Paperpal

Build me a focused academic writing assistant workflow for the personal core of Paperpal. Requirements:

- Use exactly this stack: Next.js 15 + TypeScript + SQLite. Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
- Paid product context: Language editing, citations, research checks, and manuscript assistance. Build only this DIY scope: Build a private academic writing assistant workspace that sends user text to one chosen model, stores versions, applies reusable instructions, and exports Markdown.
- For academic writing assistant, accept source text, a named instruction preset, and a user-selected model credential.
- Generate a draft as a new revision, preserving the source and recording prompt/model metadata.
- Let the writer compare revisions, accept edits, and export Markdown.
- Use a local web page with input, progress, review, and export views. Required input or access: OpenAI API key in .env. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A model failure cannot overwrite the source; quoted facts must stay traceable to supplied text or be marked unverified.
- Out of scope: brand-trained workflows; team governance and integrations. 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 Paperpal

## Project scope
Build a private academic writing assistant workspace that sends user text to one chosen model, stores versions, applies reusable instructions, and exports Markdown.

Catalogue verdict: no. Do not mistake the interface for the product. Paperpal's durable value is model, data, workflow, 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
- OpenAI API key in .env
- Node.js 22
- SQLite database
- Explicit README warning that this is a consolation build, not a production replacement

## Stack and architecture
- Use exactly this stack: Next.js 15 + TypeScript + SQLite.
- Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
- Interface for this academic writing assistant workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- A model failure cannot overwrite the source; quoted facts must stay traceable to supplied text or be marked unverified.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: brand-trained workflows.

## Agent implementation rules
- Project rule, data: Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
- Project rule, behavior: For academic writing assistant, accept source text, a named instruction preset, and a user-selected model credential.
- Project rule, recovery: A model failure cannot overwrite the source; quoted facts must stay traceable to supplied text or be marked unverified.

## 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 academic writing assistant operation with sample or user-owned data: For academic writing assistant, accept source text, a named instruction preset, and a user-selected model credential.
- Show a concrete result or export: Let the writer compare revisions, accept edits, and export Markdown.
- State the practical limit: brand-trained workflows.

## Engineering roadmap
1. Phase 1, architecture and data: Use exactly this stack: Next.js 15 + TypeScript + SQLite. Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
2. Phase 2, implement: For academic writing assistant, accept source text, a named instruction preset, and a user-selected model credential.
3. Phase 3, implement: Generate a draft as a new revision, preserving the source and recording prompt/model metadata.
4. Phase 4, review and output: Let the writer compare revisions, accept edits, and export Markdown.
5. Phase 5, recovery and acceptance: Verify this invariant with a saved fixture: A model failure cannot overwrite the source; quoted facts must stay traceable to supplied text or be marked unverified. State the practical limit: brand-trained workflows.

## Paid-product capabilities outside this build
- brand-trained workflows
- team governance and integrations
- vendor-managed prompt and quality tuning
- proprietary models or classifiers

## Implementation prompt
Build me a focused academic writing assistant workflow for the personal core of Paperpal. Requirements:

- Use exactly this stack: Next.js 15 + TypeScript + SQLite. Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
- Paid product context: Language editing, citations, research checks, and manuscript assistance. Build only this DIY scope: Build a private academic writing assistant workspace that sends user text to one chosen model, stores versions, applies reusable instructions, and exports Markdown.
- For academic writing assistant, accept source text, a named instruction preset, and a user-selected model credential.
- Generate a draft as a new revision, preserving the source and recording prompt/model metadata.
- Let the writer compare revisions, accept edits, and export Markdown.
- Use a local web page with input, progress, review, and export views. Required input or access: OpenAI API key in .env. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A model failure cannot overwrite the source; quoted facts must stay traceable to supplied text or be marked unverified.
- Out of scope: brand-trained workflows; team governance and integrations. 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.