fix: resolve mint fallback review comments

.env.example

@@ -45,6 +45,9 @@ ROUTSTR_SECRET_KEY=
 # ENABLE_ANALYTICS_SHARING=true
 # CASHU_MINTS="https://mint.minibits.cash/Bitcoin,https://mint.cubabitcoin.org,https://ecashmint.otrta.me"
 # MINT_OPERATION_CONCURRENCY=4
+# MINT_OPERATION_TIMEOUT_SECONDS=30
+# MINT_MAX_CONCURRENCY=4
+# MINT_RETRY_MAX_ATTEMPTS=3
 # RECEIVE_LN_ADDRESS=
 # REFUND_SWEEP_CLAIM_TIMEOUT_SECONDS=900
 

docs/provider/configuration.md

@@ -136,6 +136,10 @@ Use environment variables for:
 | `NSEC`               | Legacy seed for the Nostr private key (otherwise set from the admin UI) | —                |
 | `ENABLE_ANALYTICS_SHARING` | Enable usage analytics sharing to Nostr | `true`                         |
 | `CASHU_MINTS`        | Comma-separated mint URLs         | `https://mint.minibits.cash/Bitcoin` |
+| `MINT_OPERATION_CONCURRENCY` | Concurrent mint/unit balance reads | `4` |
+| `MINT_OPERATION_TIMEOUT_SECONDS` | Per-attempt timeout for mint network calls | `30` |
+| `MINT_MAX_CONCURRENCY` | Concurrent operations allowed per mint (`0` disables the limit) | `4` |
+| `MINT_RETRY_MAX_ATTEMPTS` | Retries after a timeout or HTTP 429 (`0` disables retries) | `3` |
 | `RECEIVE_LN_ADDRESS` | Lightning address for withdrawals | —                                    |
 | `MIN_PAYOUT_SAT`     | Min payout balance in sats (applies to all mints) | `210`                |
 | `PAYOUT_INTERVAL_SECONDS` | Payout loop interval (seconds) | `900`                            |
@@ -143,6 +147,11 @@ Use environment variables for:
 | `CORS_ORIGINS`       | Allowed CORS origins              | `*`                                  |
 | `RELAYS`             | Nostr relays (comma-separated)    | (default set)                        |
 
+Mint HTTP 429 responses create a per-mint cooldown. Operations that already hold
+Routstr's wallet mutation lock fail fast during that cooldown instead of waiting
+while blocking every other wallet mutation. Callers receive an error and may retry
+later; the current response does not include the cooldown duration.
+
 ### Priority
 
 Environment variables are read on startup. Dashboard settings override them and persist in the database. Once you change a setting in the dashboard, the env var is ignored for that setting.

routstr/balance.py

@@ -215,7 +215,7 @@ async def topup_wallet_endpoint(
         raise HTTPException(status_code=400, detail="Invalid token format")
 
     source_mint = token_mint_url(cashu_token, "unknown")
-    logger.warning(
+    logger.info(
         "Cashu wallet top-up started",
         extra={
             "event": "cashu_topup_started",
@@ -259,7 +259,7 @@ async def topup_wallet_endpoint(
         )
         raise HTTPException(status_code=status_code, detail=message)
 
-    logger.warning(
+    logger.info(
         "Cashu wallet top-up completed",
         extra={
             "event": "cashu_topup_completed",

routstr/lightning.py

@@ -3,8 +3,9 @@ import hashlib
 import re
 import secrets
 import time
+from contextlib import asynccontextmanager
 from dataclasses import dataclass
-from typing import Any
+from typing import Any, AsyncGenerator
 
 from fastapi import APIRouter, Depends, Header, HTTPException
 from pydantic import BaseModel, Field
@@ -15,11 +16,13 @@ from sqlmodel.ext.asyncio.session import AsyncSession
 from .core.db import ApiKey, LightningInvoice, create_session, get_session
 from .core.logging import get_logger
 from .core.settings import settings
+from .mint import (
+    is_mint_rate_limited,
+    mint_cooldown_remaining,
+    run_mint_operation,
+)
 from .wallet import (
     MintConnectionError,
-    _is_mint_rate_limited,
-    _mint_cooldown_remaining,
-    _mint_operation,
     get_wallet,
     is_mint_connection_error,
     wallet_operation_guard,
@@ -31,7 +34,31 @@ lightning_router = APIRouter(prefix="/lightning")
 
 # Avoid duplicate work within one process. Cross-process credit fencing is done
 # by the conditional pending -> paid update in _finalize_invoice_settlement().
-_invoice_settlement_locks: dict[str, asyncio.Lock] = {}
+@dataclass
+class _InvoiceLockEntry:
+    lock: asyncio.Lock
+    users: int = 0
+
+
+_invoice_settlement_locks: dict[str, _InvoiceLockEntry] = {}
+
+
+@asynccontextmanager
+async def _invoice_settlement_lock(invoice_id: str) -> AsyncGenerator[None, None]:
+    """Serialize one invoice and remove its lock after the last waiter leaves."""
+
+    entry = _invoice_settlement_locks.get(invoice_id)
+    if entry is None:
+        entry = _InvoiceLockEntry(asyncio.Lock())
+        _invoice_settlement_locks[invoice_id] = entry
+    entry.users += 1
+    try:
+        async with entry.lock:
+            yield
+    finally:
+        entry.users -= 1
+        if entry.users == 0 and _invoice_settlement_locks.get(invoice_id) is entry:
+            del _invoice_settlement_locks[invoice_id]
 
 
 @dataclass(frozen=True)
@@ -142,11 +169,11 @@ async def _request_mint_with_fallback(
     configured = allowed_mints or [settings.primary_mint, *settings.cashu_mints]
     candidates = list(dict.fromkeys(configured))
     for mint_url in candidates:
-        cooldown = _mint_cooldown_remaining(mint_url)
+        cooldown = mint_cooldown_remaining(mint_url)
         if cooldown > 0:
             tried.append(f"{mint_url}: cooling down")
             logger.info(
-                "Skipping rate-limited mint",
+                "Skipping mint during cooldown",
                 extra={
                     "mint_url": mint_url,
                     "cooldown_seconds": round(cooldown, 2),
@@ -156,7 +183,7 @@ async def _request_mint_with_fallback(
             continue
         try:
             wallet = await get_wallet(mint_url, "sat", retry_on_rate_limit=False)
-            quote = await _mint_operation(
+            quote = await run_mint_operation(
                 lambda: wallet.request_mint(amount_sats),
                 op_name="request_mint_invoice",
                 mint_url=mint_url,
@@ -165,7 +192,7 @@ async def _request_mint_with_fallback(
             return quote.request, quote.quote, mint_url
         except Exception as e:
             tried.append(f"{mint_url}: {type(e).__name__}")
-            if not is_mint_connection_error(e) and not _is_mint_rate_limited(e):
+            if not is_mint_connection_error(e) and not is_mint_rate_limited(e):
                 raise
             logger.warning(
                 "request_mint failed, trying fallback mint",
@@ -352,8 +379,7 @@ async def recover_invoice(
 async def check_invoice_payment(
     invoice: LightningInvoice, session: AsyncSession
 ) -> None:
-    lock = _invoice_settlement_locks.setdefault(invoice.id, asyncio.Lock())
-    async with lock, wallet_operation_guard():
+    async with _invoice_settlement_lock(invoice.id), wallet_operation_guard():
         minted = False
         try:
             # Snapshot the row and end the caller's read transaction before any
@@ -368,7 +394,7 @@ async def check_invoice_payment(
 
             mint_url = settlement.mint_url or settings.primary_mint
             wallet = await get_wallet(mint_url, "sat")
-            mint_status = await _mint_operation(
+            mint_status = await run_mint_operation(
                 lambda: wallet.get_mint_quote(settlement.payment_hash),
                 op_name="get_mint_quote",
                 mint_url=mint_url,
@@ -483,7 +509,7 @@ async def _mint_invoice_quote(
         return
 
     try:
-        await _mint_operation(
+        await run_mint_operation(
             lambda: wallet.mint(invoice.amount_sats, quote_id=invoice.payment_hash),
             op_name=f"invoice_mint_{invoice.purpose}",
             mint_url=mint_url,

