run_from_scratch

README.md

@@ -113,13 +113,13 @@ See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
 |       | ⮑ Extended                             |   :white_check_mark:    |   :white_check_mark:    |        :white_check_mark:   |   :white_check_mark:    |          | :white_check_mark:    |
 |       | Reflect and Review                          |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |          |   :white_check_mark:    |    :white_check_mark:    |
 |       | Update CHANGELOG.md                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |       |
-|       | Find similar issue                          |   :white_check_mark:    |                         |                             |          |          |       |
+|       | Find similar issue                          |   :white_check_mark:    |                         |   :white_check_mark:                          |          |          |       |
 |       | Add Documentation                           |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
 |       |                                             |        |        |      |      |      |
 | USAGE | CLI                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |
 |       | App / webhook                               |   :white_check_mark:    |   :white_check_mark:    |           |          |          |
 |       | Tagging bot                                 |   :white_check_mark:    |        |           |          |          |
-|       | Actions                                     |   :white_check_mark:    |        |           |          |          |
+|       | Actions                                     |   :white_check_mark:    |        | :white_check_mark: |          |          |
 |       | Web server                                  |       |        |           |          |          |  :white_check_mark:   |
 |       |                                             |        |        |      |      |      |
 | CORE  | PR compression                              |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |

pr_agent/git_providers/bitbucket_provider.py

@@ -10,12 +10,12 @@ from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
 from ..log import get_logger
 from .git_provider import FilePatchInfo, GitProvider
+import ast
 
 
 class BitbucketProvider(GitProvider):
     def __init__(
-        self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
+        self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
-    ):
         s = requests.Session()
         try:
             bearer = context.get("bitbucket_bearer_token", None)
@@ -32,12 +32,15 @@ class BitbucketProvider(GitProvider):
         self.repo = None
         self.pr_num = None
         self.pr = None
+        self.feature = None
+        self.issue_num = None
+        self.issue_name = None
         self.temp_comments = []
         self.incremental = incremental
-        if pr_url:
+        if pr_url and 'pull' in pr_url:
             self.set_pr(pr_url)
-        self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"]
+            self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"]
-        self.bitbucket_pull_request_api_url = self.pr._BitbucketBase__data["links"]['self']['href']
+            self.bitbucket_pull_request_api_url = self.pr._BitbucketBase__data["links"]['self']['href']
 
     def get_repo_settings(self):
         try:
@@ -228,6 +231,27 @@ class BitbucketProvider(GitProvider):
             raise ValueError("Unable to convert PR number to integer") from e
 
         return workspace_slug, repo_slug, pr_number
+    
+    @staticmethod
+    def _parse_issue_url(issue_url: str) -> Tuple[str, int]:
+        parsed_url = urlparse(issue_url)
+
+        if "bitbucket.org" not in parsed_url.netloc:
+            raise ValueError("The provided URL is not a valid Bitbucket URL")
+
+        path_parts = parsed_url.path.strip('/').split('/')
+        if len(path_parts) < 5 or path_parts[2] != "issues":
+            raise ValueError("The provided URL does not appear to be a Bitbucket issue URL")
+        
+        workspace_slug = path_parts[0]
+        repo_slug = path_parts[1]
+        try:
+            issue_number = int(path_parts[3])
+        except ValueError as e:
+            raise ValueError("Unable to convert issue number to integer") from e
+        
+        return workspace_slug, repo_slug, issue_number
+
 
     def _get_repo(self):
         if self.repo is None:
@@ -263,3 +287,81 @@ class BitbucketProvider(GitProvider):
     # bitbucket does not support labels
     def get_labels(self):
         pass
+
+    def get_issue(self, workspace_slug, repo_name, original_issue_number):
+        issue = self.bitbucket_client.repositories.get(workspace_slug, repo_name).issues.get(original_issue_number)
+        return issue
+    
+    def get_issue_url(self, issue):
+        return issue._BitbucketBase__data['links']['html']['href']
+    
+    def get_issue_body(self, issue):
+        return issue.content['raw']
+    
+    def get_issue_number(self, issue):
+        return issue.id
+    
+    def get_issue_comment_body(self, comment):
+        return comment['content']['raw']
+    
+    def get_issue_comment_user(self, comment):
+        return comment['user']['display_name']
+    
+    def get_issue_created_at(self, issue):
+        return str(issue.created_on)
+    
+    def get_username(self, issue, workspace_slug):
+        return workspace_slug
+
+    
+    def get_repo_issues(self, repo_obj):
+        return repo_obj._Repository__issues.each()
+
+   
+    def get_issues_comments(self, workspace_slug, repo_name, original_issue_number):
+        import requests
+
+        url = f"https://api.bitbucket.org/2.0/repositories/{workspace_slug}/{repo_name}/issues/{original_issue_number}/comments"
+
+        payload = {}
+        headers = {}
+
+        response = requests.request("GET", url, headers=headers, data=payload)
+        return response.json()['values']
+    
+    def create_issue_comment(self, similar_issues_str, workspace_slug, repo_name, original_issue_number):
+        url = f"https://api.bitbucket.org/2.0/repositories/{workspace_slug}/{repo_name}/issues/{original_issue_number}/comments"
+        payload = json.dumps({
+        "content": {
+            "raw": similar_issues_str
+        }
+        })
+        headers = {
+        'Authorization': f'Bearer {get_settings().get("BITBUCKET.BEARER_TOKEN", None)}',
+        'Content-Type': 'application/json'
+        }
+
+        response = requests.request("POST", url, headers=headers, data=payload)
+
+    def get_repo_obj(self, workspace_slug, repo_name):
+        return self.bitbucket_client.repositories.get(workspace_slug, repo_name)
+    
+    def get_repo_name_for_indexing(self, repo_obj):
+        return repo_obj._BitbucketBase__data['full_name'].lower().replace('/', '-').replace('_/', '-')
+    
+    def check_if_issue_pull_request(self, issue):
+        return False
+    
+    def get_issue_numbers(self, issue):
+        list_of_issue_numbers = []
+        for issue in issue:
+            list_of_issue_numbers.append(issue.id)
+        return str(list_of_issue_numbers)
+    
+    def get_issue_numbers_from_list(self, issues):
+        # convert str to list'
+        int_list = ast.literal_eval(issues)
+        int_list = [int(x) for x in int_list]
+        for issue_number in int_list:
+            return issue_number
+

pr_agent/git_providers/github_provider.py

@@ -241,7 +241,7 @@ class GithubProvider(GitProvider):
                 self.github_user_id = self.github_client.get_user().raw_data['login']
             except Exception as e:
                 self.github_user_id = ""
-                # logging.exception(f"Failed to get user id, error: {e}")
+                # get_logger().exception(f"Failed to get user id, error: {e}")
         return self.github_user_id
 
     def get_notifications(self, since: datetime):
@@ -335,8 +335,9 @@ class GithubProvider(GitProvider):
             issue_number = int(path_parts[3])
         except ValueError as e:
             raise ValueError("Unable to convert issue number to integer") from e
+        workspace_slug = None
 
-        return repo_name, issue_number
+        return workspace_slug, repo_name, issue_number
 
     def _get_github_client(self):
         deployment_type = get_settings().get("GITHUB.DEPLOYMENT_TYPE", "user")
@@ -453,3 +454,62 @@ class GithubProvider(GitProvider):
             return pr_id
         except:
             return ""
+        
+    def get_repo_issues(self, repo_obj):
+        return list(repo_obj.get_issues(state='all'))
+    
+    def get_issues_comments(self, workspace_slug, repo_name, original_issue_number):
+        return self.repo_obj.get_issue(original_issue_number)
+    
+    def get_issue_url(self, issue):
+        return issue.html_url
+    
+    def create_issue_comment(self, similar_issues_str, workspace_slug, repo_name, original_issue_number):
+        try:
+            issue = self.repo_obj.get_issue(original_issue_number)
+            issue.create_comment(similar_issues_str)
+        except Exception as e:
+            get_logger().exception(f"Failed to create issue comment, error: {e}")
+
+    def get_issue_body(self, issue):
+        return issue.body
+        
+    def get_issue_number(self, issue):
+        return issue.number
+    
+    def get_issues_comments(self, workspace_slug, repo_name, original_issue_number):
+        issue = self.repo_obj.get_issue(original_issue_number)
+        return list(issue.get_comments())
+    
+    def get_issue_body(self, issue):
+        return issue.body
+    
+    def get_username(self, issue, workspace_slug):
+        return issue.user.login
+    
+    def get_issue_created_at(self, issue):
+        return str(issue.created_at)
+    
+    def get_issue_comment_body(self, comment):
+        return comment.body
+    
+    def get_issue(self, workspace_slug, repo_name, original_issue_number):
+        return self.repo_obj.get_issue(int(original_issue_number))
+    
+    def get_repo_obj(self, workspace_slug, repo_name):
+        return self.github_client.get_repo(repo_name)
+    
+    def get_repo_name_for_indexing(self, repo_obj):
+        return repo_obj.full_name.lower().replace('/', '-').replace('_/', '-')
+    
+    def check_if_issue_pull_request(self, issue):
+        if issue.pull_request:
+            return True
+        return False
+    
+    def get_issue_numbers(self, issues_list):
+        return str([issue.number for issue in issues_list])
+    
+    def get_issue_numbers_from_list(self, r):
+        return int(r.split('.')[0].split('_')[-1])
+

