Compare commits

..
Author SHA1 Message Date
9qeklajc 558ef52e7c Merge branch 'fix-open-claude-cost-calculation' into otrta
# Conflicts:
#	routstr/upstream/base.py
2026-03-29 23:37:52 +02:00
9qeklajc dcd924b57d Merge branch 'fix-display-api-key-infos' into otrta 2026-03-29 23:36:32 +02:00
9qeklajc ce380d2aed Merge branch 'simplify-x-cashu-refund' into otrta 2026-03-29 23:36:31 +02:00
9qeklajc 8f96cb6e85 fix handling x cashu for messages endpoint 2026-03-29 23:35:26 +02:00
9qeklajc 5174c42e7c fix claude code and open code 2026-03-28 00:48:15 +01:00
9qeklajc 8c1ab05016 fix open code cost calculation 2026-03-27 22:53:40 +01:00
31 changed files with 3219 additions and 4297 deletions
+7 -19
View File
@@ -51,26 +51,14 @@ curl https://api.routstr.com/v1/chat/completions \
## Quick Start (Docker)
If you are a node runner, start a Routstr Core instance using Docker Compose:
If you are a node runner, start a Routstr Core instance and configure upstream access in the dashboard.
1. **Prepare your `.env`**:
```bash
ADMIN_PASSWORD=mysecretpassword
NAME="My AI Node"
DESCRIPTION="Fast access to models"
NSEC=yournsec
RECEIVE_LN_ADDRESS=yourname@wallet.com
```
2. **Start the services**:
```bash
docker compose up -d
```
3. **Configure**:
Open [http://localhost:8000/admin/](http://localhost:8000/admin/) to connect your AI providers and set pricing.
For full instructions, see the **[Provider Quick Start Guide](https://docs.routstr.com/provider/quickstart/)**.
```bash
docker run -d \
--name routstr-proxy \
-p 8000:8000 \
ghcr.io/routstr/proxy:latest
```
## Development
+18 -5
View File
@@ -6,7 +6,16 @@ Production deployment guide for Routstr Provider nodes.
For production, use Docker Compose with persistent storage and optional Tor support.
Use the included `compose.yml` for a flexible setup that handles both the UI and the node execution. This is useful for development or when you want to manage Tor as a separate service.
### Unified Setup (All-in-one)
To build and run the node with the UI integrated in a single container using the multi-stage build:
```bash
docker build -f Dockerfile.full -t routstr-full .
docker run -d -p 8000:8000 --env-file .env routstr-full
```
### Advanced Setup (Separated UI & Node)
Use the included `compose.yml` for a more flexible setup that separates the UI build process from the node execution. This is useful for development or when you want to manage Tor as a separate service.
```bash
docker compose up -d
@@ -175,16 +184,20 @@ docker compose up -d
## Building from Source
### Using Docker Compose
The easiest way to build everything from source:
### Unified Image (UI + Node)
The easiest way to build everything from source into a single production-ready image:
```bash
docker compose build
docker build -f Dockerfile.full -t routstr-full .
```
### Individual Components
If you prefer building the node only (requires manual UI build first):
If you prefer building them separately or using Docker Compose:
```bash
# Build using compose
docker compose build
# Or build the node only (requires manual UI build first)
docker build -t routstr-node .
```
+24 -12
View File
@@ -35,7 +35,6 @@ ADMIN_PASSWORD=mysecretpassword
# Node Identity
NAME="My AI Node"
DESCRIPTION="Fast access to models"
NSEC=yournsec
# Lightning Payouts
RECEIVE_LN_ADDRESS=yourname@wallet.com
@@ -44,10 +43,32 @@ RECEIVE_LN_ADDRESS=yourname@wallet.com
## 2. Start the Node
The recommended way to run Routstr is using Docker Compose, which handles the node, the UI, and optional services like Tor.
You can run the pre-built image directly:
```bash
docker compose up -d
docker run -d \
--name routstr \
-p 8000:8000 \
--env-file .env \
-v routstr-data:/app/data \
ghcr.io/routstr/proxy:latest
```
*Note: The pre-built image does not contain the UI. For the all-in-one experience with the Admin Dashboard, use the Build from Source instructions below.*
### Build from Source (Recommended)
If you want to build the node and UI yourself from source, use the unified Dockerfile:
```bash
git clone https://github.com/routstr/routstr-core.git
cd routstr-core
# Edit your .env with ADMIN_PASSWORD and API keys
cp .env.example .env
nano .env
docker build -f Dockerfile.full -t routstr-local .
docker run -d -p 8000:8000 --env-file .env --name routstr routstr-local
```
Verify it's running:
@@ -56,15 +77,6 @@ Verify it's running:
curl http://localhost:8000/v1/info
```
### Build from Source (Optional)
If you've cloned the repository and want to build the images yourself:
```bash
docker compose build
docker compose up -d
```
---
## 3. Configure via Dashboard
@@ -1,33 +0,0 @@
"""add forwarded_model_id to models
Revision ID: b1c2d3e4f5a6
Revises: a776ca70e5fe
Create Date: 2026-04-05 00:00:00.000000
"""
import sqlalchemy as sa
import sqlmodel
from alembic import op
# revision identifiers, used by Alembic.
revision = "b1c2d3e4f5a6"
down_revision = "a776ca70e5fe"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.add_column(
"models",
sa.Column(
"forwarded_model_id",
sqlmodel.sql.sqltypes.AutoString(),
nullable=True,
),
)
# Backfill: set forwarded_model_id = id for all existing rows
op.execute("UPDATE models SET forwarded_model_id = id WHERE forwarded_model_id IS NULL")
def downgrade() -> None:
op.drop_column("models", "forwarded_model_id")
@@ -1,36 +0,0 @@
"""add source to cashu_transactions
Revision ID: c3d4e5f6a7b8
Revises: b1c2d3e4f5a6
Create Date: 2026-04-10 00:00:00.000000
"""
import sqlalchemy as sa
import sqlmodel
from alembic import op
# revision identifiers, used by Alembic.
revision = "c3d4e5f6a7b8"
down_revision = "b1c2d3e4f5a6"
branch_labels = None
depends_on = None
def upgrade() -> None:
conn = op.get_bind()
inspector = sa.inspect(conn)
columns = [col["name"] for col in inspector.get_columns("cashu_transactions")]
if "source" not in columns:
op.add_column(
"cashu_transactions",
sa.Column(
"source",
sqlmodel.sql.sqltypes.AutoString(),
nullable=False,
server_default="x-cashu",
),
)
def downgrade() -> None:
op.drop_column("cashu_transactions", "source")
-8
View File
@@ -217,10 +217,6 @@ def create_model_mappings(
if prefixed_id not in aliases:
aliases.append(prefixed_id)
# Register forwarded_model_id as a routable alias
if model_to_use.forwarded_model_id and model_to_use.forwarded_model_id not in aliases:
aliases.append(model_to_use.forwarded_model_id)
# Try to set each alias
for alias in aliases:
_add_candidate(alias, model_to_use, upstream)
@@ -309,10 +305,6 @@ def create_model_mappings(
if prefixed_id not in aliases:
aliases.append(prefixed_id)
# Register forwarded_model_id as a routable alias
if model_to_use.forwarded_model_id and model_to_use.forwarded_model_id not in aliases:
aliases.append(model_to_use.forwarded_model_id)
for alias in aliases:
_add_candidate(alias, model_to_use, upstream_for_override)
seen_model_provider.add(dedupe_key)
+32 -199
View File
@@ -7,7 +7,6 @@ from datetime import datetime
from typing import Optional
from fastapi import HTTPException
from sqlalchemy import case
from sqlalchemy.exc import IntegrityError
from sqlmodel import col, select, update
@@ -23,7 +22,6 @@ from .payment.cost_calculation import (
from .wallet import credit_balance, deserialize_token_from_string
logger = get_logger(__name__)
payments_logger = get_logger("routstr.payments")
# TODO: implement prepaid api key (not like it was before)
# PREPAID_API_KEY = os.environ.get("PREPAID_API_KEY", None)
@@ -586,18 +584,6 @@ async def pay_for_request(
"total_requests": billing_key.total_requests,
},
)
payments_logger.info(
"RESERVE",
extra={
"event": "reserve",
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"cost_reserved": cost_per_request,
"balance": billing_key.balance,
"reserved_balance": billing_key.reserved_balance,
"total_spent": billing_key.total_spent,
},
)
return cost_per_request
@@ -649,17 +635,6 @@ async def revert_pay_for_request(
await session.refresh(billing_key)
if billing_key.hashed_key != key.hashed_key:
await session.refresh(key)
payments_logger.info(
"REVERT",
extra={
"event": "revert",
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"cost_reverted": cost_per_request,
"balance": billing_key.balance,
"reserved_balance": billing_key.reserved_balance,
},
)
return True
@@ -753,51 +728,24 @@ async def adjust_payment_for_tokens(
},
)
# Finalize by releasing reservation and charging max cost
if billing_key.reserved_balance < deducted_max_cost:
logger.error(
"reserved_balance below deducted_max_cost before MaxCost finalization — clamping to 0",
extra={
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"reserved_balance": billing_key.reserved_balance,
"deducted_max_cost": deducted_max_cost,
"total_cost_msats": cost.total_msats,
"balance": billing_key.balance,
"total_spent": billing_key.total_spent,
"model": model,
},
)
safe_reserved = case(
(col(ApiKey.reserved_balance) >= deducted_max_cost,
col(ApiKey.reserved_balance) - deducted_max_cost),
else_=0,
)
finalize_stmt = (
update(ApiKey)
.where(col(ApiKey.hashed_key) == billing_key.hashed_key)
.values(
reserved_balance=safe_reserved,
balance=col(ApiKey.balance) - cost.total_msats,
total_spent=col(ApiKey.total_spent) + cost.total_msats,
)
)
result = await session.exec(finalize_stmt) # type: ignore[call-overload]
# Also update total_spent and reserved_balance on the child key if it's different
# Also update total_spent and balance on the child key if it's different
if billing_key.hashed_key != key.hashed_key:
child_safe_reserved = case(
(col(ApiKey.reserved_balance) >= deducted_max_cost,
col(ApiKey.reserved_balance) - deducted_max_cost),
else_=0,
)
child_stmt = (
update(ApiKey)
.where(col(ApiKey.hashed_key) == key.hashed_key)
.values(
total_spent=col(ApiKey.total_spent) + cost.total_msats,
reserved_balance=child_safe_reserved,
balance=col(ApiKey.balance) - cost.total_msats,
)
)
await session.exec(child_stmt) # type: ignore[call-overload]
@@ -832,23 +780,6 @@ async def adjust_payment_for_tokens(
"model": model,
},
)
payments_logger.info(
"FINALIZE",
extra={
"event": "finalize",
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"model": model,
"cost_reserved": deducted_max_cost,
"cost_charged": cost.total_msats,
"input_tokens": cost.input_tokens,
"output_tokens": cost.output_tokens,
"balance": billing_key.balance,
"reserved_balance": billing_key.reserved_balance,
"total_spent": billing_key.total_spent,
"finalize_type": "max_cost",
},
)
return cost.dict()
case CostData() as cost:
@@ -882,51 +813,24 @@ async def adjust_payment_for_tokens(
"model": model,
},
)
if billing_key.reserved_balance < deducted_max_cost:
logger.error(
"reserved_balance below deducted_max_cost on exact-cost finalization — clamping to 0",
extra={
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"reserved_balance": billing_key.reserved_balance,
"deducted_max_cost": deducted_max_cost,
"total_cost_msats": total_cost_msats,
"balance": billing_key.balance,
"total_spent": billing_key.total_spent,
"model": model,
},
)
exact_safe_reserved = case(
(col(ApiKey.reserved_balance) >= deducted_max_cost,
col(ApiKey.reserved_balance) - deducted_max_cost),
else_=0,
)
finalize_stmt = (
update(ApiKey)
.where(col(ApiKey.hashed_key) == billing_key.hashed_key)
.values(
reserved_balance=exact_safe_reserved,
balance=col(ApiKey.balance) - total_cost_msats,
total_spent=col(ApiKey.total_spent) + total_cost_msats,
)
)
await session.exec(finalize_stmt) # type: ignore[call-overload]
# Also update total_spent and reserved_balance on the child key if it's different
# Also update total_spent and balance on the child key if it's different
if billing_key.hashed_key != key.hashed_key:
child_exact_safe_reserved = case(
(col(ApiKey.reserved_balance) >= deducted_max_cost,
col(ApiKey.reserved_balance) - deducted_max_cost),
else_=0,
)
child_stmt = (
update(ApiKey)
.where(col(ApiKey.hashed_key) == key.hashed_key)
.values(
total_spent=col(ApiKey.total_spent) + total_cost_msats,
reserved_balance=child_exact_safe_reserved,
balance=col(ApiKey.balance) - total_cost_msats,
)
)
await session.exec(child_stmt) # type: ignore[call-overload]
@@ -935,55 +839,44 @@ async def adjust_payment_for_tokens(
await session.refresh(billing_key)
if billing_key.hashed_key != key.hashed_key:
await session.refresh(key)
payments_logger.info(
"FINALIZE",
extra={
"event": "finalize",
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"model": model,
"cost_reserved": deducted_max_cost,
"cost_charged": total_cost_msats,
"input_tokens": cost.input_tokens,
"output_tokens": cost.output_tokens,
"balance": billing_key.balance,
"reserved_balance": billing_key.reserved_balance,
"total_spent": billing_key.total_spent,
"finalize_type": "exact",
},
)
return cost.dict()
# actual cost exceeded discounted reservation (due to tolerance_percentage)
# this should never happen why do we handle this???
if cost_difference > 0:
