fmt u

Reset reserved balance on startup

.github/workflows/test.yml

@@ -59,25 +59,30 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
           node-version: "18"
-          cache: "npm"
-          cache-dependency-path: ui/package-lock.json
+          cache: "pnpm"
+          cache-dependency-path: ui/pnpm-lock.yaml
 
       - name: Install UI dependencies
         working-directory: ./ui
-        run: npm ci
+        run: pnpm install --frozen-lockfile
 
       - name: Run UI format check
         working-directory: ./ui
-        run: npm run format-check
+        run: pnpm run format-check
 
       - name: Run UI linting
         working-directory: ./ui
-        run: npm run lint
+        run: pnpm run lint
 
       - name: Run UI build
         working-directory: ./ui
-        run: npm run build
+        run: pnpm run build

examples/create_child_keys.py

@@ -0,0 +1,45 @@
+import json
+import sys
+
+import httpx
+
+
+def create_child_keys(base_url: str, api_key: str, count: int = 3) -> list[str]:
+    headers = {"Authorization": f"Bearer {api_key}"}
+
+    print(f"Requesting {count} child keys from {base_url}...")
+
+    child_keys = []
+
+    for i in range(count):
+        try:
+            response = httpx.post(f"{base_url}/v1/balance/child-key", headers=headers)
+            if response.status_code == 200:
+                data = response.json()
+                child_keys.append(data["api_key"])
+                print(
+                    f"  [{i + 1}] Created: {data['api_key']} (Cost: {data['cost_msats']} msats)"
+                )
+            else:
+                print(f"  [{i + 1}] Failed: {response.status_code} - {response.text}")
+        except Exception as e:
+            print(f"  [{i + 1}] Error: {str(e)}")
+
+    return child_keys
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python create_child_keys.py <api_key_or_cashu_token> [base_url]")
+        sys.exit(1)
+
+    auth_key = sys.argv[1]
+    base_url = sys.argv[2] if len(sys.argv) > 2 else "http://localhost:8000"
+
+    keys = create_child_keys(base_url, auth_key)
+
+    if keys:
+        print("\nSuccessfully created child keys:")
+        print(json.dumps(keys, indent=2))
+    else:
+        print("\nNo child keys were created.")

migrations/versions/a86e5348850b_.py

@@ -0,0 +1,42 @@
+"""
+
+Revision ID: a86e5348850b
+Revises: b9667ffc5701
+Create Date: 2026-01-10 18:57:48.475781
+"""
+
+import sqlalchemy as sa
+import sqlmodel
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "a86e5348850b"
+down_revision = "b9667ffc5701"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Use batch_alter_table for SQLite compatibility
+    with op.batch_alter_table("api_keys", schema=None) as batch_op:
+        batch_op.add_column(
+            sa.Column(
+                "parent_key_hash", sqlmodel.sql.sqltypes.AutoString(), nullable=True
+            )
+        )
+        batch_op.create_index(
+            batch_op.f("ix_api_keys_parent_key_hash"), ["parent_key_hash"], unique=False
+        )
+        batch_op.create_foreign_key(
+            "fk_api_keys_parent_key_hash",
+            "api_keys",
+            ["parent_key_hash"],
+            ["hashed_key"],
+        )
+
+
+def downgrade() -> None:
+    with op.batch_alter_table("api_keys", schema=None) as batch_op:
+        batch_op.drop_constraint("fk_api_keys_parent_key_hash", type_="foreignkey")
+        batch_op.drop_index(batch_op.f("ix_api_keys_parent_key_hash"))
+        batch_op.drop_column("parent_key_hash")

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "routstr"
-version = "0.2.1"
+version = "0.2.2"
 description = "Payment proxy for your LLM endpoint using cashu and nostr."
 readme = "README.md"
 requires-python = ">=3.11"

routstr/auth.py

@@ -286,30 +286,55 @@ async def validate_bearer_key(
     )
 
 
+async def get_billing_key(key: ApiKey, session: AsyncSession) -> ApiKey:
+    """Returns the key that should be charged for the request."""
+    if key.parent_key_hash:
+        parent = await session.get(ApiKey, key.parent_key_hash)
+        if parent:
+            # We want to keep the total_requests and total_spent on the child key
+            # but use the balance and reserved_balance of the parent.
+            # However, pay_for_request updates reserved_balance and total_requests.
+            # To stay simple, we charge the parent's balance and update parent's total_requests.
+            return parent
+        else:
+            logger.error(
+                "Parent key not found for child key",
+                extra={
+                    "child_key_hash": key.hashed_key[:8] + "...",
+                    "parent_key_hash": key.parent_key_hash[:8] + "...",
+                },
+            )
+    return key
+
+
 async def pay_for_request(
     key: ApiKey, cost_per_request: int, session: AsyncSession
 ) -> int:
     """Process payment for a request."""
 
+    billing_key = await get_billing_key(key, session)
+
     logger.info(
         "Processing payment for request",
         extra={
             "key_hash": key.hashed_key[:8] + "...",
-            "current_balance": key.balance,
+            "billing_key_hash": billing_key.hashed_key[:8] + "...",
+            "current_balance": billing_key.balance,
             "required_cost": cost_per_request,
-            "sufficient_balance": key.balance >= cost_per_request,
+            "sufficient_balance": billing_key.balance >= cost_per_request,
         },
     )
 
-    if key.total_balance < cost_per_request:
+    if billing_key.total_balance < cost_per_request:
         logger.warning(
             "Insufficient balance for request",
             extra={
                 "key_hash": key.hashed_key[:8] + "...",
-                "balance": key.balance,
-                "reserved_balance": key.reserved_balance,
+                "billing_key_hash": billing_key.hashed_key[:8] + "...",
+                "balance": billing_key.balance,
+                "reserved_balance": billing_key.reserved_balance,
                 "required": cost_per_request,
-                "shortfall": cost_per_request - key.total_balance,
+                "shortfall": cost_per_request - billing_key.total_balance,
             },
         )
 
@@ -317,7 +342,7 @@ async def pay_for_request(
             status_code=402,
             detail={
                 "error": {
-                    "message": f"Insufficient balance: {cost_per_request} mSats required. {key.total_balance} available. (reserved: {key.reserved_balance})",
+                    "message": f"Insufficient balance: {cost_per_request} mSats required. {billing_key.total_balance} available. (reserved: {billing_key.reserved_balance})",
                     "type": "insufficient_quota",
                     "code": "insufficient_balance",
                 }
@@ -328,15 +353,16 @@ async def pay_for_request(
         "Charging base cost for request",
         extra={
             "key_hash": key.hashed_key[:8] + "...",
+            "billing_key_hash": billing_key.hashed_key[:8] + "...",
             "cost": cost_per_request,
-            "balance_before": key.balance,
+            "balance_before": billing_key.balance,
         },
     )
 
     # Charge the base cost for the request atomically to avoid race conditions
     stmt = (
         update(ApiKey)
-        .where(col(ApiKey.hashed_key) == key.hashed_key)
+        .where(col(ApiKey.hashed_key) == billing_key.hashed_key)
         .where(col(ApiKey.balance) - col(ApiKey.reserved_balance) >= cost_per_request)
         .values(
             reserved_balance=col(ApiKey.reserved_balance) + cost_per_request,
@@ -344,6 +370,16 @@ async def pay_for_request(
         )
     )
     result = await session.exec(stmt)  # type: ignore[call-overload]
+
+    # Also increment total_requests 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)
+            .values(total_requests=col(ApiKey.total_requests) + 1)
+        )
+        await session.exec(child_stmt)  # type: ignore[call-overload]
+
     await session.commit()
 
     if result.rowcount == 0:
@@ -351,8 +387,9 @@ async def pay_for_request(
             "Concurrent request depleted balance",
             extra={
                 "key_hash": key.hashed_key[:8] + "...",
+                "billing_key_hash": billing_key.hashed_key[:8] + "...",
                 "required_cost": cost_per_request,
-                "current_balance": key.balance,
+                "current_balance": billing_key.balance,
             },
         )
 
@@ -361,23 +398,26 @@ async def pay_for_request(
             status_code=402,
             detail={
                 "error": {
-                    "message": f"Insufficient balance: {cost_per_request} mSats required. {key.balance} available.",
+                    "message": f"Insufficient balance: {cost_per_request} mSats required. {billing_key.balance} available.",
                     "type": "insufficient_quota",
                     "code": "insufficient_balance",
                 }
             },
         )
 
-    await session.refresh(key)
+    await session.refresh(billing_key)
+    if billing_key.hashed_key != key.hashed_key:
+        await session.refresh(key)
 
     logger.info(
         "Payment processed successfully",
         extra={
             "key_hash": key.hashed_key[:8] + "...",
+            "billing_key_hash": billing_key.hashed_key[:8] + "...",
             "charged_amount": cost_per_request,
-            "new_balance": key.balance,
-            "total_spent": key.total_spent,
-            "total_requests": key.total_requests,
+            "new_balance": billing_key.balance,
+            "total_spent": billing_key.total_spent,
+            "total_requests": billing_key.total_requests,
         },
     )
 
@@ -387,9 +427,11 @@ async def pay_for_request(
 async def revert_pay_for_request(
     key: ApiKey, session: AsyncSession, cost_per_request: int
 ) -> None:
+    billing_key = await get_billing_key(key, session)
+
     stmt = (
         update(ApiKey)
-        .where(col(ApiKey.hashed_key) == key.hashed_key)
+        .where(col(ApiKey.hashed_key) == billing_key.hashed_key)
         .values(
             reserved_balance=col(ApiKey.reserved_balance) - cost_per_request,
             total_requests=col(ApiKey.total_requests) - 1,
@@ -397,27 +439,40 @@ async def revert_pay_for_request(
     )
 
     result = await session.exec(stmt)  # type: ignore[call-overload]
+
+    # Also decrement total_requests 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)
+            .values(total_requests=col(ApiKey.total_requests) - 1)
+        )
+        await session.exec(child_stmt)  # type: ignore[call-overload]
+
     await session.commit()
     if result.rowcount == 0:
         logger.error(
             "Failed to revert payment - insufficient reserved balance",
             extra={
                 "key_hash": key.hashed_key[:8] + "...",
+                "billing_key_hash": billing_key.hashed_key[:8] + "...",
                 "cost_to_revert": cost_per_request,
-                "current_reserved_balance": key.reserved_balance,
+                "current_reserved_balance": billing_key.reserved_balance,
             },
         )
         raise HTTPException(
             status_code=402,
             detail={
                 "error": {
-                    "message": f"failed to revert request payment: {cost_per_request} mSats required. {key.balance} available.",
+                    "message": f"failed to revert request payment: {cost_per_request} mSats required. {billing_key.balance} available.",
                     "type": "payment_error",
                     "code": "payment_error",
                 }
             },
         )
-    await session.refresh(key)
+    await session.refresh(billing_key)
+    if billing_key.hashed_key != key.hashed_key:
+        await session.refresh(key)
 
 
 async def adjust_payment_for_tokens(
@@ -428,25 +483,58 @@ async def adjust_payment_for_tokens(
     This is called after the initial payment and the upstream request is complete.
     Returns cost data to be included in the response.
     """
+    billing_key = await get_billing_key(key, session)
     model = response_data.get("model", "unknown")
 
     logger.debug(
         "Starting payment adjustment for tokens",
         extra={
             "key_hash": key.hashed_key[:8] + "...",
+            "billing_key_hash": billing_key.hashed_key[:8] + "...",
             "model": model,
             "deducted_max_cost": deducted_max_cost,
-            "current_balance": key.balance,
+            "current_balance": billing_key.balance,
             "has_usage": "usage" in response_data,
         },
     )
 
+    async def release_reservation_only() -> None:
+        """Fallback to release reservation without charging when main update fails."""
+        try:
+            release_stmt = (
+                update(ApiKey)
+                .where(col(ApiKey.hashed_key) == billing_key.hashed_key)
+                .values(
+                    reserved_balance=col(ApiKey.reserved_balance) - deducted_max_cost
+                )
+            )
+            await session.exec(release_stmt)  # type: ignore[call-overload]
+            await session.commit()
+            logger.warning(
+                "Released reservation without charging (fallback)",
+                extra={
+                    "key_hash": key.hashed_key[:8] + "...",
+                    "billing_key_hash": billing_key.hashed_key[:8] + "...",
+                    "deducted_max_cost": deducted_max_cost,
+                },
+            )
+        except Exception as e:
+            logger.error(
+                "Failed to release reservation in fallback",
+                extra={
+                    "error": str(e),
+                    "key_hash": key.hashed_key[:8] + "...",
+                    "billing_key_hash": billing_key.hashed_key[:8] + "...",
+                },
+            )
+
     match await calculate_cost(response_data, deducted_max_cost, session):
         case MaxCostData() as cost:
             logger.debug(
                 "Using max cost data (no token adjustment)",
                 extra={
                     "key_hash": key.hashed_key[:8] + "...",
+                    "billing_key_hash": billing_key.hashed_key[:8] + "...",
                     "model": model,
                     "max_cost": cost.total_msats,
                 },
@@ -454,7 +542,7 @@ async def adjust_payment_for_tokens(
             # Finalize by releasing reservation and charging max cost
             finalize_stmt = (
                 update(ApiKey)
-                .where(col(ApiKey.hashed_key) == key.hashed_key)
+                .where(col(ApiKey.hashed_key) == billing_key.hashed_key)
                 .values(
                     reserved_balance=col(ApiKey.reserved_balance) - deducted_max_cost,
                     balance=col(ApiKey.balance) - cost.total_msats,
@@ -462,26 +550,41 @@ async def adjust_payment_for_tokens(
                 )
             )
             result = await session.exec(finalize_stmt)  # type: ignore[call-overload]
+
+            # Also update total_spent 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)
+                    .values(total_spent=col(ApiKey.total_spent) + cost.total_msats)
+                )
+                await session.exec(child_stmt)  # type: ignore[call-overload]
+
             await session.commit()
             if result.rowcount == 0:
                 logger.error(
-                    "Failed to finalize max-cost payment - insufficient reserved balance",
+                    "Failed to finalize max-cost payment - retrying reservation release",
                     extra={
                         "key_hash": key.hashed_key[:8] + "...",
+                        "billing_key_hash": billing_key.hashed_key[:8] + "...",
                         "deducted_max_cost": deducted_max_cost,
-                        "current_reserved_balance": key.reserved_balance,
+                        "current_reserved_balance": billing_key.reserved_balance,
                         "total_cost": cost.total_msats,
                         "model": model,
                     },
                 )
+                await release_reservation_only()
             else:
-                await session.refresh(key)
+                await session.refresh(billing_key)
+                if billing_key.hashed_key != key.hashed_key:
+                    await session.refresh(key)
                 logger.info(
                     "Max cost payment finalized",
                     extra={
                         "key_hash": key.hashed_key[:8] + "...",
+                        "billing_key_hash": billing_key.hashed_key[:8] + "...",
                         "charged_amount": cost.total_msats,
-                        "new_balance": key.balance,
+                        "new_balance": billing_key.balance,
                         "model": model,
                     },
                 )
@@ -497,6 +600,7 @@ async def adjust_payment_for_tokens(
                 "Calculated token-based cost",
                 extra={
                     "key_hash": key.hashed_key[:8] + "...",
+                    "billing_key_hash": billing_key.hashed_key[:8] + "...",
                     "model": model,
                     "token_cost": cost.total_msats,
                     "deducted_max_cost": deducted_max_cost,
@@ -509,11 +613,15 @@ async def adjust_payment_for_tokens(
             if cost_difference == 0:
                 logger.debug(
                     "Finalizing with exact reserved cost",
-                    extra={"key_hash": key.hashed_key[:8] + "...", "model": model},
+                    extra={
+                        "key_hash": key.hashed_key[:8] + "...",
+                        "billing_key_hash": billing_key.hashed_key[:8] + "...",
+                        "model": model,
+                    },
                 )
                 finalize_stmt = (
                     update(ApiKey)
-                    .where(col(ApiKey.hashed_key) == key.hashed_key)
+                    .where(col(ApiKey.hashed_key) == billing_key.hashed_key)
                     .values(
                         reserved_balance=col(ApiKey.reserved_balance)
                         - deducted_max_cost,
@@ -522,8 +630,20 @@ async def adjust_payment_for_tokens(
                     )
                 )
                 await session.exec(finalize_stmt)  # type: ignore[call-overload]
+
+                # Also update total_spent 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)
+                        .values(total_spent=col(ApiKey.total_spent) + total_cost_msats)
+                    )
+                    await session.exec(child_stmt)  # type: ignore[call-overload]
+
                 await session.commit()
-                await session.refresh(key)
+                await session.refresh(billing_key)
+                if billing_key.hashed_key != key.hashed_key:
+                    await session.refresh(key)
                 return cost.dict()
 
             # this should never happen why do we handle this???
@@ -533,16 +653,17 @@ async def adjust_payment_for_tokens(
                     "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": key.balance,
-                        "sufficient_balance": key.balance >= 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) == key.hashed_key)
+                    .where(col(ApiKey.hashed_key) == billing_key.hashed_key)
                     .values(
                         reserved_balance=col(ApiKey.reserved_balance)
                         - deducted_max_cost,
@@ -551,30 +672,45 @@ async def adjust_payment_for_tokens(
                     )
                 )
                 result = await session.exec(finalize_stmt)  # type: ignore[call-overload]
+
+                # Also update total_spent 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)
+                        .values(total_spent=col(ApiKey.total_spent) + total_cost_msats)
+                    )
+                    await session.exec(child_stmt)  # type: ignore[call-overload]
+
                 await session.commit()
 
                 if result.rowcount:
                     cost.total_msats = total_cost_msats
-                    await session.refresh(key)
+                    await session.refresh(billing_key)
+                    if billing_key.hashed_key != key.hashed_key:
+                        await session.refresh(key)
 
                     logger.info(
                         "Finalized payment with additional charge",
                         extra={
                             "key_hash": key.hashed_key[:8] + "...",
+                            "billing_key_hash": billing_key.hashed_key[:8] + "...",
                             "charged_amount": total_cost_msats,
-                            "new_balance": key.balance,
+                            "new_balance": billing_key.balance,
                             "model": model,
                         },
                     )
                 else:
                     logger.warning(
-                        "Failed to finalize additional charge (concurrent operation)",
+                        "Failed to finalize additional charge - releasing reservation",
                         extra={
                             "key_hash": key.hashed_key[:8] + "...",
+                            "billing_key_hash": billing_key.hashed_key[:8] + "...",
                             "attempted_charge": total_cost_msats,
                             "model": model,
                         },
                     )
+                    await release_reservation_only()
             else:
                 # Refund some of the base cost
                 refund = abs(cost_difference)
@@ -582,15 +718,16 @@ async def adjust_payment_for_tokens(
                     "Refunding excess payment",
                     extra={
                         "key_hash": key.hashed_key[:8] + "...",
+                        "billing_key_hash": billing_key.hashed_key[:8] + "...",
                         "refund_amount": refund,
-                        "current_balance": key.balance,
+                        "current_balance": billing_key.balance,
                         "model": model,
                     },
                 )
 
                 refund_stmt = (
                     update(ApiKey)
-                    .where(col(ApiKey.hashed_key) == key.hashed_key)
+                    .where(col(ApiKey.hashed_key) == billing_key.hashed_key)
                     .values(
                         reserved_balance=col(ApiKey.reserved_balance)
                         - deducted_max_cost,
@@ -599,41 +736,54 @@ async def adjust_payment_for_tokens(
                     )
                 )
                 result = await session.exec(refund_stmt)  # type: ignore[call-overload]
+
+                # Also update total_spent 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)
+                        .values(total_spent=col(ApiKey.total_spent) + total_cost_msats)
+                    )
+                    await session.exec(child_stmt)  # type: ignore[call-overload]
+
                 await session.commit()
 
                 if result.rowcount == 0:
                     logger.error(
-                        "Failed to finalize payment - insufficient reserved balance",
+                        "Failed to finalize payment - releasing reservation",
                         extra={
                             "key_hash": key.hashed_key[:8] + "...",
+                            "billing_key_hash": billing_key.hashed_key[:8] + "...",
                             "deducted_max_cost": deducted_max_cost,
-                            "current_reserved_balance": key.reserved_balance,
+                            "current_reserved_balance": billing_key.reserved_balance,
                             "total_cost": total_cost_msats,
                             "model": model,
                         },
                     )
-                    # Still return the cost data even if we couldn't properly finalize
-                    # The reservation was already made, so the user has paid
+                    await release_reservation_only()
+                else:
+                    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
-                await session.refresh(key)
-
-                logger.info(
-                    "Refund processed successfully",
-                    extra={
-                        "key_hash": key.hashed_key[:8] + "...",
-                        "refunded_amount": refund,
-                        "new_balance": key.balance,
-                        "final_cost": cost.total_msats,
-                        "model": model,
-                    },
-                )
+                    logger.info(
+                        "Refund processed successfully",
+                        extra={
+                            "key_hash": key.hashed_key[:8] + "...",
+                            "billing_key_hash": billing_key.hashed_key[:8] + "...",
+                            "refunded_amount": refund,
+                            "new_balance": billing_key.balance,
+                            "final_cost": cost.total_msats,
+                            "model": model,
+                        },
+                    )
 
             return cost.dict()
 
         case CostDataError() as error:
             logger.error(
-                "Cost calculation error during payment adjustment",
+                "Cost calculation error during payment adjustment - releasing reservation",
                 extra={
                     "key_hash": key.hashed_key[:8] + "...",
                     "model": model,
@@ -641,6 +791,7 @@ async def adjust_payment_for_tokens(
                     "error_code": error.code,
                 },
             )
+            await release_reservation_only()
 
             raise HTTPException(
                 status_code=400,
@@ -652,7 +803,12 @@ async def adjust_payment_for_tokens(
                     }
                 },
             )
-    # Fallback return to satisfy type checker; execution should not reach here
+    # Fallback: should not reach here, but release reservation just in case
+    logger.error(
+        "Unexpected fallback in adjust_payment_for_tokens - releasing reservation",
+        extra={"key_hash": key.hashed_key[:8] + "...", "model": model},
+    )
+    await release_reservation_only()
     return {
         "base_msats": deducted_max_cost,
         "input_msats": 0,

routstr/balance.py

@@ -32,16 +32,30 @@ async def get_key_from_header(
     )
 
 
-# TODO: remove this endpoint when frontend is updated
-@router.get("/", include_in_schema=False)
-async def account_info(key: ApiKey = Depends(get_key_from_header)) -> dict:
+async def get_balance_info(key: ApiKey, session: AsyncSession) -> dict:
+    from .auth import get_billing_key
+
+    billing_key = await get_billing_key(key, session)
     return {
         "api_key": "sk-" + key.hashed_key,
-        "balance": key.balance,
-        "reserved": key.reserved_balance,
+        "balance": billing_key.balance,
+        "reserved": billing_key.reserved_balance,
+        "is_child": key.parent_key_hash is not None,
+        "parent_key": "sk-" + key.parent_key_hash if key.parent_key_hash else None,
+        "total_requests": key.total_requests,
+        "total_spent": key.total_spent,
     }
 
 
+# TODO: remove this endpoint when frontend is updated
+@router.get("/", include_in_schema=False)
+async def account_info(
+    key: ApiKey = Depends(get_key_from_header),
+    session: AsyncSession = Depends(get_session),
+) -> dict:
+    return await get_balance_info(key, session)
+
+
 # TODO: Implement POST /v1/wallet/create endpoint
 # This endpoint should accept:
 # - cashu_token (required): The eCash token to deposit
@@ -66,12 +80,11 @@ async def create_balance(
 
 
 @router.get("/info")
-async def wallet_info(key: ApiKey = Depends(get_key_from_header)) -> dict:
-    return {
-        "api_key": "sk-" + key.hashed_key,
-        "balance": key.balance,
-        "reserved": key.reserved_balance,
-    }
+async def wallet_info(
+    key: ApiKey = Depends(get_key_from_header),
+    session: AsyncSession = Depends(get_session),
+) -> dict:
+    return await get_balance_info(key, session)
 
 
 class TopupRequest(BaseModel):
@@ -85,6 +98,10 @@ async def topup_wallet_endpoint(
     key: ApiKey = Depends(get_key_from_header),
     session: AsyncSession = Depends(get_session),
 ) -> dict[str, int]:
+    from .auth import get_billing_key
+
+    billing_key = await get_billing_key(key, session)
+
     if topup_request is not None:
         cashu_token = topup_request.cashu_token
     if cashu_token is None:
@@ -94,7 +111,7 @@ async def topup_wallet_endpoint(
     if len(cashu_token) < 10 or "cashu" not in cashu_token:
         raise HTTPException(status_code=400, detail="Invalid token format")
     try:
-        amount_msats = await credit_balance(cashu_token, key, session)
+        amount_msats = await credit_balance(cashu_token, billing_key, session)
     except ValueError as e:
         error_msg = str(e)
         if "already spent" in error_msg.lower():
@@ -154,7 +171,14 @@ async def refund_wallet_endpoint(
         return cached
 
     key: ApiKey = await validate_bearer_key(bearer_value, session)
-    remaining_balance_msats: int = key.balance
+
+    if key.parent_key_hash:
+        raise HTTPException(
+            status_code=400,
+            detail="Cannot refund child key. Please refund the parent key instead.",
+        )
+
+    remaining_balance_msats: int = key.total_balance
 
     if key.refund_currency == "sat":
         remaining_balance = remaining_balance_msats // 1000
@@ -227,6 +251,53 @@ async def donate(token: str, ref: str | None = None) -> str:
         return "Invalid token."
 
 
+@router.post("/child-key")
+async def create_child_key(
+    key: ApiKey = Depends(get_key_from_header),
+    session: AsyncSession = Depends(get_session),
+) -> dict:
+    """Creates a child API key that uses the parent's balance."""
+    # Check if this is already a child key
+    if key.parent_key_hash:
+        raise HTTPException(
+            status_code=400,
+            detail="Cannot create a child key for another child key.",
+        )
+
+    cost = settings.child_key_cost
+
+    if key.total_balance < cost:
+        raise HTTPException(
+            status_code=402,
+            detail=f"Insufficient balance to create child key. {cost} mSats required.",
+        )
+
+    # Deduct cost from parent
+    key.balance -= cost
+    key.total_spent += cost
+    session.add(key)
+
+    # Generate new key
+    import secrets
+
+    new_key_raw = secrets.token_hex(32)
+    new_key_hash = new_key_raw  # We use the raw key as the hash for sk- keys
+
+    child_key = ApiKey(
+        hashed_key=new_key_hash,
+        balance=0,
+        parent_key_hash=key.hashed_key,
+    )
+    session.add(child_key)
+    await session.commit()
+
+    return {
+        "api_key": "sk-" + new_key_hash,
+        "cost_msats": cost,
+        "parent_balance": key.balance,
+    }
+
+
 @router.api_route(
     "/{path:path}",
     methods=["GET", "POST", "PUT", "DELETE"],

routstr/core/admin.py

@@ -124,7 +124,7 @@ async def partial_apikeys(request: Request) -> str:
 
     rows = "".join(
         [
-            f"<tr><td>{key.hashed_key}</td><td>{key.balance}</td><td>{key.total_spent}</td><td>{key.total_requests}</td><td>{key.refund_address}</td><td>{fmt_time(key.key_expiry_time)}</td></tr>"
+            f"<tr><td>{key.hashed_key}{' <br><small>(Child of ' + key.parent_key_hash[:8] + '...)</small>' if key.parent_key_hash else ''}</td><td>{key.balance}</td><td>{key.total_spent}</td><td>{key.total_requests}</td><td>{key.refund_address}</td><td>{fmt_time(key.key_expiry_time)}</td></tr>"
             for key in api_keys
         ]
     )
@@ -158,6 +158,7 @@ async def get_temporary_balances_api(request: Request) -> list[dict[str, object]
             "total_requests": key.total_requests,
             "refund_address": key.refund_address,
             "key_expiry_time": key.key_expiry_time,
+            "parent_key_hash": key.parent_key_hash,
         }
         for key in api_keys
     ]
@@ -3080,6 +3081,9 @@ async def get_logs_api(
     level: str | None = None,
     request_id: str | None = None,
     search: str | None = None,
+    status_codes: str | None = Query(None, description="Comma-separated status codes"),
+    methods: str | None = Query(None, description="Comma-separated HTTP methods"),
+    endpoints: str | None = Query(None, description="Comma-separated endpoints"),
     limit: int = 100,
 ) -> dict[str, object]:
     """
@@ -3090,16 +3094,32 @@ async def get_logs_api(
         level: Filter by log level
         request_id: Filter by request ID
         search: Search text in message and name fields (case-insensitive)
+        status_codes: Comma-separated list of HTTP status codes
+        methods: Comma-separated list of HTTP methods
+        endpoints: Comma-separated list of endpoints
         limit: Maximum number of entries to return
 
     Returns:
         Dict containing logs and filter metadata
     """
+    status_code_list = None
+    if status_codes:
+        try:
+            status_code_list = [int(s.strip()) for s in status_codes.split(",")]
+        except ValueError:
+            pass
+
+    method_list = [m.strip() for m in methods.split(",")] if methods else None
+    endpoint_list = [e.strip() for e in endpoints.split(",")] if endpoints else None
+
     log_entries = log_manager.search_logs(
         date=date,
         level=level,
         request_id=request_id,
         search_text=search,
+        status_codes=status_code_list,
+        methods=method_list,
+        endpoints=endpoint_list,
         limit=limit,
     )
 
@@ -3110,6 +3130,9 @@ async def get_logs_api(
         "level": level,
         "request_id": request_id,
         "search": search,
+        "status_codes": status_codes,
+        "methods": methods,
+        "endpoints": endpoints,
         "limit": limit,
     }
 

routstr/core/db.py

@@ -6,7 +6,7 @@ from typing import AsyncGenerator
 from alembic import command
 from alembic.config import Config
 from sqlalchemy.ext.asyncio.engine import create_async_engine
-from sqlmodel import Field, Relationship, SQLModel, func, select
+from sqlmodel import Field, Relationship, SQLModel, func, select, update
 from sqlmodel.ext.asyncio.session import AsyncSession
 
 from .logging import get_logger
@@ -47,12 +47,23 @@ class ApiKey(SQLModel, table=True):  # type: ignore
         default=None,
         description="Currency of the cashu-token",
     )
+    parent_key_hash: str | None = Field(
+        default=None, foreign_key="api_keys.hashed_key", index=True
+    )
 
     @property
     def total_balance(self) -> int:
         return self.balance - self.reserved_balance
 
 
+async def reset_all_reserved_balances(session: AsyncSession) -> None:
+    logger.info("Resetting all reserved balances to 0")
+    stmt = update(ApiKey).values(reserved_balance=0)
+    await session.exec(stmt)  # type: ignore[call-overload]
+    await session.commit()
+    logger.info("Reserved balances reset successfully")
+
+
 class ModelRow(SQLModel, table=True):  # type: ignore
     __tablename__ = "models"
     id: str = Field(primary_key=True)

routstr/core/log_manager.py

@@ -105,6 +105,9 @@ class LogManager:
         level: str | None = None,
         request_id: str | None = None,
         search_text: str | None = None,
+        status_codes: list[int] | None = None,
+        methods: list[str] | None = None,
+        endpoints: list[str] | None = None,
         limit: int = 100,
     ) -> list[dict[str, Any]]:
         """
@@ -134,7 +137,13 @@ class LogManager:
 
         for log_data in iterator:
             if not self._matches_filters(
-                log_data, level, request_id, search_text_lower
+                log_data,
+                level,
+                request_id,
+                search_text_lower,
+                status_codes,
+                methods,
+                endpoints,
             ):
                 continue
 
@@ -153,6 +162,9 @@ class LogManager:
         level: str | None,
         request_id: str | None,
         search_text_lower: str | None,
+        status_codes: list[int] | None = None,
+        methods: list[str] | None = None,
+        endpoints: list[str] | None = None,
     ) -> bool:
         if level and log_data.get("levelname", "").upper() != level.upper():
             return False
@@ -160,6 +172,36 @@ class LogManager:
         if request_id and log_data.get("request_id") != request_id:
             return False
 
+        if status_codes:
+            entry_status = log_data.get("status_code")
+            if entry_status is not None:
+                try:
+                    if int(entry_status) not in status_codes:
+                        return False
+                except (ValueError, TypeError):
+                    return False
+            else:
+                return False
+
+        if methods:
+            entry_method = log_data.get("method", "").upper()
+            if entry_method not in [m.upper() for m in methods]:
+                return False
+
+        if endpoints:
+            entry_path = log_data.get("path", "")
+            matched = False
+            for endpoint in endpoints:
+                clean_endpoint = endpoint.lstrip("/")
+                if entry_path.startswith(clean_endpoint):
+                    matched = True
+                    break
+                if clean_endpoint in entry_path:
+                    matched = True
+                    break
+            if not matched:
+                return False
+
         if search_text_lower:
             message = str(log_data.get("message", "")).lower()
             name = str(log_data.get("name", "")).lower()

routstr/core/main.py

@@ -13,10 +13,7 @@ from starlette.exceptions import HTTPException
 from ..balance import balance_router, deprecated_wallet_router
 from ..discovery import providers_cache_refresher, providers_router
 from ..nip91 import announce_provider
-from ..payment.models import (
-    models_router,
-    update_sats_pricing,
-)
+from ..payment.models import models_router, update_sats_pricing
 from ..payment.price import update_prices_periodically
 from ..proxy import initialize_upstreams, proxy_router, refresh_model_maps_periodically
 from ..wallet import periodic_payout
@@ -33,9 +30,9 @@ setup_logging()
 logger = get_logger(__name__)
 
 if os.getenv("VERSION_SUFFIX") is not None:
-    __version__ = f"0.2.1-{os.getenv('VERSION_SUFFIX')}"
+    __version__ = f"0.2.2-{os.getenv('VERSION_SUFFIX')}"
 else:
-    __version__ = "0.2.1"
+    __version__ = "0.2.2"
 
