Files
neuron-tai/packages/node/meshnet_node/cli.py
2026-07-13 21:58:08 +02:00

548 lines
23 KiB
Python

"""meshnet-node CLI entry point — mining-style UX."""
from __future__ import annotations
import argparse
import os
import socket
import sys
import time
from pathlib import Path
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 _apply_relay_concurrency_flag(value: int | None) -> None:
"""Expose relay bridge worker cap via CLI (env MESHNET_RELAY_CONCURRENCY)."""
if value is not None:
os.environ["MESHNET_RELAY_CONCURRENCY"] = str(max(1, value))
def _load_env_defaults() -> None:
"""Load machine-specific, local, and user-level node 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 _run_node(cfg: dict) -> None:
"""Start the node and hand off to the live dashboard. Blocks until Ctrl-C."""
from .startup import run_startup
from .dashboard import run_dashboard
start_time = time.monotonic()
try:
node = run_startup(
tracker_url=cfg["tracker_url"],
port=cfg.get("port", 7000),
model=cfg.get("model_name") or None,
model_id=cfg.get("model_hf_repo") or None,
shard_start=cfg.get("shard_start"),
shard_end=cfg.get("shard_end"),
quantization=cfg.get("quantization", "auto").replace("bf16", "bfloat16"),
wallet_path=Path(cfg["wallet_path"]) if cfg.get("wallet_path") else None,
cache_dir=Path(cfg["download_dir"]) if cfg.get("download_dir") else None,
host=cfg.get("host", "0.0.0.0"),
advertise_host=cfg.get("advertise_host"),
route_timeout=float(cfg.get("route_timeout", 30.0)),
vram_mb_override=cfg.get("vram_mb_override"),
max_loaded_shards=int(cfg.get("max_loaded_shards", 1)),
debug=bool(cfg.get("debug", False)),
tracker_source_disabled=bool(cfg.get("tracker_source_disabled", False)),
torch_threads=cfg.get("torch_threads"),
torch_interop_threads=cfg.get("torch_interop_threads"),
node_name=cfg.get("node_name"),
force_cpu=bool(cfg.get("force_cpu", False)),
)
except Exception as exc:
print(f"\nERROR: {exc}", file=sys.stderr, flush=True)
sys.exit(1)
try:
run_dashboard(node, cfg, start_time)
except KeyboardInterrupt:
pass
finally:
node.stop()
req = getattr(node, "chat_completion_count", 0)
elapsed = time.monotonic() - start_time
h, rem = divmod(int(elapsed), 3600)
m, s = divmod(rem, 60)
print(
f"\nmeshnet-node stopped. "
f"Served {req} requests in {h:02d}:{m:02d}:{s:02d}.",
flush=True,
)
def _resolve_model_flags(
model: str | None,
model_id: str | None,
) -> tuple[str | None, str | None]:
"""Return (model_name, hf_repo_or_none) from --model / --model-id flags."""
explicit = model_id or model
if not explicit:
return None, None
from .model_catalog import resolve_model_alias
preset = resolve_model_alias(explicit)
if preset is not None:
return preset.name, preset.hf_repo
if "/" in explicit:
return explicit.split("/")[-1], explicit
return explicit, None
def _first_available_port(host: str, start: int = 7000, attempts: int = 100) -> int:
"""Return the first TCP port bindable on host, starting at start."""
bind_host = "" if host == "0.0.0.0" else host
for port in range(start, start + attempts):
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
try:
sock.bind((bind_host, port))
except OSError:
continue
return port
raise OSError(f"no available TCP port in range {start}-{start + attempts - 1}")
def _cmd_default(args) -> int:
"""No subcommand: wizard if no config, else start with saved config."""
from .config import load_config, save_config, merge_cli_overrides
from .wizard import run_wizard
cfg = load_config()
if cfg is None or args.reset_config:
if args.reset_config and cfg is not None:
print("Resetting config — re-running setup wizard.\n")
try:
cfg = run_wizard()
except KeyboardInterrupt:
print("\nSetup cancelled.")
