fix: improve message formatting and set default activation for providers

- In PerplexityLabs.py, added logic to filter consecutive assistant messages and update message array accordingly
- Modified PerplexityLabs.py to change "messages" field to use the new formatted message list
- Adjusted error handling in PerplexityLabs.py to include a newline in error messages
- Import os in BlackForestLabs_Flux1KontextDev.py and replace media filename assignment with basename if media is None
- In Groq.py, set "active_by_default" to True for the provider
- In OpenRouter.py, added "active_by_default" as True
- In Together.py, set "active_by_default" to True
- In HuggingFaceInference.py, set "working" to False
- In models.py, changed default_model to "openai/gpt-oss-120b" instead of previous value
- In backend_api.py, added a null check in jsonify_provider_models to return 404 if response is None, and simplified get_provider_models call

g4f/Provider/PerplexityLabs.py

@@ -66,11 +66,25 @@ class PerplexityLabs(AsyncGeneratorProvider, ProviderModelMixin):
                 assert(await ws.receive_str() == "3probe")
                 await ws.send_str("5")
                 assert(await ws.receive_str() == "6")
+                format_messages = []
+                last_is_assistant = False
+                for message in messages:
+                    if message["role"] == "assistant":
+                        if last_is_assistant:
+                            continue
+                        last_is_assistant = True
+                    else:
+                        last_is_assistant = False
+                    if isinstance(message["content"], str):
+                        format_messages.append({
+                            "role": message["role"],
+                            "text": message["content"]
+                        })
                 message_data = {
                     "version": "2.18",
                     "source": "default",
                     "model": model,
-                    "messages": [message for message in messages if isinstance(message["content"], str)],
+                    "messages": format_messages
                 }
                 await ws.send_str("42" + json.dumps(["perplexity_labs", message_data]))
                 last_message = 0
@@ -92,7 +106,7 @@ class PerplexityLabs(AsyncGeneratorProvider, ProviderModelMixin):
                         # Handle error responses
                         if message_type.endswith("_query_progress") and data.get("status") == "failed":
                             error_message = data.get("text", "Unknown API error")
-                            raise ResponseError(f"API Error: {error_message}")
+                            raise ResponseError(f"API Error: {error_message}\n")
                         
                         # Handle normal responses
                         if "output" in data:

g4f/Provider/hf_space/BlackForestLabs_Flux1KontextDev.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import os
 import uuid
 
 from ...typing import AsyncResult, Messages, MediaListType
@@ -83,6 +84,8 @@ class BlackForestLabs_Flux1KontextDev(AsyncGeneratorProvider, ProviderModelMixin
             if media:
                 data = FormData()
                 for i in range(len(media)):
+                    if media[i][1] is None and isinstance(media[i][0], str):
+                        media[i] = media[i][0], os.path.basename(media[i][0])
                     media[i] = (to_bytes(media[i][0]), media[i][1])
                 for image, image_name in media:
                     data.add_field(f"files", image, filename=image_name)

g4f/Provider/needs_auth/Groq.py

@@ -8,6 +8,7 @@ class Groq(OpenaiTemplate):
     api_base = "https://api.groq.com/openai/v1"
     working = True
     needs_auth = True
+    active_by_default = True
     default_model = "mixtral-8x7b-32768"
     fallback_models = [
         "distil-whisper-large-v3-en",

g4f/Provider/needs_auth/OpenRouter.py

@@ -8,4 +8,5 @@ class OpenRouter(OpenaiTemplate):
     login_url = "https://openrouter.ai/settings/keys"
     api_base = "https://openrouter.ai/api/v1"
     working = True
-    needs_auth = True
+    needs_auth = True
+    active_by_default = True

g4f/Provider/needs_auth/Together.py

@@ -16,7 +16,7 @@ class Together(OpenaiTemplate):
     api_base = "https://api.together.xyz/v1"
     models_endpoint = "https://api.together.xyz/v1/models"
 
-    active_by_default = False
+    active_by_default = True
     working = True
     needs_auth = True
     supports_stream = True

g4f/Provider/needs_auth/hf/HuggingFaceInference.py

@@ -24,7 +24,7 @@ provider_together_urls = {
 class HuggingFaceInference(AsyncGeneratorProvider, ProviderModelMixin):
     url = "https://huggingface.co"
     parent = "HuggingFace"
-    working = True
+    working = False
 
     default_model = default_model
     default_image_model = default_image_model

g4f/Provider/needs_auth/hf/models.py

@@ -1,4 +1,4 @@
-default_model = "Qwen/Qwen2.5-72B-Instruct"
+default_model = "openai/gpt-oss-120b"
 default_image_model = "black-forest-labs/FLUX.1-dev"
 image_models = [    
     default_image_model,

g4f/gui/server/backend_api.py

@@ -122,6 +122,8 @@ class Backend_Api(Api):
         def jsonify_provider_models(**kwargs):
             try:
                 response = self.get_provider_models(**kwargs)
+                if response is None:
+                    return jsonify({"error": {"message": "Provider not found"}}), 404
             except MissingAuthError as e:
                 return jsonify({"error": {"message": f"{type(e).__name__}: {e}"}}), 401
             except Exception as e:
@@ -596,10 +598,7 @@ class Backend_Api(Api):
         api_key = request.headers.get("x_api_key")
         api_base = request.headers.get("x_api_base")
         ignored = request.headers.get("x_ignored", "").split()
-        models = super().get_provider_models(provider, api_key, api_base, ignored)
+        return super().get_provider_models(provider, api_key, api_base, ignored)
-        if models is None:
-            return "Provider not found", 404
-        return models
 
     def _format_json(self, response_type: str, content = None, **kwargs) -> str:
         """