Skip to content

Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)

Python

Refactor rate limiting configuration to use unified provider settings

Alishahryar1054f9869b7a2
diff --git a/.env.example b/.env.example
index 990c2e85..fa458d74 100644
--- a/.env.example
+++ b/.env.example
@@ -1,5 +1,7 @@
# Provider: "nvidia_nim" | "open_router"
PROVIDER_TYPE=nvidia_nim
+PROVIDER_RATE_LIMIT=40
+PROVIDER_RATE_WINDOW=60
# All Claude model requests are mapped to this model
MODEL="stepfun-ai/step-3.5-flash"
@@ -7,14 +9,9 @@ MODEL="stepfun-ai/step-3.5-flash"
# NVIDIA NIM Config
NVIDIA_NIM_API_KEY=""
-NVIDIA_NIM_RATE_LIMIT=40
-NVIDIA_NIM_RATE_WINDOW=60
-
# OpenRouter Config
OPENROUTER_API_KEY=""
-OPENROUTER_RATE_LIMIT=1
-OPENROUTER_RATE_WINDOW=1
# Telegram Config
diff --git a/README.md b/README.md
index e50c613d..052f02bc 100644
--- a/README.md
+++ b/README.md
@@ -201,10 +201,8 @@ Browse: [openrouter.ai/models](https://openrouter.ai/models)
| `ALLOWED_TELEGRAM_USER_ID` | Allowed Telegram User ID | `""` |
| `MESSAGING_RATE_LIMIT` | Telegram messages per window | `1` |
| `MESSAGING_RATE_WINDOW` | Messaging window (seconds) | `1` |
-| `NVIDIA_NIM_RATE_LIMIT` | NIM API requests per window | `40` |
-| `NVIDIA_NIM_RATE_WINDOW` | NIM rate limit window (seconds)| `60` |
-| `OPENROUTER_RATE_LIMIT` | OpenRouter requests per window | `40` |
-| `OPENROUTER_RATE_WINDOW` | OpenRouter rate limit window | `60` |
+| `PROVIDER_RATE_LIMIT` | LLM API requests per window | `40` |
+| `PROVIDER_RATE_WINDOW` | Rate limit window (seconds) | `60` |
- **NVIDIA NIM** base URL: `https://integrate.api.nvidia.com/v1`
- **OpenRouter** base URL: `https://openrouter.ai/api/v1`
diff --git a/api/dependencies.py b/api/dependencies.py
index b4f96e27..7ec3dc63 100644
--- a/api/dependencies.py
+++ b/api/dependencies.py
@@ -29,8 +29,8 @@ def get_provider() -> BaseProvider:
config = ProviderConfig(
api_key=settings.nvidia_nim_api_key,
base_url=NVIDIA_NIM_BASE_URL,
- rate_limit=settings.nvidia_nim_rate_limit,
- rate_window=settings.nvidia_nim_rate_window,
+ rate_limit=settings.provider_rate_limit,
+ rate_window=settings.provider_rate_window,
nim_settings=settings.nim,
)
_provider = NvidiaNimProvider(config)
@@ -41,8 +41,8 @@ def get_provider() -> BaseProvider:
config = ProviderConfig(
api_key=settings.open_router_api_key,
base_url="https://openrouter.ai/api/v1",
- rate_limit=settings.open_router_rate_limit,
- rate_window=settings.open_router_rate_window,
+ rate_limit=settings.provider_rate_limit,
+ rate_window=settings.provider_rate_window,
nim_settings=settings.nim,
)
_provider = OpenRouterProvider(config)
diff --git a/config/settings.py b/config/settings.py
index 29cfd455..a6f96894 100644
--- a/config/settings.py
+++ b/config/settings.py
@@ -24,12 +24,6 @@ class Settings(BaseSettings):
# ==================== OpenRouter Config ====================
open_router_api_key: str = Field(default="", validation_alias="OPENROUTER_API_KEY")
- open_router_rate_limit: int = Field(
- default=40, validation_alias="OPENROUTER_RATE_LIMIT"
- )
- open_router_rate_window: int = Field(
- default=60, validation_alias="OPENROUTER_RATE_WINDOW"
- )
# ==================== Messaging Platform Selection ====================
messaging_platform: str = "telegram"
@@ -41,9 +35,11 @@ class Settings(BaseSettings):
# All Claude model requests are mapped to this single model
model: str = "moonshotai/kimi-k2-thinking"
- # ==================== Rate Limiting ====================
- nvidia_nim_rate_limit: int = 40
- nvidia_nim_rate_window: int = 60
+ # ==================== Provider Rate Limiting ====================
+ provider_rate_limit: int = Field(default=40, validation_alias="PROVIDER_RATE_LIMIT")
+ provider_rate_window: int = Field(
+ default=60, validation_alias="PROVIDER_RATE_WINDOW"
+ )
# ==================== Fast Prefix Detection ====================
fast_prefix_detection: bool = True
diff --git a/tests/test_config.py b/tests/test_config.py
index db1f5d48..69781701 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -21,8 +21,8 @@ class TestSettings:
from config.settings import Settings
settings = Settings()
- assert isinstance(settings.nvidia_nim_rate_limit, int)
- assert isinstance(settings.nvidia_nim_rate_window, int)
+ assert isinstance(settings.provider_rate_limit, int)
+ assert isinstance(settings.provider_rate_window, int)
assert isinstance(settings.nim.temperature, float)
assert isinstance(settings.fast_prefix_detection, bool)
assert isinstance(settings.max_cli_sessions, int)
diff --git a/tests/test_dependencies.py b/tests/test_dependencies.py
index 25b65996..abe91d8f 100644
--- a/tests/test_dependencies.py
+++ b/tests/test_dependencies.py
@@ -11,11 +11,9 @@ def _make_mock_settings(**overrides):
mock = MagicMock()
mock.provider_type = "nvidia_nim"
mock.nvidia_nim_api_key = "test_key"
- mock.nvidia_nim_rate_limit = 40
- mock.nvidia_nim_rate_window = 60
+ mock.provider_rate_limit = 40
+ mock.provider_rate_window = 60
mock.open_router_api_key = "test_openrouter_key"
- mock.open_router_rate_limit = 40
- mock.open_router_rate_window = 60
mock.nim = NimSettings()
for key, value in overrides.items():
setattr(mock, key, value)