fix(clinepass): address external review -- logging, unicode, dead code, UI, README

Fixes from two independent reviews of the provider addition:

* `main.py`: drop the provider's own `logging.post_call`. The shared
  `BaseLLMHTTPHandler` already logs post-call, so this double-fired callbacks and
  overwrote raw-response metadata; on the async path `response` is still a
  coroutine there, so callbacks ran before the request completed. Also adopt the
  `Final` annotations and `_dispatch_client_http(ctx)` used by the sibling
  `_complete_*` blocks.
* `transformation.py`: `json.dumps(..., ensure_ascii=False)` when rebuilding the
  unwrapped body -- the default escapes non-ASCII to `\uXXXX`, and
  `OpenAIGPTConfig.transform_response` hands `raw_response.text` straight to
  `logging.post_call`, so observability backends received mangled text.
* `transformation.py`: remove two unreachable branches. `httpx.StreamError` cannot
  arrive, because `BaseLLMHTTPHandler` returns `get_model_response_iterator()`
  without calling `transform_response` when streaming (the only paths that do call
  it set `stream=False`, so the body is fully buffered). The
  `max_completion_tokens` fallback cannot fire either, because `request_data` is
  the post-`map_openai_params` payload and the mapping has already rewritten that
  key to `max_tokens`.
* `transformation.py`: modernise typing to builtin generics and PEP 604 unions,
  matching the repo's UP006/UP007/UP035/UP045 rules and the CometAPI house style.
* UI: add `CLINEPASS` to the `Providers` enum and `provider_map`.
  `CredentialModal` builds its options from `Object.entries(Providers)`, so
  backend credential metadata alone left the provider unselectable.
* README: add the provider table row, ticking only the endpoints
  `provider_endpoints_support.json` declares.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

README.md

@@ -317,6 +317,7 @@ Set `LITELLM_PROXY_API_BASE` and `LITELLM_PROXY_API_KEY` and every model call th
 | [Bytez (`bytez`)](https://docs.litellm.ai/docs/providers/bytez) | ✅ | ✅ | ✅ |  |  |  |  |  |  |  |
 | [Cerebras (`cerebras`)](https://docs.litellm.ai/docs/providers/cerebras) | ✅ | ✅ | ✅ |  |  |  |  |  |  |  |
 | [Clarifai (`clarifai`)](https://docs.litellm.ai/docs/providers/clarifai) | ✅ | ✅ | ✅ |  |  |  |  |  |  |  |
+| [ClinePass (`clinepass`)](https://docs.litellm.ai/docs/providers/clinepass) | ✅ | ✅ | ✅ |  |  |  |  |  |  |  |
 | [Cloudflare AI Workers (`cloudflare`)](https://docs.litellm.ai/docs/providers/cloudflare_workers) | ✅ | ✅ | ✅ |  |  |  |  |  |  |  |
 | [Codestral (`codestral`)](https://docs.litellm.ai/docs/providers/codestral) | ✅ | ✅ | ✅ |  |  |  |  |  |  |  |
 | [Cognition (`cognition`)](https://docs.litellm.ai/docs/providers/cognition) | ✅ | ✅ | ✅ |  |  |  |  |  |  |  |

litellm/llms/clinepass/chat/transformation.py

@@ -15,7 +15,7 @@ Documentation: https://docs.cline.bot/
 """
 
 import json
-from typing import Any, List, Optional, Tuple, Union
+from typing import Any, Final
 
 import httpx
 
@@ -27,10 +27,10 @@ from litellm.types.utils import ModelResponse
 from ...openai.chat.gpt_transformation import OpenAIGPTConfig
 from ..common_utils import ClinePassException
 
-CLINEPASS_API_BASE = "https://api.cline.bot/api/v1"
+CLINEPASS_API_BASE: Final = "https://api.cline.bot/api/v1"
 
 # ClinePass nests the completion under this key on non-streaming responses.
-CLINEPASS_RESPONSE_ENVELOPE_KEY = "data"
+CLINEPASS_RESPONSE_ENVELOPE_KEY: Final = "data"
 
 # The qualifier ClinePass expects on outbound model ids.
 #
@@ -42,14 +42,14 @@ CLINEPASS_RESPONSE_ENVELOPE_KEY = "data"
 # model an unrecognised namespace resolves to a different, date-pinned snapshot
 # (``cline-pass/deepseek-v4-flash`` -> ``deepseek/deepseek-v4-flash``, while
 # ``clinepass/deepseek-v4-flash`` -> ``deepseek/deepseek-v4-flash-0731``).
-CLINEPASS_MODEL_PREFIX = "cline-pass/"
+CLINEPASS_MODEL_PREFIX: Final = "cline-pass/"
 
 # Headers that describe the original byte stream and would be wrong once the
 # body is rewritten by _unwrap_response_envelope().
-_BODY_SPECIFIC_HEADERS = ("content-length", "content-encoding")
+_BODY_SPECIFIC_HEADERS: Final = ("content-length", "content-encoding")
 
 
-def _as_positive_number(value: Any) -> Optional[float]:
+def _as_positive_number(value: Any) -> float | None:
     """Return ``value`` as a positive number, or ``None`` if it is not one.
 
