docs: restructure TASKS.md into a catalog — one file per task in TASKS/

TASKS.md is now the index (status table, open items, research pointer).
33 files: 32 task files + 1 research facts file. The full take-saga
narrative and all design decisions are preserved verbatim; the catalog
makes the queue readable without opening every task body. Schema and
AGENTS.md updated to reflect the new layout.

TASKS/task-33-bandwidth-step-down.md

@@ -0,0 +1,21 @@
+# TASK 33 — Bandwidth auto step-down (queued 2026-09-01; v1 per the complete-v1 ruling)
+
+> Catalog: [`TASKS.md`](../TASKS.md) — status and requirements live here.
+
+
+**Goal:** when the upload can't hold the tier, drop it automatically instead of drowning viewers in
+freeze frames. The `variable` reusable stream (shipped) makes this zero-API; the governor that decides
+WHEN is what TASKS.md:25 always claimed existed and was never built.
+
+1. ☐ Pure `StepDownPolicy` — sliding window over the encoder's reported dropped-frame rate
+   (`StreamHealth`, already parsed): sustained overrun → downgrade exactly one 16:9 tier
+   (1080p60 → 1080p30 → 720p60 → 720p30). Hysteresis cooldown; **one-way within a broadcast**
+   (no oscillation — a recovered connection doesn't climb back mid-show; the creator may manually
+   step up). Vertical tier stays a manual choice.
+2. ☐ Restart machinery = TASK 32 slice 1 (tier change is an encoder relaunch at new W×H/FPS over the
+   same pipe/URL; the master canvas is 1920×1080 regardless, so geometry never rewrites).
+3. ☐ Surface: the resolution badge + dropdown update to the landed tier; ONE Info toast
+   ("Quality lowered to hold your stream") — no nagging after that.
+4. ☐ Tests: pure-policy units (drop-rate windows, one-way, cooldown) + the ONE integration: fake
+   health stream with sustained drops → exactly one lower-tier encoder restart.
+