routstr/mint.py

@@ -0,0 +1,338 @@
+"""Shared policy for bounded, rate-aware Cashu mint API operations."""
+
+from __future__ import annotations
+
+import asyncio
+import socket
+import time
+from contextlib import asynccontextmanager
+from contextvars import ContextVar
+from typing import Any, AsyncGenerator, Awaitable, Callable
+
+import httpx
+
+from .core.logging import get_logger
+from .core.settings import settings
+
+logger = get_logger(__name__)
+
+MINT_TRANSPORT_EXCEPTIONS: tuple[type[BaseException], ...] = (
+    httpx.NetworkError,
+    httpx.TimeoutException,
+    ConnectionError,
+    socket.gaierror,
+    asyncio.TimeoutError,
+)
+
+MINT_TRANSPORT_COOLDOWN_SECONDS = 30.0
+_MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS = 60.0
+_MINT_RATE_LIMIT_MAX_COOLDOWN_SECONDS = 7 * 60 * 60
+
+_fail_fast_depth: ContextVar[int] = ContextVar("mint_fail_fast_depth", default=0)
+
+
+class MintRateLimitedError(httpx.HTTPStatusError):
+    """Typed boundary error preserving a Cashu mint's HTTP 429 response."""
+
+
+class MintCooldownError(Exception):
+    """A mint is cooling down and this operation must not wait."""
+
+    def __init__(self, mint_url: str, retry_after_seconds: float):
+        self.mint_url = mint_url
+        self.retry_after_seconds = max(0.0, retry_after_seconds)
+        super().__init__(
+            f"Mint {mint_url} is cooling down; retry after "
+            f"{self.retry_after_seconds:.2f}s"
+        )
+
+
+@asynccontextmanager
+async def fail_fast_mint_operations() -> AsyncGenerator[None, None]:
+    """Make mint cooldown/probe waits fail fast in the current task.
+
+    Wallet mutation code holds a process-wide file lock. It enters this scope so
+    an existing mint cooldown can never turn that lock into a multi-hour wait.
+    """
+
+    token = _fail_fast_depth.set(_fail_fast_depth.get() + 1)
+    try:
+        yield
+    finally:
+        _fail_fast_depth.reset(token)
+
+
+class MintRateGuard:
+    """Limit concurrency and remember per-mint cooldown/probe state."""
+
+    _guards: dict[str, "MintRateGuard"] = {}
+
+    @classmethod
+    def get(cls, mint_url: str) -> "MintRateGuard":
+        concurrency = settings.mint_max_concurrency
+        guard = cls._guards.get(mint_url)
+        if guard is None or guard._max_concurrency != concurrency:
+            guard = cls(mint_url, concurrency)
+            cls._guards[mint_url] = guard
+        return guard
+
+    def __init__(self, mint_url: str, max_concurrency: int):
+        self._mint_url = mint_url
+        self._max_concurrency = max_concurrency
+        self._semaphore = (
+            asyncio.Semaphore(max_concurrency) if max_concurrency > 0 else None
+        )
+        self._cooldown_until = 0.0
+        self._cooldown_reason: str | None = None
+        self._consecutive_rate_limits = 0
+        self._needs_probe = False
+        self._probe_lock = asyncio.Lock()
+
+    def apply_cooldown(self, delay: float, *, reason: str | None = None) -> None:
+        deadline = time.monotonic() + max(0.0, delay)
+        if deadline >= self._cooldown_until:
+            self._cooldown_until = deadline
+            if reason is not None:
+                self._cooldown_reason = reason
+        elif self._cooldown_reason is None and reason is not None:
+            self._cooldown_reason = reason
+        self._needs_probe = True
+
+    def apply_rate_limit_cooldown(self, retry_after: float | None = None) -> float:
+        remaining = self.cooldown_remaining()
+        if remaining > 0 and self._cooldown_reason == "rate_limited":
+            minimum = min(
+                _MINT_RATE_LIMIT_MAX_COOLDOWN_SECONDS,
+                max(_MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS, retry_after or 0.0),
+            )
+            if minimum > remaining:
+                self.apply_cooldown(minimum, reason="rate_limited")
+                return minimum
+            return remaining
+
+        self._consecutive_rate_limits += 1
+        base = max(_MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS, retry_after or 0.0)
+        multiplier = 2 ** min(self._consecutive_rate_limits - 1, 10)
+        delay = min(_MINT_RATE_LIMIT_MAX_COOLDOWN_SECONDS, base * multiplier)
+        self.apply_cooldown(delay, reason="rate_limited")
+        return delay
+
+    def cooldown_remaining(self) -> float:
+        return max(0.0, self._cooldown_until - time.monotonic())
+
+    def cooldown_reason(self) -> str | None:
+        return self._cooldown_reason if self.cooldown_remaining() > 0 else None
+
+    def _raise_if_wait_forbidden(self) -> None:
+        if _fail_fast_depth.get() and (
+            self._needs_probe or self.cooldown_remaining() > 0
+        ):
+            raise MintCooldownError(self._mint_url, self.cooldown_remaining())
+
+    async def _wait_for_cooldown(self) -> None:
+        while True:
+            self._raise_if_wait_forbidden()
+            deadline = self._cooldown_until
+            wait = max(0.0, deadline - time.monotonic())
+            if wait <= 0:
+                return
+            logger.debug(
+                "Mint rate guard: cooling down",
+                extra={"mint_url": self._mint_url, "wait_seconds": round(wait, 2)},
+            )
+            await asyncio.sleep(wait)
+            if self._cooldown_until <= deadline:
+                return
+
+    async def _run_probe(self, factory: Callable[[], Awaitable[Any]]) -> Any:
+        await self._wait_for_cooldown()
+        logger.info(
+            "Mint cooldown ended; sending one probe request",
+            extra={"event": "mint_cooldown_probe_started", "mint_url": self._mint_url},
+        )
+        try:
+            result = await factory()
+        except Exception as error:
+            if is_mint_rate_limited(error):
+                retry_after = None
+                if isinstance(error, httpx.HTTPStatusError):
+                    retry_after = parse_retry_after(error.response.headers)
+                delay = max(
+                    _MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS,
+                    retry_after or 0.0,
+                )
+                self.apply_cooldown(delay, reason="rate_limited")
+            else:
+                self.apply_cooldown(1.0)
+            logger.warning(
+                "Mint cooldown probe failed",
+                extra={
+                    "event": "mint_cooldown_probe_failed",
+                    "mint_url": self._mint_url,
+                    "error": str(error),
+                    "error_type": type(error).__name__,
+                    "cooldown_seconds": round(self.cooldown_remaining(), 2),
+                    "consecutive_rate_limits": self._consecutive_rate_limits,
+                },
+            )
+            raise
+
+        self._needs_probe = False
+        self._cooldown_until = 0.0
+        self._cooldown_reason = None
+        self._consecutive_rate_limits = 0
+        logger.info(
+            "Mint cooldown probe succeeded; restoring normal concurrency",
+            extra={
+                "event": "mint_cooldown_probe_succeeded",
+                "mint_url": self._mint_url,
+            },
+        )
+        return result
+
+    async def run(self, factory: Callable[[], Awaitable[Any]]) -> Any:
+        while True:
+            self._raise_if_wait_forbidden()
+            if self._needs_probe or self.cooldown_remaining() > 0:
+                async with self._probe_lock:
+                    self._raise_if_wait_forbidden()
+                    if self.cooldown_remaining() > 0:
+                        self._needs_probe = True
+                    if self._needs_probe:
+                        return await self._run_probe(factory)
+                continue
+
+            if self._semaphore is None:
+                return await factory()
+            async with self._semaphore:
+                self._raise_if_wait_forbidden()
+                if self._needs_probe:
+                    continue
+                return await factory()
+
+
+def mint_cooldown_remaining(mint_url: str) -> float:
+    return MintRateGuard.get(mint_url).cooldown_remaining()
+
+
+def mint_cooldown_reason(mint_url: str) -> str | None:
+    return MintRateGuard.get(mint_url).cooldown_reason()
+
+
+def is_mint_rate_limited(error: BaseException) -> bool:
+    """Return whether an exception chain represents HTTP 429/cooldown."""
+
+    current: BaseException | None = error
+    seen: set[int] = set()
+    while current is not None and id(current) not in seen:
+        seen.add(id(current))
+        if isinstance(current, MintCooldownError):
+            return True
+        if isinstance(current, httpx.HTTPStatusError):
+            if current.response.status_code == 429:
+                return True
+        current = current.__cause__ or current.__context__
+    return False
+
+
+def parse_retry_after(headers: Any) -> float | None:
+    raw = headers.get("retry-after") or headers.get("Retry-After")
+    if raw is None:
+        return None
+    try:
+        return float(str(raw).strip())
+    except (TypeError, ValueError):
+        return None
+
+
+async def run_mint_operation(
+    factory: Callable[[], Awaitable[Any]],
+    *,
+    op_name: str = "mint_operation",
+    mint_url: str = "",
+    retry_timeouts: bool = True,
+    retry_on_rate_limit: bool = True,
+) -> Any:
+    """Run one mint operation with bounded concurrency and adaptive cooldown."""
+
+    guard = MintRateGuard.get(mint_url) if mint_url else None
+    timeout = settings.mint_operation_timeout_seconds
+    max_attempts = settings.mint_retry_max_attempts + 1
+
+    async def timed_factory() -> Any:
+        if timeout > 0:
+            return await asyncio.wait_for(factory(), timeout=timeout)
+        return await factory()
+
+    async def invoke() -> Any:
+        if guard is not None:
+            return await guard.run(timed_factory)
+        return await timed_factory()
+
+    for attempt in range(max_attempts):
+        try:
+            return await invoke()
+        except MintCooldownError:
+            raise
+        except (asyncio.TimeoutError, httpx.TimeoutException) as exc:
+            if retry_timeouts and attempt < max_attempts - 1:
+                backoff = (2**attempt) + (time.monotonic() % 1.0)
+                logger.warning(
+                    "Mint operation timed out, retrying",
+                    extra={
+                        "op_name": op_name,
+                        "mint_url": mint_url,
+                        "attempt": attempt + 1,
+                        "backoff_seconds": round(backoff, 2),
+                    },
+                )
+                await asyncio.sleep(backoff)
+                continue
+            raise httpx.TimeoutException(
+                f"{op_name} timed out (attempts: {attempt + 1})"
+            ) from exc
+        except Exception as exc:
+            if not is_mint_rate_limited(exc):
+                raise
+
+            backoff = (2**attempt) + (time.monotonic() % 1.0)
+            if isinstance(exc, httpx.HTTPStatusError):
+                retry_after = parse_retry_after(exc.response.headers)
+                if retry_after is not None:
+                    backoff = max(retry_after, backoff)
+            cooldown = backoff
+            if guard is not None:
+                cooldown = guard.apply_rate_limit_cooldown(backoff)
+
+            if not retry_on_rate_limit:
+                logger.warning(
+                    "Mint rate-limited, skipping retries for fallback",
+                    extra={
+                        "op_name": op_name,
+                        "mint_url": mint_url,
+                        "cooldown_seconds": round(cooldown, 2),
+                        "consecutive_rate_limits": guard._consecutive_rate_limits
+                        if guard is not None
+                        else attempt + 1,
+                    },
+                )
+                raise
+
+            if attempt >= max_attempts - 1:
+                raise
+            logger.warning(
+                "Mint rate-limited, applying cooldown",
+                extra={
+                    "op_name": op_name,
+                    "mint_url": mint_url,
+                    "attempt": attempt + 1,
+                    "cooldown_seconds": round(cooldown, 2),
+                    "consecutive_rate_limits": guard._consecutive_rate_limits
+                    if guard is not None
+                    else attempt + 1,
+                },
+            )
+            if guard is None:
+                await asyncio.sleep(cooldown)
+
+    raise RuntimeError(f"{op_name}: exhausted retries unexpectedly")

routstr/payment/helpers.py

@@ -18,18 +18,6 @@ from ..wallet import deserialize_token_from_string
 
 logger = get_logger(__name__)
 
-# Interim policy: when Routstr must move value to another trusted mint, the
-# cross-mint Lightning round trip can consume fees that are not visible to the
-# client. Reserve 5% headroom until the fee-payer policy is made explicit.
-_MINT_FEE_ALLOWANCE = 0.05
-
-
-def apply_mint_fee_allowance(cost_msat: int) -> int:
-    """Reserve headroom for possible trusted-mint fallback fees."""
-    adjusted = math.ceil(cost_msat * (1 - _MINT_FEE_ALLOWANCE))
-    return max(settings.min_request_msat, adjusted)
-
-
 def check_token_balance(headers: dict, body: dict, max_cost_for_model: int) -> None:
     if x_cashu := headers.get("x-cashu", None):
         cashu_token = x_cashu

routstr/payment/lnurl.py

@@ -1,17 +1,13 @@
 from __future__ import annotations
 
-import asyncio
 import math
 from typing import TypedDict
 
 import httpx
+from cashu.core.base import MeltQuoteState
 from cashu.wallet.wallet import Proof, Wallet
 
-# The Cashu library issues POST /v1/melt/bolt11 with timeout=None, so a hung or
-# very slow mint can block a melt (and any caller, e.g. the payout loop)
-# indefinitely. _mint_operation (imported lazily in raw_send_to_lnurl to avoid
-# a circular import with wallet.py) bounds it via MINT_OPERATION_TIMEOUT_SECONDS.
-MELT_TIMEOUT_SECONDS = 60
+from ..mint import MINT_TRANSPORT_EXCEPTIONS, run_mint_operation
 
 try:
     from bech32 import bech32_decode, convertbits  # type: ignore
@@ -222,9 +218,7 @@ async def raw_send_to_lnurl(
         lnurl_data["callback_url"], final_amount
     )
 
-    from ..wallet import _mint_operation
-
-    melt_quote_resp = await _mint_operation(
+    melt_quote_resp = await run_mint_operation(
         lambda: wallet.melt_quote(invoice=bolt11_invoice),
         op_name="lnurl_melt_quote",
         mint_url=str(wallet.url),
@@ -234,22 +228,44 @@ async def raw_send_to_lnurl(
         proofs, _ = await wallet.select_to_send(proofs, amount, set_reserved=True)
 
     try:
-        _ = await asyncio.wait_for(
-            _mint_operation(
-                lambda: wallet.melt(
-                    proofs=proofs,
-                    invoice=bolt11_invoice,
-                    fee_reserve_sat=melt_quote_resp.fee_reserve,
-                    quote_id=melt_quote_resp.quote,
-                ),
-                op_name="lnurl_melt",
-                mint_url=str(wallet.url),
-                retry_timeouts=False,
+        melt_response = await run_mint_operation(
+            lambda: wallet.melt(
+                proofs=proofs,
+                invoice=bolt11_invoice,
+                fee_reserve_sat=melt_quote_resp.fee_reserve,
+                quote_id=melt_quote_resp.quote,
             ),
-            timeout=MELT_TIMEOUT_SECONDS,
+            op_name="lnurl_melt",
+            mint_url=str(wallet.url),
+            retry_timeouts=False,
         )
-    except (httpx.TimeoutException, asyncio.TimeoutError) as e:
+    except MINT_TRANSPORT_EXCEPTIONS as error:
+        melt_response = None
+        melt_error: BaseException | None = error
+    else:
+        melt_error = None
+
+    if getattr(melt_response, "state", None) == MeltQuoteState.paid:
+        return final_amount
+
+    try:
+        quote = await run_mint_operation(
+            lambda: wallet.get_melt_quote(melt_quote_resp.quote),
+            op_name="reconcile_lnurl_melt_quote",
+            mint_url=str(wallet.url),
+            retry_timeouts=False,
+        )
+    except Exception as reconciliation_error:
         raise LNURLError(
-            f"Melt timed out after {MELT_TIMEOUT_SECONDS}s (mint unresponsive)"
-        ) from e
-    return final_amount
+            "Melt outcome is ambiguous; quote reconciliation failed and proofs "
+            "must not be retried"
+        ) from reconciliation_error
+
+    if quote is not None and quote.state == MeltQuoteState.paid:
+        return final_amount
+
+    state = getattr(getattr(quote, "state", None), "value", "unknown")
+    raise LNURLError(
+        "Melt outcome is ambiguous; proofs must not be retried "
+        f"(quote_state={state})"
+    ) from melt_error

routstr/proxy.py

@@ -27,7 +27,6 @@ from .core.db import (
 from .core.exceptions import UpstreamError
 from .core.not_found import build_not_found_response
 from .payment.helpers import (
-    apply_mint_fee_allowance,
     calculate_discounted_max_cost,
     check_token_balance,
     create_error_response,
@@ -354,7 +353,6 @@ async def _proxy(
     max_cost_for_model = await calculate_discounted_max_cost(
         _max_cost_for_model, request_body_dict, model_obj=model_obj
     )
-    max_cost_for_model = apply_mint_fee_allowance(max_cost_for_model)
 
     check_token_balance(headers, request_body_dict, max_cost_for_model)
 
@@ -493,9 +491,6 @@ async def _proxy(
             candidate_max = await calculate_discounted_max_cost(
                 candidate_max, request_body_dict, model_obj=model_obj
             )
-            # Apply the same interim 5% trusted-mint fee headroom used for the
-            # first candidate; failover must not silently change admission.
-            candidate_max = apply_mint_fee_allowance(candidate_max)
             if candidate_max > max_cost_for_model:
                 await revert_pay_for_request(
                     key, session, max_cost_for_model, reservation_snapshot

routstr/wallet.py

@@ -2,16 +2,15 @@ import asyncio
 import fcntl
 import os
 import re
-import socket
 import time
 import typing
 from contextlib import asynccontextmanager
 from contextvars import ContextVar
 from pathlib import Path
-from typing import Any, AsyncGenerator, Awaitable, Callable, TypedDict
+from typing import AsyncGenerator, TypedDict
 
 import httpx
-from cashu.core.base import MintQuote, Proof, Token
+from cashu.core.base import MeltQuoteState, MintQuote, Proof, Token
 from cashu.core.mint_info import MintInfo as _CashuMintInfo
 from cashu.wallet.helpers import deserialize_token_from_string
 from cashu.wallet.wallet import Wallet as _CashuWallet
@@ -21,8 +20,27 @@ from sqlmodel import col, select, update
 from .core import db, get_logger
 from .core.db import store_cashu_transaction_with_retry as store_cashu_transaction
 from .core.settings import settings
+from .mint import (
+    MINT_TRANSPORT_COOLDOWN_SECONDS,
+    MINT_TRANSPORT_EXCEPTIONS,
+    MintRateGuard,
+    MintRateLimitedError,
+    fail_fast_mint_operations,
+    is_mint_rate_limited,
+    mint_cooldown_reason,
+    mint_cooldown_remaining,
+    run_mint_operation,
+)
 from .payment.lnurl import raw_send_to_lnurl
 
+# Backwards-compatible aliases for callers/tests that imported the former
+# wallet-local policy. Production modules use the public routstr.mint API.
+_MintRateGuard = MintRateGuard
+_mint_operation = run_mint_operation
+_mint_cooldown_remaining = mint_cooldown_remaining
+_mint_cooldown_reason = mint_cooldown_reason
+_is_mint_rate_limited = is_mint_rate_limited
+
 # cashu still declares Optional[X] without explicit defaults on MintInfo.
 # Under pydantic v2 those are required, but real mints omit many of them.
 # Default Optional fields to None at import time so balance fetches don't 422.
@@ -69,7 +87,8 @@ async def wallet_operation_guard() -> AsyncGenerator[None, None]:
             except BlockingIOError:
                 await _scheduler_sleep(0.05)
         depth_token = _wallet_operation_depth.set(1)
-        yield
+        async with fail_fast_mint_operations():
+            yield
     finally:
         if depth_token is not None:
             _wallet_operation_depth.reset(depth_token)
@@ -94,6 +113,20 @@ def _mints_to_inspect() -> list[str]:
     return mint_urls
 
 
+class Wallet(_CashuWallet):
+    """Cashu adapter that preserves HTTP 429 for Routstr's mint policy."""
+
+    @staticmethod
+    def raise_on_error_request(resp: httpx.Response) -> None:
+        if resp.status_code == 429:
+            raise MintRateLimitedError(
+                "Cashu mint rate limited",
+                request=resp.request,
+                response=resp,
+            )
+        _CashuWallet.raise_on_error_request(resp)
+
+
 class MintConnectionError(Exception):
     """The mint could not be reached (network transport failure).
 
@@ -116,339 +149,6 @@ class TokenConsumedError(Exception):
     """
 
 
-class MintRateLimitedError(httpx.HTTPStatusError):
-    """Typed boundary error preserving a Cashu mint's HTTP 429 response."""
-
-
-class Wallet(_CashuWallet):
-    """Cashu wallet adapter that preserves rate-limit status information.
-
-    Cashu's default response adapter converts JSON error bodies into plain
-    ``Exception`` instances before calling ``raise_for_status``. Intercept 429
-    here so Routstr's fallback and cooldown policy can use the real status
-    without unreliable message matching.
-    """
-
-    @staticmethod
-    def raise_on_error_request(resp: httpx.Response) -> None:
-        if resp.status_code == 429:
-            raise MintRateLimitedError(
-                "Cashu mint rate limited",
-                request=resp.request,
-                response=resp,
-            )
-        _CashuWallet.raise_on_error_request(resp)
-
-
-# httpx base classes cover their subclasses. HTTPStatusError is excluded on
-# purpose — that means the mint answered, just with an error status.
-_MINT_TRANSPORT_COOLDOWN_SECONDS = 30.0
-_MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS = 60.0
-_MINT_RATE_LIMIT_MAX_COOLDOWN_SECONDS = 7 * 60 * 60
-
-_TRANSPORT_EXC_TYPES: tuple[type[BaseException], ...] = (
-    httpx.NetworkError,
-    httpx.TimeoutException,
-    ConnectionError,  # refused/reset/aborted
-    socket.gaierror,  # DNS failure
-    asyncio.TimeoutError,
-)
-
-
-class _MintRateGuard:
-    """Limit concurrency and remember per-mint rate-limit cooldowns."""
-
-    _guards: dict[str, "_MintRateGuard"] = {}
-
-    @classmethod
-    def get(cls, mint_url: str) -> "_MintRateGuard":
-        concurrency = settings.mint_max_concurrency
-        guard = cls._guards.get(mint_url)
-        if guard is None or guard._max_concurrency != concurrency:
-            guard = cls(mint_url, concurrency)
-            cls._guards[mint_url] = guard
-        return guard
-
-    def __init__(self, mint_url: str, max_concurrency: int):
-        self._mint_url = mint_url
-        self._max_concurrency = max_concurrency
-        self._semaphore = (
-            asyncio.Semaphore(max_concurrency) if max_concurrency > 0 else None
-        )
-        self._cooldown_until = 0.0
-        self._cooldown_reason: str | None = None
-        self._consecutive_rate_limits = 0
-        self._needs_probe = False
-        self._probe_lock = asyncio.Lock()
-
-    def apply_cooldown(self, delay: float, *, reason: str | None = None) -> None:
-        deadline = time.monotonic() + max(0.0, delay)
-        if deadline >= self._cooldown_until:
-            self._cooldown_until = deadline
-            if reason is not None:
-                self._cooldown_reason = reason
-        elif self._cooldown_reason is None and reason is not None:
-            self._cooldown_reason = reason
-        self._needs_probe = True
-
-    def apply_rate_limit_cooldown(self, retry_after: float | None = None) -> float:
-        remaining = self.cooldown_remaining()
-        if remaining > 0 and self._cooldown_reason == "rate_limited":
-            minimum = min(
-                _MINT_RATE_LIMIT_MAX_COOLDOWN_SECONDS,
-                max(_MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS, retry_after or 0.0),
-            )
-            if minimum > remaining:
-                self.apply_cooldown(minimum, reason="rate_limited")
-                return minimum
-            return remaining
-
-        self._consecutive_rate_limits += 1
-        base = max(_MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS, retry_after or 0.0)
-        multiplier = 2 ** min(self._consecutive_rate_limits - 1, 10)
-        delay = min(_MINT_RATE_LIMIT_MAX_COOLDOWN_SECONDS, base * multiplier)
-        self.apply_cooldown(delay, reason="rate_limited")
-        return delay
-
-    def cooldown_remaining(self) -> float:
-        return max(0.0, self._cooldown_until - time.monotonic())
-
-    def cooldown_reason(self) -> str | None:
-        return self._cooldown_reason if self.cooldown_remaining() > 0 else None
-
-    async def _wait_for_cooldown(self) -> None:
-        while True:
-            deadline = self._cooldown_until
-            wait = max(0.0, deadline - time.monotonic())
-            if wait <= 0:
-                return
-            logger.debug(
-                "Mint rate guard: cooling down",
-                extra={"mint_url": self._mint_url, "wait_seconds": round(wait, 2)},
-            )
-            await asyncio.sleep(wait)
-            if self._cooldown_until <= deadline:
-                return
-
-    async def _run_probe(self, factory: Callable[[], Awaitable[Any]]) -> Any:
-        await self._wait_for_cooldown()
-        logger.warning(
-            "Mint cooldown ended; sending one probe request",
-            extra={"event": "mint_cooldown_probe_started", "mint_url": self._mint_url},
-        )
-        try:
-            result = await factory()
-        except Exception as error:
-            # Keep queued callers behind the probe.  On a rate-limit,
-            # re-apply the *same* cooldown the caller already set rather
-            # than calling apply_rate_limit_cooldown() — the probe is a
-            # recovery check, not a new request that should escalate the
-            # exponential backoff counter.
-            if _is_mint_rate_limited(error):
-                retry_after = None
-                if isinstance(error, httpx.HTTPStatusError):
-                    retry_after = _parse_retry_after(error.response.headers)
-                delay = max(
-                    _MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS,
-                    retry_after or 0.0,
-                )
-                self.apply_cooldown(delay, reason="rate_limited")
-            else:
-                self.apply_cooldown(1.0)
-            logger.warning(
-                "Mint cooldown probe failed",
-                extra={
-                    "event": "mint_cooldown_probe_failed",
-                    "mint_url": self._mint_url,
-                    "error": str(error),
-                    "error_type": type(error).__name__,
-                    "cooldown_seconds": round(self.cooldown_remaining(), 2),
-                    "consecutive_rate_limits": self._consecutive_rate_limits,
-                },
-            )
-            raise
-
-        self._needs_probe = False
-        self._cooldown_until = 0.0
-        self._cooldown_reason = None
-        self._consecutive_rate_limits = 0
-        logger.warning(
-            "Mint cooldown probe succeeded; restoring normal concurrency",
-            extra={
-                "event": "mint_cooldown_probe_succeeded",
-                "mint_url": self._mint_url,
-            },
-        )
-        return result
-
-    async def run(self, factory: Callable[[], Awaitable[Any]]) -> Any:
-        while True:
-            if self._needs_probe or self.cooldown_remaining() > 0:
-                async with self._probe_lock:
-                    if self.cooldown_remaining() > 0:
-                        self._needs_probe = True
-                    if self._needs_probe:
-                        return await self._run_probe(factory)
-                continue
-
-            if self._semaphore is None:
-                return await factory()
-            async with self._semaphore:
-                if self._needs_probe:
-                    continue
-                return await factory()
-
-
-def _mint_cooldown_remaining(mint_url: str) -> float:
-    return _MintRateGuard.get(mint_url).cooldown_remaining()
-
-
-def _mint_cooldown_reason(mint_url: str) -> str | None:
-    return _MintRateGuard.get(mint_url).cooldown_reason()
-
-
-def _is_mint_rate_limited(error: BaseException) -> bool:
-    """True if the mint returned an HTTP 429 (Too Many Requests).
-
-    Only matches ``httpx.HTTPStatusError`` with status code 429 — never
-    classifies based on the exception's message text.  Substring matching
-    on ``"rate limit"`` / ``"too many requests"`` was removed because it
-    catches unrelated errors (e.g. a 503 whose body happens to mention
-    "database rate exceeded"), which triggers unnecessary exponential
-    backoff and can block state recovery indefinitely.
-    """
-    current: BaseException | None = error
-    seen: set[int] = set()
-    while current is not None and id(current) not in seen:
-        seen.add(id(current))
-        if isinstance(current, httpx.HTTPStatusError):
-            if current.response.status_code == 429:
-                return True
-        current = current.__cause__ or current.__context__
-    return False
-
-
-async def _mint_operation(
-    factory: Callable[[], Awaitable[Any]],
-    *,
-    op_name: str = "mint_operation",
-    mint_url: str = "",
-    retry_timeouts: bool = True,
-    retry_on_rate_limit: bool = True,
-) -> Any:
-    """Run a mint operation with bounded concurrency and adaptive cooldown.
-
-    The timeout applies to each network attempt. Queueing, cooldown, and retry
-    backoff are deliberately outside it so the shipped 60-second 429 cooldown
-    is not cancelled by the 30-second operation timeout. ``factory`` must
-    return a fresh coroutine for every retry.
-
-    When ``retry_on_rate_limit`` is False a 429 is not retried in-place — the
-    cooldown is still applied to the per-mint guard (so subsequent operations on
-    that mint wait), but the exception is re-raised so the caller (typically
-    ``_request_mint_with_fallback``) can immediately try a different mint.
-    """
-    guard = _MintRateGuard.get(mint_url) if mint_url else None
-    timeout = settings.mint_operation_timeout_seconds
-    max_attempts = settings.mint_retry_max_attempts + 1
-
-    async def timed_factory() -> Any:
-        if timeout > 0:
-            return await asyncio.wait_for(factory(), timeout=timeout)
-        return await factory()
-
-    async def invoke() -> Any:
-        if guard is not None:
-            return await guard.run(timed_factory)
-        return await timed_factory()
-
-    async def run_with_retries() -> Any:
-        for attempt in range(max_attempts):
-            try:
-                return await invoke()
-            except (asyncio.TimeoutError, httpx.TimeoutException) as exc:
-                if retry_timeouts and attempt < max_attempts - 1:
-                    backoff = (2**attempt) + (time.monotonic() % 1.0)
-                    logger.warning(
-                        "Mint operation timed out, retrying",
-                        extra={
-                            "op_name": op_name,
-                            "mint_url": mint_url,
-                            "attempt": attempt + 1,
-                            "backoff_seconds": round(backoff, 2),
-                        },
-                    )
-                    await asyncio.sleep(backoff)
-                    continue
-                raise httpx.TimeoutException(
-                    f"{op_name} timed out (attempts: {attempt + 1})"
-                ) from exc
-            except Exception as exc:
-                if not _is_mint_rate_limited(exc):
-                    raise
-
-                # Apply cooldown to the guard regardless — even when we're
-                # about to re-raise for fallback, the guard must remember that
-                # this mint is rate-limited for future operations.
-                backoff = (2**attempt) + (time.monotonic() % 1.0)
-                if isinstance(exc, httpx.HTTPStatusError):
-                    retry_after = _parse_retry_after(exc.response.headers)
-                    if retry_after is not None:
-                        backoff = max(retry_after, backoff)
-                cooldown = backoff
-                if guard is not None:
-                    cooldown = guard.apply_rate_limit_cooldown(backoff)
-
-                # When the caller has a fallback strategy (trusted-mint
-                # list), re-raise immediately so the caller can try the next
-                # mint instead of waiting through this mint's cooldown.
-                if not retry_on_rate_limit:
-                    logger.warning(
-                        "Mint rate-limited, skipping retries for fallback",
-                        extra={
-                            "op_name": op_name,
-                            "mint_url": mint_url,
-                            "cooldown_seconds": round(cooldown, 2),
-                            "consecutive_rate_limits": guard._consecutive_rate_limits
-                            if guard is not None
-                            else attempt + 1,
-                        },
-                    )
-                    raise
-
-                if attempt >= max_attempts - 1:
-                    raise
-                logger.warning(
-                    "Mint rate-limited, applying cooldown",
-                    extra={
-                        "op_name": op_name,
-                        "mint_url": mint_url,
-                        "attempt": attempt + 1,
-                        "cooldown_seconds": round(cooldown, 2),
-                        "consecutive_rate_limits": guard._consecutive_rate_limits
-                        if guard is not None
-                        else attempt + 1,
-                    },
-                )
-                if guard is None:
-                    await asyncio.sleep(cooldown)
-
-        raise RuntimeError(f"{op_name}: exhausted retries unexpectedly")
-
-    return await run_with_retries()
-
-
-def _parse_retry_after(headers: Any) -> float | None:
-    """Parse a Retry-After header (delta-seconds form) into seconds."""
-    raw = headers.get("retry-after") or headers.get("Retry-After")
-    if raw is None:
-        return None
-    try:
-        return float(str(raw).strip())
-    except (TypeError, ValueError):
-        return None
-
-
 def is_source_mint_connection_error(error: BaseException) -> bool:
     seen: set[int] = set()
     current: BaseException | None = error
@@ -475,7 +175,7 @@ def is_mint_connection_error(error: BaseException) -> bool:
             return False
         if isinstance(current, MintConnectionError):
             return True
-        if isinstance(current, _TRANSPORT_EXC_TYPES):
+        if isinstance(current, MINT_TRANSPORT_EXCEPTIONS):
             return True
         current = current.__cause__ or current.__context__
     return False
@@ -519,7 +219,7 @@ def classify_redemption_error(
             "The mint that issued this Cashu token is unreachable; the token cannot be redeemed at another mint",
             "cashu_source_mint_unreachable",
         )
-    if _is_mint_rate_limited(error):
+    if is_mint_rate_limited(error):
         return (
             "mint_rate_limited",
             503,
@@ -605,14 +305,14 @@ async def _redeem_same_mint(
     drifts insolvent.
     """
     try:
-        await _mint_operation(
+        await run_mint_operation(
             lambda: wallet.load_mint(keyset_id=token_obj.keysets[0]),
             op_name="redeem_load_mint",
             mint_url=token_obj.mint,
         )
         wallet.verify_proofs_dleq(token_obj.proofs)
         input_fees = wallet.get_fees_for_proofs(token_obj.proofs)
-        await _mint_operation(
+        await run_mint_operation(
             lambda: wallet.split(proofs=token_obj.proofs, amount=0, include_fees=True),
             op_name="redeem_split",
             mint_url=token_obj.mint,
@@ -655,7 +355,7 @@ async def recieve_token(
         destinations = list(
             dict.fromkeys([settings.primary_mint, *settings.cashu_mints])
         )
-        logger.warning(
+        logger.info(
             "Cashu cross-mint swap required",
             extra={
                 "event": "cashu_swap_started",
@@ -667,7 +367,7 @@ async def recieve_token(
         )
         return await swap_to_trusted_mint(token_obj, wallet)
 
-    logger.warning(
+    logger.info(
         "Trying same-mint Cashu redemption",
         extra={
             "event": "cashu_same_mint_redemption",
@@ -769,12 +469,12 @@ async def find_trusted_mint_with_funds(
 
     balances: dict[str, int] = {}
     for mint_url in candidates:
-        if _mint_cooldown_remaining(mint_url) > 0:
+        if mint_cooldown_remaining(mint_url) > 0:
             continue
         try:
             wallet = await get_wallet(mint_url, unit, retry_on_rate_limit=False)
         except Exception as error:
-            if is_mint_connection_error(error) or _is_mint_rate_limited(error):
+            if is_mint_connection_error(error) or is_mint_rate_limited(error):
                 balances[mint_url] = 0
                 continue
             raise
@@ -819,6 +519,17 @@ def _net_minted_amount(amount_msat: int, token_unit: str, fees: int) -> int:
     return int(remaining_msat)
 
 
+def _melt_definitively_failed(error: Exception) -> bool:
+    """Return whether the mint authoritatively rejected the Lightning payment.
+
+    Cashu releases the reserved proofs for these responses, so the token remains
+    reusable. Transport failures and unknown errors are deliberately excluded:
+    after dispatch their payment outcome may still be pending or paid.
+    """
+    message = str(error).strip()
+    return message.lower() == "could not pay invoice." or "(Code: 20004)" in message
+
+
 def _melt_insufficient_shortfall(error: Exception) -> int | None:
     """
     Classify a melt failure: return the observed shortfall (in the token unit)
@@ -871,7 +582,7 @@ async def _request_mint_with_fallback(
             f"Token value is too small after fee deduction or unit conversion."
         )
     candidates = list(dict.fromkeys([settings.primary_mint, *settings.cashu_mints]))
-    logger.warning(
+    logger.info(
         "Trying trusted destination mints",
         extra={
             "event": "cashu_destination_candidates",
@@ -883,7 +594,7 @@ async def _request_mint_with_fallback(
     )
     tried: list[str] = []
     for candidate_index, mint_url in enumerate(candidates, start=1):
-        cooldown = _mint_cooldown_remaining(mint_url)
+        cooldown = mint_cooldown_remaining(mint_url)
         if cooldown > 0:
             tried.append(f"{mint_url}: cooling down")
             logger.warning(
@@ -898,7 +609,7 @@ async def _request_mint_with_fallback(
                 },
             )
             continue
-        logger.warning(
+        logger.info(
             "Trying destination mint",
             extra={
                 "event": "cashu_destination_attempt",
@@ -917,13 +628,13 @@ async def _request_mint_with_fallback(
                     settings.primary_mint_unit,
                     retry_on_rate_limit=False,
                 )
-            quote = await _mint_operation(
+            quote = await run_mint_operation(
                 lambda: wallet.request_mint(amount),
                 op_name=op_name,
                 mint_url=mint_url,
                 retry_on_rate_limit=False,
             )
-            logger.warning(
+            logger.info(
                 "Destination mint selected",
                 extra={
                     "event": "cashu_destination_selected",
@@ -937,12 +648,12 @@ async def _request_mint_with_fallback(
         except Exception as error:
             tried.append(f"{mint_url}: {type(error).__name__}")
             connection_failure = is_mint_connection_error(error)
-            rate_limited = _is_mint_rate_limited(error)
+            rate_limited = is_mint_rate_limited(error)
             if not connection_failure and not rate_limited:
                 raise
             if connection_failure:
-                _MintRateGuard.get(mint_url).apply_cooldown(
-                    _MINT_TRANSPORT_COOLDOWN_SECONDS, reason="unreachable"
+                MintRateGuard.get(mint_url).apply_cooldown(
+                    MINT_TRANSPORT_COOLDOWN_SECONDS, reason="unreachable"
                 )
             logger.warning(
                 "Destination mint failed",
@@ -993,7 +704,7 @@ async def _calculate_swap_amount(
 
     if token_mint_url == settings.primary_mint:
         logger.info(
-            "swap_to_primary_mint: skipping fee estimation (same mint)",
+            "swap_to_trusted_mint: skipping fee estimation (same mint)",
             extra={"minted_amount": receive_amount},
         )
         return int(receive_amount)
@@ -1005,7 +716,7 @@ async def _calculate_swap_amount(
     # logs.  Guard early with full diagnostic context instead.
     if receive_amount <= 0:
         logger.error(
-            "swap_to_primary_mint: receive_amount is zero or negative, cannot estimate fees",
+            "swap_to_trusted_mint: receive_amount is zero or negative, cannot estimate fees",
             extra={
                 "amount_msat": amount_msat,
                 "token_unit": token_unit,
@@ -1022,7 +733,7 @@ async def _calculate_swap_amount(
         )
 
     logger.info(
-        "swap_to_primary_mint: estimating fees",
+        "swap_to_trusted_mint: estimating fees",
         extra={
             "dummy_amount": receive_amount,
             "unit": settings.primary_mint_unit,
@@ -1040,7 +751,7 @@ async def _calculate_swap_amount(
             primary_wallet=primary_wallet,
         )
         stage = "source_fee_quote"
-        dummy_melt_quote = await _mint_operation(
+        dummy_melt_quote = await run_mint_operation(
             lambda: token_wallet.melt_quote(dummy_mint_quote.request),
             op_name="swap_fee_est_melt_quote",
             mint_url=token_mint_url,
@@ -1055,7 +766,7 @@ async def _calculate_swap_amount(
             raise ValueError(f"Fees ({total_fees} {token_unit}) exceed token amount")
 
         logger.info(
-            "swap_to_primary_mint: fee estimation result",
+            "swap_to_trusted_mint: fee estimation result",
             extra={
                 "token_amount_sat": _msats_to_sats(amount_msat),
                 "estimated_fee": total_fees,
@@ -1105,10 +816,62 @@ async def _calculate_swap_amount(
         raise ValueError(f"Failed to estimate fees: {e}") from e
 
 
+async def _reconcile_ambiguous_melt(
+    wallet: Wallet, quote_id: str, proofs: list[Proof]
+) -> bool:
+    """Confirm a dispatched melt is paid or conservatively mark it ambiguous.
+
+    A PAID quote is authoritative and does not require a proof-state lookup.
+    Every other immediate snapshot remains unsafe to retry: an in-flight
+    Lightning payment can still move UNPAID/UNSPENT to PENDING or PAID after the
+    cancelled HTTP request returns.
+    """
+    try:
+        quote = await run_mint_operation(
+            lambda: wallet.get_melt_quote(quote_id),
+            op_name="reconcile_swap_melt_quote",
+            mint_url=str(wallet.url),
+            retry_timeouts=False,
+        )
+    except Exception as error:
+        raise TokenConsumedError(
+            "Source melt outcome is unknown; reconciliation required"
+        ) from error
+
+    if quote is not None and quote.state == MeltQuoteState.paid:
+        return True
+
+    try:
+        proof_response = await run_mint_operation(
+            lambda: wallet.check_proof_state(proofs),
+            op_name="reconcile_swap_proofs",
+            mint_url=str(wallet.url),
+            retry_timeouts=False,
+        )
+        proof_states = [state.state.value for state in proof_response.states]
+    except Exception:
+        proof_states = []
+
+    quote_state = getattr(getattr(quote, "state", None), "value", "unknown")
+    raise TokenConsumedError(
+        "Source melt outcome is ambiguous; reconciliation required "
+        f"(quote_state={quote_state}, proof_states={proof_states})"
+    )
+
+
+async def _confirm_melt_paid(
+    wallet: Wallet, quote_id: str, proofs: list[Proof], response: object
+) -> bool:
+    """Accept a melt response only when PAID is explicit or reconciled."""
+    if getattr(response, "state", None) == MeltQuoteState.paid:
+        return True
+    return await _reconcile_ambiguous_melt(wallet, quote_id, proofs)
+
+
 async def swap_to_trusted_mint(
     token_obj: Token, token_wallet: Wallet
 ) -> tuple[int, str, str]:
-    logger.warning(
+    logger.info(
         "Starting Cashu cross-mint swap",
         extra={
             "event": "cashu_swap_started",
@@ -1135,7 +898,7 @@ async def swap_to_trusted_mint(
     # NUT-02 input fee still applies; _redeem_same_mint accounts for it.
     if token_obj.mint == settings.primary_mint:
         logger.info(
-            "swap_to_primary_mint: token already on primary mint, skipping swap",
+            "swap_to_trusted_mint: token already on primary mint, skipping swap",
             extra={
                 "mint": token_obj.mint,
                 "amount": token_amount,
@@ -1166,7 +929,7 @@ async def swap_to_trusted_mint(
         attempt += 1
         if minted_amount <= 0:
             logger.error(
-                "swap_to_primary_mint: minted_amount is zero or negative before requesting quote",
+                "swap_to_trusted_mint: minted_amount is zero or negative before requesting quote",
                 extra={
                     "minted_amount": minted_amount,
                     "attempt": attempt,
@@ -1188,7 +951,7 @@ async def swap_to_trusted_mint(
             primary_wallet=primary_wallet,
         )
         logger.info(
-            "swap_to_primary_mint: mint quote received",
+            "swap_to_trusted_mint: mint quote received",
             extra={
                 "mint_quote_id": mint_quote.quote,
                 "attempt": attempt,
@@ -1196,7 +959,7 @@ async def swap_to_trusted_mint(
             },
         )
 
-        logger.warning(
+        logger.info(
             "Requesting melt quote from source mint",
             extra={
                 "event": "cashu_source_melt_quote_attempt",
@@ -1206,7 +969,7 @@ async def swap_to_trusted_mint(
             },
         )
         try:
-            melt_quote = await _mint_operation(
+            melt_quote = await run_mint_operation(
                 lambda: token_wallet.melt_quote(mint_quote.request),
                 op_name="swap_melt_quote",
                 mint_url=token_obj.mint,
@@ -1232,7 +995,7 @@ async def swap_to_trusted_mint(
         input_fees = token_wallet.get_fees_for_proofs(token_obj.proofs)
         total_needed = melt_quote.amount + melt_quote.fee_reserve + input_fees
         logger.info(
-            "swap_to_primary_mint: melt quote received",
+            "swap_to_trusted_mint: melt quote received",
             extra={
                 "melt_quote_id": melt_quote.quote,
                 "melt_amount": melt_quote.amount,
@@ -1252,7 +1015,7 @@ async def swap_to_trusted_mint(
             )
             if attempt >= _MAX_SWAP_ATTEMPTS or recomputed <= 0:
                 logger.warning(
-                    "swap_to_primary_mint: insufficient token amount for melt fees",
+                    "swap_to_trusted_mint: insufficient token amount for melt fees",
                     extra={
                         "token_amount": token_amount,
                         "melt_amount": melt_quote.amount,
@@ -1269,7 +1032,7 @@ async def swap_to_trusted_mint(
                     f"(amount: {melt_quote.amount} + fee: {melt_quote.fee_reserve} + input_fees: {input_fees})"
                 )
             logger.warning(
-                "swap_to_primary_mint: melt quote exceeds token amount, retrying",
+                "swap_to_trusted_mint: melt quote exceeds token amount, retrying",
                 extra={
                     "total_needed": total_needed,
                     "token_amount": token_amount,
@@ -1281,7 +1044,7 @@ async def swap_to_trusted_mint(
             continue
 
         try:
-            _ = await _mint_operation(
+            melt_response = await run_mint_operation(
                 lambda: token_wallet.melt(
                     proofs=token_obj.proofs,
                     invoice=mint_quote.request,
@@ -1292,36 +1055,45 @@ async def swap_to_trusted_mint(
                 mint_url=token_obj.mint,
                 retry_timeouts=False,
             )
+            await _confirm_melt_paid(
+                token_wallet, melt_quote.quote, token_obj.proofs, melt_response
+            )
         except Exception as e:
-            # A down mint won't fix itself by retrying with a smaller amount.
-            if is_mint_connection_error(e):
-                logger.error(
-                    "Source mint became unreachable during melt",
-                    extra={
-                        "event": "cashu_source_mint_unreachable",
-                        "stage": "source_melt",
-                        "error": str(e),
-                        "error_type": type(e).__name__,
-                        "source_mint": token_obj.mint,
-                        "destination_mint": dest_mint_url,
-                        "attempt": attempt,
-                    },
-                )
-                raise SourceMintConnectionError(
-                    "Issuing Cashu mint is unreachable"
-                ) from e
             shortfall = _melt_insufficient_shortfall(e)
-            recomputed = 0
-            if shortfall is not None:
-                observed_extra_fee += shortfall
-                recomputed = _net_minted_amount(
-                    amount_msat,
-                    token_obj.unit,
-                    melt_quote.fee_reserve + input_fees + observed_extra_fee,
-                )
-            if shortfall is None or attempt >= _MAX_SWAP_ATTEMPTS or recomputed <= 0:
+            if shortfall is None:
+                if isinstance(e, TokenConsumedError):
+                    raise
+                if _melt_definitively_failed(e):
+                    raise ValueError(
+                        f"Failed to melt token from foreign mint {token_obj.mint}: {e}"
+                    ) from e
+                if is_mint_connection_error(e):
+                    await _reconcile_ambiguous_melt(
+                        token_wallet, melt_quote.quote, token_obj.proofs
+                    )
+                    logger.info(
+                        "Source melt reconciled as paid; minting on destination",
+                        extra={
+                            "event": "cashu_source_melt_reconciled_paid",
+                            "source_mint": token_obj.mint,
+                            "destination_mint": dest_mint_url,
+                            "melt_quote_id": melt_quote.quote,
+                        },
+                    )
+                    break
+                raise TokenConsumedError(
+                    "Source melt failed after dispatch; outcome requires reconciliation"
+                ) from e
+
+            observed_extra_fee += shortfall
+            recomputed = _net_minted_amount(
+                amount_msat,
+                token_obj.unit,
+                melt_quote.fee_reserve + input_fees + observed_extra_fee,
+            )
+            if attempt >= _MAX_SWAP_ATTEMPTS or recomputed <= 0:
                 logger.error(
-                    "swap_to_primary_mint: melt failed",
+                    "swap_to_trusted_mint: melt failed",
                     extra={
                         "error": str(e),
                         "error_type": type(e).__name__,
@@ -1336,7 +1108,7 @@ async def swap_to_trusted_mint(
                     f"Failed to melt token from foreign mint {token_obj.mint}: {e}"
                 ) from e
             logger.warning(
-                "swap_to_primary_mint: mint demanded more than quoted at melt, retrying",
+                "swap_to_trusted_mint: mint demanded more than quoted at melt, retrying",
                 extra={
                     "shortfall": shortfall,
                     "retry_minted_amount": recomputed,
@@ -1348,7 +1120,7 @@ async def swap_to_trusted_mint(
 
         break
 
-    logger.warning(
+    logger.info(
         "Source melt succeeded; minting on destination",
         extra={
             "event": "cashu_destination_mint_attempt",
@@ -1361,9 +1133,9 @@ async def swap_to_trusted_mint(
     await dest_wallet.load_proofs(reload=True)
     pre_mint_balance = dest_wallet.available_balance.amount
     try:
-        _ = await _mint_operation(
+        _ = await run_mint_operation(
             lambda: dest_wallet.mint(minted_amount, quote_id=mint_quote.quote),
-            op_name="swap_mint_on_primary",
+            op_name="swap_mint_on_destination",
             mint_url=dest_mint_url,
             retry_timeouts=False,
         )
@@ -1373,7 +1145,7 @@ async def swap_to_trusted_mint(
             # bump_secret_derivation ran locally. Recover orphaned proofs and
             # advance the counter so the next request derives fresh secrets.
             logger.warning(
-                "swap_to_primary_mint: outputs already signed — recovering orphaned proofs",
+                "swap_to_trusted_mint: outputs already signed — recovering orphaned proofs",
                 extra={
                     "mint_quote_id": mint_quote.quote,
                     "minted_amount": minted_amount,
@@ -1388,7 +1160,7 @@ async def swap_to_trusted_mint(
                 post_recovery_balance = dest_wallet.available_balance.amount
                 balance_gained = post_recovery_balance - pre_mint_balance
                 logger.info(
-                    "swap_to_primary_mint: recovery scan completed",
+                    "swap_to_trusted_mint: recovery scan completed",
                     extra={
                         "pre_mint_balance": pre_mint_balance,
                         "post_recovery_balance": post_recovery_balance,
@@ -1411,7 +1183,7 @@ async def swap_to_trusted_mint(
                 raise
             except Exception as recovery_err:
                 logger.error(
-                    "swap_to_primary_mint: recovery failed",
+                    "swap_to_trusted_mint: recovery failed",
                     extra={"error": str(recovery_err)},
                 )
                 raise TokenConsumedError(
@@ -1419,7 +1191,7 @@ async def swap_to_trusted_mint(
                 ) from e
         else:
             logger.error(
-                "swap_to_primary_mint: mint on primary failed after successful melt",
+                "swap_to_trusted_mint: mint on primary failed after successful melt",
                 extra={
                     "error": str(e),
                     "error_type": type(e).__name__,
@@ -1432,7 +1204,7 @@ async def swap_to_trusted_mint(
                 "Mint on primary failed after successful melt"
             ) from e
 
-    logger.warning(
+    logger.info(
         "Cashu cross-mint swap completed",
         extra={
             "event": "cashu_swap_completed",
@@ -1595,13 +1367,13 @@ async def get_wallet(
             now = time.monotonic()
             last = _wallet_last_load.get(id)
             if last is None or now - last >= _WALLOAD_RELOAD_MIN_INTERVAL_SECONDS:
-                await _mint_operation(
+                await run_mint_operation(
                     lambda: _wallets[id].load_mint(),
                     op_name="load_mint",
                     mint_url=mint_url,
                     retry_on_rate_limit=retry_on_rate_limit,
                 )
-                await _mint_operation(
+                await run_mint_operation(
                     lambda: _wallets[id].load_proofs(reload=True),
                     op_name="load_proofs",
                     mint_url=mint_url,
@@ -1640,7 +1412,7 @@ async def slow_filter_spend_proofs(
     batch_size = 1000
     for i in range(0, len(proofs), batch_size):
         pb = proofs[i : i + batch_size]
-        proof_states = await _mint_operation(
+        proof_states = await run_mint_operation(
             lambda: wallet.check_proof_state(pb),
             op_name="check_proof_state",
             mint_url=str(wallet.url),
@@ -1652,12 +1424,7 @@ async def slow_filter_spend_proofs(
             else:
                 _spent_proofs.append(proof)
     if _spent_proofs:
-        await _mint_operation(
-            lambda: wallet.set_reserved_for_send(_spent_proofs, reserved=True),
-            op_name="set_reserved_spent_proofs",
-            mint_url=str(wallet.url),
-            retry_timeouts=False,
-        )
+        await wallet.set_reserved_for_send(_spent_proofs, reserved=True)
     return _proofs
 
 
@@ -1686,7 +1453,7 @@ async def _get_supported_mint_units(mint_url: str) -> list[str]:
         return cached[1]
 
     wallet = await get_wallet(mint_url, settings.primary_mint_unit, load=False)
-    keysets = await _mint_operation(
+    keysets = await run_mint_operation(
         lambda: wallet._get_keysets(),
         op_name="get_mint_keysets",
         mint_url=mint_url,
@@ -1750,7 +1517,7 @@ async def fetch_all_balances(
                 mint_units[mint_url] = await _get_supported_mint_units(mint_url)
             except Exception as error:
                 connection_failure = is_mint_connection_error(error)
-                rate_limited = _is_mint_rate_limited(error)
+                rate_limited = is_mint_rate_limited(error)
                 error_code = (
                     "rate_limited"
                     if rate_limited
@@ -1759,12 +1526,12 @@ async def fetch_all_balances(
                     else "mint_error"
                 )
                 if connection_failure:
-                    _MintRateGuard.get(mint_url).apply_cooldown(
+                    MintRateGuard.get(mint_url).apply_cooldown(
                         _BALANCE_FETCH_RETRY_SECONDS, reason="unreachable"
                     )
                 retry_delay = max(
                     _BALANCE_FETCH_RETRY_SECONDS,
-                    _mint_cooldown_remaining(mint_url),
+                    mint_cooldown_remaining(mint_url),
                 )
                 discovery_errors.append(
                     _balance_error(
@@ -1819,9 +1586,9 @@ async def fetch_all_balances(
                     retry_after_seconds=failure[0] - now,
                 )
 
-            cooldown = _mint_cooldown_remaining(mint_url)
+            cooldown = mint_cooldown_remaining(mint_url)
             if cooldown > 0:
-                error_code = _mint_cooldown_reason(mint_url) or "cooldown"
+                error_code = mint_cooldown_reason(mint_url) or "cooldown"
                 error = {
                     "rate_limited": "Mint is rate limited",
                     "unreachable": "Mint is unreachable",
@@ -1846,7 +1613,7 @@ async def fetch_all_balances(
                     proofs = await slow_filter_spend_proofs(proofs, wallet)
             except Exception as error:
                 connection_failure = is_mint_connection_error(error)
-                rate_limited = _is_mint_rate_limited(error)
+                rate_limited = is_mint_rate_limited(error)
                 error_code = (
                     "rate_limited"
                     if rate_limited
@@ -1855,16 +1622,16 @@ async def fetch_all_balances(
                     else "mint_error"
                 )
                 if rate_limited:
-                    _MintRateGuard.get(mint_url).apply_rate_limit_cooldown(
+                    MintRateGuard.get(mint_url).apply_rate_limit_cooldown(
                         _BALANCE_FETCH_RETRY_SECONDS
                     )
                 elif connection_failure:
-                    _MintRateGuard.get(mint_url).apply_cooldown(
+                    MintRateGuard.get(mint_url).apply_cooldown(
                         _BALANCE_FETCH_RETRY_SECONDS, reason=error_code
                     )
                 retry_delay = max(
                     _BALANCE_FETCH_RETRY_SECONDS,
-                    _mint_cooldown_remaining(mint_url),
+                    mint_cooldown_remaining(mint_url),
                 )
                 _balance_fetch_failures[key] = (
                     time.monotonic() + retry_delay,

tests/integration/test_insufficient_balance.py

@@ -208,25 +208,30 @@ async def test_pay_for_request_succeeds_when_balance_equals_cost(
 
 
 @pytest.mark.asyncio
-async def test_five_percent_mint_fallback_headroom_is_admitted_and_reserved(
+async def test_full_model_maximum_is_required_and_reserved(
     integration_session: AsyncSession,
 ) -> None:
     from routstr.auth import pay_for_request, validate_bearer_key
-    from routstr.payment.helpers import apply_mint_fee_allowance
 
-    key = _key(balance=95_000)
-    integration_session.add(key)
+    short_key = _key(balance=95_000)
+    exact_key = _key(balance=100_000)
+    integration_session.add(short_key)
+    integration_session.add(exact_key)
     await integration_session.commit()
 
-    admission_cost = apply_mint_fee_allowance(100_000)
-    validated = await validate_bearer_key(
-        f"sk-{key.hashed_key}", integration_session, min_cost=admission_cost
-    )
-    await pay_for_request(validated, admission_cost, integration_session)
+    with pytest.raises(HTTPException) as insufficient:
+        await validate_bearer_key(
+            f"sk-{short_key.hashed_key}", integration_session, min_cost=100_000
+        )
+    assert insufficient.value.status_code == 402
 
-    await integration_session.refresh(key)
-    assert admission_cost == 95_000
-    assert key.reserved_balance == 95_000
+    validated = await validate_bearer_key(
+        f"sk-{exact_key.hashed_key}", integration_session, min_cost=100_000
+    )
+    await pay_for_request(validated, 100_000, integration_session)
+
+    await integration_session.refresh(exact_key)
+    assert exact_key.reserved_balance == 100_000
 
 
 # ---------------------------------------------------------------------------
@@ -288,7 +293,7 @@ async def test_http_402_response_shape_on_insufficient_balance(
     error = body["detail"]["error"]
     assert error["code"] == "insufficient_balance"
     assert error["type"] == "insufficient_quota"
-    assert "591.744 sats (591744 msats) required" in error["message"]
+    assert "622.888 sats (622888 msats) required" in error["message"]
     assert "20.32 sats (20320 msats) available" in error["message"]
 
     # Balance must be completely untouched

tests/integration/test_swap_fee_retry.py

@@ -20,6 +20,7 @@ from collections.abc import Callable
 from unittest.mock import AsyncMock, Mock, patch
 
 import pytest
+from cashu.core.base import MeltQuoteState
 from httpx import AsyncClient, Response
 
 from routstr.core.settings import settings
@@ -81,7 +82,9 @@ def _make_swap_mocks(
             quote=f"melt_quote_{invoice}", amount=invoice, fee_reserve=_next_fee()
         )
     )
-    mock_token_wallet.melt = AsyncMock(return_value=Mock())
+    mock_token_wallet.melt = AsyncMock(
+        return_value=Mock(state=MeltQuoteState.paid)
+    )
 
     return mock_token, mock_token_wallet, mock_primary_wallet
 
@@ -144,7 +147,7 @@ async def test_topup_retries_when_melt_demands_more_than_quoted(
             "Mint Error: not enough inputs provided for melt. "
             "Provided: 179, needed: 180 (Code: 11000)"
         ),
-        Mock(),
+        Mock(state=MeltQuoteState.paid),
     ]
 
     response = await _post_topup(

tests/unit/test_fetch_all_balances.py

@@ -161,7 +161,7 @@ async def test_fetch_all_balances_backs_off_after_connection_failure() -> None:
         patch.object(settings, "primary_mint", "http://mint:3338"),
         patch("routstr.wallet.get_wallet", get_wallet),
         patch("routstr.wallet.db.create_session", _fake_session),
-        patch("routstr.wallet.time.monotonic", return_value=10),
+        patch("routstr.mint.time.monotonic", return_value=10),
         patch("routstr.wallet.logger.warning") as warning,
     ):
         first = await fetch_all_balances(units=["sat"])
@@ -180,7 +180,7 @@ async def test_fetch_all_balances_backs_off_after_connection_failure() -> None:
         patch.object(settings, "primary_mint", "http://mint:3338"),
         patch("routstr.wallet.get_wallet", get_wallet),
         patch("routstr.wallet.db.create_session", _fake_session),
-        patch("routstr.wallet.time.monotonic", return_value=71),
+        patch("routstr.mint.time.monotonic", return_value=71),
         patch("routstr.wallet.logger.warning"),
     ):
         await fetch_all_balances(units=["sat"])
@@ -219,7 +219,7 @@ async def test_balance_failure_applies_mint_cooldown_to_other_units() -> None:
         patch.object(settings, "primary_mint", mint),
         patch("routstr.wallet.get_wallet", get_wallet),
         patch("routstr.wallet.db.create_session", _fake_session),
-        patch("routstr.wallet.time.monotonic", return_value=10),
+        patch("routstr.mint.time.monotonic", return_value=10),
         patch("routstr.wallet.logger.warning") as warning,
     ):
         details, *_ = await fetch_all_balances(units=["sat", "msat"])

tests/unit/test_lightning_settlement.py

@@ -155,6 +155,7 @@ async def test_non_pending_invoice_is_not_minted() -> None:
 
     get_wallet.assert_not_awaited()
     session.commit.assert_awaited_once()
+    assert _invoice_settlement_locks == {}
 
 
 @pytest.mark.asyncio
@@ -212,3 +213,4 @@ async def test_concurrent_invoice_checks_finalize_once_in_process() -> None:
 
     assert invoice.status == "paid"
     finalize.assert_awaited_once()
+    assert _invoice_settlement_locks == {}

tests/unit/test_lnurl_melt_timeout.py

@@ -1,70 +1,127 @@
-"""raw_send_to_lnurl() must not hang forever on an unresponsive mint.
-
-The Cashu library issues POST /v1/melt/bolt11 with timeout=None, so a hung
-mint would block the melt (and the payout loop) indefinitely. raw_send_to_lnurl
-now wraps wallet.melt() in asyncio.wait_for(MELT_TIMEOUT_SECONDS) and surfaces a
-timeout as LNURLError instead of hanging.
-"""
+"""LNURL melt attempts must not misclassify ambiguous payment outcomes."""
 
 import asyncio
+from typing import Any
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
+from cashu.core.base import MeltQuoteState
 
-from routstr.payment import lnurl
+from routstr.core.settings import settings
 from routstr.payment.lnurl import LNURLError, raw_send_to_lnurl
 
+LNURL_DATA = {
+    "callback_url": "https://ln.tld/cb",
+    "min_sendable": 1_000,
+    "max_sendable": 100_000_000,
+}
 
-@pytest.mark.asyncio
-async def test_raw_send_to_lnurl_times_out_on_hung_melt() -> None:
+
+def _wallet() -> tuple[MagicMock, list[MagicMock]]:
     proofs = [MagicMock(amount=1000)]
-
-    wallet = MagicMock()
+    wallet = MagicMock(url="https://mint.test")
     wallet.melt_quote = AsyncMock(return_value=MagicMock(fee_reserve=1, quote="q"))
     wallet.select_to_send = AsyncMock(return_value=(proofs, None))
+    return wallet, proofs
+
+
+def _lnurl_patches() -> tuple[Any, Any]:
+    return (
+        patch(
+            "routstr.payment.lnurl.get_lnurl_data",
+            AsyncMock(return_value=LNURL_DATA),
+        ),
+        patch(
+            "routstr.payment.lnurl.get_lnurl_invoice",
+            AsyncMock(return_value=("lnbc1...", {})),
+        ),
+    )
+
+
+@pytest.mark.asyncio
+async def test_raw_send_to_lnurl_timeout_keeps_unpaid_outcome_ambiguous() -> None:
+    wallet, proofs = _wallet()
 
     async def _hang(**kwargs: object) -> None:
-        await asyncio.sleep(5)  # far longer than the patched timeout
+        await asyncio.sleep(5)
 
     wallet.melt = AsyncMock(side_effect=_hang)
+    wallet.get_melt_quote = AsyncMock(
+        return_value=MagicMock(state=MeltQuoteState.unpaid)
+    )
+    data_patch, invoice_patch = _lnurl_patches()
 
-    lnurl_data = {
-        "callback_url": "https://ln.tld/cb",
-        "min_sendable": 1_000,
-        "max_sendable": 100_000_000,
-    }
-
-    with patch.object(lnurl, "MELT_TIMEOUT_SECONDS", 0.05), patch(
-        "routstr.payment.lnurl.get_lnurl_data", AsyncMock(return_value=lnurl_data)
-    ), patch(
-        "routstr.payment.lnurl.get_lnurl_invoice",
-        AsyncMock(return_value=("lnbc1...", {})),
+    with (
+        patch.object(settings, "mint_operation_timeout_seconds", 0.05),
+        patch.object(settings, "mint_retry_max_attempts", 0),
+        data_patch,
+        invoice_patch,
+        pytest.raises(LNURLError, match="outcome is ambiguous"),
     ):
-        with pytest.raises(LNURLError, match="Melt timed out"):
-            await raw_send_to_lnurl(wallet, proofs, "owner@ln.tld", "sat", amount=1000)
+        await raw_send_to_lnurl(wallet, proofs, "owner@ln.tld", "sat", amount=1000)
+
+    wallet.get_melt_quote.assert_awaited_once_with("q")
+    wallet.set_reserved_for_melt.assert_not_called()
 
