refactor: remove count info from todo summary

pr_agent/algo/utils.py

@@ -164,7 +164,7 @@ def convert_to_markdown_v2(output_data: dict,
     if gfm_supported:
         markdown_text += "<table>\n"
 
-    todos_summary = output_data['review'].pop('todos_summary', '')
+    todo_summary = output_data['review'].pop('todo_summary', '')
     for key, value in output_data['review'].items():
         if value is None or value == '' or value == {} or value == []:
             if key.lower() not in ['can_be_split', 'key_issues_to_review']:
@@ -289,7 +289,7 @@ def convert_to_markdown_v2(output_data: dict,
                     markdown_text += f"{emoji}&nbsp;<strong>No TODO sections</strong>"
                 else:
                     markdown_text += f"{emoji}&nbsp;<strong>TODO sections ({todo_entry_label})</strong>\n"
-                    markdown_text += f"<details{details_open_attr}><summary>{todos_summary}</summary>\n\n"
+                    markdown_text += f"<details{details_open_attr}><summary>{todo_summary}</summary>\n\n"
                     markdown_text += markdown_todo_items
                     markdown_text += "\n</details>\n"
                 markdown_text += "</td></tr>\n"
@@ -297,7 +297,7 @@ def convert_to_markdown_v2(output_data: dict,
                 if is_value_no(value):
                     markdown_text += f"### {emoji} No TODO sections\n\n"
                 else:
-                    markdown_text += f"### {emoji} TODO sections ({todo_entry_label})\n<details{details_open_attr}><summary>{todos_summary}</summary>\n\n"
+                    markdown_text += f"### {emoji} TODO sections ({todo_entry_label})\n<details{details_open_attr}><summary>{todo_summary}</summary>\n\n"
                     markdown_text += markdown_todo_items
                     markdown_text += "\n</details>\n\n"
         elif 'can be split' in key_nice.lower():

pr_agent/settings/pr_reviewer_prompts.toml

@@ -109,18 +109,15 @@ class Review(BaseModel):
 {%- endif %}
 {%- if require_todo_scan %}
     todo_sections: Union[List[TodoSection], str] = Field(description="A list of TODO comments found in the code. Return 'No' (as a string) if there are no TODO comments.")
-    todos_summary: str = Field(description="When writing TODO section summaries, use this format:
+    todo_summary: str = Field(description="Summarize the functional areas of the TODO comments found in the code.
-      [count] TODOs found about [functional area based on TODO content]
+      - Focus on describing the *functional areas* of the TODOs, such as:
-
-      - The [count] is the number of TODO items, equal to the length of the `todo_sections` list.
-      - Functional areas describe what the TODOs are about:
           testing, error handling, validation, documentation, performance,
           security, logging, refactoring, API design, UI/UX
 
-      Example:
+      - Example:
-        3 TODOs found about input validation and error handling
+          TODO related to input validation and error handling
 
-      Return 'No' (as a string) if there are no TODO comments.")
+      - Return 'No' (as a string) if there are no TODO comments.")
 {%- endif %}
 {%- if require_can_be_split_review %}
     can_be_split: List[SubPR] = Field(min_items=0, max_items=3, description="Can this PR, which contains {{ num_pr_files }} changed files in total, be divided into smaller sub-PRs with distinct tasks that can be reviewed and merged independently, regardless of the order ? Make sure that the sub-PRs are indeed independent, with no code dependencies between them, and that each sub-PR represent a meaningful independent task. Output an empty list if the PR code does not need to be split.")
@@ -170,7 +167,7 @@ review:
     No
   todo_sections: |
     No
-  todos_summary: |
+  todo_summary: |
     No
 {%- if require_can_be_split_review %}
   can_be_split:
@@ -292,7 +289,7 @@ review:
     No
   todo_sections: |
     No
-  todos_summary: |
+  todo_summary: |
     No
 {%- if require_can_be_split_review %}
   can_be_split: