docs(runbook): correct flywheel (nil→local) + instrumentation-fixed note

Two corrections after the #73 investigation: (1) the router routes cold
(nil pass-rate) calls to the LOCAL fast tier, not cloud — the earlier
"pay in on cloud" description was wrong (per policy.go). (2) Note that
pass-rate logging was broken until v0.11.1 (#73) and is now verified;
reset the window to 2026-06-30→07-14. Refs #73, #35.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

docs/runbooks/exercising-pass-rate-traffic.md

@@ -55,26 +55,35 @@ In normal sessions, invoke the pod's tools instead of reviewing/debugging inline
 
 Each call logs an outcome to ingestion → `/pass-rate` ticks up.
 
-## Step 3 — the flywheel (cold-start behavior is the gate)
+## Step 3 — how routing actually picks the model
 
-The router's cold start **is** the data gate — same loop:
+Per `internal/routing/policy.go`:
 
-1. With pass-rate `nil` (cold), the policy routes to the **thinking / cloud**
+1. pass-rate `nil` (cold) → **local** fast tier. The router defaults to local
-   model — it won't trust the local fast model without history.
+   from invocation #1, not to cloud — so the fast tier is exercised immediately.
-2. As `review` / `debug` accumulate **passes**, pass-rate climbs past the floor
+2. pass-rate `>= 0.90` (floor) → **local**; `< 0.70` (ceil) → **cloud/thinking**;
-   (`HYPERGUILD_ROUTE_LOCAL_FLOOR=0.90`) and the router starts sending those
+   in the `[0.70, 0.90)` band a request-hash bit samples 50/50.
-   skills to the **local fast tier**.
+3. On a local execution error the router falls open to the thinking model for
-3. So early calls "pay in" on cloud to build the record; then the local tier
+   that one call (logged `thinking_fallback`).
-   activates automatically. Exercising the traffic is what spins it up.
 
-The fast tier is now **`koala/qwen36-35b-a3b`** (Qwen3.6-35B-A3B MTP), promoted
+So you are not "paying in on cloud" — cold calls already run on the (validated)
-2026-06-29 after clearing the tool-call gate (infra `c66a195`,
+local fast tier **`koala/qwen36-35b-a3b`** (Qwen3.6-35B-A3B MTP, promoted
-`HYPERGUILD_FAST_MODEL`).
+2026-06-29, infra `c66a195`, `HYPERGUILD_FAST_MODEL`). Accumulating passes just
+keeps it there once real pass-rate is computed.
+
+> **Instrumentation note (#73, fixed 2026-06-30):** until v0.11.1 the pod logged
+> successes as `"skip"` (not `"pass"`), under `skill:"_routing"`, via an
+> unauthenticated POST that silently 401'd — so `/pass-rate` stayed at zero no
+> matter how much you used it. That's fixed and verified (a real review call now
+> moves `/pass-rate?skill=review` 0→1). If you see traffic not registering,
+> re-check #73's three failure modes first.
 
 ## Target & verification
 
-- **50 logged invocations** across `review` + `debug` within the 14-day window
+- **50 logged invocations** across `review` + `debug` within the 14-day window.
-  (opened 2026-06-26, **kill-date 2026-07-10**) → ~4–5 calls/day.
+  The clock restarts **2026-06-30** (the day instrumentation was verified working;
+  the original 2026-06-26→07-10 window measured broken plumbing) → **kill-date
+  2026-07-14**, ~4 calls/day (1 already logged from the #73 smoke test).
 - Check progress anytime:
 
   ```bash