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

fix(providers): map httpx exceptions natively and remove type ignores

Alishahryar11aedf4763c9f
diff --git a/providers/common/error_mapping.py b/providers/common/error_mapping.py
index dfb156da..55f622e5 100644
--- a/providers/common/error_mapping.py
+++ b/providers/common/error_mapping.py
@@ -62,8 +62,10 @@ def append_request_id(message: str, request_id: str | None) -> str:
def map_error(e: Exception) -> Exception:
- """Map OpenAI exception to specific ProviderError."""
+ """Map OpenAI or HTTPX exception to specific ProviderError."""
message = get_user_facing_error_message(e)
+
+ # Map OpenAI Specific Errors
if isinstance(e, openai.AuthenticationError):
return AuthenticationError(message, raw_error=str(e))
if isinstance(e, openai.RateLimitError):
@@ -82,4 +84,20 @@ def map_error(e: Exception) -> Exception:
message, status_code=getattr(e, "status_code", 500), raw_error=str(e)
)
+ # Map raw HTTPX Errors
+ if isinstance(e, httpx.HTTPStatusError):
+ status = e.response.status_code
+ if status in (401, 403):
+ return AuthenticationError(message, raw_error=str(e))
+ if status == 429:
+ GlobalRateLimiter.get_instance().set_blocked(60)
+ return RateLimitError(message, raw_error=str(e))
+ if status == 400:
+ return InvalidRequestError(message, raw_error=str(e))
+ if status >= 500:
+ if status in (502, 503, 504):
+ return OverloadedError(message, raw_error=str(e))
+ return APIError(message, status_code=status, raw_error=str(e))
+ return APIError(message, status_code=status, raw_error=str(e))
+
return e
diff --git a/providers/lmstudio/client.py b/providers/lmstudio/client.py
index ce5ababc..7b5dbdf0 100644
--- a/providers/lmstudio/client.py
+++ b/providers/lmstudio/client.py
@@ -104,10 +104,18 @@ class LMStudioProvider(BaseProvider):
)
if response.status_code != 200:
- text = await response.aread()
- error_msg = f"HTTP {response.status_code}: {text.decode('utf-8', errors='replace')}"
- logger.error("{}_ERROR:{} {}", tag, req_tag, error_msg)
- raise RuntimeError(f"LMStudio natively returned error: {error_msg}")
+ try:
+ response.raise_for_status()
+ except httpx.HTTPStatusError as e:
+ text = await response.aread()
+ logger.error(
+ "{}_ERROR:{} HTTP {}: {}",
+ tag,
+ req_tag,
+ response.status_code,
+ text.decode("utf-8", errors="replace"),
+ )
+ raise e
async for line in response.aiter_lines():
if line:
diff --git a/tests/providers/test_lmstudio.py b/tests/providers/test_lmstudio.py
index a0910b6d..201e5910 100644
--- a/tests/providers/test_lmstudio.py
+++ b/tests/providers/test_lmstudio.py
@@ -167,8 +167,6 @@ async def test_stream_response(lmstudio_provider):
async def test_stream_response_adds_max_tokens_if_missing(lmstudio_provider):
"""Fallback max_tokens to 81920 if not present."""
req = MockRequest()
- # Replace the existing method completely to avoid proxy mapping errors from type checkers
- req.model_dump = lambda **kwargs: {"model": "test"} # type: ignore
mock_response = MagicMock()
mock_response.status_code = 200
@@ -179,6 +177,7 @@ async def test_stream_response_adds_max_tokens_if_missing(lmstudio_provider):
mock_response.aiter_lines = empty_aiter
with (
+ patch.object(req, "model_dump", return_value={"model": "test"}),
patch.object(lmstudio_provider._client, "build_request") as mock_build,
patch.object(
lmstudio_provider._client,
@@ -202,6 +201,11 @@ async def test_stream_error_status_code(lmstudio_provider):
mock_response = MagicMock()
mock_response.status_code = 500
mock_response.aread = AsyncMock(return_value=b"Internal Server Error")
+ mock_response.raise_for_status = MagicMock(
+ side_effect=httpx.HTTPStatusError(
+ "Internal Server Error", request=MagicMock(), response=mock_response
+ )
+ )
with (
patch.object(