Conversation
Co-authored-by: brunoborges <[email protected]>
|
@copilot which plan is better? Especially considering we will be using AI to generate the translations later on, automatically, whenever a new slug is added. |
Co-authored-by: brunoborges <[email protected]>
Plan B is the better fit for an AI-driven workflow. I've added a detailed breakdown in Plan A (overlay) is awkward for AI because the AI must know which fields to omit from the overlay ( Plan B (full replacement) is ideal because:
The recommended automation loop is: detect new/changed English slug → AI translates → schema validation → commit to |
|
@copilot ok let's get rid of Plan A, and focus on Plan B. |
…an focus Co-authored-by: brunoborges <[email protected]>
Done (commit |
|
@copilot rewrite Plan B as Internationalization Spec. |
Co-authored-by: brunoborges <[email protected]>
Done (commit |
|
The specification suggests using the Python script, but the copilot-instructions.md in this repo are strictly pointing at the Java-based generator (triggered with jbang). If the instructions are not clear, make it so. |
Co-authored-by: brunoborges <[email protected]>
Fixed in commit |
specs/i18n/directory with initial i18n proposalsspecs/i18n/i18n-spec.md(Internationalization Specification)python3 html-generators/generate.pyreferences in the spec withjbang html-generators/generate.javato match the project's canonical build toolingOriginal prompt
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.