DeepL Pro

Build me a focused translation management and website localization workflow for the personal core of DeepL Pro. Requirements:

- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and one optional machine-translation API. Model the inputs, state transitions, and outputs named in this translation management and website localization prompt; keep source IDs and timestamps.
- Paid product context: Connect a local translation memory editor to a user-supplied model API. Build only this DIY scope: Connect a local translation memory editor to a user-supplied model API, preserve context, review translations, import and export standard files, and publish approved strings.
- Implement projects, locales, keys, namespaces, descriptions, screenshots, translations, and review status.
- Import and export JSON, YAML, PO, and XLIFF while preserving placeholders and plural forms.
- Add glossary checks, missing-string filters, translation memory, comments, and reviewer assignment. Add backups, locale deletion safeguards, and a pseudo-localization preview.
- Use a local web page with input, progress, review, and export views. Required input or access: self-hosted deployment; source locale files. Keep credentials in .env.
- Recovery: If optional DeepL or OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs.
- Out of scope: DeepL's proprietary translation model, document handling, privacy operations, and language quality; professional translator marketplace. 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 DeepL Pro

## Project scope
Connect a local translation memory editor to a user-supplied model API, preserve context, review translations, import and export standard files, and publish approved strings.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For DeepL Pro, connect a local translation memory editor to a user-supplied model API. The hard boundary is deepl's proprietary translation model, document handling, privacy operations, and language quality, plus translation memory, collaboration, and deployment integrations.
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
- PostgreSQL
- self-hosted deployment
- source locale files
- optional DeepL or OpenAI API key

## Stack and architecture
- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and one optional machine-translation API.
- Model the inputs, state transitions, and outputs named in this translation management and website localization prompt; keep source IDs and timestamps.
- Interface for this translation management and website localization workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- If optional DeepL or OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: DeepL's proprietary translation model, document handling, privacy operations, and language quality.

## Agent implementation rules
- Project rule, data: Model the inputs, state transitions, and outputs named in this translation management and website localization prompt; keep source IDs and timestamps.
- Project rule, behavior: Implement projects, locales, keys, namespaces, descriptions, screenshots, translations, and review status.
- Project rule, recovery: If optional DeepL or OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result.

## 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 translation management and website localization operation with sample or user-owned data: Implement projects, locales, keys, namespaces, descriptions, screenshots, translations, and review status.
- Show a concrete result or export: Import and export JSON, YAML, PO, and XLIFF while preserving placeholders and plural forms.
- State the practical limit: DeepL's proprietary translation model, document handling, privacy operations, and language quality.

## Engineering roadmap
1. Phase 1, architecture and data: Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and one optional machine-translation API. Model the inputs, state transitions, and outputs named in this translation management and website localization prompt; keep source IDs and timestamps.
2. Phase 2, implement: Implement projects, locales, keys, namespaces, descriptions, screenshots, translations, and review status.
3. Phase 3, implement: Import and export JSON, YAML, PO, and XLIFF while preserving placeholders and plural forms.
4. Phase 4, review and output: Add glossary checks, missing-string filters, translation memory, comments, and reviewer assignment. Import and export JSON, YAML, PO, and XLIFF while preserving placeholders and plural forms.
5. Phase 5, recovery and acceptance: If optional DeepL or OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result. Verify this invariant with a saved fixture: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs. State the practical limit: DeepL's proprietary translation model, document handling, privacy operations, and language quality.

## Paid-product capabilities outside this build
- DeepL's proprietary translation model, document handling, privacy operations, and language quality
- professional translator marketplace
- advanced translation memory
- website proxy network
- enterprise workflows and integrations

## Implementation prompt
Build me a focused translation management and website localization workflow for the personal core of DeepL Pro. Requirements:

- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and one optional machine-translation API. Model the inputs, state transitions, and outputs named in this translation management and website localization prompt; keep source IDs and timestamps.
- Paid product context: Connect a local translation memory editor to a user-supplied model API. Build only this DIY scope: Connect a local translation memory editor to a user-supplied model API, preserve context, review translations, import and export standard files, and publish approved strings.
- Implement projects, locales, keys, namespaces, descriptions, screenshots, translations, and review status.
- Import and export JSON, YAML, PO, and XLIFF while preserving placeholders and plural forms.
- Add glossary checks, missing-string filters, translation memory, comments, and reviewer assignment. Add backups, locale deletion safeguards, and a pseudo-localization preview.
- Use a local web page with input, progress, review, and export views. Required input or access: self-hosted deployment; source locale files. Keep credentials in .env.
- Recovery: If optional DeepL or OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs.
- Out of scope: DeepL's proprietary translation model, document handling, privacy operations, and language quality; professional translator marketplace. 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.