# Always release the reservation and charge min(actual_cost, balance).
# Using a CASE expression makes this a single atomic UPDATE — no
# multi-level fallback needed and balance can never go negative.
chargeable = case(
(col(ApiKey.balance) >= total_cost_msats, total_cost_msats),
else_=col(ApiKey.balance),
# Need to charge more than reserved, finalize by releasing reservation and charging total
logger.info(
"Additional charge required for token usage",
extra={
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"additional_charge": cost_difference,
"current_balance": billing_key.balance,
"sufficient_balance": billing_key.balance >= cost_difference,
"model": model,
},
)
finalize_stmt = (
update(ApiKey)
.where(col(ApiKey.hashed_key) == billing_key.hashed_key)
.where(col(ApiKey.reserved_balance) >= deducted_max_cost)
.values(
reserved_balance=col(ApiKey.reserved_balance) - deducted_max_cost,
balance=col(ApiKey.balance) - chargeable,
total_spent=col(ApiKey.total_spent) + chargeable,
reserved_balance=col(ApiKey.reserved_balance)
- deducted_max_cost,
balance=col(ApiKey.balance) - total_cost_msats,
total_spent=col(ApiKey.total_spent) + total_cost_msats,
)
)
result = await session.exec(finalize_stmt) # type: ignore[call-overload]
# Also update total_spent and reserved_balance on the child key if it's different
if billing_key.hashed_key != key.hashed_key:
child_stmt = (
update(ApiKey)
.where(col(ApiKey.hashed_key) == key.hashed_key)
.where(col(ApiKey.reserved_balance) >= deducted_max_cost)
.values(
reserved_balance=col(ApiKey.reserved_balance) - deducted_max_cost,
total_spent=col(ApiKey.total_spent) + min(billing_key.balance, total_cost_msats),
total_spent=col(ApiKey.total_spent) + total_cost_msats,
reserved_balance=col(ApiKey.reserved_balance)
- deducted_max_cost,
)
)
await session.exec(child_stmt) # type: ignore[call-overload]
@@ -991,10 +884,11 @@ async def adjust_payment_for_tokens(
await session.commit()
if result.rowcount:
cost.total_msats = total_cost_msats
await session.refresh(billing_key)
if billing_key.hashed_key != key.hashed_key:
await session.refresh(key)
cost.total_msats = total_cost_msats
logger.info(
"Finalized payment with additional charge",
extra={
@@ -1005,28 +899,9 @@ async def adjust_payment_for_tokens(
"model": model,
},
)
payments_logger.info(
"FINALIZE",
extra={
"event": "finalize",
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"model": model,
"cost_reserved": deducted_max_cost,
"cost_charged": total_cost_msats,
"input_tokens": cost.input_tokens,
"output_tokens": cost.output_tokens,
"balance": billing_key.balance,
"reserved_balance": billing_key.reserved_balance,
"total_spent": billing_key.total_spent,
"finalize_type": "overrun",
},
)
else:
# Guard fired: reservation was already released by a concurrent
# finalization for this key. Nothing left to do.
logger.warning(
"Finalization skipped - reservation already released",
"Failed to finalize additional charge - releasing reservation",
extra={
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
@@ -1034,6 +909,7 @@ async def adjust_payment_for_tokens(
"model": model,
},
)
await release_reservation_only()
else:
# Refund some of the base cost
refund = abs(cost_difference)
@@ -1048,33 +924,12 @@ async def adjust_payment_for_tokens(
},
)
if billing_key.reserved_balance < deducted_max_cost:
logger.error(
"reserved_balance below deducted_max_cost on refund finalization — clamping to 0",
extra={
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"reserved_balance": billing_key.reserved_balance,
"deducted_max_cost": deducted_max_cost,
"total_cost_msats": total_cost_msats,
"refund_amount": refund,
"balance": billing_key.balance,
"total_spent": billing_key.total_spent,
"model": model,
},
)
refund_safe_reserved = case(
(col(ApiKey.reserved_balance) >= deducted_max_cost,
col(ApiKey.reserved_balance) - deducted_max_cost),
else_=0,
)
refund_stmt = (
update(ApiKey)
.where(col(ApiKey.hashed_key) == billing_key.hashed_key)
.values(
reserved_balance=refund_safe_reserved,
reserved_balance=col(ApiKey.reserved_balance)
- deducted_max_cost,
balance=col(ApiKey.balance) - total_cost_msats,
total_spent=col(ApiKey.total_spent) + total_cost_msats,
)
@@ -1083,17 +938,13 @@ async def adjust_payment_for_tokens(
# Also update total_spent and reserved_balance on the child key if it's different
if billing_key.hashed_key != key.hashed_key:
child_refund_safe_reserved = case(
(col(ApiKey.reserved_balance) >= deducted_max_cost,
col(ApiKey.reserved_balance) - deducted_max_cost),
else_=0,
)
child_stmt = (
update(ApiKey)
.where(col(ApiKey.hashed_key) == key.hashed_key)
.values(
total_spent=col(ApiKey.total_spent) + total_cost_msats,
reserved_balance=child_refund_safe_reserved,
reserved_balance=col(ApiKey.reserved_balance)
- deducted_max_cost,
)
)
await session.exec(child_stmt) # type: ignore[call-overload]
@@ -1130,24 +981,6 @@ async def adjust_payment_for_tokens(
"model": model,
},
)
payments_logger.info(
"FINALIZE",
extra={
"event": "finalize",
"key_hash": key.hashed_key[:8] + "...",
"billing_key_hash": billing_key.hashed_key[:8] + "...",
"model": model,
"cost_reserved": deducted_max_cost,
"cost_charged": total_cost_msats,
"refunded": refund,
"input_tokens": cost.input_tokens,
"output_tokens": cost.output_tokens,
"balance": billing_key.balance,
"reserved_balance": billing_key.reserved_balance,
"total_spent": billing_key.total_spent,
"finalize_type": "refund",
},
)
return cost.dict()
+23 -89
View File
@@ -10,13 +10,7 @@ from pydantic import BaseModel
from sqlmodel import select
from .auth import get_billing_key, validate_bearer_key
from .core.db import (
ApiKey,
AsyncSession,
CashuTransaction,
get_session,
store_cashu_transaction,
)
from .core.db import ApiKey, AsyncSession, CashuTransaction, get_session
from .core.logging import get_logger
from .core.settings import settings
from .lightning import lightning_router
@@ -211,57 +205,37 @@ async def _refund_cache_set(authorization: str, value: dict[str, str]) -> None:
_refund_cache[key] = (expiry, value)
@router.post("/refund", response_model=None)
@router.post("/refund")
async def refund_wallet_endpoint(
authorization: Annotated[str | None, Header()] = None,
authorization: Annotated[str, Header(...)],
x_cashu: Annotated[str | None, Header()] = None,
session: AsyncSession = Depends(get_session),
) -> JSONResponse | dict[str, str]:
if x_cashu:
# Find the "in" transaction by the original payment token
in_tx_result = await session.exec(
select(CashuTransaction).where(
CashuTransaction.token == x_cashu,
CashuTransaction.type == "in",
)
)
in_tx = in_tx_result.first()
if in_tx is None:
raise HTTPException(status_code=404, detail="Refund not found")
# Use the request_id to find the associated "out" (refund) transaction
if in_tx.request_id is None:
raise HTTPException(status_code=404, detail="Refund not found")
out_tx_result = await session.exec(
select(CashuTransaction).where(
CashuTransaction.request_id == in_tx.request_id,
CashuTransaction.type == "out",
)
)
out_tx = out_tx_result.first()
if out_tx is None:
raise HTTPException(status_code=404, detail="Refund not found")
if out_tx.swept:
raise HTTPException(status_code=410, detail="Refund has been swept")
out_tx.collected = True
session.add(out_tx)
await session.commit()
body: dict[str, str] = {"token": out_tx.token}
if out_tx.unit == "sat":
body["sats"] = str(out_tx.amount)
else:
body["msats"] = str(out_tx.amount)
return JSONResponse(content=body, headers={"X-Cashu": out_tx.token})
if authorization is None or not authorization.startswith("Bearer "):
) -> dict[str, str]:
if not authorization.startswith("Bearer "):
raise HTTPException(
status_code=401,
detail="Invalid authorization. Use 'Bearer <cashu-token>' or 'Bearer <api-key>'",
)
bearer_value: str = authorization[7:]
if x_cashu:
payment_token_hash = hashlib.sha256(x_cashu.strip().encode()).hexdigest()
result = await session.get(CashuTransaction, payment_token_hash)
if result is None:
raise HTTPException(status_code=404, detail="Refund not found")
if result.swept:
raise HTTPException(status_code=410, detail="Refund has been swept")
result.collected = True
session.add(result)
await session.commit()
body: dict[str, str] = {"token": result.token}
if result.unit == "sat":
body["sats"] = str(result.amount)
else:
body["msats"] = str(result.amount)
return JSONResponse(content=body, headers={"X-Cashu": result.token})
key: ApiKey = await validate_bearer_key(bearer_value, session)
if key.total_balance <= 0:
@@ -274,12 +248,6 @@ async def refund_wallet_endpoint(
detail="Cannot refund child key. Please refund the parent key instead.",
)
if key.reserved_balance > 0:
raise HTTPException(
status_code=400,
detail="Cannot refund key. There are ongoing requests for this api key.",
)
remaining_balance_msats: int = key.total_balance
if key.refund_currency == "sat":
@@ -316,17 +284,6 @@ async def refund_wallet_endpoint(
else:
result["msats"] = str(remaining_balance_msats)
if "token" in result:
logger.info(
"refund_wallet_endpoint: cashu token issued",
extra={
"path": "/v1/wallet/refund",
"token": result["token"],
"amount": remaining_balance,
"currency": key.refund_currency or "sat",
},
)
except HTTPException:
# Re-raise HTTP exceptions (like 400 for balance too small)
raise
@@ -345,34 +302,11 @@ async def refund_wallet_endpoint(
await _refund_cache_set(bearer_value, result)
previous_reserved_balance = key.reserved_balance
key.balance = 0
key.reserved_balance = 0
session.add(key)
await session.commit()
if "token" in result:
try:
await store_cashu_transaction(
token=result["token"],
amount=remaining_balance,
unit=key.refund_currency or "sat",
mint_url=key.refund_mint_url,
typ="out",
collected=False,
source="apikey",
)
except Exception:
pass # store_cashu_transaction already logs
logger.info(
"refund_wallet_endpoint: refund successful",
extra={
"refunded_msats": remaining_balance_msats,
"previous_reserved_balance": previous_reserved_balance,
},
)
return result
-3
View File
@@ -295,7 +295,6 @@ class ModelCreate(BaseModel):
canonical_slug: str | None = None
alias_ids: list[str] | None = None
enabled: bool = True
forwarded_model_id: str | None = None
@admin_router.post(
@@ -340,7 +339,6 @@ async def upsert_provider_model(
json.dumps(payload.alias_ids) if payload.alias_ids else None
)
existing_row.enabled = payload.enabled
existing_row.forwarded_model_id = payload.forwarded_model_id or payload.id
session.add(existing_row)
await session.commit()
@@ -373,7 +371,6 @@ async def upsert_provider_model(
),
upstream_provider_id=provider_id,
enabled=payload.enabled,
forwarded_model_id=payload.forwarded_model_id or payload.id,
)
session.add(row)
await session.commit()
-22
View File
@@ -10,7 +10,6 @@ from alembic import command
from alembic.config import Config
from alembic.util.exc import CommandError
from sqlalchemy import UniqueConstraint
from sqlalchemy.exc import OperationalError
from sqlalchemy.ext.asyncio.engine import create_async_engine
from sqlmodel import Field, Relationship, SQLModel, func, select, update
from sqlmodel.ext.asyncio.session import AsyncSession
@@ -106,10 +105,6 @@ class ModelRow(SQLModel, table=True): # type: ignore
default=None, description="JSON array of model alias IDs"
)
enabled: bool = Field(default=True, description="Whether this model is enabled")
forwarded_model_id: str | None = Field(
default=None,
description="Model ID to use when forwarding requests to upstream provider. Defaults to id if not set.",
)
upstream_provider: "UpstreamProviderRow" = Relationship(back_populates="models")
@@ -155,10 +150,6 @@ class CashuTransaction(SQLModel, table=True): # type: ignore
)
collected: bool = Field(default=False)
swept: bool = Field(default=False)
source: str = Field(
default="x-cashu",
description="Payment source: x-cashu or apikey",
)
async def store_cashu_transaction(
@@ -170,7 +161,6 @@ async def store_cashu_transaction(
request_id: str | None = None,
collected: bool = False,
created_at: int | None = None,
source: str = "x-cashu",
) -> None:
try:
async with create_session() as session:
@@ -183,7 +173,6 @@ async def store_cashu_transaction(
request_id=request_id,
collected=collected,
created_at=created_at or int(time.time()),
source=source,
)
session.add(tx)
await session.commit()
@@ -338,17 +327,6 @@ def run_migrations() -> None:
command.stamp(alembic_cfg, "head")
else:
raise
except OperationalError as e:
if "duplicate column name" in str(e).lower():
logger.warning(
"Migration hit a column that already exists (likely added via "
"create_all on another branch). Stamping to current head.",
extra={"error": str(e)},
)
_clear_alembic_version()
command.stamp(alembic_cfg, "head")
else:
raise
logger.info("Database migrations completed successfully")
+8
View File
@@ -38,6 +38,11 @@ class LoggingMiddleware(BaseHTTPMiddleware):
except Exception:
pass
# Extract request info
client_host = None
if request.client:
client_host = request.client.host
# Log incoming request
logger.info(
"Incoming request",
@@ -46,6 +51,7 @@ class LoggingMiddleware(BaseHTTPMiddleware):
"method": request.method,
"path": request.url.path,
"query_params": dict(request.query_params),
"client_host": client_host,
"headers": {
k: v
for k, v in request.headers.items()
