Improve YAML parsing with additional fallback strategies for AI predictions

Pr 1736

docs/docs/usage-guide/additional_configurations.md

@@ -164,6 +164,7 @@ Qodo Merge allows you to automatically ignore certain PRs based on various crite
 
 - PRs with specific titles (using regex matching)
 - PRs between specific branches (using regex matching)
+- PRs from specific repositories (using regex matching)
 - PRs not from specific folders
 - PRs containing specific labels
 - PRs opened by specific users
@@ -172,7 +173,7 @@ Qodo Merge allows you to automatically ignore certain PRs based on various crite
 
 To ignore PRs with a specific title such as "[Bump]: ...", you can add the following to your `configuration.toml` file:
 
-```
+```toml
 [config]
 ignore_pr_title = ["\\[Bump\\]"]
 ```
@@ -183,7 +184,7 @@ Where the `ignore_pr_title` is a list of regex patterns to match the PR title yo
 
 To ignore PRs from specific source or target branches, you can add the following to your `configuration.toml` file:
 
-```
+```toml
 [config]
 ignore_pr_source_branches = ['develop', 'main', 'master', 'stage']
 ignore_pr_target_branches = ["qa"]
@@ -192,6 +193,18 @@ ignore_pr_target_branches = ["qa"]
 Where the `ignore_pr_source_branches` and `ignore_pr_target_branches` are lists of regex patterns to match the source and target branches you want to ignore.
 They are not mutually exclusive, you can use them together or separately.
 
+### Ignoring PRs from specific repositories
+
+To ignore PRs from specific repositories, you can add the following to your `configuration.toml` file:
+
+```toml
+[config]
+ignore_repositories = ["my-org/my-repo1", "my-org/my-repo2"]
+```
+
+Where the `ignore_repositories` is a list of regex patterns to match the repositories you want to ignore. This is useful when you have multiple repositories and want to exclude certain ones from analysis.
+
+
 ### Ignoring PRs not from specific folders
 
 To allow only specific folders (often needed in large monorepos), set:

docs/docs/usage-guide/changing_a_model.md

@@ -16,6 +16,23 @@ You can give parameters via a configuration file, or from environment variables.
     See [litellm documentation](https://litellm.vercel.app/docs/proxy/quick_start#supported-llms) for the environment variables needed per model, as they may vary and change over time. Our documentation per-model may not always be up-to-date with the latest changes.
     Failing to set the needed keys of a specific model will usually result in litellm not identifying the model type, and failing to utilize it.
 
+### OpenAI like API
+To use an OpenAI like API, set the following in your `.secrets.toml` file:
+
+```toml
+[openai]
+api_base = "https://api.openai.com/v1"
+api_key = "sk-..."
+```
+
+or use the environment variables (make sure to use double underscores `__`):
+
+```bash
+OPENAI__API_BASE=https://api.openai.com/v1
+OPENAI__KEY=sk-...
+```
+
+
 ### Azure
 
 To use Azure, set in your `.secrets.toml` (working from CLI), or in the GitHub `Settings > Secrets and variables` (working from GitHub App or GitHub Action):

pr_agent/algo/__init__.py

@@ -58,6 +58,7 @@ MAX_TOKENS = {
     'vertex_ai/claude-3-7-sonnet@20250219': 200000,
     'vertex_ai/gemini-1.5-pro': 1048576,
     'vertex_ai/gemini-2.5-pro-preview-03-25': 1048576,
+    'vertex_ai/gemini-2.5-pro-preview-05-06': 1048576,
     'vertex_ai/gemini-1.5-flash': 1048576,
     'vertex_ai/gemini-2.0-flash': 1048576,
     'vertex_ai/gemini-2.5-flash-preview-04-17': 1048576,
@@ -66,6 +67,7 @@ MAX_TOKENS = {
     'gemini/gemini-1.5-flash': 1048576,
     'gemini/gemini-2.0-flash': 1048576,
     'gemini/gemini-2.5-pro-preview-03-25': 1048576,
+    'gemini/gemini-2.5-pro-preview-05-06': 1048576,
     'codechat-bison': 6144,
     'codechat-bison-32k': 32000,
     'anthropic.claude-instant-v1': 100000,

pr_agent/algo/ai_handlers/litellm_ai_handler.py

@@ -59,6 +59,7 @@ class LiteLLMAIHandler(BaseAiHandler):
             litellm.api_version = get_settings().openai.api_version
         if get_settings().get("OPENAI.API_BASE", None):
             litellm.api_base = get_settings().openai.api_base
+            self.api_base = get_settings().openai.api_base
         if get_settings().get("ANTHROPIC.KEY", None):
             litellm.anthropic_key = get_settings().anthropic.key
         if get_settings().get("COHERE.KEY", None):

pr_agent/algo/utils.py

@@ -731,8 +731,9 @@ def try_fix_yaml(response_text: str,
                  response_text_original="") -> dict:
     response_text_lines = response_text.split('\n')
 
-    keys_yaml = ['relevant line:', 'suggestion content:', 'relevant file:', 'existing code:', 'improved code:']
+    keys_yaml = ['relevant line:', 'suggestion content:', 'relevant file:', 'existing code:', 'improved code:', 'label:']
     keys_yaml = keys_yaml + keys_fix_yaml
+
     # first fallback - try to convert 'relevant line: ...' to relevant line: |-\n        ...'
     response_text_lines_copy = response_text_lines.copy()
     for i in range(0, len(response_text_lines_copy)):
@@ -747,8 +748,29 @@ def try_fix_yaml(response_text: str,
     except:
         pass
 
-    # second fallback - try to extract only range from first ```yaml to ````
-    snippet_pattern = r'```(yaml)?[\s\S]*?```'
+    # 1.5 fallback - try to convert '|' to '|2'. Will solve cases of indent decreasing during the code
+    response_text_copy = copy.deepcopy(response_text)
+    response_text_copy = response_text_copy.replace('|\n', '|2\n')
+    try:
+        data = yaml.safe_load(response_text_copy)
+        get_logger().info(f"Successfully parsed AI prediction after replacing | with |2")
+        return data
+    except:
+        # if it fails, we can try to add spaces to the lines that are not indented properly, and contain '}'.
+        response_text_lines_copy = response_text_copy.split('\n')
+        for i in range(0, len(response_text_lines_copy)):
+            initial_space = len(response_text_lines_copy[i]) - len(response_text_lines_copy[i].lstrip())
+            if initial_space == 2 and '|2' not in response_text_lines_copy[i] and '}' in response_text_lines_copy[i]:
+                response_text_lines_copy[i] = '    ' + response_text_lines_copy[i].lstrip()
+        try:
+            data = yaml.safe_load('\n'.join(response_text_lines_copy))
+            get_logger().info(f"Successfully parsed AI prediction after replacing | with |2 and adding spaces")
+            return data
+        except:
+            pass
+
+    # second fallback - try to extract only range from first ```yaml to the last ```
+    snippet_pattern = r'```yaml([\s\S]*?)```(?=\s*$|")'
     snippet = re.search(snippet_pattern, '\n'.join(response_text_lines_copy))
     if not snippet:
         snippet = re.search(snippet_pattern, response_text_original) # before we removed the "```"
@@ -803,16 +825,47 @@ def try_fix_yaml(response_text: str,
     except:
         pass
 
-    # sixth fallback - try to remove last lines
-    for i in range(1, len(response_text_lines)):
-        response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
+    # sixth fallback - replace tabs with spaces
+    if '\t' in response_text:
+        response_text_copy = copy.deepcopy(response_text)
+        response_text_copy = response_text_copy.replace('\t', '    ')
         try:
-            data = yaml.safe_load(response_text_lines_tmp)
-            get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
+            data = yaml.safe_load(response_text_copy)
+            get_logger().info(f"Successfully parsed AI prediction after replacing tabs with spaces")
             return data
         except:
             pass
 
+    # seventh fallback - add indent for sections of code blocks
+    response_text_copy = copy.deepcopy(response_text)
+    response_text_copy_lines = response_text_copy.split('\n')
+    start_line = -1
+    for i, line in enumerate(response_text_copy_lines):
+        if 'existing_code:' in line or 'improved_code:' in line:
+            start_line = i
+        elif line.endswith(': |') or line.endswith(': |-') or line.endswith(': |2') or line.endswith(':'):
+            start_line = -1
+        elif start_line != -1:
+            response_text_copy_lines[i] = '    ' + line
+    response_text_copy = '\n'.join(response_text_copy_lines)
+    try:
+        data = yaml.safe_load(response_text_copy)
+        get_logger().info(f"Successfully parsed AI prediction after adding indent for sections of code blocks")
+        return data
+    except:
+        pass
+
+    # # sixth fallback - try to remove last lines
+    # for i in range(1, len(response_text_lines)):
+    #     response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
+    #     try:
+    #         data = yaml.safe_load(response_text_lines_tmp)
+    #         get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
+    #         return data
+    #     except:
+    #         pass
+
+
 
 def set_custom_labels(variables, git_provider=None):
     if not get_settings().config.enable_custom_labels:

pr_agent/git_providers/utils.py

@@ -6,8 +6,7 @@ from dynaconf import Dynaconf
 from starlette_context import context
 
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import (get_git_provider,
-                                    get_git_provider_with_context)
+from pr_agent.git_providers import get_git_provider_with_context
 from pr_agent.log import get_logger
 
 

pr_agent/identity_providers/identity_provider.py

@@ -10,7 +10,7 @@ class Eligibility(Enum):
 
 class IdentityProvider(ABC):
     @abstractmethod
-    def verify_eligibility(self, git_provider, git_provier_id, pr_url):
+    def verify_eligibility(self, git_provider, git_provider_id, pr_url):
         pass
 
     @abstractmethod

pr_agent/servers/bitbucket_app.py

@@ -127,6 +127,14 @@ def should_process_pr_logic(data) -> bool:
         source_branch = pr_data.get("source", {}).get("branch", {}).get("name", "")
         target_branch = pr_data.get("destination", {}).get("branch", {}).get("name", "")
         sender = _get_username(data)
+        repo_full_name = pr_data.get("destination", {}).get("repository", {}).get("full_name", "")
+
+        # logic to ignore PRs from specific repositories
+        ignore_repos = get_settings().get("CONFIG.IGNORE_REPOSITORIES", [])
+        if repo_full_name and ignore_repos:
+            if any(re.search(regex, repo_full_name) for regex in ignore_repos):
+                get_logger().info(f"Ignoring PR from repository '{repo_full_name}' due to 'config.ignore_repositories' setting")
+                return False
 
         # logic to ignore PRs from specific users
         ignore_pr_users = get_settings().get("CONFIG.IGNORE_PR_AUTHORS", [])

pr_agent/servers/github_app.py

@@ -258,6 +258,14 @@ def should_process_pr_logic(body) -> bool:
         source_branch = pull_request.get("head", {}).get("ref", "")
         target_branch = pull_request.get("base", {}).get("ref", "")
         sender = body.get("sender", {}).get("login")
+        repo_full_name = body.get("repository", {}).get("full_name", "")
+
+        # logic to ignore PRs from specific repositories
+        ignore_repos = get_settings().get("CONFIG.IGNORE_REPOSITORIES", [])
+        if ignore_repos and repo_full_name:
+            if any(re.search(regex, repo_full_name) for regex in ignore_repos):
+                get_logger().info(f"Ignoring PR from repository '{repo_full_name}' due to 'config.ignore_repositories' setting")
+                return False
 
         # logic to ignore PRs from specific users
         ignore_pr_users = get_settings().get("CONFIG.IGNORE_PR_AUTHORS", [])

pr_agent/servers/gitlab_webhook.py

@@ -113,6 +113,14 @@ def should_process_pr_logic(data) -> bool:
             return False
         title = data['object_attributes'].get('title')
         sender = data.get("user", {}).get("username", "")
+        repo_full_name = data.get('project', {}).get('path_with_namespace', "")
+
+        # logic to ignore PRs from specific repositories
+        ignore_repos = get_settings().get("CONFIG.IGNORE_REPOSITORIES", [])
+        if ignore_repos and repo_full_name:
+            if any(re.search(regex, repo_full_name) for regex in ignore_repos):
+                get_logger().info(f"Ignoring MR from repository '{repo_full_name}' due to 'config.ignore_repositories' setting")
+                return False
 
         # logic to ignore PRs from specific users
         ignore_pr_users = get_settings().get("CONFIG.IGNORE_PR_AUTHORS", [])

pr_agent/settings/configuration.toml

@@ -55,6 +55,7 @@ ignore_pr_target_branches = [] # a list of regular expressions of target branche
 ignore_pr_source_branches = [] # a list of regular expressions of source branches to ignore from PR agent when an PR is created
 ignore_pr_labels = [] # labels to ignore from PR agent when an PR is created
 ignore_pr_authors = [] # authors to ignore from PR agent when an PR is created
+ignore_repositories = [] # a list of regular expressions of repository full names (e.g. "org/repo") to ignore from PR agent processing
