Merge branch 'main' into small-block-state-root

Amp-Thread-ID: https://ampcode.com/threads/T-019c649c-0e7d-74ce-9e41-be800680229a

.changelog/big-mules-cook.md

@@ -0,0 +1,4 @@
+---
+---
+
+Added site-level meta description for SEO.

.changelog/bold-frogs-run.md

@@ -0,0 +1,5 @@
+---
+reth-transaction-pool: patch
+---
+
+Renamed and documented validation methods for clarity. `validate_one_no_state` and `validate_one_against_state` are now public methods `validate_stateless` and `validate_stateful` with improved documentation explaining their respective validation phases.

.changelog/config.toml

@@ -0,0 +1,20 @@
+# Changelogs configuration for reth
+# https://github.com/wevm/changelogs
+
+# How to bump packages that depend on changed packages
+dependent_bump = "patch"
+
+[changelog]
+# Generate per-crate changelogs (vs single root changelog)
+format = "per-crate"
+
+# Fixed groups: all always share the same version
+# reth binaries share version
+[[fixed]]
+members = ["reth"]
+
+# Packages to ignore (internal/test-only crates)
+ignore = [
+    "reth-testing-utils",
+    "reth-bench",
+]

.changelog/cute-bears-paint.md

@@ -0,0 +1,17 @@
+---
+reth: minor
+reth-cli-commands: minor
+reth-e2e-test-utils: minor
+reth-ethereum-cli: minor
+reth-node-core: minor
+reth-optimism-bin: minor
+reth-optimism-cli: minor
+reth-prune: patch
+reth-stages: patch
+reth-storage-api: minor
+reth-storage-db-api: minor
+reth-storage-db-common: patch
+reth-storage-provider: patch
+---
+
+Introduced `--storage.v2` flag to control storage mode defaults, replacing the `edge` feature flag with `rocksdb` feature. The new flag enables v2 storage settings (static files + RocksDB routing) while individual `--static-files.*` and `--rocksdb.*` flags can still override defaults. Updated feature gates from `edge` to `rocksdb` across all affected crates.

.changelog/dry-ants-bow.md

@@ -0,0 +1,5 @@
+---
+reth: patch
+---
+
+Removed Windows platform support from the codebase, including the Windows cross-compilation Dockerfile, build targets in Cross.toml and Makefile, and Windows-specific options in the bug report template.

.changelog/dry-ducks-write.md

@@ -0,0 +1,5 @@
+---
+reth-network: minor
+---
+
+Added reason label to backed_off_peers metric. The metric now tracks backed off peers by reason (too_many_peers, graceful_close, connection_error) to improve observability.

.changelog/eager-mules-fold.md

@@ -0,0 +1,5 @@
+---
+reth-trie-sparse-parallel: patch
+---
+
+Fixed parallel sparse trie to skip revealing disconnected leaves by checking parent branch reachability before inserting leaf nodes.

.changelog/easy-clouds-meow.md

@@ -0,0 +1,5 @@
+---
+ef-tests: patch
+---
+
+Removed reth-stateless crate and stateless validation from ef-tests.

.changelog/evil-pigs-cry.md

@@ -0,0 +1,6 @@
+---
+reth-engine-tree: patch
+reth-trie-sparse-parallel: patch
+---
+
+Added tracing spans and debug logs to sparse trie operations for better observability during parallel state root computation.

.changelog/fair-winds-growl.md

@@ -0,0 +1,6 @@
+---
+reth-exex: patch
+reth-exex-types: patch
+---
+
+Added configurable backfill thresholds to ExEx notifications stream and added regression tests for state provider parity between pipeline and backfill execution paths.

.changelog/fast-fish-cry.md

@@ -0,0 +1,4 @@
+---
+---
+
+Added WebSocket subscription integration tests for eth_subscribe.

.changelog/fast-seals-play.md

@@ -0,0 +1,5 @@
+---
+reth-transaction-pool: minor
+---
+
+Added `consensus_ref` method to `PoolTransaction` trait for borrowing consensus transactions without cloning.

.changelog/fast-waves-smile.md

@@ -0,0 +1,4 @@
+---
+---
+
+Improved nightly Docker build failure Slack notification with more detailed formatting and context.

.changelog/gentle-moons-cry.md

@@ -0,0 +1,5 @@
+---
+reth-engine-tree: patch
+---
+
+Reordered cache size calculations in `ExecutionCache::new` to group related operations together.

.changelog/icy-lions-slide.md

@@ -0,0 +1,7 @@
+---
+reth: patch
+reth-cli-commands: patch
+reth-node-core: patch
+---
+
+Removed experimental ress protocol support for stateless Ethereum nodes.

.changelog/lazy-lakes-shout.md

@@ -0,0 +1,5 @@
+---
+reth-node-builder: patch
+---
+
+Removed biased select in engine service loop to allow fair scheduling of shutdown requests alongside event processing.

.changelog/lively-clams-drink.md

@@ -0,0 +1,5 @@
+---
+reth-transaction-pool: patch
+---
+
+Fixed swapped arguments in `blob_tx_priority` function calls, correcting the parameter order to match the function signature.

.changelog/lively-clouds-bake.md

@@ -0,0 +1,4 @@
+---
+---
+
+Improved documentation overview page with better structure and clarity.

.changelog/lively-deer-shout.md

@@ -0,0 +1,5 @@
+---
+reth: patch
+---
+
+Re-enabled changelog workflow to run automatically on pull requests.

.changelog/lively-foxes-play.md

@@ -0,0 +1,5 @@
+---
+reth-node-events: patch
+---
+
+Updated consensus engine log message to be more accurate about received updates.

.changelog/merry-koalas-nod.md

@@ -0,0 +1,6 @@
+---
+reth-rpc-eth-api: minor
+reth-rpc-server-types: minor
+---
+
+Added `eth_getStorageValues` RPC method for batch storage slot retrieval across multiple addresses.

.changelog/mild-foxes-bark.md

@@ -0,0 +1,6 @@
+---
+reth-chainspec: minor
+reth-network-peers: minor
+---
+
+Removed OP stack bootnodes from default chain configurations and network peers module.

.changelog/nice-trees-drink.md

@@ -0,0 +1,9 @@
+---
+reth-network-api: minor
+reth-network-types: minor
+reth-network: minor
+reth-node-core: minor
+reth: minor
+---
+
+Added optional ENR fork ID enforcement to filter out peers from incompatible networks during peer discovery, controlled by the `--enforce-enr-fork-id` CLI flag.

.changelog/nice-waves-bow.md

@@ -0,0 +1,5 @@
+---
+reth-primitives: patch
+---
+
+Moved feature-referenced dependencies from dev-dependencies to optional dependencies to ensure they are available when their corresponding features are enabled.

.changelog/old-dogs-shake.md

@@ -0,0 +1,5 @@
+---
+reth-transaction-pool: minor
+---
+
+Added `IntoIter: Send` bounds to `validate_transactions` and `validate_transactions_with_origin` in the `TransactionValidator` trait, avoiding unnecessary `Vec` collects. Simplified default `validate_transactions_with_origin` to delegate to `validate_transactions`.

.changelog/proud-wolves-spin.md

@@ -0,0 +1,5 @@
+---
+reth-storage-api: patch
+---
+
+Added `Arc` to `auto_impl` derive for storage-api traits to support automatic `Arc` wrapper implementations.

.changelog/quiet-foxes-dance.md

@@ -0,0 +1,6 @@
+---
+reth-static-file-types: patch
+reth-provider: patch
+---
+
+Move changeset offsets from segment header to external `.csoff` sidecar file for incremental writes and crash recovery.

.changelog/quiet-frogs-whisper.md

@@ -0,0 +1,5 @@
+---
+reth-provider: patch
+---
+
+Removed unused staging types from ProviderFactoryBuilder.

.changelog/shy-tigers-dry.md

@@ -0,0 +1,5 @@
+---
+reth: patch
+---
+
+Added automated changelog generation infrastructure using wevm/changelogs-rs with Claude Code integration. Configured per-crate changelog format with fixed version groups for reth binaries and exclusions for internal test utilities.

.changelog/swift-owls-fly.md

@@ -0,0 +1,5 @@
+---
+reth-trie-sparse: minor
+---
+
+Removed `SerialSparseTrie` from the workspace, consolidating on `ParallelSparseTrie` as the single sparse trie implementation in `reth-trie-sparse`.

.changelog/vain-lakes-cry.md

@@ -0,0 +1,5 @@
+---
+reth: patch
+---
+
+Updated Alloy dependencies from 1.5.2 to 1.6.1.

.changelog/vast-waves-fold.md

@@ -0,0 +1,4 @@
+---
+---
+
+Expanded CLI integration tests with subcommand help coverage, config TOML validation, genesis JSON validation, and send transaction round-trip test for dev mode.

.changelog/warm-foxes-glow.md

@@ -0,0 +1,5 @@
+---
+reth-network: minor
+---
+
+Added direction labels to `closed_sessions` and `pending_session_failures` metrics. Operators can now distinguish session closures and failures by direction (`active`, `incoming_pending`, `outgoing_pending` for closed sessions; `inbound`, `outbound` for pending session failures).

.changelog/warm-foxes-jump.md

@@ -0,0 +1,4 @@
+---
+---
+
+Moved Kurtosis CI failure notifications to the hive Slack channel.

.changelog/warm-geese-build.md

@@ -0,0 +1,7 @@
+---
+reth-rpc-api: minor
+reth-rpc-builder: patch
+reth-rpc: minor
+---
+
+Added `subscribeFinalizedChainNotifications` RPC endpoint that buffers committed chain notifications and emits them once a new finalized block is received.

.changelog/zesty-birds-smile.md

@@ -0,0 +1,6 @@
+---
+reth-trie: minor
+reth-trie-parallel: minor
+---
+
+Added `root_node` and `storage_root_node` methods to proof calculators for efficient root-only calculations. These methods directly return the root node without requiring dummy targets, replacing the previous workaround of passing fake targets to proof generation.

.config/zepter.yaml

@@ -12,7 +12,7 @@ workflows:
         # Check that `A` activates the features of `B`.
         "propagate-feature",
         # These are the features to check:
-        "--features=std,op,dev,asm-keccak,jemalloc,jemalloc-prof,tracy-allocator,tracy,serde-bincode-compat,serde,test-utils,arbitrary,bench,alloy-compat,min-error-logs,min-warn-logs,min-info-logs,min-debug-logs,min-trace-logs,otlp,otlp-logs,js-tracer,portable,keccak-cache-global,trie-debug",
+        "--features=std,op,dev,asm-keccak,jemalloc,jemalloc-prof,tracy-allocator,tracy,serde-bincode-compat,serde,test-utils,arbitrary,bench,alloy-compat,min-error-logs,min-warn-logs,min-info-logs,min-debug-logs,min-trace-logs,otlp,otlp-logs,js-tracer,portable,keccak-cache-global",
         # Do not try to add a new section to `[features]` of `A` only because `B` exposes that feature. There are edge-cases where this is still needed, but we can add them manually.
         "--left-side-feature-missing=ignore",
         # Ignore the case that `A` it outside of the workspace. Otherwise it will report errors in external dependencies that we have no influence on.

.github/CODEOWNERS

@@ -1,7 +1,7 @@
 *                           @gakonst
 crates/chain-state/         @fgimenez @mattsse
 crates/chainspec/           @Rjected @joshieDo @mattsse
-crates/cli/                 @mattsse @Rjected
+crates/cli/                 @mattsse
 crates/config/              @shekhirin @mattsse @Rjected 
 crates/consensus/           @mattsse @Rjected
 crates/e2e-test-utils/      @mattsse @Rjected @klkvr @fgimenez

.github/actionlint.yaml

@@ -5,4 +5,3 @@ self-hosted-runner:
     - depot-ubuntu-latest-4
     - depot-ubuntu-latest-8
     - depot-ubuntu-latest-16
-    - available

.github/scripts/bench-job-summary.js

@@ -1,106 +0,0 @@
-// Generates a rich GitHub Actions job summary for reth-bench results.
-//
-// Reads from environment:
-//   BENCH_WORK_DIR       – Directory containing summary.json
-//   BENCH_PR             – PR number (may be empty)
-//   BENCH_ACTOR          – GitHub user who triggered the bench
-//   BENCH_CORES          – CPU core limit (0 = all)
-//   BENCH_WARMUP_BLOCKS  – Number of warmup blocks
-//   BENCH_SAMPLY         – 'true' if samply profiling was enabled
-//   BENCH_ABBA           – 'true' if ABBA interleaved order was used
-//
-// Usage from actions/github-script:
-//   const jobSummary = require('./.github/scripts/bench-job-summary.js');
-//   await jobSummary({ core, context, chartSha, grafanaUrl, runId });
-
-const fs = require('fs');
-const { verdict, loadSamplyUrls, blocksLabel, metricRows, waitTimeRows } = require('./bench-utils');
-
-module.exports = async function ({ core, context, chartSha, grafanaUrl, runId }) {
-  let summary;
-  try {
-    summary = JSON.parse(fs.readFileSync(process.env.BENCH_WORK_DIR + '/summary.json', 'utf8'));
-  } catch (e) {
-    await core.summary.addRaw('⚠️ Benchmark completed but failed to load summary.').write();
-    return;
-  }
-
-  const repo = `${context.repo.owner}/${context.repo.repo}`;
-  const prNumber = process.env.BENCH_PR;
-  const actor = process.env.BENCH_ACTOR;
-  const commitUrl = `https://github.com/${repo}/commit`;
-
-  const { emoji, label } = verdict(summary.changes);
-  const baselineLink = `[\`${summary.baseline.name}\`](${commitUrl}/${summary.baseline.ref})`;
-  const featureLink = `[\`${summary.feature.name}\`](${commitUrl}/${summary.feature.ref})`;
-  const diffUrl = `https://github.com/${repo}/compare/${summary.baseline.ref}...${summary.feature.ref}`;
-
-  // Header & metadata
-  const metaParts = [];
-  if (prNumber) metaParts.push(`**[PR #${prNumber}](https://github.com/${repo}/pull/${prNumber})**`);
-  metaParts.push(`triggered by @${actor}`);
-
-  let md = `# ${emoji} ${label}\n\n`;
-  md += metaParts.join(' · ') + '\n\n';
-  md += `**Baseline:** ${baselineLink}\n`;
-  md += `**Feature:** ${featureLink} ([diff](${diffUrl}))\n`;
-  md += blocksLabel(summary).map(p => `**${p.key}:** ${p.value}`).join(' · ') + '\n\n';
-
-  // Main comparison table
-  const rows = metricRows(summary);
-  md += `| Metric | Baseline | Feature | Change |\n`;
-  md += `|--------|----------|---------|--------|\n`;
-  for (const r of rows) {
-    md += `| ${r.label} | ${r.baseline} | ${r.feature} | ${r.change} |\n`;
-  }
-  md += '\n';
-
-  // Wait time breakdown
-  const wtRows = waitTimeRows(summary);
-  if (wtRows.length > 0) {
-    md += `### Wait Time Breakdown\n\n`;
-    md += `| Metric | Baseline | Feature |\n`;
-    md += `|--------|----------|--------|\n`;
-    for (const r of wtRows) {
-      md += `| ${r.title} | ${r.baseline} | ${r.feature} |\n`;
-    }
-    md += '\n';
-  }
-
-  // Charts
-  if (chartSha) {
-    const prNum = prNumber || '0';
-    const baseUrl = `https://raw.githubusercontent.com/decofe/reth-bench-charts/${chartSha}/pr/${prNum}/${runId}`;
-    const charts = [
-      { file: 'latency_throughput.png', label: 'Latency, Throughput & Diff' },
-      { file: 'wait_breakdown.png', label: 'Wait Time Breakdown' },
-      { file: 'gas_vs_latency.png', label: 'Gas vs Latency' },
-    ];
-    md += `### Charts\n\n`;
-    for (const chart of charts) {
-      md += `<details><summary>${chart.label}</summary>\n\n`;
-      md += `![${chart.label}](${baseUrl}/${chart.file})\n\n`;
-      md += `</details>\n\n`;
-    }
-  }
-
-  // Samply profiles
-  const samplyUrls = loadSamplyUrls(process.env.BENCH_WORK_DIR);
-  const samplyLinks = Object.entries(samplyUrls).map(([run, url]) => `- **${run}**: [Firefox Profiler](${url})`);
-  if (samplyLinks.length > 0) {
-    md += `### Samply Profiles\n\n${samplyLinks.join('\n')}\n\n`;
-  }
-
-  // Grafana
-  if (grafanaUrl) {
-    md += `### Grafana Dashboard\n\n[View real-time metrics](${grafanaUrl})\n\n`;
-  }
-
-  // Node errors
-  try {
-    const errors = fs.readFileSync(process.env.BENCH_WORK_DIR + '/errors.md', 'utf8');
-    if (errors.trim()) md += '\n' + errors + '\n';
-  } catch {}
-
-  await core.summary.addRaw(md).write();
-};

.github/scripts/bench-metrics-proxy.py

@@ -1,276 +0,0 @@
-#!/usr/bin/env python3
-"""
-Prometheus metrics proxy that fetches from a local reth node and
-re-exposes with additional benchmark labels.
-
-Reads labels from a JSON file (updated by local-reth-bench.sh between runs)
-and injects them into every Prometheus metric line.
-
-Returns empty 200 when reth is not running (clean Grafana gaps).
-"""
-import argparse
-import ipaddress
-import json
-import subprocess
-import sys
-import time
-from http.server import HTTPServer, BaseHTTPRequestHandler
-from urllib.request import urlopen
-from urllib.error import URLError
-
-
-def read_labels(path):
-    try:
-        with open(path) as f:
-            return json.load(f)
-    except (FileNotFoundError, json.JSONDecodeError):
-        return {}
-
-
-def inject_labels(metrics_bytes, label_str, label_names):
-    """Inject labels into Prometheus text format.
-
-    Operates on bytes and uses simple string ops instead of regex
-    for speed on large payloads (reth exposes thousands of metrics).
-
-    Skips injecting into lines that already contain any of the label names
-    to avoid duplicate labels (which Prometheus rejects).
-    """
-    if not label_str:
-        return metrics_bytes
-
-    label_bytes = label_str.encode("utf-8")
-    # Pre-encode label names for fast duplicate detection
-    label_name_bytes = [n.encode("utf-8") for n in label_names]
-    out = []
-    for line in metrics_bytes.split(b"\n"):
-        # Skip comments and blank lines
-        if line.startswith(b"#") or not line:
-            out.append(line)
-            continue
-
-        brace = line.find(b"{")
-        space = line.find(b" ")
-
-        if space == -1:
-            # Malformed, pass through
-            out.append(line)
-        elif brace != -1 and brace < space:
-            # Has labels: metric{existing="val"} 123
-            close = line.find(b"}", brace)
-            if close == -1:
-                out.append(line)
-                continue
-
-            # Filter out labels that already exist in this line
-            existing = line[brace + 1:close]
-            inject = label_bytes
-            if existing:
-                for name in label_name_bytes:
-                    if name + b"=" in existing:
-                        # Rebuild inject string excluding this label
-                        inject = _remove_label(inject, name)
-                if not inject:
-                    out.append(line)
-                    continue
-
-            if close == brace + 1:
-                # Empty braces: metric{} 123
-                out.append(line[:close] + inject + line[close:])
-            else:
-                out.append(line[:close] + b"," + inject + line[close:])
-        else:
-            # No labels: metric 123
-            out.append(line[:space] + b"{" + label_bytes + b"}" + line[space:])
-
-    return b"\n".join(out)
-
-
-def _remove_label(label_bytes, name):
-    """Remove a single label (name=\"...\") from a comma-separated label string."""
-    parts = []
-    for part in label_bytes.split(b","):
-        if not part.startswith(name + b"="):
-            parts.append(part)
-    return b",".join(parts)
-
-
-def build_label_str(labels):
-    """Pre-format the label injection string: key1="val1",key2="val2" """
-    if not labels:
-        return ""
-    return ",".join(f'{k}="{v}"' for k, v in sorted(labels.items()))
-
-
-def build_elapsed_gauge(labels):
-    """Build a bench_elapsed_seconds gauge from run_start_epoch in labels."""
-    start = labels.get("run_start_epoch")
-    if not start:
-        return b""
-    try:
-        elapsed = time.time() - float(start)
-    except (ValueError, TypeError):
-        return b""
-    # Build labels excluding internal keys
-    display = {k: v for k, v in labels.items()
-               if k not in ("run_start_epoch", "reference_epoch")}
-    lstr = build_label_str(display)
-    return (
-        f"# HELP bench_elapsed_seconds Seconds since benchmark run started\n"
-        f"# TYPE bench_elapsed_seconds gauge\n"
-        f"bench_elapsed_seconds{{{lstr}}} {elapsed:.1f}\n"
-    ).encode("utf-8")
-
-
-def compute_timestamp_ms(labels):
-    """Compute a synthetic timestamp so all runs share a common time origin.
-
-    Returns the timestamp in milliseconds, or None if not enough info.
-    Uses: reference_epoch + (now - run_start_epoch) → all runs overlay at
-    the same Grafana time range.
-    """
-    ref = labels.get("reference_epoch")
-    start = labels.get("run_start_epoch")
-    if not ref or not start:
-        return None
-    try:
-        elapsed = time.time() - float(start)
-        return int((float(ref) + elapsed) * 1000)
-    except (ValueError, TypeError):
-        return None
-
-
-def inject_timestamps(metrics_bytes, timestamp_ms):
-    """Append a Prometheus timestamp (ms) to every data line.
-
-    Prometheus text format: metric{labels} value [timestamp_ms]
-    Adding timestamps causes Prometheus to store all runs' samples
-    at the same relative time, enabling natural overlay in Grafana.
-    """
-    if timestamp_ms is None:
-        return metrics_bytes
-
-    ts = str(timestamp_ms).encode("utf-8")
-    out = []
-    for line in metrics_bytes.split(b"\n"):
-        if line.startswith(b"#") or not line:
-            out.append(line)
-        else:
-            out.append(line + b" " + ts)
-    return b"\n".join(out)
-
-
-class MetricsHandler(BaseHTTPRequestHandler):
-    # Use HTTP/1.1 so Content-Length is respected and Prometheus
-    # doesn't have to rely on connection close to detect end of body.
-    protocol_version = "HTTP/1.1"
-
-    def do_GET(self):
-        src = self.client_address[0]
-        try:
-            resp = urlopen(self.server.upstream, timeout=2)
-            metrics = resp.read()
-        except (URLError, ConnectionError, OSError):
-            # reth not running — return empty 200
-            self._send(b"")
-            #print(f"  scrape from {src}: empty (reth not running)", flush=True)
-            return
-
-        all_labels = read_labels(self.server.labels_file)
-        # Internal keys — not injected as Prometheus labels
-        internal = ("run_start_epoch", "reference_epoch")
-        labels = {k: v for k, v in all_labels.items() if k not in internal}
-        label_str = build_label_str(labels)
-        label_names = sorted(labels.keys())
-
-        t0 = time.monotonic()
-        result = inject_labels(metrics, label_str, label_names)
-        result += build_elapsed_gauge(all_labels)
-        ts_ms = compute_timestamp_ms(all_labels)
-        result = inject_timestamps(result, ts_ms)
-        dt = time.monotonic() - t0
-
-        self._send(result)
-        print(f"  scrape from {src}: {len(metrics)} -> {len(result)} bytes, "
-              f"inject {dt*1000:.1f}ms", flush=True)
-
-    def _send(self, body):
-        self.send_response(200)
-        self.send_header("Content-Type", "text/plain; version=0.0.4")
-        self.send_header("Content-Length", str(len(body)))
-        self.send_header("Connection", "close")
-        self.end_headers()
-        if body:
-            self.wfile.write(body)
-
-    def log_message(self, format, *args):
-        pass  # suppress per-request logging
-
-
-def resolve_bind_address(subnet_cidr):
-    """Find the local IP address that belongs to the given subnet.
-
-    Uses ``ip -j addr show`` to enumerate interfaces and returns the first
-    address that falls within *subnet_cidr* (e.g. ``10.10.0.0/24``).
-    """
-    network = ipaddress.ip_network(subnet_cidr, strict=False)
-    try:
-        result = subprocess.run(
-            ["ip", "-j", "addr", "show"],
-            capture_output=True, text=True, check=True,
-        )
-        interfaces = json.loads(result.stdout)
-    except (subprocess.CalledProcessError, FileNotFoundError, json.JSONDecodeError) as exc:
-        print(f"Error: cannot enumerate interfaces: {exc}", file=sys.stderr)
-        sys.exit(1)
-
-    for iface in interfaces:
-        for addr_info in iface.get("addr_info", []):
-            try:
-                addr = ipaddress.ip_address(addr_info["local"])
-            except (KeyError, ValueError):
-                continue
-            if addr in network:
-                return str(addr)
-
-    print(f"Error: no interface address found in subnet {subnet_cidr}", file=sys.stderr)
-    sys.exit(1)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Prometheus metrics proxy with label injection")
-    parser.add_argument("--labels", default="/tmp/bench-metrics-labels.json",
-                        help="Path to JSON file with labels to inject (default: /tmp/bench-metrics-labels.json)")
-    parser.add_argument("--upstream", default="http://127.0.0.1:9100/",
-                        help="Upstream reth metrics URL (default: http://127.0.0.1:9100/)")
-
-    bind_group = parser.add_mutually_exclusive_group()
-    bind_group.add_argument("--bind", default=None,
-                            help="Address to bind the proxy (default: 0.0.0.0)")
-    bind_group.add_argument("--subnet", default=None,
-                            help="Auto-detect bind address from a local interface in this subnet (e.g. 10.10.0.0/24)")
-
-    parser.add_argument("--port", type=int, default=9090,
-                        help="Port to bind the proxy (default: 9090)")
-    args = parser.parse_args()
-
-    if args.subnet:
-        bind_addr = resolve_bind_address(args.subnet)
-    elif args.bind:
-        bind_addr = args.bind
-    else:
-        bind_addr = "0.0.0.0"
-
-    server = HTTPServer((bind_addr, args.port), MetricsHandler)
-    server.upstream = args.upstream
-    server.labels_file = args.labels
-
-    print(f"bench-metrics-proxy listening on {bind_addr}:{args.port}")
-    print(f"  upstream: {args.upstream}")
-    print(f"  labels:   {args.labels}")
-    sys.stdout.flush()
-    server.serve_forever()
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/bench-reth-build.sh

@@ -1,76 +0,0 @@
-#!/usr/bin/env bash
-#
-# Builds reth binaries for benchmarking from local source only.
-#
-# Usage: bench-reth-build.sh <baseline|feature> <source-dir> <commit>
-#
-#   baseline — build the baseline binary at <commit> (merge-base)
-#              source-dir must be checked out at <commit>
-#   feature  — build the candidate binary + reth-bench at <commit>
-#              source-dir must be checked out at <commit>
-#
-# Outputs:
-#   baseline: <source-dir>/target/profiling/reth (or reth-bb if BENCH_BIG_BLOCKS=true)
-#   feature:  <source-dir>/target/profiling/reth (or reth-bb), reth-bench installed to cargo bin
-#
-# Optional env: BENCH_BIG_BLOCKS (true/false) — build reth-bb instead of reth
-set -euxo pipefail
-
-MODE="$1"
-SOURCE_DIR="$2"
-COMMIT="$3"
-
-BIG_BLOCKS="${BENCH_BIG_BLOCKS:-false}"
-# The node binary to build: reth-bb for big blocks, reth otherwise
-if [ "$BIG_BLOCKS" = "true" ]; then
-  NODE_BIN="reth-bb"
-  NODE_PKG="-p reth-bb"
-else
-  NODE_BIN="reth"
-  NODE_PKG="--bin reth"
-fi
-
-# Tracy support: when BENCH_TRACY is "on" or "full", add Tracy cargo features
-# and frame pointers for accurate stack traces.
-EXTRA_FEATURES=""
-EXTRA_RUSTFLAGS=""
-if [ "${BENCH_TRACY:-off}" != "off" ]; then
-  EXTRA_FEATURES="tracy,tracy-client/ondemand"
-  EXTRA_RUSTFLAGS=" -C force-frame-pointers=yes"
-fi
-
-# Build the requested node binary with the benchmark profile.
-build_node_binary() {
-  local features_arg=""
-  local workspace_arg=""
-
-  cd "$SOURCE_DIR"
-  if [ -n "$EXTRA_FEATURES" ]; then
-    # --workspace is needed for cross-package feature syntax (tracy-client/ondemand)
-    features_arg="--features ${EXTRA_FEATURES}"
-    workspace_arg="--workspace"
-  fi
-
-  # shellcheck disable=SC2086
-  RUSTFLAGS="-C target-cpu=native${EXTRA_RUSTFLAGS}" \
-    cargo build --locked --profile profiling $NODE_PKG $workspace_arg $features_arg
-}
-
-case "$MODE" in
-  baseline|main)
-    echo "Building baseline ${NODE_BIN} (${COMMIT}) from source..."
-    build_node_binary
-    ;;
-
-  feature|branch)
-    echo "Building feature ${NODE_BIN} (${COMMIT}) from source..."
-    rustup show active-toolchain || rustup default stable
-    build_node_binary
-    make -C "$SOURCE_DIR" install-reth-bench
-    ;;
-
-  *)
-    echo "Usage: $0 <baseline|feature> <source-dir> <commit>"
-    exit 1
-    ;;
-esac

.github/scripts/bench-reth-charts.py

@@ -1,260 +0,0 @@
-#!/usr/bin/env python3
-"""Generate benchmark charts from reth-bench CSV output.
-
-Usage:
-    bench-engine-charts.py <combined_csv> --output-dir <dir> [--baseline <baseline_csv>]
-
-Generates three PNG charts:
-  1. newPayload latency + Ggas/s per block (+ latency diff when baseline present)
-  2. Wait breakdown (persistence, execution cache, sparse trie) per block
-  3. Scatter plot of gas used vs latency
-
-When --baseline is provided, charts overlay both datasets for comparison.
-"""
-
-import argparse
-import csv
-import sys
-from pathlib import Path
-
-import numpy as np
-
-try:
-    import matplotlib
-
-    matplotlib.use("Agg")
-    import matplotlib.pyplot as plt
-except ImportError:
-    print("matplotlib is required: pip install matplotlib", file=sys.stderr)
-    sys.exit(1)
-
-GIGAGAS = 1_000_000_000
-
-
-def parse_combined_csv(path: str) -> list[dict]:
-    rows = []
-    with open(path) as f:
-        reader = csv.DictReader(f)
-        for row in reader:
-            rows.append(
-                {
-                    "block_number": int(row["block_number"]),
-                    "gas_used": int(row["gas_used"]),
-                    "new_payload_latency_us": int(row["new_payload_latency"]),
-                    "persistence_wait_us": int(row["persistence_wait"])
-                    if row.get("persistence_wait")
-                    else None,
-                    "execution_cache_wait_us": int(row.get("execution_cache_wait", 0)),
-                    "sparse_trie_wait_us": int(row.get("sparse_trie_wait", 0)),
-                }
-            )
-    return rows
-
-
-def plot_latency_and_throughput(
-    feature: list[dict], baseline: list[dict] | None, out: Path,
-    baseline_name: str = "baseline", feature_name: str = "feature",
-):
-    num_plots = 3 if baseline else 2
-    fig, axes = plt.subplots(num_plots, 1, figsize=(12, 4 * num_plots), sharex=True)
-    ax1, ax2 = axes[0], axes[1]
-
-    feat_x = [r["block_number"] for r in feature]
-    feat_lat = [r["new_payload_latency_us"] / 1_000 for r in feature]
-    feat_ggas = []
-    for r in feature:
-        lat_s = r["new_payload_latency_us"] / 1_000_000
-        feat_ggas.append(r["gas_used"] / lat_s / GIGAGAS if lat_s > 0 else 0)
-
-    if baseline:
-        base_x = [r["block_number"] for r in baseline]
-        base_lat = [r["new_payload_latency_us"] / 1_000 for r in baseline]
-        base_ggas = []
-        for r in baseline:
-            lat_s = r["new_payload_latency_us"] / 1_000_000
-            base_ggas.append(r["gas_used"] / lat_s / GIGAGAS if lat_s > 0 else 0)
-        l, = ax1.plot(base_x, base_lat, linewidth=0.8, label=baseline_name, alpha=0.7)
-        ax1.axhline(np.median(base_lat), color=l.get_color(), linestyle="--", linewidth=1, alpha=0.7, label=f"{baseline_name} median")
-        l, = ax2.plot(base_x, base_ggas, linewidth=0.8, label=baseline_name, alpha=0.7)
-        ax2.axhline(np.median(base_ggas), color=l.get_color(), linestyle="--", linewidth=1, alpha=0.7, label=f"{baseline_name} median")
-
-    l, = ax1.plot(feat_x, feat_lat, linewidth=0.8, label=feature_name)
-    ax1.axhline(np.median(feat_lat), color=l.get_color(), linestyle="--", linewidth=1, label=f"{feature_name} median")
-    ax1.set_ylabel("Latency (ms)")
-    ax1.set_title("newPayload Latency per Block")
-    ax1.grid(True, alpha=0.3)
-    ax1.legend()
-
-    l, = ax2.plot(feat_x, feat_ggas, linewidth=0.8, label=feature_name)
-    ax2.axhline(np.median(feat_ggas), color=l.get_color(), linestyle="--", linewidth=1, label=f"{feature_name} median")
-    ax2.set_ylabel("Ggas/s")
-    ax2.set_title("Execution Throughput per Block")
-    ax2.grid(True, alpha=0.3)
-    ax2.legend()
-
-    if baseline:
-        ax3 = axes[2]
-        base_by_block = {r["block_number"]: r["new_payload_latency_us"] for r in baseline}
-        blocks, diffs = [], []
-        for r in feature:
-            bn = r["block_number"]
-            if bn in base_by_block and base_by_block[bn] > 0:
-                pct = (r["new_payload_latency_us"] - base_by_block[bn]) / base_by_block[bn] * 100
-                blocks.append(bn)
-                diffs.append(pct)
-        if blocks:
-            colors = ["green" if d <= 0 else "red" for d in diffs]
-            ax3.bar(blocks, diffs, width=1.0, color=colors, alpha=0.7, edgecolor="none")
-            ax3.axhline(0, color="black", linewidth=0.5)
-        ax3.set_ylabel("Δ Latency (%)")
-        ax3.set_title("Per-Block newPayload Latency Change (feature vs baseline)")
-        ax3.grid(True, alpha=0.3, axis="y")
-
-    axes[-1].set_xlabel("Block Number")
-    fig.tight_layout()
-    fig.savefig(out, dpi=150)
-    plt.close(fig)
-
-
-def plot_wait_breakdown(
-    feature: list[dict], baseline: list[dict] | None, out: Path,
-    baseline_name: str = "baseline", feature_name: str = "feature",
-):
-    series = [
-        ("Persistence Wait", "persistence_wait_us"),
-        ("State Cache Wait", "execution_cache_wait_us"),
-        ("Trie Cache Wait", "sparse_trie_wait_us"),
-    ]
-
-    fig, axes = plt.subplots(len(series), 1, figsize=(12, 3 * len(series)), sharex=True)
-    for ax, (label, key) in zip(axes, series):
-        if baseline:
-            bx = [r["block_number"] for r in baseline if r[key] is not None]
-            by = [r[key] / 1_000 for r in baseline if r[key] is not None]
-            if bx:
-                ax.plot(bx, by, linewidth=0.8, label=baseline_name, alpha=0.7)
-
-        fx = [r["block_number"] for r in feature if r[key] is not None]
-        fy = [r[key] / 1_000 for r in feature if r[key] is not None]
-        if fx:
-            ax.plot(fx, fy, linewidth=0.8, label=feature_name)
-
-        ax.set_ylabel("ms")
-        ax.set_title(label)
-        ax.grid(True, alpha=0.3)
-        if baseline:
-            ax.legend()
-
-    axes[-1].set_xlabel("Block Number")
-    fig.suptitle("Wait Time Breakdown per Block", fontsize=14, y=1.01)
-    fig.tight_layout()
-    fig.savefig(out, dpi=150, bbox_inches="tight")
-    plt.close(fig)
-
-
-def _add_regression(ax, x, y, color, label):
-    """Add a linear regression line to the axes."""
-    if len(x) < 2:
-        return
-    xa, ya = np.array(x), np.array(y)
-    m, b = np.polyfit(xa, ya, 1)
-    x_range = np.linspace(xa.min(), xa.max(), 100)
-    ax.plot(x_range, m * x_range + b, color=color, linewidth=1.5, alpha=0.8,
-            label=label)
-
-
-def plot_gas_vs_latency(
-    feature: list[dict], baseline: list[dict] | None, out: Path,
-    baseline_name: str = "baseline", feature_name: str = "feature",
-):
-    fig, ax = plt.subplots(figsize=(8, 6))
-
-    if baseline:
-        bgas = [r["gas_used"] / 1_000_000 for r in baseline]
-        blat = [r["new_payload_latency_us"] / 1_000 for r in baseline]
-        ax.scatter(bgas, blat, s=8, alpha=0.5)
-        _add_regression(ax, bgas, blat, "tab:blue", baseline_name)
-
-    fgas = [r["gas_used"] / 1_000_000 for r in feature]
-    flat = [r["new_payload_latency_us"] / 1_000 for r in feature]
-    ax.scatter(fgas, flat, s=8, alpha=0.6)
-    _add_regression(ax, fgas, flat, "tab:orange", feature_name)
-
-    ax.set_xlabel("Gas Used (Mgas)")
-    ax.set_ylabel("newPayload Latency (ms)")
-    ax.set_title("Gas Used vs Latency")
-    ax.grid(True, alpha=0.3)
-    ax.legend()
-    fig.tight_layout()
-    fig.savefig(out, dpi=150)
-    plt.close(fig)
-
-
-def merge_csvs(paths: list[str]) -> list[dict]:
-    """Parse and merge multiple CSVs, averaging values for duplicate blocks."""
-    by_block: dict[int, list[dict]] = {}
-    for path in paths:
-        for row in parse_combined_csv(path):
-            by_block.setdefault(row["block_number"], []).append(row)
-
-    merged = []
-    for bn in sorted(by_block):
-        rows = by_block[bn]
-        if len(rows) == 1:
-            merged.append(rows[0])
-        else:
-            avg = {"block_number": bn}
-            for key in ("gas_used", "new_payload_latency_us"):
-                avg[key] = int(sum(r[key] for r in rows) / len(rows))
-            for key in ("persistence_wait_us", "execution_cache_wait_us", "sparse_trie_wait_us"):
-                vals = [r[key] for r in rows if r[key] is not None]
-                avg[key] = int(sum(vals) / len(vals)) if vals else None
-            merged.append(avg)
-    return merged
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Generate benchmark charts")
-    parser.add_argument(
-        "--feature", nargs="+", required=True,
-        help="Path(s) to feature combined_latency.csv",
-    )
-    parser.add_argument(
-        "--output-dir", required=True, help="Output directory for PNG charts"
-    )
-    parser.add_argument(
-        "--baseline", nargs="+", help="Path(s) to baseline combined_latency.csv"
-    )
-    parser.add_argument("--baseline-name", default="baseline", help="Label for baseline")
-    parser.add_argument("--feature-name", "--branch-name", default="feature", help="Label for feature")
-    args = parser.parse_args()
-
-    feature = merge_csvs(args.feature)
-    if not feature:
-        print("No results found in feature CSV(s)", file=sys.stderr)
-        sys.exit(1)
-
-    baseline = None
-    if args.baseline:
-        baseline = merge_csvs(args.baseline)
-        if not baseline:
-            print(
-                "Warning: no results in baseline CSV(s), skipping comparison",
-                file=sys.stderr,
-            )
-            baseline = None
-
-    out_dir = Path(args.output_dir)
-    out_dir.mkdir(parents=True, exist_ok=True)
-
-    bname = args.baseline_name
-    fname = args.feature_name
-    plot_latency_and_throughput(feature, baseline, out_dir / "latency_throughput.png", bname, fname)
-    plot_wait_breakdown(feature, baseline, out_dir / "wait_breakdown.png", bname, fname)
-    plot_gas_vs_latency(feature, baseline, out_dir / "gas_vs_latency.png", bname, fname)
-
-    print(f"Charts written to {out_dir}")
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/bench-reth-local.sh

@@ -1,567 +0,0 @@
-#!/usr/bin/env bash
-#
-# local-reth-bench.sh — Run the reth Engine API benchmark locally.
-#
-# Replicates the CI bench.yml workflow (build, local snapshot validation, system tuning,
-# interleaved B-F-F-B execution, summary, charts) without any GitHub
-# Actions glue (no PR comments, no artifact upload, no Slack).
-#
-# Usage:
-#   local-reth-bench.sh <baseline-ref> <feature-ref> [options]
-#
-# Options:
-#   --blocks N      Number of blocks to benchmark (default: 500)
-#   --warmup N      Number of warmup blocks (default: 100)
-#   --cores N       Limit reth to N CPU cores, 0 = all available (default: 0)
-#   --samply        Enable samply profiling
-#   --tracy MODE    Tracy profiling: off, on, full (default: off)
-#   --tracy-filter F Tracy tracing filter (default: debug)
-#   --no-tune       Skip system tuning (useful on dev machines / macOS)
-#
-# Requires: the reth repo at RETH_REPO (default: ~/reth)
-#
-# Dependencies (install before first run):
-#   schelk, cpupower, taskset, stdbuf, python3, curl,
-#   make, uv, jq, Rust toolchain (cargo/rustup)
-# Optional:
-#   mc for Tracy profile upload
-#
-# The script delegates to the existing bench-reth-*.sh scripts in the reth
-# repo for the actual build, snapshot, and run steps.
-set -euxo pipefail
-
-# ── PATH ──────────────────────────────────────────────────────────────
-# Ensure cargo and user-local bins (uv) are visible
-export PATH="$HOME/.local/bin:$HOME/.cargo/bin:$PATH"
-
-# ── Defaults ──────────────────────────────────────────────────────────
-RETH_REPO="${RETH_REPO:-$HOME/reth}"
-BLOCKS=500
-WARMUP=100
-CORES=0
-SAMPLY=false
-TRACY="off"
-TRACY_FILTER="debug"
-TUNE=true
-BASELINE_REF=""
-FEATURE_REF=""
-
-# ── Parse arguments ──────────────────────────────────────────────────
-usage() {
-  cat <<EOF
-Usage: $(basename "$0") <baseline-ref> <feature-ref> [options]
-
-Options:
-  --blocks N         Number of blocks to benchmark (default: 500)
-  --warmup N         Number of warmup blocks (default: 100)
-  --cores N          Limit reth to N CPU cores (default: 0 = all)
-  --samply           Enable samply profiling
-  --tracy MODE       Tracy profiling: off, on, full (default: off)
-                       on   = tracing only (lower overhead)
-                       full = tracing + CPU sampling (higher overhead)
-  --tracy-filter F   Tracy tracing filter (default: debug)
-  --no-tune          Skip system tuning
-EOF
-  exit 1
-}
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --blocks)       BLOCKS="$2"; shift 2 ;;
-    --warmup)       WARMUP="$2"; shift 2 ;;
-    --cores)        CORES="$2"; shift 2 ;;
-    --samply)       SAMPLY=true; shift ;;
-    --tracy)        TRACY="$2"; shift 2 ;;
-    --tracy-filter) TRACY_FILTER="$2"; shift 2 ;;
-    --no-tune)      TUNE=false; shift ;;
-    --help|-h)  usage ;;
-    -*)         echo "Unknown option: $1"; usage ;;
-    *)
-      if [ -z "$BASELINE_REF" ]; then
-        BASELINE_REF="$1"
-      elif [ -z "$FEATURE_REF" ]; then
-        FEATURE_REF="$1"
-      else
-        echo "Unexpected argument: $1"; usage
-      fi
-      shift
-      ;;
-  esac
-done
-
-if [ -z "$BASELINE_REF" ] || [ -z "$FEATURE_REF" ]; then
-  echo "Error: both <baseline-ref> and <feature-ref> are required."
-  usage
-fi
-
-# Validate --tracy value
-case "$TRACY" in
-  off|on|full) ;;
-  *) echo "Error: --tracy must be off, on, or full (got: $TRACY)"; usage ;;
-esac
-
-# Samply + tracy=full are mutually exclusive (both use perf sampling)
-if [ "$SAMPLY" = "true" ] && [ "$TRACY" = "full" ]; then
-  echo "Warning: samply and tracy=full both use perf sampling; downgrading tracy to 'on'."
-  TRACY="on"
-fi
-
-# ── Check dependencies ───────────────────────────────────────────────
-missing=()
-for cmd in schelk cpupower taskset stdbuf python3 curl make uv jq cargo; do
-  command -v "$cmd" &>/dev/null || missing+=("$cmd")
-done
-if [ ${#missing[@]} -gt 0 ]; then
-  echo "Error: missing required tools: ${missing[*]}"
-  echo "See the CI 'Install dependencies' step in .github/workflows/bench.yml for install instructions."
-  exit 1
-fi
-
-if [ "$TRACY" != "off" ]; then
-  if ! command -v tracy-capture &>/dev/null; then
-    echo "Error: tracy-capture is required for --tracy $TRACY"
-    exit 1
-  fi
-fi
-
-# Ensure tools that run via sudo are in a sudo-visible path.
-# The bench scripts use `sudo schelk` / `sudo samply` but cargo installs
-# them to ~/.cargo/bin which sudo's secure_path doesn't include.
-for cmd in schelk samply; do
-  if command -v "$cmd" &>/dev/null && ! sudo sh -c "command -v $cmd" &>/dev/null; then
-    echo "Installing $cmd to /usr/local/bin (needed for sudo)..."
-    sudo install "$(command -v "$cmd")" /usr/local/bin/
-  fi
-done
-
-if [ ! -d "$RETH_REPO/.git" ]; then
-  echo "Error: RETH_REPO=$RETH_REPO is not a git repository."
-  echo "Set RETH_REPO or clone reth to ~/reth"
-  exit 1
-fi
-
-# ── Resolve paths ────────────────────────────────────────────────────
-SELF_DIR="$(cd "$(dirname "$0")" && pwd)"
-SCRIPTS_DIR="${RETH_REPO}/.github/scripts"
-BENCH_WORK_DIR="${RETH_REPO}/../bench-work-$(date +%Y%m%d-%H%M%S)"
-BASELINE_SRC="${RETH_REPO}/../reth-baseline"
-FEATURE_SRC="${RETH_REPO}/../reth-feature"
-
-mkdir -p "$BENCH_WORK_DIR"
-BENCH_WORK_DIR="$(cd "$BENCH_WORK_DIR" && pwd)"
-
-# ── Global cleanup trap (restores system tuning on any exit) ─────────
-TUNING_APPLIED=false
-CSTATE_PID=
-METRICS_PROXY_PID=
-cleanup_global() {
-  [ -n "$METRICS_PROXY_PID" ] && kill "$METRICS_PROXY_PID" 2>/dev/null || true
-  if [ "$TUNING_APPLIED" = true ]; then
-    echo
-    echo "▸ Restoring system settings..."
-    [ -n "$CSTATE_PID" ] && kill "$CSTATE_PID" 2>/dev/null || true
-    sudo systemctl start irqbalance cron atd 2>/dev/null || true
-    echo "  System settings restored."
-  fi
-}
-trap cleanup_global EXIT
-
-echo "═══════════════════════════════════════════════════════════"
-echo "  reth local benchmark"
-echo "═══════════════════════════════════════════════════════════"
-echo "  Baseline ref : $BASELINE_REF"
-echo "  Feature ref  : $FEATURE_REF"
-echo "  Blocks       : $BLOCKS"
-echo "  Warmup       : $WARMUP"
-echo "  Cores        : $CORES"
-echo "  Samply       : $SAMPLY"
-echo "  Tracy        : $TRACY"
-echo "  Tracy filter : $TRACY_FILTER"
-echo "  System tune  : $TUNE"
-echo "  Work dir     : $BENCH_WORK_DIR"
-echo "  Reth repo    : $RETH_REPO"
-echo "═══════════════════════════════════════════════════════════"
-echo
-
-# Enable sccache if available (matches CI's RUSTC_WRAPPER=sccache)
-if command -v sccache &>/dev/null; then
-  export RUSTC_WRAPPER="sccache"
-fi
-
-# Export env vars expected by the bench-reth-*.sh scripts
-export BENCH_BLOCKS="$BLOCKS"
-export BENCH_WARMUP_BLOCKS="$WARMUP"
-export BENCH_CORES="$CORES"
-export BENCH_SAMPLY="$SAMPLY"
-export BENCH_TRACY="$TRACY"
-export BENCH_TRACY_FILTER="$TRACY_FILTER"
-export BENCH_WORK_DIR
-export SCHELK_MOUNT="${SCHELK_MOUNT:-/reth-bench}"
-export BENCH_RPC_URL="${BENCH_RPC_URL:-https://ethereum.reth.rs/rpc}"
-export BENCH_METRICS_ADDR="127.0.0.1:9100"
-
-# ── Step 1: Resolve refs to full SHAs ────────────────────────────────
-echo "▸ Resolving git refs..."
-cd "$RETH_REPO"
-
-resolve_ref() {
-  local ref="$1"
-  git fetch origin "$ref" --quiet 2>/dev/null || true
-  git rev-parse "$ref" 2>/dev/null \
-    || git rev-parse "origin/$ref" 2>/dev/null \
-    || { echo "Error: cannot resolve ref '$ref'"; exit 1; }
-}
-
-BASELINE_SHA="$(resolve_ref "$BASELINE_REF")"
-FEATURE_SHA="$(resolve_ref "$FEATURE_REF")"
-echo "  Baseline SHA : $BASELINE_SHA"
-echo "  Feature SHA  : $FEATURE_SHA"
-echo
-
-# ── Step 2: Prepare source directories ───────────────────────────────
-echo "▸ Preparing source directories..."
-
-prepare_source() {
-  local src_dir="$1" ref="$2"
-  if [ -d "$src_dir" ]; then
-    git -C "$src_dir" fetch origin "$ref" 2>/dev/null || true
-  else
-    git clone --recurse-submodules "$RETH_REPO" "$src_dir"
-  fi
-  git -C "$src_dir" checkout "$ref" --force
-  git -C "$src_dir" submodule update --init --recursive
-}
-
-prepare_source "$BASELINE_SRC" "$BASELINE_SHA"
-prepare_source "$FEATURE_SRC" "$FEATURE_SHA"
-BASELINE_SRC="$(cd "$BASELINE_SRC" && pwd)"
-FEATURE_SRC="$(cd "$FEATURE_SRC" && pwd)"
-echo "  Baseline src : $BASELINE_SRC"
-echo "  Feature src  : $FEATURE_SRC"
-echo
-
-# ── Step 3: Validate local snapshot ──────────────────────────────────
-echo "▸ Validating local snapshot..."
-cd "$RETH_REPO"
-"${SCRIPTS_DIR}/bench-reth-snapshot.sh"
-echo "  Snapshot is ready."
-echo
-
-# ── Step 4: Build binaries in parallel ───────────────────────────────
-echo "▸ Building binaries (parallel)..."
-cd "$RETH_REPO"
-
-FAIL=0
-
-"${SCRIPTS_DIR}/bench-reth-build.sh" baseline "$BASELINE_SRC" "$BASELINE_SHA" &
-PID_BASELINE=$!
-
-"${SCRIPTS_DIR}/bench-reth-build.sh" feature "$FEATURE_SRC" "$FEATURE_SHA" &
-PID_FEATURE=$!
-
-wait $PID_BASELINE || FAIL=1
-wait $PID_FEATURE  || FAIL=1
-
-if [ $FAIL -ne 0 ]; then
-  echo "Error: one or more build tasks failed"
-  exit 1
-fi
-echo "  Binaries built successfully."
-echo
-
-# ── Step 5: System tuning (optional) ────────────────────────────────
-if [ "$TUNE" = "true" ]; then
-  echo "▸ Applying system tuning..."
-
-  sudo cpupower frequency-set -g performance 2>/dev/null || true
-
-  # Disable turbo boost (Intel + AMD)
-  echo 1 | sudo tee /sys/devices/system/cpu/intel_pstate/no_turbo 2>/dev/null || true
-  echo 0 | sudo tee /sys/devices/system/cpu/cpufreq/boost 2>/dev/null || true
-
-  sudo swapoff -a 2>/dev/null || true
-  echo 0 | sudo tee /proc/sys/kernel/randomize_va_space 2>/dev/null || true
-
-  # Disable SMT (hyperthreading)
-  for cpu in /sys/devices/system/cpu/cpu*/topology/thread_siblings_list; do
-    [ -f "$cpu" ] || continue
-    first=$(cut -d, -f1 < "$cpu" | cut -d- -f1)
-    current=$(echo "$cpu" | grep -o 'cpu[0-9]*' | grep -o '[0-9]*')
-    if [ "$current" != "$first" ]; then
-      echo 0 | sudo tee "/sys/devices/system/cpu/cpu${current}/online" 2>/dev/null || true
-    fi
-  done
-  echo "  Online CPUs: $(nproc)"
-
-  # Disable transparent huge pages
-  for p in /sys/kernel/mm/transparent_hugepage /sys/kernel/mm/transparent_hugepages; do
-    if [ -d "$p" ]; then
-      echo never | sudo tee "$p/enabled" 2>/dev/null || true
-      echo never | sudo tee "$p/defrag" 2>/dev/null || true
-      break
-    fi
-  done
-
-  # Prevent deep C-states
-  sudo sh -c 'exec 3<>/dev/cpu_dma_latency; echo -ne "\x00\x00\x00\x00" >&3; sleep infinity' &
-  CSTATE_PID=$!
-
-  # Pin IRQs to core 0
-  for irq in /proc/irq/*/smp_affinity_list; do
-    echo 0 | sudo tee "$irq" 2>/dev/null || true
-  done
-
-  # Stop noisy background services
-  sudo systemctl stop irqbalance cron atd unattended-upgrades snapd 2>/dev/null || true
-
-  TUNING_APPLIED=true
-
-  # Log environment for reproducibility (matches CI)
-  echo "  === Benchmark environment ==="
-  echo "  Kernel : $(uname -r)"
-  lscpu | grep -E 'Model name|CPU\(s\)|MHz|NUMA' | sed 's/^/  /'
-  echo "  Governor : $(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 2>/dev/null || echo unknown)"
-  echo "  Freq     : $(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq 2>/dev/null || echo unknown)"
-  echo "  THP      : $(cat /sys/kernel/mm/transparent_hugepage/enabled 2>/dev/null || cat /sys/kernel/mm/transparent_hugepages/enabled 2>/dev/null || echo unknown)"
-  free -h | sed 's/^/  /'
-  echo "  System tuning applied."
-  echo
-fi
-
-# ── Step 5b: Tracefs mount (tracy=full only) ─────────────────────────
-if [ "$TRACY" = "full" ] && [ "$(uname)" = "Linux" ]; then
-  echo "▸ Mounting tracefs for Tracy full mode..."
-  sudo mount -t tracefs tracefs /sys/kernel/tracing -o mode=755 2>/dev/null || true
-fi
-
-# ── Tracy upload & viewer helpers ────────────────────────────────────
-TRACY_VIEWER_BASE="${TRACY_VIEWER_BASE:-}"
-
-tracy_viewer_url() {
-  local profile_url="$1"
-  if [ -z "$TRACY_VIEWER_BASE" ]; then
-    echo ""
-    return
-  fi
-  local encoded
-  encoded=$(python3 -c "import urllib.parse, sys; print(urllib.parse.quote(sys.argv[1], safe=''))" "$profile_url")
-  echo "${TRACY_VIEWER_BASE}?profile_url=${encoded}"
-}
-
-upload_tracy() {
-  local label="$1" output_dir="$2" sha="$3"
-  local tracy_file="$output_dir/tracy-profile.tracy"
-
-  if [ ! -f "$tracy_file" ]; then
-    echo "  Tracy: no profile found, skipping upload."
-    return
-  fi
-
-  local timestamp short_sha remote_name bucket mc_alias
-  timestamp=$(date +%Y%m%d-%H%M%S)
-  short_sha="${sha:0:7}"
-  remote_name="${label}-${short_sha}-${timestamp}.tracy"
-  bucket="${TRACY_BUCKET:-tracy-profiles}"
-  mc_alias="${MC_ALIAS:-minio}"
-  local minio_base="${TRACY_MINIO_URL:-http://minio.minio.svc.cluster.local:9000}"
-
-  echo "  Tracy: uploading profile..."
-  if mc cp "$tracy_file" "${mc_alias}/${bucket}/${remote_name}"; then
-    local url="${minio_base}/${bucket}/${remote_name}"
-    echo "$url" > "$output_dir/tracy_url.txt"
-    local viewer
-    viewer=$(tracy_viewer_url "$url")
-    if [ -n "$viewer" ]; then
-      echo "$viewer" > "$output_dir/tracy_viewer_url.txt"
-      echo "  Tracy: uploaded → $viewer"
-    else
-      echo "  Tracy: uploaded → $url"
-    fi
-  else
-    echo "  Tracy: upload failed (non-fatal)."
-  fi
-
-  # Delete large profile to free disk
-  rm -f "$tracy_file"
-}
-
-# ── Step 6: Pre-flight cleanup ───────────────────────────────────────
-echo "▸ Pre-flight cleanup..."
-pkill -f bench-metrics-proxy 2>/dev/null || true
-sudo systemctl stop "${RETH_SCOPE:-reth-bench.scope}" 2>/dev/null || true
-sudo systemctl reset-failed "${RETH_SCOPE:-reth-bench.scope}" 2>/dev/null || true
-sudo schelk recover -y --kill || sudo schelk full-recover -y || true
-echo
-
-# ── Step 7: Interleaved benchmark runs (B-F-F-B) ────────────────────
-# This ordering reduces systematic bias from thermal drift and cache warming.
-BASELINE_BIN="${BASELINE_SRC}/target/profiling/reth"
-FEATURE_BIN="${FEATURE_SRC}/target/profiling/reth"
-
-# Start metrics proxy (reth → label injection → Prometheus)
-LABELS_FILE="/tmp/bench-metrics-labels.json"
-echo '{}' > "$LABELS_FILE"
-METRICS_SUBNET="${METRICS_SUBNET:-10.10.0.0/24}"
-METRICS_PORT="${METRICS_PORT:-9090}"
-python3 "${SELF_DIR}/bench-metrics-proxy.py" \
-  --labels "$LABELS_FILE" \
-  --upstream "http://${BENCH_METRICS_ADDR}/" \
-  --subnet "$METRICS_SUBNET" \
-  --port "$METRICS_PORT" &
-METRICS_PROXY_PID=$!
-echo "▸ Metrics proxy started (PID $METRICS_PROXY_PID) on subnet ${METRICS_SUBNET}, port ${METRICS_PORT}"
-
-# Unique benchmark ID: local-<timestamp> for local runs, ci-<run_id> for CI
-BENCH_ID="local-$(basename "$BENCH_WORK_DIR" | sed 's/bench-work-//')"
-# Reference epoch: shared time origin so all runs overlay in Grafana.
-# The proxy maps each run's elapsed time onto this common origin.
-BENCH_REFERENCE_EPOCH=$(date +%s)
-
-write_labels() {
-  local run_label="$1" run_type="$2" ref="$3" sha="$4"
-  LAST_RUN_START=$(date +%s)
-  cat > "$LABELS_FILE" <<-EOF
-	{"benchmark_run":"${run_label}","run_type":"${run_type}","git_ref":"${ref}","bench_sha":"${sha}","benchmark_id":"${BENCH_ID}","run_start_epoch":"${LAST_RUN_START}","reference_epoch":"${BENCH_REFERENCE_EPOCH}"}
-	EOF
-}
-
-run_bench() {
-  local label="$1" binary="$2" output_dir="$3"
-  echo "▸ Running benchmark: ${label}..."
-  cd "$RETH_REPO"
-  if command -v taskset &>/dev/null; then
-    taskset -c 0 "${SCRIPTS_DIR}/bench-reth-run.sh" "$label" "$binary" "$output_dir"
-  else
-    "${SCRIPTS_DIR}/bench-reth-run.sh" "$label" "$binary" "$output_dir"
-  fi
-  echo "  ✓ ${label} complete."
-  echo
-}
-
-write_labels "baseline-1" "baseline" "$BASELINE_REF" "$BASELINE_SHA"
-run_bench "baseline-1" "$BASELINE_BIN" "$BENCH_WORK_DIR/baseline-1"
-
-write_labels "feature-1" "feature" "$FEATURE_REF" "$FEATURE_SHA"
-run_bench "feature-1"  "$FEATURE_BIN"  "$BENCH_WORK_DIR/feature-1"
-
-write_labels "feature-2" "feature" "$FEATURE_REF" "$FEATURE_SHA"
-run_bench "feature-2"  "$FEATURE_BIN"  "$BENCH_WORK_DIR/feature-2"
-
-write_labels "baseline-2" "baseline" "$BASELINE_REF" "$BASELINE_SHA"
-run_bench "baseline-2" "$BASELINE_BIN" "$BENCH_WORK_DIR/baseline-2"
-
-# ── Compute Grafana URL ──────────────────────────────────────────────
-GRAFANA_BASE_URL="https://tempoxyz.grafana.net/d/reth-bench-ghr/reth-bench-ghr"
-GRAFANA_DATASOURCE="ef57fux92e9z4e"
-LAST_RUN_DURATION=$(( $(date +%s) - LAST_RUN_START ))
-FROM_MS=$(( BENCH_REFERENCE_EPOCH * 1000 ))
-TO_MS=$(( (BENCH_REFERENCE_EPOCH + LAST_RUN_DURATION) * 1000 ))
-GRAFANA_URL="${GRAFANA_BASE_URL}?orgId=1&from=${FROM_MS}&to=${TO_MS}&timezone=browser&var-datasource=${GRAFANA_DATASOURCE}&var-job=reth-bench&var-benchmark_id=${BENCH_ID}&var-benchmark_run=\$__all"
-
-# ── Step 8: Scan logs for errors ─────────────────────────────────────
-echo "▸ Scanning logs for errors..."
-ERRORS_FILE="$BENCH_WORK_DIR/errors.md"
-found_errors=false
-for run_dir in baseline-1 feature-1 feature-2 baseline-2; do
-  LOG="$BENCH_WORK_DIR/$run_dir/node.log"
-  [ -f "$LOG" ] || continue
-  panics=$(grep -c -E 'panicked at' "$LOG" 2>/dev/null || true)
-  errors=$(grep -c ' ERROR ' "$LOG" 2>/dev/null || true)
-  if [ "$panics" -gt 0 ] || [ "$errors" -gt 0 ]; then
-    if [ "$found_errors" = false ]; then
-      printf '### ⚠️ Node Errors\n\n' >> "$ERRORS_FILE"
-      found_errors=true
-    fi
-    printf '<details><summary><b>%s</b>: %d panic(s), %d error(s)</summary>\n\n' \
-      "$run_dir" "$panics" "$errors" >> "$ERRORS_FILE"
-    if [ "$panics" -gt 0 ]; then
-      printf '**Panics:**\n```\n' >> "$ERRORS_FILE"
-      grep -E 'panicked at' "$LOG" | head -10 >> "$ERRORS_FILE"
-      printf '```\n' >> "$ERRORS_FILE"
-    fi
-    if [ "$errors" -gt 0 ]; then
-      printf '**Errors (first 20):**\n```\n' >> "$ERRORS_FILE"
-      grep ' ERROR ' "$LOG" | head -20 >> "$ERRORS_FILE"
-      printf '```\n' >> "$ERRORS_FILE"
-    fi
-    printf '\n</details>\n\n' >> "$ERRORS_FILE"
-  fi
-done
-if [ "$found_errors" = true ]; then
-  echo "  ⚠ Errors found — see $ERRORS_FILE"
-else
-  echo "  No errors found."
-fi
-echo
-
-# ── Step 9: Parse results ───────────────────────────────────────────
-echo "▸ Parsing results..."
-cd "$RETH_REPO"
-
-SUMMARY_ARGS=(
-  --output-summary "$BENCH_WORK_DIR/summary.json"
-  --output-markdown "$BENCH_WORK_DIR/comment.md"
-  --repo "paradigmxyz/reth"
-  --baseline-ref "$BASELINE_SHA"
-  --baseline-name "$BASELINE_REF"
-  --feature-name "$FEATURE_REF"
-  --feature-ref "$FEATURE_SHA"
-  --baseline-csv "$BENCH_WORK_DIR/baseline-1/combined_latency.csv" "$BENCH_WORK_DIR/baseline-2/combined_latency.csv"
-  --feature-csv "$BENCH_WORK_DIR/feature-1/combined_latency.csv" "$BENCH_WORK_DIR/feature-2/combined_latency.csv"
-  --gas-csv "$BENCH_WORK_DIR/feature-1/total_gas.csv"
-  --grafana-url "$GRAFANA_URL"
-)
-
-python3 "${SCRIPTS_DIR}/bench-reth-summary.py" "${SUMMARY_ARGS[@]}"
-echo
-
-# ── Step 10: Generate charts ─────────────────────────────────────────
-echo "▸ Generating charts..."
-CHART_ARGS=(
-  --output-dir "$BENCH_WORK_DIR/charts"
-  --feature "$BENCH_WORK_DIR/feature-1/combined_latency.csv" "$BENCH_WORK_DIR/feature-2/combined_latency.csv"
-  --baseline "$BENCH_WORK_DIR/baseline-1/combined_latency.csv" "$BENCH_WORK_DIR/baseline-2/combined_latency.csv"
-  --baseline-name "$BASELINE_REF"
-  --feature-name "$FEATURE_REF"
-)
-
-if python3 -c "import matplotlib" 2>/dev/null; then
-  python3 "${SCRIPTS_DIR}/bench-reth-charts.py" "${CHART_ARGS[@]}"
-elif command -v uv &>/dev/null; then
-  uv run --with matplotlib python3 "${SCRIPTS_DIR}/bench-reth-charts.py" "${CHART_ARGS[@]}"
-else
-  echo "  Warning: matplotlib not available, skipping chart generation."
-fi
-echo
-
-# ── Step 11: Upload Tracy profiles ────────────────────────────────────
-if [ "$TRACY" != "off" ]; then
-  echo "▸ Uploading Tracy profiles..."
-  upload_tracy "baseline-1" "$BENCH_WORK_DIR/baseline-1" "$BASELINE_SHA"
-  upload_tracy "feature-1"  "$BENCH_WORK_DIR/feature-1"  "$FEATURE_SHA"
-  upload_tracy "feature-2"  "$BENCH_WORK_DIR/feature-2"  "$FEATURE_SHA"
-  upload_tracy "baseline-2" "$BENCH_WORK_DIR/baseline-2" "$BASELINE_SHA"
-  echo
-fi
-
-# ── Done (system restore happens via EXIT trap) ─────────────────────
-echo "═══════════════════════════════════════════════════════════"
-echo "  Benchmark complete!"
-echo "═══════════════════════════════════════════════════════════"
-echo "  Results  : $BENCH_WORK_DIR/summary.json"
-echo "  Markdown : $BENCH_WORK_DIR/comment.md"
-echo "  Charts   : $BENCH_WORK_DIR/charts/"
-if [ -f "$ERRORS_FILE" ]; then
-  echo "  Errors   : $ERRORS_FILE"
-fi
-echo "  Grafana  : $GRAFANA_URL"
-if [ "$TRACY" != "off" ]; then
-  echo "  ─── Tracy Profiles ───"
-  for run_dir in baseline-1 feature-1 feature-2 baseline-2; do
-    url_file="$BENCH_WORK_DIR/$run_dir/tracy_viewer_url.txt"
-    if [ -f "$url_file" ]; then
-      echo "  $run_dir : $(cat "$url_file")"
-    fi
-  done
-fi
-echo "═══════════════════════════════════════════════════════════"

