feat(ml): prompt registry + per-request variant selection

Replaces the hardcoded "v1" label with a real prompt registry:

  ml/serving/prompts.py       — keyed by version: v1 (baseline),
                                v2-mentor (calm/specific persona),
                                v3-few-shot (v1 persona + curated examples)
  ml/serving/main.py          — POST /generate accepts optional prompt_version,
                                422 on unknown, echoes the version actually used
                                back in the response
  services/api/src/config.ts  — TIP_PROMPT_VERSION: empty / single / comma-list
                                (uniform random per request)
  services/api/src/routes/recommender.ts
                              — pickPromptVersion() drives selection; the
                                response's prompt_version (not a stale TS
                                constant) is what lands in tip_scores so the
                                #92 reward-analytics dashboard shows real
                                per-variant reaction rates

Closes #84.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

services/api/src/routes/__tests__/recommender.test.ts

@@ -134,6 +134,7 @@ describe('POST /recommend integration', () => {
           json: async () => ({
             candidates: [{ id: 'adv-1', content: 'Take a break.', rationale: 'You deserve it.' }],
             model: 'tip-generator',
+            prompt_version: 'v1',
           }),
         } as any);
       }