Optimize PR commit retrieval and caching in GitHub provider and utils

pr_agent/git_providers/github_provider.py

@@ -34,8 +34,11 @@ class GithubProvider(GitProvider):
         self.incremental = incremental
         if pr_url and 'pull' in pr_url:
             self.set_pr(pr_url)
-            self.last_commit_id = list(self.pr.get_commits())[-1]
+            self.pr_commits = self.pr.get_commits()
+            self.last_commit_id = list(self.pr_commits)[-1]
             self.pr_url = self.get_pr_url() # pr_url for github actions can be as api.github.com, so we need to get the url from the pr object
+        else:
+            self.pr_commits = None
 
     def is_supported(self, capability: str) -> bool:
         return True
@@ -50,7 +53,8 @@ class GithubProvider(GitProvider):
             self.get_incremental_commits()
 
     def get_incremental_commits(self):
-        self.commits = list(self.pr.get_commits())
+        if not self.pr_commits:
+            self.pr_commits = list(self.pr.get_commits())
 
         self.previous_review = self.get_previous_review(full=True, incremental=True)
         if self.previous_review:
@@ -68,14 +72,14 @@ class GithubProvider(GitProvider):
     def get_commit_range(self):
         last_review_time = self.previous_review.created_at
         first_new_commit_index = None
-        for index in range(len(self.commits) - 1, -1, -1):
-            if self.commits[index].commit.author.date > last_review_time:
-                self.incremental.first_new_commit = self.commits[index]
+        for index in range(len(self.pr_commits) - 1, -1, -1):
+            if self.pr_commits[index].commit.author.date > last_review_time:
+                self.incremental.first_new_commit = self.pr_commits[index]
                 first_new_commit_index = index
             else:
-                self.incremental.last_seen_commit = self.commits[index]
+                self.incremental.last_seen_commit = self.pr_commits[index]
                 break
-        return self.commits[first_new_commit_index:] if first_new_commit_index is not None else []
+        return self.pr_commits[first_new_commit_index:] if first_new_commit_index is not None else []
 
     def get_previous_review(self, *, full: bool, incremental: bool):
         if not (full or incremental):
@@ -94,9 +98,13 @@ class GithubProvider(GitProvider):
     def get_files(self):
         if self.incremental.is_incremental and self.file_set:
             return self.file_set.values()
-        if not self.git_files:
-            # bring files from GitHub only once
-            self.git_files = self.pr.get_files()
+        try:
+            git_files = context.get("git_files", None)
+            if git_files:
+                return git_files
+        except Exception:
+            pass
+        self.git_files = context["git_files"] = self.pr.get_files()
         return self.git_files
 
     @retry(exceptions=RateLimitExceeded,
@@ -111,8 +119,12 @@ class GithubProvider(GitProvider):
             or renamed files in the merge request.
         """
         try:
-            if self.diff_files:
-                return self.diff_files
+            try:
+                diff_files = context.get("diff_files", None)
+                if diff_files:
+                    return diff_files
+            except Exception:
+                pass
 
             files = self.get_files()
             diff_files = []
@@ -156,6 +168,7 @@ class GithubProvider(GitProvider):
                 diff_files.append(file_patch_canonical_structure)
 
             self.diff_files = diff_files
+            context["diff_files"] = diff_files
             return diff_files
 
         except GithubException.RateLimitExceededException as e:

pr_agent/git_providers/utils.py

@@ -7,14 +7,22 @@ from dynaconf import Dynaconf
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.log import get_logger
+from starlette_context import context
 
 
 def apply_repo_settings(pr_url):
     if get_settings().config.use_repo_settings_file:
         repo_settings_file = None
         try:
-            git_provider = get_git_provider()(pr_url)
-            repo_settings = git_provider.get_repo_settings()
+            try:
+                repo_settings = context.get("git_files", None)
+            except Exception:
+                repo_settings = None
+                pass
+            if not repo_settings:
+                git_provider = get_git_provider()(pr_url)
+                repo_settings = git_provider.get_repo_settings()
+
             if repo_settings:
                 repo_settings_file = None
                 fd, repo_settings_file = tempfile.mkstemp(suffix='.toml')