xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-02 11:50:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

Combine all modified file that been compressed into one list at the end of the PR

Browse Source
This commit is contained in:
Hussam.lawen
2023-07-06 11:12:41 +03:00
parent 84231f99dc
commit 0ce42e786e
1 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
pr_agent/algo/pr_processing.py
View File

@ -32,8 +32,12 @@ def get_pr_diff(git_provider: [GithubProvider, Any], token_handler: TokenHandler
return "\n".join(patches_extended) return "\n".join(patches_extended)
# if we are over the limit, start pruning # if we are over the limit, start pruning
patches_compressed = pr_generate_compressed_diff(pr_languages, token_handler) patches_compressed, modified_file_names = pr_generate_compressed_diff(pr_languages, token_handler)
return "\n".join(patches_compressed) final_diff = "\n".join(patches_compressed)
if modified_file_names:
modified_list_str = "Modified files:\n" + "\n".join(modified_file_names)
final_diff = final_diff + "\n\n" + modified_list_str
return final_diff
def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -> \ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -> \
@ -67,7 +71,7 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -
return patches_extended, total_tokens return patches_extended, total_tokens
def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) -> list: def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) -> (list, list):
# Apply Diff Minimization techniques to reduce the number of tokens: # Apply Diff Minimization techniques to reduce the number of tokens:
# 0. Start from the largest diff patch to smaller ones # 0. Start from the largest diff patch to smaller ones
# 1. Don't use extend context lines around diff # 1. Don't use extend context lines around diff
@ -76,7 +80,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) ->
# 4. Minimize all remaining files when you reach token limit # 4. Minimize all remaining files when you reach token limit
patches = [] patches = []
modified_files = []
# sort each one of the languages in top_langs by the number of tokens in the diff # sort each one of the languages in top_langs by the number of tokens in the diff
sorted_files = [] sorted_files = []
for lang in top_langs: for lang in top_langs:
@ -105,14 +109,16 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) ->
# until we meet the requirements # until we meet the requirements
if settings.config.verbosity_level >= 2: if settings.config.verbosity_level >= 2:
logging.warning(f"Patch too large, minimizing it, {file.filename}") logging.warning(f"Patch too large, minimizing it, {file.filename}")
patch = "File was modified" patch = None
modified_files.append(file.filename)
if patch: if patch:
patch_final = f"## {file.filename}\n\n{patch}\n" patch_final = f"## {file.filename}\n\n{patch}\n"
patches.append(patch_final) patches.append(patch_final)
total_tokens += token_handler.count_tokens(patch_final) total_tokens += token_handler.count_tokens(patch_final)
if settings.config.verbosity_level >= 2: if settings.config.verbosity_level >= 2:
logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}") logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
return patches
return patches, modified_files
def load_large_diff(file, new_file_content_str: str, original_file_content_str: str, patch: str) -> str: def load_large_diff(file, new_file_content_str: str, original_file_content_str: str, patch: str) -> str: