popov/neuron-tai
1
0
Fork 0
Code Issues 42 Pull Requests Actions Packages Projects Releases Wiki Activity

fix: finish master branch integration compatibility

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-17 14:35:05 +03:00
parent f0197bfa83
commit b7d40c5bcf
3 changed files with 252 additions and 195 deletions
Download Patch File Download Diff File Expand all files Collapse all files

364
packages/tracker/meshnet_tracker/server.py
View File

@@ -45,7 +45,7 @@ import urllib.parse
import urllib.request
import uuid
from collections import deque
from dataclasses import dataclass, field
from dataclasses import dataclass, field, replace
from importlib.resources import files
from pathlib import Path
from typing import Any
@@ -53,13 +53,10 @@ from typing import Any
from .accounts import DEFAULT_ACCOUNTS_DB_PATH, AccountStore
from .auth import is_validator_token, sign_hive_request, verify_hive_request
from .capability import (
DEFAULT_POLICY as DEFAULT_CAPABILITY_POLICY,
POLICY_COMPAT,
POLICY_ENFORCE,
STATE_ABSENT,
STATE_ADMITTED,
STATE_MODEL_MISMATCH,
STATE_SHARD_MISMATCH,
STATE_UNCERTIFIED,
CapabilityState,
absent_state,
evaluate_report,
@@ -68,7 +65,7 @@ from .capability import (
)
from .wallet_proof import binding_message, verify_wallet_signature
from .billing import DEFAULT_BILLING_DB_PATH, BillingLedger
from .calibration import DEFAULT_CALIBRATION_DB_PATH, ToplocCalibrationStore
from .calibration import ToplocCalibrationStore
from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH, HfPricingLog, refresh_preset_price
from .gossip import NodeGossip
from .logging_setup import tracker_logger
@@ -84,9 +81,16 @@ from .routing_stats import (
)
from .model_files import files_for_layer_range, snapshot_dir_for_repo
from .raft import RaftNode
from .recipe import (
CertificationLedger,
DistributedForwardEvidence,
PresentedIdentity,
RecipeIdentityError,
RecipeStatus,
)
_CONSOLE_LIMIT = 1000
_CONSOLE_LIMIT = 300
_PROXY_PROGRESS_LOG_INTERVAL = 5.0
_SESSION_COOKIE_NAME = "meshnet_session"
@@ -792,6 +796,7 @@ def _capability_from_registration(
hf_repo: str | None,
shard_start: int | None,
shard_end: int | None,
recipe_certifications: CertificationLedger,
) -> CapabilityState:
"""The tracker's verdict on the proof carried by one registration payload.
@@ -811,6 +816,7 @@ def _capability_from_registration(
declared_recipe_version=(
recipe_version if isinstance(recipe_version, str) else None
),
ledger=recipe_certifications,
)
@@ -830,6 +836,11 @@ def _admitted_nodes(nodes: list["_NodeEntry"], policy: str | None) -> list["_Nod
return [node for node in nodes if _capability_routable(node, effective)]
def _route_identity_partition(node: "_NodeEntry") -> tuple[str, ...]:
fingerprint = _node_admission(node).fingerprint
return ("legacy",) if fingerprint is None else ("exact", *fingerprint)
def _select_route(
nodes: list[_NodeEntry],
required_start: int,
@@ -853,29 +864,51 @@ def _select_route(
],
key=lambda n: (n.shard_start, -n.shard_end), # type: ignore[operator]
)
route: list[_NodeEntry] = []
covered_up_to = required_start - 1
def _routing_score(node: "_NodeEntry") -> float:
return _effective_throughput(node, model) * _reputation_multiplier(node, contracts)
while covered_up_to < required_end:
best: _NodeEntry | None = None
for node in candidates:
if node.shard_start <= covered_up_to + 1 and node.shard_end > covered_up_to:
if best is None:
best = node
elif node.shard_end > best.shard_end:
best = node
elif node.shard_end == best.shard_end and _routing_score(node) > _routing_score(best):
best = node
if best is None:
missing = covered_up_to + 1
return [], f"no route available: no registered node covers layer {missing}"
route.append(best)
covered_up_to = best.shard_end
candidates = [n for n in candidates if n is not best]
partitions: dict[tuple[str, ...], list[_NodeEntry]] = {}
for node in candidates:
partitions.setdefault(_route_identity_partition(node), []).append(node)
complete: list[list[_NodeEntry]] = []
furthest = required_start - 1
for partition in partitions.values():
pool = list(partition)
route: list[_NodeEntry] = []
covered_up_to = required_start - 1
while covered_up_to < required_end:
best: _NodeEntry | None = None
for node in pool:
if node.shard_start <= covered_up_to + 1 and node.shard_end > covered_up_to:
if best is None:
best = node
elif node.shard_end > best.shard_end:
best = node
elif (
node.shard_end == best.shard_end
and _routing_score(node) > _routing_score(best)
):
best = node
if best is None:
break
route.append(best)
covered_up_to = best.shard_end
pool = [node for node in pool if node is not best]
furthest = max(furthest, covered_up_to)
if covered_up_to >= required_end:
complete.append(route)
if not complete:
return [], f"no route available: no registered node covers layer {furthest + 1}"
route = max(
complete,
key=lambda candidate: (
min(_routing_score(node) for node in candidate),
-len(candidate),
),
)
return route, ""
@@ -911,7 +944,12 @@ def _enumerate_routes(
for head in heads:
route = [head]
covered_up_to = head.shard_end
pool = [n for n in sharded if n is not head]
head_partition = _route_identity_partition(head)
pool = [
node
for node in sharded
if node is not head and _route_identity_partition(node) == head_partition
]
while covered_up_to < required_end:
best = None
for n in pool:
@@ -1101,15 +1139,19 @@ def _registration_quantization(body: dict, quantizations: list[str]) -> str | No
An absent field predates the protocol adding it: it means "unknown", not
"unsupported", so the node keeps the best precision it advertises and stays
routable. An explicit "auto" means the same thing — the node's CLI default
delegates the choice, it does not refuse one. Anything else the node states
explicitly is taken at its word -- a null, a non-string, or an unsupported
name leaves it with no usable precision and routing excludes it.
routable. Anything the node states explicitly is taken at its word -- a null,
a non-string, or an unsupported name leaves it with no usable precision and
routing excludes it.
"""
declared = body.get("quantization")
declared_auto = isinstance(declared, str) and declared.strip().lower() == "auto"
if "quantization" in body and not declared_auto:
return _normalize_quantization(declared)
if "quantization" in body:
raw = body["quantization"]
if isinstance(raw, str) and raw.strip().lower() == "auto":
supported = [
normalized for value in quantizations
if (normalized := _normalize_quantization(value)) is not None
]
return max(supported, key=lambda value: _QUANTIZATION_QUALITY[value]) if supported else None
return _normalize_quantization(raw)
supported = [
normalized for value in quantizations
if (normalized := _normalize_quantization(value)) is not None
@@ -1228,7 +1270,6 @@ def _node_capacity_summary(node: _NodeEntry, preset: dict | None = None) -> dict
"quantization": node.quantization,
"benchmark_tokens_per_sec": node.benchmark_tokens_per_sec,
"effective_throughput": round(_effective_throughput(node), 4),
"loaded_model_bytes": _assignment_memory_bytes(node, preset),
}
if preset is not None:
summary["max_assignable_layers"] = _node_layer_capacity(node, preset)
@@ -1536,39 +1577,6 @@ def _request_model_load_locked(
return None
def _force_model_load_locked(
server: "_TrackerHTTPServer", model_key: str, node_id: str | None = None,
) -> dict | None:
"""Replace the fastest ready assignment after an explicit admin eviction."""
resolved_name, preset = _resolve_model_preset(server.model_presets, model_key)
if preset is None or not preset.get("hf_repo"):
return None
start, end = _preset_layer_bounds(preset)
# An explicit admin eviction is permitted to recover a stuck/loading node
# and to use the preset default precision. It must only avoid a node that
# already has another assignment in flight.
candidates = [
node for node in server.registry.values()
if node.pending_new_assignment is None
and (node_id is None or node.node_id == node_id)
]
if not candidates:
return None
node = max(candidates, key=lambda item: item.benchmark_tokens_per_sec)
shard_end = min(end, start + max(1, min(_node_layer_capacity(node, preset), end - start + 1)) - 1)
quantization = _node_quantization(node, preset)
directive = _load_directive(node, str(preset["hf_repo"]), start, shard_end, quantization)
replaced = node.hf_repo or node.model
node.model, node.hf_repo = resolved_name, str(preset["hf_repo"])
node.shard_start, node.shard_end, node.quantization = start, shard_end, quantization
node.managed_assignment, node.pending_new_assignment = True, directive
node.pending_directives.append(directive)
_tracker_log(server, "warn", "model load forced", node_id=node.node_id,
model=resolved_name, replaced_model=replaced, shard=f"{start}-{shard_end}")
return {"node_id": node.node_id, "model": resolved_name, "hf_repo": preset["hf_repo"],
"shard_start": start, "shard_end": shard_end, "replaced_model": replaced}
def _release_model_locked(
server: "_TrackerHTTPServer", model_key: str, node_id: str | None = None,
) -> int:
@@ -2126,14 +2134,24 @@ def _find_pinned_route(
hop_count: int,
) -> list[_NodeEntry] | None:
"""First combination of exactly ``hop_count`` distinct nodes covering the
layer range, where every node extends coverage (US-030 benchmark routes)."""
layer range, where every node extends coverage (US-030 benchmark routes).
Benchmark combos run real inference, so they obey the same DGR-003 rule as
every other route builder: one route, one exact identity. A combo that mixed
two fingerprints — or an exact Shard with a legacy one — would measure a
numerically incoherent route and record the garbage as a benchmark.
"""
for combo in itertools.permutations(nodes, hop_count):
covered = required_start - 1
valid = True
partition = _route_identity_partition(combo[0])
for candidate in combo:
if candidate.shard_start is None or candidate.shard_end is None:
valid = False
break
if _route_identity_partition(candidate) != partition:
valid = False
break
if candidate.shard_start > covered + 1 or candidate.shard_end <= covered:
valid = False
break
@@ -2584,8 +2602,8 @@ def _estimate_prompt_tokens(body: dict) -> int | None:
def _requested_completion_token_limit(body: dict) -> int | None:
for field in ("max_completion_tokens", "max_tokens"):
value = body.get(field)
for key in ("max_completion_tokens", "max_tokens"):
value = body.get(key)
if isinstance(value, bool):
return None
if isinstance(value, (int, float)):
@@ -2917,9 +2935,11 @@ class _TrackerHTTPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
relay_status: dict | None = None,
test_runner: "TestRunManager | None" = None,
capability_policy: str | None = None,
recipe_certifications: CertificationLedger | None = None,
) -> None:
super().__init__(addr, handler)
self.registry = registry
self.recipe_certifications = recipe_certifications or CertificationLedger()
self.capability_policy = normalize_policy(
capability_policy if capability_policy is not None else policy_from_env()
)
@@ -2964,7 +2984,7 @@ class _TrackerHTTPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
class _TrackerHandler(http.server.BaseHTTPRequestHandler):
def log_message(self, fmt, *args): # noqa: suppress request logs in tests
def log_message(self, fmt, *args): # suppress request logs in tests
pass
def _send_json(self, status: int, data: dict, headers: dict[str, str] | None = None) -> None:
@@ -3113,12 +3133,6 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
if self.path == "/v1/models/load":
self._handle_model_load_request()
return
if self.path == "/v1/models/release":
self._handle_model_release_request()
return
if self.path == "/v1/nodes/release-all":
self._handle_node_release_all_request()
return
if self.path == "/v1/models/vote":
self._handle_model_coverage_vote()
return
@@ -3221,16 +3235,6 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
self.send_response(404)
self.end_headers()
def _model_pricing_payload(self, model: str) -> dict | None:
server: _TrackerHTTPServer = self.server # type: ignore[assignment]
if server.billing is None:
return None
in_rate, out_rate = server.billing.prices_for(model)
return {
"input_per_1k_usdt": in_rate,
"output_per_1k_usdt": out_rate,
}
def _handle_models(self):
server: _TrackerHTTPServer = self.server # type: ignore[assignment]
created = int(time.time())
@@ -3246,6 +3250,8 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
seen_ids: set[str] = set()
for name, preset in server.model_presets.items():
model_nodes = [node for node in alive if _node_matches_preset(node, name, preset)]
if not model_nodes and not preset.get("recommended"):
continue
required_start, required_end = _preset_layer_bounds(preset)
coverage = _coverage_percentage(
model_nodes,
@@ -3284,7 +3290,6 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
"shard_coverage_percentage": coverage,
"served_model_copies": served_copies,
"quantizations": quantizations,
"pricing": self._model_pricing_payload(name),
})
seen_ids.add(name)
