Support Dynamic Thinking Models (#23281)

* Add ability to toggle thinking

* Disable thinking for descriptions automatically

* mypy

* Cleanup

frigate/api/chat.py

@@ -1173,6 +1173,7 @@ async def chat_completion(
                     messages=conversation,
                     tools=tools if tools else None,
                     tool_choice="auto",
+                    enable_thinking=body.enable_thinking,
                 ):
                     if await request.is_disconnected():
                         logger.debug("Client disconnected, stopping chat stream")
@@ -1267,6 +1268,7 @@ async def chat_completion(
                 messages=conversation,
                 tools=tools if tools else None,
                 tool_choice="auto",
+                enable_thinking=body.enable_thinking,
             )
 
             if response.get("finish_reason") == "error":

frigate/api/defs/request/chat_body.py

@@ -36,3 +36,10 @@ class ChatCompletionRequest(BaseModel):
         default=False,
         description="If true, stream the final assistant response in the body as newline-delimited JSON.",
     )
+    enable_thinking: Optional[bool] = Field(
+        default=None,
+        description=(
+            "Per-request thinking toggle. None means use the provider default. "
+            "Ignored by providers that do not expose a per-request thinking switch."
+        ),
+    )