Add support for base_url in GitHub SDK

Fix a bug in GitLab webhook

INSTALL.md

@@ -101,6 +101,7 @@ python3 -m pr_agent.cli --pr_url <pr_url> ask <your question>
 python3 -m pr_agent.cli --pr_url <pr_url> describe
 python3 -m pr_agent.cli --pr_url <pr_url> improve
 python3 -m pr_agent.cli --pr_url <pr_url> add_docs
+python3 -m pr_agent.cli --pr_url <pr_url> generate_labels
 python3 -m pr_agent.cli --issue_url <issue_url> similar_issue
 ...
 ```

Usage.md

@@ -37,7 +37,9 @@ To ignore files or directories, edit the **[ignore.toml](/pr_agent/settings/igno
  - `IGNORE.GLOB`
  - `IGNORE.REGEX`
 
-See [dynaconf envvars documentation](https://www.dynaconf.com/envvars/).
+For example, to ignore python files in a PR, set:
+
+`ignore.glob = ['*.py']`
 
 #### git provider
 The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configuration file determines the GIT provider that will be used by PR-Agent. Currently, the following providers are supported:
@@ -310,6 +312,7 @@ To use Google's Vertex AI platform and its associated models (chat-bison/codecha
 ``` 
 [config] # in configuration.toml
 model = "vertex_ai/codechat-bison"
+fallback_models="vertex_ai/codechat-bison"
 
 [vertexai] # in .secrets.toml
 vertex_project = "my-google-cloud-project"

pr_agent/algo/utils.py

@@ -286,37 +286,39 @@ def _fix_key_value(key: str, value: str):
     return key, value
 
 
-def load_yaml(review_text: str) -> dict:
-    review_text = review_text.removeprefix('```yaml').rstrip('`')
+def load_yaml(response_text: str) -> dict:
+    response_text = response_text.removeprefix('```yaml').rstrip('`')
     try:
-        data = yaml.safe_load(review_text)
+        data = yaml.safe_load(response_text)
     except Exception as e:
         get_logger().error(f"Failed to parse AI prediction: {e}")
-        data = try_fix_yaml(review_text)
+        data = try_fix_yaml(response_text)
     return data
 
-def try_fix_yaml(review_text: str) -> dict:
-    review_text_lines = review_text.split('\n')
+def try_fix_yaml(response_text: str) -> dict:
+    response_text_lines = response_text.split('\n')
 
+    keys = ['relevant line:', 'suggestion content:', 'relevant file:']
     # first fallback - try to convert 'relevant line: ...' to relevant line: |-\n        ...'
-    review_text_lines_copy = review_text_lines.copy()
-    for i in range(0, len(review_text_lines_copy)):
-        if 'relevant line:' in review_text_lines_copy[i] and not '|-' in review_text_lines_copy[i]:
-            review_text_lines_copy[i] = review_text_lines_copy[i].replace('relevant line: ',
-                                                    'relevant line: |-\n        ')
+    response_text_lines_copy = response_text_lines.copy()
+    for i in range(0, len(response_text_lines_copy)):
+        for key in keys:
+            if key in response_text_lines_copy[i] and not '|-' in response_text_lines_copy[i]:
+                response_text_lines_copy[i] = response_text_lines_copy[i].replace(f'{key}',
+                                                                                  f'{key} |-\n        ')
     try:
-        data = yaml.load('\n'.join(review_text_lines_copy), Loader=yaml.SafeLoader)
-        get_logger().info(f"Successfully parsed AI prediction after adding |-\n        to relevant line")
+        data = yaml.safe_load('\n'.join(response_text_lines_copy))
+        get_logger().info(f"Successfully parsed AI prediction after adding |-\n")
         return data
     except:
-        get_logger().debug(f"Failed to parse AI prediction after adding |-\n        to relevant line")
+        get_logger().info(f"Failed to parse AI prediction after adding |-\n")
 
     # second fallback - try to remove last lines
     data = {}
-    for i in range(1, len(review_text_lines)):
-        review_text_lines_tmp = '\n'.join(review_text_lines[:-i])
+    for i in range(1, len(response_text_lines)):
+        response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
         try:
-            data = yaml.load(review_text_lines_tmp, Loader=yaml.SafeLoader)
+            data = yaml.safe_load(response_text_lines_tmp,)
             get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
             break
         except:

pr_agent/git_providers/github_provider.py

@@ -405,7 +405,7 @@ class GithubProvider(GitProvider):
                 raise ValueError("GitHub app installation ID is required when using GitHub app deployment")
             auth = AppAuthentication(app_id=app_id, private_key=private_key,
                                      installation_id=self.installation_id)
-            return Github(app_auth=auth)
+            return Github(app_auth=auth, base_url=get_settings().github.base_url)
 
         if deployment_type == 'user':
             try:
@@ -414,7 +414,7 @@ class GithubProvider(GitProvider):
                 raise ValueError(
                     "GitHub token is required when using user deployment. See: "
                     "https://github.com/Codium-ai/pr-agent#method-2-run-from-source") from e
-            return Github(auth=Auth.Token(token))
+            return Github(auth=Auth.Token(token), base_url=get_settings().github.base_url)
 
     def _get_repo(self):
         if hasattr(self, 'repo_obj') and \

pr_agent/servers/gitlab_webhook.py

@@ -38,7 +38,7 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
         try:
             secret_dict = json.loads(secret)
             gitlab_token = secret_dict["gitlab_token"]
-            log_context["sender"] = secret_dict["id"]
+            log_context["sender"] = secret_dict.get("token_name", secret_dict.get("id", "unknown"))
             context["settings"] = copy.deepcopy(global_settings)
             context["settings"].gitlab.personal_access_token = gitlab_token
         except Exception as e:

pr_agent/servers/help.py

@@ -1,12 +1,14 @@
-commands_text = "> **/review [-i]**: Request a review of your Pull Request. For an incremental review, which only " \
-                "considers changes since the last review, include the '-i' option.\n" \
-                "> **/describe**: Modify the PR title and description based on the contents of the PR.\n" \
-                "> **/improve [--extended]**: Suggest improvements to the code in the PR. Extended mode employs several calls, and provides a more thorough feedback. \n" \
-                "> **/ask \\<QUESTION\\>**: Pose a question about the PR.\n" \
-                "> **/update_changelog**: Update the changelog based on the PR's contents.\n\n" \
-                ">To edit any configuration parameter from **configuration.toml**, add --config_path=new_value\n" \
+commands_text = "> **/review**: Request a review of your Pull Request.\n" \
+                "> **/describe**: Update the PR title and description based on the contents of the PR.\n" \
+                "> **/improve [--extended]**: Suggest code improvements. Extended mode provides a higher quality feedback.\n" \
+                "> **/ask \\<QUESTION\\>**: Ask a question about the PR.\n" \
+                "> **/update_changelog**: Update the changelog based on the PR's contents.\n" \
+                "> **/add_docs**: Generate docstring for new components introduced in the PR.\n" \
+                "> **/generate_labels**: Generate labels for the PR based on the PR's contents.\n" \
+                "> see the [tools guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md) for more details.\n\n" \
+                ">To edit any configuration parameter from the [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml), add --config_path=new_value.\n" \
                 ">For example: /review --pr_reviewer.extra_instructions=\"focus on the file: ...\" \n" \
-                ">To list the possible configuration parameters, use the **/config** command.\n" \
+                ">To list the possible configuration parameters, add a **/config** comment.\n" \
 
 
 def bot_help_text(user: str):

pr_agent/servers/serverless.py

@@ -3,10 +3,8 @@ from mangum import Mangum
 from starlette.middleware import Middleware
 from starlette_context.middleware import RawContextMiddleware
 
-from pr_agent.log import setup_logger
 from pr_agent.servers.github_app import router
 
-setup_logger()
 
 middleware = [Middleware(RawContextMiddleware)]
 app = FastAPI(middleware=middleware)

pr_agent/settings/configuration.toml

@@ -79,6 +79,7 @@ extra_instructions = ""
 # The type of deployment to create. Valid values are 'app' or 'user'.
 deployment_type = "user"
 ratelimit_retries = 5
+base_url = "https://api.github.com"
 
 [github_action]
 # auto_review = true    # set as env var in .github/workflows/pr-agent.yaml

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -90,16 +90,19 @@ Code suggestions:
 Example output:
 ```yaml
 Code suggestions:
-  - relevant file: |-
+- relevant file: |-
     src/file1.py
   suggestion content: |-
     Add a docstring to func1()
   existing code: |-
     def func1():
-    relevant lines start: 12
-    relevant lines end: 12
+  relevant lines start: |-
+    12
+  relevant lines end: |-
+    12
   improved code: |-
     ...
+...
 ```
 
 

pr_agent/tools/pr_reviewer.py

@@ -249,11 +249,15 @@ class PRReviewer:
         # Add help text if not in CLI mode
         if not get_settings().get("CONFIG.CLI_MODE", False):
             markdown_text += "\n### How to use\n"
+            if self.git_provider.is_supported("gfm_markdown"):
+                markdown_text += "\n**<details><summary> Instructions**</summary>\n"
             bot_user = "[bot]" if get_settings().github_app.override_deployment_type else get_settings().github_app.bot_user
             if user and bot_user not in user:
                 markdown_text += bot_help_text(user)
             else:
                 markdown_text += actions_help_text
+            if self.git_provider.is_supported("gfm_markdown"):
+                markdown_text += "\n</details>\n"
 
         # Add custom labels from the review prediction (effort, security)
         self.set_review_labels(data)
@@ -274,14 +278,7 @@ class PRReviewer:
         if get_settings().pr_reviewer.num_code_suggestions == 0:
             return
 
-        review_text = self.prediction.strip()
-        review_text = review_text.removeprefix('```yaml').rstrip('`')
-        try:
-            data = yaml.load(review_text, Loader=SafeLoader)
-        except Exception as e:
-            get_logger().error(f"Failed to parse AI prediction: {e}")
-            data = try_fix_yaml(review_text)
-
+        data = load_yaml(self.prediction.strip())
         comments: List[str] = []
         for suggestion in data.get('PR Feedback', {}).get('Code feedback', []):
             relevant_file = suggestion.get('relevant file', '').strip()

pr_agent/tools/pr_similar_issue.py

@@ -8,6 +8,7 @@ import pinecone
 from pinecone_datasets import Dataset, DatasetMetadata
 from pydantic import BaseModel, Field
 
+from pr_agent.algo import MAX_TOKENS
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import get_max_tokens
 from pr_agent.config_loader import get_settings

tests/unittest/test_load_yaml.py

@@ -2,6 +2,9 @@
 # Generated by CodiumAI
 
 import pytest
+import yaml
+from yaml.scanner import ScannerError
+
 from pr_agent.algo.utils import load_yaml
 
 
@@ -12,7 +15,7 @@ class TestLoadYaml:
         expected_output = {'name': 'John Smith', 'age': 35}
         assert load_yaml(yaml_str) == expected_output
 
-    def test_load_complicated_yaml(self):
+    def test_load_invalid_yaml1(self):
         yaml_str = \
 '''\
 PR Analysis:
@@ -26,7 +29,23 @@ PR Feedback:
   Code feedback:
     - relevant file: pr_agent/settings/pr_description_prompts.toml
       suggestion: Consider using a more descriptive variable name than 'user' for the command prompt. A more descriptive name would make the code more readable and maintainable. [medium]
-      relevant line: 'user="""PR Info:'
+      relevant line: user="""PR Info: aaa
   Security concerns: No'''
-        expected_output = {'PR Analysis': {'Main theme': 'Enhancing the `/describe` command prompt by adding title and description', 'Type of PR': 'Enhancement', 'Relevant tests added': False, 'Focused PR': 'Yes, the PR is focused on enhancing the `/describe` command prompt.'}, 'PR Feedback': {'General suggestions': 'The PR seems to be well-structured and focused on a specific enhancement. However, it would be beneficial to add tests to ensure the new feature works as expected.', 'Code feedback': [{'relevant file': 'pr_agent/settings/pr_description_prompts.toml', 'suggestion': "Consider using a more descriptive variable name than 'user' for the command prompt. A more descriptive name would make the code more readable and maintainable. [medium]", 'relevant line': 'user="""PR Info:'}], 'Security concerns': False}}
+        with pytest.raises(ScannerError):
+            yaml.safe_load(yaml_str)
+
+        expected_output = {'PR Analysis': {'Main theme': 'Enhancing the `/describe` command prompt by adding title and description', 'Type of PR': 'Enhancement', 'Relevant tests added': False, 'Focused PR': 'Yes, the PR is focused on enhancing the `/describe` command prompt.'}, 'PR Feedback': {'General suggestions': 'The PR seems to be well-structured and focused on a specific enhancement. However, it would be beneficial to add tests to ensure the new feature works as expected.', 'Code feedback': [{'relevant file': 'pr_agent/settings/pr_description_prompts.toml', 'suggestion': "Consider using a more descriptive variable name than 'user' for the command prompt. A more descriptive name would make the code more readable and maintainable. [medium]", 'relevant line': 'user="""PR Info: aaa'}], 'Security concerns': False}}
         assert load_yaml(yaml_str) == expected_output
+
+    def test_load_invalid_yaml2(self):
+        yaml_str = '''\
+- relevant file: src/app.py:
+  suggestion content: The print statement is outside inside the if __name__ ==: \
+  '''
+        with pytest.raises(ScannerError):
+            yaml.safe_load(yaml_str)
+
+        expected_output =[{'relevant file': 'src/app.py:',
+  'suggestion content': 'The print statement is outside inside the if __name__ ==:   '}]
+        assert load_yaml(yaml_str) == expected_output
+