 
 @asynccontextmanager
@@ -61,6 +58,10 @@ async def lifespan(_: FastAPI) -> AsyncGenerator[None, None]:
         # Initialize application settings (env -> computed -> DB precedence)
         async with create_session() as session:
             s = await SettingsService.initialize(session)
+            if s.reset_reserved_balance_on_startup:
+                from .db import reset_all_reserved_balances
+
+                await reset_all_reserved_balances(session)
 
         # Apply app metadata from settings
         try:

routstr/core/settings.py

@@ -6,7 +6,7 @@ import os
 from datetime import datetime, timezone
 from typing import Any
 
-from pydantic.v1 import BaseModel, BaseSettings, Field
+from pydantic.v1 import BaseModel, BaseSettings, Field, validator
 from sqlmodel.ext.asyncio.session import AsyncSession
 
 
@@ -37,6 +37,13 @@ class Settings(BaseSettings):
 
     # Cashu
     cashu_mints: list[str] = Field(default_factory=list, env="CASHU_MINTS")
+
+    @validator("cashu_mints", pre=True, each_item=True)
+    def normalize_mint_url(cls, v: str) -> str:
+        if isinstance(v, str):
+            return v.rstrip("/")
+        return v
+
     receive_ln_address: str = Field(default="", env="RECEIVE_LN_ADDRESS")
     primary_mint: str = Field(default="", env="PRIMARY_MINT_URL")
     primary_mint_unit: str = Field(default="sat", env="PRIMARY_MINT_UNIT")
@@ -52,8 +59,12 @@ class Settings(BaseSettings):
     exchange_fee: float = Field(default=1.005, env="EXCHANGE_FEE")
     upstream_provider_fee: float = Field(default=1.05, env="UPSTREAM_PROVIDER_FEE")
     tolerance_percentage: float = Field(default=1.0, env="TOLERANCE_PERCENTAGE")
+    child_key_cost: int = Field(default=1000, env="CHILD_KEY_COST")
     # Minimum per-request charge in millisatoshis when model pricing is free/zero
     min_request_msat: int = Field(default=1, env="MIN_REQUEST_MSAT")
+    reset_reserved_balance_on_startup: bool = Field(
+        default=True, env="RESET_RESERVED_BALANCE_ON_STARTUP"
+    )  # deactivate in horizontal scaling setups
 
     # Network
     cors_origins: list[str] = Field(default_factory=lambda: ["*"], env="CORS_ORIGINS")

routstr/payment/cost_calculation.py

@@ -48,13 +48,6 @@ async def calculate_cost(  # todo: can be sync
         },
     )
 
-    cost_data = MaxCostData(
-        base_msats=max_cost,
-        input_msats=0,
-        output_msats=0,
-        total_msats=max_cost,
-    )
-
     if "usage" not in response_data or response_data["usage"] is None:
         logger.warning(
             "No usage data in response, using base cost only",
@@ -63,7 +56,12 @@ async def calculate_cost(  # todo: can be sync
                 "model": response_data.get("model", "unknown"),
             },
         )
-        return cost_data
+        return MaxCostData(
+            base_msats=0,
+            input_msats=0,
+            output_msats=0,
+            total_msats=0,
+        )
 
     usage_data = response_data["usage"]
 
@@ -178,7 +176,12 @@ async def calculate_cost(  # todo: can be sync
                 "model": response_data.get("model", "unknown"),
             },
         )
-        return cost_data
+        return MaxCostData(
+            base_msats=max_cost,
+            input_msats=0,
+            output_msats=0,
+            total_msats=max_cost,
+        )
 
     input_tokens = usage_data.get("prompt_tokens", 0)
     output_tokens = usage_data.get("completion_tokens", 0)
@@ -192,8 +195,16 @@ async def calculate_cost(  # todo: can be sync
     )
 
     # added for response api
-    input_tokens = input_tokens if input_tokens != 0 else  response_data.get("usage", {}).get("input_tokens", 0)
-    output_tokens = output_tokens if output_tokens != 0 else  response_data.get("usage", {}).get("output_tokens", 0)
+    input_tokens = (
+        input_tokens
+        if input_tokens != 0
+        else response_data.get("usage", {}).get("input_tokens", 0)
+    )
+    output_tokens = (
+        output_tokens
+        if output_tokens != 0
+        else response_data.get("usage", {}).get("output_tokens", 0)
+    )
 
     input_msats = round(input_tokens / 1000 * MSATS_PER_1K_INPUT_TOKENS, 3)
 

routstr/payment/lnurl.py

@@ -283,7 +283,7 @@ async def raw_send_to_lnurl(
             f"({min_sendable_sat} - {max_sendable_sat} {unit})"
         )
 
-    estimated_fees_sat = int(max(math.ceil((amount_msat / 1000) * 0.01), 2))
+    estimated_fees_sat = int(max(math.ceil((amount_msat / 1000) * 0.01), 2)) + 1
     estimated_fees_msat = estimated_fees_sat * 1000
     final_amount = amount_msat - estimated_fees_msat
 

routstr/proxy.py

@@ -16,6 +16,7 @@ from .core.db import (
     create_session,
     get_session,
 )
+from .core.settings import settings
 from .payment.helpers import (
     calculate_discounted_max_cost,
     check_token_balance,
@@ -25,6 +26,7 @@ from .payment.helpers import (
 from .payment.models import Model
 from .upstream import BaseUpstreamProvider
 from .upstream.helpers import init_upstreams
+from .wallet import deserialize_token_from_string
 
 logger = get_logger(__name__)
 proxy_router = APIRouter()
@@ -146,6 +148,24 @@ async def proxy(
     else:
         model_id = request_body_dict.get("model", "unknown")
 
+    if "https://testnut.cashu.space" in settings.cashu_mints:
+        try:
+            token_str = None
+            if x_cashu_header := headers.get("x-cashu"):
+                token_str = x_cashu_header
+            elif auth_header := headers.get("authorization"):
+                parts = auth_header.split(" ")
+                if len(parts) > 1 and not parts[1].startswith("sk-"):
+                    token_str = parts[1]
+
+            if token_str:
+                token_obj = deserialize_token_from_string(token_str)
+                if token_obj.mint == "https://testnut.cashu.space":
+                    model_id = "mock/gpt-420-mock"
+                    request_body_dict["model"] = model_id
+        except Exception:
+            pass
+
     model_obj = get_model_instance(model_id)
     if not model_obj:
         return create_error_response(
@@ -337,7 +357,7 @@ def extract_model_from_responses_request(request_body_dict: dict[str, Any]) -> s
 
     logger.warning(
         "No model found in Responses API request",
-        extra={"body_keys": list(request_body_dict.keys())}
+        extra={"body_keys": list(request_body_dict.keys())},
     )
     return "unknown"
 

routstr/upstream/base.py

@@ -234,7 +234,11 @@ class BaseUpstreamProvider:
                     )
 
                 # Handle model in input field (alternative format)
-                if "input" in data and isinstance(data["input"], dict) and "model" in data["input"]:
+                if (
+                    "input" in data
+                    and isinstance(data["input"], dict)
+                    and "model" in data["input"]
+                ):
                     original_model = model_obj.id
                     transformed_model = self.transform_model_name(original_model)
                     data["input"]["model"] = transformed_model
@@ -443,6 +447,11 @@ class BaseUpstreamProvider:
                 async with create_session() as new_session:
                     fresh_key = await new_session.get(key.__class__, key.hashed_key)
                     if not fresh_key:
+                        logger.warning(
+                            "Key not found when finalizing streaming payment",
+                            extra={"key_hash": key.hashed_key[:8] + "..."},
+                        )
+                        usage_finalized = True
                         return None
                     try:
                         fallback: dict = {
@@ -471,6 +480,7 @@ class BaseUpstreamProvider:
                                 "key_hash": key.hashed_key[:8] + "...",
                             },
                         )
+                        usage_finalized = True
                         return None
 
             try:
@@ -580,8 +590,10 @@ class BaseUpstreamProvider:
                         "key_hash": key.hashed_key[:8] + "...",
                     },
                 )
-                await finalize_without_usage()
                 raise
+            finally:
+                if not usage_finalized:
+                    await finalize_without_usage()
 
         # Remove inaccurate encoding headers from upstream response
         response_headers = dict(response.headers)
@@ -734,6 +746,11 @@ class BaseUpstreamProvider:
                 async with create_session() as new_session:
                     fresh_key = await new_session.get(key.__class__, key.hashed_key)
                     if not fresh_key:
+                        logger.warning(
+                            "Key not found when finalizing Responses API streaming payment",
+                            extra={"key_hash": key.hashed_key[:8] + "..."},
+                        )
+                        usage_finalized = True
                         return None
                     try:
                         fallback: dict = {
@@ -762,6 +779,7 @@ class BaseUpstreamProvider:
                                 "key_hash": key.hashed_key[:8] + "...",
                             },
                         )
+                        usage_finalized = True
                         return None
 
             try:
@@ -779,8 +797,13 @@ class BaseUpstreamProvider:
 
                                     # Track reasoning tokens for Responses API
                                     if usage := obj.get("usage", {}):
-                                        if isinstance(usage, dict) and "reasoning_tokens" in usage:
-                                            reasoning_tokens += usage.get("reasoning_tokens", 0)
+                                        if (
+                                            isinstance(usage, dict)
+                                            and "reasoning_tokens" in usage
+                                        ):
+                                            reasoning_tokens += usage.get(
+                                                "reasoning_tokens", 0
+                                            )
                             except json.JSONDecodeError:
                                 pass
                     except Exception:
@@ -881,8 +904,10 @@ class BaseUpstreamProvider:
                         "key_hash": key.hashed_key[:8] + "...",
                     },
                 )
-                await finalize_without_usage()
                 raise
+            finally:
+                if not usage_finalized:
+                    await finalize_without_usage()
 
         # Remove inaccurate encoding headers from upstream response
         response_headers = dict(response.headers)
@@ -933,8 +958,8 @@ class BaseUpstreamProvider:
                     "model": response_json.get("model", "unknown"),
                     "has_usage": "usage" in response_json,
                     "has_reasoning_tokens": "usage" in response_json
-                        and isinstance(response_json.get("usage"), dict)
-                        and "reasoning_tokens" in response_json["usage"],
+                    and isinstance(response_json.get("usage"), dict)
+                    and "reasoning_tokens" in response_json["usage"],
                 },
             )
 
@@ -1001,6 +1026,44 @@ class BaseUpstreamProvider:
             )
             raise
 
+    async def _finalize_generic_streaming_payment(
+        self, key_hash: str, max_cost: int, path: str
+    ) -> None:
+        """Background task to finalize payment for generic streaming requests."""
+        async with create_session() as session:
+            key = await session.get(ApiKey, key_hash)
+            if not key:
+                logger.warning(
+                    "Key not found during background payment finalization",
+                    extra={"key_hash": key_hash[:8] + "..."},
+                )
+                return
+
+            try:
+                # Finalize with "unknown" model and no usage to release reservation/charge max cost
+                await adjust_payment_for_tokens(
+                    key,
+                    {"model": "unknown", "usage": None},
+                    session,
+                    max_cost,
+                )
+                logger.info(
+                    "Finalized generic streaming payment in background",
+                    extra={
+                        "path": path,
+                        "key_hash": key_hash[:8] + "...",
+                    },
+                )
+            except Exception as e:
+                logger.error(
+                    "Error finalizing generic streaming payment in background",
+                    extra={
+                        "error": str(e),
+                        "key_hash": key_hash[:8] + "...",
+                        "path": path,
+                    },
+                )
+
     async def forward_request(
         self,
         request: Request,
@@ -1152,6 +1215,12 @@ class BaseUpstreamProvider:
             background_tasks = BackgroundTasks()
             background_tasks.add_task(response.aclose)
             background_tasks.add_task(client.aclose)
+            background_tasks.add_task(
+                self._finalize_generic_streaming_payment,
+                key.hashed_key,
+                max_cost_for_model,
+                path,
+            )
 
             logger.debug(
                 "Streaming non-chat response",
@@ -1355,9 +1424,15 @@ class BaseUpstreamProvider:
             background_tasks = BackgroundTasks()
             background_tasks.add_task(response.aclose)
             background_tasks.add_task(client.aclose)
+            background_tasks.add_task(
+                self._finalize_generic_streaming_payment,
+                key.hashed_key,
+                max_cost_for_model,
+                path,
+            )
 
             logger.debug(
-                "Streaming non-chat response",
+                "Streaming non-Responses API response",
                 extra={
                     "path": path,
                     "status_code": response.status_code,
@@ -2503,7 +2578,10 @@ class BaseUpstreamProvider:
                         usage_data = data_json["usage"]
                         model = data_json.get("model")
                         # Track reasoning tokens for Responses API
-                        if isinstance(usage_data, dict) and "reasoning_tokens" in usage_data:
+                        if (
+                            isinstance(usage_data, dict)
+                            and "reasoning_tokens" in usage_data
+                        ):
                             reasoning_tokens = usage_data.get("reasoning_tokens", 0)
                     elif "model" in data_json and not model:
                         model = data_json["model"]

routstr/upstream/fake.py

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

routstr/upstream/gemini.py

@@ -187,11 +187,44 @@ class GeminiUpstreamProvider(BaseUpstreamProvider):
                 )
 
                 async def stream_with_cost() -> AsyncGenerator[bytes, None]:
+                    payment_finalized = False
+
+                    async def finalize_payment() -> None:
+                        nonlocal payment_finalized
+                        if payment_finalized:
+                            return
+                        from ..auth import adjust_payment_for_tokens
+                        from ..core.db import create_session
+
+                        async with create_session() as new_session:
+                            fresh_key = await new_session.get(
+                                key.__class__, key.hashed_key
+                            )
+                            if fresh_key:
+                                try:
+                                    await adjust_payment_for_tokens(
+                                        fresh_key,
+                                        {
+                                            "model": model_obj.id,
+                                            "usage": final_usage_data,
+                                        },
+                                        new_session,
+                                        max_cost_for_model,
+                                    )
+                                    payment_finalized = True
+                                except Exception as cost_error:
+                                    logger.error(
+                                        "Error finalizing Gemini streaming payment in fallback",
+                                        extra={
+                                            "error": str(cost_error),
+                                            "key_hash": key.hashed_key[:8] + "...",
+                                        },
+                                    )
+
                     try:
                         async for chunk in response_generator:
                             sse_data = f"data: {json.dumps(chunk)}\n\n"
                             yield sse_data.encode()
-
                     except Exception as e:
                         logger.error(
                             "Error in Gemini streaming response",
@@ -202,6 +235,9 @@ class GeminiUpstreamProvider(BaseUpstreamProvider):
                             },
                         )
                         raise
+                    finally:
+                        if not payment_finalized:
+                            await finalize_payment()
 
                 return StreamingResponse(
                     stream_with_cost(),

routstr/upstream/helpers.py

@@ -218,6 +218,14 @@ async def init_upstreams() -> list[BaseUpstreamProvider]:
         results = await asyncio.gather(*tasks)
         upstreams = [p for p in results if p is not None]
 
+        if "https://testnut.cashu.space" in settings.cashu_mints:
+            from .fake import MockUpstreamProvider
+
+            mock_provider = MockUpstreamProvider("mock", "mock")
+            await mock_provider.refresh_models_cache()
+            upstreams.append(mock_provider)
+            logger.info("Initialized MockUpstreamProvider for testnut mint")
+
         return upstreams
 
 

routstr/wallet.py

@@ -81,7 +81,7 @@ async def swap_to_primary_mint(
         amount_msat = token_amount
     else:
         raise ValueError("Invalid unit")
-    estimated_fee_sat = math.ceil(max(amount_msat // 1000 * 0.01, 2))
+    estimated_fee_sat = math.ceil(max(amount_msat // 1000 * 0.01, 2)) + 1
     amount_msat_after_fee = amount_msat - estimated_fee_sat * 1000
     primary_wallet = await get_wallet(settings.primary_mint, settings.primary_mint_unit)
 
@@ -313,6 +313,8 @@ async def periodic_payout() -> None:
         try:
             async with db.create_session() as session:
                 for mint_url in settings.cashu_mints:
+                    if mint_url == "https://testnut.cashu.space":
+                        continue
                     for unit in ["sat", "msat"]:
                         wallet = await get_wallet(mint_url, unit)
                         proofs = get_proofs_per_mint_and_unit(

scripts/reproduce_bug_staging.py

@@ -0,0 +1,101 @@
+import asyncio
+
+import httpx
+
+BASE_URL = input("Enter routstr URL: ")
+API_KEY = input("Enter key or token: ")
+
+
+async def get_balance(client: httpx.AsyncClient) -> int:
+    response = await client.get("/v1/balance/info")
+    response.raise_for_status()
+    data = response.json()
+    print(f"Current Balance Info: {data}")
+    return data.get("reserved", 0)
+
+
+async def reproduce() -> None:
+    headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}
+
+    async with httpx.AsyncClient(
+        base_url=BASE_URL, headers=headers, timeout=30.0
+    ) as client:
+        print("Checking initial balance...")
+        try:
+            initial_reserved = await get_balance(client)
+        except Exception as e:
+            print(f"Failed to get balance: {e}")
+            return
+
+        print("\nStarting streaming request...")
+        try:
+            # Create a separate client for the stream so we can close it independently if needed,
+            # but usually just breaking the loop and exiting the context manager is enough.
+            # However, to be sure we simulate a harsh disconnect, we can just cancel the task or close the client.
+
+            async with client.stream(
+                "POST",
+                "/v1/chat/completions",
+                json={
+                    "model": "gpt-5-nano",
+                    "messages": [
+                        {
+                            "role": "user",
+                            "content": "Write a long poem about the ocean.",
+                        }
+                    ],
+                    "stream": True,
+                },
+            ) as response:
+                print(f"Stream status: {response.status_code}")
+                if response.status_code != 200:
+                    err_bytes = await response.aread()
+                    try:
+                        err_str = err_bytes.decode()
+                    except Exception:
+                        err_str = repr(err_bytes)
+                    print(f"Error: {err_str}")
+                    return
+
+                print("Stream started. Reading a few chunks...")
+                count = 0
+                async for chunk in response.aiter_bytes():
+                    print(f"Received chunk: {len(chunk)} bytes")
+                    count += 1
+                    if count >= 3:
+                        print("Simulating client disconnect (breaking stream)...")
+                        break
+
+        except Exception as e:
+            print(f"Stream interrupted (expected): {e}")
+
+        # Wait a bit for the server to realize we disconnected (though with asyncio it might be immediate or depend on keepalive)
+        print("\nWaiting for server to process disconnect...")
+        await asyncio.sleep(21)
+
+        print("\nChecking final balance...")
+        try:
+            final_reserved = await get_balance(client)
+        except Exception:
+            # Retry once if connection was closed
+            async with httpx.AsyncClient(
+                base_url=BASE_URL, headers=headers, timeout=30.0
+            ) as new_client:
+                final_reserved = await get_balance(new_client)
+
+        if final_reserved > initial_reserved:
+            print(
+                f"\n[FAIL] Bug reproduced! Reserved balance increased: {initial_reserved} -> {final_reserved}"
+            )
+            print(f"Accumulated reserved balance: {final_reserved - initial_reserved}")
+        else:
+            print(
+                f"\n[PASS] Reserved balance released correctly: {initial_reserved} -> {final_reserved}"
+            )
+
+
+if __name__ == "__main__":
+    try:
+        asyncio.run(reproduce())
+    except KeyboardInterrupt:
+        pass

tests/integration/test_child_keys.py

@@ -0,0 +1,137 @@
+import secrets
+from typing import Any
+
+import pytest
+from fastapi import HTTPException
+from sqlmodel.ext.asyncio.session import AsyncSession
+
+from routstr.auth import adjust_payment_for_tokens, pay_for_request
+from routstr.balance import create_child_key
+from routstr.core.db import ApiKey
+from routstr.core.settings import settings
+
+
+@pytest.mark.asyncio
+async def test_child_key_flow(integration_session: AsyncSession) -> None:
+    # 1. Create a parent key with balance
+    parent_raw = "parent_test_key_" + secrets.token_hex(4)
+    parent_key = ApiKey(
+        hashed_key=parent_raw,
+        balance=10000,  # 10 sats
+    )
+    integration_session.add(parent_key)
+    await integration_session.commit()
+    await integration_session.refresh(parent_key)
+
+    # Mock settings
+    settings.child_key_cost = 1000  # 1 sat
+
+    # 2. Call create_child_key
+    result = await create_child_key(parent_key, integration_session)
+
+    assert "api_key" in result
+    assert result["cost_msats"] == 1000
+    assert result["parent_balance"] == 9000
+
+    child_key_raw = result["api_key"][3:]  # remove sk-
+
+    # 3. Verify child key exists in DB
+    child_key_db = await integration_session.get(ApiKey, child_key_raw)
+    assert child_key_db is not None
+    assert child_key_db.parent_key_hash == parent_key.hashed_key
+    assert child_key_db.balance == 0
+
+    # 4. Test payment with child key
+    cost = 500
+    await pay_for_request(child_key_db, cost, integration_session)
+
+    # Refresh keys
+    await integration_session.refresh(parent_key)
+    await integration_session.refresh(child_key_db)
+
+    # Parent should be charged
+    assert parent_key.reserved_balance == 500
+    assert parent_key.total_requests == 1
+
+    # Child should have total_requests incremented
+    assert child_key_db.total_requests == 1
+
+    # 5. Test adjustment
+    response_data = {"model": "test-model", "usage": {"total_tokens": 10}}
+
+    # Mock calculate_cost
+    import routstr.auth
+    from routstr.payment.cost_calculation import CostData
+
+    async def mock_calculate_cost(*args: Any, **kwargs: Any) -> CostData:
+        return CostData(
+            base_msats=0, input_msats=200, output_msats=200, total_msats=400
+        )
+
+    # Patch calculate_cost
+    original_calculate_cost = routstr.auth.calculate_cost
+    routstr.auth.calculate_cost = mock_calculate_cost
+
+    try:
+        adjustment = await adjust_payment_for_tokens(
+            child_key_db, response_data, integration_session, 500
+        )
+        assert adjustment["total_msats"] == 400
+
+        # Refresh keys
+        await integration_session.refresh(parent_key)
+        await integration_session.refresh(child_key_db)
+
+        # Parent should have updated balance and total_spent
+        assert parent_key.reserved_balance == 0
+        assert parent_key.balance == 9000 - 400
+        assert (
+            parent_key.total_spent == 1400
+        )  # 1000 for child key creation + 400 for request
+
+        # Child should also have total_spent updated
+        assert child_key_db.total_spent == 400
+
+    finally:
+        routstr.auth.calculate_cost = original_calculate_cost
+
+
+@pytest.mark.asyncio
+async def test_child_key_insufficient_balance(
+    integration_session: AsyncSession,
+) -> None:
+    parent_key = ApiKey(
+        hashed_key="poor_parent_" + secrets.token_hex(4),
+        balance=500,
+    )
+    integration_session.add(parent_key)
+    await integration_session.commit()
+    await integration_session.refresh(parent_key)
+
+    settings.child_key_cost = 1000
+
+    with pytest.raises(HTTPException) as exc:
+        await create_child_key(parent_key, integration_session)
+    assert exc.value.status_code == 402
+
+
+@pytest.mark.asyncio
+async def test_child_key_cannot_create_child(integration_session: AsyncSession) -> None:
+    parent_key = ApiKey(
+        hashed_key="parent_" + secrets.token_hex(4),
+        balance=10000,
+    )
+    child_key = ApiKey(
+        hashed_key="child_" + secrets.token_hex(4),
+        balance=0,
+        parent_key_hash=parent_key.hashed_key,
+    )
+    integration_session.add(parent_key)
+    integration_session.add(child_key)
+    await integration_session.commit()
+    await integration_session.refresh(child_key)
+
+    with pytest.raises(HTTPException) as exc:
+        await create_child_key(child_key, integration_session)
+    assert exc.value.status_code == 400
+    assert "Cannot create a child key for another child key" in str(exc.value.detail)