# Note: the preset's hf_repo is deliberately NOT added to seen_ids —
@@ -3295,15 +3300,7 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
node.hf_repo or node.model
for node in alive
if node.model is not None
# Explicit HF repositories are emitted as stable identifiers even
# when they also resolve to a short-name preset; clients may use
# either identifier when selecting a model.
and (
node.hf_repo is not None
or _resolve_model_preset(
server.model_presets, node.model,
)[1] is None
)
and node.model not in server.model_presets
and node.shard_start is not None
and node.shard_end is not None
and node.num_layers is not None
@@ -3344,7 +3341,6 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
required_start,
required_end,
),
"pricing": self._model_pricing_payload(model_id),
})
seen_ids.add(model_id)
self._send_json(200, {"object": "list", "data": data})
@@ -3404,11 +3400,6 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
"endpoint": node.endpoint,
"relay_addr": node.relay_addr,
"peer_id": node.peer_id,
"wallet_address": node.wallet_address,
"hardware_profile": dict(node.hardware_profile),
"ram_bytes": node.ram_bytes,
"vram_bytes": node.vram_bytes,
"max_loaded_shards": node.max_loaded_shards,
}
for node in tracker_nodes
],
@@ -3432,7 +3423,12 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
memory_pool = _memory_pool_map(server)
def capacity_for(node: _NodeEntry) -> dict:
return _node_capacity_summary(node, _preset_for_node(server, node))
preset = None
if node.model:
preset = server.model_presets.get(node.model)
if preset is None and node.hf_repo and node.num_layers:
preset = _hf_rebalance_preset([node])
return _node_capacity_summary(node, preset)
def throughput_for(node: _NodeEntry) -> dict:
if server.stats is None:
@@ -4649,6 +4645,7 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
hf_repo=hf_repo,
shard_start=shard_start,
shard_end=shard_end,
recipe_certifications=server.recipe_certifications,
)
node_id = _node_id_for_registration(
@@ -4842,20 +4839,6 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
entry.uptime_seconds = float(body["uptime_seconds"])
if "status" in body and body["status"] in ("ready", "loading"):
entry.status = body["status"]
completed_directives = body.get("completed_directives", [])
if isinstance(completed_directives, list):
for directive in completed_directives:
if not isinstance(directive, dict) or directive.get("action") not in {"DROP_SHARD", "DROP_ALL_SHARDS"}:
continue
# A node has confirmed the release. Stop advertising its
# old route immediately so the dashboard and routing state
# agree with the runtime.
entry.model = "stub-model"
entry.hf_repo = None
entry.shard_start = None
entry.shard_end = None
entry.tracker_mode = False
entry.status = "ready"
if "friendly_name" in body:
try:
entry.friendly_name = _normalize_friendly_name(body.get("friendly_name"))
@@ -4927,68 +4910,14 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
if not isinstance(model, str) or not model.strip():
self._send_json(400, {"error": "model is required"})
return
node_id = body.get("node_id")
if node_id is not None and (not isinstance(node_id, str) or not node_id):
self._send_json(400, {"error": "node_id must be a non-empty string"})
return
_resolved_name, preset = _resolve_model_preset(server.model_presets, model)
if preset is None or str(preset.get("hf_repo") or "").strip().lower() == "stub-model":
self._send_json(400, {"error": "stub-model is a local test backend and cannot be loaded onto a node"})
return
with server.lock:
self._purge_expired_nodes()
assignment = _request_model_load_locked(server, model, node_id)
if assignment is None and body.get("force") is True:
assignment = _force_model_load_locked(server, model, node_id)
assignment = _request_model_load_locked(server, model)
if assignment is None:
self._send_json(409, {"error": "no ready joined node has an available model slot and sufficient capacity"})
return
self._send_json(202, {"status": "queued", "assignment": assignment})
def _handle_model_release_request(self):
server: _TrackerHTTPServer = self.server # type: ignore[assignment]
if not self._require_role("admin", "validator"):
return
body = self._read_json_body()
if body is None:
return
model = body.get("model")
if not isinstance(model, str) or not model.strip():
self._send_json(400, {"error": "model is required"})
return
node_id = body.get("node_id")
if node_id is not None and (not isinstance(node_id, str) or not node_id):
self._send_json(400, {"error": "node_id must be a non-empty string"})
return
with server.lock:
self._purge_expired_nodes()
released = _release_model_locked(server, model, node_id)
if not released:
self._send_json(404, {"error": "no served shards found for model"})
return
self._send_json(202, {"status": "release_queued", "released": released})
def _handle_node_release_all_request(self):
server: _TrackerHTTPServer = self.server # type: ignore[assignment]
if not self._require_role("admin", "validator"):
return
body = self._read_json_body()
if body is None:
return
node_id = body.get("node_id")
if not isinstance(node_id, str) or not node_id:
self._send_json(400, {"error": "node_id must be a non-empty string"})
return
with server.lock:
self._purge_expired_nodes()
released = _release_all_node_models_locked(server, node_id)
if not released:
self._send_json(404, {"error": "no loaded models found for node"})
return
self._send_json(202, {
"status": "release_queued", "released": released, "node_id": node_id,
})
def _handle_model_coverage_vote(self):
"""Record a rolling wish-list signal for an unavailable precision."""