     ``bool`` is rejected explicitly: it is a subclass of ``int``, and ``True``
@@ -99,8 +99,6 @@ def _correct_truncated_finish_reason(response: ModelResponse, request_data: dict
         return response
 
     max_tokens = _as_positive_number(request_data.get("max_tokens"))
-    if max_tokens is None:
-        max_tokens = _as_positive_number(request_data.get("max_completion_tokens"))
     if max_tokens is None:
         return response
 
@@ -128,9 +126,8 @@ def _unwrap_response_envelope(raw_response: httpx.Response) -> httpx.Response:
     """
     try:
         payload = raw_response.json()
-    except (ValueError, httpx.StreamError):
-        # Not a JSON body, or a streaming response that has not been read --
-        # either way there is no envelope to strip.
+    except ValueError:
+        # Not a JSON body -- there is no envelope to strip.
         return raw_response
 
     if not isinstance(payload, dict) or "choices" in payload:
@@ -153,7 +150,7 @@ def _unwrap_response_envelope(raw_response: httpx.Response) -> httpx.Response:
     return httpx.Response(
         status_code=raw_response.status_code,
         headers=headers,
-        content=json.dumps(inner).encode("utf-8"),
+        content=json.dumps(inner, ensure_ascii=False).encode("utf-8"),
         request=original_request,
     )
 
@@ -180,7 +177,7 @@ class ClinePassConfig(OpenAIGPTConfig):
 
     def _get_openai_compatible_provider_info(
         self, api_base: str | None, api_key: str | None
-    ) -> Tuple[str | None, str | None]:
+    ) -> tuple[str | None, str | None]:
         api_base = api_base or get_secret_str("CLINEPASS_API_BASE") or CLINEPASS_API_BASE
         dynamic_api_key = api_key or get_secret_str("CLINEPASS_API_KEY")
         return api_base, dynamic_api_key
@@ -203,7 +200,7 @@ class ClinePassConfig(OpenAIGPTConfig):
 
         return f"{api_base}/chat/completions"
 
-    def get_models(self, api_key: Optional[str] = None, api_base: Optional[str] = None) -> List[str]:
+    def get_models(self, api_key: str | None = None, api_base: str | None = None) -> list[str]:
         """ClinePass exposes no model catalog.
 
         ``GET https://api.cline.bot/api/v1/models`` returns HTTP 404, and the
@@ -235,7 +232,7 @@ class ClinePassConfig(OpenAIGPTConfig):
     def transform_request(
         self,
         model: str,
-        messages: List[AllMessageValues],
+        messages: list[AllMessageValues],
         optional_params: dict,
         litellm_params: dict,
         headers: dict,
@@ -259,7 +256,7 @@ class ClinePassConfig(OpenAIGPTConfig):
         model_response: ModelResponse,
         logging_obj: Any,
         request_data: dict,
-        messages: List[AllMessageValues],
+        messages: list[AllMessageValues],
         optional_params: dict,
         litellm_params: dict,
         encoding: Any,
@@ -282,7 +279,7 @@ class ClinePassConfig(OpenAIGPTConfig):
         return _correct_truncated_finish_reason(response, request_data)
 
     def get_error_class(
-        self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
+        self, error_message: str, status_code: int, headers: dict | httpx.Headers
     ) -> BaseLLMException:
         return ClinePassException(
             message=error_message,

litellm/main.py

@@ -2449,22 +2449,22 @@ def _complete_aiohttp_openai(
 
 
 def _complete_clinepass(ctx: _CompletionDispatchContext) -> _CompletionDispatchResult:
-    acompletion = ctx.acompletion
+    acompletion: Final = ctx.acompletion
     api_base = ctx.api_base
     api_key = ctx.api_key
-    client = ctx.client
-    custom_llm_provider = ctx.custom_llm_provider
-    headers = ctx.headers
-    litellm_params = ctx.litellm_params
-    logging = ctx.logging
-    messages = ctx.messages
-    model = ctx.model
-    model_response = ctx.model_response
-    optional_params = ctx.optional_params
-    provider_config = ctx.provider_config
-    shared_session = ctx.shared_session
-    stream = ctx.stream
-    timeout = ctx.timeout
+    client: Final = _dispatch_client_http(ctx)
+    custom_llm_provider: Final = ctx.custom_llm_provider
+    headers: Final = ctx.headers
+    litellm_params: Final = ctx.litellm_params
+    logging: Final = ctx.logging
+    messages: Final = ctx.messages
+    model: Final = ctx.model
+    model_response: Final = ctx.model_response
+    optional_params: Final = ctx.optional_params
+    provider_config: Final = ctx.provider_config
+    shared_session: Final = ctx.shared_session
+    stream: Final = ctx.stream
+    timeout: Final = ctx.timeout
 
     api_key = api_key or get_secret_str("CLINEPASS_API_KEY") or litellm.api_key
 
@@ -2473,7 +2473,7 @@ def _complete_clinepass(ctx: _CompletionDispatchContext) -> _CompletionDispatchR
     )
 
     ## COMPLETION CALL
-    response = base_llm_http_handler.completion(
+    response: Final = base_llm_http_handler.completion(
         model=model,
         messages=messages,
         headers=headers,
@@ -2493,9 +2493,6 @@ def _complete_clinepass(ctx: _CompletionDispatchContext) -> _CompletionDispatchR
         provider_config=provider_config,
     )
 
-    ## LOGGING
-    logging.post_call(input=messages, api_key=api_key, original_response=response)
-
     return response
 
 

ui/litellm-dashboard/src/components/provider_info_helpers.tsx

@@ -89,6 +89,7 @@ export enum Providers {
   Cerebras = "Cerebras",
   CHATGPT = "ChatGPT Subscription",
   CLARIFAI = "Clarifai",
+  CLINEPASS = "ClinePass",
   CLOUDFLARE = "Cloudflare",
   CODESTRAL = "Codestral",
   Cognition = "Cognition",
@@ -208,6 +209,7 @@ export const provider_map: Record<string, string> = {
   Cerebras: "cerebras",
   CHATGPT: "chatgpt",
   CLARIFAI: "clarifai",
+  CLINEPASS: "clinepass",
   CLOUDFLARE: "cloudflare",
   CODESTRAL: "codestral",
   Cognition: "cognition",