DeFi Overview

<!-- autoresearch: variation B — sharper output via regime verdict + sustainable-vs-incentive yield split + fees fundamentals + per-mover "why it matters" -->

> **${var}** — Chain or protocol to focus on (e.g. `solana`, `aave`, `arbitrum`). If empty, full market overview.

Read `memory/MEMORY.md` for context. Read the last 2 days of `memory/logs/` to avoid repeating numbers and to cite yesterday's figure when flagging today's change.

## Thesis

The original produced a table of numbers. This version produces a **read of the market**: one verdict line at the top, then only items that *changed* or *matter*, each with a one-line reason a reader should care. TVL alone is lagging and emission-subsidized — we pair it with fees/revenue (real fundamentals) and split yields into sustainable (`apyBase`) vs incentive-driven (`apyReward`) so readers stop chasing scam-tier APYs.

## Focus mode

- `var` empty → full market overview.
- `var` matches a chain name in `/v2/chains` (case-insensitive) → chain focus: scope DEX volume, fees, and yields to that chain; keep a 2-line market header for context.
- `var` matches a protocol slug in `/protocols` → protocol focus: pull `/protocol/{slug}`, `/summary/fees/{slug}`, `/summary/dexs/{slug}` if DEX; compare against its chain and its 30-day self.
- `var` matches neither → proceed as full overview and note `var unresolved: ${var}` in the footer.

## Steps

### 1. Fetch (public, no auth — use WebFetch if curl fails)

```bash
# TVL
curl -fsS "https://api.llama.fi/v2/chains"                        > .tmp/chains.json
curl -fsS "https://api.llama.fi/protocols"                        > .tmp/protocols.json

# Volumes & fundamentals (these are the endpoints the old version was missing)
curl -fsS "https://api.llama.fi/overview/dexs?excludeTotalDataChart=true&excludeTotalDataChartBreakdown=true"  > .tmp/dexs.json
curl -fsS "https://api.llama.fi/overview/fees?excludeTotalDataChart=true&excludeTotalDataChartBreakdown=true"  > .tmp/fees.json

# Stablecoins
curl -fsS "https://stablecoins.llama.fi/stablecoins?includePrices=false"  > .tmp/stables.json

# Yields
curl -fsS "https://yields.llama.fi/pools"                         > .tmp/pools.json
```

For each endpoint, if curl fails or returns non-JSON, retry once with **WebFetch** against the same URL. Mark the source `ok` or `fail` — carry this into the footer. Never block the whole run on a single source.

`/protocols` and `/v2/chains` already include `change_1d` / `change_7d` / `tvl` — use these directly, do not diff manually. `/overview/dexs` and `/overview/fees` return `total24h`, `total7d`, `change_1d`, `change_7d`, `change_1m`, `protocols[]`.

If `var` is a chain, additionally fetch `/overview/dexs/{chain}` and `/overview/fees/{chain}` and filter pools by `chain == var`.

### 2. Compute the verdict (ONE line, leads the message)

Score three dimensions from the last 24h:

- `tvl_d = overall TVL change_1d` (sum across `/v2/chains`)
- `vol_d = DEX volume change_1d` (from `/overview/dexs`)
- `stable_d = stablecoin supply change_1d` (sum from `/stablecoins`)

Verdict rules (pick the first that matches):
- All three > +2% → **Risk-on** — capital flowing in across TVL, volume, and stables.
- Two of three < −2% → **Risk-off** — capital unwinding.
- `|tvl_d| < 1% AND |vol_d| < 5%` → **Sideways** — no conviction; grind day.
- Otherwise → **Mixed** — describe the split in ≤12 words (e.g. "TVL drifting up on steady volume, stables flat").

### 3. Pick what goes in the message

Each section caps at 3 items. **Drop any section whose best item fails its inclusion rule** — don't pad.

**Top chains** (3 items): rank by TVL; show `change_1d` only if `|change_1d| >= 1%`, otherwise suppress the delta.

**Movers — chains** (1 up, 1 down): filter `|change_1d| >= 5% AND tvl >= $500M`. Require a ≤15-word "why" grounded in what you observed (unlock, points program, bridge activity, depeg, exploit, launch). If you can't name a cause from the data or memory, write `"no obvious catalyst"` — do not invent one.

**Movers — protocols** (1 up, 1 down): filter `|change_1d| >= 10% AND tvl >= $100M`. Same "why" rule.

**Fundamentals — fees leaders** (top 3 by 24h fees from `/overview/fees`): include `change_1d` in fees vs 7d average. This replaces the old "top protocols by TVL" padding — fees > TVL for real demand.

**Fundamentals — fees-beating-TVL** (up to 2): protocols where `fees change_7d > +20% AND TVL change_7d < +5%`. These are where real demand is outpacing emission-subsidized capital. Skip section if none.

**DEX volume**: 24h total + top 3 DEXes with `change_1d`.

**Stablecoins**: total supply + any single stablecoin with `|change_1d| >= 1%` (usually only notable shifts survive).

**Yields** — split into two sub-sections, **each with a hard filter**:

- **Real yield (sustainable)** — 3 pools max. Filter:
  `apyBase > 0 AND apyReward_share < 0.5 AND outlier == false AND predictions.binnedConfidence >= 2 AND apyMean30d >= apy * 0.5 AND tvlUsd >= $10M`.
  Rank by `apyBase` descending.
- **Incentive yield (points / emissions)** — 2 pools max. Filter:
  `apyReward > 0 AND outlier == false AND tvlUsd >= $25M`. Tag with the reward token symbol. Rank by `apy` descending.

If zero pools survive either filter, omit that sub-section and note it in the footer (`real_yield=0` etc.) — this is itself a signal.

### 4. Compare against yesterday's log

Read `memory/logs/${yesterday}.md`. If a mover appears today whose direction flipped (e.g. chain was top gainer yesterday, now top loser), prepend `↔` and note the reversal in its "why" line. If a yield pool from yesterday's Real-yield list is missing today, check whether it failed a filter (outlier flipped, APY collapsed) — this is worth one line under Yields.

### 5. Notify

Send via `./notify` (single call, under 4000 chars, plain markdown). Template:

```
*DeFi — ${today}* — <Verdict>: <≤12-word regime read>

*TVL:* $X.XXT (+X.X% 24h, +X.X% 7d)

*Top chains*
1. Ethereum — $XXXB (+X.X%)
2. Solana — $XXB (+X.