feat(mood-insights): promote mood to a discovery outcome and surface it

Two changes that turn the descriptive relations surfaces into a
statistically-gated discovery view on the mood page.

Mood as an outcome: the FDR-controlled all-pairs correlation discovery
engine treated mood only as a behaviour (a lag source). Promote it to an
outcome channel too, so the scan also surfaces "behaviour today → next-day
mood" relations (e.g. more daylight today → better mood tomorrow) alongside
the existing "mood today → next-day outcome" direction. The self-pair is
skipped and Benjamini-Hochberg already controls the larger pair family this
opens up. The discovery route now feeds the shared mood daily-mean series
into both roles.

Surface the discovery slice: the engine was computed but never rendered.
The mood Insights page now shows the mood-involving pairs that survive the
false-discovery correction, each phrased observationally with its paired-day
count, r, and BH q-value, plus the honest "X of N tested" footer. The
surface self-fetches the correlation route and degrades to nothing when the
operator has disabled it. Observational only, with the standing disclaimer.

src/lib/insights/__tests__/correlation-discovery.test.ts

@@ -95,3 +95,48 @@ describe("discoverCorrelations", () => {
     expect(result.discovered).toHaveLength(0);
   });
 });
+
+// ── F3 — MOOD as a discoverable OUTCOME channel ─────────────────────
+
+import { DISCOVERY_OUTCOMES } from "../correlation-discovery";
+
+describe("MOOD as outcome (F3)", () => {
+  it("registers MOOD in the outcome matrix", () => {
+    expect(DISCOVERY_OUTCOMES).toContain("MOOD");
+  });
+
+  it("surfaces a behaviour → next-day MOOD relation", () => {
+    // 30 contiguous days; daylight on day D drives mood on day D+1.
+    const n = 30;
+    const daylight = Array.from({ length: n }, (_, i) => 60 + (i % 10) * 5);
+    // mood[D+1] tracks daylight[D] with light noise → strong lagged r.
+    const mood = Array.from({ length: n }, (_, i) => {
+      const driver = i === 0 ? 60 : 60 + ((i - 1) % 10) * 5;
+      return 1 + (driver - 60) / 45 + (i % 2 === 0 ? 0.02 : -0.02);
+    });
+    const result = discoverCorrelations([
+      { key: "TIME_IN_DAYLIGHT", role: "behaviour", points: series(daylight) },
+      { key: "MOOD", role: "outcome", points: series(mood) },
+    ]);
+    const pair = result.discovered.find(
+      (p) => p.behaviour === "TIME_IN_DAYLIGHT" && p.outcome === "MOOD",
+    );
+    expect(pair).toBeDefined();
+    expect(pair!.r).toBeGreaterThan(0.5);
+  });
+
+  it("never tests the MOOD → MOOD self-pair", () => {
+    const n = 30;
+    const mood = Array.from({ length: n }, (_, i) => 3 + (i % 3));
+    const result = discoverCorrelations([
+      { key: "MOOD", role: "behaviour", points: series(mood) },
+      { key: "MOOD", role: "outcome", points: series(mood) },
+    ]);
+    expect(
+      result.discovered.find(
+        (p) => p.behaviour === "MOOD" && p.outcome === "MOOD",
+      ),
+    ).toBeUndefined();
+    expect(result.pairsTested).toBe(0);
+  });
+});

src/lib/insights/correlation-discovery.ts

@@ -249,6 +249,13 @@ export const DISCOVERY_OUTCOMES = [
   "HEART_RATE_VARIABILITY",
   "RESTING_HEART_RATE",
   "WEIGHT",
+  // v1.11.5 (F3) — mood is now an OUTCOME channel too, not only a behaviour.
+  // The discovery loop skips the MOOD→MOOD self-pair (`b.key === o.key`), so
+  // promoting it lets the FDR scan surface "behaviour today → next-day mood"
+  // relations (e.g. more daylight today → better mood tomorrow) in addition
+  // to the existing "mood today → next-day outcome" direction. BH-FDR
+  // already controls the larger pair family this opens up.
+  "MOOD",
   // Wrist temperature is a credible future OUTCOME channel (near-daily, so
   // n ≥ 20 is reachable; "did a hard workout / late alcohol raise next-night
   // temperature?"), but it is deliberately NOT a channel yet: it is