tests/integration/test_example.py

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

tests/integration/test_provider_management.py

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

tests/integration/test_proxy_get_endpoints.py

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

tests/integration/test_proxy_post_endpoints.py

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

tests/integration/test_wallet_information.py

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

tests/integration/test_wallet_refund.py

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

ui/Dockerfile

@@ -4,17 +4,22 @@ FROM base AS deps
 RUN apk add --no-cache libc6-compat
 WORKDIR /app
 
-COPY package.json yarn.lock* package-lock.json* pnpm-lock.yaml* .npmrc* ./
-RUN npm i
+RUN corepack enable pnpm && corepack prepare pnpm@latest --activate
+
+COPY package.json pnpm-lock.yaml* ./
+RUN pnpm install --frozen-lockfile
 
 FROM base AS builder
 WORKDIR /app
+
+RUN corepack enable pnpm && corepack prepare pnpm@latest --activate
+
 COPY --from=deps /app/node_modules ./node_modules
 COPY . .
 
 ENV NEXT_TELEMETRY_DISABLED=1
 
-RUN npm run build
+RUN pnpm run build
 FROM base AS runner
 WORKDIR /app
 

ui/Dockerfile.build

@@ -6,12 +6,14 @@ RUN apk add --no-cache libc6-compat
 WORKDIR /app
 
 # Copy package files
-COPY package.json package-lock.json* pnpm-lock.yaml* ./
-RUN npm ci
+COPY package.json pnpm-lock.yaml* ./
+RUN corepack enable pnpm && corepack prepare pnpm@latest --activate
+RUN pnpm install --frozen-lockfile
 
 # Build the UI
 FROM base AS builder
 WORKDIR /app
+RUN corepack enable pnpm && corepack prepare pnpm@latest --activate
 COPY --from=deps /app/node_modules ./node_modules
 COPY . .
 
@@ -27,7 +29,7 @@ ENV NODE_ENV=production
 ENV NEXT_TELEMETRY_DISABLED=1
 
 # Build the application
-RUN npm run build && \
+RUN pnpm run build && \
     echo "UI build completed at $(date)"
 
 # Use the builder stage as the final stage

ui/app/logs/log-filters.tsx

@@ -21,7 +21,17 @@ import {
   PopoverTrigger,
 } from '@/components/ui/popover';
 import { Calendar } from '@/components/ui/calendar';
-import { CalendarIcon, Filter, X } from 'lucide-react';
+import { Badge } from '@/components/ui/badge';
+import {
+  Command,
+  CommandEmpty,
+  CommandGroup,
+  CommandInput,
+  CommandItem,
+  CommandList,
+} from '@/components/ui/command';
+import { Checkbox } from '@/components/ui/checkbox';
+import { CalendarIcon, Filter, X, Plus } from 'lucide-react';
 import { useState, useEffect } from 'react';
 import { format } from 'date-fns';
 import { cn } from '@/lib/utils';
@@ -31,11 +41,17 @@ interface LogFiltersProps {
   selectedLevel: string;
   requestId: string;
   searchText: string;
+  selectedStatusCodes: string[];
+  selectedMethods: string[];
+  selectedEndpoints: string[];
   limit: number;
   onDateChange: (date: string) => void;
   onLevelChange: (level: string) => void;
   onRequestIdChange: (requestId: string) => void;
   onSearchTextChange: (searchText: string) => void;
+  onStatusCodesChange: (statusCodes: string[]) => void;
+  onMethodsChange: (methods: string[]) => void;
+  onEndpointsChange: (endpoints: string[]) => void;
   onLimitChange: (limit: number) => void;
   onClearFilters: () => void;
 }
@@ -43,16 +59,87 @@ interface LogFiltersProps {
 const LOG_LEVELS = ['TRACE', 'DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'];
 const PRESET_LIMITS = ['25', '50', '100', '200', '500', '1000'];
 
+const STATUS_CODE_OPTIONS = [
+  '200',
+  '201',
+  '204',
+  '400',
+  '401',
+  '402',
+  '403',
+  '404',
+  '422',
+  '429',
+  '500',
+  '502',
+  '503',
+  '504',
+];
+
+const METHOD_OPTIONS = [
+  'GET',
+  'POST',
+  'PUT',
+  'DELETE',
+  'PATCH',
+  'OPTIONS',
+  'HEAD',
+];
+
+const ENDPOINT_OPTIONS = [
+  '/chat/completions',
+  '/v1/chat/completions',
+  '/models',
+  '/v1/models',
+  '/responses',
+  '/v1/responses',
+  'v1/embeddings/models',
+  '/embeddings/models',
+];
+
+interface FilterBadgeProps {
+  value: string;
+  onRemove: (value: string) => void;
+}
+
+function FilterBadge({ value, onRemove }: FilterBadgeProps) {
+  return (
+    <Badge
+      variant='secondary'
+      className='flex items-center gap-1 px-1 font-normal'
+    >
+      {value}
+      <button
+        type='button'
+        onClick={(e) => {
+          e.preventDefault();
+          e.stopPropagation();
+          onRemove(value);
+        }}
+        className='hover:bg-muted-foreground/20 rounded-full'
+      >
+        <X className='h-3 w-3' />
+      </button>
+    </Badge>
+  );
+}
+
 export function LogFilters({
   selectedDate,
   selectedLevel,
   requestId,
   searchText,
+  selectedStatusCodes,
+  selectedMethods,
+  selectedEndpoints,
   limit,
   onDateChange,
   onLevelChange,
   onRequestIdChange,
   onSearchTextChange,
+  onStatusCodesChange,
+  onMethodsChange,
+  onEndpointsChange,
   onLimitChange,
   onClearFilters,
 }: LogFiltersProps) {
@@ -68,6 +155,10 @@ export function LogFilters({
       : undefined
   );
 
+  const [statusSearch, setStatusSearch] = useState('');
+  const [methodSearch, setMethodSearch] = useState('');
+  const [endpointSearch, setEndpointSearch] = useState('');
+
   useEffect(() => {
     const currentIsPreset = PRESET_LIMITS.includes(limit.toString());
     setIsCustom(!currentIsPreset);
@@ -129,6 +220,31 @@ export function LogFilters({
     }
   };
 
+  const toggleSelection = (
+    current: string[],
+    value: string,
+    onChange: (val: string[]) => void
+  ) => {
+    if (current.includes(value)) {
+      onChange(current.filter((v) => v !== value));
+    } else {
+      onChange([...current, value]);
+    }
+  };
+
+  const handleQuickStatusCode = (range: '4xx' | '5xx') => {
+    const codes = STATUS_CODE_OPTIONS.filter((c) => c.startsWith(range[0]));
+    const newSelection = new Set([...selectedStatusCodes]);
+    const allIncluded = codes.every((c) => selectedStatusCodes.includes(c));
+
+    if (allIncluded) {
+      codes.forEach((c) => newSelection.delete(c));
+    } else {
+      codes.forEach((c) => newSelection.add(c));
+    }
+    onStatusCodesChange(Array.from(newSelection));
+  };
+
   return (
     <Card className='mb-6'>
       <CardHeader>
@@ -137,7 +253,8 @@ export function LogFilters({
           Filters
         </CardTitle>
         <CardDescription>
-          Filter logs by date, level, request ID, text search, and limit
+          Filter logs by date, level, request ID, text search, status code,
+          method, endpoint and limit
         </CardDescription>
       </CardHeader>
       <CardContent>
@@ -197,6 +314,337 @@ export function LogFilters({
             </Select>
           </div>
 
