Files
neuron-tai/packages/tracker/meshnet_tracker/cli.py
2026-07-12 11:17:03 +03:00

478 lines
16 KiB
Python

"""meshnet-tracker CLI entry point."""
import argparse
import os
import socket
import sys
import time
from pathlib import Path
from .accounts import DEFAULT_ACCOUNTS_DB_PATH
from .billing import DEFAULT_BILLING_DB_PATH
from .capability import ALL_POLICIES as ALL_CAPABILITY_POLICIES
from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH
from .logging_setup import (
DEFAULT_LOG_BACKUP_COUNT,
DEFAULT_LOG_DIR,
DEFAULT_LOG_MAX_BYTES,
configure_tracker_file_logging,
)
from .routing_stats import RoutingConfig
from .server import (
DEFAULT_CALLER_CREDIT_USDT,
DEFAULT_DEVNET_TOPUP_USDT,
TrackerServer,
derive_relay_url_from_public_tracker_url,
)
DEFAULT_REGISTRY_DB_PATH = "meshnet_registry.sqlite3"
def _load_env_file(path: Path) -> None:
"""Load simple KEY=VALUE pairs from an env file without overriding env vars."""
if not path.exists():
return
try:
lines = path.read_text().splitlines()
except OSError:
return
for line in lines:
text = line.strip()
if not text or text.startswith("#"):
continue
if text.startswith("export "):
text = text[len("export "):].strip()
if "=" not in text:
continue
key, value = text.split("=", 1)
key = key.strip()
if not key or key in os.environ:
continue
value = value.strip()
if len(value) >= 2 and value[0] == value[-1] and value[0] in {"'", '"'}:
value = value[1:-1]
os.environ[key] = value
def _load_env_defaults() -> None:
"""Load machine-specific, local, and user-level tracker env defaults."""
machine = socket.gethostname().strip()
if machine:
_load_env_file(Path.cwd() / f".env.{machine}")
_load_env_file(Path.cwd() / ".env")
_load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
for path in os.environ.get("PYTHONPATH", "").split(os.pathsep):
if path and path not in sys.path:
sys.path.insert(0, path)
def _routing_config_from_args(args: argparse.Namespace) -> RoutingConfig | None:
"""Build a RoutingConfig from CLI flags; None keeps env-var/server defaults."""
overrides = {
"explore_share": args.route_explore_share,
"weight_alpha": args.route_weight_alpha,
"stats_half_life_seconds": args.route_stats_half_life,
}
set_values = {key: value for key, value in overrides.items() if value is not None}
if not set_values:
return None
return RoutingConfig(**set_values)
def main() -> None:
_load_env_defaults()
common = argparse.ArgumentParser(add_help=False)
common.add_argument("--host", default="0.0.0.0", help="Host interface to listen on")
common.add_argument("--port", type=int, default=8080, help="Port to listen on")
common.add_argument(
"--heartbeat-timeout",
type=float,
default=30.0,
help="Seconds before a node is removed from the registry after missed heartbeat",
)
common.add_argument(
"--cluster-peers",
default="",
help="Comma-separated URLs of peer tracker nodes (enables Raft cluster mode)",
)
common.add_argument(
"--self-url",
default=None,
help="This tracker's own URL as seen by peers (auto-derived from --host/--port if omitted)",
)
common.add_argument(
"--stats-db",
default=None,
metavar="PATH",
help="SQLite database path for persistent model usage statistics",
)
common.add_argument(
"--capability-policy",
choices=list(ALL_CAPABILITY_POLICIES),
default=None,
help=(
"How to treat nodes that present no capability proof (ADR-0023): "
"'compat' (default) still routes pre-capability nodes; 'enforce' routes "
"only nodes whose proof covers the model and shard they advertise. "
"A broken or mismatched proof is never routed under either policy. "
"Falls back to $MESHNET_TRACKER_CAPABILITY_POLICY when omitted."
),
)
common.add_argument(
"--relay-url",
default=None,
help="Public ws(s):// relay URL advertised to nodes, for example wss://ai.neuron.d-popov.com/ws",
)
common.add_argument(
"--embedded-relay",
action="store_true",
help="Run the relay WebSocket server in this tracker process (still uses meshnet_relay.RelayServer)",
)
common.add_argument(
"--relay-host",
default="127.0.0.1",
help="Bind address for --embedded-relay (default: 127.0.0.1; use 0.0.0.0 only when exposing the relay port directly)",
)
common.add_argument(
"--relay-port",
type=int,
default=8765,
help="Bind port for --embedded-relay (default: 8765)",
)
common.add_argument(
"--relay-max-peers",
type=int,
default=500,
help="Maximum WebSocket peers accepted by --embedded-relay",
)
common.add_argument(
"--billing-db",
default=DEFAULT_BILLING_DB_PATH,
metavar="PATH",
help=(
"SQLite database path for the USDT billing ledger "
f"(default: {DEFAULT_BILLING_DB_PATH}; ADR-0015)"
),
)
common.add_argument(
"--no-billing",
action="store_true",
help="Disable the USDT billing ledger",
)
common.add_argument(
"--max-charge-per-request",
type=float,
default=None,
help=(
"Reject chat completion requests whose prompt plus requested completion "
"token bound would cost more than this many USDT"
),
)
common.add_argument(
"--starting-credit",
type=float,
default=DEFAULT_CALLER_CREDIT_USDT,
metavar="USDT",
help=(
"One-time Caller Credit granted when an account creates its first "
f"API key (default: {DEFAULT_CALLER_CREDIT_USDT}; set 0 to require "
"deposits before inference)"
),
)
common.add_argument(
"--devnet-topup",
type=float,
default=DEFAULT_DEVNET_TOPUP_USDT,
metavar="USDT",
help=(
"Dashboard devnet top-up faucet: each click credits this many USDT "
f"to one of the account's keys (default: {DEFAULT_DEVNET_TOPUP_USDT}; "
"MUST be 0 on mainnet deployments)"
),
)
common.add_argument(
"--registry-db",
default=DEFAULT_REGISTRY_DB_PATH,
metavar="PATH",
help=(
"SQLite database path for persisted strike/ban/reputation registry "
f"state (default: {DEFAULT_REGISTRY_DB_PATH})"
),
)
common.add_argument(
"--no-registry-contracts",
action="store_true",
help="Disable the local contract registry used for strike/ban/reputation enforcement",
)
common.add_argument(
"--accounts-db",
default=DEFAULT_ACCOUNTS_DB_PATH,
metavar="PATH",
help=(
"SQLite database path for dashboard user accounts "
f"(default: {DEFAULT_ACCOUNTS_DB_PATH})"
),
)
common.add_argument(
"--no-accounts",
action="store_true",
help="Disable dashboard user accounts (registration/login)",
)
common.add_argument(
"--solana-rpc-url",
default=None,
help="Solana RPC URL (e.g. https://api.devnet.solana.com); enables the on-chain treasury",
)
common.add_argument(
"--usdt-mint",
default=None,
help="SPL mint address of (mock) USDT — see scripts/devnet_setup.py",
)
common.add_argument(
"--treasury-keypair",
default=None,
metavar="PATH",
help="Treasury keypair JSON path (only on settlement-capable trackers)",
)
common.add_argument(
"--settle-period",
type=float,
default=86400.0,
help="Max seconds between payouts to a node (dev: 60, prod: 86400)",
)
common.add_argument(
"--payout-threshold",
type=float,
default=5.0,
help="Pending USDT that triggers an immediate payout (dev: 0)",
)
common.add_argument(
"--payout-dust-floor",
type=float,
default=0.01,
help="Never pay out less than this many USDT",
)
common.add_argument(
"--validator-service-token",
default=None,
help=(
"Service token the validator uses on POST /v1/billing/forfeit "
"(default: MESHNET_VALIDATOR_SERVICE_TOKEN env; ADR-0017)"
),
)
common.add_argument(
"--hive-secret",
default=None,
help=(
"Shared secret authenticating gossip between tracker peers "
"(default: MESHNET_HIVE_SECRET env; required for multi-tracker replication)"
),
)
common.add_argument(
"--toploc-calibration-db",
default=None,
metavar="PATH",
help=(
"SQLite path for the AH-021 honest-noise TOPLOC calibration corpus "
"(enables POST /v1/calibration/toploc/run + GET /v1/calibration/toploc/results)"
),
)
common.add_argument(
"--toploc-reference-node-url",
default=None,
help="Reference node the calibration job teacher-forces claimed tokens against (see validator README)",
)
common.add_argument(
"--toploc-calibration-gate-min-hardware-profiles",
type=int,
default=1,
help=(
"Distinct (GPU model, dtype) profiles the corpus must cover before "
"gate_status.ready is true (alpha exception: fleet size is acceptable)"
),
)
common.add_argument(
"--enable-hf-pricing",
action="store_true",
help=(
"Enable the daily dynamic pricing refresh (issue 23): for presets with a "
"curated hf_aliases list, sets the client price to 80%% of the cheapest "
"matching HuggingFace inference-marketplace rate. Presets without "
"hf_aliases are unaffected and keep their static price."
),
)
common.add_argument(
"--hf-pricing-log-db",
default=None,
metavar="PATH",
help=(
"SQLite database path for the dynamic pricing change log "
f"(default when --enable-hf-pricing is set: {DEFAULT_HF_PRICING_LOG_DB_PATH}; "
"enables GET /v1/pricing/hf/history)"
),
)
common.add_argument(
"--hf-pricing-refresh-interval",
type=float,
default=86400.0,
help="Seconds between dynamic pricing refresh passes (default: daily)",
)
common.add_argument(
"--models-dir",
default=None,
metavar="PATH",
help="Local HuggingFace snapshot root advertised as tracker model-file source (default: MESHNET_MODELS_DIR)",
)
common.add_argument(
"--route-explore-share",
type=float,
default=None,
metavar="FRACTION",
help=(
"Fraction of requests routed down unproven/stale routes to gather "
"throughput statistics (ADR-0021; default 0.3, lower once traffic grows)"
),
)
common.add_argument(
"--route-weight-alpha",
type=float,
default=None,
metavar="ALPHA",
help=(
"Traffic weight exponent among proven routes: share ∝ tps^alpha "
"(default 1.0 — a 1.5x-faster route gets 1.5x the traffic)"
),
)
common.add_argument(
"--route-stats-half-life",
type=float,
default=None,
metavar="SECONDS",
help="Half-life for decaying route throughput observations (default 600)",
)
common.add_argument(
"--log-dir",
default=DEFAULT_LOG_DIR,
metavar="PATH",
help=(
"Directory for rotating tracker logs "
f"(default: {DEFAULT_LOG_DIR}; files: info.log, warning.log, error.log)"
),
)
common.add_argument(
"--log-max-bytes",
type=int,
default=DEFAULT_LOG_MAX_BYTES,
metavar="BYTES",
help=f"Rotate each tracker log file after this many bytes (default: {DEFAULT_LOG_MAX_BYTES})",
)
common.add_argument(
"--log-backup-count",
type=int,
default=DEFAULT_LOG_BACKUP_COUNT,
metavar="N",
help=f"Number of rotated tracker log files to keep per level (default: {DEFAULT_LOG_BACKUP_COUNT})",
)
common.add_argument(
"--enable-test-runner",
action="store_true",
help=(
"Enable the admin-only dashboard test runner API "
"(disabled by default; also honors MESHNET_ENABLE_TEST_RUNNER=1)"
),
)
common.add_argument(
"--no-file-logs",
action="store_true",
help="Disable rotating tracker log files and only write to the terminal",
)
parser = argparse.ArgumentParser(
prog="meshnet-tracker",
description="Distributed Inference Network node registry and route selection",
parents=[common],
)
subparsers = parser.add_subparsers(dest="command")
subparsers.add_parser("start", help="Start the tracker server", parents=[common])
args = parser.parse_args()
if args.enable_test_runner:
os.environ["MESHNET_ENABLE_TEST_RUNNER"] = "1"
if args.command in {None, "start"}:
if not args.no_file_logs:
log_dir = configure_tracker_file_logging(
args.log_dir,
max_bytes=args.log_max_bytes,
backup_count=args.log_backup_count,
)
print(f"meshnet-tracker logs: {log_dir}", flush=True)
cluster_peers = [u.strip() for u in args.cluster_peers.split(",") if u.strip()]
relay_url = args.relay_url or derive_relay_url_from_public_tracker_url(args.self_url)
treasury = None
if args.solana_rpc_url and args.usdt_mint and args.treasury_keypair:
from meshnet_contracts.solana_adapter import SolanaCustodialTreasury
treasury = SolanaCustodialTreasury(
args.solana_rpc_url, args.usdt_mint, args.treasury_keypair,
)
contracts = None
if not args.no_registry_contracts:
from meshnet_contracts import LocalSolanaContracts # type: ignore[import-not-found]
contracts = LocalSolanaContracts(registry_db=args.registry_db)
server = TrackerServer(
host=args.host,
port=args.port,
heartbeat_timeout=args.heartbeat_timeout,
cluster_peers=cluster_peers or None,
cluster_self_url=args.self_url,
stats_db=getattr(args, "stats_db", None),
capability_policy=getattr(args, "capability_policy", None),
relay_url=relay_url,
embedded_relay=args.embedded_relay,
embedded_relay_host=args.relay_host,
embedded_relay_port=args.relay_port,
embedded_relay_max_peers=args.relay_max_peers,
enable_billing=not args.no_billing,
billing_db=None if args.no_billing else args.billing_db,
max_charge_per_request=args.max_charge_per_request,
starting_credit=args.starting_credit,
devnet_topup_amount=args.devnet_topup,
contracts=contracts,
accounts_db=None if args.no_accounts else args.accounts_db,
treasury=treasury,
settle_period=args.settle_period,
payout_threshold=args.payout_threshold,
payout_dust_floor=args.payout_dust_floor,
validator_service_token=args.validator_service_token,
hive_secret=args.hive_secret,
toploc_calibration_db=args.toploc_calibration_db,
toploc_reference_node_url=args.toploc_reference_node_url,
toploc_calibration_gate_min_hardware_profiles=args.toploc_calibration_gate_min_hardware_profiles,
enable_hf_pricing=args.enable_hf_pricing,
hf_pricing_log_db=(
args.hf_pricing_log_db
or (DEFAULT_HF_PRICING_LOG_DB_PATH if args.enable_hf_pricing else None)
),
hf_pricing_refresh_interval=args.hf_pricing_refresh_interval,
models_dir=args.models_dir,
routing_config=_routing_config_from_args(args),
enable_test_runner=args.enable_test_runner,
)
port = server.start()
print(f"meshnet-tracker listening on http://{args.host}:{port}", flush=True)
try:
while True:
time.sleep(1)
except KeyboardInterrupt:
server.stop()
sys.exit(0)
else:
parser.print_help()
if __name__ == "__main__":
main()