feat(core): Add client_name to token status reporting

- [feat] Add `client_name` parameter to `report_token_status()` and its payload (hf_token_utils.py:102,142-143)
- [update] Add `client_name` parameter to various handler functions (chat_handler.py:chat_respond(), image_handler.py:generate_image(), generate_image_to_image(), tts_handler.py:generate_text_to_speech(), video_handler.py:generate_video())
- [update] Pass `client_name` to `report_token_status()` calls in handler functions (chat_handler.py:126,130,134,148, image_handler.py:109,118,126,134,233,242,250,258, tts_handler.py:112,121,129,137, video_handler.py:95,103,111,119)
- [update] Pass `client_name` from `handle_*` functions to their respective generation/response functions (chat_handler.py:200,276, image_handler.py:305,334, tts_handler.py:186, video_handler.py:156)
- [refactor] Rename `_username` to `username` in handler functions (chat_handler.py:180,219, image_handler.py:292,320, tts_handler.py:172, video_handler.py:144)

chat_handler.py

@@ -33,6 +33,7 @@ def chat_respond(
     max_tokens,
     temperature,
     top_p,
+    client_name: str | None = None,
 ):
     """
     Chat completion function using HF-Inferoxy token management.
@@ -125,14 +126,14 @@ def chat_respond(
         
         # Report successful token usage
         if token_id:
-            report_token_status(token_id, "success", api_key=proxy_api_key)
+            report_token_status(token_id, "success", api_key=proxy_api_key, client_name=client_name)
             
     except ConnectionError as e:
         # Handle proxy connection errors
         error_msg = f"Cannot connect to HF-Inferoxy server: {str(e)}"
         print(f"🔌 Chat connection error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         yield format_error_message("Connection Error", "Unable to connect to the proxy server. Please check if it's running.")
         
     except TimeoutError as e:
@@ -140,7 +141,7 @@ def chat_respond(
         error_msg = f"Request timed out: {str(e)}"
         print(f"⏰ Chat timeout: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         yield format_error_message("Timeout Error", "The request took too long. The server may be overloaded. Please try again.")
         
     except HfHubHTTPError as e:
@@ -148,7 +149,7 @@ def chat_respond(
         error_msg = str(e)
         print(f"🤗 Chat HF error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         
         # Provide more user-friendly error messages
         if "401" in error_msg:
@@ -179,7 +180,7 @@ def handle_chat_submit(message, history, system_msg, model_name, provider, max_t
 
     # Enforce org-based access control via HF OAuth token
     access_token = getattr(hf_token, "token", None) if hf_token is not None else None
-    is_allowed, access_msg, _username, _matched = check_org_access(access_token)
+    is_allowed, access_msg, username, _matched = check_org_access(access_token)
     if not is_allowed:
         # Show access denied as assistant message
         assistant_response = format_access_denied_message(access_msg)
@@ -199,7 +200,8 @@ def handle_chat_submit(message, history, system_msg, model_name, provider, max_t
         provider,
         max_tokens, 
         temperature, 
-        top_p
+        top_p,
+        client_name=username
     )
     
     # Stream the assistant response token by token
@@ -218,7 +220,7 @@ def handle_chat_retry(history, system_msg, model_name, provider, max_tokens, tem
     """
     # Enforce org-based access control via HF OAuth token
     access_token = getattr(hf_token, "token", None) if hf_token is not None else None
-    is_allowed, access_msg, _username, _matched = check_org_access(access_token)
+    is_allowed, access_msg, username, _matched = check_org_access(access_token)
     if not is_allowed:
         # Show access denied as assistant message
         assistant_response = format_access_denied_message(access_msg)
@@ -273,7 +275,8 @@ def handle_chat_retry(history, system_msg, model_name, provider, max_tokens, tem
         provider,
         max_tokens,
         temperature,
-        top_p
+        top_p,
+        client_name=username
     )
 
     assistant_response = ""

hf_token_utils.py

@@ -99,7 +99,8 @@ def report_token_status(
     status: str = "success", 
     error: Optional[str] = None,
     proxy_url: str = None,
-    api_key: str = None
+    api_key: str = None,
+    client_name: Optional[str] = None
 ) -> bool:
     """
     Report token usage status back to the proxy server with timeout handling.
@@ -141,6 +142,9 @@ def report_token_status(
         if error_type:
             payload["error_type"] = error_type
     
+    if client_name:
+        payload["client_name"] = client_name
+
     headers = {"Content-Type": "application/json"}
     if api_key:
         headers["Authorization"] = f"Bearer {api_key}"

image_handler.py

@@ -42,6 +42,7 @@ def generate_image(
     num_inference_steps: int = IMAGE_CONFIG["num_inference_steps"],
     guidance_scale: float = IMAGE_CONFIG["guidance_scale"],
     seed: int = IMAGE_CONFIG["seed"],
+    client_name: str | None = None,
 ):
     """
     Generate an image using the specified model and provider through HF-Inferoxy.
@@ -108,7 +109,7 @@ def generate_image(
         
