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>

.env.example

@@ -37,3 +37,11 @@ TODOIST_CLIENT_SECRET=
 NATS_URL=
 # How often the background scheduler refreshes Todoist tasks per active user (ms).
 TODOIST_SYNC_INTERVAL_MS=900000
+
+# Tip prompt selection — empty = use ml/serving default (v1).
+# Pin a single variant: "v2-mentor"
+# Rotate uniformly across variants: "v1,v2-mentor,v3-few-shot"
+# Buckets show up in the admin reward-analytics dashboard (#92).
+TIP_PROMPT_VERSION=
+# Default version on the Python side when the API doesn't specify one.
+DEFAULT_PROMPT_VERSION=v1