Merge pull request #1207 from Codium-ai/tr/fixes_metadata

Tr/fixes metadata

docs/docs/core-abilities/metadata.md

@@ -8,7 +8,8 @@ PR-Agent initially retrieves for each PR the following data:
 - PR diff patches, in [hunk diff](https://loicpefferkorn.net/2014/02/diff-files-what-are-hunks-and-how-to-extract-them/) format
 - The entire content of the files that were modified in the PR
 
-In addition, PR-Agent can incorporate supplementary information provided by the user and more tailored to his specific preferences, like [`extra_instructions` and `organization best practices`](https://pr-agent-docs.codium.ai/tools/improve/#extra-instructions-and-best-practices) that can be used to enhance the PR analysis.
+!!! tip "Tip: Organization-level metadata"
+    In addition to the inputs above, PR-Agent can incorporate supplementary preferences provided by the user, like [`extra_instructions` and `organization best practices`](https://pr-agent-docs.codium.ai/tools/improve/#extra-instructions-and-best-practices). This information can be used to enhance the PR analysis.
 
 (2)
 By default, the first command that PR-Agent executes is [`describe`](https://pr-agent-docs.codium.ai/tools/describe/), which generates three types of outputs:

pr_agent/algo/utils.py

@@ -967,9 +967,11 @@ def process_description(description_full: str):
                 try:
                     if isinstance(file_data, tuple):
                         file_data = file_data[0]
-                    # pattern = r'<details>\s*<summary><strong>(.*?)</strong><dd><code>(.*?)</code>.*?</summary>\s*<hr>\s*(.*?)\s*((?:\*.*\s*)*)</details>'
-                    pattern = r'<details>\s*<summary><strong>(.*?)</strong><dd><code>(.*?)</code>.*?</summary>\s*<hr>\s*(.*?)\n\n\s*(.*?)</details>'
+                    pattern = r'<details>\s*<summary><strong>(.*?)</strong>\s*<dd><code>(.*?)</code>.*?</summary>\s*<hr>\s*(.*?)\s*<li>(.*?)</details>'
                     res = re.search(pattern, file_data, re.DOTALL)
+                    if not res or res.lastindex != 4:
+                        pattern_back = r'<details>\s*<summary><strong>(.*?)</strong><dd><code>(.*?)</code>.*?</summary>\s*<hr>\s*(.*?)\n\n\s*(.*?)</details>'
+                        res = re.search(pattern_back, file_data, re.DOTALL)
                     if res and res.lastindex == 4:
                         short_filename = res.group(1).strip()
                         short_summary = res.group(2).strip()

pr_agent/tools/pr_code_suggestions.py

@@ -517,8 +517,7 @@ def _get_is_extended(self, args: list[str]) -> bool:
 
     async def _prepare_prediction_extended(self, model: str) -> dict:
         self.patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
-                                                    max_calls=get_settings().pr_code_suggestions.max_number_of_calls,
-                                                    pr_description_files =self.pr_description_files)
+                                                    max_calls=get_settings().pr_code_suggestions.max_number_of_calls)
         if self.patches_diff_list:
             get_logger().info(f"Number of PR chunk calls: {len(self.patches_diff_list)}")
             get_logger().debug(f"PR diff:", artifact=self.patches_diff_list)