Merge branch 'main' into lupin012/trace_rawTransaction_impl

Author: lupin012

.claude/skills/launch-bal-devnet-2/SKILL.md

@@ -0,0 +1,185 @@
+---
+name: launch-bal-devnet-2
+description: Launch erigon + Lighthouse on the bal-devnet-2 ethpandaops devnet (EIP-7928 Block Access Lists). Manages start/stop of both EL and CL clients with proper port offsets and JWT auth.
+allowed-tools: Bash, Read, Write, Edit, Glob
+allowed-prompts:
+  - tool: Bash
+    prompt: start, stop, and manage erigon and lighthouse processes for bal-devnet-2
+---
+
+# Launch bal-devnet-2 (EIP-7928 BAL Devnet)
+
+Run erigon (EL) + Lighthouse (CL) on the bal-devnet-2 ethpandaops devnet for testing EIP-7928 Block Access Lists.
+
+## Network Details
+
+| Parameter | Value |
+|-----------|-------|
+| Chain ID | 7033429093 |
+| Genesis timestamp | 1770388190 |
+| Amsterdam timestamp | 1770400508 (epoch 32) |
+| Lighthouse image | `ethpandaops/lighthouse:bal-devnet-2-65bb283` |
+| Lighthouse version | v8.0.1 (commit 65bb283, branch bal-devnet-2) |
+| Explorer | https://explorer.bal-devnet-2.ethpandaops.io |
+| Faucet | https://faucet.bal-devnet-2.ethpandaops.io |
+| RPC | https://rpc.bal-devnet-2.ethpandaops.io |
+| Checkpoint sync | https://checkpoint-sync.bal-devnet-2.ethpandaops.io |
+
+## Working Directory
+
+Ask the user where they want the working directory. Default suggestion: `~/bal-devnet-2/`.
+Use `$WORKDIR` throughout to refer to the chosen path.
+
+```
+$WORKDIR/
+├── genesis.json              # EL genesis
+├── config.yaml               # CL beacon config
+├── genesis.ssz               # CL genesis state
+├── testnet-config/           # Lighthouse testnet dir (config.yaml + genesis.ssz + deploy files)
+├── start-erigon.sh           # Erigon start script (run FIRST)
+├── start-lighthouse.sh       # Lighthouse start script (run SECOND)
+├── stop.sh                   # Stop both erigon + Lighthouse
+├── clean.sh                  # Stop, wipe data, re-init genesis
+├── erigon-data/              # Erigon datadir (contains jwt.hex)
+├── lighthouse-data/          # Lighthouse datadir
+├── erigon-console.log        # Erigon stdout/stderr
+└── lighthouse-console.log    # Lighthouse stdout/stderr
+```
+
+## Port Assignments (offset +100)
+
+| Service | Port | Protocol |
+|---------|------|----------|
+| Erigon HTTP RPC | 8645 | TCP |
+| Erigon Engine API (authrpc) | 8651 | TCP |
+| Erigon WebSocket | 8646 | TCP |
+| Erigon P2P | 30403 | TCP+UDP |
+| Erigon gRPC | 9190 | TCP |
+| Erigon Torrent | 42169 | TCP+UDP |
+| Erigon pprof | 6160 | TCP |
+| Erigon metrics | 6161 | TCP |
+| Lighthouse P2P | 9100 | TCP+UDP |
+| Lighthouse QUIC | 9101 | UDP |
+| Lighthouse HTTP API | 5152 | TCP |
+| Lighthouse metrics | 5264 | TCP |
+
+## Workflow
+
+### Step 1: Check Prerequisites
+
+1. Verify erigon binary exists at `./build/bin/erigon`. If not, invoke `/erigon-build`.
+2. Verify the Lighthouse Docker image is available:
+   ```bash
+   docker image inspect ethpandaops/lighthouse:bal-devnet-2-65bb283 > /dev/null 2>&1
+   ```
+   If not, pull it:
+   ```bash
+   docker pull ethpandaops/lighthouse:bal-devnet-2-65bb283
+   ```
+3. Verify config files exist in `$WORKDIR` (genesis.json, testnet-config/).
+   If not, download them:
+   ```bash
+   mkdir -p $WORKDIR/testnet-config
+   curl -sL -o $WORKDIR/genesis.json https://config.bal-devnet-2.ethpandaops.io/el/genesis.json
+   curl -sL -o $WORKDIR/testnet-config/config.yaml https://config.bal-devnet-2.ethpandaops.io/cl/config.yaml
+   curl -sL -o $WORKDIR/testnet-config/genesis.ssz https://config.bal-devnet-2.ethpandaops.io/cl/genesis.ssz
+   echo "0" > $WORKDIR/testnet-config/deposit_contract_block.txt
+   echo "0" > $WORKDIR/testnet-config/deploy_block.txt
+   ```
+
+### Step 2: Initialize Datadir (first run only)
+
+If `$WORKDIR/erigon-data/chaindata` does not exist:
+```bash
+./build/bin/erigon init --datadir $WORKDIR/erigon-data $WORKDIR/genesis.json
+```
+
+### Step 3: Create Scripts (first run only)
+
+If the start/stop/clean scripts don't exist yet, generate them. The scripts must use absolute paths based on `$WORKDIR`. Key details:
+
+**start-erigon.sh** — Runs erigon with `--externalcl`. Must start FIRST (creates JWT secret).
+- Env vars: `ERIGON_EXEC3_PARALLEL=true`, `ERIGON_ASSERT=true`, `ERIGON_EXEC3_WORKERS=12`, `LOG_HASH_MISMATCH_REASON=true`
+- Flags: `--datadir=$WORKDIR/erigon-data`, `--externalcl`, `--networkid=7033429093`, all 16 EL bootnodes, erigon static peers, `--prune.mode=minimal`, all offset ports (see port table), `--http.api=eth,erigon,engine,debug`, `--pprof`, `--metrics`
+- EL bootnodes: fetch from `https://config.bal-devnet-2.ethpandaops.io/api/v1/nodes/inventory` (extract enode URLs from `execution.enode` fields)
+
+**start-lighthouse.sh** — Runs Lighthouse via Docker with `--network=host`. Must start SECOND.
+- Checks JWT exists at `$WORKDIR/erigon-data/jwt.hex`
+- Docker container name: `bal-devnet-2-lighthouse`
+- Mounts: `$WORKDIR/testnet-config:/config:ro`, `$WORKDIR/lighthouse-data:/data`, JWT as `/jwt.hex:ro`
+- Flags: `--testnet-dir=/config`, `--execution-endpoint=http://127.0.0.1:8651`, `--execution-jwt=/jwt.hex`, all 15 CL ENR bootnodes, offset ports, `--checkpoint-sync-url=https://checkpoint-sync.bal-devnet-2.ethpandaops.io`
+- CL bootnodes: fetch from same inventory URL (extract ENR entries from `consensus.enr` fields)
+
+**stop.sh** — Stops Lighthouse (`docker stop bal-devnet-2-lighthouse`) then erigon (`pkill -f "datadir.*bal-devnet-2/erigon-data"`).
+
+**clean.sh** — Runs `stop.sh`, removes erigon chain data (chaindata, snapshots, txpool, nodes, temp) and lighthouse data, re-initializes genesis.
+
+### Step 4: Start Erigon (FIRST)
+
+Erigon must start first because it creates the JWT secret that Lighthouse needs.
+
+```bash
+cd $WORKDIR && nohup bash start-erigon.sh > erigon-console.log 2>&1 &
+```
+
+Verify it started:
+- Check `tail $WORKDIR/erigon-console.log` for startup messages
+- Check JWT exists: `ls $WORKDIR/erigon-data/jwt.hex`
+- Check port binding: `ss -tlnp | grep 8651`
+
+### Step 5: Start Lighthouse (SECOND)
+
+After erigon is running and JWT exists:
+
+```bash
+cd $WORKDIR && nohup bash start-lighthouse.sh > lighthouse-console.log 2>&1 &
+```
+
+Verify it started:
+- Check `tail $WORKDIR/lighthouse-console.log` for "Lighthouse started"
+- Look for "Loaded checkpoint block and state" (checkpoint sync)
+- Look for `peers: "N"` showing peer connections
+
+### Step 6: Monitor
+
+```bash
+# Erigon sync progress
+tail -f $WORKDIR/erigon-console.log
+
+# Lighthouse sync progress
+tail -f $WORKDIR/lighthouse-console.log
+
+# Check erigon block height via RPC
+curl -s http://localhost:8645 -X POST -H "Content-Type: application/json" \
+  -d '{"jsonrpc":"2.0","method":"eth_blockNumber","params":[],"id":1}' | python3 -m json.tool
+
+# Check lighthouse sync status
+curl -s http://localhost:5152/eth/v1/node/syncing | python3 -m json.tool
+```
+
+### Step 7: Stop
+
+```bash
+bash $WORKDIR/stop.sh
+```
+
+This stops Lighthouse (via `docker stop`) then erigon (via `pkill`).
+
+### Step 8: Clean (wipe data and re-init)
+
+```bash
+bash $WORKDIR/clean.sh
+```
+
+This runs `stop.sh`, removes erigon chain data (chaindata, snapshots, txpool, nodes, temp) and lighthouse data, then re-initializes genesis. After clean, start again with Steps 4-5.
+
+## Troubleshooting
+
+| Problem | Solution |
+|---------|----------|
+| JWT auth fails | Ensure erigon started first and `jwt.hex` exists. Lighthouse must mount the same file. |
+| No EL peers | Check firewall allows port 30403. Try adding `--nat=extip:<your-ip>`. |
+| No CL peers | Check firewall allows port 9100/9101. ENR bootnodes may have changed — re-fetch from inventory. |
+| "Head is optimistic" | Normal during initial sync. Erigon is behind Lighthouse. Will resolve as erigon catches up. |
+| Engine API timeout | Check erigon is running and authrpc port 8651 is accessible. |
+| Port conflict | Check `ss -tlnp | grep <port>`. Kill conflicting process or use higher offset. |

Makefile

@@ -189,6 +189,7 @@ COMMANDS += evm
 COMMANDS += caplin
 COMMANDS += snapshots
 COMMANDS += diag
+COMMANDS += mcp
 
 # build each command using %.cmd rule
 $(COMMANDS): %: %.cmd

cl/beacon/handler/block_production.go

@@ -47,6 +47,7 @@ import (
 	"github.com/erigontech/erigon/cl/gossip"
 	"github.com/erigontech/erigon/cl/persistence/beacon_indicies"
 	"github.com/erigontech/erigon/cl/phase1/core/state"
+	"github.com/erigontech/erigon/cl/phase1/network/subnets"
 	"github.com/erigontech/erigon/cl/transition"
 	"github.com/erigontech/erigon/cl/transition/impl/eth2"
 	"github.com/erigontech/erigon/cl/transition/machine"
@@ -143,8 +144,13 @@ func (a *ApiHandler) GetEthV1ValidatorAttestationData(
 	}
 
 	defer func() {
+		epoch := *slot / a.beaconChainCfg.SlotsPerEpoch
+		committeesPerSlot := a.syncedData.CommitteeCount(epoch)
+		subnet := subnets.ComputeSubnetForAttestation(
+			committeesPerSlot, *slot, *committeeIndex,
+			a.beaconChainCfg.SlotsPerEpoch, 64)
 		a.logger.Debug("Produced Attestation", "slot", *slot,
-			"committee_index", *committeeIndex, "cached", ok, "beacon_block_root",
+			"committee_index", *committeeIndex, "subnet", subnet, "cached", ok, "beacon_block_root",
 			attestationData.BeaconBlockRoot, "duration", time.Since(start))
 	}()
 

cl/p2p/mock_services/p2p_manager_mock.go

@@ -101,13 +101,22 @@ func (g *GossipManager) Close() error {
 }
 
 func (g *GossipManager) newPubsubValidator(service serviceintf.Service[any], conditions ...ConditionFunc) pubsub.ValidatorEx {
+	var selfID peer.ID
+	if h := g.p2p.Host(); h != nil {
+		selfID = h.ID()
+	}
 	return func(ctx context.Context, pid peer.ID, msg *pubsub.Message) (result pubsub.ValidationResult) {
 		defer func() {
 			if r := recover(); r != nil {
 				log.Error("[GossipManager] panic in validator, rejecting message", "err", r, "topic", msg.GetTopic())
 				result = pubsub.ValidationReject
 			}
 		}()
+		// Skip validation for self-published messages: they were already validated
+		// by ProcessMessage before Publish was called.
+		if selfID != "" && pid == selfID {
+			return pubsub.ValidationAccept
+		}
 		curVersion := g.beaconConfig.GetCurrentStateVersion(g.ethClock.GetCurrentEpoch())
 		// parse the topic and subnet
 		topic := msg.GetTopic()
@@ -252,8 +261,18 @@ func (g *GossipManager) Publish(ctx context.Context, name string, data []byte) e
 	if topicHandle == nil {
 		return fmt.Errorf("topic not found: %s", topic)
 	}
+	// Log peer count for attestation topics to help diagnose propagation issues
+	if gossip.IsTopicBeaconAttestation(name) {
+		peerCount := len(g.p2p.Pubsub().ListPeers(topic))
+		if peerCount == 0 {
+			log.Warn("[Gossip] Publishing attestation with NO peers on subnet", "topic", name, "peerCount", peerCount)
+		} else if peerCount < 3 {
+			log.Debug("[Gossip] Publishing attestation with low peer count", "topic", name, "peerCount", peerCount)
+		}
+	}
 	// Note: before publishing the message to the network, Publish() internally runs the validator function.
-	return topicHandle.topic.Publish(ctx, compressedData, pubsub.WithReadiness(pubsub.MinTopicSize(1)))
+	// Removed MinTopicSize(1) - don't fail if no peers on subnet, message will propagate when peers join
+	return topicHandle.topic.Publish(ctx, compressedData)
 }
 
 func (g *GossipManager) goCheckForkAndResubscribe(ctx context.Context) {

cl/phase1/network/gossip/gossip_manager.go

@@ -247,7 +247,7 @@ func (a *aggregateAndProofServiceImpl) ProcessMessage(
 			index: aggregateAndProof.SignedAggregateAndProof.Message.AggregatorIndex,
 		}
 		if a.seenAggreatorIndexes.Contains(seenIndex) {
-			return nil
+			return fmt.Errorf("%w: aggregator already seen", ErrIgnore)
 		}
 
 		committee, err := headState.GetBeaconCommitee(slot, committeeIndex)

cl/phase1/network/services/aggregate_and_proof_service.go

@@ -263,7 +263,7 @@ func (s *attestationService) ProcessMessage(ctx context.Context, subnet *uint64,
 		// mark the validator as seen
 		epochLastTime, ok := s.validatorAttestationSeen.Get(vIndex)
 		if ok && epochLastTime == targetEpoch {
-			return nil
+			return fmt.Errorf("validator already seen in target epoch %w", ErrIgnore)
 		}
 		s.validatorAttestationSeen.Add(vIndex, targetEpoch)