Merge remote-tracking branch 'origin/main' into feature/gitlab_provider

README.md

@@ -86,8 +86,8 @@ pip install -r requirements.txt
 3. Copy the secrets template file and fill in your OpenAI key and your GitHub user token:
 
 ```
-cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets
+cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
-# Edit .secrets file
+# Edit .secrets.toml file
 ```
 
 4. Run the appropriate Python scripts from the scripts folder:
@@ -147,8 +147,8 @@ git clone https://github.com/Codium-ai/pr-agent.git
    - Copy your app's webhook secret to the webhook_secret field.
 
 ```
-cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets
+cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
-# Edit .secrets file
+# Edit .secrets.toml file
 ```
 
 6. Build a Docker image for the app and optionally push it to a Docker repository. We'll use Dockerhub as an example:
@@ -186,7 +186,7 @@ Here is a quick overview of the different sub-tools of PR Reviewer:
   - PR description and title
   - PR type classification
   - Is the PR covered by relevant tests
-  - Is the PR minimal and focused
+  - Is this a focused PR
   - Are there security concerns
 - PR Feedback
   - General PR suggestions
@@ -202,7 +202,7 @@ This is how a typical output of the PR Reviewer looks like:
 - 🔍 **Description and title:** Yes
 - 📌 **Type of PR:** Enhancement
 - 🧪 **Relevant tests added:** No
-- ✨ **Minimal and focused:** Yes, the PR is focused on adding two new handlers for language extension and token counting.
+- ✨ **Focused PR:** Yes, the PR is focused on adding two new handlers for language extension and token counting.
 - 🔒 **Security concerns:** No, the PR does not introduce possible security concerns or issues.
 
 #### PR Feedback
@@ -245,7 +245,7 @@ The different tools and sub-tools used by CodiumAI pr-agent are easily configura
 You can enable/disable the different PR Reviewer sub-sections with the following flags:
 
 ```
-require_minimal_and_focused_review=true
+require_focused_review=true
 require_tests_review=true
 require_security_review=true
 ```

pr_agent/algo/pr_processing.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import difflib
 import logging
-from typing import Any, Dict, Tuple, Union
+from typing import Any, Tuple, Union
 
 from pr_agent.algo.git_patch_processing import extend_patch, handle_patch_deletions
 from pr_agent.algo.language_handler import sort_files_by_main_languages
@@ -14,7 +14,8 @@ DELETED_FILES_ = "Deleted files:\n"
 
 MORE_MODIFIED_FILES_ = "More modified files:\n"
 
-OUTPUT_BUFFER_TOKENS = 800
+OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1000
+OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
 PATCH_EXTRA_LINES = 3
 
 
@@ -32,11 +33,12 @@ def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHa
     patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler)
 
     # if we are under the limit, return the full diff
-    if total_tokens + OUTPUT_BUFFER_TOKENS < token_handler.limit:
+    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < token_handler.limit:
         return "\n".join(patches_extended)
 
     # if we are over the limit, start pruning
-    patches_compressed, modified_file_names, deleted_file_names = pr_generate_compressed_diff(pr_languages, token_handler)
+    patches_compressed, modified_file_names, deleted_file_names = pr_generate_compressed_diff(pr_languages,
+                                                                                              token_handler)
     final_diff = "\n".join(patches_compressed)
     if modified_file_names:
         modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names)
@@ -115,12 +117,12 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) ->
         new_patch_tokens = token_handler.count_tokens(patch)
 
         # Hard Stop, no more tokens
-        if total_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS // 2:
+        if total_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
             logging.warning(f"File was fully skipped, no more tokens: {file.filename}.")
             continue
 
         # If the patch is too large, just show the file name
-        if total_tokens + new_patch_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS:
+        if total_tokens + new_patch_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
             # Current logic is to skip the patch if it's too large
             # TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
             #  until we meet the requirements

pr_agent/algo/utils.py

@@ -12,7 +12,7 @@ def convert_to_markdown(output_data: dict) -> str:
         "Type of PR": "📌",
         "Relevant tests added": "🧪",
         "Unrelated changes": "⚠️",
-        "Minimal and focused": "✨",
+        "Focused PR": "✨",
         "Security concerns": "🔒",
         "General PR suggestions": "💡",
         "Code suggestions": "🤖"

pr_agent/servers/github_polling.py

@@ -38,6 +38,7 @@ async def polling_loop():
     async with aiohttp.ClientSession() as session:
         while True:
             try:
+                await asyncio.sleep(5)
                 headers = {
                     "Accept": "application/vnd.github.v3+json",
                     "Authorization": f"Bearer {token}"
@@ -86,10 +87,8 @@ async def polling_loop():
                     elif response.status != 304:
                         print(f"Failed to fetch notifications. Status code: {response.status}")
 
-                await asyncio.sleep(5)
             except Exception as e:
                 logging.error(f"Exception during processing of a notification: {e}")
-                await asyncio.sleep(5)
 
 if __name__ == '__main__':
     asyncio.run(polling_loop())

pr_agent/settings/.secrets_template.toml

@@ -1,5 +1,5 @@
 # QUICKSTART:
-# Copy this file to .secrets in the same folder.
+# Copy this file to .secrets.toml in the same folder.
 # The minimum workable settings - set openai.key to your API key.
 # Set github.deployment_type to "user" and github.user_token to your GitHub personal access token.
 # This will allow you to run the CLI scripts in the scripts/ folder and the github_polling server.

pr_agent/settings/configuration.toml

@@ -5,7 +5,7 @@ publish_review=true
 verbosity_level=0  # 0,1,2
 
 [pr_reviewer]
-require_minimal_and_focused_review=true
+require_focused_review=true
 require_tests_review=true
 require_security_review=true
 extended_code_suggestions=false

pr_agent/settings/pr_reviewer_prompts.toml

@@ -30,10 +30,10 @@ You must use the following JSON schema to format your answer:
       "description": "yes\\no question: does this PR have relevant tests ?"
     },
 {%- endif %}
-{%- if require_minimal_and_focused %}
+{%- if require_focused %}
-    "Minimal and focused": {
+    "Focused PR": {
       "type": "string",
-      "description": "is this PR as minimal and focused as possible, with all code changes centered around a single coherent theme, described in the PR description and title ?" Make sure to explain your answer"
+      "description": "Is this a focused PR, in the sense that it has a clear and coherent title and description, and all PR code diff changes are properly derived from the title and description? Explain your response."
     }
   },
 {%- endif %}
@@ -106,8 +106,8 @@ Example output:
 {%- if require_tests %}
         "Relevant tests added": "No",
 {%- endif %}
-{%- if require_minimal_and_focused %}
+{%- if require_focused %}
-        "Minimal and focused": "yes\\no, because ..."
+        "Focused PR": "yes\\no, because ..."
 {%- endif %}
     },
     "PR Feedback":

pr_agent/tools/pr_reviewer.py

@@ -33,7 +33,7 @@ class PRReviewer:
             "diff": "",  # empty diff for initial calculation
             "require_tests": settings.pr_reviewer.require_tests_review,
             "require_security": settings.pr_reviewer.require_security_review,
-            "require_minimal_and_focused": settings.pr_reviewer.require_minimal_and_focused_review,
+            "require_focused": settings.pr_reviewer.require_focused_review,
             'extended_code_suggestions': settings.pr_reviewer.extended_code_suggestions,
             'num_code_suggestions': settings.pr_reviewer.num_code_suggestions,
         }

tests/unit/test_convert_to_markdown.py

@@ -1,6 +1,6 @@
 # Generated by CodiumAI
 from pr_agent.algo.utils import convert_to_markdown
-
+import pytest
 """
 Code Analysis
 
@@ -50,7 +50,7 @@ class TestConvertToMarkdown:
             'Type of PR': 'Test type',
             'Relevant tests added': 'no',
             'Unrelated changes': 'n/a',  # won't be included in the output
-            'Minimal and focused': 'Yes',
+            'Focused PR': 'Yes',
             'General PR suggestions': 'general suggestion...',
             'Code suggestions': [
                 {
@@ -74,12 +74,11 @@ class TestConvertToMarkdown:
 - 🔍 **Description and title:** Test description
 - 📌 **Type of PR:** Test type
 - 🧪 **Relevant tests added:** no
-- ✨ **Minimal and focused:** Yes
+- ✨ **Focused PR:** Yes
 - 💡 **General PR suggestions:** general suggestion...
 
 - 🤖 **Code suggestions:**
 
-- **suggestion 1:**
   - **Code example:**
     - **Before:**
         ```
@@ -90,7 +89,6 @@ class TestConvertToMarkdown:
         Code after
         ```
 
-- **suggestion 2:**
   - **Code example:**
     - **Before:**
         ```
@@ -116,7 +114,7 @@ class TestConvertToMarkdown:
             'Type of PR': {},
             'Relevant tests added': {},
             'Unrelated changes': {},
-            'Minimal and focused': {},
+            'Focused PR': {},
             'General PR suggestions': {},
             'Code suggestions': {}
         }

tests/unit/test_parse_code_suggestion.py

@@ -47,7 +47,7 @@ class TestParseCodeSuggestion:
             "Suggestion number": "one",
             "Description": "This is a suggestion"
         }
-        expected_output = "- **suggestion one:**\n  - **Description:** This is a suggestion\n\n"
+        expected_output = "   **Description:** This is a suggestion\n\n"
         assert parse_code_suggestion(input_data) == expected_output
 
     # Tests that function returns correct output when 'before' or 'after' key has a non-string value
@@ -70,7 +70,7 @@ class TestParseCodeSuggestion:
             'before': 'Before 1',
             'after': 'After 1'
         }
-        expected_output = "- **suggestion 1:**\n  - **suggestion:** Suggestion 1\n  - **description:** Description 1\n  - **before:** Before 1\n  - **after:** After 1\n\n"  # noqa: E501
+        expected_output = "   **suggestion:** Suggestion 1\n   **description:** Description 1\n   **before:** Before 1\n   **after:** After 1\n\n"
         assert parse_code_suggestion(code_suggestions) == expected_output
 
     # Tests that function returns correct output when input dictionary has 'code example' key
@@ -84,5 +84,5 @@ class TestParseCodeSuggestion:
                 'after': 'After 2'
             }
         }
-        expected_output = "- **suggestion 2:**\n  - **suggestion:** Suggestion 2\n  - **description:** Description 2\n  - **code example:**\n    - **before:**\n        ```\n        Before 2\n        ```\n    - **after:**\n        ```\n        After 2\n        ```\n\n"  # noqa: E501
+        expected_output = "   **suggestion:** Suggestion 2\n   **description:** Description 2\n  - **code example:**\n    - **before:**\n        ```\n        Before 2\n        ```\n    - **after:**\n        ```\n        After 2\n        ```\n\n"
         assert parse_code_suggestion(code_suggestions) == expected_output