.github/scripts/bench-reth-run.sh

@@ -1,352 +0,0 @@
-#!/usr/bin/env bash
-#
-# Runs a single reth-bench cycle: mount snapshot → start node → warmup →
-# benchmark → stop node → recover snapshot.
-#
-# Usage: bench-reth-run.sh <label> <binary> <output-dir>
-#
-# Required env: SCHELK_MOUNT, BENCH_RPC_URL, BENCH_BLOCKS, BENCH_WARMUP_BLOCKS
-# Optional env: BENCH_BIG_BLOCKS (true/false), BENCH_WORK_DIR (for big blocks path)
-#               BENCH_BAL (false/true/feature/baseline; only used with big blocks)
-#               BENCH_WAIT_TIME (duration like 500ms, default empty)
-#               BENCH_BASELINE_ARGS (extra reth node args for baseline runs)
-#               BENCH_FEATURE_ARGS (extra reth node args for feature runs)
-#               BENCH_OTLP_TRACES_ENDPOINT (OTLP HTTP endpoint for traces, e.g. https://host/insert/opentelemetry/v1/traces)
-#               BENCH_OTLP_LOGS_ENDPOINT (OTLP HTTP endpoint for logs, e.g. https://host/insert/opentelemetry/v1/logs)
-#               BENCH_OTLP_DISABLED (true to skip OTLP export even if endpoints are set)
-set -euxo pipefail
-
-LABEL="$1"
-BINARY="$2"
-OUTPUT_DIR="$3"
-DATADIR_NAME="datadir"
-if [ "${BENCH_BIG_BLOCKS:-false}" = "true" ]; then
-  DATADIR_NAME="datadir-big-blocks"
-fi
-DATADIR="$SCHELK_MOUNT/$DATADIR_NAME"
-mkdir -p "$OUTPUT_DIR"
-LOG="${OUTPUT_DIR}/node.log"
-
-RETH_SCOPE="${RETH_SCOPE:-reth-bench.scope}"
-
-cleanup() {
-  kill "$TAIL_PID" 2>/dev/null || true
-  # Stop tracy-capture first (SIGINT makes it disconnect and flush to disk)
-  # Must happen before killing reth, otherwise reth keeps streaming data.
-  if [ -n "${TRACY_PID:-}" ] && kill -0 "$TRACY_PID" 2>/dev/null; then
-    echo "Stopping tracy-capture..."
-    kill -INT "$TRACY_PID" 2>/dev/null || true
-    for i in $(seq 1 30); do
-      kill -0 "$TRACY_PID" 2>/dev/null || break
-      if [ $((i % 10)) -eq 0 ]; then
-        echo "Waiting for tracy-capture to finish writing... (${i}s)"
-      fi
-      sleep 1
-    done
-    if kill -0 "$TRACY_PID" 2>/dev/null; then
-      echo "tracy-capture still running after 30s, killing..."
-      kill -9 "$TRACY_PID" 2>/dev/null || true
-    fi
-    wait "$TRACY_PID" 2>/dev/null || true
-  fi
-  if sudo systemctl is-active "$RETH_SCOPE" >/dev/null 2>&1; then
-    if [ "${BENCH_SAMPLY:-false}" = "true" ]; then
-      # Send SIGINT to the inner reth process by exact name (not -f which
-      # would also match samply's cmdline containing "reth"). Samply will
-      # capture reth's exit and save the profile.
-      sudo pkill -INT -x reth 2>/dev/null || true
-      # Wait for samply to finish writing the profile and exit
-      for i in $(seq 1 120); do
-        sudo pgrep -x samply > /dev/null 2>&1 || break
-        if [ $((i % 10)) -eq 0 ]; then
-          echo "Waiting for samply to finish writing profile... (${i}s)"
-        fi
-        sleep 1
-      done
-      if sudo pgrep -x samply > /dev/null 2>&1; then
-        echo "Samply still running after 120s, sending SIGTERM..."
-        sudo pkill -x samply 2>/dev/null || true
-      fi
-    fi
-    # Stop the entire systemd scope — kills all processes in the cgroup.
-    # This is reliable regardless of process reparenting or PID wrapper issues.
-    sudo systemctl stop "$RETH_SCOPE" 2>/dev/null || true
-    sleep 1
-  fi
-  sudo systemctl reset-failed "$RETH_SCOPE" 2>/dev/null || true
-  # Fix ownership of reth-created files (reth runs as root)
-  sudo chown -R "$(id -un):$(id -gn)" "$OUTPUT_DIR" 2>/dev/null || true
-  # Let schelk recover the mounted volume in place so dm-era can restore only
-  # the changed blocks and clean up its own state.
-  sudo schelk recover -y --kill || true
-}
-TAIL_PID=
-TRACY_PID=
-trap cleanup EXIT
-
-# Clean up stale state from a previous cancelled run.
-# Stop any leftover reth process in the scope, then recover schelk state.
-sudo systemctl stop "$RETH_SCOPE" 2>/dev/null || true
-sudo systemctl reset-failed "$RETH_SCOPE" 2>/dev/null || true
-sudo schelk recover -y --kill || sudo schelk full-recover -y || true
-
-# Mount
-sudo schelk mount -y || true
-if [ ! -d "$DATADIR/db" ] || [ ! -d "$DATADIR/static_files" ]; then
-  echo "::error::Failed to mount benchmark datadir at ${DATADIR}"
-  ls -la "$SCHELK_MOUNT" || true
-  ls -la "$DATADIR" || true
-  exit 1
-fi
-sync
-sudo sh -c 'echo 3 > /proc/sys/vm/drop_caches'
-echo "=== Cache state after drop ==="
-free -h
-grep Cached /proc/meminfo
-
-# Start reth
-# CPU layout: core 0 = OS/IRQs/reth-bench/aux, cores 1+ = reth node
-RETH_BENCH="$(which reth-bench)"
-ONLINE=$(nproc --all)
-MAX_RETH=$(( ONLINE - 1 ))
-if [ "${BENCH_CORES:-0}" -gt 0 ] && [ "$BENCH_CORES" -lt "$MAX_RETH" ]; then
-  MAX_RETH=$BENCH_CORES
-fi
-RETH_CPUS="1-${MAX_RETH}"
-
-BIG_BLOCKS="${BENCH_BIG_BLOCKS:-false}"
-
-RETH_ARGS=(
-  node
-  --datadir "$DATADIR"
-  --log.file.directory "$OUTPUT_DIR/reth-logs"
-  --engine.accept-execution-requests-hash
-  --http
-  --http.port 8545
-  --ws
-  --ws.api all
-  --authrpc.port 8551
-  --disable-discovery
-  --no-persist-peers
-)
-
-# Gate flag on binary support (older baselines may not have it).
-# Uses --help which exits immediately via clap without node init.
-SYNC_STATE_IDLE=false
-if "$BINARY" node --help 2>/dev/null | grep -qF -- '--debug.startup-sync-state-idle'; then
-  RETH_ARGS+=(--debug.startup-sync-state-idle)
-  SYNC_STATE_IDLE=true
-fi
-
-# Append per-label extra node args (baseline or feature)
-EXTRA_NODE_ARGS=""
-case "$LABEL" in
-  baseline*) EXTRA_NODE_ARGS="${BENCH_BASELINE_ARGS:-}" ;;
-  feature*)  EXTRA_NODE_ARGS="${BENCH_FEATURE_ARGS:-}" ;;
-esac
-if [ -n "$EXTRA_NODE_ARGS" ]; then
-  # Word-split the string into individual args
-  # shellcheck disable=SC2206
-  RETH_ARGS+=($EXTRA_NODE_ARGS)
-fi
-
-if [ -n "${BENCH_METRICS_ADDR:-}" ]; then
-  RETH_ARGS+=(--metrics "$BENCH_METRICS_ADDR")
-fi
-
-# OTLP traces and logs export
-if [ "${BENCH_OTLP_DISABLED:-false}" != "true" ]; then
-  if [ -n "${BENCH_OTLP_TRACES_ENDPOINT:-}" ]; then
-    RETH_ARGS+=(--tracing-otlp="${BENCH_OTLP_TRACES_ENDPOINT}" --tracing-otlp.service-name=reth-bench)
-  fi
-  if [ -n "${BENCH_OTLP_LOGS_ENDPOINT:-}" ]; then
-    RETH_ARGS+=(--logs-otlp="${BENCH_OTLP_LOGS_ENDPOINT}" --logs-otlp.filter=debug)
-  fi
-fi
-
-# Tracy profiling: add --log.tracy flags and set environment
-if [ "${BENCH_TRACY:-off}" != "off" ]; then
-  RETH_ARGS+=(--log.tracy --log.tracy.filter "${BENCH_TRACY_FILTER:-debug}")
-  if [ "${BENCH_TRACY}" = "on" ]; then
-    export TRACY_NO_SYS_TRACE=1
-  elif [ "${BENCH_TRACY}" = "full" ]; then
-    export TRACY_SAMPLING_HZ="${BENCH_TRACY_SAMPLING_HZ:-1}"
-  fi
-fi
-
-SUDO_ENV=()
-if [ -n "${OTEL_RESOURCE_ATTRIBUTES:-}" ]; then
-  SUDO_ENV+=("OTEL_RESOURCE_ATTRIBUTES=${OTEL_RESOURCE_ATTRIBUTES}")
-  SUDO_ENV+=("OTEL_BSP_MAX_QUEUE_SIZE=65536" "OTEL_BLRP_MAX_QUEUE_SIZE=65536")
-fi
-
-# Limit reth memory to 95% of available RAM to prevent OOM kills
-TOTAL_MEM_KB=$(awk '/^MemTotal:/ {print $2}' /proc/meminfo)
-MEM_LIMIT=$(( TOTAL_MEM_KB * 95 / 100 * 1024 ))
-echo "Memory limit: $(( MEM_LIMIT / 1024 / 1024 ))MB (95% of $(( TOTAL_MEM_KB / 1024 ))MB)"
-
-if [ "${BENCH_SAMPLY:-false}" = "true" ]; then
-  RETH_ARGS+=(--log.samply)
-  SAMPLY="$(which samply)"
-  sudo systemd-run --quiet --scope --collect --unit="$RETH_SCOPE" \
-    -p MemoryMax="$MEM_LIMIT" -p AllowedCPUs="$RETH_CPUS" \
-    env "${SUDO_ENV[@]}" nice -n -20 \
-    "$SAMPLY" record --save-only --presymbolicate --rate 10000 \
-    --output "$OUTPUT_DIR/samply-profile.json.gz" \
-    -- "$BINARY" "${RETH_ARGS[@]}" \
-    > "$LOG" 2>&1 &
-else
-  sudo systemd-run --quiet --scope --collect --unit="$RETH_SCOPE" \
-    -p MemoryMax="$MEM_LIMIT" -p AllowedCPUs="$RETH_CPUS" \
-    env "${SUDO_ENV[@]}" nice -n -20 "$BINARY" "${RETH_ARGS[@]}" \
-    > "$LOG" 2>&1 &
-fi
-stdbuf -oL tail -f "$LOG" | sed -u "s/^/[reth] /" &
-TAIL_PID=$!
-
-for i in $(seq 1 60); do
-  if curl -sf http://127.0.0.1:8545 -X POST \
-    -H 'Content-Type: application/json' \
-    -d '{"jsonrpc":"2.0","method":"eth_blockNumber","params":[],"id":1}' \
-    > /dev/null 2>&1; then
-    echo "reth (${LABEL}) RPC is up after ${i}s"
-    break
-  fi
-  if [ "$i" -eq 60 ]; then
-    echo "::error::reth (${LABEL}) failed to start within 60s"
-    cat "$LOG"
-    exit 1
-  fi
-  sleep 1
-done
-
-# Wait for the pipeline to finish (eth_syncing returns false) so the
-# engine is in live mode and can accept newPayload calls.
-# Only possible when --debug.startup-sync-state-idle is supported.
-if [ "$SYNC_STATE_IDLE" = "true" ]; then
-  for i in $(seq 1 300); do
-    SYNC_RESULT=$(curl -sf http://127.0.0.1:8545 -X POST \
-      -H 'Content-Type: application/json' \
-      -d '{"jsonrpc":"2.0","method":"eth_syncing","params":[],"id":1}' 2>/dev/null || true)
-    if [ -n "$SYNC_RESULT" ] && jq -e '.result == false' <<< "$SYNC_RESULT" > /dev/null 2>&1; then
-      echo "reth (${LABEL}) pipeline finished after ${i}s, engine is live"
-      break
-    fi
-    if [ "$i" -eq 300 ]; then
-      echo "::error::reth (${LABEL}) pipeline did not finish within 300s"
-      cat "$LOG"
-      exit 1
-    fi
-    sleep 1
-  done
-else
-  echo "reth (${LABEL}) binary does not support --debug.startup-sync-state-idle, skipping sync wait"
-fi
-
-# Run reth-bench with high priority but as the current user so output
-# files are not root-owned (avoids EACCES on next checkout).
-BENCH_NICE="sudo nice -n -20 sudo -u $(id -un)"
-
-# Build optional flags
-EXTRA_BENCH_ARGS=(--reth-new-payload)
-if [ -n "${BENCH_WAIT_TIME:-}" ]; then
-  EXTRA_BENCH_ARGS+=(--wait-time "$BENCH_WAIT_TIME")
-fi
-
-if [ "$BIG_BLOCKS" = "true" ]; then
-  # Big blocks mode: replay pre-generated payloads
-  BIG_BLOCKS_DIR="${BENCH_BIG_BLOCKS_DIR:-${BENCH_WORK_DIR}/big-blocks}"
-  BENCH_BAL_MODE="${BENCH_BAL:-false}"
-
-  BB_BENCH_ARGS=(--reth-new-payload)
-  if [ -n "${BENCH_WAIT_TIME:-}" ]; then
-    BB_BENCH_ARGS+=(--wait-time "$BENCH_WAIT_TIME")
-  fi
-  case "$BENCH_BAL_MODE" in
-    false)
-      ;;
-    true)
-      BB_BENCH_ARGS+=(--bal)
-      ;;
-    baseline)
-      if [[ "$LABEL" == baseline* ]]; then
-        BB_BENCH_ARGS+=(--bal)
-      fi
-      ;;
-    feature)
-      if [[ "$LABEL" == feature* ]]; then
-        BB_BENCH_ARGS+=(--bal)
-      fi
-      ;;
-    *)
-      echo "::error::Unknown BENCH_BAL value: $BENCH_BAL_MODE"
-      exit 1
-      ;;
-  esac
-
-  # Warmup
-  WARMUP="${BENCH_WARMUP_BLOCKS:-50}"
-  if [ "$WARMUP" -gt 0 ] 2>/dev/null; then
-    echo "Running big blocks warmup (${WARMUP} payloads)..."
-    $BENCH_NICE "$RETH_BENCH" replay-payloads \
-      "${BB_BENCH_ARGS[@]}" \
-      --count "$WARMUP" \
-      --payload-dir "$BIG_BLOCKS_DIR/payloads" \
-      --engine-rpc-url http://127.0.0.1:8551 \
-      --jwt-secret "$DATADIR/jwt.hex" 2>&1 | sed -u "s/^/[bench] /"
-  fi
-
-  # Start tracy-capture after warmup so profile only covers the benchmark
-  if [ "${BENCH_TRACY:-off}" != "off" ]; then
-    echo "Starting tracy-capture..."
-    tracy-capture -f -o "$OUTPUT_DIR/tracy-profile.tracy" &
-    TRACY_PID=$!
-    sleep 0.5  # give tracy-capture time to connect
-  fi
-
-  # Benchmark — skip warmup payloads so they aren't measured
-  BB_SKIP=0
-  if [ "$WARMUP" -gt 0 ] 2>/dev/null; then
-    BB_SKIP="$WARMUP"
-  fi
-  if [ "${BENCH_BLOCKS:-0}" -gt 0 ] 2>/dev/null; then
-    BB_BENCH_ARGS+=(--count "$BENCH_BLOCKS")
-  fi
-
-  echo "Running big blocks benchmark (replay-payloads, skip=${BB_SKIP})..."
-  $BENCH_NICE "$RETH_BENCH" replay-payloads \
-    "${BB_BENCH_ARGS[@]}" \
-    --skip "$BB_SKIP" \
-    --payload-dir "$BIG_BLOCKS_DIR/payloads" \
-    --engine-rpc-url http://127.0.0.1:8551 \
-    --jwt-secret "$DATADIR/jwt.hex" \
-    --output "$OUTPUT_DIR" 2>&1 | sed -u "s/^/[bench] /"
-else
-  # Standard mode: warmup + new-payload-fcu
-  # Warmup
-  $BENCH_NICE "$RETH_BENCH" new-payload-fcu \
-    --rpc-url "$BENCH_RPC_URL" \
-    --engine-rpc-url http://127.0.0.1:8551 \
-    --jwt-secret "$DATADIR/jwt.hex" \
-    --advance "${BENCH_WARMUP_BLOCKS:-50}" \
-    "${EXTRA_BENCH_ARGS[@]}" 2>&1 | sed -u "s/^/[bench] /"
-
-  # Start tracy-capture after warmup so profile only covers the benchmark
-  if [ "${BENCH_TRACY:-off}" != "off" ]; then
-    echo "Starting tracy-capture..."
-    tracy-capture -f -o "$OUTPUT_DIR/tracy-profile.tracy" &
-    TRACY_PID=$!
-    sleep 0.5  # give tracy-capture time to connect
-  fi
-
-  # Benchmark
-  $BENCH_NICE "$RETH_BENCH" new-payload-fcu \
-    --rpc-url "$BENCH_RPC_URL" \
-    --engine-rpc-url http://127.0.0.1:8551 \
-    --jwt-secret "$DATADIR/jwt.hex" \
-    --advance "$BENCH_BLOCKS" \
-    "${EXTRA_BENCH_ARGS[@]}" \
-    --output "$OUTPUT_DIR" 2>&1 | sed -u "s/^/[bench] /"
-fi
-
-# cleanup runs via trap

.github/scripts/bench-reth-snapshot.sh

@@ -1,56 +0,0 @@
-#!/usr/bin/env bash
-#
-# Validates that the benchmark snapshot has already been populated into the
-# local schelk volume.
-#
-# Usage: bench-reth-snapshot.sh [--check]
-#   --check   Exit 0 if the local snapshot is ready, 10 if it is missing.
-#
-# Required env:
-#   SCHELK_MOUNT – schelk mount point (e.g. /reth-bench)
-# Optional env:
-#   BENCH_BIG_BLOCKS   – true when validating the big-blocks snapshot datadir
-#   BENCH_SNAPSHOT_NAME – expected snapshot label for log/error output
-set -euxo pipefail
-
-: "${SCHELK_MOUNT:?SCHELK_MOUNT must be set}"
-
-DATADIR_NAME="datadir"
-if [ "${BENCH_BIG_BLOCKS:-false}" = "true" ]; then
-  DATADIR_NAME="datadir-big-blocks"
-fi
-DATADIR="$SCHELK_MOUNT/$DATADIR_NAME"
-
-describe_snapshot() {
-  if [ -n "${BENCH_SNAPSHOT_NAME:-}" ]; then
-    printf '%s' "${BENCH_SNAPSHOT_NAME}"
-  elif [ "${BENCH_BIG_BLOCKS:-false}" = "true" ]; then
-    printf '%s' 'big-block weekly snapshot'
-  else
-    printf '%s' 'benchmark snapshot'
-  fi
-}
-
-snapshot_ready() {
-  [ -d "$DATADIR/db" ] && [ -d "$DATADIR/static_files" ]
-}
-
-EXPECTED_SNAPSHOT="$(describe_snapshot)"
-
-sudo schelk recover -y --kill || sudo schelk full-recover -y || true
-sudo schelk mount -y || true
-
-if snapshot_ready; then
-  echo "Found local ${EXPECTED_SNAPSHOT} at ${DATADIR}"
-  exit 0
-fi
-
-echo "::error::Missing local ${EXPECTED_SNAPSHOT} at ${DATADIR}. Benchmarks no longer download snapshots; pre-populate the local schelk data first."
-ls -la "$SCHELK_MOUNT" || true
-ls -la "$DATADIR" || true
-
-if [ "${1:-}" = "--check" ]; then
-  exit 10
-fi
-
-exit 1

.github/scripts/bench-reth-summary.py

@@ -1,646 +0,0 @@
-#!/usr/bin/env python3
-"""Parse reth-bench CSV output and generate a summary JSON + markdown comparison.
-
-Usage:
-    bench-reth-summary.py <combined_csv> <gas_csv> \
-        --output-summary <summary.json> \
-        --output-markdown <comment.md> \
-        --baseline-csv <baseline_combined.csv> \
-        [--repo <owner/repo>] \
-        [--baseline-ref <sha>] \
-        [--feature-name <name>] \
-        [--feature-sha <sha>]
-
-Generates a paired statistical comparison between baseline and feature.
-Matches blocks by number and computes per-block diffs to cancel out gas
-variance. Fails if baseline or feature CSV is missing or empty.
-"""
-
-import argparse
-import csv
-import json
-import math
-import random
-import sys
-
-GIGAGAS = 1_000_000_000
-T_CRITICAL = 1.96  # two-tailed 95% confidence
-BOOTSTRAP_ITERATIONS = 10_000
-
-
-def _opt_int(row: dict, key: str) -> int | None:
-    """Return int value for a CSV field, or None if missing/empty."""
-    v = row.get(key)
-    if v is None or v == "":
-        return None
-    return int(v)
-
-
-def parse_combined_csv(path: str) -> list[dict]:
-    """Parse combined_latency.csv into a list of per-block dicts."""
-    rows = []
-    with open(path) as f:
-        reader = csv.DictReader(f)
-        for row in reader:
-            rows.append(
-                {
-                    "block_number": int(row["block_number"]),
-                    "gas_used": int(row["gas_used"]),
-                    "gas_limit": int(row["gas_limit"]),
-                    "transaction_count": int(row["transaction_count"]),
-                    "new_payload_latency_us": int(row["new_payload_latency"]),
-                    "fcu_latency_us": int(row["fcu_latency"]),
-                    "total_latency_us": int(row["total_latency"]),
-                    "persistence_wait_us": _opt_int(row, "persistence_wait"),
-                    "execution_cache_wait_us": _opt_int(row, "execution_cache_wait"),
-                    "sparse_trie_wait_us": _opt_int(row, "sparse_trie_wait"),
-                }
-            )
-    return rows
-
-
-def parse_gas_csv(path: str) -> list[dict]:
-    """Parse total_gas.csv into a list of per-block dicts."""
-    rows = []
-    with open(path) as f:
-        reader = csv.DictReader(f)
-        for row in reader:
-            rows.append(
-                {
-                    "block_number": int(row["block_number"]),
-                    "gas_used": int(row["gas_used"]),
-                    "time_us": int(row["time"]),
-                }
-            )
-    return rows
-
-
-def stddev(values: list[float], mean: float) -> float:
-    if len(values) < 2:
-        return 0.0
-    return math.sqrt(sum((v - mean) ** 2 for v in values) / (len(values) - 1))
-
-
-def percentile(sorted_vals: list[float], pct: int) -> float:
-    if not sorted_vals:
-        return 0.0
-    idx = int(len(sorted_vals) * pct / 100)
-    idx = min(idx, len(sorted_vals) - 1)
-    return sorted_vals[idx]
-
-
-def compute_stats(combined: list[dict]) -> dict:
-    """Compute per-run statistics from parsed CSV data."""
-    n = len(combined)
-    if n == 0:
-        return {}
-
-    latencies_ms = [r["new_payload_latency_us"] / 1_000 for r in combined]
-    sorted_lat = sorted(latencies_ms)
-    mean_lat = sum(latencies_ms) / n
-    std_lat = stddev(latencies_ms, mean_lat)
-
-    mgas_s_values = []
-    for r in combined:
-        lat_s = r["new_payload_latency_us"] / 1_000_000
-        if lat_s > 0:
-            mgas_s_values.append(r["gas_used"] / lat_s / 1_000_000)
-    mean_mgas_s = sum(mgas_s_values) / len(mgas_s_values) if mgas_s_values else 0
-
-    total_latencies_ms = [r["total_latency_us"] / 1_000 for r in combined]
-    wall_clock_s = sum(total_latencies_ms) / 1_000
-    mean_total_lat_ms = sum(total_latencies_ms) / n
-
-    # Persistence wait mean (for main table)
-    persist_values_ms = []
-    for r in combined:
-        v = r.get("persistence_wait_us")
-        if v is not None:
-            persist_values_ms.append(v / 1_000)
-    mean_persist_ms = sum(persist_values_ms) / len(persist_values_ms) if persist_values_ms else 0.0
-
-    return {
-        "n": n,
-        "mean_ms": mean_lat,
-        "stddev_ms": std_lat,
-        "p50_ms": percentile(sorted_lat, 50),
-        "p90_ms": percentile(sorted_lat, 90),
-        "p99_ms": percentile(sorted_lat, 99),
-        "mean_mgas_s": mean_mgas_s,
-        "wall_clock_s": wall_clock_s,
-        "mean_total_lat_ms": mean_total_lat_ms,
-        "mean_persist_ms": mean_persist_ms,
-    }
-
-
-def compute_wait_stats(combined: list[dict], field: str) -> dict:
-    """Compute mean/p50/p95 for a wait time field (in ms)."""
-    values_ms = []
-    for r in combined:
-        v = r.get(field)
-        if v is not None:
-            values_ms.append(v / 1_000)
-    if not values_ms:
-        return {}
-    n = len(values_ms)
-    mean_val = sum(values_ms) / n
-    sorted_vals = sorted(values_ms)
-    return {
-        "mean_ms": mean_val,
-        "p50_ms": percentile(sorted_vals, 50),
-        "p95_ms": percentile(sorted_vals, 95),
-    }
-
-
-def _paired_data(
-    baseline: list[dict], feature: list[dict]
-) -> tuple[list[tuple[float, float]], list[float], list[float], list[float], list[float]]:
-    """Match blocks and return paired latencies and per-block diffs.
-
-    Returns:
-        pairs: list of (baseline_ms, feature_ms) tuples
-        lat_diffs_ms: list of feature − baseline latency diffs in ms
-        mgas_diffs: list of feature − baseline Mgas/s diffs
-        total_lat_diffs_ms: list of feature − baseline total latency diffs in ms
-        persist_diffs_ms: list of feature − baseline persistence wait diffs in ms
-    """
-    baseline_by_block = {r["block_number"]: r for r in baseline}
-    feature_by_block = {r["block_number"]: r for r in feature}
-    common_blocks = sorted(set(baseline_by_block) & set(feature_by_block))
-
-    pairs = []
-    lat_diffs_ms = []
-    mgas_diffs = []
-    total_lat_diffs_ms = []
-    persist_diffs_ms = []
-    for bn in common_blocks:
-        b = baseline_by_block[bn]
-        f = feature_by_block[bn]
-        b_ms = b["new_payload_latency_us"] / 1_000
-        f_ms = f["new_payload_latency_us"] / 1_000
-        pairs.append((b_ms, f_ms))
-        lat_diffs_ms.append(f_ms - b_ms)
-        b_lat_s = b["new_payload_latency_us"] / 1_000_000
-        f_lat_s = f["new_payload_latency_us"] / 1_000_000
-        if b_lat_s > 0 and f_lat_s > 0:
-            mgas_diffs.append(
-                f["gas_used"] / f_lat_s / 1_000_000
-                - b["gas_used"] / b_lat_s / 1_000_000
-            )
-        total_lat_diffs_ms.append(
-            f["total_latency_us"] / 1_000 - b["total_latency_us"] / 1_000
-        )
-        b_persist = (b.get("persistence_wait_us") or 0) / 1_000
-        f_persist = (f.get("persistence_wait_us") or 0) / 1_000
-        persist_diffs_ms.append(f_persist - b_persist)
-    return pairs, lat_diffs_ms, mgas_diffs, total_lat_diffs_ms, persist_diffs_ms
-
-
-def compute_paired_stats(
-    baseline_runs: list[list[dict]],
-    feature_runs: list[list[dict]],
-) -> dict:
-    """Compute paired statistics between baseline and feature runs.
-
-    Each pair (baseline_runs[i], feature_runs[i]) produces per-block diffs.
-    All diffs are pooled for the final CI.
-    """
-    all_pairs = []
-    all_lat_diffs = []
-    all_mgas_diffs = []
-    all_total_lat_diffs = []
-    all_persist_diffs = []
-    blocks_per_pair = []
-    for baseline, feature in zip(baseline_runs, feature_runs):
-        pairs, lat_diffs, mgas_diffs, total_lat_diffs, persist_diffs = _paired_data(baseline, feature)
-        all_pairs.extend(pairs)
-        all_lat_diffs.extend(lat_diffs)
-        all_mgas_diffs.extend(mgas_diffs)
-        all_total_lat_diffs.extend(total_lat_diffs)
-        all_persist_diffs.extend(persist_diffs)
-        blocks_per_pair.append(len(pairs))
-
-    if not all_lat_diffs:
-        return {}
-
-    n = len(all_lat_diffs)
-    mean_diff = sum(all_lat_diffs) / n
-    std_diff = stddev(all_lat_diffs, mean_diff)
-    se = std_diff / math.sqrt(n) if n > 0 else 0.0
-    ci = T_CRITICAL * se
-
-    # Bootstrap CI on difference-of-percentiles (resample paired blocks)
-    base_lats = sorted([p[0] for p in all_pairs])
-    feature_lats = sorted([p[1] for p in all_pairs])
-    p50_diff = percentile(feature_lats, 50) - percentile(base_lats, 50)
-    p90_diff = percentile(feature_lats, 90) - percentile(base_lats, 90)
-    p99_diff = percentile(feature_lats, 99) - percentile(base_lats, 99)
-
-    rng = random.Random(42)
-    p50_boot, p90_boot, p99_boot = [], [], []
-    for _ in range(BOOTSTRAP_ITERATIONS):
-        sample = rng.choices(all_pairs, k=n)
-        b_sorted = sorted(p[0] for p in sample)
-        f_sorted = sorted(p[1] for p in sample)
-        p50_boot.append(percentile(f_sorted, 50) - percentile(b_sorted, 50))
-        p90_boot.append(percentile(f_sorted, 90) - percentile(b_sorted, 90))
-        p99_boot.append(percentile(f_sorted, 99) - percentile(b_sorted, 99))
-    p50_boot.sort()
-    p90_boot.sort()
-    p99_boot.sort()
-    lo = int(BOOTSTRAP_ITERATIONS * 0.025)
-    hi = int(BOOTSTRAP_ITERATIONS * 0.975)
-
-    mean_mgas_diff = sum(all_mgas_diffs) / len(all_mgas_diffs) if all_mgas_diffs else 0.0
-    std_mgas_diff = stddev(all_mgas_diffs, mean_mgas_diff) if len(all_mgas_diffs) > 1 else 0.0
-    mgas_se = std_mgas_diff / math.sqrt(len(all_mgas_diffs)) if all_mgas_diffs else 0.0
-    mgas_ci = T_CRITICAL * mgas_se
-
-    mean_total_diff = sum(all_total_lat_diffs) / len(all_total_lat_diffs) if all_total_lat_diffs else 0.0
-    std_total_diff = stddev(all_total_lat_diffs, mean_total_diff) if len(all_total_lat_diffs) > 1 else 0.0
-    total_se = std_total_diff / math.sqrt(len(all_total_lat_diffs)) if all_total_lat_diffs else 0.0
-    wall_clock_ci_ms = T_CRITICAL * total_se
-
-    mean_persist_diff = sum(all_persist_diffs) / len(all_persist_diffs) if all_persist_diffs else 0.0
-    std_persist_diff = stddev(all_persist_diffs, mean_persist_diff) if len(all_persist_diffs) > 1 else 0.0
-    persist_se = std_persist_diff / math.sqrt(len(all_persist_diffs)) if all_persist_diffs else 0.0
-    persist_ci_ms = T_CRITICAL * persist_se
-
-    return {
-        "n": n,
-        "mean_diff_ms": mean_diff,
-        "ci_ms": ci,
-        "p50_diff_ms": p50_diff,
-        "p50_ci_ms": (p50_boot[hi] - p50_boot[lo]) / 2,
-        "p90_diff_ms": p90_diff,
-        "p90_ci_ms": (p90_boot[hi] - p90_boot[lo]) / 2,
-        "p99_diff_ms": p99_diff,
-        "p99_ci_ms": (p99_boot[hi] - p99_boot[lo]) / 2,
-        "mean_mgas_diff": mean_mgas_diff,
-        "mgas_ci": mgas_ci,
-        "wall_clock_ci_ms": wall_clock_ci_ms,
-        "persist_ci_ms": persist_ci_ms,
-        "blocks": max(blocks_per_pair),
-    }
-
-
-
-def format_duration(seconds: float) -> str:
-    if seconds >= 60:
-        return f"{seconds / 60:.1f}min"
-    return f"{seconds}s"
-
-
-def format_gas(gas: int) -> str:
-    if gas >= GIGAGAS:
-        return f"{gas / GIGAGAS:.1f}G"
-    if gas >= 1_000_000:
-        return f"{gas / 1_000_000:.1f}M"
-    return f"{gas:,}"
-
-
-
-def fmt_ms(v: float) -> str:
-    return f"{v:.2f}ms"
-
-
-def fmt_mgas(v: float) -> str:
-    return f"{v:.2f}"
-
-
-def fmt_s(v: float) -> str:
-    return f"{v:.2f}s"
-
-
-def display_bal_mode(bal_mode: str | None) -> str | None:
-    if not bal_mode or bal_mode == "false":
-        return None
-    if bal_mode == "both":
-        return "true"
-    return bal_mode
-
-
-def significance(pct: float, ci_pct: float, lower_is_better: bool) -> str:
-    """Return significance label: 'good', 'bad', or 'neutral'."""
-    significant = abs(pct) > ci_pct
-    if not significant:
-        return "neutral"
-    elif (pct < 0) == lower_is_better:
-        return "good"
-    else:
-        return "bad"
-
-
-def change_str(pct: float, ci_pct: float, lower_is_better: bool) -> str:
-    """Format change% with paired CI significance.
-
-    Significant if the CI doesn't cross zero (i.e. |pct| > ci_pct).
-    """
-    sig = significance(pct, ci_pct, lower_is_better)
-    emoji = {"good": "✅", "bad": "❌", "neutral": "⚪"}[sig]
-    return f"{pct:+.2f}% {emoji} (±{ci_pct:.2f}%)"
-
-
-def compute_changes(
-    baseline_stats: dict, feature_stats: dict, paired_stats: dict
-) -> dict:
-    """Pre-compute change percentages and significance for each metric."""
-    def pct(base: float, feat: float) -> float:
-        return (feat - base) / base * 100.0 if base > 0 else 0.0
-
-    def ci_pct(ci_ms: float, base_ms: float) -> float:
-        return ci_ms / base_ms * 100.0 if base_ms > 0 else 0.0
-
-    metrics = [
-        ("mean", "mean_ms", "ci_ms", "mean_ms", True),
-        ("p50", "p50_ms", "p50_ci_ms", "p50_ms", True),
-        ("p90", "p90_ms", "p90_ci_ms", "p90_ms", True),
-        ("p99", "p99_ms", "p99_ci_ms", "p99_ms", True),
-        ("mgas_s", "mean_mgas_s", "mgas_ci", "mean_mgas_s", False),
-        ("wall_clock", "wall_clock_s", "wall_clock_ci_ms", "mean_total_lat_ms", True),
-        ("persist_wait", "mean_persist_ms", "persist_ci_ms", "mean_persist_ms", True),
-    ]
-    changes = {}
-    for name, stat_key, ci_key, base_key, lower_is_better in metrics:
-        p = pct(baseline_stats[stat_key], feature_stats[stat_key])
-        c = ci_pct(paired_stats[ci_key], baseline_stats[base_key])
-        changes[name] = {
-            "pct": round(p, 4),
-            "ci_pct": round(c, 4),
-            "sig": significance(p, c, lower_is_better),
-        }
-    return changes
-
-
-def generate_comparison_table(
-    run1: dict,
-    run2: dict,
-    paired: dict,
-    repo: str,
-    baseline_ref: str,
-    baseline_name: str,
-    feature_name: str,
-    feature_sha: str,
-    big_blocks: bool = False,
-    warmup_blocks: str | None = None,
-    wait_time: str | None = None,
-    bal_mode: str | None = None,
-) -> str:
-    """Generate a markdown comparison table between baseline and feature."""
-    n = paired["blocks"]
-
-    def pct(base: float, feat: float) -> float:
-        return (feat - base) / base * 100.0 if base > 0 else 0.0
-
-    mean_pct = pct(run1["mean_ms"], run2["mean_ms"])
-    gas_pct = pct(run1["mean_mgas_s"], run2["mean_mgas_s"])
-    wall_pct = pct(run1["wall_clock_s"], run2["wall_clock_s"])
-
-    p50_pct = pct(run1["p50_ms"], run2["p50_ms"])
-    p90_pct = pct(run1["p90_ms"], run2["p90_ms"])
-    p99_pct = pct(run1["p99_ms"], run2["p99_ms"])
-
-    persist_pct = pct(run1["mean_persist_ms"], run2["mean_persist_ms"])
-
-    # Bootstrap CIs as % of baseline percentile
-    p50_ci_pct = paired["p50_ci_ms"] / run1["p50_ms"] * 100.0 if run1["p50_ms"] > 0 else 0.0
-    p90_ci_pct = paired["p90_ci_ms"] / run1["p90_ms"] * 100.0 if run1["p90_ms"] > 0 else 0.0
-    p99_ci_pct = paired["p99_ci_ms"] / run1["p99_ms"] * 100.0 if run1["p99_ms"] > 0 else 0.0
-
-    # CI as a percentage of baseline mean
-    lat_ci_pct = paired["ci_ms"] / run1["mean_ms"] * 100.0 if run1["mean_ms"] > 0 else 0.0
-    mgas_ci_pct = paired["mgas_ci"] / run1["mean_mgas_s"] * 100.0 if run1["mean_mgas_s"] > 0 else 0.0
-    wall_ci_pct = paired["wall_clock_ci_ms"] / run1["mean_total_lat_ms"] * 100.0 if run1["mean_total_lat_ms"] > 0 else 0.0
-    persist_ci_pct = paired["persist_ci_ms"] / run1["mean_persist_ms"] * 100.0 if run1["mean_persist_ms"] > 0 else 0.0
-
-    base_url = f"https://github.com/{repo}/commit"
-    baseline_label = f"[`{baseline_name}`]({base_url}/{baseline_ref})"
-    feature_label = f"[`{feature_name}`]({base_url}/{feature_sha})"
-
-    lines = [
-        f"| Metric | {baseline_label} | {feature_label} | Change |",
-        "|--------|------|--------|--------|",
-        f"| Mean | {fmt_ms(run1['mean_ms'])} | {fmt_ms(run2['mean_ms'])} | {change_str(mean_pct, lat_ci_pct, lower_is_better=True)} |",
-        f"| StdDev | {fmt_ms(run1['stddev_ms'])} | {fmt_ms(run2['stddev_ms'])} | |",
-        f"| P50 | {fmt_ms(run1['p50_ms'])} | {fmt_ms(run2['p50_ms'])} | {change_str(p50_pct, p50_ci_pct, lower_is_better=True)} |",
-        f"| P90 | {fmt_ms(run1['p90_ms'])} | {fmt_ms(run2['p90_ms'])} | {change_str(p90_pct, p90_ci_pct, lower_is_better=True)} |",
-        f"| P99 | {fmt_ms(run1['p99_ms'])} | {fmt_ms(run2['p99_ms'])} | {change_str(p99_pct, p99_ci_pct, lower_is_better=True)} |",
-        f"| Mgas/s | {fmt_mgas(run1['mean_mgas_s'])} | {fmt_mgas(run2['mean_mgas_s'])} | {change_str(gas_pct, mgas_ci_pct, lower_is_better=False)} |",
-        f"| Wall Clock | {fmt_s(run1['wall_clock_s'])} | {fmt_s(run2['wall_clock_s'])} | {change_str(wall_pct, wall_ci_pct, lower_is_better=True)} |",
-        f"| Persist Wait | {fmt_ms(run1['mean_persist_ms'])} | {fmt_ms(run2['mean_persist_ms'])} | {change_str(persist_pct, persist_ci_pct, lower_is_better=True)} |",
-        "",
-    ]
-    meta_parts = [f"{n} {'big blocks' if big_blocks else 'blocks'}"]
-    if warmup_blocks:
-        meta_parts.append(f"{warmup_blocks} warmup")
-    if wait_time:
-        meta_parts.append(f"wait time: {wait_time}")
-    display_mode = display_bal_mode(bal_mode)
-    if big_blocks and display_mode:
-        meta_parts.append(f"BAL: {display_mode}")
-    lines.append(f"*{', '.join(meta_parts)}*")
-    return "\n".join(lines)
-
-
-def generate_wait_time_table(
-    title: str,
-    baseline_stats: dict,
-    feature_stats: dict,
-    baseline_label: str,
-    feature_label: str,
-) -> str:
-    """Generate a markdown table for a wait time metric."""
-    if not baseline_stats or not feature_stats:
-        return ""
-    lines = [
-        f"### {title}",
-        "",
-        f"| Metric | {baseline_label} | {feature_label} |",
-        "|--------|------|--------|",
-        f"| Mean | {fmt_ms(baseline_stats['mean_ms'])} | {fmt_ms(feature_stats['mean_ms'])} |",
-        f"| P50 | {fmt_ms(baseline_stats['p50_ms'])} | {fmt_ms(feature_stats['p50_ms'])} |",
-        f"| P95 | {fmt_ms(baseline_stats['p95_ms'])} | {fmt_ms(feature_stats['p95_ms'])} |",
-    ]
-    return "\n".join(lines)
-
-
-def generate_markdown(
-    summary: dict, comparison_table: str,
-    wait_time_tables: list[str] | None = None,
-    behind_baseline: int = 0, repo: str = "", baseline_ref: str = "", baseline_name: str = "",
-    grafana_url: str | None = None,
-) -> str:
-    """Generate a markdown comment body."""
-    lines = ["## Benchmark Results", ""]
-    if behind_baseline > 0:
-        s = "s" if behind_baseline > 1 else ""
-        diff_link = f"https://github.com/{repo}/compare/{baseline_ref[:12]}...{baseline_name}"
-        lines.append(f"> ⚠️ Feature is [**{behind_baseline} commit{s} behind `{baseline_name}`**]({diff_link}). Consider rebasing for accurate results.")
-        lines.append("")
-    lines.append(comparison_table)
-    if wait_time_tables:
-        lines.append("")
-        lines.append("<details>")
-        lines.append("<summary>Wait Time Breakdown</summary>")
-        lines.append("")
-        for table in wait_time_tables:
-            if table:
-                lines.append(table)
-                lines.append("")
-        lines.append("</details>")
-    if grafana_url:
-        lines.append("")
-        lines.append(f"**[Grafana Dashboard]({grafana_url})**")
-    return "\n".join(lines)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Parse reth-bench ABBA results")
-    parser.add_argument(
-        "--baseline-csv", nargs="+", required=True,
-        help="Baseline combined_latency.csv files (A1, A2)",
-    )
-    parser.add_argument(
-        "--feature-csv", "--branch-csv", nargs="+", required=True,
-        help="Feature combined_latency.csv files (B1, B2)",
-    )
-    parser.add_argument("--gas-csv", required=True, help="Path to total_gas.csv")
-    parser.add_argument(
-        "--output-summary", required=True, help="Output JSON summary path"
-    )
-    parser.add_argument("--output-markdown", required=True, help="Output markdown path")
-    parser.add_argument(
-        "--repo", default="paradigmxyz/reth", help="GitHub repo (owner/name)"
-    )
-    parser.add_argument("--baseline-ref", default=None, help="Baseline commit SHA")
-    parser.add_argument("--baseline-name", default=None, help="Baseline display name")
-    parser.add_argument("--feature-name", "--branch-name", default=None, help="Feature branch name")
-    parser.add_argument("--feature-ref", "--branch-sha", "--feature-sha", default=None, help="Feature commit SHA")
-    parser.add_argument("--behind-baseline", "--behind-main", type=int, default=0, help="Commits behind baseline")
-    parser.add_argument("--big-blocks", action="store_true", default=False, help="Big blocks mode")
-    parser.add_argument("--warmup-blocks", default=None, help="Number of warmup blocks")
-    parser.add_argument("--wait-time", default=None, help="Wait time interval used between blocks")
-    parser.add_argument("--bal-mode", default=None, help="BAL mode (true, feature, baseline)")
-    parser.add_argument("--grafana-url", default=None, help="Grafana dashboard URL for this benchmark run")
-    args = parser.parse_args()
-
-    if len(args.baseline_csv) != len(args.feature_csv):
-        print("Must provide equal number of baseline and feature CSVs", file=sys.stderr)
-        sys.exit(1)
-
-    baseline_runs = []
-    feature_runs = []
-    for path in args.baseline_csv:
-        data = parse_combined_csv(path)
-        if not data:
-            print(f"No results in {path}", file=sys.stderr)
-            sys.exit(1)
-        baseline_runs.append(data)
-    for path in args.feature_csv:
-        data = parse_combined_csv(path)
-        if not data:
-            print(f"No results in {path}", file=sys.stderr)
-            sys.exit(1)
-        feature_runs.append(data)
-
-    gas = parse_gas_csv(args.gas_csv)
-
-    all_baseline = [r for run in baseline_runs for r in run]
-    all_feature = [r for run in feature_runs for r in run]
-
-    baseline_stats = compute_stats(all_baseline)
-    feature_stats = compute_stats(all_feature)
-    paired_stats = compute_paired_stats(baseline_runs, feature_runs)
-
-    if not paired_stats:
-        print("No common blocks between baseline and feature runs", file=sys.stderr)
-        sys.exit(1)
-
-    baseline_ref = args.baseline_ref or "main"
-    baseline_name = args.baseline_name or "baseline"
-    feature_name = args.feature_name or "feature"
-    feature_sha = args.feature_ref or "unknown"
-    bal_mode = display_bal_mode(args.bal_mode)
-
-    comparison_table = generate_comparison_table(
-        baseline_stats,
-        feature_stats,
-        paired_stats,
-        repo=args.repo,
-        baseline_ref=baseline_ref,
-        baseline_name=baseline_name,
-        feature_name=feature_name,
-        feature_sha=feature_sha,
-        big_blocks=args.big_blocks,
-        warmup_blocks=args.warmup_blocks,
-        wait_time=args.wait_time,
-        bal_mode=bal_mode,
-    )
-    print(f"Generated comparison ({paired_stats['n']} paired blocks, "
-          f"mean diff {paired_stats['mean_diff_ms']:+.3f}ms ± {paired_stats['ci_ms']:.3f}ms)")
-
-    base_url = f"https://github.com/{args.repo}/commit"
-    baseline_label = f"[`{baseline_name}`]({base_url}/{baseline_ref})"
-    feature_label = f"[`{feature_name}`]({base_url}/{feature_sha})"
-
-    wait_fields = [
-        ("persistence_wait_us", "Persistence Wait"),
-        ("sparse_trie_wait_us", "Trie Cache Update Wait"),
-        ("execution_cache_wait_us", "Execution Cache Update Wait"),
-    ]
-    wait_time_tables = []
-    wait_time_data = {}
-    for field, title in wait_fields:
-        b_stats = compute_wait_stats(all_baseline, field)
-        f_stats = compute_wait_stats(all_feature, field)
-        if b_stats and f_stats:
-            wait_time_data[field] = {
-                "title": title,
-                "baseline": b_stats,
-                "feature": f_stats,
-            }
-        table = generate_wait_time_table(title, b_stats, f_stats, baseline_label, feature_label)
-        if table:
-            wait_time_tables.append(table)
-
-    summary = {
-        "blocks": paired_stats["blocks"],
-        "big_blocks": args.big_blocks,
-        "warmup_blocks": args.warmup_blocks,
-        "wait_time": args.wait_time,
-        "bal_mode": bal_mode,
-        "baseline": {
-            "name": baseline_name,
-            "ref": baseline_ref,
-            "stats": baseline_stats,
-        },
-        "feature": {
-            "name": feature_name,
-            "ref": feature_sha,
-            "stats": feature_stats,
-        },
-        "paired": paired_stats,
-        "changes": compute_changes(baseline_stats, feature_stats, paired_stats),
-        "wait_times": wait_time_data,
-    }
-    with open(args.output_summary, "w") as f:
-        json.dump(summary, f, indent=2)
-    print(f"Summary written to {args.output_summary}")
-
-    markdown = generate_markdown(
-        summary, comparison_table,
-        wait_time_tables=wait_time_tables,
-        behind_baseline=args.behind_baseline,
-        repo=args.repo,
-        baseline_ref=baseline_ref,
-        baseline_name=baseline_name,
-        grafana_url=args.grafana_url,
-    )
-
-    with open(args.output_markdown, "w") as f:
-        f.write(markdown)
-    print(f"Markdown written to {args.output_markdown}")
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/bench-scheduled-refs.sh

@@ -1,336 +0,0 @@
-#!/usr/bin/env bash
-#
-# Resolves baseline and feature refs for scheduled benchmark runs.
-#
-# Supports three modes:
-#   nightly — Queries the latest successful scheduled docker.yml run via
-#             GitHub API to find the nightly Docker image commit. Compares
-#             with the last successful feature ref to detect staleness.
-#   hourly  — Compares origin/main HEAD against the last successfully
-#             benchmarked commit (falls back to HEAD~1 on first run).
-#             Checks for in-progress sibling runs to avoid overlap.
-#   release — Compares the latest GitHub release tag against the current
-#             nightly Docker build. Baseline is the release tag commit,
-#             feature is the nightly commit.
-#
-# Usage: bench-scheduled-refs.sh <force> <mode>
-#   force — "true" to run even if no new commit (bypass skip logic)
-#   mode  — "nightly", "hourly", or "release"
-#
-# Outputs (via GITHUB_OUTPUT):
-#   baseline-ref    — commit SHA for baseline
-#   feature-ref     — commit SHA for feature
-#   should-skip     — "true" if no new commit since last run or sibling in progress
-#   is-stale        — "true" if latest nightly build is >24h old (nightly only)
-#   stale-age-hours — age of the nightly build in hours (nightly only)
-#   nightly-created — ISO timestamp of the nightly build (nightly only)
-#   release-tag     — release tag name (release mode only, e.g. "v2.0.0")
-#
-# Reads:
-#   state/nightly-last-feature-ref  (nightly, from decofe/reth-bench-charts repo)
-#   state/hourly-last-feature-ref   (hourly, from decofe/reth-bench-charts repo)
-#   state/release-last-feature-ref  (release, from decofe/reth-bench-charts repo)
-#
-# Requires: gh (GitHub CLI), jq, date, git (hourly mode), curl, DEREK_TOKEN env
-set -euxo pipefail
-
-FORCE="${1:-false}"
-MODE="${2:-nightly}"
-REPO="${GITHUB_REPOSITORY:-paradigmxyz/reth}"
-
-echo "Mode: $MODE, Force: $FORCE"
-
-# ==========================================================================
-# Hourly mode: compare origin/main HEAD vs HEAD~1
-# ==========================================================================
-if [ "$MODE" = "hourly" ]; then
-
-  # --- Step 1: Resolve feature ref from git ---
-  echo "::group::Resolving hourly refs from git"
-  git fetch origin main --depth=2 --quiet
-  FEATURE_REF=$(git rev-parse origin/main)
-  echo "Feature (HEAD): $FEATURE_REF"
-  echo "::endgroup::"
-
-  # --- Step 2: Check for in-progress sibling runs ---
-  echo "::group::Checking for in-progress sibling runs"
-  CURRENT_RUN_ID="${GITHUB_RUN_ID:-0}"
-  IN_PROGRESS=$(gh run list \
-    -R "$REPO" \
-    --workflow=bench-scheduled.yml \
-    --status=in_progress \
-    --json databaseId \
-    --jq "[.[] | select(.databaseId != $CURRENT_RUN_ID)] | length")
-
-  SHOULD_SKIP="false"
-  if [ "$IN_PROGRESS" -gt 0 ]; then
-    echo "::warning::Previous bench run still in progress ($IN_PROGRESS sibling run(s) found). Skipping."
-    SHOULD_SKIP="true"
-    # Output a flag so the workflow can send a Slack alert
-    echo "long-running=true" >> "$GITHUB_OUTPUT"
-  else
-    echo "No in-progress sibling runs"
-    echo "long-running=false" >> "$GITHUB_OUTPUT"
-  fi
-  echo "::endgroup::"
-
-  # --- Step 3: Read last successful feature ref from charts repo ---
-  echo "::group::Reading persisted state"
-  LAST_FEATURE_REF=""
-  STATE_URL="https://raw.githubusercontent.com/decofe/reth-bench-charts/state/state/hourly-last-feature-ref"
-  if RAW=$(curl -sfL -H "Authorization: token ${DEREK_TOKEN}" "$STATE_URL"); then
-    LAST_FEATURE_REF=$(echo "$RAW" | tr -d '[:space:]')
-    echo "Previous feature ref: $LAST_FEATURE_REF"
-  else
-    echo "No persisted state found (first run)"
-  fi
-  echo "::endgroup::"
-
-  # --- Step 4: Determine baseline and skip logic ---
-  echo "::group::Resolving baseline and skip logic"
-  if [ "$SHOULD_SKIP" = "true" ]; then
-    BASELINE_REF=$(git rev-parse origin/main~1)
-    echo "Already marked skip (sibling in progress)"
-  elif [ -z "$LAST_FEATURE_REF" ]; then
-    # First run: no previous state, fall back to HEAD~1
-    BASELINE_REF=$(git rev-parse origin/main~1)
-    echo "First run — using HEAD~1 as baseline"
-  elif [ "$LAST_FEATURE_REF" = "$FEATURE_REF" ]; then
-    BASELINE_REF="$LAST_FEATURE_REF"
-    if [ "$FORCE" = "true" ] || [ "$FORCE" = "--force" ]; then
-      echo "No new commits on main, but force=true — running anyway"
-    else
-      SHOULD_SKIP="true"
-      echo "No new commits on main since last run — will skip"
-    fi
-  else
-    # Normal case: use last benchmarked commit as baseline
-    BASELINE_REF="$LAST_FEATURE_REF"
-    echo "New commit(s) on main detected — comparing against last benchmarked commit"
-  fi
-
-  echo "Baseline: $BASELINE_REF"
-  echo "Feature:  $FEATURE_REF"
-  echo "Skip:     $SHOULD_SKIP"
-  echo "::endgroup::"
-
-  # --- Step 5: Write outputs ---
-  {
-    echo "baseline-ref=$BASELINE_REF"
-    echo "feature-ref=$FEATURE_REF"
-    echo "should-skip=$SHOULD_SKIP"
-    echo "is-stale=false"
-    echo "stale-age-hours=0"
-    echo "nightly-created="
-  } >> "$GITHUB_OUTPUT"
-  exit 0
-fi
-
-# ==========================================================================
-# Release mode: compare latest GitHub release tag vs current nightly build
-# ==========================================================================
-if [ "$MODE" = "release" ]; then
-
-  # --- Step 1: Resolve feature ref from latest nightly Docker build ---
-  echo "::group::Querying latest nightly docker build"
-  RUNS_JSON=$(gh run list \
-    -R "$REPO" \
-    --workflow=docker.yml \
-    --event=schedule \
-    --status=completed \
-    --limit 5 \
-    --json headSha,createdAt,conclusion)
-
-  LATEST=$(echo "$RUNS_JSON" | jq -r '[.[] | select(.conclusion == "success")] | first // empty')
-  if [ -z "$LATEST" ]; then
-    echo "::error::No successful scheduled docker.yml run found in the last 5 runs"
-    exit 1
-  fi
-
-  FEATURE_REF=$(echo "$LATEST" | jq -r '.headSha')
-  echo "Nightly commit (feature): $FEATURE_REF"
-  echo "::endgroup::"
-
-  # --- Step 2: Resolve baseline ref from latest GitHub release ---
-  echo "::group::Resolving latest release tag"
-  RELEASE_JSON=$(gh release view --repo "$REPO" --json tagName,targetCommitish,publishedAt 2>/dev/null || echo "{}")
-  RELEASE_TAG=$(echo "$RELEASE_JSON" | jq -r '.tagName // empty')
-
-  if [ -z "$RELEASE_TAG" ]; then
-    echo "::error::No release found on $REPO"
-    exit 1
-  fi
-
-  # Resolve the tag to a commit SHA
-  BASELINE_REF=$(gh api "repos/$REPO/git/ref/tags/$RELEASE_TAG" --jq '.object.sha' 2>/dev/null || true)
-
-  # If tag points to an annotated tag object, dereference to the commit
-  if [ -n "$BASELINE_REF" ]; then
-    OBJ_TYPE=$(gh api "repos/$REPO/git/tags/$BASELINE_REF" --jq '.object.type' 2>/dev/null || echo "commit")
-    if [ "$OBJ_TYPE" = "commit" ]; then
-      BASELINE_REF=$(gh api "repos/$REPO/git/tags/$BASELINE_REF" --jq '.object.sha' 2>/dev/null || echo "$BASELINE_REF")
-    fi
-  fi
-
-  if [ -z "$BASELINE_REF" ]; then
-    echo "::error::Could not resolve release tag $RELEASE_TAG to a commit"
-    exit 1
-  fi
-
-  echo "Release tag: $RELEASE_TAG"
-  echo "Release commit (baseline): $BASELINE_REF"
-  echo "::endgroup::"
-
-  # --- Step 3: Read last successful feature ref from charts repo ---
-  echo "::group::Reading persisted state"
-  LAST_FEATURE_REF=""
-  STATE_URL="https://raw.githubusercontent.com/decofe/reth-bench-charts/state/state/release-last-feature-ref"
-  if RAW=$(curl -sfL -H "Authorization: token ${DEREK_TOKEN}" "$STATE_URL"); then
-    LAST_FEATURE_REF=$(echo "$RAW" | tr -d '[:space:]')
-    echo "Previous feature ref: $LAST_FEATURE_REF"
-  else
-    echo "No persisted state found (first run)"
-  fi
-  echo "::endgroup::"
-
-  # --- Step 4: Skip logic ---
-  echo "::group::Resolving skip logic"
-  SHOULD_SKIP="false"
-  if [ -n "$LAST_FEATURE_REF" ] && [ "$LAST_FEATURE_REF" = "$FEATURE_REF" ]; then
-    if [ "$FORCE" = "true" ] || [ "$FORCE" = "--force" ]; then
-      echo "No new nightly, but force=true — running anyway"
-    else
-      SHOULD_SKIP="true"
-      echo "No new nightly since last release regression run — will skip"
-    fi
-  else
-    echo "New nightly detected or first run"
-  fi
-
-  echo "Baseline: $BASELINE_REF ($RELEASE_TAG)"
-  echo "Feature:  $FEATURE_REF"
-  echo "Skip:     $SHOULD_SKIP"
-  echo "::endgroup::"
-
-  # --- Step 5: Write outputs ---
-  {
-    echo "baseline-ref=$BASELINE_REF"
-    echo "feature-ref=$FEATURE_REF"
-    echo "should-skip=$SHOULD_SKIP"
-    echo "is-stale=false"
-    echo "stale-age-hours=0"
-    echo "nightly-created="
-    echo "long-running=false"
-    echo "release-tag=$RELEASE_TAG"
-  } >> "$GITHUB_OUTPUT"
-  exit 0
-fi
-
-# ==========================================================================
-# Nightly mode: query latest Docker nightly build (original logic)
-# ==========================================================================
-
-# --- Step 1: Query latest successful scheduled docker.yml run ---
-echo "::group::Querying latest nightly docker build"
-
-RUNS_JSON=$(gh run list \
-  -R "$REPO" \
-  --workflow=docker.yml \
-  --event=schedule \
-  --status=completed \
-  --limit 5 \
-  --json headSha,createdAt,conclusion)
-
-# Find the most recent successful run
-LATEST=$(echo "$RUNS_JSON" | jq -r '[.[] | select(.conclusion == "success")] | first // empty')
-
-if [ -z "$LATEST" ]; then
-  echo "::error::No successful scheduled docker.yml run found in the last 5 runs"
-  echo "Runs found: $RUNS_JSON"
-  exit 1
-fi
-
-FEATURE_REF=$(echo "$LATEST" | jq -r '.headSha')
-CREATED_AT=$(echo "$LATEST" | jq -r '.createdAt')
-echo "Latest nightly commit: $FEATURE_REF"
-echo "Built at: $CREATED_AT"
-echo "::endgroup::"
-
-# --- Step 2: Staleness check ---
-echo "::group::Checking staleness"
-NOW_EPOCH=$(date +%s)
-# Handle both GNU date (-d) and BSD date (-j -f) for cross-platform compat
-CREATED_EPOCH=$(date -d "$CREATED_AT" +%s 2>/dev/null || \
-  date -j -f "%Y-%m-%dT%H:%M:%SZ" "$CREATED_AT" +%s 2>/dev/null || \
-  date -j -f "%Y-%m-%dT%T%z" "$CREATED_AT" +%s 2>/dev/null || \
-  { echo "::error::Cannot parse date: $CREATED_AT"; exit 1; })
-
-AGE_SECONDS=$(( NOW_EPOCH - CREATED_EPOCH ))
-AGE_HOURS=$(( AGE_SECONDS / 3600 ))
-IS_STALE="false"
-
-if [ "$AGE_HOURS" -gt 24 ]; then
-  IS_STALE="true"
-  echo "::warning::STALE NIGHTLY: Build is ${AGE_HOURS}h old (>24h threshold)"
-  echo "This indicates the nightly docker build failed — no new image was produced"
-else
-  echo "Nightly build age: ${AGE_HOURS}h (within 24h threshold)"
-fi
-echo "::endgroup::"
-
-# --- Step 3: Read last successful feature ref from charts repo ---
-echo "::group::Reading persisted state"
-LAST_FEATURE_REF=""
-STATE_URL="https://raw.githubusercontent.com/decofe/reth-bench-charts/state/state/nightly-last-feature-ref"
-if RAW=$(curl -sfL -H "Authorization: token ${DEREK_TOKEN}" "$STATE_URL"); then
-  LAST_FEATURE_REF=$(echo "$RAW" | tr -d '[:space:]')
-  echo "Previous feature ref: $LAST_FEATURE_REF"
-else
-  echo "No persisted state found (first run)"
-fi
-echo "::endgroup::"
-
-# --- Step 4: Determine baseline and skip logic ---
-echo "::group::Resolving refs"
-SHOULD_SKIP="false"
-BASELINE_REF="$FEATURE_REF"  # default for first run
-
-if [ "$IS_STALE" = "true" ]; then
-  # Stale = error path, don't skip (will alert and fail downstream)
-  SHOULD_SKIP="false"
-  BASELINE_REF="${LAST_FEATURE_REF:-$FEATURE_REF}"
-  echo "Stale nightly detected — will alert and fail"
-elif [ -z "$LAST_FEATURE_REF" ]; then
-  # First run: baseline = feature (self-comparison to establish baseline)
-  BASELINE_REF="$FEATURE_REF"
-  echo "First run — will benchmark nightly against itself to establish baseline"
-elif [ "$LAST_FEATURE_REF" = "$FEATURE_REF" ]; then
-  # No new nightly since last successful run
-  if [ "$FORCE" = "true" ] || [ "$FORCE" = "--force" ]; then
-    echo "No new nightly, but force=true — running anyway"
-    BASELINE_REF="$LAST_FEATURE_REF"
-  else
-    SHOULD_SKIP="true"
-    echo "No new nightly since last run — will skip"
-  fi
-else
-  # Normal case: new nightly available
-  BASELINE_REF="$LAST_FEATURE_REF"
-  echo "New nightly detected"
-fi
-
-echo "Baseline: $BASELINE_REF"
-echo "Feature:  $FEATURE_REF"
-echo "Skip:     $SHOULD_SKIP"
-echo "Stale:    $IS_STALE"
-echo "::endgroup::"
-
-# --- Step 5: Write outputs ---
-{
-  echo "baseline-ref=$BASELINE_REF"
-  echo "feature-ref=$FEATURE_REF"
-  echo "should-skip=$SHOULD_SKIP"
-  echo "is-stale=$IS_STALE"
-  echo "stale-age-hours=$AGE_HOURS"
-  echo "nightly-created=$CREATED_AT"
-} >> "$GITHUB_OUTPUT"

.github/scripts/bench-slack-notify.js

@@ -1,318 +0,0 @@
-// Sends Slack notifications for reth-bench results.
-//
-// Reads from environment:
-//   SLACK_BENCH_BOT_TOKEN  – Slack Bot User OAuth Token (xoxb-...)
-//   SLACK_BENCH_CHANNEL    – Public channel ID for significant improvements
-//   BENCH_WORK_DIR         – Directory containing summary.json
-//   BENCH_PR               – PR number (may be empty)
-//   BENCH_ACTOR            – GitHub user who triggered the bench
-//   BENCH_JOB_URL          – URL to the Actions job page
-//   BENCH_BASELINE_ARGS    – Extra CLI args for the baseline reth node
-//   BENCH_FEATURE_ARGS     – Extra CLI args for the feature reth node
-//   BENCH_SAMPLY           – 'true' if samply profiling was enabled
-//
-// Usage from actions/github-script:
-//   const notify = require('./.github/scripts/bench-slack-notify.js');
-//   await notify.success({ core, context });
-//   await notify.failure({ core, context, failedStep: '...' });
-
-const fs = require('fs');
-const path = require('path');
-const { fmtChange, fmtMs, verdict, loadSamplyUrls, blocksLabel, metricRows, waitTimeRows } = require('./bench-utils');
-
-const SLACK_API = 'https://slack.com/api/chat.postMessage';
-
-function loadSlackUsers(repoRoot) {
-  try {
-    const raw = fs.readFileSync(path.join(repoRoot, '.github', 'scripts', 'bench-slack-users.json'), 'utf8');
-    const data = JSON.parse(raw);
-    // Filter out non-user-ID entries (like _comment)
-    const users = {};
-    for (const [k, v] of Object.entries(data)) {
-      if (!k.startsWith('_') && typeof v === 'string' && v.startsWith('U')) {
-        users[k] = v;
-      }
-    }
-    return users;
-  } catch {
-    return {};
-  }
-}
-
-async function postToSlack(token, channel, blocks, text, core, threadTs) {
-  const payload = { channel, blocks, text, unfurl_links: false };
-  if (threadTs) payload.thread_ts = threadTs;
-  const resp = await fetch(SLACK_API, {
-    method: 'POST',
-    headers: {
-      'Authorization': `Bearer ${token}`,
-      'Content-Type': 'application/json',
-    },
-    body: JSON.stringify(payload),
-  });
-  const data = await resp.json();
-  if (!data.ok) {
-    core.warning(`Slack API error (channel ${channel}): ${JSON.stringify(data)}`);
-  }
-  return data;
-}
-
-function cell(text) {
-  const s = String(text);
-  return { type: 'raw_text', text: s || ' ' };
-}
-
-// Slack shortcodes for verdict (Block Kit header doesn't support unicode emoji)
-const SLACK_VERDICT = {
-  '⚠️': ':warning:',
-  '❌': ':x:',
-  '✅': ':white_check_mark:',
-  '⚪': ':white_circle:',
-};
-
-function buildSuccessBlocks({ summary, prNumber, actor, actorSlackId, jobUrl, repo, samplyUrls }) {
-  const { emoji, label } = verdict(summary.changes);
-  const headerEmoji = SLACK_VERDICT[emoji] || emoji;
-
-  const prUrl = prNumber ? `https://github.com/${repo}/pull/${prNumber}` : '';
-  const commitUrl = `https://github.com/${repo}/commit`;
-  const baselineLink = `<${commitUrl}/${summary.baseline.ref}|${summary.baseline.name}>`;
-  const featureLink = `<${commitUrl}/${summary.feature.ref}|${summary.feature.name}>`;
-
-  // Meta line
-  const metaParts = [];
-  if (prNumber) metaParts.push(`*<${prUrl}|PR #${prNumber}>*`);
-  metaParts.push(`triggered by ${actorSlackId ? `<@${actorSlackId}>` : `@${actor}`}`);
-
-  // Baseline/feature lines with samply profile links
-  let baselineLine = `*Baseline:* ${baselineLink}`;
-  const bl1 = samplyUrls['baseline-1'];
-  const bl2 = samplyUrls['baseline-2'];
-  if (bl1) baselineLine += ` | <${bl1}|Samply 1>`;
-  if (bl2) baselineLine += ` | <${bl2}|Samply 2>`;
-
-  let featureLine = `*Feature:* ${featureLink}`;
-  const fl1 = samplyUrls['feature-1'];
-  const fl2 = samplyUrls['feature-2'];
-  if (fl1) featureLine += ` | <${fl1}|Samply 1>`;
-  if (fl2) featureLine += ` | <${fl2}|Samply 2>`;
-
-  const countsLine = blocksLabel(summary).map(p => `*${p.key}:* ${p.value}`).join(' | ');
-
-  const baselineArgs = process.env.BENCH_BASELINE_ARGS || '';
-  const featureArgs = process.env.BENCH_FEATURE_ARGS || '';
-  const argsLines = [];
-  if (baselineArgs) argsLines.push(`*Baseline Args:* \`${baselineArgs}\``);
-  if (featureArgs) argsLines.push(`*Feature Args:* \`${featureArgs}\``);
-
-  const sectionText = [metaParts.join(' | '), '', baselineLine, featureLine, ...argsLines, countsLine].join('\n');
-
-  // Action buttons
-  const diffUrl = `https://github.com/${repo}/compare/${summary.baseline.ref}...${summary.feature.ref}`;
-  const buttons = [
-    {
-      type: 'button',
-      text: { type: 'plain_text', text: 'CI :github:', emoji: true },
-      url: jobUrl,
-      action_id: 'ci_button',
-    },
-    {
-      type: 'button',
-      text: { type: 'plain_text', text: 'Diff :github:', emoji: true },
-      url: diffUrl,
-      action_id: 'diff_button',
-    },
-  ];
-
-  // Build table rows from shared metricRows
-  const rows = metricRows(summary);
-  const tableRows = [
-    [cell('Metric'), cell('Baseline'), cell('Feature'), cell('Change')],
-    ...rows.map(r => [cell(r.label), cell(r.baseline), cell(r.feature), cell(r.change || ' ')]),
-  ];
-
-  const blocks = [
-    {
-      type: 'header',
-      text: { type: 'plain_text', text: `${headerEmoji} ${label}`, emoji: true },
-    },
-    {
-      type: 'section',
-      text: { type: 'mrkdwn', text: sectionText },
-    },
-    {
-      type: 'table',
-      column_settings: [
-        { align: 'left' },
-        { align: 'right' },
-        { align: 'right' },
-        { align: 'right' },
-      ],
-      rows: tableRows,
-    },
-    {
-      type: 'actions',
-      elements: buttons,
-    },
-  ];
-
-  // Wait times as a separate table block (sent as threaded reply due to Slack one-table limit)
-  const threadBlocks = [];
-  const wtRows = waitTimeRows(summary);
-  if (wtRows.length > 0) {
-    const waitTableRows = [
-      [cell('Wait Time'), cell('Baseline'), cell('Feature')],
-      ...wtRows.map(r => [cell(r.title), cell(r.baseline), cell(r.feature)]),
-    ];
-    threadBlocks.push({
-      type: 'table',
-      column_settings: [
-        { align: 'left' },
-        { align: 'right' },
-        { align: 'right' },
-      ],
-      rows: waitTableRows,
-    });
-  }
-
-  return { blocks, threadBlocks };
-}
-
-function buildFailureBlocks({ prNumber, actor, actorSlackId, jobUrl, repo, failedStep }) {
-  const prUrl = prNumber ? `https://github.com/${repo}/pull/${prNumber}` : '';
-  const actorMention = actorSlackId ? `<@${actorSlackId}>` : `@${actor}`;
-  const parts = [
-    prNumber ? `*<${prUrl}|PR #${prNumber}>*` : '',
-    `by ${actorMention}`,
-    `failed while *${failedStep}*`,
-  ].filter(Boolean);
-
-  const buttons = [
-    {
-      type: 'button',
-      text: { type: 'plain_text', text: 'CI :github:', emoji: true },
-      url: jobUrl,
-      action_id: 'ci_button',
-    },
-  ];
-
-  return [
-    {
-      type: 'header',
-      text: { type: 'plain_text', text: ':rotating_light: Bench Failed', emoji: true },
-    },
-    {
-      type: 'section',
-      text: { type: 'mrkdwn', text: parts.join(' | ') },
-    },
-    {
-      type: 'actions',
-      elements: buttons,
-    },
-  ];
-}
-
-async function success({ core, context }) {
-  const token = process.env.SLACK_BENCH_BOT_TOKEN;
-  if (!token) {
-    core.info('SLACK_BENCH_BOT_TOKEN not set, skipping Slack notification');
-    return;
-  }
-
-  let summary;
-  try {
-    summary = JSON.parse(fs.readFileSync(process.env.BENCH_WORK_DIR + '/summary.json', 'utf8'));
-  } catch (e) {
-    core.warning('Could not read summary.json for Slack notification');
-    return;
-  }
-
-  const repo = `${context.repo.owner}/${context.repo.repo}`;
-  const prNumber = process.env.BENCH_PR;
-  const actor = process.env.BENCH_ACTOR;
-  const jobUrl = process.env.BENCH_JOB_URL ||
-    `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
-
-  const samplyUrls = loadSamplyUrls(process.env.BENCH_WORK_DIR);
-
-  const slackUsers = loadSlackUsers(process.env.GITHUB_WORKSPACE || '.');
-  const actorSlackId = slackUsers[actor];
-
-  const { blocks, threadBlocks } = buildSuccessBlocks({ summary, prNumber, actor, actorSlackId, jobUrl, repo, samplyUrls });
-  const text = `Bench: ${summary.baseline.name} vs ${summary.feature.name}`;
-
-  async function sendWithThread(ch) {
-    const res = await postToSlack(token, ch, blocks, text, core);
-    if (res.ok && res.ts && threadBlocks.length > 0) {
-      for (const tb of threadBlocks) {
-        await postToSlack(token, ch, [tb], 'Wait time breakdown', core, res.ts);
-      }
-    }
-  }
-
-  const slackMode = process.env.BENCH_SLACK || 'always';
-
-  // Post to public channel if any metric shows significant improvement or regression
-  const channel = process.env.SLACK_BENCH_CHANNEL;
-  let postedToChannel = false;
-  if (channel) {
-    const changes = summary.changes || {};
-    const hasImprovement = Object.values(changes).some(c => c.sig === 'good');
-    if (hasImprovement) {
-      await sendWithThread(channel);
-      postedToChannel = true;
-    } else {
-      core.info('No significant improvement, skipping public channel notification');
-    }
-  }
-
-  // In on-win mode, only notify on improvement — skip DM fallback entirely
-  if (slackMode === 'on-win') {
-    if (!postedToChannel) {
-      core.info('on-win mode: no improvement detected, skipping all notifications');
-    }
-    return;
-  }
-
-  // DM the actor only when results were not posted to the public channel
-  if (!postedToChannel) {
-    if (actorSlackId) {
-      await sendWithThread(actorSlackId);
-    } else {
-      core.info(`No Slack user mapping for GitHub user '${actor}', skipping DM`);
-    }
-  } else {
-    core.info(`Results posted to channel, skipping DM to ${actor}`);
-  }
-}
-
-async function failure({ core, context, failedStep }) {
-  const token = process.env.SLACK_BENCH_BOT_TOKEN;
-  if (!token) {
-    core.info('SLACK_BENCH_BOT_TOKEN not set, skipping Slack notification');
-    return;
-  }
-
-  const repo = `${context.repo.owner}/${context.repo.repo}`;
-  const prNumber = process.env.BENCH_PR;
-  const actor = process.env.BENCH_ACTOR;
-  const jobUrl = process.env.BENCH_JOB_URL ||
-    `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
-
-  const slackUsers = loadSlackUsers(process.env.GITHUB_WORKSPACE || '.');
-  const actorSlackId = slackUsers[actor];
-
-  const blocks = buildFailureBlocks({ prNumber, actor, actorSlackId, jobUrl, repo, failedStep });
-  const text = `Bench failed while ${failedStep}`;
-
-  // Always DM the actor
-  if (actorSlackId) {
-    await postToSlack(token, actorSlackId, blocks, text, core);
-  } else {
-    core.info(`No Slack user mapping for GitHub user '${actor}', skipping DM`);
-  }
-
-  // Only DM for failures, don't post to public channel
-}
-
-module.exports = { success, failure };

.github/scripts/bench-slack-users.json

@@ -1,25 +0,0 @@
-{
-  "_comment": "Maps GitHub usernames to Slack user IDs. Find yours: Slack profile > ··· > Copy member ID.",
-  "shekhirin": "U09FAL2UMLJ",
-  "mattsse": "U09FQNPMRT3",
-  "klkvr": "U09FAK95FC2",
-  "joshieDo": "U09LHN6GYAU",
-  "mediocregopher": "U09FF75KMQU",
-  "yongkangc": "U09FB0ECTD4",
-  "gakonst": "U092SEPDM40",
-  "Rjected": "U09F6SCKRGT",
-  "DaniPopes": "U09FAT8EK2A",
-  "emmajam": "U0A34UN92HW",
-  "onbjerg": "U09FB0UK5AA",
-  "fgimenez": "U09G3GP7CSU",
-  "rakita": "U09FB3Z2M7Y",
-  "jxom": "U09F72MG083",
-  "tmm": "U0AD0U8E88N",
-  "pepyakin": "U0A7HKMGEHJ",
-  "grandizzy": "U09F8DBDDRT",
-  "SuperFluffy": "U095BKHB2Q4",
-  "kamsz": "U0A2563UBRD",
-  "zerosnacks": "U09FARPMN74",
-  "samczsun": "U096R14E4H3",
-  "laibe": "U09FARE0B9Q"
-}

.github/scripts/bench-update-status.js

@@ -1,27 +0,0 @@
-// Updates the reth-bench PR comment with current status.
-//
-// Reads from environment:
-//   BENCH_COMMENT_ID  – GitHub comment ID to update
-//   BENCH_JOB_URL     – URL to the Actions job page
-//   BENCH_CONFIG      – Config line (blocks, warmup, refs)
-//   BENCH_ACTOR       – User who triggered the benchmark
-//
-// Usage from actions/github-script:
-//   const s = require('./.github/scripts/bench-update-status.js');
-//   await s({github, context, status: 'Building baseline binary...'});
-
-function buildBody(status) {
-  return `cc @${process.env.BENCH_ACTOR}\n\n🚀 Benchmark started! [View job](${process.env.BENCH_JOB_URL})\n\n⏳ **Status:** ${status}\n\n${process.env.BENCH_CONFIG}`;
-}
-
-async function updateStatus({ github, context, status }) {
-  await github.rest.issues.updateComment({
-    owner: context.repo.owner,
-    repo: context.repo.repo,
-    comment_id: parseInt(process.env.BENCH_COMMENT_ID),
-    body: buildBody(status),
-  });
-}
-
-updateStatus.buildBody = buildBody;
-module.exports = updateStatus;

.github/scripts/bench-upload-clickhouse.py

@@ -1,150 +0,0 @@
-#!/usr/bin/env python3
-"""Upload bench-scheduled summary.json results to ClickHouse.
-
-Reads the summary JSON produced by bench-reth-summary.py and inserts a row
-into the bench_dual_comparisons table so the PM dashboard can display results.
-
-Usage:
-    bench-upload-clickhouse.py \
-        --summary <summary.json> \
-        --workflow-name <name> \
-        --chain <chain>
-
-Environment variables:
-    CLICKHOUSE_HOST      ClickHouse host URL
-    CLICKHOUSE_USER      ClickHouse username
-    CLICKHOUSE_PASSWORD  ClickHouse password
-    CLICKHOUSE_DATABASE  ClickHouse database (default: "default")
-"""
-
-import argparse
-import json
-import os
-import sys
-import urllib.request
-import urllib.error
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Upload benchmark results to ClickHouse")
-    parser.add_argument("--summary", required=True, help="Path to summary.json")
-    parser.add_argument("--workflow-name", required=True, help="Workflow name for ClickHouse")
-    parser.add_argument("--chain", default="mainnet", help="Chain name")
-    parser.add_argument("--grafana-url", default="", help="Grafana dashboard URL")
-    parser.add_argument("--github-diff-url", default="", help="GitHub diff URL")
-    parser.add_argument("--job-url", default="", help="CI job URL")
-    args = parser.parse_args()
-
-    ch_host = os.environ.get("CLICKHOUSE_HOST", "")
-    ch_user = os.environ.get("CLICKHOUSE_USER", "")
-    ch_password = os.environ.get("CLICKHOUSE_PASSWORD", "")
-    ch_database = os.environ.get("CLICKHOUSE_DATABASE", "default")
-    ch_table = "bench_dual_comparisons"
-
-    if not ch_host or not ch_user or not ch_password:
-        print("Missing ClickHouse credentials, skipping upload", file=sys.stderr)
-        sys.exit(0)
-
-    with open(args.summary) as f:
-        summary = json.load(f)
-
-    baseline = summary["baseline"]
-    feature = summary["feature"]
-    b_stats = baseline["stats"]
-    f_stats = feature["stats"]
-    changes = summary["changes"]
-    blocks = summary["blocks"]
-
-    # Extract wait time data
-    wait_times = summary.get("wait_times", {})
-    def wait_mean(field):
-        wt = wait_times.get(field, {})
-        b = wt.get("baseline", {}).get("mean_ms", 0.0)
-        f = wt.get("feature", {}).get("mean_ms", 0.0)
-        return b, f
-
-    b_persist, f_persist = wait_mean("persistence_wait_us")
-    b_exec_cache, f_exec_cache = wait_mean("execution_cache_wait_us")
-    b_sparse, f_sparse = wait_mean("sparse_trie_wait_us")
-
-    # gas_per_second: summary uses mean_mgas_s (Mgas/s), ClickHouse stores gas/s
-    b_gas_per_second = b_stats["mean_mgas_s"] * 1_000_000
-    f_gas_per_second = f_stats["mean_mgas_s"] * 1_000_000
-
-    mean_change = changes.get("mean", {}).get("pct", 0.0)
-    gas_change = changes.get("mgas_s", {}).get("pct", 0.0)
-    latency_improved = 1 if mean_change < 0 else 0
-    throughput_improved = 1 if gas_change > 0 else 0
-
-    big_blocks = "true" if summary.get("big_blocks", False) else "false"
-    warmup_blocks = summary.get("warmup_blocks", 0) or 0
-
-    def esc(s):
-        return str(s).replace("'", "\\'")
-
-    insert = f"""
-    INSERT INTO {ch_database}.{ch_table} (
-        workflow_name, chain,
-        baseline_ref, baseline_commit,
-        feature_ref, feature_commit,
-        blocks,
-        baseline_total_latency_ms, baseline_gas_per_second,
-        baseline_latency_mean_ms, baseline_latency_median_ms,
-        baseline_latency_p90_ms, baseline_latency_p99_ms,
-        feature_total_latency_ms, feature_gas_per_second,
-        feature_latency_mean_ms, feature_latency_median_ms,
-        feature_latency_p90_ms, feature_latency_p99_ms,
-        mean_latency_change_percent, gas_per_second_change_percent,
-        latency_improved, throughput_improved,
-        warmup_blocks, big_blocks,
-        grafana_benchmark_url, github_diff_url, argo_workflow_url,
-        baseline_persistence_wait_mean_ms, baseline_execution_cache_wait_mean_ms,
-        baseline_sparse_trie_wait_mean_ms,
-        feature_persistence_wait_mean_ms, feature_execution_cache_wait_mean_ms,
-        feature_sparse_trie_wait_mean_ms
-    ) VALUES (
-        '{esc(args.workflow_name)}', '{esc(args.chain)}',
-        '{esc(baseline["ref"])}', '{esc(baseline["ref"])}',
-        '{esc(feature["ref"])}', '{esc(feature["ref"])}',
-        {blocks},
-        {b_stats.get("wall_clock_s", 0) * 1000}, {b_gas_per_second},
-        {b_stats["mean_ms"]}, {b_stats["p50_ms"]},
-        {b_stats["p90_ms"]}, {b_stats["p99_ms"]},
-        {f_stats.get("wall_clock_s", 0) * 1000}, {f_gas_per_second},
-        {f_stats["mean_ms"]}, {f_stats["p50_ms"]},
-        {f_stats["p90_ms"]}, {f_stats["p99_ms"]},
-        {mean_change}, {gas_change},
-        {latency_improved}, {throughput_improved},
-        {warmup_blocks}, '{big_blocks}',
-        '{esc(args.grafana_url)}', '{esc(args.github_diff_url)}', '{esc(args.job_url)}',
-        {b_persist}, {b_exec_cache}, {b_sparse},
-        {f_persist}, {f_exec_cache}, {f_sparse}
-    );
-    """
-
-    # Build ClickHouse HTTP URL (credentials via headers, never in URL)
-    host = ch_host.rstrip("/")
-    if not host.startswith("http"):
-        host = f"https://{host}:8443"
-
-    url = f"{host}/?database={ch_database}"
-
-    req = urllib.request.Request(url, data=insert.encode("utf-8"), method="POST")
-    req.add_header("Content-Type", "text/plain")
-    req.add_header("X-ClickHouse-User", ch_user)
-    req.add_header("X-ClickHouse-Key", ch_password)
-
-    try:
-        with urllib.request.urlopen(req) as resp:
-            body = resp.read().decode("utf-8")
-            if body.strip():
-                print(f"ClickHouse response: {body}")
-        print(f"Successfully uploaded benchmark results to ClickHouse ({args.workflow_name})")
-    except urllib.error.HTTPError as e:
-        body = e.read().decode("utf-8")
-        print(f"ClickHouse upload failed ({e.code}): {body}", file=sys.stderr)
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/bench-utils.js

@@ -1,112 +0,0 @@
-// Shared utilities for reth-bench result rendering.
-//
-// Used by bench-job-summary.js and bench-slack-notify.js.
-
-const fs = require('fs');
-const path = require('path');
-
-const SIG_EMOJI = { good: '✅', bad: '❌', neutral: '⚪' };
-
-function fmtMs(v) { return v.toFixed(2) + 'ms'; }
-function fmtMgas(v) { return v.toFixed(2); }
-function fmtS(v) { return v.toFixed(2) + 's'; }
-
-function fmtChange(ch) {
-  if (!ch || (!ch.pct && !ch.ci_pct)) return '';
-  const pctStr = `${ch.pct >= 0 ? '+' : ''}${ch.pct.toFixed(2)}%`;
-  const ciStr = ch.ci_pct ? ` (±${ch.ci_pct.toFixed(2)}%)` : '';
-  return `${pctStr}${ciStr} ${SIG_EMOJI[ch.sig]}`;
-}
-
-function verdict(changes) {
-  const vals = Object.values(changes);
-  const hasBad = vals.some(v => v.sig === 'bad');
-  const hasGood = vals.some(v => v.sig === 'good');
-  if (hasBad && hasGood) return { emoji: '⚠️', label: 'Mixed Results' };
-  if (hasBad) return { emoji: '❌', label: 'Regression' };
-  if (hasGood) return { emoji: '✅', label: 'Improvement' };
-  return { emoji: '⚪', label: 'No Difference' };
-}
-
-function loadSamplyUrls(workDir) {
-  const urls = {};
-  for (const run of ['baseline-1', 'baseline-2', 'feature-1', 'feature-2']) {
-    try {
-      const url = fs.readFileSync(path.join(workDir, run, 'samply-profile-url.txt'), 'utf8').trim();
-      if (url) urls[run] = url;
-    } catch {}
-  }
-  return urls;
-}
-
-function balModeLabel(mode) {
-  switch (mode) {
-    case 'true':
-    case 'feature':
-    case 'baseline':
-      return mode;
-    case 'both':
-      return 'true';
-    default:
-      return '';
-  }
-}
-
-function blocksLabel(summary) {
-  const parts = [];
-  if (summary.big_blocks) {
-    parts.push({ key: 'Big Blocks', value: summary.blocks });
-    const balMode = balModeLabel(summary.bal_mode || summary.bal || process.env.BENCH_BAL || 'false');
-    if (balMode) parts.push({ key: 'BAL', value: balMode });
-  } else {
-    const warmup = summary.warmup_blocks || process.env.BENCH_WARMUP_BLOCKS || '';
-    if (warmup) parts.push({ key: 'Warmup', value: warmup });
-    parts.push({ key: 'Blocks', value: summary.blocks });
-  }
-  const cores = process.env.BENCH_CORES || '0';
-  if (cores !== '0') parts.push({ key: 'Cores', value: cores });
-  if (summary.wait_time) parts.push({ key: 'Wait time', value: summary.wait_time });
-  return parts;
-}
-
-// The 7 metric rows shared by all renderers.
-// Returns an array of { label, baseline, feature, change } objects.
-function metricRows(summary) {
-  const b = summary.baseline.stats;
-  const f = summary.feature.stats;
-  const c = summary.changes;
-  return [
-    { label: 'Mean',       baseline: fmtMs(b.mean_ms),       feature: fmtMs(f.mean_ms),       change: fmtChange(c.mean) },
-    { label: 'StdDev',     baseline: fmtMs(b.stddev_ms),     feature: fmtMs(f.stddev_ms),     change: '' },
-    { label: 'P50',        baseline: fmtMs(b.p50_ms),        feature: fmtMs(f.p50_ms),        change: fmtChange(c.p50) },
-    { label: 'P90',        baseline: fmtMs(b.p90_ms),        feature: fmtMs(f.p90_ms),        change: fmtChange(c.p90) },
-    { label: 'P99',        baseline: fmtMs(b.p99_ms),        feature: fmtMs(f.p99_ms),        change: fmtChange(c.p99) },
-    { label: 'Mgas/s',     baseline: fmtMgas(b.mean_mgas_s), feature: fmtMgas(f.mean_mgas_s), change: fmtChange(c.mgas_s) },
-    { label: 'Wall Clock', baseline: fmtS(b.wall_clock_s),   feature: fmtS(f.wall_clock_s),   change: fmtChange(c.wall_clock) },
-    { label: 'Persist Wait', baseline: fmtMs(b.mean_persist_ms || 0), feature: fmtMs(f.mean_persist_ms || 0), change: fmtChange(c.persist_wait) },
-  ];
-}
-
-// Wait time rows: one row per metric showing mean values.
-function waitTimeRows(summary) {
-  const waitTimes = summary.wait_times || {};
-  const rows = [];
-  for (const key of Object.keys(waitTimes)) {
-    const wt = waitTimes[key];
-    rows.push({ title: wt.title, baseline: fmtMs(wt.baseline.mean_ms), feature: fmtMs(wt.feature.mean_ms) });
-  }
-  return rows;
-}
-
-module.exports = {
-  SIG_EMOJI,
-  fmtMs,
-  fmtMgas,
-  fmtS,
-  fmtChange,
-  verdict,
-  loadSamplyUrls,
-  blocksLabel,
-  metricRows,
-  waitTimeRows,
-};

.github/scripts/check_rv32imac.sh

@@ -1,7 +1,10 @@
 #!/usr/bin/env bash
-set -uxo pipefail
+set -uo pipefail
 
 crates_to_check=(
+    reth-codecs-derive
+    reth-primitives
+    reth-primitives-traits
     reth-network-peers
     reth-trie-common
     reth-trie-sparse

.github/scripts/check_wasm.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-set -uxo pipefail
+set -uo pipefail
 
 readarray -t crates < <(
   cargo metadata --format-version=1 --no-deps | jq -r '.packages[].name' | grep '^reth' | sort
@@ -22,7 +22,6 @@ exclude_crates=(
   reth-downloaders
   reth-e2e-test-utils
   reth-engine-service
-  reth-execution-cache
   reth-engine-tree
   reth-engine-util
   reth-eth-wire
@@ -56,7 +55,6 @@ exclude_crates=(
   reth-ress-provider
   # The following are not supposed to be working
   reth # all of the crates below
-  reth-bb # binary-only, uses tokio features unsupported on wasm
   reth-storage-rpc-provider
   reth-invalid-block-hooks # reth-provider
   reth-libmdbx # mdbx

.github/scripts/fetch-grafana-dashboard.py

@@ -1,244 +0,0 @@
-#!/usr/bin/env python3
-"""
-Fetch a Grafana dashboard and convert it to the portable import format.
-
-Fetches the dashboard via API, replaces internal datasource/variable references
-with template variables, and adds __inputs/__requires/__elements so the JSON is
-importable on any Grafana instance.
-
-Usage:
-    export FETCH_GRAFANA_DASHBOARD_URL=https://<NAMESPACE>.grafana.net
-    export FETCH_GRAFANA_DASHBOARD_TOKEN=glsa_...
-
-    python3 .github/scripts/fetch-grafana-dashboard.py <dashboard-uid> > output.json
-"""
-
-import json
-import os
-import sys
-import urllib.request
-
-PANEL_TYPE_NAMES = {
-    "bargauge": "Bar gauge",
-    "gauge": "Gauge",
-    "heatmap": "Heatmap",
-    "piechart": "Pie chart",
-    "stat": "Stat",
-    "table": "Table",
-    "timeseries": "Time series",
-    "barchart": "Bar chart",
-    "text": "Text",
-    "dashlist": "Dashboard list",
-    "logs": "Logs",
-    "nodeGraph": "Node Graph",
-    "histogram": "Histogram",
-    "candlestick": "Candlestick",
-    "state-timeline": "State timeline",
-    "status-history": "Status history",
-    "geomap": "Geomap",
-    "canvas": "Canvas",
-    "news": "News",
-    "xychart": "XY Chart",
-    "trend": "Trend",
-    "datagrid": "Datagrid",
-    "flamegraph": "Flame Graph",
-    "traces": "Traces",
-}
-
-
-def fetch_json(base_url: str, token: str, path: str) -> dict:
-    url = f"{base_url}{path}"
-    req = urllib.request.Request(url, headers={"Authorization": f"Bearer {token}"})
-    with urllib.request.urlopen(req) as resp:
-        return json.loads(resp.read())
-
-
-def fetch_dashboard(base_url: str, token: str, uid: str) -> dict:
-    return fetch_json(base_url, token, f"/api/dashboards/uid/{uid}")
-
-
-def fetch_grafana_version(base_url: str) -> str:
-    req = urllib.request.Request(f"{base_url}/api/health")
-    with urllib.request.urlopen(req) as resp:
-        data = json.loads(resp.read())
-    # version string like "13.0.0-23940615780.patch2" -> take just the semver part
-    version = data.get("version", "")
-    # strip build metadata after the first hyphen if it looks like a pre-release
-    parts = version.split("-")
-    return parts[0] if parts else version
-
-
-def collect_panel_types(panels: list) -> set[str]:
-    types = set()
-    for panel in panels:
-        ptype = panel.get("type", "")
-        if ptype and ptype != "row":
-            types.add(ptype)
-        # nested panels inside collapsed rows
-        for sub in panel.get("panels", []):
-            sub_type = sub.get("type", "")
-            if sub_type and sub_type != "row":
-                types.add(sub_type)
-    return types
-
-
-def has_expression_datasource(dashboard: dict) -> bool:
-    return "__expr__" in json.dumps(dashboard)
-
-
-def make_exportable(dashboard: dict, grafana_version: str = "") -> dict:
-    dash = json.loads(json.dumps(dashboard))  # deep copy
-
-    # --- Strip internal fields ---
-    dash.pop("id", None)
-
-    # --- Rewrite links: point to the public repo instead of internal ---
-    dash["links"] = [
-        {
-            "asDropdown": False,
-            "icon": "external link",
-            "includeVars": False,
-            "keepTime": False,
-            "tags": [],
-            "targetBlank": True,
-            "title": "Source (GitHub)",
-            "tooltip": "View source file in repository",
-            "type": "link",
-            "url": "https://github.com/paradigmxyz/reth/tree/main/etc/grafana/dashboards",
-        }
-    ]
-
-    # --- Datasource: victoriametrics -> prometheus ---
-    dash_str = json.dumps(dash)
-    dash_str = dash_str.replace("victoriametrics-metrics-datasource", "prometheus")
-    dash = json.loads(dash_str)
-
-    # --- Templating: instance_label constant -> ${VAR_INSTANCE_LABEL} ---
-    # Also strip default-value fields the API returns that are not needed for import
-    STRIP_VAR_DEFAULTS = {"allowCustomValue", "regexApplyTo"}
-    for var in dash.get("templating", {}).get("list", []):
-        if var.get("name") == "instance_label" and var.get("type") == "constant":
-            var["query"] = "${VAR_INSTANCE_LABEL}"
-            var["current"] = {
-                "value": "${VAR_INSTANCE_LABEL}",
-                "text": "${VAR_INSTANCE_LABEL}",
-                "selected": False,
-            }
-            var["options"] = [
-                {
-                    "value": "${VAR_INSTANCE_LABEL}",
-                    "text": "${VAR_INSTANCE_LABEL}",
-                    "selected": False,
-                }
-            ]
-        # Clear current values for query/datasource vars (not meaningful for import)
-        elif var.get("type") in ("query", "datasource"):
-            var["current"] = {}
-        # Remove noisy default fields
-        for field in STRIP_VAR_DEFAULTS:
-            var.pop(field, None)
-        # Strip falsy defaults on query/datasource vars (API returns them, export omits them)
-        if var.get("type") in ("query", "datasource"):
-            for field in ("hide", "multi", "skipUrlSync"):
-                if not var.get(field):
-                    var.pop(field, None)
-
-    # --- Build __inputs ---
-    inputs = [
-        {
-            "name": "DS_PROMETHEUS",
-            "label": "Prometheus",
-            "description": "",
-            "type": "datasource",
-            "pluginId": "prometheus",
-            "pluginName": "Prometheus",
-        },
-    ]
-
-    if has_expression_datasource(dash):
-        inputs.append(
-            {
-                "name": "DS_EXPRESSION",
-                "label": "Expression",
-                "description": "",
-                "type": "datasource",
-                "pluginId": "__expr__",
-            }
-        )
-
-    inputs.append(
-        {
-            "name": "VAR_INSTANCE_LABEL",
-            "type": "constant",
-            "label": "Instance Label",
-            "value": "job",
-            "description": "",
-        }
-    )
-
-    # --- Build __requires ---
-    requires = []
-
-    if has_expression_datasource(dash):
-        requires.append({"type": "datasource", "id": "__expr__", "version": "1.0.0"})
-
-    panel_types = collect_panel_types(dash.get("panels", []))
-    for pt in sorted(panel_types):
-        requires.append(
-            {
-                "type": "panel",
-                "id": pt,
-                "name": PANEL_TYPE_NAMES.get(pt, pt),
-                "version": "",
-            }
-        )
-
-    requires.append(
-        {"type": "grafana", "id": "grafana", "name": "Grafana", "version": grafana_version}
-    )
-    requires.append(
-        {
-            "type": "datasource",
-            "id": "prometheus",
-            "name": "Prometheus",
-            "version": "1.0.0",
-        }
-    )
-
-    # --- Assemble output (with __inputs/__requires/__elements first) ---
-    output = {
-        "__inputs": inputs,
-        "__elements": {},
-        "__requires": requires,
-    }
-    output.update(dash)
-
-    return output
-
-
-def main():
-    if len(sys.argv) < 2:
-        print(f"Usage: {sys.argv[0]} <dashboard-uid>", file=sys.stderr)
-        sys.exit(1)
-
-    uid = sys.argv[1]
-    base_url = os.environ.get("FETCH_GRAFANA_DASHBOARD_URL", "").rstrip("/")
-    token = os.environ.get("FETCH_GRAFANA_DASHBOARD_TOKEN", "")
-
-    if not base_url or not token:
-        print(
-            "Error: FETCH_GRAFANA_DASHBOARD_URL and FETCH_GRAFANA_DASHBOARD_TOKEN env vars required",
-            file=sys.stderr,
-        )
-        sys.exit(1)
-
-    resp = fetch_dashboard(base_url, token, uid)
-    dashboard = resp["dashboard"]
-
-    grafana_version = fetch_grafana_version(base_url)
-    exported = make_exportable(dashboard, grafana_version)
-    print(json.dumps(exported, indent=2))
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/hive/Dockerfile

@@ -7,7 +7,7 @@ FROM lukemathwalker/cargo-chef:latest-rust-1 AS chef
 WORKDIR /app
 
 # Install system dependencies
-RUN apt-get update && apt-get install -y libclang-dev pkg-config
+RUN apt-get update && apt-get -y upgrade && apt-get install -y libclang-dev pkg-config
 
 # 
 # We prepare the build plan

.github/scripts/hive/build_simulators.sh

@@ -11,14 +11,8 @@ go build .
 
