ruff fix

Introduce child key

routstr/algorithm.py

@@ -84,93 +84,26 @@ def get_provider_penalty(provider: "BaseUpstreamProvider") -> float:
     return penalty
 
 
-def should_prefer_model(
-    candidate_model: "Model",
-    candidate_provider: "BaseUpstreamProvider",
-    current_model: "Model",
-    current_provider: "BaseUpstreamProvider",
-    alias: str,
-) -> bool:
-    """Determine if candidate model should replace current model for an alias.
-
-    This is the core decision function for model prioritization. It considers:
-    1. Alias matching quality (exact match vs. canonical slug match)
-    2. Model cost (lower is better)
-    3. Provider penalties (e.g., slight preference against OpenRouter)
-
-    Args:
-        candidate_model: The new model being considered
-        candidate_provider: Provider offering the candidate model
-        current_model: The currently selected model for this alias
-        current_provider: Provider offering the current model
-        alias: The model alias being mapped
-
-    Returns:
-        True if candidate should replace current, False otherwise
-    """
-
-    def get_base_model_id(model_id: str) -> str:
-        """Get base model ID by removing provider prefix."""
-        return model_id.split("/", 1)[1] if "/" in model_id else model_id
-
-    def alias_priority(model: "Model") -> int:
-        """Rank how strong the mapping of alias->model is.
-
-        Highest priority when alias exactly equals the model ID without provider prefix.
-        Next when alias equals canonical slug without prefix. Otherwise lowest.
-        """
-        model_base = get_base_model_id(model.id)
-        if model_base == alias:
-            return 3
-        if model.canonical_slug:
-            canonical_base = get_base_model_id(model.canonical_slug)
-            if canonical_base == alias:
-                return 2
-        return 1
-
-    candidate_alias_priority = alias_priority(candidate_model)
-    current_alias_priority = alias_priority(current_model)
-
-    # If candidate has better alias match, prefer it regardless of cost
-    if candidate_alias_priority > current_alias_priority:
-        return True
-
-    # If current has better alias match, keep it regardless of cost
-    if current_alias_priority > candidate_alias_priority:
-        return False
-
-    # Same alias priority - compare costs
-    candidate_cost = calculate_model_cost_score(candidate_model)
-    current_cost = calculate_model_cost_score(current_model)
-
-    # Apply provider penalties
-    candidate_adjusted = candidate_cost * get_provider_penalty(candidate_provider)
-    current_adjusted = current_cost * get_provider_penalty(current_provider)
-
-    # Prefer lower adjusted cost
-    should_replace = candidate_adjusted < current_adjusted
-
-    return should_replace
-
-
 def create_model_mappings(
     upstreams: list["BaseUpstreamProvider"],
     overrides_by_id: dict[str, tuple],
     disabled_model_ids: set[str],
-) -> tuple[dict[str, "Model"], dict[str, "BaseUpstreamProvider"], dict[str, "Model"]]:
+) -> tuple[
+    dict[str, "Model"], dict[str, list["BaseUpstreamProvider"]], dict[str, "Model"]
+]:
     """Create optimal model mappings based on cost and provider preferences.
 
     This is the main entry point for the algorithm. It processes all upstream providers
     and creates three mappings based on cost optimization:
 
     1. model_instances: alias -> Model (all model aliases mapped to their Model objects)
-    2. provider_map: alias -> UpstreamProvider (which provider to use for each alias)
+    2. provider_map: alias -> List[UpstreamProvider] (sorted list of providers for each alias)
     3. unique_models: base_id -> Model (unique models without provider prefixes)
 
     The algorithm:
     - Processes non-OpenRouter providers first (they're typically cheaper)
     - Then processes OpenRouter models (they can still win if cheaper)
-    - For each model alias, uses should_prefer_model() to select the best provider
+    - For each model alias, collects all candidates and sorts them by priority and cost.
 
     Args:
         upstreams: List of all upstream provider instances
@@ -183,8 +116,7 @@ def create_model_mappings(
     from .payment.models import _row_to_model
     from .upstream.helpers import resolve_model_alias
 
-    model_instances: dict[str, "Model"] = {}
-    provider_map: dict[str, "BaseUpstreamProvider"] = {}
+    candidates: dict[str, list[tuple["Model", "BaseUpstreamProvider"]]] = {}
     unique_models: dict[str, "Model"] = {}
 
     # Separate OpenRouter from other providers
@@ -202,24 +134,14 @@ def create_model_mappings(
         """Get base model ID by removing provider prefix."""
         return model_id.split("/", 1)[1] if "/" in model_id else model_id
 
-    def _maybe_set_alias(
+    def _add_candidate(
         alias: str, model: "Model", provider: "BaseUpstreamProvider"
     ) -> None:
-        """Set alias to model/provider if not set or if new model is preferred."""
+        """Add candidate model/provider for an alias."""
         alias_lower = alias.lower()
-        existing_model = model_instances.get(alias_lower)
-        if not existing_model:
-            # No existing mapping, set it
-            model_instances[alias_lower] = model
-            provider_map[alias_lower] = provider
-        else:
-            # Check if candidate should replace existing
-            existing_provider = provider_map[alias_lower]
-            if should_prefer_model(
-                model, provider, existing_model, existing_provider, alias
-            ):
-                model_instances[alias_lower] = model
-                provider_map[alias_lower] = provider
+        if alias_lower not in candidates:
+            candidates[alias_lower] = []
+        candidates[alias_lower].append((model, provider))
 
     def process_provider_models(
         upstream: "BaseUpstreamProvider", is_openrouter: bool = False
@@ -266,21 +188,55 @@ def create_model_mappings(
 
             # Try to set each alias
             for alias in aliases:
-                _maybe_set_alias(alias, model_to_use, upstream)
+                _add_candidate(alias, model_to_use, upstream)
 
-    # Process non-OpenRouter providers first (they're typically cheaper)
+    # Process non-OpenRouter providers first
     for upstream in other_upstreams:
         process_provider_models(upstream, is_openrouter=False)
 
-    # Process OpenRouter last - models only win if they're cheaper or better matched
+    # Process OpenRouter last
     if openrouter:
         process_provider_models(openrouter, is_openrouter=True)
 
