Build your own Stardew Valley.

# Build an original game inspired by Stardew Valley

You are an experienced game designer and gameplay engineer. Build a working, polished MVP from the brief below. Implement the core journeys end to end; a static mockup is not sufficient. Inspect the current environment, make sensible implementation decisions, and get started. Ask a question only if a missing answer genuinely blocks implementation.

Starting platform: Desktop. Explicit customized Product & audience and Tech stack requirements take precedence over this starting target.

## Product & audience
Build an original desktop farming game called Sproutstead, inspired by the farming loop of Stardew Valley. Scope the MVP to one small original farm, three crop types, a seed shop, a shipping box, and a short repeating day cycle. Players buy seeds, prepare soil, plant, water, sleep, harvest, and sell. Create an original world, art, writing, and sound; do not recreate its town, characters, maps, crops, or stories.

## Design
Use an original top-down 2D farm with clear tile interaction, a visible selected tool, inventory hotbar, stamina, day/time, and money. Highlight the target tile and state why an action fails. Use keyboard/controller-friendly navigation and clickable menus; keep shop and sleep confirmation readable without tiny pixel text.

## Features
1. Farm actions: implement till, plant, water, and harvest on a bounded grid. Validate tool, range, crop state, inventory, and stamina before applying an action atomically; repeated clicks cannot spend or harvest twice.

2. Crop simulation: define three original crops with seed cost, growth days, and sell value. Advance growth once per completed day only when the prior day was watered; reset watered flags after advancing.

3. Inventory and shop: manage stack limits and selected tools; buy seeds, store crops, and place crops in a shipping box. Calculate money and item changes together, reject invalid quantities, and expose full-inventory cases.

4. Day loop: run a documented short day timer and stamina budget, allow sleep with confirmation, and process shipping revenue once during the day transition. Pause/resume freezes time; a simple rescue/reset location prevents getting stuck.

5. Persistence: save the farm, inventory, money, day, and transition revision atomically at sleep and on manual save. Retain a backup, load paused, and validate crops/items so a corrupted save does not destroy the previous one.

## Tech stack
Use Godot with GDScript for a small native desktop 2D game. Isolate farm actions, economy, and day progression in a deterministic simulation model separate from scenes, animation, and input. Use original tile art or permitted placeholders and plain versioned save data. Day transitions should be idempotent and atomic, with a temporary-save/replace strategy and explicit failure messages.

## Data & behavior
Farm {width, height, tiles}; Tile {tilled, cropId, plantedDay, growthStage, watered}; CropDefinition; Player {position, stamina, inventory, selectedTool}; Economy {money, shippingItems}; Calendar {day, timeTick, processedTransitionId}; SaveVersion; Settings. Bound the farm and inventory size.

Acceptance checks and scope:
Test watering twice, an unwatered day, harvesting with full inventory, buying exact remaining stock/funds, selling once across reload, sleep/save failure, and pause during the day. Complete a seed-to-sale loop for each crop and reopen the save. Exclude copied town/story content, seasons, NPC relationships, fishing, combat, multiplayer, and a full life-simulation promise.

## Originality and assets
The named product is a reference for general workflows only. Use an original product name, visual identity, wording, layout, and assets. Do not copy proprietary code, branded logos, distinctive screens, private APIs, paid templates, or protected media. Use original or appropriately licensed sample data and assets. Build from this brief rather than scraping the reference service. Do not imply affiliation with the referenced company.

## Implementation quality
- Make every visible control work, with clear loading, success, empty, validation, and failure states. Remove controls for unimplemented features.
- Support the target platform and responsive or resizable layouts where appropriate. Use platform-appropriate accessibility semantics, labels, keyboard operation, visible focus, sufficient contrast, and reduced-motion preferences. Provide alternatives for drag-only interactions.
- Validate inputs at the relevant boundary. Treat imported or user-generated content as untrusted; render it safely. Confirm destructive actions or offer undo.
- Keep state changes reliable across navigation and reloads. Never silently lose edits. Handle persistence and network errors with an actionable message.
- Keep the scope realistic. Prioritize the complete primary journey. If a custom Features section differs from the baseline, update the data model, design, and acceptance checks to match it; explicit custom requirements take precedence over baseline assumptions.
- Provide realistic original sample content and a useful empty state. Keep sample data clearly separate from user-created data.

## Delivery and verification
1. Inspect the repository and outline the implementation in a few sentences.
2. Implement the app and connect its actual data flow. Continue until the primary journey works.
3. Run appropriate checks and test the acceptance cases above on the target platform. Verify responsive layouts and keyboard navigation when browser tools are available. For native projects, build with the available SDK and test an emulator or device when possible; report any missing native verification honestly. For games, verify the rules and gameplay loop, not only the menus.
4. Fix observed failures, then provide the runnable result, setup/run instructions, a brief explanation of what is implemented, and any specific configuration or verification limits.

This is a focused MVP. Do not add billing, AI services, or unrelated features unless explicitly requested in the brief. Start building now.