return 1
save_config(cfg)
print(f"\nConfig saved to ~/.config/meshnet/config.json\n")
# Apply CLI overrides on top of saved config
overrides: dict = {}
model_name, hf_repo = _resolve_model_flags(args.model, getattr(args, "model_id", None))
if model_name is not None:
overrides["model_name"] = model_name
overrides["model_hf_repo"] = hf_repo or ""
if args.quantization:
overrides["quantization"] = args.quantization
if args.download_dir:
overrides["download_dir"] = args.download_dir
if args.tracker:
overrides["tracker_url"] = args.tracker
if args.wallet:
overrides["wallet_path"] = args.wallet
if args.shard_start is not None:
overrides["shard_start"] = args.shard_start
if args.shard_end is not None:
overrides["shard_end"] = args.shard_end
if args.port is not None:
overrides["port"] = args.port
if args.host:
overrides["host"] = args.host
if args.advertise_host:
overrides["advertise_host"] = args.advertise_host
if getattr(args, "node_name", None):
overrides["node_name"] = args.node_name
if args.route_timeout != 30.0:
overrides["route_timeout"] = args.route_timeout
if getattr(args, "memory", None) is not None:
overrides["vram_mb_override"] = args.memory
if getattr(args, "max_shards", None) is not None:
overrides["max_loaded_shards"] = args.max_shards
if args.debug:
overrides["debug"] = True
if getattr(args, "tracker_source_disabled", False):
overrides["tracker_source_disabled"] = True
if getattr(args, "torch_threads", None) is not None:
overrides["torch_threads"] = args.torch_threads
if getattr(args, "torch_interop_threads", None) is not None:
overrides["torch_interop_threads"] = args.torch_interop_threads
if getattr(args, "cpu", False):
overrides["force_cpu"] = True
_apply_relay_concurrency_flag(getattr(args, "relay_concurrency", None))
if overrides:
cfg = merge_cli_overrides(cfg, **overrides)
_run_node(cfg)
return 0
def _cmd_models(args) -> int:
"""List curated models (with optional HF Hub browse)."""
from .wizard import print_models_table, _browse_hf_interactive
if args.browse:
from .model_catalog import browse_hf_hub
print("Fetching HuggingFace Hub top models...\n")
try:
models = browse_hf_hub(top_n=20)
print(f"{'#':<4} {'Repo':<60} {'Downloads':>12}")
print(f"{''*4} {''*60} {''*12}")
for i, m in enumerate(models, 1):
dl = m["downloads"]
dl_str = (
f"{dl/1e6:.1f}M" if dl >= 1_000_000
else f"{dl/1e3:.0f}k" if dl >= 1000
else str(dl)
)
print(f"{i:<4} {m['repo']:<60} {dl_str:>12}")
except RuntimeError as exc:
print(f"Error: {exc}", file=sys.stderr)
return 1
else:
print_models_table()
return 0
def _cmd_config(args) -> int:
"""Print current config."""
import json
from .config import load_config, config_path
cfg = load_config()
if cfg is None:
print("No config file found. Run `meshnet-node` to start setup.")
return 1
print(f"Config: {config_path()}")
print(json.dumps(cfg, indent=2))
return 0
def _doctor_overrides(args) -> dict:
"""CLI flags that change *what* doctor validates, applied on top of config."""
overrides: dict = {}
model_name, hf_repo = _resolve_model_flags(
getattr(args, "model", None), getattr(args, "model_id", None)
)
if model_name is not None:
overrides["model_name"] = model_name
overrides["model_hf_repo"] = hf_repo or ""
for flag, key in (
("quantization", "quantization"),
("download_dir", "download_dir"),
("shard_start", "shard_start"),
("shard_end", "shard_end"),
):
value = getattr(args, flag, None)
if value is not None:
overrides[key] = value
if getattr(args, "cpu", False):
overrides["force_cpu"] = True
return overrides
def _cmd_doctor(args) -> int:
"""Validate the selected model/shard with a bounded real forward."""
import json
import traceback
from .config import DEFAULTS, load_config, merge_cli_overrides
from .doctor import (
DoctorError,
default_report_path,
render_result,
resolve_selection,
run_doctor,
write_reports,
)
debug = bool(getattr(args, "debug", False))
cfg = load_config() or dict(DEFAULTS)
overrides = _doctor_overrides(args)
if overrides:
cfg = merge_cli_overrides(cfg, **overrides)
try:
selection = resolve_selection(cfg)
result = run_doctor(
selection,
recipe_id=args.recipe,
all_recipes=args.all_recipes,
)
except DoctorError as exc:
# Bad input (no model, unknown recipe): there is nothing to report on.
if debug:
traceback.print_exc()
print(f"ERROR: {exc}", file=sys.stderr, flush=True)
if exc.hint:
print(f" {exc.hint}", file=sys.stderr, flush=True)
return 1
written = write_reports(
result.reports,
Path(args.report) if args.report else default_report_path(),
)
if args.json:
print(json.dumps([r.to_dict() for r in result.reports], indent=2, sort_keys=True))
else:
print(render_result(result, report_path=written))
if debug:
for item in result.results:
if item.error is not None:
traceback.print_exception(
type(item.error), item.error, item.error.__traceback__
)
return result.exit_code
def _cmd_start(args) -> int:
"""Legacy `start` subcommand — preserves backward compatibility with existing tests."""
from .config import DEFAULTS
# Build a transient config from flags (don't write to disk)
cfg = dict(DEFAULTS)
if args.tracker:
cfg["tracker_url"] = args.tracker
cfg["port"] = args.port if args.port is not None else _first_available_port(args.host)
if args.no_model:
cfg["model_name"] = ""
cfg["model_hf_repo"] = ""
else:
model_name, hf_repo = _resolve_model_flags(
args.model or cfg.get("model_hf_repo") or cfg.get("model_name") or None,
args.model_id,
)
if model_name is not None:
cfg["model_name"] = model_name
cfg["model_hf_repo"] = hf_repo or ""
cfg["quantization"] = args.quantization
cfg["host"] = args.host
if args.shard_start is not None:
cfg["shard_start"] = args.shard_start
if args.shard_end is not None:
cfg["shard_end"] = args.shard_end
if args.wallet:
cfg["wallet_path"] = args.wallet
if args.download_dir:
cfg["download_dir"] = args.download_dir
if getattr(args, "node_name", None):
cfg["node_name"] = args.node_name
_apply_relay_concurrency_flag(getattr(args, "relay_concurrency", None))
# Legacy start: just run without the dashboard (keep original blocking loop)
from .startup import run_startup
try:
node = run_startup(
tracker_url=cfg["tracker_url"],
port=cfg["port"],
model=cfg["model_name"],
model_id=cfg.get("model_hf_repo") or None,
shard_start=cfg.get("shard_start"),
shard_end=cfg.get("shard_end"),
quantization=cfg["quantization"].replace("bf16", "bfloat16"),
wallet_path=Path(cfg["wallet_path"]) if cfg.get("wallet_path") else None,
cache_dir=Path(cfg["download_dir"]) if cfg.get("download_dir") else None,
host=cfg["host"],
advertise_host=getattr(args, "advertise_host", None),
route_timeout=getattr(args, "route_timeout", 30.0),
vram_mb_override=getattr(args, "memory", None),
max_loaded_shards=getattr(args, "max_shards", 1),
debug=getattr(args, "debug", False),
tracker_source_disabled=getattr(args, "tracker_source_disabled", False),
torch_threads=getattr(args, "torch_threads", None),
torch_interop_threads=getattr(args, "torch_interop_threads", None),
node_name=cfg.get("node_name"),
force_cpu=getattr(args, "cpu", False),
)
except Exception as exc:
print(f"ERROR: {exc}", file=sys.stderr, flush=True)
sys.exit(1)
try:
while True:
time.sleep(1)
except KeyboardInterrupt:
node.stop()
return 0
def main() -> None:
_load_env_defaults()
parser = argparse.ArgumentParser(
prog="meshnet-node",
description="Distributed AI Inference — Node Client",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog=(
"Run with no arguments to start the setup wizard.\n"
"After first setup, `meshnet-node` starts using your saved config.\n\n"
"Subcommands:\n"
" models List supported models\n"
" models --browse Browse HuggingFace Hub\n"
" config Show current config\n"
" doctor Check this node can really run its selected shard\n"
),
)
# Flags that apply to the no-subcommand (default) path
parser.add_argument("--model", metavar="MODEL", help="Model name or HuggingFace repo ID to serve")
parser.add_argument("--model-id", metavar="MODEL", help="Alias for --model (catalog name or HuggingFace repo)")
parser.add_argument("--quantization", "-q", choices=["bf16", "int8", "nf4", "bfloat16"],
help="Quantization level")
parser.add_argument("--download-dir", metavar="PATH", help="Model download directory")
parser.add_argument("--tracker", metavar="URL", help="Tracker URL")
parser.add_argument("--tracker-source-disabled", action="store_true",
help="Skip tracker/peer model-file sources and download from HuggingFace directly")
parser.add_argument("--wallet", metavar="PATH", help="Wallet file path")
parser.add_argument("--shard-start", type=int, metavar="N", help="Pin shard start layer")
parser.add_argument("--shard-end", type=int, metavar="N", help="Pin shard end layer")
parser.add_argument("--port", type=int, metavar="N", help="Port to listen on")
parser.add_argument("--host", metavar="ADDR", help="Interface to bind (default 0.0.0.0)")
parser.add_argument("--advertise-host", metavar="ADDR", help="Host/IP advertised to the tracker")
parser.add_argument("--node-name", metavar="NAME", help="Friendly display name shown on the tracker dashboard")
parser.add_argument("--route-timeout", type=float, metavar="SEC", default=30.0,
help="Seconds to wait for tracker route lookup (default 30)")
parser.add_argument("--memory", type=int, metavar="MB", default=None,
help="Override autodetected VRAM/RAM budget in MB used for shard assignment")
parser.add_argument("--max-shards", type=int, metavar="N", default=None,
help="Maximum shard slots this node advertises to the tracker (default 1)")
parser.add_argument("--torch-threads", type=int, metavar="N",
help="Set PyTorch intra-op CPU worker threads")
parser.add_argument("--torch-interop-threads", type=int, metavar="N",
help="Set PyTorch inter-op CPU worker threads")
parser.add_argument("--cpu", action="store_true",
help="Force CPU inference even when a GPU is available")
parser.add_argument("--relay-concurrency", type=int, metavar="N",
help="Max concurrent relay-http-request workers (env MESHNET_RELAY_CONCURRENCY)")
parser.add_argument("--debug", action="store_true", help="Enable verbose node debug logging")
parser.add_argument("--no-tui", action="store_true", help="Plain-text output (no rich dashboard)")
parser.add_argument("--compact", action="store_true", help="Single-line status output")
parser.add_argument("--reset-config", action="store_true", help="Re-run wizard even if config exists")
subparsers = parser.add_subparsers(dest="command")
# models subcommand
models_cmd = subparsers.add_parser("models", help="List supported models")
models_cmd.add_argument("--browse", action="store_true", help="Browse HuggingFace Hub top-20")
# config subcommand
subparsers.add_parser("config", help="Show current saved config")
# doctor subcommand — validate the selected shard with a real forward
doctor_cmd = subparsers.add_parser(
"doctor",
help="Check this node can really run its selected model shard",
)
