API: Fix finish_reason returns

OAI expects finish_reason to be "stop" or "length" (there are others,
but they're not in the current scope of this project).

Make all completions and chat completions responses return this
from the model generation itself rather than putting a placeholder.

Signed-off-by: kingbri <bdashore3@proton.me>

endpoints/OAI/types/chat_completion.py

@@ -24,7 +24,7 @@ class ChatCompletionMessage(BaseModel):
 class ChatCompletionRespChoice(BaseModel):
     # Index is 0 since we aren't using multiple choices
     index: int = 0
-    finish_reason: str
+    finish_reason: Optional[str] = None
     message: ChatCompletionMessage
     logprobs: Optional[ChatCompletionLogprobs] = None
 
@@ -32,7 +32,7 @@ class ChatCompletionRespChoice(BaseModel):
 class ChatCompletionStreamChoice(BaseModel):
     # Index is 0 since we aren't using multiple choices
     index: int = 0
-    finish_reason: Optional[str]
+    finish_reason: Optional[str] = None
     delta: Union[ChatCompletionMessage, dict] = {}
     logprobs: Optional[ChatCompletionLogprobs] = None
 

endpoints/OAI/types/completion.py

@@ -22,7 +22,7 @@ class CompletionRespChoice(BaseModel):
 
     # Index is 0 since we aren't using multiple choices
     index: int = 0
-    finish_reason: str
+    finish_reason: Optional[str] = None
     logprobs: Optional[CompletionLogProbs] = None
     text: str