 
 @pytest.mark.asyncio
-async def test_raw_send_to_lnurl_succeeds_within_timeout() -> None:
-    """A prompt melt still returns the net amount, unaffected by the guard."""
-    proofs = [MagicMock(amount=1000)]
+async def test_raw_send_to_lnurl_timeout_reconciled_paid_is_success() -> None:
+    wallet, proofs = _wallet()
 
-    wallet = MagicMock()
-    wallet.melt_quote = AsyncMock(return_value=MagicMock(fee_reserve=1, quote="q"))
-    wallet.select_to_send = AsyncMock(return_value=(proofs, None))
-    wallet.melt = AsyncMock(return_value=MagicMock())
+    async def _hang(**kwargs: object) -> None:
+        await asyncio.sleep(5)
 
-    lnurl_data = {
-        "callback_url": "https://ln.tld/cb",
-        "min_sendable": 1_000,
-        "max_sendable": 100_000_000,
-    }
+    wallet.melt = AsyncMock(side_effect=_hang)
+    wallet.get_melt_quote = AsyncMock(
+        return_value=MagicMock(state=MeltQuoteState.paid)
+    )
+    data_patch, invoice_patch = _lnurl_patches()
 
-    with patch.object(lnurl, "MELT_TIMEOUT_SECONDS", 5), patch(
-        "routstr.payment.lnurl.get_lnurl_data", AsyncMock(return_value=lnurl_data)
-    ), patch(
-        "routstr.payment.lnurl.get_lnurl_invoice",
-        AsyncMock(return_value=("lnbc1...", {})),
+    with (
+        patch.object(settings, "mint_operation_timeout_seconds", 0.05),
+        patch.object(settings, "mint_retry_max_attempts", 0),
+        data_patch,
+        invoice_patch,
+    ):
+        paid = await raw_send_to_lnurl(
+            wallet, proofs, "owner@ln.tld", "sat", amount=1000
+        )
+
+    assert paid > 0
+    wallet.get_melt_quote.assert_awaited_once_with("q")
+
+
+@pytest.mark.asyncio
+async def test_raw_send_to_lnurl_pending_response_stays_ambiguous() -> None:
+    wallet, proofs = _wallet()
+    wallet.melt = AsyncMock(return_value=MagicMock(state=MeltQuoteState.pending))
+    wallet.get_melt_quote = AsyncMock(
+        return_value=MagicMock(state=MeltQuoteState.pending)
+    )
+    data_patch, invoice_patch = _lnurl_patches()
+
+    with (
+        patch.object(settings, "mint_operation_timeout_seconds", 5),
+        data_patch,
+        invoice_patch,
+        pytest.raises(LNURLError, match="outcome is ambiguous"),
+    ):
+        await raw_send_to_lnurl(wallet, proofs, "owner@ln.tld", "sat", amount=1000)
+
+    wallet.get_melt_quote.assert_awaited_once_with("q")
+
+
+@pytest.mark.asyncio
+async def test_raw_send_to_lnurl_succeeds_on_explicit_paid_response() -> None:
+    wallet, proofs = _wallet()
+    wallet.melt = AsyncMock(return_value=MagicMock(state=MeltQuoteState.paid))
+    wallet.get_melt_quote = AsyncMock()
+    data_patch, invoice_patch = _lnurl_patches()
+
+    with (
+        patch.object(settings, "mint_operation_timeout_seconds", 5),
+        data_patch,
+        invoice_patch,
     ):
         paid = await raw_send_to_lnurl(
             wallet, proofs, "owner@ln.tld", "sat", amount=1000
@@ -72,3 +129,4 @@ async def test_raw_send_to_lnurl_succeeds_within_timeout() -> None:
 
     assert paid > 0
     wallet.melt.assert_awaited_once()
+    wallet.get_melt_quote.assert_not_awaited()

tests/unit/test_melt_reconciliation.py

@@ -0,0 +1,91 @@
+from unittest.mock import AsyncMock, Mock
+
+import pytest
+from cashu.core.base import MeltQuoteState, ProofSpentState
+
+from routstr.wallet import (
+    TokenConsumedError,
+    _confirm_melt_paid,
+    _reconcile_ambiguous_melt,
+)
+
+
+@pytest.mark.asyncio
+async def test_paid_quote_is_authoritative_when_proof_lookup_would_fail() -> None:
+    wallet = Mock(
+        url="http://source-mint:3338",
+        get_melt_quote=AsyncMock(return_value=Mock(state=MeltQuoteState.paid)),
+        check_proof_state=AsyncMock(side_effect=RuntimeError("proof API unavailable")),
+    )
+
+    assert await _reconcile_ambiguous_melt(wallet, "quote-1", [Mock()]) is True
+    wallet.check_proof_state.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_timeout_snapshot_unpaid_unspent_remains_non_retryable() -> None:
+    wallet = Mock(
+        url="http://source-mint:3338",
+        get_melt_quote=AsyncMock(return_value=Mock(state=MeltQuoteState.unpaid)),
+        check_proof_state=AsyncMock(
+            return_value=Mock(states=[Mock(state=ProofSpentState.unspent)])
+        ),
+    )
+
+    with pytest.raises(TokenConsumedError, match="ambiguous"):
+        await _reconcile_ambiguous_melt(wallet, "quote-2", [Mock()])
+
+
+@pytest.mark.asyncio
+async def test_successful_pending_melt_response_requires_reconciliation() -> None:
+    wallet = Mock(
+        url="http://source-mint:3338",
+        get_melt_quote=AsyncMock(return_value=Mock(state=MeltQuoteState.pending)),
+        check_proof_state=AsyncMock(
+            return_value=Mock(states=[Mock(state=ProofSpentState.pending)])
+        ),
+    )
+
+    with pytest.raises(TokenConsumedError, match="ambiguous"):
+        await _confirm_melt_paid(
+            wallet,
+            "quote-pending",
+            [Mock()],
+            Mock(state=MeltQuoteState.pending),
+        )
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    ("quote_state", "proof_state"),
+    [
+        (MeltQuoteState.pending, ProofSpentState.pending),
+        (MeltQuoteState.unpaid, ProofSpentState.spent),
+        (MeltQuoteState.unpaid, ProofSpentState.pending),
+    ],
+)
+async def test_ambiguous_or_consumed_melt_is_never_reported_unspent(
+    quote_state: MeltQuoteState, proof_state: ProofSpentState
+) -> None:
+    wallet = Mock(
+        url="http://source-mint:3338",
+        get_melt_quote=AsyncMock(return_value=Mock(state=quote_state)),
+        check_proof_state=AsyncMock(
+            return_value=Mock(states=[Mock(state=proof_state)])
+        ),
+    )
+
+    with pytest.raises(TokenConsumedError, match="reconciliation required"):
+        await _reconcile_ambiguous_melt(wallet, "quote-3", [Mock()])
+
+
+@pytest.mark.asyncio
+async def test_failed_melt_reconciliation_is_non_retryable() -> None:
+    wallet = Mock(
+        url="http://source-mint:3338",
+        get_melt_quote=AsyncMock(side_effect=RuntimeError("mint unavailable")),
+        check_proof_state=AsyncMock(),
+    )
+
+    with pytest.raises(TokenConsumedError, match="outcome is unknown"):
+        await _reconcile_ambiguous_melt(wallet, "quote-4", [Mock()])

tests/unit/test_mint.py

@@ -0,0 +1,65 @@
+from unittest.mock import AsyncMock, Mock, patch
+
+import httpx
+import pytest
+from cashu.core.base import Unit
+
+from routstr.mint import (
+    MintCooldownError,
+    MintRateGuard,
+    MintRateLimitedError,
+    fail_fast_mint_operations,
+)
+from routstr.wallet import Wallet
+
+
+@pytest.mark.asyncio
+async def test_cooldown_fails_fast_while_wallet_mutation_scope_is_held() -> None:
+    guard = MintRateGuard("http://mint:3338", max_concurrency=1)
+    guard.apply_cooldown(3600, reason="rate_limited")
+    operation = AsyncMock(return_value="should not run")
+
+    with (
+        patch("routstr.mint.asyncio.sleep", AsyncMock()) as sleep,
+        pytest.raises(MintCooldownError) as caught,
+    ):
+        async with fail_fast_mint_operations():
+            await guard.run(operation)
+
+    assert caught.value.retry_after_seconds > 0
+    operation.assert_not_awaited()
+    sleep.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_cashu_429_dispatches_through_wallet_override() -> None:
+    async def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(
+            429,
+            request=request,
+            json={"detail": "too many requests", "code": 42900},
+        )
+
+    wallet = object.__new__(Wallet)
+    wallet.url = "http://mint:3338"
+    wallet.db = Mock()
+    wallet.keysets = {"loaded": Mock()}
+    wallet.mint_info = Mock()
+    wallet.mint_info.requires_blind_auth_path.return_value = False
+    wallet.mint_info.requires_clear_auth_path.return_value = False
+    wallet.auth_db = None
+    wallet.auth_keyset_id = None
+
+    real_client = httpx.AsyncClient
+
+    def client_factory(*args: object, **kwargs: object) -> httpx.AsyncClient:
+        return real_client(
+            transport=httpx.MockTransport(handler),
+            base_url=str(kwargs["base_url"]),
+        )
+
+    with (
+        patch("cashu.wallet.v1_api.httpx.AsyncClient", side_effect=client_factory),
+        pytest.raises(MintRateLimitedError),
+    ):
+        await wallet.mint_quote(1, Unit.sat)

tests/unit/test_payment_helpers.py

@@ -7,21 +7,7 @@ os.environ["UPSTREAM_BASE_URL"] = "http://test"
 os.environ["UPSTREAM_API_KEY"] = "test"
 
 from routstr.core.settings import settings  # noqa: E402
-from routstr.payment.helpers import (  # noqa: E402
-    apply_mint_fee_allowance,
-    get_max_cost_for_model,
-)
-
-
-def test_mint_fee_allowance_reserves_five_percent_fallback_headroom() -> None:
-    # Interim policy: Routstr may pay hidden cross-mint Lightning fees when a
-    # trusted-mint fallback is required.
-    assert apply_mint_fee_allowance(124_886) == 118_642
-
-
-def test_mint_fee_allowance_never_drops_below_minimum() -> None:
-    with patch.object(settings, "min_request_msat", 100):
-        assert apply_mint_fee_allowance(50) == 100
+from routstr.payment.helpers import get_max_cost_for_model  # noqa: E402
 
 
 async def test_get_max_cost_for_model_known() -> None:

tests/unit/test_stale_reservations.py

@@ -422,4 +422,4 @@ async def test_proxy_reverts_reservation_on_client_disconnect() -> None:
         with pytest.raises(asyncio.CancelledError):
             await proxy_module.proxy(request, "v1/chat/completions", session=session)
 
-    revert_mock.assert_awaited_once_with(key, session, 950, reservation_snapshot)
+    revert_mock.assert_awaited_once_with(key, session, 1000, reservation_snapshot)

tests/unit/test_upstream_rate_limit.py

@@ -406,4 +406,4 @@ async def test_proxy_loop_surfaces_rate_limit_and_reverts_once() -> None:
     assert RAW_ORG_ID not in serialized
     assert "org-[REDACTED]" in serialized
     # Single upstream failed -> reservation reverted exactly once (no double-charge).
-    revert_mock.assert_awaited_once_with(key, session, 950, reservation)
+    revert_mock.assert_awaited_once_with(key, session, 1000, reservation)

tests/unit/test_wallet.py

@@ -7,6 +7,7 @@ from unittest.mock import AsyncMock, Mock, patch
 
 import httpx
 import pytest
+from cashu.core.base import MeltQuoteState
 
 from routstr.core.db import ApiKey
 from routstr.wallet import (
@@ -639,7 +640,9 @@ def _make_swap_mocks(
             quote=f"melt_quote_{invoice}", amount=invoice, fee_reserve=_next_fee()
         )
     )
-    mock_token_wallet.melt = AsyncMock(return_value=Mock())
+    mock_token_wallet.melt = AsyncMock(
+        return_value=Mock(state=MeltQuoteState.paid)
+    )
 
     return mock_token, mock_token_wallet, mock_primary_wallet
 
@@ -770,7 +773,7 @@ async def test_swap_retries_when_melt_demands_more_than_quoted() -> None:
             "Mint Error: not enough inputs provided for melt. "
             "Provided: 179, needed: 180 (Code: 11000)"
         ),
-        Mock(),
+        Mock(state=MeltQuoteState.paid),
     ]
 
     from routstr.core.settings import settings
@@ -801,7 +804,7 @@ async def test_swap_retries_on_cdk_unbalanced_error() -> None:
     )
     mock_token_wallet.melt.side_effect = [
         Exception("Mint Error: Transaction unbalanced: 179, 178, 2 (Code: 11005)"),
-        Mock(),
+        Mock(state=MeltQuoteState.paid),
     ]
 
     from routstr.core.settings import settings
@@ -1522,22 +1525,32 @@ async def test_swap_fee_estimation_transport_error_raises_mint_connection_error(
 