@@ -94,6 +100,7 @@ class LoggingMiddleware(BaseHTTPMiddleware):
"path": request.url.path,
"status_code": response.status_code,
"duration_ms": round(duration * 1000, 2),
"client_host": client_host,
},
)
if hasattr(response, "headers"):
@@ -113,6 +120,7 @@ class LoggingMiddleware(BaseHTTPMiddleware):
"method": request.method,
"path": request.url.path,
"duration_ms": round(duration * 1000, 2),
"client_host": client_host,
"error": str(e),
"error_type": type(e).__name__,
},
+1 -1
View File
@@ -74,7 +74,7 @@ class Settings(BaseSettings):
enable_pricing_refresh: bool = Field(default=True, env="ENABLE_PRICING_REFRESH")
enable_models_refresh: bool = Field(default=True, env="ENABLE_MODELS_REFRESH")
refund_cache_ttl_seconds: int = Field(default=3600, env="REFUND_CACHE_TTL_SECONDS")
refund_sweep_ttl_seconds: int = Field(default=604800, env="REFUND_SWEEP_TTL_SECONDS")
refund_sweep_ttl_seconds: int = Field(default=86400, env="REFUND_SWEEP_TTL_SECONDS")
# Logging
log_level: str = Field(default="INFO", env="LOG_LEVEL")
+18 -41
View File
@@ -109,20 +109,12 @@ async def calculate_cost( # todo: can be sync
)
usd_cost = 0.0
input_usd = 0.0
output_usd = 0.0
# Prioritize cost_details.upstream_inference_cost
if "cost_details" in usage_data:
usd_cost = float(
usage_data["cost_details"].get("upstream_inference_cost", 0) or 0
)
input_usd = float(
usage_data["cost_details"].get("upstream_inference_prompt_cost", 0) or 0
)
output_usd = float(
usage_data["cost_details"].get("upstream_inference_completions_cost", 0)
or 0
)
# Fallback to cost field if upstream_inference_cost is 0
if usd_cost == 0 and "cost" in usage_data:
@@ -131,34 +123,12 @@ async def calculate_cost( # todo: can be sync
except Exception:
pass
MSATS_PER_1K_INPUT_TOKENS: float = (
float(settings.fixed_per_1k_input_tokens) * 1000.0
)
MSATS_PER_1K_OUTPUT_TOKENS: float = (
float(settings.fixed_per_1k_output_tokens) * 1000.0
)
if usd_cost > 0:
try:
sats_per_usd = 1.0 / sats_usd_price()
cost_in_sats = usd_cost * sats_per_usd
cost_in_msats = math.ceil(cost_in_sats * 1000)
input_msats = 0
output_msats = 0
if input_usd > 0 or output_usd > 0:
input_msats = int((input_usd * sats_per_usd) * 1000)
output_msats = int((output_usd * sats_per_usd) * 1000)
else:
total_tokens = input_tokens + output_tokens
if total_tokens > 0:
input_ratio = input_tokens / total_tokens
input_msats = int(cost_in_msats * input_ratio)
output_msats = cost_in_msats - input_msats
else:
output_msats = cost_in_msats
logger.info(
"Using cost from usage data/details",
extra={
@@ -170,9 +140,9 @@ async def calculate_cost( # todo: can be sync
)
return CostData(
base_msats=0,
input_msats=input_msats,
output_msats=output_msats,
base_msats=-1,
input_msats=-1, # Cost field doesn't break down by token type
output_msats=-1,
total_msats=cost_in_msats,
total_usd=usd_cost,
input_tokens=input_tokens,
@@ -189,6 +159,13 @@ async def calculate_cost( # todo: can be sync
)
# Fall through to token-based calculation
MSATS_PER_1K_INPUT_TOKENS: float = (
float(settings.fixed_per_1k_input_tokens) * 1000.0
)
MSATS_PER_1K_OUTPUT_TOKENS: float = (
float(settings.fixed_per_1k_output_tokens) * 1000.0
)
if not settings.fixed_pricing:
response_model = response_data.get("model", "")
logger.debug(
@@ -254,10 +231,10 @@ async def calculate_cost( # todo: can be sync
output_tokens=output_tokens,
)
calc_input_msats = round(input_tokens / 1000 * MSATS_PER_1K_INPUT_TOKENS, 3)
input_msats = round(input_tokens / 1000 * MSATS_PER_1K_INPUT_TOKENS, 3)
calc_output_msats = round(output_tokens / 1000 * MSATS_PER_1K_OUTPUT_TOKENS, 3)
token_based_cost = math.ceil(calc_input_msats + calc_output_msats)
output_msats = round(output_tokens / 1000 * MSATS_PER_1K_OUTPUT_TOKENS, 3)
token_based_cost = math.ceil(input_msats + output_msats)
total_usd = (token_based_cost / 1000.0) * sats_usd_price()
logger.info(
@@ -265,8 +242,8 @@ async def calculate_cost( # todo: can be sync
extra={
"input_tokens": input_tokens,
"output_tokens": output_tokens,
"input_cost_msats": calc_input_msats,
"output_cost_msats": calc_output_msats,
"input_cost_msats": input_msats,
"output_cost_msats": output_msats,
"total_cost_msats": token_based_cost,
"total_usd": total_usd,
"model": response_data.get("model", "unknown"),
@@ -275,8 +252,8 @@ async def calculate_cost( # todo: can be sync
return CostData(
base_msats=0,
input_msats=int(calc_input_msats),
output_msats=int(calc_output_msats),
input_msats=int(input_msats),
output_msats=int(output_msats),
total_msats=token_based_cost,
total_usd=total_usd,
input_tokens=input_tokens,
+1 -10
View File
@@ -60,7 +60,6 @@ class Model(BaseModel):
upstream_provider_id: int | str | None = None
canonical_slug: str | None = None
alias_ids: list[str] | None = None
forwarded_model_id: str | None = None
def __hash__(self) -> int:
return hash(self.id)
@@ -178,7 +177,6 @@ def _row_to_model(
upstream_provider_id=row.upstream_provider_id,
canonical_slug=getattr(row, "canonical_slug", None),
alias_ids=json.loads(row.alias_ids) if row.alias_ids else None,
forwarded_model_id=getattr(row, "forwarded_model_id", None) or row.id,
)
if apply_provider_fee:
@@ -331,7 +329,6 @@ def _update_model_sats_pricing(model: Model, sats_to_usd: float) -> Model:
upstream_provider_id=model.upstream_provider_id,
canonical_slug=model.canonical_slug,
alias_ids=model.alias_ids,
forwarded_model_id=model.forwarded_model_id,
)
except Exception as e:
logger.error(
@@ -414,10 +411,4 @@ async def models(session: AsyncSession = Depends(get_session)) -> dict:
from ..proxy import get_unique_models
items = get_unique_models()
data = []
for model in items:
m = model.dict()
if model.forwarded_model_id:
m["id"] = model.forwarded_model_id
data.append(m)
return {"data": data}
return {"data": items}
+3 -10
View File
@@ -207,7 +207,7 @@ async def proxy(
elif auth := headers.get("authorization", None):
key = await get_bearer_token_key(
headers, path, session, auth, max_cost_for_model, model_id
headers, path, session, auth, max_cost_for_model
)
else:
@@ -387,12 +387,7 @@ async def proxy(
async def get_bearer_token_key(
headers: dict,
path: str,
session: AsyncSession,
auth: str,
min_cost: int = 0,
model_id: str = "unknown",
headers: dict, path: str, session: AsyncSession, auth: str, min_cost: int = 0
) -> ApiKey:
"""Handle bearer token authentication proxy requests."""
parts = auth.split()
@@ -462,13 +457,11 @@ async def get_bearer_token_key(
except Exception as e:
key_preview = bearer_key[:20] + "..." if len(bearer_key) > 20 else bearer_key
logger.error(
f"Bearer token validation failed: {type(e).__name__}: {e} path={path} model={model_id!r} min_cost={min_cost} key={key_preview!r}",
f"Bearer token validation failed: {type(e).__name__}: {e} path={path} key={key_preview!r}",
extra={
"error": str(e),
"error_type": type(e).__name__,
"path": path,
"model_id": model_id,
"min_cost_msat": min_cost,
"bearer_key_preview": key_preview,
},
)
+919 -807
View File
File diff suppressed because it is too large Load Diff
+1 -15
View File
@@ -155,20 +155,6 @@ async def swap_to_primary_mint(
raise ValueError("Invalid unit")
primary_wallet = await get_wallet(settings.primary_mint, settings.primary_mint_unit)
# If the token is already from the primary mint, we don't need to swap
# and we definitely don't want to calculate or pay fees.
if token_obj.mint == settings.primary_mint:
logger.info(
"swap_to_primary_mint: token already on primary mint, skipping swap",
extra={
"mint": token_obj.mint,
"amount": token_amount,
"unit": token_obj.unit,
},
)
await token_wallet.split(proofs=token_obj.proofs, amount=0, include_fees=True)
return token_amount, token_obj.unit, token_obj.mint
minted_amount = await _calculate_swap_amount(
amount_msat,
token_obj.unit,
@@ -549,7 +535,7 @@ async def periodic_refund_sweep() -> None:
except Exception as e:
error_msg = str(e).lower()
if "already spent" in error_msg:
refund.collected = True
refund.swept = True
session.add(refund)
logger.info(
"Refund already spent (client collected), marking swept",
-7
View File
@@ -380,13 +380,6 @@ async def integration_session(
yield session
@pytest_asyncio.fixture
async def patched_db_engine(integration_engine: Any) -> AsyncGenerator[None, None]:
"""Patch the global db engine so create_session() uses the test engine."""
with patch("routstr.core.db.engine", integration_engine):
yield
class DatabaseSnapshot:
"""Utility to capture and compare database states"""
@@ -1,369 +0,0 @@
"""
Integration tests for the balance-goes-negative bug in adjust_payment_for_tokens.
Root cause: when actual token cost exceeds the discounted reservation
(cost_difference > 0, caused by tolerance_percentage discounting the reservation),
the finalization UPDATE had no WHERE guard on balance, allowing balance to go negative.
Fix: added `.where(col(ApiKey.balance) >= total_cost_msats)` so the UPDATE is a no-op
when balance is insufficient, then falls back to charging only deducted_max_cost.
"""
import uuid
from unittest.mock import patch
import pytest
from sqlmodel.ext.asyncio.session import AsyncSession
from routstr.core.db import ApiKey
from routstr.payment.cost_calculation import CostData
def _make_key(balance: int, reserved: int) -> ApiKey:
return ApiKey(
hashed_key=f"test_{uuid.uuid4().hex}",
balance=balance,
reserved_balance=reserved,
total_spent=0,
total_requests=1,
)
async def _refresh(session: AsyncSession, key: ApiKey) -> ApiKey:
await session.refresh(key)
return key
# ---------------------------------------------------------------------------
# Helper: build a CostData where token cost > deducted_max_cost
# ---------------------------------------------------------------------------
def _cost_data(total_msats: int) -> CostData:
return CostData(
base_msats=0,
input_msats=total_msats // 2,
output_msats=total_msats - total_msats // 2,
total_msats=total_msats,
total_usd=0.0,
input_tokens=100,
output_tokens=100,
)
# ---------------------------------------------------------------------------
# Test 1 — exact reproduction of the bug
#
# Setup: balance == deducted_max_cost (user has just enough for the reservation,
# nothing extra). Actual token cost is 1% higher (tolerance_percentage).
#
# Before fix: balance -= total_cost_msats → goes negative.
# After fix: WHERE balance >= total_cost_msats fails → fallback charges
# deducted_max_cost → balance reaches 0, never negative.
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_balance_never_negative_when_cost_exceeds_reservation(
integration_session: AsyncSession,
) -> None:
"""Balance must not go negative when actual token cost > discounted reservation."""
from routstr.auth import adjust_payment_for_tokens
deducted_max_cost = 990 # reserved (1% below true max of 1000)
actual_token_cost = 1000 # actual cost at true max
# User has balance exactly equal to the reservation — tight budget
key = _make_key(balance=deducted_max_cost, reserved=deducted_max_cost)
integration_session.add(key)
await integration_session.commit()
response_data = {"model": "test-model", "usage": {"prompt_tokens": 100, "completion_tokens": 100}}
with patch(
"routstr.auth.calculate_cost",
return_value=_cost_data(actual_token_cost),
):
await adjust_payment_for_tokens(key, response_data, integration_session, deducted_max_cost)
await _refresh(integration_session, key)
assert key.balance >= 0, f"Balance went negative: {key.balance}"
assert key.reserved_balance >= 0, f"Reserved balance went negative: {key.reserved_balance}"
assert key.reserved_balance == 0, "Reservation must be fully released after finalization"
# ---------------------------------------------------------------------------
# Test 2 — balance is ZERO after the reservation is accounted for
# (absolute floor case)
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_balance_floor_at_zero_on_overrun(
integration_session: AsyncSession,
) -> None:
"""When balance exactly covers deducted_max_cost and cost overruns, balance reaches 0 not negative."""
from routstr.auth import adjust_payment_for_tokens
deducted_max_cost = 500
actual_token_cost = 550 # 10% overrun
key = _make_key(balance=500, reserved=500)
integration_session.add(key)
await integration_session.commit()
response_data = {"model": "test-model", "usage": {"prompt_tokens": 50, "completion_tokens": 50}}
with patch(
"routstr.auth.calculate_cost",
return_value=_cost_data(actual_token_cost),
):
await adjust_payment_for_tokens(key, response_data, integration_session, deducted_max_cost)
await _refresh(integration_session, key)
assert key.balance == 0, (
f"Expected balance=0 (charged deducted_max_cost fallback), got {key.balance}"
)
assert key.reserved_balance == 0, f"Reserved balance should be 0, got {key.reserved_balance}"
# Fallback charges deducted_max_cost
assert key.total_spent == deducted_max_cost, (
f"Expected total_spent={deducted_max_cost}, got {key.total_spent}"
)
# ---------------------------------------------------------------------------
# Test 3 — balance has enough room: full token cost should be charged
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_full_cost_charged_when_balance_sufficient_for_overrun(
integration_session: AsyncSession,
) -> None:
"""When balance covers total_cost_msats, the full amount is charged (not just deducted_max_cost)."""