 # Run each hive command in the background for each simulator and wait
 echo "Building images"
-./hive -client reth --sim "ethereum/eels/consume-engine" \
-    --sim.buildarg fixtures=https://github.com/ethereum/execution-spec-tests/releases/download/v5.3.0/fixtures_develop.tar.gz \
-    --sim.buildarg branch=forks/osaka \
-    --sim.timelimit 1s || true &
-./hive -client reth --sim "ethereum/eels/consume-rlp" \
-    --sim.buildarg fixtures=https://github.com/ethereum/execution-spec-tests/releases/download/v5.3.0/fixtures_develop.tar.gz \
-    --sim.buildarg branch=forks/osaka \
-    --sim.timelimit 1s || true &
+# TODO: test code has been moved from https://github.com/ethereum/execution-spec-tests to https://github.com/ethereum/execution-specs  we need to pin eels branch with `--sim.buildarg branch=<release-branch-name>` once we have the fusaka release tagged on the new repo
+./hive -client reth --sim "ethereum/eels" --sim.buildarg fixtures=https://github.com/ethereum/execution-spec-tests/releases/download/v5.3.0/fixtures_develop.tar.gz -sim.timelimit 1s || true &
 ./hive -client reth --sim "ethereum/engine" -sim.timelimit 1s || true &
 ./hive -client reth --sim "devp2p" -sim.timelimit 1s || true &
 ./hive -client reth --sim "ethereum/rpc-compat" -sim.timelimit 1s || true &

.github/scripts/hive/expected_failures.yaml

@@ -1,6 +1,9 @@
 # tracked by https://github.com/paradigmxyz/reth/issues/13879
 rpc-compat:
   - debug_getRawBlock/get-invalid-number (reth)
+  - debug_getRawHeader/get-invalid-number (reth)
+  - debug_getRawReceipts/get-invalid-number (reth)
+  - debug_getRawReceipts/get-block-n (reth)
   - debug_getRawTransaction/get-invalid-hash (reth)
 
   - eth_getStorageAt/get-storage-invalid-key-too-large (reth)
@@ -13,11 +16,28 @@ rpc-compat:
   # syncing mode, the test expects syncing to be false on start
   - eth_syncing/check-syncing (reth)
 
-engine-withdrawals: [ ]
+# no fix due to https://github.com/paradigmxyz/reth/issues/8732
+engine-withdrawals:
+  - Withdrawals Fork On Genesis (Paris) (reth)
+  - Withdrawals Fork on Block 1 (Paris) (reth)
+  - Withdrawals Fork on Block 2 (Paris) (reth)
+  - Withdrawals Fork on Block 3 (Paris) (reth)
+  - Withdraw to a single account (Paris) (reth)
+  - Withdraw to two accounts (Paris) (reth)
+  - Withdraw many accounts (Paris) (reth)
+  - Withdraw zero amount (Paris) (reth)
+  - Empty Withdrawals (Paris) (reth)
+  - Corrupted Block Hash Payload (INVALID) (Paris) (reth)
+  - Withdrawals Fork on Canonical Block 8 / Side Block 7 - 10 Block Re-Org (Paris) (reth)
 
 engine-api: [ ]
 
-engine-cancun: [ ]
+# no fix due to https://github.com/paradigmxyz/reth/issues/8732
+engine-cancun:
+  - Invalid PayloadAttributes, Missing BeaconRoot, Syncing=True (Cancun) (reth)
+  # the test fails with older versions of the code for which it passed before, probably related to changes
+  # in hive or its dependencies
+  - Blob Transaction Ordering, Multiple Clients (Cancun) (reth)
 
 sync: [ ]
 
@@ -29,7 +49,7 @@ engine-auth: [ ]
 #   The test artificially creates an empty account with storage, then tests EIP-7610's behavior.
 #   On mainnet, ~25 such accounts exist as contract addresses (derived from keccak(prefix, caller,
 #   nonce/salt), not from public keys). No private key exists for contract addresses. To trigger
-#   this with EIP-7702, you'd need to recover a private key from one of the already deployed contract addresses - mathematically impossible.
+#   this with EIP-7702, you'd need to recover a private key from one of the already deployed contract addresses - mathematically impossible. 
 #
 # tests/paris/eip7610_create_collision/test_initcollision.py::test_init_collision_*
 #   Requires hash collision on create2 address to target already deployed accounts with storage.
@@ -39,6 +59,10 @@ engine-auth: [ ]
 #
 # System contract tests (already fixed and deployed):
 #
+# tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout and test_invalid_log_length
+#   System contract is already fixed and deployed; tests cover scenarios where contract is
+#   malformed which can't happen retroactively. No point in adding checks.
+#
 # tests/prague/eip7002_el_triggerable_withdrawals/test_contract_deployment.py::test_system_contract_deployment
 # tests/prague/eip7251_consolidations/test_contract_deployment.py::test_system_contract_deployment
 #   Post-fork system contract deployment tests. Should fix for spec compliance but not realistic
@@ -47,8 +71,32 @@ eels/consume-engine:
   - tests/prague/eip7702_set_code_tx/test_set_code_txs.py::test_set_code_to_non_empty_storage[fork_Prague-blockchain_test_engine-zero_nonce]-reth
   - tests/prague/eip7251_consolidations/test_contract_deployment.py::test_system_contract_deployment[fork_CancunToPragueAtTime15k-blockchain_test_engine-deploy_after_fork-nonzero_balance]-reth
   - tests/prague/eip7251_consolidations/test_contract_deployment.py::test_system_contract_deployment[fork_CancunToPragueAtTime15k-blockchain_test_engine-deploy_after_fork-zero_balance]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_amount_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_amount_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_index_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_index_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_pubkey_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_pubkey_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_signature_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_signature_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_withdrawal_credentials_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Prague-blockchain_test_engine-log_argument_withdrawal_credentials_size-value_zero]-reth
   - tests/prague/eip7002_el_triggerable_withdrawals/test_contract_deployment.py::test_system_contract_deployment[fork_CancunToPragueAtTime15k-blockchain_test_engine-deploy_after_fork-nonzero_balance]-reth
   - tests/prague/eip7002_el_triggerable_withdrawals/test_contract_deployment.py::test_system_contract_deployment[fork_CancunToPragueAtTime15k-blockchain_test_engine-deploy_after_fork-zero_balance]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_log_length[fork_Prague-blockchain_test_engine-slice_bytes_False]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_log_length[fork_Prague-blockchain_test_engine-slice_bytes_True]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_amount_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_amount_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_index_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_index_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_pubkey_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_pubkey_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_signature_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_signature_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_withdrawal_credentials_offset-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_layout[fork_Osaka-blockchain_test_engine-log_argument_withdrawal_credentials_size-value_zero]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_log_length[fork_Osaka-blockchain_test_engine-slice_bytes_False]-reth
+  - tests/prague/eip6110_deposits/test_modified_contract.py::test_invalid_log_length[fork_Osaka-blockchain_test_engine-slice_bytes_True]-reth
   - tests/paris/eip7610_create_collision/test_initcollision.py::test_init_collision_create_tx[fork_Osaka-tx_type_0-blockchain_test_engine_from_state_test-non-empty-balance-revert-initcode]-reth
   - tests/paris/eip7610_create_collision/test_initcollision.py::test_init_collision_create_tx[fork_Prague-tx_type_0-blockchain_test_engine_from_state_test-non-empty-balance-correct-initcode]-reth
   - tests/paris/eip7610_create_collision/test_initcollision.py::test_init_collision_create_tx[fork_Paris-tx_type_1-blockchain_test_engine_from_state_test-non-empty-balance-correct-initcode]-reth

.github/scripts/hive/ignored_tests.yaml

@@ -11,16 +11,18 @@
 #
 # When a test should no longer be ignored, remove it from this list.
 
+# flaky
+engine-withdrawals:
+  - Withdrawals Fork on Block 1 - 8 Block Re-Org NewPayload (Paris) (reth)
+  - Withdrawals Fork on Block 8 - 10 Block Re-Org NewPayload (Paris) (reth)
+  - Withdrawals Fork on Canonical Block 8 / Side Block 7 - 10 Block Re-Org (Paris) (reth)
+  - Sync after 128 blocks - Withdrawals on Block 2 - Multiple Withdrawal Accounts (Paris) (reth)
 engine-cancun:
   - Transaction Re-Org, New Payload on Revert Back (Cancun) (reth)
   - Transaction Re-Org, Re-Org to Different Block (Cancun) (reth)
   - Transaction Re-Org, Re-Org Out (Cancun) (reth)
   - Invalid Missing Ancestor ReOrg, StateRoot, EmptyTxs=False, Invalid P9 (Cancun) (reth)
-  # Hive test infra bug: geth sidecar switched to PathScheme for state storage, which has
-  # strict trie integrity requirements incompatible with inserting intentionally invalid blocks.
-  # Affects all clients, not just reth. Tracked: https://github.com/ethereum/hive/issues/1382
-  - Invalid Missing Ancestor Syncing ReOrg, Timestamp, EmptyTxs=False, CanonicalReOrg=False, Invalid P8 (Cancun) (reth)
-  - Invalid Missing Ancestor Syncing ReOrg, Timestamp, EmptyTxs=False, CanonicalReOrg=True, Invalid P8 (Cancun) (reth)
+  - Multiple New Payloads Extending Canonical Chain, Wait for Canonical Payload (Cancun) (reth)
 engine-api:
   - Transaction Re-Org, Re-Org Out (Paris) (reth)
   - Transaction Re-Org, Re-Org to Different Block (Paris) (reth)
@@ -30,3 +32,5 @@ engine-api:
   - Invalid Missing Ancestor Syncing ReOrg, Transaction Signature, EmptyTxs=False, CanonicalReOrg=True, Invalid P9 (Paris) (reth)
   - Invalid Missing Ancestor Syncing ReOrg, Transaction Signature, EmptyTxs=False, CanonicalReOrg=False, Invalid P9 (Paris) (reth)
   - Invalid Missing Ancestor ReOrg, StateRoot, EmptyTxs=True, Invalid P10 (Paris) (reth)
+  - Multiple New Payloads Extending Canonical Chain, Wait for Canonical Payload (Paris) (reth)
+  - Multiple New Payloads Extending Canonical Chain, Set Head to First Payload Received (Paris) (reth)

.github/scripts/hive/run_simulator.sh

@@ -6,20 +6,8 @@ cd hivetests/
 sim="${1}"
 limit="${2}"
 
-# Use lower parallelism for eels tests to avoid OOM-killing the runner
-parallelism=16
-if [[ "${sim}" == *"eels"* ]]; then
-    parallelism=4
-fi
-
 run_hive() {
-    hive \
-  --sim "${sim}" \
-  --sim.limit "${limit}" \
-  --sim.limit.exact=false \
-  --sim.parallelism "${parallelism}" \
-  --client reth \
-  2>&1 | tee /tmp/log || true
+    hive --sim "${sim}" --sim.limit "${limit}" --sim.parallelism 16 --client reth 2>&1 | tee /tmp/log || true
 }
 
 check_log() {

.github/scripts/install_geth.sh

@@ -2,7 +2,7 @@
 
 # Installs Geth (https://geth.ethereum.org) in $HOME/bin for x86_64 Linux.
 
-set -exo pipefail
+set -eo pipefail
 
 GETH_BUILD=${GETH_BUILD:-"1.13.4-3f907d6a"}
 

.github/scripts/verify_image_arch.sh

@@ -7,7 +7,7 @@
 # Environment:
 #   DRY_RUN=true  - Skip actual verification, just print what would be checked.
 
-set -euxo pipefail
+set -euo pipefail
 
 TARGETS="${1:-}"
 REGISTRY="${2:-}"

.github/workflows/book.yml

@@ -15,7 +15,7 @@ env:
 
 jobs:
   build:
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-8' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-8
     timeout-minutes: 90
     steps:
       - name: Checkout
@@ -47,10 +47,10 @@ jobs:
           echo "Vocs Build Complete"
 
       - name: Setup Pages
-        uses: actions/configure-pages@v6
+        uses: actions/configure-pages@v5
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v5
+        uses: actions/upload-pages-artifact@v4
         with:
           path: "./docs/vocs/docs/dist"
 
@@ -74,4 +74,4 @@ jobs:
     steps:
       - name: Deploy to GitHub Pages
         id: deployment
-        uses: actions/deploy-pages@v5
+        uses: actions/deploy-pages@v4

.github/workflows/changelog.yml

@@ -0,0 +1,25 @@
+name: Changelog
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+
+jobs:
+  changelog:
+    # Skip for fork PRs since they can't access secrets
+    if: github.event.pull_request.head.repo.full_name == github.repository
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.sha }}
+      - run: npm install -g @anthropic-ai/claude-code
+      - uses: wevm/changelogs/check@master
+        with:
+          ai: 'claude -p'
+        env:
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

.github/workflows/check-alloy.yml

@@ -25,7 +25,7 @@ env:
 jobs:
   check:
     name: Check compilation with patched alloy
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-16' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-16
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4

.github/workflows/compact.yml

@@ -18,7 +18,7 @@ env:
 name: compact-codec
 jobs:
   compact-codec:
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     strategy:
       matrix:
         bin:

.github/workflows/docker-test.yml

@@ -6,7 +6,7 @@ on:
       hive_target:
         required: true
         type: string
-        description: "Docker bake target to build (e.g. hive)"
+        description: "Docker bake target to build (e.g. hive-stable, hive-edge)"
       artifact_name:
         required: false
         type: string
@@ -15,6 +15,7 @@ on:
 
 jobs:
   build:
+    if: github.repository == 'paradigmxyz/reth'
     timeout-minutes: 45
     runs-on: ubuntu-latest
     permissions:
@@ -30,22 +31,10 @@ jobs:
           echo "sha=${{ github.sha }}" >> "$GITHUB_OUTPUT"
           echo "describe=$(git describe --always --tags)" >> "$GITHUB_OUTPUT"
 
-      - name: Detect fork
-        id: fork
-        run: |
-          if [ "${{ github.event_name }}" = "pull_request" ] && [ "${{ github.event.pull_request.head.repo.full_name }}" != "${{ github.repository }}" ]; then
-            echo "is_fork=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "is_fork=false" >> "$GITHUB_OUTPUT"
-          fi
-
-      # Depot build (upstream only)
       - name: Set up Depot CLI
-        if: steps.fork.outputs.is_fork == 'false'
         uses: depot/setup-action@v1
 
-      - name: Build reth image (Depot)
-        if: steps.fork.outputs.is_fork == 'false'
+      - name: Build reth image
         uses: depot/bake-action@v1
         env:
           DEPOT_TOKEN: ${{ secrets.DEPOT_TOKEN }}
@@ -57,26 +46,8 @@ jobs:
           targets: ${{ inputs.hive_target }}
           push: false
 
-      # Docker build (forks)
-      - name: Set up Docker Buildx
-        if: steps.fork.outputs.is_fork == 'true'
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build reth image (Docker)
-        if: steps.fork.outputs.is_fork == 'true'
-        uses: docker/bake-action@v6
-        env:
-          VERGEN_GIT_SHA: ${{ steps.git.outputs.sha }}
-          VERGEN_GIT_DESCRIBE: ${{ steps.git.outputs.describe }}
-        with:
-          files: docker-bake.hcl
-          targets: ${{ inputs.hive_target }}
-          push: false
-          set: |
-            *.dockerfile=Dockerfile
-
       - name: Upload reth image
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v6
         with:
           name: ${{ inputs.artifact_name }}
           path: ./artifacts

.github/workflows/docker.yml

@@ -45,7 +45,7 @@ jobs:
         uses: depot/setup-action@v1
 
       - name: Log in to GHCR
-        uses: docker/login-action@v4
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
@@ -138,8 +138,6 @@ jobs:
             *Run:* <https://github.com/paradigmxyz/reth/actions/runs/${{ github.run_id }}|View logs>
 
             *Action required:* Re-run the workflow or investigate the build failure.
-
-            <@U0AAA8F0JEM> investigate and re-run if flaky
           SLACK_FOOTER: "paradigmxyz/reth · docker.yml"
           MSG_MINIMAL: true
           SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK_URL }}

.github/workflows/e2e.yml

@@ -20,7 +20,7 @@ concurrency:
 jobs:
   test:
     name: e2e-testsuite
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-4
     env:
       RUST_BACKTRACE: 1
     timeout-minutes: 90
@@ -47,7 +47,7 @@ jobs:
 
   rocksdb:
     name: e2e-rocksdb
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-4
     env:
       RUST_BACKTRACE: 1
     timeout-minutes: 60
@@ -63,6 +63,6 @@ jobs:
         run: |
           cargo nextest run \
             --no-fail-fast \
-            --locked \
+            --locked --features "edge" \
             -p reth-e2e-test-utils \
             -E 'binary(rocksdb)'

.github/workflows/fetch-grafana-dashboard.yml

@@ -1,62 +0,0 @@
-name: Fetch Grafana Dashboard
-
-on:
-  workflow_dispatch:
-    inputs:
-      dashboard_uid:
-        description: "Grafana dashboard UID to export"
-        required: true
-        default: "2k8BXz24x"
-      target_path:
-        description: "Target file path in the repo (e.g. etc/grafana/dashboards/overview.json)"
-        required: true
-        default: "etc/grafana/dashboards/overview.json"
-
-jobs:
-  fetch:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - uses: actions/checkout@v6
-
-      - uses: actions/setup-python@v6
-        with:
-          python-version: "3.12"
-
-      - name: Fetch dashboard from Grafana
-        env:
-          FETCH_GRAFANA_DASHBOARD_URL: ${{ secrets.FETCH_GRAFANA_DASHBOARD_URL }}
-          FETCH_GRAFANA_DASHBOARD_TOKEN: ${{ secrets.FETCH_GRAFANA_DASHBOARD_TOKEN }}
-        run: |
-          python3 .github/scripts/fetch-grafana-dashboard.py "${{ inputs.dashboard_uid }}" \
-            > "${{ inputs.target_path }}"
-
-      - name: Check for changes
-        id: diff
-        run: |
-          if git diff --quiet "${{ inputs.target_path }}"; then
-            echo "changed=false" >> "$GITHUB_OUTPUT"
-            echo "No changes detected."
-          else
-            echo "changed=true" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: Create pull request
-        if: steps.diff.outputs.changed == 'true'
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          TARGET="${{ inputs.target_path }}"
-          FILENAME="$(basename "$TARGET")"
-          BRANCH="chore/sync-grafana-${FILENAME%.*}-$(date +%Y%m%d-%H%M%S)"
-          git config user.name "github-actions[bot]"
-          git config user.email "github-actions[bot]@users.noreply.github.com"
-          git checkout -b "$BRANCH"
-          git add "$TARGET"
-          git commit -m "chore: update Grafana dashboard ${FILENAME}"
-          git push origin "$BRANCH"
-          gh pr create \
-            --title "chore: update Grafana dashboard ${FILENAME}" \
-            --body "Automated export from Grafana (dashboard UID: \`${{ inputs.dashboard_uid }}\`, target: \`${TARGET}\`)."

.github/workflows/grafana.yml

@@ -11,22 +11,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v6
-      - name: Validate dashboard format
+      - name: Check for ${DS_PROMETHEUS} in overview.json
         run: |
-          python3 -c "
-          import json, sys
-          with open('etc/grafana/dashboards/overview.json') as f:
-              d = json.load(f)
-          errors = []
-          if '__inputs' not in d:
-              errors.append('missing __inputs')
-          if '__requires' not in d:
-              errors.append('missing __requires')
-          if d.get('id') is not None:
-              errors.append('contains internal id field — use export-dashboard.py')
-          if errors:
-              for e in errors:
-                  print(f'Error: {e}', file=sys.stderr)
-              sys.exit(1)
-          print('✓ overview.json is a valid exported dashboard')
-          "
+          if grep -Fn '${DS_PROMETHEUS}' etc/grafana/dashboards/overview.json; then
+            echo "Error: overview.json contains '\${DS_PROMETHEUS}' placeholder"
+            echo "Please replace it with '\${datasource}'"
+            exit 1
+          fi
+          echo "✓ overview.json does not contain '\${DS_PROMETHEUS}' placeholder"

.github/workflows/hive.yml

@@ -15,17 +15,24 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  build-reth:
+  build-reth-stable:
     uses: ./.github/workflows/docker-test.yml
     with:
-      hive_target: hive
-      artifact_name: "reth"
+      hive_target: hive-stable
+      artifact_name: "reth-stable"
+    secrets: inherit
+
+  build-reth-edge:
+    uses: ./.github/workflows/docker-test.yml
+    with:
+      hive_target: hive-edge
+      artifact_name: "reth-edge"
     secrets: inherit
 
   prepare-hive:
     if: github.repository == 'paradigmxyz/reth'
     timeout-minutes: 45
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-4
     steps:
       - uses: actions/checkout@v6
       - name: Checkout hive tests
@@ -68,7 +75,7 @@ jobs:
           chmod +x hive
 
       - name: Upload hive assets
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v6
         with:
           name: hive_assets
           path: ./hive_assets
@@ -77,6 +84,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
+        storage: [stable, edge]
         # ethereum/rpc to be deprecated:
         # https://github.com/ethereum/hive/pull/1117
         scenario:
@@ -176,11 +184,11 @@ jobs:
           - sim: ethereum/eels/consume-rlp
             limit: .*tests/paris.*
     needs:
-      - build-reth
+      - build-reth-stable
+      - build-reth-edge
       - prepare-hive
-    name: ${{ matrix.scenario.sim }}${{ matrix.scenario.limit && format(' - {0}', matrix.scenario.limit) }}
-    # Use larger runners for eels tests to avoid OOM runner crashes
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && (contains(matrix.scenario.sim, 'eels') && 'depot-ubuntu-latest-8' || 'depot-ubuntu-latest-4') || 'ubuntu-latest' }}
+    name: ${{ matrix.storage }} / ${{ matrix.scenario.sim }}${{ matrix.scenario.limit && format(' - {0}', matrix.scenario.limit) }}
+    runs-on: depot-ubuntu-latest-4
     permissions:
       issues: write
     steps:
@@ -189,15 +197,15 @@ jobs:
           fetch-depth: 0
 
       - name: Download hive assets
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: hive_assets
           path: /tmp
 
       - name: Download reth image
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
-          name: reth
+          name: reth-${{ matrix.storage }}
           path: /tmp
 
       - name: Load Docker images

.github/workflows/integration.yml

@@ -22,14 +22,15 @@ concurrency:
 
 jobs:
   test:
-    name: test / ${{ matrix.network }}
+    name: test / ${{ matrix.network }} / ${{ matrix.storage }}
     if: github.event_name != 'schedule'
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-4
     env:
       RUST_BACKTRACE: 1
     strategy:
       matrix:
         network: ["ethereum"]
+        storage: ["stable", "edge"]
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v6
@@ -46,7 +47,7 @@ jobs:
         run: |
           cargo nextest run \
             --no-fail-fast \
-            --locked --features "asm-keccak ${{ matrix.network }}" \
+            --locked --features "asm-keccak ${{ matrix.network }} ${{ matrix.storage == 'edge' && 'edge' || '' }}" \
             --workspace --exclude ef-tests \
             -E "kind(test) and not binary(e2e_testsuite)"
 

.github/workflows/kurtosis.yml

@@ -31,7 +31,7 @@ jobs:
     strategy:
       fail-fast: false
     name: run kurtosis
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     needs:
       - build-reth
     steps:
@@ -40,7 +40,7 @@ jobs:
           fetch-depth: 0
 
       - name: Download reth image
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: artifacts
           path: /tmp

.github/workflows/label-pr.yml

@@ -16,7 +16,7 @@ jobs:
           fetch-depth: 0
 
       - name: Label PRs
-        uses: actions/github-script@v9
+        uses: actions/github-script@v8
         with:
           script: |
             const label_pr = require('./.github/scripts/label_pr.js')

.github/workflows/lint.yml

@@ -13,7 +13,7 @@ env:
 jobs:
   clippy-binaries:
     name: clippy binaries / ${{ matrix.type }}
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 30
     strategy:
       matrix:
@@ -42,7 +42,7 @@ jobs:
 
   clippy:
     name: clippy
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -59,7 +59,7 @@ jobs:
           RUSTFLAGS: -D warnings
 
   wasm:
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -79,7 +79,7 @@ jobs:
           .github/scripts/check_wasm.sh
 
   riscv:
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v6
@@ -98,7 +98,7 @@ jobs:
 
   crate-checks:
     name: crate-checks (${{ matrix.partition }}/${{ matrix.total_partitions }})
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-4
     strategy:
       matrix:
         partition: [1, 2, 3]
@@ -117,7 +117,7 @@ jobs:
 
   msrv:
     name: MSRV
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-8' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -135,7 +135,7 @@ jobs:
 
   docs:
     name: docs
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-4
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -153,7 +153,7 @@ jobs:
 
   fmt:
     name: fmt
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -167,7 +167,7 @@ jobs:
 
   udeps:
     name: udeps
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -182,7 +182,7 @@ jobs:
 
   book:
     name: book
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 30
     steps:
       - uses: actions/checkout@v6
@@ -237,9 +237,34 @@ jobs:
       - name: Ensure no arbitrary or proptest dependency on default build
         run: cargo tree --package reth -e=features,no-dev | grep -Eq "arbitrary|proptest" && exit 1 || exit 0
 
+  # Checks that selected crates can compile with power set of features
+  features:
+    name: features
+    runs-on: depot-ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - uses: actions/checkout@v6
+      - uses: rui314/setup-mold@v1
+      - uses: dtolnay/rust-toolchain@clippy
+      - uses: mozilla-actions/sccache-action@v0.0.9
+      - uses: Swatinem/rust-cache@v2
+        with:
+          cache-on-failure: true
+      - name: cargo install cargo-hack
+        uses: taiki-e/install-action@cargo-hack
+      - run: |
+          cargo hack check \
+            --package reth-codecs \
+            --package reth-primitives-traits \
+            --package reth-primitives \
+            --feature-powerset \
+            --depth 2
+        env:
+          RUSTFLAGS: -D warnings
+
   # Check crates correctly propagate features
   feature-propagation:
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     timeout-minutes: 20
     steps:
       - uses: actions/checkout@v6
@@ -272,6 +297,7 @@ jobs:
       - typos
       - grafana
       - no-test-deps
+      - features
       - feature-propagation
       - deny
     timeout-minutes: 30

.github/workflows/pr-audit.yml

@@ -1,30 +0,0 @@
-name: Pull request audit
-
-on:
-  pull_request:
-    types: [labeled]
-
-jobs:
-  publish:
-    runs-on: ubuntu-latest
-    if: github.event.label.name == 'cyclops'
-    steps:
-      - name: Publish event
-        run: |
-          set -euo pipefail
-
-          echo "${{ secrets.EVENTS_KEY }}" > ${{ runner.temp }}/key
-          echo "${{ secrets.EVENTS_CERT }}" > ${{ runner.temp }}/cert
-
-          curl -sf -o /dev/null -X POST ${{ secrets.EVENTS_ARGS }} \
-            -H "Content-Type: application/json" \
-            --key ${{ runner.temp }}/key \
-            --cert ${{ runner.temp }}/cert \
-            -d '{
-              "repository": "${{ github.repository }}",
-              "event": "pr_audit",
-              "data": {
-                "pr_number": ${{ github.event.pull_request.number }},
-                "sha": "${{ github.event.pull_request.head.sha }}"
-              }
-            }'

.github/workflows/release-reproducible.yml

@@ -52,7 +52,7 @@ jobs:
         uses: docker/setup-buildx-action@v3
 
       - name: Log in to GitHub Container Registry
-        uses: docker/login-action@v4
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}

.github/workflows/release.yml

@@ -37,7 +37,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Extract version
-        run: echo "VERSION=${GITHUB_REF_NAME//\//-}" >> $GITHUB_OUTPUT
+        run: echo "VERSION=${GITHUB_REF_NAME}" >> $GITHUB_OUTPUT
         id: extract_version
     outputs:
       VERSION: ${{ steps.extract_version.outputs.VERSION }}
@@ -73,24 +73,22 @@ jobs:
             os: ubuntu-24.04
             profile: maxperf
             allow_fail: false
-            rustflags: "-C target-cpu=x86-64-v3 -C target-feature=+pclmulqdq"
-            native: true
           - target: aarch64-unknown-linux-gnu
-            os: ubuntu-24.04-arm
+            os: ubuntu-24.04
             profile: maxperf
             allow_fail: false
-            rustflags: ""
-            native: true
           - target: x86_64-apple-darwin
             os: macos-14
             profile: maxperf
             allow_fail: false
-            rustflags: "-C target-cpu=x86-64-v3 -C target-feature=+pclmulqdq"
           - target: aarch64-apple-darwin
             os: macos-14
             profile: maxperf
             allow_fail: false
-            rustflags: ""
+          - target: riscv64gc-unknown-linux-gnu
+            os: ubuntu-24.04
+            profile: maxperf
+            allow_fail: true
         build:
           - command: build
             binary: reth
@@ -102,7 +100,6 @@ jobs:
           target: ${{ matrix.configs.target }}
       - uses: mozilla-actions/sccache-action@v0.0.9
       - name: Install cross main
-        if: ${{ !matrix.configs.native }}
         id: cross_main
         run: |
           cargo install cross --locked --git https://github.com/cross-rs/cross
@@ -117,14 +114,7 @@ jobs:
           echo "MACOSX_DEPLOYMENT_TARGET=$(xcrun -sdk macosx --show-sdk-platform-version)" >> $GITHUB_ENV
 
       - name: Build Reth
-        env:
-          CC: clang
-        run: |
-          if [ "${{ matrix.configs.native }}" = "true" ]; then
-            make PROFILE=${{ matrix.configs.profile }} EXTRA_RUSTFLAGS="${{ matrix.configs.rustflags }}" ${{ matrix.build.command }}-native-${{ matrix.configs.target }}
-          else
-            make PROFILE=${{ matrix.configs.profile }} EXTRA_RUSTFLAGS="${{ matrix.configs.rustflags }}" ${{ matrix.build.command }}-${{ matrix.configs.target }}
-          fi
+        run: make PROFILE=${{ matrix.configs.profile }} ${{ matrix.build.command }}-${{ matrix.configs.target }}
       - name: Move binary
         run: |
           mkdir artifacts
@@ -145,19 +135,18 @@ jobs:
 
       - name: Upload artifact
         if: ${{ github.event.inputs.dry_run != 'true' }}
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v6
         with:
           name: ${{ matrix.build.binary }}-${{ needs.extract-version.outputs.VERSION }}-${{ matrix.configs.target }}.tar.gz
           path: ${{ matrix.build.binary }}-${{ needs.extract-version.outputs.VERSION }}-${{ matrix.configs.target }}.tar.gz
 
       - name: Upload signature
         if: ${{ github.event.inputs.dry_run != 'true' }}
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v6
         with:
           name: ${{ matrix.build.binary }}-${{ needs.extract-version.outputs.VERSION }}-${{ matrix.configs.target }}.tar.gz.asc
           path: ${{ matrix.build.binary }}-${{ needs.extract-version.outputs.VERSION }}-${{ matrix.configs.target }}.tar.gz.asc
 
-
   draft-release:
     name: draft release
     runs-on: ubuntu-latest
@@ -175,7 +164,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Download artifacts
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
       - name: Generate full changelog
         id: changelog
         run: |
@@ -195,7 +184,7 @@ jobs:
           fi
 
           body=$(cat <<- "ENDBODY"
-          ![image](https://raw.githubusercontent.com/paradigmxyz/reth/main/assets/reth-2.png)
+          ![image](https://raw.githubusercontent.com/paradigmxyz/reth/main/assets/reth-prod.png)
 
           ## Testing Checklist (DELETE ME)
 

.github/workflows/reproducible-build.yml

@@ -43,7 +43,7 @@ jobs:
           echo "Binaries SHA256 on ${{ matrix.machine }}: $(cat checksum.sha256)"
 
       - name: Upload the hash
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v6
         with:
           name: checksum-${{ matrix.machine }}
           path: |
@@ -56,12 +56,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download artifacts from machine-1
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: checksum-machine-1
           path: machine-1/
       - name: Download artifacts from machine-2
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: checksum-machine-2
           path: machine-2/

.github/workflows/stage.yml

@@ -23,7 +23,7 @@ jobs:
     name: stage-run-test
     # Only run stage commands test in merge groups
     if: github.event_name == 'merge_group'
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     env:
       RUST_LOG: info,sync=error
       RUST_BACKTRACE: 1
@@ -51,12 +51,15 @@ jobs:
       - name: Run execution stage
         run: |
           reth stage run execution --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints
-      # NOTE: account-hashing, storage-hashing, and hashing stages are omitted.
-      # With storage v2 (now default), these stages are no-ops because the
-      # execution stage writes directly to HashedAccounts/HashedStorages.
-      # Running them here is harmful: `stage run` unwinds before executing,
-      # and the unwind reverts the hashed state that execution wrote, but
-      # the no-op execute never restores it — causing merkle to fail.
+      - name: Run account-hashing stage
+        run: |
+          reth stage run account-hashing --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints
+      - name: Run storage hashing stage
+        run: |
+          reth stage run storage-hashing --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints
+      - name: Run hashing stage
+        run: |
+          reth stage run hashing --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints
       - name: Run merkle stage
         run: |
           reth stage run merkle --from ${{ env.FROM_BLOCK }} --to ${{ env.TO_BLOCK }} --commit --checkpoints

.github/workflows/sync-era.yml

@@ -19,7 +19,7 @@ jobs:
   sync:
     if: github.repository == 'paradigmxyz/reth'
     name: sync (${{ matrix.chain.bin }})
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     env:
       RUST_LOG: info,sync=error
       RUST_BACKTRACE: 1

.github/workflows/sync.yml

@@ -19,7 +19,7 @@ jobs:
   sync:
     if: github.repository == 'paradigmxyz/reth'
     name: sync (${{ matrix.chain.bin }})
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     env:
       RUST_LOG: info,sync=error
       RUST_BACKTRACE: 1

.github/workflows/unit.yml

@@ -19,13 +19,15 @@ concurrency:
 
 jobs:
   test:
-    name: test / ${{ matrix.type }}
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-4' || 'ubuntu-latest' }}
+    name: test / ${{ matrix.type }} / ${{ matrix.storage }}
+    runs-on: depot-ubuntu-latest-4
     env:
       RUST_BACKTRACE: 1
+      EDGE_FEATURES: ${{ matrix.storage == 'edge' && 'edge' || '' }}
     strategy:
       matrix:
         type: [ethereum]
+        storage: [stable, edge]
         include:
           - type: ethereum
             features: asm-keccak ethereum
@@ -48,14 +50,14 @@ jobs:
         run: |
           cargo nextest run \
             --no-fail-fast \
-            --features "${{ matrix.features }}" --locked \
+            --features "${{ matrix.features }} $EDGE_FEATURES" --locked \
             ${{ matrix.exclude_args }} --workspace \
             --exclude ef-tests --no-tests=warn \
             -E "!kind(test) and not binary(e2e_testsuite)"
 
   state:
     name: Ethereum state tests
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest-8' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest-4
     env:
       RUST_LOG: info,sync=error
       RUST_BACKTRACE: 1
@@ -90,7 +92,7 @@ jobs:
 
   doc:
     name: doc tests
-    runs-on: ${{ github.repository == 'paradigmxyz/reth' && 'depot-ubuntu-latest' || 'ubuntu-latest' }}
+    runs-on: depot-ubuntu-latest
     env:
       RUST_BACKTRACE: 1
     timeout-minutes: 30

