docs: VISION Stage 0 — keep "unprompted" as ideal, note measurement gap

Reframes "unprompted" from an enforced criterion to a named measurement
limitation: organic-vs-prompted returns aren't distinguishable from any data
Tapir holds, so in practice all returns are counted and the result read with that
caveat (a nudged return is a weaker signal). Adds a "how it's measured" note
pointing at summary_actions (acts) + a new append-only login-events table
(read-returns), which accrue from deploy onward. Honest about the gap rather than
silently dropping the word.

VISION.md

@@ -59,8 +59,11 @@ to the next stage's ambition until the current stage's test passes.
 ### Stage 0 — Useful to me or a friend (the gate)
 
 > **Headline test:** Over a 3–4 week window, *either* the maintainer *or* at least one
-> onboarded friend returns to Tapir **unprompted** and reads/acts on summaries in **≥2
+> onboarded friend returns to Tapir and reads/acts on summaries in **≥2 separate weeks**.
-> separate weeks**. The test is *return usage* (behavioural), not stated approval.
+> The test is *return usage* (behavioural), not stated approval. The ideal signal is an
+> **unprompted** return (organic, not because the maintainer nudged them) — but see the
+> measurement note below: we currently cannot distinguish prompted from organic returns, so
+> in practice we count all returns and read the result with that caveat.
 
 - Captions-first summarization works end-to-end for real subscriptions (the maintainer's
   and onboarded friends').
@@ -69,12 +72,24 @@ to the next stage's ambition until the current stage's test passes.
   most of the time.
 - **Why behavioural, not feedback.** Friend *feedback* is gathered and genuinely valuable —
   but it is **not** the gate. Asked-for feedback from friendly users is the least reliable
-  signal in product development (politeness bias); whether they *come back on their own* is
+  signal in product development (politeness bias); whether they *come back* is the thing we
-  the thing we actually care about. So the gate measures returns, not nice words.
+  actually care about. So the gate measures returns, not nice words.
+- **Measurement note — "unprompted" is an ideal we can't yet measure.** Whether a return was
+  organic or prompted by a nudge is not captured by any data Tapir holds (it's context only
+  the maintainer has). Rather than waive the standard, we name the gap: *unprompted* return
+  is the signal we genuinely want; *returns* (prompted or not) is what the data can show. A
+  return that needed a nudge is a weaker signal than one that didn't, and the result is read
+  with that in mind. If distinguishing them ever matters enough, the maintainer tracks nudges
+  manually or a future build records prompt events — neither is in scope now.
 - **Why "me OR a friend".** This replaces the original "useful to *me*, specifically" gate
   (2026-06-03 decision, recorded in DECISIONS.md ADR-016). Getting signal from friendly
   users is valuable enough to count — but the bar stays behavioural so it can't be cleared
   by a polite reaction. (Ties to the 2026-07-01 check-in.)
+- **How it's measured.** Return usage is read from two sources: `summary_actions` (timestamped
+  watch/skip/save per user) answers "acted in ≥2 distinct weeks"; an append-only login-events
+  table (see infra/Tapir build) answers "returned/read in ≥2 distinct weeks" even without an
+  action click — the honest signal for a *reading* product. Login events accrue only from their
+  deploy date onward, so the gate window's data begins then.
 - **This is the gate.** Hardening (Stage 1) and any SaaS ambition stay deferred until this
   behavioural signal exists. Note: multi-user machinery was deliberately built *ahead* of
   this gate (ADR-012) with isolation enforced — that was an explicit, recorded call, not a