from routstr.auth import adjust_payment_for_tokens
deducted_max_cost = 990
actual_token_cost = 1000
# User has extra balance beyond the reservation
key = _make_key(balance=2000, reserved=990)
integration_session.add(key)
await integration_session.commit()
response_data = {"model": "test-model", "usage": {"prompt_tokens": 100, "completion_tokens": 100}}
with patch(
"routstr.auth.calculate_cost",
return_value=_cost_data(actual_token_cost),
):
await adjust_payment_for_tokens(key, response_data, integration_session, deducted_max_cost)
await _refresh(integration_session, key)
assert key.balance >= 0, f"Balance went negative: {key.balance}"
assert key.reserved_balance == 0, f"Reservation not released: {key.reserved_balance}"
assert key.total_spent == actual_token_cost, (
f"Expected full charge of {actual_token_cost}, got {key.total_spent}"
)
assert key.balance == 2000 - actual_token_cost, (
f"Expected balance={2000 - actual_token_cost}, got {key.balance}"
)
# ---------------------------------------------------------------------------
# Test 4 — concurrent finalizations with cost overrun
#
# Multiple requests finish concurrently. Each has a small overrun.
# None should drive balance negative.
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_concurrent_cost_overruns_never_negative(
integration_session: AsyncSession,
patched_db_engine: None,
) -> None:
"""Concurrent finalization with cost overruns must never produce negative balance."""
import asyncio
from routstr.auth import adjust_payment_for_tokens, pay_for_request
from routstr.core.db import create_session
deducted_max_cost = 990
actual_token_cost = 1000
n_requests = 5
# Fund the key with exactly enough for n_requests reservations + a tiny buffer
starting_balance = deducted_max_cost * n_requests
key_hash = f"test_concurrent_{uuid.uuid4().hex}"
async with create_session() as session:
key = ApiKey(
hashed_key=key_hash,
balance=starting_balance,
reserved_balance=0,
total_spent=0,
total_requests=0,
)
session.add(key)
await session.commit()
# Reserve n_requests slots (sequentially, as pay_for_request is atomic)
async with create_session() as session:
key_to_reserve = await session.get(ApiKey, key_hash)
assert key_to_reserve is not None
for _ in range(n_requests):
await pay_for_request(key_to_reserve, deducted_max_cost, session)
await session.refresh(key_to_reserve)
# Now finalize all concurrently with cost overrun
async def finalize() -> None:
response_data = {
"model": "test-model",
"usage": {"prompt_tokens": 100, "completion_tokens": 100},
}
async with create_session() as session:
fresh_key = await session.get(ApiKey, key_hash)
assert fresh_key is not None
with patch(
"routstr.auth.calculate_cost",
return_value=_cost_data(actual_token_cost),
):
await adjust_payment_for_tokens(
fresh_key, response_data, session, deducted_max_cost
)
await asyncio.gather(*[finalize() for _ in range(n_requests)])
async with create_session() as session:
final_key = await session.get(ApiKey, key_hash)
assert final_key is not None
assert final_key.balance >= 0, (
f"Balance went negative after concurrent overruns: {final_key.balance}"
)
assert final_key.reserved_balance == 0, (
f"Reserved balance not fully released: {final_key.reserved_balance}"
)
assert final_key.total_spent <= starting_balance, (
f"Total spent ({final_key.total_spent}) exceeds starting balance ({starting_balance})"
)
# Every request must have been charged at least deducted_max_cost — no free inference.
assert final_key.total_spent == starting_balance, (
f"Expected total_spent={starting_balance} (all {n_requests} reservations charged), "
f"got {final_key.total_spent} — at least one request got free inference"
)
# ---------------------------------------------------------------------------
# Test 5 — overrun with no balance at all (reserved_balance == balance)
# simulates a user who topped up to exactly the reservation floor
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_zero_free_balance_overrun_is_safe(
integration_session: AsyncSession,
) -> None:
"""User with zero free balance (all reserved) should never go negative on overrun."""
from routstr.auth import adjust_payment_for_tokens
deducted_max_cost = 1000
actual_token_cost = 1050
# balance == reserved_balance: zero free balance
key = _make_key(balance=1000, reserved=1000)
integration_session.add(key)
await integration_session.commit()
response_data = {"model": "test-model", "usage": {"prompt_tokens": 50, "completion_tokens": 100}}
with patch(
"routstr.auth.calculate_cost",
return_value=_cost_data(actual_token_cost),
):
await adjust_payment_for_tokens(key, response_data, integration_session, deducted_max_cost)
await _refresh(integration_session, key)
assert key.balance >= 0, f"Balance went negative: {key.balance}"
assert key.reserved_balance >= 0, f"Reserved balance went negative: {key.reserved_balance}"
# ---------------------------------------------------------------------------
# Test 6 — parallel requests: second finalization must not get free inference
#
# Root cause of the bug fixed in auth.py:
# `.where(col(ApiKey.balance) >= total_cost_msats)` ignores other requests'
# reservations, so after Request A charges total_cost_msats, balance can drop
# below deducted_max_cost, causing Request B's fallback to release for free.
#
# Fix: use `balance - reserved_balance + deducted_max_cost >= total_cost_msats`
# so the check accounts for concurrent reservations.
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_parallel_requests_no_free_inference(
integration_session: AsyncSession,
patched_db_engine: None,
) -> None:
"""Second parallel finalization must be charged even when first depleted free balance."""
import asyncio
from routstr.auth import adjust_payment_for_tokens
from routstr.core.db import create_session
deducted_max_cost = 100
actual_token_cost = 150 # overrun: 50 more than reserved
# Fund the key with exactly 2 * deducted_max_cost.
# Both requests pre-reserved 100 each → balance=200, reserved=200, free=0.
# Old check (balance >= total_cost_msats):
# Request A: 200 >= 150 ✓ → charges 150 → balance=50, reserved=100
# Request B: 50 >= 150 ✗ → fallback: 50 >= 100 ✗ → releases FREE
# New check (balance - reserved + deducted >= total_cost_msats):
# Both fall to fallback (0 free balance).
# Both charge deducted_max_cost=100 → total_spent=200, balance=0.
starting_balance = deducted_max_cost * 2
key_hash = f"test_parallel_no_free_{uuid.uuid4().hex}"
async with create_session() as session:
key = ApiKey(
hashed_key=key_hash,
balance=starting_balance,
reserved_balance=deducted_max_cost * 2, # both slots pre-reserved
total_spent=0,
total_requests=2,
)
session.add(key)
await session.commit()
async def finalize() -> None:
response_data = {
"model": "test-model",
"usage": {"prompt_tokens": 50, "completion_tokens": 100},
}
async with create_session() as session:
fresh_key = await session.get(ApiKey, key_hash)
assert fresh_key is not None
with patch(
"routstr.auth.calculate_cost",
return_value=_cost_data(actual_token_cost),
):
await adjust_payment_for_tokens(
fresh_key, response_data, session, deducted_max_cost
)
await asyncio.gather(finalize(), finalize())
async with create_session() as session:
final_key = await session.get(ApiKey, key_hash)
assert final_key is not None
assert final_key.balance >= 0, f"Balance went negative: {final_key.balance}"
assert final_key.reserved_balance == 0, (
f"Reserved balance not released: {final_key.reserved_balance}"
)
# Both requests must have been charged — no free inference.
assert final_key.total_spent == starting_balance, (
f"Expected total_spent={starting_balance} (both reservations charged), "
f"got {final_key.total_spent} — one request got free inference"
)
@@ -1,240 +0,0 @@
"""
Tests showing how a user hits "Insufficient balance: X mSats required for this model"
when their balance is too low for the model's cost.
The log line that triggered this:
WARNING Insufficient billing balance during validation
ERROR Bearer token validation failed: HTTPException: 402:
{'error': {'message': 'Insufficient balance: 622888 mSats required
for this model. 20320 available.', ...}}
This happens in validate_bearer_key (auth.py) when:
billing_key.total_balance < min_cost (model's max cost)
and also in pay_for_request when the atomic UPDATE finds no available balance.
"""
import uuid
from unittest.mock import patch
import pytest
from fastapi import HTTPException
from httpx import AsyncClient
from sqlmodel.ext.asyncio.session import AsyncSession
from routstr.core.db import ApiKey
def _key(balance: int, reserved: int = 0) -> ApiKey:
return ApiKey(
hashed_key=f"test_{uuid.uuid4().hex}",
balance=balance,
reserved_balance=reserved,
total_spent=0,
)
# ---------------------------------------------------------------------------
# Test 1 — simplest case: balance < model cost → pay_for_request raises 402
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_pay_for_request_raises_402_when_balance_too_low(
integration_session: AsyncSession,
) -> None:
"""
User has 20_000 msats. Model costs 622_888 msats.
pay_for_request must raise HTTP 402 with a clear message.
"""
from routstr.auth import pay_for_request
model_cost = 622_888
user_balance = 20_000
key = _key(balance=user_balance)
integration_session.add(key)
await integration_session.commit()
with pytest.raises(HTTPException) as exc_info:
await pay_for_request(key, model_cost, integration_session)
assert exc_info.value.status_code == 402
detail = exc_info.value.detail
assert isinstance(detail, dict)
error = detail["error"]
assert error["code"] == "insufficient_balance"
assert str(model_cost) in error["message"]
assert str(user_balance) in error["message"]
# Balance must be untouched
await integration_session.refresh(key)
assert key.balance == user_balance
assert key.reserved_balance == 0
# ---------------------------------------------------------------------------
# Test 2 — balance is zero
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_pay_for_request_raises_402_on_zero_balance(
integration_session: AsyncSession,
) -> None:
"""User with zero balance cannot make any request."""
from routstr.auth import pay_for_request
key = _key(balance=0)
integration_session.add(key)
await integration_session.commit()
with pytest.raises(HTTPException) as exc_info:
await pay_for_request(key, 1_000, integration_session)
assert exc_info.value.status_code == 402
detail = exc_info.value.detail
assert isinstance(detail, dict)
assert detail["error"]["code"] == "insufficient_balance"
# ---------------------------------------------------------------------------
# Test 3 — all balance is reserved (total_balance = balance - reserved = 0)
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_pay_for_request_raises_402_when_all_balance_reserved(
integration_session: AsyncSession,
) -> None:
"""
User has 50_000 msats balance but 50_000 is already reserved for in-flight
requests. Free balance (total_balance) = 0. Should get 402.
"""
from routstr.auth import pay_for_request
key = _key(balance=50_000, reserved=50_000)
integration_session.add(key)
await integration_session.commit()
with pytest.raises(HTTPException) as exc_info:
await pay_for_request(key, 1_000, integration_session)
assert exc_info.value.status_code == 402
# Balance and reserved must be untouched
await integration_session.refresh(key)
assert key.balance == 50_000
assert key.reserved_balance == 50_000
# ---------------------------------------------------------------------------
# Test 4 — balance just one msat below model cost
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_pay_for_request_raises_402_one_msat_short(
integration_session: AsyncSession,
) -> None:
"""Off-by-one: balance is exactly model_cost - 1."""
from routstr.auth import pay_for_request
model_cost = 10_000
key = _key(balance=model_cost - 1)
integration_session.add(key)
await integration_session.commit()
with pytest.raises(HTTPException) as exc_info:
await pay_for_request(key, model_cost, integration_session)
assert exc_info.value.status_code == 402
await integration_session.refresh(key)
assert key.balance == model_cost - 1 # untouched
assert key.reserved_balance == 0
# ---------------------------------------------------------------------------
# Test 5 — balance exactly equal to model cost → succeeds
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_pay_for_request_succeeds_when_balance_equals_cost(
integration_session: AsyncSession,
) -> None:
"""Balance == model cost: the request should be reserved successfully."""
from routstr.auth import pay_for_request
model_cost = 10_000
key = _key(balance=model_cost)
integration_session.add(key)
await integration_session.commit()
# Should not raise
await pay_for_request(key, model_cost, integration_session)
await integration_session.refresh(key)
assert key.reserved_balance == model_cost
assert key.balance == model_cost # balance unchanged, only reserved goes up
# ---------------------------------------------------------------------------
# Test 6 — HTTP layer returns 402 JSON with the right shape
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_http_402_response_shape_on_insufficient_balance(
integration_client: AsyncClient,
integration_session: AsyncSession,
) -> None:
"""
End-to-end: POST /v1/chat/completions with a key whose balance is far below
the mocked model cost returns HTTP 402 with the expected JSON error body.
Matches exactly the log snippet in the bug report:
'Insufficient balance: X mSats required for this model. Y available.'
