This commit is contained in:
Dobromir Popov
2026-07-08 20:00:56 +03:00
28 changed files with 14182 additions and 12368 deletions

View File

@@ -1,13 +1,13 @@
"""meshnet-tracker CLI entry point."""
import argparse
import os
import sys
import time
from pathlib import Path
from .accounts import DEFAULT_ACCOUNTS_DB_PATH
from .billing import DEFAULT_BILLING_DB_PATH
"""meshnet-tracker CLI entry point."""
import argparse
import os
import sys
import time
from pathlib import Path
from .accounts import DEFAULT_ACCOUNTS_DB_PATH
from .billing import DEFAULT_BILLING_DB_PATH
from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH
from .logging_setup import (
DEFAULT_LOG_BACKUP_COUNT,
@@ -15,258 +15,299 @@ from .logging_setup import (
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 local and user-level tracker env defaults before parsing arguments."""
_load_env_file(Path.cwd() / ".env")
_load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
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(
"--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(
"--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)",
)
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 local and user-level tracker env defaults before parsing arguments."""
_load_env_file(Path.cwd() / ".env")
_load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
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(
"--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(
"--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,
@@ -295,18 +336,18 @@ def main() -> None:
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()
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.command in {None, "start"}:
if not args.no_file_logs:
log_dir = configure_tracker_file_logging(
@@ -316,62 +357,63 @@ def main() -> None:
)
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),
relay_url=relay_url,
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,
)
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()
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),
relay_url=relay_url,
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),
)
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()

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,257 @@
"""Learned route statistics for dynamic bandit-style route selection (ADR-0021).
The tracker treats each viable route (ordered chain of node shards covering a
model) as a bandit arm. Observed end-to-end tokens/sec per route is kept as a
time-decayed EWMA. Selection splits traffic between:
- **exploit**: weighted-random among *proven* routes, weight ∝ tps ** alpha
(alpha=1.0 → a 1.5x-faster route gets 1.5x the traffic);
- **scout**: with probability `explore_share`, the least-measured unproven or
stale route is chosen so the tracker keeps learning as the network morphs.
Staleness has two mechanisms:
- continuous: sample mass decays with `stats_half_life_seconds`, so old
observations fade;
- abrupt: every node join/leave bumps the model's *topology epoch*; stats from
an older epoch keep their EWMA as a prior but drop back into the scout pool
until re-measured.
Route signatures embed node ids and shard ranges, so a node re-registering
with a different shard produces a new arm automatically.
"""
from __future__ import annotations
import random
import threading
import time
from dataclasses import dataclass, field
from typing import Any, Iterable
@dataclass(frozen=True)
class RoutingConfig:
explore_share: float = 0.3
weight_alpha: float = 1.0
stats_half_life_seconds: float = 600.0
min_sample_tokens: int = 8
# One fresh sample has mass 1.0 and decays from there; 0.5 keeps a single
# observation "proven" for one half-life before demoting it to the scout pool.
min_proven_weight: float = 0.5
max_candidate_routes: int = 8
prune_after_seconds: float = 86400.0
@dataclass
class RouteStat:
ewma_tps: float = 0.0
weight: float = 0.0 # decayed effective sample mass
last_sample_ts: float = 0.0
epoch: int = 0
samples: int = 0 # lifetime raw sample count (display only)
def decayed_weight(self, now: float, half_life: float) -> float:
if self.weight <= 0.0:
return 0.0
age = max(0.0, now - self.last_sample_ts)
return self.weight * 0.5 ** (age / half_life)
@dataclass
class RouteCandidate:
nodes: list[Any]
signature: str
prior_tps: float = 0.0
def route_signature(model_key: str, nodes: Iterable[Any]) -> str:
hops = "->".join(
f"{getattr(n, 'node_id', '?')}[{getattr(n, 'shard_start', '?')}-{getattr(n, 'shard_end', '?')}]"
for n in nodes
)
return f"{model_key}|{hops}"
class RouteStatsStore:
"""Thread-safe per-route decayed throughput statistics."""
def __init__(self, config: RoutingConfig | None = None) -> None:
self.config = config or RoutingConfig()
self._lock = threading.Lock()
self._stats: dict[str, RouteStat] = {}
self._epochs: dict[str, int] = {}
def epoch(self, model_key: str) -> int:
with self._lock:
return self._epochs.get(model_key, 0)
def bump_epoch(self, model_keys: Iterable[str | None]) -> None:
"""Mark the topology changed for the given model keys (node join/leave)."""
with self._lock:
for key in model_keys:
if key:
self._epochs[key] = self._epochs.get(key, 0) + 1
def record_sample(
self,
model_key: str,
signature: str,
tokens: int,
elapsed_seconds: float,
now: float | None = None,
) -> bool:
"""Fold one completed request into the route's EWMA.
Returns False (and records nothing) for samples below
`min_sample_tokens` — near-empty completions come from broken routes
and would poison the arm with meaningless throughput values.
"""
cfg = self.config
if tokens < cfg.min_sample_tokens or elapsed_seconds <= 0.0:
return False
tps = tokens / elapsed_seconds
ts = time.time() if now is None else now
with self._lock:
stat = self._stats.get(signature)
if stat is None:
stat = RouteStat()
self._stats[signature] = stat
carried = stat.decayed_weight(ts, cfg.stats_half_life_seconds)
total = carried + 1.0
stat.ewma_tps = (stat.ewma_tps * carried + tps) / total
stat.weight = total
stat.last_sample_ts = ts
stat.epoch = self._epochs.get(model_key, 0)
stat.samples += 1
return True
def snapshot(self, signature: str, model_key: str, now: float | None = None) -> dict:
"""Point-in-time view of one route's learned state."""
ts = time.time() if now is None else now
cfg = self.config
with self._lock:
stat = self._stats.get(signature)
current_epoch = self._epochs.get(model_key, 0)
if stat is None:
return {"tps": None, "weight": 0.0, "samples": 0, "status": "unsampled"}
weight = stat.decayed_weight(ts, cfg.stats_half_life_seconds)
if stat.epoch != current_epoch:
status = "stale"
elif weight < cfg.min_proven_weight:
status = "decayed" if stat.samples else "unsampled"
else:
status = "proven"
return {
"tps": round(stat.ewma_tps, 4) if stat.samples else None,
"weight": round(weight, 4),
"samples": stat.samples,
"status": status,
}
def prune(self, now: float | None = None) -> int:
"""Drop routes with no samples for `prune_after_seconds`."""
ts = time.time() if now is None else now
cutoff = ts - self.config.prune_after_seconds
with self._lock:
dead = [sig for sig, stat in self._stats.items() if stat.last_sample_ts < cutoff]
for sig in dead:
del self._stats[sig]
return len(dead)
def choose_route(
candidates: list[RouteCandidate],
store: RouteStatsStore,
model_key: str,
rng: random.Random | None = None,
now: float | None = None,
) -> tuple[RouteCandidate | None, dict]:
"""Pick a route: ε-scout among unproven arms, else weighted ∝ tps**alpha.
Returns (candidate, decision) where decision explains the pick for logs
and diagnostics: {"mode": "scout"|"exploit"|"prior", ...}.
"""
if not candidates:
return None, {"mode": "none"}
rng = rng or random
cfg = store.config
proven: list[tuple[RouteCandidate, float]] = []
scouts: list[tuple[RouteCandidate, float]] = []
for cand in candidates:
snap = store.snapshot(cand.signature, model_key, now=now)
if snap["status"] == "proven":
proven.append((cand, max(float(snap["tps"] or 0.0), 1e-6)))
else:
scouts.append((cand, float(snap["weight"])))
if scouts and (not proven or rng.random() < cfg.explore_share):
# Least-measured first so new/stale arms accumulate samples fastest;
# tiebreak on prior estimate so plausible routes get scouted first.
scouts.sort(key=lambda item: (item[1], -item[0].prior_tps))
pick = scouts[0][0]
return pick, {"mode": "scout", "signature": pick.signature}
if proven:
weights = [tps ** cfg.weight_alpha for _, tps in proven]
pick = rng.choices([cand for cand, _ in proven], weights=weights, k=1)[0]
return pick, {
"mode": "exploit",
"signature": pick.signature,
"candidates": len(proven),
}
# No stats anywhere yet — fall back to the prior (benchmark-derived) estimate.
weights = [max(cand.prior_tps, 1e-6) ** cfg.weight_alpha for cand in candidates]
pick = rng.choices(candidates, weights=weights, k=1)[0]
return pick, {"mode": "prior", "signature": pick.signature}
def route_table(
candidates: list[RouteCandidate],
store: RouteStatsStore,
model_key: str,
now: float | None = None,
) -> list[dict]:
"""Diagnostics rows: learned tps, coefficient vs best, expected traffic share."""
cfg = store.config
rows = []
for cand in candidates:
snap = store.snapshot(cand.signature, model_key, now=now)
rows.append({"candidate": cand, **snap})
proven = [r for r in rows if r["status"] == "proven"]
scouts = [r for r in rows if r["status"] != "proven"]
best_tps = max((float(r["tps"]) for r in proven), default=0.0)
exploit_budget = 1.0 - (cfg.explore_share if scouts and proven else 0.0)
if not proven:
exploit_budget = 0.0
weight_sum = sum(float(r["tps"]) ** cfg.weight_alpha for r in proven) or 1.0
out = []
for r in rows:
cand: RouteCandidate = r["candidate"]
if r["status"] == "proven":
share = exploit_budget * (float(r["tps"]) ** cfg.weight_alpha) / weight_sum
coefficient = round(float(r["tps"]) / best_tps, 3) if best_tps else None
else:
share = (
(cfg.explore_share if proven else 1.0) / len(scouts)
if scouts
else 0.0
)
coefficient = None
out.append({
"signature": cand.signature,
"hops": [
{
"node_id": getattr(n, "node_id", "?"),
"shard": f"{getattr(n, 'shard_start', '?')}-{getattr(n, 'shard_end', '?')}",
"endpoint": getattr(n, "endpoint", "?"),
}
for n in cand.nodes
],
"tps": r["tps"],
"coefficient": coefficient,
"expected_share": round(share, 4),
"samples": r["samples"],
"weight": r["weight"],
"status": r["status"],
"prior_tps": round(cand.prior_tps, 4),
})
out.sort(key=lambda r: (-(r["tps"] or 0.0), -r["prior_tps"]))
return out

File diff suppressed because it is too large Load Diff