 #
 is_auto_command = false # will be auto-set to true if the command is triggered by an automation
 enable_ai_metadata = false # will enable adding ai metadata

requirements.txt

@@ -13,7 +13,7 @@ google-cloud-aiplatform==1.38.0
 google-generativeai==0.8.3
 google-cloud-storage==2.10.0
 Jinja2==3.1.2
-litellm==1.66.3
+litellm==1.69.3
 loguru==0.7.2
 msrest==0.7.1
 openai>=1.55.3

tests/unittest/test_ignore_repositories.py

@@ -0,0 +1,79 @@
+import pytest
+from pr_agent.servers.github_app import should_process_pr_logic as github_should_process_pr_logic
+from pr_agent.servers.bitbucket_app import should_process_pr_logic as bitbucket_should_process_pr_logic
+from pr_agent.servers.gitlab_webhook import should_process_pr_logic as gitlab_should_process_pr_logic
+from pr_agent.config_loader import get_settings
+
+def make_bitbucket_payload(full_name):
+    return {
+        "data": {
+            "pullrequest": {
+                "title": "Test PR",
+                "source": {"branch": {"name": "feature/test"}},
+                "destination": {
+                    "branch": {"name": "main"},
+                    "repository": {"full_name": full_name}
+                }
+            },
+            "actor": {"username": "user", "type": "user"}
+        }
+    }
+
+def make_github_body(full_name):
+    return {
+        "pull_request": {},
+        "repository": {"full_name": full_name},
+        "sender": {"login": "user"}
+    }
+
+def make_gitlab_body(full_name):
+    return {
+        "object_attributes": {"title": "Test MR"},
+        "project": {"path_with_namespace": full_name}
+    }
+
+PROVIDERS = [
+    ("github", github_should_process_pr_logic, make_github_body),
+    ("bitbucket", bitbucket_should_process_pr_logic, make_bitbucket_payload),
+    ("gitlab", gitlab_should_process_pr_logic, make_gitlab_body),
+]
+
+class TestIgnoreRepositories:
+    def setup_method(self):
+        get_settings().set("CONFIG.IGNORE_REPOSITORIES", [])
+
+    @pytest.mark.parametrize("provider_name, provider_func, body_func", PROVIDERS)
+    def test_should_ignore_matching_repository(self, provider_name, provider_func, body_func):
+        get_settings().set("CONFIG.IGNORE_REPOSITORIES", ["org/repo-to-ignore"])
+        body = {
+            "pull_request": {},
+            "repository": {"full_name": "org/repo-to-ignore"},
+            "sender": {"login": "user"}
+        }
+        result = provider_func(body_func(body["repository"]["full_name"]))
+        # print(f"DEBUG: Provider={provider_name}, test_should_ignore_matching_repository, result={result}")
+        assert result is False, f"{provider_name}: PR from ignored repository should be ignored (return False)"
+
+    @pytest.mark.parametrize("provider_name, provider_func, body_func", PROVIDERS)
+    def test_should_not_ignore_non_matching_repository(self, provider_name, provider_func, body_func):
+        get_settings().set("CONFIG.IGNORE_REPOSITORIES", ["org/repo-to-ignore"])
+        body = {
+            "pull_request": {},
+            "repository": {"full_name": "org/other-repo"},
+            "sender": {"login": "user"}
+        }
+        result = provider_func(body_func(body["repository"]["full_name"]))
+        # print(f"DEBUG: Provider={provider_name}, test_should_not_ignore_non_matching_repository, result={result}")
+        assert result is True, f"{provider_name}: PR from non-ignored repository should not be ignored (return True)"
+
+    @pytest.mark.parametrize("provider_name, provider_func, body_func", PROVIDERS)
+    def test_should_not_ignore_when_config_empty(self, provider_name, provider_func, body_func):
+        get_settings().set("CONFIG.IGNORE_REPOSITORIES", [])
+        body = {
+            "pull_request": {},
+            "repository": {"full_name": "org/repo-to-ignore"},
+            "sender": {"login": "user"}
+        }
+        result = provider_func(body_func(body["repository"]["full_name"]))
+        # print(f"DEBUG: Provider={provider_name}, test_should_not_ignore_when_config_empty, result={result}")
+        assert result is True, f"{provider_name}: PR should not be ignored if ignore_repositories config is empty"