AGENTS.md

@@ -1,549 +0,0 @@
-# Reth Development Guide for AI Agents
-
-This guide provides comprehensive instructions for AI agents working on the Reth codebase. It covers the architecture, development workflows, and critical guidelines for effective contributions.
-
-## Project Overview
-
-Reth is a high-performance Ethereum execution client written in Rust, focusing on modularity, performance, and contributor-friendliness. The codebase is organized into well-defined crates with clear boundaries and responsibilities.
-
-## Architecture Overview
-
-### Core Components
-
-1. **Consensus (`crates/consensus/`)**: Validates blocks according to Ethereum consensus rules
-2. **Storage (`crates/storage/`)**: Hybrid database using MDBX + static files for optimal performance
-3. **Networking (`crates/net/`)**: P2P networking stack with discovery, sync, and transaction propagation
-4. **RPC (`crates/rpc/`)**: JSON-RPC server supporting all standard Ethereum APIs
-5. **Execution (`crates/evm/`, `crates/ethereum/`)**: Transaction execution and state transitions
-6. **Pipeline (`crates/stages/`)**: Staged sync architecture for blockchain synchronization
-7. **Trie (`crates/trie/`)**: Merkle Patricia Trie implementation with parallel state root computation
-8. **Node Builder (`crates/node/`)**: High-level node orchestration and configuration
-9. **The Consensus Engine (`crates/engine/`)**: Handles processing blocks received from the consensus layer with the Engine API (newPayload, forkchoiceUpdated)
-
-### Key Design Principles
-
-- **Modularity**: Each crate can be used as a standalone library
-- **Performance**: Extensive use of parallelism, memory-mapped I/O, and optimized data structures
-- **Extensibility**: Traits and generic types allow for different chain implementations
-- **Type Safety**: Strong typing throughout with minimal use of dynamic dispatch
-
-## Development Workflow
-
-### Code Style and Standards
-
-1. **Formatting**: Always use nightly rustfmt
-   ```bash
-   cargo +nightly fmt --all
-   ```
-
-2. **Linting**: Run clippy with all features
-   ```bash
-   cargo +nightly clippy --workspace --lib --examples --tests --benches --all-features 
-   ```
-
-3. **Testing**: Use nextest for faster test execution
-   ```bash
-   cargo nextest run --workspace
-   ```
-
-### Common Contribution Types
-
-Based on actual recent PRs, here are typical contribution patterns:
-
-#### 1. Small Bug Fixes (1-10 lines)
-Real example: Fixing beacon block root handling ([#16767](https://github.com/paradigmxyz/reth/pull/16767))
-```rust
-// Changed a single line to fix logic error
-- parent_beacon_block_root: parent.parent_beacon_block_root(),
-+ parent_beacon_block_root: parent.parent_beacon_block_root().map(|_| B256::ZERO),
-```
-
-#### 2. Integration with Upstream Changes
-Real example: Integrating revm updates ([#16752](https://github.com/paradigmxyz/reth/pull/16752))
-```rust
-// Update code to use new APIs from dependencies
-- if self.fork_tracker.is_shanghai_activated() {
--     if let Err(err) = transaction.ensure_max_init_code_size(MAX_INIT_CODE_BYTE_SIZE) {
-+ if let Some(init_code_size_limit) = self.fork_tracker.max_initcode_size() {
-+     if let Err(err) = transaction.ensure_max_init_code_size(init_code_size_limit) {
-```
-
-#### 3. Adding Comprehensive Tests
-Real example: ETH69 protocol tests ([#16759](https://github.com/paradigmxyz/reth/pull/16759))
-```rust
-#[tokio::test(flavor = "multi_thread")]
-async fn test_eth69_peers_can_connect() {
-    // Create test network with specific protocol versions
-    let p0 = PeerConfig::with_protocols(NoopProvider::default(), Some(EthVersion::Eth69.into()));
-    // Test connection and version negotiation
-}
-```
-
-#### 4. Making Components Generic
-Real example: Making EthEvmConfig generic over chainspec ([#16758](https://github.com/paradigmxyz/reth/pull/16758))
-```rust
-// Before: Hardcoded to ChainSpec
-- pub struct EthEvmConfig<EvmFactory = EthEvmFactory> {
--     pub executor_factory: EthBlockExecutorFactory<RethReceiptBuilder, Arc<ChainSpec>, EvmFactory>,
-
-// After: Generic over any chain spec type
-+ pub struct EthEvmConfig<C = ChainSpec, EvmFactory = EthEvmFactory>
-+ where
-+     C: EthereumHardforks,
-+ {
-+     pub executor_factory: EthBlockExecutorFactory<RethReceiptBuilder, Arc<C>, EvmFactory>,
-```
-
-#### 5. Resource Management Improvements
-Real example: ETL directory cleanup ([#16770](https://github.com/paradigmxyz/reth/pull/16770))
-```rust
-// Add cleanup logic on startup
-+ if let Err(err) = fs::remove_dir_all(&etl_path) {
-+     warn!(target: "reth::cli", ?etl_path, %err, "Failed to remove ETL path on launch");
-+ }
-```
-
-#### 6. Feature Additions
-Real example: Sharded mempool support ([#16756](https://github.com/paradigmxyz/reth/pull/16756))
-```rust
-// Add new filtering policies for transaction announcements
-pub struct ShardedMempoolAnnouncementFilter<T> {
-    pub inner: T,
-    pub shard_bits: u8,
-    pub node_id: Option<B256>,
-}
-```
-
-### Testing Guidelines
-
-1. **Unit Tests**: Test individual functions and components
-2. **Integration Tests**: Test interactions between components
-3. **Benchmarks**: For performance-critical code
-4. **Fuzz Tests**: For parsing and serialization code
-5. **Property Tests**: For checking component correctness on a wide variety of inputs
-
-Example test structure:
-```rust
-#[cfg(test)]
-mod tests {
-    use super::*;
-    
-    #[test]
-    fn test_component_behavior() {
-        // Arrange
-        let component = Component::new();
-        
-        // Act
-        let result = component.operation();
-        
-        // Assert
-        assert_eq!(result, expected);
-    }
-}
-```
-
-### Performance Considerations
-
-1. **Avoid Allocations in Hot Paths**: Use references and borrowing
-2. **Parallel Processing**: Use rayon for CPU-bound parallel work
-3. **Async/Await**: Use tokio for I/O-bound operations
-4. **File Operations**: Use `reth_fs_util` instead of `std::fs` for better error handling
-
-### Common Pitfalls
-
-1. **Don't Block Async Tasks**: Use `spawn_blocking` for CPU-intensive work or work with lots of blocking I/O
-2. **Handle Errors Properly**: Use `?` operator and proper error types
-
-### What to Avoid
-
-Based on PR patterns, avoid:
-
-1. **Large, sweeping changes**: Keep PRs focused and reviewable
-2. **Mixing unrelated changes**: One logical change per PR
-3. **Ignoring CI failures**: All checks must pass
-4. **Incomplete implementations**: Finish features before submitting
-5. **Modifying libmdbx sources**: Never modify files in `crates/storage/libmdbx-rs/mdbx-sys/libmdbx/` - this is vendored third-party code
-
-### CI Requirements
-
-Before submitting changes, ensure:
-
-1. **Format Check**: `cargo +nightly fmt --all --check`
-2. **Clippy**: No warnings
-3. **Tests Pass**: All unit and integration tests
-4. **Documentation**: Update relevant docs and add doc comments with `cargo docs --document-private-items`
-5. **CLI Docs** (if CLI changed): Run `make update-book-cli` (see below)
-6. **Commit Messages**: Follow conventional format (feat:, fix:, chore:, etc.)
-
-### CLI Reference Docs (`book` CI Job)
-
-The CLI reference pages under `docs/vocs/docs/pages/cli/` are **auto-generated** from the `reth` binary's `--help` output. **Do not edit these files manually** — any hand edits will be overwritten and CI will fail regardless.
-
-When you add, remove, or modify CLI commands, subcommands, or flags, regenerate the CLI docs by running:
-
-```bash
-make update-book-cli
-```
-
-This builds `reth` in debug mode and runs `docs/cli/update.sh` to regenerate all CLI pages. Commit the resulting changes.
-
-The `book` CI job (`.github/workflows/lint.yml`) enforces this by regenerating the docs and running `git diff --exit-code`. If the committed docs don't match the generated output, CI fails. Manually editing these pages is never productive — always use `make update-book-cli`.
-
-### Opening PRs against <https://github.com/paradigmxyz/reth>
-
-#### Titles
-
-Use [Conventional Commits](https://www.conventionalcommits.org/) with an optional scope:
-
-```
-<type>(<scope>): <short description>
-```
-
-**Types**: `feat`, `fix`, `perf`, `refactor`, `docs`, `test`, `chore`
-
-**Scope** (optional): crate or area, e.g. `evm`, `trie`, `rpc`, `engine`, `net`
-
-Examples:
-- `fix(rpc): correct gas estimation for ERC-20 transfers`
-- `perf: batch trie updates to reduce cursor overhead`
-- `feat(engine): add new_payload_interval metric`
-
-#### Descriptions
-
-Keep it short. Say what changed and why — nothing more.
-
-**Do:**
-- Write 1–3 sentences summarizing the change
-- Explain _why_ if the diff doesn't make it obvious
-- Link related issues or EIPs
-- Include benchmark numbers for perf changes
-
-**Don't:**
-- List every file changed — that's what the diff is for
-- Repeat the title in the body
-- Add "Files changed" or "Changes" sections
-- Write walls of text that go stale when the diff is updated
-- Use filler like "This PR introduces...", "comprehensive", "robust", "enhance", "leverage"
-
-**Template:**
-
-```
-Closes #<issue>
-
-<what changed, 1-3 sentences>
-
-<why, if not obvious from the diff>
-```
-
-**Good example:**
-
-```
-Closes #16800
-
-Adds fallback for external IP resolution so node startup doesn't fail
-when STUN is unreachable. Falls back to the configured default.
-```
-
-**Bad example:**
-
-```
-## Summary
-This PR introduces comprehensive improvements to the IP resolution system.
-
-## Changes
-- Modified `crates/net/discv4/src/lib.rs` to add fallback
-- Modified `crates/net/discv4/src/config.rs` to add default IP
-- Added tests in `crates/net/discv4/src/tests/ip.rs`
-
-## Files Changed
-- crates/net/discv4/src/lib.rs
-- crates/net/discv4/src/config.rs
-- crates/net/discv4/src/tests/ip.rs
-```
-
-#### Labels and CI
-
-Label PRs appropriately, first check the available labels and then apply the relevant ones:
-* when changes are RPC related, add A-rpc label
-* when changes are docs related, add C-docs label
-* ... and so on, check the available labels for more options.
-* if being tasked to open a pr, ensure that all changes are properly formatted: `cargo +nightly fmt --all`
-
-If changes in reth include changes to dependencies, run commands `zepter` and `make lint-toml` before finalizing the pr. Assume `zepter` binary is installed.
-
-### Debugging Tips
-
-1. **Logging**: Use `tracing` crate with appropriate levels
-   ```rust
-   tracing::debug!(target: "reth::component", ?value, "description");
-   ```
-
-2. **Metrics**: Add metrics for monitoring
-   ```rust
-   metrics::counter!("reth_component_operations").increment(1);
-   ```
-
-3. **Test Isolation**: Use separate test databases/directories
-
-### Finding Where to Contribute
-
-1. **Check Issues**: Look for issues labeled `good-first-issue` or `help-wanted`
-2. **Review TODOs**: Search for `TODO` comments in the codebase
-3. **Improve Tests**: Areas with low test coverage are good targets
-4. **Documentation**: Improve code comments and documentation
-5. **Performance**: Profile and optimize hot paths (with benchmarks)
-
-### Common PR Patterns
-
-#### Small, Focused Changes
-Most PRs change only 1-5 files. Examples:
-- Single-line bug fixes
-- Adding a missing trait implementation
-- Updating error messages
-- Adding test cases for edge conditions
-
-#### Integration Work
-When dependencies update (especially revm), code needs updating:
-- Check for breaking API changes
-- Update to use new features (like EIP implementations)
-- Ensure compatibility with new versions
-
-#### Test Improvements
-Tests often need expansion for:
-- New protocol versions (ETH68, ETH69)
-- Edge cases in state transitions
-- Network behavior under specific conditions
-- Concurrent operations
-
-#### Making Code More Generic
-Common refactoring pattern:
-- Replace concrete types with generics
-- Add trait bounds for flexibility
-- Enable reuse across different chain types
-
-#### When to Comment
-
-Write comments that remain valuable after the PR is merged. Future readers won't have PR context - they only see the current code.
-
-##### ✅ DO: Add Value
-
-**Explain WHY and non-obvious behavior:**
-```rust
-// Process must handle allocations atomically to prevent race conditions
-// between dealloc on drop and concurrent limit checks
-unsafe impl GlobalAlloc for LimitedAllocator { ... }
-
-// Binary search requires sorted input. Panics on unsorted slices.
-fn find_index(items: &[Item], target: &Item) -> Option<usize>
-
-// Timeout set to 5s to match EVM block processing limits
-const TRACER_TIMEOUT: Duration = Duration::from_secs(5);
-```
-
-**Document constraints and assumptions:**
-```rust
-/// Returns heap size estimate.
-/// 
-/// Note: May undercount shared references (Rc/Arc). For precise
-/// accounting, combine with an allocator-based approach.
-fn deep_size_of(&self) -> usize
-```
-
-**Explain complex logic:**
-```rust
-// We reset limits at task start because tokio reuses threads in
-// spawn_blocking pool. Without reset, second task inherits first
-// task's allocation count and immediately hits limit.
-THREAD_ALLOCATED.with(|allocated| allocated.set(0));
-```
-
-##### ❌ DON'T: Describe Changes
-```rust
-// ❌ BAD - Describes the change, not the code
-// Changed from Vec to HashMap for O(1) lookups
-
-// ✅ GOOD - Explains the decision
-// HashMap provides O(1) symbol lookups during trace replay
-```
-```rust
-// ❌ BAD - PR-specific context
-// Fix for issue #234 where memory wasn't freed
-
-// ✅ GOOD - Documents the actual behavior
-// Explicitly drop allocations before limit check to ensure
-// accurate accounting
-```
-```rust
-// ❌ BAD - States the obvious
-// Increment counter
-counter += 1;
-
-// ✅ GOOD - Explains non-obvious purpose
-// Track allocations across all threads for global limit enforcement
-GLOBAL_COUNTER.fetch_add(1, Ordering::SeqCst);
-```
-
-✅ **Comment when:**
-- Non-obvious behavior or edge cases
-- Performance trade-offs
-- Safety requirements (unsafe blocks must always be documented)
-- Limitations or gotchas
-- Why simpler alternatives don't work
-
-❌ **Don't comment when:**
-- Code is self-explanatory
-- Just restating the code in English
-- Describing what changed in this PR
-
-##### The Test: "Will this make sense in 6 months?"
-
-Before adding a comment, ask: Would someone reading just the current code (no PR, no history) find this helpful?
-
-
-#### Rust Style Guides
-
-##### Type Ordering in Files
-
-When defining structs, traits, and functions in a file, follow this ordering convention. The file's primary type (matching the file name) comes first, followed by supporting public types, then private types and helpers.
-
-```rust
-use ...;
-
-/// The primary type of this file (matches filename).
-pub struct PayloadProcessor { ... }
-
-impl PayloadProcessor { ... }
-
-// Followed by public auxiliary types that support the primary type
-
-/// Configuration for the processor.
-pub struct PayloadProcessorConfig { ... }
-
-/// Result type returned by processor operations.
-pub struct ProcessorResult { ... }
-
-// Followed by public traits related to the primary type
-
-pub trait ProcessorExt { ... }
-
-// Followed by private helper types
-
-struct InternalState { ... }
-
-// Followed by private helper functions
-
-fn validate_input() { ... }
-```
-
-❌ **Bad**: Adding new traits and auxiliary types **above** the file's primary type (see [#22133](https://github.com/paradigmxyz/reth/pull/22133)):
-
-```rust
-use ...;
-
-// ❌ BAD - new auxiliary struct added before the file's main type
-pub struct CacheWaitDurations { ... }
-
-// ❌ BAD - new trait added before the file's main type  
-pub trait WaitForCaches { ... }
-
-// The file's primary type is buried below unrelated additions
-pub struct PayloadProcessor { ... }
-```
-
-✅ **Good**: New types go **after** the primary type:
-
-```rust
-use ...;
-
-// ✅ The file's primary type stays at the top
-pub struct PayloadProcessor { ... }
-
-impl PayloadProcessor { ... }
-
-// ✅ Auxiliary types follow the primary type
-pub struct CacheWaitDurations { ... }
-
-pub trait WaitForCaches { ... }
-
-impl WaitForCaches for PayloadProcessor { ... }
-```
-
-### Example Contribution Workflow
-
-Let's say you want to fix a bug where external IP resolution fails on startup:
-
-1. **Create a branch**:
-   ```bash
-   git checkout -b fix-external-ip-resolution
-   ```
-
-2. **Find the relevant code**:
-   ```bash
-   # Search for IP resolution code
-   rg "external.*ip" --type rust
-   ```
-
-3. **Reason about the problem, when the problem is identified, make the fix**:
-   ```rust
-   // In crates/net/discv4/src/lib.rs
-   pub fn resolve_external_ip() -> Option<IpAddr> {
-       // Add fallback mechanism
-       nat::external_ip()
-           .or_else(|| nat::external_ip_from_stun())
-           .or_else(|| Some(DEFAULT_IP))
-   }
-   ```
-
-4. **Add a test**:
-   ```rust
-   #[test]
-   fn test_external_ip_fallback() {
-       // Test that resolution has proper fallbacks
-   }
-   ```
-
-5. **Run checks** (IMPORTANT!):
-   ```bash
-   cargo +nightly fmt --all
-   cargo clippy --workspace --all-features # Make sure WHOLE WORKSPACE compiles!
-   cargo nextest run -p reth-discv4
-   ```
-
-6. **Commit with clear message**:
-   ```bash
-   git commit -m "fix: add fallback for external IP resolution
-
-   Previously, node startup could fail if external IP resolution
-   failed. This adds fallback mechanisms to ensure the node can
-   always start with a reasonable default."
-   ```
-
-## Quick Reference
-
-### Essential Commands
-
-```bash
-# Format code
-cargo +nightly fmt --all
-
-# Run lints
-cargo +nightly clippy --workspace --all-features
-
-# Run tests
-cargo nextest run --workspace
-
-# Run specific benchmark
-cargo bench --bench bench_name
-
-# Build optimized binary
-cargo build --release
-
-# Check compilation for all features
-cargo check --workspace --all-features
-
-# Check documentation
-cargo docs --document-private-items
-
-# Regenerate CLI reference docs (after CLI changes)
-make update-book-cli
-```

CLAUDE.md

@@ -1 +0,0 @@
-AGENTS.md

CLAUDE.md

@@ -0,0 +1,391 @@
+# Reth Development Guide for AI Agents
+
+This guide provides comprehensive instructions for AI agents working on the Reth codebase. It covers the architecture, development workflows, and critical guidelines for effective contributions.
+
+## Project Overview
+
+Reth is a high-performance Ethereum execution client written in Rust, focusing on modularity, performance, and contributor-friendliness. The codebase is organized into well-defined crates with clear boundaries and responsibilities.
+
+## Architecture Overview
+
+### Core Components
+
+1. **Consensus (`crates/consensus/`)**: Validates blocks according to Ethereum consensus rules
+2. **Storage (`crates/storage/`)**: Hybrid database using MDBX + static files for optimal performance
+3. **Networking (`crates/net/`)**: P2P networking stack with discovery, sync, and transaction propagation
+4. **RPC (`crates/rpc/`)**: JSON-RPC server supporting all standard Ethereum APIs
+5. **Execution (`crates/evm/`, `crates/ethereum/`)**: Transaction execution and state transitions
+6. **Pipeline (`crates/stages/`)**: Staged sync architecture for blockchain synchronization
+7. **Trie (`crates/trie/`)**: Merkle Patricia Trie implementation with parallel state root computation
+8. **Node Builder (`crates/node/`)**: High-level node orchestration and configuration
+9. **The Consensus Engine (`crates/engine/`)**: Handles processing blocks received from the consensus layer with the Engine API (newPayload, forkchoiceUpdated)
+
+### Key Design Principles
+
+- **Modularity**: Each crate can be used as a standalone library
+- **Performance**: Extensive use of parallelism, memory-mapped I/O, and optimized data structures
+- **Extensibility**: Traits and generic types allow for different chain implementations
+- **Type Safety**: Strong typing throughout with minimal use of dynamic dispatch
+
+## Development Workflow
+
+### Code Style and Standards
+
+1. **Formatting**: Always use nightly rustfmt
+   ```bash
+   cargo +nightly fmt --all
+   ```
+
+2. **Linting**: Run clippy with all features
+   ```bash
+   cargo +nightly clippy --workspace --lib --examples --tests --benches --all-features 
+   ```
+
+3. **Testing**: Use nextest for faster test execution
+   ```bash
+   cargo nextest run --workspace
+   ```
+
+### Common Contribution Types
+
+Based on actual recent PRs, here are typical contribution patterns:
+
+#### 1. Small Bug Fixes (1-10 lines)
+Real example: Fixing beacon block root handling ([#16767](https://github.com/paradigmxyz/reth/pull/16767))
+```rust
+// Changed a single line to fix logic error
+- parent_beacon_block_root: parent.parent_beacon_block_root(),
++ parent_beacon_block_root: parent.parent_beacon_block_root().map(|_| B256::ZERO),
+```
+
+#### 2. Integration with Upstream Changes
+Real example: Integrating revm updates ([#16752](https://github.com/paradigmxyz/reth/pull/16752))
+```rust
+// Update code to use new APIs from dependencies
+- if self.fork_tracker.is_shanghai_activated() {
+-     if let Err(err) = transaction.ensure_max_init_code_size(MAX_INIT_CODE_BYTE_SIZE) {
++ if let Some(init_code_size_limit) = self.fork_tracker.max_initcode_size() {
++     if let Err(err) = transaction.ensure_max_init_code_size(init_code_size_limit) {
+```
+
+#### 3. Adding Comprehensive Tests
+Real example: ETH69 protocol tests ([#16759](https://github.com/paradigmxyz/reth/pull/16759))
+```rust
+#[tokio::test(flavor = "multi_thread")]
+async fn test_eth69_peers_can_connect() {
+    // Create test network with specific protocol versions
+    let p0 = PeerConfig::with_protocols(NoopProvider::default(), Some(EthVersion::Eth69.into()));
+    // Test connection and version negotiation
+}
+```
+
+#### 4. Making Components Generic
+Real example: Making EthEvmConfig generic over chainspec ([#16758](https://github.com/paradigmxyz/reth/pull/16758))
+```rust
+// Before: Hardcoded to ChainSpec
+- pub struct EthEvmConfig<EvmFactory = EthEvmFactory> {
+-     pub executor_factory: EthBlockExecutorFactory<RethReceiptBuilder, Arc<ChainSpec>, EvmFactory>,
+
+// After: Generic over any chain spec type
++ pub struct EthEvmConfig<C = ChainSpec, EvmFactory = EthEvmFactory>
++ where
++     C: EthereumHardforks,
++ {
++     pub executor_factory: EthBlockExecutorFactory<RethReceiptBuilder, Arc<C>, EvmFactory>,
+```
+
+#### 5. Resource Management Improvements
+Real example: ETL directory cleanup ([#16770](https://github.com/paradigmxyz/reth/pull/16770))
+```rust
+// Add cleanup logic on startup
++ if let Err(err) = fs::remove_dir_all(&etl_path) {
++     warn!(target: "reth::cli", ?etl_path, %err, "Failed to remove ETL path on launch");
++ }
+```
+
+#### 6. Feature Additions
+Real example: Sharded mempool support ([#16756](https://github.com/paradigmxyz/reth/pull/16756))
+```rust
+// Add new filtering policies for transaction announcements
+pub struct ShardedMempoolAnnouncementFilter<T> {
+    pub inner: T,
+    pub shard_bits: u8,
+    pub node_id: Option<B256>,
+}
+```
+
+### Testing Guidelines
+
+1. **Unit Tests**: Test individual functions and components
+2. **Integration Tests**: Test interactions between components
+3. **Benchmarks**: For performance-critical code
+4. **Fuzz Tests**: For parsing and serialization code
+5. **Property Tests**: For checking component correctness on a wide variety of inputs
+
+Example test structure:
+```rust
+#[cfg(test)]
+mod tests {
+    use super::*;
+    
+    #[test]
+    fn test_component_behavior() {
+        // Arrange
+        let component = Component::new();
+        
+        // Act
+        let result = component.operation();
+        
+        // Assert
+        assert_eq!(result, expected);
+    }
+}
+```
+
+### Performance Considerations
+
+1. **Avoid Allocations in Hot Paths**: Use references and borrowing
+2. **Parallel Processing**: Use rayon for CPU-bound parallel work
+3. **Async/Await**: Use tokio for I/O-bound operations
+4. **File Operations**: Use `reth_fs_util` instead of `std::fs` for better error handling
+
+### Common Pitfalls
+
+1. **Don't Block Async Tasks**: Use `spawn_blocking` for CPU-intensive work or work with lots of blocking I/O
+2. **Handle Errors Properly**: Use `?` operator and proper error types
+
+### What to Avoid
+
+Based on PR patterns, avoid:
+
+1. **Large, sweeping changes**: Keep PRs focused and reviewable
+2. **Mixing unrelated changes**: One logical change per PR
+3. **Ignoring CI failures**: All checks must pass
+4. **Incomplete implementations**: Finish features before submitting
+5. **Modifying libmdbx sources**: Never modify files in `crates/storage/libmdbx-rs/mdbx-sys/libmdbx/` - this is vendored third-party code
+
+### CI Requirements
+
+Before submitting changes, ensure:
+
+1. **Format Check**: `cargo +nightly fmt --all --check`
+2. **Clippy**: No warnings
+3. **Tests Pass**: All unit and integration tests
+4. **Documentation**: Update relevant docs and add doc comments with `cargo docs --document-private-items`
+5. **Commit Messages**: Follow conventional format (feat:, fix:, chore:, etc.)
+
+### Opening PRs against <https://github.com/paradigmxyz/reth>
+
+Label PRs appropriately, first check the available labels and then apply the relevant ones:
+* when changes are RPC related, add A-rpc label
+* when changes are docs related, add C-docs label
+* ... and so on, check the available labels for more options.
+* if being tasked to open a pr, ensure that all changes are properly formatted: `cargo +nightly fmt --all`
+
+If changes in reth include changes to dependencies, run commands `zepter` and `make lint-toml` before finalizing the pr. Assume `zepter` binary is installed.
+
+### Debugging Tips
+
+1. **Logging**: Use `tracing` crate with appropriate levels
+   ```rust
+   tracing::debug!(target: "reth::component", ?value, "description");
+   ```
+
+2. **Metrics**: Add metrics for monitoring
+   ```rust
+   metrics::counter!("reth_component_operations").increment(1);
+   ```
+
+3. **Test Isolation**: Use separate test databases/directories
+
+### Finding Where to Contribute
+
+1. **Check Issues**: Look for issues labeled `good-first-issue` or `help-wanted`
+2. **Review TODOs**: Search for `TODO` comments in the codebase
+3. **Improve Tests**: Areas with low test coverage are good targets
+4. **Documentation**: Improve code comments and documentation
+5. **Performance**: Profile and optimize hot paths (with benchmarks)
+
+### Common PR Patterns
+
+#### Small, Focused Changes
+Most PRs change only 1-5 files. Examples:
+- Single-line bug fixes
+- Adding a missing trait implementation
+- Updating error messages
+- Adding test cases for edge conditions
+
+#### Integration Work
+When dependencies update (especially revm), code needs updating:
+- Check for breaking API changes
+- Update to use new features (like EIP implementations)
+- Ensure compatibility with new versions
+
+#### Test Improvements
+Tests often need expansion for:
+- New protocol versions (ETH68, ETH69)
+- Edge cases in state transitions
+- Network behavior under specific conditions
+- Concurrent operations
+
+#### Making Code More Generic
+Common refactoring pattern:
+- Replace concrete types with generics
+- Add trait bounds for flexibility
+- Enable reuse across different chain types
+
+#### When to Comment
+
+Write comments that remain valuable after the PR is merged. Future readers won't have PR context - they only see the current code.
+
+##### ✅ DO: Add Value
+
+**Explain WHY and non-obvious behavior:**
+```rust
+// Process must handle allocations atomically to prevent race conditions
+// between dealloc on drop and concurrent limit checks
+unsafe impl GlobalAlloc for LimitedAllocator { ... }
+
+// Binary search requires sorted input. Panics on unsorted slices.
+fn find_index(items: &[Item], target: &Item) -> Option<usize>
+
+// Timeout set to 5s to match EVM block processing limits
+const TRACER_TIMEOUT: Duration = Duration::from_secs(5);
+```
+
+**Document constraints and assumptions:**
+```rust
+/// Returns heap size estimate.
+/// 
+/// Note: May undercount shared references (Rc/Arc). For precise
+/// accounting, combine with an allocator-based approach.
+fn deep_size_of(&self) -> usize
+```
+
+**Explain complex logic:**
+```rust
+// We reset limits at task start because tokio reuses threads in
+// spawn_blocking pool. Without reset, second task inherits first
+// task's allocation count and immediately hits limit.
+THREAD_ALLOCATED.with(|allocated| allocated.set(0));
+```
+
+##### ❌ DON'T: Describe Changes
+```rust
+// ❌ BAD - Describes the change, not the code
+// Changed from Vec to HashMap for O(1) lookups
+
+// ✅ GOOD - Explains the decision
+// HashMap provides O(1) symbol lookups during trace replay
+```
+```rust
+// ❌ BAD - PR-specific context
+// Fix for issue #234 where memory wasn't freed
+
+// ✅ GOOD - Documents the actual behavior
+// Explicitly drop allocations before limit check to ensure
+// accurate accounting
+```
+```rust
+// ❌ BAD - States the obvious
+// Increment counter
+counter += 1;
+
+// ✅ GOOD - Explains non-obvious purpose
+// Track allocations across all threads for global limit enforcement
+GLOBAL_COUNTER.fetch_add(1, Ordering::SeqCst);
+```
+
+✅ **Comment when:**
+- Non-obvious behavior or edge cases
+- Performance trade-offs
+- Safety requirements (unsafe blocks must always be documented)
+- Limitations or gotchas
+- Why simpler alternatives don't work
+
+❌ **Don't comment when:**
+- Code is self-explanatory
+- Just restating the code in English
+- Describing what changed in this PR
+
+##### The Test: "Will this make sense in 6 months?"
+
+Before adding a comment, ask: Would someone reading just the current code (no PR, no history) find this helpful?
+
+
+### Example Contribution Workflow
+
+Let's say you want to fix a bug where external IP resolution fails on startup:
+
+1. **Create a branch**:
+   ```bash
+   git checkout -b fix-external-ip-resolution
+   ```
+
+2. **Find the relevant code**:
+   ```bash
+   # Search for IP resolution code
+   rg "external.*ip" --type rust
+   ```
+
+3. **Reason about the problem, when the problem is identified, make the fix**:
+   ```rust
+   // In crates/net/discv4/src/lib.rs
+   pub fn resolve_external_ip() -> Option<IpAddr> {
+       // Add fallback mechanism
+       nat::external_ip()
+           .or_else(|| nat::external_ip_from_stun())
+           .or_else(|| Some(DEFAULT_IP))
+   }
+   ```
+
+4. **Add a test**:
+   ```rust
+   #[test]
+   fn test_external_ip_fallback() {
+       // Test that resolution has proper fallbacks
+   }
+   ```
+
+5. **Run checks** (IMPORTANT!):
+   ```bash
+   cargo +nightly fmt --all
+   cargo clippy --workspace --all-features # Make sure WHOLE WORKSPACE compiles!
+   cargo nextest run -p reth-discv4
+   ```
+
+6. **Commit with clear message**:
+   ```bash
+   git commit -m "fix: add fallback for external IP resolution
+
+   Previously, node startup could fail if external IP resolution
+   failed. This adds fallback mechanisms to ensure the node can
+   always start with a reasonable default."
+   ```
+
+## Quick Reference
+
+### Essential Commands
+
+```bash
+# Format code
+cargo +nightly fmt --all
+
+# Run lints
+cargo +nightly clippy --workspace --all-features
+
+# Run tests
+cargo nextest run --workspace
+
+# Run specific benchmark
+cargo bench --bench bench_name
+
+# Build optimized binary
+cargo build --release
+
+# Check compilation for all features
+cargo check --workspace --all-features
+
+# Check documentation
+cargo docs --document-private-items 
+```

Cargo.toml

@@ -1,5 +1,5 @@
 [workspace.package]
-version = "2.1.0"
+version = "1.11.0"
 edition = "2024"
 rust-version = "1.93"
 license = "MIT OR Apache-2.0"
@@ -9,8 +9,8 @@ exclude = [".github/"]
 
 [workspace]
 members = [
-    "bin/reth-bb/",
     "bin/reth-bench/",
+    "bin/reth-bench-compare/",
     "bin/reth/",
     "crates/storage/rpc-provider/",
     "crates/chain-state/",
@@ -27,7 +27,6 @@ members = [
     "crates/engine/invalid-block-hooks/",
     "crates/engine/local",
     "crates/engine/primitives/",
-    "crates/engine/execution-cache/",
     "crates/engine/tree/",
     "crates/engine/util/",
     "crates/era",
@@ -78,6 +77,8 @@ members = [
     "crates/payload/primitives/",
     "crates/payload/validator/",
     "crates/payload/util/",
+    "crates/primitives-traits/",
+    "crates/primitives/",
     "crates/prune/db",
     "crates/prune/prune",
     "crates/prune/types",
@@ -99,6 +100,8 @@ members = [
     "crates/stages/types/",
     "crates/static-file/static-file",
     "crates/static-file/types/",
+    "crates/storage/codecs/",
+    "crates/storage/codecs/derive/",
     "crates/storage/db-api/",
     "crates/storage/db-common",
     "crates/storage/db-models/",
@@ -109,6 +112,7 @@ members = [
     "crates/storage/nippy-jar/",
     "crates/storage/provider/",
     "crates/storage/storage-api/",
+    "crates/storage/zstd-compressors/",
     "crates/tasks/",
     "crates/tokio-util/",
     "crates/tracing/",
@@ -129,7 +133,6 @@ members = [
     "examples/custom-node-components/",
     "examples/custom-payload-builder/",
     "examples/custom-rlpx-subprotocol",
-    "examples/custom-auth-http-middleware",
     "examples/custom-rpc-middleware",
     "examples/db-access",
     "examples/exex-subscription",
@@ -166,7 +169,6 @@ rust.rust_2018_idioms = { level = "deny", priority = -1 }
 rust.unreachable_pub = "warn"
 rust.unused_must_use = "deny"
 rust.rust_2024_incompatible_pat = "warn"
-rust.unexpected_cfgs = { level = "warn", check-cfg = ['cfg(tokio_unstable)'] }
 rustdoc.all = "warn"
 # rust.unnameable-types = "warn"
 