# These mirror the top-level selection flags. argparse.SUPPRESS keeps an
# unpassed subcommand flag from overwriting the top-level one, so both
# `meshnet-node --model X doctor` and `meshnet-node doctor --model X` work.
doctor_cmd.add_argument("--model", metavar="MODEL", default=argparse.SUPPRESS,
help="Model name or HuggingFace repo ID to validate")
doctor_cmd.add_argument("--model-id", metavar="MODEL", default=argparse.SUPPRESS,
help="Alias for --model")
doctor_cmd.add_argument("--quantization", "-q", default=argparse.SUPPRESS,
choices=["bf16", "int8", "nf4", "bfloat16", "auto"],
help="Quantization level to validate")
doctor_cmd.add_argument("--download-dir", metavar="PATH", default=argparse.SUPPRESS,
help="Model download directory")
doctor_cmd.add_argument("--shard-start", type=int, metavar="N", default=argparse.SUPPRESS,
help="Pin shard start layer")
doctor_cmd.add_argument("--shard-end", type=int, metavar="N", default=argparse.SUPPRESS,
help="Pin shard end layer")
doctor_cmd.add_argument("--cpu", action="store_true", default=argparse.SUPPRESS,
help="Validate CPU execution even when a GPU is available")
doctor_cmd.add_argument("--debug", action="store_true", default=argparse.SUPPRESS,
help="Print the full traceback behind a failure")
doctor_cmd.add_argument("--recipe", metavar="ID", default=None,
help="Recipe to validate (default: baseline)")
doctor_cmd.add_argument("--all-recipes", action="store_true",
help="Validate every recipe in the catalogue, not just the selected one")
doctor_cmd.add_argument("--report", metavar="PATH", default=None,
help="Where to write the capability report JSON")
doctor_cmd.add_argument("--json", action="store_true",
help="Print the capability report JSON instead of a summary")
# start subcommand (legacy / backward-compat)
start_cmd = subparsers.add_parser("start", help="Start node (legacy flags)")
start_cmd.add_argument("--tracker")
start_cmd.add_argument("--port", type=int)
start_cmd.add_argument("--model", help="Model name or HuggingFace repo ID")
start_cmd.add_argument("--no-model", action="store_true", help="Start a registry-only node without loading a model")
start_cmd.add_argument("--model-id", help="Alias for --model (catalog name or HuggingFace repo)")
start_cmd.add_argument("--shard-start", type=int)
start_cmd.add_argument("--shard-end", type=int)
start_cmd.add_argument("--quantization", choices=["auto", "bfloat16", "int8", "nf4", "bf16"], default="auto")
start_cmd.add_argument("--host", default="0.0.0.0")
start_cmd.add_argument("--advertise-host")
start_cmd.add_argument("--node-name", help="Friendly display name shown on the tracker dashboard")
start_cmd.add_argument("--tracker-mode", action="store_true")
start_cmd.add_argument("--tracker-url", default=None)
start_cmd.add_argument("--wallet")
start_cmd.add_argument("--download-dir")
start_cmd.add_argument("--route-timeout", type=float, default=30.0,
help="Seconds to wait for tracker route lookup (default 30)")
start_cmd.add_argument("--memory", type=int, default=None, metavar="MB",
help="Override autodetected VRAM/RAM budget in MB used for shard assignment")
start_cmd.add_argument("--max-shards", type=int, default=1, metavar="N",
help="Maximum shard slots this node advertises to the tracker (default 1)")
start_cmd.add_argument("--torch-threads", type=int, metavar="N",
help="Set PyTorch intra-op CPU worker threads")
start_cmd.add_argument("--torch-interop-threads", type=int, metavar="N",
help="Set PyTorch inter-op CPU worker threads")
start_cmd.add_argument("--cpu", action="store_true",
help="Force CPU inference even when a GPU is available")
start_cmd.add_argument("--relay-concurrency", type=int, metavar="N",
help="Max concurrent relay-http-request workers (env MESHNET_RELAY_CONCURRENCY)")
start_cmd.add_argument("--debug", action="store_true", help="Enable verbose node debug logging")
start_cmd.add_argument("--tracker-source-disabled", action="store_true",
help="Skip tracker/peer model-file sources and download from HuggingFace directly")
args = parser.parse_args()
if args.command == "models":
sys.exit(_cmd_models(args))
elif args.command == "config":
sys.exit(_cmd_config(args))
elif args.command == "doctor":
sys.exit(_cmd_doctor(args))
elif args.command == "start":
sys.exit(_cmd_start(args))
else:
# Default: wizard or start with saved config
sys.exit(_cmd_default(args))
if __name__ == "__main__":
main()