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>

ml/serving/main.py

@@ -31,6 +31,8 @@ import numpy as np
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 
+from prompts import get_prompt
+
 app = FastAPI(title="oO ML Serving", version="1.0.0")
 
 LITELLM_URL = os.getenv("LITELLM_URL", "http://localhost:4000")
@@ -181,6 +183,7 @@ class GenerateRequest(BaseModel):
     user_id: str
     context: PromptContext = PromptContext()
     n: int = 3
+    prompt_version: Optional[str] = None  # None → server default (env DEFAULT_PROMPT_VERSION)
 
 
 class TipCandidate(BaseModel):
@@ -193,33 +196,11 @@ class TipCandidate(BaseModel):
 class GenerateResponse(BaseModel):
     candidates: list[TipCandidate]
     model: str
+    prompt_version: str
     prompt_tokens: int = 0
     completion_tokens: int = 0
 
 
-_GENERATE_SYSTEM = (
-    "You are a personal productivity coach. "
-    "Given the user's current context, generate actionable, specific tips. "
-    "Respond ONLY with a JSON array of objects, each with keys: "
-    '"id" (short slug), "content" (the tip, ≤2 sentences), "rationale" (why now, ≤1 sentence). '
-    "No markdown, no prose outside the JSON array."
-)
-
-
-def _build_prompt(ctx: PromptContext, n: int) -> str:
-    lines = [f"Time: {ctx.hour_of_day:02d}:00, day_of_week={ctx.day_of_week}"]
-    if ctx.tasks:
-        overdue = [t for t in ctx.tasks if t.get("is_overdue")]
-        lines.append(f"Tasks: {len(ctx.tasks)} total, {len(overdue)} overdue")
-        for t in ctx.tasks[:5]:
-            due = t.get("due_date", "no due date")
-            lines.append(f"  - [{t.get('priority','?')}] {t.get('content','?')} (due: {due})")
-    for k, v in ctx.extra.items():
-        lines.append(f"{k}: {v}")
-    lines.append(f"\nGenerate {n} tips as a JSON array.")
-    return "\n".join(lines)
-
-
 # ── Endpoints ──────────────────────────────────────────────────────────────
 
 @app.get("/health")
@@ -253,10 +234,14 @@ async def generate(req: GenerateRequest) -> GenerateResponse:
     Retries up to _MAX_GENERATE_RETRIES times on malformed JSON, appending
     a correction hint to the conversation so the model can self-correct.
     """
-    prompt = _build_prompt(req.context, req.n)
+    try:
+        prompt_template = get_prompt(req.prompt_version)
+    except KeyError as e:
+        raise HTTPException(status_code=422, detail=f"Unknown prompt_version: {e.args[0]}")
+    user_msg = prompt_template.build_user(req.context, req.n)
     messages: list[dict] = [
-        {"role": "system", "content": _GENERATE_SYSTEM},
-        {"role": "user", "content": prompt},
+        {"role": "system", "content": prompt_template.system},
+        {"role": "user", "content": user_msg},
     ]
     headers = {"Authorization": f"Bearer {LITELLM_MASTER_KEY}"}
     last_parse_error: str = ""
@@ -313,6 +298,7 @@ async def generate(req: GenerateRequest) -> GenerateResponse:
     return GenerateResponse(
         candidates=candidates,
         model=model_used,
+        prompt_version=prompt_template.version,
         prompt_tokens=total_usage["prompt_tokens"],
         completion_tokens=total_usage["completion_tokens"],
     )