@@ -320,14 +322,15 @@ reth = { path = "bin/reth" }
 reth-storage-rpc-provider = { path = "crates/storage/rpc-provider" }
 reth-basic-payload-builder = { path = "crates/payload/basic" }
 reth-bench = { path = "bin/reth-bench" }
+reth-bench-compare = { path = "bin/reth-bench-compare" }
 reth-chain-state = { path = "crates/chain-state" }
 reth-chainspec = { path = "crates/chainspec", default-features = false }
 reth-cli = { path = "crates/cli/cli" }
 reth-cli-commands = { path = "crates/cli/commands" }
 reth-cli-runner = { path = "crates/cli/runner" }
 reth-cli-util = { path = "crates/cli/util" }
-reth-codecs = { version = "0.3.1", default-features = false }
-reth-codecs-derive = "0.3.1"
+reth-codecs = { path = "crates/storage/codecs" }
+reth-codecs-derive = { path = "crates/storage/codecs/derive" }
 reth-config = { path = "crates/config", default-features = false }
 reth-consensus = { path = "crates/consensus/consensus", default-features = false }
 reth-consensus-common = { path = "crates/consensus/common", default-features = false }
@@ -343,7 +346,6 @@ reth-downloaders = { path = "crates/net/downloaders" }
 reth-e2e-test-utils = { path = "crates/e2e-test-utils" }
 reth-ecies = { path = "crates/net/ecies" }
 reth-engine-local = { path = "crates/engine/local" }
-reth-execution-cache = { path = "crates/engine/execution-cache" }
 reth-engine-primitives = { path = "crates/engine/primitives", default-features = false }
 reth-engine-tree = { path = "crates/engine/tree" }
 reth-engine-util = { path = "crates/engine/util" }
@@ -395,7 +397,8 @@ reth-payload-builder-primitives = { path = "crates/payload/builder-primitives" }
 reth-payload-primitives = { path = "crates/payload/primitives" }
 reth-payload-validator = { path = "crates/payload/validator" }
 reth-payload-util = { path = "crates/payload/util" }
-reth-primitives-traits = { version = "0.3.1", default-features = false }
+reth-primitives = { path = "crates/primitives", default-features = false }
+reth-primitives-traits = { path = "crates/primitives-traits", default-features = false }
 reth-provider = { path = "crates/storage/provider" }
 reth-prune = { path = "crates/prune/prune" }
 reth-prune-types = { path = "crates/prune/types", default-features = false }
@@ -411,7 +414,6 @@ reth-rpc-eth-types = { path = "crates/rpc/rpc-eth-types", default-features = fal
 reth-rpc-layer = { path = "crates/rpc/rpc-layer" }
 reth-rpc-server-types = { path = "crates/rpc/rpc-server-types" }
 reth-rpc-convert = { path = "crates/rpc/rpc-convert" }
-reth-rpc-traits = { version = "0.3.1", default-features = false }
 reth-stages = { path = "crates/stages/stages" }
 reth-stages-api = { path = "crates/stages/api" }
 reth-stages-types = { path = "crates/stages/types", default-features = false }
@@ -430,59 +432,70 @@ reth-trie-common = { path = "crates/trie/common", default-features = false }
 reth-trie-db = { path = "crates/trie/db" }
 reth-trie-parallel = { path = "crates/trie/parallel" }
 reth-trie-sparse = { path = "crates/trie/sparse", default-features = false }
-reth-zstd-compressors = { version = "0.3.1", default-features = false }
+reth-zstd-compressors = { path = "crates/storage/zstd-compressors", default-features = false }
 
 # revm
-revm = { version = "=37.0.0", default-features = false }
-revm-bytecode = { version = "=10.0.0", default-features = false }
-revm-database = { version = "=13.0.0", default-features = false }
-revm-state = { version = "=11.0.0", default-features = false }
-revm-primitives = { version = "=23.0.0", default-features = false }
-revm-interpreter = { version = "=35.0.0", default-features = false }
-revm-database-interface = { version = "=11.0.0", default-features = false }
-revm-inspectors = "=0.39.0"
+revm = { version = "34.0.0", default-features = false }
+revm-bytecode = { version = "8.0.0", default-features = false }
+revm-database = { version = "10.0.0", default-features = false }
+revm-state = { version = "9.0.0", default-features = false }
+revm-primitives = { version = "22.0.0", default-features = false }
+revm-interpreter = { version = "32.0.0", default-features = false }
+revm-database-interface = { version = "9.0.0", default-features = false }
+op-revm = { version = "15.0.0", default-features = false }
+revm-inspectors = "0.34.2"
 
 # eth
 alloy-dyn-abi = "1.5.6"
 alloy-primitives = { version = "1.5.6", default-features = false, features = ["map-foldhash"] }
 alloy-sol-types = { version = "1.5.6", default-features = false }
 
-alloy-chains = { version = "0.2.33", default-features = false }
+alloy-chains = { version = "0.2.5", default-features = false }
 alloy-eip2124 = { version = "0.2.0", default-features = false }
-alloy-eip7928 = { version = "0.3.4", default-features = false }
-alloy-evm = { version = "0.33.0", default-features = false }
+alloy-eip7928 = { version = "0.3.0", default-features = false }
+alloy-evm = { version = "0.27.2", default-features = false }
 alloy-rlp = { version = "0.3.13", default-features = false, features = ["core-net"] }
 alloy-trie = { version = "0.9.4", default-features = false }
 
-alloy-hardforks = "0.4.7"
+alloy-hardforks = "0.4.5"
 
-alloy-consensus = { version = "2.0.1", default-features = false }
-alloy-contract = { version = "2.0.1", default-features = false }
-alloy-eips = { version = "2.0.1", default-features = false }
-alloy-genesis = { version = "2.0.1", default-features = false }
-alloy-json-rpc = { version = "2.0.1", default-features = false }
-alloy-network = { version = "2.0.1", default-features = false }
-alloy-network-primitives = { version = "2.0.1", default-features = false }
-alloy-provider = { version = "2.0.1", features = ["reqwest", "debug-api"], default-features = false }
-alloy-pubsub = { version = "2.0.1", default-features = false }
-alloy-rpc-client = { version = "2.0.1", default-features = false }
-alloy-rpc-types = { version = "2.0.1", features = ["eth"], default-features = false }
-alloy-rpc-types-admin = { version = "2.0.1", default-features = false }
-alloy-rpc-types-anvil = { version = "2.0.1", default-features = false }
-alloy-rpc-types-beacon = { version = "2.0.1", default-features = false }
-alloy-rpc-types-debug = { version = "2.0.1", default-features = false }
-alloy-rpc-types-engine = { version = "2.0.1", default-features = false }
-alloy-rpc-types-eth = { version = "2.0.1", default-features = false }
-alloy-rpc-types-mev = { version = "2.0.1", default-features = false }
-alloy-rpc-types-trace = { version = "2.0.1", default-features = false }
-alloy-rpc-types-txpool = { version = "2.0.1", default-features = false }
-alloy-serde = { version = "2.0.1", default-features = false }
-alloy-signer = { version = "2.0.1", default-features = false }
-alloy-signer-local = { version = "2.0.1", default-features = false }
-alloy-transport = { version = "2.0.1" }
-alloy-transport-http = { version = "2.0.1", features = ["reqwest-rustls-tls"], default-features = false }
-alloy-transport-ipc = { version = "2.0.1", default-features = false }
-alloy-transport-ws = { version = "2.0.1", default-features = false }
+alloy-consensus = { version = "1.6.3", default-features = false }
+alloy-contract = { version = "1.6.3", default-features = false }
+alloy-eips = { version = "1.6.3", default-features = false }
+alloy-genesis = { version = "1.6.3", default-features = false }
+alloy-json-rpc = { version = "1.6.3", default-features = false }
+alloy-network = { version = "1.6.3", default-features = false }
+alloy-network-primitives = { version = "1.6.3", default-features = false }
+alloy-provider = { version = "1.6.3", features = ["reqwest", "debug-api"], default-features = false }
+alloy-pubsub = { version = "1.6.3", default-features = false }
+alloy-rpc-client = { version = "1.6.3", default-features = false }
+alloy-rpc-types = { version = "1.6.3", features = ["eth"], default-features = false }
+alloy-rpc-types-admin = { version = "1.6.3", default-features = false }
+alloy-rpc-types-anvil = { version = "1.6.3", default-features = false }
+alloy-rpc-types-beacon = { version = "1.6.3", default-features = false }
+alloy-rpc-types-debug = { version = "1.6.3", default-features = false }
+alloy-rpc-types-engine = { version = "1.6.3", default-features = false }
+alloy-rpc-types-eth = { version = "1.6.3", default-features = false }
+alloy-rpc-types-mev = { version = "1.6.3", default-features = false }
+alloy-rpc-types-trace = { version = "1.6.3", default-features = false }
+alloy-rpc-types-txpool = { version = "1.6.3", default-features = false }
+alloy-serde = { version = "1.6.3", default-features = false }
+alloy-signer = { version = "1.6.3", default-features = false }
+alloy-signer-local = { version = "1.6.3", default-features = false }
+alloy-transport = { version = "1.6.3" }
+alloy-transport-http = { version = "1.6.3", features = ["reqwest-rustls-tls"], default-features = false }
+alloy-transport-ipc = { version = "1.6.3", default-features = false }
+alloy-transport-ws = { version = "1.6.3", default-features = false }
+
+# op
+alloy-op-evm = { version = "0.27.2", default-features = false }
+alloy-op-hardforks = "0.4.4"
+op-alloy-rpc-types = { version = "0.23.1", default-features = false }
+op-alloy-rpc-types-engine = { version = "0.23.1", default-features = false }
+op-alloy-network = { version = "0.23.1", default-features = false }
+op-alloy-consensus = { version = "0.23.1", default-features = false }
+op-alloy-rpc-jsonrpsee = { version = "0.23.1", default-features = false }
+op-alloy-flz = { version = "0.13.1", default-features = false }
 
 # misc
 either = { version = "1.15.0", default-features = false }
@@ -494,7 +507,6 @@ bincode = "1.3"
 bitflags = "2.4"
 boyer-moore-magiclen = "0.2.16"
 bytes = { version = "1.11.1", default-features = false }
-blake3 = "1.8"
 brotli = "8"
 cfg-if = "1.0"
 clap = "4"
@@ -507,30 +519,26 @@ eyre = "0.6"
 fdlimit = "0.3.0"
 fixed-map = { version = "0.9", default-features = false }
 humantime = "2.1"
-imbl = "7"
 humantime-serde = "1.1"
 itertools = { version = "0.14", default-features = false }
 linked_hash_set = "0.1"
-libc = "0.2"
 lz4 = "1.28.1"
 modular-bitfield = "0.13.1"
 notify = { version = "8.0.0", default-features = false, features = ["macos_fsevent"] }
 nybbles = { version = "0.4.8", default-features = false }
 once_cell = { version = "1.19", default-features = false, features = ["critical-section"] }
 parking_lot = "0.12"
-quanta = "0.12"
 paste = "1.0"
 rand = "0.9"
 rayon = "1.7"
-thread-priority = "3.0.0"
 rustc-hash = { version = "2.0", default-features = false }
 schnellru = "0.2"
 serde = { version = "1.0", default-features = false }
 serde_json = { version = "1.0", default-features = false, features = ["alloc"] }
 serde_with = { version = "3", default-features = false, features = ["macros"] }
 sha2 = { version = "0.10", default-features = false }
+shellexpand = "3.0.0"
 shlex = "1.3"
-slotmap = "1"
 smallvec = "1"
 strum = { version = "0.27", default-features = false }
 strum_macros = "0.27"
@@ -560,7 +568,7 @@ proc-macro2 = "1.0"
 quote = "1.0"
 
 # tokio
-tokio = { version = "1.51.1", default-features = false }
+tokio = { version = "1.44.2", default-features = false }
 tokio-stream = "0.1.11"
 tokio-tungstenite = "0.28.0"
 tokio-util = { version = "0.7.4", features = ["codec"] }
@@ -572,10 +580,10 @@ async-trait = "0.1.68"
 futures = "0.3"
 futures-core = "0.3"
 futures-util = { version = "0.3", default-features = false }
-hyper = "1.9"
+hyper = "1.3"
 hyper-util = "0.1.5"
 pin-project = "1.0.12"
-reqwest = { version = "0.13", default-features = false, features = ["rustls", "stream"] }
+reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "rustls-tls-native-roots", "stream"] }
 tracing-futures = "0.2"
 tower = "0.5"
 tower-http = "0.6"
@@ -625,7 +633,7 @@ tracing-opentelemetry = "0.32"
 arbitrary = "1.3"
 assert_matches = "1.5.0"
 criterion = { package = "codspeed-criterion-compat", version = "4.3" }
-insta = "1.47"
+insta = "1.41"
 proptest = "1.7"
 proptest-derive = "0.7"
 similar-asserts = { version = "1.5.0", features = ["serde"] }
@@ -641,9 +649,8 @@ ethereum_ssz_derive = "0.10.1"
 # allocators
 jemalloc_pprof = { version = "0.8", default-features = false }
 tikv-jemalloc-ctl = "0.6"
-tikv-jemalloc-sys = "0.6"
 tikv-jemallocator = "0.6"
-tracy-client = { version = "0.18.0", features = ["demangle"] }
+tracy-client = "0.18.0"
 snmalloc-rs = { version = "0.3.7", features = ["build_cc"] }
 
 aes = "0.8.1"
@@ -656,7 +663,6 @@ cipher = "0.4.3"
 comfy-table = "7.0"
 concat-kdf = "0.1.0"
 crossbeam-channel = "0.5.13"
-crossbeam-queue = "0.3"
 crossbeam-utils = "0.8"
 crossterm = "0.29.0"
 csv = "1.3.0"
@@ -673,8 +679,10 @@ indexmap = "2"
 interprocess = "2.2.0"
 lz4_flex = { version = "0.12", default-features = false }
 memmap2 = "0.9.4"
+mev-share-sse = { version = "0.5.0", default-features = false }
 num-traits = "0.2.15"
 page_size = "0.6.0"
+parity-scale-codec = "3.2.1"
 plain_hasher = "0.2"
 pretty_assertions = "1.4"
 ratatui = { version = "0.30", default-features = false }
@@ -687,7 +695,7 @@ snap = "1.1.1"
 socket2 = { version = "0.6", default-features = false }
 sysinfo = { version = "0.38", default-features = false }
 tracing-journald = "0.3"
-tracing-logfmt = "0.3.7"
+tracing-logfmt = "=0.3.5"
 tracing-samply = "0.1"
 tracing-subscriber = { version = "0.3", default-features = false }
 tracing-tracy = "0.11"
@@ -702,22 +710,52 @@ vergen-git2 = "9.1.0"
 ipnet = "2.11"
 
 [patch.crates-io]
-revm = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-bytecode = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-context = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-context-interface = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-database = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-database-interface = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-handler = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-inspector = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-interpreter = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-precompile = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-primitives = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-state = { git = "https://github.com/bluealloy/revm", rev = "fe2549d85fb9e201e7b629f8b47bcca46d49aa1d" }
-revm-inspectors = { git = "https://github.com/paradigmxyz/revm-inspectors", rev = "a2c7a41977b468d016a339f560acb76e002766f3" }
-alloy-evm = { git = "https://github.com/alloy-rs/evm", rev = "da7633f6bc9554f5a6e60773ef21b8e9d6e0cca6" }
-reth-codecs = { git = "https://github.com/paradigmxyz/reth-core", rev = "c763480b9fa51957fbdb69b7caead5dfc4e3752c" }
-reth-codecs-derive = { git = "https://github.com/paradigmxyz/reth-core", rev = "c763480b9fa51957fbdb69b7caead5dfc4e3752c" }
-reth-primitives-traits = { git = "https://github.com/paradigmxyz/reth-core", rev = "c763480b9fa51957fbdb69b7caead5dfc4e3752c" }
-reth-rpc-traits = { git = "https://github.com/paradigmxyz/reth-core", rev = "c763480b9fa51957fbdb69b7caead5dfc4e3752c" }
-reth-zstd-compressors = { git = "https://github.com/paradigmxyz/reth-core", rev = "c763480b9fa51957fbdb69b7caead5dfc4e3752c" }
+# alloy-consensus = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-contract = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-eips = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-genesis = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-json-rpc = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-network = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-network-primitives = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-provider = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-pubsub = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-client = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-admin = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-anvil = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-beacon = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-debug = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-engine = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-eth = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-mev = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-trace = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-rpc-types-txpool = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-serde = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-signer = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-signer-local = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-transport = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-transport-http = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-transport-ipc = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+# alloy-transport-ws = { git = "https://github.com/alloy-rs/alloy", rev = "3049f232fbb44d1909883e154eb38ec5962f53a3" }
+
+# op-alloy-consensus = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
+# op-alloy-network = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
+# op-alloy-rpc-types = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
+# op-alloy-rpc-types-engine = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
+# op-alloy-rpc-jsonrpsee = { git = "https://github.com/alloy-rs/op-alloy", rev = "a79d6fc" }
+#
+# revm-inspectors = { git = "https://github.com/paradigmxyz/revm-inspectors", rev = "1207e33" }
+#
+# jsonrpsee = { git = "https://github.com/paradigmxyz/jsonrpsee", branch = "matt/make-rpc-service-pub" }
+# jsonrpsee-core = { git = "https://github.com/paradigmxyz/jsonrpsee", branch = "matt/make-rpc-service-pub" }
+# jsonrpsee-server = { git = "https://github.com/paradigmxyz/jsonrpsee", branch = "matt/make-rpc-service-pub" }
+# jsonrpsee-http-client = { git = "https://github.com/paradigmxyz/jsonrpsee", branch = "matt/make-rpc-service-pub" }
+# jsonrpsee-types = { git = "https://github.com/paradigmxyz/jsonrpsee", branch = "matt/make-rpc-service-pub" }
+
+# alloy-evm = { git = "https://github.com/alloy-rs/evm", rev = "df124c0" }
+# alloy-op-evm = { git = "https://github.com/alloy-rs/evm", rev = "df124c0" }
+
+# revm-inspectors = { git = "https://github.com/paradigmxyz/revm-inspectors", rev = "3020ea8" }
+
+# alloy-evm = { git = "https://github.com/alloy-rs/evm", rev = "072c248" }
+# alloy-op-evm = { git = "https://github.com/alloy-rs/evm", rev = "072c248" }

Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker.io/docker/dockerfile:1.7-labs
 
-FROM lukemathwalker/cargo-chef:latest-rust-1.93 AS chef
+FROM lukemathwalker/cargo-chef:latest-rust-1 AS chef
 WORKDIR /app
 
 LABEL org.opencontainers.image.source=https://github.com/paradigmxyz/reth

Dockerfile.depot

@@ -4,7 +4,7 @@
 # Usage:
 #   reth: --build-arg BINARY=reth
 
-FROM rust:1.93 AS builder
+FROM rust:1 AS builder
 WORKDIR /app
 
 LABEL org.opencontainers.image.source=https://github.com/paradigmxyz/reth

Makefile

@@ -17,9 +17,6 @@ FEATURES ?=
 # Cargo profile for builds. Default is for local builds, CI uses an override.
 PROFILE ?= release
 
-# Extra RUSTFLAGS to append to build targets (e.g., "-C target-cpu=x86-64-v3")
-EXTRA_RUSTFLAGS ?=
-
 # Extra flags for Cargo
 CARGO_INSTALL_EXTRA_FLAGS ?=
 
@@ -70,14 +67,14 @@ build-%-reproducible:
 	LC_ALL=C \
 	TZ=UTC \
 	JEMALLOC_OVERRIDE=/usr/lib/x86_64-linux-gnu/libjemalloc.a \
-	cargo build --bin reth --features "$(FEATURES)" --profile "reproducible" --locked --target x86_64-unknown-linux-gnu
+	cargo build --bin reth --features "$(FEATURES) jemalloc-unprefixed" --profile "reproducible" --locked --target x86_64-unknown-linux-gnu
 
 .PHONY: build-debug
 build-debug: ## Build the reth binary into `target/debug` directory.
 	cargo build --bin reth --features "$(FEATURES)"
 # Builds the reth binary natively.
 build-native-%:
-	$(if $(EXTRA_RUSTFLAGS),RUSTFLAGS="$(EXTRA_RUSTFLAGS)") cargo build --bin reth --target $* --features "$(FEATURES)" --profile "$(PROFILE)"
+	cargo build --bin reth --target $* --features "$(FEATURES)" --profile "$(PROFILE)"
 
 # The following commands use `cross` to build a cross-compile.
 #
@@ -95,12 +92,11 @@ build-native-%:
 # on other systems. JEMALLOC_SYS_WITH_LG_PAGE=16 tells jemalloc to use 64-KiB
 # pages. See: https://github.com/paradigmxyz/reth/issues/6742
 build-aarch64-unknown-linux-gnu: export JEMALLOC_SYS_WITH_LG_PAGE=16
-build-native-aarch64-unknown-linux-gnu: export JEMALLOC_SYS_WITH_LG_PAGE=16
 
 # Note: The additional rustc compiler flags are for intrinsics needed by MDBX.
 # See: https://github.com/cross-rs/cross/wiki/FAQ#undefined-reference-with-build-std
 build-%:
-	RUSTFLAGS="-C link-arg=-lgcc -Clink-arg=-static-libgcc $(EXTRA_RUSTFLAGS)" \
+	RUSTFLAGS="-C link-arg=-lgcc -Clink-arg=-static-libgcc" \
 		cross build --bin reth --target $* --features "$(FEATURES)" --profile "$(PROFILE)"
 
 # Unfortunately we can't easily use cross to build for Darwin because of licensing issues.

README.md

@@ -7,9 +7,9 @@
 
 **Modular, contributor-friendly and blazing-fast implementation of the Ethereum protocol**
 
-![](./assets/reth-2.png)
+![](./assets/reth-prod.png)
 
-**[Install](https://reth.rs/installation/installation)**
+**[Install](https://paradigmxyz.github.io/reth/installation/installation.html)**
 | [User Docs](https://reth.rs)
 | [Developer Docs](./docs)
 | [Crate Docs](https://reth.rs/docs)
@@ -18,43 +18,51 @@
 [gh-lint]: https://github.com/paradigmxyz/reth/actions/workflows/lint.yml
 [tg-badge]: https://img.shields.io/endpoint?color=neon&logo=telegram&label=chat&url=https%3A%2F%2Ftg.sumanjay.workers.dev%2Fparadigm%5Freth
 
+> **Note: OP-Reth has moved**
+>
+> The Optimism (op-reth) crates have been moved to [ethereum-optimism/optimism](https://github.com/ethereum-optimism/optimism).
+> Git contribution history has been preserved. If you are looking for op-reth, please see the new repository.
+
 ## What is Reth?
 
-Reth (short for Rust Ethereum, [pronunciation](https://x.com/kelvinfichter/status/1597653609411268608)) is a production-ready Ethereum execution layer client focused on modularity, performance, and user-friendliness. Reth is compatible with all Ethereum Consensus Layer (CL) implementations that support the [Engine API](https://github.com/ethereum/execution-apis/tree/a0d03086564ab1838b462befbc083f873dcf0c0f/src/engine). It is built and driven forward by [Paradigm](https://paradigm.xyz/), and is licensed under the Apache and MIT licenses.
-
-> **Note:** OP-Reth has moved to [ethereum-optimism/optimism](https://github.com/ethereum-optimism/optimism). Git history has been preserved.
+Reth (short for Rust Ethereum, [pronunciation](https://x.com/kelvinfichter/status/1597653609411268608)) is a new Ethereum full node implementation that is focused on being user-friendly, highly modular, as well as being fast and efficient. Reth is an Execution Layer (EL) and is compatible with all Ethereum Consensus Layer (CL) implementations that support the [Engine API](https://github.com/ethereum/execution-apis/tree/a0d03086564ab1838b462befbc083f873dcf0c0f/src/engine). It is originally built and driven forward by [Paradigm](https://paradigm.xyz/), and is licensed under the Apache and MIT licenses.
 
 ## Goals
 
-1. **Modularity**: Every component is built to be used as a library: well-tested, documented and benchmarked. Import crates, mix and match, and innovate on top of them. Learn more about the project's components [here](./docs/repo/layout.md).
-2. **Performance**: Built with Rust, [Alloy](https://github.com/alloy-rs/alloy/), [revm](https://github.com/bluealloy/revm/), and [Foundry](https://github.com/foundry-rs/foundry/) — battle-tested and optimized for speed. Check the [ethPandaOps Lab Dashboard](https://lab.ethpandaops.io/ethereum/execution/timings) for a third-party comparison against other Ethereum clients.
-Here's what that looks like in practice, measured with [reth-bench](https://github.com/paradigmxyz/reth/tree/main/bin/reth-bench) on Ethereum Mainnet:
+As a full Ethereum node, Reth allows users to connect to the Ethereum network and interact with the Ethereum blockchain. This includes sending and receiving transactions/logs/traces, as well as accessing and interacting with smart contracts. Building a successful Ethereum node requires creating a high-quality implementation that is both secure and efficient, as well as being easy to use on consumer hardware. It also requires building a strong community of contributors who can help support and improve the software.
 
-![](./assets/reth-perf.png)
+More concretely, our goals are:
 
-3. **Free for anyone to use any way they want**: Apache/MIT licensed, no business license restrictions.
-4. **Client Diversity**: More client implementations make Ethereum more antifragile.
-5. **Support as many EVM chains as possible**: Reth can sync Ethereum and other EVM chains. If you're building one, reach out.
-6. **Configurability**: Profiles for different use cases — from high-performance RPC operators to hobbyists on consumer hardware.
+1. **Modularity**: Every component of Reth is built to be used as a library: well-tested, heavily documented and benchmarked. We envision that developers will import the node's crates, mix and match, and innovate on top of them. Examples of such usage include but are not limited to spinning up standalone P2P networks, talking directly to a node's database, or "unbundling" the node into the components you need. To achieve that, we are licensing Reth under the Apache/MIT permissive license. You can learn more about the project's components [here](./docs/repo/layout.md).
+2. **Performance**: Reth aims to be fast, so we use Rust and the [Erigon staged-sync](https://erigon.substack.com/p/erigon-stage-sync-and-control-flows) node architecture. We also use our Ethereum libraries (including [Alloy](https://github.com/alloy-rs/alloy/) and [revm](https://github.com/bluealloy/revm/)) which we've battle-tested and optimized via [Foundry](https://github.com/foundry-rs/foundry/).
+3. **Free for anyone to use any way they want**: Reth is free open source software, built for the community, by the community. By licensing the software under the Apache/MIT license, we want developers to use it without being bound by business licenses, or having to think about the implications of GPL-like licenses.
+4. **Client Diversity**: The Ethereum protocol becomes more antifragile when no node implementation dominates. This ensures that if there's a software bug, the network does not finalize a bad block. By building a new client, we hope to contribute to Ethereum's antifragility.
+5. **Support as many EVM chains as possible**: We aspire that Reth can full-sync not only Ethereum, but also other chains like Optimism, Polygon, BNB Smart Chain, and more. If you're working on any of these projects, please reach out. Note: OP-Reth has moved to [ethereum-optimism/optimism](https://github.com/ethereum-optimism/optimism).
+6. **Configurability**: We want to solve for node operators that care about fast historical queries, but also for hobbyists who cannot operate on large hardware. We also want to support teams and individuals who want both sync from genesis and via "fast sync". We envision that Reth will be configurable enough and provide configurable "profiles" for the tradeoffs that each team faces.
 
 ## Status
 
 Reth is production ready, and suitable for usage in mission-critical environments such as staking or high-uptime services. We also actively recommend professional node operators to switch to Reth in production for performance and cost reasons in use cases where high performance with great margins is required such as RPC, MEV, Indexing, Simulations, and P2P activities.
 
-- We released **Reth 2.0** in April 2026. See the [release notes](https://github.com/paradigmxyz/reth/releases/tag/v2.0.0) and [blog post](https://www.paradigm.xyz/2026/04/releasing-reth-2-0).
+More historical context below:
+
 - We released 1.0 "production-ready" stable Reth in June 2024.
   - Reth completed an audit with [Sigma Prime](https://sigmaprime.io/), the developers of [Lighthouse](https://github.com/sigp/lighthouse), the Rust Consensus Layer implementation. Find it [here](./audit/sigma_prime_audit_v2.pdf).
-  - Revm (the EVM used in Reth) underwent an audit with [Guido Vranken](https://x.com/guidovranken) (#1 [Ethereum Bug Bounty](https://ethereum.org/en/bug-bounty)).
+  - Revm (the EVM used in Reth) underwent an audit with [Guido Vranken](https://x.com/guidovranken) (#1 [Ethereum Bug Bounty](https://ethereum.org/en/bug-bounty)). We will publish the results soon.
 - We released multiple iterative beta versions, up to [beta.9](https://github.com/paradigmxyz/reth/releases/tag/v0.2.0-beta.9) on Monday June 3, 2024, the last beta release.
 - We released [beta](https://github.com/paradigmxyz/reth/releases/tag/v0.2.0-beta.1) on Monday March 4, 2024, our first breaking change to the database model, providing faster query speed, smaller database footprint, and allowing "history" to be mounted on separate drives.
 - We shipped iterative improvements until the last alpha release on February 28, 2024, [0.1.0-alpha.21](https://github.com/paradigmxyz/reth/releases/tag/v0.1.0-alpha.21).
 - We [initially announced](https://www.paradigm.xyz/2023/06/reth-alpha) [0.1.0-alpha.1](https://github.com/paradigmxyz/reth/releases/tag/v0.1.0-alpha.1) on June 20, 2023.
 
-### Storage compatibility
+### Database compatibility
 
-Storage V2 is the default for new nodes in Reth 2.0. Existing V1 nodes continue to work, but V1 support will be removed in a future release — all users are encouraged to migrate. V2 snapshots are available at [snapshots.reth.rs](https://snapshots.reth.rs/).
+We do not have any breaking database changes since beta.1, and we do not plan any in the near future.
 
-![](./assets/reth-storage.png)
+Reth [v0.2.0-beta.1](https://github.com/paradigmxyz/reth/releases/tag/v0.2.0-beta.1) includes
+a [set of breaking database changes](https://github.com/paradigmxyz/reth/pull/5191) that makes it impossible to use database files produced by earlier versions.
+
+If you had a database produced by alpha versions of Reth, you need to drop it with `reth db drop`
+(using the same arguments such as `--config` or `--datadir` that you passed to `reth node`), and resync using the same `reth node` command you've used before.
 
 ## For Users
 

bin/reth-bb/Cargo.toml

@@ -1,107 +0,0 @@
-[package]
-name = "reth-bb"
-version.workspace = true
-edition.workspace = true
-rust-version.workspace = true
-license.workspace = true
-homepage.workspace = true
-repository.workspace = true
-description = "Reth node configured for big block payload execution"
-
-[lints]
-workspace = true
-
-[dependencies]
-# reth
-reth-ethereum-cli.workspace = true
-reth-chainspec.workspace = true
-reth-ethereum-primitives.workspace = true
-reth-cli-util.workspace = true
-reth-node-core.workspace = true
-reth-node-ethereum.workspace = true
-reth-node-builder.workspace = true
-reth-node-api.workspace = true
-reth-ethereum-consensus.workspace = true
-reth-engine-primitives = { workspace = true, features = ["std"] }
-reth-engine-tree.workspace = true
-reth-primitives-traits.workspace = true
-reth-payload-primitives.workspace = true
-reth-provider.workspace = true
-reth-rpc-api.workspace = true
-reth-rpc-engine-api.workspace = true
-reth-evm.workspace = true
-reth-evm-ethereum.workspace = true
-reth-ethereum-forks.workspace = true
-reth-revm.workspace = true
-reth-consensus.workspace = true
-reth-chain-state.workspace = true
-reth-errors.workspace = true
-reth-storage-errors.workspace = true
-
-# alloy
-alloy-rpc-types = { workspace = true, features = ["engine"] }
-alloy-primitives.workspace = true
-alloy-rlp.workspace = true
-alloy-consensus.workspace = true
-alloy-eips.workspace = true
-alloy-evm.workspace = true
-
-# tracing
-tracing.workspace = true
-
-# misc
-clap = { workspace = true, features = ["derive", "env"] }
-jsonrpsee = { workspace = true, features = ["server", "macros"] }
-async-trait.workspace = true
-derive_more.workspace = true
-crossbeam-channel.workspace = true
-tokio = { workspace = true, features = ["sync"] }
-revm.workspace = true
-revm-primitives.workspace = true
-alloy-hardforks.workspace = true
-metrics.workspace = true
-
-# std
-eyre.workspace = true
-
-[features]
-default = [
-    "jemalloc",
-    "reth-cli-util/jemalloc",
-    "asm-keccak",
-    "keccak-cache-global",
-    "min-debug-logs",
-]
-
-jemalloc = [
-    "reth-cli-util/jemalloc",
-    "reth-node-core/jemalloc",
-    "reth-ethereum-cli/jemalloc",
-    "reth-provider/jemalloc",
-]
-
-asm-keccak = [
-    "reth-node-core/asm-keccak",
-    "reth-ethereum-cli/asm-keccak",
-    "reth-node-ethereum/asm-keccak",
-    "alloy-primitives/asm-keccak",
-    "alloy-evm/asm-keccak",
-    "revm/asm-keccak",
-    "revm-primitives/asm-keccak",
-]
-
-keccak-cache-global = [
-    "reth-node-core/keccak-cache-global",
-    "reth-node-ethereum/keccak-cache-global",
-    "alloy-primitives/keccak-cache-global",
-]
-
-min-debug-logs = [
-    "tracing/release_max_level_debug",
-    "reth-ethereum-cli/min-debug-logs",
-    "reth-node-core/min-debug-logs",
-]
-
-[[bin]]
-name = "reth-bb"
-path = "src/main.rs"