-    # Log provider distribution
+    # Sort candidates and build final maps
+    model_instances: dict[str, "Model"] = {}
+    provider_map: dict[str, list["BaseUpstreamProvider"]] = {}
+
+    def alias_priority(model: "Model", alias: str) -> int:
+        """Rank how strong the mapping of alias->model is."""
+        model_base = get_base_model_id(model.id)
+        if model_base == alias:
+            return 3
+        if model.canonical_slug:
+            canonical_base = get_base_model_id(model.canonical_slug)
+            if canonical_base == alias:
+                return 2
+        return 1
+
+    for alias, items in candidates.items():
+        # Sort key: (priority DESC, cost ASC)
+        # Using negative cost for DESC sort overall to keep high priority first
+        def sort_key(item: tuple["Model", "BaseUpstreamProvider"]) -> tuple[int, float]:
+            model, provider = item
+            priority = alias_priority(model, alias)
+            cost = calculate_model_cost_score(model)
+            penalty = get_provider_penalty(provider)
+            adjusted_cost = cost * penalty
+            return (priority, -adjusted_cost)
+
+        items.sort(key=sort_key, reverse=True)
+
+        best_model, best_provider = items[0]
+        model_instances[alias] = best_model
+        provider_map[alias] = [p for _, p in items]
+
+    # Log provider distribution (using top provider for stats)
     provider_counts: dict[str, int] = {}
-    for provider in provider_map.values():
-        provider_name = getattr(provider, "upstream_name", "unknown")
-        provider_counts[provider_name] = provider_counts.get(provider_name, 0) + 1
+    for providers in provider_map.values():
+        if providers:
+            provider = providers[0]
+            provider_name = getattr(provider, "upstream_name", "unknown")
+            provider_counts[provider_name] = provider_counts.get(provider_name, 0) + 1
 
     logger.debug(
         f"Updated model mappings with ({len(unique_models)} unique models and {len(model_instances)} aliases)",

routstr/core/exceptions.py

@@ -6,6 +6,15 @@ from .logging import get_logger
 logger = get_logger(__name__)
 
 
+class UpstreamError(Exception):
+    """Exception raised when an upstream provider fails."""
+
+    def __init__(self, message: str, status_code: int = 502):
+        self.message = message
+        self.status_code = status_code
+        super().__init__(message)
+
+
 async def http_exception_handler(request: Request, exc: Exception) -> JSONResponse:
     """Handle HTTP exceptions and include request ID in response."""
     request_id = getattr(request.state, "request_id", "unknown")

routstr/core/main.py

@@ -63,6 +63,11 @@ async def lifespan(_: FastAPI) -> AsyncGenerator[None, None]:
 
                 await reset_all_reserved_balances(session)
 
+        if not s.admin_password:
+            logger.warning(
+                f"Admin password is not set. Visit {s.http_url or 'http://localhost:8000'}/admin to set the password."
+            )
+
         # Apply app metadata from settings
         try:
             app.title = s.name

routstr/core/settings.py

@@ -6,7 +6,7 @@ import os
 from datetime import datetime, timezone
 from typing import Any
 
-from pydantic.v1 import BaseModel, BaseSettings, Field, validator
+from pydantic.v1 import BaseModel, BaseSettings, Field
 from sqlmodel.ext.asyncio.session import AsyncSession
 
 
@@ -37,13 +37,6 @@ class Settings(BaseSettings):
 
     # Cashu
     cashu_mints: list[str] = Field(default_factory=list, env="CASHU_MINTS")
-
-    @validator("cashu_mints", pre=True, each_item=True)
-    def normalize_mint_url(cls, v: str) -> str:
-        if isinstance(v, str):
-            return v.rstrip("/")
-        return v
-
     receive_ln_address: str = Field(default="", env="RECEIVE_LN_ADDRESS")
     primary_mint: str = Field(default="", env="PRIMARY_MINT_URL")
     primary_mint_unit: str = Field(default="sat", env="PRIMARY_MINT_UNIT")
@@ -70,7 +63,7 @@ class Settings(BaseSettings):
     cors_origins: list[str] = Field(default_factory=lambda: ["*"], env="CORS_ORIGINS")
     tor_proxy_url: str = Field(default="socks5://127.0.0.1:9050", env="TOR_PROXY_URL")
     providers_refresh_interval_seconds: int = Field(
-        default=300, env="PROVIDERS_REFRESH_INTERVAL_SECONDS"
+        default=0, env="PROVIDERS_REFRESH_INTERVAL_SECONDS"
     )
     pricing_refresh_interval_seconds: int = Field(
         default=120, env="PRICING_REFRESH_INTERVAL_SECONDS"

routstr/discovery.py

@@ -6,7 +6,7 @@ from typing import Any
 
 import httpx
 import websockets
-from fastapi import APIRouter
+from fastapi import APIRouter, HTTPException
 
 from .core.logging import get_logger
 from .core.settings import settings
@@ -389,6 +389,9 @@ async def get_providers(
     Return cached providers. If include_json, return provider+health; otherwise provider only.
     Optional filter by pubkey.
     """
+    if settings.providers_refresh_interval_seconds == 0:
+        raise HTTPException(status_code=404, detail="Provider discovery is disabled")
+
     cache = await get_cache()
     if not cache:
         await refresh_providers_cache(pubkey=pubkey)

routstr/payment/models.py

@@ -253,6 +253,11 @@ async def list_models(
             else 1.01,
         )
         for r in rows
+        if include_disabled
+        or (
+            r.upstream_provider_id in providers_by_id
+            and providers_by_id[r.upstream_provider_id].enabled
+        )
     ]
 
 
@@ -265,6 +270,8 @@ async def get_model_by_id(
     if not row or not row.enabled:
         return None
     provider = await session.get(UpstreamProviderRow, provider_id)
+    if not provider or not provider.enabled:
+        return None
     provider_fee = provider.provider_fee if provider else 1.01
     return _row_to_model(row, apply_provider_fee=True, provider_fee=provider_fee)
 

routstr/payment/price.py

@@ -79,15 +79,29 @@ async def _fetch_btc_usd_price() -> float:
     """Fetch the lowest BTC/USD price from multiple exchanges."""
     async with httpx.AsyncClient(timeout=30.0) as client:
         try:
-            prices = await asyncio.gather(
-                _kraken_btc_usd(client),
-                _coinbase_btc_usd(client),
-                _binance_btc_usdt(client),
-            )
-            valid_prices = [price for price in prices if price is not None]
+            tasks = [
+                asyncio.create_task(_kraken_btc_usd(client)),
+                asyncio.create_task(_coinbase_btc_usd(client)),
+                asyncio.create_task(_binance_btc_usdt(client)),
+            ]
+            valid_prices: list[float] = []
+
+            for future in asyncio.as_completed(tasks):
+                price = await future
+                if price is not None:
+                    valid_prices.append(price)
+
+                if len(valid_prices) >= 2:
+                    break
+
+            for task in tasks:
+                if not task.done():
+                    task.cancel()
+
             if not valid_prices:
                 logger.error("No valid BTC prices obtained from any exchange")
                 raise ValueError("Unable to fetch BTC price from any exchange")
+
             return min(valid_prices)
         except Exception as e:
             logger.error(

routstr/proxy.py

@@ -16,7 +16,7 @@ from .core.db import (
     create_session,
     get_session,
 )
-from .core.settings import settings
+from .core.exceptions import UpstreamError
 from .payment.helpers import (
     calculate_discounted_max_cost,
     check_token_balance,
@@ -26,14 +26,15 @@ from .payment.helpers import (
 from .payment.models import Model
 from .upstream import BaseUpstreamProvider
 from .upstream.helpers import init_upstreams
-from .wallet import deserialize_token_from_string
 
 logger = get_logger(__name__)
 proxy_router = APIRouter()
 
 _upstreams: list[BaseUpstreamProvider] = []
 _model_instances: dict[str, Model] = {}  # All aliases -> Model
-_provider_map: dict[str, BaseUpstreamProvider] = {}  # All aliases -> Provider
+_provider_map: dict[
+    str, list[BaseUpstreamProvider]
+] = {}  # All aliases -> List[Provider]
 _unique_models: dict[str, Model] = {}  # Unique model.id -> Model (no duplicates)
 
 
@@ -70,8 +71,8 @@ def get_model_instance(model_id: str) -> Model | None:
     return _model_instances.get(model_id.lower())
 
 
-def get_provider_for_model(model_id: str) -> BaseUpstreamProvider | None:
-    """Get UpstreamProvider for model ID from global cache."""
+def get_provider_for_model(model_id: str) -> list[BaseUpstreamProvider] | None:
+    """Get UpstreamProvider list for model ID from global cache."""
     return _provider_map.get(model_id.lower())
 
 
@@ -98,6 +99,8 @@ async def refresh_model_maps() -> None:
     disabled_model_ids: set[str] = set()
 
     for provider in provider_rows:
+        if not provider.enabled:
+            continue
         for model in provider.models:
             if model.enabled:
                 overrides_by_id[model.id] = (model, provider.provider_fee)
@@ -148,32 +151,14 @@ async def proxy(
     else:
         model_id = request_body_dict.get("model", "unknown")
 
-    if "https://testnut.cashu.space" in settings.cashu_mints:
-        try:
-            token_str = None
-            if x_cashu_header := headers.get("x-cashu"):
-                token_str = x_cashu_header
-            elif auth_header := headers.get("authorization"):
-                parts = auth_header.split(" ")
-                if len(parts) > 1 and not parts[1].startswith("sk-"):
-                    token_str = parts[1]
-
-            if token_str:
-                token_obj = deserialize_token_from_string(token_str)
-                if token_obj.mint == "https://testnut.cashu.space":
-                    model_id = "mock/gpt-420-mock"
-                    request_body_dict["model"] = model_id
-        except Exception:
-            pass
-
     model_obj = get_model_instance(model_id)
     if not model_obj:
         return create_error_response(
             "invalid_model", f"Model '{model_id}' not found", 400, request=request
         )
 
-    upstream = get_provider_for_model(model_id)
-    if not upstream:
+    upstreams = get_provider_for_model(model_id)
+    if not upstreams:
         return create_error_response(
             "invalid_model",
             f"No provider found for model '{model_id}'",
@@ -181,6 +166,10 @@ async def proxy(
             request=request,
         )
 
+    # todo figure out cost calculation since fallback provider is usually not the same price
+    # Use first provider for initial checks/cost calculation
+    # primary_upstream = upstreams[0]
+
     _max_cost_for_model = await get_max_cost_for_model(
         model=model_id, session=session, model_obj=model_obj
     )
@@ -190,14 +179,31 @@ async def proxy(
     check_token_balance(headers, request_body_dict, max_cost_for_model)
 
     if x_cashu := headers.get("x-cashu", None):
-        if is_responses_api:
-            return await upstream.handle_x_cashu_responses(
-                request, x_cashu, path, max_cost_for_model, model_obj
-            )
-        else:
-            return await upstream.handle_x_cashu(
-                request, x_cashu, path, max_cost_for_model, model_obj
-            )
+        last_error = None
+        for i, upstream in enumerate(upstreams):
+            try:
+                if is_responses_api:
+                    return await upstream.handle_x_cashu_responses(
+                        request, x_cashu, path, max_cost_for_model, model_obj
+                    )
+                else:
+                    return await upstream.handle_x_cashu(
+                        request, x_cashu, path, max_cost_for_model, model_obj
+                    )
+            except UpstreamError as e:
+                logger.warning(
+                    f"Upstream {upstream.provider_type} failed (x-cashu): {e}"
+                )
+                if i == len(upstreams) - 1:
+                    last_error = e
+                continue
+
+        return create_error_response(
+            "upstream_error",
+            str(last_error) if last_error else "All upstreams failed",
+            502,
+            request=request,
+        )
 
     elif auth := headers.get("authorization", None):
         key = await get_bearer_token_key(headers, path, session, auth)
@@ -212,56 +218,152 @@ async def proxy(
             )
 
         logger.debug("Processing unauthenticated GET request", extra={"path": path})
-        headers = upstream.prepare_headers(dict(request.headers))
-        return await upstream.forward_get_request(request, path, headers)
+
+        last_error_response = None
+        for i, upstream in enumerate(upstreams):
+            try:
+                headers = upstream.prepare_headers(dict(request.headers))
+                response = await upstream.forward_get_request(request, path, headers)
+
+                if response.status_code in [502, 429] and i < len(upstreams) - 1:
+                    error_message = ""
+                    try:
+                        if hasattr(response, "body"):
+                            body_bytes = response.body
+                            data = json.loads(body_bytes)
+                            if "error" in data:
+                                error_data = data["error"]
+                                if isinstance(error_data, dict):
+                                    error_message = error_data.get("message", "")
+                                elif isinstance(error_data, str):
+                                    error_message = error_data
+                    except Exception:
+                        pass
+
+                    await upstream.on_upstream_error_redirect(
+                        response.status_code, error_message
+                    )
+
+                    logger.warning(
+                        f"Upstream {upstream.provider_type} returned {response.status_code} (GET), trying next provider",
+                        extra={
+                            "status_code": response.status_code,
+                            "upstream": upstream.provider_type,
+                        },
+                    )
+                    continue
+                return response
+            except UpstreamError as e:
+                logger.warning(f"Upstream {upstream.provider_type} failed (GET): {e}")
+                if i == len(upstreams) - 1:
+                    last_error_response = create_error_response(
+                        "upstream_error", str(e), 502, request=request
+                    )
+                continue
+        return last_error_response or create_error_response(
+            "upstream_error", "All upstreams failed", 502, request=request
+        )
 
     if request_body_dict:
         await pay_for_request(key, max_cost_for_model, session)
 
-    headers = upstream.prepare_headers(dict(request.headers))
+    for i, upstream in enumerate(upstreams):
+        headers = upstream.prepare_headers(dict(request.headers))
 
-    if is_responses_api:
-        response = await upstream.forward_responses_request(
-            request,
-            path,
-            headers,
-            request_body,
-            key,
-            max_cost_for_model,
-            session,
-            model_obj,
-        )
-    else:
-        response = await upstream.forward_request(
-            request,
-            path,
-            headers,
-            request_body,
-            key,
-            max_cost_for_model,
-            session,
-            model_obj,
-        )
+        try:
+            if is_responses_api:
+                response = await upstream.forward_responses_request(
+                    request,
+                    path,
+                    headers,
+                    request_body,
+                    key,
+                    max_cost_for_model,
+                    session,
+                    model_obj,
+                )
+            else:
+                response = await upstream.forward_request(
+                    request,
+                    path,
+                    headers,
+                    request_body,
+                    key,
+                    max_cost_for_model,
+                    session,
+                    model_obj,
+                )
 
-    if response.status_code != 200:
-        await revert_pay_for_request(key, session, max_cost_for_model)
-        logger.warning(
-            "Upstream request failed, revert payment",
-            extra={
-                "status_code": response.status_code,
-                "path": path,
-                "key_hash": key.hashed_key[:8] + "...",
-                "key_balance": key.balance,
-                "max_cost_for_model": max_cost_for_model,
-                "upstream_headers": response.headers
-                if hasattr(response, "headers")
-                else None,
-            },
-        )
-        # Return the mapped error response generated earlier rather than masking with 502
-        return response
+            if response.status_code != 200:
+                # Check if we should retry (502 Upstream Error or 429 Rate Limit)
+                should_retry = response.status_code in [502, 429, 400, 401, 403, 404]
+                if should_retry and i < len(upstreams) - 1:
+                    error_message = ""
+                    try:
+                        if hasattr(response, "body"):
+                            body_bytes = response.body
+                            data = json.loads(body_bytes)
+                            if "error" in data:
+                                error_data = data["error"]
+                                if isinstance(error_data, dict):
+                                    error_message = error_data.get("message", "")
+                                elif isinstance(error_data, str):
+                                    error_message = error_data
+                    except Exception:
+                        pass
 
-    return response
+                    await upstream.on_upstream_error_redirect(
+                        response.status_code, error_message
+                    )
+
+                    logger.warning(
+                        f"Upstream {upstream.provider_type} returned {response.status_code}, trying next provider",
+                        extra={
+                            "status_code": response.status_code,
+                            "upstream": upstream.provider_type,
+                        },
+                    )
+                    continue
+
+                # 4xx error (user error), or other non-retryable error, or last provider failed
+                await revert_pay_for_request(key, session, max_cost_for_model)
+                logger.warning(
+                    "Upstream request failed, revert payment",
+                    extra={
+                        "status_code": response.status_code,
+                        "path": path,
+                        "key_hash": key.hashed_key[:8] + "...",
+                        "key_balance": key.balance,
+                        "max_cost_for_model": max_cost_for_model,
+                        "upstream_headers": response.headers
+                        if hasattr(response, "headers")
+                        else None,
+                    },
+                )
+                return response
+
+            return response
+
+        except UpstreamError as e:
+            logger.warning(
+                f"Upstream {upstream.provider_type} failed: {e}",
+                extra={"retry": i < len(upstreams) - 1},
+            )
+
+            # If this was the last provider
+            if i == len(upstreams) - 1:
+                await revert_pay_for_request(key, session, max_cost_for_model)
+                return create_error_response(
+                    "upstream_error", str(e), 502, request=request
+                )
+
+            # Otherwise loop continues to next provider
+            continue
+
+    # Should not be reached given logic above
+    return create_error_response(
+        "upstream_error", "All upstreams failed", 502, request=request
+    )
 
 
 async def get_bearer_token_key(

routstr/upstream/base.py

@@ -15,6 +15,7 @@ from pydantic import BaseModel
 from ..auth import adjust_payment_for_tokens
 from ..core import get_logger
 from ..core.db import ApiKey, AsyncSession, create_session
+from ..core.exceptions import UpstreamError
 
 if TYPE_CHECKING:
     from ..core.db import UpstreamProviderRow
@@ -340,6 +341,20 @@ class BaseUpstreamProvider:
                 message = preview[:500]
         return message, upstream_code
 
+    async def on_upstream_error_redirect(
+        self, status_code: int, error_message: str
+    ) -> None:
+        """Hook called when the proxy redirects to another provider due to an error.
+
+        Subclasses can implement this to perform actions like disabling the provider
+        if it's out of balance.
+
+        Args:
+            status_code: The HTTP status code returned by the upstream
+            error_message: The error message extracted from the upstream response
+        """
+        pass
+
     async def map_upstream_error_response(
         self, request: Request, path: str, upstream_response: httpx.Response
     ) -> Response:
@@ -1148,6 +1163,14 @@ class BaseUpstreamProvider:
             )
 
             if response.status_code != 200:
+                if response.status_code >= 500:
+                    await response.aclose()
+                    await client.aclose()
+                    raise UpstreamError(
+                        f"Upstream returned status {response.status_code}",
+                        status_code=response.status_code,
+                    )
+
                 try:
                     mapped_error = await self.map_upstream_error_response(
                         request, path, response
@@ -1238,6 +1261,9 @@ class BaseUpstreamProvider:
                 background=background_tasks,
             )
 
+        except UpstreamError:
+            raise
+
         except httpx.RequestError as exc:
             await client.aclose()
             error_type = type(exc).__name__
@@ -1265,9 +1291,7 @@ class BaseUpstreamProvider:
             else:
                 error_message = f"Error connecting to upstream service: {error_type}"
 
-            return create_error_response(
-                "upstream_error", error_message, 502, request=request
-            )
+            raise UpstreamError(error_message, status_code=502)
 
         except Exception as exc:
             await client.aclose()
@@ -1380,6 +1404,14 @@ class BaseUpstreamProvider:
             )
 
             if response.status_code != 200:
+                if response.status_code >= 500:
+                    await response.aclose()
+                    await client.aclose()
+                    raise UpstreamError(
+                        f"Upstream returned status {response.status_code}",
+                        status_code=response.status_code,
+                    )
+
                 try:
                     mapped_error = await self.map_upstream_error_response(
                         request, path, response
@@ -1447,6 +1479,9 @@ class BaseUpstreamProvider:
                 background=background_tasks,
             )
 
+        except UpstreamError:
+            raise
+
         except httpx.RequestError as exc:
             await client.aclose()
             error_type = type(exc).__name__
@@ -1474,9 +1509,7 @@ class BaseUpstreamProvider:
             else:
                 error_message = f"Error connecting to upstream service: {error_type}"
 
