mirror of
https://github.com/chainstacklabs/pumpfun-bonkfun-bot.git
synced 2026-07-31 09:17:43 +00:00
a33f4fd035
Audited every script in learning-examples/ against mainnet. Broken — found by running them, all invisible offline: - listen_geyser.py crashed with IndexError after ~11 coins: it never resolved v0 address-lookup-table accounts, which geyser reports in meta.loaded_writable_addresses / loaded_readonly_addresses. Resolving them removes the crash and brings detections level with the WebSocket listeners, 35 coins each per 150 s. - compare_listeners.py logged 13,090,862 error lines / 888 MB in 150 s and never printed its own 30-second report: the inner recv() loop caught ConnectionClosed in a broad handler that only logged, so every following recv() raised at once and the outer reconnect handler was unreachable. Now 12 KB and exit 0. Same shape fixed in compare_migration_listeners.py, listen_blocksubscribe.py and extract_blocksubscribe_transactions.py; the last two also gained the reconnect loop their siblings already had. - decode_from_gettransaction.py matched instructions on account count instead of discriminator, reporting a real 19-account create_v2 as claim_cashback with every account under the wrong name. It also walked only top-level instructions, and in 40 consecutive pump.fun transactions there was 1 top-level pump instruction against 8 inner ones. - decode_from_blocksubscribe.py crashed on every real create_v2: on chain the trailing args are variable length, 0001 in one tx and 00 in another, so is_cashback_enabled can be absent entirely. - poll_bonding_curve_progress.py polled a hardcoded dead mint and took no argv. Obsolete: - Delete listen_blocksubscribe_old_raydium.py. Seven minutes on mainnet produced 0 initialize2 events while the wrapper listener caught 3 real migrations. - Delete the duplicate geyser stubs and protos under listen-new-tokens/. The protos were byte-identical to src/geyser/proto and the stubs had drifted; both geyser examples now import src.geyser.generated. - Recapture all four fixtures. The old ones were from Aug 2024 and included a 49-byte pre-creator bonding curve. Behind the protocol: - fetch_price.py, get_bonding_curve_status.py, poll_bonding_curve_progress.py and decode_from_getaccountinfo.py never read quote_mint and scaled by a hardcoded 1e9. Against a live USDC-paired curve the price was off by 1000x. - get_pumpswap_pools.py stopped parsing at coin_creator and missed the i128 virtual_quote_reserves. Live pools carry 17.5845 SOL of them, which under-prices by 3.5-23.9% when ignored. Duplication and naming: - Merge manual_buy_cu_optimized.py into manual_buy.py --cu-optimized. The deleted file's docstring said 512 KB while its code used 16 MB; simulation confirms 512 KB and 4 MB both fail MaxLoadedAccountsDataSizeExceeded on Token-2022 mints, so 16 MB is the correct value. - Merge listen_logsubscribe_abc.py into listen_logsubscribe.py. Its ATA derivation hardcoded the legacy token program, so every Associated BC it printed for a Token2022 coin was an address that does not exist on chain. Fixed on merge and cross-checked 59/59 against on-chain accounts. - Remove 19 dead symbols. BREAKING_FEE_RECIPIENTS is still live in the PumpSwap scripts and stays there. - Normalize naming: kebab-case directories, RPC method names as one lowercase token, scripts verb-first. Rules documented in CLAUDE.md. get_graduating_tokens.py is knowingly left broken: getProgramAccounts over the whole pump program is now rejected by providers and it needs a getProgramAccountsV2 rewrite, which belongs in its own PR. Verified: both offline gates pass, all 41 examples parse, every read-only script exercised on mainnet against SOL- and USDC-paired coins, no new ruff findings (427 -> 413). No script that spends real funds was run. Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
202 lines
6.9 KiB
Python
202 lines
6.9 KiB
Python
import base64
|
|
import hashlib
|
|
import json
|
|
import struct
|
|
import sys
|
|
|
|
from solders.transaction import Transaction, VersionedTransaction
|
|
|
|
|
|
def load_idl(file_path):
|
|
with open(file_path) as f:
|
|
return json.load(f)
|
|
|
|
|
|
def load_transaction(file_path):
|
|
with open(file_path) as f:
|
|
data = json.load(f)
|
|
return data
|
|
|
|
|
|
def decode_instruction(ix_data, ix_def):
|
|
"""Decode an instruction's args based on its IDL definition.
