Merge pull request #1904 from qodo-ai/tr/suggestions_depth

Tr/suggestions depth

docs/docs/tools/describe.md

@@ -57,9 +57,10 @@ Everything below this marker is treated as previously auto-generated content and
 ![Describe comment](https://codium.ai/images/pr_agent/pr_description_user_description.png){width=512}
 
 ### Sequence Diagram Support 
-When the `enable_pr_diagram` option is enabled in your configuration, the `/describe` tool will include a `Mermaid` sequence diagram in the PR description.
+The `/describe` tool includes a Mermaid sequence diagram showing component/function interactions. 
+
+This option is enabled by default via the `pr_description.enable_pr_diagram` param.
 
-This diagram represents interactions between components/functions based on the PR content.
 
 [//]: # (### How to enable\disable)
 

docs/docs/tools/improve.md

@@ -437,9 +437,26 @@ dual_publishing_score_threshold = x
 
 Where x represents the minimum score threshold (>=) for suggestions to be presented as committable PR comments in addition to the table. Default is -1 (disabled).
 
+### Controlling suggestions depth
+
+> `💎 feature`
+
+You can control the depth and comprehensiveness of the code suggestions by using the `pr_code_suggestions.suggestions_depth` parameter.
+
+Available options:
+
+- `selective` - Shows only suggestions above a score threshold of 6
+- `regular` - Default mode with balanced suggestion coverage  
+- `exhaustive` - Provides maximum suggestion comprehensiveness
+
+(Alternatively, use numeric values: 1, 2, or 3 respectively)
+
+We recommend starting with `regular` mode, then exploring `exhaustive` mode, which can provide more comprehensive suggestions and enhanced bug detection.
+
+
 ### Self-review
 
-> `💎 feature` Platforms supported: GitHub, GitLab
+> `💎 feature. Platforms supported: GitHub, GitLab`
 
 If you set in a configuration file:
 
@@ -521,6 +538,10 @@ Note: Chunking is primarily relevant for large PRs. For most PRs (up to 600 line
         <td><b>enable_chat_in_code_suggestions</b></td>
         <td>If set to true, QM bot will interact with comments made on code changes it has proposed. Default is true.</td>
       </tr>
+      <tr>
+        <td><b>suggestions_depth 💎</b></td>
+        <td> Controls the depth of the suggestions. Can be set to 'selective', 'regular', or 'exhaustive'. Default is 'regular'.</td>
+      </tr>
       <tr>
         <td><b>dual_publishing_score_threshold</b></td>
         <td>Minimum score threshold for suggestions to be presented as committable PR comments in addition to the table. Default is -1 (disabled).</td>

docs/docs/usage-guide/additional_configurations.md

@@ -250,3 +250,15 @@ Where the `ignore_pr_authors` is a list of usernames that you want to ignore.
 
 !!! note
     There is one specific case where bots will receive an automatic response - when they generated a PR with a _failed test_. In that case, the [`ci_feedback`](https://qodo-merge-docs.qodo.ai/tools/ci_feedback/) tool will be invoked.
+
+### Ignoring Generated Files by Language/Framework
+
+To automatically exclude files generated by specific languages or frameworks, you can add the following to your `configuration.toml` file:
+
+```
+[config]
+ignore_language_framework = ['protobuf', ...]
+```
+
+You can view the list of auto-generated file patterns in [`generated_code_ignore.toml`](https://github.com/qodo-ai/pr-agent/blob/main/pr_agent/settings/generated_code_ignore.toml). 
+Files matching these glob patterns will be automatically excluded from PR Agent analysis.

pr_agent/algo/file_filter.py

@@ -2,6 +2,7 @@ import fnmatch
 import re
 
 from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
 
 
 def filter_ignored(files, platform = 'github'):
@@ -17,7 +18,17 @@ def filter_ignored(files, platform = 'github'):
         glob_setting = get_settings().ignore.glob
         if isinstance(glob_setting, str):  # --ignore.glob=[.*utils.py], --ignore.glob=.*utils.py
             glob_setting = glob_setting.strip('[]').split(",")
-        patterns += [fnmatch.translate(glob) for glob in glob_setting]
+        patterns += translate_globs_to_regexes(glob_setting)
+
+        code_generators = get_settings().config.get('ignore_language_framework', [])
+        if isinstance(code_generators, str):
+            get_logger().warning("'ignore_language_framework' should be a list. Skipping language framework filtering.")
+            code_generators = []
+        for cg in code_generators:
+            glob_patterns = get_settings().generated_code.get(cg, [])
+            if isinstance(glob_patterns, str):
+                glob_patterns = [glob_patterns]
+            patterns += translate_globs_to_regexes(glob_patterns)
 
