fix(tracker): close alpha accounting review gaps

Address post-review blockers from the alpha hardening diff: charge non-stream completions that omit usage, include prompt tokens in max_charge_per_request enforcement, and wire the CLI to a persisted local registry contract by default.

Verification: .venv/bin/python -m compileall -q packages tests; focused billing/CLI checks passed; full pytest: 314 passed, 3 skipped, 1 env failure from existing meshnet-node on port 7000.

packages/tracker/meshnet_tracker/cli.py

@@ -8,6 +8,8 @@ from .accounts import DEFAULT_ACCOUNTS_DB_PATH
 from .billing import DEFAULT_BILLING_DB_PATH
 from .server import TrackerServer, derive_relay_url_from_public_tracker_url
 
+DEFAULT_REGISTRY_DB_PATH = "meshnet_registry.sqlite3"
+
 
 def main() -> None:
     common = argparse.ArgumentParser(add_help=False)
@@ -49,20 +51,34 @@ def main() -> None:
             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 requested token limit would "
-            "cost more than this many USDT"
-        ),
-    )
+    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(
+        "--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,
@@ -149,6 +165,11 @@ def main() -> None:
             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,
@@ -158,9 +179,10 @@ def main() -> None:
             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,
-            accounts_db=None if args.no_accounts else args.accounts_db,
+            billing_db=None if args.no_billing else args.billing_db,
+            max_charge_per_request=args.max_charge_per_request,
+            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,

packages/tracker/meshnet_tracker/server.py

@@ -1293,15 +1293,43 @@ def _request_total_token_upper_bound(body: dict) -> int | None:
 
 def _billable_non_stream_tokens(payload: dict, request_body: dict) -> int:
     reported = _usage_total_tokens(payload)
-    if reported is None:
-        return 0
-    billable = max(0, reported)
     upper_bound = _request_total_token_upper_bound(request_body)
+    if reported is None:
+        completion_estimate = _observed_non_stream_completion_tokens(payload)
+        if completion_estimate > 0:
+            billable = completion_estimate + (_estimate_prompt_tokens(request_body) or 0)
+        elif upper_bound is not None:
+            billable = upper_bound
+        else:
+            return 0
+        return min(billable, upper_bound) if upper_bound is not None else billable
+    billable = max(0, reported)
     if upper_bound is not None:
         billable = min(billable, upper_bound)
     return billable
 
 
+def _observed_non_stream_completion_tokens(payload: dict) -> int:
+    choices = payload.get("choices")
+    if not isinstance(choices, list):
+        return 0
+    observed = 0
+    for choice in choices:
+        if not isinstance(choice, dict):
+            continue
+        message = choice.get("message")
+        estimated: int | None = None
+        if isinstance(message, dict):
+            estimated = _estimate_text_tokens(message.get("content"))
+        if estimated is None:
+            estimated = _estimate_text_tokens(choice.get("text"))
+        if estimated is not None:
+            observed += estimated
+        elif choice:
+            observed += 1
+    return observed
+
+
 def _observed_stream_tokens(payload: dict) -> int:
     choices = payload.get("choices")
     if not isinstance(choices, list):
@@ -1881,7 +1909,8 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
                         "code": "missing_token_limit",
                     }})
                     return
-                estimated_charge = server.billing.price_for(model) * token_limit / 1000.0
+                total_token_bound = _request_total_token_upper_bound(body) or token_limit
+                estimated_charge = server.billing.price_for(model) * total_token_bound / 1000.0
                 if estimated_charge > server.max_charge_per_request:
                     self._send_json(402, {"error": {
                         "message": (

tests/test_billing_ledger.py

@@ -21,6 +21,7 @@ from meshnet_tracker.server import (
     _billable_non_stream_tokens,
     _billable_stream_tokens,
     _estimate_prompt_tokens,
+    _observed_non_stream_completion_tokens,
     _observed_stream_tokens,
 )
 
@@ -99,6 +100,14 @@ def test_non_stream_billable_tokens_cap_usage_by_request_bound():
     assert _billable_non_stream_tokens(payload, request) == 5
 
 
+def test_non_stream_billable_tokens_fallback_when_usage_missing():
+    payload = {"choices": [{"message": {"role": "assistant", "content": "ok now"}}]}
+    request = {"messages": [{"role": "user", "content": "hello tracker"}], "max_tokens": 10}
+
+    assert _observed_non_stream_completion_tokens(payload) == 2
+    assert _billable_non_stream_tokens(payload, request) == 4
+
+
 def test_stream_billable_tokens_allow_usage_to_lower_observed_count_only():
     observed_payload = {
         "choices": [{
@@ -557,7 +566,12 @@ def test_proxy_chat_rejects_request_above_spend_cap_before_routing():
             r.read()
 
         with pytest.raises(urllib.error.HTTPError) as exc_info:
-            _chat(tracker_url, api_key="capped-client", max_tokens=1000)
+            _chat(
+                tracker_url,
+                api_key="capped-client",
+                messages=[{"role": "user", "content": " ".join(["prompt"] * 1000)}],
+                max_tokens=1,
+            )
         body = json.loads(exc_info.value.read())
         assert exc_info.value.code == 402
         assert body["error"]["code"] == "spend_cap_exceeded"