Merge remote-tracking branch 'origin/main' into tr/user_description

# Conflicts:
#	pr_agent/git_providers/git_provider.py

docs/DESCRIBE.md

@@ -48,7 +48,8 @@ Under the section 'pr_description', the [configuration file](./../pr_agent/setti
 
 - `final_update_message`: if set to true, it will add a comment message [`PR Description updated to latest commit...`](https://github.com/Codium-ai/pr-agent/pull/499#issuecomment-1837412176) after finishing calling `/describe`. Default is true.
 
-- `enable_semantic_files_types`: if set to true, "PR changes walkthrough" section will be generated. Default is true.
+- `enable_semantic_files_types`: if set to true, "Changes walkthrough" section will be generated. Default is true.
+- `collapsible_file_list`: if set to true, the file list in the "Changes walkthrough" section will be collapsible. If set to "adaptive", the file list will be collapsible only if there are more than 8 files. Default is "adaptive".
   
 ### Markers template
 

pr_agent/git_providers/git_provider.py

@@ -74,20 +74,22 @@ class GitProvider(ABC):
 
     def get_user_description(self) -> str:
         description = (self.get_pr_description_full() or "").strip()
+        description_lowercase = description.lower()
         # if the existing description wasn't generated by the pr-agent, just return it as-is
-        if not any(description.startswith(header) for header in ("## PR Type", "## PR Description")):
+        if not self._is_generated_by_pr_agent(description_lowercase):
             return description
         # if the existing description was generated by the pr-agent, but it doesn't contain the user description,
         # return nothing (empty string) because it means there is no user description
-        if "## User Description:" not in description:
+        user_description_header = "## user description"
+        if user_description_header not in description_lowercase:
             return ""
+        # otherwise, extract the original user description from the existing pr-agent description and return it
+        user_description_start_position = description_lowercase.find(user_description_header) + len(user_description_header)
+        return description[user_description_start_position:].split("\n", 1)[-1].strip()
 
-        # # otherwise, extract the original user description from the existing pr-agent description and return it
-        # return description.split("## User Description:", 1)[1].strip()
-
-        # the 'user description' is in the beginning. extract it
-        return description.split("\n\n___", 1)[0].strip()
-
+    def _is_generated_by_pr_agent(self, description_lowercase: str) -> bool:
+        possible_headers = ("## pr type", "## pr description", "## pr labels", "## type", "## description", "## labels", "### 🤖 generated by pr agent")
+        return any(description_lowercase.startswith(header) for header in possible_headers)
 
     @abstractmethod
     def get_repo_settings(self):

pr_agent/settings/configuration.toml

@@ -51,11 +51,10 @@ keep_original_user_title=false
 use_bullet_points=true
 extra_instructions = ""
 enable_pr_type=true
-enable_file_walkthrough=false
-enable_semantic_files_types=true
 final_update_message = true
-
-
+## changes walkthrough section
+enable_semantic_files_types=true
+collapsible_file_list='adaptive' # true, false, 'adaptive'
 # markers
 use_description_markers=false
 include_generated_by_header=true

pr_agent/settings/pr_description_prompts.toml

@@ -35,12 +35,6 @@ class PRType(str, Enum):
 
 {%- endif %}
 
-{%- if enable_file_walkthrough %}
-class FileWalkthrough(BaseModel):
-    filename: str = Field(description="the relevant file full path")
-    changes_in_file: str = Field(description="minimal and concise summary of the changes in the relevant file")
-{%- endif %}
-
 {%- if enable_semantic_files_types %}
 
 Class FileDescription(BaseModel):

pr_agent/tools/pr_description.py

@@ -52,7 +52,6 @@ class PRDescription:
             "commit_messages_str": self.git_provider.get_commit_messages(),
             "enable_custom_labels": get_settings().config.enable_custom_labels,
             "custom_labels_class": "",  # will be filled if necessary in 'set_custom_labels' function
-            "enable_file_walkthrough": get_settings().pr_description.enable_file_walkthrough,
             "enable_semantic_files_types": get_settings().pr_description.enable_semantic_files_types,
         }
 
@@ -251,16 +250,15 @@ class PRDescription:
             summary = f"{ai_header}{ai_summary}"
             body = body.replace('pr_agent:summary', summary)
 
-        if not re.search(r'<!--\s*pr_agent:walkthrough\s*-->', body):
-            ai_walkthrough = self.data.get('PR Main Files Walkthrough')
-            if ai_walkthrough:
-                walkthrough = str(ai_header)
-                for file in ai_walkthrough:
-                    filename = file['filename'].replace("'", "`")
-                    description = file['changes in file'].replace("'", "`")
-                    walkthrough += f'- `{filename}`: {description}\n'
-
-                body = body.replace('pr_agent:walkthrough', walkthrough)
+        ai_walkthrough = self.data.get('pr_files')
+        if ai_walkthrough and not re.search(r'<!--\s*pr_agent:walkthrough\s*-->', body):
+            try:
+                walkthrough_gfm = ""
+                walkthrough_gfm = self.process_pr_files_prediction(walkthrough_gfm, self.file_label_dict)
+                body = body.replace('pr_agent:walkthrough', walkthrough_gfm)
+            except Exception as e:
+                get_logger().error(f"Failing to process walkthrough {self.pr_id}: {e}")
+                body = body.replace('pr_agent:walkthrough', "")
 
         return title, body
 
@@ -299,7 +297,7 @@ class PRDescription:
         for idx, (key, value) in enumerate(self.data.items()):
             if key == 'pr_files':
                 value = self.file_label_dict
-                key_publish = "PR changes walkthrough"
+                key_publish = "Changes walkthrough"
             else:
                 key_publish = key.rstrip(':').replace("_", " ").capitalize()
             pr_body += f"## {key_publish}\n"
@@ -333,7 +331,7 @@ class PRDescription:
             try:
                 filename = file['filename'].replace("'", "`").replace('"', '`')
                 changes_summary = file['changes_summary']
-                label = file['label']
+                label = file.get('label')
                 if label not in self.file_label_dict:
                     self.file_label_dict[label] = []
                 self.file_label_dict[label].append((filename, changes_summary))
@@ -342,6 +340,9 @@ class PRDescription:
                 pass
 
     def process_pr_files_prediction(self, pr_body, value):
+        use_collapsible_file_list = get_settings().pr_description.collapsible_file_list
+        if use_collapsible_file_list == "adaptive":
+            use_collapsible_file_list = len(value) > 8
         if not self.git_provider.is_supported("gfm_markdown"):
             get_logger().info(f"Disabling semantic files types for {self.pr_id} since gfm_markdown is not supported")
             return pr_body
@@ -356,7 +357,11 @@ class PRDescription:
                 s_label = semantic_label.strip("'").strip('"')
                 pr_body += f"""<tr><td><strong>{s_label.capitalize()}</strong></td>"""
                 list_tuples = value[semantic_label]
-                pr_body += f"""<td><details><summary>{len(list_tuples)} files</summary><table>"""
+
+                if use_collapsible_file_list:
+                    pr_body += f"""<td><details><summary>{len(list_tuples)} files</summary><table>"""
+                else:
+                    pr_body += f"""<td><table>"""
                 for filename, file_change_description in list_tuples:
                     filename = filename.replace("'", "`")
                     filename_publish = filename.split("/")[-1]
@@ -395,7 +400,10 @@ class PRDescription:
 
 </tr>                    
 """
-                pr_body += """</table></details></td></tr>"""
+                if use_collapsible_file_list:
+                    pr_body += """</table></details></td></tr>"""
+                else:
+                    pr_body += """</table></td></tr>"""
             pr_body += """</tr></tbody></table>"""
 
         except Exception as e: