Merge remote-tracking branch 'origin/main'

pr_agent/git_providers/bitbucket_provider.py

@@ -235,7 +235,7 @@ class BitbucketProvider(GitProvider):
         except Exception as e:
             get_logger().exception(f"Failed to remove comment, error: {e}")
 
-    # funtion to create_inline_comment
+    # function to create_inline_comment
     def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
         position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
                                                                             relevant_file.strip('`'),
@@ -404,7 +404,7 @@ class BitbucketProvider(GitProvider):
 
     def get_commit_messages(self):
         return ""  # not implemented yet
-    
+
     # bitbucket does not support labels
     def publish_description(self, pr_title: str, description: str):
         payload = json.dumps({
@@ -424,7 +424,7 @@ class BitbucketProvider(GitProvider):
     # bitbucket does not support labels
     def publish_labels(self, pr_types: list):
         pass
-    
+
     # bitbucket does not support labels
     def get_pr_labels(self, update=False):
         pass

pr_agent/git_providers/bitbucket_server_provider.py

@@ -211,7 +211,7 @@ class BitbucketServerProvider(GitProvider):
     def remove_comment(self, comment):
         pass
 
-    # funtion to create_inline_comment
+    # function to create_inline_comment
     def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
                               absolute_position: int = None):
 

pr_agent/git_providers/github_provider.py

@@ -107,7 +107,7 @@ class GithubProvider(GitProvider):
             git_files = context.get("git_files", None)
             if git_files:
                 return git_files
-            self.git_files = list(self.pr.get_files()) # 'list' to hanlde pagination
+            self.git_files = list(self.pr.get_files()) # 'list' to handle pagination
             context["git_files"] = self.git_files
             return self.git_files
         except Exception:

pr_agent/servers/azuredevops_server_webhook.py

@@ -41,7 +41,7 @@ def handle_request(
 ):
     log_context["action"] = body
     log_context["api_url"] = url
-    
+
     async def inner():
         try:
             with get_logger().contextualize(**log_context):
@@ -89,7 +89,7 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
     get_logger().info(json.dumps(data))
 
     actions = []
-    if data["eventType"] == "git.pullrequest.created": 
+    if data["eventType"] == "git.pullrequest.created":
         # API V1 (latest)
         pr_url = unquote(data["resource"]["_links"]["web"]["href"].replace("_apis/git/repositories", "_git"))
         log_context["event"] = data["eventType"]
@@ -102,7 +102,7 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
                 repo = data["resource"]["pullRequest"]["repository"]["webUrl"]
                 pr_url = unquote(f'{repo}/pullrequest/{data["resource"]["pullRequest"]["pullRequestId"]}')
                 actions = [data["resource"]["comment"]["content"]]
-            else: 
+            else:
                 # API V1 not supported as it does not contain the PR URL
                 return JSONResponse(
                     status_code=status.HTTP_400_BAD_REQUEST,
@@ -120,7 +120,7 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
 
     log_context["event"] = data["eventType"]
     log_context["api_url"] = pr_url
-    
+
     for action in actions:
         try:
             handle_request(background_tasks, pr_url, action, log_context)
@@ -131,13 +131,13 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
                 content=json.dumps({"message": "Internal server error"}),
             )
     return JSONResponse(
-        status_code=status.HTTP_202_ACCEPTED, content=jsonable_encoder({"message": "webhook triggerd successfully"})
+        status_code=status.HTTP_202_ACCEPTED, content=jsonable_encoder({"message": "webhook triggered successfully"})
     )
 
 @router.get("/")
 async def root():
     return {"status": "ok"}
-    
+
 def start():
     app = FastAPI(middleware=[Middleware(RawContextMiddleware)])
     app.include_router(router)

pr_agent/servers/gunicorn_config.py

@@ -0,0 +1,191 @@
+import multiprocessing
+import os
+
+# from prometheus_client import multiprocess
+
+# Sample Gunicorn configuration file.
+
+#
+# Server socket
+#
+#   bind - The socket to bind.
+#
+#       A string of the form: 'HOST', 'HOST:PORT', 'unix:PATH'.
+#       An IP is a valid HOST.
+#
+#   backlog - The number of pending connections. This refers
+#       to the number of clients that can be waiting to be
+#       served. Exceeding this number results in the client
+#       getting an error when attempting to connect. It should
+#       only affect servers under significant load.
+#
+#       Must be a positive integer. Generally set in the 64-2048
+#       range.
+#
+
+# bind = '0.0.0.0:5000'
+bind = '0.0.0.0:3000'
+backlog = 2048
+
+#
+# Worker processes
+#
+#   workers - The number of worker processes that this server
+#       should keep alive for handling requests.
+#
+#       A positive integer generally in the 2-4 x $(NUM_CORES)
+#       range. You'll want to vary this a bit to find the best
+#       for your particular application's work load.
+#
+#   worker_class - The type of workers to use. The default
+#       sync class should handle most 'normal' types of work
+#       loads. You'll want to read
+#       http://docs.gunicorn.org/en/latest/design.html#choosing-a-worker-type
+#       for information on when you might want to choose one
+#       of the other worker classes.
+#
+#       A string referring to a Python path to a subclass of
+#       gunicorn.workers.base.Worker. The default provided values
+#       can be seen at
+#       http://docs.gunicorn.org/en/latest/settings.html#worker-class
+#
+#   worker_connections - For the eventlet and gevent worker classes
+#       this limits the maximum number of simultaneous clients that
+#       a single process can handle.
+#
+#       A positive integer generally set to around 1000.
+#
+#   timeout - If a worker does not notify the master process in this
+#       number of seconds it is killed and a new worker is spawned
+#       to replace it.
+#
+#       Generally set to thirty seconds. Only set this noticeably
+#       higher if you're sure of the repercussions for sync workers.
+#       For the non sync workers it just means that the worker
+#       process is still communicating and is not tied to the length
+#       of time required to handle a single request.
+#
+#   keepalive - The number of seconds to wait for the next request
+#       on a Keep-Alive HTTP connection.
+#
+#       A positive integer. Generally set in the 1-5 seconds range.
+#
+
+if os.getenv('GUNICORN_WORKERS', None):
+    workers = int(os.getenv('GUNICORN_WORKERS'))
+else:
+    cores = multiprocessing.cpu_count()
+    workers = cores * 2 + 1
+worker_connections = 1000
+timeout = 240
+keepalive = 2
+
+#
+#   spew - Install a trace function that spews every line of Python
+#       that is executed when running the server. This is the
+#       nuclear option.
+#
+#       True or False
+#
+
+spew = False
+
+#
+# Server mechanics
+#
+#   daemon - Detach the main Gunicorn process from the controlling
+#       terminal with a standard fork/fork sequence.
+#
+#       True or False
+#
+#   raw_env - Pass environment variables to the execution environment.
+#
+#   pidfile - The path to a pid file to write
+#
+#       A path string or None to not write a pid file.
+#
+#   user - Switch worker processes to run as this user.
+#
+#       A valid user id (as an integer) or the name of a user that
+#       can be retrieved with a call to pwd.getpwnam(value) or None
+#       to not change the worker process user.
+#
+#   group - Switch worker process to run as this group.
+#
+#       A valid group id (as an integer) or the name of a user that
+#       can be retrieved with a call to pwd.getgrnam(value) or None
+#       to change the worker processes group.
+#
+#   umask - A mask for file permissions written by Gunicorn. Note that
+#       this affects unix socket permissions.
+#
+#       A valid value for the os.umask(mode) call or a string
+#       compatible with int(value, 0) (0 means Python guesses
+#       the base, so values like "0", "0xFF", "0022" are valid
+#       for decimal, hex, and octal representations)
+#
+#   tmp_upload_dir - A directory to store temporary request data when
+#       requests are read. This will most likely be disappearing soon.
+#
+#       A path to a directory where the process owner can write. Or
+#       None to signal that Python should choose one on its own.
+#
+
+daemon = False
+raw_env = []
+pidfile = None
+umask = 0
+user = None
+group = None
+tmp_upload_dir = None
+
+#
+#   Logging
+#
+#   logfile - The path to a log file to write to.
+#
+#       A path string. "-" means log to stdout.
+#
+#   loglevel - The granularity of log output
+#
+#       A string of "debug", "info", "warning", "error", "critical"
+#
+
+errorlog = '-'
+loglevel = 'info'
+accesslog = None
+access_log_format = '%(h)s %(l)s %(u)s %(t)s "%(r)s" %(s)s %(b)s "%(f)s" "%(a)s"'
+
+#
+# Process naming
+#
+#   proc_name - A base to use with setproctitle to change the way
+#       that Gunicorn processes are reported in the system process
+#       table. This affects things like 'ps' and 'top'. If you're
+#       going to be running more than one instance of Gunicorn you'll
+#       probably want to set a name to tell them apart. This requires
+#       that you install the setproctitle module.
+#
+#       A string or None to choose a default of something like 'gunicorn'.
+#
+
+proc_name = None
+
+
+#
+# Server hooks
+#
+#   post_fork - Called just after a worker has been forked.
+#
+#       A callable that takes a server and worker instance
+#       as arguments.
+#
+#   pre_fork - Called just prior to forking the worker subprocess.
+#
+#       A callable that accepts the same arguments as after_fork
+#
+#   pre_exec - Called just prior to forking off a secondary
+#       master process during things like config reloading.
+#
+#       A callable that takes a server instance as the sole argument.
+#

pr_agent/settings/pr_evaluate_prompt_response.toml

@@ -40,8 +40,8 @@ After that, rank each response. Criterions to rank each response:
 - How well does the response follow the specific task instructions and requirements?
 - How well does the response analyze and understand the PR code diff?
 - How well will a person perceive it as a good response that correctly addresses the task?
-- How well does the reponse prioritize key feedback, related to the task instructions, that a human reader seeing that feedback would also consider as important?
-- Don't neccessarily rank higher a response that is longer. A shorter response might be better if it is more concise, and still addresses the task better.
+- How well does the response prioritize key feedback, related to the task instructions, that a human reader seeing that feedback would also consider as important?
+- Don't necessarily rank higher a response that is longer. A shorter response might be better if it is more concise, and still addresses the task better.
 
 
 The output must be a YAML object equivalent to type $PRRankRespones, according to the following Pydantic definitions:

pr_agent/settings/pr_reviewer_prompts.toml

@@ -73,7 +73,7 @@ class Review(BaseModel):
     security_concerns: str = Field(description="does this PR code introduce possible vulnerabilities such as exposure of sensitive information (e.g., API keys, secrets, passwords), or security concerns like SQL injection, XSS, CSRF, and others ? Answer 'No' if there are no possible issues. If there are security concerns or issues, start your answer with a short header, such as: 'Sensitive information exposure: ...', 'SQL injection: ...' etc. Explain your answer. Be specific and give examples if possible")
 {%- 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 meaningfull independent task. Output an empty list if the PR code does not needd to be split.")
+    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.")
 {%- endif %}
 {%- if num_code_suggestions > 0 %}