|
|
|
|
Supports the primitive scalar types and the `OptionBool` defined type
|
|
(added in the late-Feb 2026 cashback upgrade — `OptionBool` is a struct
|
|
wrapping a single bool, so it serializes as 1 byte on the wire).
|
|
|
|
Trailing args can be absent from the wire entirely: two real mainnet
|
|
`create_v2` instructions carry `0001` and `00` respectively after `creator`,
|
|
so `is_cashback_enabled` is there in one and omitted in the other. Anything
|
|
the data runs out for is reported as None rather than raising.
|
|
"""
|
|
args = {}
|
|
offset = 8 # Skip 8-byte discriminator
|
|
|
|
# Width each type needs before it can be read at all; strings carry their own
|
|
# 4-byte length prefix.
|
|
widths = {
|
|
"u64": 8,
|
|
"i64": 8,
|
|
"u32": 4,
|
|
"u16": 2,
|
|
"u8": 1,
|
|
"bool": 1,
|
|
"pubkey": 32,
|
|
"string": 4,
|
|
}
|
|
|
|
for arg in ix_def["args"]:
|
|
t = arg["type"]
|
|
needed = widths.get(t, 1) if isinstance(t, str) else 1
|
|
if offset + needed > len(ix_data):
|
|
# Truncated trailing arg: the sender omitted it.
|
|
args[arg["name"]] = None
|
|
continue
|
|
|
|
if t == "u64":
|
|
value = struct.unpack_from("<Q", ix_data, offset)[0]
|
|
offset += 8
|
|
elif t == "i64":
|
|
value = struct.unpack_from("<q", ix_data, offset)[0]
|
|
offset += 8
|
|
elif t == "u32":
|
|
value = struct.unpack_from("<I", ix_data, offset)[0]
|
|
offset += 4
|
|
elif t == "u16":
|
|
value = struct.unpack_from("<H", ix_data, offset)[0]
|
|
offset += 2
|
|
elif t == "u8":
|
|
value = ix_data[offset]
|
|
offset += 1
|
|
elif t == "bool":
|
|
value = bool(ix_data[offset])
|
|
offset += 1
|
|
elif t == "pubkey":
|
|
value = ix_data[offset : offset + 32].hex()
|
|
offset += 32
|
|
elif t == "string":
|
|
length = struct.unpack_from("<I", ix_data, offset)[0]
|
|
offset += 4
|
|
value = ix_data[offset : offset + length].decode("utf-8")
|
|
offset += length
|
|
elif isinstance(t, dict) and "defined" in t:
|
|
defined_name = t["defined"]["name"] if isinstance(t["defined"], dict) else t["defined"]
|
|
if defined_name == "OptionBool":
|
|
value = bool(ix_data[offset])
|
|
offset += 1
|
|
else:
|
|
raise ValueError(f"Unsupported defined type: {defined_name}")
|
|
else:
|
|
raise ValueError(f"Unsupported type: {t}")
|
|
|
|
args[arg["name"]] = value
|
|
|
|
return args
|
|
|
|
|
|
def calculate_discriminator(instruction_name):
|
|
sha = hashlib.sha256()
|
|
sha.update(instruction_name.encode("utf-8"))
|
|
discriminator_bytes = sha.digest()[:8]
|
|
discriminator = struct.unpack("<Q", discriminator_bytes)[0]
|
|
return discriminator
|
|
|
|
|
|
def decode_transaction(tx_data, idl):
|
|
decoded_instructions = []
|
|
|
|
# Decode the base64 transaction data
|
|
tx_data_decoded = base64.b64decode(tx_data["transaction"][0])
|
|
|
|
# Check if it's a versioned transaction
|
|
if tx_data.get("version") == 0:
|
|
# Use solders library for versioned transactions
|
|
transaction = VersionedTransaction.from_bytes(tx_data_decoded)
|
|
instructions = transaction.message.instructions
|
|
account_keys = transaction.message.account_keys
|
|
print("Versioned transaction detected")
|
|
else:
|
|
# Use legacy deserialization for older transactions
|
|
transaction = Transaction.from_bytes(tx_data_decoded)
|
|
instructions = transaction.message.instructions
|
|
account_keys = transaction.message.account_keys
|
|
print("Legacy transaction detected")
|
|
|
|
print(f"Number of instructions: {len(instructions)}")
|
|
|
|
for idx, ix in enumerate(instructions):
|
|
program_id = str(account_keys[ix.program_id_index])
|
|
print(f"\nInstruction {idx}:")
|
|
print(f"Program ID: {program_id}")
|
|
|
|
if (
|
|
program_id == "6EF8rrecthR5Dkzon8Nwu78hRvfCKubJ14M5uBEwF6P"
|
|
): # Pump Fun Program
|
|
ix_data = bytes(ix.data)
|
|
discriminator = struct.unpack("<Q", ix_data[:8])[0]
|
|
|
|
print(f"Discriminator: {discriminator:016x}")
|
|
|
|
for idl_ix in idl["instructions"]:
|
|
idl_discriminator = calculate_discriminator(f"global:{idl_ix['name']}")
|
|
|
|
if discriminator == idl_discriminator:
|
|
decoded_args = decode_instruction(ix_data, idl_ix)
|
|
accounts = [str(account_keys[acc_idx]) for acc_idx in ix.accounts]
|
|
decoded_instructions.append(
|
|
{
|
|
"name": idl_ix["name"],
|
|
"args": decoded_args,
|
|
"accounts": accounts,
|
|
"program": program_id,
|
|
}
|
|
)
|
|
break
|
|
else:
|
|
decoded_instructions.append(
|
|
{
|
|
"name": "Unknown",
|
|
"data": ix_data.hex(),
|
|
"accounts": [
|
|
str(account_keys[acc_idx]) for acc_idx in ix.accounts
|
|
],
|
|
"program": program_id,
|
|
}
|
|
)
|
|
else:
|
|
instruction_name = "External"
|
|
if program_id == "ComputeBudget111111111111111111111111111111":
|
|
if ix.data[:1] == b"\x03":
|
|
instruction_name = "ComputeBudget: Set compute unit limit"
|
|
elif ix.data[:1] == b"\x02":
|
|
instruction_name = "ComputeBudget: Set compute unit price"
|
|
elif program_id == "ATokenGPvbdGVxr1b2hvZbsiqW5xWH25efTNsLJA8knL":
|
|
instruction_name = "Associated Token Account: Create"
|
|
|
|
decoded_instructions.append(
|
|
{
|
|
"name": instruction_name,
|
|
"programId": program_id,
|
|
"data": bytes(ix.data).hex(),
|
|
"accounts": [str(account_keys[acc_idx]) for acc_idx in ix.accounts],
|
|
}
|
|
)
|
|
|
|
return decoded_instructions
|
|
|
|
|
|
tx_file_path = ""
|
|
|
|
if len(sys.argv) != 2:
|
|
tx_file_path = "learning-examples/blocksubscribe-transactions/raw_create_tx_from_blocksubscribe.json"
|
|
print(f"No path provided, using the path: {tx_file_path}")
|
|
else:
|
|
tx_file_path = sys.argv[1]
|
|
|
|
idl = load_idl("idl/pump_fun_idl.json")
|
|
tx_data = load_transaction(tx_file_path)
|
|
|
|
decoded_instructions = decode_transaction(tx_data, idl)
|
|
print(json.dumps(decoded_instructions, indent=2))
|