         # compile all valid patterns
         compiled_patterns = []
@@ -66,3 +77,11 @@ def filter_ignored(files, platform = 'github'):
         print(f"Could not filter file list: {e}")
 
     return files
+
+def translate_globs_to_regexes(globs: list):
+    regexes = []
+    for pattern in globs:
+        regexes.append(fnmatch.translate(pattern))
+        if pattern.startswith("**/"): # cover root-level files
+            regexes.append(fnmatch.translate(pattern[3:]))
+    return regexes

pr_agent/config_loader.py

@@ -14,6 +14,7 @@ global_settings = Dynaconf(
     settings_files=[join(current_dir, f) for f in [
         "settings/configuration.toml",
         "settings/ignore.toml",
+        "settings/generated_code_ignore.toml",
         "settings/language_extensions.toml",
         "settings/pr_reviewer_prompts.toml",
         "settings/pr_questions_prompts.toml",

pr_agent/settings/configuration.toml

@@ -56,6 +56,7 @@ ignore_pr_source_branches = [] # a list of regular expressions of source branche
 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
+ignore_language_framework = [] # a list of code-generation languages or frameworks (e.g. 'protobuf', 'go_gen') whose auto-generated source files will be excluded from analysis
 #
 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

pr_agent/settings/generated_code_ignore.toml

@@ -0,0 +1,42 @@
+[generated_code]
+
+# Protocol Buffers
+protobuf = [
+  "**/*.pb.go",
+  "**/*.pb.cc",
+  "**/*_pb2.py",
+  "**/*.pb.swift",
+  "**/*.pb.rb",
+  "**/*.pb.php",
+  "**/*.pb.h"
+]
+
+# OpenAPI / Swagger stubs
+openapi = [
+  "**/__generated__/**",
+  "**/openapi_client/**",
+  "**/openapi_server/**"
+]
+swagger = [
+  "**/swagger.json",
+  "**/swagger.yaml"
+]
+
+# GraphQL codegen
+graphql = [
+  "**/*.graphql.ts",
+  "**/*.generated.ts",
+  "**/*.graphql.js"
+]
+
+# RPC / gRPC Generators 
+grpc_python      = ["**/*_grpc.py"]
+grpc_java        = ["**/*Grpc.java"]
+grpc_csharp      = ["**/*Grpc.cs"]
+grpc_typescript  = ["**/*_grpc.ts", "**/*_grpc.js"]
+
+# Go code generators
+go_gen = [
+  "**/*_gen.go",
+  "**/*generated.go"
+]

tests/unittest/test_file_filter.py

@@ -80,3 +80,53 @@ class TestIgnoreFilter:
 
         filtered_files = filter_ignored(files)
         assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."
+    
+    def test_language_framework_ignores(self, monkeypatch):
+        """
+        Test files are ignored based on language/framework mapping (e.g., protobuf).
+        """
+        monkeypatch.setattr(global_settings.config, 'ignore_language_framework', ['protobuf', 'go_gen'])
+
+        files = [
+            type('', (object,), {'filename': 'main.go'})(),
+            type('', (object,), {'filename': 'dir1/service.pb.go'})(),
+            type('', (object,), {'filename': 'dir1/dir/data_pb2.py'})(),
+            type('', (object,), {'filename': 'file.py'})(),
+            type('', (object,), {'filename': 'dir2/file_gen.go'})(),
+            type('', (object,), {'filename': 'file.generated.go'})()
+        ]
+        expected = [
+            files[0],
+            files[3]
+        ]
+
+        filtered = filter_ignored(files)
+        assert filtered == expected, (
+            f"Expected {[f.filename for f in expected]}, "
+            f"but got {[f.filename for f in filtered]}"
+        )
+
+    def test_skip_invalid_ignore_language_framework(self, monkeypatch):
+        """
+        Test skipping of generated code filtering when ignore_language_framework is not a list
+        """
+        monkeypatch.setattr(global_settings.config, 'ignore_language_framework', 'protobuf')
+
+        files = [
+            type('', (object,), {'filename': 'main.go'})(),
+            type('', (object,), {'filename': 'file.py'})(),
+            type('', (object,), {'filename': 'dir1/service.pb.go'})(),
+            type('', (object,), {'filename': 'file_pb2.py'})()
+        ]
+        expected = [
+            files[0],
+            files[1],
+            files[2],
+            files[3]
+        ]
+
+        filtered = filter_ignored(files)
+        assert filtered == expected, (
+            f"Expected {[f.filename for f in expected]}, "
+            f"but got {[f.filename for f in filtered]}"
+        )