"""
from unittest.mock import AsyncMock, MagicMock
model_cost = 622_888
user_balance = 20_320
key = _key(balance=user_balance)
integration_session.add(key)
await integration_session.commit()
# Minimal model stub so proxy routing doesn't 400 before reaching balance check
mock_model = MagicMock()
mock_model.sats_pricing = None
# Upstream stub — never reached because balance check fires first
mock_upstream = MagicMock()
mock_upstream.prepare_headers = MagicMock(return_value={})
with (
patch("routstr.proxy.get_model_instance", return_value=mock_model),
patch("routstr.proxy.get_provider_for_model", return_value=[mock_upstream]),
# Patch where it is used (proxy imports it at module level)
patch(
"routstr.proxy.get_max_cost_for_model",
new=AsyncMock(return_value=model_cost),
),
):
response = await integration_client.post(
"/v1/chat/completions",
headers={"Authorization": f"Bearer sk-{key.hashed_key}"},
json={
"model": "gpt-4o",
"messages": [{"role": "user", "content": "hello"}],
},
)
assert response.status_code == 402
body = response.json()
# FastAPI wraps HTTPException detail under "detail"
error = body["detail"]["error"]
assert error["code"] == "insufficient_balance"
assert error["type"] == "insufficient_quota"
assert str(model_cost) in error["message"]
assert str(user_balance) in error["message"]
# Balance must be completely untouched
await integration_session.refresh(key)
assert key.balance == user_balance
assert key.reserved_balance == 0
assert key.total_spent == 0
@@ -1,268 +0,0 @@
"""
Tests for the reservation lifecycle:
1. Reserve → reserved_balance increases, available (total_balance) decreases.
2. Reserve → revert → reserved_balance restored, balance untouched.
3. Reserve → finalise → reserved_balance released, balance charged.
4. Two parallel reserves, only one fits → second blocked with 402.
5. Three parallel reserves, two fit, third blocked with 402.
6. Sequential reserves until balance exhausted → next request blocked.
Reservation invariant enforced by the atomic WHERE clause in pay_for_request:
balance - reserved_balance >= cost_per_request
"""
import asyncio
import uuid
import pytest
from fastapi import HTTPException
from sqlmodel.ext.asyncio.session import AsyncSession
from routstr.auth import pay_for_request, revert_pay_for_request
from routstr.core.db import ApiKey, create_session
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _make_key(balance: int, reserved: int = 0) -> ApiKey:
return ApiKey(
hashed_key=f"test_{uuid.uuid4().hex}",
balance=balance,
reserved_balance=reserved,
total_spent=0,
total_requests=0,
)
async def _persist(session: AsyncSession, key: ApiKey) -> ApiKey:
session.add(key)
await session.commit()
await session.refresh(key)
return key
# ---------------------------------------------------------------------------
# Test 1 — Reserve: reserved_balance increases, available balance decreases
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_reserve_increases_reserved_balance(
integration_session: AsyncSession,
) -> None:
"""pay_for_request must increment reserved_balance by cost_per_request."""
cost = 100
key = await _persist(integration_session, _make_key(balance=500))
await pay_for_request(key, cost, integration_session)
await integration_session.refresh(key)
assert key.reserved_balance == cost
assert key.balance == 500 # balance column is NOT decremented on reserve
assert key.total_balance == 500 - cost # available = balance - reserved
# ---------------------------------------------------------------------------
# Test 2 — Revert: reserved_balance restored, balance untouched
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_revert_releases_reservation(
integration_session: AsyncSession,
) -> None:
"""revert_pay_for_request must release the reservation without touching balance."""
cost = 150
key = await _persist(integration_session, _make_key(balance=300))
await pay_for_request(key, cost, integration_session)
await integration_session.refresh(key)
assert key.reserved_balance == cost
await revert_pay_for_request(key, integration_session, cost)
await integration_session.refresh(key)
assert key.reserved_balance == 0
assert key.balance == 300 # balance unchanged after revert
# ---------------------------------------------------------------------------
# Test 3 — Finalise: reservation released + balance charged
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_finalise_releases_reservation_and_charges_balance(
integration_session: AsyncSession,
) -> None:
"""adjust_payment_for_tokens must zero reserved_balance and deduct actual cost."""
from unittest.mock import patch
from routstr.auth import adjust_payment_for_tokens
from routstr.payment.cost_calculation import CostData
cost = 100
actual = 80 # actual < reserved → refund path
key = await _persist(integration_session, _make_key(balance=500))
await pay_for_request(key, cost, integration_session)
await integration_session.refresh(key)
assert key.reserved_balance == cost
cost_data = CostData(
base_msats=0,
input_msats=40,
output_msats=40,
total_msats=actual,
total_usd=0.0,
input_tokens=50,
output_tokens=50,
)
response_data = {"model": "test-model", "usage": {"prompt_tokens": 50, "completion_tokens": 50}}
with patch("routstr.auth.calculate_cost", return_value=cost_data):
await adjust_payment_for_tokens(key, response_data, integration_session, cost)
await integration_session.refresh(key)
assert key.reserved_balance == 0
assert key.balance == 500 - actual
assert key.total_spent == actual
# ---------------------------------------------------------------------------
# Test 4 — Concurrent: second parallel reserve blocked when balance exhausted
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_concurrent_second_reserve_blocked_when_balance_exhausted(
patched_db_engine: None,
) -> None:
"""When two requests race for the same balance, only one succeeds; the other gets 402."""
cost = 300
key_hash = f"test_concurrent_{uuid.uuid4().hex}"
async with create_session() as session:
key = ApiKey(
hashed_key=key_hash,
balance=300, # exactly enough for ONE reservation
reserved_balance=0,
total_spent=0,
total_requests=0,
)
session.add(key)
await session.commit()
results: list[str] = []
async def attempt_reserve() -> None:
async with create_session() as session:
fresh_key = await session.get(ApiKey, key_hash)
assert fresh_key is not None
try:
await pay_for_request(fresh_key, cost, session)
results.append("success")
except HTTPException as exc:
assert exc.status_code == 402
results.append("blocked")
await asyncio.gather(attempt_reserve(), attempt_reserve())
assert sorted(results) == ["blocked", "success"], (
f"Expected exactly one success and one 402, got: {results}"
)
async with create_session() as session:
final = await session.get(ApiKey, key_hash)
assert final is not None
# reserved_balance must equal exactly one reservation (not two)
assert final.reserved_balance == cost, (
f"Expected reserved_balance={cost}, got {final.reserved_balance}"
)
assert final.balance == 300, "Balance column must not be modified by reservation"
# ---------------------------------------------------------------------------
# Test 5 — Concurrent: three requests, two fit, third blocked
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_three_parallel_reserves_third_blocked(
patched_db_engine: None,
) -> None:
"""Balance covers two reservations exactly; the third concurrent request must be blocked."""
cost = 100
key_hash = f"test_three_parallel_{uuid.uuid4().hex}"
async with create_session() as session:
key = ApiKey(
hashed_key=key_hash,
balance=200, # fits exactly 2 reservations of 100
reserved_balance=0,
total_spent=0,
total_requests=0,
)
session.add(key)
await session.commit()
results: list[str] = []
async def attempt_reserve() -> None:
async with create_session() as session:
fresh_key = await session.get(ApiKey, key_hash)
assert fresh_key is not None
try:
await pay_for_request(fresh_key, cost, session)
results.append("success")
except HTTPException as exc:
assert exc.status_code == 402
results.append("blocked")
await asyncio.gather(
attempt_reserve(),
attempt_reserve(),
attempt_reserve(),
)
successes = results.count("success")
blocked = results.count("blocked")
assert successes == 2, f"Expected 2 successes, got {successes}: {results}"
assert blocked == 1, f"Expected 1 blocked, got {blocked}: {results}"
async with create_session() as session:
final = await session.get(ApiKey, key_hash)
assert final is not None
assert final.reserved_balance == cost * 2, (
f"Expected reserved_balance={cost * 2}, got {final.reserved_balance}"
)
assert final.balance == 200, "Balance column must not be modified by reservation"
# ---------------------------------------------------------------------------
# Test 6 — Sequential exhaustion: reserve until empty, next request blocked
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_sequential_reserves_block_when_balance_exhausted(
integration_session: AsyncSession,
) -> None:
"""Repeated reservations should block as soon as available balance drops below cost."""
cost = 100
key = await _persist(integration_session, _make_key(balance=250))
# First two succeed (100 + 100 = 200 ≤ 250)
await pay_for_request(key, cost, integration_session)
await pay_for_request(key, cost, integration_session)
await integration_session.refresh(key)
assert key.reserved_balance == 200
assert key.total_balance == 50 # 250 - 200
# Third: only 50 available, need 100 → blocked
with pytest.raises(HTTPException) as exc_info:
await pay_for_request(key, cost, integration_session)
assert exc_info.value.status_code == 402
await integration_session.refresh(key)
assert key.reserved_balance == 200 # unchanged after failed reserve
+18 -168
View File
@@ -1,42 +1,27 @@
import json
from unittest.mock import AsyncMock, MagicMock, patch
import hashlib
from unittest.mock import AsyncMock, MagicMock
import pytest
from fastapi.responses import JSONResponse
from routstr.balance import refund_wallet_endpoint
from routstr.core.db import ApiKey, CashuTransaction
from routstr.core.db import CashuTransaction
def _make_cashu_tx(
token: str,
amount: int,
unit: str,
type: str = "out",
request_id: str | None = "req-abc",
swept: bool = False,
collected: bool = False,
) -> CashuTransaction:
tx = CashuTransaction(token=token, amount=amount, unit=unit, type=type, request_id=request_id)
def _make_cashu_tx(token: str, amount: int, unit: str, swept: bool = False) -> CashuTransaction:
tx = CashuTransaction(token=token, amount=amount, unit=unit)
tx.swept = swept
tx.collected = collected
tx.collected = False
return tx
def _exec_result(tx: CashuTransaction | None) -> MagicMock:
result = MagicMock()
result.first.return_value = tx
return result
@pytest.mark.asyncio
async def test_refund_x_cashu_returns_token() -> None:
x_cashu_token = "cashuAtest_token_value"
in_tx = _make_cashu_tx(token=x_cashu_token, amount=0, unit="msat", type="in", request_id="req-abc")
out_tx = _make_cashu_tx(token="cashuArefund_token", amount=1000, unit="msat", type="out", request_id="req-abc")
expected_hash = hashlib.sha256(x_cashu_token.strip().encode()).hexdigest()
tx = _make_cashu_tx(token="cashuArefund_token", amount=1000, unit="msat")
session = MagicMock()
session.exec = AsyncMock(side_effect=[_exec_result(in_tx), _exec_result(out_tx)])
session.get = AsyncMock(return_value=tx)
session.add = MagicMock()
session.commit = AsyncMock()
@@ -46,22 +31,22 @@ async def test_refund_x_cashu_returns_token() -> None:
session=session,
)
assert isinstance(result, JSONResponse)
session.get.assert_awaited_once_with(CashuTransaction, expected_hash)
import json
body = json.loads(result.body)
assert body["token"] == "cashuArefund_token"
assert body["msats"] == "1000"
assert result.headers["X-Cashu"] == "cashuArefund_token"
assert out_tx.collected is True
assert tx.collected is True
@pytest.mark.asyncio
async def test_refund_x_cashu_sat_unit() -> None:
x_cashu_token = "cashuAsat_token"
in_tx = _make_cashu_tx(token=x_cashu_token, amount=0, unit="sat", type="in", request_id="req-sat")
out_tx = _make_cashu_tx(token="cashuArefund_sat", amount=500, unit="sat", type="out", request_id="req-sat")
tx = _make_cashu_tx(token="cashuArefund_sat", amount=500, unit="sat")
session = MagicMock()
session.exec = AsyncMock(side_effect=[_exec_result(in_tx), _exec_result(out_tx)])
session.get = AsyncMock(return_value=tx)
session.add = MagicMock()
session.commit = AsyncMock()
@@ -71,7 +56,7 @@ async def test_refund_x_cashu_sat_unit() -> None:
session=session,
)
assert isinstance(result, JSONResponse)
import json
body = json.loads(result.body)
assert body["token"] == "cashuArefund_sat"
assert body["sats"] == "500"
@@ -84,7 +69,7 @@ async def test_refund_x_cashu_not_found_raises_404() -> None:
from fastapi import HTTPException
session = MagicMock()
session.exec = AsyncMock(return_value=_exec_result(None))
session.get = AsyncMock(return_value=None)
with pytest.raises(HTTPException) as exc_info:
await refund_wallet_endpoint(
@@ -100,11 +85,10 @@ async def test_refund_x_cashu_not_found_raises_404() -> None:
async def test_refund_x_cashu_swept_raises_410() -> None:
from fastapi import HTTPException
in_tx = _make_cashu_tx(token="cashuAswept_token", amount=0, unit="msat", type="in", request_id="req-swept")
out_tx = _make_cashu_tx(token="cashuAswept", amount=100, unit="msat", type="out", request_id="req-swept", swept=True)
tx = _make_cashu_tx(token="cashuAswept", amount=100, unit="msat", swept=True)
session = MagicMock()
session.exec = AsyncMock(side_effect=[_exec_result(in_tx), _exec_result(out_tx)])
session.get = AsyncMock(return_value=tx)
with pytest.raises(HTTPException) as exc_info:
await refund_wallet_endpoint(
@@ -114,137 +98,3 @@ async def test_refund_x_cashu_swept_raises_410() -> None:
)
assert exc_info.value.status_code == 410
# ---------------------------------------------------------------------------
# source field defaults
# ---------------------------------------------------------------------------
def test_cashu_transaction_source_defaults_to_x_cashu() -> None:
tx = CashuTransaction(token="cashuAtest", amount=100, unit="msat")
assert tx.source == "x-cashu"
def test_cashu_transaction_source_can_be_apikey() -> None:
tx = CashuTransaction(token="cashuAtest", amount=100, unit="msat", source="apikey")
assert tx.source == "apikey"
# ---------------------------------------------------------------------------
# apikey-based refund: token logging and CashuTransaction storage
# ---------------------------------------------------------------------------
def _make_api_key(
balance: int = 5000,
refund_currency: str | None = "sat",
refund_mint_url: str | None = "https://mint.example.com",
refund_address: str | None = None,
parent_key_hash: str | None = None,
) -> ApiKey:
key = ApiKey(hashed_key="testhash")
key.balance = balance
key.reserved_balance = 0
key.refund_currency = refund_currency
key.refund_mint_url = refund_mint_url
key.refund_address = refund_address
key.parent_key_hash = parent_key_hash
key.total_spent = 0
key.total_requests = 0
return key
@pytest.mark.asyncio
async def test_apikey_refund_stores_cashu_transaction_with_apikey_source() -> None:
key = _make_api_key(balance=5000, refund_currency="sat")
refund_token = "cashuArefund_apikey_token"
session = MagicMock()
session.add = MagicMock()
session.commit = AsyncMock()
with (
patch("routstr.balance.validate_bearer_key", AsyncMock(return_value=key)),
patch("routstr.balance.get_billing_key", AsyncMock(return_value=key)),
patch("routstr.balance.send_token", AsyncMock(return_value=refund_token)),
patch("routstr.balance.store_cashu_transaction", AsyncMock()) as mock_store,
patch("routstr.balance._refund_cache_get", AsyncMock(return_value=None)),
patch("routstr.balance._refund_cache_set", AsyncMock()),
):
result = await refund_wallet_endpoint(
authorization="Bearer sk-testhash",
x_cashu=None,
session=session,
)
assert isinstance(result, dict)
assert result["token"] == refund_token
mock_store.assert_awaited_once()
call_kwargs = mock_store.call_args.kwargs
assert call_kwargs["source"] == "apikey"
assert call_kwargs["token"] == refund_token
assert call_kwargs["typ"] == "out"
@pytest.mark.asyncio
async def test_apikey_refund_logs_token() -> None:
key = _make_api_key(balance=5000, refund_currency="sat")
refund_token = "cashuAlogged_token"
session = MagicMock()
session.add = MagicMock()
session.commit = AsyncMock()
with (
patch("routstr.balance.validate_bearer_key", AsyncMock(return_value=key)),
patch("routstr.balance.get_billing_key", AsyncMock(return_value=key)),
patch("routstr.balance.send_token", AsyncMock(return_value=refund_token)),
patch("routstr.balance.store_cashu_transaction", AsyncMock()),
patch("routstr.balance._refund_cache_get", AsyncMock(return_value=None)),
patch("routstr.balance._refund_cache_set", AsyncMock()),
patch("routstr.balance.logger") as mock_logger,
):
await refund_wallet_endpoint(
authorization="Bearer sk-testhash",
x_cashu=None,
session=session,
)
calls = [str(c) for c in mock_logger.info.call_args_list]
assert any("cashu token issued" in c for c in calls)
@pytest.mark.asyncio
async def test_apikey_refund_log_includes_path() -> None:
key = _make_api_key(balance=5000, refund_currency="sat")
refund_token = "cashuApath_token"
session = MagicMock()
session.add = MagicMock()
session.commit = AsyncMock()
with (
patch("routstr.balance.validate_bearer_key", AsyncMock(return_value=key)),
patch("routstr.balance.get_billing_key", AsyncMock(return_value=key)),
patch("routstr.balance.send_token", AsyncMock(return_value=refund_token)),
patch("routstr.balance.store_cashu_transaction", AsyncMock()),
patch("routstr.balance._refund_cache_get", AsyncMock(return_value=None)),
patch("routstr.balance._refund_cache_set", AsyncMock()),
patch("routstr.balance.logger") as mock_logger,
):
await refund_wallet_endpoint(
authorization="Bearer sk-testhash",
x_cashu=None,
session=session,
)
# Find the "cashu token issued" call and verify extra contains the path
token_issued_calls = [
c for c in mock_logger.info.call_args_list
if c.args and "cashu token issued" in c.args[0]
]
assert len(token_issued_calls) == 1
extra = token_issued_calls[0].kwargs.get("extra", {})
assert extra.get("path") == "/v1/wallet/refund"
-27
View File
@@ -220,33 +220,6 @@ async def test_recieve_token_untrusted_mint() -> None:
@pytest.mark.asyncio
@pytest.mark.asyncio
async def test_swap_to_primary_mint_already_on_primary() -> None:
from routstr.core.settings import settings
from routstr.wallet import swap_to_primary_mint
mock_token = Mock()
mock_token.mint = settings.primary_mint
mock_token.amount = 1000
mock_token.unit = "sat"
mock_token.proofs = []
mock_token_wallet = Mock()
mock_token_wallet.split = AsyncMock(return_value=None)
mock_token_wallet.request_mint = AsyncMock()
mock_token_wallet.melt_quote = AsyncMock()
with patch("routstr.wallet.get_wallet", AsyncMock(return_value=mock_token_wallet)):
amount, unit, mint = await swap_to_primary_mint(mock_token, mock_token_wallet)
assert amount == 1000
assert unit == "sat"
assert mint == settings.primary_mint
mock_token_wallet.split.assert_called_once()
mock_token_wallet.request_mint.assert_not_called()
mock_token_wallet.melt_quote.assert_not_called()
async def test_swap_to_primary_mint_success() -> None:
"""Test successful swap with dynamic fee calculation."""
from routstr.wallet import swap_to_primary_mint
-216
View File
@@ -1,216 +0,0 @@
import json
import os
from unittest.mock import AsyncMock, patch
import httpx
import pytest
os.environ.setdefault("UPSTREAM_BASE_URL", "http://test")
os.environ.setdefault("UPSTREAM_API_KEY", "test")
from routstr.payment.cost_calculation import CostData # noqa: E402
from routstr.upstream.base import BaseUpstreamProvider # noqa: E402
def _make_provider() -> BaseUpstreamProvider:
return BaseUpstreamProvider(base_url="http://test", api_key="test-key")
def _make_httpx_response(status_code: int = 200) -> httpx.Response:
return httpx.Response(status_code, headers={})
def _make_cost_data(total_msats: int = 5000) -> CostData:
return CostData(
base_msats=0,
input_msats=3000,
output_msats=2000,
total_msats=total_msats,
total_usd=0.00025,
input_tokens=100,
output_tokens=50,
)
# ---------------------------------------------------------------------------
# Non-streaming (chat completions)
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_non_streaming_includes_cost_sats() -> None:
provider = _make_provider()
cost_data = _make_cost_data(total_msats=5000)
response_body = {
"model": "gpt-4o",
"usage": {
"prompt_tokens": 100,
"completion_tokens": 50,
"total_tokens": 150,
"cost": 0.00025,
},
}
content_str = json.dumps(response_body)
httpx_response = _make_httpx_response()
with (
patch.object(provider, "get_x_cashu_cost", new=AsyncMock(return_value=cost_data)),
patch.object(provider, "send_refund", new=AsyncMock(return_value="cashuA_refund_token")),
):
response = await provider.handle_x_cashu_non_streaming_response(
content_str=content_str,
response=httpx_response,
amount=10000,
unit="msat",
max_cost_for_model=10000,
mint=None,
payment_token_hash=None,
)
body = json.loads(response.body)
assert "cost_sats" in body["usage"]
assert body["usage"]["cost_sats"] == 5 # 5000 msats // 1000
@pytest.mark.asyncio
async def test_non_streaming_cost_sats_value_rounds_down() -> None:
provider = _make_provider()
cost_data = _make_cost_data(total_msats=1999)
response_body = {"model": "gpt-4o", "usage": {"prompt_tokens": 10}}
content_str = json.dumps(response_body)
with (
patch.object(provider, "get_x_cashu_cost", new=AsyncMock(return_value=cost_data)),
patch.object(provider, "send_refund", new=AsyncMock(return_value="cashuA_refund_token")),
):
response = await provider.handle_x_cashu_non_streaming_response(
content_str=content_str,
response=_make_httpx_response(),
amount=10000,
unit="msat",
max_cost_for_model=10000,
)
body = json.loads(response.body)
assert body["usage"]["cost_sats"] == 1 # 1999 // 1000
@pytest.mark.asyncio
async def test_non_streaming_preserves_existing_usage_fields() -> None:
provider = _make_provider()
cost_data = _make_cost_data(total_msats=3000)
response_body = {
"model": "gpt-4o",
"usage": {
"prompt_tokens": 100,
"completion_tokens": 50,
"total_tokens": 150,
"cost": 0.00015,
},
}
with (
patch.object(provider, "get_x_cashu_cost", new=AsyncMock(return_value=cost_data)),
patch.object(provider, "send_refund", new=AsyncMock(return_value="cashuA_refund_token")),
):
response = await provider.handle_x_cashu_non_streaming_response(
content_str=json.dumps(response_body),
response=_make_httpx_response(),
amount=10000,
unit="msat",
max_cost_for_model=10000,
)
body = json.loads(response.body)
usage = body["usage"]
assert usage["prompt_tokens"] == 100
assert usage["completion_tokens"] == 50
assert usage["total_tokens"] == 150
assert usage["cost"] == 0.00015
assert usage["cost_sats"] == 3
# ---------------------------------------------------------------------------
# Streaming (chat completions)
# ---------------------------------------------------------------------------
async def _collect_streaming(response: object) -> list[str]:
chunks: list[str] = []
async for chunk in response.body_iterator: # type: ignore[attr-defined]
if isinstance(chunk, bytes):
chunks.append(chunk.decode("utf-8"))
else:
chunks.append(str(chunk))
return chunks
@pytest.mark.asyncio
async def test_streaming_includes_cost_sats_in_usage_chunk() -> None:
provider = _make_provider()
cost_data = _make_cost_data(total_msats=7000)
usage_chunk = {
"id": "chatcmpl-123",
"model": "gpt-4o",
"usage": {"prompt_tokens": 100, "completion_tokens": 50, "total_tokens": 150},
}
content_str = "\n".join([
'data: {"id":"chatcmpl-123","model":"gpt-4o","choices":[]}',
f"data: {json.dumps(usage_chunk)}",
"data: [DONE]",
])
with patch.object(provider, "get_x_cashu_cost", new=AsyncMock(return_value=cost_data)):
response = await provider.handle_x_cashu_streaming_response(
content_str=content_str,
response=_make_httpx_response(),
amount=10000,
unit="msat",
max_cost_for_model=10000,
mint=None,
payment_token_hash=None,
)
chunks = await _collect_streaming(response)
full_output = "".join(chunks)
usage_line = next(
line for line in full_output.split("\n") if '"usage"' in line and "cost_sats" in line
)
data_json = json.loads(usage_line.lstrip("data: ").strip())
assert data_json["usage"]["cost_sats"] == 7 # 7000 // 1000
@pytest.mark.asyncio
async def test_streaming_non_usage_chunks_unmodified() -> None:
provider = _make_provider()
cost_data = _make_cost_data(total_msats=2000)
regular_chunk = {"id": "chatcmpl-123", "model": "gpt-4o", "choices": [{"delta": {"content": "hi"}}]}
usage_chunk = {"id": "chatcmpl-123", "model": "gpt-4o", "usage": {"prompt_tokens": 10}}
content_str = "\n".join([
f"data: {json.dumps(regular_chunk)}",
f"data: {json.dumps(usage_chunk)}",
"data: [DONE]",
])
with patch.object(provider, "get_x_cashu_cost", new=AsyncMock(return_value=cost_data)):
response = await provider.handle_x_cashu_streaming_response(
content_str=content_str,
response=_make_httpx_response(),
amount=10000,
unit="msat",
max_cost_for_model=10000,
)
chunks = await _collect_streaming(response)
lines = [
line for line in "".join(chunks).split("\n")
if line.startswith("data: ") and line != "data: [DONE]"
]
regular_line_data = json.loads(lines[0][6:])
# regular chunk should not have cost_sats injected
assert "cost_sats" not in regular_line_data.get("usage", {})
+131 -201
View File
@@ -22,7 +22,6 @@ import {
SelectValue,
} from '@/components/ui/select';
import { Badge } from '@/components/ui/badge';
import { Tabs, TabsContent, TabsList, TabsTrigger } from '@/components/ui/tabs';
import {
Table,
TableBody,
@@ -48,8 +47,6 @@ import {
Copy,
Check,
Receipt,
Key,
Zap,
} from 'lucide-react';
import { AdminService, type Transaction } from '@/lib/api/services/admin';
import { format } from 'date-fns';
@@ -57,118 +54,6 @@ import { toast } from 'sonner';
const STORAGE_KEY = 'routstr-transaction-filters';
function TransactionTable({
transactions,
copiedId,
onCopy,
getStatusBadge,
}: {
transactions: Transaction[];
copiedId: string | null;
onCopy: (text: string, id: string) => void;
getStatusBadge: (tx: Transaction) => React.ReactNode;
}) {
if (transactions.length === 0) {
return (
<Empty className='py-8'>
<EmptyHeader>
<EmptyMedia variant='icon'>
<Receipt className='h-4 w-4' />
</EmptyMedia>
<EmptyTitle>No transactions found</EmptyTitle>
<EmptyDescription>
Try adjusting your filters or check back later.
</EmptyDescription>
</EmptyHeader>
</Empty>
);
}
return (
<ScrollArea className='h-[55svh] min-h-[420px] w-full sm:h-[600px]'>
<Table>
<TableHeader>
<TableRow>
<TableHead>Type</TableHead>
<TableHead>Amount</TableHead>
<TableHead>Status</TableHead>
<TableHead>Request ID</TableHead>
<TableHead>Mint</TableHead>
<TableHead>Date</TableHead>
<TableHead className='text-right'>Actions</TableHead>
</TableRow>
</TableHeader>
<TableBody>
{transactions.map((tx) => (
<TableRow key={tx.id}>
<TableCell>
<div className='flex items-center gap-2'>
{tx.type === 'in' ? (
<ArrowDownLeft className='h-4 w-4 text-green-500' />
) : (
<ArrowUpRight className='h-4 w-4 text-blue-500' />
)}
<span className='capitalize'>{tx.type}</span>
</div>
</TableCell>
<TableCell className='font-mono'>
{tx.amount} {tx.unit}
</TableCell>
<TableCell>{getStatusBadge(tx)}</TableCell>
<TableCell>
{tx.request_id ? (
<div className='flex items-center gap-1 text-xs'>
<span className='max-w-[150px] truncate font-mono'>
{tx.request_id}
</span>
<Button
variant='ghost'
size='icon'
className='h-4 w-4'
onClick={() => onCopy(tx.request_id!, tx.id + '-req')}
>
{copiedId === tx.id + '-req' ? (
<Check className='h-3 w-3' />
) : (
<Copy className='h-3 w-3' />
)}
</Button>
</div>
) : (
<span className='text-muted-foreground text-xs'></span>
)}
</TableCell>
<TableCell>
<div className='flex max-w-[150px] items-center gap-1 truncate text-xs'>
<span className='truncate'>{tx.mint_url}</span>
</div>
</TableCell>
<TableCell className='text-xs whitespace-nowrap'>
{format(tx.created_at * 1000, 'yyyy-MM-dd HH:mm:ss')}
</TableCell>
<TableCell className='text-right'>
<Button
variant='ghost'
size='icon'
className='h-8 w-8'
onClick={() => onCopy(tx.token, tx.id + '-token')}
title='Copy Token'
>
{copiedId === tx.id + '-token' ? (
<Check className='h-4 w-4' />
) : (
<Copy className='h-4 w-4' />
)}
</Button>
</TableCell>
</TableRow>
))}
</TableBody>
</Table>
</ScrollArea>
);
}
export default function TransactionsPage() {
const [search, setSearch] = useState('');
const [type, setType] = useState<string>('all');
@@ -260,41 +145,12 @@ export default function TransactionsPage() {
.filter(Boolean)
.join(' • ');
const xcashuTxs =
data?.transactions.filter((tx) => !tx.source || tx.source === 'x-cashu') ??
[];
const apikeyTxs =
data?.transactions.filter((tx) => tx.source === 'apikey') ?? [];
const renderCardContent = (txs: Transaction[]) => {
if (isLoading) {
return (
<div className='space-y-2'>
{Array.from({ length: 8 }).map((_, index) => (
<Skeleton
key={`tx-loading-${index}`}
className='h-16 w-full rounded-lg'
/>
))}
</div>
);
}
return (
<TransactionTable
transactions={txs}
copiedId={copiedId}
onCopy={copyToClipboard}
getStatusBadge={getStatusBadge}
/>
);
};
return (
<AppPageShell contentClassName='mx-auto w-full max-w-5xl overflow-x-hidden'>
<div className='space-y-6'>
<PageHeader
title='Cashu Transactions'
description='View all incoming and outgoing Cashu token transactions.'
title='X-Cashu Transactions'
description='View all incoming and outgoing X-Cashu token transactions.'
actions={
<Button
onClick={() => refetch()}
@@ -372,64 +228,138 @@ export default function TransactionsPage() {
</CardContent>
</Card>
<Tabs defaultValue='x-cashu'>
<TabsList className='mb-4'>
<TabsTrigger value='x-cashu' className='flex items-center gap-2'>
<Zap className='h-4 w-4' />
X-Cashu
<Card>
<CardHeader>
<div className='flex flex-col items-start gap-2 sm:flex-row sm:items-center sm:justify-between'>
<CardTitle>Transaction History</CardTitle>
{data && (
<Badge variant='secondary' className='ml-1'>
{xcashuTxs.length}
<Badge variant='secondary'>
{data.transactions.length} entries
</Badge>
)}
</TabsTrigger>
<TabsTrigger value='apikey' className='flex items-center gap-2'>
<Key className='h-4 w-4' />
API Key Refunds
{data && (
<Badge variant='secondary' className='ml-1'>
{apikeyTxs.length}
</Badge>
)}
</TabsTrigger>
</TabsList>
<TabsContent value='x-cashu'>
<Card>
<CardHeader>
<div className='flex flex-col items-start gap-2 sm:flex-row sm:items-center sm:justify-between'>
<CardTitle>X-Cashu Transaction History</CardTitle>
{hasActiveFilters && (
<CardDescription>
Filtered by {activeFilterDescription}
</CardDescription>
)}
</div>
</CardHeader>
<CardContent className='overflow-hidden'>
{renderCardContent(xcashuTxs)}
</CardContent>
</Card>
</TabsContent>
<TabsContent value='apikey'>
<Card>
<CardHeader>
<div className='flex flex-col items-start gap-2 sm:flex-row sm:items-center sm:justify-between'>
<CardTitle>API Key Refund History</CardTitle>
{hasActiveFilters && (
<CardDescription>
Filtered by {activeFilterDescription}
</CardDescription>
)}
</div>
</CardHeader>
<CardContent className='overflow-hidden'>
{renderCardContent(apikeyTxs)}
</CardContent>
</Card>
</TabsContent>
</Tabs>
</div>
{hasActiveFilters && (
<CardDescription>
Showing transactions filtered by {activeFilterDescription}
</CardDescription>
)}
</CardHeader>
<CardContent className='overflow-hidden'>
{isLoading ? (
<div className='space-y-2'>
{Array.from({ length: 8 }).map((_, index) => (
<Skeleton
key={`tx-loading-${index}`}
className='h-16 w-full rounded-lg'
/>
))}
</div>
) : data?.transactions && data.transactions.length > 0 ? (
<ScrollArea className='h-[55svh] min-h-[420px] w-full sm:h-[600px]'>
<Table>
<TableHeader>
<TableRow>
<TableHead>Type</TableHead>
<TableHead>Amount</TableHead>
<TableHead>Status</TableHead>
<TableHead>Request ID</TableHead>
<TableHead>Mint</TableHead>
<TableHead>Date</TableHead>
<TableHead className='text-right'>Actions</TableHead>
</TableRow>
</TableHeader>
<TableBody>
{data.transactions.map((tx) => (
<TableRow key={tx.id}>
<TableCell>
<div className='flex items-center gap-2'>
{tx.type === 'in' ? (
<ArrowDownLeft className='h-4 w-4 text-green-500' />
) : (
<ArrowUpRight className='h-4 w-4 text-blue-500' />
)}
<span className='capitalize'>{tx.type}</span>
</div>
</TableCell>
<TableCell className='font-mono'>
{tx.amount} {tx.unit}
</TableCell>
<TableCell>{getStatusBadge(tx)}</TableCell>
<TableCell>
{tx.request_id ? (
<div className='flex items-center gap-1 text-xs'>
<span className='max-w-[150px] truncate font-mono'>
{tx.request_id}
</span>
<Button
variant='ghost'
size='icon'
className='h-4 w-4'
onClick={() =>
copyToClipboard(
tx.request_id!,
tx.id + '-req'
)
}
>
{copiedId === tx.id + '-req' ? (
<Check className='h-3 w-3' />
) : (
<Copy className='h-3 w-3' />
)}
</Button>
</div>
) : (
<span className='text-muted-foreground text-xs'>
</span>
)}
</TableCell>
<TableCell>
<div className='flex max-w-[150px] items-center gap-1 truncate text-xs'>
<span className='truncate'>{tx.mint_url}</span>
</div>
</TableCell>
<TableCell className='text-xs whitespace-nowrap'>
{format(tx.created_at * 1000, 'yyyy-MM-dd HH:mm:ss')}
</TableCell>
<TableCell className='text-right'>
<Button
variant='ghost'
size='icon'
className='h-8 w-8'
onClick={() =>
copyToClipboard(tx.token, tx.id + '-token')
}
title='Copy Token'
>
{copiedId === tx.id + '-token' ? (
<Check className='h-4 w-4' />
) : (
<Copy className='h-4 w-4' />
)}
</Button>
</TableCell>
</TableRow>
))}
</TableBody>
</Table>
</ScrollArea>
) : (
<Empty className='py-8'>
<EmptyHeader>
<EmptyMedia variant='icon'>
<Receipt className='h-4 w-4' />
</EmptyMedia>
<EmptyTitle>No transactions found</EmptyTitle>
<EmptyDescription>
Try adjusting your filters or check back later.
</EmptyDescription>
</EmptyHeader>
</Empty>
)}
</CardContent>
</Card>
</div>
</AppPageShell>
);
+2 -56
View File
@@ -1,6 +1,6 @@
'use client';
import React, { useCallback, useEffect, useMemo, useState } from 'react';
import React, { useEffect, useMemo, useState } from 'react';
import { useForm } from 'react-hook-form';
import { z } from 'zod';
import { zodResolver } from '@hookform/resolvers/zod';
@@ -39,7 +39,7 @@ import {
FormMessage,
} from '@/components/ui/form';
import { Switch } from '@/components/ui/switch';
import { Check, Copy, Loader2, Plus } from 'lucide-react';
import { Loader2, Plus } from 'lucide-react';
import { toast } from 'sonner';
import { AdminService, type AdminModel } from '@/lib/api/services/admin';
@@ -64,7 +64,6 @@ const FormSchema = z.object({
instruct_type: z.string().default(''),
canonical_slug: z.string().default(''),
alias_ids_raw: z.string().default(''),
forwarded_model_id: z.string().default(''),
upstream_provider_id: z.string().default(''),
input_cost: z.coerce.number().min(0).default(0),
output_cost: z.coerce.number().min(0).default(0),
@@ -105,7 +104,6 @@ export function AddProviderModelDialog({
const [isPresetOpen, setIsPresetOpen] = useState(false);
const [selectedPresetLabel, setSelectedPresetLabel] =
useState('Select a preset');
const [forwardedModelIdCopied, setForwardedModelIdCopied] = useState(false);
const form = useForm<FormData>({
resolver: zodResolver(FormSchema) as never,
@@ -121,7 +119,6 @@ export function AddProviderModelDialog({
instruct_type: '',
canonical_slug: '',
alias_ids_raw: '',
forwarded_model_id: '',
upstream_provider_id: '',
input_cost: 0,
output_cost: 0,
@@ -183,7 +180,6 @@ export function AddProviderModelDialog({
: '',
canonical_slug: initialData.canonical_slug || '',
alias_ids_raw: listToString(initialData.alias_ids),
forwarded_model_id: initialData.forwarded_model_id || initialData.id,
upstream_provider_id:
typeof initialData.upstream_provider_id === 'string'
? initialData.upstream_provider_id
@@ -227,7 +223,6 @@ export function AddProviderModelDialog({
instruct_type: '',
canonical_slug: '',
alias_ids_raw: '',
forwarded_model_id: '',
upstream_provider_id: '',
input_cost: 0,
output_cost: 0,
@@ -285,7 +280,6 @@ export function AddProviderModelDialog({
);
form.setValue('canonical_slug', model.canonical_slug || '');
form.setValue('alias_ids_raw', listToString(model.alias_ids));
form.setValue('forwarded_model_id', model.forwarded_model_id || model.id);
form.setValue(
'upstream_provider_id',
typeof model.upstream_provider_id === 'string'
@@ -391,7 +385,6 @@ export function AddProviderModelDialog({
canonical_slug: data.canonical_slug?.trim() || null,
alias_ids: listFromString(data.alias_ids_raw || ''),
enabled: data.enabled,
forwarded_model_id: data.forwarded_model_id?.trim() || data.id,
};
if (isEdit) {
@@ -527,53 +520,6 @@ export function AddProviderModelDialog({
)}
/>
<FormField
control={form.control}
name='forwarded_model_id'
render={({ field }) => {
const handleCopy = () => {
const value = field.value || form.getValues('id');
if (!value) return;
navigator.clipboard.writeText(value);
setForwardedModelIdCopied(true);
setTimeout(() => setForwardedModelIdCopied(false), 1500);
};
return (
<FormItem>
<FormLabel>Upstream Model ID</FormLabel>
<FormControl>
<div className='flex gap-2'>
<Input
placeholder={
form.watch('id') || 'e.g., openai/gpt-4o'
}
{...field}
/>
<Button
type='button'
variant='outline'
size='icon'
onClick={handleCopy}
title='Copy model ID'
>
{forwardedModelIdCopied ? (
<Check className='h-4 w-4 text-green-500' />
) : (
<Copy className='h-4 w-4' />
)}
</Button>
</div>
</FormControl>
<FormDescription>
Model ID sent to the upstream provider. Defaults to the
model&apos;s own ID.
</FormDescription>
<FormMessage />
</FormItem>
);
}}
/>
<FormField
control={form.control}
name='name'
+577
View File
@@ -0,0 +1,577 @@
'use client';
import React, { useState, useEffect, useCallback } from 'react';
import { useForm } from 'react-hook-form';
import { zodResolver } from '@hookform/resolvers/zod';
import { z } from 'zod';
import { type Model } from '@/lib/api/schemas/models';
import { AdminService, type AdminModel } from '@/lib/api/services/admin';
import { Button } from '@/components/ui/button';
import { Input } from '@/components/ui/input';
import { Textarea } from '@/components/ui/textarea';
import {
Dialog,
DialogContent,
DialogDescription,
DialogHeader,
DialogTitle,
} from '@/components/ui/dialog';
import {
Form,
FormControl,
FormDescription,
FormField,
FormItem,
FormLabel,
FormMessage,
} from '@/components/ui/form';
import { Edit3, Loader2 } from 'lucide-react';
import { toast } from 'sonner';
import { Switch } from '@/components/ui/switch';
const EditModelFormSchema = z.object({
name: z.string().min(1, 'Name is required'),
description: z.string().optional(),
context_length: z.number().min(0),
prompt: z.number().min(0),
completion: z.number().min(0),
enabled: z.boolean(),
});
type EditModelFormData = z.infer<typeof EditModelFormSchema>;
const roundToFiveDecimals = (value: number | undefined | null): number => {
if (value === undefined || value === null || isNaN(value)) {
return 0;
}
return Math.round(value * 100000) / 100000;
};
const toNumber = (value: unknown, fallback = 0): number => {
if (typeof value === 'number' && Number.isFinite(value)) {
return value;
}
if (typeof value === 'string') {
const parsed = Number(value);
if (Number.isFinite(parsed)) {
return parsed;
}
}
return fallback;
};
const toStringArray = (value: unknown, fallback: string[]): string[] => {
if (!Array.isArray(value)) {
return fallback;
}
const filtered = value.filter(
(item): item is string => typeof item === 'string'
);
return filtered.length > 0 ? filtered : fallback;
};
interface EditModelFormProps {
model: Model;
providerId?: number;
onModelUpdate?: () => void;
onCancel?: () => void;
isOpen: boolean;
}
interface AdminModelData {
id: string;
name: string;
description?: string;
created: number;
context_length: number;
architecture: {
modality: string;
input_modalities: string[];
output_modalities: string[];
tokenizer: string;
instruct_type: string | null;
};
pricing: {
prompt: number;
completion: number;
request: number;
image: number;
web_search: number;
internal_reasoning: number;
};
per_request_limits: null | undefined;
top_provider: null | undefined;
upstream_provider_id: number;
enabled: boolean;
}
const normalizeAdminModelData = (
adminModel: AdminModel,
fallbackModel: Model,
providerId: number
): AdminModelData => {
const pricingRecord =
adminModel.pricing && typeof adminModel.pricing === 'object'
? (adminModel.pricing as Record<string, unknown>)
: {};
const architectureRecord =
adminModel.architecture && typeof adminModel.architecture === 'object'
? (adminModel.architecture as Record<string, unknown>)
: {};
return {
id: adminModel.id,
name: adminModel.name,
description: adminModel.description || '',
created: toNumber(adminModel.created, Math.floor(Date.now() / 1000)),
context_length: Math.max(
0,
Math.trunc(
toNumber(adminModel.context_length, fallbackModel.contextLength || 4096)
)
),
architecture: {
modality:
typeof architectureRecord.modality === 'string'
? architectureRecord.modality
: fallbackModel.modelType || 'text',
input_modalities: toStringArray(architectureRecord.input_modalities, [
fallbackModel.modelType || 'text',
]),
output_modalities: toStringArray(architectureRecord.output_modalities, [
fallbackModel.modelType || 'text',
]),
tokenizer:
typeof architectureRecord.tokenizer === 'string'
? architectureRecord.tokenizer
: '',
instruct_type:
typeof architectureRecord.instruct_type === 'string'
? architectureRecord.instruct_type
: null,
},
pricing: {
prompt: roundToFiveDecimals(
toNumber(pricingRecord.prompt, fallbackModel.input_cost)
),
completion: roundToFiveDecimals(
toNumber(pricingRecord.completion, fallbackModel.output_cost)
),
request: toNumber(pricingRecord.request, 0),
image: toNumber(pricingRecord.image, 0),
web_search: toNumber(pricingRecord.web_search, 0),
internal_reasoning: toNumber(pricingRecord.internal_reasoning, 0),
},
per_request_limits:
adminModel.per_request_limits === null ||
adminModel.per_request_limits === undefined
? adminModel.per_request_limits
: null,
top_provider:
adminModel.top_provider === null || adminModel.top_provider === undefined
? adminModel.top_provider
: null,
upstream_provider_id:
typeof adminModel.upstream_provider_id === 'number'
? adminModel.upstream_provider_id
: providerId,
enabled: adminModel.enabled !== false,
};
};
export function EditModelForm({
model,
providerId,
onModelUpdate,
onCancel,
isOpen,
}: EditModelFormProps) {
const [isSubmitting, setIsSubmitting] = useState(false);
const [adminModelData, setAdminModelData] = useState<AdminModelData | null>(
null
);
const [isNewOverride, setIsNewOverride] = useState(false);
const form = useForm<EditModelFormData>({
resolver: zodResolver(EditModelFormSchema),
defaultValues: {
name: model.name,
description: model.description || '',
context_length: model.contextLength || 4096,
prompt: roundToFiveDecimals(model.input_cost),
completion: roundToFiveDecimals(model.output_cost),
enabled: model.isEnabled !== false,
},
});
const loadAdminModel = useCallback(async () => {
if (!providerId) {
console.error('loadAdminModel called without providerId');
return;
}
try {
const adminModel = await AdminService.getProviderModel(
providerId,
model.id
);
const normalizedAdminModel = normalizeAdminModelData(
adminModel,
model,
providerId
);
setAdminModelData(normalizedAdminModel);
setIsNewOverride(false);
form.reset({
name: normalizedAdminModel.name,
description: normalizedAdminModel.description || '',
context_length: normalizedAdminModel.context_length,
prompt: normalizedAdminModel.pricing.prompt,
completion: normalizedAdminModel.pricing.completion,
enabled: normalizedAdminModel.enabled !== false,
});
} catch {
setIsNewOverride(true);
setAdminModelData({
id: model.full_name,
name: model.name,
description: model.description || '',
created: Math.floor(Date.now() / 1000),
context_length: model.contextLength || 4096,
architecture: {
modality: model.modelType || 'text',
input_modalities: [model.modelType || 'text'],
output_modalities: [model.modelType || 'text'],
tokenizer: '',
instruct_type: null,
},
pricing: {
prompt: roundToFiveDecimals(model.input_cost),
completion: roundToFiveDecimals(model.output_cost),
request: 0,
image: 0,
web_search: 0,
internal_reasoning: 0,
},
per_request_limits: null,
top_provider: null,
upstream_provider_id: providerId,
enabled: model.isEnabled !== false,
});
form.reset({
name: model.name,
description: model.description || '',
context_length: model.contextLength || 4096,
prompt: roundToFiveDecimals(model.input_cost),
completion: roundToFiveDecimals(model.output_cost),
enabled: model.isEnabled !== false,
});
}
}, [providerId, model, form]);
useEffect(() => {
if (isOpen && providerId) {
loadAdminModel();
} else if (isOpen && !providerId) {
console.error('EditModelForm opened without providerId', {
model,
providerId,
});
toast.error('Missing provider information for this model');
}
}, [isOpen, providerId, model, loadAdminModel]);
const onSubmit = async (data: EditModelFormData) => {
if (!providerId) {
console.error('onSubmit called without providerId', {
model,
providerId,
});
toast.error('Missing provider ID - cannot update model');
return;
}
if (!adminModelData) {
console.error('onSubmit called without adminModelData', {
model,
providerId,
adminModelData,
});
toast.error('Model data not loaded - please try reopening the form');
return;
}
setIsSubmitting(true);
try {
const payload = {
id: adminModelData.id,
name: data.name,
description: data.description || '',
created: adminModelData.created || Math.floor(Date.now() / 1000),
context_length: data.context_length,
architecture: adminModelData.architecture || {
modality: 'text',
input_modalities: ['text'],
output_modalities: ['text'],
tokenizer: '',
instruct_type: null,
},
pricing: {
prompt: roundToFiveDecimals(data.prompt),
completion: roundToFiveDecimals(data.completion),
request: 0,
image: 0,
web_search: 0,
internal_reasoning: 0,
},
per_request_limits: adminModelData.per_request_limits,
top_provider: adminModelData.top_provider,
upstream_provider_id: providerId,
enabled: data.enabled,
};
if (isNewOverride) {
await AdminService.createProviderModel(providerId, payload);
toast.success('Model override created successfully!');
} else {
await AdminService.updateProviderModel(
providerId,
adminModelData.id,
payload
);
toast.success('Model updated successfully!');
}
onModelUpdate?.();
onCancel?.();
} catch (error) {
const action = isNewOverride ? 'create' : 'update';
toast.error(`Failed to ${action} model. Please try again.`);
console.error(`Error ${action}ing model:`, error);
} finally {
setIsSubmitting(false);
}
};
const handleClose = () => {
if (!isSubmitting) {
onCancel?.();
}
};
return (
<Dialog open={isOpen} onOpenChange={handleClose}>
<DialogContent className='max-h-[90vh] overflow-y-auto sm:max-w-[600px]'>
<DialogHeader>
<DialogTitle className='flex items-center gap-2'>
<Edit3 className='h-5 w-5' />
{isNewOverride ? 'Create Model Override' : 'Edit Model Override'}
</DialogTitle>
<DialogDescription>
{isNewOverride
? `Create an override for &quot;${model.name}&quot;`
: `Update the model override for &quot;${model.name}&quot;`}
</DialogDescription>
</DialogHeader>
<Form {...form}>
<form onSubmit={form.handleSubmit(onSubmit)} className='space-y-4'>
<div className='grid grid-cols-1 gap-4 sm:grid-cols-2'>
<FormField
control={form.control}
name='name'
render={({ field }) => (
<FormItem>
<FormLabel>Display Name *</FormLabel>
<FormControl>
<Input
placeholder='e.g., GPT-4'
{...field}
className='w-full'
/>
</FormControl>
<FormDescription>
Custom display name for the model
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
<FormField
control={form.control}
name='context_length'
render={({ field }) => (
<FormItem>
<FormLabel>Context Length *</FormLabel>
<FormControl>
<Input
type='number'
min='0'
placeholder='4096'
value={field.value ?? ''}
onChange={(e) => {
const value = e.target.value;
field.onChange(
value === '' ? 0 : parseInt(value, 10) || 0
);
}}
onBlur={(e) => {
const value = parseInt(e.target.value, 10);
field.onChange(
Number.isNaN(value) ? 0 : Math.max(0, value)
);
}}
className='w-full'
/>
</FormControl>
<FormDescription>
Maximum context window size
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
</div>
<FormField
control={form.control}
name='description'
render={({ field }) => (
<FormItem>
<FormLabel>Description</FormLabel>
<FormControl>
<Textarea
placeholder='Brief description of the model...'
{...field}
rows={3}
className='w-full'
/>
</FormControl>
<FormDescription>
Optional description or notes about the model
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
<div className='grid grid-cols-1 gap-4 sm:grid-cols-2'>
<FormField
control={form.control}
name='prompt'
render={({ field }) => (
<FormItem>
<FormLabel>Input Cost (per 1M tokens) *</FormLabel>
<FormControl>
<Input
type='number'
step='0.00001'
min='0'
placeholder='5.00000'
value={field.value ?? ''}
onChange={(e) => {
const value = e.target.value;
field.onChange(value === '' ? 0 : parseFloat(value));
}}
onBlur={(e) => {
const value = parseFloat(e.target.value);
field.onChange(roundToFiveDecimals(value));
}}
className='w-full'
/>
</FormControl>
<FormDescription>
Cost in USD per 1,000,000 input tokens (max 5 decimals)
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
<FormField
control={form.control}
name='completion'
render={({ field }) => (
<FormItem>
<FormLabel>Output Cost (per 1M tokens) *</FormLabel>
<FormControl>
<Input
type='number'
step='0.00001'
min='0'
placeholder='15.00000'
value={field.value ?? ''}
onChange={(e) => {
const value = e.target.value;
field.onChange(value === '' ? 0 : parseFloat(value));
}}
onBlur={(e) => {
const value = parseFloat(e.target.value);
field.onChange(roundToFiveDecimals(value));
}}
className='w-full'
/>
</FormControl>
<FormDescription>
Cost in USD per 1,000,000 output tokens (max 5 decimals)
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
</div>
<FormField
control={form.control}
name='enabled'
render={({ field }) => (
<FormItem className='flex flex-row items-center justify-between rounded-lg border p-4'>
<div className='space-y-0.5'>
<FormLabel className='text-base'>Model Enabled</FormLabel>
<FormDescription>
Enable or disable this model override
</FormDescription>
</div>
<FormControl>
<Switch
checked={field.value}
onCheckedChange={field.onChange}
/>
</FormControl>
</FormItem>
)}
/>
<div className='flex justify-end gap-2 pt-4'>
<Button
type='button'
variant='outline'
onClick={handleClose}
disabled={isSubmitting}
>
Cancel
</Button>
<Button type='submit' disabled={isSubmitting}>
{isSubmitting ? (
<>
<Loader2 className='mr-2 h-4 w-4 animate-spin' />
{isNewOverride ? 'Creating...' : 'Updating...'}
</>
) : isNewOverride ? (
'Create Override'
) : (
'Update Model'
)}
</Button>
</div>
</form>
</Form>
</DialogContent>
</Dialog>
);
}
@@ -50,6 +50,7 @@ export function CashuPaymentWorkflow({
const [apiKeyInput, setApiKeyInput] = useState(apiKey);
const [isCreatingKey, setIsCreatingKey] = useState(false);
const [isTopupLoading, setIsTopupLoading] = useState(false);
const [hasInteractedManage, setHasInteractedManage] = useState(false);
const [hasInteractedTopup, setHasInteractedTopup] = useState(false);
const [balanceLimit, setBalanceLimit] = useState<string>('');
const [balanceLimitReset, setBalanceLimitReset] = useState<string>('');
@@ -294,6 +295,7 @@ export function CashuPaymentWorkflow({
<ApiKeyInput
value={apiKeyInput}
onApiKeyChange={handleApiKeyChange}
onFocus={() => setHasInteractedManage(true)}
/>
<div className='flex gap-2'>
<Button
@@ -1,6 +1,6 @@
'use client';
import { useState } from 'react';
import { useCallback, useState } from 'react';
import Image from 'next/image';
import { Copy, Loader2, Zap, KeyRound } from 'lucide-react';
import { toast } from 'sonner';
@@ -10,6 +10,7 @@ import { Input } from '@/components/ui/input';
import { Textarea } from '@/components/ui/textarea';
import { Label } from '@/components/ui/label';
import { Badge } from '@/components/ui/badge';
import { Separator } from '@/components/ui/separator';
import { Tabs, TabsContent, TabsList, TabsTrigger } from '@/components/ui/tabs';
interface RoutstrCreateKeySectionProps {
-2
View File
@@ -76,7 +76,6 @@ export const AdminModelSchema = z.object({
canonical_slug: z.string().nullable().optional(),
alias_ids: z.array(z.string()).nullable().optional(),
enabled: z.boolean().default(true),
forwarded_model_id: z.string().nullable().optional(),
});
export const ProviderModelsSchema = z.object({
@@ -1135,7 +1134,6 @@ export interface Transaction {
created_at: number;
collected: boolean;
swept: boolean;
source: 'x-cashu' | 'apikey';
}
export interface TransactionsResponse {
Generated
+1432 -1432
View File
File diff suppressed because it is too large Load Diff