or cancelled model job retains its prompt and source assets; an exported image must reopen at the recorded dimensions.

## 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 art generation operation with sample or user-owned data: For AI art generation, accept a prompt, selected model, seed, and output dimensions; validate the model path or declared provider credential.
- Show a concrete result or export: Preview the image, allow a prompt revision, and export the image with a JSON sidecar recording generation settings.
- State the practical limit: licensed training data and style tuning.

## Engineering roadmap
1. Phase 1, architecture and data: Use exactly this stack: Python 3.12 + FastAPI + ComfyUI API + React. Model prompts, model settings, generation jobs, source assets, and exported images; keep stable source IDs and timestamps.
2. Phase 2, implement: For AI art generation, accept a prompt, selected model, seed, and output dimensions; validate the model path or declared provider credential.
3. Phase 3, implement: Run one generation job and persist model parameters, status, and the produced file path.
4. Phase 4, review and output: Preview the image, allow a prompt revision, and export the image with a JSON sidecar recording generation settings.
5. Phase 5, recovery and acceptance: Verify this invariant with a saved fixture: A failed or cancelled model job retains its prompt and source assets; an exported image must reopen at the recorded dimensions. State the practical limit: licensed training data and style tuning.

## Paid-product capabilities outside this build
- licensed training data and style tuning
- fast elastic inference
- safety, moderation, and mobile distribution
- the vendor's proprietary model quality

## Implementation prompt
Build me a focused AI art generation workflow for the personal core of NightCafe. Requirements:

- Use exactly this stack: Python 3.12 + FastAPI + ComfyUI API + React. Model prompts, model settings, generation jobs, source assets, and exported images; keep stable source IDs and timestamps.
- Paid product context: Community AI art generation using multiple models and credit plans. Build only this DIY scope: Build the closest honest personal AI art generation console around a locally available image model, with prompt history and file export.
- For AI art generation, accept a prompt, selected model, seed, and output dimensions; validate the model path or declared provider credential.
- Run one generation job and persist model parameters, status, and the produced file path.
- Preview the image, allow a prompt revision, and export the image with a JSON sidecar recording generation settings.
- Use a local web page with input, progress, review, and export views. Required input or access: GPU-capable machine or user-provided inference API; model weights obtained under their own licence.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A failed or cancelled model job retains its prompt and source assets; an exported image must reopen at the recorded dimensions.
- Out of scope: licensed training data and style tuning; fast elastic inference. 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.