         # Report successful token usage
         if token_id:
-            report_token_status(token_id, "success", api_key=proxy_api_key)
+            report_token_status(token_id, "success", api_key=proxy_api_key, client_name=client_name)
         
         return image, format_success_message("Image generated", f"using {model_name} on {provider}")
         
@@ -117,7 +118,7 @@ def generate_image(
         error_msg = f"Cannot connect to HF-Inferoxy server: {str(e)}"
         print(f"🔌 Image connection error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         return None, format_error_message("Connection Error", "Unable to connect to the proxy server. Please check if it's running.")
         
     except TimeoutError as e:
@@ -125,7 +126,7 @@ def generate_image(
         error_msg = f"Image generation timed out: {str(e)}"
         print(f"⏰ Image timeout: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         return None, format_error_message("Timeout Error", f"Image generation took too long (>{IMAGE_GENERATION_TIMEOUT//60} minutes). Try reducing image size or steps.")
         
     except HfHubHTTPError as e:
@@ -133,7 +134,7 @@ def generate_image(
         error_msg = str(e)
         print(f"🤗 Image HF error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         
         # Provide more user-friendly error messages
         if "401" in error_msg:
@@ -165,6 +166,7 @@ def generate_image_to_image(
     num_inference_steps: int = IMAGE_CONFIG["num_inference_steps"],
     guidance_scale: float = IMAGE_CONFIG["guidance_scale"],
     seed: int = IMAGE_CONFIG["seed"],
+    client_name: str | None = None,
 ):
     """
     Generate an image using image-to-image generation with the specified model and provider through HF-Inferoxy.
@@ -231,7 +233,7 @@ def generate_image_to_image(
         
         # Report successful token usage
         if token_id:
-            report_token_status(token_id, "success", api_key=proxy_api_key)
+            report_token_status(token_id, "success", api_key=proxy_api_key, client_name=client_name)
         
         return image, format_success_message("Image-to-image generated", f"using {model_name} on {provider}")
         
@@ -240,7 +242,7 @@ def generate_image_to_image(
         error_msg = f"Cannot connect to HF-Inferoxy server: {str(e)}"
         print(f"🔌 Image-to-Image connection error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         return None, format_error_message("Connection Error", "Unable to connect to the proxy server. Please check if it's running.")
         
     except TimeoutError as e:
@@ -248,7 +250,7 @@ def generate_image_to_image(
         error_msg = f"Image-to-image generation timed out: {str(e)}"
         print(f"⏰ Image-to-Image timeout: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         return None, format_error_message("Timeout Error", f"Image-to-image generation took too long (>{IMAGE_GENERATION_TIMEOUT//60} minutes). Try reducing steps.")
         
     except HfHubHTTPError as e:
@@ -256,7 +258,7 @@ def generate_image_to_image(
         error_msg = str(e)
         print(f"🤗 Image-to-Image HF error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         
         # Provide more user-friendly error messages
         if "401" in error_msg:
@@ -289,7 +291,7 @@ def handle_image_to_image_generation(input_image_val, prompt_val, model_val, pro
     
     # Enforce org-based access control via HF OAuth token
     access_token = getattr(hf_token, "token", None) if hf_token is not None else None
-    is_allowed, access_msg, _username, _matched = check_org_access(access_token)
+    is_allowed, access_msg, username, _matched = check_org_access(access_token)
     if not is_allowed:
         return None, format_access_denied_message(access_msg)
     
@@ -302,7 +304,8 @@ def handle_image_to_image_generation(input_image_val, prompt_val, model_val, pro
         negative_prompt=negative_prompt_val,
         num_inference_steps=steps_val,
         guidance_scale=guidance_val,
-        seed=seed_val
+        seed=seed_val,
+        client_name=username
     )
 
 
@@ -317,7 +320,7 @@ def handle_image_generation(prompt_val, model_val, provider_val, negative_prompt
     
     # Enforce org-based access control via HF OAuth token
     access_token = getattr(hf_token, "token", None) if hf_token is not None else None
-    is_allowed, access_msg, _username, _matched = check_org_access(access_token)
+    is_allowed, access_msg, username, _matched = check_org_access(access_token)
     if not is_allowed:
         return None, format_access_denied_message(access_msg)
     
@@ -331,5 +334,6 @@ def handle_image_generation(prompt_val, model_val, provider_val, negative_prompt
         height=height_val,
         num_inference_steps=steps_val,
         guidance_scale=guidance_val,
-        seed=seed_val
+        seed=seed_val,
+        client_name=username
     )

tts_handler.py

@@ -36,6 +36,7 @@ def generate_text_to_speech(
     exaggeration: float = 0.25,
     temperature: float = 0.7,
     cfg: float = 0.5,
+    client_name: str | None = None,
 ):
     """
     Generate speech from text using the specified model and provider through HF-Inferoxy.
@@ -110,7 +111,7 @@ def generate_text_to_speech(
         
         # Report successful token usage
         if token_id:
-            report_token_status(token_id, "success", api_key=proxy_api_key)
+            report_token_status(token_id, "success", api_key=proxy_api_key, client_name=client_name)
         
         return audio, format_success_message("Speech generated", f"using {model_name} on {provider} with voice {voice}")
         
@@ -119,7 +120,7 @@ def generate_text_to_speech(
         error_msg = f"Cannot connect to HF-Inferoxy server: {str(e)}"
         print(f"🔌 TTS connection error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         return None, format_error_message("Connection Error", "Unable to connect to the proxy server. Please check if it's running.")
         
     except TimeoutError as e:
@@ -127,7 +128,7 @@ def generate_text_to_speech(
         error_msg = f"TTS generation timed out: {str(e)}"
         print(f"⏰ TTS timeout: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         return None, format_error_message("Timeout Error", f"TTS generation took too long (>{TTS_GENERATION_TIMEOUT//60} minutes). Try shorter text.")
         
     except HfHubHTTPError as e:
@@ -135,7 +136,7 @@ def generate_text_to_speech(
         error_msg = str(e)
         print(f"🤗 TTS HF error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         
         # Provide more user-friendly error messages
         if "401" in error_msg:
@@ -170,7 +171,7 @@ def handle_text_to_speech_generation(text_val, model_val, provider_val, voice_va
     
     # Enforce org-based access control via HF OAuth token
     access_token = getattr(hf_token, "token", None) if hf_token is not None else None
-    is_allowed, access_msg, _username, _matched = check_org_access(access_token)
+    is_allowed, access_msg, username, _matched = check_org_access(access_token)
     if not is_allowed:
         return None, format_access_denied_message(access_msg)
     
@@ -184,5 +185,6 @@ def handle_text_to_speech_generation(text_val, model_val, provider_val, voice_va
         audio_url=audio_url_val,
         exaggeration=exaggeration_val,
         temperature=temperature_val,
-        cfg=cfg_val
+        cfg=cfg_val,
+        client_name=username
     )

video_handler.py

@@ -32,6 +32,7 @@ def generate_video(
     num_inference_steps: int | None = None,
     guidance_scale: float | None = None,
     seed: int | None = None,
+    client_name: str | None = None,
 ):
     """
     Generate a video using the specified model and provider through HF-Inferoxy.
@@ -93,7 +94,7 @@ def generate_video(
 
         # Report successful token usage
         if token_id:
-            report_token_status(token_id, "success", api_key=proxy_api_key)
+            report_token_status(token_id, "success", api_key=proxy_api_key, client_name=client_name)
 
         return video_output, format_success_message("Video generated", f"using {model_name} on {provider}")
 
@@ -101,21 +102,21 @@ def generate_video(
         error_msg = f"Cannot connect to HF-Inferoxy server: {str(e)}"
         print(f"🔌 Video connection error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         return None, format_error_message("Connection Error", "Unable to connect to the proxy server. Please check if it's running.")
 
     except TimeoutError as e:
         error_msg = f"Video generation timed out: {str(e)}"
         print(f"⏰ Video timeout: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         return None, format_error_message("Timeout Error", f"Video generation took too long (>{VIDEO_GENERATION_TIMEOUT//60} minutes). Try a shorter prompt.")
 
     except HfHubHTTPError as e:
         error_msg = str(e)
         print(f"🤗 Video HF error: {error_msg}")
         if token_id:
-            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key)
+            report_token_status(token_id, "error", error_msg, api_key=proxy_api_key, client_name=client_name)
         if "401" in error_msg:
             return None, format_error_message("Authentication Error", "Invalid or expired API token. The proxy will provide a new token on retry.")
         elif "402" in error_msg:
@@ -141,7 +142,7 @@ def handle_video_generation(prompt_val, model_val, provider_val, steps_val, guid
         return None, format_error_message("Validation Error", "Please enter a prompt for video generation")
 
     access_token = getattr(hf_token, "token", None) if hf_token is not None else None
-    is_allowed, access_msg, _username, _matched = check_org_access(access_token)
+    is_allowed, access_msg, username, _matched = check_org_access(access_token)
     if not is_allowed:
         return None, format_access_denied_message(access_msg)
 
@@ -152,6 +153,7 @@ def handle_video_generation(prompt_val, model_val, provider_val, steps_val, guid
         num_inference_steps=steps_val if steps_val is not None else None,
         guidance_scale=guidance_val if guidance_val is not None else None,
         seed=seed_val if seed_val is not None else None,
+        client_name=username,
     )