-            return create_error_response(
-                "upstream_error", error_message, 502, request=request
-            )
+            raise UpstreamError(error_message, status_code=502)
 
         except Exception as exc:
             await client.aclose()

routstr/upstream/fake.py

@@ -1,265 +0,0 @@
-import asyncio
-import json
-import random
-from typing import AsyncIterator
-
-from fastapi import Request
-from fastapi.responses import Response, StreamingResponse
-
-from ..core.db import ApiKey, AsyncSession
-from ..payment.models import Architecture, Model, Pricing
-from .base import BaseUpstreamProvider
-
-
-class MockUpstreamProvider(BaseUpstreamProvider):
-    """Fack Mock Upstream provider specifically for Testing."""
-
-    provider_type = "mock"
-
-    async def forward_request(
-        self,
-        request: Request,
-        path: str,
-        headers: dict,
-        request_body: bytes | None,
-        key: ApiKey,
-        max_cost_for_model: int,
-        session: AsyncSession,
-        model_obj: Model,
-    ) -> Response | StreamingResponse:
-        if path.endswith("chat/completions"):
-            is_streaming = False
-            if request_body:
-                request_data = json.loads(request_body)
-                is_streaming = request_data.get("stream", False)
-
-            if is_streaming:
-
-                async def fake_streaming_response(
-                    chunk_size: int | None = None,
-                ) -> AsyncIterator[bytes]:
-                    suffix = random.randint(1000, 9999)
-                    req_id = f"gen-mock-stream-{suffix}"
-                    created = 1766138895
-                    model = "mock/gpt-420-mock"
-
-                    def make_chunk(
-                        delta: dict,
-                        finish_reason: str | None = None,
-                        usage: dict | None = None,
-                    ) -> bytes:
-                        chunk = {
-                            "id": req_id,
-                            "provider": "MockProvider",
-                            "model": model,
-                            "object": "chat.completion.chunk",
-                            "created": created,
-                            "choices": [
-                                {
-                                    "index": 0,
-                                    "delta": delta,
-                                    "finish_reason": finish_reason,
-                                    "native_finish_reason": "completed"
-                                    if finish_reason
-                                    else None,
-                                    "logprobs": None,
-                                }
-                            ],
-                        }
-                        if usage:
-                            chunk["usage"] = usage
-                        return f"data: {json.dumps(chunk)}\n\n".encode()
-
-                    # 1. Initial chunk
-                    yield make_chunk({"role": "assistant", "content": ""})
-                    await asyncio.sleep(0.02)
-
-                    # 2. Reasoning chunks
-                    reasoning_tokens = ["Mock", " reason", "ing", "..."]
-                    for token in reasoning_tokens:
-                        delta = {
-                            "role": "assistant",
-                            "content": "",
-                            "reasoning": token,
-                            "reasoning_details": [
-                                {
-                                    "type": "reasoning.summary",
-                                    "summary": token,
-                                    "format": "openai-responses-v1",
-                                    "index": 0,
-                                }
-                            ],
-                        }
-                        yield make_chunk(delta)
-                        await asyncio.sleep(0.03)
-
-                    # 3. Content chunks
-                    content_tokens = ["This", " is", " a", " mock", " stream", "."]
-                    for token in content_tokens:
-                        yield make_chunk({"role": "assistant", "content": token})
-                        await asyncio.sleep(0.03)
-
-                    # 4. Finish chunk
-                    yield make_chunk(
-                        {"role": "assistant", "content": ""}, finish_reason="stop"
-                    )
-
-                    # 5. Usage chunk
-                    usage_data = {
-                        "prompt_tokens": 10,
-                        "completion_tokens": 20,
-                        "total_tokens": 30,
-                        "cost": 0.001,
-                        "is_byok": False,
-                        "prompt_tokens_details": {
-                            "cached_tokens": 0,
-                            "audio_tokens": 0,
-                            "video_tokens": 0,
-                        },
-                        "cost_details": {
-                            "upstream_inference_cost": None,
-                            "upstream_inference_prompt_cost": 0,
-                            "upstream_inference_completions_cost": 0.001,
-                        },
-                        "completion_tokens_details": {
-                            "reasoning_tokens": 10,
-                            "image_tokens": 0,
-                        },
-                    }
-
-                    usage_chunk = {
-                        "id": req_id,
-                        "provider": "MockProvider",
-                        "model": model,
-                        "object": "chat.completion.chunk",
-                        "created": created,
-                        "choices": [
-                            {
-                                "index": 0,
-                                "delta": {"role": "assistant", "content": ""},
-                                "finish_reason": None,
-                                "native_finish_reason": None,
-                                "logprobs": None,
-                            }
-                        ],
-                        "usage": usage_data,
-                    }
-                    yield f"data: {json.dumps(usage_chunk)}\n\n".encode()
-
-                    # 6. DONE
-                    yield b"data: [DONE]\n\n"
-
-                    # 7. Cost
-                    cost_chunk = {
-                        "cost": {
-                            "base_msats": 0,
-                            "input_msats": 2,
-                            "output_msats": 10,
-                            "total_msats": 12,
-                        }
-                    }
-                    yield f"data: {json.dumps(cost_chunk)}\n\n".encode()
-
-                return StreamingResponse(
-                    fake_streaming_response(),
-                    200,
-                )
-
-            else:
-                suffix = random.randint(1000, 9999)
-                content_dict = {
-                    "id": f"gen-mock-{suffix}",
-                    "provider": "MockProvider",
-                    "model": "mock/gpt-5-mini",
-                    "object": "chat.completion",
-                    "created": 1766138655,
-                    "choices": [
-                        {
-                            "logprobs": None,
-                            "finish_reason": "length",
-                            "native_finish_reason": "max_output_tokens",
-                            "index": 0,
-                            "message": {
-                                "role": "assistant",
-                                "content": f"Mock Content {suffix}",
-                                "refusal": None,
-                                "reasoning": f"Mock Reasoning {suffix}",
-                                "reasoning_details": [
-                                    {
-                                        "format": "openai-responses-v1",
-                                        "index": 0,
-                                        "type": "reasoning.summary",
-                                        "summary": f"Mock Summary {suffix}",
-                                    },
-                                    {
-                                        "id": f"rs_mock_{suffix}",
-                                        "format": "openai-responses-v1",
-                                        "index": 0,
-                                        "type": "reasoning.encrypted",
-                                        "data": "mock_encrypted_data",
-                                    },
-                                ],
-                            },
-                        }
-                    ],
-                    "usage": {
-                        "prompt_tokens": 10,
-                        "completion_tokens": 10,
-                        "total_tokens": 20,
-                        "cost": 0,
-                        "is_byok": False,
-                        "prompt_tokens_details": {
-                            "cached_tokens": 0,
-                            "audio_tokens": 0,
-                            "video_tokens": 0,
-                        },
-                        "cost_details": {
-                            "upstream_inference_cost": None,
-                            "upstream_inference_prompt_cost": 0,
-                            "upstream_inference_completions_cost": 0,
-                        },
-                        "completion_tokens_details": {
-                            "reasoning_tokens": 5,
-                            "image_tokens": 0,
-                        },
-                    },
-                    "cost": {
-                        "base_msats": 0,
-                        "input_msats": 0,
-                        "output_msats": 0,
-                        "total_msats": 0,
-                    },
-                }
-                return Response(json.dumps(content_dict).encode(), 200)
-
-        elif path.endswith("embeddings"):
-            raise NotImplementedError
-        elif path.endswith("responses"):
-            raise NotImplementedError
-        else:
-            raise NotImplementedError
-
-    async def fetch_models(self) -> list[Model]:
-        return [
-            Model(
-                id="mock/gpt-420-mock",
-                name="mock/gpt-420-mock",
-                created=0,
-                description="mock model for testing",
-                context_length=8192,
-                architecture=Architecture(
-                    modality="text",
-                    input_modalities=["text"],
-                    output_modalities=["text"],
-                    tokenizer="",
-                    instruct_type=None,
-                ),
-                pricing=Pricing(prompt=0.01, completion=0.01),
-            ),
-        ]
-
-    def transform_model_name(self, model_id: str) -> str:
-        return "fake-model"
-
-    async def get_balance(self) -> float | None:
-        return 420.69

routstr/upstream/helpers.py

@@ -102,6 +102,8 @@ async def get_all_models_with_overrides(
             )
             for row in override_rows
             if row.upstream_provider_id is not None
+            and row.upstream_provider_id in providers_by_id
+            and providers_by_id[row.upstream_provider_id].enabled
         }
 
     all_models: dict[str, Model] = {}
@@ -218,14 +220,6 @@ async def init_upstreams() -> list[BaseUpstreamProvider]:
         results = await asyncio.gather(*tasks)
         upstreams = [p for p in results if p is not None]
 
-        if "https://testnut.cashu.space" in settings.cashu_mints:
-            from .fake import MockUpstreamProvider
-
-            mock_provider = MockUpstreamProvider("mock", "mock")
-            await mock_provider.refresh_models_cache()
-            upstreams.append(mock_provider)
-            logger.info("Initialized MockUpstreamProvider for testnut mint")
-
         return upstreams
 
 

routstr/upstream/ppqai.py

@@ -196,6 +196,37 @@ class PPQAIUpstreamProvider(BaseUpstreamProvider):
             )
             return []
 
+    async def on_upstream_error_redirect(
+        self, status_code: int, error_message: str
+    ) -> None:
+        if "insufficient balance" in error_message.lower():
+            logger.warning(
+                f"Disabling PPQ.AI provider ({self.base_url}) due to insufficient balance",
+                extra={"error": error_message},
+            )
+            from sqlmodel import select
+
+            from ..core.db import UpstreamProviderRow, create_session
+
+            async with create_session() as session:
+                statement = select(UpstreamProviderRow).where(
+                    UpstreamProviderRow.base_url == self.base_url
+                    and UpstreamProviderRow.api_key == self.api_key
+                )
+                result = await session.exec(statement)
+                provider = result.first()
+
+                if provider:
+                    provider.enabled = False
+                    session.add(provider)
+                    await session.commit()
+
+                    # Trigger re-initialization of providers
+                    # Import here to avoid circular dependency
+                    from ..proxy import reinitialize_upstreams
+
+                    await reinitialize_upstreams()
+
     async def create_account(self) -> dict[str, object]:
         """Create a new PPQ.AI account.
 

routstr/wallet.py

@@ -313,8 +313,6 @@ async def periodic_payout() -> None:
         try:
             async with db.create_session() as session:
                 for mint_url in settings.cashu_mints:
-                    if mint_url == "https://testnut.cashu.space":
-                        continue
                     for unit in ["sat", "msat"]:
                         wallet = await get_wallet(mint_url, unit)
                         proofs = get_proofs_per_mint_and_unit(

tests/integration/test_example.py

@@ -10,7 +10,6 @@ from httpx import AsyncClient
 
 from .utils import (
     CashuTokenGenerator,
-    PerformanceValidator,
     ResponseValidator,
 )
 
@@ -159,30 +158,7 @@ async def test_error_handling(
     assert response.status_code == 401
 
 
-@pytest.mark.integration
-@pytest.mark.asyncio
-async def test_performance_requirements(integration_client: AsyncClient) -> None:
-    """Test that endpoints meet performance requirements"""
 
-    validator = PerformanceValidator()
-
-    # Test info endpoint performance
-    for i in range(50):
-        start = validator.start_timing("info_endpoint")
-        response = await integration_client.get("/")
-        validator.end_timing("info_endpoint", start)
-        assert response.status_code == 200
-
-    # Validate 95th percentile is under 500ms
-    result = validator.validate_response_time(
-        "info_endpoint", max_duration=0.5, percentile=0.95
-    )
-
-    assert result["valid"], (
-        f"Performance requirement failed: "
-        f"95th percentile was {result['percentile_time']:.3f}s "
-        f"(required < {result['max_allowed']}s)"
-    )
 
 
 @pytest.mark.integration

tests/integration/test_performance_load.py

@@ -9,6 +9,7 @@ import gc
 import statistics
 import time
 from typing import Any, Dict, List
+from unittest.mock import patch
 
 import psutil
 import pytest
@@ -105,42 +106,46 @@ class TestPerformanceBaseline:
             ("GET", "/v1/wallet/info", authenticated_client, None),
         ]
 
-        # Warm up
-        for _ in range(10):
-            await integration_client.get("/")
+        # Enable provider discovery for this test
+        with patch(
+            "routstr.core.settings.settings.providers_refresh_interval_seconds", 300
+        ):
+            # Warm up
+            for _ in range(10):
+                await integration_client.get("/")
 
-        # Test each endpoint
-        for method, path, client, data in endpoints:
-            response_times = []
+            # Test each endpoint
+            for method, path, client, data in endpoints:
+                response_times = []
 
-            for i in range(100):
-                start = time.time()
+                for i in range(100):
+                    start = time.time()
 
-                if method == "GET":
-                    response = await client.get(path)
-                else:
-                    response = await client.post(path, json=data)
+                    if method == "GET":
+                        response = await client.get(path)
+                    else:
+                        response = await client.post(path, json=data)
 
-                duration = time.time() - start
-                response_times.append(duration * 1000)  # Convert to ms
+                    duration = time.time() - start
+                    response_times.append(duration * 1000)  # Convert to ms
 
-                assert response.status_code in [200, 201]
+                    assert response.status_code in [200, 201]
 
-                if i % 10 == 0:
-                    metrics.record_system_metrics()
+                    if i % 10 == 0:
+                        metrics.record_system_metrics()
 
-            # Verify 95th percentile < 500ms
-            p95 = sorted(response_times)[int(len(response_times) * 0.95)]
-            assert p95 < 500, (
-                f"{method} {path} p95 response time {p95}ms exceeds 500ms limit"
-            )
+                # Verify 95th percentile < 500ms
+                p95 = sorted(response_times)[int(len(response_times) * 0.95)]
+                assert p95 < 500, (
+                    f"{method} {path} p95 response time {p95}ms exceeds 500ms limit"
+                )
 
-            print(f"\n{method} {path}:")
-            print(f"  Mean: {statistics.mean(response_times):.2f}ms")
-            print(f"  P95: {p95:.2f}ms")
-            print(
-                f"  P99: {sorted(response_times)[int(len(response_times) * 0.99)]:.2f}ms"
-            )
+                print(f"\n{method} {path}:")
+                print(f"  Mean: {statistics.mean(response_times):.2f}ms")
+                print(f"  P95: {p95:.2f}ms")
+                print(
+                    f"  P99: {sorted(response_times)[int(len(response_times) * 0.99)]:.2f}ms"
+                )
 
 
 @pytest.mark.integration

tests/integration/test_provider_management.py

@@ -3,7 +3,7 @@ Integration tests for provider management functionality.
 Tests GET /v1/providers/ endpoint for listing and managing providers.
 """
 
-from typing import Any
+from typing import Any, Generator
 from unittest.mock import patch
 
 import pytest
@@ -11,7 +11,7 @@ from httpx import AsyncClient
 
 from routstr.discovery import _PROVIDERS_CACHE
 
-from .utils import PerformanceValidator, ResponseValidator
+from .utils import ResponseValidator
 
 
 @pytest.fixture(autouse=True)
@@ -19,6 +19,15 @@ def _clear_providers_cache() -> None:
     _PROVIDERS_CACHE.clear()
 
 
+@pytest.fixture(autouse=True)
+def _enable_provider_discovery() -> Generator[None, Any, Any]:
+    """Enable provider discovery for all tests in this module"""
+    with patch(
+        "routstr.core.settings.settings.providers_refresh_interval_seconds", 300
+    ):
+        yield
+
+
 @pytest.mark.integration
 @pytest.mark.asyncio
 async def test_providers_endpoint_default_response(
@@ -518,46 +527,6 @@ async def test_providers_endpoint_response_format(
             assert isinstance(data_json["providers"], list)
 
 
-@pytest.mark.integration
-@pytest.mark.asyncio
-async def test_providers_endpoint_performance(integration_client: AsyncClient) -> None:
-    """Test providers endpoint meets performance requirements"""
-
-    # Mock quick responses to avoid network delays
-    mock_events: list[dict[str, Any]] = [
-        {
-            "id": f"event{i}",
-            "content": f"Provider: http://provider{i}.onion",
-            "created_at": 1234567890 + i,
-        }
-        for i in range(5)
-    ]
-
-    validator = PerformanceValidator()
-
-    with patch(
-        "routstr.discovery.query_nostr_relay_for_providers", return_value=mock_events
-    ):
-        with patch("routstr.discovery.fetch_provider_health") as mock_fetch:
-            mock_fetch.return_value = {"status_code": 200, "json": {"status": "online"}}
-
-            # Test multiple requests
-            for i in range(10):
-                start = validator.start_timing("providers_endpoint")
-                response = await integration_client.get("/v1/providers/")
-                validator.end_timing("providers_endpoint", start)
-
-                assert response.status_code == 200
-
-    # Validate performance (should be fast with mocked dependencies)
-    perf_result = validator.validate_response_time(
-        "providers_endpoint",
-        max_duration=2.0,  # Allow more time since it involves multiple operations
-        percentile=0.95,
-    )
-    assert perf_result["valid"], f"Performance requirement failed: {perf_result}"
-
-
 @pytest.mark.integration
 @pytest.mark.asyncio
 async def test_providers_endpoint_concurrent_requests(

tests/integration/test_proxy_get_endpoints.py

@@ -18,7 +18,6 @@ from routstr.core.db import ApiKey
 
 from .utils import (
     ConcurrencyTester,
-    PerformanceValidator,
 )
 
 
@@ -551,39 +550,7 @@ async def test_proxy_get_concurrent_requests(
             assert response.status_code == 200
 
 
-@pytest.mark.integration
-@pytest.mark.asyncio
-async def test_proxy_get_performance_requirements(
-    integration_client: AsyncClient, authenticated_client: AsyncClient
-) -> None:
-    """Test that GET proxy requests meet performance requirements"""
 
-    validator = PerformanceValidator()
-
-    with patch("httpx.AsyncClient.request") as mock_request:
-        mock_response = AsyncMock()
-        mock_response.status_code = 200
-        mock_response.headers = {"content-type": "application/json"}
-        mock_response.json = MagicMock(return_value={"performance": "test"})
-        mock_response.text = '{"performance": "test"}'
-        mock_response.iter_bytes = AsyncMock(return_value=[b'{"performance": "test"}'])
-        mock_request.return_value = mock_response
-
-        # Test multiple requests for performance measurement
-        for i in range(20):
-            start = validator.start_timing("proxy_get")
-            response = await authenticated_client.get(f"/v1/perf-test-{i}")
-            validator.end_timing("proxy_get", start)
-
-            assert response.status_code == 200
-
-    # Validate performance requirements
-    perf_result = validator.validate_response_time(
-        "proxy_get",
-        max_duration=1.0,  # Should complete within 1 second
-        percentile=0.95,
-    )
-    assert perf_result["valid"], f"Performance requirement failed: {perf_result}"
 
 
 @pytest.mark.integration

tests/integration/test_proxy_post_endpoints.py

@@ -15,7 +15,6 @@ from httpx import ASGITransport, AsyncClient
 
 from .utils import (
     ConcurrencyTester,
-    PerformanceValidator,
 )
 
 
@@ -290,55 +289,7 @@ async def test_proxy_post_unauthorized_access(integration_client: AsyncClient) -
     assert response.status_code in [400, 401]
 
 
-@pytest.mark.integration
-@pytest.mark.asyncio
-async def test_proxy_post_performance(
-    integration_client: AsyncClient, authenticated_client: AsyncClient
-) -> None:
-    """Test POST endpoint performance requirements"""
 
-    test_payload = {
-        "model": "gpt-3.5-turbo",
-        "messages": [{"role": "user", "content": "Performance test"}],
-    }
-
-    validator = PerformanceValidator()
-
-    with patch("httpx.AsyncClient.send") as mock_send:
-        # Mock fast responses
-        async def mock_iter_bytes(*args: Any, **kwargs: Any) -> Any:
-            yield b'{"choices": [{"message": {"content": "Fast"}}], "usage": {"total_tokens": 5}}'
-
-        mock_response = AsyncMock()
-        mock_response.status_code = 200
-        mock_response.headers = {"content-type": "application/json"}
-        response_data = {
-            "choices": [{"message": {"content": "Fast"}}],
-            "usage": {"total_tokens": 5},
-        }
-        mock_response.text = json.dumps(response_data)
-        mock_response.json = AsyncMock(return_value=response_data)
-        mock_response.iter_bytes = mock_iter_bytes
-        mock_response.aiter_bytes = mock_iter_bytes
-        mock_send.return_value = mock_response
-
-        # Run multiple requests for performance measurement
-        for i in range(20):
-            start = validator.start_timing("proxy_post")
-            response = await authenticated_client.post(
-                "/v1/chat/completions", json=test_payload
-            )
-            validator.end_timing("proxy_post", start)
-
-            assert response.status_code == 200
-
-    # Validate performance
-    perf_result = validator.validate_response_time(
-        "proxy_post",
-        max_duration=1.5,  # Allow slightly more time for POST
-        percentile=0.95,
-    )
-    assert perf_result["valid"], f"Performance requirement failed: {perf_result}"
 
 
 @pytest.mark.integration

tests/integration/test_wallet_information.py

@@ -3,7 +3,7 @@ Integration tests for wallet information retrieval endpoints.
 Tests GET /v1/wallet/ and GET /v1/wallet/info endpoints with various scenarios.
 """
 
-import time
+
 from datetime import datetime, timedelta
 from typing import Any
 
@@ -367,30 +367,4 @@ async def test_wallet_info_with_special_characters_in_headers(
     # Note: Current implementation doesn't return refund_address in response
 
 
-@pytest.mark.integration
-@pytest.mark.asyncio
-@pytest.mark.slow
-async def test_wallet_endpoints_performance(authenticated_client: AsyncClient) -> None:
-    """Test wallet endpoints meet performance requirements"""
 
-    # Warm up
-    await authenticated_client.get("/v1/wallet/")
-
-    # Measure response times
-    response_times = []
-
-    for _ in range(50):
-        start_time = time.time()
-        response = await authenticated_client.get("/v1/wallet/")
-        end_time = time.time()
-
-        assert response.status_code == 200
-        response_times.append(end_time - start_time)
-
-    # Calculate statistics
-    avg_time = sum(response_times) / len(response_times)
-    max_time = max(response_times)
-
-    # Performance assertions
-    assert avg_time < 0.1  # Average should be under 100ms
-    assert max_time < 0.5  # No request should take more than 500ms

tests/integration/test_wallet_refund.py

@@ -537,42 +537,4 @@ async def test_refund_with_expired_key(
         assert response.json()["recipient"] == "expired@ln.address"
 
 
-@pytest.mark.integration
-@pytest.mark.asyncio
-@pytest.mark.slow
-async def test_refund_performance(
-    integration_client: AsyncClient, testmint_wallet: Any
-) -> None:
-    """Test refund endpoint performance"""
 
-    import time
-
-    # Create multiple API keys
-    api_keys = []
-    for i in range(10):
-        token = await testmint_wallet.mint_tokens(100 + i)
-        # Use cashu token as Bearer auth to create API key
-        integration_client.headers["Authorization"] = f"Bearer {token}"
-        response = await integration_client.get("/v1/wallet/info")
-        assert response.status_code == 200
-        api_keys.append(response.json()["api_key"])
-
-    # Measure refund times
-    refund_times = []
-
-    for api_key in api_keys:
-        integration_client.headers["Authorization"] = f"Bearer {api_key}"
-
-        start_time = time.time()
-        response = await integration_client.post("/v1/wallet/refund")
-        end_time = time.time()
-
-        assert response.status_code == 200
-        refund_times.append(end_time - start_time)
-
-    # Performance assertions
-    avg_time = sum(refund_times) / len(refund_times)
-    max_time = max(refund_times)
-
-    assert avg_time < 0.5  # Average under 500ms
-    assert max_time < 1.0  # No refund takes more than 1 second

tests/unit/test_algorithm.py

@@ -10,7 +10,6 @@ os.environ["UPSTREAM_API_KEY"] = "test"
 from routstr.algorithm import (  # noqa: E402
     calculate_model_cost_score,
     get_provider_penalty,
-    should_prefer_model,
 )
 from routstr.payment.models import Architecture, Model, Pricing  # noqa: E402
 
@@ -100,100 +99,3 @@ def test_get_provider_penalty_openrouter() -> None:
     provider = create_test_provider("openrouter", "https://openrouter.ai/api/v1")
     penalty = get_provider_penalty(provider)
     assert penalty == 1.001
-
-
-def test_should_prefer_model_cheaper_wins() -> None:
-    """Test that cheaper model is preferred."""
-    cheap_model = create_test_model("cheap", prompt_price=0.001, completion_price=0.002)
-    expensive_model = create_test_model(
-        "expensive", prompt_price=0.03, completion_price=0.06
-    )
-
-    provider1 = create_test_provider("provider1")
-    provider2 = create_test_provider("provider2")
-
-    # Cheaper model should win
-    assert should_prefer_model(
-        cheap_model, provider1, expensive_model, provider2, "test-alias"
-    )
-
-    # More expensive model should not win
-    assert not should_prefer_model(
-        expensive_model, provider2, cheap_model, provider1, "test-alias"
-    )
-
-
-def test_should_prefer_model_exact_match_wins() -> None:
-    """Test that exact alias match beats cheaper price."""
-    # Make model IDs match the alias differently
-    exact_match = create_test_model(
-        "test-model", prompt_price=0.03, completion_price=0.06
-    )
-    no_match = create_test_model(
-        "other-model", prompt_price=0.001, completion_price=0.002
-    )
-
-    provider1 = create_test_provider("provider1")
-    provider2 = create_test_provider("provider2")
-
-    # Exact match should win even though it's more expensive
-    assert should_prefer_model(
-        exact_match, provider1, no_match, provider2, "test-model"
-    )
-
-
-def test_should_prefer_model_openrouter_slight_penalty() -> None:
-    """Test that OpenRouter has slight penalty compared to other providers."""
-    model1 = create_test_model("model1", prompt_price=0.001, completion_price=0.002)
-    model2 = create_test_model("model2", prompt_price=0.001, completion_price=0.002)
-
-    regular_provider = create_test_provider("regular", "http://provider.com")
-    openrouter_provider = create_test_provider(
-        "openrouter", "https://openrouter.ai/api/v1"
-    )
-
-    # Regular provider should be preferred over OpenRouter at same cost
-    assert should_prefer_model(
-        model1, regular_provider, model2, openrouter_provider, "test-alias"
-    )
-
-    # OpenRouter should not replace regular provider at same cost
-    assert not should_prefer_model(
-        model2, openrouter_provider, model1, regular_provider, "test-alias"
-    )
-
-
-def test_should_prefer_model_openrouter_can_win_if_cheaper() -> None:
-    """Test that OpenRouter can still win if significantly cheaper."""
-    cheap_model = create_test_model(
-        "cheap", prompt_price=0.0001, completion_price=0.0002
-    )
-    expensive_model = create_test_model(
-        "expensive", prompt_price=0.03, completion_price=0.06
-    )
-
-    regular_provider = create_test_provider("regular", "http://provider.com")
-    openrouter_provider = create_test_provider(
-        "openrouter", "https://openrouter.ai/api/v1"
-    )
-
-    # OpenRouter should win if it's much cheaper (even with penalty)
-    assert should_prefer_model(
-        cheap_model,
-        openrouter_provider,
-        expensive_model,
-        regular_provider,
-        "test-alias",
-    )
-
-
-def test_should_prefer_model_same_cost_first_wins() -> None:
-    """Test that when costs are identical, current model is kept."""
-    model1 = create_test_model("model1", prompt_price=0.001, completion_price=0.002)
-    model2 = create_test_model("model2", prompt_price=0.001, completion_price=0.002)
-
-    provider1 = create_test_provider("provider1")
-    provider2 = create_test_provider("provider2")
-
-    # When costs are equal, should not replace
-    assert not should_prefer_model(model2, provider2, model1, provider1, "test-alias")