pr_agent/tools/pr_similar_issue.py

@@ -19,19 +19,17 @@ MODEL = "text-embedding-ada-002"
 
 class PRSimilarIssue:
     def __init__(self, issue_url: str, args: list = None):
-        if get_settings().config.git_provider != "github":
-            raise Exception("Only github is supported for similar issue tool")
 
         self.cli_mode = get_settings().CONFIG.CLI_MODE
         self.max_issues_to_scan = get_settings().pr_similar_issue.max_issues_to_scan
         self.issue_url = issue_url
         self.git_provider = get_git_provider()()
-        repo_name, issue_number = self.git_provider._parse_issue_url(issue_url.split('=')[-1])
+        self.workspace_slug, self.repo_name, self.issue_number = self.git_provider._parse_issue_url(issue_url.split('=')[-1])
-        self.git_provider.repo = repo_name
+        self.git_provider.repo = self.repo_name
-        self.git_provider.repo_obj = self.git_provider.github_client.get_repo(repo_name)
+        self.git_provider.repo_obj = self.git_provider.get_repo_obj(self.workspace_slug, self.repo_name)
         self.token_handler = TokenHandler()
         repo_obj = self.git_provider.repo_obj
-        repo_name_for_index = self.repo_name_for_index = repo_obj.full_name.lower().replace('/', '-').replace('_/', '-')
+        repo_name_for_index = self.repo_name_for_index = self.git_provider.get_repo_name_for_indexing(repo_obj)
         index_name = self.index_name = "codium-ai-pr-agent-issues"
 
         # assuming pinecone api key and environment are set in secrets file
@@ -40,17 +38,17 @@ class PRSimilarIssue:
             environment = get_settings().pinecone.environment
         except Exception:
             if not self.cli_mode:
-                repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
+                workspace_slug, repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
-                issue_main = self.git_provider.repo_obj.get_issue(original_issue_number)
+                issue_main = self.git_provider.get_issue(workspace_slug, repo_name, original_issue_number)
                 issue_main.create_comment("Please set pinecone api key and environment in secrets file")
             raise Exception("Please set pinecone api key and environment in secrets file")
 
         # check if index exists, and if repo is already indexed
         run_from_scratch = False
         if run_from_scratch:  # for debugging
-            if not index_name in pinecone.list_indexes():
+            pinecone.init(api_key=api_key, environment=environment)
+            if index_name in pinecone.list_indexes():
                 get_logger().info('Removing index...')
-                pinecone.init(api_key=api_key, environment=environment)
                 pinecone.delete_index(index_name)
                 get_logger().info('Done')
 
@@ -72,19 +70,20 @@ class PRSimilarIssue:
             get_logger().info('Indexing the entire repo...')
 
             get_logger().info('Getting issues...')
-            issues = list(repo_obj.get_issues(state='all'))
+            issues = self.git_provider.get_repo_issues(repo_obj)
             get_logger().info('Done')
             self._update_index_with_issues(issues, repo_name_for_index, upsert=upsert)
         else:  # update index if needed
             pinecone_index = pinecone.Index(index_name=index_name)
             issues_to_update = []
-            issues_paginated_list = repo_obj.get_issues(state='all')
+            issues_paginated_list = self.git_provider.get_repo_issues(repo_obj)
             counter = 1
             for issue in issues_paginated_list:
-                if issue.pull_request:
+                issue_pull_request = self.git_provider.check_if_issue_pull_request(issue)
+                if issue_pull_request:
                     continue
                 issue_str, comments, number = self._process_issue(issue)
-                issue_key = f"issue_{number}"
+                issue_key = f"issue_{number}"   
                 id = issue_key + "." + "issue"
                 res = pinecone_index.fetch([id]).to_dict()
                 is_new_issue = True
@@ -106,8 +105,8 @@ class PRSimilarIssue:
 
