Merge pull request #187 from Codium-ai/ok/limit_description

Limiting Description and Commit Messages Length

pr_agent/algo/pr_processing.py

@@ -11,7 +11,7 @@ from github import RateLimitExceededException
 from pr_agent.algo import MAX_TOKENS
 from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
 from pr_agent.algo.language_handler import sort_files_by_main_languages
-from pr_agent.algo.token_handler import TokenHandler
+from pr_agent.algo.token_handler import TokenHandler, get_token_encoder
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider
 
@@ -284,3 +284,26 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
                         absolute_position = start2 + delta - 1
                         break
     return position, absolute_position
+
+
+def clip_tokens(text: str, max_tokens: int) -> str:
+    """
+    Clip the number of tokens in a string to a maximum number of tokens.
+
+    Args:
+        text (str): The string to clip.
+        max_tokens (int): The maximum number of tokens allowed in the string.
+
+    Returns:
+        str: The clipped string.
+    """
+    # We'll estimate the number of tokens by hueristically assuming 2.5 tokens per word
+    encoder = get_token_encoder()
+    num_input_tokens = len(encoder.encode(text))
+    if num_input_tokens <= max_tokens:
+        return text
+    num_chars = len(text)
+    chars_per_token = num_chars / num_input_tokens
+    num_output_chars = int(chars_per_token * max_tokens)
+    clipped_text = text[:num_output_chars]
+    return clipped_text

pr_agent/algo/token_handler.py

@@ -4,6 +4,10 @@ from tiktoken import encoding_for_model, get_encoding
 from pr_agent.config_loader import get_settings
 
 
+def get_token_encoder():
+    return encoding_for_model(get_settings().config.model) if "gpt" in get_settings().config.model else get_encoding(
+        "cl100k_base")
+
 class TokenHandler:
     """
     A class for handling tokens in the context of a pull request.
@@ -27,7 +31,7 @@ class TokenHandler:
         - system: The system string.
         - user: The user string.
         """
-        self.encoder = encoding_for_model(get_settings().config.model) if "gpt" in get_settings().config.model else get_encoding("cl100k_base")
+        self.encoder = get_token_encoder()
         self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
 
     def _get_system_user_tokens(self, pr, encoder, vars: dict, system, user):