fixes

code/app.py

@@ -15,7 +15,7 @@ from modules.config.constants import (
     GITHUB_REPO,
     DOCS_WEBSITE,
     ALL_TIME_TOKENS_ALLOCATED,
-    TOKENS_LEFT
+    TOKENS_LEFT,
 )
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles
@@ -209,7 +209,9 @@ async def cooldown(request: Request):
     user_info = await get_user_info_from_cookie(request)
     user_details = await get_user_details(user_info["email"])
     current_datetime = get_time()
-    cooldown, cooldown_end_time = await check_user_cooldown(user_details, current_datetime)
+    cooldown, cooldown_end_time = await check_user_cooldown(
+        user_details, current_datetime
+    )
     print(f"User in cooldown: {cooldown}")
     print(f"Cooldown end time: {cooldown_end_time}")
     if cooldown and "admin" not in get_user_role(user_info["email"]):
@@ -240,9 +242,13 @@ async def post_signin(request: Request):
     user_details.metadata["last_login"] = current_datetime
     # if new user, set the number of tries
     if "tokens_left" not in user_details.metadata:
-        user_details.metadata["tokens_left"] = TOKENS_LEFT # set the number of tokens left for the new user
+        user_details.metadata["tokens_left"] = (
+            TOKENS_LEFT  # set the number of tokens left for the new user
+        )
         if "all_time_tokens_allocated" not in user_details.metadata:
-            user_details.metadata["all_time_tokens_allocated"] = ALL_TIME_TOKENS_ALLOCATED
+            user_details.metadata["all_time_tokens_allocated"] = (
+                ALL_TIME_TOKENS_ALLOCATED
+            )
         if "in_cooldown" not in user_details.metadata:
             user_details.metadata["in_cooldown"] = False
         await update_user_info(user_details)
@@ -252,8 +258,10 @@ async def post_signin(request: Request):
     ):
         cooldown, _ = await check_user_cooldown(user_details, current_datetime)
         if cooldown:
+            user_details.metadata["in_cooldown"] = True
             return RedirectResponse("/cooldown")
         else:
+            user_details.metadata["in_cooldown"] = False
             await reset_tokens_for_user(user_details)
 
     if user_info:
@@ -268,7 +276,9 @@ async def post_signin(request: Request):
                 "role": role,
                 "jwt_token": jwt_token,
                 "tokens_left": user_details.metadata["tokens_left"],
-                "all_time_tokens_allocated": user_details.metadata["all_time_tokens_allocated"],
+                "all_time_tokens_allocated": user_details.metadata[
+                    "all_time_tokens_allocated"
+                ],
                 "total_tokens_allocated": ALL_TIME_TOKENS_ALLOCATED,
             },
         )
@@ -331,7 +341,6 @@ async def get_tokens_left(request: Request):
     except Exception as e:
         print(f"Error getting tokens left: {e}")
         return {"tokens_left": 0}
-        
 
 
 mount_chainlit(app=app, target="main.py", path=CHAINLIT_PATH)

code/main.py

@@ -222,6 +222,7 @@ class Chatbot:
             "view_sources": llm_settings.get("view_sources"),
             "follow_up_questions": llm_settings.get("follow_up_questions"),
         }
+        print("Settings Dict: ", settings_dict)
         await cl.Message(
             author=SYSTEM,
             content="LLM settings have been updated. You can continue with your Query!",
@@ -373,9 +374,10 @@ class Chatbot:
         # if not, return message saying they have run out of tokens
         if user.metadata["tokens_left"] <= 0 and "admin" not in user.metadata["role"]:
             current_datetime = get_time()
-            cooldown, cooldown_end_time = await check_user_cooldown(user, current_datetime)
+            cooldown, cooldown_end_time = await check_user_cooldown(
+                user, current_datetime
+            )
             if cooldown:
-                user.metadata["in_cooldown"] = True
                 # get time left in cooldown
                 # convert both to datetime objects
                 cooldown_end_time = datetime.fromisoformat(cooldown_end_time).replace(
@@ -392,7 +394,6 @@ class Chatbot:
                 minutes, seconds = divmod(remainder, 60)
                 # Format the time as 00 hrs 00 mins 00 secs
                 formatted_time = f"{hours:02} hrs {minutes:02} mins {seconds:02} secs"
-                await update_user_info(user)
                 await cl.Message(
                     content=(
                         "Ah, seems like you have run out of tokens...Click "
@@ -402,8 +403,12 @@ class Chatbot:
                     ),
                     author=SYSTEM,
                 ).send()
+                user.metadata["in_cooldown"] = True
+                await update_user_info(user)
                 return
 
+        user.metadata["in_cooldown"] = False
+
         llm_settings = cl.user_session.get("llm_settings", {})
         view_sources = llm_settings.get("view_sources", False)
         stream = llm_settings.get("stream_response", False)
@@ -483,15 +488,21 @@ class Chatbot:
         # # update user info with token count
         if "admin" not in user.metadata["role"]:
             user.metadata["tokens_left"] = user.metadata["tokens_left"] - token_count
-            user.metadata["all_time_tokens_allocated"] = user.metadata["all_time_tokens_allocated"] - token_count
-            await reset_tokens_for_user(user) # regenerate tokens for the user
+            user.metadata["all_time_tokens_allocated"] = (
+                user.metadata["all_time_tokens_allocated"] - token_count
+            )
+            await reset_tokens_for_user(user)  # regenerate tokens for the user
         user.metadata["last_message_time"] = get_time()
         await update_user_info(user)
 
         tokens_left = user.metadata["tokens_left"]
         if tokens_left < 0:
             tokens_left = 0
-        answer_with_sources += '\n\n<footer><span style="font-size: 0.8em; text-align: right; display: block;">Tokens Left: ' + str(tokens_left) + '</span></footer>\n'
+        answer_with_sources += (
+            '\n\n<footer><span style="font-size: 0.8em; text-align: right; display: block;">Tokens Left: '
+            + str(tokens_left)
+            + "</span></footer>\n"
+        )
 
         await cl.Message(
             content=answer_with_sources,

code/modules/chat_processor/helpers.py

@@ -186,12 +186,13 @@ async def check_user_cooldown(user_info, current_time):
     if elapsed_time_in_seconds < COOLDOWN_TIME:
         return True, cooldown_end_time_iso  # Return in ISO 8601 format
 
-    user.metadata["in_cooldown"] = False
+    user_info["metadata"]["in_cooldown"] = False
     # If not in cooldown, regenerate tokens
     await reset_tokens_for_user(user_info)
 
     return False, None
 
+
 async def reset_tokens_for_user(user_info):
     user_info = convert_to_dict(user_info)
     last_message_time_str = user_info["metadata"].get("last_message_time")
@@ -212,29 +213,42 @@ async def reset_tokens_for_user(user_info):
 
     # Calculate how many tokens should have been regenerated proportionally
     if current_tokens < max_tokens:
-        # Determine the time required to fully regenerate tokens from current state
+        # Determine the time required to fully regenerate tokens from the current state
         if current_tokens < 0:
-            time_to_full_regen = REGEN_TIME * (1 + abs(current_tokens) / max_tokens) # more time to regenerate if tokens left is negative
+            time_to_full_regen = REGEN_TIME * (
+                1 + abs(current_tokens) / max_tokens
+            )  # more time to regenerate if tokens left is negative
         else:
-            time_to_full_regen = REGEN_TIME * (1 - current_tokens / max_tokens) # less time to regenerate if tokens left is positive
+            time_to_full_regen = REGEN_TIME * (
+                1 - current_tokens / max_tokens
+            )  # less time to regenerate if tokens left is positive
 
         # Calculate the proportion of this time that has elapsed
-        proportion_of_time_elapsed = min(elapsed_time_in_seconds / time_to_full_regen, 1.0)
+        proportion_of_time_elapsed = elapsed_time_in_seconds / time_to_full_regen
+
+        # Ensure the proportion doesn't exceed 1.0
+        proportion_of_time_elapsed = min(proportion_of_time_elapsed, 1.0)
 
         # Calculate the tokens to regenerate based on the elapsed proportion
-        tokens_to_regenerate = int(proportion_of_time_elapsed * (max_tokens - current_tokens))
+        tokens_to_regenerate = int(
+            proportion_of_time_elapsed * (max_tokens - current_tokens)
+        )
 
         # Ensure tokens_to_regenerate is positive and doesn't exceed the maximum
         if tokens_to_regenerate > 0:
             new_token_count = min(current_tokens + tokens_to_regenerate, max_tokens)
 
-            print(f"\n\n Adding {tokens_to_regenerate} tokens to the user, Time left for full credits: {time_to_full_regen - elapsed_time_in_seconds} \n\n")
+            print(
+                f"\n\n Adding {tokens_to_regenerate} tokens to the user, Time left for full credits: {max(0, time_to_full_regen - elapsed_time_in_seconds)} \n\n"
+            )
 
             # Update the user's token count
             user_info["metadata"]["tokens_left"] = new_token_count
 
             await update_user_info(user_info)
 
+
+
 async def get_thread_step_info(thread_id):
     step = await literal_client.api.get_step(thread_id)
     return step