# Prompt Versioning

## Objective

Tie every AI output to the exact prompt version that produced it.

Immutable, numbered versions of each prompt, with the run configuration recorded and every output stamped with the version used.

## Before You Begin

This feature is being added to an application that already exists and already
works. Do not scaffold a new project, and do not assume a blank slate.

Inspect the codebase first and establish:

- The existing application structure and where code of this kind already lives.
- The framework and version in use.
- The existing design system — colours, spacing, typography, and component conventions.
- Existing UI components you can reuse instead of writing new ones.
- The existing database structure, if this feature needs to persist anything.
- The existing authentication and authorization system, if this feature is user-scoped.
- Dependencies already installed, so you don't add a library that duplicates one.
- The existing test setup and conventions.

Only start writing code once you understand the above. If the application
already implements part of this feature, extend it rather than replacing it.

## Implementation Instructions

1. Make every publish create a new immutable version rather than overwriting the previous text. Editing history in place destroys the only record of what produced last month's outputs.
2. Capture the whole run configuration with each version, not just the wording: which model tier and parameters were used, which tools were available, and the expected output shape. A prompt that behaves differently under different settings is not one prompt.
3. Stamp every generated output with the version identifier that produced it, and keep that stamp with the record so an output found later can be traced back to its exact instructions.
4. Keep the active version per environment separate, so promoting a version in a test environment does not change what production runs. Publishing to production must be a deliberate act.
5. Support rollback to any earlier version without discarding newer drafts. Rolling back must change which version is active, not delete the work that came after it.

## UI and UX Requirements

Match the application's existing design system exactly. Reuse its components,
spacing, and typography. This feature should look like it was always there.

## Responsive Requirements

Works on mobile, tablet, and desktop. Touch targets are large enough to hit on a
phone, and nothing overflows horizontally at 320px.

## Accessibility Requirements

- Fully keyboard navigable.
- Correct semantic elements and ARIA roles.
- Visible focus states.
- Meets WCAG AA contrast.
- Dynamic changes are announced to screen readers.
- Respects prefers-reduced-motion.

## Edge Cases

- A published version must be immutable. Allowing an edit in place means every output stamped with that version is now attributed to text that no longer exists.
- Model tier, parameters, available tools, and output schema must be recorded with the version. Without them, a reproduction attempt runs the same words under different conditions and gets different results for reasons nobody can see.
- Rolling back must leave newer drafts intact and re-promotable, rather than treating rollback as a delete of everything after the target version.
- Each environment must track its own active version, or a test promotion silently changes what customers receive.
- Comparing versions is meaningless unless both are run against the same fixed evaluation cases. Store a shared set of cases and their results per version rather than judging on ad hoc examples.
- An output stamped with a version that has been deleted must still resolve to something readable, so version records must be retained for as long as any output references them.
- Version storage grows without limit if every keystroke is a version. Distinguish drafts, which may be overwritten, from published versions, which may not.
- A run started against one version and completed after a promotion must be recorded under the version it actually used, not the one that is active when it finishes.

## Testing

Exercise the feature end to end in the running application. Cover every edge case
above, then run the existing test suite and confirm nothing regressed.

## Acceptance Criteria

- [ ] Publishing creates a new immutable version and never modifies an existing one.
- [ ] Each version records the model tier, parameters, available tools, and expected output shape used with it.
- [ ] Every generated output is stamped with the version that produced it and remains traceable later.
- [ ] Each environment has its own active version and promotion between them is explicit.
- [ ] Rollback changes the active version without deleting newer drafts.
- [ ] Two versions can be compared against the same stored evaluation cases with results retained per version.
- [ ] The feature matches the existing design system.
- [ ] No existing functionality is broken.

## Adaptation Rules

- Match the existing design system. Do not introduce a new colour palette,
  spacing scale, or component library.
- Reuse existing components and utilities wherever they fit.
- Follow the naming, file layout, and code style already present.
- Do not upgrade, replace, or remove existing dependencies to make this
  feature fit. Adapt the feature to the app, not the app to the feature.
- Do not break existing functionality. If a change is genuinely required in
  existing code, make the smallest one that works and say so.
- If something in these instructions conflicts with how the application is
  built, follow the application and explain the deviation.

## Final Verification

Before you report the work as done:

1. Re-read the acceptance criteria above and check each one against what you
   actually built.
2. Run the application and exercise the feature end to end.
3. Run the existing test suite and confirm you have broken nothing.
4. Check the feature on mobile, tablet, and desktop widths.
5. Check keyboard navigation and focus handling.
6. Summarize what changed: files added, files modified, and anything you
   deliberately did differently because of how this application is built.

If any acceptance criterion is unmet, fix it before reporting completion.