server: _TrackerHTTPServer = self.server # type: ignore[assignment]
@@ -6639,7 +6568,7 @@ class TrackerServer:
embedded_relay_port: int = 8765,
embedded_relay_max_peers: int = 500,
billing: BillingLedger | None = None,
enable_billing: bool = True,
enable_billing: bool = False,
billing_db: str | None = None,
accounts: AccountStore | None = None,
accounts_db: str | None = None,
@@ -6693,6 +6622,7 @@ class TrackerServer:
self._embedded_relay: Any | None = None
self._embedded_relay_actual_port: int | None = None
self._registry: dict[str, _NodeEntry] = {}
self._recipe_certifications = CertificationLedger()
self._lock = threading.Lock()
self._server: _TrackerHTTPServer | None = None
self._thread: threading.Thread | None = None
@@ -6802,6 +6732,84 @@ class TrackerServer:
self._test_runner: TestRunManager | None = test_runner
self.port: int | None = None
def certify_recipe(
self,
identity: PresentedIdentity,
evidence: DistributedForwardEvidence,
) -> RecipeStatus:
"""Promote one exact recipe from tracker-recorded distributed evidence.
This is the tracker's only certification authority. The evidence names
the nodes that served the forward; this method refuses to take any of
them on the evidence's word. For each one it goes back to what *this
tracker* re-derived at admission and requires the evidence to describe
the same Shard: same route fingerprint, same registered range, and the
same shard binding digest — the derivative's own bytes and exact range.
Without the binding check, a route fingerprint is range-independent by
design (:mod:`meshnet_tracker.recipe`), so evidence could name the right
recipe while describing splits nobody on the route was actually serving,
and the certification would attach to blobs that never ran.
"""
with self._lock:
for node_id, participant in zip(
evidence.node_ids, evidence.participants, strict=True
):
node = self._registry.get(node_id)
if node is None:
raise RecipeIdentityError(
f"certification participant {node_id!r} is not registered"
)
admitted = node.capability
if admitted.fingerprint != identity.key:
raise RecipeIdentityError(
f"certification participant {node_id!r} is not admitted under "
"the promoted fingerprint"
)
if admitted.state not in (STATE_UNCERTIFIED, STATE_ADMITTED):
raise RecipeIdentityError(
f"certification participant {node_id!r} has capability state "
f"{admitted.state!r}"
)
registered_range = (
node.shard_start,
None if node.shard_end is None else node.shard_end + 1,
)
if registered_range != (
participant.shard_start,
participant.shard_end,
):
raise RecipeIdentityError(
f"certification participant {node_id!r} range differs from its "
"registered Shard range"
)
# The exact bytes and range this node was admitted on. A node that
# registered without an identity has no binding, and cannot be a
# participant in an exact certification at all.
if admitted.shard_binding_digest is None:
raise RecipeIdentityError(
f"certification participant {node_id!r} registered no exact "
"Shard binding; it cannot certify a recipe"
)
if admitted.shard_binding_digest != participant.shard_binding_digest:
raise RecipeIdentityError(
f"certification participant {node_id!r} presents a Shard "
"binding this tracker did not admit it on; the evidence "
"describes different derivative bytes or a different range"
)
status = self._recipe_certifications.certify(identity, evidence)
for node in self._registry.values():
if (
node.capability.state == STATE_UNCERTIFIED
and node.capability.fingerprint == identity.key
):
node.capability = replace(
node.capability.with_state(STATE_ADMITTED, status.detail),
certification=status.status,
)
return status
def _start_embedded_relay(self) -> dict:
"""Start the shared RelayServer class in-process for tracker+relay deployments."""
if not self._embedded_relay_enabled:
@@ -6887,6 +6895,7 @@ class TrackerServer:
relay_status=http_relay_status,
test_runner=self._test_runner,
capability_policy=self._capability_policy,
recipe_certifications=self._recipe_certifications,
)
self.port = self._server.server_address[1]
@@ -7096,10 +7105,6 @@ class TrackerServer:
shard_end = int(payload["shard_end"]) if payload.get("shard_end") is not None else None
except (TypeError, ValueError):
return
try:
friendly_name = _normalize_friendly_name(payload.get("friendly_name"))
except ValueError:
friendly_name = None
# The replicated payload is the raw registration body, so the follower can
# resolve precision exactly as the leader did -- including telling a legacy
# absent `quantization` from a declared one. Dropping these fields here
@@ -7145,6 +7150,7 @@ class TrackerServer:
hf_repo=payload.get("hf_repo"),
shard_start=shard_start,
shard_end=shard_end,
recipe_certifications=self._recipe_certifications,
),
)
with self._lock: