dockerhub

INSTALL.md Fixed typo in the hyperlink

Dockerfile.bitbucket_pipeline

@@ -0,0 +1,18 @@
+FROM python:3.10 as base
+
+ENV OPENAI_API_KEY=${OPENAI_API_KEY} \
+    BITBUCKET_BEARER_TOKEN=${BITBUCKET_BEARER_TOKEN} \
+    BITBUCKET_PR_ID=${BITBUCKET_PR_ID} \
+    BITBUCKET_REPO_SLUG=${BITBUCKET_REPO_SLUG} \
+    BITBUCKET_WORKSPACE=${BITBUCKET_WORKSPACE}
+
+
+WORKDIR /app
+ADD pyproject.toml .
+ADD requirements.txt .
+RUN pip install . && rm pyproject.toml requirements.txt
+ENV PYTHONPATH=/app
+ADD pr_agent pr_agent
+ADD bitbucket_pipeline/entrypoint.sh /
+RUN chmod +x /entrypoint.sh
+ENTRYPOINT ["/entrypoint.sh"]

Dockerfile.github_action_dockerhub

@@ -1 +1 @@
-FROM codiumai/pr-agent:github_action
+FROM codiumai/pr-agent:0.8-github_action

INSTALL.md

@@ -16,6 +16,7 @@ There are several ways to use PR-Agent:
 - [Method 6: Deploy as a Lambda Function](INSTALL.md#method-6---deploy-as-a-lambda-function)
 - [Method 7: AWS CodeCommit](INSTALL.md#method-7---aws-codecommit-setup)
 - [Method 8: Run a GitLab webhook server](INSTALL.md#method-8---run-a-gitlab-webhook-server)
+- [Method 9: Run as a Bitbucket Pipeline](INSTALL.md#method-9-run-as-a-bitbucket-pipeline)
 ---
 
 ### Method 1: Use Docker image (no installation required)
@@ -122,7 +123,7 @@ jobs:
           OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 ```
-** if you want to pin your action to a specific commit for stability reasons
+** if you want to pin your action to a specific release (v0.7 for example) for stability reasons, use:
 ```yaml
 on:
   pull_request:
@@ -139,7 +140,7 @@ jobs:
     steps:
       - name: PR Agent action step
         id: pragent
-        uses: Codium-ai/pr-agent@<commit_sha>
+        uses: Codium-ai/pr-agent@v0.7
         env:
           OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -155,7 +156,7 @@ The GITHUB_TOKEN secret is automatically created by GitHub.
 3. Merge this change to your main branch. 
 When you open your next PR, you should see a comment from `github-actions` bot with a review of your PR, and instructions on how to use the rest of the tools.
 
-4. You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the [configuration](./Usage.md) file. Some examples:
+4. You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the [configuration](pr_agent/settings/configuration.toml) file. Some examples:
 ```yaml
       env:
         # ... previous environment values
@@ -370,4 +371,63 @@ In the "Trigger" section, check the ‘comments’ and ‘merge request events
 6. Test your installation by opening a merge request or commenting or a merge request using one of CodiumAI's commands.
 
 
+
+### Method 9: Run as a Bitbucket Pipeline
+
+
+You can use our pre-build Bitbucket-Pipeline docker image to run as Bitbucket-Pipeline.
+
+1. Add the following file in your repository bitbucket_pipelines.yml
+
+```yaml
+  pipelines:
+    pull-requests:
+      '**':
+        - step:
+            name: PR Agent Pipeline
+            caches:
+              - pip
+            image: python:3.8
+            services:
+              - docker
+            script:
+              - git clone https://github.com/Codium-ai/pr-agent.git
+              - cd pr-agent
+              - docker build -t bitbucket_runner:latest -f Dockerfile.bitbucket_pipeline .
+              - docker run -e OPENAI_API_KEY=$OPENAI_API_KEY -e BITBUCKET_BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN -e BITBUCKET_PR_ID=$BITBUCKET_PR_ID -e BITBUCKET_REPO_SLUG=$BITBUCKET_REPO_SLUG -e BITBUCKET_WORKSPACE=$BITBUCKET_WORKSPACE bitbucket_runner:latest
+```
+
+2. Add the following secret to your repository under Repository settings > Pipelines > Repository variables.
+OPENAI_API_KEY: <your key>
+BITBUCKET_BEARER_TOKEN: <your token>
+
+3. To get BITBUCKET_BEARER_TOKEN follow these steps
+  So here is my step by step tutorial
+  i) Insert your workspace name instead of {workspace_name} and go to the following link in order to create an OAuth consumer.
+
+      https://bitbucket.org/{workspace_name}/workspace/settings/api
+
+      set callback URL to http://localhost:8976 (doesn't need to be a real server there)
+      select permissions: repository -> read
+
+  ii) use consumer's Key as a {client_id} and open the following URL in the browser
+
+      https://bitbucket.org/site/oauth2/authorize?client_id={client_id}&response_type=code
+
+  iii)
+      after you press "Grant access" in the browser it will redirect you to
+
+      http://localhost:8976?code=<CODE>
+
+  iv) use the code from the previous step and consumer's Key as a {client_id}, and consumer's Secret as {client_secret}
+
+      curl -X POST -u "{client_id}:{client_secret}" \
+          https://bitbucket.org/site/oauth2/access_token \
+          -d grant_type=authorization_code \
+          -d code={code} \
+
+
+After completing this steps, you just to place this access token in the repository varibles.
+
+
 =======

README.md

@@ -32,6 +32,8 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 
 See the [usage guide](./Usage.md) for instructions how to run the different tools from [CLI](./Usage.md#working-from-a-local-repo-cli), or by [online usage](./Usage.md#online-usage), as well as additional details on optional commands and configurations.
 
+[Release notes](./RELEASE_NOTES.md)
+
 <h3>Example results:</h3>
 </div>
 <h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1687561986">/describe:</a></h4>
@@ -157,6 +159,7 @@ There are several ways to use PR-Agent:
 - [Method 6: Deploy as a Lambda Function](INSTALL.md#method-6---deploy-as-a-lambda-function)
 - [Method 7: AWS CodeCommit](INSTALL.md#method-7---aws-codecommit-setup)
 - [Method 8: Run a GitLab webhook server](INSTALL.md#method-8---run-a-gitlab-webhook-server)
+- [Method 9: Run as a Bitbucket Pipeline](INSTALL.md#method-9-run-as-a-bitbucket-pipeline)
 
 ## How it works
 

RELEASE_NOTES.md

@@ -1,3 +1,19 @@
+## [Version 0.8] - 2023-09-27
+- codiumai/pr-agent:0.8
+- codiumai/pr-agent:0.8-github_app
+- codiumai/pr-agent:0.8-bitbucket-app
+- codiumai/pr-agent:0.8-gitlab_webhook
+- codiumai/pr-agent:0.8-github_polling
+- codiumai/pr-agent:0.8-github_action
+
+### Added::Algo
+- GitHub Action: Can control which tools will run automatically when a new PR is created. (see usage guide: https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
+- Code suggestion tool: Will try to avoid an 'add comments' suggestion  (see https://github.com/Codium-ai/pr-agent/pull/327)
+
+### Fixed
+- Gitlab: Fixed a bug of improper usage of pr_id
+
+
 ## [Version 0.7] - 2023-09-20
 
 ### Docker Tags
@@ -8,17 +24,18 @@
 - codiumai/pr-agent:0.7-github_polling
 - codiumai/pr-agent:0.7-github_action
  
-### Added
+### Added::Algo
-- 
+- New tool /similar_issue - Currently on GitHub app and CLI: indexes the issues in the repo, find the most similar issues to the target issue.
+- Describe markers: Empower the /describe tool with a templating capability (see more details in https://github.com/Codium-ai/pr-agent/pull/273).
+- New feature in the /review tool - added an estimated effort estimation to the review (https://github.com/Codium-ai/pr-agent/pull/306).
 
-### Changed
+### Added::Infrastructure
-- 
+- Implementation of a GitLab webhook.
-
+- Implementation of a BitBucket app.
-### Deprecated
-- 
-
-### Removed
-- 
 
 ### Fixed
--
+- Protection against no code suggestions generated.
+- Resilience to repositories where the languages cannot be automatically detected.
+
+
+

Usage.md

@@ -142,7 +142,21 @@ user="""
 Note that the new prompt will need to generate an output compatible with the relevant [post-process function](./pr_agent/tools/pr_description.py#L137).
 
 ### Working with GitHub Action
-TBD
+You can configure settings in GitHub action by adding environment variables under the env section in `.github/workflows/pr_agent.yml` file. Some examples:
+```yaml
+      env:
+        # ... previous environment values
+        OPENAI.ORG: "<Your organization name under your OpenAI account>"
+        PR_REVIEWER.REQUIRE_TESTS_REVIEW: "false" # Disable tests review
+        PR_CODE_SUGGESTIONS.NUM_CODE_SUGGESTIONS: 6 # Increase number of code suggestions
+        github_action.auto_review: "true" # Enable auto review
+        github_action.auto_describe: "true" # Enable auto describe
+        github_action.auto_improve: "false" # Disable auto improve      
+```
+specifically, `github_action.auto_review`, `github_action.auto_describe` and `github_action.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
+
+if not set, the default option is that only the `review` tool will run automatically when a new PR is opened.
+
 
 ### Appendix - additional configurations walkthrough
 

bitbucket_pipeline/entrypoint.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+python /app/pr_agent/servers/bitbucket_pipeline_runner.py

pr_agent/algo/git_patch_processing.py

@@ -40,12 +40,16 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
                         extended_patch_lines.extend(
                             original_lines[start1 + size1 - 1:start1 + size1 - 1 + num_lines])
 
+                    res = list(match.groups())
+                    for i in range(len(res)):
+                        if res[i] is None:
+                            res[i] = 0
                     try:
-                        start1, size1, start2, size2 = map(int, match.groups()[:4])
+                        start1, size1, start2, size2 = map(int, res[:4])
                     except:  # '@@ -0,0 +1 @@' case
-                        start1, size1, size2 = map(int, match.groups()[:3])
+                        start1, size1, size2 = map(int, res[:3])
                         start2 = 0
-                    section_header = match.groups()[4]
+                    section_header = res[4]
                     extended_start1 = max(1, start1 - num_lines)
                     extended_size1 = size1 + (start1 - extended_start1) + num_lines
                     extended_start2 = max(1, start2 - num_lines)
@@ -207,10 +211,15 @@ __old hunk__
                 old_content_lines = []
             if match:
                 prev_header_line = header_line
+
+            res = list(match.groups())
+            for i in range(len(res)):
+                if res[i] is None:
+                    res[i] = 0
             try:
-                start1, size1, start2, size2 = map(int, match.groups()[:4])
+                start1, size1, start2, size2 = map(int, res[:4])
             except: # '@@ -0,0 +1 @@' case
-                start1, size1, size2 = map(int, match.groups()[:3])
+                start1, size1, size2 = map(int, res[:3])
                 start2 = 0
 
         elif line.startswith('+'):

pr_agent/git_providers/codecommit_provider.py

@@ -233,8 +233,20 @@ class CodeCommitProvider(GitProvider):
         raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
 
     def get_title(self):
-        return self.pr.get("title", "")
+        return self.pr.title
 
+    def get_pr_id(self):
+        """
+        Returns the PR ID in the format: "repo_name/pr_number".
+        Note: This is an internal identifier for PR-Agent, 
+        and is not the same as the CodeCommit PR identifier.
+        """
+        try:
+            pr_id = f"{self.repo_name}/{self.pr_num}"
+            return pr_id
+        except:
+            return ""
+        
     def get_languages(self):
         """
         Returns a dictionary of languages, containing the percentage of each language used in the PR.

pr_agent/git_providers/git_provider.py

@@ -127,6 +127,9 @@ class GitProvider(ABC):
     def get_commit_messages(self):
         pass
 
+    def get_pr_id(self):
+        return ""
+
 def get_main_pr_language(languages, files) -> str:
     """
     Get the main language of the commit. Return an empty string if cannot determine.

pr_agent/git_providers/github_provider.py

@@ -239,9 +239,10 @@ class GithubProvider(GitProvider):
     def get_user_id(self):
         if not self.github_user_id:
             try:
-                self.github_user_id = self.github_client.get_user().login
+                self.github_user_id = self.github_client.get_user().raw_data['login']
             except Exception as e:
-                logging.exception(f"Failed to get user id, error: {e}")
+                self.github_user_id = ""
+                # logging.exception(f"Failed to get user id, error: {e}")
         return self.github_user_id
 
     def get_notifications(self, since: datetime):
@@ -446,3 +447,10 @@ class GithubProvider(GitProvider):
                 logging.info(f"Failed adding line link, error: {e}")
 
         return ""
+
+    def get_pr_id(self):
+        try:
+            pr_id = f"{self.repo}/{self.pr_num}"
+            return pr_id
+        except:
+            return ""

pr_agent/git_providers/gitlab_provider.py

@@ -378,4 +378,11 @@ class GitLabProvider(GitProvider):
             commit_messages_str = ""
         if max_tokens:
             commit_messages_str = clip_tokens(commit_messages_str, max_tokens)
-        return commit_messages_str
+        return commit_messages_str
+
+    def get_pr_id(self):
+        try:
+            pr_id = self.mr.web_url
+            return pr_id
+        except:
+            return ""

pr_agent/servers/bitbucket_pipeline_runner.py

@@ -0,0 +1,34 @@
+import os
+from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.config_loader import get_settings
+from pr_agent.tools.pr_reviewer import PRReviewer
+import asyncio
+
+async def run_action():
+    try:
+        pull_request_id = os.environ.get("BITBUCKET_PR_ID", '')
+        slug = os.environ.get("BITBUCKET_REPO_SLUG", '')
+        workspace = os.environ.get("BITBUCKET_WORKSPACE", '')
+        bearer_token = os.environ.get('BITBUCKET_BEARER_TOKEN', None)
+        OPENAI_KEY = os.environ.get('OPENAI_API_KEY') or os.environ.get('OPENAI.KEY')
+        OPENAI_ORG = os.environ.get('OPENAI_ORG') or os.environ.get('OPENAI.ORG')
+        # Check if required environment variables are set
+        if not bearer_token:
+            print("BITBUCKET_BEARER_TOKEN not set")
+            return
+        
+        if not OPENAI_KEY:
+            print("OPENAI_KEY not set")
+            return
+        # Set the environment variables in the settings
+        get_settings().set("BITBUCKET.BEARER_TOKEN", bearer_token)
+        get_settings().set("OPENAI.KEY", OPENAI_KEY)
+        if OPENAI_ORG:
+            get_settings().set("OPENAI.ORG", OPENAI_ORG)
+        if pull_request_id and slug and workspace:
+            pr_url = f"https://bitbucket.org/{workspace}/{slug}/pull-requests/{pull_request_id}"
+            await PRReviewer(pr_url).run()
+    except Exception as e:
+        print(f"An error occurred: {e}")
+if __name__ == "__main__":
+    asyncio.run(run_action())

pr_agent/servers/github_action_runner.py

@@ -5,6 +5,8 @@ import os
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
+from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_reviewer import PRReviewer
 
 
@@ -53,7 +55,15 @@ async def run_action():
         if action in ["opened", "reopened"]:
             pr_url = event_payload.get("pull_request", {}).get("url")
             if pr_url:
-                await PRReviewer(pr_url).run()
+                auto_review = os.environ.get('github_action.auto_review', None)
+                if auto_review is None or (isinstance(auto_review, str) and auto_review.lower() == 'true'):
+                    await PRReviewer(pr_url).run()
+                auto_describe = os.environ.get('github_action.auto_describe', None)
+                if isinstance(auto_describe, str) and auto_describe.lower() == 'true':
+                    await PRDescription(pr_url).run()
+                auto_improve = os.environ.get('github_action.auto_improve', None)
+                if isinstance(auto_improve, str) and auto_improve.lower() == 'true':
+                    await PRCodeSuggestions(pr_url).run()
 
     # Handle issue comment event
     elif GITHUB_EVENT_NAME == "issue_comment":

pr_agent/settings/configuration.toml

@@ -58,6 +58,11 @@ extra_instructions = ""
 deployment_type = "user"
 ratelimit_retries = 5
 
+[github_action]
+# auto_review = true    # set as env var in .github/workflows/pr-agent.yaml
+# auto_describe = true  # set as env var in .github/workflows/pr-agent.yaml
+# auto_improve = true   # set as env var in .github/workflows/pr-agent.yaml
+
 [github_app]
 # these toggles allows running the github app from custom deployments
 bot_user = "github-actions[bot]"

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -34,7 +34,7 @@ Specific instructions:
 - Provide up to {{ num_code_suggestions }} code suggestions.
 - Prioritize suggestions that address major problems, issues and bugs in the code.
   As a second priority, suggestions should focus on best practices, code readability, maintainability, enhancments, performance, and other aspects.
-  Don't suggest to add docstring or type hints.
+  Don't suggest to add docstring, type hints, or comments.
   Try to provide diverse and insightful suggestions.
 - Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
   Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the '__new hunk__' code.

pr_agent/settings/pr_reviewer_prompts.toml

@@ -22,13 +22,13 @@ code line that already existed in the file....
 ...
 '
 
-Thre review should focus on new code added in the PR (lines starting with '+'), and not on code that already existed in the file (lines starting with '-', or without prefix).
+The review should focus on new code added in the PR (lines starting with '+'), and not on code that already existed in the file (lines starting with '-', or without prefix).
 
 {%- if num_code_suggestions > 0 %}
 - Provide up to {{ num_code_suggestions }} code suggestions.
 - Focus on important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningful code improvements, like performance, vulnerability, modularity, and best practices.
 - Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the PR code.
-- Don't suggest to add docstring or type hints.
+- Don't suggest to add docstring, type hints, or comments.
 - Suggestions should focus on improving the new code added in the PR (lines starting with '+')
 {%- endif %}
 

pr_agent/tools/pr_code_suggestions.py

@@ -22,7 +22,10 @@ class PRCodeSuggestions:
         )
 
         # extended mode
-        self.is_extended = any(["extended" in arg for arg in args])
+        try:
+            self.is_extended = any(["extended" in arg for arg in args])
+        except:
+            self.is_extended = False
         if self.is_extended:
             num_code_suggestions = get_settings().pr_code_suggestions.num_code_suggestions_per_chunk
         else:

pr_agent/tools/pr_description.py

@@ -29,7 +29,7 @@ class PRDescription:
         self.main_pr_language = get_main_pr_language(
             self.git_provider.get_languages(), self.git_provider.get_files()
         )
-        self.pr_id = f"{self.git_provider.repo}/{self.git_provider.pr_num}"
+        self.pr_id = self.git_provider.get_pr_id()
 
         # Initialize the AI handler
         self.ai_handler = AiHandler()
@@ -67,7 +67,7 @@ class PRDescription:
         try:
             logging.info(f"Generating a PR description {self.pr_id}")
             if get_settings().config.publish_output:
-                self.git_provider.publish_comment("Preparing pr description...", is_temporary=True)
+                self.git_provider.publish_comment("Preparing PR description...", is_temporary=True)
 
             await retry_with_fallback_models(self._prepare_prediction)
 

tests/unittest/test_codecommit_client.py

@@ -110,7 +110,7 @@ class TestCodeCommitProvider:
         # Mock the response from the AWS client for get_pull_request method
         api.boto_client.get_pull_request.return_value = {
             "pullRequest": {
-                "pullRequestId": "3",
+                "pullRequestId": "321",
                 "title": "My PR",
                 "description": "My PR description",
                 "pullRequestTargets": [

tests/unittest/test_codecommit_provider.py

@@ -1,6 +1,8 @@
 import pytest
+from unittest.mock import patch
 from pr_agent.git_providers.codecommit_provider import CodeCommitFile
 from pr_agent.git_providers.codecommit_provider import CodeCommitProvider
+from pr_agent.git_providers.codecommit_provider import PullRequestCCMimic
 from pr_agent.git_providers.git_provider import EDIT_TYPE
 
 
@@ -25,6 +27,21 @@ class TestCodeCommitFile:
 
 
 class TestCodeCommitProvider:
+    def test_get_title(self):
+        # Test that the get_title() function returns the PR title
+        with patch.object(CodeCommitProvider, "__init__", lambda x, y: None):
+            provider = CodeCommitProvider(None)
+            provider.pr = PullRequestCCMimic("My Test PR Title", [])
+            assert provider.get_title() == "My Test PR Title"
+
+    def test_get_pr_id(self):
+        # Test that the get_pr_id() function returns the correct ID
+        with patch.object(CodeCommitProvider, "__init__", lambda x, y: None):
+            provider = CodeCommitProvider(None)
+            provider.repo_name = "my_test_repo"
+            provider.pr_num = 321
+            assert provider.get_pr_id() == "my_test_repo/321"
+
     def test_parse_pr_url(self):
         # Test that the _parse_pr_url() function can extract the repo name and PR number from a CodeCommit URL
         url = "https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/my_test_repo/pull-requests/321"
@@ -169,4 +186,4 @@ class TestCodeCommitProvider:
     def test_remove_markdown_html(self):
         input = "## PR Feedback\n<details><summary>Code feedback:</summary>\nfile foo\n</summary>\n"
         expect = "## PR Feedback\nCode feedback:\nfile foo\n\n"
-        assert CodeCommitProvider._remove_markdown_html(input) == expect
+        assert CodeCommitProvider._remove_markdown_html(input) == expect