+          <div className='space-y-2'>
+            <Label>Status Codes</Label>
+            <Popover>
+              <PopoverTrigger asChild>
+                <Button
+                  variant='outline'
+                  className='w-full justify-start text-left font-normal'
+                >
+                  <div className='flex flex-wrap gap-1'>
+                    {selectedStatusCodes.length > 0 ? (
+                      selectedStatusCodes.map((code) => (
+                        <FilterBadge
+                          key={code}
+                          value={code}
+                          onRemove={(val) =>
+                            toggleSelection(
+                              selectedStatusCodes,
+                              val,
+                              onStatusCodesChange
+                            )
+                          }
+                        />
+                      ))
+                    ) : (
+                      <span className='text-muted-foreground'>All codes</span>
+                    )}
+                  </div>
+                </Button>
+              </PopoverTrigger>
+              <PopoverContent className='w-64 p-0' align='start'>
+                <Command>
+                  <CommandInput
+                    placeholder='Search or add status code...'
+                    value={statusSearch}
+                    onValueChange={setStatusSearch}
+                  />
+                  <CommandList>
+                    {selectedStatusCodes.length > 0 && (
+                      <CommandGroup heading='Selected'>
+                        {selectedStatusCodes.map((code) => (
+                          <CommandItem
+                            key={`selected-${code}`}
+                            onSelect={() =>
+                              toggleSelection(
+                                selectedStatusCodes,
+                                code,
+                                onStatusCodesChange
+                              )
+                            }
+                          >
+                            <Checkbox checked={true} className='mr-2' />
+                            {code}
+                          </CommandItem>
+                        ))}
+                      </CommandGroup>
+                    )}
+                    {statusSearch &&
+                      !STATUS_CODE_OPTIONS.includes(statusSearch) &&
+                      !selectedStatusCodes.includes(statusSearch) && (
+                        <CommandGroup heading='Custom'>
+                          <CommandItem
+                            onSelect={() => {
+                              if (/^\d+$/.test(statusSearch)) {
+                                toggleSelection(
+                                  selectedStatusCodes,
+                                  statusSearch,
+                                  onStatusCodesChange
+                                );
+                                setStatusSearch('');
+                              }
+                            }}
+                          >
+                            <Plus className='mr-2 h-4 w-4' />
+                            Add &quot;{statusSearch}&quot;
+                          </CommandItem>
+                        </CommandGroup>
+                      )}
+                    <CommandEmpty>No results found.</CommandEmpty>
+                    <CommandGroup heading='Quick Filters'>
+                      <CommandItem
+                        onSelect={() => handleQuickStatusCode('4xx')}
+                      >
+                        <Checkbox
+                          checked={STATUS_CODE_OPTIONS.filter((c) =>
+                            c.startsWith('4')
+                          ).every((c) => selectedStatusCodes.includes(c))}
+                          className='mr-2'
+                        />
+                        4xx Errors
+                      </CommandItem>
+                      <CommandItem
+                        onSelect={() => handleQuickStatusCode('5xx')}
+                      >
+                        <Checkbox
+                          checked={STATUS_CODE_OPTIONS.filter((c) =>
+                            c.startsWith('5')
+                          ).every((c) => selectedStatusCodes.includes(c))}
+                          className='mr-2'
+                        />
+                        5xx Errors
+                      </CommandItem>
+                    </CommandGroup>
+                    <CommandGroup heading='Common Codes'>
+                      {STATUS_CODE_OPTIONS.filter(
+                        (code) => !selectedStatusCodes.includes(code)
+                      ).map((code) => (
+                        <CommandItem
+                          key={code}
+                          onSelect={() =>
+                            toggleSelection(
+                              selectedStatusCodes,
+                              code,
+                              onStatusCodesChange
+                            )
+                          }
+                        >
+                          <Checkbox checked={false} className='mr-2' />
+                          {code}
+                        </CommandItem>
+                      ))}
+                    </CommandGroup>
+                  </CommandList>
+                </Command>
+              </PopoverContent>
+            </Popover>
+          </div>
+
+          <div className='space-y-2'>
+            <Label>HTTP Methods</Label>
+            <Popover>
+              <PopoverTrigger asChild>
+                <Button
+                  variant='outline'
+                  className='w-full justify-start text-left font-normal'
+                >
+                  <div className='flex flex-wrap gap-1'>
+                    {selectedMethods.length > 0 ? (
+                      selectedMethods.map((method) => (
+                        <FilterBadge
+                          key={method}
+                          value={method}
+                          onRemove={(val) =>
+                            toggleSelection(
+                              selectedMethods,
+                              val,
+                              onMethodsChange
+                            )
+                          }
+                        />
+                      ))
+                    ) : (
+                      <span className='text-muted-foreground'>All methods</span>
+                    )}
+                  </div>
+                </Button>
+              </PopoverTrigger>
+              <PopoverContent className='w-64 p-0' align='start'>
+                <Command>
+                  <CommandInput
+                    placeholder='Search or add method...'
+                    value={methodSearch}
+                    onValueChange={setMethodSearch}
+                  />
+                  <CommandList>
+                    {selectedMethods.length > 0 && (
+                      <CommandGroup heading='Selected'>
+                        {selectedMethods.map((method) => (
+                          <CommandItem
+                            key={`selected-${method}`}
+                            onSelect={() =>
+                              toggleSelection(
+                                selectedMethods,
+                                method,
+                                onMethodsChange
+                              )
+                            }
+                          >
+                            <Checkbox checked={true} className='mr-2' />
+                            {method}
+                          </CommandItem>
+                        ))}
+                      </CommandGroup>
+                    )}
+                    {methodSearch &&
+                      !METHOD_OPTIONS.includes(methodSearch.toUpperCase()) &&
+                      !selectedMethods.includes(methodSearch.toUpperCase()) && (
+                        <CommandGroup heading='Custom'>
+                          <CommandItem
+                            onSelect={() => {
+                              toggleSelection(
+                                selectedMethods,
+                                methodSearch.toUpperCase(),
+                                onMethodsChange
+                              );
+                              setMethodSearch('');
+                            }}
+                          >
+                            <Plus className='mr-2 h-4 w-4' />
+                            Add &quot;{methodSearch.toUpperCase()}&quot;
+                          </CommandItem>
+                        </CommandGroup>
+                      )}
+                    <CommandEmpty>No results found.</CommandEmpty>
+                    <CommandGroup>
+                      {METHOD_OPTIONS.filter(
+                        (method) => !selectedMethods.includes(method)
+                      ).map((method) => (
+                        <CommandItem
+                          key={method}
+                          onSelect={() =>
+                            toggleSelection(
+                              selectedMethods,
+                              method,
+                              onMethodsChange
+                            )
+                          }
+                        >
+                          <Checkbox checked={false} className='mr-2' />
+                          {method}
+                        </CommandItem>
+                      ))}
+                    </CommandGroup>
+                  </CommandList>
+                </Command>
+              </PopoverContent>
+            </Popover>
+          </div>
+
+          <div className='space-y-2'>
+            <Label>Endpoints</Label>
+            <Popover>
+              <PopoverTrigger asChild>
+                <Button
+                  variant='outline'
+                  className='w-full justify-start text-left font-normal'
+                >
+                  <div className='flex flex-wrap gap-1 overflow-hidden'>
+                    {selectedEndpoints.length > 0 ? (
+                      selectedEndpoints.map((endpoint) => (
+                        <FilterBadge
+                          key={endpoint}
+                          value={endpoint}
+                          onRemove={(val) =>
+                            toggleSelection(
+                              selectedEndpoints,
+                              val,
+                              onEndpointsChange
+                            )
+                          }
+                        />
+                      ))
+                    ) : (
+                      <span className='text-muted-foreground'>
+                        All endpoints
+                      </span>
+                    )}
+                  </div>
+                </Button>
+              </PopoverTrigger>
+              <PopoverContent className='w-80 p-0' align='start'>
+                <Command>
+                  <CommandInput
+                    placeholder='Search or add endpoint pattern...'
+                    value={endpointSearch}
+                    onValueChange={setEndpointSearch}
+                  />
+                  <CommandList>
+                    {selectedEndpoints.length > 0 && (
+                      <CommandGroup heading='Selected'>
+                        {selectedEndpoints.map((endpoint) => (
+                          <CommandItem
+                            key={`selected-${endpoint}`}
+                            onSelect={() =>
+                              toggleSelection(
+                                selectedEndpoints,
+                                endpoint,
+                                onEndpointsChange
+                              )
+                            }
+                          >
+                            <Checkbox checked={true} className='mr-2' />
+                            {endpoint}
+                          </CommandItem>
+                        ))}
+                      </CommandGroup>
+                    )}
+                    {endpointSearch &&
+                      !ENDPOINT_OPTIONS.includes(endpointSearch) &&
+                      !selectedEndpoints.includes(endpointSearch) && (
+                        <CommandGroup heading='Custom'>
+                          <CommandItem
+                            onSelect={() => {
+                              toggleSelection(
+                                selectedEndpoints,
+                                endpointSearch,
+                                onEndpointsChange
+                              );
+                              setEndpointSearch('');
+                            }}
+                          >
+                            <Plus className='mr-2 h-4 w-4' />
+                            Add &quot;{endpointSearch}&quot;
+                          </CommandItem>
+                        </CommandGroup>
+                      )}
+                    <CommandEmpty>No results found.</CommandEmpty>
+                    <CommandGroup heading='Common Endpoints'>
+                      {ENDPOINT_OPTIONS.filter(
+                        (endpoint) => !selectedEndpoints.includes(endpoint)
+                      ).map((endpoint) => (
+                        <CommandItem
+                          key={endpoint}
+                          onSelect={() =>
+                            toggleSelection(
+                              selectedEndpoints,
+                              endpoint,
+                              onEndpointsChange
+                            )
+                          }
+                        >
+                          <Checkbox checked={false} className='mr-2' />
+                          {endpoint}
+                        </CommandItem>
+                      ))}
+                    </CommandGroup>
+                  </CommandList>
+                </Command>
+              </PopoverContent>
+            </Popover>
+          </div>
+
           <div className='space-y-2'>
             <Label htmlFor='request-id'>Request ID</Label>
             <Input

ui/app/logs/page.tsx

@@ -1,6 +1,6 @@
 'use client';
 
-import { useState } from 'react';
+import { useState, useEffect } from 'react';
 import { useQuery } from '@tanstack/react-query';
 import { AppSidebar } from '@/components/app-sidebar';
 import { SiteHeader } from '@/components/site-header';
@@ -22,15 +22,66 @@ import { LogFilters } from './log-filters';
 import { LogEntryCard } from './log-entry-card';
 import { LogDetailsDialog } from './log-details-dialog';
 
+const STORAGE_KEY = 'routstr-log-filters';
+
 export default function LogsPage() {
   const [selectedDate, setSelectedDate] = useState<string>('all');
   const [selectedLevel, setSelectedLevel] = useState<string>('all');
   const [requestId, setRequestId] = useState<string>('');
   const [searchText, setSearchText] = useState<string>('');
+  const [selectedStatusCodes, setSelectedStatusCodes] = useState<string[]>([]);
+  const [selectedMethods, setSelectedMethods] = useState<string[]>([]);
+  const [selectedEndpoints, setSelectedEndpoints] = useState<string[]>([]);
   const [limit, setLimit] = useState<number>(100);
   const [selectedLog, setSelectedLog] = useState<LogEntry | null>(null);
   const [isDialogOpen, setIsDialogOpen] = useState<boolean>(false);
 
+  // Load filters from localStorage on mount
+  useEffect(() => {
+    const saved = localStorage.getItem(STORAGE_KEY);
+    if (saved) {
+      try {
+        const parsed = JSON.parse(saved);
+        if (parsed.selectedDate) setSelectedDate(parsed.selectedDate);
+        if (parsed.selectedLevel) setSelectedLevel(parsed.selectedLevel);
+        if (parsed.requestId) setRequestId(parsed.requestId);
+        if (parsed.searchText) setSearchText(parsed.searchText);
+        if (parsed.selectedStatusCodes)
+          setSelectedStatusCodes(parsed.selectedStatusCodes);
+        if (parsed.selectedMethods) setSelectedMethods(parsed.selectedMethods);
+        if (parsed.selectedEndpoints)
+          setSelectedEndpoints(parsed.selectedEndpoints);
+        if (parsed.limit) setLimit(parsed.limit);
+      } catch (e) {
+        console.error('Failed to load filters from localStorage', e);
+      }
+    }
+  }, []);
+
+  // Save filters to localStorage whenever they change
+  useEffect(() => {
+    const filters = {
+      selectedDate,
+      selectedLevel,
+      requestId,
+      searchText,
+      selectedStatusCodes,
+      selectedMethods,
+      selectedEndpoints,
+      limit,
+    };
+    localStorage.setItem(STORAGE_KEY, JSON.stringify(filters));
+  }, [
+    selectedDate,
+    selectedLevel,
+    requestId,
+    searchText,
+    selectedStatusCodes,
+    selectedMethods,
+    selectedEndpoints,
+    limit,
+  ]);
+
   const {
     data: logsData,
     refetch: refetchLogs,
@@ -42,6 +93,9 @@ export default function LogsPage() {
       selectedLevel,
       requestId,
       searchText,
+      selectedStatusCodes,
+      selectedMethods,
+      selectedEndpoints,
       limit,
     ],
     queryFn: () =>
@@ -50,6 +104,16 @@ export default function LogsPage() {
         level: selectedLevel === 'all' ? undefined : selectedLevel,
         request_id: requestId || undefined,
         search: searchText || undefined,
+        status_codes:
+          selectedStatusCodes.length > 0
+            ? selectedStatusCodes.join(',')
+            : undefined,
+        methods:
+          selectedMethods.length > 0 ? selectedMethods.join(',') : undefined,
+        endpoints:
+          selectedEndpoints.length > 0
+            ? selectedEndpoints.join(',')
+            : undefined,
         limit: limit,
       }),
     refetchInterval: 30000,
@@ -60,6 +124,9 @@ export default function LogsPage() {
     setSelectedLevel('all');
     setRequestId('');
     setSearchText('');
+    setSelectedStatusCodes([]);
+    setSelectedMethods([]);
+    setSelectedEndpoints([]);
     setLimit(100);
   };
 
@@ -100,11 +167,17 @@ export default function LogsPage() {
             selectedLevel={selectedLevel}
             requestId={requestId}
             searchText={searchText}
+            selectedStatusCodes={selectedStatusCodes}
+            selectedMethods={selectedMethods}
+            selectedEndpoints={selectedEndpoints}
             limit={limit}
             onDateChange={setSelectedDate}
             onLevelChange={setSelectedLevel}
             onRequestIdChange={setRequestId}
             onSearchTextChange={setSearchText}
+            onStatusCodesChange={setSelectedStatusCodes}
+            onMethodsChange={setSelectedMethods}
+            onEndpointsChange={setSelectedEndpoints}
             onLimitChange={setLimit}
             onClearFilters={handleClearFilters}
           />
@@ -122,13 +195,22 @@ export default function LogsPage() {
               {(selectedDate !== 'all' ||
                 selectedLevel !== 'all' ||
                 requestId ||
-                searchText) && (
+                searchText ||
+                selectedStatusCodes.length > 0 ||
+                selectedMethods.length > 0 ||
+                selectedEndpoints.length > 0) && (
                 <CardDescription className='text-xs sm:text-sm'>
                   Showing logs
                   {selectedDate !== 'all' && ` for ${selectedDate}`}
                   {selectedLevel !== 'all' && ` with level ${selectedLevel}`}
                   {requestId && ` with request ID ${requestId}`}
                   {searchText && ` matching "${searchText}"`}
+                  {selectedStatusCodes.length > 0 &&
+                    ` with status ${selectedStatusCodes.join(', ')}`}
+                  {selectedMethods.length > 0 &&
+                    ` with method ${selectedMethods.join(', ')}`}
+                  {selectedEndpoints.length > 0 &&
+                    ` with endpoint ${selectedEndpoints.join(', ')}`}
                 </CardDescription>
               )}
             </CardHeader>

ui/app/logs/types.ts

@@ -17,6 +17,9 @@ export interface LogsResponse {
   level: string | null;
   request_id: string | null;
   search: string | null;
+  status_codes: string | null;
+  methods: string | null;
+  endpoints: string | null;
   limit: number;
 }
 

ui/app/providers/page.tsx

@@ -208,7 +208,12 @@ function ProviderBalance({
     return <Skeleton className='h-9 w-24' />;
   }
 
-  if (error || !balanceData?.ok || !balanceData.balance_data) {
+  if (
+    error ||
+    !balanceData?.ok ||
+    balanceData.balance_data === undefined ||
+    balanceData.balance_data === null
+  ) {
     return null;
   }
 

ui/components/temporary-balances.tsx

@@ -60,7 +60,11 @@ export function TemporaryBalances({
     let totalRequests = 0;
 
     balances.forEach((balance) => {
-      totalBalance += balance.balance || 0;
+      // Only count parents for total balance to avoid double counting
+      // since child keys use parent balance
+      if (!balance.parent_key_hash) {
+        totalBalance += balance.balance || 0;
+      }
       totalSpent += balance.total_spent || 0;
       totalRequests += balance.total_requests || 0;
     });
@@ -72,6 +76,34 @@ export function TemporaryBalances({
     ? calculateTotals(data)
     : { totalBalance: 0, totalSpent: 0, totalRequests: 0 };
 
+  // Group parents and children
+  const hierarchicalData = (() => {
+    if (!data) return [];
+
+    const parents = filteredData.filter((item) => !item.parent_key_hash);
+    const result: (TemporaryBalance & { isChild?: boolean })[] = [];
+
+    parents.forEach((parent) => {
+      result.push(parent);
+      const children = data.filter(
+        (item) => item.parent_key_hash === parent.hashed_key
+      );
+      children.forEach((child) => {
+        result.push({ ...child, isChild: true });
+      });
+    });
+
+    // Add children whose parents didn't match the search or aren't in the list
+    const orphans = filteredData.filter(
+      (item) =>
+        item.parent_key_hash &&
+        !result.some((r) => r.hashed_key === item.hashed_key)
+    );
+    result.push(...orphans.map((o) => ({ ...o, isChild: true })));
+
+    return result;
+  })();
+
   return (
     <>
       <Card className='h-full w-full shadow-sm'>
@@ -182,22 +214,37 @@ export function TemporaryBalances({
                   <div className='text-right'>Expiry Time</div>
                 </div>
 
-                {filteredData.length > 0 ? (
-                  filteredData.map((balance, index) => (
+                {hierarchicalData.length > 0 ? (
+                  hierarchicalData.map((balance, index) => (
                     <div
                       key={index}
                       className={cn(
                         'hover:bg-muted/50 border-t p-3 text-sm transition-colors',
-                        balance.balance === 0 && 'opacity-60'
+                        balance.balance === 0 &&
+                          !balance.isChild &&
+                          'opacity-60',
+                        balance.isChild &&
+                          'ml-4 border-l-2 border-l-blue-200 bg-blue-50/30'
                       )}
                     >
                       {/* Desktop Layout */}
                       <div className='hidden grid-cols-6 gap-2 md:grid'>
-                        <div className='max-w-32 truncate font-mono text-xs break-all'>
+                        <div className='flex max-w-48 items-center gap-2 truncate font-mono text-xs break-all'>
+                          {balance.isChild && (
+                            <span className='rounded bg-blue-100 px-1 py-0.5 text-[10px] font-bold text-blue-700 uppercase'>
+                              Child
+                            </span>
+                          )}
                           {balance.hashed_key}
                         </div>
                         <div className='text-right font-mono'>
-                          {formatBalance(balance.balance)}
+                          {balance.isChild ? (
+                            <span className='text-muted-foreground italic'>
+                              (Parent)
+                            </span>
+                          ) : (
+                            formatBalance(balance.balance)
+                          )}
                         </div>
                         <div className='text-right font-mono'>
                           {formatBalance(balance.total_spent)}
@@ -226,13 +273,20 @@ export function TemporaryBalances({
 
                       {/* Mobile Layout */}
                       <div className='space-y-3 md:hidden'>
-                        <div className='space-y-1'>
-                          <span className='text-muted-foreground text-xs font-medium'>
-                            Key
-                          </span>
-                          <div className='font-mono text-xs break-all'>
-                            {balance.hashed_key}
+                        <div className='flex items-center justify-between'>
+                          <div className='space-y-1'>
+                            <span className='text-muted-foreground text-xs font-medium'>
+                              {balance.isChild ? 'Child Key' : 'Key'}
+                            </span>
+                            <div className='font-mono text-xs break-all'>
+                              {balance.hashed_key}
+                            </div>
                           </div>
+                          {balance.isChild && (
+                            <span className='rounded bg-blue-100 px-1.5 py-0.5 text-[10px] font-bold text-blue-700 uppercase'>
+                              Child
+                            </span>
+                          )}
                         </div>
 
                         <div className='grid grid-cols-2 gap-3'>
@@ -241,7 +295,13 @@ export function TemporaryBalances({
                               Balance
                             </div>
                             <div className='truncate font-mono text-sm'>
-                              {formatBalance(balance.balance)}
+                              {balance.isChild ? (
+                                <span className='text-muted-foreground text-xs italic'>
+                                  (Uses Parent)
+                                </span>
+                              ) : (
+                                formatBalance(balance.balance)
+                              )}
                             </div>
                           </div>
                           <div className='space-y-1'>

ui/lib/api/services/admin.ts

@@ -926,6 +926,7 @@ export const TemporaryBalanceSchema = z.object({
   total_requests: z.number(),
   refund_address: z.string().nullable(),
   key_expiry_time: z.number().nullable(),
+  parent_key_hash: z.string().nullable().optional(),
 });
 
 export type TemporaryBalance = z.infer<typeof TemporaryBalanceSchema>;

ui/package.json

@@ -15,6 +15,7 @@
     "@dnd-kit/core": "^6.3.1",
     "@dnd-kit/modifiers": "^9.0.0",
     "@dnd-kit/sortable": "^10.0.0",
+    "@dnd-kit/utilities": "^3.2.2",
     "@hookform/resolvers": "^5.0.1",
     "@radix-ui/react-alert-dialog": "^1.1.10",
     "@radix-ui/react-avatar": "^1.1.6",
@@ -40,17 +41,17 @@
     "@radix-ui/react-toggle": "^1.1.6",
     "@radix-ui/react-toggle-group": "^1.1.6",
     "@radix-ui/react-tooltip": "^1.2.3",
-    "@tanstack/react-query": "^5.74.4",
+    "@tanstack/react-query": "^5.90.16",
     "@tanstack/react-table": "^8.21.3",
     "axios": "^1.13.2",
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
     "cmdk": "^1.1.1",
-    "date-fns": "^3.6.0",
+    "date-fns": "^4.1.0",
     "embla-carousel-react": "^8.6.0",
     "input-otp": "^1.4.2",
-    "lucide-react": "^0.501.0",
-    "next": "15.3.1",
+    "lucide-react": "^0.562.0",
+    "next": "15.5.9",
     "next-themes": "^0.4.6",
     "qrcode": "^1.5.4",
     "qrcode.react": "^4.2.0",
@@ -67,21 +68,21 @@
     "zustand": "^5.0.3"
   },
   "devDependencies": {
-    "@eslint/eslintrc": "^3",
-    "@tailwindcss/postcss": "^4",
-    "@tanstack/react-query-devtools": "^5.74.4",
+    "@eslint/eslintrc": "^3.3.3",
+    "@tailwindcss/postcss": "^4.1.18",
+    "@tanstack/react-query-devtools": "^5.91.2",
     "@types/node": "^20",
     "@types/qrcode": "^1.5.6",
     "@types/react": "^19",
     "@types/react-dom": "^19",
     "eslint": "^9.25.0",
-    "eslint-config-next": "15.3.1",
+    "eslint-config-next": "15.5.9",
     "eslint-config-prettier": "^10.1.2",
     "eslint-plugin-prettier": "^5.2.6",
     "eslint-plugin-react": "^7.37.5",
     "prettier": "^3.5.3",
     "prettier-plugin-tailwindcss": "^0.6.11",
-    "tailwindcss": "^4",
+    "tailwindcss": "^4.1.18",
     "typescript": "^5"
   }
 }

ui/tsconfig.json

@@ -22,6 +22,12 @@
       "@/*": ["./*"]
     }
   },
-  "include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", ".next/types/**/*.ts"],
+  "include": [
+    "next-env.d.ts",
+    "**/*.ts",
+    "**/*.tsx",
+    ".next/types/**/*.ts",
+    ".next/dev/types/**/*.ts"
+  ],
   "exclude": ["node_modules"]
 }

uv.lock

@@ -1878,7 +1878,7 @@ wheels = [
 
 [[package]]
 name = "routstr"
-version = "0.2.1"
+version = "0.2.2"
 source = { editable = "." }
 dependencies = [
     { name = "aiosqlite" },