     async def run(self):
         get_logger().info('Getting issue...')
-        repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
+        workspace_slug, repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
-        issue_main = self.git_provider.repo_obj.get_issue(original_issue_number)
+        issue_main = self.git_provider.get_issue(workspace_slug, repo_name, original_issue_number)
         issue_str, comments, number = self._process_issue(issue_main)
         openai.api_key = get_settings().openai.key
         get_logger().info('Done')
@@ -129,11 +128,11 @@ class PRSimilarIssue:
                 continue
 
             try:
-                issue_number = int(r["id"].split('.')[0].split('_')[-1])
+                issue_id= r['id']
+                issue_number = self.git_provider.get_issue_numbers_from_list(issue_id)
             except:
                 get_logger().debug(f"Failed to parse issue number from {r['id']}")
                 continue
-
             if original_issue_number == issue_number:
                 continue
             if issue_number not in relevant_issues_number_list:
@@ -148,33 +147,32 @@ class PRSimilarIssue:
         get_logger().info('Publishing response...')
         similar_issues_str = "### Similar Issues\n___\n\n"
         for i, issue_number_similar in enumerate(relevant_issues_number_list):
-            issue = self.git_provider.repo_obj.get_issue(issue_number_similar)
+            issue = self.git_provider.get_issue(workspace_slug, repo_name, issue_number_similar)
             title = issue.title
-            url = issue.html_url
+            url = self.git_provider.get_issue_url(issue)
-            if relevant_comment_number_list[i] != -1:
-                url = list(issue.get_comments())[relevant_comment_number_list[i]].html_url
             similar_issues_str += f"{i + 1}. **[{title}]({url})** (score={score_list[i]})\n\n"
         if get_settings().config.publish_output:
-            response = issue_main.create_comment(similar_issues_str)
+            response = self.git_provider.create_issue_comment(similar_issues_str, workspace_slug, repo_name, original_issue_number)
         get_logger().info(similar_issues_str)
         get_logger().info('Done')
 
     def _process_issue(self, issue):
         header = issue.title
-        body = issue.body
+        body = self.git_provider.get_issue_body(issue)
-        number = issue.number
+        number = self.git_provider.get_issue_number(issue)
         if get_settings().pr_similar_issue.skip_comments:
             comments = []
         else:
-            comments = list(issue.get_comments())
+            comments = self.git_provider.get_issues_comments(self.workspace_slug, self.repo_name, self.issue_number)
         issue_str = f"Issue Header: \"{header}\"\n\nIssue Body:\n{body}"
         return issue_str, comments, number
 
     def _update_index_with_issues(self, issues_list, repo_name_for_index, upsert=False):
         get_logger().info('Processing issues...')
         corpus = Corpus()
+        issues = self.git_provider.get_issue_numbers(issues_list)
         example_issue_record = Record(
-            id=f"example_issue_{repo_name_for_index}",
+            id=str(issues),
             text="example_issue",
             metadata=Metadata(repo=repo_name_for_index)
         )
@@ -182,7 +180,9 @@ class PRSimilarIssue:
 
         counter = 0
         for issue in issues_list:
-            if issue.pull_request:
+
+            issue_pull_request = self.git_provider.check_if_issue_pull_request(issue)
+            if issue_pull_request:
                 continue
 
             counter += 1
@@ -194,8 +194,8 @@ class PRSimilarIssue:
 
             issue_str, comments, number = self._process_issue(issue)
             issue_key = f"issue_{number}"
-            username = issue.user.login
+            username = self.git_provider.get_username(issue, self.workspace_slug)
-            created_at = str(issue.created_at)
+            created_at = self.git_provider.get_issue_created_at(issue)
             if len(issue_str) < 8000 or \
                     self.token_handler.count_tokens(issue_str) < MAX_TOKENS[MODEL]:  # fast reject first
                 issue_record = Record(
@@ -209,7 +209,7 @@ class PRSimilarIssue:
                 corpus.append(issue_record)
                 if comments:
                     for j, comment in enumerate(comments):
-                        comment_body = comment.body
+                        comment_body = self.git_provider.get_issue_comment_body(comment)
                         num_words_comment = len(comment_body.split())
                         if num_words_comment < 10 or not isinstance(comment_body, str):
                             continue