Enhanced chat output with bold formatting and fixed token count calculation in prompt builders: Co-authored-by: MindFlow <mf@mindflo.ai>

Author: steegecs

mindflow/cli/commands/chat.py

@@ -26,6 +26,7 @@ def chat(prompt_args: Tuple[str], skip_index: bool):
 
     from typing import List
     from result import Ok
+    from termcolor import colored
 
     from mindflow.core.commands.chat import run_chat
     from mindflow.core.commands.index import run_index
@@ -34,15 +35,15 @@ def chat(prompt_args: Tuple[str], skip_index: bool):
     from mindflow.core.types.store_traits.json import save_json_store
 
     async def stream_chat(settings: Settings, prompt: str):
-        print("\nGPT:")
+        click.echo(colored("\nGPT:", attrs=["bold"]))
         async for char_stream_chunk in run_chat(settings, [], prompt):
             if isinstance(char_stream_chunk, Ok):
                 click.echo(char_stream_chunk.value, nl=False)
             else:
                 click.echo(char_stream_chunk.value)
 
     async def stream_query(settings: Settings, file_paths: List[str], prompt: str):
-        print("\nGPT:")
+        click.echo(colored("\nGPT:", attrs=["bold"]))
         async for char_stream_chunk in run_query(settings, file_paths, prompt):
             if isinstance(char_stream_chunk, Ok):
                 click.echo(char_stream_chunk.value, nl=False)

mindflow/core/prompt_builders.py

@@ -55,9 +55,9 @@ def prune_messages_to_fit_context_window(
     for i in range(0, len(messages)):
         if (
             get_token_count_of_text_for_model(
-                configured_model.tokenizer, json.dumps(messages[i : len(messages) - 1])
+                configured_model.tokenizer, json.dumps(messages[i : len(messages)])
             )
             < configured_model.model.hard_token_limit - 1500
         ):
-            return messages[i : len(messages) - 1]
+            return messages[i : len(messages)]
     return []