From fb83c70d238b7d247a5f25217383f476b356cea3 Mon Sep 17 00:00:00 2001
From: openhands <openhands@all-hands.dev>
Date: Mon, 16 Mar 2026 15:50:19 +0000
Subject: [PATCH] fix: chore: fetch and cache Uniswap V3 replay datasets for
 evolution backtesting (#883)

- Add fetch-datasets.sh wrapper that fetches HIGHER/WETH, DEGEN/WETH,
  and TOSHI/WETH 30-day event caches via fetch-events.ts; reads
  INFURA_API_KEY from env and fails with a helpful error if unset
- Update .gitignore from cache/ (whole dir) to cache/*.jsonl so the
  pattern is precise to the generated data files; cache/ is already
  covered by the repo-root .gitignore via its own cache/ rule

JSONL cache files are gitignored and must be generated locally by
running ./fetch-datasets.sh with INFURA_API_KEY set.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 onchain/script/backtesting/.gitignore        |  2 +-
 onchain/script/backtesting/fetch-datasets.sh | 53 ++++++++++++++++++++
 2 files changed, 54 insertions(+), 1 deletion(-)
 create mode 100755 onchain/script/backtesting/fetch-datasets.sh

diff --git a/onchain/script/backtesting/.gitignore b/onchain/script/backtesting/.gitignore
index 7663573..e6e14ec 100644
--- a/onchain/script/backtesting/.gitignore
+++ b/onchain/script/backtesting/.gitignore
@@ -1,2 +1,2 @@
 # Cache files generated by fetch-events.ts at runtime — do not commit
-cache/
+cache/*.jsonl
diff --git a/onchain/script/backtesting/fetch-datasets.sh b/onchain/script/backtesting/fetch-datasets.sh
new file mode 100755
index 0000000..c4a4ddc
--- /dev/null
+++ b/onchain/script/backtesting/fetch-datasets.sh
@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+# fetch-datasets.sh — Download and cache Uniswap V3 replay datasets for the
+# evolution backtester. Re-running is safe: fetch-events.ts has resume support.
+#
+# Usage:
+#   INFURA_API_KEY=<key> ./fetch-datasets.sh
+#   # or export the variable beforehand:
+#   export INFURA_API_KEY=<key>
+#   ./fetch-datasets.sh
+#
+# Alternatively derive the key from BASE_RPC_URL:
+#   export INFURA_API_KEY=$(echo "$BASE_RPC_URL" | grep -oP '/v3/\K.*')
+
+set -euo pipefail
+
+: "${INFURA_API_KEY:?INFURA_API_KEY is required. Set it directly or derive from BASE_RPC_URL: export INFURA_API_KEY=\$(echo \"\$BASE_RPC_URL\" | grep -oP '/v3/\\K.*')}"
+
+export INFURA_API_KEY
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+cd "$SCRIPT_DIR"
+
+mkdir -p cache
+
+echo "=== Fetching HIGHER/WETH (last 30 days) ==="
+npx tsx fetch-events.ts \
+  --pool 0xCC28456d4Ff980CeE3457Ca809a257E52Cd9CDb0 \
+  --days 30 \
+  --output cache/higher-weth-30d.jsonl
+
+echo "=== Fetching DEGEN/WETH (last 30 days) ==="
+npx tsx fetch-events.ts \
+  --pool 0x0cA6485b7e9cF814A3Fd09d81672B07323535b64 \
+  --days 30 \
+  --output cache/degen-weth-30d.jsonl
+
+echo "=== Fetching TOSHI/WETH (last 30 days) ==="
+npx tsx fetch-events.ts \
+  --pool 0x4b0Aaf3EBb163dd45F663b38b6d93f6093EBC2d3 \
+  --days 30 \
+  --output cache/toshi-weth-30d.jsonl
+
+echo ""
+echo "=== Done. Event counts: ==="
+for f in cache/higher-weth-30d.jsonl cache/degen-weth-30d.jsonl cache/toshi-weth-30d.jsonl; do
+  if [ -f "$f" ]; then
+    count=$(wc -l < "$f")
+    echo "  $f: $count events"
+  else
+    echo "  $f: MISSING"
+  fi
+done