feat(coach): give every read-only assessment surface a way out

Status cards and derived-score sheets read one way: they state a verdict and
end there. The metric pages already carried the hand-off; the score sheets
passed neither an opener nor a scope, so they painted no action at all.

- Score sheets (sleep / readiness / recovery / stress / strain) gain the same
  auto-sent opener the metric pages use, each scoped to the inputs that drive
  the composite rather than to a block it has no equivalent of.
- Workout detail's coach launch carries the workout itself. The chat request
  gains an optional workoutId; on the FIRST turn the route narrows by
  { id, userId } and pins ONE bounded evidence section onto the snapshot.
  Later turns reuse the pinned snapshot, so per-turn work stays constant in
  conversation length.
- /coach?workout=<id> covers the full-page and maximize paths.

The workout block deliberately does not take the fenced transport the stored-
document path takes: a workout row is the user's own sensor record, and the
projection admits no free text. That is enforced, not assumed — sport_type is
a TEXT column, so it is re-asserted against the closed sport union, metadata
is excluded apart from its numeric zone durations read through a Zod slice,
and a recursive guard throws on any non-numeric leaf.

Own-history sport averages move to src/lib/workouts/sport-context.ts so the
narrative and the detail page cannot quote different figures.

src/app/api/workouts/[id]/route.ts

@@ -38,15 +38,11 @@ import {
   parseWhoopZoneDurations,
 } from "@/lib/workouts/zones";
 import { computeSplits } from "@/lib/workouts/splits";
+import { buildSportContext } from "@/lib/workouts/sport-context";
 import type { RouteCoordinate } from "@/lib/workouts/route-svg";
 
 type RouteParams = { params: Promise<{ id: string }> };
 
-/** Own-history lookback for the sport-average comparison line. */
-const SPORT_CONTEXT_LOOKBACK_DAYS = 180;
-/** Slim-row cap for the sport-average read. */
-const SPORT_CONTEXT_MAX_ROWS = 500;
-
 export const GET = apiHandler(
   async (request: NextRequest, { params }: RouteParams) => {
     const { user } = await requireAuth();
@@ -248,63 +244,3 @@ export const GET = apiHandler(
   },
 );
 
-/**
- * The user's own recent average for a sport — rendered as one muted
- * comparison line. Cross-source twins are collapsed through
- * `pickCanonicalWorkoutRows()` first so a run recorded by two paired
- * watches counts once. Comparisons are to the user's own history only
- * (non-diagnostic standard).
- */
-async function buildSportContext(
-  userId: string,
-  sportType: string,
-  sourcePriorityJson: unknown,
-): Promise<{
-  count: number;
-  avgDurationSec: number;
-  avgDistanceM: number | null;
-  avgAvgHr: number | null;
-} | null> {
-  const since = new Date(
-    Date.now() - SPORT_CONTEXT_LOOKBACK_DAYS * 24 * 60 * 60 * 1000,
-  );
-  const rows = await prisma.workout.findMany({
-    where: { userId, sportType, startedAt: { gte: since } },
-    orderBy: [{ startedAt: "asc" }, { id: "asc" }],
-    take: SPORT_CONTEXT_MAX_ROWS,
-    select: {
-      id: true,
-      source: true,
-      startedAt: true,
-      sportType: true,
-      durationSec: true,
-      totalDistanceM: true,
-      avgHeartRate: true,
-    },
-  });
-  const canonical = pickCanonicalWorkoutRows(rows, sourcePriorityJson);
-  if (canonical.length === 0) return null;
-
-  let durationSum = 0;
-  let distanceSum = 0;
-  let distanceCount = 0;
-  let hrSum = 0;
-  let hrCount = 0;
-  for (const r of canonical) {
-    durationSum += r.durationSec;
-    if (r.totalDistanceM != null) {
-      distanceSum += r.totalDistanceM;
-      distanceCount += 1;
-    }
-    if (r.avgHeartRate != null) {
-      hrSum += r.avgHeartRate;
-      hrCount += 1;
-    }
-  }
-  return {
-    count: canonical.length,
-    avgDurationSec: Math.round(durationSum / canonical.length),
-    avgDistanceM: distanceCount > 0 ? distanceSum / distanceCount : null,
-    avgAvgHr: hrCount > 0 ? Math.round(hrSum / hrCount) : null,
-  };
-}