 
 @pytest.mark.asyncio
-async def test_swap_melt_transport_error_raises_mint_connection_error() -> None:
-    """A transport failure during melt is surfaced as MintConnectionError and
-    is NOT retried — the mint is down, not demanding higher fees."""
+async def test_swap_melt_transport_error_is_never_reported_reusable() -> None:
+    """A timed-out melt remains ambiguous even when an immediate snapshot says
+    UNPAID/UNSPENT, so callers must not receive the original token for retry."""
     from routstr.wallet import swap_to_primary_mint
 
     mock_token, mock_token_wallet, mock_primary_wallet = _make_swap_mocks(
         1000, fee_reserves=[10, 10]
     )
     mock_token_wallet.melt = AsyncMock(side_effect=httpx.ConnectTimeout("timed out"))
+    from cashu.core.base import MeltQuoteState, ProofSpentState
+
+    mock_token_wallet.get_melt_quote = AsyncMock(
+        return_value=Mock(state=MeltQuoteState.unpaid)
+    )
+    mock_token_wallet.check_proof_state = AsyncMock(
+        return_value=Mock(
+            states=[Mock(state=ProofSpentState.unspent) for _ in mock_token.proofs]
+        )
+    )
 
     from routstr.core.settings import settings
 
     with patch.object(settings, "primary_mint", "http://primary:3338"):
         with patch.object(settings, "primary_mint_unit", "sat"):
             with patch("routstr.wallet.get_wallet", return_value=mock_primary_wallet):
-                with pytest.raises(MintConnectionError):
+                with pytest.raises(TokenConsumedError, match="ambiguous"):
                     await swap_to_primary_mint(mock_token, mock_token_wallet)
 
     assert mock_token_wallet.melt.call_count == 1
@@ -1595,8 +1608,8 @@ async def test_mint_rate_guard_waits_for_adaptive_cooldown() -> None:
     guard._cooldown_until = 15.0
     operation = AsyncMock(return_value="ok")
 
-    with patch("routstr.wallet.time.monotonic", return_value=10.0):
-        with patch("routstr.wallet.asyncio.sleep", AsyncMock()) as sleep:
+    with patch("routstr.mint.time.monotonic", return_value=10.0):
+        with patch("routstr.mint.asyncio.sleep", AsyncMock()) as sleep:
             assert await guard.run(operation) == "ok"
 
     sleep.assert_awaited_once_with(5.0)
@@ -1611,7 +1624,7 @@ async def test_mint_rate_guard_exponentially_backs_off_repeated_429s() -> None:
     expected_delays = [60, 120, 240, 480, 960, 1920, 3840, 7680, 15360, 25200]
     now = 0.0
 
-    with patch("routstr.wallet.time.monotonic") as monotonic:
+    with patch("routstr.mint.time.monotonic") as monotonic:
         for index, expected in enumerate(expected_delays, start=1):
             monotonic.return_value = now
             assert guard.apply_rate_limit_cooldown(60) == expected
@@ -1682,8 +1695,8 @@ async def test_mint_rate_guard_keeps_cooldown_when_concurrency_is_unlimited() ->
     operation = AsyncMock(return_value="ok")
     with (
         patch.object(settings, "mint_max_concurrency", 0),
-        patch("routstr.wallet.time.monotonic", return_value=0),
-        patch("routstr.wallet.asyncio.sleep", AsyncMock()) as sleep,
+        patch("routstr.mint.time.monotonic", return_value=0),
+        patch("routstr.mint.asyncio.sleep", AsyncMock()) as sleep,
     ):
         guard = _MintRateGuard.get("http://mint:3338")
         guard.apply_cooldown(5)
@@ -1715,8 +1728,8 @@ async def test_mint_operation_honors_retry_after_as_minimum() -> None:
     with patch.object(settings, "mint_retry_max_attempts", 1):
         with patch.object(settings, "mint_operation_timeout_seconds", 0):
             with patch.object(settings, "mint_max_concurrency", 1):
-                with patch("routstr.wallet.time.monotonic", return_value=0.1):
-                    with patch("routstr.wallet.asyncio.sleep", sleep):
+                with patch("routstr.mint.time.monotonic", return_value=0.1):
+                    with patch("routstr.mint.asyncio.sleep", sleep):
                         result = await _mint_operation(
                             factory, mint_url="http://mint:3338"
                         )
@@ -1734,7 +1747,7 @@ async def test_mint_operation_timeout_excludes_adaptive_cooldown() -> None:
     with (
         patch.object(settings, "mint_max_concurrency", 1),
         patch.object(settings, "mint_operation_timeout_seconds", 0.01),
-        patch("routstr.wallet.asyncio.sleep", AsyncMock()) as sleep,
+        patch("routstr.mint.asyncio.sleep", AsyncMock()) as sleep,
     ):
         guard = _MintRateGuard.get("http://mint:3338")
         guard.apply_cooldown(60)
@@ -1763,7 +1776,7 @@ async def test_default_timeout_allows_retry_after_rate_limit_cooldown() -> None:
         patch.object(settings, "mint_retry_max_attempts", 3),
         patch.object(settings, "mint_operation_timeout_seconds", 30),
         patch.object(settings, "mint_max_concurrency", 1),
-        patch("routstr.wallet.asyncio.sleep", AsyncMock()),
+        patch("routstr.mint.asyncio.sleep", AsyncMock()),
     ):
         assert await _mint_operation(operation, mint_url="http://mint:3338") == "ok"
 
@@ -1780,7 +1793,7 @@ async def test_mint_operation_retries_httpx_timeout_only_when_safe() -> None:
 
     with patch.object(settings, "mint_retry_max_attempts", 2):
         with patch.object(settings, "mint_operation_timeout_seconds", 0):
-            with patch("routstr.wallet.asyncio.sleep", AsyncMock()):
+            with patch("routstr.mint.asyncio.sleep", AsyncMock()):
                 assert await _mint_operation(retrying) == "ok"
                 with pytest.raises(httpx.TimeoutException):
                     await _mint_operation(non_retrying, retry_timeouts=False)
@@ -1802,7 +1815,7 @@ async def test_get_wallet_initializes_and_loads_once_concurrently() -> None:
     ) as create:
         # A fresh wallet must load even when the host has been up for less than
         # the reload interval.
-        with patch("routstr.wallet.time.monotonic", return_value=10.0):
+        with patch("routstr.mint.time.monotonic", return_value=10.0):
             first, second = await asyncio.gather(
                 get_wallet("http://mint:3338"), get_wallet("http://mint:3338")
             )
@@ -1833,7 +1846,7 @@ async def test_get_wallet_can_surface_429_without_retrying() -> None:
         patch("routstr.wallet.Wallet.with_db", AsyncMock(return_value=wallet)),
         patch.object(settings, "mint_retry_max_attempts", 3),
         patch.object(settings, "mint_operation_timeout_seconds", 0),
-        patch("routstr.wallet.asyncio.sleep", AsyncMock()) as sleep,
+        patch("routstr.mint.asyncio.sleep", AsyncMock()) as sleep,
     ):
         with pytest.raises(httpx.HTTPStatusError):
             await get_wallet("http://mint:3338", retry_on_rate_limit=False)
@@ -1965,7 +1978,7 @@ async def test_swap_falls_back_when_primary_wallet_cannot_load() -> None:
         melt_quote=AsyncMock(
             return_value=Mock(quote="melt_q", amount=990, fee_reserve=10)
         ),
-        melt=AsyncMock(return_value=Mock()),
+        melt=AsyncMock(return_value=Mock(state=MeltQuoteState.paid)),
     )
 
     mint_quote = Mock(quote="mint_q_secondary", request="lnbc1secondary")
@@ -1994,6 +2007,7 @@ async def test_swap_falls_back_when_primary_wallet_cannot_load() -> None:
         patch("asyncio.sleep", AsyncMock()),
         patch("routstr.wallet.get_wallet", side_effect=mock_get),
         patch("routstr.wallet.logger.warning") as warning,
+        patch("routstr.wallet.logger.info") as info,
     ):
         amount, unit, mint_url = await swap_to_primary_mint(token, source_wallet)
 
@@ -2003,7 +2017,7 @@ async def test_swap_falls_back_when_primary_wallet_cannot_load() -> None:
     assert any(call.args[0] == secondary for call in mock_get.await_args_list)
     events = {
         call.kwargs["extra"]["event"]
-        for call in warning.call_args_list
+        for call in [*warning.call_args_list, *info.call_args_list]
         if "extra" in call.kwargs and "event" in call.kwargs["extra"]
     }
     assert "cashu_destination_failed" in events
@@ -2181,8 +2195,8 @@ async def test_wallet_fallback_skips_mint_during_cooldown() -> None:
         patch.object(settings, "cashu_mints", [primary, secondary]),
         patch.object(settings, "mint_max_concurrency", 0),
         patch.object(settings, "mint_operation_timeout_seconds", 0),
-        patch("routstr.wallet.time.monotonic", return_value=10),
-        patch("routstr.wallet.asyncio.sleep", AsyncMock()) as sleep,
+        patch("routstr.mint.time.monotonic", return_value=10),
+        patch("routstr.mint.asyncio.sleep", AsyncMock()) as sleep,
         patch(
             "routstr.wallet.get_wallet",
             AsyncMock(side_effect=lambda mint, *args, **kwargs: wallets[mint]),
@@ -2378,49 +2392,28 @@ def test_classify_500_with_rate_limit_text_is_not_mint_rate_limited() -> None:
 
 @pytest.mark.asyncio
 async def test_probe_does_not_escalate_consecutive_rate_limits() -> None:
-    """When a probe fails with a rate limit, _consecutive_rate_limits should
-    NOT increment — the probe is a recovery check, not a new request."""
-    from routstr.wallet import _MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS, _MintRateGuard
+    from routstr.mint import MintRateGuard
 
-    guard = _MintRateGuard("http://mint", max_concurrency=0)
-
-    # Simulate initial rate limit: apply_rate_limit_cooldown increments counter
+    guard = MintRateGuard("http://mint", max_concurrency=0)
     guard.apply_rate_limit_cooldown()
-    assert guard._consecutive_rate_limits == 1
-    cooldown_before = guard._cooldown_until
-    assert cooldown_before > 0
+    guard._cooldown_until = 0.0
 
-    # Simulate probe failure: _run_probe uses apply_cooldown, NOT
-    # apply_rate_limit_cooldown, so the counter stays at 1.
-    guard.apply_cooldown(_MINT_RATE_LIMIT_BASE_COOLDOWN_SECONDS, reason="rate_limited")
-    assert guard._consecutive_rate_limits == 1  # unchanged!
+    with pytest.raises(httpx.HTTPStatusError):
+        await guard.run(AsyncMock(side_effect=_http_429_error()))
+
+    assert guard._consecutive_rate_limits == 1
     assert guard._needs_probe is True
 
 
 @pytest.mark.asyncio
 async def test_probe_recovery_resets_consecutive_rate_limits() -> None:
-    """A successful probe resets _consecutive_rate_limits to 0."""
-    from routstr.wallet import _MintRateGuard
+    from routstr.mint import MintRateGuard
 
-    guard = _MintRateGuard("http://mint", max_concurrency=0)
-
-    # First rate limit: increments to 1, sets 60s cooldown.
+    guard = MintRateGuard("http://mint", max_concurrency=0)
     guard.apply_rate_limit_cooldown()
-    assert guard._consecutive_rate_limits == 1
-
-    # Manually expire the cooldown so the next call creates a fresh one.
     guard._cooldown_until = 0.0
-    guard._cooldown_reason = None
 
-    # Second rate limit (after cooldown expired): increments to 2.
-    guard.apply_rate_limit_cooldown()
-    assert guard._consecutive_rate_limits == 2
-
-    # Simulate a successful probe by resetting (as _run_probe does)
-    guard._needs_probe = False
-    guard._cooldown_until = 0.0
-    guard._cooldown_reason = None
-    guard._consecutive_rate_limits = 0
+    assert await guard.run(AsyncMock(return_value="ok")) == "ok"
 
     assert guard._consecutive_rate_limits == 0
     assert guard._needs_probe is False